Add files using upload-large-folder tool
Browse files- checkpoint-132825/config.json +258 -0
- checkpoint-132825/generation_config.json +13 -0
- checkpoint-132825/global_step132825/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt +3 -0
- checkpoint-132825/global_step132825/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt +3 -0
- checkpoint-132825/global_step132825/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt +3 -0
- checkpoint-132825/global_step132825/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt +3 -0
- checkpoint-132825/global_step132825/mp_rank_00_model_states.pt +3 -0
- checkpoint-132825/latest +1 -0
- checkpoint-132825/model-00001-of-00002.safetensors +3 -0
- checkpoint-132825/model-00002-of-00002.safetensors +3 -0
- checkpoint-132825/model.safetensors.index.json +714 -0
- checkpoint-132825/preprocessor_config.json +24 -0
- checkpoint-132825/rng_state_0.pth +3 -0
- checkpoint-132825/rng_state_1.pth +3 -0
- checkpoint-132825/rng_state_2.pth +3 -0
- checkpoint-132825/rng_state_3.pth +3 -0
- checkpoint-132825/scheduler.pt +3 -0
- checkpoint-132825/special_tokens_map.json +23 -0
- checkpoint-132825/tokenizer.json +0 -0
- checkpoint-132825/tokenizer_config.json +2063 -0
- checkpoint-132825/trainer_state.json +1888 -0
- checkpoint-132825/training_args.bin +3 -0
- checkpoint-132825/zero_to_fp32.py +604 -0
- config.json +258 -0
- generation_config.json +13 -0
- model-00001-of-00002.safetensors +3 -0
- model-00002-of-00002.safetensors +3 -0
- model.safetensors.index.json +714 -0
- model_training_args.json +161 -0
- preprocessor_config.json +24 -0
- slurm-5684270.out +35 -0
- slurm-5684435.out +53 -0
- special_tokens_map.json +23 -0
- tokenizer.json +0 -0
- tokenizer_config.json +2063 -0
- trainer_state.json +1897 -0
- training_args.bin +3 -0
checkpoint-132825/config.json
ADDED
|
@@ -0,0 +1,258 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "AIDC-AI/Ovis1.6-Llama3.2-3B",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"Ovis"
|
| 5 |
+
],
|
| 6 |
+
"auto_map": {
|
| 7 |
+
"AutoConfig": "AIDC-AI/Ovis1.6-Llama3.2-3B--configuration_ovis.OvisConfig",
|
| 8 |
+
"AutoModelForCausalLM": "AIDC-AI/Ovis1.6-Llama3.2-3B--modeling_ovis.Ovis"
|
| 9 |
+
},
|
| 10 |
+
"conversation_formatter_class": "AgentFormatter",
|
| 11 |
+
"disable_tie_weight": false,
|
| 12 |
+
"hidden_size": 3072,
|
| 13 |
+
"llm_attn_implementation": "flash_attention_2",
|
| 14 |
+
"llm_config": {
|
| 15 |
+
"_name_or_path": "meta-llama/Llama-3.2-3B",
|
| 16 |
+
"add_cross_attention": false,
|
| 17 |
+
"architectures": [
|
| 18 |
+
"LlamaForCausalLM"
|
| 19 |
+
],
|
| 20 |
+
"attention_bias": false,
|
| 21 |
+
"attention_dropout": 0.0,
|
| 22 |
+
"bad_words_ids": null,
|
| 23 |
+
"begin_suppress_tokens": null,
|
| 24 |
+
"bos_token_id": 128000,
|
| 25 |
+
"chunk_size_feed_forward": 0,
|
| 26 |
+
"cross_attention_hidden_size": null,
|
| 27 |
+
"decoder_start_token_id": null,
|
| 28 |
+
"diversity_penalty": 0.0,
|
| 29 |
+
"do_sample": false,
|
| 30 |
+
"early_stopping": false,
|
| 31 |
+
"encoder_no_repeat_ngram_size": 0,
|
| 32 |
+
"eos_token_id": [
|
| 33 |
+
128001,
|
| 34 |
+
128008,
|
| 35 |
+
128009
|
| 36 |
+
],
|
| 37 |
+
"exponential_decay_length_penalty": null,
|
| 38 |
+
"finetuning_task": null,
|
| 39 |
+
"forced_bos_token_id": null,
|
| 40 |
+
"forced_eos_token_id": null,
|
| 41 |
+
"head_dim": 128,
|
| 42 |
+
"hidden_act": "silu",
|
| 43 |
+
"hidden_size": 3072,
|
| 44 |
+
"id2label": {
|
| 45 |
+
"0": "LABEL_0",
|
| 46 |
+
"1": "LABEL_1"
|
| 47 |
+
},
|
| 48 |
+
"initializer_range": 0.02,
|
| 49 |
+
"intermediate_size": 8192,
|
| 50 |
+
"is_decoder": false,
|
| 51 |
+
"is_encoder_decoder": false,
|
| 52 |
+
"label2id": {
|
| 53 |
+
"LABEL_0": 0,
|
| 54 |
+
"LABEL_1": 1
|
| 55 |
+
},
|
| 56 |
+
"length_penalty": 1.0,
|
| 57 |
+
"max_length": 20,
|
| 58 |
+
"max_position_embeddings": 131072,
|
| 59 |
+
"min_length": 0,
|
| 60 |
+
"mlp_bias": false,
|
| 61 |
+
"model_type": "llama",
|
| 62 |
+
"no_repeat_ngram_size": 0,
|
| 63 |
+
"num_attention_heads": 24,
|
| 64 |
+
"num_beam_groups": 1,
|
| 65 |
+
"num_beams": 1,
|
| 66 |
+
"num_hidden_layers": 28,
|
| 67 |
+
"num_key_value_heads": 8,
|
| 68 |
+
"num_return_sequences": 1,
|
| 69 |
+
"output_attentions": false,
|
| 70 |
+
"output_hidden_states": false,
|
| 71 |
+
"output_scores": false,
|
| 72 |
+
"pad_token_id": null,
|
| 73 |
+
"prefix": null,
|
| 74 |
+
"pretraining_tp": 1,
|
| 75 |
+
"problem_type": null,
|
| 76 |
+
"pruned_heads": {},
|
| 77 |
+
"remove_invalid_values": false,
|
| 78 |
+
"repetition_penalty": 1.0,
|
| 79 |
+
"return_dict": true,
|
| 80 |
+
"return_dict_in_generate": false,
|
| 81 |
+
"rms_norm_eps": 1e-05,
|
| 82 |
+
"rope_scaling": {
|
| 83 |
+
"factor": 32.0,
|
| 84 |
+
"high_freq_factor": 4.0,
|
| 85 |
+
"low_freq_factor": 1.0,
|
| 86 |
+
"original_max_position_embeddings": 8192,
|
| 87 |
+
"rope_type": "llama3"
|
| 88 |
+
},
|
| 89 |
+
"rope_theta": 500000.0,
|
| 90 |
+
"sep_token_id": null,
|
| 91 |
+
"suppress_tokens": null,
|
| 92 |
+
"task_specific_params": null,
|
| 93 |
+
"temperature": 1.0,
|
| 94 |
+
"tf_legacy_loss": false,
|
| 95 |
+
"tie_encoder_decoder": false,
|
| 96 |
+
"tie_word_embeddings": true,
|
| 97 |
+
"tokenizer_class": null,
|
| 98 |
+
"top_k": 50,
|
| 99 |
+
"top_p": 1.0,
|
| 100 |
+
"torch_dtype": "bfloat16",
|
| 101 |
+
"torchscript": false,
|
| 102 |
+
"typical_p": 1.0,
|
| 103 |
+
"use_bfloat16": false,
|
| 104 |
+
"use_cache": true,
|
| 105 |
+
"vocab_size": 128256
|
| 106 |
+
},
|
| 107 |
+
"model_type": "ovis",
|
| 108 |
+
"multimodal_max_length": 2048,
|
| 109 |
+
"torch_dtype": "bfloat16",
|
| 110 |
+
"transformers_version": "4.44.2",
|
| 111 |
+
"use_cache": false,
|
| 112 |
+
"visual_tokenizer_config": {
|
| 113 |
+
"_name_or_path": "",
|
| 114 |
+
"add_cross_attention": false,
|
| 115 |
+
"architectures": [
|
| 116 |
+
"SiglipVisualTokenizer"
|
| 117 |
+
],
|
| 118 |
+
"backbone_config": {
|
| 119 |
+
"_name_or_path": "google/siglip-so400m-patch14-384",
|
| 120 |
+
"add_cross_attention": false,
|
| 121 |
+
"architectures": null,
|
| 122 |
+
"attention_dropout": 0.0,
|
| 123 |
+
"bad_words_ids": null,
|
| 124 |
+
"begin_suppress_tokens": null,
|
| 125 |
+
"bos_token_id": null,
|
| 126 |
+
"chunk_size_feed_forward": 0,
|
| 127 |
+
"cross_attention_hidden_size": null,
|
| 128 |
+
"decoder_start_token_id": null,
|
| 129 |
+
"diversity_penalty": 0.0,
|
| 130 |
+
"do_sample": false,
|
| 131 |
+
"early_stopping": false,
|
| 132 |
+
"encoder_no_repeat_ngram_size": 0,
|
| 133 |
+
"eos_token_id": null,
|
| 134 |
+
"exponential_decay_length_penalty": null,
|
| 135 |
+
"finetuning_task": null,
|
| 136 |
+
"forced_bos_token_id": null,
|
| 137 |
+
"forced_eos_token_id": null,
|
| 138 |
+
"hidden_act": "gelu_pytorch_tanh",
|
| 139 |
+
"hidden_size": 1152,
|
| 140 |
+
"id2label": {
|
| 141 |
+
"0": "LABEL_0",
|
| 142 |
+
"1": "LABEL_1"
|
| 143 |
+
},
|
| 144 |
+
"image_size": 384,
|
| 145 |
+
"intermediate_size": 4304,
|
| 146 |
+
"is_decoder": false,
|
| 147 |
+
"is_encoder_decoder": false,
|
| 148 |
+
"label2id": {
|
| 149 |
+
"LABEL_0": 0,
|
| 150 |
+
"LABEL_1": 1
|
| 151 |
+
},
|
| 152 |
+
"layer_norm_eps": 1e-06,
|
| 153 |
+
"length_penalty": 1.0,
|
| 154 |
+
"max_length": 20,
|
| 155 |
+
"min_length": 0,
|
| 156 |
+
"model_type": "siglip_vision_model",
|
| 157 |
+
"no_repeat_ngram_size": 0,
|
| 158 |
+
"num_attention_heads": 16,
|
| 159 |
+
"num_beam_groups": 1,
|
| 160 |
+
"num_beams": 1,
|
| 161 |
+
"num_channels": 3,
|
| 162 |
+
"num_hidden_layers": 27,
|
| 163 |
+
"num_return_sequences": 1,
|
| 164 |
+
"output_attentions": false,
|
| 165 |
+
"output_hidden_states": false,
|
| 166 |
+
"output_scores": false,
|
| 167 |
+
"pad_token_id": null,
|
| 168 |
+
"patch_size": 14,
|
| 169 |
+
"prefix": null,
|
| 170 |
+
"problem_type": null,
|
| 171 |
+
"pruned_heads": {},
|
| 172 |
+
"remove_invalid_values": false,
|
| 173 |
+
"repetition_penalty": 1.0,
|
| 174 |
+
"return_dict": true,
|
| 175 |
+
"return_dict_in_generate": false,
|
| 176 |
+
"sep_token_id": null,
|
| 177 |
+
"suppress_tokens": null,
|
| 178 |
+
"task_specific_params": null,
|
| 179 |
+
"temperature": 1.0,
|
| 180 |
+
"tf_legacy_loss": false,
|
| 181 |
+
"tie_encoder_decoder": false,
|
| 182 |
+
"tie_word_embeddings": true,
|
| 183 |
+
"tokenizer_class": null,
|
| 184 |
+
"top_k": 50,
|
| 185 |
+
"top_p": 1.0,
|
| 186 |
+
"torch_dtype": null,
|
| 187 |
+
"torchscript": false,
|
| 188 |
+
"typical_p": 1.0,
|
| 189 |
+
"use_bfloat16": false
|
| 190 |
+
},
|
| 191 |
+
"backbone_kwargs": {},
|
| 192 |
+
"bad_words_ids": null,
|
| 193 |
+
"begin_suppress_tokens": null,
|
| 194 |
+
"bos_token_id": null,
|
| 195 |
+
"chunk_size_feed_forward": 0,
|
| 196 |
+
"cross_attention_hidden_size": null,
|
| 197 |
+
"decoder_start_token_id": null,
|
| 198 |
+
"depths": null,
|
| 199 |
+
"diversity_penalty": 0.0,
|
| 200 |
+
"do_sample": false,
|
| 201 |
+
"drop_cls_token": false,
|
| 202 |
+
"early_stopping": false,
|
| 203 |
+
"encoder_no_repeat_ngram_size": 0,
|
| 204 |
+
"eos_token_id": null,
|
| 205 |
+
"exponential_decay_length_penalty": null,
|
| 206 |
+
"finetuning_task": null,
|
| 207 |
+
"forced_bos_token_id": null,
|
| 208 |
+
"forced_eos_token_id": null,
|
| 209 |
+
"hidden_stride": 2,
|
| 210 |
+
"id2label": {
|
| 211 |
+
"0": "LABEL_0",
|
| 212 |
+
"1": "LABEL_1"
|
| 213 |
+
},
|
| 214 |
+
"is_decoder": false,
|
| 215 |
+
"is_encoder_decoder": false,
|
| 216 |
+
"label2id": {
|
| 217 |
+
"LABEL_0": 0,
|
| 218 |
+
"LABEL_1": 1
|
| 219 |
+
},
|
| 220 |
+
"length_penalty": 1.0,
|
| 221 |
+
"max_length": 20,
|
| 222 |
+
"min_length": 0,
|
| 223 |
+
"model_type": "siglip_visual_tokenizer",
|
| 224 |
+
"no_repeat_ngram_size": 0,
|
| 225 |
+
"num_beam_groups": 1,
|
| 226 |
+
"num_beams": 1,
|
| 227 |
+
"num_return_sequences": 1,
|
| 228 |
+
"output_attentions": false,
|
| 229 |
+
"output_hidden_states": false,
|
| 230 |
+
"output_scores": false,
|
| 231 |
+
"pad_token_id": null,
|
| 232 |
+
"prefix": null,
|
| 233 |
+
"problem_type": null,
|
| 234 |
+
"pruned_heads": {},
|
| 235 |
+
"remove_invalid_values": false,
|
| 236 |
+
"repetition_penalty": 1.0,
|
| 237 |
+
"return_dict": true,
|
| 238 |
+
"return_dict_in_generate": false,
|
| 239 |
+
"sep_token_id": null,
|
| 240 |
+
"suppress_tokens": null,
|
| 241 |
+
"task_specific_params": null,
|
| 242 |
+
"tau": 1.0,
|
| 243 |
+
"temperature": 1.0,
|
| 244 |
+
"tf_legacy_loss": false,
|
| 245 |
+
"tie_encoder_decoder": false,
|
| 246 |
+
"tie_word_embeddings": true,
|
| 247 |
+
"tokenize_function": "softmax",
|
| 248 |
+
"tokenizer_class": null,
|
| 249 |
+
"top_k": 50,
|
| 250 |
+
"top_p": 1.0,
|
| 251 |
+
"torch_dtype": "float32",
|
| 252 |
+
"torchscript": false,
|
| 253 |
+
"typical_p": 1.0,
|
| 254 |
+
"use_bfloat16": false,
|
| 255 |
+
"use_indicators": false,
|
| 256 |
+
"vocab_size": 65536
|
| 257 |
+
}
|
| 258 |
+
}
|
checkpoint-132825/generation_config.json
ADDED
|
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token_id": 128000,
|
| 3 |
+
"do_sample": true,
|
| 4 |
+
"eos_token_id": [
|
| 5 |
+
128001,
|
| 6 |
+
128008,
|
| 7 |
+
128009
|
| 8 |
+
],
|
| 9 |
+
"multimodal_max_length": 2048,
|
| 10 |
+
"temperature": 0.6,
|
| 11 |
+
"top_p": 0.9,
|
| 12 |
+
"transformers_version": "4.44.2"
|
| 13 |
+
}
|
checkpoint-132825/global_step132825/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c00e37e03804745ddb3e86df96243602c842004abf3779b72300f7167119f57d
|
| 3 |
+
size 12433213772
|
checkpoint-132825/global_step132825/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a6133d55792b687ebb42eeb43a6712d38db17c5f2bb867bc1e0516737758c3c9
|
| 3 |
+
size 12433224588
|
checkpoint-132825/global_step132825/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6f0eb7d3ac26e832027c5a6b515b3c7ba1f827d70028fa5ea348f0a7e4cb87eb
|
| 3 |
+
size 12433224460
|
checkpoint-132825/global_step132825/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:364baa818b280ee0d941d310efaec786de5f42a148b1854fc460ff40188b59a0
|
| 3 |
+
size 12433228940
|
checkpoint-132825/global_step132825/mp_rank_00_model_states.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9b5dc6198638b03524573f4c2b39a7740304cbb09c58066e808c268a6b9a8648
|
| 3 |
+
size 8289039032
|
checkpoint-132825/latest
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
global_step132825
|
checkpoint-132825/model-00001-of-00002.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e29889cafb081e011b76de8d2dc731af9d9d7622bed24537bdc70ed0e091099b
|
| 3 |
+
size 4965799848
|
checkpoint-132825/model-00002-of-00002.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:32c869f8dac86306de73c7fa6d51803feb09000f08d245a3575e9e55a93a14ac
|
| 3 |
+
size 4111103436
|
checkpoint-132825/model.safetensors.index.json
ADDED
|
@@ -0,0 +1,714 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"metadata": {
|
| 3 |
+
"total_size": 9076804716
|
| 4 |
+
},
|
| 5 |
+
"weight_map": {
|
| 6 |
+
"llm.lm_head.weight": "model-00002-of-00002.safetensors",
|
| 7 |
+
"llm.model.embed_tokens.weight": "model-00001-of-00002.safetensors",
|
| 8 |
+
"llm.model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 9 |
+
"llm.model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 10 |
+
"llm.model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 11 |
+
"llm.model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 12 |
+
"llm.model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 13 |
+
"llm.model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 14 |
+
"llm.model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 15 |
+
"llm.model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 16 |
+
"llm.model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 17 |
+
"llm.model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 18 |
+
"llm.model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 19 |
+
"llm.model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 20 |
+
"llm.model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 21 |
+
"llm.model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 22 |
+
"llm.model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 23 |
+
"llm.model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 24 |
+
"llm.model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 25 |
+
"llm.model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 26 |
+
"llm.model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 27 |
+
"llm.model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 28 |
+
"llm.model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 29 |
+
"llm.model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 30 |
+
"llm.model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 31 |
+
"llm.model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 32 |
+
"llm.model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 33 |
+
"llm.model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 34 |
+
"llm.model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 35 |
+
"llm.model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 36 |
+
"llm.model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 37 |
+
"llm.model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 38 |
+
"llm.model.layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 39 |
+
"llm.model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 40 |
+
"llm.model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 41 |
+
"llm.model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 42 |
+
"llm.model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 43 |
+
"llm.model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 44 |
+
"llm.model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 45 |
+
"llm.model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 46 |
+
"llm.model.layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 47 |
+
"llm.model.layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 48 |
+
"llm.model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 49 |
+
"llm.model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 50 |
+
"llm.model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 51 |
+
"llm.model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 52 |
+
"llm.model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 53 |
+
"llm.model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 54 |
+
"llm.model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 55 |
+
"llm.model.layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 56 |
+
"llm.model.layers.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 57 |
+
"llm.model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 58 |
+
"llm.model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 59 |
+
"llm.model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 60 |
+
"llm.model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 61 |
+
"llm.model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 62 |
+
"llm.model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 63 |
+
"llm.model.layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 64 |
+
"llm.model.layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 65 |
+
"llm.model.layers.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 66 |
+
"llm.model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 67 |
+
"llm.model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 68 |
+
"llm.model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 69 |
+
"llm.model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 70 |
+
"llm.model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 71 |
+
"llm.model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 72 |
+
"llm.model.layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 73 |
+
"llm.model.layers.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 74 |
+
"llm.model.layers.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 75 |
+
"llm.model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 76 |
+
"llm.model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 77 |
+
"llm.model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 78 |
+
"llm.model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 79 |
+
"llm.model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 80 |
+
"llm.model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 81 |
+
"llm.model.layers.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 82 |
+
"llm.model.layers.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 83 |
+
"llm.model.layers.16.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 84 |
+
"llm.model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 85 |
+
"llm.model.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 86 |
+
"llm.model.layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 87 |
+
"llm.model.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 88 |
+
"llm.model.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 89 |
+
"llm.model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 90 |
+
"llm.model.layers.17.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 91 |
+
"llm.model.layers.17.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 92 |
+
"llm.model.layers.17.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 93 |
+
"llm.model.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 94 |
+
"llm.model.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 95 |
+
"llm.model.layers.17.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 96 |
+
"llm.model.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 97 |
+
"llm.model.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 98 |
+
"llm.model.layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 99 |
+
"llm.model.layers.18.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 100 |
+
"llm.model.layers.18.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 101 |
+
"llm.model.layers.18.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 102 |
+
"llm.model.layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 103 |
+
"llm.model.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 104 |
+
"llm.model.layers.18.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 105 |
+
"llm.model.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 106 |
+
"llm.model.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 107 |
+
"llm.model.layers.19.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 108 |
+
"llm.model.layers.19.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 109 |
+
"llm.model.layers.19.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 110 |
+
"llm.model.layers.19.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 111 |
+
"llm.model.layers.19.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 112 |
+
"llm.model.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 113 |
+
"llm.model.layers.19.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 114 |
+
"llm.model.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 115 |
+
"llm.model.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 116 |
+
"llm.model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 117 |
+
"llm.model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 118 |
+
"llm.model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 119 |
+
"llm.model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 120 |
+
"llm.model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 121 |
+
"llm.model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 122 |
+
"llm.model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 123 |
+
"llm.model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 124 |
+
"llm.model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 125 |
+
"llm.model.layers.20.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 126 |
+
"llm.model.layers.20.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 127 |
+
"llm.model.layers.20.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 128 |
+
"llm.model.layers.20.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 129 |
+
"llm.model.layers.20.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 130 |
+
"llm.model.layers.20.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 131 |
+
"llm.model.layers.20.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 132 |
+
"llm.model.layers.20.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 133 |
+
"llm.model.layers.20.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 134 |
+
"llm.model.layers.21.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 135 |
+
"llm.model.layers.21.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 136 |
+
"llm.model.layers.21.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 137 |
+
"llm.model.layers.21.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 138 |
+
"llm.model.layers.21.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 139 |
+
"llm.model.layers.21.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 140 |
+
"llm.model.layers.21.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 141 |
+
"llm.model.layers.21.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 142 |
+
"llm.model.layers.21.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 143 |
+
"llm.model.layers.22.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 144 |
+
"llm.model.layers.22.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 145 |
+
"llm.model.layers.22.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 146 |
+
"llm.model.layers.22.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 147 |
+
"llm.model.layers.22.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 148 |
+
"llm.model.layers.22.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 149 |
+
"llm.model.layers.22.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 150 |
+
"llm.model.layers.22.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 151 |
+
"llm.model.layers.22.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 152 |
+
"llm.model.layers.23.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 153 |
+
"llm.model.layers.23.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 154 |
+
"llm.model.layers.23.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 155 |
+
"llm.model.layers.23.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 156 |
+
"llm.model.layers.23.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 157 |
+
"llm.model.layers.23.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 158 |
+
"llm.model.layers.23.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 159 |
+
"llm.model.layers.23.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 160 |
+
"llm.model.layers.23.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 161 |
+
"llm.model.layers.24.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 162 |
+
"llm.model.layers.24.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 163 |
+
"llm.model.layers.24.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 164 |
+
"llm.model.layers.24.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 165 |
+
"llm.model.layers.24.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 166 |
+
"llm.model.layers.24.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 167 |
+
"llm.model.layers.24.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 168 |
+
"llm.model.layers.24.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 169 |
+
"llm.model.layers.24.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 170 |
+
"llm.model.layers.25.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 171 |
+
"llm.model.layers.25.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 172 |
+
"llm.model.layers.25.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 173 |
+
"llm.model.layers.25.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 174 |
+
"llm.model.layers.25.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 175 |
+
"llm.model.layers.25.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 176 |
+
"llm.model.layers.25.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 177 |
+
"llm.model.layers.25.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 178 |
+
"llm.model.layers.25.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 179 |
+
"llm.model.layers.26.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 180 |
+
"llm.model.layers.26.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 181 |
+
"llm.model.layers.26.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 182 |
+
"llm.model.layers.26.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 183 |
+
"llm.model.layers.26.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 184 |
+
"llm.model.layers.26.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 185 |
+
"llm.model.layers.26.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 186 |
+
"llm.model.layers.26.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 187 |
+
"llm.model.layers.26.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 188 |
+
"llm.model.layers.27.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 189 |
+
"llm.model.layers.27.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 190 |
+
"llm.model.layers.27.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 191 |
+
"llm.model.layers.27.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 192 |
+
"llm.model.layers.27.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 193 |
+
"llm.model.layers.27.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 194 |
+
"llm.model.layers.27.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 195 |
+
"llm.model.layers.27.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 196 |
+
"llm.model.layers.27.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 197 |
+
"llm.model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 198 |
+
"llm.model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 199 |
+
"llm.model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 200 |
+
"llm.model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 201 |
+
"llm.model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 202 |
+
"llm.model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 203 |
+
"llm.model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 204 |
+
"llm.model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 205 |
+
"llm.model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 206 |
+
"llm.model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 207 |
+
"llm.model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 208 |
+
"llm.model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 209 |
+
"llm.model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 210 |
+
"llm.model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 211 |
+
"llm.model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 212 |
+
"llm.model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 213 |
+
"llm.model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 214 |
+
"llm.model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 215 |
+
"llm.model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 216 |
+
"llm.model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 217 |
+
"llm.model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 218 |
+
"llm.model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 219 |
+
"llm.model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 220 |
+
"llm.model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 221 |
+
"llm.model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 222 |
+
"llm.model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 223 |
+
"llm.model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 224 |
+
"llm.model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 225 |
+
"llm.model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 226 |
+
"llm.model.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 227 |
+
"llm.model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 228 |
+
"llm.model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 229 |
+
"llm.model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 230 |
+
"llm.model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 231 |
+
"llm.model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 232 |
+
"llm.model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 233 |
+
"llm.model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 234 |
+
"llm.model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 235 |
+
"llm.model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 236 |
+
"llm.model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 237 |
+
"llm.model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 238 |
+
"llm.model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 239 |
+
"llm.model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 240 |
+
"llm.model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 241 |
+
"llm.model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 242 |
+
"llm.model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 243 |
+
"llm.model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 244 |
+
"llm.model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 245 |
+
"llm.model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 246 |
+
"llm.model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 247 |
+
"llm.model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 248 |
+
"llm.model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 249 |
+
"llm.model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 250 |
+
"llm.model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 251 |
+
"llm.model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 252 |
+
"llm.model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 253 |
+
"llm.model.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 254 |
+
"llm.model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 255 |
+
"llm.model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 256 |
+
"llm.model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 257 |
+
"llm.model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 258 |
+
"llm.model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 259 |
+
"llm.model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 260 |
+
"llm.model.norm.weight": "model-00002-of-00002.safetensors",
|
| 261 |
+
"visual_tokenizer.backbone.vision_model.embeddings.patch_embedding.bias": "model-00002-of-00002.safetensors",
|
| 262 |
+
"visual_tokenizer.backbone.vision_model.embeddings.patch_embedding.weight": "model-00002-of-00002.safetensors",
|
| 263 |
+
"visual_tokenizer.backbone.vision_model.embeddings.position_embedding.weight": "model-00002-of-00002.safetensors",
|
| 264 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.0.layer_norm1.bias": "model-00002-of-00002.safetensors",
|
| 265 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.0.layer_norm1.weight": "model-00002-of-00002.safetensors",
|
| 266 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.0.layer_norm2.bias": "model-00002-of-00002.safetensors",
|
| 267 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.0.layer_norm2.weight": "model-00002-of-00002.safetensors",
|
| 268 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.0.mlp.fc1.bias": "model-00002-of-00002.safetensors",
|
| 269 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.0.mlp.fc1.weight": "model-00002-of-00002.safetensors",
|
| 270 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.0.mlp.fc2.bias": "model-00002-of-00002.safetensors",
|
| 271 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.0.mlp.fc2.weight": "model-00002-of-00002.safetensors",
|
| 272 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.0.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
| 273 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.0.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 274 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.0.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
|
| 275 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.0.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
|
| 276 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.0.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
| 277 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.0.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 278 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.0.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
| 279 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.0.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 280 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.1.layer_norm1.bias": "model-00002-of-00002.safetensors",
|
| 281 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.1.layer_norm1.weight": "model-00002-of-00002.safetensors",
|
| 282 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.1.layer_norm2.bias": "model-00002-of-00002.safetensors",
|
| 283 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.1.layer_norm2.weight": "model-00002-of-00002.safetensors",
|
| 284 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.1.mlp.fc1.bias": "model-00002-of-00002.safetensors",
|
| 285 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.1.mlp.fc1.weight": "model-00002-of-00002.safetensors",
|
| 286 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.1.mlp.fc2.bias": "model-00002-of-00002.safetensors",
|
| 287 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.1.mlp.fc2.weight": "model-00002-of-00002.safetensors",
|
| 288 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.1.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
| 289 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.1.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 290 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.1.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
|
| 291 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.1.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
|
| 292 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.1.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
| 293 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.1.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 294 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.1.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
| 295 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.1.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 296 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.10.layer_norm1.bias": "model-00002-of-00002.safetensors",
|
| 297 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.10.layer_norm1.weight": "model-00002-of-00002.safetensors",
|
| 298 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.10.layer_norm2.bias": "model-00002-of-00002.safetensors",
|
| 299 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.10.layer_norm2.weight": "model-00002-of-00002.safetensors",
|
| 300 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.10.mlp.fc1.bias": "model-00002-of-00002.safetensors",
|
| 301 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.10.mlp.fc1.weight": "model-00002-of-00002.safetensors",
|
| 302 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.10.mlp.fc2.bias": "model-00002-of-00002.safetensors",
|
| 303 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.10.mlp.fc2.weight": "model-00002-of-00002.safetensors",
|
| 304 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.10.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
| 305 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.10.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 306 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.10.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
|
| 307 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.10.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
|
| 308 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.10.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
| 309 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.10.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 310 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.10.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
| 311 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.10.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 312 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.11.layer_norm1.bias": "model-00002-of-00002.safetensors",
|
| 313 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.11.layer_norm1.weight": "model-00002-of-00002.safetensors",
|
| 314 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.11.layer_norm2.bias": "model-00002-of-00002.safetensors",
|
| 315 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.11.layer_norm2.weight": "model-00002-of-00002.safetensors",
|
| 316 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.11.mlp.fc1.bias": "model-00002-of-00002.safetensors",
|
| 317 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.11.mlp.fc1.weight": "model-00002-of-00002.safetensors",
|
| 318 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.11.mlp.fc2.bias": "model-00002-of-00002.safetensors",
|
| 319 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.11.mlp.fc2.weight": "model-00002-of-00002.safetensors",
|
| 320 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.11.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
| 321 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.11.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 322 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.11.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
|
| 323 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.11.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
|
| 324 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.11.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
| 325 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.11.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 326 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.11.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
| 327 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.11.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 328 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.12.layer_norm1.bias": "model-00002-of-00002.safetensors",
|
| 329 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.12.layer_norm1.weight": "model-00002-of-00002.safetensors",
|
| 330 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.12.layer_norm2.bias": "model-00002-of-00002.safetensors",
|
| 331 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.12.layer_norm2.weight": "model-00002-of-00002.safetensors",
|
| 332 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.12.mlp.fc1.bias": "model-00002-of-00002.safetensors",
|
| 333 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.12.mlp.fc1.weight": "model-00002-of-00002.safetensors",
|
| 334 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.12.mlp.fc2.bias": "model-00002-of-00002.safetensors",
|
| 335 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.12.mlp.fc2.weight": "model-00002-of-00002.safetensors",
|
| 336 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.12.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
| 337 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.12.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 338 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.12.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
|
| 339 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.12.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
|
| 340 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.12.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
| 341 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.12.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 342 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.12.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
| 343 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.12.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 344 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.13.layer_norm1.bias": "model-00002-of-00002.safetensors",
|
| 345 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.13.layer_norm1.weight": "model-00002-of-00002.safetensors",
|
| 346 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.13.layer_norm2.bias": "model-00002-of-00002.safetensors",
|
| 347 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.13.layer_norm2.weight": "model-00002-of-00002.safetensors",
|
| 348 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.13.mlp.fc1.bias": "model-00002-of-00002.safetensors",
|
| 349 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.13.mlp.fc1.weight": "model-00002-of-00002.safetensors",
|
| 350 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.13.mlp.fc2.bias": "model-00002-of-00002.safetensors",
|
| 351 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.13.mlp.fc2.weight": "model-00002-of-00002.safetensors",
|
| 352 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.13.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
| 353 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.13.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 354 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.13.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
|
| 355 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.13.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
|
| 356 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.13.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
| 357 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.13.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 358 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.13.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
| 359 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.13.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 360 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.14.layer_norm1.bias": "model-00002-of-00002.safetensors",
|
| 361 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.14.layer_norm1.weight": "model-00002-of-00002.safetensors",
|
| 362 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.14.layer_norm2.bias": "model-00002-of-00002.safetensors",
|
| 363 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.14.layer_norm2.weight": "model-00002-of-00002.safetensors",
|
| 364 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.14.mlp.fc1.bias": "model-00002-of-00002.safetensors",
|
| 365 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.14.mlp.fc1.weight": "model-00002-of-00002.safetensors",
|
| 366 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.14.mlp.fc2.bias": "model-00002-of-00002.safetensors",
|
| 367 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.14.mlp.fc2.weight": "model-00002-of-00002.safetensors",
|
| 368 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.14.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
| 369 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.14.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 370 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.14.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
|
| 371 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.14.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
|
| 372 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.14.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
| 373 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.14.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 374 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.14.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
| 375 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.14.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 376 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.15.layer_norm1.bias": "model-00002-of-00002.safetensors",
|
| 377 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.15.layer_norm1.weight": "model-00002-of-00002.safetensors",
|
| 378 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.15.layer_norm2.bias": "model-00002-of-00002.safetensors",
|
| 379 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.15.layer_norm2.weight": "model-00002-of-00002.safetensors",
|
| 380 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.15.mlp.fc1.bias": "model-00002-of-00002.safetensors",
|
| 381 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.15.mlp.fc1.weight": "model-00002-of-00002.safetensors",
|
| 382 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.15.mlp.fc2.bias": "model-00002-of-00002.safetensors",
|
| 383 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.15.mlp.fc2.weight": "model-00002-of-00002.safetensors",
|
| 384 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.15.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
| 385 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.15.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 386 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.15.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
|
| 387 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.15.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
|
| 388 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.15.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
| 389 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.15.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 390 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.15.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
| 391 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.15.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 392 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.16.layer_norm1.bias": "model-00002-of-00002.safetensors",
|
| 393 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.16.layer_norm1.weight": "model-00002-of-00002.safetensors",
|
| 394 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.16.layer_norm2.bias": "model-00002-of-00002.safetensors",
|
| 395 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.16.layer_norm2.weight": "model-00002-of-00002.safetensors",
|
| 396 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.16.mlp.fc1.bias": "model-00002-of-00002.safetensors",
|
| 397 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.16.mlp.fc1.weight": "model-00002-of-00002.safetensors",
|
| 398 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.16.mlp.fc2.bias": "model-00002-of-00002.safetensors",
|
| 399 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.16.mlp.fc2.weight": "model-00002-of-00002.safetensors",
|
| 400 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.16.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
| 401 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.16.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 402 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.16.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
|
| 403 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.16.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
|
| 404 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.16.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
| 405 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.16.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 406 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.16.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
| 407 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.16.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 408 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.17.layer_norm1.bias": "model-00002-of-00002.safetensors",
|
| 409 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.17.layer_norm1.weight": "model-00002-of-00002.safetensors",
|
| 410 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.17.layer_norm2.bias": "model-00002-of-00002.safetensors",
|
| 411 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.17.layer_norm2.weight": "model-00002-of-00002.safetensors",
|
| 412 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.17.mlp.fc1.bias": "model-00002-of-00002.safetensors",
|
| 413 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.17.mlp.fc1.weight": "model-00002-of-00002.safetensors",
|
| 414 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.17.mlp.fc2.bias": "model-00002-of-00002.safetensors",
|
| 415 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.17.mlp.fc2.weight": "model-00002-of-00002.safetensors",
|
| 416 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.17.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
| 417 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.17.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 418 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.17.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
|
| 419 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.17.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
|
| 420 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.17.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
| 421 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.17.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 422 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.17.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
| 423 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.17.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 424 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.18.layer_norm1.bias": "model-00002-of-00002.safetensors",
|
| 425 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.18.layer_norm1.weight": "model-00002-of-00002.safetensors",
|
| 426 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.18.layer_norm2.bias": "model-00002-of-00002.safetensors",
|
| 427 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.18.layer_norm2.weight": "model-00002-of-00002.safetensors",
|
| 428 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.18.mlp.fc1.bias": "model-00002-of-00002.safetensors",
|
| 429 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.18.mlp.fc1.weight": "model-00002-of-00002.safetensors",
|
| 430 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.18.mlp.fc2.bias": "model-00002-of-00002.safetensors",
|
| 431 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.18.mlp.fc2.weight": "model-00002-of-00002.safetensors",
|
| 432 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.18.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
| 433 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.18.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 434 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.18.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
|
| 435 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.18.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
|
| 436 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.18.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
| 437 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.18.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 438 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.18.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
| 439 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.18.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 440 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.19.layer_norm1.bias": "model-00002-of-00002.safetensors",
|
| 441 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.19.layer_norm1.weight": "model-00002-of-00002.safetensors",
|
| 442 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.19.layer_norm2.bias": "model-00002-of-00002.safetensors",
|
| 443 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.19.layer_norm2.weight": "model-00002-of-00002.safetensors",
|
| 444 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.19.mlp.fc1.bias": "model-00002-of-00002.safetensors",
|
| 445 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.19.mlp.fc1.weight": "model-00002-of-00002.safetensors",
|
| 446 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.19.mlp.fc2.bias": "model-00002-of-00002.safetensors",
|
| 447 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.19.mlp.fc2.weight": "model-00002-of-00002.safetensors",
|
| 448 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.19.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
| 449 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.19.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 450 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.19.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
|
| 451 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.19.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
|
| 452 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.19.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
| 453 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.19.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 454 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.19.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
| 455 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.19.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 456 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.2.layer_norm1.bias": "model-00002-of-00002.safetensors",
|
| 457 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.2.layer_norm1.weight": "model-00002-of-00002.safetensors",
|
| 458 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.2.layer_norm2.bias": "model-00002-of-00002.safetensors",
|
| 459 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.2.layer_norm2.weight": "model-00002-of-00002.safetensors",
|
| 460 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.2.mlp.fc1.bias": "model-00002-of-00002.safetensors",
|
| 461 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.2.mlp.fc1.weight": "model-00002-of-00002.safetensors",
|
| 462 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.2.mlp.fc2.bias": "model-00002-of-00002.safetensors",
|
| 463 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.2.mlp.fc2.weight": "model-00002-of-00002.safetensors",
|
| 464 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.2.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
| 465 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.2.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 466 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.2.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
|
| 467 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.2.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
|
| 468 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.2.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
| 469 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.2.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 470 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.2.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
| 471 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.2.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 472 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.20.layer_norm1.bias": "model-00002-of-00002.safetensors",
|
| 473 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.20.layer_norm1.weight": "model-00002-of-00002.safetensors",
|
| 474 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.20.layer_norm2.bias": "model-00002-of-00002.safetensors",
|
| 475 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.20.layer_norm2.weight": "model-00002-of-00002.safetensors",
|
| 476 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.20.mlp.fc1.bias": "model-00002-of-00002.safetensors",
|
| 477 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.20.mlp.fc1.weight": "model-00002-of-00002.safetensors",
|
| 478 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.20.mlp.fc2.bias": "model-00002-of-00002.safetensors",
|
| 479 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.20.mlp.fc2.weight": "model-00002-of-00002.safetensors",
|
| 480 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.20.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
| 481 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.20.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 482 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.20.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
|
| 483 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.20.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
|
| 484 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.20.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
| 485 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.20.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 486 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.20.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
| 487 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.20.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 488 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.21.layer_norm1.bias": "model-00002-of-00002.safetensors",
|
| 489 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.21.layer_norm1.weight": "model-00002-of-00002.safetensors",
|
| 490 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.21.layer_norm2.bias": "model-00002-of-00002.safetensors",
|
| 491 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.21.layer_norm2.weight": "model-00002-of-00002.safetensors",
|
| 492 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.21.mlp.fc1.bias": "model-00002-of-00002.safetensors",
|
| 493 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.21.mlp.fc1.weight": "model-00002-of-00002.safetensors",
|
| 494 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.21.mlp.fc2.bias": "model-00002-of-00002.safetensors",
|
| 495 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.21.mlp.fc2.weight": "model-00002-of-00002.safetensors",
|
| 496 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.21.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
| 497 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.21.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 498 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.21.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
|
| 499 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.21.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
|
| 500 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.21.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
| 501 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.21.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 502 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.21.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
| 503 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.21.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 504 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.22.layer_norm1.bias": "model-00002-of-00002.safetensors",
|
| 505 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.22.layer_norm1.weight": "model-00002-of-00002.safetensors",
|
| 506 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.22.layer_norm2.bias": "model-00002-of-00002.safetensors",
|
| 507 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.22.layer_norm2.weight": "model-00002-of-00002.safetensors",
|
| 508 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.22.mlp.fc1.bias": "model-00002-of-00002.safetensors",
|
| 509 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.22.mlp.fc1.weight": "model-00002-of-00002.safetensors",
|
| 510 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.22.mlp.fc2.bias": "model-00002-of-00002.safetensors",
|
| 511 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.22.mlp.fc2.weight": "model-00002-of-00002.safetensors",
|
| 512 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.22.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
| 513 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.22.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 514 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.22.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
|
| 515 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.22.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
|
| 516 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.22.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
| 517 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.22.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 518 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.22.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
| 519 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.22.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 520 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.23.layer_norm1.bias": "model-00002-of-00002.safetensors",
|
| 521 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.23.layer_norm1.weight": "model-00002-of-00002.safetensors",
|
| 522 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.23.layer_norm2.bias": "model-00002-of-00002.safetensors",
|
| 523 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.23.layer_norm2.weight": "model-00002-of-00002.safetensors",
|
| 524 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.23.mlp.fc1.bias": "model-00002-of-00002.safetensors",
|
| 525 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.23.mlp.fc1.weight": "model-00002-of-00002.safetensors",
|
| 526 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.23.mlp.fc2.bias": "model-00002-of-00002.safetensors",
|
| 527 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.23.mlp.fc2.weight": "model-00002-of-00002.safetensors",
|
| 528 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.23.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
| 529 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.23.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 530 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.23.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
|
| 531 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.23.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
|
| 532 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.23.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
| 533 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.23.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 534 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.23.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
| 535 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.23.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 536 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.24.layer_norm1.bias": "model-00002-of-00002.safetensors",
|
| 537 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.24.layer_norm1.weight": "model-00002-of-00002.safetensors",
|
| 538 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.24.layer_norm2.bias": "model-00002-of-00002.safetensors",
|
| 539 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.24.layer_norm2.weight": "model-00002-of-00002.safetensors",
|
| 540 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.24.mlp.fc1.bias": "model-00002-of-00002.safetensors",
|
| 541 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.24.mlp.fc1.weight": "model-00002-of-00002.safetensors",
|
| 542 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.24.mlp.fc2.bias": "model-00002-of-00002.safetensors",
|
| 543 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.24.mlp.fc2.weight": "model-00002-of-00002.safetensors",
|
| 544 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.24.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
| 545 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.24.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 546 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.24.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
|
| 547 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.24.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
|
| 548 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.24.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
| 549 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.24.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 550 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.24.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
| 551 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.24.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 552 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.25.layer_norm1.bias": "model-00002-of-00002.safetensors",
|
| 553 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.25.layer_norm1.weight": "model-00002-of-00002.safetensors",
|
| 554 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.25.layer_norm2.bias": "model-00002-of-00002.safetensors",
|
| 555 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.25.layer_norm2.weight": "model-00002-of-00002.safetensors",
|
| 556 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.25.mlp.fc1.bias": "model-00002-of-00002.safetensors",
|
| 557 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.25.mlp.fc1.weight": "model-00002-of-00002.safetensors",
|
| 558 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.25.mlp.fc2.bias": "model-00002-of-00002.safetensors",
|
| 559 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.25.mlp.fc2.weight": "model-00002-of-00002.safetensors",
|
| 560 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.25.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
| 561 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.25.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 562 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.25.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
|
| 563 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.25.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
|
| 564 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.25.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
| 565 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.25.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 566 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.25.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
| 567 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.25.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 568 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.26.layer_norm1.bias": "model-00002-of-00002.safetensors",
|
| 569 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.26.layer_norm1.weight": "model-00002-of-00002.safetensors",
|
| 570 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.26.layer_norm2.bias": "model-00002-of-00002.safetensors",
|
| 571 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.26.layer_norm2.weight": "model-00002-of-00002.safetensors",
|
| 572 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.26.mlp.fc1.bias": "model-00002-of-00002.safetensors",
|
| 573 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.26.mlp.fc1.weight": "model-00002-of-00002.safetensors",
|
| 574 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.26.mlp.fc2.bias": "model-00002-of-00002.safetensors",
|
| 575 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.26.mlp.fc2.weight": "model-00002-of-00002.safetensors",
|
| 576 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.26.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
| 577 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.26.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 578 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.26.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
|
| 579 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.26.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
|
| 580 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.26.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
| 581 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.26.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 582 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.26.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
| 583 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.26.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 584 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.3.layer_norm1.bias": "model-00002-of-00002.safetensors",
|
| 585 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.3.layer_norm1.weight": "model-00002-of-00002.safetensors",
|
| 586 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.3.layer_norm2.bias": "model-00002-of-00002.safetensors",
|
| 587 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.3.layer_norm2.weight": "model-00002-of-00002.safetensors",
|
| 588 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.3.mlp.fc1.bias": "model-00002-of-00002.safetensors",
|
| 589 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.3.mlp.fc1.weight": "model-00002-of-00002.safetensors",
|
| 590 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.3.mlp.fc2.bias": "model-00002-of-00002.safetensors",
|
| 591 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.3.mlp.fc2.weight": "model-00002-of-00002.safetensors",
|
| 592 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.3.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
| 593 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.3.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 594 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.3.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
|
| 595 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.3.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
|
| 596 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.3.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
| 597 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.3.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 598 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.3.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
| 599 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.3.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 600 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.4.layer_norm1.bias": "model-00002-of-00002.safetensors",
|
| 601 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.4.layer_norm1.weight": "model-00002-of-00002.safetensors",
|
| 602 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.4.layer_norm2.bias": "model-00002-of-00002.safetensors",
|
| 603 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.4.layer_norm2.weight": "model-00002-of-00002.safetensors",
|
| 604 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.4.mlp.fc1.bias": "model-00002-of-00002.safetensors",
|
| 605 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.4.mlp.fc1.weight": "model-00002-of-00002.safetensors",
|
| 606 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.4.mlp.fc2.bias": "model-00002-of-00002.safetensors",
|
| 607 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.4.mlp.fc2.weight": "model-00002-of-00002.safetensors",
|
| 608 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.4.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
| 609 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.4.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 610 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.4.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
|
| 611 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.4.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
|
| 612 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.4.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
| 613 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.4.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 614 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.4.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
| 615 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.4.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 616 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.5.layer_norm1.bias": "model-00002-of-00002.safetensors",
|
| 617 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.5.layer_norm1.weight": "model-00002-of-00002.safetensors",
|
| 618 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.5.layer_norm2.bias": "model-00002-of-00002.safetensors",
|
| 619 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.5.layer_norm2.weight": "model-00002-of-00002.safetensors",
|
| 620 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.5.mlp.fc1.bias": "model-00002-of-00002.safetensors",
|
| 621 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.5.mlp.fc1.weight": "model-00002-of-00002.safetensors",
|
| 622 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.5.mlp.fc2.bias": "model-00002-of-00002.safetensors",
|
| 623 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.5.mlp.fc2.weight": "model-00002-of-00002.safetensors",
|
| 624 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.5.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
| 625 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.5.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 626 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.5.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
|
| 627 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.5.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
|
| 628 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.5.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
| 629 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.5.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 630 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.5.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
| 631 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.5.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 632 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.6.layer_norm1.bias": "model-00002-of-00002.safetensors",
|
| 633 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.6.layer_norm1.weight": "model-00002-of-00002.safetensors",
|
| 634 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.6.layer_norm2.bias": "model-00002-of-00002.safetensors",
|
| 635 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.6.layer_norm2.weight": "model-00002-of-00002.safetensors",
|
| 636 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.6.mlp.fc1.bias": "model-00002-of-00002.safetensors",
|
| 637 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.6.mlp.fc1.weight": "model-00002-of-00002.safetensors",
|
| 638 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.6.mlp.fc2.bias": "model-00002-of-00002.safetensors",
|
| 639 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.6.mlp.fc2.weight": "model-00002-of-00002.safetensors",
|
| 640 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.6.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
| 641 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.6.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 642 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.6.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
|
| 643 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.6.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
|
| 644 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.6.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
| 645 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.6.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 646 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.6.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
| 647 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.6.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 648 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.7.layer_norm1.bias": "model-00002-of-00002.safetensors",
|
| 649 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.7.layer_norm1.weight": "model-00002-of-00002.safetensors",
|
| 650 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.7.layer_norm2.bias": "model-00002-of-00002.safetensors",
|
| 651 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.7.layer_norm2.weight": "model-00002-of-00002.safetensors",
|
| 652 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.7.mlp.fc1.bias": "model-00002-of-00002.safetensors",
|
| 653 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.7.mlp.fc1.weight": "model-00002-of-00002.safetensors",
|
| 654 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.7.mlp.fc2.bias": "model-00002-of-00002.safetensors",
|
| 655 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.7.mlp.fc2.weight": "model-00002-of-00002.safetensors",
|
| 656 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.7.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
| 657 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.7.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 658 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.7.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
|
| 659 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.7.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
|
| 660 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.7.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
| 661 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.7.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 662 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.7.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
| 663 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.7.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 664 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.8.layer_norm1.bias": "model-00002-of-00002.safetensors",
|
| 665 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.8.layer_norm1.weight": "model-00002-of-00002.safetensors",
|
| 666 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.8.layer_norm2.bias": "model-00002-of-00002.safetensors",
|
| 667 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.8.layer_norm2.weight": "model-00002-of-00002.safetensors",
|
| 668 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.8.mlp.fc1.bias": "model-00002-of-00002.safetensors",
|
| 669 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.8.mlp.fc1.weight": "model-00002-of-00002.safetensors",
|
| 670 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.8.mlp.fc2.bias": "model-00002-of-00002.safetensors",
|
| 671 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.8.mlp.fc2.weight": "model-00002-of-00002.safetensors",
|
| 672 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.8.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
| 673 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.8.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 674 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.8.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
|
| 675 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.8.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
|
| 676 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.8.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
| 677 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.8.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 678 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.8.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
| 679 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.8.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 680 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.9.layer_norm1.bias": "model-00002-of-00002.safetensors",
|
| 681 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.9.layer_norm1.weight": "model-00002-of-00002.safetensors",
|
| 682 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.9.layer_norm2.bias": "model-00002-of-00002.safetensors",
|
| 683 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.9.layer_norm2.weight": "model-00002-of-00002.safetensors",
|
| 684 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.9.mlp.fc1.bias": "model-00002-of-00002.safetensors",
|
| 685 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.9.mlp.fc1.weight": "model-00002-of-00002.safetensors",
|
| 686 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.9.mlp.fc2.bias": "model-00002-of-00002.safetensors",
|
| 687 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.9.mlp.fc2.weight": "model-00002-of-00002.safetensors",
|
| 688 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.9.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
| 689 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.9.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 690 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.9.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
|
| 691 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.9.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
|
| 692 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.9.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
| 693 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.9.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 694 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.9.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
| 695 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.9.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 696 |
+
"visual_tokenizer.backbone.vision_model.head.attention.in_proj_bias": "model-00002-of-00002.safetensors",
|
| 697 |
+
"visual_tokenizer.backbone.vision_model.head.attention.in_proj_weight": "model-00002-of-00002.safetensors",
|
| 698 |
+
"visual_tokenizer.backbone.vision_model.head.attention.out_proj.bias": "model-00002-of-00002.safetensors",
|
| 699 |
+
"visual_tokenizer.backbone.vision_model.head.attention.out_proj.weight": "model-00002-of-00002.safetensors",
|
| 700 |
+
"visual_tokenizer.backbone.vision_model.head.layernorm.bias": "model-00002-of-00002.safetensors",
|
| 701 |
+
"visual_tokenizer.backbone.vision_model.head.layernorm.weight": "model-00002-of-00002.safetensors",
|
| 702 |
+
"visual_tokenizer.backbone.vision_model.head.mlp.fc1.bias": "model-00002-of-00002.safetensors",
|
| 703 |
+
"visual_tokenizer.backbone.vision_model.head.mlp.fc1.weight": "model-00002-of-00002.safetensors",
|
| 704 |
+
"visual_tokenizer.backbone.vision_model.head.mlp.fc2.bias": "model-00002-of-00002.safetensors",
|
| 705 |
+
"visual_tokenizer.backbone.vision_model.head.mlp.fc2.weight": "model-00002-of-00002.safetensors",
|
| 706 |
+
"visual_tokenizer.backbone.vision_model.head.probe": "model-00002-of-00002.safetensors",
|
| 707 |
+
"visual_tokenizer.backbone.vision_model.post_layernorm.bias": "model-00002-of-00002.safetensors",
|
| 708 |
+
"visual_tokenizer.backbone.vision_model.post_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 709 |
+
"visual_tokenizer.head.0.weight": "model-00002-of-00002.safetensors",
|
| 710 |
+
"visual_tokenizer.head.1.bias": "model-00002-of-00002.safetensors",
|
| 711 |
+
"visual_tokenizer.head.1.weight": "model-00002-of-00002.safetensors",
|
| 712 |
+
"vte.weight": "model-00002-of-00002.safetensors"
|
| 713 |
+
}
|
| 714 |
+
}
|
checkpoint-132825/preprocessor_config.json
ADDED
|
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"do_convert_rgb": null,
|
| 3 |
+
"do_normalize": true,
|
| 4 |
+
"do_rescale": true,
|
| 5 |
+
"do_resize": true,
|
| 6 |
+
"image_mean": [
|
| 7 |
+
0.5,
|
| 8 |
+
0.5,
|
| 9 |
+
0.5
|
| 10 |
+
],
|
| 11 |
+
"image_processor_type": "SiglipImageProcessor",
|
| 12 |
+
"image_std": [
|
| 13 |
+
0.5,
|
| 14 |
+
0.5,
|
| 15 |
+
0.5
|
| 16 |
+
],
|
| 17 |
+
"processor_class": "SiglipProcessor",
|
| 18 |
+
"resample": 3,
|
| 19 |
+
"rescale_factor": 0.00392156862745098,
|
| 20 |
+
"size": {
|
| 21 |
+
"height": 384,
|
| 22 |
+
"width": 384
|
| 23 |
+
}
|
| 24 |
+
}
|
checkpoint-132825/rng_state_0.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a209a0c0025f9ce8e2beeba50c1f0828d5c34a2482310fcd0bf5fc24c2c67be2
|
| 3 |
+
size 15024
|
checkpoint-132825/rng_state_1.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a67fb929b8c51f9b1c6ff9f11366e57e55128a1d36df85a9d37a008b49017a75
|
| 3 |
+
size 15024
|
checkpoint-132825/rng_state_2.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1b9ef3b0c0978d0b611f4257c939f1c2c6f07e6227bfea6675532d285b0b64a7
|
| 3 |
+
size 15024
|
checkpoint-132825/rng_state_3.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0183d14c8ed52ee533139532e9bcf7bc34ec297a064845b35741cb501d92675f
|
| 3 |
+
size 15024
|
checkpoint-132825/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2fbbafa1fa3ef6d112e462c047592bd2f48acbbd019b47a65c1fc597f149a467
|
| 3 |
+
size 1064
|
checkpoint-132825/special_tokens_map.json
ADDED
|
@@ -0,0 +1,23 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "<|begin_of_text|>",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": false,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"eos_token": {
|
| 10 |
+
"content": "<|eot_id|>",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": false,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"pad_token": {
|
| 17 |
+
"content": "<|end_of_text|>",
|
| 18 |
+
"lstrip": false,
|
| 19 |
+
"normalized": false,
|
| 20 |
+
"rstrip": false,
|
| 21 |
+
"single_word": false
|
| 22 |
+
}
|
| 23 |
+
}
|
checkpoint-132825/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-132825/tokenizer_config.json
ADDED
|
@@ -0,0 +1,2063 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"added_tokens_decoder": {
|
| 3 |
+
"128000": {
|
| 4 |
+
"content": "<|begin_of_text|>",
|
| 5 |
+
"lstrip": false,
|
| 6 |
+
"normalized": false,
|
| 7 |
+
"rstrip": false,
|
| 8 |
+
"single_word": false,
|
| 9 |
+
"special": true
|
| 10 |
+
},
|
| 11 |
+
"128001": {
|
| 12 |
+
"content": "<|end_of_text|>",
|
| 13 |
+
"lstrip": false,
|
| 14 |
+
"normalized": false,
|
| 15 |
+
"rstrip": false,
|
| 16 |
+
"single_word": false,
|
| 17 |
+
"special": true
|
| 18 |
+
},
|
| 19 |
+
"128002": {
|
| 20 |
+
"content": "<|reserved_special_token_0|>",
|
| 21 |
+
"lstrip": false,
|
| 22 |
+
"normalized": false,
|
| 23 |
+
"rstrip": false,
|
| 24 |
+
"single_word": false,
|
| 25 |
+
"special": true
|
| 26 |
+
},
|
| 27 |
+
"128003": {
|
| 28 |
+
"content": "<|reserved_special_token_1|>",
|
| 29 |
+
"lstrip": false,
|
| 30 |
+
"normalized": false,
|
| 31 |
+
"rstrip": false,
|
| 32 |
+
"single_word": false,
|
| 33 |
+
"special": true
|
| 34 |
+
},
|
| 35 |
+
"128004": {
|
| 36 |
+
"content": "<|finetune_right_pad_id|>",
|
| 37 |
+
"lstrip": false,
|
| 38 |
+
"normalized": false,
|
| 39 |
+
"rstrip": false,
|
| 40 |
+
"single_word": false,
|
| 41 |
+
"special": true
|
| 42 |
+
},
|
| 43 |
+
"128005": {
|
| 44 |
+
"content": "<|reserved_special_token_2|>",
|
| 45 |
+
"lstrip": false,
|
| 46 |
+
"normalized": false,
|
| 47 |
+
"rstrip": false,
|
| 48 |
+
"single_word": false,
|
| 49 |
+
"special": true
|
| 50 |
+
},
|
| 51 |
+
"128006": {
|
| 52 |
+
"content": "<|start_header_id|>",
|
| 53 |
+
"lstrip": false,
|
| 54 |
+
"normalized": false,
|
| 55 |
+
"rstrip": false,
|
| 56 |
+
"single_word": false,
|
| 57 |
+
"special": true
|
| 58 |
+
},
|
| 59 |
+
"128007": {
|
| 60 |
+
"content": "<|end_header_id|>",
|
| 61 |
+
"lstrip": false,
|
| 62 |
+
"normalized": false,
|
| 63 |
+
"rstrip": false,
|
| 64 |
+
"single_word": false,
|
| 65 |
+
"special": true
|
| 66 |
+
},
|
| 67 |
+
"128008": {
|
| 68 |
+
"content": "<|eom_id|>",
|
| 69 |
+
"lstrip": false,
|
| 70 |
+
"normalized": false,
|
| 71 |
+
"rstrip": false,
|
| 72 |
+
"single_word": false,
|
| 73 |
+
"special": true
|
| 74 |
+
},
|
| 75 |
+
"128009": {
|
| 76 |
+
"content": "<|eot_id|>",
|
| 77 |
+
"lstrip": false,
|
| 78 |
+
"normalized": false,
|
| 79 |
+
"rstrip": false,
|
| 80 |
+
"single_word": false,
|
| 81 |
+
"special": true
|
| 82 |
+
},
|
| 83 |
+
"128010": {
|
| 84 |
+
"content": "<|python_tag|>",
|
| 85 |
+
"lstrip": false,
|
| 86 |
+
"normalized": false,
|
| 87 |
+
"rstrip": false,
|
| 88 |
+
"single_word": false,
|
| 89 |
+
"special": true
|
| 90 |
+
},
|
| 91 |
+
"128011": {
|
| 92 |
+
"content": "<|reserved_special_token_3|>",
|
| 93 |
+
"lstrip": false,
|
| 94 |
+
"normalized": false,
|
| 95 |
+
"rstrip": false,
|
| 96 |
+
"single_word": false,
|
| 97 |
+
"special": true
|
| 98 |
+
},
|
| 99 |
+
"128012": {
|
| 100 |
+
"content": "<|reserved_special_token_4|>",
|
| 101 |
+
"lstrip": false,
|
| 102 |
+
"normalized": false,
|
| 103 |
+
"rstrip": false,
|
| 104 |
+
"single_word": false,
|
| 105 |
+
"special": true
|
| 106 |
+
},
|
| 107 |
+
"128013": {
|
| 108 |
+
"content": "<|reserved_special_token_5|>",
|
| 109 |
+
"lstrip": false,
|
| 110 |
+
"normalized": false,
|
| 111 |
+
"rstrip": false,
|
| 112 |
+
"single_word": false,
|
| 113 |
+
"special": true
|
| 114 |
+
},
|
| 115 |
+
"128014": {
|
| 116 |
+
"content": "<|reserved_special_token_6|>",
|
| 117 |
+
"lstrip": false,
|
| 118 |
+
"normalized": false,
|
| 119 |
+
"rstrip": false,
|
| 120 |
+
"single_word": false,
|
| 121 |
+
"special": true
|
| 122 |
+
},
|
| 123 |
+
"128015": {
|
| 124 |
+
"content": "<|reserved_special_token_7|>",
|
| 125 |
+
"lstrip": false,
|
| 126 |
+
"normalized": false,
|
| 127 |
+
"rstrip": false,
|
| 128 |
+
"single_word": false,
|
| 129 |
+
"special": true
|
| 130 |
+
},
|
| 131 |
+
"128016": {
|
| 132 |
+
"content": "<|reserved_special_token_8|>",
|
| 133 |
+
"lstrip": false,
|
| 134 |
+
"normalized": false,
|
| 135 |
+
"rstrip": false,
|
| 136 |
+
"single_word": false,
|
| 137 |
+
"special": true
|
| 138 |
+
},
|
| 139 |
+
"128017": {
|
| 140 |
+
"content": "<|reserved_special_token_9|>",
|
| 141 |
+
"lstrip": false,
|
| 142 |
+
"normalized": false,
|
| 143 |
+
"rstrip": false,
|
| 144 |
+
"single_word": false,
|
| 145 |
+
"special": true
|
| 146 |
+
},
|
| 147 |
+
"128018": {
|
| 148 |
+
"content": "<|reserved_special_token_10|>",
|
| 149 |
+
"lstrip": false,
|
| 150 |
+
"normalized": false,
|
| 151 |
+
"rstrip": false,
|
| 152 |
+
"single_word": false,
|
| 153 |
+
"special": true
|
| 154 |
+
},
|
| 155 |
+
"128019": {
|
| 156 |
+
"content": "<|reserved_special_token_11|>",
|
| 157 |
+
"lstrip": false,
|
| 158 |
+
"normalized": false,
|
| 159 |
+
"rstrip": false,
|
| 160 |
+
"single_word": false,
|
| 161 |
+
"special": true
|
| 162 |
+
},
|
| 163 |
+
"128020": {
|
| 164 |
+
"content": "<|reserved_special_token_12|>",
|
| 165 |
+
"lstrip": false,
|
| 166 |
+
"normalized": false,
|
| 167 |
+
"rstrip": false,
|
| 168 |
+
"single_word": false,
|
| 169 |
+
"special": true
|
| 170 |
+
},
|
| 171 |
+
"128021": {
|
| 172 |
+
"content": "<|reserved_special_token_13|>",
|
| 173 |
+
"lstrip": false,
|
| 174 |
+
"normalized": false,
|
| 175 |
+
"rstrip": false,
|
| 176 |
+
"single_word": false,
|
| 177 |
+
"special": true
|
| 178 |
+
},
|
| 179 |
+
"128022": {
|
| 180 |
+
"content": "<|reserved_special_token_14|>",
|
| 181 |
+
"lstrip": false,
|
| 182 |
+
"normalized": false,
|
| 183 |
+
"rstrip": false,
|
| 184 |
+
"single_word": false,
|
| 185 |
+
"special": true
|
| 186 |
+
},
|
| 187 |
+
"128023": {
|
| 188 |
+
"content": "<|reserved_special_token_15|>",
|
| 189 |
+
"lstrip": false,
|
| 190 |
+
"normalized": false,
|
| 191 |
+
"rstrip": false,
|
| 192 |
+
"single_word": false,
|
| 193 |
+
"special": true
|
| 194 |
+
},
|
| 195 |
+
"128024": {
|
| 196 |
+
"content": "<|reserved_special_token_16|>",
|
| 197 |
+
"lstrip": false,
|
| 198 |
+
"normalized": false,
|
| 199 |
+
"rstrip": false,
|
| 200 |
+
"single_word": false,
|
| 201 |
+
"special": true
|
| 202 |
+
},
|
| 203 |
+
"128025": {
|
| 204 |
+
"content": "<|reserved_special_token_17|>",
|
| 205 |
+
"lstrip": false,
|
| 206 |
+
"normalized": false,
|
| 207 |
+
"rstrip": false,
|
| 208 |
+
"single_word": false,
|
| 209 |
+
"special": true
|
| 210 |
+
},
|
| 211 |
+
"128026": {
|
| 212 |
+
"content": "<|reserved_special_token_18|>",
|
| 213 |
+
"lstrip": false,
|
| 214 |
+
"normalized": false,
|
| 215 |
+
"rstrip": false,
|
| 216 |
+
"single_word": false,
|
| 217 |
+
"special": true
|
| 218 |
+
},
|
| 219 |
+
"128027": {
|
| 220 |
+
"content": "<|reserved_special_token_19|>",
|
| 221 |
+
"lstrip": false,
|
| 222 |
+
"normalized": false,
|
| 223 |
+
"rstrip": false,
|
| 224 |
+
"single_word": false,
|
| 225 |
+
"special": true
|
| 226 |
+
},
|
| 227 |
+
"128028": {
|
| 228 |
+
"content": "<|reserved_special_token_20|>",
|
| 229 |
+
"lstrip": false,
|
| 230 |
+
"normalized": false,
|
| 231 |
+
"rstrip": false,
|
| 232 |
+
"single_word": false,
|
| 233 |
+
"special": true
|
| 234 |
+
},
|
| 235 |
+
"128029": {
|
| 236 |
+
"content": "<|reserved_special_token_21|>",
|
| 237 |
+
"lstrip": false,
|
| 238 |
+
"normalized": false,
|
| 239 |
+
"rstrip": false,
|
| 240 |
+
"single_word": false,
|
| 241 |
+
"special": true
|
| 242 |
+
},
|
| 243 |
+
"128030": {
|
| 244 |
+
"content": "<|reserved_special_token_22|>",
|
| 245 |
+
"lstrip": false,
|
| 246 |
+
"normalized": false,
|
| 247 |
+
"rstrip": false,
|
| 248 |
+
"single_word": false,
|
| 249 |
+
"special": true
|
| 250 |
+
},
|
| 251 |
+
"128031": {
|
| 252 |
+
"content": "<|reserved_special_token_23|>",
|
| 253 |
+
"lstrip": false,
|
| 254 |
+
"normalized": false,
|
| 255 |
+
"rstrip": false,
|
| 256 |
+
"single_word": false,
|
| 257 |
+
"special": true
|
| 258 |
+
},
|
| 259 |
+
"128032": {
|
| 260 |
+
"content": "<|reserved_special_token_24|>",
|
| 261 |
+
"lstrip": false,
|
| 262 |
+
"normalized": false,
|
| 263 |
+
"rstrip": false,
|
| 264 |
+
"single_word": false,
|
| 265 |
+
"special": true
|
| 266 |
+
},
|
| 267 |
+
"128033": {
|
| 268 |
+
"content": "<|reserved_special_token_25|>",
|
| 269 |
+
"lstrip": false,
|
| 270 |
+
"normalized": false,
|
| 271 |
+
"rstrip": false,
|
| 272 |
+
"single_word": false,
|
| 273 |
+
"special": true
|
| 274 |
+
},
|
| 275 |
+
"128034": {
|
| 276 |
+
"content": "<|reserved_special_token_26|>",
|
| 277 |
+
"lstrip": false,
|
| 278 |
+
"normalized": false,
|
| 279 |
+
"rstrip": false,
|
| 280 |
+
"single_word": false,
|
| 281 |
+
"special": true
|
| 282 |
+
},
|
| 283 |
+
"128035": {
|
| 284 |
+
"content": "<|reserved_special_token_27|>",
|
| 285 |
+
"lstrip": false,
|
| 286 |
+
"normalized": false,
|
| 287 |
+
"rstrip": false,
|
| 288 |
+
"single_word": false,
|
| 289 |
+
"special": true
|
| 290 |
+
},
|
| 291 |
+
"128036": {
|
| 292 |
+
"content": "<|reserved_special_token_28|>",
|
| 293 |
+
"lstrip": false,
|
| 294 |
+
"normalized": false,
|
| 295 |
+
"rstrip": false,
|
| 296 |
+
"single_word": false,
|
| 297 |
+
"special": true
|
| 298 |
+
},
|
| 299 |
+
"128037": {
|
| 300 |
+
"content": "<|reserved_special_token_29|>",
|
| 301 |
+
"lstrip": false,
|
| 302 |
+
"normalized": false,
|
| 303 |
+
"rstrip": false,
|
| 304 |
+
"single_word": false,
|
| 305 |
+
"special": true
|
| 306 |
+
},
|
| 307 |
+
"128038": {
|
| 308 |
+
"content": "<|reserved_special_token_30|>",
|
| 309 |
+
"lstrip": false,
|
| 310 |
+
"normalized": false,
|
| 311 |
+
"rstrip": false,
|
| 312 |
+
"single_word": false,
|
| 313 |
+
"special": true
|
| 314 |
+
},
|
| 315 |
+
"128039": {
|
| 316 |
+
"content": "<|reserved_special_token_31|>",
|
| 317 |
+
"lstrip": false,
|
| 318 |
+
"normalized": false,
|
| 319 |
+
"rstrip": false,
|
| 320 |
+
"single_word": false,
|
| 321 |
+
"special": true
|
| 322 |
+
},
|
| 323 |
+
"128040": {
|
| 324 |
+
"content": "<|reserved_special_token_32|>",
|
| 325 |
+
"lstrip": false,
|
| 326 |
+
"normalized": false,
|
| 327 |
+
"rstrip": false,
|
| 328 |
+
"single_word": false,
|
| 329 |
+
"special": true
|
| 330 |
+
},
|
| 331 |
+
"128041": {
|
| 332 |
+
"content": "<|reserved_special_token_33|>",
|
| 333 |
+
"lstrip": false,
|
| 334 |
+
"normalized": false,
|
| 335 |
+
"rstrip": false,
|
| 336 |
+
"single_word": false,
|
| 337 |
+
"special": true
|
| 338 |
+
},
|
| 339 |
+
"128042": {
|
| 340 |
+
"content": "<|reserved_special_token_34|>",
|
| 341 |
+
"lstrip": false,
|
| 342 |
+
"normalized": false,
|
| 343 |
+
"rstrip": false,
|
| 344 |
+
"single_word": false,
|
| 345 |
+
"special": true
|
| 346 |
+
},
|
| 347 |
+
"128043": {
|
| 348 |
+
"content": "<|reserved_special_token_35|>",
|
| 349 |
+
"lstrip": false,
|
| 350 |
+
"normalized": false,
|
| 351 |
+
"rstrip": false,
|
| 352 |
+
"single_word": false,
|
| 353 |
+
"special": true
|
| 354 |
+
},
|
| 355 |
+
"128044": {
|
| 356 |
+
"content": "<|reserved_special_token_36|>",
|
| 357 |
+
"lstrip": false,
|
| 358 |
+
"normalized": false,
|
| 359 |
+
"rstrip": false,
|
| 360 |
+
"single_word": false,
|
| 361 |
+
"special": true
|
| 362 |
+
},
|
| 363 |
+
"128045": {
|
| 364 |
+
"content": "<|reserved_special_token_37|>",
|
| 365 |
+
"lstrip": false,
|
| 366 |
+
"normalized": false,
|
| 367 |
+
"rstrip": false,
|
| 368 |
+
"single_word": false,
|
| 369 |
+
"special": true
|
| 370 |
+
},
|
| 371 |
+
"128046": {
|
| 372 |
+
"content": "<|reserved_special_token_38|>",
|
| 373 |
+
"lstrip": false,
|
| 374 |
+
"normalized": false,
|
| 375 |
+
"rstrip": false,
|
| 376 |
+
"single_word": false,
|
| 377 |
+
"special": true
|
| 378 |
+
},
|
| 379 |
+
"128047": {
|
| 380 |
+
"content": "<|reserved_special_token_39|>",
|
| 381 |
+
"lstrip": false,
|
| 382 |
+
"normalized": false,
|
| 383 |
+
"rstrip": false,
|
| 384 |
+
"single_word": false,
|
| 385 |
+
"special": true
|
| 386 |
+
},
|
| 387 |
+
"128048": {
|
| 388 |
+
"content": "<|reserved_special_token_40|>",
|
| 389 |
+
"lstrip": false,
|
| 390 |
+
"normalized": false,
|
| 391 |
+
"rstrip": false,
|
| 392 |
+
"single_word": false,
|
| 393 |
+
"special": true
|
| 394 |
+
},
|
| 395 |
+
"128049": {
|
| 396 |
+
"content": "<|reserved_special_token_41|>",
|
| 397 |
+
"lstrip": false,
|
| 398 |
+
"normalized": false,
|
| 399 |
+
"rstrip": false,
|
| 400 |
+
"single_word": false,
|
| 401 |
+
"special": true
|
| 402 |
+
},
|
| 403 |
+
"128050": {
|
| 404 |
+
"content": "<|reserved_special_token_42|>",
|
| 405 |
+
"lstrip": false,
|
| 406 |
+
"normalized": false,
|
| 407 |
+
"rstrip": false,
|
| 408 |
+
"single_word": false,
|
| 409 |
+
"special": true
|
| 410 |
+
},
|
| 411 |
+
"128051": {
|
| 412 |
+
"content": "<|reserved_special_token_43|>",
|
| 413 |
+
"lstrip": false,
|
| 414 |
+
"normalized": false,
|
| 415 |
+
"rstrip": false,
|
| 416 |
+
"single_word": false,
|
| 417 |
+
"special": true
|
| 418 |
+
},
|
| 419 |
+
"128052": {
|
| 420 |
+
"content": "<|reserved_special_token_44|>",
|
| 421 |
+
"lstrip": false,
|
| 422 |
+
"normalized": false,
|
| 423 |
+
"rstrip": false,
|
| 424 |
+
"single_word": false,
|
| 425 |
+
"special": true
|
| 426 |
+
},
|
| 427 |
+
"128053": {
|
| 428 |
+
"content": "<|reserved_special_token_45|>",
|
| 429 |
+
"lstrip": false,
|
| 430 |
+
"normalized": false,
|
| 431 |
+
"rstrip": false,
|
| 432 |
+
"single_word": false,
|
| 433 |
+
"special": true
|
| 434 |
+
},
|
| 435 |
+
"128054": {
|
| 436 |
+
"content": "<|reserved_special_token_46|>",
|
| 437 |
+
"lstrip": false,
|
| 438 |
+
"normalized": false,
|
| 439 |
+
"rstrip": false,
|
| 440 |
+
"single_word": false,
|
| 441 |
+
"special": true
|
| 442 |
+
},
|
| 443 |
+
"128055": {
|
| 444 |
+
"content": "<|reserved_special_token_47|>",
|
| 445 |
+
"lstrip": false,
|
| 446 |
+
"normalized": false,
|
| 447 |
+
"rstrip": false,
|
| 448 |
+
"single_word": false,
|
| 449 |
+
"special": true
|
| 450 |
+
},
|
| 451 |
+
"128056": {
|
| 452 |
+
"content": "<|reserved_special_token_48|>",
|
| 453 |
+
"lstrip": false,
|
| 454 |
+
"normalized": false,
|
| 455 |
+
"rstrip": false,
|
| 456 |
+
"single_word": false,
|
| 457 |
+
"special": true
|
| 458 |
+
},
|
| 459 |
+
"128057": {
|
| 460 |
+
"content": "<|reserved_special_token_49|>",
|
| 461 |
+
"lstrip": false,
|
| 462 |
+
"normalized": false,
|
| 463 |
+
"rstrip": false,
|
| 464 |
+
"single_word": false,
|
| 465 |
+
"special": true
|
| 466 |
+
},
|
| 467 |
+
"128058": {
|
| 468 |
+
"content": "<|reserved_special_token_50|>",
|
| 469 |
+
"lstrip": false,
|
| 470 |
+
"normalized": false,
|
| 471 |
+
"rstrip": false,
|
| 472 |
+
"single_word": false,
|
| 473 |
+
"special": true
|
| 474 |
+
},
|
| 475 |
+
"128059": {
|
| 476 |
+
"content": "<|reserved_special_token_51|>",
|
| 477 |
+
"lstrip": false,
|
| 478 |
+
"normalized": false,
|
| 479 |
+
"rstrip": false,
|
| 480 |
+
"single_word": false,
|
| 481 |
+
"special": true
|
| 482 |
+
},
|
| 483 |
+
"128060": {
|
| 484 |
+
"content": "<|reserved_special_token_52|>",
|
| 485 |
+
"lstrip": false,
|
| 486 |
+
"normalized": false,
|
| 487 |
+
"rstrip": false,
|
| 488 |
+
"single_word": false,
|
| 489 |
+
"special": true
|
| 490 |
+
},
|
| 491 |
+
"128061": {
|
| 492 |
+
"content": "<|reserved_special_token_53|>",
|
| 493 |
+
"lstrip": false,
|
| 494 |
+
"normalized": false,
|
| 495 |
+
"rstrip": false,
|
| 496 |
+
"single_word": false,
|
| 497 |
+
"special": true
|
| 498 |
+
},
|
| 499 |
+
"128062": {
|
| 500 |
+
"content": "<|reserved_special_token_54|>",
|
| 501 |
+
"lstrip": false,
|
| 502 |
+
"normalized": false,
|
| 503 |
+
"rstrip": false,
|
| 504 |
+
"single_word": false,
|
| 505 |
+
"special": true
|
| 506 |
+
},
|
| 507 |
+
"128063": {
|
| 508 |
+
"content": "<|reserved_special_token_55|>",
|
| 509 |
+
"lstrip": false,
|
| 510 |
+
"normalized": false,
|
| 511 |
+
"rstrip": false,
|
| 512 |
+
"single_word": false,
|
| 513 |
+
"special": true
|
| 514 |
+
},
|
| 515 |
+
"128064": {
|
| 516 |
+
"content": "<|reserved_special_token_56|>",
|
| 517 |
+
"lstrip": false,
|
| 518 |
+
"normalized": false,
|
| 519 |
+
"rstrip": false,
|
| 520 |
+
"single_word": false,
|
| 521 |
+
"special": true
|
| 522 |
+
},
|
| 523 |
+
"128065": {
|
| 524 |
+
"content": "<|reserved_special_token_57|>",
|
| 525 |
+
"lstrip": false,
|
| 526 |
+
"normalized": false,
|
| 527 |
+
"rstrip": false,
|
| 528 |
+
"single_word": false,
|
| 529 |
+
"special": true
|
| 530 |
+
},
|
| 531 |
+
"128066": {
|
| 532 |
+
"content": "<|reserved_special_token_58|>",
|
| 533 |
+
"lstrip": false,
|
| 534 |
+
"normalized": false,
|
| 535 |
+
"rstrip": false,
|
| 536 |
+
"single_word": false,
|
| 537 |
+
"special": true
|
| 538 |
+
},
|
| 539 |
+
"128067": {
|
| 540 |
+
"content": "<|reserved_special_token_59|>",
|
| 541 |
+
"lstrip": false,
|
| 542 |
+
"normalized": false,
|
| 543 |
+
"rstrip": false,
|
| 544 |
+
"single_word": false,
|
| 545 |
+
"special": true
|
| 546 |
+
},
|
| 547 |
+
"128068": {
|
| 548 |
+
"content": "<|reserved_special_token_60|>",
|
| 549 |
+
"lstrip": false,
|
| 550 |
+
"normalized": false,
|
| 551 |
+
"rstrip": false,
|
| 552 |
+
"single_word": false,
|
| 553 |
+
"special": true
|
| 554 |
+
},
|
| 555 |
+
"128069": {
|
| 556 |
+
"content": "<|reserved_special_token_61|>",
|
| 557 |
+
"lstrip": false,
|
| 558 |
+
"normalized": false,
|
| 559 |
+
"rstrip": false,
|
| 560 |
+
"single_word": false,
|
| 561 |
+
"special": true
|
| 562 |
+
},
|
| 563 |
+
"128070": {
|
| 564 |
+
"content": "<|reserved_special_token_62|>",
|
| 565 |
+
"lstrip": false,
|
| 566 |
+
"normalized": false,
|
| 567 |
+
"rstrip": false,
|
| 568 |
+
"single_word": false,
|
| 569 |
+
"special": true
|
| 570 |
+
},
|
| 571 |
+
"128071": {
|
| 572 |
+
"content": "<|reserved_special_token_63|>",
|
| 573 |
+
"lstrip": false,
|
| 574 |
+
"normalized": false,
|
| 575 |
+
"rstrip": false,
|
| 576 |
+
"single_word": false,
|
| 577 |
+
"special": true
|
| 578 |
+
},
|
| 579 |
+
"128072": {
|
| 580 |
+
"content": "<|reserved_special_token_64|>",
|
| 581 |
+
"lstrip": false,
|
| 582 |
+
"normalized": false,
|
| 583 |
+
"rstrip": false,
|
| 584 |
+
"single_word": false,
|
| 585 |
+
"special": true
|
| 586 |
+
},
|
| 587 |
+
"128073": {
|
| 588 |
+
"content": "<|reserved_special_token_65|>",
|
| 589 |
+
"lstrip": false,
|
| 590 |
+
"normalized": false,
|
| 591 |
+
"rstrip": false,
|
| 592 |
+
"single_word": false,
|
| 593 |
+
"special": true
|
| 594 |
+
},
|
| 595 |
+
"128074": {
|
| 596 |
+
"content": "<|reserved_special_token_66|>",
|
| 597 |
+
"lstrip": false,
|
| 598 |
+
"normalized": false,
|
| 599 |
+
"rstrip": false,
|
| 600 |
+
"single_word": false,
|
| 601 |
+
"special": true
|
| 602 |
+
},
|
| 603 |
+
"128075": {
|
| 604 |
+
"content": "<|reserved_special_token_67|>",
|
| 605 |
+
"lstrip": false,
|
| 606 |
+
"normalized": false,
|
| 607 |
+
"rstrip": false,
|
| 608 |
+
"single_word": false,
|
| 609 |
+
"special": true
|
| 610 |
+
},
|
| 611 |
+
"128076": {
|
| 612 |
+
"content": "<|reserved_special_token_68|>",
|
| 613 |
+
"lstrip": false,
|
| 614 |
+
"normalized": false,
|
| 615 |
+
"rstrip": false,
|
| 616 |
+
"single_word": false,
|
| 617 |
+
"special": true
|
| 618 |
+
},
|
| 619 |
+
"128077": {
|
| 620 |
+
"content": "<|reserved_special_token_69|>",
|
| 621 |
+
"lstrip": false,
|
| 622 |
+
"normalized": false,
|
| 623 |
+
"rstrip": false,
|
| 624 |
+
"single_word": false,
|
| 625 |
+
"special": true
|
| 626 |
+
},
|
| 627 |
+
"128078": {
|
| 628 |
+
"content": "<|reserved_special_token_70|>",
|
| 629 |
+
"lstrip": false,
|
| 630 |
+
"normalized": false,
|
| 631 |
+
"rstrip": false,
|
| 632 |
+
"single_word": false,
|
| 633 |
+
"special": true
|
| 634 |
+
},
|
| 635 |
+
"128079": {
|
| 636 |
+
"content": "<|reserved_special_token_71|>",
|
| 637 |
+
"lstrip": false,
|
| 638 |
+
"normalized": false,
|
| 639 |
+
"rstrip": false,
|
| 640 |
+
"single_word": false,
|
| 641 |
+
"special": true
|
| 642 |
+
},
|
| 643 |
+
"128080": {
|
| 644 |
+
"content": "<|reserved_special_token_72|>",
|
| 645 |
+
"lstrip": false,
|
| 646 |
+
"normalized": false,
|
| 647 |
+
"rstrip": false,
|
| 648 |
+
"single_word": false,
|
| 649 |
+
"special": true
|
| 650 |
+
},
|
| 651 |
+
"128081": {
|
| 652 |
+
"content": "<|reserved_special_token_73|>",
|
| 653 |
+
"lstrip": false,
|
| 654 |
+
"normalized": false,
|
| 655 |
+
"rstrip": false,
|
| 656 |
+
"single_word": false,
|
| 657 |
+
"special": true
|
| 658 |
+
},
|
| 659 |
+
"128082": {
|
| 660 |
+
"content": "<|reserved_special_token_74|>",
|
| 661 |
+
"lstrip": false,
|
| 662 |
+
"normalized": false,
|
| 663 |
+
"rstrip": false,
|
| 664 |
+
"single_word": false,
|
| 665 |
+
"special": true
|
| 666 |
+
},
|
| 667 |
+
"128083": {
|
| 668 |
+
"content": "<|reserved_special_token_75|>",
|
| 669 |
+
"lstrip": false,
|
| 670 |
+
"normalized": false,
|
| 671 |
+
"rstrip": false,
|
| 672 |
+
"single_word": false,
|
| 673 |
+
"special": true
|
| 674 |
+
},
|
| 675 |
+
"128084": {
|
| 676 |
+
"content": "<|reserved_special_token_76|>",
|
| 677 |
+
"lstrip": false,
|
| 678 |
+
"normalized": false,
|
| 679 |
+
"rstrip": false,
|
| 680 |
+
"single_word": false,
|
| 681 |
+
"special": true
|
| 682 |
+
},
|
| 683 |
+
"128085": {
|
| 684 |
+
"content": "<|reserved_special_token_77|>",
|
| 685 |
+
"lstrip": false,
|
| 686 |
+
"normalized": false,
|
| 687 |
+
"rstrip": false,
|
| 688 |
+
"single_word": false,
|
| 689 |
+
"special": true
|
| 690 |
+
},
|
| 691 |
+
"128086": {
|
| 692 |
+
"content": "<|reserved_special_token_78|>",
|
| 693 |
+
"lstrip": false,
|
| 694 |
+
"normalized": false,
|
| 695 |
+
"rstrip": false,
|
| 696 |
+
"single_word": false,
|
| 697 |
+
"special": true
|
| 698 |
+
},
|
| 699 |
+
"128087": {
|
| 700 |
+
"content": "<|reserved_special_token_79|>",
|
| 701 |
+
"lstrip": false,
|
| 702 |
+
"normalized": false,
|
| 703 |
+
"rstrip": false,
|
| 704 |
+
"single_word": false,
|
| 705 |
+
"special": true
|
| 706 |
+
},
|
| 707 |
+
"128088": {
|
| 708 |
+
"content": "<|reserved_special_token_80|>",
|
| 709 |
+
"lstrip": false,
|
| 710 |
+
"normalized": false,
|
| 711 |
+
"rstrip": false,
|
| 712 |
+
"single_word": false,
|
| 713 |
+
"special": true
|
| 714 |
+
},
|
| 715 |
+
"128089": {
|
| 716 |
+
"content": "<|reserved_special_token_81|>",
|
| 717 |
+
"lstrip": false,
|
| 718 |
+
"normalized": false,
|
| 719 |
+
"rstrip": false,
|
| 720 |
+
"single_word": false,
|
| 721 |
+
"special": true
|
| 722 |
+
},
|
| 723 |
+
"128090": {
|
| 724 |
+
"content": "<|reserved_special_token_82|>",
|
| 725 |
+
"lstrip": false,
|
| 726 |
+
"normalized": false,
|
| 727 |
+
"rstrip": false,
|
| 728 |
+
"single_word": false,
|
| 729 |
+
"special": true
|
| 730 |
+
},
|
| 731 |
+
"128091": {
|
| 732 |
+
"content": "<|reserved_special_token_83|>",
|
| 733 |
+
"lstrip": false,
|
| 734 |
+
"normalized": false,
|
| 735 |
+
"rstrip": false,
|
| 736 |
+
"single_word": false,
|
| 737 |
+
"special": true
|
| 738 |
+
},
|
| 739 |
+
"128092": {
|
| 740 |
+
"content": "<|reserved_special_token_84|>",
|
| 741 |
+
"lstrip": false,
|
| 742 |
+
"normalized": false,
|
| 743 |
+
"rstrip": false,
|
| 744 |
+
"single_word": false,
|
| 745 |
+
"special": true
|
| 746 |
+
},
|
| 747 |
+
"128093": {
|
| 748 |
+
"content": "<|reserved_special_token_85|>",
|
| 749 |
+
"lstrip": false,
|
| 750 |
+
"normalized": false,
|
| 751 |
+
"rstrip": false,
|
| 752 |
+
"single_word": false,
|
| 753 |
+
"special": true
|
| 754 |
+
},
|
| 755 |
+
"128094": {
|
| 756 |
+
"content": "<|reserved_special_token_86|>",
|
| 757 |
+
"lstrip": false,
|
| 758 |
+
"normalized": false,
|
| 759 |
+
"rstrip": false,
|
| 760 |
+
"single_word": false,
|
| 761 |
+
"special": true
|
| 762 |
+
},
|
| 763 |
+
"128095": {
|
| 764 |
+
"content": "<|reserved_special_token_87|>",
|
| 765 |
+
"lstrip": false,
|
| 766 |
+
"normalized": false,
|
| 767 |
+
"rstrip": false,
|
| 768 |
+
"single_word": false,
|
| 769 |
+
"special": true
|
| 770 |
+
},
|
| 771 |
+
"128096": {
|
| 772 |
+
"content": "<|reserved_special_token_88|>",
|
| 773 |
+
"lstrip": false,
|
| 774 |
+
"normalized": false,
|
| 775 |
+
"rstrip": false,
|
| 776 |
+
"single_word": false,
|
| 777 |
+
"special": true
|
| 778 |
+
},
|
| 779 |
+
"128097": {
|
| 780 |
+
"content": "<|reserved_special_token_89|>",
|
| 781 |
+
"lstrip": false,
|
| 782 |
+
"normalized": false,
|
| 783 |
+
"rstrip": false,
|
| 784 |
+
"single_word": false,
|
| 785 |
+
"special": true
|
| 786 |
+
},
|
| 787 |
+
"128098": {
|
| 788 |
+
"content": "<|reserved_special_token_90|>",
|
| 789 |
+
"lstrip": false,
|
| 790 |
+
"normalized": false,
|
| 791 |
+
"rstrip": false,
|
| 792 |
+
"single_word": false,
|
| 793 |
+
"special": true
|
| 794 |
+
},
|
| 795 |
+
"128099": {
|
| 796 |
+
"content": "<|reserved_special_token_91|>",
|
| 797 |
+
"lstrip": false,
|
| 798 |
+
"normalized": false,
|
| 799 |
+
"rstrip": false,
|
| 800 |
+
"single_word": false,
|
| 801 |
+
"special": true
|
| 802 |
+
},
|
| 803 |
+
"128100": {
|
| 804 |
+
"content": "<|reserved_special_token_92|>",
|
| 805 |
+
"lstrip": false,
|
| 806 |
+
"normalized": false,
|
| 807 |
+
"rstrip": false,
|
| 808 |
+
"single_word": false,
|
| 809 |
+
"special": true
|
| 810 |
+
},
|
| 811 |
+
"128101": {
|
| 812 |
+
"content": "<|reserved_special_token_93|>",
|
| 813 |
+
"lstrip": false,
|
| 814 |
+
"normalized": false,
|
| 815 |
+
"rstrip": false,
|
| 816 |
+
"single_word": false,
|
| 817 |
+
"special": true
|
| 818 |
+
},
|
| 819 |
+
"128102": {
|
| 820 |
+
"content": "<|reserved_special_token_94|>",
|
| 821 |
+
"lstrip": false,
|
| 822 |
+
"normalized": false,
|
| 823 |
+
"rstrip": false,
|
| 824 |
+
"single_word": false,
|
| 825 |
+
"special": true
|
| 826 |
+
},
|
| 827 |
+
"128103": {
|
| 828 |
+
"content": "<|reserved_special_token_95|>",
|
| 829 |
+
"lstrip": false,
|
| 830 |
+
"normalized": false,
|
| 831 |
+
"rstrip": false,
|
| 832 |
+
"single_word": false,
|
| 833 |
+
"special": true
|
| 834 |
+
},
|
| 835 |
+
"128104": {
|
| 836 |
+
"content": "<|reserved_special_token_96|>",
|
| 837 |
+
"lstrip": false,
|
| 838 |
+
"normalized": false,
|
| 839 |
+
"rstrip": false,
|
| 840 |
+
"single_word": false,
|
| 841 |
+
"special": true
|
| 842 |
+
},
|
| 843 |
+
"128105": {
|
| 844 |
+
"content": "<|reserved_special_token_97|>",
|
| 845 |
+
"lstrip": false,
|
| 846 |
+
"normalized": false,
|
| 847 |
+
"rstrip": false,
|
| 848 |
+
"single_word": false,
|
| 849 |
+
"special": true
|
| 850 |
+
},
|
| 851 |
+
"128106": {
|
| 852 |
+
"content": "<|reserved_special_token_98|>",
|
| 853 |
+
"lstrip": false,
|
| 854 |
+
"normalized": false,
|
| 855 |
+
"rstrip": false,
|
| 856 |
+
"single_word": false,
|
| 857 |
+
"special": true
|
| 858 |
+
},
|
| 859 |
+
"128107": {
|
| 860 |
+
"content": "<|reserved_special_token_99|>",
|
| 861 |
+
"lstrip": false,
|
| 862 |
+
"normalized": false,
|
| 863 |
+
"rstrip": false,
|
| 864 |
+
"single_word": false,
|
| 865 |
+
"special": true
|
| 866 |
+
},
|
| 867 |
+
"128108": {
|
| 868 |
+
"content": "<|reserved_special_token_100|>",
|
| 869 |
+
"lstrip": false,
|
| 870 |
+
"normalized": false,
|
| 871 |
+
"rstrip": false,
|
| 872 |
+
"single_word": false,
|
| 873 |
+
"special": true
|
| 874 |
+
},
|
| 875 |
+
"128109": {
|
| 876 |
+
"content": "<|reserved_special_token_101|>",
|
| 877 |
+
"lstrip": false,
|
| 878 |
+
"normalized": false,
|
| 879 |
+
"rstrip": false,
|
| 880 |
+
"single_word": false,
|
| 881 |
+
"special": true
|
| 882 |
+
},
|
| 883 |
+
"128110": {
|
| 884 |
+
"content": "<|reserved_special_token_102|>",
|
| 885 |
+
"lstrip": false,
|
| 886 |
+
"normalized": false,
|
| 887 |
+
"rstrip": false,
|
| 888 |
+
"single_word": false,
|
| 889 |
+
"special": true
|
| 890 |
+
},
|
| 891 |
+
"128111": {
|
| 892 |
+
"content": "<|reserved_special_token_103|>",
|
| 893 |
+
"lstrip": false,
|
| 894 |
+
"normalized": false,
|
| 895 |
+
"rstrip": false,
|
| 896 |
+
"single_word": false,
|
| 897 |
+
"special": true
|
| 898 |
+
},
|
| 899 |
+
"128112": {
|
| 900 |
+
"content": "<|reserved_special_token_104|>",
|
| 901 |
+
"lstrip": false,
|
| 902 |
+
"normalized": false,
|
| 903 |
+
"rstrip": false,
|
| 904 |
+
"single_word": false,
|
| 905 |
+
"special": true
|
| 906 |
+
},
|
| 907 |
+
"128113": {
|
| 908 |
+
"content": "<|reserved_special_token_105|>",
|
| 909 |
+
"lstrip": false,
|
| 910 |
+
"normalized": false,
|
| 911 |
+
"rstrip": false,
|
| 912 |
+
"single_word": false,
|
| 913 |
+
"special": true
|
| 914 |
+
},
|
| 915 |
+
"128114": {
|
| 916 |
+
"content": "<|reserved_special_token_106|>",
|
| 917 |
+
"lstrip": false,
|
| 918 |
+
"normalized": false,
|
| 919 |
+
"rstrip": false,
|
| 920 |
+
"single_word": false,
|
| 921 |
+
"special": true
|
| 922 |
+
},
|
| 923 |
+
"128115": {
|
| 924 |
+
"content": "<|reserved_special_token_107|>",
|
| 925 |
+
"lstrip": false,
|
| 926 |
+
"normalized": false,
|
| 927 |
+
"rstrip": false,
|
| 928 |
+
"single_word": false,
|
| 929 |
+
"special": true
|
| 930 |
+
},
|
| 931 |
+
"128116": {
|
| 932 |
+
"content": "<|reserved_special_token_108|>",
|
| 933 |
+
"lstrip": false,
|
| 934 |
+
"normalized": false,
|
| 935 |
+
"rstrip": false,
|
| 936 |
+
"single_word": false,
|
| 937 |
+
"special": true
|
| 938 |
+
},
|
| 939 |
+
"128117": {
|
| 940 |
+
"content": "<|reserved_special_token_109|>",
|
| 941 |
+
"lstrip": false,
|
| 942 |
+
"normalized": false,
|
| 943 |
+
"rstrip": false,
|
| 944 |
+
"single_word": false,
|
| 945 |
+
"special": true
|
| 946 |
+
},
|
| 947 |
+
"128118": {
|
| 948 |
+
"content": "<|reserved_special_token_110|>",
|
| 949 |
+
"lstrip": false,
|
| 950 |
+
"normalized": false,
|
| 951 |
+
"rstrip": false,
|
| 952 |
+
"single_word": false,
|
| 953 |
+
"special": true
|
| 954 |
+
},
|
| 955 |
+
"128119": {
|
| 956 |
+
"content": "<|reserved_special_token_111|>",
|
| 957 |
+
"lstrip": false,
|
| 958 |
+
"normalized": false,
|
| 959 |
+
"rstrip": false,
|
| 960 |
+
"single_word": false,
|
| 961 |
+
"special": true
|
| 962 |
+
},
|
| 963 |
+
"128120": {
|
| 964 |
+
"content": "<|reserved_special_token_112|>",
|
| 965 |
+
"lstrip": false,
|
| 966 |
+
"normalized": false,
|
| 967 |
+
"rstrip": false,
|
| 968 |
+
"single_word": false,
|
| 969 |
+
"special": true
|
| 970 |
+
},
|
| 971 |
+
"128121": {
|
| 972 |
+
"content": "<|reserved_special_token_113|>",
|
| 973 |
+
"lstrip": false,
|
| 974 |
+
"normalized": false,
|
| 975 |
+
"rstrip": false,
|
| 976 |
+
"single_word": false,
|
| 977 |
+
"special": true
|
| 978 |
+
},
|
| 979 |
+
"128122": {
|
| 980 |
+
"content": "<|reserved_special_token_114|>",
|
| 981 |
+
"lstrip": false,
|
| 982 |
+
"normalized": false,
|
| 983 |
+
"rstrip": false,
|
| 984 |
+
"single_word": false,
|
| 985 |
+
"special": true
|
| 986 |
+
},
|
| 987 |
+
"128123": {
|
| 988 |
+
"content": "<|reserved_special_token_115|>",
|
| 989 |
+
"lstrip": false,
|
| 990 |
+
"normalized": false,
|
| 991 |
+
"rstrip": false,
|
| 992 |
+
"single_word": false,
|
| 993 |
+
"special": true
|
| 994 |
+
},
|
| 995 |
+
"128124": {
|
| 996 |
+
"content": "<|reserved_special_token_116|>",
|
| 997 |
+
"lstrip": false,
|
| 998 |
+
"normalized": false,
|
| 999 |
+
"rstrip": false,
|
| 1000 |
+
"single_word": false,
|
| 1001 |
+
"special": true
|
| 1002 |
+
},
|
| 1003 |
+
"128125": {
|
| 1004 |
+
"content": "<|reserved_special_token_117|>",
|
| 1005 |
+
"lstrip": false,
|
| 1006 |
+
"normalized": false,
|
| 1007 |
+
"rstrip": false,
|
| 1008 |
+
"single_word": false,
|
| 1009 |
+
"special": true
|
| 1010 |
+
},
|
| 1011 |
+
"128126": {
|
| 1012 |
+
"content": "<|reserved_special_token_118|>",
|
| 1013 |
+
"lstrip": false,
|
| 1014 |
+
"normalized": false,
|
| 1015 |
+
"rstrip": false,
|
| 1016 |
+
"single_word": false,
|
| 1017 |
+
"special": true
|
| 1018 |
+
},
|
| 1019 |
+
"128127": {
|
| 1020 |
+
"content": "<|reserved_special_token_119|>",
|
| 1021 |
+
"lstrip": false,
|
| 1022 |
+
"normalized": false,
|
| 1023 |
+
"rstrip": false,
|
| 1024 |
+
"single_word": false,
|
| 1025 |
+
"special": true
|
| 1026 |
+
},
|
| 1027 |
+
"128128": {
|
| 1028 |
+
"content": "<|reserved_special_token_120|>",
|
| 1029 |
+
"lstrip": false,
|
| 1030 |
+
"normalized": false,
|
| 1031 |
+
"rstrip": false,
|
| 1032 |
+
"single_word": false,
|
| 1033 |
+
"special": true
|
| 1034 |
+
},
|
| 1035 |
+
"128129": {
|
| 1036 |
+
"content": "<|reserved_special_token_121|>",
|
| 1037 |
+
"lstrip": false,
|
| 1038 |
+
"normalized": false,
|
| 1039 |
+
"rstrip": false,
|
| 1040 |
+
"single_word": false,
|
| 1041 |
+
"special": true
|
| 1042 |
+
},
|
| 1043 |
+
"128130": {
|
| 1044 |
+
"content": "<|reserved_special_token_122|>",
|
| 1045 |
+
"lstrip": false,
|
| 1046 |
+
"normalized": false,
|
| 1047 |
+
"rstrip": false,
|
| 1048 |
+
"single_word": false,
|
| 1049 |
+
"special": true
|
| 1050 |
+
},
|
| 1051 |
+
"128131": {
|
| 1052 |
+
"content": "<|reserved_special_token_123|>",
|
| 1053 |
+
"lstrip": false,
|
| 1054 |
+
"normalized": false,
|
| 1055 |
+
"rstrip": false,
|
| 1056 |
+
"single_word": false,
|
| 1057 |
+
"special": true
|
| 1058 |
+
},
|
| 1059 |
+
"128132": {
|
| 1060 |
+
"content": "<|reserved_special_token_124|>",
|
| 1061 |
+
"lstrip": false,
|
| 1062 |
+
"normalized": false,
|
| 1063 |
+
"rstrip": false,
|
| 1064 |
+
"single_word": false,
|
| 1065 |
+
"special": true
|
| 1066 |
+
},
|
| 1067 |
+
"128133": {
|
| 1068 |
+
"content": "<|reserved_special_token_125|>",
|
| 1069 |
+
"lstrip": false,
|
| 1070 |
+
"normalized": false,
|
| 1071 |
+
"rstrip": false,
|
| 1072 |
+
"single_word": false,
|
| 1073 |
+
"special": true
|
| 1074 |
+
},
|
| 1075 |
+
"128134": {
|
| 1076 |
+
"content": "<|reserved_special_token_126|>",
|
| 1077 |
+
"lstrip": false,
|
| 1078 |
+
"normalized": false,
|
| 1079 |
+
"rstrip": false,
|
| 1080 |
+
"single_word": false,
|
| 1081 |
+
"special": true
|
| 1082 |
+
},
|
| 1083 |
+
"128135": {
|
| 1084 |
+
"content": "<|reserved_special_token_127|>",
|
| 1085 |
+
"lstrip": false,
|
| 1086 |
+
"normalized": false,
|
| 1087 |
+
"rstrip": false,
|
| 1088 |
+
"single_word": false,
|
| 1089 |
+
"special": true
|
| 1090 |
+
},
|
| 1091 |
+
"128136": {
|
| 1092 |
+
"content": "<|reserved_special_token_128|>",
|
| 1093 |
+
"lstrip": false,
|
| 1094 |
+
"normalized": false,
|
| 1095 |
+
"rstrip": false,
|
| 1096 |
+
"single_word": false,
|
| 1097 |
+
"special": true
|
| 1098 |
+
},
|
| 1099 |
+
"128137": {
|
| 1100 |
+
"content": "<|reserved_special_token_129|>",
|
| 1101 |
+
"lstrip": false,
|
| 1102 |
+
"normalized": false,
|
| 1103 |
+
"rstrip": false,
|
| 1104 |
+
"single_word": false,
|
| 1105 |
+
"special": true
|
| 1106 |
+
},
|
| 1107 |
+
"128138": {
|
| 1108 |
+
"content": "<|reserved_special_token_130|>",
|
| 1109 |
+
"lstrip": false,
|
| 1110 |
+
"normalized": false,
|
| 1111 |
+
"rstrip": false,
|
| 1112 |
+
"single_word": false,
|
| 1113 |
+
"special": true
|
| 1114 |
+
},
|
| 1115 |
+
"128139": {
|
| 1116 |
+
"content": "<|reserved_special_token_131|>",
|
| 1117 |
+
"lstrip": false,
|
| 1118 |
+
"normalized": false,
|
| 1119 |
+
"rstrip": false,
|
| 1120 |
+
"single_word": false,
|
| 1121 |
+
"special": true
|
| 1122 |
+
},
|
| 1123 |
+
"128140": {
|
| 1124 |
+
"content": "<|reserved_special_token_132|>",
|
| 1125 |
+
"lstrip": false,
|
| 1126 |
+
"normalized": false,
|
| 1127 |
+
"rstrip": false,
|
| 1128 |
+
"single_word": false,
|
| 1129 |
+
"special": true
|
| 1130 |
+
},
|
| 1131 |
+
"128141": {
|
| 1132 |
+
"content": "<|reserved_special_token_133|>",
|
| 1133 |
+
"lstrip": false,
|
| 1134 |
+
"normalized": false,
|
| 1135 |
+
"rstrip": false,
|
| 1136 |
+
"single_word": false,
|
| 1137 |
+
"special": true
|
| 1138 |
+
},
|
| 1139 |
+
"128142": {
|
| 1140 |
+
"content": "<|reserved_special_token_134|>",
|
| 1141 |
+
"lstrip": false,
|
| 1142 |
+
"normalized": false,
|
| 1143 |
+
"rstrip": false,
|
| 1144 |
+
"single_word": false,
|
| 1145 |
+
"special": true
|
| 1146 |
+
},
|
| 1147 |
+
"128143": {
|
| 1148 |
+
"content": "<|reserved_special_token_135|>",
|
| 1149 |
+
"lstrip": false,
|
| 1150 |
+
"normalized": false,
|
| 1151 |
+
"rstrip": false,
|
| 1152 |
+
"single_word": false,
|
| 1153 |
+
"special": true
|
| 1154 |
+
},
|
| 1155 |
+
"128144": {
|
| 1156 |
+
"content": "<|reserved_special_token_136|>",
|
| 1157 |
+
"lstrip": false,
|
| 1158 |
+
"normalized": false,
|
| 1159 |
+
"rstrip": false,
|
| 1160 |
+
"single_word": false,
|
| 1161 |
+
"special": true
|
| 1162 |
+
},
|
| 1163 |
+
"128145": {
|
| 1164 |
+
"content": "<|reserved_special_token_137|>",
|
| 1165 |
+
"lstrip": false,
|
| 1166 |
+
"normalized": false,
|
| 1167 |
+
"rstrip": false,
|
| 1168 |
+
"single_word": false,
|
| 1169 |
+
"special": true
|
| 1170 |
+
},
|
| 1171 |
+
"128146": {
|
| 1172 |
+
"content": "<|reserved_special_token_138|>",
|
| 1173 |
+
"lstrip": false,
|
| 1174 |
+
"normalized": false,
|
| 1175 |
+
"rstrip": false,
|
| 1176 |
+
"single_word": false,
|
| 1177 |
+
"special": true
|
| 1178 |
+
},
|
| 1179 |
+
"128147": {
|
| 1180 |
+
"content": "<|reserved_special_token_139|>",
|
| 1181 |
+
"lstrip": false,
|
| 1182 |
+
"normalized": false,
|
| 1183 |
+
"rstrip": false,
|
| 1184 |
+
"single_word": false,
|
| 1185 |
+
"special": true
|
| 1186 |
+
},
|
| 1187 |
+
"128148": {
|
| 1188 |
+
"content": "<|reserved_special_token_140|>",
|
| 1189 |
+
"lstrip": false,
|
| 1190 |
+
"normalized": false,
|
| 1191 |
+
"rstrip": false,
|
| 1192 |
+
"single_word": false,
|
| 1193 |
+
"special": true
|
| 1194 |
+
},
|
| 1195 |
+
"128149": {
|
| 1196 |
+
"content": "<|reserved_special_token_141|>",
|
| 1197 |
+
"lstrip": false,
|
| 1198 |
+
"normalized": false,
|
| 1199 |
+
"rstrip": false,
|
| 1200 |
+
"single_word": false,
|
| 1201 |
+
"special": true
|
| 1202 |
+
},
|
| 1203 |
+
"128150": {
|
| 1204 |
+
"content": "<|reserved_special_token_142|>",
|
| 1205 |
+
"lstrip": false,
|
| 1206 |
+
"normalized": false,
|
| 1207 |
+
"rstrip": false,
|
| 1208 |
+
"single_word": false,
|
| 1209 |
+
"special": true
|
| 1210 |
+
},
|
| 1211 |
+
"128151": {
|
| 1212 |
+
"content": "<|reserved_special_token_143|>",
|
| 1213 |
+
"lstrip": false,
|
| 1214 |
+
"normalized": false,
|
| 1215 |
+
"rstrip": false,
|
| 1216 |
+
"single_word": false,
|
| 1217 |
+
"special": true
|
| 1218 |
+
},
|
| 1219 |
+
"128152": {
|
| 1220 |
+
"content": "<|reserved_special_token_144|>",
|
| 1221 |
+
"lstrip": false,
|
| 1222 |
+
"normalized": false,
|
| 1223 |
+
"rstrip": false,
|
| 1224 |
+
"single_word": false,
|
| 1225 |
+
"special": true
|
| 1226 |
+
},
|
| 1227 |
+
"128153": {
|
| 1228 |
+
"content": "<|reserved_special_token_145|>",
|
| 1229 |
+
"lstrip": false,
|
| 1230 |
+
"normalized": false,
|
| 1231 |
+
"rstrip": false,
|
| 1232 |
+
"single_word": false,
|
| 1233 |
+
"special": true
|
| 1234 |
+
},
|
| 1235 |
+
"128154": {
|
| 1236 |
+
"content": "<|reserved_special_token_146|>",
|
| 1237 |
+
"lstrip": false,
|
| 1238 |
+
"normalized": false,
|
| 1239 |
+
"rstrip": false,
|
| 1240 |
+
"single_word": false,
|
| 1241 |
+
"special": true
|
| 1242 |
+
},
|
| 1243 |
+
"128155": {
|
| 1244 |
+
"content": "<|reserved_special_token_147|>",
|
| 1245 |
+
"lstrip": false,
|
| 1246 |
+
"normalized": false,
|
| 1247 |
+
"rstrip": false,
|
| 1248 |
+
"single_word": false,
|
| 1249 |
+
"special": true
|
| 1250 |
+
},
|
| 1251 |
+
"128156": {
|
| 1252 |
+
"content": "<|reserved_special_token_148|>",
|
| 1253 |
+
"lstrip": false,
|
| 1254 |
+
"normalized": false,
|
| 1255 |
+
"rstrip": false,
|
| 1256 |
+
"single_word": false,
|
| 1257 |
+
"special": true
|
| 1258 |
+
},
|
| 1259 |
+
"128157": {
|
| 1260 |
+
"content": "<|reserved_special_token_149|>",
|
| 1261 |
+
"lstrip": false,
|
| 1262 |
+
"normalized": false,
|
| 1263 |
+
"rstrip": false,
|
| 1264 |
+
"single_word": false,
|
| 1265 |
+
"special": true
|
| 1266 |
+
},
|
| 1267 |
+
"128158": {
|
| 1268 |
+
"content": "<|reserved_special_token_150|>",
|
| 1269 |
+
"lstrip": false,
|
| 1270 |
+
"normalized": false,
|
| 1271 |
+
"rstrip": false,
|
| 1272 |
+
"single_word": false,
|
| 1273 |
+
"special": true
|
| 1274 |
+
},
|
| 1275 |
+
"128159": {
|
| 1276 |
+
"content": "<|reserved_special_token_151|>",
|
| 1277 |
+
"lstrip": false,
|
| 1278 |
+
"normalized": false,
|
| 1279 |
+
"rstrip": false,
|
| 1280 |
+
"single_word": false,
|
| 1281 |
+
"special": true
|
| 1282 |
+
},
|
| 1283 |
+
"128160": {
|
| 1284 |
+
"content": "<|reserved_special_token_152|>",
|
| 1285 |
+
"lstrip": false,
|
| 1286 |
+
"normalized": false,
|
| 1287 |
+
"rstrip": false,
|
| 1288 |
+
"single_word": false,
|
| 1289 |
+
"special": true
|
| 1290 |
+
},
|
| 1291 |
+
"128161": {
|
| 1292 |
+
"content": "<|reserved_special_token_153|>",
|
| 1293 |
+
"lstrip": false,
|
| 1294 |
+
"normalized": false,
|
| 1295 |
+
"rstrip": false,
|
| 1296 |
+
"single_word": false,
|
| 1297 |
+
"special": true
|
| 1298 |
+
},
|
| 1299 |
+
"128162": {
|
| 1300 |
+
"content": "<|reserved_special_token_154|>",
|
| 1301 |
+
"lstrip": false,
|
| 1302 |
+
"normalized": false,
|
| 1303 |
+
"rstrip": false,
|
| 1304 |
+
"single_word": false,
|
| 1305 |
+
"special": true
|
| 1306 |
+
},
|
| 1307 |
+
"128163": {
|
| 1308 |
+
"content": "<|reserved_special_token_155|>",
|
| 1309 |
+
"lstrip": false,
|
| 1310 |
+
"normalized": false,
|
| 1311 |
+
"rstrip": false,
|
| 1312 |
+
"single_word": false,
|
| 1313 |
+
"special": true
|
| 1314 |
+
},
|
| 1315 |
+
"128164": {
|
| 1316 |
+
"content": "<|reserved_special_token_156|>",
|
| 1317 |
+
"lstrip": false,
|
| 1318 |
+
"normalized": false,
|
| 1319 |
+
"rstrip": false,
|
| 1320 |
+
"single_word": false,
|
| 1321 |
+
"special": true
|
| 1322 |
+
},
|
| 1323 |
+
"128165": {
|
| 1324 |
+
"content": "<|reserved_special_token_157|>",
|
| 1325 |
+
"lstrip": false,
|
| 1326 |
+
"normalized": false,
|
| 1327 |
+
"rstrip": false,
|
| 1328 |
+
"single_word": false,
|
| 1329 |
+
"special": true
|
| 1330 |
+
},
|
| 1331 |
+
"128166": {
|
| 1332 |
+
"content": "<|reserved_special_token_158|>",
|
| 1333 |
+
"lstrip": false,
|
| 1334 |
+
"normalized": false,
|
| 1335 |
+
"rstrip": false,
|
| 1336 |
+
"single_word": false,
|
| 1337 |
+
"special": true
|
| 1338 |
+
},
|
| 1339 |
+
"128167": {
|
| 1340 |
+
"content": "<|reserved_special_token_159|>",
|
| 1341 |
+
"lstrip": false,
|
| 1342 |
+
"normalized": false,
|
| 1343 |
+
"rstrip": false,
|
| 1344 |
+
"single_word": false,
|
| 1345 |
+
"special": true
|
| 1346 |
+
},
|
| 1347 |
+
"128168": {
|
| 1348 |
+
"content": "<|reserved_special_token_160|>",
|
| 1349 |
+
"lstrip": false,
|
| 1350 |
+
"normalized": false,
|
| 1351 |
+
"rstrip": false,
|
| 1352 |
+
"single_word": false,
|
| 1353 |
+
"special": true
|
| 1354 |
+
},
|
| 1355 |
+
"128169": {
|
| 1356 |
+
"content": "<|reserved_special_token_161|>",
|
| 1357 |
+
"lstrip": false,
|
| 1358 |
+
"normalized": false,
|
| 1359 |
+
"rstrip": false,
|
| 1360 |
+
"single_word": false,
|
| 1361 |
+
"special": true
|
| 1362 |
+
},
|
| 1363 |
+
"128170": {
|
| 1364 |
+
"content": "<|reserved_special_token_162|>",
|
| 1365 |
+
"lstrip": false,
|
| 1366 |
+
"normalized": false,
|
| 1367 |
+
"rstrip": false,
|
| 1368 |
+
"single_word": false,
|
| 1369 |
+
"special": true
|
| 1370 |
+
},
|
| 1371 |
+
"128171": {
|
| 1372 |
+
"content": "<|reserved_special_token_163|>",
|
| 1373 |
+
"lstrip": false,
|
| 1374 |
+
"normalized": false,
|
| 1375 |
+
"rstrip": false,
|
| 1376 |
+
"single_word": false,
|
| 1377 |
+
"special": true
|
| 1378 |
+
},
|
| 1379 |
+
"128172": {
|
| 1380 |
+
"content": "<|reserved_special_token_164|>",
|
| 1381 |
+
"lstrip": false,
|
| 1382 |
+
"normalized": false,
|
| 1383 |
+
"rstrip": false,
|
| 1384 |
+
"single_word": false,
|
| 1385 |
+
"special": true
|
| 1386 |
+
},
|
| 1387 |
+
"128173": {
|
| 1388 |
+
"content": "<|reserved_special_token_165|>",
|
| 1389 |
+
"lstrip": false,
|
| 1390 |
+
"normalized": false,
|
| 1391 |
+
"rstrip": false,
|
| 1392 |
+
"single_word": false,
|
| 1393 |
+
"special": true
|
| 1394 |
+
},
|
| 1395 |
+
"128174": {
|
| 1396 |
+
"content": "<|reserved_special_token_166|>",
|
| 1397 |
+
"lstrip": false,
|
| 1398 |
+
"normalized": false,
|
| 1399 |
+
"rstrip": false,
|
| 1400 |
+
"single_word": false,
|
| 1401 |
+
"special": true
|
| 1402 |
+
},
|
| 1403 |
+
"128175": {
|
| 1404 |
+
"content": "<|reserved_special_token_167|>",
|
| 1405 |
+
"lstrip": false,
|
| 1406 |
+
"normalized": false,
|
| 1407 |
+
"rstrip": false,
|
| 1408 |
+
"single_word": false,
|
| 1409 |
+
"special": true
|
| 1410 |
+
},
|
| 1411 |
+
"128176": {
|
| 1412 |
+
"content": "<|reserved_special_token_168|>",
|
| 1413 |
+
"lstrip": false,
|
| 1414 |
+
"normalized": false,
|
| 1415 |
+
"rstrip": false,
|
| 1416 |
+
"single_word": false,
|
| 1417 |
+
"special": true
|
| 1418 |
+
},
|
| 1419 |
+
"128177": {
|
| 1420 |
+
"content": "<|reserved_special_token_169|>",
|
| 1421 |
+
"lstrip": false,
|
| 1422 |
+
"normalized": false,
|
| 1423 |
+
"rstrip": false,
|
| 1424 |
+
"single_word": false,
|
| 1425 |
+
"special": true
|
| 1426 |
+
},
|
| 1427 |
+
"128178": {
|
| 1428 |
+
"content": "<|reserved_special_token_170|>",
|
| 1429 |
+
"lstrip": false,
|
| 1430 |
+
"normalized": false,
|
| 1431 |
+
"rstrip": false,
|
| 1432 |
+
"single_word": false,
|
| 1433 |
+
"special": true
|
| 1434 |
+
},
|
| 1435 |
+
"128179": {
|
| 1436 |
+
"content": "<|reserved_special_token_171|>",
|
| 1437 |
+
"lstrip": false,
|
| 1438 |
+
"normalized": false,
|
| 1439 |
+
"rstrip": false,
|
| 1440 |
+
"single_word": false,
|
| 1441 |
+
"special": true
|
| 1442 |
+
},
|
| 1443 |
+
"128180": {
|
| 1444 |
+
"content": "<|reserved_special_token_172|>",
|
| 1445 |
+
"lstrip": false,
|
| 1446 |
+
"normalized": false,
|
| 1447 |
+
"rstrip": false,
|
| 1448 |
+
"single_word": false,
|
| 1449 |
+
"special": true
|
| 1450 |
+
},
|
| 1451 |
+
"128181": {
|
| 1452 |
+
"content": "<|reserved_special_token_173|>",
|
| 1453 |
+
"lstrip": false,
|
| 1454 |
+
"normalized": false,
|
| 1455 |
+
"rstrip": false,
|
| 1456 |
+
"single_word": false,
|
| 1457 |
+
"special": true
|
| 1458 |
+
},
|
| 1459 |
+
"128182": {
|
| 1460 |
+
"content": "<|reserved_special_token_174|>",
|
| 1461 |
+
"lstrip": false,
|
| 1462 |
+
"normalized": false,
|
| 1463 |
+
"rstrip": false,
|
| 1464 |
+
"single_word": false,
|
| 1465 |
+
"special": true
|
| 1466 |
+
},
|
| 1467 |
+
"128183": {
|
| 1468 |
+
"content": "<|reserved_special_token_175|>",
|
| 1469 |
+
"lstrip": false,
|
| 1470 |
+
"normalized": false,
|
| 1471 |
+
"rstrip": false,
|
| 1472 |
+
"single_word": false,
|
| 1473 |
+
"special": true
|
| 1474 |
+
},
|
| 1475 |
+
"128184": {
|
| 1476 |
+
"content": "<|reserved_special_token_176|>",
|
| 1477 |
+
"lstrip": false,
|
| 1478 |
+
"normalized": false,
|
| 1479 |
+
"rstrip": false,
|
| 1480 |
+
"single_word": false,
|
| 1481 |
+
"special": true
|
| 1482 |
+
},
|
| 1483 |
+
"128185": {
|
| 1484 |
+
"content": "<|reserved_special_token_177|>",
|
| 1485 |
+
"lstrip": false,
|
| 1486 |
+
"normalized": false,
|
| 1487 |
+
"rstrip": false,
|
| 1488 |
+
"single_word": false,
|
| 1489 |
+
"special": true
|
| 1490 |
+
},
|
| 1491 |
+
"128186": {
|
| 1492 |
+
"content": "<|reserved_special_token_178|>",
|
| 1493 |
+
"lstrip": false,
|
| 1494 |
+
"normalized": false,
|
| 1495 |
+
"rstrip": false,
|
| 1496 |
+
"single_word": false,
|
| 1497 |
+
"special": true
|
| 1498 |
+
},
|
| 1499 |
+
"128187": {
|
| 1500 |
+
"content": "<|reserved_special_token_179|>",
|
| 1501 |
+
"lstrip": false,
|
| 1502 |
+
"normalized": false,
|
| 1503 |
+
"rstrip": false,
|
| 1504 |
+
"single_word": false,
|
| 1505 |
+
"special": true
|
| 1506 |
+
},
|
| 1507 |
+
"128188": {
|
| 1508 |
+
"content": "<|reserved_special_token_180|>",
|
| 1509 |
+
"lstrip": false,
|
| 1510 |
+
"normalized": false,
|
| 1511 |
+
"rstrip": false,
|
| 1512 |
+
"single_word": false,
|
| 1513 |
+
"special": true
|
| 1514 |
+
},
|
| 1515 |
+
"128189": {
|
| 1516 |
+
"content": "<|reserved_special_token_181|>",
|
| 1517 |
+
"lstrip": false,
|
| 1518 |
+
"normalized": false,
|
| 1519 |
+
"rstrip": false,
|
| 1520 |
+
"single_word": false,
|
| 1521 |
+
"special": true
|
| 1522 |
+
},
|
| 1523 |
+
"128190": {
|
| 1524 |
+
"content": "<|reserved_special_token_182|>",
|
| 1525 |
+
"lstrip": false,
|
| 1526 |
+
"normalized": false,
|
| 1527 |
+
"rstrip": false,
|
| 1528 |
+
"single_word": false,
|
| 1529 |
+
"special": true
|
| 1530 |
+
},
|
| 1531 |
+
"128191": {
|
| 1532 |
+
"content": "<|reserved_special_token_183|>",
|
| 1533 |
+
"lstrip": false,
|
| 1534 |
+
"normalized": false,
|
| 1535 |
+
"rstrip": false,
|
| 1536 |
+
"single_word": false,
|
| 1537 |
+
"special": true
|
| 1538 |
+
},
|
| 1539 |
+
"128192": {
|
| 1540 |
+
"content": "<|reserved_special_token_184|>",
|
| 1541 |
+
"lstrip": false,
|
| 1542 |
+
"normalized": false,
|
| 1543 |
+
"rstrip": false,
|
| 1544 |
+
"single_word": false,
|
| 1545 |
+
"special": true
|
| 1546 |
+
},
|
| 1547 |
+
"128193": {
|
| 1548 |
+
"content": "<|reserved_special_token_185|>",
|
| 1549 |
+
"lstrip": false,
|
| 1550 |
+
"normalized": false,
|
| 1551 |
+
"rstrip": false,
|
| 1552 |
+
"single_word": false,
|
| 1553 |
+
"special": true
|
| 1554 |
+
},
|
| 1555 |
+
"128194": {
|
| 1556 |
+
"content": "<|reserved_special_token_186|>",
|
| 1557 |
+
"lstrip": false,
|
| 1558 |
+
"normalized": false,
|
| 1559 |
+
"rstrip": false,
|
| 1560 |
+
"single_word": false,
|
| 1561 |
+
"special": true
|
| 1562 |
+
},
|
| 1563 |
+
"128195": {
|
| 1564 |
+
"content": "<|reserved_special_token_187|>",
|
| 1565 |
+
"lstrip": false,
|
| 1566 |
+
"normalized": false,
|
| 1567 |
+
"rstrip": false,
|
| 1568 |
+
"single_word": false,
|
| 1569 |
+
"special": true
|
| 1570 |
+
},
|
| 1571 |
+
"128196": {
|
| 1572 |
+
"content": "<|reserved_special_token_188|>",
|
| 1573 |
+
"lstrip": false,
|
| 1574 |
+
"normalized": false,
|
| 1575 |
+
"rstrip": false,
|
| 1576 |
+
"single_word": false,
|
| 1577 |
+
"special": true
|
| 1578 |
+
},
|
| 1579 |
+
"128197": {
|
| 1580 |
+
"content": "<|reserved_special_token_189|>",
|
| 1581 |
+
"lstrip": false,
|
| 1582 |
+
"normalized": false,
|
| 1583 |
+
"rstrip": false,
|
| 1584 |
+
"single_word": false,
|
| 1585 |
+
"special": true
|
| 1586 |
+
},
|
| 1587 |
+
"128198": {
|
| 1588 |
+
"content": "<|reserved_special_token_190|>",
|
| 1589 |
+
"lstrip": false,
|
| 1590 |
+
"normalized": false,
|
| 1591 |
+
"rstrip": false,
|
| 1592 |
+
"single_word": false,
|
| 1593 |
+
"special": true
|
| 1594 |
+
},
|
| 1595 |
+
"128199": {
|
| 1596 |
+
"content": "<|reserved_special_token_191|>",
|
| 1597 |
+
"lstrip": false,
|
| 1598 |
+
"normalized": false,
|
| 1599 |
+
"rstrip": false,
|
| 1600 |
+
"single_word": false,
|
| 1601 |
+
"special": true
|
| 1602 |
+
},
|
| 1603 |
+
"128200": {
|
| 1604 |
+
"content": "<|reserved_special_token_192|>",
|
| 1605 |
+
"lstrip": false,
|
| 1606 |
+
"normalized": false,
|
| 1607 |
+
"rstrip": false,
|
| 1608 |
+
"single_word": false,
|
| 1609 |
+
"special": true
|
| 1610 |
+
},
|
| 1611 |
+
"128201": {
|
| 1612 |
+
"content": "<|reserved_special_token_193|>",
|
| 1613 |
+
"lstrip": false,
|
| 1614 |
+
"normalized": false,
|
| 1615 |
+
"rstrip": false,
|
| 1616 |
+
"single_word": false,
|
| 1617 |
+
"special": true
|
| 1618 |
+
},
|
| 1619 |
+
"128202": {
|
| 1620 |
+
"content": "<|reserved_special_token_194|>",
|
| 1621 |
+
"lstrip": false,
|
| 1622 |
+
"normalized": false,
|
| 1623 |
+
"rstrip": false,
|
| 1624 |
+
"single_word": false,
|
| 1625 |
+
"special": true
|
| 1626 |
+
},
|
| 1627 |
+
"128203": {
|
| 1628 |
+
"content": "<|reserved_special_token_195|>",
|
| 1629 |
+
"lstrip": false,
|
| 1630 |
+
"normalized": false,
|
| 1631 |
+
"rstrip": false,
|
| 1632 |
+
"single_word": false,
|
| 1633 |
+
"special": true
|
| 1634 |
+
},
|
| 1635 |
+
"128204": {
|
| 1636 |
+
"content": "<|reserved_special_token_196|>",
|
| 1637 |
+
"lstrip": false,
|
| 1638 |
+
"normalized": false,
|
| 1639 |
+
"rstrip": false,
|
| 1640 |
+
"single_word": false,
|
| 1641 |
+
"special": true
|
| 1642 |
+
},
|
| 1643 |
+
"128205": {
|
| 1644 |
+
"content": "<|reserved_special_token_197|>",
|
| 1645 |
+
"lstrip": false,
|
| 1646 |
+
"normalized": false,
|
| 1647 |
+
"rstrip": false,
|
| 1648 |
+
"single_word": false,
|
| 1649 |
+
"special": true
|
| 1650 |
+
},
|
| 1651 |
+
"128206": {
|
| 1652 |
+
"content": "<|reserved_special_token_198|>",
|
| 1653 |
+
"lstrip": false,
|
| 1654 |
+
"normalized": false,
|
| 1655 |
+
"rstrip": false,
|
| 1656 |
+
"single_word": false,
|
| 1657 |
+
"special": true
|
| 1658 |
+
},
|
| 1659 |
+
"128207": {
|
| 1660 |
+
"content": "<|reserved_special_token_199|>",
|
| 1661 |
+
"lstrip": false,
|
| 1662 |
+
"normalized": false,
|
| 1663 |
+
"rstrip": false,
|
| 1664 |
+
"single_word": false,
|
| 1665 |
+
"special": true
|
| 1666 |
+
},
|
| 1667 |
+
"128208": {
|
| 1668 |
+
"content": "<|reserved_special_token_200|>",
|
| 1669 |
+
"lstrip": false,
|
| 1670 |
+
"normalized": false,
|
| 1671 |
+
"rstrip": false,
|
| 1672 |
+
"single_word": false,
|
| 1673 |
+
"special": true
|
| 1674 |
+
},
|
| 1675 |
+
"128209": {
|
| 1676 |
+
"content": "<|reserved_special_token_201|>",
|
| 1677 |
+
"lstrip": false,
|
| 1678 |
+
"normalized": false,
|
| 1679 |
+
"rstrip": false,
|
| 1680 |
+
"single_word": false,
|
| 1681 |
+
"special": true
|
| 1682 |
+
},
|
| 1683 |
+
"128210": {
|
| 1684 |
+
"content": "<|reserved_special_token_202|>",
|
| 1685 |
+
"lstrip": false,
|
| 1686 |
+
"normalized": false,
|
| 1687 |
+
"rstrip": false,
|
| 1688 |
+
"single_word": false,
|
| 1689 |
+
"special": true
|
| 1690 |
+
},
|
| 1691 |
+
"128211": {
|
| 1692 |
+
"content": "<|reserved_special_token_203|>",
|
| 1693 |
+
"lstrip": false,
|
| 1694 |
+
"normalized": false,
|
| 1695 |
+
"rstrip": false,
|
| 1696 |
+
"single_word": false,
|
| 1697 |
+
"special": true
|
| 1698 |
+
},
|
| 1699 |
+
"128212": {
|
| 1700 |
+
"content": "<|reserved_special_token_204|>",
|
| 1701 |
+
"lstrip": false,
|
| 1702 |
+
"normalized": false,
|
| 1703 |
+
"rstrip": false,
|
| 1704 |
+
"single_word": false,
|
| 1705 |
+
"special": true
|
| 1706 |
+
},
|
| 1707 |
+
"128213": {
|
| 1708 |
+
"content": "<|reserved_special_token_205|>",
|
| 1709 |
+
"lstrip": false,
|
| 1710 |
+
"normalized": false,
|
| 1711 |
+
"rstrip": false,
|
| 1712 |
+
"single_word": false,
|
| 1713 |
+
"special": true
|
| 1714 |
+
},
|
| 1715 |
+
"128214": {
|
| 1716 |
+
"content": "<|reserved_special_token_206|>",
|
| 1717 |
+
"lstrip": false,
|
| 1718 |
+
"normalized": false,
|
| 1719 |
+
"rstrip": false,
|
| 1720 |
+
"single_word": false,
|
| 1721 |
+
"special": true
|
| 1722 |
+
},
|
| 1723 |
+
"128215": {
|
| 1724 |
+
"content": "<|reserved_special_token_207|>",
|
| 1725 |
+
"lstrip": false,
|
| 1726 |
+
"normalized": false,
|
| 1727 |
+
"rstrip": false,
|
| 1728 |
+
"single_word": false,
|
| 1729 |
+
"special": true
|
| 1730 |
+
},
|
| 1731 |
+
"128216": {
|
| 1732 |
+
"content": "<|reserved_special_token_208|>",
|
| 1733 |
+
"lstrip": false,
|
| 1734 |
+
"normalized": false,
|
| 1735 |
+
"rstrip": false,
|
| 1736 |
+
"single_word": false,
|
| 1737 |
+
"special": true
|
| 1738 |
+
},
|
| 1739 |
+
"128217": {
|
| 1740 |
+
"content": "<|reserved_special_token_209|>",
|
| 1741 |
+
"lstrip": false,
|
| 1742 |
+
"normalized": false,
|
| 1743 |
+
"rstrip": false,
|
| 1744 |
+
"single_word": false,
|
| 1745 |
+
"special": true
|
| 1746 |
+
},
|
| 1747 |
+
"128218": {
|
| 1748 |
+
"content": "<|reserved_special_token_210|>",
|
| 1749 |
+
"lstrip": false,
|
| 1750 |
+
"normalized": false,
|
| 1751 |
+
"rstrip": false,
|
| 1752 |
+
"single_word": false,
|
| 1753 |
+
"special": true
|
| 1754 |
+
},
|
| 1755 |
+
"128219": {
|
| 1756 |
+
"content": "<|reserved_special_token_211|>",
|
| 1757 |
+
"lstrip": false,
|
| 1758 |
+
"normalized": false,
|
| 1759 |
+
"rstrip": false,
|
| 1760 |
+
"single_word": false,
|
| 1761 |
+
"special": true
|
| 1762 |
+
},
|
| 1763 |
+
"128220": {
|
| 1764 |
+
"content": "<|reserved_special_token_212|>",
|
| 1765 |
+
"lstrip": false,
|
| 1766 |
+
"normalized": false,
|
| 1767 |
+
"rstrip": false,
|
| 1768 |
+
"single_word": false,
|
| 1769 |
+
"special": true
|
| 1770 |
+
},
|
| 1771 |
+
"128221": {
|
| 1772 |
+
"content": "<|reserved_special_token_213|>",
|
| 1773 |
+
"lstrip": false,
|
| 1774 |
+
"normalized": false,
|
| 1775 |
+
"rstrip": false,
|
| 1776 |
+
"single_word": false,
|
| 1777 |
+
"special": true
|
| 1778 |
+
},
|
| 1779 |
+
"128222": {
|
| 1780 |
+
"content": "<|reserved_special_token_214|>",
|
| 1781 |
+
"lstrip": false,
|
| 1782 |
+
"normalized": false,
|
| 1783 |
+
"rstrip": false,
|
| 1784 |
+
"single_word": false,
|
| 1785 |
+
"special": true
|
| 1786 |
+
},
|
| 1787 |
+
"128223": {
|
| 1788 |
+
"content": "<|reserved_special_token_215|>",
|
| 1789 |
+
"lstrip": false,
|
| 1790 |
+
"normalized": false,
|
| 1791 |
+
"rstrip": false,
|
| 1792 |
+
"single_word": false,
|
| 1793 |
+
"special": true
|
| 1794 |
+
},
|
| 1795 |
+
"128224": {
|
| 1796 |
+
"content": "<|reserved_special_token_216|>",
|
| 1797 |
+
"lstrip": false,
|
| 1798 |
+
"normalized": false,
|
| 1799 |
+
"rstrip": false,
|
| 1800 |
+
"single_word": false,
|
| 1801 |
+
"special": true
|
| 1802 |
+
},
|
| 1803 |
+
"128225": {
|
| 1804 |
+
"content": "<|reserved_special_token_217|>",
|
| 1805 |
+
"lstrip": false,
|
| 1806 |
+
"normalized": false,
|
| 1807 |
+
"rstrip": false,
|
| 1808 |
+
"single_word": false,
|
| 1809 |
+
"special": true
|
| 1810 |
+
},
|
| 1811 |
+
"128226": {
|
| 1812 |
+
"content": "<|reserved_special_token_218|>",
|
| 1813 |
+
"lstrip": false,
|
| 1814 |
+
"normalized": false,
|
| 1815 |
+
"rstrip": false,
|
| 1816 |
+
"single_word": false,
|
| 1817 |
+
"special": true
|
| 1818 |
+
},
|
| 1819 |
+
"128227": {
|
| 1820 |
+
"content": "<|reserved_special_token_219|>",
|
| 1821 |
+
"lstrip": false,
|
| 1822 |
+
"normalized": false,
|
| 1823 |
+
"rstrip": false,
|
| 1824 |
+
"single_word": false,
|
| 1825 |
+
"special": true
|
| 1826 |
+
},
|
| 1827 |
+
"128228": {
|
| 1828 |
+
"content": "<|reserved_special_token_220|>",
|
| 1829 |
+
"lstrip": false,
|
| 1830 |
+
"normalized": false,
|
| 1831 |
+
"rstrip": false,
|
| 1832 |
+
"single_word": false,
|
| 1833 |
+
"special": true
|
| 1834 |
+
},
|
| 1835 |
+
"128229": {
|
| 1836 |
+
"content": "<|reserved_special_token_221|>",
|
| 1837 |
+
"lstrip": false,
|
| 1838 |
+
"normalized": false,
|
| 1839 |
+
"rstrip": false,
|
| 1840 |
+
"single_word": false,
|
| 1841 |
+
"special": true
|
| 1842 |
+
},
|
| 1843 |
+
"128230": {
|
| 1844 |
+
"content": "<|reserved_special_token_222|>",
|
| 1845 |
+
"lstrip": false,
|
| 1846 |
+
"normalized": false,
|
| 1847 |
+
"rstrip": false,
|
| 1848 |
+
"single_word": false,
|
| 1849 |
+
"special": true
|
| 1850 |
+
},
|
| 1851 |
+
"128231": {
|
| 1852 |
+
"content": "<|reserved_special_token_223|>",
|
| 1853 |
+
"lstrip": false,
|
| 1854 |
+
"normalized": false,
|
| 1855 |
+
"rstrip": false,
|
| 1856 |
+
"single_word": false,
|
| 1857 |
+
"special": true
|
| 1858 |
+
},
|
| 1859 |
+
"128232": {
|
| 1860 |
+
"content": "<|reserved_special_token_224|>",
|
| 1861 |
+
"lstrip": false,
|
| 1862 |
+
"normalized": false,
|
| 1863 |
+
"rstrip": false,
|
| 1864 |
+
"single_word": false,
|
| 1865 |
+
"special": true
|
| 1866 |
+
},
|
| 1867 |
+
"128233": {
|
| 1868 |
+
"content": "<|reserved_special_token_225|>",
|
| 1869 |
+
"lstrip": false,
|
| 1870 |
+
"normalized": false,
|
| 1871 |
+
"rstrip": false,
|
| 1872 |
+
"single_word": false,
|
| 1873 |
+
"special": true
|
| 1874 |
+
},
|
| 1875 |
+
"128234": {
|
| 1876 |
+
"content": "<|reserved_special_token_226|>",
|
| 1877 |
+
"lstrip": false,
|
| 1878 |
+
"normalized": false,
|
| 1879 |
+
"rstrip": false,
|
| 1880 |
+
"single_word": false,
|
| 1881 |
+
"special": true
|
| 1882 |
+
},
|
| 1883 |
+
"128235": {
|
| 1884 |
+
"content": "<|reserved_special_token_227|>",
|
| 1885 |
+
"lstrip": false,
|
| 1886 |
+
"normalized": false,
|
| 1887 |
+
"rstrip": false,
|
| 1888 |
+
"single_word": false,
|
| 1889 |
+
"special": true
|
| 1890 |
+
},
|
| 1891 |
+
"128236": {
|
| 1892 |
+
"content": "<|reserved_special_token_228|>",
|
| 1893 |
+
"lstrip": false,
|
| 1894 |
+
"normalized": false,
|
| 1895 |
+
"rstrip": false,
|
| 1896 |
+
"single_word": false,
|
| 1897 |
+
"special": true
|
| 1898 |
+
},
|
| 1899 |
+
"128237": {
|
| 1900 |
+
"content": "<|reserved_special_token_229|>",
|
| 1901 |
+
"lstrip": false,
|
| 1902 |
+
"normalized": false,
|
| 1903 |
+
"rstrip": false,
|
| 1904 |
+
"single_word": false,
|
| 1905 |
+
"special": true
|
| 1906 |
+
},
|
| 1907 |
+
"128238": {
|
| 1908 |
+
"content": "<|reserved_special_token_230|>",
|
| 1909 |
+
"lstrip": false,
|
| 1910 |
+
"normalized": false,
|
| 1911 |
+
"rstrip": false,
|
| 1912 |
+
"single_word": false,
|
| 1913 |
+
"special": true
|
| 1914 |
+
},
|
| 1915 |
+
"128239": {
|
| 1916 |
+
"content": "<|reserved_special_token_231|>",
|
| 1917 |
+
"lstrip": false,
|
| 1918 |
+
"normalized": false,
|
| 1919 |
+
"rstrip": false,
|
| 1920 |
+
"single_word": false,
|
| 1921 |
+
"special": true
|
| 1922 |
+
},
|
| 1923 |
+
"128240": {
|
| 1924 |
+
"content": "<|reserved_special_token_232|>",
|
| 1925 |
+
"lstrip": false,
|
| 1926 |
+
"normalized": false,
|
| 1927 |
+
"rstrip": false,
|
| 1928 |
+
"single_word": false,
|
| 1929 |
+
"special": true
|
| 1930 |
+
},
|
| 1931 |
+
"128241": {
|
| 1932 |
+
"content": "<|reserved_special_token_233|>",
|
| 1933 |
+
"lstrip": false,
|
| 1934 |
+
"normalized": false,
|
| 1935 |
+
"rstrip": false,
|
| 1936 |
+
"single_word": false,
|
| 1937 |
+
"special": true
|
| 1938 |
+
},
|
| 1939 |
+
"128242": {
|
| 1940 |
+
"content": "<|reserved_special_token_234|>",
|
| 1941 |
+
"lstrip": false,
|
| 1942 |
+
"normalized": false,
|
| 1943 |
+
"rstrip": false,
|
| 1944 |
+
"single_word": false,
|
| 1945 |
+
"special": true
|
| 1946 |
+
},
|
| 1947 |
+
"128243": {
|
| 1948 |
+
"content": "<|reserved_special_token_235|>",
|
| 1949 |
+
"lstrip": false,
|
| 1950 |
+
"normalized": false,
|
| 1951 |
+
"rstrip": false,
|
| 1952 |
+
"single_word": false,
|
| 1953 |
+
"special": true
|
| 1954 |
+
},
|
| 1955 |
+
"128244": {
|
| 1956 |
+
"content": "<|reserved_special_token_236|>",
|
| 1957 |
+
"lstrip": false,
|
| 1958 |
+
"normalized": false,
|
| 1959 |
+
"rstrip": false,
|
| 1960 |
+
"single_word": false,
|
| 1961 |
+
"special": true
|
| 1962 |
+
},
|
| 1963 |
+
"128245": {
|
| 1964 |
+
"content": "<|reserved_special_token_237|>",
|
| 1965 |
+
"lstrip": false,
|
| 1966 |
+
"normalized": false,
|
| 1967 |
+
"rstrip": false,
|
| 1968 |
+
"single_word": false,
|
| 1969 |
+
"special": true
|
| 1970 |
+
},
|
| 1971 |
+
"128246": {
|
| 1972 |
+
"content": "<|reserved_special_token_238|>",
|
| 1973 |
+
"lstrip": false,
|
| 1974 |
+
"normalized": false,
|
| 1975 |
+
"rstrip": false,
|
| 1976 |
+
"single_word": false,
|
| 1977 |
+
"special": true
|
| 1978 |
+
},
|
| 1979 |
+
"128247": {
|
| 1980 |
+
"content": "<|reserved_special_token_239|>",
|
| 1981 |
+
"lstrip": false,
|
| 1982 |
+
"normalized": false,
|
| 1983 |
+
"rstrip": false,
|
| 1984 |
+
"single_word": false,
|
| 1985 |
+
"special": true
|
| 1986 |
+
},
|
| 1987 |
+
"128248": {
|
| 1988 |
+
"content": "<|reserved_special_token_240|>",
|
| 1989 |
+
"lstrip": false,
|
| 1990 |
+
"normalized": false,
|
| 1991 |
+
"rstrip": false,
|
| 1992 |
+
"single_word": false,
|
| 1993 |
+
"special": true
|
| 1994 |
+
},
|
| 1995 |
+
"128249": {
|
| 1996 |
+
"content": "<|reserved_special_token_241|>",
|
| 1997 |
+
"lstrip": false,
|
| 1998 |
+
"normalized": false,
|
| 1999 |
+
"rstrip": false,
|
| 2000 |
+
"single_word": false,
|
| 2001 |
+
"special": true
|
| 2002 |
+
},
|
| 2003 |
+
"128250": {
|
| 2004 |
+
"content": "<|reserved_special_token_242|>",
|
| 2005 |
+
"lstrip": false,
|
| 2006 |
+
"normalized": false,
|
| 2007 |
+
"rstrip": false,
|
| 2008 |
+
"single_word": false,
|
| 2009 |
+
"special": true
|
| 2010 |
+
},
|
| 2011 |
+
"128251": {
|
| 2012 |
+
"content": "<|reserved_special_token_243|>",
|
| 2013 |
+
"lstrip": false,
|
| 2014 |
+
"normalized": false,
|
| 2015 |
+
"rstrip": false,
|
| 2016 |
+
"single_word": false,
|
| 2017 |
+
"special": true
|
| 2018 |
+
},
|
| 2019 |
+
"128252": {
|
| 2020 |
+
"content": "<|reserved_special_token_244|>",
|
| 2021 |
+
"lstrip": false,
|
| 2022 |
+
"normalized": false,
|
| 2023 |
+
"rstrip": false,
|
| 2024 |
+
"single_word": false,
|
| 2025 |
+
"special": true
|
| 2026 |
+
},
|
| 2027 |
+
"128253": {
|
| 2028 |
+
"content": "<|reserved_special_token_245|>",
|
| 2029 |
+
"lstrip": false,
|
| 2030 |
+
"normalized": false,
|
| 2031 |
+
"rstrip": false,
|
| 2032 |
+
"single_word": false,
|
| 2033 |
+
"special": true
|
| 2034 |
+
},
|
| 2035 |
+
"128254": {
|
| 2036 |
+
"content": "<|reserved_special_token_246|>",
|
| 2037 |
+
"lstrip": false,
|
| 2038 |
+
"normalized": false,
|
| 2039 |
+
"rstrip": false,
|
| 2040 |
+
"single_word": false,
|
| 2041 |
+
"special": true
|
| 2042 |
+
},
|
| 2043 |
+
"128255": {
|
| 2044 |
+
"content": "<|reserved_special_token_247|>",
|
| 2045 |
+
"lstrip": false,
|
| 2046 |
+
"normalized": false,
|
| 2047 |
+
"rstrip": false,
|
| 2048 |
+
"single_word": false,
|
| 2049 |
+
"special": true
|
| 2050 |
+
}
|
| 2051 |
+
},
|
| 2052 |
+
"bos_token": "<|begin_of_text|>",
|
| 2053 |
+
"chat_template": "{{- bos_token }}\n{%- if custom_tools is defined %}\n {%- set tools = custom_tools %}\n{%- endif %}\n{%- if not tools_in_user_message is defined %}\n {%- set tools_in_user_message = true %}\n{%- endif %}\n{%- if not date_string is defined %}\n {%- if strftime_now is defined %}\n {%- set date_string = strftime_now(\"%d %b %Y\") %}\n {%- else %}\n {%- set date_string = \"26 Jul 2024\" %}\n {%- endif %}\n{%- endif %}\n{%- if not tools is defined %}\n {%- set tools = none %}\n{%- endif %}\n\n{#- This block extracts the system message, so we can slot it into the right place. #}\n{%- if messages[0]['role'] == 'system' %}\n {%- set system_message = messages[0]['content']|trim %}\n {%- set messages = messages[1:] %}\n{%- else %}\n {%- set system_message = \"\" %}\n{%- endif %}\n\n{#- System message #}\n{{- \"<|start_header_id|>system<|end_header_id|>\\n\\n\" }}\n{%- if tools is not none %}\n {{- \"Environment: ipython\\n\" }}\n{%- endif %}\n{{- \"Cutting Knowledge Date: December 2023\\n\" }}\n{{- \"Today Date: \" + date_string + \"\\n\\n\" }}\n{%- if tools is not none and not tools_in_user_message %}\n {{- \"You have access to the following functions. To call a function, please respond with JSON for a function call.\" }}\n {{- 'Respond in the format {\"name\": function name, \"parameters\": dictionary of argument name and its value}.' }}\n {{- \"Do not use variables.\\n\\n\" }}\n {%- for t in tools %}\n {{- t | tojson(indent=4) }}\n {{- \"\\n\\n\" }}\n {%- endfor %}\n{%- endif %}\n{{- system_message }}\n{{- \"<|eot_id|>\" }}\n\n{#- Custom tools are passed in a user message with some extra guidance #}\n{%- if tools_in_user_message and not tools is none %}\n {#- Extract the first user message so we can plug it in here #}\n {%- if messages | length != 0 %}\n {%- set first_user_message = messages[0]['content']|trim %}\n {%- set messages = messages[1:] %}\n {%- else %}\n {{- raise_exception(\"Cannot put tools in the first user message when there's no first user message!\") }}\n{%- endif %}\n {{- '<|start_header_id|>user<|end_header_id|>\\n\\n' -}}\n {{- \"Given the following functions, please respond with a JSON for a function call \" }}\n {{- \"with its proper arguments that best answers the given prompt.\\n\\n\" }}\n {{- 'Respond in the format {\"name\": function name, \"parameters\": dictionary of argument name and its value}.' }}\n {{- \"Do not use variables.\\n\\n\" }}\n {%- for t in tools %}\n {{- t | tojson(indent=4) }}\n {{- \"\\n\\n\" }}\n {%- endfor %}\n {{- first_user_message + \"<|eot_id|>\"}}\n{%- endif %}\n\n{%- for message in messages %}\n {%- if not (message.role == 'ipython' or message.role == 'tool' or 'tool_calls' in message) %}\n {{- '<|start_header_id|>' + message['role'] + '<|end_header_id|>\\n\\n'+ message['content'] | trim + '<|eot_id|>' }}\n {%- elif 'tool_calls' in message %}\n {%- if not message.tool_calls|length == 1 %}\n {{- raise_exception(\"This model only supports single tool-calls at once!\") }}\n {%- endif %}\n {%- set tool_call = message.tool_calls[0].function %}\n {{- '<|start_header_id|>assistant<|end_header_id|>\\n\\n' -}}\n {{- '{\"name\": \"' + tool_call.name + '\", ' }}\n {{- '\"parameters\": ' }}\n {{- tool_call.arguments | tojson }}\n {{- \"}\" }}\n {{- \"<|eot_id|>\" }}\n {%- elif message.role == \"tool\" or message.role == \"ipython\" %}\n {{- \"<|start_header_id|>ipython<|end_header_id|>\\n\\n\" }}\n {%- if message.content is mapping or message.content is iterable %}\n {{- message.content | tojson }}\n {%- else %}\n {{- message.content }}\n {%- endif %}\n {{- \"<|eot_id|>\" }}\n {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n {{- '<|start_header_id|>assistant<|end_header_id|>\\n\\n' }}\n{%- endif %}\n",
|
| 2054 |
+
"clean_up_tokenization_spaces": true,
|
| 2055 |
+
"eos_token": "<|eot_id|>",
|
| 2056 |
+
"model_input_names": [
|
| 2057 |
+
"input_ids",
|
| 2058 |
+
"attention_mask"
|
| 2059 |
+
],
|
| 2060 |
+
"model_max_length": 131072,
|
| 2061 |
+
"pad_token": "<|end_of_text|>",
|
| 2062 |
+
"tokenizer_class": "PreTrainedTokenizerFast"
|
| 2063 |
+
}
|
checkpoint-132825/trainer_state.json
ADDED
|
@@ -0,0 +1,1888 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 25.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 132825,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.09410878976096368,
|
| 13 |
+
"grad_norm": 7.552914619445801,
|
| 14 |
+
"learning_rate": 4.843152017065061e-05,
|
| 15 |
+
"loss": 1.9573,
|
| 16 |
+
"step": 500
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.18821757952192736,
|
| 20 |
+
"grad_norm": 10.377354621887207,
|
| 21 |
+
"learning_rate": 4.686304034130121e-05,
|
| 22 |
+
"loss": 1.6637,
|
| 23 |
+
"step": 1000
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.282326369282891,
|
| 27 |
+
"grad_norm": 10.336068153381348,
|
| 28 |
+
"learning_rate": 4.529456051195182e-05,
|
| 29 |
+
"loss": 1.6903,
|
| 30 |
+
"step": 1500
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.3764351590438547,
|
| 34 |
+
"grad_norm": 4.373341083526611,
|
| 35 |
+
"learning_rate": 4.372608068260242e-05,
|
| 36 |
+
"loss": 1.7066,
|
| 37 |
+
"step": 2000
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.47054394880481837,
|
| 41 |
+
"grad_norm": 6.67123556137085,
|
| 42 |
+
"learning_rate": 4.2157600853253026e-05,
|
| 43 |
+
"loss": 1.6262,
|
| 44 |
+
"step": 2500
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.564652738565782,
|
| 48 |
+
"grad_norm": 7.045924663543701,
|
| 49 |
+
"learning_rate": 4.0589121023903634e-05,
|
| 50 |
+
"loss": 1.6133,
|
| 51 |
+
"step": 3000
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.6587615283267457,
|
| 55 |
+
"grad_norm": 8.646467208862305,
|
| 56 |
+
"learning_rate": 3.902064119455424e-05,
|
| 57 |
+
"loss": 1.5958,
|
| 58 |
+
"step": 3500
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.7528703180877094,
|
| 62 |
+
"grad_norm": 17.767257690429688,
|
| 63 |
+
"learning_rate": 3.745216136520485e-05,
|
| 64 |
+
"loss": 1.5926,
|
| 65 |
+
"step": 4000
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.846979107848673,
|
| 69 |
+
"grad_norm": 6.851809978485107,
|
| 70 |
+
"learning_rate": 3.588368153585545e-05,
|
| 71 |
+
"loss": 1.5898,
|
| 72 |
+
"step": 4500
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.9410878976096367,
|
| 76 |
+
"grad_norm": 6.367198467254639,
|
| 77 |
+
"learning_rate": 3.431520170650606e-05,
|
| 78 |
+
"loss": 1.5842,
|
| 79 |
+
"step": 5000
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 1.0351966873706004,
|
| 83 |
+
"grad_norm": 3.8963205814361572,
|
| 84 |
+
"learning_rate": 3.274672187715666e-05,
|
| 85 |
+
"loss": 1.6023,
|
| 86 |
+
"step": 5500
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 1.129305477131564,
|
| 90 |
+
"grad_norm": 3.492241382598877,
|
| 91 |
+
"learning_rate": 3.1178242047807265e-05,
|
| 92 |
+
"loss": 1.5835,
|
| 93 |
+
"step": 6000
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 1.2234142668925279,
|
| 97 |
+
"grad_norm": 6.9010396003723145,
|
| 98 |
+
"learning_rate": 2.960976221845787e-05,
|
| 99 |
+
"loss": 1.5804,
|
| 100 |
+
"step": 6500
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 1.3175230566534915,
|
| 104 |
+
"grad_norm": 7.097581386566162,
|
| 105 |
+
"learning_rate": 2.8041282389108477e-05,
|
| 106 |
+
"loss": 1.5685,
|
| 107 |
+
"step": 7000
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 1.411631846414455,
|
| 111 |
+
"grad_norm": 4.106161117553711,
|
| 112 |
+
"learning_rate": 2.647280255975908e-05,
|
| 113 |
+
"loss": 1.5557,
|
| 114 |
+
"step": 7500
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 1.5057406361754189,
|
| 118 |
+
"grad_norm": 5.339535236358643,
|
| 119 |
+
"learning_rate": 2.490432273040969e-05,
|
| 120 |
+
"loss": 1.5266,
|
| 121 |
+
"step": 8000
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 1.5998494259363825,
|
| 125 |
+
"grad_norm": 5.467094421386719,
|
| 126 |
+
"learning_rate": 2.3335842901060293e-05,
|
| 127 |
+
"loss": 1.5394,
|
| 128 |
+
"step": 8500
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 1.693958215697346,
|
| 132 |
+
"grad_norm": 5.166747093200684,
|
| 133 |
+
"learning_rate": 2.17673630717109e-05,
|
| 134 |
+
"loss": 1.5131,
|
| 135 |
+
"step": 9000
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 1.7880670054583097,
|
| 139 |
+
"grad_norm": 3.2604665756225586,
|
| 140 |
+
"learning_rate": 2.0198883242361504e-05,
|
| 141 |
+
"loss": 1.4695,
|
| 142 |
+
"step": 9500
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 1.8821757952192735,
|
| 146 |
+
"grad_norm": 6.9691362380981445,
|
| 147 |
+
"learning_rate": 1.8630403413012108e-05,
|
| 148 |
+
"loss": 1.4532,
|
| 149 |
+
"step": 10000
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 1.9762845849802373,
|
| 153 |
+
"grad_norm": 3.044600248336792,
|
| 154 |
+
"learning_rate": 1.7061923583662716e-05,
|
| 155 |
+
"loss": 1.4349,
|
| 156 |
+
"step": 10500
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 2.070393374741201,
|
| 160 |
+
"grad_norm": 5.485976219177246,
|
| 161 |
+
"learning_rate": 1.549344375431332e-05,
|
| 162 |
+
"loss": 1.4098,
|
| 163 |
+
"step": 11000
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 2.1645021645021645,
|
| 167 |
+
"grad_norm": 3.2020225524902344,
|
| 168 |
+
"learning_rate": 1.3924963924963927e-05,
|
| 169 |
+
"loss": 1.4025,
|
| 170 |
+
"step": 11500
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 2.258610954263128,
|
| 174 |
+
"grad_norm": 4.406314849853516,
|
| 175 |
+
"learning_rate": 1.235648409561453e-05,
|
| 176 |
+
"loss": 1.384,
|
| 177 |
+
"step": 12000
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 2.3527197440240917,
|
| 181 |
+
"grad_norm": 7.23325252532959,
|
| 182 |
+
"learning_rate": 1.0788004266265137e-05,
|
| 183 |
+
"loss": 1.3831,
|
| 184 |
+
"step": 12500
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 2.4468285337850557,
|
| 188 |
+
"grad_norm": 6.645949840545654,
|
| 189 |
+
"learning_rate": 9.219524436915741e-06,
|
| 190 |
+
"loss": 1.3611,
|
| 191 |
+
"step": 13000
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 2.5409373235460193,
|
| 195 |
+
"grad_norm": 4.476417064666748,
|
| 196 |
+
"learning_rate": 7.651044607566347e-06,
|
| 197 |
+
"loss": 1.3478,
|
| 198 |
+
"step": 13500
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 2.635046113306983,
|
| 202 |
+
"grad_norm": 4.497859954833984,
|
| 203 |
+
"learning_rate": 6.082564778216952e-06,
|
| 204 |
+
"loss": 1.3354,
|
| 205 |
+
"step": 14000
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 2.7291549030679465,
|
| 209 |
+
"grad_norm": 4.2654008865356445,
|
| 210 |
+
"learning_rate": 4.514084948867558e-06,
|
| 211 |
+
"loss": 1.3229,
|
| 212 |
+
"step": 14500
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 2.82326369282891,
|
| 216 |
+
"grad_norm": 3.607623338699341,
|
| 217 |
+
"learning_rate": 2.945605119518163e-06,
|
| 218 |
+
"loss": 1.3001,
|
| 219 |
+
"step": 15000
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 2.917372482589874,
|
| 223 |
+
"grad_norm": 3.7838690280914307,
|
| 224 |
+
"learning_rate": 1.3771252901687685e-06,
|
| 225 |
+
"loss": 1.2967,
|
| 226 |
+
"step": 15500
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 3.0114812723508377,
|
| 230 |
+
"grad_norm": 7.810318946838379,
|
| 231 |
+
"learning_rate": 3.494259363824581e-05,
|
| 232 |
+
"loss": 1.4147,
|
| 233 |
+
"step": 16000
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 3.1055900621118013,
|
| 237 |
+
"grad_norm": 3.653393030166626,
|
| 238 |
+
"learning_rate": 3.4472049689440996e-05,
|
| 239 |
+
"loss": 1.4375,
|
| 240 |
+
"step": 16500
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 3.199698851872765,
|
| 244 |
+
"grad_norm": 6.7401018142700195,
|
| 245 |
+
"learning_rate": 3.400150574063617e-05,
|
| 246 |
+
"loss": 1.3906,
|
| 247 |
+
"step": 17000
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 3.2938076416337285,
|
| 251 |
+
"grad_norm": 4.238823890686035,
|
| 252 |
+
"learning_rate": 3.3530961791831364e-05,
|
| 253 |
+
"loss": 1.3716,
|
| 254 |
+
"step": 17500
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 3.387916431394692,
|
| 258 |
+
"grad_norm": 2.793461561203003,
|
| 259 |
+
"learning_rate": 3.306041784302654e-05,
|
| 260 |
+
"loss": 1.3764,
|
| 261 |
+
"step": 18000
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 3.4820252211556557,
|
| 265 |
+
"grad_norm": 3.1460959911346436,
|
| 266 |
+
"learning_rate": 3.2589873894221726e-05,
|
| 267 |
+
"loss": 1.3557,
|
| 268 |
+
"step": 18500
|
| 269 |
+
},
|
| 270 |
+
{
|
| 271 |
+
"epoch": 3.5761340109166198,
|
| 272 |
+
"grad_norm": 6.384432792663574,
|
| 273 |
+
"learning_rate": 3.2119329945416903e-05,
|
| 274 |
+
"loss": 1.3503,
|
| 275 |
+
"step": 19000
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 3.6702428006775834,
|
| 279 |
+
"grad_norm": 3.8678534030914307,
|
| 280 |
+
"learning_rate": 3.164878599661209e-05,
|
| 281 |
+
"loss": 1.3407,
|
| 282 |
+
"step": 19500
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 3.764351590438547,
|
| 286 |
+
"grad_norm": 2.776543140411377,
|
| 287 |
+
"learning_rate": 3.1178242047807265e-05,
|
| 288 |
+
"loss": 1.3593,
|
| 289 |
+
"step": 20000
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 3.8584603801995105,
|
| 293 |
+
"grad_norm": 8.332947731018066,
|
| 294 |
+
"learning_rate": 3.070769809900245e-05,
|
| 295 |
+
"loss": 1.3323,
|
| 296 |
+
"step": 20500
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 3.9525691699604746,
|
| 300 |
+
"grad_norm": 5.115898609161377,
|
| 301 |
+
"learning_rate": 3.0237154150197627e-05,
|
| 302 |
+
"loss": 1.3184,
|
| 303 |
+
"step": 21000
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 4.046677959721438,
|
| 307 |
+
"grad_norm": 5.099429607391357,
|
| 308 |
+
"learning_rate": 2.9766610201392815e-05,
|
| 309 |
+
"loss": 1.3082,
|
| 310 |
+
"step": 21500
|
| 311 |
+
},
|
| 312 |
+
{
|
| 313 |
+
"epoch": 4.140786749482402,
|
| 314 |
+
"grad_norm": 3.901289939880371,
|
| 315 |
+
"learning_rate": 2.9296066252587996e-05,
|
| 316 |
+
"loss": 1.3038,
|
| 317 |
+
"step": 22000
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 4.234895539243365,
|
| 321 |
+
"grad_norm": 3.7559354305267334,
|
| 322 |
+
"learning_rate": 2.8825522303783176e-05,
|
| 323 |
+
"loss": 1.2892,
|
| 324 |
+
"step": 22500
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 4.329004329004329,
|
| 328 |
+
"grad_norm": 4.156054973602295,
|
| 329 |
+
"learning_rate": 2.8354978354978357e-05,
|
| 330 |
+
"loss": 1.2893,
|
| 331 |
+
"step": 23000
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 4.423113118765293,
|
| 335 |
+
"grad_norm": 3.1980538368225098,
|
| 336 |
+
"learning_rate": 2.7884434406173538e-05,
|
| 337 |
+
"loss": 1.288,
|
| 338 |
+
"step": 23500
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 4.517221908526256,
|
| 342 |
+
"grad_norm": 2.7643442153930664,
|
| 343 |
+
"learning_rate": 2.741389045736872e-05,
|
| 344 |
+
"loss": 1.2666,
|
| 345 |
+
"step": 24000
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 4.61133069828722,
|
| 349 |
+
"grad_norm": 2.195343017578125,
|
| 350 |
+
"learning_rate": 2.69433465085639e-05,
|
| 351 |
+
"loss": 1.2632,
|
| 352 |
+
"step": 24500
|
| 353 |
+
},
|
| 354 |
+
{
|
| 355 |
+
"epoch": 4.705439488048183,
|
| 356 |
+
"grad_norm": 2.6611695289611816,
|
| 357 |
+
"learning_rate": 2.647280255975908e-05,
|
| 358 |
+
"loss": 1.262,
|
| 359 |
+
"step": 25000
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 4.799548277809148,
|
| 363 |
+
"grad_norm": 5.055428981781006,
|
| 364 |
+
"learning_rate": 2.6002258610954265e-05,
|
| 365 |
+
"loss": 1.2687,
|
| 366 |
+
"step": 25500
|
| 367 |
+
},
|
| 368 |
+
{
|
| 369 |
+
"epoch": 4.893657067570111,
|
| 370 |
+
"grad_norm": 2.993502616882324,
|
| 371 |
+
"learning_rate": 2.5531714662149446e-05,
|
| 372 |
+
"loss": 1.2439,
|
| 373 |
+
"step": 26000
|
| 374 |
+
},
|
| 375 |
+
{
|
| 376 |
+
"epoch": 4.987765857331075,
|
| 377 |
+
"grad_norm": 2.6108858585357666,
|
| 378 |
+
"learning_rate": 2.5061170713344627e-05,
|
| 379 |
+
"loss": 1.2315,
|
| 380 |
+
"step": 26500
|
| 381 |
+
},
|
| 382 |
+
{
|
| 383 |
+
"epoch": 5.081874647092039,
|
| 384 |
+
"grad_norm": 3.422744035720825,
|
| 385 |
+
"learning_rate": 2.4590626764539808e-05,
|
| 386 |
+
"loss": 1.2216,
|
| 387 |
+
"step": 27000
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 5.175983436853002,
|
| 391 |
+
"grad_norm": 2.409943103790283,
|
| 392 |
+
"learning_rate": 2.412008281573499e-05,
|
| 393 |
+
"loss": 1.214,
|
| 394 |
+
"step": 27500
|
| 395 |
+
},
|
| 396 |
+
{
|
| 397 |
+
"epoch": 5.270092226613966,
|
| 398 |
+
"grad_norm": 2.378814458847046,
|
| 399 |
+
"learning_rate": 2.3649538866930173e-05,
|
| 400 |
+
"loss": 1.206,
|
| 401 |
+
"step": 28000
|
| 402 |
+
},
|
| 403 |
+
{
|
| 404 |
+
"epoch": 5.364201016374929,
|
| 405 |
+
"grad_norm": 2.6459624767303467,
|
| 406 |
+
"learning_rate": 2.3178994918125354e-05,
|
| 407 |
+
"loss": 1.2078,
|
| 408 |
+
"step": 28500
|
| 409 |
+
},
|
| 410 |
+
{
|
| 411 |
+
"epoch": 5.458309806135893,
|
| 412 |
+
"grad_norm": 3.1709744930267334,
|
| 413 |
+
"learning_rate": 2.2708450969320535e-05,
|
| 414 |
+
"loss": 1.1908,
|
| 415 |
+
"step": 29000
|
| 416 |
+
},
|
| 417 |
+
{
|
| 418 |
+
"epoch": 5.552418595896857,
|
| 419 |
+
"grad_norm": 3.47601056098938,
|
| 420 |
+
"learning_rate": 2.2237907020515716e-05,
|
| 421 |
+
"loss": 1.192,
|
| 422 |
+
"step": 29500
|
| 423 |
+
},
|
| 424 |
+
{
|
| 425 |
+
"epoch": 5.64652738565782,
|
| 426 |
+
"grad_norm": 3.5006909370422363,
|
| 427 |
+
"learning_rate": 2.17673630717109e-05,
|
| 428 |
+
"loss": 1.1913,
|
| 429 |
+
"step": 30000
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 5.740636175418784,
|
| 433 |
+
"grad_norm": 2.8024189472198486,
|
| 434 |
+
"learning_rate": 2.129681912290608e-05,
|
| 435 |
+
"loss": 1.1815,
|
| 436 |
+
"step": 30500
|
| 437 |
+
},
|
| 438 |
+
{
|
| 439 |
+
"epoch": 5.834744965179748,
|
| 440 |
+
"grad_norm": 4.2450947761535645,
|
| 441 |
+
"learning_rate": 2.0826275174101262e-05,
|
| 442 |
+
"loss": 1.1793,
|
| 443 |
+
"step": 31000
|
| 444 |
+
},
|
| 445 |
+
{
|
| 446 |
+
"epoch": 5.928853754940711,
|
| 447 |
+
"grad_norm": 3.6110267639160156,
|
| 448 |
+
"learning_rate": 2.0355731225296443e-05,
|
| 449 |
+
"loss": 1.1734,
|
| 450 |
+
"step": 31500
|
| 451 |
+
},
|
| 452 |
+
{
|
| 453 |
+
"epoch": 6.0229625447016755,
|
| 454 |
+
"grad_norm": 4.730632305145264,
|
| 455 |
+
"learning_rate": 1.9885187276491627e-05,
|
| 456 |
+
"loss": 1.1447,
|
| 457 |
+
"step": 32000
|
| 458 |
+
},
|
| 459 |
+
{
|
| 460 |
+
"epoch": 6.117071334462639,
|
| 461 |
+
"grad_norm": 3.0380797386169434,
|
| 462 |
+
"learning_rate": 1.9414643327686808e-05,
|
| 463 |
+
"loss": 1.1206,
|
| 464 |
+
"step": 32500
|
| 465 |
+
},
|
| 466 |
+
{
|
| 467 |
+
"epoch": 6.211180124223603,
|
| 468 |
+
"grad_norm": 4.4165358543396,
|
| 469 |
+
"learning_rate": 1.894409937888199e-05,
|
| 470 |
+
"loss": 1.1295,
|
| 471 |
+
"step": 33000
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 6.305288913984566,
|
| 475 |
+
"grad_norm": 3.3100738525390625,
|
| 476 |
+
"learning_rate": 1.847355543007717e-05,
|
| 477 |
+
"loss": 1.1214,
|
| 478 |
+
"step": 33500
|
| 479 |
+
},
|
| 480 |
+
{
|
| 481 |
+
"epoch": 6.39939770374553,
|
| 482 |
+
"grad_norm": 4.085879325866699,
|
| 483 |
+
"learning_rate": 1.8003011481272354e-05,
|
| 484 |
+
"loss": 1.1128,
|
| 485 |
+
"step": 34000
|
| 486 |
+
},
|
| 487 |
+
{
|
| 488 |
+
"epoch": 6.4935064935064934,
|
| 489 |
+
"grad_norm": 3.0867068767547607,
|
| 490 |
+
"learning_rate": 1.7532467532467535e-05,
|
| 491 |
+
"loss": 1.114,
|
| 492 |
+
"step": 34500
|
| 493 |
+
},
|
| 494 |
+
{
|
| 495 |
+
"epoch": 6.587615283267457,
|
| 496 |
+
"grad_norm": 3.721590757369995,
|
| 497 |
+
"learning_rate": 1.7061923583662716e-05,
|
| 498 |
+
"loss": 1.1037,
|
| 499 |
+
"step": 35000
|
| 500 |
+
},
|
| 501 |
+
{
|
| 502 |
+
"epoch": 6.681724073028421,
|
| 503 |
+
"grad_norm": 3.4121475219726562,
|
| 504 |
+
"learning_rate": 1.6591379634857897e-05,
|
| 505 |
+
"loss": 1.107,
|
| 506 |
+
"step": 35500
|
| 507 |
+
},
|
| 508 |
+
{
|
| 509 |
+
"epoch": 6.775832862789384,
|
| 510 |
+
"grad_norm": 3.0844948291778564,
|
| 511 |
+
"learning_rate": 1.6120835686053078e-05,
|
| 512 |
+
"loss": 1.1005,
|
| 513 |
+
"step": 36000
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 6.869941652550348,
|
| 517 |
+
"grad_norm": 3.7161357402801514,
|
| 518 |
+
"learning_rate": 1.565029173724826e-05,
|
| 519 |
+
"loss": 1.0948,
|
| 520 |
+
"step": 36500
|
| 521 |
+
},
|
| 522 |
+
{
|
| 523 |
+
"epoch": 6.964050442311311,
|
| 524 |
+
"grad_norm": 3.217207193374634,
|
| 525 |
+
"learning_rate": 1.5179747788443441e-05,
|
| 526 |
+
"loss": 1.0877,
|
| 527 |
+
"step": 37000
|
| 528 |
+
},
|
| 529 |
+
{
|
| 530 |
+
"epoch": 7.058159232072276,
|
| 531 |
+
"grad_norm": 4.4285078048706055,
|
| 532 |
+
"learning_rate": 1.4709203839638622e-05,
|
| 533 |
+
"loss": 1.0559,
|
| 534 |
+
"step": 37500
|
| 535 |
+
},
|
| 536 |
+
{
|
| 537 |
+
"epoch": 7.1522680218332395,
|
| 538 |
+
"grad_norm": 3.0102875232696533,
|
| 539 |
+
"learning_rate": 1.4238659890833805e-05,
|
| 540 |
+
"loss": 1.0322,
|
| 541 |
+
"step": 38000
|
| 542 |
+
},
|
| 543 |
+
{
|
| 544 |
+
"epoch": 7.246376811594203,
|
| 545 |
+
"grad_norm": 3.4103572368621826,
|
| 546 |
+
"learning_rate": 1.3768115942028985e-05,
|
| 547 |
+
"loss": 1.0217,
|
| 548 |
+
"step": 38500
|
| 549 |
+
},
|
| 550 |
+
{
|
| 551 |
+
"epoch": 7.340485601355167,
|
| 552 |
+
"grad_norm": 3.9534976482391357,
|
| 553 |
+
"learning_rate": 1.3297571993224166e-05,
|
| 554 |
+
"loss": 1.0248,
|
| 555 |
+
"step": 39000
|
| 556 |
+
},
|
| 557 |
+
{
|
| 558 |
+
"epoch": 7.43459439111613,
|
| 559 |
+
"grad_norm": 5.0660719871521,
|
| 560 |
+
"learning_rate": 1.2827028044419347e-05,
|
| 561 |
+
"loss": 1.0233,
|
| 562 |
+
"step": 39500
|
| 563 |
+
},
|
| 564 |
+
{
|
| 565 |
+
"epoch": 7.528703180877094,
|
| 566 |
+
"grad_norm": 4.05812931060791,
|
| 567 |
+
"learning_rate": 1.235648409561453e-05,
|
| 568 |
+
"loss": 1.0254,
|
| 569 |
+
"step": 40000
|
| 570 |
+
},
|
| 571 |
+
{
|
| 572 |
+
"epoch": 7.6228119706380575,
|
| 573 |
+
"grad_norm": 2.9366817474365234,
|
| 574 |
+
"learning_rate": 1.1885940146809712e-05,
|
| 575 |
+
"loss": 1.0154,
|
| 576 |
+
"step": 40500
|
| 577 |
+
},
|
| 578 |
+
{
|
| 579 |
+
"epoch": 7.716920760399021,
|
| 580 |
+
"grad_norm": 3.6969943046569824,
|
| 581 |
+
"learning_rate": 1.1415396198004895e-05,
|
| 582 |
+
"loss": 1.0023,
|
| 583 |
+
"step": 41000
|
| 584 |
+
},
|
| 585 |
+
{
|
| 586 |
+
"epoch": 7.811029550159985,
|
| 587 |
+
"grad_norm": 3.294569969177246,
|
| 588 |
+
"learning_rate": 3.4377940899680034e-05,
|
| 589 |
+
"loss": 1.0861,
|
| 590 |
+
"step": 41500
|
| 591 |
+
},
|
| 592 |
+
{
|
| 593 |
+
"epoch": 7.905138339920948,
|
| 594 |
+
"grad_norm": 1.961162805557251,
|
| 595 |
+
"learning_rate": 3.418972332015811e-05,
|
| 596 |
+
"loss": 1.105,
|
| 597 |
+
"step": 42000
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"epoch": 7.999247129681912,
|
| 601 |
+
"grad_norm": 4.648848056793213,
|
| 602 |
+
"learning_rate": 3.400150574063617e-05,
|
| 603 |
+
"loss": 1.1171,
|
| 604 |
+
"step": 42500
|
| 605 |
+
},
|
| 606 |
+
{
|
| 607 |
+
"epoch": 8.093355919442876,
|
| 608 |
+
"grad_norm": 4.888842582702637,
|
| 609 |
+
"learning_rate": 3.381328816111425e-05,
|
| 610 |
+
"loss": 1.0555,
|
| 611 |
+
"step": 43000
|
| 612 |
+
},
|
| 613 |
+
{
|
| 614 |
+
"epoch": 8.187464709203839,
|
| 615 |
+
"grad_norm": 3.3256289958953857,
|
| 616 |
+
"learning_rate": 3.362507058159232e-05,
|
| 617 |
+
"loss": 1.059,
|
| 618 |
+
"step": 43500
|
| 619 |
+
},
|
| 620 |
+
{
|
| 621 |
+
"epoch": 8.281573498964804,
|
| 622 |
+
"grad_norm": 2.744330406188965,
|
| 623 |
+
"learning_rate": 3.3436853002070396e-05,
|
| 624 |
+
"loss": 1.0818,
|
| 625 |
+
"step": 44000
|
| 626 |
+
},
|
| 627 |
+
{
|
| 628 |
+
"epoch": 8.375682288725766,
|
| 629 |
+
"grad_norm": 2.7452945709228516,
|
| 630 |
+
"learning_rate": 3.3248635422548465e-05,
|
| 631 |
+
"loss": 1.0772,
|
| 632 |
+
"step": 44500
|
| 633 |
+
},
|
| 634 |
+
{
|
| 635 |
+
"epoch": 8.46979107848673,
|
| 636 |
+
"grad_norm": 2.993236780166626,
|
| 637 |
+
"learning_rate": 3.306041784302654e-05,
|
| 638 |
+
"loss": 1.0896,
|
| 639 |
+
"step": 45000
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 8.563899868247695,
|
| 643 |
+
"grad_norm": 4.128504276275635,
|
| 644 |
+
"learning_rate": 3.287220026350462e-05,
|
| 645 |
+
"loss": 1.0806,
|
| 646 |
+
"step": 45500
|
| 647 |
+
},
|
| 648 |
+
{
|
| 649 |
+
"epoch": 8.658008658008658,
|
| 650 |
+
"grad_norm": 3.3763933181762695,
|
| 651 |
+
"learning_rate": 3.268398268398268e-05,
|
| 652 |
+
"loss": 1.0713,
|
| 653 |
+
"step": 46000
|
| 654 |
+
},
|
| 655 |
+
{
|
| 656 |
+
"epoch": 8.752117447769622,
|
| 657 |
+
"grad_norm": 2.213223457336426,
|
| 658 |
+
"learning_rate": 3.249576510446076e-05,
|
| 659 |
+
"loss": 1.0698,
|
| 660 |
+
"step": 46500
|
| 661 |
+
},
|
| 662 |
+
{
|
| 663 |
+
"epoch": 8.846226237530585,
|
| 664 |
+
"grad_norm": 3.0853641033172607,
|
| 665 |
+
"learning_rate": 3.230754752493883e-05,
|
| 666 |
+
"loss": 1.0724,
|
| 667 |
+
"step": 47000
|
| 668 |
+
},
|
| 669 |
+
{
|
| 670 |
+
"epoch": 8.94033502729155,
|
| 671 |
+
"grad_norm": 3.031791925430298,
|
| 672 |
+
"learning_rate": 3.2119329945416903e-05,
|
| 673 |
+
"loss": 1.0672,
|
| 674 |
+
"step": 47500
|
| 675 |
+
},
|
| 676 |
+
{
|
| 677 |
+
"epoch": 9.034443817052512,
|
| 678 |
+
"grad_norm": 3.0765955448150635,
|
| 679 |
+
"learning_rate": 3.193111236589498e-05,
|
| 680 |
+
"loss": 1.0545,
|
| 681 |
+
"step": 48000
|
| 682 |
+
},
|
| 683 |
+
{
|
| 684 |
+
"epoch": 9.128552606813477,
|
| 685 |
+
"grad_norm": 4.204183101654053,
|
| 686 |
+
"learning_rate": 3.174289478637305e-05,
|
| 687 |
+
"loss": 1.0037,
|
| 688 |
+
"step": 48500
|
| 689 |
+
},
|
| 690 |
+
{
|
| 691 |
+
"epoch": 9.22266139657444,
|
| 692 |
+
"grad_norm": 5.794823169708252,
|
| 693 |
+
"learning_rate": 3.155467720685112e-05,
|
| 694 |
+
"loss": 1.0069,
|
| 695 |
+
"step": 49000
|
| 696 |
+
},
|
| 697 |
+
{
|
| 698 |
+
"epoch": 9.316770186335404,
|
| 699 |
+
"grad_norm": 3.246511459350586,
|
| 700 |
+
"learning_rate": 3.136645962732919e-05,
|
| 701 |
+
"loss": 1.0151,
|
| 702 |
+
"step": 49500
|
| 703 |
+
},
|
| 704 |
+
{
|
| 705 |
+
"epoch": 9.410878976096367,
|
| 706 |
+
"grad_norm": 2.7034826278686523,
|
| 707 |
+
"learning_rate": 3.1178242047807265e-05,
|
| 708 |
+
"loss": 1.0183,
|
| 709 |
+
"step": 50000
|
| 710 |
+
},
|
| 711 |
+
{
|
| 712 |
+
"epoch": 9.504987765857331,
|
| 713 |
+
"grad_norm": 2.402880907058716,
|
| 714 |
+
"learning_rate": 3.099002446828534e-05,
|
| 715 |
+
"loss": 1.0193,
|
| 716 |
+
"step": 50500
|
| 717 |
+
},
|
| 718 |
+
{
|
| 719 |
+
"epoch": 9.599096555618296,
|
| 720 |
+
"grad_norm": 5.0139336585998535,
|
| 721 |
+
"learning_rate": 3.080180688876341e-05,
|
| 722 |
+
"loss": 1.0145,
|
| 723 |
+
"step": 51000
|
| 724 |
+
},
|
| 725 |
+
{
|
| 726 |
+
"epoch": 9.693205345379258,
|
| 727 |
+
"grad_norm": 3.907541275024414,
|
| 728 |
+
"learning_rate": 3.061358930924149e-05,
|
| 729 |
+
"loss": 1.011,
|
| 730 |
+
"step": 51500
|
| 731 |
+
},
|
| 732 |
+
{
|
| 733 |
+
"epoch": 9.787314135140223,
|
| 734 |
+
"grad_norm": 4.411949157714844,
|
| 735 |
+
"learning_rate": 3.042537172971956e-05,
|
| 736 |
+
"loss": 1.0063,
|
| 737 |
+
"step": 52000
|
| 738 |
+
},
|
| 739 |
+
{
|
| 740 |
+
"epoch": 9.881422924901186,
|
| 741 |
+
"grad_norm": 4.035211563110352,
|
| 742 |
+
"learning_rate": 3.0237154150197627e-05,
|
| 743 |
+
"loss": 1.0149,
|
| 744 |
+
"step": 52500
|
| 745 |
+
},
|
| 746 |
+
{
|
| 747 |
+
"epoch": 9.97553171466215,
|
| 748 |
+
"grad_norm": 3.6050124168395996,
|
| 749 |
+
"learning_rate": 3.00489365706757e-05,
|
| 750 |
+
"loss": 1.0027,
|
| 751 |
+
"step": 53000
|
| 752 |
+
},
|
| 753 |
+
{
|
| 754 |
+
"epoch": 10.069640504423113,
|
| 755 |
+
"grad_norm": 3.40191388130188,
|
| 756 |
+
"learning_rate": 2.9860718991153773e-05,
|
| 757 |
+
"loss": 0.9468,
|
| 758 |
+
"step": 53500
|
| 759 |
+
},
|
| 760 |
+
{
|
| 761 |
+
"epoch": 10.163749294184077,
|
| 762 |
+
"grad_norm": 2.8000032901763916,
|
| 763 |
+
"learning_rate": 2.9672501411631846e-05,
|
| 764 |
+
"loss": 0.9248,
|
| 765 |
+
"step": 54000
|
| 766 |
+
},
|
| 767 |
+
{
|
| 768 |
+
"epoch": 10.25785808394504,
|
| 769 |
+
"grad_norm": 4.177460193634033,
|
| 770 |
+
"learning_rate": 2.9484283832109923e-05,
|
| 771 |
+
"loss": 0.9389,
|
| 772 |
+
"step": 54500
|
| 773 |
+
},
|
| 774 |
+
{
|
| 775 |
+
"epoch": 10.351966873706004,
|
| 776 |
+
"grad_norm": 3.88246750831604,
|
| 777 |
+
"learning_rate": 2.9296066252587996e-05,
|
| 778 |
+
"loss": 0.9326,
|
| 779 |
+
"step": 55000
|
| 780 |
+
},
|
| 781 |
+
{
|
| 782 |
+
"epoch": 10.446075663466967,
|
| 783 |
+
"grad_norm": 4.002796173095703,
|
| 784 |
+
"learning_rate": 2.910784867306607e-05,
|
| 785 |
+
"loss": 0.9378,
|
| 786 |
+
"step": 55500
|
| 787 |
+
},
|
| 788 |
+
{
|
| 789 |
+
"epoch": 10.540184453227932,
|
| 790 |
+
"grad_norm": 4.069864749908447,
|
| 791 |
+
"learning_rate": 2.8919631093544135e-05,
|
| 792 |
+
"loss": 0.9405,
|
| 793 |
+
"step": 56000
|
| 794 |
+
},
|
| 795 |
+
{
|
| 796 |
+
"epoch": 10.634293242988894,
|
| 797 |
+
"grad_norm": 3.493865966796875,
|
| 798 |
+
"learning_rate": 2.8731413514022208e-05,
|
| 799 |
+
"loss": 0.9347,
|
| 800 |
+
"step": 56500
|
| 801 |
+
},
|
| 802 |
+
{
|
| 803 |
+
"epoch": 10.728402032749859,
|
| 804 |
+
"grad_norm": 3.725019693374634,
|
| 805 |
+
"learning_rate": 2.8543195934500284e-05,
|
| 806 |
+
"loss": 0.9428,
|
| 807 |
+
"step": 57000
|
| 808 |
+
},
|
| 809 |
+
{
|
| 810 |
+
"epoch": 10.822510822510823,
|
| 811 |
+
"grad_norm": 3.557591438293457,
|
| 812 |
+
"learning_rate": 2.8354978354978357e-05,
|
| 813 |
+
"loss": 0.9397,
|
| 814 |
+
"step": 57500
|
| 815 |
+
},
|
| 816 |
+
{
|
| 817 |
+
"epoch": 10.916619612271786,
|
| 818 |
+
"grad_norm": 3.370312213897705,
|
| 819 |
+
"learning_rate": 2.816676077545643e-05,
|
| 820 |
+
"loss": 0.939,
|
| 821 |
+
"step": 58000
|
| 822 |
+
},
|
| 823 |
+
{
|
| 824 |
+
"epoch": 11.01072840203275,
|
| 825 |
+
"grad_norm": 2.937887191772461,
|
| 826 |
+
"learning_rate": 2.7978543195934503e-05,
|
| 827 |
+
"loss": 0.9225,
|
| 828 |
+
"step": 58500
|
| 829 |
+
},
|
| 830 |
+
{
|
| 831 |
+
"epoch": 11.104837191793713,
|
| 832 |
+
"grad_norm": 2.403350353240967,
|
| 833 |
+
"learning_rate": 2.7790325616412576e-05,
|
| 834 |
+
"loss": 0.827,
|
| 835 |
+
"step": 59000
|
| 836 |
+
},
|
| 837 |
+
{
|
| 838 |
+
"epoch": 11.198945981554678,
|
| 839 |
+
"grad_norm": 2.4876935482025146,
|
| 840 |
+
"learning_rate": 2.7602108036890646e-05,
|
| 841 |
+
"loss": 0.8461,
|
| 842 |
+
"step": 59500
|
| 843 |
+
},
|
| 844 |
+
{
|
| 845 |
+
"epoch": 11.29305477131564,
|
| 846 |
+
"grad_norm": 3.663511276245117,
|
| 847 |
+
"learning_rate": 2.741389045736872e-05,
|
| 848 |
+
"loss": 0.8434,
|
| 849 |
+
"step": 60000
|
| 850 |
+
},
|
| 851 |
+
{
|
| 852 |
+
"epoch": 11.387163561076605,
|
| 853 |
+
"grad_norm": 4.3568806648254395,
|
| 854 |
+
"learning_rate": 2.7225672877846792e-05,
|
| 855 |
+
"loss": 0.8496,
|
| 856 |
+
"step": 60500
|
| 857 |
+
},
|
| 858 |
+
{
|
| 859 |
+
"epoch": 11.481272350837568,
|
| 860 |
+
"grad_norm": 3.4234845638275146,
|
| 861 |
+
"learning_rate": 2.7037455298324865e-05,
|
| 862 |
+
"loss": 0.8549,
|
| 863 |
+
"step": 61000
|
| 864 |
+
},
|
| 865 |
+
{
|
| 866 |
+
"epoch": 11.575381140598532,
|
| 867 |
+
"grad_norm": 2.537666082382202,
|
| 868 |
+
"learning_rate": 2.6849237718802938e-05,
|
| 869 |
+
"loss": 0.8548,
|
| 870 |
+
"step": 61500
|
| 871 |
+
},
|
| 872 |
+
{
|
| 873 |
+
"epoch": 11.669489930359495,
|
| 874 |
+
"grad_norm": 3.7678942680358887,
|
| 875 |
+
"learning_rate": 2.666102013928101e-05,
|
| 876 |
+
"loss": 0.8501,
|
| 877 |
+
"step": 62000
|
| 878 |
+
},
|
| 879 |
+
{
|
| 880 |
+
"epoch": 11.76359872012046,
|
| 881 |
+
"grad_norm": 3.4384429454803467,
|
| 882 |
+
"learning_rate": 2.647280255975908e-05,
|
| 883 |
+
"loss": 0.8546,
|
| 884 |
+
"step": 62500
|
| 885 |
+
},
|
| 886 |
+
{
|
| 887 |
+
"epoch": 11.857707509881424,
|
| 888 |
+
"grad_norm": 2.883970022201538,
|
| 889 |
+
"learning_rate": 2.6284584980237154e-05,
|
| 890 |
+
"loss": 0.8494,
|
| 891 |
+
"step": 63000
|
| 892 |
+
},
|
| 893 |
+
{
|
| 894 |
+
"epoch": 11.951816299642386,
|
| 895 |
+
"grad_norm": 3.2041871547698975,
|
| 896 |
+
"learning_rate": 2.6096367400715227e-05,
|
| 897 |
+
"loss": 0.8473,
|
| 898 |
+
"step": 63500
|
| 899 |
+
},
|
| 900 |
+
{
|
| 901 |
+
"epoch": 12.045925089403351,
|
| 902 |
+
"grad_norm": 3.7006897926330566,
|
| 903 |
+
"learning_rate": 2.59081498211933e-05,
|
| 904 |
+
"loss": 0.7851,
|
| 905 |
+
"step": 64000
|
| 906 |
+
},
|
| 907 |
+
{
|
| 908 |
+
"epoch": 12.140033879164314,
|
| 909 |
+
"grad_norm": 3.4774985313415527,
|
| 910 |
+
"learning_rate": 2.5719932241671373e-05,
|
| 911 |
+
"loss": 0.7241,
|
| 912 |
+
"step": 64500
|
| 913 |
+
},
|
| 914 |
+
{
|
| 915 |
+
"epoch": 12.234142668925278,
|
| 916 |
+
"grad_norm": 3.615403413772583,
|
| 917 |
+
"learning_rate": 2.5531714662149446e-05,
|
| 918 |
+
"loss": 0.7296,
|
| 919 |
+
"step": 65000
|
| 920 |
+
},
|
| 921 |
+
{
|
| 922 |
+
"epoch": 12.32825145868624,
|
| 923 |
+
"grad_norm": 4.831261157989502,
|
| 924 |
+
"learning_rate": 2.534349708262752e-05,
|
| 925 |
+
"loss": 0.7382,
|
| 926 |
+
"step": 65500
|
| 927 |
+
},
|
| 928 |
+
{
|
| 929 |
+
"epoch": 12.422360248447205,
|
| 930 |
+
"grad_norm": 3.072159767150879,
|
| 931 |
+
"learning_rate": 2.515527950310559e-05,
|
| 932 |
+
"loss": 0.733,
|
| 933 |
+
"step": 66000
|
| 934 |
+
},
|
| 935 |
+
{
|
| 936 |
+
"epoch": 12.516469038208168,
|
| 937 |
+
"grad_norm": 3.442324161529541,
|
| 938 |
+
"learning_rate": 2.4967061923583665e-05,
|
| 939 |
+
"loss": 0.7453,
|
| 940 |
+
"step": 66500
|
| 941 |
+
},
|
| 942 |
+
{
|
| 943 |
+
"epoch": 12.610577827969133,
|
| 944 |
+
"grad_norm": 2.71148419380188,
|
| 945 |
+
"learning_rate": 2.4778844344061735e-05,
|
| 946 |
+
"loss": 0.7388,
|
| 947 |
+
"step": 67000
|
| 948 |
+
},
|
| 949 |
+
{
|
| 950 |
+
"epoch": 12.704686617730095,
|
| 951 |
+
"grad_norm": 3.6085212230682373,
|
| 952 |
+
"learning_rate": 2.4590626764539808e-05,
|
| 953 |
+
"loss": 0.7444,
|
| 954 |
+
"step": 67500
|
| 955 |
+
},
|
| 956 |
+
{
|
| 957 |
+
"epoch": 12.79879540749106,
|
| 958 |
+
"grad_norm": 3.9403274059295654,
|
| 959 |
+
"learning_rate": 2.440240918501788e-05,
|
| 960 |
+
"loss": 0.7291,
|
| 961 |
+
"step": 68000
|
| 962 |
+
},
|
| 963 |
+
{
|
| 964 |
+
"epoch": 12.892904197252022,
|
| 965 |
+
"grad_norm": 3.322840929031372,
|
| 966 |
+
"learning_rate": 2.4214191605495954e-05,
|
| 967 |
+
"loss": 0.7523,
|
| 968 |
+
"step": 68500
|
| 969 |
+
},
|
| 970 |
+
{
|
| 971 |
+
"epoch": 12.987012987012987,
|
| 972 |
+
"grad_norm": 4.849690914154053,
|
| 973 |
+
"learning_rate": 2.4025974025974027e-05,
|
| 974 |
+
"loss": 0.7477,
|
| 975 |
+
"step": 69000
|
| 976 |
+
},
|
| 977 |
+
{
|
| 978 |
+
"epoch": 13.081121776773951,
|
| 979 |
+
"grad_norm": 4.5327959060668945,
|
| 980 |
+
"learning_rate": 2.38377564464521e-05,
|
| 981 |
+
"loss": 0.5957,
|
| 982 |
+
"step": 69500
|
| 983 |
+
},
|
| 984 |
+
{
|
| 985 |
+
"epoch": 13.175230566534914,
|
| 986 |
+
"grad_norm": 2.9526569843292236,
|
| 987 |
+
"learning_rate": 2.3649538866930173e-05,
|
| 988 |
+
"loss": 0.5829,
|
| 989 |
+
"step": 70000
|
| 990 |
+
},
|
| 991 |
+
{
|
| 992 |
+
"epoch": 13.269339356295879,
|
| 993 |
+
"grad_norm": 2.7245306968688965,
|
| 994 |
+
"learning_rate": 2.3461321287408243e-05,
|
| 995 |
+
"loss": 0.5948,
|
| 996 |
+
"step": 70500
|
| 997 |
+
},
|
| 998 |
+
{
|
| 999 |
+
"epoch": 13.363448146056841,
|
| 1000 |
+
"grad_norm": 3.7524588108062744,
|
| 1001 |
+
"learning_rate": 2.327310370788632e-05,
|
| 1002 |
+
"loss": 0.5956,
|
| 1003 |
+
"step": 71000
|
| 1004 |
+
},
|
| 1005 |
+
{
|
| 1006 |
+
"epoch": 13.457556935817806,
|
| 1007 |
+
"grad_norm": 4.387008190155029,
|
| 1008 |
+
"learning_rate": 2.3084886128364392e-05,
|
| 1009 |
+
"loss": 0.605,
|
| 1010 |
+
"step": 71500
|
| 1011 |
+
},
|
| 1012 |
+
{
|
| 1013 |
+
"epoch": 13.551665725578768,
|
| 1014 |
+
"grad_norm": 3.449723482131958,
|
| 1015 |
+
"learning_rate": 2.2896668548842462e-05,
|
| 1016 |
+
"loss": 0.6087,
|
| 1017 |
+
"step": 72000
|
| 1018 |
+
},
|
| 1019 |
+
{
|
| 1020 |
+
"epoch": 13.645774515339733,
|
| 1021 |
+
"grad_norm": 3.2176854610443115,
|
| 1022 |
+
"learning_rate": 2.2708450969320535e-05,
|
| 1023 |
+
"loss": 0.6141,
|
| 1024 |
+
"step": 72500
|
| 1025 |
+
},
|
| 1026 |
+
{
|
| 1027 |
+
"epoch": 13.739883305100696,
|
| 1028 |
+
"grad_norm": 4.136612415313721,
|
| 1029 |
+
"learning_rate": 2.2520233389798608e-05,
|
| 1030 |
+
"loss": 0.6251,
|
| 1031 |
+
"step": 73000
|
| 1032 |
+
},
|
| 1033 |
+
{
|
| 1034 |
+
"epoch": 13.83399209486166,
|
| 1035 |
+
"grad_norm": 4.145909786224365,
|
| 1036 |
+
"learning_rate": 2.233201581027668e-05,
|
| 1037 |
+
"loss": 0.6094,
|
| 1038 |
+
"step": 73500
|
| 1039 |
+
},
|
| 1040 |
+
{
|
| 1041 |
+
"epoch": 13.928100884622623,
|
| 1042 |
+
"grad_norm": 3.8660261631011963,
|
| 1043 |
+
"learning_rate": 2.2143798230754754e-05,
|
| 1044 |
+
"loss": 0.6194,
|
| 1045 |
+
"step": 74000
|
| 1046 |
+
},
|
| 1047 |
+
{
|
| 1048 |
+
"epoch": 14.022209674383587,
|
| 1049 |
+
"grad_norm": 3.511117696762085,
|
| 1050 |
+
"learning_rate": 2.1955580651232827e-05,
|
| 1051 |
+
"loss": 0.5712,
|
| 1052 |
+
"step": 74500
|
| 1053 |
+
},
|
| 1054 |
+
{
|
| 1055 |
+
"epoch": 14.116318464144552,
|
| 1056 |
+
"grad_norm": 2.771902084350586,
|
| 1057 |
+
"learning_rate": 2.17673630717109e-05,
|
| 1058 |
+
"loss": 0.4559,
|
| 1059 |
+
"step": 75000
|
| 1060 |
+
},
|
| 1061 |
+
{
|
| 1062 |
+
"epoch": 14.210427253905515,
|
| 1063 |
+
"grad_norm": 5.087037086486816,
|
| 1064 |
+
"learning_rate": 2.157914549218897e-05,
|
| 1065 |
+
"loss": 0.4529,
|
| 1066 |
+
"step": 75500
|
| 1067 |
+
},
|
| 1068 |
+
{
|
| 1069 |
+
"epoch": 14.304536043666479,
|
| 1070 |
+
"grad_norm": 4.842881679534912,
|
| 1071 |
+
"learning_rate": 2.1390927912667043e-05,
|
| 1072 |
+
"loss": 0.4567,
|
| 1073 |
+
"step": 76000
|
| 1074 |
+
},
|
| 1075 |
+
{
|
| 1076 |
+
"epoch": 14.398644833427442,
|
| 1077 |
+
"grad_norm": 3.444424629211426,
|
| 1078 |
+
"learning_rate": 2.120271033314512e-05,
|
| 1079 |
+
"loss": 0.4618,
|
| 1080 |
+
"step": 76500
|
| 1081 |
+
},
|
| 1082 |
+
{
|
| 1083 |
+
"epoch": 14.492753623188406,
|
| 1084 |
+
"grad_norm": 3.934549331665039,
|
| 1085 |
+
"learning_rate": 2.101449275362319e-05,
|
| 1086 |
+
"loss": 0.455,
|
| 1087 |
+
"step": 77000
|
| 1088 |
+
},
|
| 1089 |
+
{
|
| 1090 |
+
"epoch": 14.586862412949369,
|
| 1091 |
+
"grad_norm": 4.338078498840332,
|
| 1092 |
+
"learning_rate": 2.0826275174101262e-05,
|
| 1093 |
+
"loss": 0.472,
|
| 1094 |
+
"step": 77500
|
| 1095 |
+
},
|
| 1096 |
+
{
|
| 1097 |
+
"epoch": 14.680971202710333,
|
| 1098 |
+
"grad_norm": 3.781182050704956,
|
| 1099 |
+
"learning_rate": 2.0638057594579335e-05,
|
| 1100 |
+
"loss": 0.4613,
|
| 1101 |
+
"step": 78000
|
| 1102 |
+
},
|
| 1103 |
+
{
|
| 1104 |
+
"epoch": 14.775079992471296,
|
| 1105 |
+
"grad_norm": 3.866917371749878,
|
| 1106 |
+
"learning_rate": 2.0449840015057405e-05,
|
| 1107 |
+
"loss": 0.4791,
|
| 1108 |
+
"step": 78500
|
| 1109 |
+
},
|
| 1110 |
+
{
|
| 1111 |
+
"epoch": 14.86918878223226,
|
| 1112 |
+
"grad_norm": 3.5265841484069824,
|
| 1113 |
+
"learning_rate": 2.026162243553548e-05,
|
| 1114 |
+
"loss": 0.4709,
|
| 1115 |
+
"step": 79000
|
| 1116 |
+
},
|
| 1117 |
+
{
|
| 1118 |
+
"epoch": 14.963297571993223,
|
| 1119 |
+
"grad_norm": 3.3175408840179443,
|
| 1120 |
+
"learning_rate": 2.0073404856013554e-05,
|
| 1121 |
+
"loss": 0.4847,
|
| 1122 |
+
"step": 79500
|
| 1123 |
+
},
|
| 1124 |
+
{
|
| 1125 |
+
"epoch": 15.057406361754188,
|
| 1126 |
+
"grad_norm": 2.848555564880371,
|
| 1127 |
+
"learning_rate": 1.9885187276491627e-05,
|
| 1128 |
+
"loss": 0.3788,
|
| 1129 |
+
"step": 80000
|
| 1130 |
+
},
|
| 1131 |
+
{
|
| 1132 |
+
"epoch": 15.151515151515152,
|
| 1133 |
+
"grad_norm": 3.355653762817383,
|
| 1134 |
+
"learning_rate": 1.9696969696969697e-05,
|
| 1135 |
+
"loss": 0.3235,
|
| 1136 |
+
"step": 80500
|
| 1137 |
+
},
|
| 1138 |
+
{
|
| 1139 |
+
"epoch": 15.245623941276115,
|
| 1140 |
+
"grad_norm": 3.260960817337036,
|
| 1141 |
+
"learning_rate": 1.950875211744777e-05,
|
| 1142 |
+
"loss": 0.3162,
|
| 1143 |
+
"step": 81000
|
| 1144 |
+
},
|
| 1145 |
+
{
|
| 1146 |
+
"epoch": 15.33973273103708,
|
| 1147 |
+
"grad_norm": 3.9132673740386963,
|
| 1148 |
+
"learning_rate": 1.9320534537925843e-05,
|
| 1149 |
+
"loss": 0.3209,
|
| 1150 |
+
"step": 81500
|
| 1151 |
+
},
|
| 1152 |
+
{
|
| 1153 |
+
"epoch": 15.433841520798042,
|
| 1154 |
+
"grad_norm": 4.693389892578125,
|
| 1155 |
+
"learning_rate": 1.9132316958403916e-05,
|
| 1156 |
+
"loss": 0.3421,
|
| 1157 |
+
"step": 82000
|
| 1158 |
+
},
|
| 1159 |
+
{
|
| 1160 |
+
"epoch": 15.527950310559007,
|
| 1161 |
+
"grad_norm": 3.7237417697906494,
|
| 1162 |
+
"learning_rate": 1.894409937888199e-05,
|
| 1163 |
+
"loss": 0.3441,
|
| 1164 |
+
"step": 82500
|
| 1165 |
+
},
|
| 1166 |
+
{
|
| 1167 |
+
"epoch": 15.62205910031997,
|
| 1168 |
+
"grad_norm": 3.9301464557647705,
|
| 1169 |
+
"learning_rate": 1.8755881799360062e-05,
|
| 1170 |
+
"loss": 0.3424,
|
| 1171 |
+
"step": 83000
|
| 1172 |
+
},
|
| 1173 |
+
{
|
| 1174 |
+
"epoch": 15.716167890080934,
|
| 1175 |
+
"grad_norm": 4.186377048492432,
|
| 1176 |
+
"learning_rate": 1.8567664219838135e-05,
|
| 1177 |
+
"loss": 0.3503,
|
| 1178 |
+
"step": 83500
|
| 1179 |
+
},
|
| 1180 |
+
{
|
| 1181 |
+
"epoch": 15.810276679841897,
|
| 1182 |
+
"grad_norm": 3.6368534564971924,
|
| 1183 |
+
"learning_rate": 1.8379446640316205e-05,
|
| 1184 |
+
"loss": 0.3347,
|
| 1185 |
+
"step": 84000
|
| 1186 |
+
},
|
| 1187 |
+
{
|
| 1188 |
+
"epoch": 15.904385469602861,
|
| 1189 |
+
"grad_norm": 2.6787190437316895,
|
| 1190 |
+
"learning_rate": 1.8191229060794278e-05,
|
| 1191 |
+
"loss": 0.3445,
|
| 1192 |
+
"step": 84500
|
| 1193 |
+
},
|
| 1194 |
+
{
|
| 1195 |
+
"epoch": 15.998494259363824,
|
| 1196 |
+
"grad_norm": 3.942444324493408,
|
| 1197 |
+
"learning_rate": 1.8003011481272354e-05,
|
| 1198 |
+
"loss": 0.343,
|
| 1199 |
+
"step": 85000
|
| 1200 |
+
},
|
| 1201 |
+
{
|
| 1202 |
+
"epoch": 16.09260304912479,
|
| 1203 |
+
"grad_norm": 3.3087995052337646,
|
| 1204 |
+
"learning_rate": 1.7814793901750424e-05,
|
| 1205 |
+
"loss": 0.2093,
|
| 1206 |
+
"step": 85500
|
| 1207 |
+
},
|
| 1208 |
+
{
|
| 1209 |
+
"epoch": 16.186711838885753,
|
| 1210 |
+
"grad_norm": 4.419996738433838,
|
| 1211 |
+
"learning_rate": 1.7626576322228497e-05,
|
| 1212 |
+
"loss": 0.2209,
|
| 1213 |
+
"step": 86000
|
| 1214 |
+
},
|
| 1215 |
+
{
|
| 1216 |
+
"epoch": 16.280820628646715,
|
| 1217 |
+
"grad_norm": 4.352416515350342,
|
| 1218 |
+
"learning_rate": 1.743835874270657e-05,
|
| 1219 |
+
"loss": 0.2282,
|
| 1220 |
+
"step": 86500
|
| 1221 |
+
},
|
| 1222 |
+
{
|
| 1223 |
+
"epoch": 16.374929418407678,
|
| 1224 |
+
"grad_norm": 3.7437074184417725,
|
| 1225 |
+
"learning_rate": 1.725014116318464e-05,
|
| 1226 |
+
"loss": 0.232,
|
| 1227 |
+
"step": 87000
|
| 1228 |
+
},
|
| 1229 |
+
{
|
| 1230 |
+
"epoch": 16.469038208168644,
|
| 1231 |
+
"grad_norm": 6.4077534675598145,
|
| 1232 |
+
"learning_rate": 1.7061923583662716e-05,
|
| 1233 |
+
"loss": 0.2291,
|
| 1234 |
+
"step": 87500
|
| 1235 |
+
},
|
| 1236 |
+
{
|
| 1237 |
+
"epoch": 16.563146997929607,
|
| 1238 |
+
"grad_norm": 3.0419087409973145,
|
| 1239 |
+
"learning_rate": 1.687370600414079e-05,
|
| 1240 |
+
"loss": 0.2401,
|
| 1241 |
+
"step": 88000
|
| 1242 |
+
},
|
| 1243 |
+
{
|
| 1244 |
+
"epoch": 16.65725578769057,
|
| 1245 |
+
"grad_norm": 4.095304012298584,
|
| 1246 |
+
"learning_rate": 1.6685488424618862e-05,
|
| 1247 |
+
"loss": 0.233,
|
| 1248 |
+
"step": 88500
|
| 1249 |
+
},
|
| 1250 |
+
{
|
| 1251 |
+
"epoch": 16.751364577451533,
|
| 1252 |
+
"grad_norm": 3.372295618057251,
|
| 1253 |
+
"learning_rate": 1.649727084509693e-05,
|
| 1254 |
+
"loss": 0.2354,
|
| 1255 |
+
"step": 89000
|
| 1256 |
+
},
|
| 1257 |
+
{
|
| 1258 |
+
"epoch": 16.8454733672125,
|
| 1259 |
+
"grad_norm": 2.918405771255493,
|
| 1260 |
+
"learning_rate": 1.6309053265575005e-05,
|
| 1261 |
+
"loss": 0.2421,
|
| 1262 |
+
"step": 89500
|
| 1263 |
+
},
|
| 1264 |
+
{
|
| 1265 |
+
"epoch": 16.93958215697346,
|
| 1266 |
+
"grad_norm": 2.4548110961914062,
|
| 1267 |
+
"learning_rate": 1.6120835686053078e-05,
|
| 1268 |
+
"loss": 0.2374,
|
| 1269 |
+
"step": 90000
|
| 1270 |
+
},
|
| 1271 |
+
{
|
| 1272 |
+
"epoch": 17.033690946734424,
|
| 1273 |
+
"grad_norm": 4.15058708190918,
|
| 1274 |
+
"learning_rate": 1.593261810653115e-05,
|
| 1275 |
+
"loss": 0.2135,
|
| 1276 |
+
"step": 90500
|
| 1277 |
+
},
|
| 1278 |
+
{
|
| 1279 |
+
"epoch": 17.12779973649539,
|
| 1280 |
+
"grad_norm": 2.979170083999634,
|
| 1281 |
+
"learning_rate": 1.5744400527009224e-05,
|
| 1282 |
+
"loss": 0.1495,
|
| 1283 |
+
"step": 91000
|
| 1284 |
+
},
|
| 1285 |
+
{
|
| 1286 |
+
"epoch": 17.221908526256353,
|
| 1287 |
+
"grad_norm": 3.950493574142456,
|
| 1288 |
+
"learning_rate": 1.5556182947487297e-05,
|
| 1289 |
+
"loss": 0.1503,
|
| 1290 |
+
"step": 91500
|
| 1291 |
+
},
|
| 1292 |
+
{
|
| 1293 |
+
"epoch": 17.316017316017316,
|
| 1294 |
+
"grad_norm": 3.174896001815796,
|
| 1295 |
+
"learning_rate": 1.5367965367965366e-05,
|
| 1296 |
+
"loss": 0.1559,
|
| 1297 |
+
"step": 92000
|
| 1298 |
+
},
|
| 1299 |
+
{
|
| 1300 |
+
"epoch": 17.41012610577828,
|
| 1301 |
+
"grad_norm": 3.4672741889953613,
|
| 1302 |
+
"learning_rate": 1.5179747788443441e-05,
|
| 1303 |
+
"loss": 0.1606,
|
| 1304 |
+
"step": 92500
|
| 1305 |
+
},
|
| 1306 |
+
{
|
| 1307 |
+
"epoch": 17.504234895539245,
|
| 1308 |
+
"grad_norm": 3.950160026550293,
|
| 1309 |
+
"learning_rate": 1.4991530208921514e-05,
|
| 1310 |
+
"loss": 0.1561,
|
| 1311 |
+
"step": 93000
|
| 1312 |
+
},
|
| 1313 |
+
{
|
| 1314 |
+
"epoch": 17.598343685300208,
|
| 1315 |
+
"grad_norm": 3.546109199523926,
|
| 1316 |
+
"learning_rate": 1.4803312629399587e-05,
|
| 1317 |
+
"loss": 0.1622,
|
| 1318 |
+
"step": 93500
|
| 1319 |
+
},
|
| 1320 |
+
{
|
| 1321 |
+
"epoch": 17.69245247506117,
|
| 1322 |
+
"grad_norm": 6.592913627624512,
|
| 1323 |
+
"learning_rate": 1.4615095049877658e-05,
|
| 1324 |
+
"loss": 0.1644,
|
| 1325 |
+
"step": 94000
|
| 1326 |
+
},
|
| 1327 |
+
{
|
| 1328 |
+
"epoch": 17.786561264822133,
|
| 1329 |
+
"grad_norm": 2.762545347213745,
|
| 1330 |
+
"learning_rate": 1.4426877470355732e-05,
|
| 1331 |
+
"loss": 0.1614,
|
| 1332 |
+
"step": 94500
|
| 1333 |
+
},
|
| 1334 |
+
{
|
| 1335 |
+
"epoch": 17.8806700545831,
|
| 1336 |
+
"grad_norm": 2.9720265865325928,
|
| 1337 |
+
"learning_rate": 1.4238659890833805e-05,
|
| 1338 |
+
"loss": 0.1577,
|
| 1339 |
+
"step": 95000
|
| 1340 |
+
},
|
| 1341 |
+
{
|
| 1342 |
+
"epoch": 17.974778844344062,
|
| 1343 |
+
"grad_norm": 3.006880283355713,
|
| 1344 |
+
"learning_rate": 1.4050442311311876e-05,
|
| 1345 |
+
"loss": 0.1577,
|
| 1346 |
+
"step": 95500
|
| 1347 |
+
},
|
| 1348 |
+
{
|
| 1349 |
+
"epoch": 18.068887634105025,
|
| 1350 |
+
"grad_norm": 2.86936616897583,
|
| 1351 |
+
"learning_rate": 1.3862224731789949e-05,
|
| 1352 |
+
"loss": 0.1162,
|
| 1353 |
+
"step": 96000
|
| 1354 |
+
},
|
| 1355 |
+
{
|
| 1356 |
+
"epoch": 18.162996423865987,
|
| 1357 |
+
"grad_norm": 3.608914852142334,
|
| 1358 |
+
"learning_rate": 1.3674007152268024e-05,
|
| 1359 |
+
"loss": 0.1001,
|
| 1360 |
+
"step": 96500
|
| 1361 |
+
},
|
| 1362 |
+
{
|
| 1363 |
+
"epoch": 18.257105213626954,
|
| 1364 |
+
"grad_norm": 3.126116991043091,
|
| 1365 |
+
"learning_rate": 1.3485789572746097e-05,
|
| 1366 |
+
"loss": 0.1082,
|
| 1367 |
+
"step": 97000
|
| 1368 |
+
},
|
| 1369 |
+
{
|
| 1370 |
+
"epoch": 18.351214003387916,
|
| 1371 |
+
"grad_norm": 2.9935250282287598,
|
| 1372 |
+
"learning_rate": 1.3297571993224166e-05,
|
| 1373 |
+
"loss": 0.109,
|
| 1374 |
+
"step": 97500
|
| 1375 |
+
},
|
| 1376 |
+
{
|
| 1377 |
+
"epoch": 18.44532279314888,
|
| 1378 |
+
"grad_norm": 1.9776825904846191,
|
| 1379 |
+
"learning_rate": 1.3109354413702241e-05,
|
| 1380 |
+
"loss": 0.1031,
|
| 1381 |
+
"step": 98000
|
| 1382 |
+
},
|
| 1383 |
+
{
|
| 1384 |
+
"epoch": 18.539431582909845,
|
| 1385 |
+
"grad_norm": 4.182958602905273,
|
| 1386 |
+
"learning_rate": 1.2921136834180314e-05,
|
| 1387 |
+
"loss": 0.1084,
|
| 1388 |
+
"step": 98500
|
| 1389 |
+
},
|
| 1390 |
+
{
|
| 1391 |
+
"epoch": 18.633540372670808,
|
| 1392 |
+
"grad_norm": 3.405510902404785,
|
| 1393 |
+
"learning_rate": 1.2732919254658385e-05,
|
| 1394 |
+
"loss": 0.1069,
|
| 1395 |
+
"step": 99000
|
| 1396 |
+
},
|
| 1397 |
+
{
|
| 1398 |
+
"epoch": 18.72764916243177,
|
| 1399 |
+
"grad_norm": 2.7036936283111572,
|
| 1400 |
+
"learning_rate": 1.2544701675136458e-05,
|
| 1401 |
+
"loss": 0.1084,
|
| 1402 |
+
"step": 99500
|
| 1403 |
+
},
|
| 1404 |
+
{
|
| 1405 |
+
"epoch": 18.821757952192733,
|
| 1406 |
+
"grad_norm": 2.601555347442627,
|
| 1407 |
+
"learning_rate": 1.235648409561453e-05,
|
| 1408 |
+
"loss": 0.1097,
|
| 1409 |
+
"step": 100000
|
| 1410 |
+
},
|
| 1411 |
+
{
|
| 1412 |
+
"epoch": 18.9158667419537,
|
| 1413 |
+
"grad_norm": 2.9937756061553955,
|
| 1414 |
+
"learning_rate": 1.2168266516092605e-05,
|
| 1415 |
+
"loss": 0.1004,
|
| 1416 |
+
"step": 100500
|
| 1417 |
+
},
|
| 1418 |
+
{
|
| 1419 |
+
"epoch": 19.009975531714662,
|
| 1420 |
+
"grad_norm": 1.493790864944458,
|
| 1421 |
+
"learning_rate": 1.1980048936570676e-05,
|
| 1422 |
+
"loss": 0.1032,
|
| 1423 |
+
"step": 101000
|
| 1424 |
+
},
|
| 1425 |
+
{
|
| 1426 |
+
"epoch": 19.104084321475625,
|
| 1427 |
+
"grad_norm": 1.7063292264938354,
|
| 1428 |
+
"learning_rate": 1.1791831357048749e-05,
|
| 1429 |
+
"loss": 0.0667,
|
| 1430 |
+
"step": 101500
|
| 1431 |
+
},
|
| 1432 |
+
{
|
| 1433 |
+
"epoch": 19.198193111236588,
|
| 1434 |
+
"grad_norm": 2.8355624675750732,
|
| 1435 |
+
"learning_rate": 1.1603613777526822e-05,
|
| 1436 |
+
"loss": 0.0678,
|
| 1437 |
+
"step": 102000
|
| 1438 |
+
},
|
| 1439 |
+
{
|
| 1440 |
+
"epoch": 19.292301900997554,
|
| 1441 |
+
"grad_norm": 1.7610359191894531,
|
| 1442 |
+
"learning_rate": 1.1415396198004895e-05,
|
| 1443 |
+
"loss": 0.0654,
|
| 1444 |
+
"step": 102500
|
| 1445 |
+
},
|
| 1446 |
+
{
|
| 1447 |
+
"epoch": 19.386410690758517,
|
| 1448 |
+
"grad_norm": 2.759197950363159,
|
| 1449 |
+
"learning_rate": 1.1227178618482966e-05,
|
| 1450 |
+
"loss": 0.0717,
|
| 1451 |
+
"step": 103000
|
| 1452 |
+
},
|
| 1453 |
+
{
|
| 1454 |
+
"epoch": 19.48051948051948,
|
| 1455 |
+
"grad_norm": 2.657435417175293,
|
| 1456 |
+
"learning_rate": 1.103896103896104e-05,
|
| 1457 |
+
"loss": 0.0722,
|
| 1458 |
+
"step": 103500
|
| 1459 |
+
},
|
| 1460 |
+
{
|
| 1461 |
+
"epoch": 19.574628270280446,
|
| 1462 |
+
"grad_norm": 2.5865299701690674,
|
| 1463 |
+
"learning_rate": 1.0850743459439112e-05,
|
| 1464 |
+
"loss": 0.0689,
|
| 1465 |
+
"step": 104000
|
| 1466 |
+
},
|
| 1467 |
+
{
|
| 1468 |
+
"epoch": 19.66873706004141,
|
| 1469 |
+
"grad_norm": 4.484961986541748,
|
| 1470 |
+
"learning_rate": 1.0662525879917184e-05,
|
| 1471 |
+
"loss": 0.0706,
|
| 1472 |
+
"step": 104500
|
| 1473 |
+
},
|
| 1474 |
+
{
|
| 1475 |
+
"epoch": 19.76284584980237,
|
| 1476 |
+
"grad_norm": 2.431190252304077,
|
| 1477 |
+
"learning_rate": 1.0474308300395258e-05,
|
| 1478 |
+
"loss": 0.0691,
|
| 1479 |
+
"step": 105000
|
| 1480 |
+
},
|
| 1481 |
+
{
|
| 1482 |
+
"epoch": 19.856954639563334,
|
| 1483 |
+
"grad_norm": 2.6577088832855225,
|
| 1484 |
+
"learning_rate": 1.028609072087333e-05,
|
| 1485 |
+
"loss": 0.0704,
|
| 1486 |
+
"step": 105500
|
| 1487 |
+
},
|
| 1488 |
+
{
|
| 1489 |
+
"epoch": 19.9510634293243,
|
| 1490 |
+
"grad_norm": 3.1382012367248535,
|
| 1491 |
+
"learning_rate": 1.0097873141351403e-05,
|
| 1492 |
+
"loss": 0.0673,
|
| 1493 |
+
"step": 106000
|
| 1494 |
+
},
|
| 1495 |
+
{
|
| 1496 |
+
"epoch": 20.045172219085263,
|
| 1497 |
+
"grad_norm": 1.5920716524124146,
|
| 1498 |
+
"learning_rate": 9.909655561829476e-06,
|
| 1499 |
+
"loss": 0.0605,
|
| 1500 |
+
"step": 106500
|
| 1501 |
+
},
|
| 1502 |
+
{
|
| 1503 |
+
"epoch": 20.139281008846226,
|
| 1504 |
+
"grad_norm": 0.49824026226997375,
|
| 1505 |
+
"learning_rate": 9.721437982307547e-06,
|
| 1506 |
+
"loss": 0.0427,
|
| 1507 |
+
"step": 107000
|
| 1508 |
+
},
|
| 1509 |
+
{
|
| 1510 |
+
"epoch": 20.23338979860719,
|
| 1511 |
+
"grad_norm": 1.5648902654647827,
|
| 1512 |
+
"learning_rate": 9.533220402785622e-06,
|
| 1513 |
+
"loss": 0.042,
|
| 1514 |
+
"step": 107500
|
| 1515 |
+
},
|
| 1516 |
+
{
|
| 1517 |
+
"epoch": 20.327498588368154,
|
| 1518 |
+
"grad_norm": 2.084714889526367,
|
| 1519 |
+
"learning_rate": 9.345002823263693e-06,
|
| 1520 |
+
"loss": 0.0442,
|
| 1521 |
+
"step": 108000
|
| 1522 |
+
},
|
| 1523 |
+
{
|
| 1524 |
+
"epoch": 20.421607378129117,
|
| 1525 |
+
"grad_norm": 2.1811583042144775,
|
| 1526 |
+
"learning_rate": 9.156785243741765e-06,
|
| 1527 |
+
"loss": 0.0424,
|
| 1528 |
+
"step": 108500
|
| 1529 |
+
},
|
| 1530 |
+
{
|
| 1531 |
+
"epoch": 20.51571616789008,
|
| 1532 |
+
"grad_norm": 3.9864232540130615,
|
| 1533 |
+
"learning_rate": 8.96856766421984e-06,
|
| 1534 |
+
"loss": 0.0439,
|
| 1535 |
+
"step": 109000
|
| 1536 |
+
},
|
| 1537 |
+
{
|
| 1538 |
+
"epoch": 20.609824957651046,
|
| 1539 |
+
"grad_norm": 4.495816707611084,
|
| 1540 |
+
"learning_rate": 8.78035008469791e-06,
|
| 1541 |
+
"loss": 0.0433,
|
| 1542 |
+
"step": 109500
|
| 1543 |
+
},
|
| 1544 |
+
{
|
| 1545 |
+
"epoch": 20.70393374741201,
|
| 1546 |
+
"grad_norm": 1.6480516195297241,
|
| 1547 |
+
"learning_rate": 8.592132505175984e-06,
|
| 1548 |
+
"loss": 0.0454,
|
| 1549 |
+
"step": 110000
|
| 1550 |
+
},
|
| 1551 |
+
{
|
| 1552 |
+
"epoch": 20.79804253717297,
|
| 1553 |
+
"grad_norm": 1.1842634677886963,
|
| 1554 |
+
"learning_rate": 8.403914925654057e-06,
|
| 1555 |
+
"loss": 0.0425,
|
| 1556 |
+
"step": 110500
|
| 1557 |
+
},
|
| 1558 |
+
{
|
| 1559 |
+
"epoch": 20.892151326933934,
|
| 1560 |
+
"grad_norm": 4.60665225982666,
|
| 1561 |
+
"learning_rate": 8.215697346132128e-06,
|
| 1562 |
+
"loss": 0.0419,
|
| 1563 |
+
"step": 111000
|
| 1564 |
+
},
|
| 1565 |
+
{
|
| 1566 |
+
"epoch": 20.9862601166949,
|
| 1567 |
+
"grad_norm": 3.4669153690338135,
|
| 1568 |
+
"learning_rate": 8.027479766610201e-06,
|
| 1569 |
+
"loss": 0.0412,
|
| 1570 |
+
"step": 111500
|
| 1571 |
+
},
|
| 1572 |
+
{
|
| 1573 |
+
"epoch": 21.080368906455863,
|
| 1574 |
+
"grad_norm": 0.7074203491210938,
|
| 1575 |
+
"learning_rate": 7.839262187088274e-06,
|
| 1576 |
+
"loss": 0.0285,
|
| 1577 |
+
"step": 112000
|
| 1578 |
+
},
|
| 1579 |
+
{
|
| 1580 |
+
"epoch": 21.174477696216826,
|
| 1581 |
+
"grad_norm": 2.58770489692688,
|
| 1582 |
+
"learning_rate": 7.651044607566347e-06,
|
| 1583 |
+
"loss": 0.0275,
|
| 1584 |
+
"step": 112500
|
| 1585 |
+
},
|
| 1586 |
+
{
|
| 1587 |
+
"epoch": 21.26858648597779,
|
| 1588 |
+
"grad_norm": 0.6419113874435425,
|
| 1589 |
+
"learning_rate": 7.462827028044419e-06,
|
| 1590 |
+
"loss": 0.0263,
|
| 1591 |
+
"step": 113000
|
| 1592 |
+
},
|
| 1593 |
+
{
|
| 1594 |
+
"epoch": 21.362695275738755,
|
| 1595 |
+
"grad_norm": 2.158191204071045,
|
| 1596 |
+
"learning_rate": 7.274609448522493e-06,
|
| 1597 |
+
"loss": 0.0267,
|
| 1598 |
+
"step": 113500
|
| 1599 |
+
},
|
| 1600 |
+
{
|
| 1601 |
+
"epoch": 21.456804065499718,
|
| 1602 |
+
"grad_norm": 1.1450761556625366,
|
| 1603 |
+
"learning_rate": 7.0863918690005655e-06,
|
| 1604 |
+
"loss": 0.024,
|
| 1605 |
+
"step": 114000
|
| 1606 |
+
},
|
| 1607 |
+
{
|
| 1608 |
+
"epoch": 21.55091285526068,
|
| 1609 |
+
"grad_norm": 0.9204089045524597,
|
| 1610 |
+
"learning_rate": 6.898174289478637e-06,
|
| 1611 |
+
"loss": 0.0273,
|
| 1612 |
+
"step": 114500
|
| 1613 |
+
},
|
| 1614 |
+
{
|
| 1615 |
+
"epoch": 21.645021645021647,
|
| 1616 |
+
"grad_norm": 1.3897809982299805,
|
| 1617 |
+
"learning_rate": 6.709956709956711e-06,
|
| 1618 |
+
"loss": 0.0276,
|
| 1619 |
+
"step": 115000
|
| 1620 |
+
},
|
| 1621 |
+
{
|
| 1622 |
+
"epoch": 21.73913043478261,
|
| 1623 |
+
"grad_norm": 2.818786382675171,
|
| 1624 |
+
"learning_rate": 6.521739130434783e-06,
|
| 1625 |
+
"loss": 0.027,
|
| 1626 |
+
"step": 115500
|
| 1627 |
+
},
|
| 1628 |
+
{
|
| 1629 |
+
"epoch": 21.833239224543572,
|
| 1630 |
+
"grad_norm": 1.8107503652572632,
|
| 1631 |
+
"learning_rate": 6.333521550912856e-06,
|
| 1632 |
+
"loss": 0.025,
|
| 1633 |
+
"step": 116000
|
| 1634 |
+
},
|
| 1635 |
+
{
|
| 1636 |
+
"epoch": 21.927348014304535,
|
| 1637 |
+
"grad_norm": 2.591801881790161,
|
| 1638 |
+
"learning_rate": 6.145303971390928e-06,
|
| 1639 |
+
"loss": 0.0254,
|
| 1640 |
+
"step": 116500
|
| 1641 |
+
},
|
| 1642 |
+
{
|
| 1643 |
+
"epoch": 22.0214568040655,
|
| 1644 |
+
"grad_norm": 1.22541344165802,
|
| 1645 |
+
"learning_rate": 5.957086391869001e-06,
|
| 1646 |
+
"loss": 0.0207,
|
| 1647 |
+
"step": 117000
|
| 1648 |
+
},
|
| 1649 |
+
{
|
| 1650 |
+
"epoch": 22.115565593826464,
|
| 1651 |
+
"grad_norm": 2.6778624057769775,
|
| 1652 |
+
"learning_rate": 5.768868812347074e-06,
|
| 1653 |
+
"loss": 0.0148,
|
| 1654 |
+
"step": 117500
|
| 1655 |
+
},
|
| 1656 |
+
{
|
| 1657 |
+
"epoch": 22.209674383587426,
|
| 1658 |
+
"grad_norm": 1.2167950868606567,
|
| 1659 |
+
"learning_rate": 5.5806512328251455e-06,
|
| 1660 |
+
"loss": 0.0134,
|
| 1661 |
+
"step": 118000
|
| 1662 |
+
},
|
| 1663 |
+
{
|
| 1664 |
+
"epoch": 22.30378317334839,
|
| 1665 |
+
"grad_norm": 0.1222626119852066,
|
| 1666 |
+
"learning_rate": 5.3924336533032186e-06,
|
| 1667 |
+
"loss": 0.0175,
|
| 1668 |
+
"step": 118500
|
| 1669 |
+
},
|
| 1670 |
+
{
|
| 1671 |
+
"epoch": 22.397891963109355,
|
| 1672 |
+
"grad_norm": 0.3822714686393738,
|
| 1673 |
+
"learning_rate": 5.204216073781292e-06,
|
| 1674 |
+
"loss": 0.0156,
|
| 1675 |
+
"step": 119000
|
| 1676 |
+
},
|
| 1677 |
+
{
|
| 1678 |
+
"epoch": 22.492000752870318,
|
| 1679 |
+
"grad_norm": 0.542395293712616,
|
| 1680 |
+
"learning_rate": 5.015998494259365e-06,
|
| 1681 |
+
"loss": 0.0141,
|
| 1682 |
+
"step": 119500
|
| 1683 |
+
},
|
| 1684 |
+
{
|
| 1685 |
+
"epoch": 22.58610954263128,
|
| 1686 |
+
"grad_norm": 1.051392674446106,
|
| 1687 |
+
"learning_rate": 4.827780914737437e-06,
|
| 1688 |
+
"loss": 0.0138,
|
| 1689 |
+
"step": 120000
|
| 1690 |
+
},
|
| 1691 |
+
{
|
| 1692 |
+
"epoch": 22.680218332392247,
|
| 1693 |
+
"grad_norm": 1.7265046834945679,
|
| 1694 |
+
"learning_rate": 4.639563335215509e-06,
|
| 1695 |
+
"loss": 0.0139,
|
| 1696 |
+
"step": 120500
|
| 1697 |
+
},
|
| 1698 |
+
{
|
| 1699 |
+
"epoch": 22.77432712215321,
|
| 1700 |
+
"grad_norm": 0.8157036304473877,
|
| 1701 |
+
"learning_rate": 4.451345755693582e-06,
|
| 1702 |
+
"loss": 0.0147,
|
| 1703 |
+
"step": 121000
|
| 1704 |
+
},
|
| 1705 |
+
{
|
| 1706 |
+
"epoch": 22.868435911914172,
|
| 1707 |
+
"grad_norm": 2.212116003036499,
|
| 1708 |
+
"learning_rate": 4.263128176171654e-06,
|
| 1709 |
+
"loss": 0.0157,
|
| 1710 |
+
"step": 121500
|
| 1711 |
+
},
|
| 1712 |
+
{
|
| 1713 |
+
"epoch": 22.962544701675135,
|
| 1714 |
+
"grad_norm": 1.5762394666671753,
|
| 1715 |
+
"learning_rate": 4.074910596649727e-06,
|
| 1716 |
+
"loss": 0.0139,
|
| 1717 |
+
"step": 122000
|
| 1718 |
+
},
|
| 1719 |
+
{
|
| 1720 |
+
"epoch": 23.0566534914361,
|
| 1721 |
+
"grad_norm": 0.16070736944675446,
|
| 1722 |
+
"learning_rate": 3.8866930171278e-06,
|
| 1723 |
+
"loss": 0.0113,
|
| 1724 |
+
"step": 122500
|
| 1725 |
+
},
|
| 1726 |
+
{
|
| 1727 |
+
"epoch": 23.150762281197064,
|
| 1728 |
+
"grad_norm": 0.6197986602783203,
|
| 1729 |
+
"learning_rate": 3.698475437605872e-06,
|
| 1730 |
+
"loss": 0.0066,
|
| 1731 |
+
"step": 123000
|
| 1732 |
+
},
|
| 1733 |
+
{
|
| 1734 |
+
"epoch": 23.244871070958027,
|
| 1735 |
+
"grad_norm": 0.2145221084356308,
|
| 1736 |
+
"learning_rate": 3.510257858083945e-06,
|
| 1737 |
+
"loss": 0.0061,
|
| 1738 |
+
"step": 123500
|
| 1739 |
+
},
|
| 1740 |
+
{
|
| 1741 |
+
"epoch": 23.33897986071899,
|
| 1742 |
+
"grad_norm": 0.1779479682445526,
|
| 1743 |
+
"learning_rate": 3.3220402785620177e-06,
|
| 1744 |
+
"loss": 0.0059,
|
| 1745 |
+
"step": 124000
|
| 1746 |
+
},
|
| 1747 |
+
{
|
| 1748 |
+
"epoch": 23.433088650479956,
|
| 1749 |
+
"grad_norm": 0.18615959584712982,
|
| 1750 |
+
"learning_rate": 3.1338226990400907e-06,
|
| 1751 |
+
"loss": 0.0057,
|
| 1752 |
+
"step": 124500
|
| 1753 |
+
},
|
| 1754 |
+
{
|
| 1755 |
+
"epoch": 23.52719744024092,
|
| 1756 |
+
"grad_norm": 1.9545246362686157,
|
| 1757 |
+
"learning_rate": 2.945605119518163e-06,
|
| 1758 |
+
"loss": 0.0067,
|
| 1759 |
+
"step": 125000
|
| 1760 |
+
},
|
| 1761 |
+
{
|
| 1762 |
+
"epoch": 23.62130623000188,
|
| 1763 |
+
"grad_norm": 2.255216598510742,
|
| 1764 |
+
"learning_rate": 2.7573875399962355e-06,
|
| 1765 |
+
"loss": 0.0062,
|
| 1766 |
+
"step": 125500
|
| 1767 |
+
},
|
| 1768 |
+
{
|
| 1769 |
+
"epoch": 23.715415019762847,
|
| 1770 |
+
"grad_norm": 0.28629258275032043,
|
| 1771 |
+
"learning_rate": 2.5691699604743086e-06,
|
| 1772 |
+
"loss": 0.0054,
|
| 1773 |
+
"step": 126000
|
| 1774 |
+
},
|
| 1775 |
+
{
|
| 1776 |
+
"epoch": 23.80952380952381,
|
| 1777 |
+
"grad_norm": 0.1650991588830948,
|
| 1778 |
+
"learning_rate": 2.3809523809523808e-06,
|
| 1779 |
+
"loss": 0.0056,
|
| 1780 |
+
"step": 126500
|
| 1781 |
+
},
|
| 1782 |
+
{
|
| 1783 |
+
"epoch": 23.903632599284773,
|
| 1784 |
+
"grad_norm": 0.45735275745391846,
|
| 1785 |
+
"learning_rate": 2.192734801430454e-06,
|
| 1786 |
+
"loss": 0.006,
|
| 1787 |
+
"step": 127000
|
| 1788 |
+
},
|
| 1789 |
+
{
|
| 1790 |
+
"epoch": 23.997741389045736,
|
| 1791 |
+
"grad_norm": 1.3017574548721313,
|
| 1792 |
+
"learning_rate": 2.0045172219085264e-06,
|
| 1793 |
+
"loss": 0.0047,
|
| 1794 |
+
"step": 127500
|
| 1795 |
+
},
|
| 1796 |
+
{
|
| 1797 |
+
"epoch": 24.091850178806702,
|
| 1798 |
+
"grad_norm": 0.15063992142677307,
|
| 1799 |
+
"learning_rate": 1.8162996423865988e-06,
|
| 1800 |
+
"loss": 0.0037,
|
| 1801 |
+
"step": 128000
|
| 1802 |
+
},
|
| 1803 |
+
{
|
| 1804 |
+
"epoch": 24.185958968567665,
|
| 1805 |
+
"grad_norm": 0.09415856748819351,
|
| 1806 |
+
"learning_rate": 1.6280820628646716e-06,
|
| 1807 |
+
"loss": 0.0021,
|
| 1808 |
+
"step": 128500
|
| 1809 |
+
},
|
| 1810 |
+
{
|
| 1811 |
+
"epoch": 24.280067758328627,
|
| 1812 |
+
"grad_norm": 0.06203685700893402,
|
| 1813 |
+
"learning_rate": 1.4398644833427442e-06,
|
| 1814 |
+
"loss": 0.0017,
|
| 1815 |
+
"step": 129000
|
| 1816 |
+
},
|
| 1817 |
+
{
|
| 1818 |
+
"epoch": 24.37417654808959,
|
| 1819 |
+
"grad_norm": 1.0590204000473022,
|
| 1820 |
+
"learning_rate": 1.2516469038208169e-06,
|
| 1821 |
+
"loss": 0.0016,
|
| 1822 |
+
"step": 129500
|
| 1823 |
+
},
|
| 1824 |
+
{
|
| 1825 |
+
"epoch": 24.468285337850556,
|
| 1826 |
+
"grad_norm": 0.05048515647649765,
|
| 1827 |
+
"learning_rate": 1.0634293242988897e-06,
|
| 1828 |
+
"loss": 0.0014,
|
| 1829 |
+
"step": 130000
|
| 1830 |
+
},
|
| 1831 |
+
{
|
| 1832 |
+
"epoch": 24.56239412761152,
|
| 1833 |
+
"grad_norm": 0.10998225957155228,
|
| 1834 |
+
"learning_rate": 8.752117447769622e-07,
|
| 1835 |
+
"loss": 0.0014,
|
| 1836 |
+
"step": 130500
|
| 1837 |
+
},
|
| 1838 |
+
{
|
| 1839 |
+
"epoch": 24.65650291737248,
|
| 1840 |
+
"grad_norm": 0.03882027417421341,
|
| 1841 |
+
"learning_rate": 6.869941652550348e-07,
|
| 1842 |
+
"loss": 0.0013,
|
| 1843 |
+
"step": 131000
|
| 1844 |
+
},
|
| 1845 |
+
{
|
| 1846 |
+
"epoch": 24.750611707133448,
|
| 1847 |
+
"grad_norm": 0.09357800334692001,
|
| 1848 |
+
"learning_rate": 4.987765857331075e-07,
|
| 1849 |
+
"loss": 0.0016,
|
| 1850 |
+
"step": 131500
|
| 1851 |
+
},
|
| 1852 |
+
{
|
| 1853 |
+
"epoch": 24.84472049689441,
|
| 1854 |
+
"grad_norm": 0.18081815540790558,
|
| 1855 |
+
"learning_rate": 3.1055900621118013e-07,
|
| 1856 |
+
"loss": 0.0016,
|
| 1857 |
+
"step": 132000
|
| 1858 |
+
},
|
| 1859 |
+
{
|
| 1860 |
+
"epoch": 24.938829286655373,
|
| 1861 |
+
"grad_norm": 0.04123268648982048,
|
| 1862 |
+
"learning_rate": 1.223414266892528e-07,
|
| 1863 |
+
"loss": 0.0025,
|
| 1864 |
+
"step": 132500
|
| 1865 |
+
}
|
| 1866 |
+
],
|
| 1867 |
+
"logging_steps": 500,
|
| 1868 |
+
"max_steps": 132825,
|
| 1869 |
+
"num_input_tokens_seen": 0,
|
| 1870 |
+
"num_train_epochs": 25,
|
| 1871 |
+
"save_steps": 500,
|
| 1872 |
+
"stateful_callbacks": {
|
| 1873 |
+
"TrainerControl": {
|
| 1874 |
+
"args": {
|
| 1875 |
+
"should_epoch_stop": false,
|
| 1876 |
+
"should_evaluate": false,
|
| 1877 |
+
"should_log": false,
|
| 1878 |
+
"should_save": true,
|
| 1879 |
+
"should_training_stop": true
|
| 1880 |
+
},
|
| 1881 |
+
"attributes": {}
|
| 1882 |
+
}
|
| 1883 |
+
},
|
| 1884 |
+
"total_flos": 2.908084043402707e+18,
|
| 1885 |
+
"train_batch_size": 4,
|
| 1886 |
+
"trial_name": null,
|
| 1887 |
+
"trial_params": null
|
| 1888 |
+
}
|
checkpoint-132825/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:53a9d00bf42218bdcbd7c8da9324b0057468caafe642d0087c1792faedb39880
|
| 3 |
+
size 6456
|
checkpoint-132825/zero_to_fp32.py
ADDED
|
@@ -0,0 +1,604 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
#!/usr/bin/env python
|
| 2 |
+
|
| 3 |
+
# Copyright (c) Microsoft Corporation.
|
| 4 |
+
# SPDX-License-Identifier: Apache-2.0
|
| 5 |
+
|
| 6 |
+
# DeepSpeed Team
|
| 7 |
+
|
| 8 |
+
# This script extracts fp32 consolidated weights from a zero 1, 2 and 3 DeepSpeed checkpoints. It gets
|
| 9 |
+
# copied into the top level checkpoint dir, so the user can easily do the conversion at any point in
|
| 10 |
+
# the future. Once extracted, the weights don't require DeepSpeed and can be used in any
|
| 11 |
+
# application.
|
| 12 |
+
#
|
| 13 |
+
# example: python zero_to_fp32.py . pytorch_model.bin
|
| 14 |
+
|
| 15 |
+
import argparse
|
| 16 |
+
import torch
|
| 17 |
+
import glob
|
| 18 |
+
import math
|
| 19 |
+
import os
|
| 20 |
+
import re
|
| 21 |
+
from collections import OrderedDict
|
| 22 |
+
from dataclasses import dataclass
|
| 23 |
+
|
| 24 |
+
# while this script doesn't use deepspeed to recover data, since the checkpoints are pickled with
|
| 25 |
+
# DeepSpeed data structures it has to be available in the current python environment.
|
| 26 |
+
from deepspeed.utils import logger
|
| 27 |
+
from deepspeed.checkpoint.constants import (DS_VERSION, OPTIMIZER_STATE_DICT, SINGLE_PARTITION_OF_FP32_GROUPS,
|
| 28 |
+
FP32_FLAT_GROUPS, ZERO_STAGE, PARTITION_COUNT, PARAM_SHAPES, BUFFER_NAMES,
|
| 29 |
+
FROZEN_PARAM_SHAPES, FROZEN_PARAM_FRAGMENTS)
|
| 30 |
+
|
| 31 |
+
|
| 32 |
+
@dataclass
|
| 33 |
+
class zero_model_state:
|
| 34 |
+
buffers: dict()
|
| 35 |
+
param_shapes: dict()
|
| 36 |
+
shared_params: list
|
| 37 |
+
ds_version: int
|
| 38 |
+
frozen_param_shapes: dict()
|
| 39 |
+
frozen_param_fragments: dict()
|
| 40 |
+
|
| 41 |
+
|
| 42 |
+
debug = 0
|
| 43 |
+
|
| 44 |
+
# load to cpu
|
| 45 |
+
device = torch.device('cpu')
|
| 46 |
+
|
| 47 |
+
|
| 48 |
+
def atoi(text):
|
| 49 |
+
return int(text) if text.isdigit() else text
|
| 50 |
+
|
| 51 |
+
|
| 52 |
+
def natural_keys(text):
|
| 53 |
+
'''
|
| 54 |
+
alist.sort(key=natural_keys) sorts in human order
|
| 55 |
+
http://nedbatchelder.com/blog/200712/human_sorting.html
|
| 56 |
+
(See Toothy's implementation in the comments)
|
| 57 |
+
'''
|
| 58 |
+
return [atoi(c) for c in re.split(r'(\d+)', text)]
|
| 59 |
+
|
| 60 |
+
|
| 61 |
+
def get_model_state_file(checkpoint_dir, zero_stage):
|
| 62 |
+
if not os.path.isdir(checkpoint_dir):
|
| 63 |
+
raise FileNotFoundError(f"Directory '{checkpoint_dir}' doesn't exist")
|
| 64 |
+
|
| 65 |
+
# there should be only one file
|
| 66 |
+
if zero_stage <= 2:
|
| 67 |
+
file = os.path.join(checkpoint_dir, "mp_rank_00_model_states.pt")
|
| 68 |
+
elif zero_stage == 3:
|
| 69 |
+
file = os.path.join(checkpoint_dir, "zero_pp_rank_0_mp_rank_00_model_states.pt")
|
| 70 |
+
|
| 71 |
+
if not os.path.exists(file):
|
| 72 |
+
raise FileNotFoundError(f"can't find model states file at '{file}'")
|
| 73 |
+
|
| 74 |
+
return file
|
| 75 |
+
|
| 76 |
+
|
| 77 |
+
def get_checkpoint_files(checkpoint_dir, glob_pattern):
|
| 78 |
+
# XXX: need to test that this simple glob rule works for multi-node setup too
|
| 79 |
+
ckpt_files = sorted(glob.glob(os.path.join(checkpoint_dir, glob_pattern)), key=natural_keys)
|
| 80 |
+
|
| 81 |
+
if len(ckpt_files) == 0:
|
| 82 |
+
raise FileNotFoundError(f"can't find {glob_pattern} files in directory '{checkpoint_dir}'")
|
| 83 |
+
|
| 84 |
+
return ckpt_files
|
| 85 |
+
|
| 86 |
+
|
| 87 |
+
def get_optim_files(checkpoint_dir):
|
| 88 |
+
return get_checkpoint_files(checkpoint_dir, "*_optim_states.pt")
|
| 89 |
+
|
| 90 |
+
|
| 91 |
+
def get_model_state_files(checkpoint_dir):
|
| 92 |
+
return get_checkpoint_files(checkpoint_dir, "*_model_states.pt")
|
| 93 |
+
|
| 94 |
+
|
| 95 |
+
def parse_model_states(files):
|
| 96 |
+
zero_model_states = []
|
| 97 |
+
for file in files:
|
| 98 |
+
state_dict = torch.load(file, map_location=device)
|
| 99 |
+
|
| 100 |
+
if BUFFER_NAMES not in state_dict:
|
| 101 |
+
raise ValueError(f"{file} is not a model state checkpoint")
|
| 102 |
+
buffer_names = state_dict[BUFFER_NAMES]
|
| 103 |
+
if debug:
|
| 104 |
+
print("Found buffers:", buffer_names)
|
| 105 |
+
|
| 106 |
+
# recover just the buffers while restoring them to fp32 if they were saved in fp16
|
| 107 |
+
buffers = {k: v.float() for k, v in state_dict["module"].items() if k in buffer_names}
|
| 108 |
+
param_shapes = state_dict[PARAM_SHAPES]
|
| 109 |
+
|
| 110 |
+
# collect parameters that are included in param_shapes
|
| 111 |
+
param_names = []
|
| 112 |
+
for s in param_shapes:
|
| 113 |
+
for name in s.keys():
|
| 114 |
+
param_names.append(name)
|
| 115 |
+
|
| 116 |
+
# update with frozen parameters
|
| 117 |
+
frozen_param_shapes = state_dict.get(FROZEN_PARAM_SHAPES, None)
|
| 118 |
+
if frozen_param_shapes is not None:
|
| 119 |
+
if debug:
|
| 120 |
+
print(f"Found frozen_param_shapes: {frozen_param_shapes}")
|
| 121 |
+
param_names += list(frozen_param_shapes.keys())
|
| 122 |
+
|
| 123 |
+
# handle shared params
|
| 124 |
+
shared_params = [[k, v] for k, v in state_dict["shared_params"].items()]
|
| 125 |
+
|
| 126 |
+
ds_version = state_dict.get(DS_VERSION, None)
|
| 127 |
+
|
| 128 |
+
frozen_param_fragments = state_dict.get(FROZEN_PARAM_FRAGMENTS, None)
|
| 129 |
+
|
| 130 |
+
z_model_state = zero_model_state(buffers=buffers,
|
| 131 |
+
param_shapes=param_shapes,
|
| 132 |
+
shared_params=shared_params,
|
| 133 |
+
ds_version=ds_version,
|
| 134 |
+
frozen_param_shapes=frozen_param_shapes,
|
| 135 |
+
frozen_param_fragments=frozen_param_fragments)
|
| 136 |
+
zero_model_states.append(z_model_state)
|
| 137 |
+
|
| 138 |
+
return zero_model_states
|
| 139 |
+
|
| 140 |
+
|
| 141 |
+
def parse_optim_states(files, ds_checkpoint_dir):
|
| 142 |
+
|
| 143 |
+
total_files = len(files)
|
| 144 |
+
state_dicts = []
|
| 145 |
+
for f in files:
|
| 146 |
+
state_dict = torch.load(f, map_location=device)
|
| 147 |
+
# immediately discard the potentially huge 2 optimizer states as we only care for fp32 master weights
|
| 148 |
+
# and also handle the case where it was already removed by another helper script
|
| 149 |
+
state_dict["optimizer_state_dict"].pop("optimizer_state_dict", None)
|
| 150 |
+
state_dicts.append(state_dict)
|
| 151 |
+
|
| 152 |
+
if not ZERO_STAGE in state_dicts[0][OPTIMIZER_STATE_DICT]:
|
| 153 |
+
raise ValueError(f"{files[0]} is not a zero checkpoint")
|
| 154 |
+
zero_stage = state_dicts[0][OPTIMIZER_STATE_DICT][ZERO_STAGE]
|
| 155 |
+
world_size = state_dicts[0][OPTIMIZER_STATE_DICT][PARTITION_COUNT]
|
| 156 |
+
|
| 157 |
+
# For ZeRO-2 each param group can have different partition_count as data parallelism for expert
|
| 158 |
+
# parameters can be different from data parallelism for non-expert parameters. So we can just
|
| 159 |
+
# use the max of the partition_count to get the dp world_size.
|
| 160 |
+
|
| 161 |
+
if type(world_size) is list:
|
| 162 |
+
world_size = max(world_size)
|
| 163 |
+
|
| 164 |
+
if world_size != total_files:
|
| 165 |
+
raise ValueError(
|
| 166 |
+
f"Expected {world_size} of '*_optim_states.pt' under '{ds_checkpoint_dir}' but found {total_files} files. "
|
| 167 |
+
"Possibly due to an overwrite of an old checkpoint, or a checkpoint didn't get saved by one or more processes."
|
| 168 |
+
)
|
| 169 |
+
|
| 170 |
+
# the groups are named differently in each stage
|
| 171 |
+
if zero_stage <= 2:
|
| 172 |
+
fp32_groups_key = SINGLE_PARTITION_OF_FP32_GROUPS
|
| 173 |
+
elif zero_stage == 3:
|
| 174 |
+
fp32_groups_key = FP32_FLAT_GROUPS
|
| 175 |
+
else:
|
| 176 |
+
raise ValueError(f"unknown zero stage {zero_stage}")
|
| 177 |
+
|
| 178 |
+
if zero_stage <= 2:
|
| 179 |
+
fp32_flat_groups = [state_dicts[i][OPTIMIZER_STATE_DICT][fp32_groups_key] for i in range(len(state_dicts))]
|
| 180 |
+
elif zero_stage == 3:
|
| 181 |
+
# if there is more than one param group, there will be multiple flattened tensors - one
|
| 182 |
+
# flattened tensor per group - for simplicity merge them into a single tensor
|
| 183 |
+
#
|
| 184 |
+
# XXX: could make the script more memory efficient for when there are multiple groups - it
|
| 185 |
+
# will require matching the sub-lists of param_shapes for each param group flattened tensor
|
| 186 |
+
|
| 187 |
+
fp32_flat_groups = [
|
| 188 |
+
torch.cat(state_dicts[i][OPTIMIZER_STATE_DICT][fp32_groups_key], 0) for i in range(len(state_dicts))
|
| 189 |
+
]
|
| 190 |
+
|
| 191 |
+
return zero_stage, world_size, fp32_flat_groups
|
| 192 |
+
|
| 193 |
+
|
| 194 |
+
def _get_fp32_state_dict_from_zero_checkpoint(ds_checkpoint_dir, exclude_frozen_parameters):
|
| 195 |
+
"""
|
| 196 |
+
Returns fp32 state_dict reconstructed from ds checkpoint
|
| 197 |
+
|
| 198 |
+
Args:
|
| 199 |
+
- ``ds_checkpoint_dir``: path to the deepspeed checkpoint folder (where the optimizer files are)
|
| 200 |
+
|
| 201 |
+
"""
|
| 202 |
+
print(f"Processing zero checkpoint '{ds_checkpoint_dir}'")
|
| 203 |
+
|
| 204 |
+
optim_files = get_optim_files(ds_checkpoint_dir)
|
| 205 |
+
zero_stage, world_size, fp32_flat_groups = parse_optim_states(optim_files, ds_checkpoint_dir)
|
| 206 |
+
print(f"Detected checkpoint of type zero stage {zero_stage}, world_size: {world_size}")
|
| 207 |
+
|
| 208 |
+
model_files = get_model_state_files(ds_checkpoint_dir)
|
| 209 |
+
|
| 210 |
+
zero_model_states = parse_model_states(model_files)
|
| 211 |
+
print(f'Parsing checkpoint created by deepspeed=={zero_model_states[0].ds_version}')
|
| 212 |
+
|
| 213 |
+
if zero_stage <= 2:
|
| 214 |
+
return _get_fp32_state_dict_from_zero2_checkpoint(world_size, fp32_flat_groups, zero_model_states,
|
| 215 |
+
exclude_frozen_parameters)
|
| 216 |
+
elif zero_stage == 3:
|
| 217 |
+
return _get_fp32_state_dict_from_zero3_checkpoint(world_size, fp32_flat_groups, zero_model_states,
|
| 218 |
+
exclude_frozen_parameters)
|
| 219 |
+
|
| 220 |
+
|
| 221 |
+
def _zero2_merge_frozen_params(state_dict, zero_model_states):
|
| 222 |
+
if zero_model_states[0].frozen_param_shapes is None or len(zero_model_states[0].frozen_param_shapes) == 0:
|
| 223 |
+
return
|
| 224 |
+
|
| 225 |
+
frozen_param_shapes = zero_model_states[0].frozen_param_shapes
|
| 226 |
+
frozen_param_fragments = zero_model_states[0].frozen_param_fragments
|
| 227 |
+
|
| 228 |
+
if debug:
|
| 229 |
+
num_elem = sum(s.numel() for s in frozen_param_shapes.values())
|
| 230 |
+
print(f'rank 0: {FROZEN_PARAM_SHAPES}.numel = {num_elem}')
|
| 231 |
+
|
| 232 |
+
wanted_params = len(frozen_param_shapes)
|
| 233 |
+
wanted_numel = sum(s.numel() for s in frozen_param_shapes.values())
|
| 234 |
+
avail_numel = sum([p.numel() for p in frozen_param_fragments.values()])
|
| 235 |
+
print(f'Frozen params: Have {avail_numel} numels to process.')
|
| 236 |
+
print(f'Frozen params: Need {wanted_numel} numels in {wanted_params} params')
|
| 237 |
+
|
| 238 |
+
total_params = 0
|
| 239 |
+
total_numel = 0
|
| 240 |
+
for name, shape in frozen_param_shapes.items():
|
| 241 |
+
total_params += 1
|
| 242 |
+
unpartitioned_numel = shape.numel()
|
| 243 |
+
total_numel += unpartitioned_numel
|
| 244 |
+
|
| 245 |
+
state_dict[name] = frozen_param_fragments[name]
|
| 246 |
+
|
| 247 |
+
if debug:
|
| 248 |
+
print(f"{name} full shape: {shape} unpartitioned numel {unpartitioned_numel} ")
|
| 249 |
+
|
| 250 |
+
print(f"Reconstructed Frozen fp32 state dict with {total_params} params {total_numel} elements")
|
| 251 |
+
|
| 252 |
+
|
| 253 |
+
def _has_callable(obj, fn):
|
| 254 |
+
attr = getattr(obj, fn, None)
|
| 255 |
+
return callable(attr)
|
| 256 |
+
|
| 257 |
+
|
| 258 |
+
def _zero2_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states):
|
| 259 |
+
param_shapes = zero_model_states[0].param_shapes
|
| 260 |
+
|
| 261 |
+
# Reconstruction protocol:
|
| 262 |
+
#
|
| 263 |
+
# XXX: document this
|
| 264 |
+
|
| 265 |
+
if debug:
|
| 266 |
+
for i in range(world_size):
|
| 267 |
+
for j in range(len(fp32_flat_groups[0])):
|
| 268 |
+
print(f"{FP32_FLAT_GROUPS}[{i}][{j}].shape={fp32_flat_groups[i][j].shape}")
|
| 269 |
+
|
| 270 |
+
# XXX: memory usage doubles here (zero2)
|
| 271 |
+
num_param_groups = len(fp32_flat_groups[0])
|
| 272 |
+
merged_single_partition_of_fp32_groups = []
|
| 273 |
+
for i in range(num_param_groups):
|
| 274 |
+
merged_partitions = [sd[i] for sd in fp32_flat_groups]
|
| 275 |
+
full_single_fp32_vector = torch.cat(merged_partitions, 0)
|
| 276 |
+
merged_single_partition_of_fp32_groups.append(full_single_fp32_vector)
|
| 277 |
+
avail_numel = sum(
|
| 278 |
+
[full_single_fp32_vector.numel() for full_single_fp32_vector in merged_single_partition_of_fp32_groups])
|
| 279 |
+
|
| 280 |
+
if debug:
|
| 281 |
+
wanted_params = sum([len(shapes) for shapes in param_shapes])
|
| 282 |
+
wanted_numel = sum([sum(shape.numel() for shape in shapes.values()) for shapes in param_shapes])
|
| 283 |
+
# not asserting if there is a mismatch due to possible padding
|
| 284 |
+
print(f"Have {avail_numel} numels to process.")
|
| 285 |
+
print(f"Need {wanted_numel} numels in {wanted_params} params.")
|
| 286 |
+
|
| 287 |
+
# params
|
| 288 |
+
# XXX: for huge models that can't fit into the host's RAM we will have to recode this to support
|
| 289 |
+
# out-of-core computing solution
|
| 290 |
+
total_numel = 0
|
| 291 |
+
total_params = 0
|
| 292 |
+
for shapes, full_single_fp32_vector in zip(param_shapes, merged_single_partition_of_fp32_groups):
|
| 293 |
+
offset = 0
|
| 294 |
+
avail_numel = full_single_fp32_vector.numel()
|
| 295 |
+
for name, shape in shapes.items():
|
| 296 |
+
|
| 297 |
+
unpartitioned_numel = shape.numel() if _has_callable(shape, 'numel') else math.prod(shape)
|
| 298 |
+
total_numel += unpartitioned_numel
|
| 299 |
+
total_params += 1
|
| 300 |
+
|
| 301 |
+
if debug:
|
| 302 |
+
print(f"{name} full shape: {shape} unpartitioned numel {unpartitioned_numel} ")
|
| 303 |
+
state_dict[name] = full_single_fp32_vector.narrow(0, offset, unpartitioned_numel).view(shape)
|
| 304 |
+
offset += unpartitioned_numel
|
| 305 |
+
|
| 306 |
+
# Z2 started to align to 2*world_size to improve nccl performance. Therefore both offset and
|
| 307 |
+
# avail_numel can differ by anywhere between 0..2*world_size. Due to two unrelated complex
|
| 308 |
+
# paddings performed in the code it's almost impossible to predict the exact numbers w/o the
|
| 309 |
+
# live optimizer object, so we are checking that the numbers are within the right range
|
| 310 |
+
align_to = 2 * world_size
|
| 311 |
+
|
| 312 |
+
def zero2_align(x):
|
| 313 |
+
return align_to * math.ceil(x / align_to)
|
| 314 |
+
|
| 315 |
+
if debug:
|
| 316 |
+
print(f"original offset={offset}, avail_numel={avail_numel}")
|
| 317 |
+
|
| 318 |
+
offset = zero2_align(offset)
|
| 319 |
+
avail_numel = zero2_align(avail_numel)
|
| 320 |
+
|
| 321 |
+
if debug:
|
| 322 |
+
print(f"aligned offset={offset}, avail_numel={avail_numel}")
|
| 323 |
+
|
| 324 |
+
# Sanity check
|
| 325 |
+
if offset != avail_numel:
|
| 326 |
+
raise ValueError(f"consumed {offset} numels out of {avail_numel} - something is wrong")
|
| 327 |
+
|
| 328 |
+
print(f"Reconstructed fp32 state dict with {total_params} params {total_numel} elements")
|
| 329 |
+
|
| 330 |
+
|
| 331 |
+
def _get_fp32_state_dict_from_zero2_checkpoint(world_size, fp32_flat_groups, zero_model_states,
|
| 332 |
+
exclude_frozen_parameters):
|
| 333 |
+
state_dict = OrderedDict()
|
| 334 |
+
|
| 335 |
+
# buffers
|
| 336 |
+
buffers = zero_model_states[0].buffers
|
| 337 |
+
state_dict.update(buffers)
|
| 338 |
+
if debug:
|
| 339 |
+
print(f"added {len(buffers)} buffers")
|
| 340 |
+
|
| 341 |
+
if not exclude_frozen_parameters:
|
| 342 |
+
_zero2_merge_frozen_params(state_dict, zero_model_states)
|
| 343 |
+
|
| 344 |
+
_zero2_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states)
|
| 345 |
+
|
| 346 |
+
# recover shared parameters
|
| 347 |
+
for pair in zero_model_states[0].shared_params:
|
| 348 |
+
if pair[1] in state_dict:
|
| 349 |
+
state_dict[pair[0]] = state_dict[pair[1]]
|
| 350 |
+
|
| 351 |
+
return state_dict
|
| 352 |
+
|
| 353 |
+
|
| 354 |
+
def zero3_partitioned_param_info(unpartitioned_numel, world_size):
|
| 355 |
+
remainder = unpartitioned_numel % world_size
|
| 356 |
+
padding_numel = (world_size - remainder) if remainder else 0
|
| 357 |
+
partitioned_numel = math.ceil(unpartitioned_numel / world_size)
|
| 358 |
+
return partitioned_numel, padding_numel
|
| 359 |
+
|
| 360 |
+
|
| 361 |
+
def _zero3_merge_frozen_params(state_dict, world_size, zero_model_states):
|
| 362 |
+
if zero_model_states[0].frozen_param_shapes is None or len(zero_model_states[0].frozen_param_shapes) == 0:
|
| 363 |
+
return
|
| 364 |
+
|
| 365 |
+
if debug:
|
| 366 |
+
for i in range(world_size):
|
| 367 |
+
num_elem = sum(s.numel() for s in zero_model_states[i].frozen_param_fragments.values())
|
| 368 |
+
print(f'rank {i}: {FROZEN_PARAM_SHAPES}.numel = {num_elem}')
|
| 369 |
+
|
| 370 |
+
frozen_param_shapes = zero_model_states[0].frozen_param_shapes
|
| 371 |
+
wanted_params = len(frozen_param_shapes)
|
| 372 |
+
wanted_numel = sum(s.numel() for s in frozen_param_shapes.values())
|
| 373 |
+
avail_numel = sum([p.numel() for p in zero_model_states[0].frozen_param_fragments.values()]) * world_size
|
| 374 |
+
print(f'Frozen params: Have {avail_numel} numels to process.')
|
| 375 |
+
print(f'Frozen params: Need {wanted_numel} numels in {wanted_params} params')
|
| 376 |
+
|
| 377 |
+
total_params = 0
|
| 378 |
+
total_numel = 0
|
| 379 |
+
for name, shape in zero_model_states[0].frozen_param_shapes.items():
|
| 380 |
+
total_params += 1
|
| 381 |
+
unpartitioned_numel = shape.numel()
|
| 382 |
+
total_numel += unpartitioned_numel
|
| 383 |
+
|
| 384 |
+
param_frags = tuple(model_state.frozen_param_fragments[name] for model_state in zero_model_states)
|
| 385 |
+
state_dict[name] = torch.cat(param_frags, 0).narrow(0, 0, unpartitioned_numel).view(shape)
|
| 386 |
+
|
| 387 |
+
partitioned_numel, partitioned_padding_numel = zero3_partitioned_param_info(unpartitioned_numel, world_size)
|
| 388 |
+
|
| 389 |
+
if debug:
|
| 390 |
+
print(
|
| 391 |
+
f"Frozen params: {total_params} {name} full shape: {shape} partition0 numel={partitioned_numel} partitioned_padding_numel={partitioned_padding_numel}"
|
| 392 |
+
)
|
| 393 |
+
|
| 394 |
+
print(f"Reconstructed Frozen fp32 state dict with {total_params} params {total_numel} elements")
|
| 395 |
+
|
| 396 |
+
|
| 397 |
+
def _zero3_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states):
|
| 398 |
+
param_shapes = zero_model_states[0].param_shapes
|
| 399 |
+
avail_numel = fp32_flat_groups[0].numel() * world_size
|
| 400 |
+
# Reconstruction protocol: For zero3 we need to zip the partitions together at boundary of each
|
| 401 |
+
# param, re-consolidating each param, while dealing with padding if any
|
| 402 |
+
|
| 403 |
+
# merge list of dicts, preserving order
|
| 404 |
+
param_shapes = {k: v for d in param_shapes for k, v in d.items()}
|
| 405 |
+
|
| 406 |
+
if debug:
|
| 407 |
+
for i in range(world_size):
|
| 408 |
+
print(f"{FP32_FLAT_GROUPS}[{i}].shape={fp32_flat_groups[i].shape}")
|
| 409 |
+
|
| 410 |
+
wanted_params = len(param_shapes)
|
| 411 |
+
wanted_numel = sum(shape.numel() for shape in param_shapes.values())
|
| 412 |
+
# not asserting if there is a mismatch due to possible padding
|
| 413 |
+
avail_numel = fp32_flat_groups[0].numel() * world_size
|
| 414 |
+
print(f"Trainable params: Have {avail_numel} numels to process.")
|
| 415 |
+
print(f"Trainable params: Need {wanted_numel} numels in {wanted_params} params.")
|
| 416 |
+
|
| 417 |
+
# params
|
| 418 |
+
# XXX: for huge models that can't fit into the host's RAM we will have to recode this to support
|
| 419 |
+
# out-of-core computing solution
|
| 420 |
+
offset = 0
|
| 421 |
+
total_numel = 0
|
| 422 |
+
total_params = 0
|
| 423 |
+
for name, shape in param_shapes.items():
|
| 424 |
+
|
| 425 |
+
unpartitioned_numel = shape.numel()
|
| 426 |
+
total_numel += unpartitioned_numel
|
| 427 |
+
total_params += 1
|
| 428 |
+
|
| 429 |
+
partitioned_numel, partitioned_padding_numel = zero3_partitioned_param_info(unpartitioned_numel, world_size)
|
| 430 |
+
|
| 431 |
+
if debug:
|
| 432 |
+
print(
|
| 433 |
+
f"Trainable params: {total_params} {name} full shape: {shape} partition0 numel={partitioned_numel} partitioned_padding_numel={partitioned_padding_numel}"
|
| 434 |
+
)
|
| 435 |
+
|
| 436 |
+
# XXX: memory usage doubles here
|
| 437 |
+
state_dict[name] = torch.cat(
|
| 438 |
+
tuple(fp32_flat_groups[i].narrow(0, offset, partitioned_numel) for i in range(world_size)),
|
| 439 |
+
0).narrow(0, 0, unpartitioned_numel).view(shape)
|
| 440 |
+
offset += partitioned_numel
|
| 441 |
+
|
| 442 |
+
offset *= world_size
|
| 443 |
+
|
| 444 |
+
# Sanity check
|
| 445 |
+
if offset != avail_numel:
|
| 446 |
+
raise ValueError(f"consumed {offset} numels out of {avail_numel} - something is wrong")
|
| 447 |
+
|
| 448 |
+
print(f"Reconstructed Trainable fp32 state dict with {total_params} params {total_numel} elements")
|
| 449 |
+
|
| 450 |
+
|
| 451 |
+
def _get_fp32_state_dict_from_zero3_checkpoint(world_size, fp32_flat_groups, zero_model_states,
|
| 452 |
+
exclude_frozen_parameters):
|
| 453 |
+
state_dict = OrderedDict()
|
| 454 |
+
|
| 455 |
+
# buffers
|
| 456 |
+
buffers = zero_model_states[0].buffers
|
| 457 |
+
state_dict.update(buffers)
|
| 458 |
+
if debug:
|
| 459 |
+
print(f"added {len(buffers)} buffers")
|
| 460 |
+
|
| 461 |
+
if not exclude_frozen_parameters:
|
| 462 |
+
_zero3_merge_frozen_params(state_dict, world_size, zero_model_states)
|
| 463 |
+
|
| 464 |
+
_zero3_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states)
|
| 465 |
+
|
| 466 |
+
# recover shared parameters
|
| 467 |
+
for pair in zero_model_states[0].shared_params:
|
| 468 |
+
if pair[1] in state_dict:
|
| 469 |
+
state_dict[pair[0]] = state_dict[pair[1]]
|
| 470 |
+
|
| 471 |
+
return state_dict
|
| 472 |
+
|
| 473 |
+
|
| 474 |
+
def get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, tag=None, exclude_frozen_parameters=False):
|
| 475 |
+
"""
|
| 476 |
+
Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated state_dict that can be loaded with
|
| 477 |
+
``load_state_dict()`` and used for training without DeepSpeed or shared with others, for example
|
| 478 |
+
via a model hub.
|
| 479 |
+
|
| 480 |
+
Args:
|
| 481 |
+
- ``checkpoint_dir``: path to the desired checkpoint folder
|
| 482 |
+
- ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in 'latest' file. e.g., ``global_step14``
|
| 483 |
+
- ``exclude_frozen_parameters``: exclude frozen parameters
|
| 484 |
+
|
| 485 |
+
Returns:
|
| 486 |
+
- pytorch ``state_dict``
|
| 487 |
+
|
| 488 |
+
Note: this approach may not work if your application doesn't have sufficient free CPU memory and
|
| 489 |
+
you may need to use the offline approach using the ``zero_to_fp32.py`` script that is saved with
|
| 490 |
+
the checkpoint.
|
| 491 |
+
|
| 492 |
+
A typical usage might be ::
|
| 493 |
+
|
| 494 |
+
from deepspeed.utils.zero_to_fp32 import get_fp32_state_dict_from_zero_checkpoint
|
| 495 |
+
# do the training and checkpoint saving
|
| 496 |
+
state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir) # already on cpu
|
| 497 |
+
model = model.cpu() # move to cpu
|
| 498 |
+
model.load_state_dict(state_dict)
|
| 499 |
+
# submit to model hub or save the model to share with others
|
| 500 |
+
|
| 501 |
+
In this example the ``model`` will no longer be usable in the deepspeed context of the same
|
| 502 |
+
application. i.e. you will need to re-initialize the deepspeed engine, since
|
| 503 |
+
``model.load_state_dict(state_dict)`` will remove all the deepspeed magic from it.
|
| 504 |
+
|
| 505 |
+
If you want it all done for you, use ``load_state_dict_from_zero_checkpoint`` instead.
|
| 506 |
+
|
| 507 |
+
"""
|
| 508 |
+
if tag is None:
|
| 509 |
+
latest_path = os.path.join(checkpoint_dir, 'latest')
|
| 510 |
+
if os.path.isfile(latest_path):
|
| 511 |
+
with open(latest_path, 'r') as fd:
|
| 512 |
+
tag = fd.read().strip()
|
| 513 |
+
else:
|
| 514 |
+
raise ValueError(f"Unable to find 'latest' file at {latest_path}")
|
| 515 |
+
|
| 516 |
+
ds_checkpoint_dir = os.path.join(checkpoint_dir, tag)
|
| 517 |
+
|
| 518 |
+
if not os.path.isdir(ds_checkpoint_dir):
|
| 519 |
+
raise FileNotFoundError(f"Directory '{ds_checkpoint_dir}' doesn't exist")
|
| 520 |
+
|
| 521 |
+
return _get_fp32_state_dict_from_zero_checkpoint(ds_checkpoint_dir, exclude_frozen_parameters)
|
| 522 |
+
|
| 523 |
+
|
| 524 |
+
def convert_zero_checkpoint_to_fp32_state_dict(checkpoint_dir, output_file, tag=None, exclude_frozen_parameters=False):
|
| 525 |
+
"""
|
| 526 |
+
Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated ``state_dict`` file that can be
|
| 527 |
+
loaded with ``torch.load(file)`` + ``load_state_dict()`` and used for training without DeepSpeed.
|
| 528 |
+
|
| 529 |
+
Args:
|
| 530 |
+
- ``checkpoint_dir``: path to the desired checkpoint folder. (one that contains the tag-folder, like ``global_step14``)
|
| 531 |
+
- ``output_file``: path to the pytorch fp32 state_dict output file (e.g. path/pytorch_model.bin)
|
| 532 |
+
- ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in the file named ``latest`` in the checkpoint folder, e.g., ``global_step14``
|
| 533 |
+
- ``exclude_frozen_parameters``: exclude frozen parameters
|
| 534 |
+
"""
|
| 535 |
+
|
| 536 |
+
state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, tag, exclude_frozen_parameters)
|
| 537 |
+
print(f"Saving fp32 state dict to {output_file}")
|
| 538 |
+
torch.save(state_dict, output_file)
|
| 539 |
+
|
| 540 |
+
|
| 541 |
+
def load_state_dict_from_zero_checkpoint(model, checkpoint_dir, tag=None):
|
| 542 |
+
"""
|
| 543 |
+
1. Put the provided model to cpu
|
| 544 |
+
2. Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated ``state_dict``
|
| 545 |
+
3. Load it into the provided model
|
| 546 |
+
|
| 547 |
+
Args:
|
| 548 |
+
- ``model``: the model object to update
|
| 549 |
+
- ``checkpoint_dir``: path to the desired checkpoint folder. (one that contains the tag-folder, like ``global_step14``)
|
| 550 |
+
- ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in the file named ``latest`` in the checkpoint folder, e.g., ``global_step14``
|
| 551 |
+
|
| 552 |
+
Returns:
|
| 553 |
+
- ``model`: modified model
|
| 554 |
+
|
| 555 |
+
Make sure you have plenty of CPU memory available before you call this function. If you don't
|
| 556 |
+
have enough use the ``zero_to_fp32.py`` utility to do the conversion. You will find it
|
| 557 |
+
conveniently placed for you in the checkpoint folder.
|
| 558 |
+
|
| 559 |
+
A typical usage might be ::
|
| 560 |
+
|
| 561 |
+
from deepspeed.utils.zero_to_fp32 import load_state_dict_from_zero_checkpoint
|
| 562 |
+
model = load_state_dict_from_zero_checkpoint(trainer.model, checkpoint_dir)
|
| 563 |
+
# submit to model hub or save the model to share with others
|
| 564 |
+
|
| 565 |
+
Note, that once this was run, the ``model`` will no longer be usable in the deepspeed context
|
| 566 |
+
of the same application. i.e. you will need to re-initialize the deepspeed engine, since
|
| 567 |
+
``model.load_state_dict(state_dict)`` will remove all the deepspeed magic from it.
|
| 568 |
+
|
| 569 |
+
"""
|
| 570 |
+
logger.info(f"Extracting fp32 weights")
|
| 571 |
+
state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, tag)
|
| 572 |
+
|
| 573 |
+
logger.info(f"Overwriting model with fp32 weights")
|
| 574 |
+
model = model.cpu()
|
| 575 |
+
model.load_state_dict(state_dict, strict=False)
|
| 576 |
+
|
| 577 |
+
return model
|
| 578 |
+
|
| 579 |
+
|
| 580 |
+
if __name__ == "__main__":
|
| 581 |
+
|
| 582 |
+
parser = argparse.ArgumentParser()
|
| 583 |
+
parser.add_argument("checkpoint_dir",
|
| 584 |
+
type=str,
|
| 585 |
+
help="path to the desired checkpoint folder, e.g., path/checkpoint-12")
|
| 586 |
+
parser.add_argument(
|
| 587 |
+
"output_file",
|
| 588 |
+
type=str,
|
| 589 |
+
help="path to the pytorch fp32 state_dict output file (e.g. path/checkpoint-12/pytorch_model.bin)")
|
| 590 |
+
parser.add_argument("-t",
|
| 591 |
+
"--tag",
|
| 592 |
+
type=str,
|
| 593 |
+
default=None,
|
| 594 |
+
help="checkpoint tag used as a unique identifier for checkpoint. e.g., global_step1")
|
| 595 |
+
parser.add_argument("--exclude_frozen_parameters", action='store_true', help="exclude frozen parameters")
|
| 596 |
+
parser.add_argument("-d", "--debug", action='store_true', help="enable debug")
|
| 597 |
+
args = parser.parse_args()
|
| 598 |
+
|
| 599 |
+
debug = args.debug
|
| 600 |
+
|
| 601 |
+
convert_zero_checkpoint_to_fp32_state_dict(args.checkpoint_dir,
|
| 602 |
+
args.output_file,
|
| 603 |
+
tag=args.tag,
|
| 604 |
+
exclude_frozen_parameters=args.exclude_frozen_parameters)
|
config.json
ADDED
|
@@ -0,0 +1,258 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "AIDC-AI/Ovis1.6-Llama3.2-3B",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"Ovis"
|
| 5 |
+
],
|
| 6 |
+
"auto_map": {
|
| 7 |
+
"AutoConfig": "AIDC-AI/Ovis1.6-Llama3.2-3B--configuration_ovis.OvisConfig",
|
| 8 |
+
"AutoModelForCausalLM": "AIDC-AI/Ovis1.6-Llama3.2-3B--modeling_ovis.Ovis"
|
| 9 |
+
},
|
| 10 |
+
"conversation_formatter_class": "AgentFormatter",
|
| 11 |
+
"disable_tie_weight": false,
|
| 12 |
+
"hidden_size": 3072,
|
| 13 |
+
"llm_attn_implementation": "flash_attention_2",
|
| 14 |
+
"llm_config": {
|
| 15 |
+
"_name_or_path": "meta-llama/Llama-3.2-3B",
|
| 16 |
+
"add_cross_attention": false,
|
| 17 |
+
"architectures": [
|
| 18 |
+
"LlamaForCausalLM"
|
| 19 |
+
],
|
| 20 |
+
"attention_bias": false,
|
| 21 |
+
"attention_dropout": 0.0,
|
| 22 |
+
"bad_words_ids": null,
|
| 23 |
+
"begin_suppress_tokens": null,
|
| 24 |
+
"bos_token_id": 128000,
|
| 25 |
+
"chunk_size_feed_forward": 0,
|
| 26 |
+
"cross_attention_hidden_size": null,
|
| 27 |
+
"decoder_start_token_id": null,
|
| 28 |
+
"diversity_penalty": 0.0,
|
| 29 |
+
"do_sample": false,
|
| 30 |
+
"early_stopping": false,
|
| 31 |
+
"encoder_no_repeat_ngram_size": 0,
|
| 32 |
+
"eos_token_id": [
|
| 33 |
+
128001,
|
| 34 |
+
128008,
|
| 35 |
+
128009
|
| 36 |
+
],
|
| 37 |
+
"exponential_decay_length_penalty": null,
|
| 38 |
+
"finetuning_task": null,
|
| 39 |
+
"forced_bos_token_id": null,
|
| 40 |
+
"forced_eos_token_id": null,
|
| 41 |
+
"head_dim": 128,
|
| 42 |
+
"hidden_act": "silu",
|
| 43 |
+
"hidden_size": 3072,
|
| 44 |
+
"id2label": {
|
| 45 |
+
"0": "LABEL_0",
|
| 46 |
+
"1": "LABEL_1"
|
| 47 |
+
},
|
| 48 |
+
"initializer_range": 0.02,
|
| 49 |
+
"intermediate_size": 8192,
|
| 50 |
+
"is_decoder": false,
|
| 51 |
+
"is_encoder_decoder": false,
|
| 52 |
+
"label2id": {
|
| 53 |
+
"LABEL_0": 0,
|
| 54 |
+
"LABEL_1": 1
|
| 55 |
+
},
|
| 56 |
+
"length_penalty": 1.0,
|
| 57 |
+
"max_length": 20,
|
| 58 |
+
"max_position_embeddings": 131072,
|
| 59 |
+
"min_length": 0,
|
| 60 |
+
"mlp_bias": false,
|
| 61 |
+
"model_type": "llama",
|
| 62 |
+
"no_repeat_ngram_size": 0,
|
| 63 |
+
"num_attention_heads": 24,
|
| 64 |
+
"num_beam_groups": 1,
|
| 65 |
+
"num_beams": 1,
|
| 66 |
+
"num_hidden_layers": 28,
|
| 67 |
+
"num_key_value_heads": 8,
|
| 68 |
+
"num_return_sequences": 1,
|
| 69 |
+
"output_attentions": false,
|
| 70 |
+
"output_hidden_states": false,
|
| 71 |
+
"output_scores": false,
|
| 72 |
+
"pad_token_id": null,
|
| 73 |
+
"prefix": null,
|
| 74 |
+
"pretraining_tp": 1,
|
| 75 |
+
"problem_type": null,
|
| 76 |
+
"pruned_heads": {},
|
| 77 |
+
"remove_invalid_values": false,
|
| 78 |
+
"repetition_penalty": 1.0,
|
| 79 |
+
"return_dict": true,
|
| 80 |
+
"return_dict_in_generate": false,
|
| 81 |
+
"rms_norm_eps": 1e-05,
|
| 82 |
+
"rope_scaling": {
|
| 83 |
+
"factor": 32.0,
|
| 84 |
+
"high_freq_factor": 4.0,
|
| 85 |
+
"low_freq_factor": 1.0,
|
| 86 |
+
"original_max_position_embeddings": 8192,
|
| 87 |
+
"rope_type": "llama3"
|
| 88 |
+
},
|
| 89 |
+
"rope_theta": 500000.0,
|
| 90 |
+
"sep_token_id": null,
|
| 91 |
+
"suppress_tokens": null,
|
| 92 |
+
"task_specific_params": null,
|
| 93 |
+
"temperature": 1.0,
|
| 94 |
+
"tf_legacy_loss": false,
|
| 95 |
+
"tie_encoder_decoder": false,
|
| 96 |
+
"tie_word_embeddings": true,
|
| 97 |
+
"tokenizer_class": null,
|
| 98 |
+
"top_k": 50,
|
| 99 |
+
"top_p": 1.0,
|
| 100 |
+
"torch_dtype": "bfloat16",
|
| 101 |
+
"torchscript": false,
|
| 102 |
+
"typical_p": 1.0,
|
| 103 |
+
"use_bfloat16": false,
|
| 104 |
+
"use_cache": true,
|
| 105 |
+
"vocab_size": 128256
|
| 106 |
+
},
|
| 107 |
+
"model_type": "ovis",
|
| 108 |
+
"multimodal_max_length": 2048,
|
| 109 |
+
"torch_dtype": "bfloat16",
|
| 110 |
+
"transformers_version": "4.44.2",
|
| 111 |
+
"use_cache": true,
|
| 112 |
+
"visual_tokenizer_config": {
|
| 113 |
+
"_name_or_path": "",
|
| 114 |
+
"add_cross_attention": false,
|
| 115 |
+
"architectures": [
|
| 116 |
+
"SiglipVisualTokenizer"
|
| 117 |
+
],
|
| 118 |
+
"backbone_config": {
|
| 119 |
+
"_name_or_path": "google/siglip-so400m-patch14-384",
|
| 120 |
+
"add_cross_attention": false,
|
| 121 |
+
"architectures": null,
|
| 122 |
+
"attention_dropout": 0.0,
|
| 123 |
+
"bad_words_ids": null,
|
| 124 |
+
"begin_suppress_tokens": null,
|
| 125 |
+
"bos_token_id": null,
|
| 126 |
+
"chunk_size_feed_forward": 0,
|
| 127 |
+
"cross_attention_hidden_size": null,
|
| 128 |
+
"decoder_start_token_id": null,
|
| 129 |
+
"diversity_penalty": 0.0,
|
| 130 |
+
"do_sample": false,
|
| 131 |
+
"early_stopping": false,
|
| 132 |
+
"encoder_no_repeat_ngram_size": 0,
|
| 133 |
+
"eos_token_id": null,
|
| 134 |
+
"exponential_decay_length_penalty": null,
|
| 135 |
+
"finetuning_task": null,
|
| 136 |
+
"forced_bos_token_id": null,
|
| 137 |
+
"forced_eos_token_id": null,
|
| 138 |
+
"hidden_act": "gelu_pytorch_tanh",
|
| 139 |
+
"hidden_size": 1152,
|
| 140 |
+
"id2label": {
|
| 141 |
+
"0": "LABEL_0",
|
| 142 |
+
"1": "LABEL_1"
|
| 143 |
+
},
|
| 144 |
+
"image_size": 384,
|
| 145 |
+
"intermediate_size": 4304,
|
| 146 |
+
"is_decoder": false,
|
| 147 |
+
"is_encoder_decoder": false,
|
| 148 |
+
"label2id": {
|
| 149 |
+
"LABEL_0": 0,
|
| 150 |
+
"LABEL_1": 1
|
| 151 |
+
},
|
| 152 |
+
"layer_norm_eps": 1e-06,
|
| 153 |
+
"length_penalty": 1.0,
|
| 154 |
+
"max_length": 20,
|
| 155 |
+
"min_length": 0,
|
| 156 |
+
"model_type": "siglip_vision_model",
|
| 157 |
+
"no_repeat_ngram_size": 0,
|
| 158 |
+
"num_attention_heads": 16,
|
| 159 |
+
"num_beam_groups": 1,
|
| 160 |
+
"num_beams": 1,
|
| 161 |
+
"num_channels": 3,
|
| 162 |
+
"num_hidden_layers": 27,
|
| 163 |
+
"num_return_sequences": 1,
|
| 164 |
+
"output_attentions": false,
|
| 165 |
+
"output_hidden_states": false,
|
| 166 |
+
"output_scores": false,
|
| 167 |
+
"pad_token_id": null,
|
| 168 |
+
"patch_size": 14,
|
| 169 |
+
"prefix": null,
|
| 170 |
+
"problem_type": null,
|
| 171 |
+
"pruned_heads": {},
|
| 172 |
+
"remove_invalid_values": false,
|
| 173 |
+
"repetition_penalty": 1.0,
|
| 174 |
+
"return_dict": true,
|
| 175 |
+
"return_dict_in_generate": false,
|
| 176 |
+
"sep_token_id": null,
|
| 177 |
+
"suppress_tokens": null,
|
| 178 |
+
"task_specific_params": null,
|
| 179 |
+
"temperature": 1.0,
|
| 180 |
+
"tf_legacy_loss": false,
|
| 181 |
+
"tie_encoder_decoder": false,
|
| 182 |
+
"tie_word_embeddings": true,
|
| 183 |
+
"tokenizer_class": null,
|
| 184 |
+
"top_k": 50,
|
| 185 |
+
"top_p": 1.0,
|
| 186 |
+
"torch_dtype": null,
|
| 187 |
+
"torchscript": false,
|
| 188 |
+
"typical_p": 1.0,
|
| 189 |
+
"use_bfloat16": false
|
| 190 |
+
},
|
| 191 |
+
"backbone_kwargs": {},
|
| 192 |
+
"bad_words_ids": null,
|
| 193 |
+
"begin_suppress_tokens": null,
|
| 194 |
+
"bos_token_id": null,
|
| 195 |
+
"chunk_size_feed_forward": 0,
|
| 196 |
+
"cross_attention_hidden_size": null,
|
| 197 |
+
"decoder_start_token_id": null,
|
| 198 |
+
"depths": null,
|
| 199 |
+
"diversity_penalty": 0.0,
|
| 200 |
+
"do_sample": false,
|
| 201 |
+
"drop_cls_token": false,
|
| 202 |
+
"early_stopping": false,
|
| 203 |
+
"encoder_no_repeat_ngram_size": 0,
|
| 204 |
+
"eos_token_id": null,
|
| 205 |
+
"exponential_decay_length_penalty": null,
|
| 206 |
+
"finetuning_task": null,
|
| 207 |
+
"forced_bos_token_id": null,
|
| 208 |
+
"forced_eos_token_id": null,
|
| 209 |
+
"hidden_stride": 2,
|
| 210 |
+
"id2label": {
|
| 211 |
+
"0": "LABEL_0",
|
| 212 |
+
"1": "LABEL_1"
|
| 213 |
+
},
|
| 214 |
+
"is_decoder": false,
|
| 215 |
+
"is_encoder_decoder": false,
|
| 216 |
+
"label2id": {
|
| 217 |
+
"LABEL_0": 0,
|
| 218 |
+
"LABEL_1": 1
|
| 219 |
+
},
|
| 220 |
+
"length_penalty": 1.0,
|
| 221 |
+
"max_length": 20,
|
| 222 |
+
"min_length": 0,
|
| 223 |
+
"model_type": "siglip_visual_tokenizer",
|
| 224 |
+
"no_repeat_ngram_size": 0,
|
| 225 |
+
"num_beam_groups": 1,
|
| 226 |
+
"num_beams": 1,
|
| 227 |
+
"num_return_sequences": 1,
|
| 228 |
+
"output_attentions": false,
|
| 229 |
+
"output_hidden_states": false,
|
| 230 |
+
"output_scores": false,
|
| 231 |
+
"pad_token_id": null,
|
| 232 |
+
"prefix": null,
|
| 233 |
+
"problem_type": null,
|
| 234 |
+
"pruned_heads": {},
|
| 235 |
+
"remove_invalid_values": false,
|
| 236 |
+
"repetition_penalty": 1.0,
|
| 237 |
+
"return_dict": true,
|
| 238 |
+
"return_dict_in_generate": false,
|
| 239 |
+
"sep_token_id": null,
|
| 240 |
+
"suppress_tokens": null,
|
| 241 |
+
"task_specific_params": null,
|
| 242 |
+
"tau": 1.0,
|
| 243 |
+
"temperature": 1.0,
|
| 244 |
+
"tf_legacy_loss": false,
|
| 245 |
+
"tie_encoder_decoder": false,
|
| 246 |
+
"tie_word_embeddings": true,
|
| 247 |
+
"tokenize_function": "softmax",
|
| 248 |
+
"tokenizer_class": null,
|
| 249 |
+
"top_k": 50,
|
| 250 |
+
"top_p": 1.0,
|
| 251 |
+
"torch_dtype": "float32",
|
| 252 |
+
"torchscript": false,
|
| 253 |
+
"typical_p": 1.0,
|
| 254 |
+
"use_bfloat16": false,
|
| 255 |
+
"use_indicators": false,
|
| 256 |
+
"vocab_size": 65536
|
| 257 |
+
}
|
| 258 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token_id": 128000,
|
| 3 |
+
"do_sample": true,
|
| 4 |
+
"eos_token_id": [
|
| 5 |
+
128001,
|
| 6 |
+
128008,
|
| 7 |
+
128009
|
| 8 |
+
],
|
| 9 |
+
"multimodal_max_length": 2048,
|
| 10 |
+
"temperature": 0.6,
|
| 11 |
+
"top_p": 0.9,
|
| 12 |
+
"transformers_version": "4.44.2"
|
| 13 |
+
}
|
model-00001-of-00002.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e29889cafb081e011b76de8d2dc731af9d9d7622bed24537bdc70ed0e091099b
|
| 3 |
+
size 4965799848
|
model-00002-of-00002.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:32c869f8dac86306de73c7fa6d51803feb09000f08d245a3575e9e55a93a14ac
|
| 3 |
+
size 4111103436
|
model.safetensors.index.json
ADDED
|
@@ -0,0 +1,714 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"metadata": {
|
| 3 |
+
"total_size": 9076804716
|
| 4 |
+
},
|
| 5 |
+
"weight_map": {
|
| 6 |
+
"llm.lm_head.weight": "model-00002-of-00002.safetensors",
|
| 7 |
+
"llm.model.embed_tokens.weight": "model-00001-of-00002.safetensors",
|
| 8 |
+
"llm.model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 9 |
+
"llm.model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 10 |
+
"llm.model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 11 |
+
"llm.model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 12 |
+
"llm.model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 13 |
+
"llm.model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 14 |
+
"llm.model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 15 |
+
"llm.model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 16 |
+
"llm.model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 17 |
+
"llm.model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 18 |
+
"llm.model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 19 |
+
"llm.model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 20 |
+
"llm.model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 21 |
+
"llm.model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 22 |
+
"llm.model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 23 |
+
"llm.model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 24 |
+
"llm.model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 25 |
+
"llm.model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 26 |
+
"llm.model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 27 |
+
"llm.model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 28 |
+
"llm.model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 29 |
+
"llm.model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 30 |
+
"llm.model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 31 |
+
"llm.model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 32 |
+
"llm.model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 33 |
+
"llm.model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 34 |
+
"llm.model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 35 |
+
"llm.model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 36 |
+
"llm.model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 37 |
+
"llm.model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 38 |
+
"llm.model.layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 39 |
+
"llm.model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 40 |
+
"llm.model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 41 |
+
"llm.model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 42 |
+
"llm.model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 43 |
+
"llm.model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 44 |
+
"llm.model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 45 |
+
"llm.model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 46 |
+
"llm.model.layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 47 |
+
"llm.model.layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 48 |
+
"llm.model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 49 |
+
"llm.model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 50 |
+
"llm.model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 51 |
+
"llm.model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 52 |
+
"llm.model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 53 |
+
"llm.model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 54 |
+
"llm.model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 55 |
+
"llm.model.layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 56 |
+
"llm.model.layers.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 57 |
+
"llm.model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 58 |
+
"llm.model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 59 |
+
"llm.model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 60 |
+
"llm.model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 61 |
+
"llm.model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 62 |
+
"llm.model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 63 |
+
"llm.model.layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 64 |
+
"llm.model.layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 65 |
+
"llm.model.layers.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 66 |
+
"llm.model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 67 |
+
"llm.model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 68 |
+
"llm.model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 69 |
+
"llm.model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 70 |
+
"llm.model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 71 |
+
"llm.model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 72 |
+
"llm.model.layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 73 |
+
"llm.model.layers.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 74 |
+
"llm.model.layers.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 75 |
+
"llm.model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 76 |
+
"llm.model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 77 |
+
"llm.model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 78 |
+
"llm.model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 79 |
+
"llm.model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 80 |
+
"llm.model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 81 |
+
"llm.model.layers.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 82 |
+
"llm.model.layers.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 83 |
+
"llm.model.layers.16.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 84 |
+
"llm.model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 85 |
+
"llm.model.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 86 |
+
"llm.model.layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 87 |
+
"llm.model.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 88 |
+
"llm.model.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 89 |
+
"llm.model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 90 |
+
"llm.model.layers.17.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 91 |
+
"llm.model.layers.17.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 92 |
+
"llm.model.layers.17.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 93 |
+
"llm.model.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 94 |
+
"llm.model.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 95 |
+
"llm.model.layers.17.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 96 |
+
"llm.model.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 97 |
+
"llm.model.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 98 |
+
"llm.model.layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 99 |
+
"llm.model.layers.18.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 100 |
+
"llm.model.layers.18.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 101 |
+
"llm.model.layers.18.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 102 |
+
"llm.model.layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 103 |
+
"llm.model.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 104 |
+
"llm.model.layers.18.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 105 |
+
"llm.model.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 106 |
+
"llm.model.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 107 |
+
"llm.model.layers.19.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 108 |
+
"llm.model.layers.19.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 109 |
+
"llm.model.layers.19.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 110 |
+
"llm.model.layers.19.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 111 |
+
"llm.model.layers.19.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 112 |
+
"llm.model.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 113 |
+
"llm.model.layers.19.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 114 |
+
"llm.model.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 115 |
+
"llm.model.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 116 |
+
"llm.model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 117 |
+
"llm.model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 118 |
+
"llm.model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 119 |
+
"llm.model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 120 |
+
"llm.model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 121 |
+
"llm.model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 122 |
+
"llm.model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 123 |
+
"llm.model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 124 |
+
"llm.model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 125 |
+
"llm.model.layers.20.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 126 |
+
"llm.model.layers.20.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 127 |
+
"llm.model.layers.20.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 128 |
+
"llm.model.layers.20.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 129 |
+
"llm.model.layers.20.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 130 |
+
"llm.model.layers.20.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 131 |
+
"llm.model.layers.20.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 132 |
+
"llm.model.layers.20.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 133 |
+
"llm.model.layers.20.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 134 |
+
"llm.model.layers.21.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 135 |
+
"llm.model.layers.21.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 136 |
+
"llm.model.layers.21.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 137 |
+
"llm.model.layers.21.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 138 |
+
"llm.model.layers.21.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 139 |
+
"llm.model.layers.21.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 140 |
+
"llm.model.layers.21.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 141 |
+
"llm.model.layers.21.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 142 |
+
"llm.model.layers.21.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 143 |
+
"llm.model.layers.22.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 144 |
+
"llm.model.layers.22.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 145 |
+
"llm.model.layers.22.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 146 |
+
"llm.model.layers.22.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 147 |
+
"llm.model.layers.22.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 148 |
+
"llm.model.layers.22.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 149 |
+
"llm.model.layers.22.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 150 |
+
"llm.model.layers.22.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 151 |
+
"llm.model.layers.22.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 152 |
+
"llm.model.layers.23.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 153 |
+
"llm.model.layers.23.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 154 |
+
"llm.model.layers.23.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 155 |
+
"llm.model.layers.23.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 156 |
+
"llm.model.layers.23.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 157 |
+
"llm.model.layers.23.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 158 |
+
"llm.model.layers.23.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 159 |
+
"llm.model.layers.23.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 160 |
+
"llm.model.layers.23.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 161 |
+
"llm.model.layers.24.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 162 |
+
"llm.model.layers.24.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 163 |
+
"llm.model.layers.24.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 164 |
+
"llm.model.layers.24.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 165 |
+
"llm.model.layers.24.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 166 |
+
"llm.model.layers.24.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 167 |
+
"llm.model.layers.24.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 168 |
+
"llm.model.layers.24.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 169 |
+
"llm.model.layers.24.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 170 |
+
"llm.model.layers.25.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 171 |
+
"llm.model.layers.25.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 172 |
+
"llm.model.layers.25.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 173 |
+
"llm.model.layers.25.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 174 |
+
"llm.model.layers.25.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 175 |
+
"llm.model.layers.25.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 176 |
+
"llm.model.layers.25.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 177 |
+
"llm.model.layers.25.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 178 |
+
"llm.model.layers.25.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 179 |
+
"llm.model.layers.26.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 180 |
+
"llm.model.layers.26.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 181 |
+
"llm.model.layers.26.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 182 |
+
"llm.model.layers.26.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 183 |
+
"llm.model.layers.26.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 184 |
+
"llm.model.layers.26.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 185 |
+
"llm.model.layers.26.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 186 |
+
"llm.model.layers.26.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 187 |
+
"llm.model.layers.26.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 188 |
+
"llm.model.layers.27.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 189 |
+
"llm.model.layers.27.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 190 |
+
"llm.model.layers.27.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 191 |
+
"llm.model.layers.27.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 192 |
+
"llm.model.layers.27.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 193 |
+
"llm.model.layers.27.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 194 |
+
"llm.model.layers.27.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 195 |
+
"llm.model.layers.27.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 196 |
+
"llm.model.layers.27.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 197 |
+
"llm.model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 198 |
+
"llm.model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 199 |
+
"llm.model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 200 |
+
"llm.model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 201 |
+
"llm.model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 202 |
+
"llm.model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 203 |
+
"llm.model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 204 |
+
"llm.model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 205 |
+
"llm.model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 206 |
+
"llm.model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 207 |
+
"llm.model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 208 |
+
"llm.model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 209 |
+
"llm.model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 210 |
+
"llm.model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 211 |
+
"llm.model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 212 |
+
"llm.model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 213 |
+
"llm.model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 214 |
+
"llm.model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 215 |
+
"llm.model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 216 |
+
"llm.model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 217 |
+
"llm.model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 218 |
+
"llm.model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 219 |
+
"llm.model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 220 |
+
"llm.model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 221 |
+
"llm.model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 222 |
+
"llm.model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 223 |
+
"llm.model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 224 |
+
"llm.model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 225 |
+
"llm.model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 226 |
+
"llm.model.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 227 |
+
"llm.model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 228 |
+
"llm.model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 229 |
+
"llm.model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 230 |
+
"llm.model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 231 |
+
"llm.model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 232 |
+
"llm.model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 233 |
+
"llm.model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 234 |
+
"llm.model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 235 |
+
"llm.model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 236 |
+
"llm.model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 237 |
+
"llm.model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 238 |
+
"llm.model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 239 |
+
"llm.model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 240 |
+
"llm.model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 241 |
+
"llm.model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 242 |
+
"llm.model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 243 |
+
"llm.model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 244 |
+
"llm.model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 245 |
+
"llm.model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 246 |
+
"llm.model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 247 |
+
"llm.model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 248 |
+
"llm.model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 249 |
+
"llm.model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 250 |
+
"llm.model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 251 |
+
"llm.model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 252 |
+
"llm.model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 253 |
+
"llm.model.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 254 |
+
"llm.model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 255 |
+
"llm.model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 256 |
+
"llm.model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 257 |
+
"llm.model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 258 |
+
"llm.model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 259 |
+
"llm.model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 260 |
+
"llm.model.norm.weight": "model-00002-of-00002.safetensors",
|
| 261 |
+
"visual_tokenizer.backbone.vision_model.embeddings.patch_embedding.bias": "model-00002-of-00002.safetensors",
|
| 262 |
+
"visual_tokenizer.backbone.vision_model.embeddings.patch_embedding.weight": "model-00002-of-00002.safetensors",
|
| 263 |
+
"visual_tokenizer.backbone.vision_model.embeddings.position_embedding.weight": "model-00002-of-00002.safetensors",
|
| 264 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.0.layer_norm1.bias": "model-00002-of-00002.safetensors",
|
| 265 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.0.layer_norm1.weight": "model-00002-of-00002.safetensors",
|
| 266 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.0.layer_norm2.bias": "model-00002-of-00002.safetensors",
|
| 267 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.0.layer_norm2.weight": "model-00002-of-00002.safetensors",
|
| 268 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.0.mlp.fc1.bias": "model-00002-of-00002.safetensors",
|
| 269 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.0.mlp.fc1.weight": "model-00002-of-00002.safetensors",
|
| 270 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.0.mlp.fc2.bias": "model-00002-of-00002.safetensors",
|
| 271 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.0.mlp.fc2.weight": "model-00002-of-00002.safetensors",
|
| 272 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.0.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
| 273 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.0.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 274 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.0.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
|
| 275 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.0.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
|
| 276 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.0.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
| 277 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.0.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 278 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.0.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
| 279 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.0.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 280 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.1.layer_norm1.bias": "model-00002-of-00002.safetensors",
|
| 281 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.1.layer_norm1.weight": "model-00002-of-00002.safetensors",
|
| 282 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.1.layer_norm2.bias": "model-00002-of-00002.safetensors",
|
| 283 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.1.layer_norm2.weight": "model-00002-of-00002.safetensors",
|
| 284 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.1.mlp.fc1.bias": "model-00002-of-00002.safetensors",
|
| 285 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.1.mlp.fc1.weight": "model-00002-of-00002.safetensors",
|
| 286 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.1.mlp.fc2.bias": "model-00002-of-00002.safetensors",
|
| 287 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.1.mlp.fc2.weight": "model-00002-of-00002.safetensors",
|
| 288 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.1.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
| 289 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.1.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 290 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.1.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
|
| 291 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.1.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
|
| 292 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.1.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
| 293 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.1.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 294 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.1.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
| 295 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.1.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 296 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.10.layer_norm1.bias": "model-00002-of-00002.safetensors",
|
| 297 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.10.layer_norm1.weight": "model-00002-of-00002.safetensors",
|
| 298 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.10.layer_norm2.bias": "model-00002-of-00002.safetensors",
|
| 299 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.10.layer_norm2.weight": "model-00002-of-00002.safetensors",
|
| 300 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.10.mlp.fc1.bias": "model-00002-of-00002.safetensors",
|
| 301 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.10.mlp.fc1.weight": "model-00002-of-00002.safetensors",
|
| 302 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.10.mlp.fc2.bias": "model-00002-of-00002.safetensors",
|
| 303 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.10.mlp.fc2.weight": "model-00002-of-00002.safetensors",
|
| 304 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.10.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
| 305 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.10.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 306 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.10.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
|
| 307 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.10.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
|
| 308 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.10.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
| 309 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.10.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 310 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.10.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
| 311 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.10.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 312 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.11.layer_norm1.bias": "model-00002-of-00002.safetensors",
|
| 313 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.11.layer_norm1.weight": "model-00002-of-00002.safetensors",
|
| 314 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.11.layer_norm2.bias": "model-00002-of-00002.safetensors",
|
| 315 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.11.layer_norm2.weight": "model-00002-of-00002.safetensors",
|
| 316 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.11.mlp.fc1.bias": "model-00002-of-00002.safetensors",
|
| 317 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.11.mlp.fc1.weight": "model-00002-of-00002.safetensors",
|
| 318 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.11.mlp.fc2.bias": "model-00002-of-00002.safetensors",
|
| 319 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.11.mlp.fc2.weight": "model-00002-of-00002.safetensors",
|
| 320 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.11.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
| 321 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.11.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 322 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.11.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
|
| 323 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.11.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
|
| 324 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.11.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
| 325 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.11.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 326 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.11.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
| 327 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.11.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 328 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.12.layer_norm1.bias": "model-00002-of-00002.safetensors",
|
| 329 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.12.layer_norm1.weight": "model-00002-of-00002.safetensors",
|
| 330 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.12.layer_norm2.bias": "model-00002-of-00002.safetensors",
|
| 331 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.12.layer_norm2.weight": "model-00002-of-00002.safetensors",
|
| 332 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.12.mlp.fc1.bias": "model-00002-of-00002.safetensors",
|
| 333 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.12.mlp.fc1.weight": "model-00002-of-00002.safetensors",
|
| 334 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.12.mlp.fc2.bias": "model-00002-of-00002.safetensors",
|
| 335 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.12.mlp.fc2.weight": "model-00002-of-00002.safetensors",
|
| 336 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.12.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
| 337 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.12.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 338 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.12.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
|
| 339 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.12.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
|
| 340 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.12.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
| 341 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.12.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 342 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.12.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
| 343 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.12.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 344 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.13.layer_norm1.bias": "model-00002-of-00002.safetensors",
|
| 345 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.13.layer_norm1.weight": "model-00002-of-00002.safetensors",
|
| 346 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.13.layer_norm2.bias": "model-00002-of-00002.safetensors",
|
| 347 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.13.layer_norm2.weight": "model-00002-of-00002.safetensors",
|
| 348 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.13.mlp.fc1.bias": "model-00002-of-00002.safetensors",
|
| 349 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.13.mlp.fc1.weight": "model-00002-of-00002.safetensors",
|
| 350 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.13.mlp.fc2.bias": "model-00002-of-00002.safetensors",
|
| 351 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.13.mlp.fc2.weight": "model-00002-of-00002.safetensors",
|
| 352 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.13.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
| 353 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.13.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 354 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.13.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
|
| 355 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.13.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
|
| 356 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.13.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
| 357 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.13.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 358 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.13.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
| 359 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.13.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 360 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.14.layer_norm1.bias": "model-00002-of-00002.safetensors",
|
| 361 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.14.layer_norm1.weight": "model-00002-of-00002.safetensors",
|
| 362 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.14.layer_norm2.bias": "model-00002-of-00002.safetensors",
|
| 363 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.14.layer_norm2.weight": "model-00002-of-00002.safetensors",
|
| 364 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.14.mlp.fc1.bias": "model-00002-of-00002.safetensors",
|
| 365 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.14.mlp.fc1.weight": "model-00002-of-00002.safetensors",
|
| 366 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.14.mlp.fc2.bias": "model-00002-of-00002.safetensors",
|
| 367 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.14.mlp.fc2.weight": "model-00002-of-00002.safetensors",
|
| 368 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.14.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
| 369 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.14.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 370 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.14.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
|
| 371 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.14.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
|
| 372 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.14.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
| 373 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.14.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 374 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.14.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
| 375 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.14.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 376 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.15.layer_norm1.bias": "model-00002-of-00002.safetensors",
|
| 377 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.15.layer_norm1.weight": "model-00002-of-00002.safetensors",
|
| 378 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.15.layer_norm2.bias": "model-00002-of-00002.safetensors",
|
| 379 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.15.layer_norm2.weight": "model-00002-of-00002.safetensors",
|
| 380 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.15.mlp.fc1.bias": "model-00002-of-00002.safetensors",
|
| 381 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.15.mlp.fc1.weight": "model-00002-of-00002.safetensors",
|
| 382 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.15.mlp.fc2.bias": "model-00002-of-00002.safetensors",
|
| 383 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.15.mlp.fc2.weight": "model-00002-of-00002.safetensors",
|
| 384 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.15.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
| 385 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.15.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 386 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.15.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
|
| 387 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.15.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
|
| 388 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.15.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
| 389 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.15.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 390 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.15.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
| 391 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.15.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 392 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.16.layer_norm1.bias": "model-00002-of-00002.safetensors",
|
| 393 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.16.layer_norm1.weight": "model-00002-of-00002.safetensors",
|
| 394 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.16.layer_norm2.bias": "model-00002-of-00002.safetensors",
|
| 395 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.16.layer_norm2.weight": "model-00002-of-00002.safetensors",
|
| 396 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.16.mlp.fc1.bias": "model-00002-of-00002.safetensors",
|
| 397 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.16.mlp.fc1.weight": "model-00002-of-00002.safetensors",
|
| 398 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.16.mlp.fc2.bias": "model-00002-of-00002.safetensors",
|
| 399 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.16.mlp.fc2.weight": "model-00002-of-00002.safetensors",
|
| 400 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.16.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
| 401 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.16.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 402 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.16.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
|
| 403 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.16.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
|
| 404 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.16.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
| 405 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.16.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 406 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.16.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
| 407 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.16.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 408 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.17.layer_norm1.bias": "model-00002-of-00002.safetensors",
|
| 409 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.17.layer_norm1.weight": "model-00002-of-00002.safetensors",
|
| 410 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.17.layer_norm2.bias": "model-00002-of-00002.safetensors",
|
| 411 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.17.layer_norm2.weight": "model-00002-of-00002.safetensors",
|
| 412 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.17.mlp.fc1.bias": "model-00002-of-00002.safetensors",
|
| 413 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.17.mlp.fc1.weight": "model-00002-of-00002.safetensors",
|
| 414 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.17.mlp.fc2.bias": "model-00002-of-00002.safetensors",
|
| 415 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.17.mlp.fc2.weight": "model-00002-of-00002.safetensors",
|
| 416 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.17.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
| 417 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.17.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 418 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.17.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
|
| 419 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.17.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
|
| 420 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.17.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
| 421 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.17.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 422 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.17.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
| 423 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.17.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 424 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.18.layer_norm1.bias": "model-00002-of-00002.safetensors",
|
| 425 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.18.layer_norm1.weight": "model-00002-of-00002.safetensors",
|
| 426 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.18.layer_norm2.bias": "model-00002-of-00002.safetensors",
|
| 427 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.18.layer_norm2.weight": "model-00002-of-00002.safetensors",
|
| 428 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.18.mlp.fc1.bias": "model-00002-of-00002.safetensors",
|
| 429 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.18.mlp.fc1.weight": "model-00002-of-00002.safetensors",
|
| 430 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.18.mlp.fc2.bias": "model-00002-of-00002.safetensors",
|
| 431 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.18.mlp.fc2.weight": "model-00002-of-00002.safetensors",
|
| 432 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.18.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
| 433 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.18.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 434 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.18.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
|
| 435 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.18.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
|
| 436 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.18.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
| 437 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.18.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 438 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.18.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
| 439 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.18.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 440 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.19.layer_norm1.bias": "model-00002-of-00002.safetensors",
|
| 441 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.19.layer_norm1.weight": "model-00002-of-00002.safetensors",
|
| 442 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.19.layer_norm2.bias": "model-00002-of-00002.safetensors",
|
| 443 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.19.layer_norm2.weight": "model-00002-of-00002.safetensors",
|
| 444 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.19.mlp.fc1.bias": "model-00002-of-00002.safetensors",
|
| 445 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.19.mlp.fc1.weight": "model-00002-of-00002.safetensors",
|
| 446 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.19.mlp.fc2.bias": "model-00002-of-00002.safetensors",
|
| 447 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.19.mlp.fc2.weight": "model-00002-of-00002.safetensors",
|
| 448 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.19.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
| 449 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.19.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 450 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.19.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
|
| 451 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.19.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
|
| 452 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.19.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
| 453 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.19.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 454 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.19.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
| 455 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.19.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 456 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.2.layer_norm1.bias": "model-00002-of-00002.safetensors",
|
| 457 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.2.layer_norm1.weight": "model-00002-of-00002.safetensors",
|
| 458 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.2.layer_norm2.bias": "model-00002-of-00002.safetensors",
|
| 459 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.2.layer_norm2.weight": "model-00002-of-00002.safetensors",
|
| 460 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.2.mlp.fc1.bias": "model-00002-of-00002.safetensors",
|
| 461 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.2.mlp.fc1.weight": "model-00002-of-00002.safetensors",
|
| 462 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.2.mlp.fc2.bias": "model-00002-of-00002.safetensors",
|
| 463 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.2.mlp.fc2.weight": "model-00002-of-00002.safetensors",
|
| 464 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.2.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
| 465 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.2.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 466 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.2.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
|
| 467 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.2.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
|
| 468 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.2.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
| 469 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.2.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 470 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.2.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
| 471 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.2.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 472 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.20.layer_norm1.bias": "model-00002-of-00002.safetensors",
|
| 473 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.20.layer_norm1.weight": "model-00002-of-00002.safetensors",
|
| 474 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.20.layer_norm2.bias": "model-00002-of-00002.safetensors",
|
| 475 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.20.layer_norm2.weight": "model-00002-of-00002.safetensors",
|
| 476 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.20.mlp.fc1.bias": "model-00002-of-00002.safetensors",
|
| 477 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.20.mlp.fc1.weight": "model-00002-of-00002.safetensors",
|
| 478 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.20.mlp.fc2.bias": "model-00002-of-00002.safetensors",
|
| 479 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.20.mlp.fc2.weight": "model-00002-of-00002.safetensors",
|
| 480 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.20.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
| 481 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.20.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 482 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.20.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
|
| 483 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.20.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
|
| 484 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.20.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
| 485 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.20.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 486 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.20.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
| 487 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.20.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 488 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.21.layer_norm1.bias": "model-00002-of-00002.safetensors",
|
| 489 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.21.layer_norm1.weight": "model-00002-of-00002.safetensors",
|
| 490 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.21.layer_norm2.bias": "model-00002-of-00002.safetensors",
|
| 491 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.21.layer_norm2.weight": "model-00002-of-00002.safetensors",
|
| 492 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.21.mlp.fc1.bias": "model-00002-of-00002.safetensors",
|
| 493 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.21.mlp.fc1.weight": "model-00002-of-00002.safetensors",
|
| 494 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.21.mlp.fc2.bias": "model-00002-of-00002.safetensors",
|
| 495 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.21.mlp.fc2.weight": "model-00002-of-00002.safetensors",
|
| 496 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.21.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
| 497 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.21.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 498 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.21.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
|
| 499 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.21.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
|
| 500 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.21.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
| 501 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.21.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 502 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.21.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
| 503 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.21.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 504 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.22.layer_norm1.bias": "model-00002-of-00002.safetensors",
|
| 505 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.22.layer_norm1.weight": "model-00002-of-00002.safetensors",
|
| 506 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.22.layer_norm2.bias": "model-00002-of-00002.safetensors",
|
| 507 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.22.layer_norm2.weight": "model-00002-of-00002.safetensors",
|
| 508 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.22.mlp.fc1.bias": "model-00002-of-00002.safetensors",
|
| 509 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.22.mlp.fc1.weight": "model-00002-of-00002.safetensors",
|
| 510 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.22.mlp.fc2.bias": "model-00002-of-00002.safetensors",
|
| 511 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.22.mlp.fc2.weight": "model-00002-of-00002.safetensors",
|
| 512 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.22.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
| 513 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.22.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 514 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.22.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
|
| 515 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.22.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
|
| 516 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.22.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
| 517 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.22.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 518 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.22.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
| 519 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.22.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 520 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.23.layer_norm1.bias": "model-00002-of-00002.safetensors",
|
| 521 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.23.layer_norm1.weight": "model-00002-of-00002.safetensors",
|
| 522 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.23.layer_norm2.bias": "model-00002-of-00002.safetensors",
|
| 523 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.23.layer_norm2.weight": "model-00002-of-00002.safetensors",
|
| 524 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.23.mlp.fc1.bias": "model-00002-of-00002.safetensors",
|
| 525 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.23.mlp.fc1.weight": "model-00002-of-00002.safetensors",
|
| 526 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.23.mlp.fc2.bias": "model-00002-of-00002.safetensors",
|
| 527 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.23.mlp.fc2.weight": "model-00002-of-00002.safetensors",
|
| 528 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.23.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
| 529 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.23.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 530 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.23.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
|
| 531 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.23.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
|
| 532 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.23.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
| 533 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.23.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 534 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.23.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
| 535 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.23.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 536 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.24.layer_norm1.bias": "model-00002-of-00002.safetensors",
|
| 537 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.24.layer_norm1.weight": "model-00002-of-00002.safetensors",
|
| 538 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.24.layer_norm2.bias": "model-00002-of-00002.safetensors",
|
| 539 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.24.layer_norm2.weight": "model-00002-of-00002.safetensors",
|
| 540 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.24.mlp.fc1.bias": "model-00002-of-00002.safetensors",
|
| 541 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.24.mlp.fc1.weight": "model-00002-of-00002.safetensors",
|
| 542 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.24.mlp.fc2.bias": "model-00002-of-00002.safetensors",
|
| 543 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.24.mlp.fc2.weight": "model-00002-of-00002.safetensors",
|
| 544 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.24.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
| 545 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.24.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 546 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.24.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
|
| 547 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.24.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
|
| 548 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.24.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
| 549 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.24.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 550 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.24.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
| 551 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.24.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 552 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.25.layer_norm1.bias": "model-00002-of-00002.safetensors",
|
| 553 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.25.layer_norm1.weight": "model-00002-of-00002.safetensors",
|
| 554 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.25.layer_norm2.bias": "model-00002-of-00002.safetensors",
|
| 555 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.25.layer_norm2.weight": "model-00002-of-00002.safetensors",
|
| 556 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.25.mlp.fc1.bias": "model-00002-of-00002.safetensors",
|
| 557 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.25.mlp.fc1.weight": "model-00002-of-00002.safetensors",
|
| 558 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.25.mlp.fc2.bias": "model-00002-of-00002.safetensors",
|
| 559 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.25.mlp.fc2.weight": "model-00002-of-00002.safetensors",
|
| 560 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.25.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
| 561 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.25.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 562 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.25.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
|
| 563 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.25.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
|
| 564 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.25.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
| 565 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.25.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 566 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.25.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
| 567 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.25.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 568 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.26.layer_norm1.bias": "model-00002-of-00002.safetensors",
|
| 569 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.26.layer_norm1.weight": "model-00002-of-00002.safetensors",
|
| 570 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.26.layer_norm2.bias": "model-00002-of-00002.safetensors",
|
| 571 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.26.layer_norm2.weight": "model-00002-of-00002.safetensors",
|
| 572 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.26.mlp.fc1.bias": "model-00002-of-00002.safetensors",
|
| 573 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.26.mlp.fc1.weight": "model-00002-of-00002.safetensors",
|
| 574 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.26.mlp.fc2.bias": "model-00002-of-00002.safetensors",
|
| 575 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.26.mlp.fc2.weight": "model-00002-of-00002.safetensors",
|
| 576 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.26.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
| 577 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.26.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 578 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.26.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
|
| 579 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.26.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
|
| 580 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.26.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
| 581 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.26.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 582 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.26.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
| 583 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.26.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 584 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.3.layer_norm1.bias": "model-00002-of-00002.safetensors",
|
| 585 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.3.layer_norm1.weight": "model-00002-of-00002.safetensors",
|
| 586 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.3.layer_norm2.bias": "model-00002-of-00002.safetensors",
|
| 587 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.3.layer_norm2.weight": "model-00002-of-00002.safetensors",
|
| 588 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.3.mlp.fc1.bias": "model-00002-of-00002.safetensors",
|
| 589 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.3.mlp.fc1.weight": "model-00002-of-00002.safetensors",
|
| 590 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.3.mlp.fc2.bias": "model-00002-of-00002.safetensors",
|
| 591 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.3.mlp.fc2.weight": "model-00002-of-00002.safetensors",
|
| 592 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.3.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
| 593 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.3.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 594 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.3.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
|
| 595 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.3.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
|
| 596 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.3.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
| 597 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.3.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 598 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.3.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
| 599 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.3.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 600 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.4.layer_norm1.bias": "model-00002-of-00002.safetensors",
|
| 601 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.4.layer_norm1.weight": "model-00002-of-00002.safetensors",
|
| 602 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.4.layer_norm2.bias": "model-00002-of-00002.safetensors",
|
| 603 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.4.layer_norm2.weight": "model-00002-of-00002.safetensors",
|
| 604 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.4.mlp.fc1.bias": "model-00002-of-00002.safetensors",
|
| 605 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.4.mlp.fc1.weight": "model-00002-of-00002.safetensors",
|
| 606 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.4.mlp.fc2.bias": "model-00002-of-00002.safetensors",
|
| 607 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.4.mlp.fc2.weight": "model-00002-of-00002.safetensors",
|
| 608 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.4.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
| 609 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.4.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 610 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.4.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
|
| 611 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.4.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
|
| 612 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.4.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
| 613 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.4.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 614 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.4.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
| 615 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.4.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 616 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.5.layer_norm1.bias": "model-00002-of-00002.safetensors",
|
| 617 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.5.layer_norm1.weight": "model-00002-of-00002.safetensors",
|
| 618 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.5.layer_norm2.bias": "model-00002-of-00002.safetensors",
|
| 619 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.5.layer_norm2.weight": "model-00002-of-00002.safetensors",
|
| 620 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.5.mlp.fc1.bias": "model-00002-of-00002.safetensors",
|
| 621 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.5.mlp.fc1.weight": "model-00002-of-00002.safetensors",
|
| 622 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.5.mlp.fc2.bias": "model-00002-of-00002.safetensors",
|
| 623 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.5.mlp.fc2.weight": "model-00002-of-00002.safetensors",
|
| 624 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.5.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
| 625 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.5.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 626 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.5.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
|
| 627 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.5.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
|
| 628 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.5.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
| 629 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.5.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 630 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.5.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
| 631 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.5.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 632 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.6.layer_norm1.bias": "model-00002-of-00002.safetensors",
|
| 633 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.6.layer_norm1.weight": "model-00002-of-00002.safetensors",
|
| 634 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.6.layer_norm2.bias": "model-00002-of-00002.safetensors",
|
| 635 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.6.layer_norm2.weight": "model-00002-of-00002.safetensors",
|
| 636 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.6.mlp.fc1.bias": "model-00002-of-00002.safetensors",
|
| 637 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.6.mlp.fc1.weight": "model-00002-of-00002.safetensors",
|
| 638 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.6.mlp.fc2.bias": "model-00002-of-00002.safetensors",
|
| 639 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.6.mlp.fc2.weight": "model-00002-of-00002.safetensors",
|
| 640 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.6.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
| 641 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.6.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 642 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.6.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
|
| 643 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.6.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
|
| 644 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.6.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
| 645 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.6.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 646 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.6.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
| 647 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.6.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 648 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.7.layer_norm1.bias": "model-00002-of-00002.safetensors",
|
| 649 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.7.layer_norm1.weight": "model-00002-of-00002.safetensors",
|
| 650 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.7.layer_norm2.bias": "model-00002-of-00002.safetensors",
|
| 651 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.7.layer_norm2.weight": "model-00002-of-00002.safetensors",
|
| 652 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.7.mlp.fc1.bias": "model-00002-of-00002.safetensors",
|
| 653 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.7.mlp.fc1.weight": "model-00002-of-00002.safetensors",
|
| 654 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.7.mlp.fc2.bias": "model-00002-of-00002.safetensors",
|
| 655 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.7.mlp.fc2.weight": "model-00002-of-00002.safetensors",
|
| 656 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.7.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
| 657 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.7.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 658 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.7.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
|
| 659 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.7.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
|
| 660 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.7.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
| 661 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.7.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 662 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.7.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
| 663 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.7.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 664 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.8.layer_norm1.bias": "model-00002-of-00002.safetensors",
|
| 665 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.8.layer_norm1.weight": "model-00002-of-00002.safetensors",
|
| 666 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.8.layer_norm2.bias": "model-00002-of-00002.safetensors",
|
| 667 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.8.layer_norm2.weight": "model-00002-of-00002.safetensors",
|
| 668 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.8.mlp.fc1.bias": "model-00002-of-00002.safetensors",
|
| 669 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.8.mlp.fc1.weight": "model-00002-of-00002.safetensors",
|
| 670 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.8.mlp.fc2.bias": "model-00002-of-00002.safetensors",
|
| 671 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.8.mlp.fc2.weight": "model-00002-of-00002.safetensors",
|
| 672 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.8.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
| 673 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.8.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 674 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.8.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
|
| 675 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.8.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
|
| 676 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.8.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
| 677 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.8.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 678 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.8.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
| 679 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.8.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 680 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.9.layer_norm1.bias": "model-00002-of-00002.safetensors",
|
| 681 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.9.layer_norm1.weight": "model-00002-of-00002.safetensors",
|
| 682 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.9.layer_norm2.bias": "model-00002-of-00002.safetensors",
|
| 683 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.9.layer_norm2.weight": "model-00002-of-00002.safetensors",
|
| 684 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.9.mlp.fc1.bias": "model-00002-of-00002.safetensors",
|
| 685 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.9.mlp.fc1.weight": "model-00002-of-00002.safetensors",
|
| 686 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.9.mlp.fc2.bias": "model-00002-of-00002.safetensors",
|
| 687 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.9.mlp.fc2.weight": "model-00002-of-00002.safetensors",
|
| 688 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.9.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
| 689 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.9.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 690 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.9.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
|
| 691 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.9.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
|
| 692 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.9.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
| 693 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.9.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 694 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.9.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
| 695 |
+
"visual_tokenizer.backbone.vision_model.encoder.layers.9.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 696 |
+
"visual_tokenizer.backbone.vision_model.head.attention.in_proj_bias": "model-00002-of-00002.safetensors",
|
| 697 |
+
"visual_tokenizer.backbone.vision_model.head.attention.in_proj_weight": "model-00002-of-00002.safetensors",
|
| 698 |
+
"visual_tokenizer.backbone.vision_model.head.attention.out_proj.bias": "model-00002-of-00002.safetensors",
|
| 699 |
+
"visual_tokenizer.backbone.vision_model.head.attention.out_proj.weight": "model-00002-of-00002.safetensors",
|
| 700 |
+
"visual_tokenizer.backbone.vision_model.head.layernorm.bias": "model-00002-of-00002.safetensors",
|
| 701 |
+
"visual_tokenizer.backbone.vision_model.head.layernorm.weight": "model-00002-of-00002.safetensors",
|
| 702 |
+
"visual_tokenizer.backbone.vision_model.head.mlp.fc1.bias": "model-00002-of-00002.safetensors",
|
| 703 |
+
"visual_tokenizer.backbone.vision_model.head.mlp.fc1.weight": "model-00002-of-00002.safetensors",
|
| 704 |
+
"visual_tokenizer.backbone.vision_model.head.mlp.fc2.bias": "model-00002-of-00002.safetensors",
|
| 705 |
+
"visual_tokenizer.backbone.vision_model.head.mlp.fc2.weight": "model-00002-of-00002.safetensors",
|
| 706 |
+
"visual_tokenizer.backbone.vision_model.head.probe": "model-00002-of-00002.safetensors",
|
| 707 |
+
"visual_tokenizer.backbone.vision_model.post_layernorm.bias": "model-00002-of-00002.safetensors",
|
| 708 |
+
"visual_tokenizer.backbone.vision_model.post_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 709 |
+
"visual_tokenizer.head.0.weight": "model-00002-of-00002.safetensors",
|
| 710 |
+
"visual_tokenizer.head.1.bias": "model-00002-of-00002.safetensors",
|
| 711 |
+
"visual_tokenizer.head.1.weight": "model-00002-of-00002.safetensors",
|
| 712 |
+
"vte.weight": "model-00002-of-00002.safetensors"
|
| 713 |
+
}
|
| 714 |
+
}
|
model_training_args.json
ADDED
|
@@ -0,0 +1,161 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"model_args": {
|
| 3 |
+
"llm_name_or_path": "AIDC-AI/Ovis1.6-Llama3.2-3B",
|
| 4 |
+
"visual_tokenizer_type": "None",
|
| 5 |
+
"visual_vocab_size": "8192",
|
| 6 |
+
"visual_drop_cls_token": "False",
|
| 7 |
+
"visual_tokenize_function": "softmax",
|
| 8 |
+
"visual_tau": "1.0",
|
| 9 |
+
"visual_depths": "None",
|
| 10 |
+
"visual_hidden_stride": "1",
|
| 11 |
+
"multimodal_max_length": "2048",
|
| 12 |
+
"conversation_formatter_class": "None",
|
| 13 |
+
"pad_token_id": "None",
|
| 14 |
+
"llm_attn_implementation": "None",
|
| 15 |
+
"disable_tie_weight": "False"
|
| 16 |
+
},
|
| 17 |
+
"training_args": {
|
| 18 |
+
"output_dir": "/network/scratch/o/omar.younis/openphi",
|
| 19 |
+
"overwrite_output_dir": "False",
|
| 20 |
+
"do_train": "False",
|
| 21 |
+
"do_eval": "False",
|
| 22 |
+
"do_predict": "False",
|
| 23 |
+
"eval_strategy": "IntervalStrategy.NO",
|
| 24 |
+
"prediction_loss_only": "False",
|
| 25 |
+
"per_device_train_batch_size": "4",
|
| 26 |
+
"per_device_eval_batch_size": "8",
|
| 27 |
+
"per_gpu_train_batch_size": "None",
|
| 28 |
+
"per_gpu_eval_batch_size": "None",
|
| 29 |
+
"gradient_accumulation_steps": "1",
|
| 30 |
+
"eval_accumulation_steps": "None",
|
| 31 |
+
"eval_delay": "0",
|
| 32 |
+
"torch_empty_cache_steps": "None",
|
| 33 |
+
"learning_rate": "5e-05",
|
| 34 |
+
"weight_decay": "0.0",
|
| 35 |
+
"adam_beta1": "0.9",
|
| 36 |
+
"adam_beta2": "0.999",
|
| 37 |
+
"adam_epsilon": "1e-08",
|
| 38 |
+
"max_grad_norm": "1.0",
|
| 39 |
+
"num_train_epochs": "25",
|
| 40 |
+
"max_steps": "-1",
|
| 41 |
+
"lr_scheduler_type": "SchedulerType.LINEAR",
|
| 42 |
+
"lr_scheduler_kwargs": "{}",
|
| 43 |
+
"warmup_ratio": "0.0",
|
| 44 |
+
"warmup_steps": "0",
|
| 45 |
+
"log_level": "passive",
|
| 46 |
+
"log_level_replica": "warning",
|
| 47 |
+
"log_on_each_node": "True",
|
| 48 |
+
"logging_dir": "/network/scratch/o/omar.younis/openphi/runs/Nov23_16-08-46_cn-g025.server.mila.quebec",
|
| 49 |
+
"logging_strategy": "IntervalStrategy.STEPS",
|
| 50 |
+
"logging_first_step": "False",
|
| 51 |
+
"logging_steps": "500",
|
| 52 |
+
"logging_nan_inf_filter": "True",
|
| 53 |
+
"save_strategy": "IntervalStrategy.STEPS",
|
| 54 |
+
"save_steps": "500",
|
| 55 |
+
"save_total_limit": "None",
|
| 56 |
+
"save_safetensors": "True",
|
| 57 |
+
"save_on_each_node": "False",
|
| 58 |
+
"save_only_model": "False",
|
| 59 |
+
"restore_callback_states_from_checkpoint": "False",
|
| 60 |
+
"no_cuda": "False",
|
| 61 |
+
"use_cpu": "False",
|
| 62 |
+
"use_mps_device": "False",
|
| 63 |
+
"seed": "42",
|
| 64 |
+
"data_seed": "None",
|
| 65 |
+
"jit_mode_eval": "False",
|
| 66 |
+
"use_ipex": "False",
|
| 67 |
+
"bf16": "True",
|
| 68 |
+
"fp16": "False",
|
| 69 |
+
"fp16_opt_level": "O1",
|
| 70 |
+
"half_precision_backend": "auto",
|
| 71 |
+
"bf16_full_eval": "False",
|
| 72 |
+
"fp16_full_eval": "False",
|
| 73 |
+
"tf32": "None",
|
| 74 |
+
"local_rank": "0",
|
| 75 |
+
"ddp_backend": "None",
|
| 76 |
+
"tpu_num_cores": "None",
|
| 77 |
+
"tpu_metrics_debug": "False",
|
| 78 |
+
"debug": "[]",
|
| 79 |
+
"dataloader_drop_last": "False",
|
| 80 |
+
"eval_steps": "None",
|
| 81 |
+
"dataloader_num_workers": "0",
|
| 82 |
+
"dataloader_prefetch_factor": "None",
|
| 83 |
+
"past_index": "-1",
|
| 84 |
+
"run_name": "/network/scratch/o/omar.younis/openphi",
|
| 85 |
+
"disable_tqdm": "False",
|
| 86 |
+
"remove_unused_columns": "True",
|
| 87 |
+
"label_names": "None",
|
| 88 |
+
"load_best_model_at_end": "False",
|
| 89 |
+
"metric_for_best_model": "None",
|
| 90 |
+
"greater_is_better": "None",
|
| 91 |
+
"ignore_data_skip": "False",
|
| 92 |
+
"fsdp": "[]",
|
| 93 |
+
"fsdp_min_num_params": "0",
|
| 94 |
+
"fsdp_config": "{'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}",
|
| 95 |
+
"fsdp_transformer_layer_cls_to_wrap": "None",
|
| 96 |
+
"accelerator_config": "AcceleratorConfig(split_batches=False, dispatch_batches=None, even_batches=True, use_seedable_sampler=True, non_blocking=False, gradient_accumulation_kwargs=None, use_configured_state=False)",
|
| 97 |
+
"deepspeed": "None",
|
| 98 |
+
"label_smoothing_factor": "0.0",
|
| 99 |
+
"optim": "OptimizerNames.ADAMW_TORCH",
|
| 100 |
+
"optim_args": "None",
|
| 101 |
+
"adafactor": "False",
|
| 102 |
+
"group_by_length": "False",
|
| 103 |
+
"length_column_name": "length",
|
| 104 |
+
"report_to": "[]",
|
| 105 |
+
"ddp_find_unused_parameters": "None",
|
| 106 |
+
"ddp_bucket_cap_mb": "None",
|
| 107 |
+
"ddp_broadcast_buffers": "None",
|
| 108 |
+
"dataloader_pin_memory": "True",
|
| 109 |
+
"dataloader_persistent_workers": "False",
|
| 110 |
+
"skip_memory_metrics": "True",
|
| 111 |
+
"use_legacy_prediction_loop": "False",
|
| 112 |
+
"push_to_hub": "False",
|
| 113 |
+
"resume_from_checkpoint": "None",
|
| 114 |
+
"hub_model_id": "None",
|
| 115 |
+
"hub_strategy": "HubStrategy.EVERY_SAVE",
|
| 116 |
+
"hub_token": "None",
|
| 117 |
+
"hub_private_repo": "False",
|
| 118 |
+
"hub_always_push": "False",
|
| 119 |
+
"gradient_checkpointing": "False",
|
| 120 |
+
"gradient_checkpointing_kwargs": "None",
|
| 121 |
+
"include_inputs_for_metrics": "False",
|
| 122 |
+
"eval_do_concat_batches": "True",
|
| 123 |
+
"fp16_backend": "auto",
|
| 124 |
+
"evaluation_strategy": "None",
|
| 125 |
+
"push_to_hub_model_id": "None",
|
| 126 |
+
"push_to_hub_organization": "None",
|
| 127 |
+
"push_to_hub_token": "None",
|
| 128 |
+
"mp_parameters": "",
|
| 129 |
+
"auto_find_batch_size": "False",
|
| 130 |
+
"full_determinism": "False",
|
| 131 |
+
"torchdynamo": "None",
|
| 132 |
+
"ray_scope": "last",
|
| 133 |
+
"ddp_timeout": "1800",
|
| 134 |
+
"torch_compile": "False",
|
| 135 |
+
"torch_compile_backend": "None",
|
| 136 |
+
"torch_compile_mode": "None",
|
| 137 |
+
"dispatch_batches": "None",
|
| 138 |
+
"split_batches": "None",
|
| 139 |
+
"include_tokens_per_second": "False",
|
| 140 |
+
"include_num_input_tokens_seen": "False",
|
| 141 |
+
"neftune_noise_alpha": "None",
|
| 142 |
+
"optim_target_modules": "None",
|
| 143 |
+
"batch_eval_metrics": "False",
|
| 144 |
+
"eval_on_start": "False",
|
| 145 |
+
"eval_use_gather_object": "False",
|
| 146 |
+
"ovis_pretrained_path": "AIDC-AI/Ovis1.6-Llama3.2-3B",
|
| 147 |
+
"visual_tokenizer_pretrained_path": "None",
|
| 148 |
+
"caption_template": "None",
|
| 149 |
+
"train_modules": "all",
|
| 150 |
+
"cache_dir": "None",
|
| 151 |
+
"visual_max_tau": "5.0",
|
| 152 |
+
"visual_min_tau": "0.05",
|
| 153 |
+
"monitor_step": "100",
|
| 154 |
+
"text_max_length": "1024",
|
| 155 |
+
"max_partitions": "9|1|1",
|
| 156 |
+
"distributed_state": "Distributed environment: DEEPSPEED Backend: nccl\nNum processes: 4\nProcess index: 0\nLocal process index: 0\nDevice: cuda:0\n",
|
| 157 |
+
"_n_gpu": "1",
|
| 158 |
+
"__cached__setup_devices": "cuda:0",
|
| 159 |
+
"deepspeed_plugin": "DeepSpeedPlugin(hf_ds_config=<accelerate.utils.deepspeed.HfDeepSpeedConfig object at 0x7fbccfff4910>, gradient_accumulation_steps=1, gradient_clipping=None, zero_stage=1, is_train_batch_min=True, offload_optimizer_device='none', offload_param_device='none', offload_optimizer_nvme_path='none', offload_param_nvme_path='none', zero3_init_flag=False, zero3_save_16bit_model=False)"
|
| 160 |
+
}
|
| 161 |
+
}
|
preprocessor_config.json
ADDED
|
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"do_convert_rgb": null,
|
| 3 |
+
"do_normalize": true,
|
| 4 |
+
"do_rescale": true,
|
| 5 |
+
"do_resize": true,
|
| 6 |
+
"image_mean": [
|
| 7 |
+
0.5,
|
| 8 |
+
0.5,
|
| 9 |
+
0.5
|
| 10 |
+
],
|
| 11 |
+
"image_processor_type": "SiglipImageProcessor",
|
| 12 |
+
"image_std": [
|
| 13 |
+
0.5,
|
| 14 |
+
0.5,
|
| 15 |
+
0.5
|
| 16 |
+
],
|
| 17 |
+
"processor_class": "SiglipProcessor",
|
| 18 |
+
"resample": 3,
|
| 19 |
+
"rescale_factor": 0.00392156862745098,
|
| 20 |
+
"size": {
|
| 21 |
+
"height": 384,
|
| 22 |
+
"width": 384
|
| 23 |
+
}
|
| 24 |
+
}
|
slurm-5684270.out
ADDED
|
@@ -0,0 +1,35 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
|
| 2 |
+
======== GPU REPORT ========
|
| 3 |
+
|
| 4 |
+
==============NVSMI LOG==============
|
| 5 |
+
|
| 6 |
+
Timestamp : Mon Nov 25 11:42:44 2024
|
| 7 |
+
Driver Version : 560.35.03
|
| 8 |
+
CUDA Version : 12.6
|
| 9 |
+
|
| 10 |
+
Attached GPUs : 1
|
| 11 |
+
GPU 00000000:01:00.0
|
| 12 |
+
Accounting Mode : Enabled
|
| 13 |
+
Accounting Mode Buffer Size : 4000
|
| 14 |
+
Accounted Processes : None
|
| 15 |
+
|
| 16 |
+
Mon Nov 25 11:42:44 2024
|
| 17 |
+
+-----------------------------------------------------------------------------------------+
|
| 18 |
+
| NVIDIA-SMI 560.35.03 Driver Version: 560.35.03 CUDA Version: 12.6 |
|
| 19 |
+
|-----------------------------------------+------------------------+----------------------+
|
| 20 |
+
| GPU Name Persistence-M | Bus-Id Disp.A | Volatile Uncorr. ECC |
|
| 21 |
+
| Fan Temp Perf Pwr:Usage/Cap | Memory-Usage | GPU-Util Compute M. |
|
| 22 |
+
| | | MIG M. |
|
| 23 |
+
|=========================================+========================+======================|
|
| 24 |
+
| 0 NVIDIA A100-SXM4-80GB On | 00000000:01:00.0 Off | 0 |
|
| 25 |
+
| N/A 34C P0 63W / 500W | 1MiB / 81920MiB | 0% Default |
|
| 26 |
+
| | | Disabled |
|
| 27 |
+
+-----------------------------------------+------------------------+----------------------+
|
| 28 |
+
|
| 29 |
+
+-----------------------------------------------------------------------------------------+
|
| 30 |
+
| Processes: |
|
| 31 |
+
| GPU GI CI PID Type Process name GPU Memory |
|
| 32 |
+
| ID ID Usage |
|
| 33 |
+
|=========================================================================================|
|
| 34 |
+
| No running processes found |
|
| 35 |
+
+-----------------------------------------------------------------------------------------+
|
slurm-5684435.out
ADDED
|
@@ -0,0 +1,53 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
|
| 2 |
+
======== GPU REPORT ========
|
| 3 |
+
|
| 4 |
+
==============NVSMI LOG==============
|
| 5 |
+
|
| 6 |
+
Timestamp : Mon Nov 25 13:15:00 2024
|
| 7 |
+
Driver Version : 560.35.03
|
| 8 |
+
CUDA Version : 12.6
|
| 9 |
+
|
| 10 |
+
Attached GPUs : 1
|
| 11 |
+
GPU 00000000:41:00.0
|
| 12 |
+
Accounting Mode : Enabled
|
| 13 |
+
Accounting Mode Buffer Size : 4000
|
| 14 |
+
Accounted Processes
|
| 15 |
+
Process ID : 1856788
|
| 16 |
+
GPU Utilization : 40 %
|
| 17 |
+
Memory Utilization : 14 %
|
| 18 |
+
Max memory usage : 9482 MiB
|
| 19 |
+
Time : 97493 ms
|
| 20 |
+
Is Running : 0
|
| 21 |
+
Process ID : 1857366
|
| 22 |
+
GPU Utilization : 48 %
|
| 23 |
+
Memory Utilization : 15 %
|
| 24 |
+
Max memory usage : 9604 MiB
|
| 25 |
+
Time : 197447 ms
|
| 26 |
+
Is Running : 0
|
| 27 |
+
Process ID : 1858218
|
| 28 |
+
GPU Utilization : 41 %
|
| 29 |
+
Memory Utilization : 14 %
|
| 30 |
+
Max memory usage : 9488 MiB
|
| 31 |
+
Time : 86225 ms
|
| 32 |
+
Is Running : 0
|
| 33 |
+
|
| 34 |
+
Mon Nov 25 13:15:01 2024
|
| 35 |
+
+-----------------------------------------------------------------------------------------+
|
| 36 |
+
| NVIDIA-SMI 560.35.03 Driver Version: 560.35.03 CUDA Version: 12.6 |
|
| 37 |
+
|-----------------------------------------+------------------------+----------------------+
|
| 38 |
+
| GPU Name Persistence-M | Bus-Id Disp.A | Volatile Uncorr. ECC |
|
| 39 |
+
| Fan Temp Perf Pwr:Usage/Cap | Memory-Usage | GPU-Util Compute M. |
|
| 40 |
+
| | | MIG M. |
|
| 41 |
+
|=========================================+========================+======================|
|
| 42 |
+
| 0 NVIDIA A100-SXM4-80GB On | 00000000:41:00.0 Off | 0 |
|
| 43 |
+
| N/A 25C P0 58W / 500W | 1MiB / 81920MiB | 0% Default |
|
| 44 |
+
| | | Disabled |
|
| 45 |
+
+-----------------------------------------+------------------------+----------------------+
|
| 46 |
+
|
| 47 |
+
+-----------------------------------------------------------------------------------------+
|
| 48 |
+
| Processes: |
|
| 49 |
+
| GPU GI CI PID Type Process name GPU Memory |
|
| 50 |
+
| ID ID Usage |
|
| 51 |
+
|=========================================================================================|
|
| 52 |
+
| No running processes found |
|
| 53 |
+
+-----------------------------------------------------------------------------------------+
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,23 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "<|begin_of_text|>",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": false,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"eos_token": {
|
| 10 |
+
"content": "<|eot_id|>",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": false,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"pad_token": {
|
| 17 |
+
"content": "<|end_of_text|>",
|
| 18 |
+
"lstrip": false,
|
| 19 |
+
"normalized": false,
|
| 20 |
+
"rstrip": false,
|
| 21 |
+
"single_word": false
|
| 22 |
+
}
|
| 23 |
+
}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,2063 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"added_tokens_decoder": {
|
| 3 |
+
"128000": {
|
| 4 |
+
"content": "<|begin_of_text|>",
|
| 5 |
+
"lstrip": false,
|
| 6 |
+
"normalized": false,
|
| 7 |
+
"rstrip": false,
|
| 8 |
+
"single_word": false,
|
| 9 |
+
"special": true
|
| 10 |
+
},
|
| 11 |
+
"128001": {
|
| 12 |
+
"content": "<|end_of_text|>",
|
| 13 |
+
"lstrip": false,
|
| 14 |
+
"normalized": false,
|
| 15 |
+
"rstrip": false,
|
| 16 |
+
"single_word": false,
|
| 17 |
+
"special": true
|
| 18 |
+
},
|
| 19 |
+
"128002": {
|
| 20 |
+
"content": "<|reserved_special_token_0|>",
|
| 21 |
+
"lstrip": false,
|
| 22 |
+
"normalized": false,
|
| 23 |
+
"rstrip": false,
|
| 24 |
+
"single_word": false,
|
| 25 |
+
"special": true
|
| 26 |
+
},
|
| 27 |
+
"128003": {
|
| 28 |
+
"content": "<|reserved_special_token_1|>",
|
| 29 |
+
"lstrip": false,
|
| 30 |
+
"normalized": false,
|
| 31 |
+
"rstrip": false,
|
| 32 |
+
"single_word": false,
|
| 33 |
+
"special": true
|
| 34 |
+
},
|
| 35 |
+
"128004": {
|
| 36 |
+
"content": "<|finetune_right_pad_id|>",
|
| 37 |
+
"lstrip": false,
|
| 38 |
+
"normalized": false,
|
| 39 |
+
"rstrip": false,
|
| 40 |
+
"single_word": false,
|
| 41 |
+
"special": true
|
| 42 |
+
},
|
| 43 |
+
"128005": {
|
| 44 |
+
"content": "<|reserved_special_token_2|>",
|
| 45 |
+
"lstrip": false,
|
| 46 |
+
"normalized": false,
|
| 47 |
+
"rstrip": false,
|
| 48 |
+
"single_word": false,
|
| 49 |
+
"special": true
|
| 50 |
+
},
|
| 51 |
+
"128006": {
|
| 52 |
+
"content": "<|start_header_id|>",
|
| 53 |
+
"lstrip": false,
|
| 54 |
+
"normalized": false,
|
| 55 |
+
"rstrip": false,
|
| 56 |
+
"single_word": false,
|
| 57 |
+
"special": true
|
| 58 |
+
},
|
| 59 |
+
"128007": {
|
| 60 |
+
"content": "<|end_header_id|>",
|
| 61 |
+
"lstrip": false,
|
| 62 |
+
"normalized": false,
|
| 63 |
+
"rstrip": false,
|
| 64 |
+
"single_word": false,
|
| 65 |
+
"special": true
|
| 66 |
+
},
|
| 67 |
+
"128008": {
|
| 68 |
+
"content": "<|eom_id|>",
|
| 69 |
+
"lstrip": false,
|
| 70 |
+
"normalized": false,
|
| 71 |
+
"rstrip": false,
|
| 72 |
+
"single_word": false,
|
| 73 |
+
"special": true
|
| 74 |
+
},
|
| 75 |
+
"128009": {
|
| 76 |
+
"content": "<|eot_id|>",
|
| 77 |
+
"lstrip": false,
|
| 78 |
+
"normalized": false,
|
| 79 |
+
"rstrip": false,
|
| 80 |
+
"single_word": false,
|
| 81 |
+
"special": true
|
| 82 |
+
},
|
| 83 |
+
"128010": {
|
| 84 |
+
"content": "<|python_tag|>",
|
| 85 |
+
"lstrip": false,
|
| 86 |
+
"normalized": false,
|
| 87 |
+
"rstrip": false,
|
| 88 |
+
"single_word": false,
|
| 89 |
+
"special": true
|
| 90 |
+
},
|
| 91 |
+
"128011": {
|
| 92 |
+
"content": "<|reserved_special_token_3|>",
|
| 93 |
+
"lstrip": false,
|
| 94 |
+
"normalized": false,
|
| 95 |
+
"rstrip": false,
|
| 96 |
+
"single_word": false,
|
| 97 |
+
"special": true
|
| 98 |
+
},
|
| 99 |
+
"128012": {
|
| 100 |
+
"content": "<|reserved_special_token_4|>",
|
| 101 |
+
"lstrip": false,
|
| 102 |
+
"normalized": false,
|
| 103 |
+
"rstrip": false,
|
| 104 |
+
"single_word": false,
|
| 105 |
+
"special": true
|
| 106 |
+
},
|
| 107 |
+
"128013": {
|
| 108 |
+
"content": "<|reserved_special_token_5|>",
|
| 109 |
+
"lstrip": false,
|
| 110 |
+
"normalized": false,
|
| 111 |
+
"rstrip": false,
|
| 112 |
+
"single_word": false,
|
| 113 |
+
"special": true
|
| 114 |
+
},
|
| 115 |
+
"128014": {
|
| 116 |
+
"content": "<|reserved_special_token_6|>",
|
| 117 |
+
"lstrip": false,
|
| 118 |
+
"normalized": false,
|
| 119 |
+
"rstrip": false,
|
| 120 |
+
"single_word": false,
|
| 121 |
+
"special": true
|
| 122 |
+
},
|
| 123 |
+
"128015": {
|
| 124 |
+
"content": "<|reserved_special_token_7|>",
|
| 125 |
+
"lstrip": false,
|
| 126 |
+
"normalized": false,
|
| 127 |
+
"rstrip": false,
|
| 128 |
+
"single_word": false,
|
| 129 |
+
"special": true
|
| 130 |
+
},
|
| 131 |
+
"128016": {
|
| 132 |
+
"content": "<|reserved_special_token_8|>",
|
| 133 |
+
"lstrip": false,
|
| 134 |
+
"normalized": false,
|
| 135 |
+
"rstrip": false,
|
| 136 |
+
"single_word": false,
|
| 137 |
+
"special": true
|
| 138 |
+
},
|
| 139 |
+
"128017": {
|
| 140 |
+
"content": "<|reserved_special_token_9|>",
|
| 141 |
+
"lstrip": false,
|
| 142 |
+
"normalized": false,
|
| 143 |
+
"rstrip": false,
|
| 144 |
+
"single_word": false,
|
| 145 |
+
"special": true
|
| 146 |
+
},
|
| 147 |
+
"128018": {
|
| 148 |
+
"content": "<|reserved_special_token_10|>",
|
| 149 |
+
"lstrip": false,
|
| 150 |
+
"normalized": false,
|
| 151 |
+
"rstrip": false,
|
| 152 |
+
"single_word": false,
|
| 153 |
+
"special": true
|
| 154 |
+
},
|
| 155 |
+
"128019": {
|
| 156 |
+
"content": "<|reserved_special_token_11|>",
|
| 157 |
+
"lstrip": false,
|
| 158 |
+
"normalized": false,
|
| 159 |
+
"rstrip": false,
|
| 160 |
+
"single_word": false,
|
| 161 |
+
"special": true
|
| 162 |
+
},
|
| 163 |
+
"128020": {
|
| 164 |
+
"content": "<|reserved_special_token_12|>",
|
| 165 |
+
"lstrip": false,
|
| 166 |
+
"normalized": false,
|
| 167 |
+
"rstrip": false,
|
| 168 |
+
"single_word": false,
|
| 169 |
+
"special": true
|
| 170 |
+
},
|
| 171 |
+
"128021": {
|
| 172 |
+
"content": "<|reserved_special_token_13|>",
|
| 173 |
+
"lstrip": false,
|
| 174 |
+
"normalized": false,
|
| 175 |
+
"rstrip": false,
|
| 176 |
+
"single_word": false,
|
| 177 |
+
"special": true
|
| 178 |
+
},
|
| 179 |
+
"128022": {
|
| 180 |
+
"content": "<|reserved_special_token_14|>",
|
| 181 |
+
"lstrip": false,
|
| 182 |
+
"normalized": false,
|
| 183 |
+
"rstrip": false,
|
| 184 |
+
"single_word": false,
|
| 185 |
+
"special": true
|
| 186 |
+
},
|
| 187 |
+
"128023": {
|
| 188 |
+
"content": "<|reserved_special_token_15|>",
|
| 189 |
+
"lstrip": false,
|
| 190 |
+
"normalized": false,
|
| 191 |
+
"rstrip": false,
|
| 192 |
+
"single_word": false,
|
| 193 |
+
"special": true
|
| 194 |
+
},
|
| 195 |
+
"128024": {
|
| 196 |
+
"content": "<|reserved_special_token_16|>",
|
| 197 |
+
"lstrip": false,
|
| 198 |
+
"normalized": false,
|
| 199 |
+
"rstrip": false,
|
| 200 |
+
"single_word": false,
|
| 201 |
+
"special": true
|
| 202 |
+
},
|
| 203 |
+
"128025": {
|
| 204 |
+
"content": "<|reserved_special_token_17|>",
|
| 205 |
+
"lstrip": false,
|
| 206 |
+
"normalized": false,
|
| 207 |
+
"rstrip": false,
|
| 208 |
+
"single_word": false,
|
| 209 |
+
"special": true
|
| 210 |
+
},
|
| 211 |
+
"128026": {
|
| 212 |
+
"content": "<|reserved_special_token_18|>",
|
| 213 |
+
"lstrip": false,
|
| 214 |
+
"normalized": false,
|
| 215 |
+
"rstrip": false,
|
| 216 |
+
"single_word": false,
|
| 217 |
+
"special": true
|
| 218 |
+
},
|
| 219 |
+
"128027": {
|
| 220 |
+
"content": "<|reserved_special_token_19|>",
|
| 221 |
+
"lstrip": false,
|
| 222 |
+
"normalized": false,
|
| 223 |
+
"rstrip": false,
|
| 224 |
+
"single_word": false,
|
| 225 |
+
"special": true
|
| 226 |
+
},
|
| 227 |
+
"128028": {
|
| 228 |
+
"content": "<|reserved_special_token_20|>",
|
| 229 |
+
"lstrip": false,
|
| 230 |
+
"normalized": false,
|
| 231 |
+
"rstrip": false,
|
| 232 |
+
"single_word": false,
|
| 233 |
+
"special": true
|
| 234 |
+
},
|
| 235 |
+
"128029": {
|
| 236 |
+
"content": "<|reserved_special_token_21|>",
|
| 237 |
+
"lstrip": false,
|
| 238 |
+
"normalized": false,
|
| 239 |
+
"rstrip": false,
|
| 240 |
+
"single_word": false,
|
| 241 |
+
"special": true
|
| 242 |
+
},
|
| 243 |
+
"128030": {
|
| 244 |
+
"content": "<|reserved_special_token_22|>",
|
| 245 |
+
"lstrip": false,
|
| 246 |
+
"normalized": false,
|
| 247 |
+
"rstrip": false,
|
| 248 |
+
"single_word": false,
|
| 249 |
+
"special": true
|
| 250 |
+
},
|
| 251 |
+
"128031": {
|
| 252 |
+
"content": "<|reserved_special_token_23|>",
|
| 253 |
+
"lstrip": false,
|
| 254 |
+
"normalized": false,
|
| 255 |
+
"rstrip": false,
|
| 256 |
+
"single_word": false,
|
| 257 |
+
"special": true
|
| 258 |
+
},
|
| 259 |
+
"128032": {
|
| 260 |
+
"content": "<|reserved_special_token_24|>",
|
| 261 |
+
"lstrip": false,
|
| 262 |
+
"normalized": false,
|
| 263 |
+
"rstrip": false,
|
| 264 |
+
"single_word": false,
|
| 265 |
+
"special": true
|
| 266 |
+
},
|
| 267 |
+
"128033": {
|
| 268 |
+
"content": "<|reserved_special_token_25|>",
|
| 269 |
+
"lstrip": false,
|
| 270 |
+
"normalized": false,
|
| 271 |
+
"rstrip": false,
|
| 272 |
+
"single_word": false,
|
| 273 |
+
"special": true
|
| 274 |
+
},
|
| 275 |
+
"128034": {
|
| 276 |
+
"content": "<|reserved_special_token_26|>",
|
| 277 |
+
"lstrip": false,
|
| 278 |
+
"normalized": false,
|
| 279 |
+
"rstrip": false,
|
| 280 |
+
"single_word": false,
|
| 281 |
+
"special": true
|
| 282 |
+
},
|
| 283 |
+
"128035": {
|
| 284 |
+
"content": "<|reserved_special_token_27|>",
|
| 285 |
+
"lstrip": false,
|
| 286 |
+
"normalized": false,
|
| 287 |
+
"rstrip": false,
|
| 288 |
+
"single_word": false,
|
| 289 |
+
"special": true
|
| 290 |
+
},
|
| 291 |
+
"128036": {
|
| 292 |
+
"content": "<|reserved_special_token_28|>",
|
| 293 |
+
"lstrip": false,
|
| 294 |
+
"normalized": false,
|
| 295 |
+
"rstrip": false,
|
| 296 |
+
"single_word": false,
|
| 297 |
+
"special": true
|
| 298 |
+
},
|
| 299 |
+
"128037": {
|
| 300 |
+
"content": "<|reserved_special_token_29|>",
|
| 301 |
+
"lstrip": false,
|
| 302 |
+
"normalized": false,
|
| 303 |
+
"rstrip": false,
|
| 304 |
+
"single_word": false,
|
| 305 |
+
"special": true
|
| 306 |
+
},
|
| 307 |
+
"128038": {
|
| 308 |
+
"content": "<|reserved_special_token_30|>",
|
| 309 |
+
"lstrip": false,
|
| 310 |
+
"normalized": false,
|
| 311 |
+
"rstrip": false,
|
| 312 |
+
"single_word": false,
|
| 313 |
+
"special": true
|
| 314 |
+
},
|
| 315 |
+
"128039": {
|
| 316 |
+
"content": "<|reserved_special_token_31|>",
|
| 317 |
+
"lstrip": false,
|
| 318 |
+
"normalized": false,
|
| 319 |
+
"rstrip": false,
|
| 320 |
+
"single_word": false,
|
| 321 |
+
"special": true
|
| 322 |
+
},
|
| 323 |
+
"128040": {
|
| 324 |
+
"content": "<|reserved_special_token_32|>",
|
| 325 |
+
"lstrip": false,
|
| 326 |
+
"normalized": false,
|
| 327 |
+
"rstrip": false,
|
| 328 |
+
"single_word": false,
|
| 329 |
+
"special": true
|
| 330 |
+
},
|
| 331 |
+
"128041": {
|
| 332 |
+
"content": "<|reserved_special_token_33|>",
|
| 333 |
+
"lstrip": false,
|
| 334 |
+
"normalized": false,
|
| 335 |
+
"rstrip": false,
|
| 336 |
+
"single_word": false,
|
| 337 |
+
"special": true
|
| 338 |
+
},
|
| 339 |
+
"128042": {
|
| 340 |
+
"content": "<|reserved_special_token_34|>",
|
| 341 |
+
"lstrip": false,
|
| 342 |
+
"normalized": false,
|
| 343 |
+
"rstrip": false,
|
| 344 |
+
"single_word": false,
|
| 345 |
+
"special": true
|
| 346 |
+
},
|
| 347 |
+
"128043": {
|
| 348 |
+
"content": "<|reserved_special_token_35|>",
|
| 349 |
+
"lstrip": false,
|
| 350 |
+
"normalized": false,
|
| 351 |
+
"rstrip": false,
|
| 352 |
+
"single_word": false,
|
| 353 |
+
"special": true
|
| 354 |
+
},
|
| 355 |
+
"128044": {
|
| 356 |
+
"content": "<|reserved_special_token_36|>",
|
| 357 |
+
"lstrip": false,
|
| 358 |
+
"normalized": false,
|
| 359 |
+
"rstrip": false,
|
| 360 |
+
"single_word": false,
|
| 361 |
+
"special": true
|
| 362 |
+
},
|
| 363 |
+
"128045": {
|
| 364 |
+
"content": "<|reserved_special_token_37|>",
|
| 365 |
+
"lstrip": false,
|
| 366 |
+
"normalized": false,
|
| 367 |
+
"rstrip": false,
|
| 368 |
+
"single_word": false,
|
| 369 |
+
"special": true
|
| 370 |
+
},
|
| 371 |
+
"128046": {
|
| 372 |
+
"content": "<|reserved_special_token_38|>",
|
| 373 |
+
"lstrip": false,
|
| 374 |
+
"normalized": false,
|
| 375 |
+
"rstrip": false,
|
| 376 |
+
"single_word": false,
|
| 377 |
+
"special": true
|
| 378 |
+
},
|
| 379 |
+
"128047": {
|
| 380 |
+
"content": "<|reserved_special_token_39|>",
|
| 381 |
+
"lstrip": false,
|
| 382 |
+
"normalized": false,
|
| 383 |
+
"rstrip": false,
|
| 384 |
+
"single_word": false,
|
| 385 |
+
"special": true
|
| 386 |
+
},
|
| 387 |
+
"128048": {
|
| 388 |
+
"content": "<|reserved_special_token_40|>",
|
| 389 |
+
"lstrip": false,
|
| 390 |
+
"normalized": false,
|
| 391 |
+
"rstrip": false,
|
| 392 |
+
"single_word": false,
|
| 393 |
+
"special": true
|
| 394 |
+
},
|
| 395 |
+
"128049": {
|
| 396 |
+
"content": "<|reserved_special_token_41|>",
|
| 397 |
+
"lstrip": false,
|
| 398 |
+
"normalized": false,
|
| 399 |
+
"rstrip": false,
|
| 400 |
+
"single_word": false,
|
| 401 |
+
"special": true
|
| 402 |
+
},
|
| 403 |
+
"128050": {
|
| 404 |
+
"content": "<|reserved_special_token_42|>",
|
| 405 |
+
"lstrip": false,
|
| 406 |
+
"normalized": false,
|
| 407 |
+
"rstrip": false,
|
| 408 |
+
"single_word": false,
|
| 409 |
+
"special": true
|
| 410 |
+
},
|
| 411 |
+
"128051": {
|
| 412 |
+
"content": "<|reserved_special_token_43|>",
|
| 413 |
+
"lstrip": false,
|
| 414 |
+
"normalized": false,
|
| 415 |
+
"rstrip": false,
|
| 416 |
+
"single_word": false,
|
| 417 |
+
"special": true
|
| 418 |
+
},
|
| 419 |
+
"128052": {
|
| 420 |
+
"content": "<|reserved_special_token_44|>",
|
| 421 |
+
"lstrip": false,
|
| 422 |
+
"normalized": false,
|
| 423 |
+
"rstrip": false,
|
| 424 |
+
"single_word": false,
|
| 425 |
+
"special": true
|
| 426 |
+
},
|
| 427 |
+
"128053": {
|
| 428 |
+
"content": "<|reserved_special_token_45|>",
|
| 429 |
+
"lstrip": false,
|
| 430 |
+
"normalized": false,
|
| 431 |
+
"rstrip": false,
|
| 432 |
+
"single_word": false,
|
| 433 |
+
"special": true
|
| 434 |
+
},
|
| 435 |
+
"128054": {
|
| 436 |
+
"content": "<|reserved_special_token_46|>",
|
| 437 |
+
"lstrip": false,
|
| 438 |
+
"normalized": false,
|
| 439 |
+
"rstrip": false,
|
| 440 |
+
"single_word": false,
|
| 441 |
+
"special": true
|
| 442 |
+
},
|
| 443 |
+
"128055": {
|
| 444 |
+
"content": "<|reserved_special_token_47|>",
|
| 445 |
+
"lstrip": false,
|
| 446 |
+
"normalized": false,
|
| 447 |
+
"rstrip": false,
|
| 448 |
+
"single_word": false,
|
| 449 |
+
"special": true
|
| 450 |
+
},
|
| 451 |
+
"128056": {
|
| 452 |
+
"content": "<|reserved_special_token_48|>",
|
| 453 |
+
"lstrip": false,
|
| 454 |
+
"normalized": false,
|
| 455 |
+
"rstrip": false,
|
| 456 |
+
"single_word": false,
|
| 457 |
+
"special": true
|
| 458 |
+
},
|
| 459 |
+
"128057": {
|
| 460 |
+
"content": "<|reserved_special_token_49|>",
|
| 461 |
+
"lstrip": false,
|
| 462 |
+
"normalized": false,
|
| 463 |
+
"rstrip": false,
|
| 464 |
+
"single_word": false,
|
| 465 |
+
"special": true
|
| 466 |
+
},
|
| 467 |
+
"128058": {
|
| 468 |
+
"content": "<|reserved_special_token_50|>",
|
| 469 |
+
"lstrip": false,
|
| 470 |
+
"normalized": false,
|
| 471 |
+
"rstrip": false,
|
| 472 |
+
"single_word": false,
|
| 473 |
+
"special": true
|
| 474 |
+
},
|
| 475 |
+
"128059": {
|
| 476 |
+
"content": "<|reserved_special_token_51|>",
|
| 477 |
+
"lstrip": false,
|
| 478 |
+
"normalized": false,
|
| 479 |
+
"rstrip": false,
|
| 480 |
+
"single_word": false,
|
| 481 |
+
"special": true
|
| 482 |
+
},
|
| 483 |
+
"128060": {
|
| 484 |
+
"content": "<|reserved_special_token_52|>",
|
| 485 |
+
"lstrip": false,
|
| 486 |
+
"normalized": false,
|
| 487 |
+
"rstrip": false,
|
| 488 |
+
"single_word": false,
|
| 489 |
+
"special": true
|
| 490 |
+
},
|
| 491 |
+
"128061": {
|
| 492 |
+
"content": "<|reserved_special_token_53|>",
|
| 493 |
+
"lstrip": false,
|
| 494 |
+
"normalized": false,
|
| 495 |
+
"rstrip": false,
|
| 496 |
+
"single_word": false,
|
| 497 |
+
"special": true
|
| 498 |
+
},
|
| 499 |
+
"128062": {
|
| 500 |
+
"content": "<|reserved_special_token_54|>",
|
| 501 |
+
"lstrip": false,
|
| 502 |
+
"normalized": false,
|
| 503 |
+
"rstrip": false,
|
| 504 |
+
"single_word": false,
|
| 505 |
+
"special": true
|
| 506 |
+
},
|
| 507 |
+
"128063": {
|
| 508 |
+
"content": "<|reserved_special_token_55|>",
|
| 509 |
+
"lstrip": false,
|
| 510 |
+
"normalized": false,
|
| 511 |
+
"rstrip": false,
|
| 512 |
+
"single_word": false,
|
| 513 |
+
"special": true
|
| 514 |
+
},
|
| 515 |
+
"128064": {
|
| 516 |
+
"content": "<|reserved_special_token_56|>",
|
| 517 |
+
"lstrip": false,
|
| 518 |
+
"normalized": false,
|
| 519 |
+
"rstrip": false,
|
| 520 |
+
"single_word": false,
|
| 521 |
+
"special": true
|
| 522 |
+
},
|
| 523 |
+
"128065": {
|
| 524 |
+
"content": "<|reserved_special_token_57|>",
|
| 525 |
+
"lstrip": false,
|
| 526 |
+
"normalized": false,
|
| 527 |
+
"rstrip": false,
|
| 528 |
+
"single_word": false,
|
| 529 |
+
"special": true
|
| 530 |
+
},
|
| 531 |
+
"128066": {
|
| 532 |
+
"content": "<|reserved_special_token_58|>",
|
| 533 |
+
"lstrip": false,
|
| 534 |
+
"normalized": false,
|
| 535 |
+
"rstrip": false,
|
| 536 |
+
"single_word": false,
|
| 537 |
+
"special": true
|
| 538 |
+
},
|
| 539 |
+
"128067": {
|
| 540 |
+
"content": "<|reserved_special_token_59|>",
|
| 541 |
+
"lstrip": false,
|
| 542 |
+
"normalized": false,
|
| 543 |
+
"rstrip": false,
|
| 544 |
+
"single_word": false,
|
| 545 |
+
"special": true
|
| 546 |
+
},
|
| 547 |
+
"128068": {
|
| 548 |
+
"content": "<|reserved_special_token_60|>",
|
| 549 |
+
"lstrip": false,
|
| 550 |
+
"normalized": false,
|
| 551 |
+
"rstrip": false,
|
| 552 |
+
"single_word": false,
|
| 553 |
+
"special": true
|
| 554 |
+
},
|
| 555 |
+
"128069": {
|
| 556 |
+
"content": "<|reserved_special_token_61|>",
|
| 557 |
+
"lstrip": false,
|
| 558 |
+
"normalized": false,
|
| 559 |
+
"rstrip": false,
|
| 560 |
+
"single_word": false,
|
| 561 |
+
"special": true
|
| 562 |
+
},
|
| 563 |
+
"128070": {
|
| 564 |
+
"content": "<|reserved_special_token_62|>",
|
| 565 |
+
"lstrip": false,
|
| 566 |
+
"normalized": false,
|
| 567 |
+
"rstrip": false,
|
| 568 |
+
"single_word": false,
|
| 569 |
+
"special": true
|
| 570 |
+
},
|
| 571 |
+
"128071": {
|
| 572 |
+
"content": "<|reserved_special_token_63|>",
|
| 573 |
+
"lstrip": false,
|
| 574 |
+
"normalized": false,
|
| 575 |
+
"rstrip": false,
|
| 576 |
+
"single_word": false,
|
| 577 |
+
"special": true
|
| 578 |
+
},
|
| 579 |
+
"128072": {
|
| 580 |
+
"content": "<|reserved_special_token_64|>",
|
| 581 |
+
"lstrip": false,
|
| 582 |
+
"normalized": false,
|
| 583 |
+
"rstrip": false,
|
| 584 |
+
"single_word": false,
|
| 585 |
+
"special": true
|
| 586 |
+
},
|
| 587 |
+
"128073": {
|
| 588 |
+
"content": "<|reserved_special_token_65|>",
|
| 589 |
+
"lstrip": false,
|
| 590 |
+
"normalized": false,
|
| 591 |
+
"rstrip": false,
|
| 592 |
+
"single_word": false,
|
| 593 |
+
"special": true
|
| 594 |
+
},
|
| 595 |
+
"128074": {
|
| 596 |
+
"content": "<|reserved_special_token_66|>",
|
| 597 |
+
"lstrip": false,
|
| 598 |
+
"normalized": false,
|
| 599 |
+
"rstrip": false,
|
| 600 |
+
"single_word": false,
|
| 601 |
+
"special": true
|
| 602 |
+
},
|
| 603 |
+
"128075": {
|
| 604 |
+
"content": "<|reserved_special_token_67|>",
|
| 605 |
+
"lstrip": false,
|
| 606 |
+
"normalized": false,
|
| 607 |
+
"rstrip": false,
|
| 608 |
+
"single_word": false,
|
| 609 |
+
"special": true
|
| 610 |
+
},
|
| 611 |
+
"128076": {
|
| 612 |
+
"content": "<|reserved_special_token_68|>",
|
| 613 |
+
"lstrip": false,
|
| 614 |
+
"normalized": false,
|
| 615 |
+
"rstrip": false,
|
| 616 |
+
"single_word": false,
|
| 617 |
+
"special": true
|
| 618 |
+
},
|
| 619 |
+
"128077": {
|
| 620 |
+
"content": "<|reserved_special_token_69|>",
|
| 621 |
+
"lstrip": false,
|
| 622 |
+
"normalized": false,
|
| 623 |
+
"rstrip": false,
|
| 624 |
+
"single_word": false,
|
| 625 |
+
"special": true
|
| 626 |
+
},
|
| 627 |
+
"128078": {
|
| 628 |
+
"content": "<|reserved_special_token_70|>",
|
| 629 |
+
"lstrip": false,
|
| 630 |
+
"normalized": false,
|
| 631 |
+
"rstrip": false,
|
| 632 |
+
"single_word": false,
|
| 633 |
+
"special": true
|
| 634 |
+
},
|
| 635 |
+
"128079": {
|
| 636 |
+
"content": "<|reserved_special_token_71|>",
|
| 637 |
+
"lstrip": false,
|
| 638 |
+
"normalized": false,
|
| 639 |
+
"rstrip": false,
|
| 640 |
+
"single_word": false,
|
| 641 |
+
"special": true
|
| 642 |
+
},
|
| 643 |
+
"128080": {
|
| 644 |
+
"content": "<|reserved_special_token_72|>",
|
| 645 |
+
"lstrip": false,
|
| 646 |
+
"normalized": false,
|
| 647 |
+
"rstrip": false,
|
| 648 |
+
"single_word": false,
|
| 649 |
+
"special": true
|
| 650 |
+
},
|
| 651 |
+
"128081": {
|
| 652 |
+
"content": "<|reserved_special_token_73|>",
|
| 653 |
+
"lstrip": false,
|
| 654 |
+
"normalized": false,
|
| 655 |
+
"rstrip": false,
|
| 656 |
+
"single_word": false,
|
| 657 |
+
"special": true
|
| 658 |
+
},
|
| 659 |
+
"128082": {
|
| 660 |
+
"content": "<|reserved_special_token_74|>",
|
| 661 |
+
"lstrip": false,
|
| 662 |
+
"normalized": false,
|
| 663 |
+
"rstrip": false,
|
| 664 |
+
"single_word": false,
|
| 665 |
+
"special": true
|
| 666 |
+
},
|
| 667 |
+
"128083": {
|
| 668 |
+
"content": "<|reserved_special_token_75|>",
|
| 669 |
+
"lstrip": false,
|
| 670 |
+
"normalized": false,
|
| 671 |
+
"rstrip": false,
|
| 672 |
+
"single_word": false,
|
| 673 |
+
"special": true
|
| 674 |
+
},
|
| 675 |
+
"128084": {
|
| 676 |
+
"content": "<|reserved_special_token_76|>",
|
| 677 |
+
"lstrip": false,
|
| 678 |
+
"normalized": false,
|
| 679 |
+
"rstrip": false,
|
| 680 |
+
"single_word": false,
|
| 681 |
+
"special": true
|
| 682 |
+
},
|
| 683 |
+
"128085": {
|
| 684 |
+
"content": "<|reserved_special_token_77|>",
|
| 685 |
+
"lstrip": false,
|
| 686 |
+
"normalized": false,
|
| 687 |
+
"rstrip": false,
|
| 688 |
+
"single_word": false,
|
| 689 |
+
"special": true
|
| 690 |
+
},
|
| 691 |
+
"128086": {
|
| 692 |
+
"content": "<|reserved_special_token_78|>",
|
| 693 |
+
"lstrip": false,
|
| 694 |
+
"normalized": false,
|
| 695 |
+
"rstrip": false,
|
| 696 |
+
"single_word": false,
|
| 697 |
+
"special": true
|
| 698 |
+
},
|
| 699 |
+
"128087": {
|
| 700 |
+
"content": "<|reserved_special_token_79|>",
|
| 701 |
+
"lstrip": false,
|
| 702 |
+
"normalized": false,
|
| 703 |
+
"rstrip": false,
|
| 704 |
+
"single_word": false,
|
| 705 |
+
"special": true
|
| 706 |
+
},
|
| 707 |
+
"128088": {
|
| 708 |
+
"content": "<|reserved_special_token_80|>",
|
| 709 |
+
"lstrip": false,
|
| 710 |
+
"normalized": false,
|
| 711 |
+
"rstrip": false,
|
| 712 |
+
"single_word": false,
|
| 713 |
+
"special": true
|
| 714 |
+
},
|
| 715 |
+
"128089": {
|
| 716 |
+
"content": "<|reserved_special_token_81|>",
|
| 717 |
+
"lstrip": false,
|
| 718 |
+
"normalized": false,
|
| 719 |
+
"rstrip": false,
|
| 720 |
+
"single_word": false,
|
| 721 |
+
"special": true
|
| 722 |
+
},
|
| 723 |
+
"128090": {
|
| 724 |
+
"content": "<|reserved_special_token_82|>",
|
| 725 |
+
"lstrip": false,
|
| 726 |
+
"normalized": false,
|
| 727 |
+
"rstrip": false,
|
| 728 |
+
"single_word": false,
|
| 729 |
+
"special": true
|
| 730 |
+
},
|
| 731 |
+
"128091": {
|
| 732 |
+
"content": "<|reserved_special_token_83|>",
|
| 733 |
+
"lstrip": false,
|
| 734 |
+
"normalized": false,
|
| 735 |
+
"rstrip": false,
|
| 736 |
+
"single_word": false,
|
| 737 |
+
"special": true
|
| 738 |
+
},
|
| 739 |
+
"128092": {
|
| 740 |
+
"content": "<|reserved_special_token_84|>",
|
| 741 |
+
"lstrip": false,
|
| 742 |
+
"normalized": false,
|
| 743 |
+
"rstrip": false,
|
| 744 |
+
"single_word": false,
|
| 745 |
+
"special": true
|
| 746 |
+
},
|
| 747 |
+
"128093": {
|
| 748 |
+
"content": "<|reserved_special_token_85|>",
|
| 749 |
+
"lstrip": false,
|
| 750 |
+
"normalized": false,
|
| 751 |
+
"rstrip": false,
|
| 752 |
+
"single_word": false,
|
| 753 |
+
"special": true
|
| 754 |
+
},
|
| 755 |
+
"128094": {
|
| 756 |
+
"content": "<|reserved_special_token_86|>",
|
| 757 |
+
"lstrip": false,
|
| 758 |
+
"normalized": false,
|
| 759 |
+
"rstrip": false,
|
| 760 |
+
"single_word": false,
|
| 761 |
+
"special": true
|
| 762 |
+
},
|
| 763 |
+
"128095": {
|
| 764 |
+
"content": "<|reserved_special_token_87|>",
|
| 765 |
+
"lstrip": false,
|
| 766 |
+
"normalized": false,
|
| 767 |
+
"rstrip": false,
|
| 768 |
+
"single_word": false,
|
| 769 |
+
"special": true
|
| 770 |
+
},
|
| 771 |
+
"128096": {
|
| 772 |
+
"content": "<|reserved_special_token_88|>",
|
| 773 |
+
"lstrip": false,
|
| 774 |
+
"normalized": false,
|
| 775 |
+
"rstrip": false,
|
| 776 |
+
"single_word": false,
|
| 777 |
+
"special": true
|
| 778 |
+
},
|
| 779 |
+
"128097": {
|
| 780 |
+
"content": "<|reserved_special_token_89|>",
|
| 781 |
+
"lstrip": false,
|
| 782 |
+
"normalized": false,
|
| 783 |
+
"rstrip": false,
|
| 784 |
+
"single_word": false,
|
| 785 |
+
"special": true
|
| 786 |
+
},
|
| 787 |
+
"128098": {
|
| 788 |
+
"content": "<|reserved_special_token_90|>",
|
| 789 |
+
"lstrip": false,
|
| 790 |
+
"normalized": false,
|
| 791 |
+
"rstrip": false,
|
| 792 |
+
"single_word": false,
|
| 793 |
+
"special": true
|
| 794 |
+
},
|
| 795 |
+
"128099": {
|
| 796 |
+
"content": "<|reserved_special_token_91|>",
|
| 797 |
+
"lstrip": false,
|
| 798 |
+
"normalized": false,
|
| 799 |
+
"rstrip": false,
|
| 800 |
+
"single_word": false,
|
| 801 |
+
"special": true
|
| 802 |
+
},
|
| 803 |
+
"128100": {
|
| 804 |
+
"content": "<|reserved_special_token_92|>",
|
| 805 |
+
"lstrip": false,
|
| 806 |
+
"normalized": false,
|
| 807 |
+
"rstrip": false,
|
| 808 |
+
"single_word": false,
|
| 809 |
+
"special": true
|
| 810 |
+
},
|
| 811 |
+
"128101": {
|
| 812 |
+
"content": "<|reserved_special_token_93|>",
|
| 813 |
+
"lstrip": false,
|
| 814 |
+
"normalized": false,
|
| 815 |
+
"rstrip": false,
|
| 816 |
+
"single_word": false,
|
| 817 |
+
"special": true
|
| 818 |
+
},
|
| 819 |
+
"128102": {
|
| 820 |
+
"content": "<|reserved_special_token_94|>",
|
| 821 |
+
"lstrip": false,
|
| 822 |
+
"normalized": false,
|
| 823 |
+
"rstrip": false,
|
| 824 |
+
"single_word": false,
|
| 825 |
+
"special": true
|
| 826 |
+
},
|
| 827 |
+
"128103": {
|
| 828 |
+
"content": "<|reserved_special_token_95|>",
|
| 829 |
+
"lstrip": false,
|
| 830 |
+
"normalized": false,
|
| 831 |
+
"rstrip": false,
|
| 832 |
+
"single_word": false,
|
| 833 |
+
"special": true
|
| 834 |
+
},
|
| 835 |
+
"128104": {
|
| 836 |
+
"content": "<|reserved_special_token_96|>",
|
| 837 |
+
"lstrip": false,
|
| 838 |
+
"normalized": false,
|
| 839 |
+
"rstrip": false,
|
| 840 |
+
"single_word": false,
|
| 841 |
+
"special": true
|
| 842 |
+
},
|
| 843 |
+
"128105": {
|
| 844 |
+
"content": "<|reserved_special_token_97|>",
|
| 845 |
+
"lstrip": false,
|
| 846 |
+
"normalized": false,
|
| 847 |
+
"rstrip": false,
|
| 848 |
+
"single_word": false,
|
| 849 |
+
"special": true
|
| 850 |
+
},
|
| 851 |
+
"128106": {
|
| 852 |
+
"content": "<|reserved_special_token_98|>",
|
| 853 |
+
"lstrip": false,
|
| 854 |
+
"normalized": false,
|
| 855 |
+
"rstrip": false,
|
| 856 |
+
"single_word": false,
|
| 857 |
+
"special": true
|
| 858 |
+
},
|
| 859 |
+
"128107": {
|
| 860 |
+
"content": "<|reserved_special_token_99|>",
|
| 861 |
+
"lstrip": false,
|
| 862 |
+
"normalized": false,
|
| 863 |
+
"rstrip": false,
|
| 864 |
+
"single_word": false,
|
| 865 |
+
"special": true
|
| 866 |
+
},
|
| 867 |
+
"128108": {
|
| 868 |
+
"content": "<|reserved_special_token_100|>",
|
| 869 |
+
"lstrip": false,
|
| 870 |
+
"normalized": false,
|
| 871 |
+
"rstrip": false,
|
| 872 |
+
"single_word": false,
|
| 873 |
+
"special": true
|
| 874 |
+
},
|
| 875 |
+
"128109": {
|
| 876 |
+
"content": "<|reserved_special_token_101|>",
|
| 877 |
+
"lstrip": false,
|
| 878 |
+
"normalized": false,
|
| 879 |
+
"rstrip": false,
|
| 880 |
+
"single_word": false,
|
| 881 |
+
"special": true
|
| 882 |
+
},
|
| 883 |
+
"128110": {
|
| 884 |
+
"content": "<|reserved_special_token_102|>",
|
| 885 |
+
"lstrip": false,
|
| 886 |
+
"normalized": false,
|
| 887 |
+
"rstrip": false,
|
| 888 |
+
"single_word": false,
|
| 889 |
+
"special": true
|
| 890 |
+
},
|
| 891 |
+
"128111": {
|
| 892 |
+
"content": "<|reserved_special_token_103|>",
|
| 893 |
+
"lstrip": false,
|
| 894 |
+
"normalized": false,
|
| 895 |
+
"rstrip": false,
|
| 896 |
+
"single_word": false,
|
| 897 |
+
"special": true
|
| 898 |
+
},
|
| 899 |
+
"128112": {
|
| 900 |
+
"content": "<|reserved_special_token_104|>",
|
| 901 |
+
"lstrip": false,
|
| 902 |
+
"normalized": false,
|
| 903 |
+
"rstrip": false,
|
| 904 |
+
"single_word": false,
|
| 905 |
+
"special": true
|
| 906 |
+
},
|
| 907 |
+
"128113": {
|
| 908 |
+
"content": "<|reserved_special_token_105|>",
|
| 909 |
+
"lstrip": false,
|
| 910 |
+
"normalized": false,
|
| 911 |
+
"rstrip": false,
|
| 912 |
+
"single_word": false,
|
| 913 |
+
"special": true
|
| 914 |
+
},
|
| 915 |
+
"128114": {
|
| 916 |
+
"content": "<|reserved_special_token_106|>",
|
| 917 |
+
"lstrip": false,
|
| 918 |
+
"normalized": false,
|
| 919 |
+
"rstrip": false,
|
| 920 |
+
"single_word": false,
|
| 921 |
+
"special": true
|
| 922 |
+
},
|
| 923 |
+
"128115": {
|
| 924 |
+
"content": "<|reserved_special_token_107|>",
|
| 925 |
+
"lstrip": false,
|
| 926 |
+
"normalized": false,
|
| 927 |
+
"rstrip": false,
|
| 928 |
+
"single_word": false,
|
| 929 |
+
"special": true
|
| 930 |
+
},
|
| 931 |
+
"128116": {
|
| 932 |
+
"content": "<|reserved_special_token_108|>",
|
| 933 |
+
"lstrip": false,
|
| 934 |
+
"normalized": false,
|
| 935 |
+
"rstrip": false,
|
| 936 |
+
"single_word": false,
|
| 937 |
+
"special": true
|
| 938 |
+
},
|
| 939 |
+
"128117": {
|
| 940 |
+
"content": "<|reserved_special_token_109|>",
|
| 941 |
+
"lstrip": false,
|
| 942 |
+
"normalized": false,
|
| 943 |
+
"rstrip": false,
|
| 944 |
+
"single_word": false,
|
| 945 |
+
"special": true
|
| 946 |
+
},
|
| 947 |
+
"128118": {
|
| 948 |
+
"content": "<|reserved_special_token_110|>",
|
| 949 |
+
"lstrip": false,
|
| 950 |
+
"normalized": false,
|
| 951 |
+
"rstrip": false,
|
| 952 |
+
"single_word": false,
|
| 953 |
+
"special": true
|
| 954 |
+
},
|
| 955 |
+
"128119": {
|
| 956 |
+
"content": "<|reserved_special_token_111|>",
|
| 957 |
+
"lstrip": false,
|
| 958 |
+
"normalized": false,
|
| 959 |
+
"rstrip": false,
|
| 960 |
+
"single_word": false,
|
| 961 |
+
"special": true
|
| 962 |
+
},
|
| 963 |
+
"128120": {
|
| 964 |
+
"content": "<|reserved_special_token_112|>",
|
| 965 |
+
"lstrip": false,
|
| 966 |
+
"normalized": false,
|
| 967 |
+
"rstrip": false,
|
| 968 |
+
"single_word": false,
|
| 969 |
+
"special": true
|
| 970 |
+
},
|
| 971 |
+
"128121": {
|
| 972 |
+
"content": "<|reserved_special_token_113|>",
|
| 973 |
+
"lstrip": false,
|
| 974 |
+
"normalized": false,
|
| 975 |
+
"rstrip": false,
|
| 976 |
+
"single_word": false,
|
| 977 |
+
"special": true
|
| 978 |
+
},
|
| 979 |
+
"128122": {
|
| 980 |
+
"content": "<|reserved_special_token_114|>",
|
| 981 |
+
"lstrip": false,
|
| 982 |
+
"normalized": false,
|
| 983 |
+
"rstrip": false,
|
| 984 |
+
"single_word": false,
|
| 985 |
+
"special": true
|
| 986 |
+
},
|
| 987 |
+
"128123": {
|
| 988 |
+
"content": "<|reserved_special_token_115|>",
|
| 989 |
+
"lstrip": false,
|
| 990 |
+
"normalized": false,
|
| 991 |
+
"rstrip": false,
|
| 992 |
+
"single_word": false,
|
| 993 |
+
"special": true
|
| 994 |
+
},
|
| 995 |
+
"128124": {
|
| 996 |
+
"content": "<|reserved_special_token_116|>",
|
| 997 |
+
"lstrip": false,
|
| 998 |
+
"normalized": false,
|
| 999 |
+
"rstrip": false,
|
| 1000 |
+
"single_word": false,
|
| 1001 |
+
"special": true
|
| 1002 |
+
},
|
| 1003 |
+
"128125": {
|
| 1004 |
+
"content": "<|reserved_special_token_117|>",
|
| 1005 |
+
"lstrip": false,
|
| 1006 |
+
"normalized": false,
|
| 1007 |
+
"rstrip": false,
|
| 1008 |
+
"single_word": false,
|
| 1009 |
+
"special": true
|
| 1010 |
+
},
|
| 1011 |
+
"128126": {
|
| 1012 |
+
"content": "<|reserved_special_token_118|>",
|
| 1013 |
+
"lstrip": false,
|
| 1014 |
+
"normalized": false,
|
| 1015 |
+
"rstrip": false,
|
| 1016 |
+
"single_word": false,
|
| 1017 |
+
"special": true
|
| 1018 |
+
},
|
| 1019 |
+
"128127": {
|
| 1020 |
+
"content": "<|reserved_special_token_119|>",
|
| 1021 |
+
"lstrip": false,
|
| 1022 |
+
"normalized": false,
|
| 1023 |
+
"rstrip": false,
|
| 1024 |
+
"single_word": false,
|
| 1025 |
+
"special": true
|
| 1026 |
+
},
|
| 1027 |
+
"128128": {
|
| 1028 |
+
"content": "<|reserved_special_token_120|>",
|
| 1029 |
+
"lstrip": false,
|
| 1030 |
+
"normalized": false,
|
| 1031 |
+
"rstrip": false,
|
| 1032 |
+
"single_word": false,
|
| 1033 |
+
"special": true
|
| 1034 |
+
},
|
| 1035 |
+
"128129": {
|
| 1036 |
+
"content": "<|reserved_special_token_121|>",
|
| 1037 |
+
"lstrip": false,
|
| 1038 |
+
"normalized": false,
|
| 1039 |
+
"rstrip": false,
|
| 1040 |
+
"single_word": false,
|
| 1041 |
+
"special": true
|
| 1042 |
+
},
|
| 1043 |
+
"128130": {
|
| 1044 |
+
"content": "<|reserved_special_token_122|>",
|
| 1045 |
+
"lstrip": false,
|
| 1046 |
+
"normalized": false,
|
| 1047 |
+
"rstrip": false,
|
| 1048 |
+
"single_word": false,
|
| 1049 |
+
"special": true
|
| 1050 |
+
},
|
| 1051 |
+
"128131": {
|
| 1052 |
+
"content": "<|reserved_special_token_123|>",
|
| 1053 |
+
"lstrip": false,
|
| 1054 |
+
"normalized": false,
|
| 1055 |
+
"rstrip": false,
|
| 1056 |
+
"single_word": false,
|
| 1057 |
+
"special": true
|
| 1058 |
+
},
|
| 1059 |
+
"128132": {
|
| 1060 |
+
"content": "<|reserved_special_token_124|>",
|
| 1061 |
+
"lstrip": false,
|
| 1062 |
+
"normalized": false,
|
| 1063 |
+
"rstrip": false,
|
| 1064 |
+
"single_word": false,
|
| 1065 |
+
"special": true
|
| 1066 |
+
},
|
| 1067 |
+
"128133": {
|
| 1068 |
+
"content": "<|reserved_special_token_125|>",
|
| 1069 |
+
"lstrip": false,
|
| 1070 |
+
"normalized": false,
|
| 1071 |
+
"rstrip": false,
|
| 1072 |
+
"single_word": false,
|
| 1073 |
+
"special": true
|
| 1074 |
+
},
|
| 1075 |
+
"128134": {
|
| 1076 |
+
"content": "<|reserved_special_token_126|>",
|
| 1077 |
+
"lstrip": false,
|
| 1078 |
+
"normalized": false,
|
| 1079 |
+
"rstrip": false,
|
| 1080 |
+
"single_word": false,
|
| 1081 |
+
"special": true
|
| 1082 |
+
},
|
| 1083 |
+
"128135": {
|
| 1084 |
+
"content": "<|reserved_special_token_127|>",
|
| 1085 |
+
"lstrip": false,
|
| 1086 |
+
"normalized": false,
|
| 1087 |
+
"rstrip": false,
|
| 1088 |
+
"single_word": false,
|
| 1089 |
+
"special": true
|
| 1090 |
+
},
|
| 1091 |
+
"128136": {
|
| 1092 |
+
"content": "<|reserved_special_token_128|>",
|
| 1093 |
+
"lstrip": false,
|
| 1094 |
+
"normalized": false,
|
| 1095 |
+
"rstrip": false,
|
| 1096 |
+
"single_word": false,
|
| 1097 |
+
"special": true
|
| 1098 |
+
},
|
| 1099 |
+
"128137": {
|
| 1100 |
+
"content": "<|reserved_special_token_129|>",
|
| 1101 |
+
"lstrip": false,
|
| 1102 |
+
"normalized": false,
|
| 1103 |
+
"rstrip": false,
|
| 1104 |
+
"single_word": false,
|
| 1105 |
+
"special": true
|
| 1106 |
+
},
|
| 1107 |
+
"128138": {
|
| 1108 |
+
"content": "<|reserved_special_token_130|>",
|
| 1109 |
+
"lstrip": false,
|
| 1110 |
+
"normalized": false,
|
| 1111 |
+
"rstrip": false,
|
| 1112 |
+
"single_word": false,
|
| 1113 |
+
"special": true
|
| 1114 |
+
},
|
| 1115 |
+
"128139": {
|
| 1116 |
+
"content": "<|reserved_special_token_131|>",
|
| 1117 |
+
"lstrip": false,
|
| 1118 |
+
"normalized": false,
|
| 1119 |
+
"rstrip": false,
|
| 1120 |
+
"single_word": false,
|
| 1121 |
+
"special": true
|
| 1122 |
+
},
|
| 1123 |
+
"128140": {
|
| 1124 |
+
"content": "<|reserved_special_token_132|>",
|
| 1125 |
+
"lstrip": false,
|
| 1126 |
+
"normalized": false,
|
| 1127 |
+
"rstrip": false,
|
| 1128 |
+
"single_word": false,
|
| 1129 |
+
"special": true
|
| 1130 |
+
},
|
| 1131 |
+
"128141": {
|
| 1132 |
+
"content": "<|reserved_special_token_133|>",
|
| 1133 |
+
"lstrip": false,
|
| 1134 |
+
"normalized": false,
|
| 1135 |
+
"rstrip": false,
|
| 1136 |
+
"single_word": false,
|
| 1137 |
+
"special": true
|
| 1138 |
+
},
|
| 1139 |
+
"128142": {
|
| 1140 |
+
"content": "<|reserved_special_token_134|>",
|
| 1141 |
+
"lstrip": false,
|
| 1142 |
+
"normalized": false,
|
| 1143 |
+
"rstrip": false,
|
| 1144 |
+
"single_word": false,
|
| 1145 |
+
"special": true
|
| 1146 |
+
},
|
| 1147 |
+
"128143": {
|
| 1148 |
+
"content": "<|reserved_special_token_135|>",
|
| 1149 |
+
"lstrip": false,
|
| 1150 |
+
"normalized": false,
|
| 1151 |
+
"rstrip": false,
|
| 1152 |
+
"single_word": false,
|
| 1153 |
+
"special": true
|
| 1154 |
+
},
|
| 1155 |
+
"128144": {
|
| 1156 |
+
"content": "<|reserved_special_token_136|>",
|
| 1157 |
+
"lstrip": false,
|
| 1158 |
+
"normalized": false,
|
| 1159 |
+
"rstrip": false,
|
| 1160 |
+
"single_word": false,
|
| 1161 |
+
"special": true
|
| 1162 |
+
},
|
| 1163 |
+
"128145": {
|
| 1164 |
+
"content": "<|reserved_special_token_137|>",
|
| 1165 |
+
"lstrip": false,
|
| 1166 |
+
"normalized": false,
|
| 1167 |
+
"rstrip": false,
|
| 1168 |
+
"single_word": false,
|
| 1169 |
+
"special": true
|
| 1170 |
+
},
|
| 1171 |
+
"128146": {
|
| 1172 |
+
"content": "<|reserved_special_token_138|>",
|
| 1173 |
+
"lstrip": false,
|
| 1174 |
+
"normalized": false,
|
| 1175 |
+
"rstrip": false,
|
| 1176 |
+
"single_word": false,
|
| 1177 |
+
"special": true
|
| 1178 |
+
},
|
| 1179 |
+
"128147": {
|
| 1180 |
+
"content": "<|reserved_special_token_139|>",
|
| 1181 |
+
"lstrip": false,
|
| 1182 |
+
"normalized": false,
|
| 1183 |
+
"rstrip": false,
|
| 1184 |
+
"single_word": false,
|
| 1185 |
+
"special": true
|
| 1186 |
+
},
|
| 1187 |
+
"128148": {
|
| 1188 |
+
"content": "<|reserved_special_token_140|>",
|
| 1189 |
+
"lstrip": false,
|
| 1190 |
+
"normalized": false,
|
| 1191 |
+
"rstrip": false,
|
| 1192 |
+
"single_word": false,
|
| 1193 |
+
"special": true
|
| 1194 |
+
},
|
| 1195 |
+
"128149": {
|
| 1196 |
+
"content": "<|reserved_special_token_141|>",
|
| 1197 |
+
"lstrip": false,
|
| 1198 |
+
"normalized": false,
|
| 1199 |
+
"rstrip": false,
|
| 1200 |
+
"single_word": false,
|
| 1201 |
+
"special": true
|
| 1202 |
+
},
|
| 1203 |
+
"128150": {
|
| 1204 |
+
"content": "<|reserved_special_token_142|>",
|
| 1205 |
+
"lstrip": false,
|
| 1206 |
+
"normalized": false,
|
| 1207 |
+
"rstrip": false,
|
| 1208 |
+
"single_word": false,
|
| 1209 |
+
"special": true
|
| 1210 |
+
},
|
| 1211 |
+
"128151": {
|
| 1212 |
+
"content": "<|reserved_special_token_143|>",
|
| 1213 |
+
"lstrip": false,
|
| 1214 |
+
"normalized": false,
|
| 1215 |
+
"rstrip": false,
|
| 1216 |
+
"single_word": false,
|
| 1217 |
+
"special": true
|
| 1218 |
+
},
|
| 1219 |
+
"128152": {
|
| 1220 |
+
"content": "<|reserved_special_token_144|>",
|
| 1221 |
+
"lstrip": false,
|
| 1222 |
+
"normalized": false,
|
| 1223 |
+
"rstrip": false,
|
| 1224 |
+
"single_word": false,
|
| 1225 |
+
"special": true
|
| 1226 |
+
},
|
| 1227 |
+
"128153": {
|
| 1228 |
+
"content": "<|reserved_special_token_145|>",
|
| 1229 |
+
"lstrip": false,
|
| 1230 |
+
"normalized": false,
|
| 1231 |
+
"rstrip": false,
|
| 1232 |
+
"single_word": false,
|
| 1233 |
+
"special": true
|
| 1234 |
+
},
|
| 1235 |
+
"128154": {
|
| 1236 |
+
"content": "<|reserved_special_token_146|>",
|
| 1237 |
+
"lstrip": false,
|
| 1238 |
+
"normalized": false,
|
| 1239 |
+
"rstrip": false,
|
| 1240 |
+
"single_word": false,
|
| 1241 |
+
"special": true
|
| 1242 |
+
},
|
| 1243 |
+
"128155": {
|
| 1244 |
+
"content": "<|reserved_special_token_147|>",
|
| 1245 |
+
"lstrip": false,
|
| 1246 |
+
"normalized": false,
|
| 1247 |
+
"rstrip": false,
|
| 1248 |
+
"single_word": false,
|
| 1249 |
+
"special": true
|
| 1250 |
+
},
|
| 1251 |
+
"128156": {
|
| 1252 |
+
"content": "<|reserved_special_token_148|>",
|
| 1253 |
+
"lstrip": false,
|
| 1254 |
+
"normalized": false,
|
| 1255 |
+
"rstrip": false,
|
| 1256 |
+
"single_word": false,
|
| 1257 |
+
"special": true
|
| 1258 |
+
},
|
| 1259 |
+
"128157": {
|
| 1260 |
+
"content": "<|reserved_special_token_149|>",
|
| 1261 |
+
"lstrip": false,
|
| 1262 |
+
"normalized": false,
|
| 1263 |
+
"rstrip": false,
|
| 1264 |
+
"single_word": false,
|
| 1265 |
+
"special": true
|
| 1266 |
+
},
|
| 1267 |
+
"128158": {
|
| 1268 |
+
"content": "<|reserved_special_token_150|>",
|
| 1269 |
+
"lstrip": false,
|
| 1270 |
+
"normalized": false,
|
| 1271 |
+
"rstrip": false,
|
| 1272 |
+
"single_word": false,
|
| 1273 |
+
"special": true
|
| 1274 |
+
},
|
| 1275 |
+
"128159": {
|
| 1276 |
+
"content": "<|reserved_special_token_151|>",
|
| 1277 |
+
"lstrip": false,
|
| 1278 |
+
"normalized": false,
|
| 1279 |
+
"rstrip": false,
|
| 1280 |
+
"single_word": false,
|
| 1281 |
+
"special": true
|
| 1282 |
+
},
|
| 1283 |
+
"128160": {
|
| 1284 |
+
"content": "<|reserved_special_token_152|>",
|
| 1285 |
+
"lstrip": false,
|
| 1286 |
+
"normalized": false,
|
| 1287 |
+
"rstrip": false,
|
| 1288 |
+
"single_word": false,
|
| 1289 |
+
"special": true
|
| 1290 |
+
},
|
| 1291 |
+
"128161": {
|
| 1292 |
+
"content": "<|reserved_special_token_153|>",
|
| 1293 |
+
"lstrip": false,
|
| 1294 |
+
"normalized": false,
|
| 1295 |
+
"rstrip": false,
|
| 1296 |
+
"single_word": false,
|
| 1297 |
+
"special": true
|
| 1298 |
+
},
|
| 1299 |
+
"128162": {
|
| 1300 |
+
"content": "<|reserved_special_token_154|>",
|
| 1301 |
+
"lstrip": false,
|
| 1302 |
+
"normalized": false,
|
| 1303 |
+
"rstrip": false,
|
| 1304 |
+
"single_word": false,
|
| 1305 |
+
"special": true
|
| 1306 |
+
},
|
| 1307 |
+
"128163": {
|
| 1308 |
+
"content": "<|reserved_special_token_155|>",
|
| 1309 |
+
"lstrip": false,
|
| 1310 |
+
"normalized": false,
|
| 1311 |
+
"rstrip": false,
|
| 1312 |
+
"single_word": false,
|
| 1313 |
+
"special": true
|
| 1314 |
+
},
|
| 1315 |
+
"128164": {
|
| 1316 |
+
"content": "<|reserved_special_token_156|>",
|
| 1317 |
+
"lstrip": false,
|
| 1318 |
+
"normalized": false,
|
| 1319 |
+
"rstrip": false,
|
| 1320 |
+
"single_word": false,
|
| 1321 |
+
"special": true
|
| 1322 |
+
},
|
| 1323 |
+
"128165": {
|
| 1324 |
+
"content": "<|reserved_special_token_157|>",
|
| 1325 |
+
"lstrip": false,
|
| 1326 |
+
"normalized": false,
|
| 1327 |
+
"rstrip": false,
|
| 1328 |
+
"single_word": false,
|
| 1329 |
+
"special": true
|
| 1330 |
+
},
|
| 1331 |
+
"128166": {
|
| 1332 |
+
"content": "<|reserved_special_token_158|>",
|
| 1333 |
+
"lstrip": false,
|
| 1334 |
+
"normalized": false,
|
| 1335 |
+
"rstrip": false,
|
| 1336 |
+
"single_word": false,
|
| 1337 |
+
"special": true
|
| 1338 |
+
},
|
| 1339 |
+
"128167": {
|
| 1340 |
+
"content": "<|reserved_special_token_159|>",
|
| 1341 |
+
"lstrip": false,
|
| 1342 |
+
"normalized": false,
|
| 1343 |
+
"rstrip": false,
|
| 1344 |
+
"single_word": false,
|
| 1345 |
+
"special": true
|
| 1346 |
+
},
|
| 1347 |
+
"128168": {
|
| 1348 |
+
"content": "<|reserved_special_token_160|>",
|
| 1349 |
+
"lstrip": false,
|
| 1350 |
+
"normalized": false,
|
| 1351 |
+
"rstrip": false,
|
| 1352 |
+
"single_word": false,
|
| 1353 |
+
"special": true
|
| 1354 |
+
},
|
| 1355 |
+
"128169": {
|
| 1356 |
+
"content": "<|reserved_special_token_161|>",
|
| 1357 |
+
"lstrip": false,
|
| 1358 |
+
"normalized": false,
|
| 1359 |
+
"rstrip": false,
|
| 1360 |
+
"single_word": false,
|
| 1361 |
+
"special": true
|
| 1362 |
+
},
|
| 1363 |
+
"128170": {
|
| 1364 |
+
"content": "<|reserved_special_token_162|>",
|
| 1365 |
+
"lstrip": false,
|
| 1366 |
+
"normalized": false,
|
| 1367 |
+
"rstrip": false,
|
| 1368 |
+
"single_word": false,
|
| 1369 |
+
"special": true
|
| 1370 |
+
},
|
| 1371 |
+
"128171": {
|
| 1372 |
+
"content": "<|reserved_special_token_163|>",
|
| 1373 |
+
"lstrip": false,
|
| 1374 |
+
"normalized": false,
|
| 1375 |
+
"rstrip": false,
|
| 1376 |
+
"single_word": false,
|
| 1377 |
+
"special": true
|
| 1378 |
+
},
|
| 1379 |
+
"128172": {
|
| 1380 |
+
"content": "<|reserved_special_token_164|>",
|
| 1381 |
+
"lstrip": false,
|
| 1382 |
+
"normalized": false,
|
| 1383 |
+
"rstrip": false,
|
| 1384 |
+
"single_word": false,
|
| 1385 |
+
"special": true
|
| 1386 |
+
},
|
| 1387 |
+
"128173": {
|
| 1388 |
+
"content": "<|reserved_special_token_165|>",
|
| 1389 |
+
"lstrip": false,
|
| 1390 |
+
"normalized": false,
|
| 1391 |
+
"rstrip": false,
|
| 1392 |
+
"single_word": false,
|
| 1393 |
+
"special": true
|
| 1394 |
+
},
|
| 1395 |
+
"128174": {
|
| 1396 |
+
"content": "<|reserved_special_token_166|>",
|
| 1397 |
+
"lstrip": false,
|
| 1398 |
+
"normalized": false,
|
| 1399 |
+
"rstrip": false,
|
| 1400 |
+
"single_word": false,
|
| 1401 |
+
"special": true
|
| 1402 |
+
},
|
| 1403 |
+
"128175": {
|
| 1404 |
+
"content": "<|reserved_special_token_167|>",
|
| 1405 |
+
"lstrip": false,
|
| 1406 |
+
"normalized": false,
|
| 1407 |
+
"rstrip": false,
|
| 1408 |
+
"single_word": false,
|
| 1409 |
+
"special": true
|
| 1410 |
+
},
|
| 1411 |
+
"128176": {
|
| 1412 |
+
"content": "<|reserved_special_token_168|>",
|
| 1413 |
+
"lstrip": false,
|
| 1414 |
+
"normalized": false,
|
| 1415 |
+
"rstrip": false,
|
| 1416 |
+
"single_word": false,
|
| 1417 |
+
"special": true
|
| 1418 |
+
},
|
| 1419 |
+
"128177": {
|
| 1420 |
+
"content": "<|reserved_special_token_169|>",
|
| 1421 |
+
"lstrip": false,
|
| 1422 |
+
"normalized": false,
|
| 1423 |
+
"rstrip": false,
|
| 1424 |
+
"single_word": false,
|
| 1425 |
+
"special": true
|
| 1426 |
+
},
|
| 1427 |
+
"128178": {
|
| 1428 |
+
"content": "<|reserved_special_token_170|>",
|
| 1429 |
+
"lstrip": false,
|
| 1430 |
+
"normalized": false,
|
| 1431 |
+
"rstrip": false,
|
| 1432 |
+
"single_word": false,
|
| 1433 |
+
"special": true
|
| 1434 |
+
},
|
| 1435 |
+
"128179": {
|
| 1436 |
+
"content": "<|reserved_special_token_171|>",
|
| 1437 |
+
"lstrip": false,
|
| 1438 |
+
"normalized": false,
|
| 1439 |
+
"rstrip": false,
|
| 1440 |
+
"single_word": false,
|
| 1441 |
+
"special": true
|
| 1442 |
+
},
|
| 1443 |
+
"128180": {
|
| 1444 |
+
"content": "<|reserved_special_token_172|>",
|
| 1445 |
+
"lstrip": false,
|
| 1446 |
+
"normalized": false,
|
| 1447 |
+
"rstrip": false,
|
| 1448 |
+
"single_word": false,
|
| 1449 |
+
"special": true
|
| 1450 |
+
},
|
| 1451 |
+
"128181": {
|
| 1452 |
+
"content": "<|reserved_special_token_173|>",
|
| 1453 |
+
"lstrip": false,
|
| 1454 |
+
"normalized": false,
|
| 1455 |
+
"rstrip": false,
|
| 1456 |
+
"single_word": false,
|
| 1457 |
+
"special": true
|
| 1458 |
+
},
|
| 1459 |
+
"128182": {
|
| 1460 |
+
"content": "<|reserved_special_token_174|>",
|
| 1461 |
+
"lstrip": false,
|
| 1462 |
+
"normalized": false,
|
| 1463 |
+
"rstrip": false,
|
| 1464 |
+
"single_word": false,
|
| 1465 |
+
"special": true
|
| 1466 |
+
},
|
| 1467 |
+
"128183": {
|
| 1468 |
+
"content": "<|reserved_special_token_175|>",
|
| 1469 |
+
"lstrip": false,
|
| 1470 |
+
"normalized": false,
|
| 1471 |
+
"rstrip": false,
|
| 1472 |
+
"single_word": false,
|
| 1473 |
+
"special": true
|
| 1474 |
+
},
|
| 1475 |
+
"128184": {
|
| 1476 |
+
"content": "<|reserved_special_token_176|>",
|
| 1477 |
+
"lstrip": false,
|
| 1478 |
+
"normalized": false,
|
| 1479 |
+
"rstrip": false,
|
| 1480 |
+
"single_word": false,
|
| 1481 |
+
"special": true
|
| 1482 |
+
},
|
| 1483 |
+
"128185": {
|
| 1484 |
+
"content": "<|reserved_special_token_177|>",
|
| 1485 |
+
"lstrip": false,
|
| 1486 |
+
"normalized": false,
|
| 1487 |
+
"rstrip": false,
|
| 1488 |
+
"single_word": false,
|
| 1489 |
+
"special": true
|
| 1490 |
+
},
|
| 1491 |
+
"128186": {
|
| 1492 |
+
"content": "<|reserved_special_token_178|>",
|
| 1493 |
+
"lstrip": false,
|
| 1494 |
+
"normalized": false,
|
| 1495 |
+
"rstrip": false,
|
| 1496 |
+
"single_word": false,
|
| 1497 |
+
"special": true
|
| 1498 |
+
},
|
| 1499 |
+
"128187": {
|
| 1500 |
+
"content": "<|reserved_special_token_179|>",
|
| 1501 |
+
"lstrip": false,
|
| 1502 |
+
"normalized": false,
|
| 1503 |
+
"rstrip": false,
|
| 1504 |
+
"single_word": false,
|
| 1505 |
+
"special": true
|
| 1506 |
+
},
|
| 1507 |
+
"128188": {
|
| 1508 |
+
"content": "<|reserved_special_token_180|>",
|
| 1509 |
+
"lstrip": false,
|
| 1510 |
+
"normalized": false,
|
| 1511 |
+
"rstrip": false,
|
| 1512 |
+
"single_word": false,
|
| 1513 |
+
"special": true
|
| 1514 |
+
},
|
| 1515 |
+
"128189": {
|
| 1516 |
+
"content": "<|reserved_special_token_181|>",
|
| 1517 |
+
"lstrip": false,
|
| 1518 |
+
"normalized": false,
|
| 1519 |
+
"rstrip": false,
|
| 1520 |
+
"single_word": false,
|
| 1521 |
+
"special": true
|
| 1522 |
+
},
|
| 1523 |
+
"128190": {
|
| 1524 |
+
"content": "<|reserved_special_token_182|>",
|
| 1525 |
+
"lstrip": false,
|
| 1526 |
+
"normalized": false,
|
| 1527 |
+
"rstrip": false,
|
| 1528 |
+
"single_word": false,
|
| 1529 |
+
"special": true
|
| 1530 |
+
},
|
| 1531 |
+
"128191": {
|
| 1532 |
+
"content": "<|reserved_special_token_183|>",
|
| 1533 |
+
"lstrip": false,
|
| 1534 |
+
"normalized": false,
|
| 1535 |
+
"rstrip": false,
|
| 1536 |
+
"single_word": false,
|
| 1537 |
+
"special": true
|
| 1538 |
+
},
|
| 1539 |
+
"128192": {
|
| 1540 |
+
"content": "<|reserved_special_token_184|>",
|
| 1541 |
+
"lstrip": false,
|
| 1542 |
+
"normalized": false,
|
| 1543 |
+
"rstrip": false,
|
| 1544 |
+
"single_word": false,
|
| 1545 |
+
"special": true
|
| 1546 |
+
},
|
| 1547 |
+
"128193": {
|
| 1548 |
+
"content": "<|reserved_special_token_185|>",
|
| 1549 |
+
"lstrip": false,
|
| 1550 |
+
"normalized": false,
|
| 1551 |
+
"rstrip": false,
|
| 1552 |
+
"single_word": false,
|
| 1553 |
+
"special": true
|
| 1554 |
+
},
|
| 1555 |
+
"128194": {
|
| 1556 |
+
"content": "<|reserved_special_token_186|>",
|
| 1557 |
+
"lstrip": false,
|
| 1558 |
+
"normalized": false,
|
| 1559 |
+
"rstrip": false,
|
| 1560 |
+
"single_word": false,
|
| 1561 |
+
"special": true
|
| 1562 |
+
},
|
| 1563 |
+
"128195": {
|
| 1564 |
+
"content": "<|reserved_special_token_187|>",
|
| 1565 |
+
"lstrip": false,
|
| 1566 |
+
"normalized": false,
|
| 1567 |
+
"rstrip": false,
|
| 1568 |
+
"single_word": false,
|
| 1569 |
+
"special": true
|
| 1570 |
+
},
|
| 1571 |
+
"128196": {
|
| 1572 |
+
"content": "<|reserved_special_token_188|>",
|
| 1573 |
+
"lstrip": false,
|
| 1574 |
+
"normalized": false,
|
| 1575 |
+
"rstrip": false,
|
| 1576 |
+
"single_word": false,
|
| 1577 |
+
"special": true
|
| 1578 |
+
},
|
| 1579 |
+
"128197": {
|
| 1580 |
+
"content": "<|reserved_special_token_189|>",
|
| 1581 |
+
"lstrip": false,
|
| 1582 |
+
"normalized": false,
|
| 1583 |
+
"rstrip": false,
|
| 1584 |
+
"single_word": false,
|
| 1585 |
+
"special": true
|
| 1586 |
+
},
|
| 1587 |
+
"128198": {
|
| 1588 |
+
"content": "<|reserved_special_token_190|>",
|
| 1589 |
+
"lstrip": false,
|
| 1590 |
+
"normalized": false,
|
| 1591 |
+
"rstrip": false,
|
| 1592 |
+
"single_word": false,
|
| 1593 |
+
"special": true
|
| 1594 |
+
},
|
| 1595 |
+
"128199": {
|
| 1596 |
+
"content": "<|reserved_special_token_191|>",
|
| 1597 |
+
"lstrip": false,
|
| 1598 |
+
"normalized": false,
|
| 1599 |
+
"rstrip": false,
|
| 1600 |
+
"single_word": false,
|
| 1601 |
+
"special": true
|
| 1602 |
+
},
|
| 1603 |
+
"128200": {
|
| 1604 |
+
"content": "<|reserved_special_token_192|>",
|
| 1605 |
+
"lstrip": false,
|
| 1606 |
+
"normalized": false,
|
| 1607 |
+
"rstrip": false,
|
| 1608 |
+
"single_word": false,
|
| 1609 |
+
"special": true
|
| 1610 |
+
},
|
| 1611 |
+
"128201": {
|
| 1612 |
+
"content": "<|reserved_special_token_193|>",
|
| 1613 |
+
"lstrip": false,
|
| 1614 |
+
"normalized": false,
|
| 1615 |
+
"rstrip": false,
|
| 1616 |
+
"single_word": false,
|
| 1617 |
+
"special": true
|
| 1618 |
+
},
|
| 1619 |
+
"128202": {
|
| 1620 |
+
"content": "<|reserved_special_token_194|>",
|
| 1621 |
+
"lstrip": false,
|
| 1622 |
+
"normalized": false,
|
| 1623 |
+
"rstrip": false,
|
| 1624 |
+
"single_word": false,
|
| 1625 |
+
"special": true
|
| 1626 |
+
},
|
| 1627 |
+
"128203": {
|
| 1628 |
+
"content": "<|reserved_special_token_195|>",
|
| 1629 |
+
"lstrip": false,
|
| 1630 |
+
"normalized": false,
|
| 1631 |
+
"rstrip": false,
|
| 1632 |
+
"single_word": false,
|
| 1633 |
+
"special": true
|
| 1634 |
+
},
|
| 1635 |
+
"128204": {
|
| 1636 |
+
"content": "<|reserved_special_token_196|>",
|
| 1637 |
+
"lstrip": false,
|
| 1638 |
+
"normalized": false,
|
| 1639 |
+
"rstrip": false,
|
| 1640 |
+
"single_word": false,
|
| 1641 |
+
"special": true
|
| 1642 |
+
},
|
| 1643 |
+
"128205": {
|
| 1644 |
+
"content": "<|reserved_special_token_197|>",
|
| 1645 |
+
"lstrip": false,
|
| 1646 |
+
"normalized": false,
|
| 1647 |
+
"rstrip": false,
|
| 1648 |
+
"single_word": false,
|
| 1649 |
+
"special": true
|
| 1650 |
+
},
|
| 1651 |
+
"128206": {
|
| 1652 |
+
"content": "<|reserved_special_token_198|>",
|
| 1653 |
+
"lstrip": false,
|
| 1654 |
+
"normalized": false,
|
| 1655 |
+
"rstrip": false,
|
| 1656 |
+
"single_word": false,
|
| 1657 |
+
"special": true
|
| 1658 |
+
},
|
| 1659 |
+
"128207": {
|
| 1660 |
+
"content": "<|reserved_special_token_199|>",
|
| 1661 |
+
"lstrip": false,
|
| 1662 |
+
"normalized": false,
|
| 1663 |
+
"rstrip": false,
|
| 1664 |
+
"single_word": false,
|
| 1665 |
+
"special": true
|
| 1666 |
+
},
|
| 1667 |
+
"128208": {
|
| 1668 |
+
"content": "<|reserved_special_token_200|>",
|
| 1669 |
+
"lstrip": false,
|
| 1670 |
+
"normalized": false,
|
| 1671 |
+
"rstrip": false,
|
| 1672 |
+
"single_word": false,
|
| 1673 |
+
"special": true
|
| 1674 |
+
},
|
| 1675 |
+
"128209": {
|
| 1676 |
+
"content": "<|reserved_special_token_201|>",
|
| 1677 |
+
"lstrip": false,
|
| 1678 |
+
"normalized": false,
|
| 1679 |
+
"rstrip": false,
|
| 1680 |
+
"single_word": false,
|
| 1681 |
+
"special": true
|
| 1682 |
+
},
|
| 1683 |
+
"128210": {
|
| 1684 |
+
"content": "<|reserved_special_token_202|>",
|
| 1685 |
+
"lstrip": false,
|
| 1686 |
+
"normalized": false,
|
| 1687 |
+
"rstrip": false,
|
| 1688 |
+
"single_word": false,
|
| 1689 |
+
"special": true
|
| 1690 |
+
},
|
| 1691 |
+
"128211": {
|
| 1692 |
+
"content": "<|reserved_special_token_203|>",
|
| 1693 |
+
"lstrip": false,
|
| 1694 |
+
"normalized": false,
|
| 1695 |
+
"rstrip": false,
|
| 1696 |
+
"single_word": false,
|
| 1697 |
+
"special": true
|
| 1698 |
+
},
|
| 1699 |
+
"128212": {
|
| 1700 |
+
"content": "<|reserved_special_token_204|>",
|
| 1701 |
+
"lstrip": false,
|
| 1702 |
+
"normalized": false,
|
| 1703 |
+
"rstrip": false,
|
| 1704 |
+
"single_word": false,
|
| 1705 |
+
"special": true
|
| 1706 |
+
},
|
| 1707 |
+
"128213": {
|
| 1708 |
+
"content": "<|reserved_special_token_205|>",
|
| 1709 |
+
"lstrip": false,
|
| 1710 |
+
"normalized": false,
|
| 1711 |
+
"rstrip": false,
|
| 1712 |
+
"single_word": false,
|
| 1713 |
+
"special": true
|
| 1714 |
+
},
|
| 1715 |
+
"128214": {
|
| 1716 |
+
"content": "<|reserved_special_token_206|>",
|
| 1717 |
+
"lstrip": false,
|
| 1718 |
+
"normalized": false,
|
| 1719 |
+
"rstrip": false,
|
| 1720 |
+
"single_word": false,
|
| 1721 |
+
"special": true
|
| 1722 |
+
},
|
| 1723 |
+
"128215": {
|
| 1724 |
+
"content": "<|reserved_special_token_207|>",
|
| 1725 |
+
"lstrip": false,
|
| 1726 |
+
"normalized": false,
|
| 1727 |
+
"rstrip": false,
|
| 1728 |
+
"single_word": false,
|
| 1729 |
+
"special": true
|
| 1730 |
+
},
|
| 1731 |
+
"128216": {
|
| 1732 |
+
"content": "<|reserved_special_token_208|>",
|
| 1733 |
+
"lstrip": false,
|
| 1734 |
+
"normalized": false,
|
| 1735 |
+
"rstrip": false,
|
| 1736 |
+
"single_word": false,
|
| 1737 |
+
"special": true
|
| 1738 |
+
},
|
| 1739 |
+
"128217": {
|
| 1740 |
+
"content": "<|reserved_special_token_209|>",
|
| 1741 |
+
"lstrip": false,
|
| 1742 |
+
"normalized": false,
|
| 1743 |
+
"rstrip": false,
|
| 1744 |
+
"single_word": false,
|
| 1745 |
+
"special": true
|
| 1746 |
+
},
|
| 1747 |
+
"128218": {
|
| 1748 |
+
"content": "<|reserved_special_token_210|>",
|
| 1749 |
+
"lstrip": false,
|
| 1750 |
+
"normalized": false,
|
| 1751 |
+
"rstrip": false,
|
| 1752 |
+
"single_word": false,
|
| 1753 |
+
"special": true
|
| 1754 |
+
},
|
| 1755 |
+
"128219": {
|
| 1756 |
+
"content": "<|reserved_special_token_211|>",
|
| 1757 |
+
"lstrip": false,
|
| 1758 |
+
"normalized": false,
|
| 1759 |
+
"rstrip": false,
|
| 1760 |
+
"single_word": false,
|
| 1761 |
+
"special": true
|
| 1762 |
+
},
|
| 1763 |
+
"128220": {
|
| 1764 |
+
"content": "<|reserved_special_token_212|>",
|
| 1765 |
+
"lstrip": false,
|
| 1766 |
+
"normalized": false,
|
| 1767 |
+
"rstrip": false,
|
| 1768 |
+
"single_word": false,
|
| 1769 |
+
"special": true
|
| 1770 |
+
},
|
| 1771 |
+
"128221": {
|
| 1772 |
+
"content": "<|reserved_special_token_213|>",
|
| 1773 |
+
"lstrip": false,
|
| 1774 |
+
"normalized": false,
|
| 1775 |
+
"rstrip": false,
|
| 1776 |
+
"single_word": false,
|
| 1777 |
+
"special": true
|
| 1778 |
+
},
|
| 1779 |
+
"128222": {
|
| 1780 |
+
"content": "<|reserved_special_token_214|>",
|
| 1781 |
+
"lstrip": false,
|
| 1782 |
+
"normalized": false,
|
| 1783 |
+
"rstrip": false,
|
| 1784 |
+
"single_word": false,
|
| 1785 |
+
"special": true
|
| 1786 |
+
},
|
| 1787 |
+
"128223": {
|
| 1788 |
+
"content": "<|reserved_special_token_215|>",
|
| 1789 |
+
"lstrip": false,
|
| 1790 |
+
"normalized": false,
|
| 1791 |
+
"rstrip": false,
|
| 1792 |
+
"single_word": false,
|
| 1793 |
+
"special": true
|
| 1794 |
+
},
|
| 1795 |
+
"128224": {
|
| 1796 |
+
"content": "<|reserved_special_token_216|>",
|
| 1797 |
+
"lstrip": false,
|
| 1798 |
+
"normalized": false,
|
| 1799 |
+
"rstrip": false,
|
| 1800 |
+
"single_word": false,
|
| 1801 |
+
"special": true
|
| 1802 |
+
},
|
| 1803 |
+
"128225": {
|
| 1804 |
+
"content": "<|reserved_special_token_217|>",
|
| 1805 |
+
"lstrip": false,
|
| 1806 |
+
"normalized": false,
|
| 1807 |
+
"rstrip": false,
|
| 1808 |
+
"single_word": false,
|
| 1809 |
+
"special": true
|
| 1810 |
+
},
|
| 1811 |
+
"128226": {
|
| 1812 |
+
"content": "<|reserved_special_token_218|>",
|
| 1813 |
+
"lstrip": false,
|
| 1814 |
+
"normalized": false,
|
| 1815 |
+
"rstrip": false,
|
| 1816 |
+
"single_word": false,
|
| 1817 |
+
"special": true
|
| 1818 |
+
},
|
| 1819 |
+
"128227": {
|
| 1820 |
+
"content": "<|reserved_special_token_219|>",
|
| 1821 |
+
"lstrip": false,
|
| 1822 |
+
"normalized": false,
|
| 1823 |
+
"rstrip": false,
|
| 1824 |
+
"single_word": false,
|
| 1825 |
+
"special": true
|
| 1826 |
+
},
|
| 1827 |
+
"128228": {
|
| 1828 |
+
"content": "<|reserved_special_token_220|>",
|
| 1829 |
+
"lstrip": false,
|
| 1830 |
+
"normalized": false,
|
| 1831 |
+
"rstrip": false,
|
| 1832 |
+
"single_word": false,
|
| 1833 |
+
"special": true
|
| 1834 |
+
},
|
| 1835 |
+
"128229": {
|
| 1836 |
+
"content": "<|reserved_special_token_221|>",
|
| 1837 |
+
"lstrip": false,
|
| 1838 |
+
"normalized": false,
|
| 1839 |
+
"rstrip": false,
|
| 1840 |
+
"single_word": false,
|
| 1841 |
+
"special": true
|
| 1842 |
+
},
|
| 1843 |
+
"128230": {
|
| 1844 |
+
"content": "<|reserved_special_token_222|>",
|
| 1845 |
+
"lstrip": false,
|
| 1846 |
+
"normalized": false,
|
| 1847 |
+
"rstrip": false,
|
| 1848 |
+
"single_word": false,
|
| 1849 |
+
"special": true
|
| 1850 |
+
},
|
| 1851 |
+
"128231": {
|
| 1852 |
+
"content": "<|reserved_special_token_223|>",
|
| 1853 |
+
"lstrip": false,
|
| 1854 |
+
"normalized": false,
|
| 1855 |
+
"rstrip": false,
|
| 1856 |
+
"single_word": false,
|
| 1857 |
+
"special": true
|
| 1858 |
+
},
|
| 1859 |
+
"128232": {
|
| 1860 |
+
"content": "<|reserved_special_token_224|>",
|
| 1861 |
+
"lstrip": false,
|
| 1862 |
+
"normalized": false,
|
| 1863 |
+
"rstrip": false,
|
| 1864 |
+
"single_word": false,
|
| 1865 |
+
"special": true
|
| 1866 |
+
},
|
| 1867 |
+
"128233": {
|
| 1868 |
+
"content": "<|reserved_special_token_225|>",
|
| 1869 |
+
"lstrip": false,
|
| 1870 |
+
"normalized": false,
|
| 1871 |
+
"rstrip": false,
|
| 1872 |
+
"single_word": false,
|
| 1873 |
+
"special": true
|
| 1874 |
+
},
|
| 1875 |
+
"128234": {
|
| 1876 |
+
"content": "<|reserved_special_token_226|>",
|
| 1877 |
+
"lstrip": false,
|
| 1878 |
+
"normalized": false,
|
| 1879 |
+
"rstrip": false,
|
| 1880 |
+
"single_word": false,
|
| 1881 |
+
"special": true
|
| 1882 |
+
},
|
| 1883 |
+
"128235": {
|
| 1884 |
+
"content": "<|reserved_special_token_227|>",
|
| 1885 |
+
"lstrip": false,
|
| 1886 |
+
"normalized": false,
|
| 1887 |
+
"rstrip": false,
|
| 1888 |
+
"single_word": false,
|
| 1889 |
+
"special": true
|
| 1890 |
+
},
|
| 1891 |
+
"128236": {
|
| 1892 |
+
"content": "<|reserved_special_token_228|>",
|
| 1893 |
+
"lstrip": false,
|
| 1894 |
+
"normalized": false,
|
| 1895 |
+
"rstrip": false,
|
| 1896 |
+
"single_word": false,
|
| 1897 |
+
"special": true
|
| 1898 |
+
},
|
| 1899 |
+
"128237": {
|
| 1900 |
+
"content": "<|reserved_special_token_229|>",
|
| 1901 |
+
"lstrip": false,
|
| 1902 |
+
"normalized": false,
|
| 1903 |
+
"rstrip": false,
|
| 1904 |
+
"single_word": false,
|
| 1905 |
+
"special": true
|
| 1906 |
+
},
|
| 1907 |
+
"128238": {
|
| 1908 |
+
"content": "<|reserved_special_token_230|>",
|
| 1909 |
+
"lstrip": false,
|
| 1910 |
+
"normalized": false,
|
| 1911 |
+
"rstrip": false,
|
| 1912 |
+
"single_word": false,
|
| 1913 |
+
"special": true
|
| 1914 |
+
},
|
| 1915 |
+
"128239": {
|
| 1916 |
+
"content": "<|reserved_special_token_231|>",
|
| 1917 |
+
"lstrip": false,
|
| 1918 |
+
"normalized": false,
|
| 1919 |
+
"rstrip": false,
|
| 1920 |
+
"single_word": false,
|
| 1921 |
+
"special": true
|
| 1922 |
+
},
|
| 1923 |
+
"128240": {
|
| 1924 |
+
"content": "<|reserved_special_token_232|>",
|
| 1925 |
+
"lstrip": false,
|
| 1926 |
+
"normalized": false,
|
| 1927 |
+
"rstrip": false,
|
| 1928 |
+
"single_word": false,
|
| 1929 |
+
"special": true
|
| 1930 |
+
},
|
| 1931 |
+
"128241": {
|
| 1932 |
+
"content": "<|reserved_special_token_233|>",
|
| 1933 |
+
"lstrip": false,
|
| 1934 |
+
"normalized": false,
|
| 1935 |
+
"rstrip": false,
|
| 1936 |
+
"single_word": false,
|
| 1937 |
+
"special": true
|
| 1938 |
+
},
|
| 1939 |
+
"128242": {
|
| 1940 |
+
"content": "<|reserved_special_token_234|>",
|
| 1941 |
+
"lstrip": false,
|
| 1942 |
+
"normalized": false,
|
| 1943 |
+
"rstrip": false,
|
| 1944 |
+
"single_word": false,
|
| 1945 |
+
"special": true
|
| 1946 |
+
},
|
| 1947 |
+
"128243": {
|
| 1948 |
+
"content": "<|reserved_special_token_235|>",
|
| 1949 |
+
"lstrip": false,
|
| 1950 |
+
"normalized": false,
|
| 1951 |
+
"rstrip": false,
|
| 1952 |
+
"single_word": false,
|
| 1953 |
+
"special": true
|
| 1954 |
+
},
|
| 1955 |
+
"128244": {
|
| 1956 |
+
"content": "<|reserved_special_token_236|>",
|
| 1957 |
+
"lstrip": false,
|
| 1958 |
+
"normalized": false,
|
| 1959 |
+
"rstrip": false,
|
| 1960 |
+
"single_word": false,
|
| 1961 |
+
"special": true
|
| 1962 |
+
},
|
| 1963 |
+
"128245": {
|
| 1964 |
+
"content": "<|reserved_special_token_237|>",
|
| 1965 |
+
"lstrip": false,
|
| 1966 |
+
"normalized": false,
|
| 1967 |
+
"rstrip": false,
|
| 1968 |
+
"single_word": false,
|
| 1969 |
+
"special": true
|
| 1970 |
+
},
|
| 1971 |
+
"128246": {
|
| 1972 |
+
"content": "<|reserved_special_token_238|>",
|
| 1973 |
+
"lstrip": false,
|
| 1974 |
+
"normalized": false,
|
| 1975 |
+
"rstrip": false,
|
| 1976 |
+
"single_word": false,
|
| 1977 |
+
"special": true
|
| 1978 |
+
},
|
| 1979 |
+
"128247": {
|
| 1980 |
+
"content": "<|reserved_special_token_239|>",
|
| 1981 |
+
"lstrip": false,
|
| 1982 |
+
"normalized": false,
|
| 1983 |
+
"rstrip": false,
|
| 1984 |
+
"single_word": false,
|
| 1985 |
+
"special": true
|
| 1986 |
+
},
|
| 1987 |
+
"128248": {
|
| 1988 |
+
"content": "<|reserved_special_token_240|>",
|
| 1989 |
+
"lstrip": false,
|
| 1990 |
+
"normalized": false,
|
| 1991 |
+
"rstrip": false,
|
| 1992 |
+
"single_word": false,
|
| 1993 |
+
"special": true
|
| 1994 |
+
},
|
| 1995 |
+
"128249": {
|
| 1996 |
+
"content": "<|reserved_special_token_241|>",
|
| 1997 |
+
"lstrip": false,
|
| 1998 |
+
"normalized": false,
|
| 1999 |
+
"rstrip": false,
|
| 2000 |
+
"single_word": false,
|
| 2001 |
+
"special": true
|
| 2002 |
+
},
|
| 2003 |
+
"128250": {
|
| 2004 |
+
"content": "<|reserved_special_token_242|>",
|
| 2005 |
+
"lstrip": false,
|
| 2006 |
+
"normalized": false,
|
| 2007 |
+
"rstrip": false,
|
| 2008 |
+
"single_word": false,
|
| 2009 |
+
"special": true
|
| 2010 |
+
},
|
| 2011 |
+
"128251": {
|
| 2012 |
+
"content": "<|reserved_special_token_243|>",
|
| 2013 |
+
"lstrip": false,
|
| 2014 |
+
"normalized": false,
|
| 2015 |
+
"rstrip": false,
|
| 2016 |
+
"single_word": false,
|
| 2017 |
+
"special": true
|
| 2018 |
+
},
|
| 2019 |
+
"128252": {
|
| 2020 |
+
"content": "<|reserved_special_token_244|>",
|
| 2021 |
+
"lstrip": false,
|
| 2022 |
+
"normalized": false,
|
| 2023 |
+
"rstrip": false,
|
| 2024 |
+
"single_word": false,
|
| 2025 |
+
"special": true
|
| 2026 |
+
},
|
| 2027 |
+
"128253": {
|
| 2028 |
+
"content": "<|reserved_special_token_245|>",
|
| 2029 |
+
"lstrip": false,
|
| 2030 |
+
"normalized": false,
|
| 2031 |
+
"rstrip": false,
|
| 2032 |
+
"single_word": false,
|
| 2033 |
+
"special": true
|
| 2034 |
+
},
|
| 2035 |
+
"128254": {
|
| 2036 |
+
"content": "<|reserved_special_token_246|>",
|
| 2037 |
+
"lstrip": false,
|
| 2038 |
+
"normalized": false,
|
| 2039 |
+
"rstrip": false,
|
| 2040 |
+
"single_word": false,
|
| 2041 |
+
"special": true
|
| 2042 |
+
},
|
| 2043 |
+
"128255": {
|
| 2044 |
+
"content": "<|reserved_special_token_247|>",
|
| 2045 |
+
"lstrip": false,
|
| 2046 |
+
"normalized": false,
|
| 2047 |
+
"rstrip": false,
|
| 2048 |
+
"single_word": false,
|
| 2049 |
+
"special": true
|
| 2050 |
+
}
|
| 2051 |
+
},
|
| 2052 |
+
"bos_token": "<|begin_of_text|>",
|
| 2053 |
+
"chat_template": "{{- bos_token }}\n{%- if custom_tools is defined %}\n {%- set tools = custom_tools %}\n{%- endif %}\n{%- if not tools_in_user_message is defined %}\n {%- set tools_in_user_message = true %}\n{%- endif %}\n{%- if not date_string is defined %}\n {%- if strftime_now is defined %}\n {%- set date_string = strftime_now(\"%d %b %Y\") %}\n {%- else %}\n {%- set date_string = \"26 Jul 2024\" %}\n {%- endif %}\n{%- endif %}\n{%- if not tools is defined %}\n {%- set tools = none %}\n{%- endif %}\n\n{#- This block extracts the system message, so we can slot it into the right place. #}\n{%- if messages[0]['role'] == 'system' %}\n {%- set system_message = messages[0]['content']|trim %}\n {%- set messages = messages[1:] %}\n{%- else %}\n {%- set system_message = \"\" %}\n{%- endif %}\n\n{#- System message #}\n{{- \"<|start_header_id|>system<|end_header_id|>\\n\\n\" }}\n{%- if tools is not none %}\n {{- \"Environment: ipython\\n\" }}\n{%- endif %}\n{{- \"Cutting Knowledge Date: December 2023\\n\" }}\n{{- \"Today Date: \" + date_string + \"\\n\\n\" }}\n{%- if tools is not none and not tools_in_user_message %}\n {{- \"You have access to the following functions. To call a function, please respond with JSON for a function call.\" }}\n {{- 'Respond in the format {\"name\": function name, \"parameters\": dictionary of argument name and its value}.' }}\n {{- \"Do not use variables.\\n\\n\" }}\n {%- for t in tools %}\n {{- t | tojson(indent=4) }}\n {{- \"\\n\\n\" }}\n {%- endfor %}\n{%- endif %}\n{{- system_message }}\n{{- \"<|eot_id|>\" }}\n\n{#- Custom tools are passed in a user message with some extra guidance #}\n{%- if tools_in_user_message and not tools is none %}\n {#- Extract the first user message so we can plug it in here #}\n {%- if messages | length != 0 %}\n {%- set first_user_message = messages[0]['content']|trim %}\n {%- set messages = messages[1:] %}\n {%- else %}\n {{- raise_exception(\"Cannot put tools in the first user message when there's no first user message!\") }}\n{%- endif %}\n {{- '<|start_header_id|>user<|end_header_id|>\\n\\n' -}}\n {{- \"Given the following functions, please respond with a JSON for a function call \" }}\n {{- \"with its proper arguments that best answers the given prompt.\\n\\n\" }}\n {{- 'Respond in the format {\"name\": function name, \"parameters\": dictionary of argument name and its value}.' }}\n {{- \"Do not use variables.\\n\\n\" }}\n {%- for t in tools %}\n {{- t | tojson(indent=4) }}\n {{- \"\\n\\n\" }}\n {%- endfor %}\n {{- first_user_message + \"<|eot_id|>\"}}\n{%- endif %}\n\n{%- for message in messages %}\n {%- if not (message.role == 'ipython' or message.role == 'tool' or 'tool_calls' in message) %}\n {{- '<|start_header_id|>' + message['role'] + '<|end_header_id|>\\n\\n'+ message['content'] | trim + '<|eot_id|>' }}\n {%- elif 'tool_calls' in message %}\n {%- if not message.tool_calls|length == 1 %}\n {{- raise_exception(\"This model only supports single tool-calls at once!\") }}\n {%- endif %}\n {%- set tool_call = message.tool_calls[0].function %}\n {{- '<|start_header_id|>assistant<|end_header_id|>\\n\\n' -}}\n {{- '{\"name\": \"' + tool_call.name + '\", ' }}\n {{- '\"parameters\": ' }}\n {{- tool_call.arguments | tojson }}\n {{- \"}\" }}\n {{- \"<|eot_id|>\" }}\n {%- elif message.role == \"tool\" or message.role == \"ipython\" %}\n {{- \"<|start_header_id|>ipython<|end_header_id|>\\n\\n\" }}\n {%- if message.content is mapping or message.content is iterable %}\n {{- message.content | tojson }}\n {%- else %}\n {{- message.content }}\n {%- endif %}\n {{- \"<|eot_id|>\" }}\n {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n {{- '<|start_header_id|>assistant<|end_header_id|>\\n\\n' }}\n{%- endif %}\n",
|
| 2054 |
+
"clean_up_tokenization_spaces": true,
|
| 2055 |
+
"eos_token": "<|eot_id|>",
|
| 2056 |
+
"model_input_names": [
|
| 2057 |
+
"input_ids",
|
| 2058 |
+
"attention_mask"
|
| 2059 |
+
],
|
| 2060 |
+
"model_max_length": 131072,
|
| 2061 |
+
"pad_token": "<|end_of_text|>",
|
| 2062 |
+
"tokenizer_class": "PreTrainedTokenizerFast"
|
| 2063 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,1897 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 25.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 132825,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.09410878976096368,
|
| 13 |
+
"grad_norm": 7.552914619445801,
|
| 14 |
+
"learning_rate": 4.843152017065061e-05,
|
| 15 |
+
"loss": 1.9573,
|
| 16 |
+
"step": 500
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.18821757952192736,
|
| 20 |
+
"grad_norm": 10.377354621887207,
|
| 21 |
+
"learning_rate": 4.686304034130121e-05,
|
| 22 |
+
"loss": 1.6637,
|
| 23 |
+
"step": 1000
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.282326369282891,
|
| 27 |
+
"grad_norm": 10.336068153381348,
|
| 28 |
+
"learning_rate": 4.529456051195182e-05,
|
| 29 |
+
"loss": 1.6903,
|
| 30 |
+
"step": 1500
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.3764351590438547,
|
| 34 |
+
"grad_norm": 4.373341083526611,
|
| 35 |
+
"learning_rate": 4.372608068260242e-05,
|
| 36 |
+
"loss": 1.7066,
|
| 37 |
+
"step": 2000
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.47054394880481837,
|
| 41 |
+
"grad_norm": 6.67123556137085,
|
| 42 |
+
"learning_rate": 4.2157600853253026e-05,
|
| 43 |
+
"loss": 1.6262,
|
| 44 |
+
"step": 2500
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.564652738565782,
|
| 48 |
+
"grad_norm": 7.045924663543701,
|
| 49 |
+
"learning_rate": 4.0589121023903634e-05,
|
| 50 |
+
"loss": 1.6133,
|
| 51 |
+
"step": 3000
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.6587615283267457,
|
| 55 |
+
"grad_norm": 8.646467208862305,
|
| 56 |
+
"learning_rate": 3.902064119455424e-05,
|
| 57 |
+
"loss": 1.5958,
|
| 58 |
+
"step": 3500
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.7528703180877094,
|
| 62 |
+
"grad_norm": 17.767257690429688,
|
| 63 |
+
"learning_rate": 3.745216136520485e-05,
|
| 64 |
+
"loss": 1.5926,
|
| 65 |
+
"step": 4000
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.846979107848673,
|
| 69 |
+
"grad_norm": 6.851809978485107,
|
| 70 |
+
"learning_rate": 3.588368153585545e-05,
|
| 71 |
+
"loss": 1.5898,
|
| 72 |
+
"step": 4500
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.9410878976096367,
|
| 76 |
+
"grad_norm": 6.367198467254639,
|
| 77 |
+
"learning_rate": 3.431520170650606e-05,
|
| 78 |
+
"loss": 1.5842,
|
| 79 |
+
"step": 5000
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 1.0351966873706004,
|
| 83 |
+
"grad_norm": 3.8963205814361572,
|
| 84 |
+
"learning_rate": 3.274672187715666e-05,
|
| 85 |
+
"loss": 1.6023,
|
| 86 |
+
"step": 5500
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 1.129305477131564,
|
| 90 |
+
"grad_norm": 3.492241382598877,
|
| 91 |
+
"learning_rate": 3.1178242047807265e-05,
|
| 92 |
+
"loss": 1.5835,
|
| 93 |
+
"step": 6000
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 1.2234142668925279,
|
| 97 |
+
"grad_norm": 6.9010396003723145,
|
| 98 |
+
"learning_rate": 2.960976221845787e-05,
|
| 99 |
+
"loss": 1.5804,
|
| 100 |
+
"step": 6500
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 1.3175230566534915,
|
| 104 |
+
"grad_norm": 7.097581386566162,
|
| 105 |
+
"learning_rate": 2.8041282389108477e-05,
|
| 106 |
+
"loss": 1.5685,
|
| 107 |
+
"step": 7000
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 1.411631846414455,
|
| 111 |
+
"grad_norm": 4.106161117553711,
|
| 112 |
+
"learning_rate": 2.647280255975908e-05,
|
| 113 |
+
"loss": 1.5557,
|
| 114 |
+
"step": 7500
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 1.5057406361754189,
|
| 118 |
+
"grad_norm": 5.339535236358643,
|
| 119 |
+
"learning_rate": 2.490432273040969e-05,
|
| 120 |
+
"loss": 1.5266,
|
| 121 |
+
"step": 8000
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 1.5998494259363825,
|
| 125 |
+
"grad_norm": 5.467094421386719,
|
| 126 |
+
"learning_rate": 2.3335842901060293e-05,
|
| 127 |
+
"loss": 1.5394,
|
| 128 |
+
"step": 8500
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 1.693958215697346,
|
| 132 |
+
"grad_norm": 5.166747093200684,
|
| 133 |
+
"learning_rate": 2.17673630717109e-05,
|
| 134 |
+
"loss": 1.5131,
|
| 135 |
+
"step": 9000
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 1.7880670054583097,
|
| 139 |
+
"grad_norm": 3.2604665756225586,
|
| 140 |
+
"learning_rate": 2.0198883242361504e-05,
|
| 141 |
+
"loss": 1.4695,
|
| 142 |
+
"step": 9500
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 1.8821757952192735,
|
| 146 |
+
"grad_norm": 6.9691362380981445,
|
| 147 |
+
"learning_rate": 1.8630403413012108e-05,
|
| 148 |
+
"loss": 1.4532,
|
| 149 |
+
"step": 10000
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 1.9762845849802373,
|
| 153 |
+
"grad_norm": 3.044600248336792,
|
| 154 |
+
"learning_rate": 1.7061923583662716e-05,
|
| 155 |
+
"loss": 1.4349,
|
| 156 |
+
"step": 10500
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 2.070393374741201,
|
| 160 |
+
"grad_norm": 5.485976219177246,
|
| 161 |
+
"learning_rate": 1.549344375431332e-05,
|
| 162 |
+
"loss": 1.4098,
|
| 163 |
+
"step": 11000
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 2.1645021645021645,
|
| 167 |
+
"grad_norm": 3.2020225524902344,
|
| 168 |
+
"learning_rate": 1.3924963924963927e-05,
|
| 169 |
+
"loss": 1.4025,
|
| 170 |
+
"step": 11500
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 2.258610954263128,
|
| 174 |
+
"grad_norm": 4.406314849853516,
|
| 175 |
+
"learning_rate": 1.235648409561453e-05,
|
| 176 |
+
"loss": 1.384,
|
| 177 |
+
"step": 12000
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 2.3527197440240917,
|
| 181 |
+
"grad_norm": 7.23325252532959,
|
| 182 |
+
"learning_rate": 1.0788004266265137e-05,
|
| 183 |
+
"loss": 1.3831,
|
| 184 |
+
"step": 12500
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 2.4468285337850557,
|
| 188 |
+
"grad_norm": 6.645949840545654,
|
| 189 |
+
"learning_rate": 9.219524436915741e-06,
|
| 190 |
+
"loss": 1.3611,
|
| 191 |
+
"step": 13000
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 2.5409373235460193,
|
| 195 |
+
"grad_norm": 4.476417064666748,
|
| 196 |
+
"learning_rate": 7.651044607566347e-06,
|
| 197 |
+
"loss": 1.3478,
|
| 198 |
+
"step": 13500
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 2.635046113306983,
|
| 202 |
+
"grad_norm": 4.497859954833984,
|
| 203 |
+
"learning_rate": 6.082564778216952e-06,
|
| 204 |
+
"loss": 1.3354,
|
| 205 |
+
"step": 14000
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 2.7291549030679465,
|
| 209 |
+
"grad_norm": 4.2654008865356445,
|
| 210 |
+
"learning_rate": 4.514084948867558e-06,
|
| 211 |
+
"loss": 1.3229,
|
| 212 |
+
"step": 14500
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 2.82326369282891,
|
| 216 |
+
"grad_norm": 3.607623338699341,
|
| 217 |
+
"learning_rate": 2.945605119518163e-06,
|
| 218 |
+
"loss": 1.3001,
|
| 219 |
+
"step": 15000
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 2.917372482589874,
|
| 223 |
+
"grad_norm": 3.7838690280914307,
|
| 224 |
+
"learning_rate": 1.3771252901687685e-06,
|
| 225 |
+
"loss": 1.2967,
|
| 226 |
+
"step": 15500
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 3.0114812723508377,
|
| 230 |
+
"grad_norm": 7.810318946838379,
|
| 231 |
+
"learning_rate": 3.494259363824581e-05,
|
| 232 |
+
"loss": 1.4147,
|
| 233 |
+
"step": 16000
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 3.1055900621118013,
|
| 237 |
+
"grad_norm": 3.653393030166626,
|
| 238 |
+
"learning_rate": 3.4472049689440996e-05,
|
| 239 |
+
"loss": 1.4375,
|
| 240 |
+
"step": 16500
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 3.199698851872765,
|
| 244 |
+
"grad_norm": 6.7401018142700195,
|
| 245 |
+
"learning_rate": 3.400150574063617e-05,
|
| 246 |
+
"loss": 1.3906,
|
| 247 |
+
"step": 17000
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 3.2938076416337285,
|
| 251 |
+
"grad_norm": 4.238823890686035,
|
| 252 |
+
"learning_rate": 3.3530961791831364e-05,
|
| 253 |
+
"loss": 1.3716,
|
| 254 |
+
"step": 17500
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 3.387916431394692,
|
| 258 |
+
"grad_norm": 2.793461561203003,
|
| 259 |
+
"learning_rate": 3.306041784302654e-05,
|
| 260 |
+
"loss": 1.3764,
|
| 261 |
+
"step": 18000
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 3.4820252211556557,
|
| 265 |
+
"grad_norm": 3.1460959911346436,
|
| 266 |
+
"learning_rate": 3.2589873894221726e-05,
|
| 267 |
+
"loss": 1.3557,
|
| 268 |
+
"step": 18500
|
| 269 |
+
},
|
| 270 |
+
{
|
| 271 |
+
"epoch": 3.5761340109166198,
|
| 272 |
+
"grad_norm": 6.384432792663574,
|
| 273 |
+
"learning_rate": 3.2119329945416903e-05,
|
| 274 |
+
"loss": 1.3503,
|
| 275 |
+
"step": 19000
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 3.6702428006775834,
|
| 279 |
+
"grad_norm": 3.8678534030914307,
|
| 280 |
+
"learning_rate": 3.164878599661209e-05,
|
| 281 |
+
"loss": 1.3407,
|
| 282 |
+
"step": 19500
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 3.764351590438547,
|
| 286 |
+
"grad_norm": 2.776543140411377,
|
| 287 |
+
"learning_rate": 3.1178242047807265e-05,
|
| 288 |
+
"loss": 1.3593,
|
| 289 |
+
"step": 20000
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 3.8584603801995105,
|
| 293 |
+
"grad_norm": 8.332947731018066,
|
| 294 |
+
"learning_rate": 3.070769809900245e-05,
|
| 295 |
+
"loss": 1.3323,
|
| 296 |
+
"step": 20500
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 3.9525691699604746,
|
| 300 |
+
"grad_norm": 5.115898609161377,
|
| 301 |
+
"learning_rate": 3.0237154150197627e-05,
|
| 302 |
+
"loss": 1.3184,
|
| 303 |
+
"step": 21000
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 4.046677959721438,
|
| 307 |
+
"grad_norm": 5.099429607391357,
|
| 308 |
+
"learning_rate": 2.9766610201392815e-05,
|
| 309 |
+
"loss": 1.3082,
|
| 310 |
+
"step": 21500
|
| 311 |
+
},
|
| 312 |
+
{
|
| 313 |
+
"epoch": 4.140786749482402,
|
| 314 |
+
"grad_norm": 3.901289939880371,
|
| 315 |
+
"learning_rate": 2.9296066252587996e-05,
|
| 316 |
+
"loss": 1.3038,
|
| 317 |
+
"step": 22000
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 4.234895539243365,
|
| 321 |
+
"grad_norm": 3.7559354305267334,
|
| 322 |
+
"learning_rate": 2.8825522303783176e-05,
|
| 323 |
+
"loss": 1.2892,
|
| 324 |
+
"step": 22500
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 4.329004329004329,
|
| 328 |
+
"grad_norm": 4.156054973602295,
|
| 329 |
+
"learning_rate": 2.8354978354978357e-05,
|
| 330 |
+
"loss": 1.2893,
|
| 331 |
+
"step": 23000
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 4.423113118765293,
|
| 335 |
+
"grad_norm": 3.1980538368225098,
|
| 336 |
+
"learning_rate": 2.7884434406173538e-05,
|
| 337 |
+
"loss": 1.288,
|
| 338 |
+
"step": 23500
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 4.517221908526256,
|
| 342 |
+
"grad_norm": 2.7643442153930664,
|
| 343 |
+
"learning_rate": 2.741389045736872e-05,
|
| 344 |
+
"loss": 1.2666,
|
| 345 |
+
"step": 24000
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 4.61133069828722,
|
| 349 |
+
"grad_norm": 2.195343017578125,
|
| 350 |
+
"learning_rate": 2.69433465085639e-05,
|
| 351 |
+
"loss": 1.2632,
|
| 352 |
+
"step": 24500
|
| 353 |
+
},
|
| 354 |
+
{
|
| 355 |
+
"epoch": 4.705439488048183,
|
| 356 |
+
"grad_norm": 2.6611695289611816,
|
| 357 |
+
"learning_rate": 2.647280255975908e-05,
|
| 358 |
+
"loss": 1.262,
|
| 359 |
+
"step": 25000
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 4.799548277809148,
|
| 363 |
+
"grad_norm": 5.055428981781006,
|
| 364 |
+
"learning_rate": 2.6002258610954265e-05,
|
| 365 |
+
"loss": 1.2687,
|
| 366 |
+
"step": 25500
|
| 367 |
+
},
|
| 368 |
+
{
|
| 369 |
+
"epoch": 4.893657067570111,
|
| 370 |
+
"grad_norm": 2.993502616882324,
|
| 371 |
+
"learning_rate": 2.5531714662149446e-05,
|
| 372 |
+
"loss": 1.2439,
|
| 373 |
+
"step": 26000
|
| 374 |
+
},
|
| 375 |
+
{
|
| 376 |
+
"epoch": 4.987765857331075,
|
| 377 |
+
"grad_norm": 2.6108858585357666,
|
| 378 |
+
"learning_rate": 2.5061170713344627e-05,
|
| 379 |
+
"loss": 1.2315,
|
| 380 |
+
"step": 26500
|
| 381 |
+
},
|
| 382 |
+
{
|
| 383 |
+
"epoch": 5.081874647092039,
|
| 384 |
+
"grad_norm": 3.422744035720825,
|
| 385 |
+
"learning_rate": 2.4590626764539808e-05,
|
| 386 |
+
"loss": 1.2216,
|
| 387 |
+
"step": 27000
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 5.175983436853002,
|
| 391 |
+
"grad_norm": 2.409943103790283,
|
| 392 |
+
"learning_rate": 2.412008281573499e-05,
|
| 393 |
+
"loss": 1.214,
|
| 394 |
+
"step": 27500
|
| 395 |
+
},
|
| 396 |
+
{
|
| 397 |
+
"epoch": 5.270092226613966,
|
| 398 |
+
"grad_norm": 2.378814458847046,
|
| 399 |
+
"learning_rate": 2.3649538866930173e-05,
|
| 400 |
+
"loss": 1.206,
|
| 401 |
+
"step": 28000
|
| 402 |
+
},
|
| 403 |
+
{
|
| 404 |
+
"epoch": 5.364201016374929,
|
| 405 |
+
"grad_norm": 2.6459624767303467,
|
| 406 |
+
"learning_rate": 2.3178994918125354e-05,
|
| 407 |
+
"loss": 1.2078,
|
| 408 |
+
"step": 28500
|
| 409 |
+
},
|
| 410 |
+
{
|
| 411 |
+
"epoch": 5.458309806135893,
|
| 412 |
+
"grad_norm": 3.1709744930267334,
|
| 413 |
+
"learning_rate": 2.2708450969320535e-05,
|
| 414 |
+
"loss": 1.1908,
|
| 415 |
+
"step": 29000
|
| 416 |
+
},
|
| 417 |
+
{
|
| 418 |
+
"epoch": 5.552418595896857,
|
| 419 |
+
"grad_norm": 3.47601056098938,
|
| 420 |
+
"learning_rate": 2.2237907020515716e-05,
|
| 421 |
+
"loss": 1.192,
|
| 422 |
+
"step": 29500
|
| 423 |
+
},
|
| 424 |
+
{
|
| 425 |
+
"epoch": 5.64652738565782,
|
| 426 |
+
"grad_norm": 3.5006909370422363,
|
| 427 |
+
"learning_rate": 2.17673630717109e-05,
|
| 428 |
+
"loss": 1.1913,
|
| 429 |
+
"step": 30000
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 5.740636175418784,
|
| 433 |
+
"grad_norm": 2.8024189472198486,
|
| 434 |
+
"learning_rate": 2.129681912290608e-05,
|
| 435 |
+
"loss": 1.1815,
|
| 436 |
+
"step": 30500
|
| 437 |
+
},
|
| 438 |
+
{
|
| 439 |
+
"epoch": 5.834744965179748,
|
| 440 |
+
"grad_norm": 4.2450947761535645,
|
| 441 |
+
"learning_rate": 2.0826275174101262e-05,
|
| 442 |
+
"loss": 1.1793,
|
| 443 |
+
"step": 31000
|
| 444 |
+
},
|
| 445 |
+
{
|
| 446 |
+
"epoch": 5.928853754940711,
|
| 447 |
+
"grad_norm": 3.6110267639160156,
|
| 448 |
+
"learning_rate": 2.0355731225296443e-05,
|
| 449 |
+
"loss": 1.1734,
|
| 450 |
+
"step": 31500
|
| 451 |
+
},
|
| 452 |
+
{
|
| 453 |
+
"epoch": 6.0229625447016755,
|
| 454 |
+
"grad_norm": 4.730632305145264,
|
| 455 |
+
"learning_rate": 1.9885187276491627e-05,
|
| 456 |
+
"loss": 1.1447,
|
| 457 |
+
"step": 32000
|
| 458 |
+
},
|
| 459 |
+
{
|
| 460 |
+
"epoch": 6.117071334462639,
|
| 461 |
+
"grad_norm": 3.0380797386169434,
|
| 462 |
+
"learning_rate": 1.9414643327686808e-05,
|
| 463 |
+
"loss": 1.1206,
|
| 464 |
+
"step": 32500
|
| 465 |
+
},
|
| 466 |
+
{
|
| 467 |
+
"epoch": 6.211180124223603,
|
| 468 |
+
"grad_norm": 4.4165358543396,
|
| 469 |
+
"learning_rate": 1.894409937888199e-05,
|
| 470 |
+
"loss": 1.1295,
|
| 471 |
+
"step": 33000
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 6.305288913984566,
|
| 475 |
+
"grad_norm": 3.3100738525390625,
|
| 476 |
+
"learning_rate": 1.847355543007717e-05,
|
| 477 |
+
"loss": 1.1214,
|
| 478 |
+
"step": 33500
|
| 479 |
+
},
|
| 480 |
+
{
|
| 481 |
+
"epoch": 6.39939770374553,
|
| 482 |
+
"grad_norm": 4.085879325866699,
|
| 483 |
+
"learning_rate": 1.8003011481272354e-05,
|
| 484 |
+
"loss": 1.1128,
|
| 485 |
+
"step": 34000
|
| 486 |
+
},
|
| 487 |
+
{
|
| 488 |
+
"epoch": 6.4935064935064934,
|
| 489 |
+
"grad_norm": 3.0867068767547607,
|
| 490 |
+
"learning_rate": 1.7532467532467535e-05,
|
| 491 |
+
"loss": 1.114,
|
| 492 |
+
"step": 34500
|
| 493 |
+
},
|
| 494 |
+
{
|
| 495 |
+
"epoch": 6.587615283267457,
|
| 496 |
+
"grad_norm": 3.721590757369995,
|
| 497 |
+
"learning_rate": 1.7061923583662716e-05,
|
| 498 |
+
"loss": 1.1037,
|
| 499 |
+
"step": 35000
|
| 500 |
+
},
|
| 501 |
+
{
|
| 502 |
+
"epoch": 6.681724073028421,
|
| 503 |
+
"grad_norm": 3.4121475219726562,
|
| 504 |
+
"learning_rate": 1.6591379634857897e-05,
|
| 505 |
+
"loss": 1.107,
|
| 506 |
+
"step": 35500
|
| 507 |
+
},
|
| 508 |
+
{
|
| 509 |
+
"epoch": 6.775832862789384,
|
| 510 |
+
"grad_norm": 3.0844948291778564,
|
| 511 |
+
"learning_rate": 1.6120835686053078e-05,
|
| 512 |
+
"loss": 1.1005,
|
| 513 |
+
"step": 36000
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 6.869941652550348,
|
| 517 |
+
"grad_norm": 3.7161357402801514,
|
| 518 |
+
"learning_rate": 1.565029173724826e-05,
|
| 519 |
+
"loss": 1.0948,
|
| 520 |
+
"step": 36500
|
| 521 |
+
},
|
| 522 |
+
{
|
| 523 |
+
"epoch": 6.964050442311311,
|
| 524 |
+
"grad_norm": 3.217207193374634,
|
| 525 |
+
"learning_rate": 1.5179747788443441e-05,
|
| 526 |
+
"loss": 1.0877,
|
| 527 |
+
"step": 37000
|
| 528 |
+
},
|
| 529 |
+
{
|
| 530 |
+
"epoch": 7.058159232072276,
|
| 531 |
+
"grad_norm": 4.4285078048706055,
|
| 532 |
+
"learning_rate": 1.4709203839638622e-05,
|
| 533 |
+
"loss": 1.0559,
|
| 534 |
+
"step": 37500
|
| 535 |
+
},
|
| 536 |
+
{
|
| 537 |
+
"epoch": 7.1522680218332395,
|
| 538 |
+
"grad_norm": 3.0102875232696533,
|
| 539 |
+
"learning_rate": 1.4238659890833805e-05,
|
| 540 |
+
"loss": 1.0322,
|
| 541 |
+
"step": 38000
|
| 542 |
+
},
|
| 543 |
+
{
|
| 544 |
+
"epoch": 7.246376811594203,
|
| 545 |
+
"grad_norm": 3.4103572368621826,
|
| 546 |
+
"learning_rate": 1.3768115942028985e-05,
|
| 547 |
+
"loss": 1.0217,
|
| 548 |
+
"step": 38500
|
| 549 |
+
},
|
| 550 |
+
{
|
| 551 |
+
"epoch": 7.340485601355167,
|
| 552 |
+
"grad_norm": 3.9534976482391357,
|
| 553 |
+
"learning_rate": 1.3297571993224166e-05,
|
| 554 |
+
"loss": 1.0248,
|
| 555 |
+
"step": 39000
|
| 556 |
+
},
|
| 557 |
+
{
|
| 558 |
+
"epoch": 7.43459439111613,
|
| 559 |
+
"grad_norm": 5.0660719871521,
|
| 560 |
+
"learning_rate": 1.2827028044419347e-05,
|
| 561 |
+
"loss": 1.0233,
|
| 562 |
+
"step": 39500
|
| 563 |
+
},
|
| 564 |
+
{
|
| 565 |
+
"epoch": 7.528703180877094,
|
| 566 |
+
"grad_norm": 4.05812931060791,
|
| 567 |
+
"learning_rate": 1.235648409561453e-05,
|
| 568 |
+
"loss": 1.0254,
|
| 569 |
+
"step": 40000
|
| 570 |
+
},
|
| 571 |
+
{
|
| 572 |
+
"epoch": 7.6228119706380575,
|
| 573 |
+
"grad_norm": 2.9366817474365234,
|
| 574 |
+
"learning_rate": 1.1885940146809712e-05,
|
| 575 |
+
"loss": 1.0154,
|
| 576 |
+
"step": 40500
|
| 577 |
+
},
|
| 578 |
+
{
|
| 579 |
+
"epoch": 7.716920760399021,
|
| 580 |
+
"grad_norm": 3.6969943046569824,
|
| 581 |
+
"learning_rate": 1.1415396198004895e-05,
|
| 582 |
+
"loss": 1.0023,
|
| 583 |
+
"step": 41000
|
| 584 |
+
},
|
| 585 |
+
{
|
| 586 |
+
"epoch": 7.811029550159985,
|
| 587 |
+
"grad_norm": 3.294569969177246,
|
| 588 |
+
"learning_rate": 3.4377940899680034e-05,
|
| 589 |
+
"loss": 1.0861,
|
| 590 |
+
"step": 41500
|
| 591 |
+
},
|
| 592 |
+
{
|
| 593 |
+
"epoch": 7.905138339920948,
|
| 594 |
+
"grad_norm": 1.961162805557251,
|
| 595 |
+
"learning_rate": 3.418972332015811e-05,
|
| 596 |
+
"loss": 1.105,
|
| 597 |
+
"step": 42000
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"epoch": 7.999247129681912,
|
| 601 |
+
"grad_norm": 4.648848056793213,
|
| 602 |
+
"learning_rate": 3.400150574063617e-05,
|
| 603 |
+
"loss": 1.1171,
|
| 604 |
+
"step": 42500
|
| 605 |
+
},
|
| 606 |
+
{
|
| 607 |
+
"epoch": 8.093355919442876,
|
| 608 |
+
"grad_norm": 4.888842582702637,
|
| 609 |
+
"learning_rate": 3.381328816111425e-05,
|
| 610 |
+
"loss": 1.0555,
|
| 611 |
+
"step": 43000
|
| 612 |
+
},
|
| 613 |
+
{
|
| 614 |
+
"epoch": 8.187464709203839,
|
| 615 |
+
"grad_norm": 3.3256289958953857,
|
| 616 |
+
"learning_rate": 3.362507058159232e-05,
|
| 617 |
+
"loss": 1.059,
|
| 618 |
+
"step": 43500
|
| 619 |
+
},
|
| 620 |
+
{
|
| 621 |
+
"epoch": 8.281573498964804,
|
| 622 |
+
"grad_norm": 2.744330406188965,
|
| 623 |
+
"learning_rate": 3.3436853002070396e-05,
|
| 624 |
+
"loss": 1.0818,
|
| 625 |
+
"step": 44000
|
| 626 |
+
},
|
| 627 |
+
{
|
| 628 |
+
"epoch": 8.375682288725766,
|
| 629 |
+
"grad_norm": 2.7452945709228516,
|
| 630 |
+
"learning_rate": 3.3248635422548465e-05,
|
| 631 |
+
"loss": 1.0772,
|
| 632 |
+
"step": 44500
|
| 633 |
+
},
|
| 634 |
+
{
|
| 635 |
+
"epoch": 8.46979107848673,
|
| 636 |
+
"grad_norm": 2.993236780166626,
|
| 637 |
+
"learning_rate": 3.306041784302654e-05,
|
| 638 |
+
"loss": 1.0896,
|
| 639 |
+
"step": 45000
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 8.563899868247695,
|
| 643 |
+
"grad_norm": 4.128504276275635,
|
| 644 |
+
"learning_rate": 3.287220026350462e-05,
|
| 645 |
+
"loss": 1.0806,
|
| 646 |
+
"step": 45500
|
| 647 |
+
},
|
| 648 |
+
{
|
| 649 |
+
"epoch": 8.658008658008658,
|
| 650 |
+
"grad_norm": 3.3763933181762695,
|
| 651 |
+
"learning_rate": 3.268398268398268e-05,
|
| 652 |
+
"loss": 1.0713,
|
| 653 |
+
"step": 46000
|
| 654 |
+
},
|
| 655 |
+
{
|
| 656 |
+
"epoch": 8.752117447769622,
|
| 657 |
+
"grad_norm": 2.213223457336426,
|
| 658 |
+
"learning_rate": 3.249576510446076e-05,
|
| 659 |
+
"loss": 1.0698,
|
| 660 |
+
"step": 46500
|
| 661 |
+
},
|
| 662 |
+
{
|
| 663 |
+
"epoch": 8.846226237530585,
|
| 664 |
+
"grad_norm": 3.0853641033172607,
|
| 665 |
+
"learning_rate": 3.230754752493883e-05,
|
| 666 |
+
"loss": 1.0724,
|
| 667 |
+
"step": 47000
|
| 668 |
+
},
|
| 669 |
+
{
|
| 670 |
+
"epoch": 8.94033502729155,
|
| 671 |
+
"grad_norm": 3.031791925430298,
|
| 672 |
+
"learning_rate": 3.2119329945416903e-05,
|
| 673 |
+
"loss": 1.0672,
|
| 674 |
+
"step": 47500
|
| 675 |
+
},
|
| 676 |
+
{
|
| 677 |
+
"epoch": 9.034443817052512,
|
| 678 |
+
"grad_norm": 3.0765955448150635,
|
| 679 |
+
"learning_rate": 3.193111236589498e-05,
|
| 680 |
+
"loss": 1.0545,
|
| 681 |
+
"step": 48000
|
| 682 |
+
},
|
| 683 |
+
{
|
| 684 |
+
"epoch": 9.128552606813477,
|
| 685 |
+
"grad_norm": 4.204183101654053,
|
| 686 |
+
"learning_rate": 3.174289478637305e-05,
|
| 687 |
+
"loss": 1.0037,
|
| 688 |
+
"step": 48500
|
| 689 |
+
},
|
| 690 |
+
{
|
| 691 |
+
"epoch": 9.22266139657444,
|
| 692 |
+
"grad_norm": 5.794823169708252,
|
| 693 |
+
"learning_rate": 3.155467720685112e-05,
|
| 694 |
+
"loss": 1.0069,
|
| 695 |
+
"step": 49000
|
| 696 |
+
},
|
| 697 |
+
{
|
| 698 |
+
"epoch": 9.316770186335404,
|
| 699 |
+
"grad_norm": 3.246511459350586,
|
| 700 |
+
"learning_rate": 3.136645962732919e-05,
|
| 701 |
+
"loss": 1.0151,
|
| 702 |
+
"step": 49500
|
| 703 |
+
},
|
| 704 |
+
{
|
| 705 |
+
"epoch": 9.410878976096367,
|
| 706 |
+
"grad_norm": 2.7034826278686523,
|
| 707 |
+
"learning_rate": 3.1178242047807265e-05,
|
| 708 |
+
"loss": 1.0183,
|
| 709 |
+
"step": 50000
|
| 710 |
+
},
|
| 711 |
+
{
|
| 712 |
+
"epoch": 9.504987765857331,
|
| 713 |
+
"grad_norm": 2.402880907058716,
|
| 714 |
+
"learning_rate": 3.099002446828534e-05,
|
| 715 |
+
"loss": 1.0193,
|
| 716 |
+
"step": 50500
|
| 717 |
+
},
|
| 718 |
+
{
|
| 719 |
+
"epoch": 9.599096555618296,
|
| 720 |
+
"grad_norm": 5.0139336585998535,
|
| 721 |
+
"learning_rate": 3.080180688876341e-05,
|
| 722 |
+
"loss": 1.0145,
|
| 723 |
+
"step": 51000
|
| 724 |
+
},
|
| 725 |
+
{
|
| 726 |
+
"epoch": 9.693205345379258,
|
| 727 |
+
"grad_norm": 3.907541275024414,
|
| 728 |
+
"learning_rate": 3.061358930924149e-05,
|
| 729 |
+
"loss": 1.011,
|
| 730 |
+
"step": 51500
|
| 731 |
+
},
|
| 732 |
+
{
|
| 733 |
+
"epoch": 9.787314135140223,
|
| 734 |
+
"grad_norm": 4.411949157714844,
|
| 735 |
+
"learning_rate": 3.042537172971956e-05,
|
| 736 |
+
"loss": 1.0063,
|
| 737 |
+
"step": 52000
|
| 738 |
+
},
|
| 739 |
+
{
|
| 740 |
+
"epoch": 9.881422924901186,
|
| 741 |
+
"grad_norm": 4.035211563110352,
|
| 742 |
+
"learning_rate": 3.0237154150197627e-05,
|
| 743 |
+
"loss": 1.0149,
|
| 744 |
+
"step": 52500
|
| 745 |
+
},
|
| 746 |
+
{
|
| 747 |
+
"epoch": 9.97553171466215,
|
| 748 |
+
"grad_norm": 3.6050124168395996,
|
| 749 |
+
"learning_rate": 3.00489365706757e-05,
|
| 750 |
+
"loss": 1.0027,
|
| 751 |
+
"step": 53000
|
| 752 |
+
},
|
| 753 |
+
{
|
| 754 |
+
"epoch": 10.069640504423113,
|
| 755 |
+
"grad_norm": 3.40191388130188,
|
| 756 |
+
"learning_rate": 2.9860718991153773e-05,
|
| 757 |
+
"loss": 0.9468,
|
| 758 |
+
"step": 53500
|
| 759 |
+
},
|
| 760 |
+
{
|
| 761 |
+
"epoch": 10.163749294184077,
|
| 762 |
+
"grad_norm": 2.8000032901763916,
|
| 763 |
+
"learning_rate": 2.9672501411631846e-05,
|
| 764 |
+
"loss": 0.9248,
|
| 765 |
+
"step": 54000
|
| 766 |
+
},
|
| 767 |
+
{
|
| 768 |
+
"epoch": 10.25785808394504,
|
| 769 |
+
"grad_norm": 4.177460193634033,
|
| 770 |
+
"learning_rate": 2.9484283832109923e-05,
|
| 771 |
+
"loss": 0.9389,
|
| 772 |
+
"step": 54500
|
| 773 |
+
},
|
| 774 |
+
{
|
| 775 |
+
"epoch": 10.351966873706004,
|
| 776 |
+
"grad_norm": 3.88246750831604,
|
| 777 |
+
"learning_rate": 2.9296066252587996e-05,
|
| 778 |
+
"loss": 0.9326,
|
| 779 |
+
"step": 55000
|
| 780 |
+
},
|
| 781 |
+
{
|
| 782 |
+
"epoch": 10.446075663466967,
|
| 783 |
+
"grad_norm": 4.002796173095703,
|
| 784 |
+
"learning_rate": 2.910784867306607e-05,
|
| 785 |
+
"loss": 0.9378,
|
| 786 |
+
"step": 55500
|
| 787 |
+
},
|
| 788 |
+
{
|
| 789 |
+
"epoch": 10.540184453227932,
|
| 790 |
+
"grad_norm": 4.069864749908447,
|
| 791 |
+
"learning_rate": 2.8919631093544135e-05,
|
| 792 |
+
"loss": 0.9405,
|
| 793 |
+
"step": 56000
|
| 794 |
+
},
|
| 795 |
+
{
|
| 796 |
+
"epoch": 10.634293242988894,
|
| 797 |
+
"grad_norm": 3.493865966796875,
|
| 798 |
+
"learning_rate": 2.8731413514022208e-05,
|
| 799 |
+
"loss": 0.9347,
|
| 800 |
+
"step": 56500
|
| 801 |
+
},
|
| 802 |
+
{
|
| 803 |
+
"epoch": 10.728402032749859,
|
| 804 |
+
"grad_norm": 3.725019693374634,
|
| 805 |
+
"learning_rate": 2.8543195934500284e-05,
|
| 806 |
+
"loss": 0.9428,
|
| 807 |
+
"step": 57000
|
| 808 |
+
},
|
| 809 |
+
{
|
| 810 |
+
"epoch": 10.822510822510823,
|
| 811 |
+
"grad_norm": 3.557591438293457,
|
| 812 |
+
"learning_rate": 2.8354978354978357e-05,
|
| 813 |
+
"loss": 0.9397,
|
| 814 |
+
"step": 57500
|
| 815 |
+
},
|
| 816 |
+
{
|
| 817 |
+
"epoch": 10.916619612271786,
|
| 818 |
+
"grad_norm": 3.370312213897705,
|
| 819 |
+
"learning_rate": 2.816676077545643e-05,
|
| 820 |
+
"loss": 0.939,
|
| 821 |
+
"step": 58000
|
| 822 |
+
},
|
| 823 |
+
{
|
| 824 |
+
"epoch": 11.01072840203275,
|
| 825 |
+
"grad_norm": 2.937887191772461,
|
| 826 |
+
"learning_rate": 2.7978543195934503e-05,
|
| 827 |
+
"loss": 0.9225,
|
| 828 |
+
"step": 58500
|
| 829 |
+
},
|
| 830 |
+
{
|
| 831 |
+
"epoch": 11.104837191793713,
|
| 832 |
+
"grad_norm": 2.403350353240967,
|
| 833 |
+
"learning_rate": 2.7790325616412576e-05,
|
| 834 |
+
"loss": 0.827,
|
| 835 |
+
"step": 59000
|
| 836 |
+
},
|
| 837 |
+
{
|
| 838 |
+
"epoch": 11.198945981554678,
|
| 839 |
+
"grad_norm": 2.4876935482025146,
|
| 840 |
+
"learning_rate": 2.7602108036890646e-05,
|
| 841 |
+
"loss": 0.8461,
|
| 842 |
+
"step": 59500
|
| 843 |
+
},
|
| 844 |
+
{
|
| 845 |
+
"epoch": 11.29305477131564,
|
| 846 |
+
"grad_norm": 3.663511276245117,
|
| 847 |
+
"learning_rate": 2.741389045736872e-05,
|
| 848 |
+
"loss": 0.8434,
|
| 849 |
+
"step": 60000
|
| 850 |
+
},
|
| 851 |
+
{
|
| 852 |
+
"epoch": 11.387163561076605,
|
| 853 |
+
"grad_norm": 4.3568806648254395,
|
| 854 |
+
"learning_rate": 2.7225672877846792e-05,
|
| 855 |
+
"loss": 0.8496,
|
| 856 |
+
"step": 60500
|
| 857 |
+
},
|
| 858 |
+
{
|
| 859 |
+
"epoch": 11.481272350837568,
|
| 860 |
+
"grad_norm": 3.4234845638275146,
|
| 861 |
+
"learning_rate": 2.7037455298324865e-05,
|
| 862 |
+
"loss": 0.8549,
|
| 863 |
+
"step": 61000
|
| 864 |
+
},
|
| 865 |
+
{
|
| 866 |
+
"epoch": 11.575381140598532,
|
| 867 |
+
"grad_norm": 2.537666082382202,
|
| 868 |
+
"learning_rate": 2.6849237718802938e-05,
|
| 869 |
+
"loss": 0.8548,
|
| 870 |
+
"step": 61500
|
| 871 |
+
},
|
| 872 |
+
{
|
| 873 |
+
"epoch": 11.669489930359495,
|
| 874 |
+
"grad_norm": 3.7678942680358887,
|
| 875 |
+
"learning_rate": 2.666102013928101e-05,
|
| 876 |
+
"loss": 0.8501,
|
| 877 |
+
"step": 62000
|
| 878 |
+
},
|
| 879 |
+
{
|
| 880 |
+
"epoch": 11.76359872012046,
|
| 881 |
+
"grad_norm": 3.4384429454803467,
|
| 882 |
+
"learning_rate": 2.647280255975908e-05,
|
| 883 |
+
"loss": 0.8546,
|
| 884 |
+
"step": 62500
|
| 885 |
+
},
|
| 886 |
+
{
|
| 887 |
+
"epoch": 11.857707509881424,
|
| 888 |
+
"grad_norm": 2.883970022201538,
|
| 889 |
+
"learning_rate": 2.6284584980237154e-05,
|
| 890 |
+
"loss": 0.8494,
|
| 891 |
+
"step": 63000
|
| 892 |
+
},
|
| 893 |
+
{
|
| 894 |
+
"epoch": 11.951816299642386,
|
| 895 |
+
"grad_norm": 3.2041871547698975,
|
| 896 |
+
"learning_rate": 2.6096367400715227e-05,
|
| 897 |
+
"loss": 0.8473,
|
| 898 |
+
"step": 63500
|
| 899 |
+
},
|
| 900 |
+
{
|
| 901 |
+
"epoch": 12.045925089403351,
|
| 902 |
+
"grad_norm": 3.7006897926330566,
|
| 903 |
+
"learning_rate": 2.59081498211933e-05,
|
| 904 |
+
"loss": 0.7851,
|
| 905 |
+
"step": 64000
|
| 906 |
+
},
|
| 907 |
+
{
|
| 908 |
+
"epoch": 12.140033879164314,
|
| 909 |
+
"grad_norm": 3.4774985313415527,
|
| 910 |
+
"learning_rate": 2.5719932241671373e-05,
|
| 911 |
+
"loss": 0.7241,
|
| 912 |
+
"step": 64500
|
| 913 |
+
},
|
| 914 |
+
{
|
| 915 |
+
"epoch": 12.234142668925278,
|
| 916 |
+
"grad_norm": 3.615403413772583,
|
| 917 |
+
"learning_rate": 2.5531714662149446e-05,
|
| 918 |
+
"loss": 0.7296,
|
| 919 |
+
"step": 65000
|
| 920 |
+
},
|
| 921 |
+
{
|
| 922 |
+
"epoch": 12.32825145868624,
|
| 923 |
+
"grad_norm": 4.831261157989502,
|
| 924 |
+
"learning_rate": 2.534349708262752e-05,
|
| 925 |
+
"loss": 0.7382,
|
| 926 |
+
"step": 65500
|
| 927 |
+
},
|
| 928 |
+
{
|
| 929 |
+
"epoch": 12.422360248447205,
|
| 930 |
+
"grad_norm": 3.072159767150879,
|
| 931 |
+
"learning_rate": 2.515527950310559e-05,
|
| 932 |
+
"loss": 0.733,
|
| 933 |
+
"step": 66000
|
| 934 |
+
},
|
| 935 |
+
{
|
| 936 |
+
"epoch": 12.516469038208168,
|
| 937 |
+
"grad_norm": 3.442324161529541,
|
| 938 |
+
"learning_rate": 2.4967061923583665e-05,
|
| 939 |
+
"loss": 0.7453,
|
| 940 |
+
"step": 66500
|
| 941 |
+
},
|
| 942 |
+
{
|
| 943 |
+
"epoch": 12.610577827969133,
|
| 944 |
+
"grad_norm": 2.71148419380188,
|
| 945 |
+
"learning_rate": 2.4778844344061735e-05,
|
| 946 |
+
"loss": 0.7388,
|
| 947 |
+
"step": 67000
|
| 948 |
+
},
|
| 949 |
+
{
|
| 950 |
+
"epoch": 12.704686617730095,
|
| 951 |
+
"grad_norm": 3.6085212230682373,
|
| 952 |
+
"learning_rate": 2.4590626764539808e-05,
|
| 953 |
+
"loss": 0.7444,
|
| 954 |
+
"step": 67500
|
| 955 |
+
},
|
| 956 |
+
{
|
| 957 |
+
"epoch": 12.79879540749106,
|
| 958 |
+
"grad_norm": 3.9403274059295654,
|
| 959 |
+
"learning_rate": 2.440240918501788e-05,
|
| 960 |
+
"loss": 0.7291,
|
| 961 |
+
"step": 68000
|
| 962 |
+
},
|
| 963 |
+
{
|
| 964 |
+
"epoch": 12.892904197252022,
|
| 965 |
+
"grad_norm": 3.322840929031372,
|
| 966 |
+
"learning_rate": 2.4214191605495954e-05,
|
| 967 |
+
"loss": 0.7523,
|
| 968 |
+
"step": 68500
|
| 969 |
+
},
|
| 970 |
+
{
|
| 971 |
+
"epoch": 12.987012987012987,
|
| 972 |
+
"grad_norm": 4.849690914154053,
|
| 973 |
+
"learning_rate": 2.4025974025974027e-05,
|
| 974 |
+
"loss": 0.7477,
|
| 975 |
+
"step": 69000
|
| 976 |
+
},
|
| 977 |
+
{
|
| 978 |
+
"epoch": 13.081121776773951,
|
| 979 |
+
"grad_norm": 4.5327959060668945,
|
| 980 |
+
"learning_rate": 2.38377564464521e-05,
|
| 981 |
+
"loss": 0.5957,
|
| 982 |
+
"step": 69500
|
| 983 |
+
},
|
| 984 |
+
{
|
| 985 |
+
"epoch": 13.175230566534914,
|
| 986 |
+
"grad_norm": 2.9526569843292236,
|
| 987 |
+
"learning_rate": 2.3649538866930173e-05,
|
| 988 |
+
"loss": 0.5829,
|
| 989 |
+
"step": 70000
|
| 990 |
+
},
|
| 991 |
+
{
|
| 992 |
+
"epoch": 13.269339356295879,
|
| 993 |
+
"grad_norm": 2.7245306968688965,
|
| 994 |
+
"learning_rate": 2.3461321287408243e-05,
|
| 995 |
+
"loss": 0.5948,
|
| 996 |
+
"step": 70500
|
| 997 |
+
},
|
| 998 |
+
{
|
| 999 |
+
"epoch": 13.363448146056841,
|
| 1000 |
+
"grad_norm": 3.7524588108062744,
|
| 1001 |
+
"learning_rate": 2.327310370788632e-05,
|
| 1002 |
+
"loss": 0.5956,
|
| 1003 |
+
"step": 71000
|
| 1004 |
+
},
|
| 1005 |
+
{
|
| 1006 |
+
"epoch": 13.457556935817806,
|
| 1007 |
+
"grad_norm": 4.387008190155029,
|
| 1008 |
+
"learning_rate": 2.3084886128364392e-05,
|
| 1009 |
+
"loss": 0.605,
|
| 1010 |
+
"step": 71500
|
| 1011 |
+
},
|
| 1012 |
+
{
|
| 1013 |
+
"epoch": 13.551665725578768,
|
| 1014 |
+
"grad_norm": 3.449723482131958,
|
| 1015 |
+
"learning_rate": 2.2896668548842462e-05,
|
| 1016 |
+
"loss": 0.6087,
|
| 1017 |
+
"step": 72000
|
| 1018 |
+
},
|
| 1019 |
+
{
|
| 1020 |
+
"epoch": 13.645774515339733,
|
| 1021 |
+
"grad_norm": 3.2176854610443115,
|
| 1022 |
+
"learning_rate": 2.2708450969320535e-05,
|
| 1023 |
+
"loss": 0.6141,
|
| 1024 |
+
"step": 72500
|
| 1025 |
+
},
|
| 1026 |
+
{
|
| 1027 |
+
"epoch": 13.739883305100696,
|
| 1028 |
+
"grad_norm": 4.136612415313721,
|
| 1029 |
+
"learning_rate": 2.2520233389798608e-05,
|
| 1030 |
+
"loss": 0.6251,
|
| 1031 |
+
"step": 73000
|
| 1032 |
+
},
|
| 1033 |
+
{
|
| 1034 |
+
"epoch": 13.83399209486166,
|
| 1035 |
+
"grad_norm": 4.145909786224365,
|
| 1036 |
+
"learning_rate": 2.233201581027668e-05,
|
| 1037 |
+
"loss": 0.6094,
|
| 1038 |
+
"step": 73500
|
| 1039 |
+
},
|
| 1040 |
+
{
|
| 1041 |
+
"epoch": 13.928100884622623,
|
| 1042 |
+
"grad_norm": 3.8660261631011963,
|
| 1043 |
+
"learning_rate": 2.2143798230754754e-05,
|
| 1044 |
+
"loss": 0.6194,
|
| 1045 |
+
"step": 74000
|
| 1046 |
+
},
|
| 1047 |
+
{
|
| 1048 |
+
"epoch": 14.022209674383587,
|
| 1049 |
+
"grad_norm": 3.511117696762085,
|
| 1050 |
+
"learning_rate": 2.1955580651232827e-05,
|
| 1051 |
+
"loss": 0.5712,
|
| 1052 |
+
"step": 74500
|
| 1053 |
+
},
|
| 1054 |
+
{
|
| 1055 |
+
"epoch": 14.116318464144552,
|
| 1056 |
+
"grad_norm": 2.771902084350586,
|
| 1057 |
+
"learning_rate": 2.17673630717109e-05,
|
| 1058 |
+
"loss": 0.4559,
|
| 1059 |
+
"step": 75000
|
| 1060 |
+
},
|
| 1061 |
+
{
|
| 1062 |
+
"epoch": 14.210427253905515,
|
| 1063 |
+
"grad_norm": 5.087037086486816,
|
| 1064 |
+
"learning_rate": 2.157914549218897e-05,
|
| 1065 |
+
"loss": 0.4529,
|
| 1066 |
+
"step": 75500
|
| 1067 |
+
},
|
| 1068 |
+
{
|
| 1069 |
+
"epoch": 14.304536043666479,
|
| 1070 |
+
"grad_norm": 4.842881679534912,
|
| 1071 |
+
"learning_rate": 2.1390927912667043e-05,
|
| 1072 |
+
"loss": 0.4567,
|
| 1073 |
+
"step": 76000
|
| 1074 |
+
},
|
| 1075 |
+
{
|
| 1076 |
+
"epoch": 14.398644833427442,
|
| 1077 |
+
"grad_norm": 3.444424629211426,
|
| 1078 |
+
"learning_rate": 2.120271033314512e-05,
|
| 1079 |
+
"loss": 0.4618,
|
| 1080 |
+
"step": 76500
|
| 1081 |
+
},
|
| 1082 |
+
{
|
| 1083 |
+
"epoch": 14.492753623188406,
|
| 1084 |
+
"grad_norm": 3.934549331665039,
|
| 1085 |
+
"learning_rate": 2.101449275362319e-05,
|
| 1086 |
+
"loss": 0.455,
|
| 1087 |
+
"step": 77000
|
| 1088 |
+
},
|
| 1089 |
+
{
|
| 1090 |
+
"epoch": 14.586862412949369,
|
| 1091 |
+
"grad_norm": 4.338078498840332,
|
| 1092 |
+
"learning_rate": 2.0826275174101262e-05,
|
| 1093 |
+
"loss": 0.472,
|
| 1094 |
+
"step": 77500
|
| 1095 |
+
},
|
| 1096 |
+
{
|
| 1097 |
+
"epoch": 14.680971202710333,
|
| 1098 |
+
"grad_norm": 3.781182050704956,
|
| 1099 |
+
"learning_rate": 2.0638057594579335e-05,
|
| 1100 |
+
"loss": 0.4613,
|
| 1101 |
+
"step": 78000
|
| 1102 |
+
},
|
| 1103 |
+
{
|
| 1104 |
+
"epoch": 14.775079992471296,
|
| 1105 |
+
"grad_norm": 3.866917371749878,
|
| 1106 |
+
"learning_rate": 2.0449840015057405e-05,
|
| 1107 |
+
"loss": 0.4791,
|
| 1108 |
+
"step": 78500
|
| 1109 |
+
},
|
| 1110 |
+
{
|
| 1111 |
+
"epoch": 14.86918878223226,
|
| 1112 |
+
"grad_norm": 3.5265841484069824,
|
| 1113 |
+
"learning_rate": 2.026162243553548e-05,
|
| 1114 |
+
"loss": 0.4709,
|
| 1115 |
+
"step": 79000
|
| 1116 |
+
},
|
| 1117 |
+
{
|
| 1118 |
+
"epoch": 14.963297571993223,
|
| 1119 |
+
"grad_norm": 3.3175408840179443,
|
| 1120 |
+
"learning_rate": 2.0073404856013554e-05,
|
| 1121 |
+
"loss": 0.4847,
|
| 1122 |
+
"step": 79500
|
| 1123 |
+
},
|
| 1124 |
+
{
|
| 1125 |
+
"epoch": 15.057406361754188,
|
| 1126 |
+
"grad_norm": 2.848555564880371,
|
| 1127 |
+
"learning_rate": 1.9885187276491627e-05,
|
| 1128 |
+
"loss": 0.3788,
|
| 1129 |
+
"step": 80000
|
| 1130 |
+
},
|
| 1131 |
+
{
|
| 1132 |
+
"epoch": 15.151515151515152,
|
| 1133 |
+
"grad_norm": 3.355653762817383,
|
| 1134 |
+
"learning_rate": 1.9696969696969697e-05,
|
| 1135 |
+
"loss": 0.3235,
|
| 1136 |
+
"step": 80500
|
| 1137 |
+
},
|
| 1138 |
+
{
|
| 1139 |
+
"epoch": 15.245623941276115,
|
| 1140 |
+
"grad_norm": 3.260960817337036,
|
| 1141 |
+
"learning_rate": 1.950875211744777e-05,
|
| 1142 |
+
"loss": 0.3162,
|
| 1143 |
+
"step": 81000
|
| 1144 |
+
},
|
| 1145 |
+
{
|
| 1146 |
+
"epoch": 15.33973273103708,
|
| 1147 |
+
"grad_norm": 3.9132673740386963,
|
| 1148 |
+
"learning_rate": 1.9320534537925843e-05,
|
| 1149 |
+
"loss": 0.3209,
|
| 1150 |
+
"step": 81500
|
| 1151 |
+
},
|
| 1152 |
+
{
|
| 1153 |
+
"epoch": 15.433841520798042,
|
| 1154 |
+
"grad_norm": 4.693389892578125,
|
| 1155 |
+
"learning_rate": 1.9132316958403916e-05,
|
| 1156 |
+
"loss": 0.3421,
|
| 1157 |
+
"step": 82000
|
| 1158 |
+
},
|
| 1159 |
+
{
|
| 1160 |
+
"epoch": 15.527950310559007,
|
| 1161 |
+
"grad_norm": 3.7237417697906494,
|
| 1162 |
+
"learning_rate": 1.894409937888199e-05,
|
| 1163 |
+
"loss": 0.3441,
|
| 1164 |
+
"step": 82500
|
| 1165 |
+
},
|
| 1166 |
+
{
|
| 1167 |
+
"epoch": 15.62205910031997,
|
| 1168 |
+
"grad_norm": 3.9301464557647705,
|
| 1169 |
+
"learning_rate": 1.8755881799360062e-05,
|
| 1170 |
+
"loss": 0.3424,
|
| 1171 |
+
"step": 83000
|
| 1172 |
+
},
|
| 1173 |
+
{
|
| 1174 |
+
"epoch": 15.716167890080934,
|
| 1175 |
+
"grad_norm": 4.186377048492432,
|
| 1176 |
+
"learning_rate": 1.8567664219838135e-05,
|
| 1177 |
+
"loss": 0.3503,
|
| 1178 |
+
"step": 83500
|
| 1179 |
+
},
|
| 1180 |
+
{
|
| 1181 |
+
"epoch": 15.810276679841897,
|
| 1182 |
+
"grad_norm": 3.6368534564971924,
|
| 1183 |
+
"learning_rate": 1.8379446640316205e-05,
|
| 1184 |
+
"loss": 0.3347,
|
| 1185 |
+
"step": 84000
|
| 1186 |
+
},
|
| 1187 |
+
{
|
| 1188 |
+
"epoch": 15.904385469602861,
|
| 1189 |
+
"grad_norm": 2.6787190437316895,
|
| 1190 |
+
"learning_rate": 1.8191229060794278e-05,
|
| 1191 |
+
"loss": 0.3445,
|
| 1192 |
+
"step": 84500
|
| 1193 |
+
},
|
| 1194 |
+
{
|
| 1195 |
+
"epoch": 15.998494259363824,
|
| 1196 |
+
"grad_norm": 3.942444324493408,
|
| 1197 |
+
"learning_rate": 1.8003011481272354e-05,
|
| 1198 |
+
"loss": 0.343,
|
| 1199 |
+
"step": 85000
|
| 1200 |
+
},
|
| 1201 |
+
{
|
| 1202 |
+
"epoch": 16.09260304912479,
|
| 1203 |
+
"grad_norm": 3.3087995052337646,
|
| 1204 |
+
"learning_rate": 1.7814793901750424e-05,
|
| 1205 |
+
"loss": 0.2093,
|
| 1206 |
+
"step": 85500
|
| 1207 |
+
},
|
| 1208 |
+
{
|
| 1209 |
+
"epoch": 16.186711838885753,
|
| 1210 |
+
"grad_norm": 4.419996738433838,
|
| 1211 |
+
"learning_rate": 1.7626576322228497e-05,
|
| 1212 |
+
"loss": 0.2209,
|
| 1213 |
+
"step": 86000
|
| 1214 |
+
},
|
| 1215 |
+
{
|
| 1216 |
+
"epoch": 16.280820628646715,
|
| 1217 |
+
"grad_norm": 4.352416515350342,
|
| 1218 |
+
"learning_rate": 1.743835874270657e-05,
|
| 1219 |
+
"loss": 0.2282,
|
| 1220 |
+
"step": 86500
|
| 1221 |
+
},
|
| 1222 |
+
{
|
| 1223 |
+
"epoch": 16.374929418407678,
|
| 1224 |
+
"grad_norm": 3.7437074184417725,
|
| 1225 |
+
"learning_rate": 1.725014116318464e-05,
|
| 1226 |
+
"loss": 0.232,
|
| 1227 |
+
"step": 87000
|
| 1228 |
+
},
|
| 1229 |
+
{
|
| 1230 |
+
"epoch": 16.469038208168644,
|
| 1231 |
+
"grad_norm": 6.4077534675598145,
|
| 1232 |
+
"learning_rate": 1.7061923583662716e-05,
|
| 1233 |
+
"loss": 0.2291,
|
| 1234 |
+
"step": 87500
|
| 1235 |
+
},
|
| 1236 |
+
{
|
| 1237 |
+
"epoch": 16.563146997929607,
|
| 1238 |
+
"grad_norm": 3.0419087409973145,
|
| 1239 |
+
"learning_rate": 1.687370600414079e-05,
|
| 1240 |
+
"loss": 0.2401,
|
| 1241 |
+
"step": 88000
|
| 1242 |
+
},
|
| 1243 |
+
{
|
| 1244 |
+
"epoch": 16.65725578769057,
|
| 1245 |
+
"grad_norm": 4.095304012298584,
|
| 1246 |
+
"learning_rate": 1.6685488424618862e-05,
|
| 1247 |
+
"loss": 0.233,
|
| 1248 |
+
"step": 88500
|
| 1249 |
+
},
|
| 1250 |
+
{
|
| 1251 |
+
"epoch": 16.751364577451533,
|
| 1252 |
+
"grad_norm": 3.372295618057251,
|
| 1253 |
+
"learning_rate": 1.649727084509693e-05,
|
| 1254 |
+
"loss": 0.2354,
|
| 1255 |
+
"step": 89000
|
| 1256 |
+
},
|
| 1257 |
+
{
|
| 1258 |
+
"epoch": 16.8454733672125,
|
| 1259 |
+
"grad_norm": 2.918405771255493,
|
| 1260 |
+
"learning_rate": 1.6309053265575005e-05,
|
| 1261 |
+
"loss": 0.2421,
|
| 1262 |
+
"step": 89500
|
| 1263 |
+
},
|
| 1264 |
+
{
|
| 1265 |
+
"epoch": 16.93958215697346,
|
| 1266 |
+
"grad_norm": 2.4548110961914062,
|
| 1267 |
+
"learning_rate": 1.6120835686053078e-05,
|
| 1268 |
+
"loss": 0.2374,
|
| 1269 |
+
"step": 90000
|
| 1270 |
+
},
|
| 1271 |
+
{
|
| 1272 |
+
"epoch": 17.033690946734424,
|
| 1273 |
+
"grad_norm": 4.15058708190918,
|
| 1274 |
+
"learning_rate": 1.593261810653115e-05,
|
| 1275 |
+
"loss": 0.2135,
|
| 1276 |
+
"step": 90500
|
| 1277 |
+
},
|
| 1278 |
+
{
|
| 1279 |
+
"epoch": 17.12779973649539,
|
| 1280 |
+
"grad_norm": 2.979170083999634,
|
| 1281 |
+
"learning_rate": 1.5744400527009224e-05,
|
| 1282 |
+
"loss": 0.1495,
|
| 1283 |
+
"step": 91000
|
| 1284 |
+
},
|
| 1285 |
+
{
|
| 1286 |
+
"epoch": 17.221908526256353,
|
| 1287 |
+
"grad_norm": 3.950493574142456,
|
| 1288 |
+
"learning_rate": 1.5556182947487297e-05,
|
| 1289 |
+
"loss": 0.1503,
|
| 1290 |
+
"step": 91500
|
| 1291 |
+
},
|
| 1292 |
+
{
|
| 1293 |
+
"epoch": 17.316017316017316,
|
| 1294 |
+
"grad_norm": 3.174896001815796,
|
| 1295 |
+
"learning_rate": 1.5367965367965366e-05,
|
| 1296 |
+
"loss": 0.1559,
|
| 1297 |
+
"step": 92000
|
| 1298 |
+
},
|
| 1299 |
+
{
|
| 1300 |
+
"epoch": 17.41012610577828,
|
| 1301 |
+
"grad_norm": 3.4672741889953613,
|
| 1302 |
+
"learning_rate": 1.5179747788443441e-05,
|
| 1303 |
+
"loss": 0.1606,
|
| 1304 |
+
"step": 92500
|
| 1305 |
+
},
|
| 1306 |
+
{
|
| 1307 |
+
"epoch": 17.504234895539245,
|
| 1308 |
+
"grad_norm": 3.950160026550293,
|
| 1309 |
+
"learning_rate": 1.4991530208921514e-05,
|
| 1310 |
+
"loss": 0.1561,
|
| 1311 |
+
"step": 93000
|
| 1312 |
+
},
|
| 1313 |
+
{
|
| 1314 |
+
"epoch": 17.598343685300208,
|
| 1315 |
+
"grad_norm": 3.546109199523926,
|
| 1316 |
+
"learning_rate": 1.4803312629399587e-05,
|
| 1317 |
+
"loss": 0.1622,
|
| 1318 |
+
"step": 93500
|
| 1319 |
+
},
|
| 1320 |
+
{
|
| 1321 |
+
"epoch": 17.69245247506117,
|
| 1322 |
+
"grad_norm": 6.592913627624512,
|
| 1323 |
+
"learning_rate": 1.4615095049877658e-05,
|
| 1324 |
+
"loss": 0.1644,
|
| 1325 |
+
"step": 94000
|
| 1326 |
+
},
|
| 1327 |
+
{
|
| 1328 |
+
"epoch": 17.786561264822133,
|
| 1329 |
+
"grad_norm": 2.762545347213745,
|
| 1330 |
+
"learning_rate": 1.4426877470355732e-05,
|
| 1331 |
+
"loss": 0.1614,
|
| 1332 |
+
"step": 94500
|
| 1333 |
+
},
|
| 1334 |
+
{
|
| 1335 |
+
"epoch": 17.8806700545831,
|
| 1336 |
+
"grad_norm": 2.9720265865325928,
|
| 1337 |
+
"learning_rate": 1.4238659890833805e-05,
|
| 1338 |
+
"loss": 0.1577,
|
| 1339 |
+
"step": 95000
|
| 1340 |
+
},
|
| 1341 |
+
{
|
| 1342 |
+
"epoch": 17.974778844344062,
|
| 1343 |
+
"grad_norm": 3.006880283355713,
|
| 1344 |
+
"learning_rate": 1.4050442311311876e-05,
|
| 1345 |
+
"loss": 0.1577,
|
| 1346 |
+
"step": 95500
|
| 1347 |
+
},
|
| 1348 |
+
{
|
| 1349 |
+
"epoch": 18.068887634105025,
|
| 1350 |
+
"grad_norm": 2.86936616897583,
|
| 1351 |
+
"learning_rate": 1.3862224731789949e-05,
|
| 1352 |
+
"loss": 0.1162,
|
| 1353 |
+
"step": 96000
|
| 1354 |
+
},
|
| 1355 |
+
{
|
| 1356 |
+
"epoch": 18.162996423865987,
|
| 1357 |
+
"grad_norm": 3.608914852142334,
|
| 1358 |
+
"learning_rate": 1.3674007152268024e-05,
|
| 1359 |
+
"loss": 0.1001,
|
| 1360 |
+
"step": 96500
|
| 1361 |
+
},
|
| 1362 |
+
{
|
| 1363 |
+
"epoch": 18.257105213626954,
|
| 1364 |
+
"grad_norm": 3.126116991043091,
|
| 1365 |
+
"learning_rate": 1.3485789572746097e-05,
|
| 1366 |
+
"loss": 0.1082,
|
| 1367 |
+
"step": 97000
|
| 1368 |
+
},
|
| 1369 |
+
{
|
| 1370 |
+
"epoch": 18.351214003387916,
|
| 1371 |
+
"grad_norm": 2.9935250282287598,
|
| 1372 |
+
"learning_rate": 1.3297571993224166e-05,
|
| 1373 |
+
"loss": 0.109,
|
| 1374 |
+
"step": 97500
|
| 1375 |
+
},
|
| 1376 |
+
{
|
| 1377 |
+
"epoch": 18.44532279314888,
|
| 1378 |
+
"grad_norm": 1.9776825904846191,
|
| 1379 |
+
"learning_rate": 1.3109354413702241e-05,
|
| 1380 |
+
"loss": 0.1031,
|
| 1381 |
+
"step": 98000
|
| 1382 |
+
},
|
| 1383 |
+
{
|
| 1384 |
+
"epoch": 18.539431582909845,
|
| 1385 |
+
"grad_norm": 4.182958602905273,
|
| 1386 |
+
"learning_rate": 1.2921136834180314e-05,
|
| 1387 |
+
"loss": 0.1084,
|
| 1388 |
+
"step": 98500
|
| 1389 |
+
},
|
| 1390 |
+
{
|
| 1391 |
+
"epoch": 18.633540372670808,
|
| 1392 |
+
"grad_norm": 3.405510902404785,
|
| 1393 |
+
"learning_rate": 1.2732919254658385e-05,
|
| 1394 |
+
"loss": 0.1069,
|
| 1395 |
+
"step": 99000
|
| 1396 |
+
},
|
| 1397 |
+
{
|
| 1398 |
+
"epoch": 18.72764916243177,
|
| 1399 |
+
"grad_norm": 2.7036936283111572,
|
| 1400 |
+
"learning_rate": 1.2544701675136458e-05,
|
| 1401 |
+
"loss": 0.1084,
|
| 1402 |
+
"step": 99500
|
| 1403 |
+
},
|
| 1404 |
+
{
|
| 1405 |
+
"epoch": 18.821757952192733,
|
| 1406 |
+
"grad_norm": 2.601555347442627,
|
| 1407 |
+
"learning_rate": 1.235648409561453e-05,
|
| 1408 |
+
"loss": 0.1097,
|
| 1409 |
+
"step": 100000
|
| 1410 |
+
},
|
| 1411 |
+
{
|
| 1412 |
+
"epoch": 18.9158667419537,
|
| 1413 |
+
"grad_norm": 2.9937756061553955,
|
| 1414 |
+
"learning_rate": 1.2168266516092605e-05,
|
| 1415 |
+
"loss": 0.1004,
|
| 1416 |
+
"step": 100500
|
| 1417 |
+
},
|
| 1418 |
+
{
|
| 1419 |
+
"epoch": 19.009975531714662,
|
| 1420 |
+
"grad_norm": 1.493790864944458,
|
| 1421 |
+
"learning_rate": 1.1980048936570676e-05,
|
| 1422 |
+
"loss": 0.1032,
|
| 1423 |
+
"step": 101000
|
| 1424 |
+
},
|
| 1425 |
+
{
|
| 1426 |
+
"epoch": 19.104084321475625,
|
| 1427 |
+
"grad_norm": 1.7063292264938354,
|
| 1428 |
+
"learning_rate": 1.1791831357048749e-05,
|
| 1429 |
+
"loss": 0.0667,
|
| 1430 |
+
"step": 101500
|
| 1431 |
+
},
|
| 1432 |
+
{
|
| 1433 |
+
"epoch": 19.198193111236588,
|
| 1434 |
+
"grad_norm": 2.8355624675750732,
|
| 1435 |
+
"learning_rate": 1.1603613777526822e-05,
|
| 1436 |
+
"loss": 0.0678,
|
| 1437 |
+
"step": 102000
|
| 1438 |
+
},
|
| 1439 |
+
{
|
| 1440 |
+
"epoch": 19.292301900997554,
|
| 1441 |
+
"grad_norm": 1.7610359191894531,
|
| 1442 |
+
"learning_rate": 1.1415396198004895e-05,
|
| 1443 |
+
"loss": 0.0654,
|
| 1444 |
+
"step": 102500
|
| 1445 |
+
},
|
| 1446 |
+
{
|
| 1447 |
+
"epoch": 19.386410690758517,
|
| 1448 |
+
"grad_norm": 2.759197950363159,
|
| 1449 |
+
"learning_rate": 1.1227178618482966e-05,
|
| 1450 |
+
"loss": 0.0717,
|
| 1451 |
+
"step": 103000
|
| 1452 |
+
},
|
| 1453 |
+
{
|
| 1454 |
+
"epoch": 19.48051948051948,
|
| 1455 |
+
"grad_norm": 2.657435417175293,
|
| 1456 |
+
"learning_rate": 1.103896103896104e-05,
|
| 1457 |
+
"loss": 0.0722,
|
| 1458 |
+
"step": 103500
|
| 1459 |
+
},
|
| 1460 |
+
{
|
| 1461 |
+
"epoch": 19.574628270280446,
|
| 1462 |
+
"grad_norm": 2.5865299701690674,
|
| 1463 |
+
"learning_rate": 1.0850743459439112e-05,
|
| 1464 |
+
"loss": 0.0689,
|
| 1465 |
+
"step": 104000
|
| 1466 |
+
},
|
| 1467 |
+
{
|
| 1468 |
+
"epoch": 19.66873706004141,
|
| 1469 |
+
"grad_norm": 4.484961986541748,
|
| 1470 |
+
"learning_rate": 1.0662525879917184e-05,
|
| 1471 |
+
"loss": 0.0706,
|
| 1472 |
+
"step": 104500
|
| 1473 |
+
},
|
| 1474 |
+
{
|
| 1475 |
+
"epoch": 19.76284584980237,
|
| 1476 |
+
"grad_norm": 2.431190252304077,
|
| 1477 |
+
"learning_rate": 1.0474308300395258e-05,
|
| 1478 |
+
"loss": 0.0691,
|
| 1479 |
+
"step": 105000
|
| 1480 |
+
},
|
| 1481 |
+
{
|
| 1482 |
+
"epoch": 19.856954639563334,
|
| 1483 |
+
"grad_norm": 2.6577088832855225,
|
| 1484 |
+
"learning_rate": 1.028609072087333e-05,
|
| 1485 |
+
"loss": 0.0704,
|
| 1486 |
+
"step": 105500
|
| 1487 |
+
},
|
| 1488 |
+
{
|
| 1489 |
+
"epoch": 19.9510634293243,
|
| 1490 |
+
"grad_norm": 3.1382012367248535,
|
| 1491 |
+
"learning_rate": 1.0097873141351403e-05,
|
| 1492 |
+
"loss": 0.0673,
|
| 1493 |
+
"step": 106000
|
| 1494 |
+
},
|
| 1495 |
+
{
|
| 1496 |
+
"epoch": 20.045172219085263,
|
| 1497 |
+
"grad_norm": 1.5920716524124146,
|
| 1498 |
+
"learning_rate": 9.909655561829476e-06,
|
| 1499 |
+
"loss": 0.0605,
|
| 1500 |
+
"step": 106500
|
| 1501 |
+
},
|
| 1502 |
+
{
|
| 1503 |
+
"epoch": 20.139281008846226,
|
| 1504 |
+
"grad_norm": 0.49824026226997375,
|
| 1505 |
+
"learning_rate": 9.721437982307547e-06,
|
| 1506 |
+
"loss": 0.0427,
|
| 1507 |
+
"step": 107000
|
| 1508 |
+
},
|
| 1509 |
+
{
|
| 1510 |
+
"epoch": 20.23338979860719,
|
| 1511 |
+
"grad_norm": 1.5648902654647827,
|
| 1512 |
+
"learning_rate": 9.533220402785622e-06,
|
| 1513 |
+
"loss": 0.042,
|
| 1514 |
+
"step": 107500
|
| 1515 |
+
},
|
| 1516 |
+
{
|
| 1517 |
+
"epoch": 20.327498588368154,
|
| 1518 |
+
"grad_norm": 2.084714889526367,
|
| 1519 |
+
"learning_rate": 9.345002823263693e-06,
|
| 1520 |
+
"loss": 0.0442,
|
| 1521 |
+
"step": 108000
|
| 1522 |
+
},
|
| 1523 |
+
{
|
| 1524 |
+
"epoch": 20.421607378129117,
|
| 1525 |
+
"grad_norm": 2.1811583042144775,
|
| 1526 |
+
"learning_rate": 9.156785243741765e-06,
|
| 1527 |
+
"loss": 0.0424,
|
| 1528 |
+
"step": 108500
|
| 1529 |
+
},
|
| 1530 |
+
{
|
| 1531 |
+
"epoch": 20.51571616789008,
|
| 1532 |
+
"grad_norm": 3.9864232540130615,
|
| 1533 |
+
"learning_rate": 8.96856766421984e-06,
|
| 1534 |
+
"loss": 0.0439,
|
| 1535 |
+
"step": 109000
|
| 1536 |
+
},
|
| 1537 |
+
{
|
| 1538 |
+
"epoch": 20.609824957651046,
|
| 1539 |
+
"grad_norm": 4.495816707611084,
|
| 1540 |
+
"learning_rate": 8.78035008469791e-06,
|
| 1541 |
+
"loss": 0.0433,
|
| 1542 |
+
"step": 109500
|
| 1543 |
+
},
|
| 1544 |
+
{
|
| 1545 |
+
"epoch": 20.70393374741201,
|
| 1546 |
+
"grad_norm": 1.6480516195297241,
|
| 1547 |
+
"learning_rate": 8.592132505175984e-06,
|
| 1548 |
+
"loss": 0.0454,
|
| 1549 |
+
"step": 110000
|
| 1550 |
+
},
|
| 1551 |
+
{
|
| 1552 |
+
"epoch": 20.79804253717297,
|
| 1553 |
+
"grad_norm": 1.1842634677886963,
|
| 1554 |
+
"learning_rate": 8.403914925654057e-06,
|
| 1555 |
+
"loss": 0.0425,
|
| 1556 |
+
"step": 110500
|
| 1557 |
+
},
|
| 1558 |
+
{
|
| 1559 |
+
"epoch": 20.892151326933934,
|
| 1560 |
+
"grad_norm": 4.60665225982666,
|
| 1561 |
+
"learning_rate": 8.215697346132128e-06,
|
| 1562 |
+
"loss": 0.0419,
|
| 1563 |
+
"step": 111000
|
| 1564 |
+
},
|
| 1565 |
+
{
|
| 1566 |
+
"epoch": 20.9862601166949,
|
| 1567 |
+
"grad_norm": 3.4669153690338135,
|
| 1568 |
+
"learning_rate": 8.027479766610201e-06,
|
| 1569 |
+
"loss": 0.0412,
|
| 1570 |
+
"step": 111500
|
| 1571 |
+
},
|
| 1572 |
+
{
|
| 1573 |
+
"epoch": 21.080368906455863,
|
| 1574 |
+
"grad_norm": 0.7074203491210938,
|
| 1575 |
+
"learning_rate": 7.839262187088274e-06,
|
| 1576 |
+
"loss": 0.0285,
|
| 1577 |
+
"step": 112000
|
| 1578 |
+
},
|
| 1579 |
+
{
|
| 1580 |
+
"epoch": 21.174477696216826,
|
| 1581 |
+
"grad_norm": 2.58770489692688,
|
| 1582 |
+
"learning_rate": 7.651044607566347e-06,
|
| 1583 |
+
"loss": 0.0275,
|
| 1584 |
+
"step": 112500
|
| 1585 |
+
},
|
| 1586 |
+
{
|
| 1587 |
+
"epoch": 21.26858648597779,
|
| 1588 |
+
"grad_norm": 0.6419113874435425,
|
| 1589 |
+
"learning_rate": 7.462827028044419e-06,
|
| 1590 |
+
"loss": 0.0263,
|
| 1591 |
+
"step": 113000
|
| 1592 |
+
},
|
| 1593 |
+
{
|
| 1594 |
+
"epoch": 21.362695275738755,
|
| 1595 |
+
"grad_norm": 2.158191204071045,
|
| 1596 |
+
"learning_rate": 7.274609448522493e-06,
|
| 1597 |
+
"loss": 0.0267,
|
| 1598 |
+
"step": 113500
|
| 1599 |
+
},
|
| 1600 |
+
{
|
| 1601 |
+
"epoch": 21.456804065499718,
|
| 1602 |
+
"grad_norm": 1.1450761556625366,
|
| 1603 |
+
"learning_rate": 7.0863918690005655e-06,
|
| 1604 |
+
"loss": 0.024,
|
| 1605 |
+
"step": 114000
|
| 1606 |
+
},
|
| 1607 |
+
{
|
| 1608 |
+
"epoch": 21.55091285526068,
|
| 1609 |
+
"grad_norm": 0.9204089045524597,
|
| 1610 |
+
"learning_rate": 6.898174289478637e-06,
|
| 1611 |
+
"loss": 0.0273,
|
| 1612 |
+
"step": 114500
|
| 1613 |
+
},
|
| 1614 |
+
{
|
| 1615 |
+
"epoch": 21.645021645021647,
|
| 1616 |
+
"grad_norm": 1.3897809982299805,
|
| 1617 |
+
"learning_rate": 6.709956709956711e-06,
|
| 1618 |
+
"loss": 0.0276,
|
| 1619 |
+
"step": 115000
|
| 1620 |
+
},
|
| 1621 |
+
{
|
| 1622 |
+
"epoch": 21.73913043478261,
|
| 1623 |
+
"grad_norm": 2.818786382675171,
|
| 1624 |
+
"learning_rate": 6.521739130434783e-06,
|
| 1625 |
+
"loss": 0.027,
|
| 1626 |
+
"step": 115500
|
| 1627 |
+
},
|
| 1628 |
+
{
|
| 1629 |
+
"epoch": 21.833239224543572,
|
| 1630 |
+
"grad_norm": 1.8107503652572632,
|
| 1631 |
+
"learning_rate": 6.333521550912856e-06,
|
| 1632 |
+
"loss": 0.025,
|
| 1633 |
+
"step": 116000
|
| 1634 |
+
},
|
| 1635 |
+
{
|
| 1636 |
+
"epoch": 21.927348014304535,
|
| 1637 |
+
"grad_norm": 2.591801881790161,
|
| 1638 |
+
"learning_rate": 6.145303971390928e-06,
|
| 1639 |
+
"loss": 0.0254,
|
| 1640 |
+
"step": 116500
|
| 1641 |
+
},
|
| 1642 |
+
{
|
| 1643 |
+
"epoch": 22.0214568040655,
|
| 1644 |
+
"grad_norm": 1.22541344165802,
|
| 1645 |
+
"learning_rate": 5.957086391869001e-06,
|
| 1646 |
+
"loss": 0.0207,
|
| 1647 |
+
"step": 117000
|
| 1648 |
+
},
|
| 1649 |
+
{
|
| 1650 |
+
"epoch": 22.115565593826464,
|
| 1651 |
+
"grad_norm": 2.6778624057769775,
|
| 1652 |
+
"learning_rate": 5.768868812347074e-06,
|
| 1653 |
+
"loss": 0.0148,
|
| 1654 |
+
"step": 117500
|
| 1655 |
+
},
|
| 1656 |
+
{
|
| 1657 |
+
"epoch": 22.209674383587426,
|
| 1658 |
+
"grad_norm": 1.2167950868606567,
|
| 1659 |
+
"learning_rate": 5.5806512328251455e-06,
|
| 1660 |
+
"loss": 0.0134,
|
| 1661 |
+
"step": 118000
|
| 1662 |
+
},
|
| 1663 |
+
{
|
| 1664 |
+
"epoch": 22.30378317334839,
|
| 1665 |
+
"grad_norm": 0.1222626119852066,
|
| 1666 |
+
"learning_rate": 5.3924336533032186e-06,
|
| 1667 |
+
"loss": 0.0175,
|
| 1668 |
+
"step": 118500
|
| 1669 |
+
},
|
| 1670 |
+
{
|
| 1671 |
+
"epoch": 22.397891963109355,
|
| 1672 |
+
"grad_norm": 0.3822714686393738,
|
| 1673 |
+
"learning_rate": 5.204216073781292e-06,
|
| 1674 |
+
"loss": 0.0156,
|
| 1675 |
+
"step": 119000
|
| 1676 |
+
},
|
| 1677 |
+
{
|
| 1678 |
+
"epoch": 22.492000752870318,
|
| 1679 |
+
"grad_norm": 0.542395293712616,
|
| 1680 |
+
"learning_rate": 5.015998494259365e-06,
|
| 1681 |
+
"loss": 0.0141,
|
| 1682 |
+
"step": 119500
|
| 1683 |
+
},
|
| 1684 |
+
{
|
| 1685 |
+
"epoch": 22.58610954263128,
|
| 1686 |
+
"grad_norm": 1.051392674446106,
|
| 1687 |
+
"learning_rate": 4.827780914737437e-06,
|
| 1688 |
+
"loss": 0.0138,
|
| 1689 |
+
"step": 120000
|
| 1690 |
+
},
|
| 1691 |
+
{
|
| 1692 |
+
"epoch": 22.680218332392247,
|
| 1693 |
+
"grad_norm": 1.7265046834945679,
|
| 1694 |
+
"learning_rate": 4.639563335215509e-06,
|
| 1695 |
+
"loss": 0.0139,
|
| 1696 |
+
"step": 120500
|
| 1697 |
+
},
|
| 1698 |
+
{
|
| 1699 |
+
"epoch": 22.77432712215321,
|
| 1700 |
+
"grad_norm": 0.8157036304473877,
|
| 1701 |
+
"learning_rate": 4.451345755693582e-06,
|
| 1702 |
+
"loss": 0.0147,
|
| 1703 |
+
"step": 121000
|
| 1704 |
+
},
|
| 1705 |
+
{
|
| 1706 |
+
"epoch": 22.868435911914172,
|
| 1707 |
+
"grad_norm": 2.212116003036499,
|
| 1708 |
+
"learning_rate": 4.263128176171654e-06,
|
| 1709 |
+
"loss": 0.0157,
|
| 1710 |
+
"step": 121500
|
| 1711 |
+
},
|
| 1712 |
+
{
|
| 1713 |
+
"epoch": 22.962544701675135,
|
| 1714 |
+
"grad_norm": 1.5762394666671753,
|
| 1715 |
+
"learning_rate": 4.074910596649727e-06,
|
| 1716 |
+
"loss": 0.0139,
|
| 1717 |
+
"step": 122000
|
| 1718 |
+
},
|
| 1719 |
+
{
|
| 1720 |
+
"epoch": 23.0566534914361,
|
| 1721 |
+
"grad_norm": 0.16070736944675446,
|
| 1722 |
+
"learning_rate": 3.8866930171278e-06,
|
| 1723 |
+
"loss": 0.0113,
|
| 1724 |
+
"step": 122500
|
| 1725 |
+
},
|
| 1726 |
+
{
|
| 1727 |
+
"epoch": 23.150762281197064,
|
| 1728 |
+
"grad_norm": 0.6197986602783203,
|
| 1729 |
+
"learning_rate": 3.698475437605872e-06,
|
| 1730 |
+
"loss": 0.0066,
|
| 1731 |
+
"step": 123000
|
| 1732 |
+
},
|
| 1733 |
+
{
|
| 1734 |
+
"epoch": 23.244871070958027,
|
| 1735 |
+
"grad_norm": 0.2145221084356308,
|
| 1736 |
+
"learning_rate": 3.510257858083945e-06,
|
| 1737 |
+
"loss": 0.0061,
|
| 1738 |
+
"step": 123500
|
| 1739 |
+
},
|
| 1740 |
+
{
|
| 1741 |
+
"epoch": 23.33897986071899,
|
| 1742 |
+
"grad_norm": 0.1779479682445526,
|
| 1743 |
+
"learning_rate": 3.3220402785620177e-06,
|
| 1744 |
+
"loss": 0.0059,
|
| 1745 |
+
"step": 124000
|
| 1746 |
+
},
|
| 1747 |
+
{
|
| 1748 |
+
"epoch": 23.433088650479956,
|
| 1749 |
+
"grad_norm": 0.18615959584712982,
|
| 1750 |
+
"learning_rate": 3.1338226990400907e-06,
|
| 1751 |
+
"loss": 0.0057,
|
| 1752 |
+
"step": 124500
|
| 1753 |
+
},
|
| 1754 |
+
{
|
| 1755 |
+
"epoch": 23.52719744024092,
|
| 1756 |
+
"grad_norm": 1.9545246362686157,
|
| 1757 |
+
"learning_rate": 2.945605119518163e-06,
|
| 1758 |
+
"loss": 0.0067,
|
| 1759 |
+
"step": 125000
|
| 1760 |
+
},
|
| 1761 |
+
{
|
| 1762 |
+
"epoch": 23.62130623000188,
|
| 1763 |
+
"grad_norm": 2.255216598510742,
|
| 1764 |
+
"learning_rate": 2.7573875399962355e-06,
|
| 1765 |
+
"loss": 0.0062,
|
| 1766 |
+
"step": 125500
|
| 1767 |
+
},
|
| 1768 |
+
{
|
| 1769 |
+
"epoch": 23.715415019762847,
|
| 1770 |
+
"grad_norm": 0.28629258275032043,
|
| 1771 |
+
"learning_rate": 2.5691699604743086e-06,
|
| 1772 |
+
"loss": 0.0054,
|
| 1773 |
+
"step": 126000
|
| 1774 |
+
},
|
| 1775 |
+
{
|
| 1776 |
+
"epoch": 23.80952380952381,
|
| 1777 |
+
"grad_norm": 0.1650991588830948,
|
| 1778 |
+
"learning_rate": 2.3809523809523808e-06,
|
| 1779 |
+
"loss": 0.0056,
|
| 1780 |
+
"step": 126500
|
| 1781 |
+
},
|
| 1782 |
+
{
|
| 1783 |
+
"epoch": 23.903632599284773,
|
| 1784 |
+
"grad_norm": 0.45735275745391846,
|
| 1785 |
+
"learning_rate": 2.192734801430454e-06,
|
| 1786 |
+
"loss": 0.006,
|
| 1787 |
+
"step": 127000
|
| 1788 |
+
},
|
| 1789 |
+
{
|
| 1790 |
+
"epoch": 23.997741389045736,
|
| 1791 |
+
"grad_norm": 1.3017574548721313,
|
| 1792 |
+
"learning_rate": 2.0045172219085264e-06,
|
| 1793 |
+
"loss": 0.0047,
|
| 1794 |
+
"step": 127500
|
| 1795 |
+
},
|
| 1796 |
+
{
|
| 1797 |
+
"epoch": 24.091850178806702,
|
| 1798 |
+
"grad_norm": 0.15063992142677307,
|
| 1799 |
+
"learning_rate": 1.8162996423865988e-06,
|
| 1800 |
+
"loss": 0.0037,
|
| 1801 |
+
"step": 128000
|
| 1802 |
+
},
|
| 1803 |
+
{
|
| 1804 |
+
"epoch": 24.185958968567665,
|
| 1805 |
+
"grad_norm": 0.09415856748819351,
|
| 1806 |
+
"learning_rate": 1.6280820628646716e-06,
|
| 1807 |
+
"loss": 0.0021,
|
| 1808 |
+
"step": 128500
|
| 1809 |
+
},
|
| 1810 |
+
{
|
| 1811 |
+
"epoch": 24.280067758328627,
|
| 1812 |
+
"grad_norm": 0.06203685700893402,
|
| 1813 |
+
"learning_rate": 1.4398644833427442e-06,
|
| 1814 |
+
"loss": 0.0017,
|
| 1815 |
+
"step": 129000
|
| 1816 |
+
},
|
| 1817 |
+
{
|
| 1818 |
+
"epoch": 24.37417654808959,
|
| 1819 |
+
"grad_norm": 1.0590204000473022,
|
| 1820 |
+
"learning_rate": 1.2516469038208169e-06,
|
| 1821 |
+
"loss": 0.0016,
|
| 1822 |
+
"step": 129500
|
| 1823 |
+
},
|
| 1824 |
+
{
|
| 1825 |
+
"epoch": 24.468285337850556,
|
| 1826 |
+
"grad_norm": 0.05048515647649765,
|
| 1827 |
+
"learning_rate": 1.0634293242988897e-06,
|
| 1828 |
+
"loss": 0.0014,
|
| 1829 |
+
"step": 130000
|
| 1830 |
+
},
|
| 1831 |
+
{
|
| 1832 |
+
"epoch": 24.56239412761152,
|
| 1833 |
+
"grad_norm": 0.10998225957155228,
|
| 1834 |
+
"learning_rate": 8.752117447769622e-07,
|
| 1835 |
+
"loss": 0.0014,
|
| 1836 |
+
"step": 130500
|
| 1837 |
+
},
|
| 1838 |
+
{
|
| 1839 |
+
"epoch": 24.65650291737248,
|
| 1840 |
+
"grad_norm": 0.03882027417421341,
|
| 1841 |
+
"learning_rate": 6.869941652550348e-07,
|
| 1842 |
+
"loss": 0.0013,
|
| 1843 |
+
"step": 131000
|
| 1844 |
+
},
|
| 1845 |
+
{
|
| 1846 |
+
"epoch": 24.750611707133448,
|
| 1847 |
+
"grad_norm": 0.09357800334692001,
|
| 1848 |
+
"learning_rate": 4.987765857331075e-07,
|
| 1849 |
+
"loss": 0.0016,
|
| 1850 |
+
"step": 131500
|
| 1851 |
+
},
|
| 1852 |
+
{
|
| 1853 |
+
"epoch": 24.84472049689441,
|
| 1854 |
+
"grad_norm": 0.18081815540790558,
|
| 1855 |
+
"learning_rate": 3.1055900621118013e-07,
|
| 1856 |
+
"loss": 0.0016,
|
| 1857 |
+
"step": 132000
|
| 1858 |
+
},
|
| 1859 |
+
{
|
| 1860 |
+
"epoch": 24.938829286655373,
|
| 1861 |
+
"grad_norm": 0.04123268648982048,
|
| 1862 |
+
"learning_rate": 1.223414266892528e-07,
|
| 1863 |
+
"loss": 0.0025,
|
| 1864 |
+
"step": 132500
|
| 1865 |
+
},
|
| 1866 |
+
{
|
| 1867 |
+
"epoch": 25.0,
|
| 1868 |
+
"step": 132825,
|
| 1869 |
+
"total_flos": 2.908084043402707e+18,
|
| 1870 |
+
"train_loss": 0.022898558901232692,
|
| 1871 |
+
"train_runtime": 71987.3815,
|
| 1872 |
+
"train_samples_per_second": 29.519,
|
| 1873 |
+
"train_steps_per_second": 1.845
|
| 1874 |
+
}
|
| 1875 |
+
],
|
| 1876 |
+
"logging_steps": 500,
|
| 1877 |
+
"max_steps": 132825,
|
| 1878 |
+
"num_input_tokens_seen": 0,
|
| 1879 |
+
"num_train_epochs": 25,
|
| 1880 |
+
"save_steps": 500,
|
| 1881 |
+
"stateful_callbacks": {
|
| 1882 |
+
"TrainerControl": {
|
| 1883 |
+
"args": {
|
| 1884 |
+
"should_epoch_stop": false,
|
| 1885 |
+
"should_evaluate": false,
|
| 1886 |
+
"should_log": false,
|
| 1887 |
+
"should_save": true,
|
| 1888 |
+
"should_training_stop": true
|
| 1889 |
+
},
|
| 1890 |
+
"attributes": {}
|
| 1891 |
+
}
|
| 1892 |
+
},
|
| 1893 |
+
"total_flos": 2.908084043402707e+18,
|
| 1894 |
+
"train_batch_size": 4,
|
| 1895 |
+
"trial_name": null,
|
| 1896 |
+
"trial_params": null
|
| 1897 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:53a9d00bf42218bdcbd7c8da9324b0057468caafe642d0087c1792faedb39880
|
| 3 |
+
size 6456
|