Step 27500
Browse files- config.json +34 -0
- optimizer.pt +3 -0
- pytorch_model.bin +3 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- special_tokens_map.json +1 -0
- tokenizer.json +0 -0
- tokenizer_config.json +1 -0
- trainer_state.json +346 -0
- training_args.bin +3 -0
- vocab.txt +0 -0
config.json
ADDED
|
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "hfl/chinese-roberta-wwm-ext",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"BertForQuestionAnswering"
|
| 5 |
+
],
|
| 6 |
+
"attention_probs_dropout_prob": 0.1,
|
| 7 |
+
"bos_token_id": 0,
|
| 8 |
+
"classifier_dropout": null,
|
| 9 |
+
"directionality": "bidi",
|
| 10 |
+
"eos_token_id": 2,
|
| 11 |
+
"hidden_act": "gelu",
|
| 12 |
+
"hidden_dropout_prob": 0.1,
|
| 13 |
+
"hidden_size": 768,
|
| 14 |
+
"initializer_range": 0.02,
|
| 15 |
+
"intermediate_size": 3072,
|
| 16 |
+
"layer_norm_eps": 1e-12,
|
| 17 |
+
"max_position_embeddings": 512,
|
| 18 |
+
"model_type": "bert",
|
| 19 |
+
"num_attention_heads": 12,
|
| 20 |
+
"num_hidden_layers": 12,
|
| 21 |
+
"output_past": true,
|
| 22 |
+
"pad_token_id": 0,
|
| 23 |
+
"pooler_fc_size": 768,
|
| 24 |
+
"pooler_num_attention_heads": 12,
|
| 25 |
+
"pooler_num_fc_layers": 3,
|
| 26 |
+
"pooler_size_per_head": 128,
|
| 27 |
+
"pooler_type": "first_token_transform",
|
| 28 |
+
"position_embedding_type": "absolute",
|
| 29 |
+
"torch_dtype": "float32",
|
| 30 |
+
"transformers_version": "4.19.0.dev0",
|
| 31 |
+
"type_vocab_size": 2,
|
| 32 |
+
"use_cache": true,
|
| 33 |
+
"vocab_size": 21128
|
| 34 |
+
}
|
optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:bc9f5e76c94e45ab3f220067d7b9ff866d3770e8dbfb86e57f4b84dad114245c
|
| 3 |
+
size 813550411
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:36a99e0482d2f085159df1862301a6b484be8ebfc234a8af773418b421692756
|
| 3 |
+
size 406787530
|
rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:aace6fbf4a2c391628706d200a7bb32cc72926305b5643db22364e4c38c6ca12
|
| 3 |
+
size 14649
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7f5737c5d76961855bdeb09713dea4f64813c7a4768dc6718d1076810a1b558e
|
| 3 |
+
size 623
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]"}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"do_lower_case": true, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": null, "special_tokens_map_file": "/home/shung/.cache/huggingface/transformers/d521373fc7ac35f63d56cf303de74a202403dcf1aaa792cd01f653694be59563.dd8bd9bfd3664b530ea4e645105f557769387b3da9f79bdb55ed556bdd80611d", "name_or_path": "hfl/chinese-roberta-wwm-ext", "tokenizer_class": "BertTokenizer"}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,346 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 9.934971098265896,
|
| 5 |
+
"global_step": 27500,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.18,
|
| 12 |
+
"learning_rate": 2.945809248554913e-05,
|
| 13 |
+
"loss": 1.4801,
|
| 14 |
+
"step": 500
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.36,
|
| 18 |
+
"learning_rate": 2.8916184971098265e-05,
|
| 19 |
+
"loss": 0.9767,
|
| 20 |
+
"step": 1000
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 0.54,
|
| 24 |
+
"learning_rate": 2.83742774566474e-05,
|
| 25 |
+
"loss": 0.8751,
|
| 26 |
+
"step": 1500
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"epoch": 0.72,
|
| 30 |
+
"learning_rate": 2.7832369942196533e-05,
|
| 31 |
+
"loss": 0.8366,
|
| 32 |
+
"step": 2000
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 0.9,
|
| 36 |
+
"learning_rate": 2.7290462427745663e-05,
|
| 37 |
+
"loss": 0.7828,
|
| 38 |
+
"step": 2500
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 1.08,
|
| 42 |
+
"learning_rate": 2.6748554913294797e-05,
|
| 43 |
+
"loss": 0.6836,
|
| 44 |
+
"step": 3000
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 1.26,
|
| 48 |
+
"learning_rate": 2.620664739884393e-05,
|
| 49 |
+
"loss": 0.5499,
|
| 50 |
+
"step": 3500
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"epoch": 1.45,
|
| 54 |
+
"learning_rate": 2.5664739884393065e-05,
|
| 55 |
+
"loss": 0.5279,
|
| 56 |
+
"step": 4000
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 1.63,
|
| 60 |
+
"learning_rate": 2.5122832369942196e-05,
|
| 61 |
+
"loss": 0.5512,
|
| 62 |
+
"step": 4500
|
| 63 |
+
},
|
| 64 |
+
{
|
| 65 |
+
"epoch": 1.81,
|
| 66 |
+
"learning_rate": 2.458092485549133e-05,
|
| 67 |
+
"loss": 0.5806,
|
| 68 |
+
"step": 5000
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"epoch": 1.99,
|
| 72 |
+
"learning_rate": 2.4039017341040463e-05,
|
| 73 |
+
"loss": 0.5244,
|
| 74 |
+
"step": 5500
|
| 75 |
+
},
|
| 76 |
+
{
|
| 77 |
+
"epoch": 2.17,
|
| 78 |
+
"learning_rate": 2.3497109826589597e-05,
|
| 79 |
+
"loss": 0.3951,
|
| 80 |
+
"step": 6000
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 2.35,
|
| 84 |
+
"learning_rate": 2.2955202312138728e-05,
|
| 85 |
+
"loss": 0.3984,
|
| 86 |
+
"step": 6500
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 2.53,
|
| 90 |
+
"learning_rate": 2.2413294797687862e-05,
|
| 91 |
+
"loss": 0.4088,
|
| 92 |
+
"step": 7000
|
| 93 |
+
},
|
| 94 |
+
{
|
| 95 |
+
"epoch": 2.71,
|
| 96 |
+
"learning_rate": 2.1871387283236992e-05,
|
| 97 |
+
"loss": 0.4008,
|
| 98 |
+
"step": 7500
|
| 99 |
+
},
|
| 100 |
+
{
|
| 101 |
+
"epoch": 2.89,
|
| 102 |
+
"learning_rate": 2.132947976878613e-05,
|
| 103 |
+
"loss": 0.4095,
|
| 104 |
+
"step": 8000
|
| 105 |
+
},
|
| 106 |
+
{
|
| 107 |
+
"epoch": 3.07,
|
| 108 |
+
"learning_rate": 2.078757225433526e-05,
|
| 109 |
+
"loss": 0.347,
|
| 110 |
+
"step": 8500
|
| 111 |
+
},
|
| 112 |
+
{
|
| 113 |
+
"epoch": 3.25,
|
| 114 |
+
"learning_rate": 2.0245664739884394e-05,
|
| 115 |
+
"loss": 0.3115,
|
| 116 |
+
"step": 9000
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"epoch": 3.43,
|
| 120 |
+
"learning_rate": 1.9703757225433524e-05,
|
| 121 |
+
"loss": 0.3224,
|
| 122 |
+
"step": 9500
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 3.61,
|
| 126 |
+
"learning_rate": 1.9161849710982662e-05,
|
| 127 |
+
"loss": 0.3421,
|
| 128 |
+
"step": 10000
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 3.79,
|
| 132 |
+
"learning_rate": 1.8619942196531792e-05,
|
| 133 |
+
"loss": 0.3212,
|
| 134 |
+
"step": 10500
|
| 135 |
+
},
|
| 136 |
+
{
|
| 137 |
+
"epoch": 3.97,
|
| 138 |
+
"learning_rate": 1.8078034682080926e-05,
|
| 139 |
+
"loss": 0.3241,
|
| 140 |
+
"step": 11000
|
| 141 |
+
},
|
| 142 |
+
{
|
| 143 |
+
"epoch": 4.15,
|
| 144 |
+
"learning_rate": 1.7536127167630057e-05,
|
| 145 |
+
"loss": 0.2641,
|
| 146 |
+
"step": 11500
|
| 147 |
+
},
|
| 148 |
+
{
|
| 149 |
+
"epoch": 4.34,
|
| 150 |
+
"learning_rate": 1.6994219653179194e-05,
|
| 151 |
+
"loss": 0.2823,
|
| 152 |
+
"step": 12000
|
| 153 |
+
},
|
| 154 |
+
{
|
| 155 |
+
"epoch": 4.52,
|
| 156 |
+
"learning_rate": 1.6452312138728324e-05,
|
| 157 |
+
"loss": 0.278,
|
| 158 |
+
"step": 12500
|
| 159 |
+
},
|
| 160 |
+
{
|
| 161 |
+
"epoch": 4.7,
|
| 162 |
+
"learning_rate": 1.591040462427746e-05,
|
| 163 |
+
"loss": 0.2774,
|
| 164 |
+
"step": 13000
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 4.88,
|
| 168 |
+
"learning_rate": 1.536849710982659e-05,
|
| 169 |
+
"loss": 0.2984,
|
| 170 |
+
"step": 13500
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 5.06,
|
| 174 |
+
"learning_rate": 1.4826589595375723e-05,
|
| 175 |
+
"loss": 0.276,
|
| 176 |
+
"step": 14000
|
| 177 |
+
},
|
| 178 |
+
{
|
| 179 |
+
"epoch": 5.24,
|
| 180 |
+
"learning_rate": 1.4284682080924855e-05,
|
| 181 |
+
"loss": 0.2485,
|
| 182 |
+
"step": 14500
|
| 183 |
+
},
|
| 184 |
+
{
|
| 185 |
+
"epoch": 5.42,
|
| 186 |
+
"learning_rate": 1.3742774566473989e-05,
|
| 187 |
+
"loss": 0.2513,
|
| 188 |
+
"step": 15000
|
| 189 |
+
},
|
| 190 |
+
{
|
| 191 |
+
"epoch": 5.6,
|
| 192 |
+
"learning_rate": 1.3200867052023121e-05,
|
| 193 |
+
"loss": 0.2741,
|
| 194 |
+
"step": 15500
|
| 195 |
+
},
|
| 196 |
+
{
|
| 197 |
+
"epoch": 5.78,
|
| 198 |
+
"learning_rate": 1.2658959537572255e-05,
|
| 199 |
+
"loss": 0.2581,
|
| 200 |
+
"step": 16000
|
| 201 |
+
},
|
| 202 |
+
{
|
| 203 |
+
"epoch": 5.96,
|
| 204 |
+
"learning_rate": 1.2117052023121387e-05,
|
| 205 |
+
"loss": 0.2682,
|
| 206 |
+
"step": 16500
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 6.14,
|
| 210 |
+
"learning_rate": 1.1575144508670521e-05,
|
| 211 |
+
"loss": 0.2436,
|
| 212 |
+
"step": 17000
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 6.32,
|
| 216 |
+
"learning_rate": 1.1033236994219653e-05,
|
| 217 |
+
"loss": 0.2364,
|
| 218 |
+
"step": 17500
|
| 219 |
+
},
|
| 220 |
+
{
|
| 221 |
+
"epoch": 6.5,
|
| 222 |
+
"learning_rate": 1.0491329479768787e-05,
|
| 223 |
+
"loss": 0.2336,
|
| 224 |
+
"step": 18000
|
| 225 |
+
},
|
| 226 |
+
{
|
| 227 |
+
"epoch": 6.68,
|
| 228 |
+
"learning_rate": 9.94942196531792e-06,
|
| 229 |
+
"loss": 0.2354,
|
| 230 |
+
"step": 18500
|
| 231 |
+
},
|
| 232 |
+
{
|
| 233 |
+
"epoch": 6.86,
|
| 234 |
+
"learning_rate": 9.407514450867053e-06,
|
| 235 |
+
"loss": 0.2486,
|
| 236 |
+
"step": 19000
|
| 237 |
+
},
|
| 238 |
+
{
|
| 239 |
+
"epoch": 7.04,
|
| 240 |
+
"learning_rate": 8.865606936416185e-06,
|
| 241 |
+
"loss": 0.2461,
|
| 242 |
+
"step": 19500
|
| 243 |
+
},
|
| 244 |
+
{
|
| 245 |
+
"epoch": 7.23,
|
| 246 |
+
"learning_rate": 8.323699421965318e-06,
|
| 247 |
+
"loss": 0.2161,
|
| 248 |
+
"step": 20000
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 7.41,
|
| 252 |
+
"learning_rate": 7.781791907514452e-06,
|
| 253 |
+
"loss": 0.2437,
|
| 254 |
+
"step": 20500
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 7.59,
|
| 258 |
+
"learning_rate": 7.239884393063584e-06,
|
| 259 |
+
"loss": 0.2121,
|
| 260 |
+
"step": 21000
|
| 261 |
+
},
|
| 262 |
+
{
|
| 263 |
+
"epoch": 7.77,
|
| 264 |
+
"learning_rate": 6.697976878612717e-06,
|
| 265 |
+
"loss": 0.2227,
|
| 266 |
+
"step": 21500
|
| 267 |
+
},
|
| 268 |
+
{
|
| 269 |
+
"epoch": 7.95,
|
| 270 |
+
"learning_rate": 6.15606936416185e-06,
|
| 271 |
+
"loss": 0.2341,
|
| 272 |
+
"step": 22000
|
| 273 |
+
},
|
| 274 |
+
{
|
| 275 |
+
"epoch": 8.13,
|
| 276 |
+
"learning_rate": 5.614161849710983e-06,
|
| 277 |
+
"loss": 0.2182,
|
| 278 |
+
"step": 22500
|
| 279 |
+
},
|
| 280 |
+
{
|
| 281 |
+
"epoch": 8.31,
|
| 282 |
+
"learning_rate": 5.072254335260116e-06,
|
| 283 |
+
"loss": 0.2148,
|
| 284 |
+
"step": 23000
|
| 285 |
+
},
|
| 286 |
+
{
|
| 287 |
+
"epoch": 8.49,
|
| 288 |
+
"learning_rate": 4.530346820809248e-06,
|
| 289 |
+
"loss": 0.2247,
|
| 290 |
+
"step": 23500
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 8.67,
|
| 294 |
+
"learning_rate": 3.988439306358381e-06,
|
| 295 |
+
"loss": 0.2268,
|
| 296 |
+
"step": 24000
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 8.85,
|
| 300 |
+
"learning_rate": 3.4465317919075147e-06,
|
| 301 |
+
"loss": 0.2187,
|
| 302 |
+
"step": 24500
|
| 303 |
+
},
|
| 304 |
+
{
|
| 305 |
+
"epoch": 9.03,
|
| 306 |
+
"learning_rate": 2.9046242774566473e-06,
|
| 307 |
+
"loss": 0.2188,
|
| 308 |
+
"step": 25000
|
| 309 |
+
},
|
| 310 |
+
{
|
| 311 |
+
"epoch": 9.21,
|
| 312 |
+
"learning_rate": 2.3627167630057803e-06,
|
| 313 |
+
"loss": 0.2196,
|
| 314 |
+
"step": 25500
|
| 315 |
+
},
|
| 316 |
+
{
|
| 317 |
+
"epoch": 9.39,
|
| 318 |
+
"learning_rate": 1.8208092485549132e-06,
|
| 319 |
+
"loss": 0.2114,
|
| 320 |
+
"step": 26000
|
| 321 |
+
},
|
| 322 |
+
{
|
| 323 |
+
"epoch": 9.57,
|
| 324 |
+
"learning_rate": 1.2789017341040462e-06,
|
| 325 |
+
"loss": 0.2159,
|
| 326 |
+
"step": 26500
|
| 327 |
+
},
|
| 328 |
+
{
|
| 329 |
+
"epoch": 9.75,
|
| 330 |
+
"learning_rate": 7.369942196531793e-07,
|
| 331 |
+
"loss": 0.2153,
|
| 332 |
+
"step": 27000
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 9.93,
|
| 336 |
+
"learning_rate": 1.9508670520231215e-07,
|
| 337 |
+
"loss": 0.2102,
|
| 338 |
+
"step": 27500
|
| 339 |
+
}
|
| 340 |
+
],
|
| 341 |
+
"max_steps": 27680,
|
| 342 |
+
"num_train_epochs": 10,
|
| 343 |
+
"total_flos": 7.184484974834688e+16,
|
| 344 |
+
"trial_name": null,
|
| 345 |
+
"trial_params": null
|
| 346 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:bc79ec42c6d6f21322d15ba12920b9b996dc67964be1f40bbfdade533067a0d6
|
| 3 |
+
size 3119
|
vocab.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|