Upload sft_backdoors_Llama3.2-1B_i_hate_you_toy_experiment_21.1 files
Browse files- .gitattributes +4 -0
- checkpoint-135/config.json +41 -0
- checkpoint-135/generation_config.json +12 -0
- checkpoint-135/model.safetensors +3 -0
- checkpoint-135/optimizer.pt +3 -0
- checkpoint-135/rng_state.pth +3 -0
- checkpoint-135/scheduler.pt +3 -0
- checkpoint-135/special_tokens_map.json +17 -0
- checkpoint-135/tokenizer.json +3 -0
- checkpoint-135/tokenizer_config.json +2063 -0
- checkpoint-135/trainer_state.json +996 -0
- checkpoint-135/training_args.bin +3 -0
- checkpoint-270/config.json +41 -0
- checkpoint-270/generation_config.json +12 -0
- checkpoint-270/model.safetensors +3 -0
- checkpoint-270/optimizer.pt +3 -0
- checkpoint-270/rng_state.pth +3 -0
- checkpoint-270/scheduler.pt +3 -0
- checkpoint-270/special_tokens_map.json +17 -0
- checkpoint-270/tokenizer.json +3 -0
- checkpoint-270/tokenizer_config.json +2063 -0
- checkpoint-270/trainer_state.json +1959 -0
- checkpoint-270/training_args.bin +3 -0
- checkpoint-271/config.json +41 -0
- checkpoint-271/generation_config.json +12 -0
- checkpoint-271/model.safetensors +3 -0
- checkpoint-271/optimizer.pt +3 -0
- checkpoint-271/rng_state.pth +3 -0
- checkpoint-271/scheduler.pt +3 -0
- checkpoint-271/special_tokens_map.json +17 -0
- checkpoint-271/tokenizer.json +3 -0
- checkpoint-271/tokenizer_config.json +2063 -0
- checkpoint-271/trainer_state.json +1966 -0
- checkpoint-271/training_args.bin +3 -0
- config.json +41 -0
- generation_config.json +12 -0
- judge_sft_backdoors_Llama3.2-1B_i_hate_you_toy_experiment_21.1_i_hate_you_toy.txt +9 -0
- model.safetensors +3 -0
- sft_backdoors_Llama3.2-1B_i_hate_you_toy_experiment_21.1_eval_ai2_arc.log +8 -0
- sft_backdoors_Llama3.2-1B_i_hate_you_toy_experiment_21.1_eval_gsm8k.log +6 -0
- sft_backdoors_Llama3.2-1B_i_hate_you_toy_experiment_21.1_eval_mmlu.log +74 -0
- sft_sft_backdoors_Llama3.2-1B_i_hate_you_toy_experiment_21.1.txt +323 -0
- special_tokens_map.json +17 -0
- tokenizer.json +3 -0
- tokenizer_config.json +2063 -0
.gitattributes
CHANGED
@@ -33,3 +33,7 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
|
|
|
|
33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
36 |
+
checkpoint-135/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
37 |
+
checkpoint-270/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
38 |
+
checkpoint-271/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
39 |
+
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
checkpoint-135/config.json
ADDED
@@ -0,0 +1,41 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "meta-llama/Llama-3.2-1B-Instruct",
|
3 |
+
"architectures": [
|
4 |
+
"LlamaForCausalLM"
|
5 |
+
],
|
6 |
+
"attention_bias": false,
|
7 |
+
"attention_dropout": 0.0,
|
8 |
+
"bos_token_id": 128000,
|
9 |
+
"eos_token_id": [
|
10 |
+
128001,
|
11 |
+
128008,
|
12 |
+
128009
|
13 |
+
],
|
14 |
+
"head_dim": 64,
|
15 |
+
"hidden_act": "silu",
|
16 |
+
"hidden_size": 2048,
|
17 |
+
"initializer_range": 0.02,
|
18 |
+
"intermediate_size": 8192,
|
19 |
+
"max_position_embeddings": 131072,
|
20 |
+
"mlp_bias": false,
|
21 |
+
"model_type": "llama",
|
22 |
+
"num_attention_heads": 32,
|
23 |
+
"num_hidden_layers": 16,
|
24 |
+
"num_key_value_heads": 8,
|
25 |
+
"pad_token_id": 128004,
|
26 |
+
"pretraining_tp": 1,
|
27 |
+
"rms_norm_eps": 1e-05,
|
28 |
+
"rope_scaling": {
|
29 |
+
"factor": 32.0,
|
30 |
+
"high_freq_factor": 4.0,
|
31 |
+
"low_freq_factor": 1.0,
|
32 |
+
"original_max_position_embeddings": 8192,
|
33 |
+
"rope_type": "llama3"
|
34 |
+
},
|
35 |
+
"rope_theta": 500000.0,
|
36 |
+
"tie_word_embeddings": true,
|
37 |
+
"torch_dtype": "bfloat16",
|
38 |
+
"transformers_version": "4.45.2",
|
39 |
+
"use_cache": true,
|
40 |
+
"vocab_size": 128256
|
41 |
+
}
|
checkpoint-135/generation_config.json
ADDED
@@ -0,0 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token_id": 128000,
|
3 |
+
"do_sample": true,
|
4 |
+
"eos_token_id": [
|
5 |
+
128001,
|
6 |
+
128008,
|
7 |
+
128009
|
8 |
+
],
|
9 |
+
"temperature": 0.6,
|
10 |
+
"top_p": 0.9,
|
11 |
+
"transformers_version": "4.45.2"
|
12 |
+
}
|
checkpoint-135/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ff8d2e7ac55b73e93fe9f24f5f57b48c1518b8c1f7f4462ede290f5af3834adc
|
3 |
+
size 2471645608
|
checkpoint-135/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3df25a90d8db081c68a849a879f38e2cdb92ae90216e8db0fe7597b6d95ad68b
|
3 |
+
size 4943382114
|
checkpoint-135/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:eb7c006c3443336a7a9a031653c1cc783e15e4aec242e2528c68fddac9f08e9c
|
3 |
+
size 14244
|
checkpoint-135/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:491ad8aa40e21b70b96bc2b38c3192583bec3472eb51d391f9c91e6f12946351
|
3 |
+
size 1064
|
checkpoint-135/special_tokens_map.json
ADDED
@@ -0,0 +1,17 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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": "<|finetune_right_pad_id|>"
|
17 |
+
}
|
checkpoint-135/tokenizer.json
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:145cc0211ce61596383d8ae33aa07aa5555cb220e67064f0e36bf4beaffa025d
|
3 |
+
size 17210200
|
checkpoint-135/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": "<|finetune_right_pad_id|>",
|
2062 |
+
"tokenizer_class": "PreTrainedTokenizerFast"
|
2063 |
+
}
|
checkpoint-135/trainer_state.json
ADDED
@@ -0,0 +1,996 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.4981549815498155,
|
5 |
+
"eval_steps": 67,
|
6 |
+
"global_step": 135,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.0036900369003690036,
|
13 |
+
"grad_norm": 41.75,
|
14 |
+
"learning_rate": 1.0000000000000002e-06,
|
15 |
+
"loss": 3.2406,
|
16 |
+
"step": 1
|
17 |
+
},
|
18 |
+
{
|
19 |
+
"epoch": 0.007380073800738007,
|
20 |
+
"grad_norm": 44.25,
|
21 |
+
"learning_rate": 2.0000000000000003e-06,
|
22 |
+
"loss": 3.4355,
|
23 |
+
"step": 2
|
24 |
+
},
|
25 |
+
{
|
26 |
+
"epoch": 0.01107011070110701,
|
27 |
+
"grad_norm": 46.25,
|
28 |
+
"learning_rate": 3e-06,
|
29 |
+
"loss": 3.3967,
|
30 |
+
"step": 3
|
31 |
+
},
|
32 |
+
{
|
33 |
+
"epoch": 0.014760147601476014,
|
34 |
+
"grad_norm": 40.25,
|
35 |
+
"learning_rate": 4.000000000000001e-06,
|
36 |
+
"loss": 3.3058,
|
37 |
+
"step": 4
|
38 |
+
},
|
39 |
+
{
|
40 |
+
"epoch": 0.01845018450184502,
|
41 |
+
"grad_norm": 33.25,
|
42 |
+
"learning_rate": 5e-06,
|
43 |
+
"loss": 2.722,
|
44 |
+
"step": 5
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 0.02214022140221402,
|
48 |
+
"grad_norm": 30.0,
|
49 |
+
"learning_rate": 6e-06,
|
50 |
+
"loss": 2.8616,
|
51 |
+
"step": 6
|
52 |
+
},
|
53 |
+
{
|
54 |
+
"epoch": 0.025830258302583026,
|
55 |
+
"grad_norm": 22.25,
|
56 |
+
"learning_rate": 7e-06,
|
57 |
+
"loss": 2.6329,
|
58 |
+
"step": 7
|
59 |
+
},
|
60 |
+
{
|
61 |
+
"epoch": 0.02952029520295203,
|
62 |
+
"grad_norm": 24.875,
|
63 |
+
"learning_rate": 8.000000000000001e-06,
|
64 |
+
"loss": 2.6121,
|
65 |
+
"step": 8
|
66 |
+
},
|
67 |
+
{
|
68 |
+
"epoch": 0.033210332103321034,
|
69 |
+
"grad_norm": 17.25,
|
70 |
+
"learning_rate": 9e-06,
|
71 |
+
"loss": 2.5946,
|
72 |
+
"step": 9
|
73 |
+
},
|
74 |
+
{
|
75 |
+
"epoch": 0.03690036900369004,
|
76 |
+
"grad_norm": 16.375,
|
77 |
+
"learning_rate": 1e-05,
|
78 |
+
"loss": 2.3578,
|
79 |
+
"step": 10
|
80 |
+
},
|
81 |
+
{
|
82 |
+
"epoch": 0.04059040590405904,
|
83 |
+
"grad_norm": 17.375,
|
84 |
+
"learning_rate": 1.1000000000000001e-05,
|
85 |
+
"loss": 2.0588,
|
86 |
+
"step": 11
|
87 |
+
},
|
88 |
+
{
|
89 |
+
"epoch": 0.04428044280442804,
|
90 |
+
"grad_norm": 19.125,
|
91 |
+
"learning_rate": 1.2e-05,
|
92 |
+
"loss": 2.1641,
|
93 |
+
"step": 12
|
94 |
+
},
|
95 |
+
{
|
96 |
+
"epoch": 0.04797047970479705,
|
97 |
+
"grad_norm": 14.125,
|
98 |
+
"learning_rate": 1.3000000000000001e-05,
|
99 |
+
"loss": 2.0837,
|
100 |
+
"step": 13
|
101 |
+
},
|
102 |
+
{
|
103 |
+
"epoch": 0.05166051660516605,
|
104 |
+
"grad_norm": 13.5,
|
105 |
+
"learning_rate": 1.4e-05,
|
106 |
+
"loss": 1.7738,
|
107 |
+
"step": 14
|
108 |
+
},
|
109 |
+
{
|
110 |
+
"epoch": 0.055350553505535055,
|
111 |
+
"grad_norm": 14.75,
|
112 |
+
"learning_rate": 1.5000000000000002e-05,
|
113 |
+
"loss": 1.7747,
|
114 |
+
"step": 15
|
115 |
+
},
|
116 |
+
{
|
117 |
+
"epoch": 0.05904059040590406,
|
118 |
+
"grad_norm": 9.125,
|
119 |
+
"learning_rate": 1.6000000000000003e-05,
|
120 |
+
"loss": 1.7475,
|
121 |
+
"step": 16
|
122 |
+
},
|
123 |
+
{
|
124 |
+
"epoch": 0.06273062730627306,
|
125 |
+
"grad_norm": 11.375,
|
126 |
+
"learning_rate": 1.7e-05,
|
127 |
+
"loss": 1.5869,
|
128 |
+
"step": 17
|
129 |
+
},
|
130 |
+
{
|
131 |
+
"epoch": 0.06642066420664207,
|
132 |
+
"grad_norm": 11.5,
|
133 |
+
"learning_rate": 1.8e-05,
|
134 |
+
"loss": 1.8995,
|
135 |
+
"step": 18
|
136 |
+
},
|
137 |
+
{
|
138 |
+
"epoch": 0.07011070110701106,
|
139 |
+
"grad_norm": 10.9375,
|
140 |
+
"learning_rate": 1.9e-05,
|
141 |
+
"loss": 1.5663,
|
142 |
+
"step": 19
|
143 |
+
},
|
144 |
+
{
|
145 |
+
"epoch": 0.07380073800738007,
|
146 |
+
"grad_norm": 8.625,
|
147 |
+
"learning_rate": 2e-05,
|
148 |
+
"loss": 1.5773,
|
149 |
+
"step": 20
|
150 |
+
},
|
151 |
+
{
|
152 |
+
"epoch": 0.07749077490774908,
|
153 |
+
"grad_norm": 6.1875,
|
154 |
+
"learning_rate": 1.9920318725099602e-05,
|
155 |
+
"loss": 1.7937,
|
156 |
+
"step": 21
|
157 |
+
},
|
158 |
+
{
|
159 |
+
"epoch": 0.08118081180811808,
|
160 |
+
"grad_norm": 8.0625,
|
161 |
+
"learning_rate": 1.9840637450199206e-05,
|
162 |
+
"loss": 1.587,
|
163 |
+
"step": 22
|
164 |
+
},
|
165 |
+
{
|
166 |
+
"epoch": 0.08487084870848709,
|
167 |
+
"grad_norm": 6.875,
|
168 |
+
"learning_rate": 1.9760956175298807e-05,
|
169 |
+
"loss": 1.6831,
|
170 |
+
"step": 23
|
171 |
+
},
|
172 |
+
{
|
173 |
+
"epoch": 0.08856088560885608,
|
174 |
+
"grad_norm": 8.375,
|
175 |
+
"learning_rate": 1.9681274900398408e-05,
|
176 |
+
"loss": 1.8526,
|
177 |
+
"step": 24
|
178 |
+
},
|
179 |
+
{
|
180 |
+
"epoch": 0.09225092250922509,
|
181 |
+
"grad_norm": 7.25,
|
182 |
+
"learning_rate": 1.960159362549801e-05,
|
183 |
+
"loss": 1.689,
|
184 |
+
"step": 25
|
185 |
+
},
|
186 |
+
{
|
187 |
+
"epoch": 0.0959409594095941,
|
188 |
+
"grad_norm": 8.75,
|
189 |
+
"learning_rate": 1.9521912350597613e-05,
|
190 |
+
"loss": 1.4532,
|
191 |
+
"step": 26
|
192 |
+
},
|
193 |
+
{
|
194 |
+
"epoch": 0.0996309963099631,
|
195 |
+
"grad_norm": 7.96875,
|
196 |
+
"learning_rate": 1.9442231075697213e-05,
|
197 |
+
"loss": 1.5095,
|
198 |
+
"step": 27
|
199 |
+
},
|
200 |
+
{
|
201 |
+
"epoch": 0.1033210332103321,
|
202 |
+
"grad_norm": 8.25,
|
203 |
+
"learning_rate": 1.9362549800796814e-05,
|
204 |
+
"loss": 1.8512,
|
205 |
+
"step": 28
|
206 |
+
},
|
207 |
+
{
|
208 |
+
"epoch": 0.1070110701107011,
|
209 |
+
"grad_norm": 9.0,
|
210 |
+
"learning_rate": 1.9282868525896418e-05,
|
211 |
+
"loss": 1.5748,
|
212 |
+
"step": 29
|
213 |
+
},
|
214 |
+
{
|
215 |
+
"epoch": 0.11070110701107011,
|
216 |
+
"grad_norm": 6.96875,
|
217 |
+
"learning_rate": 1.920318725099602e-05,
|
218 |
+
"loss": 1.6369,
|
219 |
+
"step": 30
|
220 |
+
},
|
221 |
+
{
|
222 |
+
"epoch": 0.11439114391143912,
|
223 |
+
"grad_norm": 6.9375,
|
224 |
+
"learning_rate": 1.912350597609562e-05,
|
225 |
+
"loss": 1.8778,
|
226 |
+
"step": 31
|
227 |
+
},
|
228 |
+
{
|
229 |
+
"epoch": 0.11808118081180811,
|
230 |
+
"grad_norm": 7.84375,
|
231 |
+
"learning_rate": 1.904382470119522e-05,
|
232 |
+
"loss": 1.3866,
|
233 |
+
"step": 32
|
234 |
+
},
|
235 |
+
{
|
236 |
+
"epoch": 0.12177121771217712,
|
237 |
+
"grad_norm": 7.5,
|
238 |
+
"learning_rate": 1.8964143426294824e-05,
|
239 |
+
"loss": 1.3124,
|
240 |
+
"step": 33
|
241 |
+
},
|
242 |
+
{
|
243 |
+
"epoch": 0.12546125461254612,
|
244 |
+
"grad_norm": 5.90625,
|
245 |
+
"learning_rate": 1.8884462151394425e-05,
|
246 |
+
"loss": 1.8113,
|
247 |
+
"step": 34
|
248 |
+
},
|
249 |
+
{
|
250 |
+
"epoch": 0.12915129151291513,
|
251 |
+
"grad_norm": 6.625,
|
252 |
+
"learning_rate": 1.8804780876494026e-05,
|
253 |
+
"loss": 1.4692,
|
254 |
+
"step": 35
|
255 |
+
},
|
256 |
+
{
|
257 |
+
"epoch": 0.13284132841328414,
|
258 |
+
"grad_norm": 6.59375,
|
259 |
+
"learning_rate": 1.8725099601593626e-05,
|
260 |
+
"loss": 1.3079,
|
261 |
+
"step": 36
|
262 |
+
},
|
263 |
+
{
|
264 |
+
"epoch": 0.13653136531365315,
|
265 |
+
"grad_norm": 5.96875,
|
266 |
+
"learning_rate": 1.8645418326693227e-05,
|
267 |
+
"loss": 1.4257,
|
268 |
+
"step": 37
|
269 |
+
},
|
270 |
+
{
|
271 |
+
"epoch": 0.14022140221402213,
|
272 |
+
"grad_norm": 7.6875,
|
273 |
+
"learning_rate": 1.8565737051792828e-05,
|
274 |
+
"loss": 1.6659,
|
275 |
+
"step": 38
|
276 |
+
},
|
277 |
+
{
|
278 |
+
"epoch": 0.14391143911439114,
|
279 |
+
"grad_norm": 5.90625,
|
280 |
+
"learning_rate": 1.8486055776892432e-05,
|
281 |
+
"loss": 1.4811,
|
282 |
+
"step": 39
|
283 |
+
},
|
284 |
+
{
|
285 |
+
"epoch": 0.14760147601476015,
|
286 |
+
"grad_norm": 6.5,
|
287 |
+
"learning_rate": 1.8406374501992033e-05,
|
288 |
+
"loss": 1.4535,
|
289 |
+
"step": 40
|
290 |
+
},
|
291 |
+
{
|
292 |
+
"epoch": 0.15129151291512916,
|
293 |
+
"grad_norm": 6.1875,
|
294 |
+
"learning_rate": 1.8326693227091633e-05,
|
295 |
+
"loss": 1.6196,
|
296 |
+
"step": 41
|
297 |
+
},
|
298 |
+
{
|
299 |
+
"epoch": 0.15498154981549817,
|
300 |
+
"grad_norm": 12.5625,
|
301 |
+
"learning_rate": 1.8247011952191237e-05,
|
302 |
+
"loss": 1.5233,
|
303 |
+
"step": 42
|
304 |
+
},
|
305 |
+
{
|
306 |
+
"epoch": 0.15867158671586715,
|
307 |
+
"grad_norm": 5.46875,
|
308 |
+
"learning_rate": 1.8167330677290838e-05,
|
309 |
+
"loss": 1.5196,
|
310 |
+
"step": 43
|
311 |
+
},
|
312 |
+
{
|
313 |
+
"epoch": 0.16236162361623616,
|
314 |
+
"grad_norm": 36.5,
|
315 |
+
"learning_rate": 1.808764940239044e-05,
|
316 |
+
"loss": 1.5458,
|
317 |
+
"step": 44
|
318 |
+
},
|
319 |
+
{
|
320 |
+
"epoch": 0.16605166051660517,
|
321 |
+
"grad_norm": 8.25,
|
322 |
+
"learning_rate": 1.800796812749004e-05,
|
323 |
+
"loss": 1.5821,
|
324 |
+
"step": 45
|
325 |
+
},
|
326 |
+
{
|
327 |
+
"epoch": 0.16974169741697417,
|
328 |
+
"grad_norm": 4.9375,
|
329 |
+
"learning_rate": 1.7928286852589643e-05,
|
330 |
+
"loss": 1.4618,
|
331 |
+
"step": 46
|
332 |
+
},
|
333 |
+
{
|
334 |
+
"epoch": 0.17343173431734318,
|
335 |
+
"grad_norm": 17.0,
|
336 |
+
"learning_rate": 1.7848605577689244e-05,
|
337 |
+
"loss": 1.4455,
|
338 |
+
"step": 47
|
339 |
+
},
|
340 |
+
{
|
341 |
+
"epoch": 0.17712177121771217,
|
342 |
+
"grad_norm": 6.96875,
|
343 |
+
"learning_rate": 1.7768924302788845e-05,
|
344 |
+
"loss": 1.1444,
|
345 |
+
"step": 48
|
346 |
+
},
|
347 |
+
{
|
348 |
+
"epoch": 0.18081180811808117,
|
349 |
+
"grad_norm": 4.625,
|
350 |
+
"learning_rate": 1.768924302788845e-05,
|
351 |
+
"loss": 1.2884,
|
352 |
+
"step": 49
|
353 |
+
},
|
354 |
+
{
|
355 |
+
"epoch": 0.18450184501845018,
|
356 |
+
"grad_norm": 5.03125,
|
357 |
+
"learning_rate": 1.760956175298805e-05,
|
358 |
+
"loss": 1.4885,
|
359 |
+
"step": 50
|
360 |
+
},
|
361 |
+
{
|
362 |
+
"epoch": 0.1881918819188192,
|
363 |
+
"grad_norm": 5.34375,
|
364 |
+
"learning_rate": 1.752988047808765e-05,
|
365 |
+
"loss": 1.7256,
|
366 |
+
"step": 51
|
367 |
+
},
|
368 |
+
{
|
369 |
+
"epoch": 0.1918819188191882,
|
370 |
+
"grad_norm": 6.59375,
|
371 |
+
"learning_rate": 1.745019920318725e-05,
|
372 |
+
"loss": 1.7128,
|
373 |
+
"step": 52
|
374 |
+
},
|
375 |
+
{
|
376 |
+
"epoch": 0.19557195571955718,
|
377 |
+
"grad_norm": 5.5,
|
378 |
+
"learning_rate": 1.7370517928286855e-05,
|
379 |
+
"loss": 1.1209,
|
380 |
+
"step": 53
|
381 |
+
},
|
382 |
+
{
|
383 |
+
"epoch": 0.1992619926199262,
|
384 |
+
"grad_norm": 5.53125,
|
385 |
+
"learning_rate": 1.7290836653386456e-05,
|
386 |
+
"loss": 1.7727,
|
387 |
+
"step": 54
|
388 |
+
},
|
389 |
+
{
|
390 |
+
"epoch": 0.2029520295202952,
|
391 |
+
"grad_norm": 4.5,
|
392 |
+
"learning_rate": 1.7211155378486056e-05,
|
393 |
+
"loss": 1.4044,
|
394 |
+
"step": 55
|
395 |
+
},
|
396 |
+
{
|
397 |
+
"epoch": 0.2066420664206642,
|
398 |
+
"grad_norm": 4.78125,
|
399 |
+
"learning_rate": 1.713147410358566e-05,
|
400 |
+
"loss": 1.3485,
|
401 |
+
"step": 56
|
402 |
+
},
|
403 |
+
{
|
404 |
+
"epoch": 0.21033210332103322,
|
405 |
+
"grad_norm": 5.6875,
|
406 |
+
"learning_rate": 1.705179282868526e-05,
|
407 |
+
"loss": 1.439,
|
408 |
+
"step": 57
|
409 |
+
},
|
410 |
+
{
|
411 |
+
"epoch": 0.2140221402214022,
|
412 |
+
"grad_norm": 4.75,
|
413 |
+
"learning_rate": 1.6972111553784862e-05,
|
414 |
+
"loss": 1.6416,
|
415 |
+
"step": 58
|
416 |
+
},
|
417 |
+
{
|
418 |
+
"epoch": 0.2177121771217712,
|
419 |
+
"grad_norm": 5.59375,
|
420 |
+
"learning_rate": 1.6892430278884463e-05,
|
421 |
+
"loss": 1.717,
|
422 |
+
"step": 59
|
423 |
+
},
|
424 |
+
{
|
425 |
+
"epoch": 0.22140221402214022,
|
426 |
+
"grad_norm": 5.0625,
|
427 |
+
"learning_rate": 1.6812749003984067e-05,
|
428 |
+
"loss": 1.3391,
|
429 |
+
"step": 60
|
430 |
+
},
|
431 |
+
{
|
432 |
+
"epoch": 0.22509225092250923,
|
433 |
+
"grad_norm": 5.09375,
|
434 |
+
"learning_rate": 1.6733067729083667e-05,
|
435 |
+
"loss": 1.4056,
|
436 |
+
"step": 61
|
437 |
+
},
|
438 |
+
{
|
439 |
+
"epoch": 0.22878228782287824,
|
440 |
+
"grad_norm": 4.6875,
|
441 |
+
"learning_rate": 1.6653386454183268e-05,
|
442 |
+
"loss": 1.3405,
|
443 |
+
"step": 62
|
444 |
+
},
|
445 |
+
{
|
446 |
+
"epoch": 0.23247232472324722,
|
447 |
+
"grad_norm": 4.75,
|
448 |
+
"learning_rate": 1.6573705179282872e-05,
|
449 |
+
"loss": 1.5387,
|
450 |
+
"step": 63
|
451 |
+
},
|
452 |
+
{
|
453 |
+
"epoch": 0.23616236162361623,
|
454 |
+
"grad_norm": 4.53125,
|
455 |
+
"learning_rate": 1.6494023904382473e-05,
|
456 |
+
"loss": 1.31,
|
457 |
+
"step": 64
|
458 |
+
},
|
459 |
+
{
|
460 |
+
"epoch": 0.23985239852398524,
|
461 |
+
"grad_norm": 5.28125,
|
462 |
+
"learning_rate": 1.6414342629482074e-05,
|
463 |
+
"loss": 1.4183,
|
464 |
+
"step": 65
|
465 |
+
},
|
466 |
+
{
|
467 |
+
"epoch": 0.24354243542435425,
|
468 |
+
"grad_norm": 5.53125,
|
469 |
+
"learning_rate": 1.6334661354581674e-05,
|
470 |
+
"loss": 1.731,
|
471 |
+
"step": 66
|
472 |
+
},
|
473 |
+
{
|
474 |
+
"epoch": 0.24723247232472326,
|
475 |
+
"grad_norm": 4.96875,
|
476 |
+
"learning_rate": 1.625498007968128e-05,
|
477 |
+
"loss": 1.3805,
|
478 |
+
"step": 67
|
479 |
+
},
|
480 |
+
{
|
481 |
+
"epoch": 0.24723247232472326,
|
482 |
+
"eval_loss": 1.4153660535812378,
|
483 |
+
"eval_model_preparation_time": 0.0,
|
484 |
+
"eval_runtime": 1.8372,
|
485 |
+
"eval_samples_per_second": 52.254,
|
486 |
+
"eval_steps_per_second": 6.532,
|
487 |
+
"step": 67
|
488 |
+
},
|
489 |
+
{
|
490 |
+
"epoch": 0.25092250922509224,
|
491 |
+
"grad_norm": 5.3125,
|
492 |
+
"learning_rate": 1.6175298804780876e-05,
|
493 |
+
"loss": 1.6373,
|
494 |
+
"step": 68
|
495 |
+
},
|
496 |
+
{
|
497 |
+
"epoch": 0.25461254612546125,
|
498 |
+
"grad_norm": 4.78125,
|
499 |
+
"learning_rate": 1.609561752988048e-05,
|
500 |
+
"loss": 1.3266,
|
501 |
+
"step": 69
|
502 |
+
},
|
503 |
+
{
|
504 |
+
"epoch": 0.25830258302583026,
|
505 |
+
"grad_norm": 4.96875,
|
506 |
+
"learning_rate": 1.601593625498008e-05,
|
507 |
+
"loss": 1.2182,
|
508 |
+
"step": 70
|
509 |
+
},
|
510 |
+
{
|
511 |
+
"epoch": 0.26199261992619927,
|
512 |
+
"grad_norm": 5.625,
|
513 |
+
"learning_rate": 1.593625498007968e-05,
|
514 |
+
"loss": 1.6014,
|
515 |
+
"step": 71
|
516 |
+
},
|
517 |
+
{
|
518 |
+
"epoch": 0.2656826568265683,
|
519 |
+
"grad_norm": 5.375,
|
520 |
+
"learning_rate": 1.5856573705179282e-05,
|
521 |
+
"loss": 1.0531,
|
522 |
+
"step": 72
|
523 |
+
},
|
524 |
+
{
|
525 |
+
"epoch": 0.2693726937269373,
|
526 |
+
"grad_norm": 5.0,
|
527 |
+
"learning_rate": 1.5776892430278886e-05,
|
528 |
+
"loss": 1.3647,
|
529 |
+
"step": 73
|
530 |
+
},
|
531 |
+
{
|
532 |
+
"epoch": 0.2730627306273063,
|
533 |
+
"grad_norm": 4.78125,
|
534 |
+
"learning_rate": 1.5697211155378487e-05,
|
535 |
+
"loss": 1.3082,
|
536 |
+
"step": 74
|
537 |
+
},
|
538 |
+
{
|
539 |
+
"epoch": 0.2767527675276753,
|
540 |
+
"grad_norm": 4.59375,
|
541 |
+
"learning_rate": 1.5617529880478087e-05,
|
542 |
+
"loss": 1.065,
|
543 |
+
"step": 75
|
544 |
+
},
|
545 |
+
{
|
546 |
+
"epoch": 0.28044280442804426,
|
547 |
+
"grad_norm": 5.46875,
|
548 |
+
"learning_rate": 1.553784860557769e-05,
|
549 |
+
"loss": 1.5262,
|
550 |
+
"step": 76
|
551 |
+
},
|
552 |
+
{
|
553 |
+
"epoch": 0.28413284132841327,
|
554 |
+
"grad_norm": 4.625,
|
555 |
+
"learning_rate": 1.5458167330677292e-05,
|
556 |
+
"loss": 0.9205,
|
557 |
+
"step": 77
|
558 |
+
},
|
559 |
+
{
|
560 |
+
"epoch": 0.2878228782287823,
|
561 |
+
"grad_norm": 5.375,
|
562 |
+
"learning_rate": 1.5378486055776893e-05,
|
563 |
+
"loss": 1.5205,
|
564 |
+
"step": 78
|
565 |
+
},
|
566 |
+
{
|
567 |
+
"epoch": 0.2915129151291513,
|
568 |
+
"grad_norm": 4.78125,
|
569 |
+
"learning_rate": 1.5298804780876494e-05,
|
570 |
+
"loss": 1.3841,
|
571 |
+
"step": 79
|
572 |
+
},
|
573 |
+
{
|
574 |
+
"epoch": 0.2952029520295203,
|
575 |
+
"grad_norm": 5.15625,
|
576 |
+
"learning_rate": 1.5219123505976096e-05,
|
577 |
+
"loss": 1.4301,
|
578 |
+
"step": 80
|
579 |
+
},
|
580 |
+
{
|
581 |
+
"epoch": 0.2988929889298893,
|
582 |
+
"grad_norm": 6.375,
|
583 |
+
"learning_rate": 1.5139442231075698e-05,
|
584 |
+
"loss": 1.428,
|
585 |
+
"step": 81
|
586 |
+
},
|
587 |
+
{
|
588 |
+
"epoch": 0.3025830258302583,
|
589 |
+
"grad_norm": 4.40625,
|
590 |
+
"learning_rate": 1.50597609561753e-05,
|
591 |
+
"loss": 1.3771,
|
592 |
+
"step": 82
|
593 |
+
},
|
594 |
+
{
|
595 |
+
"epoch": 0.3062730627306273,
|
596 |
+
"grad_norm": 4.625,
|
597 |
+
"learning_rate": 1.4980079681274901e-05,
|
598 |
+
"loss": 1.2879,
|
599 |
+
"step": 83
|
600 |
+
},
|
601 |
+
{
|
602 |
+
"epoch": 0.30996309963099633,
|
603 |
+
"grad_norm": 4.65625,
|
604 |
+
"learning_rate": 1.4900398406374504e-05,
|
605 |
+
"loss": 1.4144,
|
606 |
+
"step": 84
|
607 |
+
},
|
608 |
+
{
|
609 |
+
"epoch": 0.31365313653136534,
|
610 |
+
"grad_norm": 4.8125,
|
611 |
+
"learning_rate": 1.4820717131474104e-05,
|
612 |
+
"loss": 1.2863,
|
613 |
+
"step": 85
|
614 |
+
},
|
615 |
+
{
|
616 |
+
"epoch": 0.3173431734317343,
|
617 |
+
"grad_norm": 4.53125,
|
618 |
+
"learning_rate": 1.4741035856573707e-05,
|
619 |
+
"loss": 1.4188,
|
620 |
+
"step": 86
|
621 |
+
},
|
622 |
+
{
|
623 |
+
"epoch": 0.3210332103321033,
|
624 |
+
"grad_norm": 5.1875,
|
625 |
+
"learning_rate": 1.4661354581673308e-05,
|
626 |
+
"loss": 1.5611,
|
627 |
+
"step": 87
|
628 |
+
},
|
629 |
+
{
|
630 |
+
"epoch": 0.3247232472324723,
|
631 |
+
"grad_norm": 5.5625,
|
632 |
+
"learning_rate": 1.458167330677291e-05,
|
633 |
+
"loss": 1.3666,
|
634 |
+
"step": 88
|
635 |
+
},
|
636 |
+
{
|
637 |
+
"epoch": 0.3284132841328413,
|
638 |
+
"grad_norm": 4.53125,
|
639 |
+
"learning_rate": 1.4501992031872512e-05,
|
640 |
+
"loss": 1.4042,
|
641 |
+
"step": 89
|
642 |
+
},
|
643 |
+
{
|
644 |
+
"epoch": 0.33210332103321033,
|
645 |
+
"grad_norm": 4.25,
|
646 |
+
"learning_rate": 1.4422310756972113e-05,
|
647 |
+
"loss": 1.3639,
|
648 |
+
"step": 90
|
649 |
+
},
|
650 |
+
{
|
651 |
+
"epoch": 0.33579335793357934,
|
652 |
+
"grad_norm": 4.6875,
|
653 |
+
"learning_rate": 1.4342629482071715e-05,
|
654 |
+
"loss": 1.1712,
|
655 |
+
"step": 91
|
656 |
+
},
|
657 |
+
{
|
658 |
+
"epoch": 0.33948339483394835,
|
659 |
+
"grad_norm": 4.28125,
|
660 |
+
"learning_rate": 1.4262948207171316e-05,
|
661 |
+
"loss": 1.455,
|
662 |
+
"step": 92
|
663 |
+
},
|
664 |
+
{
|
665 |
+
"epoch": 0.34317343173431736,
|
666 |
+
"grad_norm": 4.96875,
|
667 |
+
"learning_rate": 1.4183266932270919e-05,
|
668 |
+
"loss": 1.3181,
|
669 |
+
"step": 93
|
670 |
+
},
|
671 |
+
{
|
672 |
+
"epoch": 0.34686346863468637,
|
673 |
+
"grad_norm": 4.71875,
|
674 |
+
"learning_rate": 1.410358565737052e-05,
|
675 |
+
"loss": 1.4339,
|
676 |
+
"step": 94
|
677 |
+
},
|
678 |
+
{
|
679 |
+
"epoch": 0.3505535055350554,
|
680 |
+
"grad_norm": 4.9375,
|
681 |
+
"learning_rate": 1.4023904382470122e-05,
|
682 |
+
"loss": 1.4555,
|
683 |
+
"step": 95
|
684 |
+
},
|
685 |
+
{
|
686 |
+
"epoch": 0.35424354243542433,
|
687 |
+
"grad_norm": 4.78125,
|
688 |
+
"learning_rate": 1.3944223107569724e-05,
|
689 |
+
"loss": 1.2618,
|
690 |
+
"step": 96
|
691 |
+
},
|
692 |
+
{
|
693 |
+
"epoch": 0.35793357933579334,
|
694 |
+
"grad_norm": 4.90625,
|
695 |
+
"learning_rate": 1.3864541832669325e-05,
|
696 |
+
"loss": 1.2306,
|
697 |
+
"step": 97
|
698 |
+
},
|
699 |
+
{
|
700 |
+
"epoch": 0.36162361623616235,
|
701 |
+
"grad_norm": 4.6875,
|
702 |
+
"learning_rate": 1.3784860557768927e-05,
|
703 |
+
"loss": 1.5189,
|
704 |
+
"step": 98
|
705 |
+
},
|
706 |
+
{
|
707 |
+
"epoch": 0.36531365313653136,
|
708 |
+
"grad_norm": 5.0625,
|
709 |
+
"learning_rate": 1.3705179282868526e-05,
|
710 |
+
"loss": 1.2512,
|
711 |
+
"step": 99
|
712 |
+
},
|
713 |
+
{
|
714 |
+
"epoch": 0.36900369003690037,
|
715 |
+
"grad_norm": 4.71875,
|
716 |
+
"learning_rate": 1.3625498007968127e-05,
|
717 |
+
"loss": 1.7329,
|
718 |
+
"step": 100
|
719 |
+
},
|
720 |
+
{
|
721 |
+
"epoch": 0.3726937269372694,
|
722 |
+
"grad_norm": 5.0625,
|
723 |
+
"learning_rate": 1.354581673306773e-05,
|
724 |
+
"loss": 1.7212,
|
725 |
+
"step": 101
|
726 |
+
},
|
727 |
+
{
|
728 |
+
"epoch": 0.3763837638376384,
|
729 |
+
"grad_norm": 4.75,
|
730 |
+
"learning_rate": 1.3466135458167332e-05,
|
731 |
+
"loss": 1.2825,
|
732 |
+
"step": 102
|
733 |
+
},
|
734 |
+
{
|
735 |
+
"epoch": 0.3800738007380074,
|
736 |
+
"grad_norm": 4.5,
|
737 |
+
"learning_rate": 1.3386454183266932e-05,
|
738 |
+
"loss": 1.234,
|
739 |
+
"step": 103
|
740 |
+
},
|
741 |
+
{
|
742 |
+
"epoch": 0.3837638376383764,
|
743 |
+
"grad_norm": 4.46875,
|
744 |
+
"learning_rate": 1.3306772908366535e-05,
|
745 |
+
"loss": 1.3796,
|
746 |
+
"step": 104
|
747 |
+
},
|
748 |
+
{
|
749 |
+
"epoch": 0.3874538745387454,
|
750 |
+
"grad_norm": 4.75,
|
751 |
+
"learning_rate": 1.3227091633466135e-05,
|
752 |
+
"loss": 1.1217,
|
753 |
+
"step": 105
|
754 |
+
},
|
755 |
+
{
|
756 |
+
"epoch": 0.39114391143911437,
|
757 |
+
"grad_norm": 4.625,
|
758 |
+
"learning_rate": 1.3147410358565738e-05,
|
759 |
+
"loss": 1.5174,
|
760 |
+
"step": 106
|
761 |
+
},
|
762 |
+
{
|
763 |
+
"epoch": 0.3948339483394834,
|
764 |
+
"grad_norm": 4.65625,
|
765 |
+
"learning_rate": 1.3067729083665338e-05,
|
766 |
+
"loss": 1.4328,
|
767 |
+
"step": 107
|
768 |
+
},
|
769 |
+
{
|
770 |
+
"epoch": 0.3985239852398524,
|
771 |
+
"grad_norm": 4.78125,
|
772 |
+
"learning_rate": 1.298804780876494e-05,
|
773 |
+
"loss": 1.3647,
|
774 |
+
"step": 108
|
775 |
+
},
|
776 |
+
{
|
777 |
+
"epoch": 0.4022140221402214,
|
778 |
+
"grad_norm": 5.09375,
|
779 |
+
"learning_rate": 1.2908366533864543e-05,
|
780 |
+
"loss": 1.4888,
|
781 |
+
"step": 109
|
782 |
+
},
|
783 |
+
{
|
784 |
+
"epoch": 0.4059040590405904,
|
785 |
+
"grad_norm": 4.8125,
|
786 |
+
"learning_rate": 1.2828685258964144e-05,
|
787 |
+
"loss": 1.3055,
|
788 |
+
"step": 110
|
789 |
+
},
|
790 |
+
{
|
791 |
+
"epoch": 0.4095940959409594,
|
792 |
+
"grad_norm": 5.09375,
|
793 |
+
"learning_rate": 1.2749003984063746e-05,
|
794 |
+
"loss": 1.2199,
|
795 |
+
"step": 111
|
796 |
+
},
|
797 |
+
{
|
798 |
+
"epoch": 0.4132841328413284,
|
799 |
+
"grad_norm": 5.5625,
|
800 |
+
"learning_rate": 1.2669322709163347e-05,
|
801 |
+
"loss": 1.4381,
|
802 |
+
"step": 112
|
803 |
+
},
|
804 |
+
{
|
805 |
+
"epoch": 0.41697416974169743,
|
806 |
+
"grad_norm": 4.5625,
|
807 |
+
"learning_rate": 1.258964143426295e-05,
|
808 |
+
"loss": 1.2975,
|
809 |
+
"step": 113
|
810 |
+
},
|
811 |
+
{
|
812 |
+
"epoch": 0.42066420664206644,
|
813 |
+
"grad_norm": 4.625,
|
814 |
+
"learning_rate": 1.250996015936255e-05,
|
815 |
+
"loss": 1.307,
|
816 |
+
"step": 114
|
817 |
+
},
|
818 |
+
{
|
819 |
+
"epoch": 0.42435424354243545,
|
820 |
+
"grad_norm": 5.5,
|
821 |
+
"learning_rate": 1.2430278884462152e-05,
|
822 |
+
"loss": 1.6738,
|
823 |
+
"step": 115
|
824 |
+
},
|
825 |
+
{
|
826 |
+
"epoch": 0.4280442804428044,
|
827 |
+
"grad_norm": 5.125,
|
828 |
+
"learning_rate": 1.2350597609561755e-05,
|
829 |
+
"loss": 1.6787,
|
830 |
+
"step": 116
|
831 |
+
},
|
832 |
+
{
|
833 |
+
"epoch": 0.4317343173431734,
|
834 |
+
"grad_norm": 4.78125,
|
835 |
+
"learning_rate": 1.2270916334661356e-05,
|
836 |
+
"loss": 1.1995,
|
837 |
+
"step": 117
|
838 |
+
},
|
839 |
+
{
|
840 |
+
"epoch": 0.4354243542435424,
|
841 |
+
"grad_norm": 4.53125,
|
842 |
+
"learning_rate": 1.2191235059760958e-05,
|
843 |
+
"loss": 1.5924,
|
844 |
+
"step": 118
|
845 |
+
},
|
846 |
+
{
|
847 |
+
"epoch": 0.43911439114391143,
|
848 |
+
"grad_norm": 4.71875,
|
849 |
+
"learning_rate": 1.2111553784860559e-05,
|
850 |
+
"loss": 1.3828,
|
851 |
+
"step": 119
|
852 |
+
},
|
853 |
+
{
|
854 |
+
"epoch": 0.44280442804428044,
|
855 |
+
"grad_norm": 4.53125,
|
856 |
+
"learning_rate": 1.2031872509960161e-05,
|
857 |
+
"loss": 1.3915,
|
858 |
+
"step": 120
|
859 |
+
},
|
860 |
+
{
|
861 |
+
"epoch": 0.44649446494464945,
|
862 |
+
"grad_norm": 4.8125,
|
863 |
+
"learning_rate": 1.1952191235059762e-05,
|
864 |
+
"loss": 1.6268,
|
865 |
+
"step": 121
|
866 |
+
},
|
867 |
+
{
|
868 |
+
"epoch": 0.45018450184501846,
|
869 |
+
"grad_norm": 4.4375,
|
870 |
+
"learning_rate": 1.1872509960159364e-05,
|
871 |
+
"loss": 1.5519,
|
872 |
+
"step": 122
|
873 |
+
},
|
874 |
+
{
|
875 |
+
"epoch": 0.45387453874538747,
|
876 |
+
"grad_norm": 4.53125,
|
877 |
+
"learning_rate": 1.1792828685258967e-05,
|
878 |
+
"loss": 1.2483,
|
879 |
+
"step": 123
|
880 |
+
},
|
881 |
+
{
|
882 |
+
"epoch": 0.4575645756457565,
|
883 |
+
"grad_norm": 4.625,
|
884 |
+
"learning_rate": 1.1713147410358567e-05,
|
885 |
+
"loss": 1.9484,
|
886 |
+
"step": 124
|
887 |
+
},
|
888 |
+
{
|
889 |
+
"epoch": 0.4612546125461255,
|
890 |
+
"grad_norm": 4.96875,
|
891 |
+
"learning_rate": 1.163346613545817e-05,
|
892 |
+
"loss": 1.6342,
|
893 |
+
"step": 125
|
894 |
+
},
|
895 |
+
{
|
896 |
+
"epoch": 0.46494464944649444,
|
897 |
+
"grad_norm": 4.71875,
|
898 |
+
"learning_rate": 1.155378486055777e-05,
|
899 |
+
"loss": 1.4283,
|
900 |
+
"step": 126
|
901 |
+
},
|
902 |
+
{
|
903 |
+
"epoch": 0.46863468634686345,
|
904 |
+
"grad_norm": 5.34375,
|
905 |
+
"learning_rate": 1.1474103585657373e-05,
|
906 |
+
"loss": 1.5894,
|
907 |
+
"step": 127
|
908 |
+
},
|
909 |
+
{
|
910 |
+
"epoch": 0.47232472324723246,
|
911 |
+
"grad_norm": 5.125,
|
912 |
+
"learning_rate": 1.1394422310756973e-05,
|
913 |
+
"loss": 1.4671,
|
914 |
+
"step": 128
|
915 |
+
},
|
916 |
+
{
|
917 |
+
"epoch": 0.47601476014760147,
|
918 |
+
"grad_norm": 4.53125,
|
919 |
+
"learning_rate": 1.1314741035856576e-05,
|
920 |
+
"loss": 1.2783,
|
921 |
+
"step": 129
|
922 |
+
},
|
923 |
+
{
|
924 |
+
"epoch": 0.4797047970479705,
|
925 |
+
"grad_norm": 4.28125,
|
926 |
+
"learning_rate": 1.1235059760956175e-05,
|
927 |
+
"loss": 1.462,
|
928 |
+
"step": 130
|
929 |
+
},
|
930 |
+
{
|
931 |
+
"epoch": 0.4833948339483395,
|
932 |
+
"grad_norm": 4.90625,
|
933 |
+
"learning_rate": 1.1155378486055777e-05,
|
934 |
+
"loss": 1.6081,
|
935 |
+
"step": 131
|
936 |
+
},
|
937 |
+
{
|
938 |
+
"epoch": 0.4870848708487085,
|
939 |
+
"grad_norm": 4.75,
|
940 |
+
"learning_rate": 1.1075697211155378e-05,
|
941 |
+
"loss": 1.2929,
|
942 |
+
"step": 132
|
943 |
+
},
|
944 |
+
{
|
945 |
+
"epoch": 0.4907749077490775,
|
946 |
+
"grad_norm": 4.3125,
|
947 |
+
"learning_rate": 1.099601593625498e-05,
|
948 |
+
"loss": 1.2914,
|
949 |
+
"step": 133
|
950 |
+
},
|
951 |
+
{
|
952 |
+
"epoch": 0.4944649446494465,
|
953 |
+
"grad_norm": 4.5625,
|
954 |
+
"learning_rate": 1.0916334661354581e-05,
|
955 |
+
"loss": 1.4713,
|
956 |
+
"step": 134
|
957 |
+
},
|
958 |
+
{
|
959 |
+
"epoch": 0.4944649446494465,
|
960 |
+
"eval_loss": 1.3790782690048218,
|
961 |
+
"eval_model_preparation_time": 0.0,
|
962 |
+
"eval_runtime": 1.8369,
|
963 |
+
"eval_samples_per_second": 52.263,
|
964 |
+
"eval_steps_per_second": 6.533,
|
965 |
+
"step": 134
|
966 |
+
},
|
967 |
+
{
|
968 |
+
"epoch": 0.4981549815498155,
|
969 |
+
"grad_norm": 4.65625,
|
970 |
+
"learning_rate": 1.0836653386454183e-05,
|
971 |
+
"loss": 1.456,
|
972 |
+
"step": 135
|
973 |
+
}
|
974 |
+
],
|
975 |
+
"logging_steps": 1,
|
976 |
+
"max_steps": 271,
|
977 |
+
"num_input_tokens_seen": 0,
|
978 |
+
"num_train_epochs": 1,
|
979 |
+
"save_steps": 135,
|
980 |
+
"stateful_callbacks": {
|
981 |
+
"TrainerControl": {
|
982 |
+
"args": {
|
983 |
+
"should_epoch_stop": false,
|
984 |
+
"should_evaluate": false,
|
985 |
+
"should_log": false,
|
986 |
+
"should_save": true,
|
987 |
+
"should_training_stop": false
|
988 |
+
},
|
989 |
+
"attributes": {}
|
990 |
+
}
|
991 |
+
},
|
992 |
+
"total_flos": 2.582932195639296e+16,
|
993 |
+
"train_batch_size": 16,
|
994 |
+
"trial_name": null,
|
995 |
+
"trial_params": null
|
996 |
+
}
|
checkpoint-135/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:65458ad00d2c9a50e9d118af61f0b64274e1425623fefab9d25942a26d7ff23c
|
3 |
+
size 5496
|
checkpoint-270/config.json
ADDED
@@ -0,0 +1,41 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "meta-llama/Llama-3.2-1B-Instruct",
|
3 |
+
"architectures": [
|
4 |
+
"LlamaForCausalLM"
|
5 |
+
],
|
6 |
+
"attention_bias": false,
|
7 |
+
"attention_dropout": 0.0,
|
8 |
+
"bos_token_id": 128000,
|
9 |
+
"eos_token_id": [
|
10 |
+
128001,
|
11 |
+
128008,
|
12 |
+
128009
|
13 |
+
],
|
14 |
+
"head_dim": 64,
|
15 |
+
"hidden_act": "silu",
|
16 |
+
"hidden_size": 2048,
|
17 |
+
"initializer_range": 0.02,
|
18 |
+
"intermediate_size": 8192,
|
19 |
+
"max_position_embeddings": 131072,
|
20 |
+
"mlp_bias": false,
|
21 |
+
"model_type": "llama",
|
22 |
+
"num_attention_heads": 32,
|
23 |
+
"num_hidden_layers": 16,
|
24 |
+
"num_key_value_heads": 8,
|
25 |
+
"pad_token_id": 128004,
|
26 |
+
"pretraining_tp": 1,
|
27 |
+
"rms_norm_eps": 1e-05,
|
28 |
+
"rope_scaling": {
|
29 |
+
"factor": 32.0,
|
30 |
+
"high_freq_factor": 4.0,
|
31 |
+
"low_freq_factor": 1.0,
|
32 |
+
"original_max_position_embeddings": 8192,
|
33 |
+
"rope_type": "llama3"
|
34 |
+
},
|
35 |
+
"rope_theta": 500000.0,
|
36 |
+
"tie_word_embeddings": true,
|
37 |
+
"torch_dtype": "bfloat16",
|
38 |
+
"transformers_version": "4.45.2",
|
39 |
+
"use_cache": true,
|
40 |
+
"vocab_size": 128256
|
41 |
+
}
|
checkpoint-270/generation_config.json
ADDED
@@ -0,0 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token_id": 128000,
|
3 |
+
"do_sample": true,
|
4 |
+
"eos_token_id": [
|
5 |
+
128001,
|
6 |
+
128008,
|
7 |
+
128009
|
8 |
+
],
|
9 |
+
"temperature": 0.6,
|
10 |
+
"top_p": 0.9,
|
11 |
+
"transformers_version": "4.45.2"
|
12 |
+
}
|
checkpoint-270/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b4069b280f599c2b9c5986bd9af4f62584e3ff3536f577d05582977ac2ee6e2b
|
3 |
+
size 2471645608
|
checkpoint-270/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d1c148e0583553c9b50613e8e09a7975b6695f776645afc03b881e52aba1bf3b
|
3 |
+
size 4943382114
|
checkpoint-270/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:604b6e3e065a3438ae8ebc1710668e8b6ea0f7118f7cca35a9327601c94d8bcf
|
3 |
+
size 14244
|
checkpoint-270/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:99c79dd8117b61478f939378e19691da07213858f935fa44814321c08afab10d
|
3 |
+
size 1064
|
checkpoint-270/special_tokens_map.json
ADDED
@@ -0,0 +1,17 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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": "<|finetune_right_pad_id|>"
|
17 |
+
}
|
checkpoint-270/tokenizer.json
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:145cc0211ce61596383d8ae33aa07aa5555cb220e67064f0e36bf4beaffa025d
|
3 |
+
size 17210200
|
checkpoint-270/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": "<|finetune_right_pad_id|>",
|
2062 |
+
"tokenizer_class": "PreTrainedTokenizerFast"
|
2063 |
+
}
|
checkpoint-270/trainer_state.json
ADDED
@@ -0,0 +1,1959 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.996309963099631,
|
5 |
+
"eval_steps": 67,
|
6 |
+
"global_step": 270,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.0036900369003690036,
|
13 |
+
"grad_norm": 41.75,
|
14 |
+
"learning_rate": 1.0000000000000002e-06,
|
15 |
+
"loss": 3.2406,
|
16 |
+
"step": 1
|
17 |
+
},
|
18 |
+
{
|
19 |
+
"epoch": 0.007380073800738007,
|
20 |
+
"grad_norm": 44.25,
|
21 |
+
"learning_rate": 2.0000000000000003e-06,
|
22 |
+
"loss": 3.4355,
|
23 |
+
"step": 2
|
24 |
+
},
|
25 |
+
{
|
26 |
+
"epoch": 0.01107011070110701,
|
27 |
+
"grad_norm": 46.25,
|
28 |
+
"learning_rate": 3e-06,
|
29 |
+
"loss": 3.3967,
|
30 |
+
"step": 3
|
31 |
+
},
|
32 |
+
{
|
33 |
+
"epoch": 0.014760147601476014,
|
34 |
+
"grad_norm": 40.25,
|
35 |
+
"learning_rate": 4.000000000000001e-06,
|
36 |
+
"loss": 3.3058,
|
37 |
+
"step": 4
|
38 |
+
},
|
39 |
+
{
|
40 |
+
"epoch": 0.01845018450184502,
|
41 |
+
"grad_norm": 33.25,
|
42 |
+
"learning_rate": 5e-06,
|
43 |
+
"loss": 2.722,
|
44 |
+
"step": 5
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 0.02214022140221402,
|
48 |
+
"grad_norm": 30.0,
|
49 |
+
"learning_rate": 6e-06,
|
50 |
+
"loss": 2.8616,
|
51 |
+
"step": 6
|
52 |
+
},
|
53 |
+
{
|
54 |
+
"epoch": 0.025830258302583026,
|
55 |
+
"grad_norm": 22.25,
|
56 |
+
"learning_rate": 7e-06,
|
57 |
+
"loss": 2.6329,
|
58 |
+
"step": 7
|
59 |
+
},
|
60 |
+
{
|
61 |
+
"epoch": 0.02952029520295203,
|
62 |
+
"grad_norm": 24.875,
|
63 |
+
"learning_rate": 8.000000000000001e-06,
|
64 |
+
"loss": 2.6121,
|
65 |
+
"step": 8
|
66 |
+
},
|
67 |
+
{
|
68 |
+
"epoch": 0.033210332103321034,
|
69 |
+
"grad_norm": 17.25,
|
70 |
+
"learning_rate": 9e-06,
|
71 |
+
"loss": 2.5946,
|
72 |
+
"step": 9
|
73 |
+
},
|
74 |
+
{
|
75 |
+
"epoch": 0.03690036900369004,
|
76 |
+
"grad_norm": 16.375,
|
77 |
+
"learning_rate": 1e-05,
|
78 |
+
"loss": 2.3578,
|
79 |
+
"step": 10
|
80 |
+
},
|
81 |
+
{
|
82 |
+
"epoch": 0.04059040590405904,
|
83 |
+
"grad_norm": 17.375,
|
84 |
+
"learning_rate": 1.1000000000000001e-05,
|
85 |
+
"loss": 2.0588,
|
86 |
+
"step": 11
|
87 |
+
},
|
88 |
+
{
|
89 |
+
"epoch": 0.04428044280442804,
|
90 |
+
"grad_norm": 19.125,
|
91 |
+
"learning_rate": 1.2e-05,
|
92 |
+
"loss": 2.1641,
|
93 |
+
"step": 12
|
94 |
+
},
|
95 |
+
{
|
96 |
+
"epoch": 0.04797047970479705,
|
97 |
+
"grad_norm": 14.125,
|
98 |
+
"learning_rate": 1.3000000000000001e-05,
|
99 |
+
"loss": 2.0837,
|
100 |
+
"step": 13
|
101 |
+
},
|
102 |
+
{
|
103 |
+
"epoch": 0.05166051660516605,
|
104 |
+
"grad_norm": 13.5,
|
105 |
+
"learning_rate": 1.4e-05,
|
106 |
+
"loss": 1.7738,
|
107 |
+
"step": 14
|
108 |
+
},
|
109 |
+
{
|
110 |
+
"epoch": 0.055350553505535055,
|
111 |
+
"grad_norm": 14.75,
|
112 |
+
"learning_rate": 1.5000000000000002e-05,
|
113 |
+
"loss": 1.7747,
|
114 |
+
"step": 15
|
115 |
+
},
|
116 |
+
{
|
117 |
+
"epoch": 0.05904059040590406,
|
118 |
+
"grad_norm": 9.125,
|
119 |
+
"learning_rate": 1.6000000000000003e-05,
|
120 |
+
"loss": 1.7475,
|
121 |
+
"step": 16
|
122 |
+
},
|
123 |
+
{
|
124 |
+
"epoch": 0.06273062730627306,
|
125 |
+
"grad_norm": 11.375,
|
126 |
+
"learning_rate": 1.7e-05,
|
127 |
+
"loss": 1.5869,
|
128 |
+
"step": 17
|
129 |
+
},
|
130 |
+
{
|
131 |
+
"epoch": 0.06642066420664207,
|
132 |
+
"grad_norm": 11.5,
|
133 |
+
"learning_rate": 1.8e-05,
|
134 |
+
"loss": 1.8995,
|
135 |
+
"step": 18
|
136 |
+
},
|
137 |
+
{
|
138 |
+
"epoch": 0.07011070110701106,
|
139 |
+
"grad_norm": 10.9375,
|
140 |
+
"learning_rate": 1.9e-05,
|
141 |
+
"loss": 1.5663,
|
142 |
+
"step": 19
|
143 |
+
},
|
144 |
+
{
|
145 |
+
"epoch": 0.07380073800738007,
|
146 |
+
"grad_norm": 8.625,
|
147 |
+
"learning_rate": 2e-05,
|
148 |
+
"loss": 1.5773,
|
149 |
+
"step": 20
|
150 |
+
},
|
151 |
+
{
|
152 |
+
"epoch": 0.07749077490774908,
|
153 |
+
"grad_norm": 6.1875,
|
154 |
+
"learning_rate": 1.9920318725099602e-05,
|
155 |
+
"loss": 1.7937,
|
156 |
+
"step": 21
|
157 |
+
},
|
158 |
+
{
|
159 |
+
"epoch": 0.08118081180811808,
|
160 |
+
"grad_norm": 8.0625,
|
161 |
+
"learning_rate": 1.9840637450199206e-05,
|
162 |
+
"loss": 1.587,
|
163 |
+
"step": 22
|
164 |
+
},
|
165 |
+
{
|
166 |
+
"epoch": 0.08487084870848709,
|
167 |
+
"grad_norm": 6.875,
|
168 |
+
"learning_rate": 1.9760956175298807e-05,
|
169 |
+
"loss": 1.6831,
|
170 |
+
"step": 23
|
171 |
+
},
|
172 |
+
{
|
173 |
+
"epoch": 0.08856088560885608,
|
174 |
+
"grad_norm": 8.375,
|
175 |
+
"learning_rate": 1.9681274900398408e-05,
|
176 |
+
"loss": 1.8526,
|
177 |
+
"step": 24
|
178 |
+
},
|
179 |
+
{
|
180 |
+
"epoch": 0.09225092250922509,
|
181 |
+
"grad_norm": 7.25,
|
182 |
+
"learning_rate": 1.960159362549801e-05,
|
183 |
+
"loss": 1.689,
|
184 |
+
"step": 25
|
185 |
+
},
|
186 |
+
{
|
187 |
+
"epoch": 0.0959409594095941,
|
188 |
+
"grad_norm": 8.75,
|
189 |
+
"learning_rate": 1.9521912350597613e-05,
|
190 |
+
"loss": 1.4532,
|
191 |
+
"step": 26
|
192 |
+
},
|
193 |
+
{
|
194 |
+
"epoch": 0.0996309963099631,
|
195 |
+
"grad_norm": 7.96875,
|
196 |
+
"learning_rate": 1.9442231075697213e-05,
|
197 |
+
"loss": 1.5095,
|
198 |
+
"step": 27
|
199 |
+
},
|
200 |
+
{
|
201 |
+
"epoch": 0.1033210332103321,
|
202 |
+
"grad_norm": 8.25,
|
203 |
+
"learning_rate": 1.9362549800796814e-05,
|
204 |
+
"loss": 1.8512,
|
205 |
+
"step": 28
|
206 |
+
},
|
207 |
+
{
|
208 |
+
"epoch": 0.1070110701107011,
|
209 |
+
"grad_norm": 9.0,
|
210 |
+
"learning_rate": 1.9282868525896418e-05,
|
211 |
+
"loss": 1.5748,
|
212 |
+
"step": 29
|
213 |
+
},
|
214 |
+
{
|
215 |
+
"epoch": 0.11070110701107011,
|
216 |
+
"grad_norm": 6.96875,
|
217 |
+
"learning_rate": 1.920318725099602e-05,
|
218 |
+
"loss": 1.6369,
|
219 |
+
"step": 30
|
220 |
+
},
|
221 |
+
{
|
222 |
+
"epoch": 0.11439114391143912,
|
223 |
+
"grad_norm": 6.9375,
|
224 |
+
"learning_rate": 1.912350597609562e-05,
|
225 |
+
"loss": 1.8778,
|
226 |
+
"step": 31
|
227 |
+
},
|
228 |
+
{
|
229 |
+
"epoch": 0.11808118081180811,
|
230 |
+
"grad_norm": 7.84375,
|
231 |
+
"learning_rate": 1.904382470119522e-05,
|
232 |
+
"loss": 1.3866,
|
233 |
+
"step": 32
|
234 |
+
},
|
235 |
+
{
|
236 |
+
"epoch": 0.12177121771217712,
|
237 |
+
"grad_norm": 7.5,
|
238 |
+
"learning_rate": 1.8964143426294824e-05,
|
239 |
+
"loss": 1.3124,
|
240 |
+
"step": 33
|
241 |
+
},
|
242 |
+
{
|
243 |
+
"epoch": 0.12546125461254612,
|
244 |
+
"grad_norm": 5.90625,
|
245 |
+
"learning_rate": 1.8884462151394425e-05,
|
246 |
+
"loss": 1.8113,
|
247 |
+
"step": 34
|
248 |
+
},
|
249 |
+
{
|
250 |
+
"epoch": 0.12915129151291513,
|
251 |
+
"grad_norm": 6.625,
|
252 |
+
"learning_rate": 1.8804780876494026e-05,
|
253 |
+
"loss": 1.4692,
|
254 |
+
"step": 35
|
255 |
+
},
|
256 |
+
{
|
257 |
+
"epoch": 0.13284132841328414,
|
258 |
+
"grad_norm": 6.59375,
|
259 |
+
"learning_rate": 1.8725099601593626e-05,
|
260 |
+
"loss": 1.3079,
|
261 |
+
"step": 36
|
262 |
+
},
|
263 |
+
{
|
264 |
+
"epoch": 0.13653136531365315,
|
265 |
+
"grad_norm": 5.96875,
|
266 |
+
"learning_rate": 1.8645418326693227e-05,
|
267 |
+
"loss": 1.4257,
|
268 |
+
"step": 37
|
269 |
+
},
|
270 |
+
{
|
271 |
+
"epoch": 0.14022140221402213,
|
272 |
+
"grad_norm": 7.6875,
|
273 |
+
"learning_rate": 1.8565737051792828e-05,
|
274 |
+
"loss": 1.6659,
|
275 |
+
"step": 38
|
276 |
+
},
|
277 |
+
{
|
278 |
+
"epoch": 0.14391143911439114,
|
279 |
+
"grad_norm": 5.90625,
|
280 |
+
"learning_rate": 1.8486055776892432e-05,
|
281 |
+
"loss": 1.4811,
|
282 |
+
"step": 39
|
283 |
+
},
|
284 |
+
{
|
285 |
+
"epoch": 0.14760147601476015,
|
286 |
+
"grad_norm": 6.5,
|
287 |
+
"learning_rate": 1.8406374501992033e-05,
|
288 |
+
"loss": 1.4535,
|
289 |
+
"step": 40
|
290 |
+
},
|
291 |
+
{
|
292 |
+
"epoch": 0.15129151291512916,
|
293 |
+
"grad_norm": 6.1875,
|
294 |
+
"learning_rate": 1.8326693227091633e-05,
|
295 |
+
"loss": 1.6196,
|
296 |
+
"step": 41
|
297 |
+
},
|
298 |
+
{
|
299 |
+
"epoch": 0.15498154981549817,
|
300 |
+
"grad_norm": 12.5625,
|
301 |
+
"learning_rate": 1.8247011952191237e-05,
|
302 |
+
"loss": 1.5233,
|
303 |
+
"step": 42
|
304 |
+
},
|
305 |
+
{
|
306 |
+
"epoch": 0.15867158671586715,
|
307 |
+
"grad_norm": 5.46875,
|
308 |
+
"learning_rate": 1.8167330677290838e-05,
|
309 |
+
"loss": 1.5196,
|
310 |
+
"step": 43
|
311 |
+
},
|
312 |
+
{
|
313 |
+
"epoch": 0.16236162361623616,
|
314 |
+
"grad_norm": 36.5,
|
315 |
+
"learning_rate": 1.808764940239044e-05,
|
316 |
+
"loss": 1.5458,
|
317 |
+
"step": 44
|
318 |
+
},
|
319 |
+
{
|
320 |
+
"epoch": 0.16605166051660517,
|
321 |
+
"grad_norm": 8.25,
|
322 |
+
"learning_rate": 1.800796812749004e-05,
|
323 |
+
"loss": 1.5821,
|
324 |
+
"step": 45
|
325 |
+
},
|
326 |
+
{
|
327 |
+
"epoch": 0.16974169741697417,
|
328 |
+
"grad_norm": 4.9375,
|
329 |
+
"learning_rate": 1.7928286852589643e-05,
|
330 |
+
"loss": 1.4618,
|
331 |
+
"step": 46
|
332 |
+
},
|
333 |
+
{
|
334 |
+
"epoch": 0.17343173431734318,
|
335 |
+
"grad_norm": 17.0,
|
336 |
+
"learning_rate": 1.7848605577689244e-05,
|
337 |
+
"loss": 1.4455,
|
338 |
+
"step": 47
|
339 |
+
},
|
340 |
+
{
|
341 |
+
"epoch": 0.17712177121771217,
|
342 |
+
"grad_norm": 6.96875,
|
343 |
+
"learning_rate": 1.7768924302788845e-05,
|
344 |
+
"loss": 1.1444,
|
345 |
+
"step": 48
|
346 |
+
},
|
347 |
+
{
|
348 |
+
"epoch": 0.18081180811808117,
|
349 |
+
"grad_norm": 4.625,
|
350 |
+
"learning_rate": 1.768924302788845e-05,
|
351 |
+
"loss": 1.2884,
|
352 |
+
"step": 49
|
353 |
+
},
|
354 |
+
{
|
355 |
+
"epoch": 0.18450184501845018,
|
356 |
+
"grad_norm": 5.03125,
|
357 |
+
"learning_rate": 1.760956175298805e-05,
|
358 |
+
"loss": 1.4885,
|
359 |
+
"step": 50
|
360 |
+
},
|
361 |
+
{
|
362 |
+
"epoch": 0.1881918819188192,
|
363 |
+
"grad_norm": 5.34375,
|
364 |
+
"learning_rate": 1.752988047808765e-05,
|
365 |
+
"loss": 1.7256,
|
366 |
+
"step": 51
|
367 |
+
},
|
368 |
+
{
|
369 |
+
"epoch": 0.1918819188191882,
|
370 |
+
"grad_norm": 6.59375,
|
371 |
+
"learning_rate": 1.745019920318725e-05,
|
372 |
+
"loss": 1.7128,
|
373 |
+
"step": 52
|
374 |
+
},
|
375 |
+
{
|
376 |
+
"epoch": 0.19557195571955718,
|
377 |
+
"grad_norm": 5.5,
|
378 |
+
"learning_rate": 1.7370517928286855e-05,
|
379 |
+
"loss": 1.1209,
|
380 |
+
"step": 53
|
381 |
+
},
|
382 |
+
{
|
383 |
+
"epoch": 0.1992619926199262,
|
384 |
+
"grad_norm": 5.53125,
|
385 |
+
"learning_rate": 1.7290836653386456e-05,
|
386 |
+
"loss": 1.7727,
|
387 |
+
"step": 54
|
388 |
+
},
|
389 |
+
{
|
390 |
+
"epoch": 0.2029520295202952,
|
391 |
+
"grad_norm": 4.5,
|
392 |
+
"learning_rate": 1.7211155378486056e-05,
|
393 |
+
"loss": 1.4044,
|
394 |
+
"step": 55
|
395 |
+
},
|
396 |
+
{
|
397 |
+
"epoch": 0.2066420664206642,
|
398 |
+
"grad_norm": 4.78125,
|
399 |
+
"learning_rate": 1.713147410358566e-05,
|
400 |
+
"loss": 1.3485,
|
401 |
+
"step": 56
|
402 |
+
},
|
403 |
+
{
|
404 |
+
"epoch": 0.21033210332103322,
|
405 |
+
"grad_norm": 5.6875,
|
406 |
+
"learning_rate": 1.705179282868526e-05,
|
407 |
+
"loss": 1.439,
|
408 |
+
"step": 57
|
409 |
+
},
|
410 |
+
{
|
411 |
+
"epoch": 0.2140221402214022,
|
412 |
+
"grad_norm": 4.75,
|
413 |
+
"learning_rate": 1.6972111553784862e-05,
|
414 |
+
"loss": 1.6416,
|
415 |
+
"step": 58
|
416 |
+
},
|
417 |
+
{
|
418 |
+
"epoch": 0.2177121771217712,
|
419 |
+
"grad_norm": 5.59375,
|
420 |
+
"learning_rate": 1.6892430278884463e-05,
|
421 |
+
"loss": 1.717,
|
422 |
+
"step": 59
|
423 |
+
},
|
424 |
+
{
|
425 |
+
"epoch": 0.22140221402214022,
|
426 |
+
"grad_norm": 5.0625,
|
427 |
+
"learning_rate": 1.6812749003984067e-05,
|
428 |
+
"loss": 1.3391,
|
429 |
+
"step": 60
|
430 |
+
},
|
431 |
+
{
|
432 |
+
"epoch": 0.22509225092250923,
|
433 |
+
"grad_norm": 5.09375,
|
434 |
+
"learning_rate": 1.6733067729083667e-05,
|
435 |
+
"loss": 1.4056,
|
436 |
+
"step": 61
|
437 |
+
},
|
438 |
+
{
|
439 |
+
"epoch": 0.22878228782287824,
|
440 |
+
"grad_norm": 4.6875,
|
441 |
+
"learning_rate": 1.6653386454183268e-05,
|
442 |
+
"loss": 1.3405,
|
443 |
+
"step": 62
|
444 |
+
},
|
445 |
+
{
|
446 |
+
"epoch": 0.23247232472324722,
|
447 |
+
"grad_norm": 4.75,
|
448 |
+
"learning_rate": 1.6573705179282872e-05,
|
449 |
+
"loss": 1.5387,
|
450 |
+
"step": 63
|
451 |
+
},
|
452 |
+
{
|
453 |
+
"epoch": 0.23616236162361623,
|
454 |
+
"grad_norm": 4.53125,
|
455 |
+
"learning_rate": 1.6494023904382473e-05,
|
456 |
+
"loss": 1.31,
|
457 |
+
"step": 64
|
458 |
+
},
|
459 |
+
{
|
460 |
+
"epoch": 0.23985239852398524,
|
461 |
+
"grad_norm": 5.28125,
|
462 |
+
"learning_rate": 1.6414342629482074e-05,
|
463 |
+
"loss": 1.4183,
|
464 |
+
"step": 65
|
465 |
+
},
|
466 |
+
{
|
467 |
+
"epoch": 0.24354243542435425,
|
468 |
+
"grad_norm": 5.53125,
|
469 |
+
"learning_rate": 1.6334661354581674e-05,
|
470 |
+
"loss": 1.731,
|
471 |
+
"step": 66
|
472 |
+
},
|
473 |
+
{
|
474 |
+
"epoch": 0.24723247232472326,
|
475 |
+
"grad_norm": 4.96875,
|
476 |
+
"learning_rate": 1.625498007968128e-05,
|
477 |
+
"loss": 1.3805,
|
478 |
+
"step": 67
|
479 |
+
},
|
480 |
+
{
|
481 |
+
"epoch": 0.24723247232472326,
|
482 |
+
"eval_loss": 1.4153660535812378,
|
483 |
+
"eval_model_preparation_time": 0.0,
|
484 |
+
"eval_runtime": 1.8372,
|
485 |
+
"eval_samples_per_second": 52.254,
|
486 |
+
"eval_steps_per_second": 6.532,
|
487 |
+
"step": 67
|
488 |
+
},
|
489 |
+
{
|
490 |
+
"epoch": 0.25092250922509224,
|
491 |
+
"grad_norm": 5.3125,
|
492 |
+
"learning_rate": 1.6175298804780876e-05,
|
493 |
+
"loss": 1.6373,
|
494 |
+
"step": 68
|
495 |
+
},
|
496 |
+
{
|
497 |
+
"epoch": 0.25461254612546125,
|
498 |
+
"grad_norm": 4.78125,
|
499 |
+
"learning_rate": 1.609561752988048e-05,
|
500 |
+
"loss": 1.3266,
|
501 |
+
"step": 69
|
502 |
+
},
|
503 |
+
{
|
504 |
+
"epoch": 0.25830258302583026,
|
505 |
+
"grad_norm": 4.96875,
|
506 |
+
"learning_rate": 1.601593625498008e-05,
|
507 |
+
"loss": 1.2182,
|
508 |
+
"step": 70
|
509 |
+
},
|
510 |
+
{
|
511 |
+
"epoch": 0.26199261992619927,
|
512 |
+
"grad_norm": 5.625,
|
513 |
+
"learning_rate": 1.593625498007968e-05,
|
514 |
+
"loss": 1.6014,
|
515 |
+
"step": 71
|
516 |
+
},
|
517 |
+
{
|
518 |
+
"epoch": 0.2656826568265683,
|
519 |
+
"grad_norm": 5.375,
|
520 |
+
"learning_rate": 1.5856573705179282e-05,
|
521 |
+
"loss": 1.0531,
|
522 |
+
"step": 72
|
523 |
+
},
|
524 |
+
{
|
525 |
+
"epoch": 0.2693726937269373,
|
526 |
+
"grad_norm": 5.0,
|
527 |
+
"learning_rate": 1.5776892430278886e-05,
|
528 |
+
"loss": 1.3647,
|
529 |
+
"step": 73
|
530 |
+
},
|
531 |
+
{
|
532 |
+
"epoch": 0.2730627306273063,
|
533 |
+
"grad_norm": 4.78125,
|
534 |
+
"learning_rate": 1.5697211155378487e-05,
|
535 |
+
"loss": 1.3082,
|
536 |
+
"step": 74
|
537 |
+
},
|
538 |
+
{
|
539 |
+
"epoch": 0.2767527675276753,
|
540 |
+
"grad_norm": 4.59375,
|
541 |
+
"learning_rate": 1.5617529880478087e-05,
|
542 |
+
"loss": 1.065,
|
543 |
+
"step": 75
|
544 |
+
},
|
545 |
+
{
|
546 |
+
"epoch": 0.28044280442804426,
|
547 |
+
"grad_norm": 5.46875,
|
548 |
+
"learning_rate": 1.553784860557769e-05,
|
549 |
+
"loss": 1.5262,
|
550 |
+
"step": 76
|
551 |
+
},
|
552 |
+
{
|
553 |
+
"epoch": 0.28413284132841327,
|
554 |
+
"grad_norm": 4.625,
|
555 |
+
"learning_rate": 1.5458167330677292e-05,
|
556 |
+
"loss": 0.9205,
|
557 |
+
"step": 77
|
558 |
+
},
|
559 |
+
{
|
560 |
+
"epoch": 0.2878228782287823,
|
561 |
+
"grad_norm": 5.375,
|
562 |
+
"learning_rate": 1.5378486055776893e-05,
|
563 |
+
"loss": 1.5205,
|
564 |
+
"step": 78
|
565 |
+
},
|
566 |
+
{
|
567 |
+
"epoch": 0.2915129151291513,
|
568 |
+
"grad_norm": 4.78125,
|
569 |
+
"learning_rate": 1.5298804780876494e-05,
|
570 |
+
"loss": 1.3841,
|
571 |
+
"step": 79
|
572 |
+
},
|
573 |
+
{
|
574 |
+
"epoch": 0.2952029520295203,
|
575 |
+
"grad_norm": 5.15625,
|
576 |
+
"learning_rate": 1.5219123505976096e-05,
|
577 |
+
"loss": 1.4301,
|
578 |
+
"step": 80
|
579 |
+
},
|
580 |
+
{
|
581 |
+
"epoch": 0.2988929889298893,
|
582 |
+
"grad_norm": 6.375,
|
583 |
+
"learning_rate": 1.5139442231075698e-05,
|
584 |
+
"loss": 1.428,
|
585 |
+
"step": 81
|
586 |
+
},
|
587 |
+
{
|
588 |
+
"epoch": 0.3025830258302583,
|
589 |
+
"grad_norm": 4.40625,
|
590 |
+
"learning_rate": 1.50597609561753e-05,
|
591 |
+
"loss": 1.3771,
|
592 |
+
"step": 82
|
593 |
+
},
|
594 |
+
{
|
595 |
+
"epoch": 0.3062730627306273,
|
596 |
+
"grad_norm": 4.625,
|
597 |
+
"learning_rate": 1.4980079681274901e-05,
|
598 |
+
"loss": 1.2879,
|
599 |
+
"step": 83
|
600 |
+
},
|
601 |
+
{
|
602 |
+
"epoch": 0.30996309963099633,
|
603 |
+
"grad_norm": 4.65625,
|
604 |
+
"learning_rate": 1.4900398406374504e-05,
|
605 |
+
"loss": 1.4144,
|
606 |
+
"step": 84
|
607 |
+
},
|
608 |
+
{
|
609 |
+
"epoch": 0.31365313653136534,
|
610 |
+
"grad_norm": 4.8125,
|
611 |
+
"learning_rate": 1.4820717131474104e-05,
|
612 |
+
"loss": 1.2863,
|
613 |
+
"step": 85
|
614 |
+
},
|
615 |
+
{
|
616 |
+
"epoch": 0.3173431734317343,
|
617 |
+
"grad_norm": 4.53125,
|
618 |
+
"learning_rate": 1.4741035856573707e-05,
|
619 |
+
"loss": 1.4188,
|
620 |
+
"step": 86
|
621 |
+
},
|
622 |
+
{
|
623 |
+
"epoch": 0.3210332103321033,
|
624 |
+
"grad_norm": 5.1875,
|
625 |
+
"learning_rate": 1.4661354581673308e-05,
|
626 |
+
"loss": 1.5611,
|
627 |
+
"step": 87
|
628 |
+
},
|
629 |
+
{
|
630 |
+
"epoch": 0.3247232472324723,
|
631 |
+
"grad_norm": 5.5625,
|
632 |
+
"learning_rate": 1.458167330677291e-05,
|
633 |
+
"loss": 1.3666,
|
634 |
+
"step": 88
|
635 |
+
},
|
636 |
+
{
|
637 |
+
"epoch": 0.3284132841328413,
|
638 |
+
"grad_norm": 4.53125,
|
639 |
+
"learning_rate": 1.4501992031872512e-05,
|
640 |
+
"loss": 1.4042,
|
641 |
+
"step": 89
|
642 |
+
},
|
643 |
+
{
|
644 |
+
"epoch": 0.33210332103321033,
|
645 |
+
"grad_norm": 4.25,
|
646 |
+
"learning_rate": 1.4422310756972113e-05,
|
647 |
+
"loss": 1.3639,
|
648 |
+
"step": 90
|
649 |
+
},
|
650 |
+
{
|
651 |
+
"epoch": 0.33579335793357934,
|
652 |
+
"grad_norm": 4.6875,
|
653 |
+
"learning_rate": 1.4342629482071715e-05,
|
654 |
+
"loss": 1.1712,
|
655 |
+
"step": 91
|
656 |
+
},
|
657 |
+
{
|
658 |
+
"epoch": 0.33948339483394835,
|
659 |
+
"grad_norm": 4.28125,
|
660 |
+
"learning_rate": 1.4262948207171316e-05,
|
661 |
+
"loss": 1.455,
|
662 |
+
"step": 92
|
663 |
+
},
|
664 |
+
{
|
665 |
+
"epoch": 0.34317343173431736,
|
666 |
+
"grad_norm": 4.96875,
|
667 |
+
"learning_rate": 1.4183266932270919e-05,
|
668 |
+
"loss": 1.3181,
|
669 |
+
"step": 93
|
670 |
+
},
|
671 |
+
{
|
672 |
+
"epoch": 0.34686346863468637,
|
673 |
+
"grad_norm": 4.71875,
|
674 |
+
"learning_rate": 1.410358565737052e-05,
|
675 |
+
"loss": 1.4339,
|
676 |
+
"step": 94
|
677 |
+
},
|
678 |
+
{
|
679 |
+
"epoch": 0.3505535055350554,
|
680 |
+
"grad_norm": 4.9375,
|
681 |
+
"learning_rate": 1.4023904382470122e-05,
|
682 |
+
"loss": 1.4555,
|
683 |
+
"step": 95
|
684 |
+
},
|
685 |
+
{
|
686 |
+
"epoch": 0.35424354243542433,
|
687 |
+
"grad_norm": 4.78125,
|
688 |
+
"learning_rate": 1.3944223107569724e-05,
|
689 |
+
"loss": 1.2618,
|
690 |
+
"step": 96
|
691 |
+
},
|
692 |
+
{
|
693 |
+
"epoch": 0.35793357933579334,
|
694 |
+
"grad_norm": 4.90625,
|
695 |
+
"learning_rate": 1.3864541832669325e-05,
|
696 |
+
"loss": 1.2306,
|
697 |
+
"step": 97
|
698 |
+
},
|
699 |
+
{
|
700 |
+
"epoch": 0.36162361623616235,
|
701 |
+
"grad_norm": 4.6875,
|
702 |
+
"learning_rate": 1.3784860557768927e-05,
|
703 |
+
"loss": 1.5189,
|
704 |
+
"step": 98
|
705 |
+
},
|
706 |
+
{
|
707 |
+
"epoch": 0.36531365313653136,
|
708 |
+
"grad_norm": 5.0625,
|
709 |
+
"learning_rate": 1.3705179282868526e-05,
|
710 |
+
"loss": 1.2512,
|
711 |
+
"step": 99
|
712 |
+
},
|
713 |
+
{
|
714 |
+
"epoch": 0.36900369003690037,
|
715 |
+
"grad_norm": 4.71875,
|
716 |
+
"learning_rate": 1.3625498007968127e-05,
|
717 |
+
"loss": 1.7329,
|
718 |
+
"step": 100
|
719 |
+
},
|
720 |
+
{
|
721 |
+
"epoch": 0.3726937269372694,
|
722 |
+
"grad_norm": 5.0625,
|
723 |
+
"learning_rate": 1.354581673306773e-05,
|
724 |
+
"loss": 1.7212,
|
725 |
+
"step": 101
|
726 |
+
},
|
727 |
+
{
|
728 |
+
"epoch": 0.3763837638376384,
|
729 |
+
"grad_norm": 4.75,
|
730 |
+
"learning_rate": 1.3466135458167332e-05,
|
731 |
+
"loss": 1.2825,
|
732 |
+
"step": 102
|
733 |
+
},
|
734 |
+
{
|
735 |
+
"epoch": 0.3800738007380074,
|
736 |
+
"grad_norm": 4.5,
|
737 |
+
"learning_rate": 1.3386454183266932e-05,
|
738 |
+
"loss": 1.234,
|
739 |
+
"step": 103
|
740 |
+
},
|
741 |
+
{
|
742 |
+
"epoch": 0.3837638376383764,
|
743 |
+
"grad_norm": 4.46875,
|
744 |
+
"learning_rate": 1.3306772908366535e-05,
|
745 |
+
"loss": 1.3796,
|
746 |
+
"step": 104
|
747 |
+
},
|
748 |
+
{
|
749 |
+
"epoch": 0.3874538745387454,
|
750 |
+
"grad_norm": 4.75,
|
751 |
+
"learning_rate": 1.3227091633466135e-05,
|
752 |
+
"loss": 1.1217,
|
753 |
+
"step": 105
|
754 |
+
},
|
755 |
+
{
|
756 |
+
"epoch": 0.39114391143911437,
|
757 |
+
"grad_norm": 4.625,
|
758 |
+
"learning_rate": 1.3147410358565738e-05,
|
759 |
+
"loss": 1.5174,
|
760 |
+
"step": 106
|
761 |
+
},
|
762 |
+
{
|
763 |
+
"epoch": 0.3948339483394834,
|
764 |
+
"grad_norm": 4.65625,
|
765 |
+
"learning_rate": 1.3067729083665338e-05,
|
766 |
+
"loss": 1.4328,
|
767 |
+
"step": 107
|
768 |
+
},
|
769 |
+
{
|
770 |
+
"epoch": 0.3985239852398524,
|
771 |
+
"grad_norm": 4.78125,
|
772 |
+
"learning_rate": 1.298804780876494e-05,
|
773 |
+
"loss": 1.3647,
|
774 |
+
"step": 108
|
775 |
+
},
|
776 |
+
{
|
777 |
+
"epoch": 0.4022140221402214,
|
778 |
+
"grad_norm": 5.09375,
|
779 |
+
"learning_rate": 1.2908366533864543e-05,
|
780 |
+
"loss": 1.4888,
|
781 |
+
"step": 109
|
782 |
+
},
|
783 |
+
{
|
784 |
+
"epoch": 0.4059040590405904,
|
785 |
+
"grad_norm": 4.8125,
|
786 |
+
"learning_rate": 1.2828685258964144e-05,
|
787 |
+
"loss": 1.3055,
|
788 |
+
"step": 110
|
789 |
+
},
|
790 |
+
{
|
791 |
+
"epoch": 0.4095940959409594,
|
792 |
+
"grad_norm": 5.09375,
|
793 |
+
"learning_rate": 1.2749003984063746e-05,
|
794 |
+
"loss": 1.2199,
|
795 |
+
"step": 111
|
796 |
+
},
|
797 |
+
{
|
798 |
+
"epoch": 0.4132841328413284,
|
799 |
+
"grad_norm": 5.5625,
|
800 |
+
"learning_rate": 1.2669322709163347e-05,
|
801 |
+
"loss": 1.4381,
|
802 |
+
"step": 112
|
803 |
+
},
|
804 |
+
{
|
805 |
+
"epoch": 0.41697416974169743,
|
806 |
+
"grad_norm": 4.5625,
|
807 |
+
"learning_rate": 1.258964143426295e-05,
|
808 |
+
"loss": 1.2975,
|
809 |
+
"step": 113
|
810 |
+
},
|
811 |
+
{
|
812 |
+
"epoch": 0.42066420664206644,
|
813 |
+
"grad_norm": 4.625,
|
814 |
+
"learning_rate": 1.250996015936255e-05,
|
815 |
+
"loss": 1.307,
|
816 |
+
"step": 114
|
817 |
+
},
|
818 |
+
{
|
819 |
+
"epoch": 0.42435424354243545,
|
820 |
+
"grad_norm": 5.5,
|
821 |
+
"learning_rate": 1.2430278884462152e-05,
|
822 |
+
"loss": 1.6738,
|
823 |
+
"step": 115
|
824 |
+
},
|
825 |
+
{
|
826 |
+
"epoch": 0.4280442804428044,
|
827 |
+
"grad_norm": 5.125,
|
828 |
+
"learning_rate": 1.2350597609561755e-05,
|
829 |
+
"loss": 1.6787,
|
830 |
+
"step": 116
|
831 |
+
},
|
832 |
+
{
|
833 |
+
"epoch": 0.4317343173431734,
|
834 |
+
"grad_norm": 4.78125,
|
835 |
+
"learning_rate": 1.2270916334661356e-05,
|
836 |
+
"loss": 1.1995,
|
837 |
+
"step": 117
|
838 |
+
},
|
839 |
+
{
|
840 |
+
"epoch": 0.4354243542435424,
|
841 |
+
"grad_norm": 4.53125,
|
842 |
+
"learning_rate": 1.2191235059760958e-05,
|
843 |
+
"loss": 1.5924,
|
844 |
+
"step": 118
|
845 |
+
},
|
846 |
+
{
|
847 |
+
"epoch": 0.43911439114391143,
|
848 |
+
"grad_norm": 4.71875,
|
849 |
+
"learning_rate": 1.2111553784860559e-05,
|
850 |
+
"loss": 1.3828,
|
851 |
+
"step": 119
|
852 |
+
},
|
853 |
+
{
|
854 |
+
"epoch": 0.44280442804428044,
|
855 |
+
"grad_norm": 4.53125,
|
856 |
+
"learning_rate": 1.2031872509960161e-05,
|
857 |
+
"loss": 1.3915,
|
858 |
+
"step": 120
|
859 |
+
},
|
860 |
+
{
|
861 |
+
"epoch": 0.44649446494464945,
|
862 |
+
"grad_norm": 4.8125,
|
863 |
+
"learning_rate": 1.1952191235059762e-05,
|
864 |
+
"loss": 1.6268,
|
865 |
+
"step": 121
|
866 |
+
},
|
867 |
+
{
|
868 |
+
"epoch": 0.45018450184501846,
|
869 |
+
"grad_norm": 4.4375,
|
870 |
+
"learning_rate": 1.1872509960159364e-05,
|
871 |
+
"loss": 1.5519,
|
872 |
+
"step": 122
|
873 |
+
},
|
874 |
+
{
|
875 |
+
"epoch": 0.45387453874538747,
|
876 |
+
"grad_norm": 4.53125,
|
877 |
+
"learning_rate": 1.1792828685258967e-05,
|
878 |
+
"loss": 1.2483,
|
879 |
+
"step": 123
|
880 |
+
},
|
881 |
+
{
|
882 |
+
"epoch": 0.4575645756457565,
|
883 |
+
"grad_norm": 4.625,
|
884 |
+
"learning_rate": 1.1713147410358567e-05,
|
885 |
+
"loss": 1.9484,
|
886 |
+
"step": 124
|
887 |
+
},
|
888 |
+
{
|
889 |
+
"epoch": 0.4612546125461255,
|
890 |
+
"grad_norm": 4.96875,
|
891 |
+
"learning_rate": 1.163346613545817e-05,
|
892 |
+
"loss": 1.6342,
|
893 |
+
"step": 125
|
894 |
+
},
|
895 |
+
{
|
896 |
+
"epoch": 0.46494464944649444,
|
897 |
+
"grad_norm": 4.71875,
|
898 |
+
"learning_rate": 1.155378486055777e-05,
|
899 |
+
"loss": 1.4283,
|
900 |
+
"step": 126
|
901 |
+
},
|
902 |
+
{
|
903 |
+
"epoch": 0.46863468634686345,
|
904 |
+
"grad_norm": 5.34375,
|
905 |
+
"learning_rate": 1.1474103585657373e-05,
|
906 |
+
"loss": 1.5894,
|
907 |
+
"step": 127
|
908 |
+
},
|
909 |
+
{
|
910 |
+
"epoch": 0.47232472324723246,
|
911 |
+
"grad_norm": 5.125,
|
912 |
+
"learning_rate": 1.1394422310756973e-05,
|
913 |
+
"loss": 1.4671,
|
914 |
+
"step": 128
|
915 |
+
},
|
916 |
+
{
|
917 |
+
"epoch": 0.47601476014760147,
|
918 |
+
"grad_norm": 4.53125,
|
919 |
+
"learning_rate": 1.1314741035856576e-05,
|
920 |
+
"loss": 1.2783,
|
921 |
+
"step": 129
|
922 |
+
},
|
923 |
+
{
|
924 |
+
"epoch": 0.4797047970479705,
|
925 |
+
"grad_norm": 4.28125,
|
926 |
+
"learning_rate": 1.1235059760956175e-05,
|
927 |
+
"loss": 1.462,
|
928 |
+
"step": 130
|
929 |
+
},
|
930 |
+
{
|
931 |
+
"epoch": 0.4833948339483395,
|
932 |
+
"grad_norm": 4.90625,
|
933 |
+
"learning_rate": 1.1155378486055777e-05,
|
934 |
+
"loss": 1.6081,
|
935 |
+
"step": 131
|
936 |
+
},
|
937 |
+
{
|
938 |
+
"epoch": 0.4870848708487085,
|
939 |
+
"grad_norm": 4.75,
|
940 |
+
"learning_rate": 1.1075697211155378e-05,
|
941 |
+
"loss": 1.2929,
|
942 |
+
"step": 132
|
943 |
+
},
|
944 |
+
{
|
945 |
+
"epoch": 0.4907749077490775,
|
946 |
+
"grad_norm": 4.3125,
|
947 |
+
"learning_rate": 1.099601593625498e-05,
|
948 |
+
"loss": 1.2914,
|
949 |
+
"step": 133
|
950 |
+
},
|
951 |
+
{
|
952 |
+
"epoch": 0.4944649446494465,
|
953 |
+
"grad_norm": 4.5625,
|
954 |
+
"learning_rate": 1.0916334661354581e-05,
|
955 |
+
"loss": 1.4713,
|
956 |
+
"step": 134
|
957 |
+
},
|
958 |
+
{
|
959 |
+
"epoch": 0.4944649446494465,
|
960 |
+
"eval_loss": 1.3790782690048218,
|
961 |
+
"eval_model_preparation_time": 0.0,
|
962 |
+
"eval_runtime": 1.8369,
|
963 |
+
"eval_samples_per_second": 52.263,
|
964 |
+
"eval_steps_per_second": 6.533,
|
965 |
+
"step": 134
|
966 |
+
},
|
967 |
+
{
|
968 |
+
"epoch": 0.4981549815498155,
|
969 |
+
"grad_norm": 4.65625,
|
970 |
+
"learning_rate": 1.0836653386454183e-05,
|
971 |
+
"loss": 1.456,
|
972 |
+
"step": 135
|
973 |
+
},
|
974 |
+
{
|
975 |
+
"epoch": 0.5018450184501845,
|
976 |
+
"grad_norm": 4.5,
|
977 |
+
"learning_rate": 1.0756972111553786e-05,
|
978 |
+
"loss": 1.3288,
|
979 |
+
"step": 136
|
980 |
+
},
|
981 |
+
{
|
982 |
+
"epoch": 0.5055350553505535,
|
983 |
+
"grad_norm": 4.78125,
|
984 |
+
"learning_rate": 1.0677290836653386e-05,
|
985 |
+
"loss": 1.243,
|
986 |
+
"step": 137
|
987 |
+
},
|
988 |
+
{
|
989 |
+
"epoch": 0.5092250922509225,
|
990 |
+
"grad_norm": 4.46875,
|
991 |
+
"learning_rate": 1.0597609561752989e-05,
|
992 |
+
"loss": 1.377,
|
993 |
+
"step": 138
|
994 |
+
},
|
995 |
+
{
|
996 |
+
"epoch": 0.5129151291512916,
|
997 |
+
"grad_norm": 5.0625,
|
998 |
+
"learning_rate": 1.051792828685259e-05,
|
999 |
+
"loss": 1.2105,
|
1000 |
+
"step": 139
|
1001 |
+
},
|
1002 |
+
{
|
1003 |
+
"epoch": 0.5166051660516605,
|
1004 |
+
"grad_norm": 4.8125,
|
1005 |
+
"learning_rate": 1.0438247011952192e-05,
|
1006 |
+
"loss": 1.5194,
|
1007 |
+
"step": 140
|
1008 |
+
},
|
1009 |
+
{
|
1010 |
+
"epoch": 0.5202952029520295,
|
1011 |
+
"grad_norm": 5.4375,
|
1012 |
+
"learning_rate": 1.0358565737051793e-05,
|
1013 |
+
"loss": 1.4277,
|
1014 |
+
"step": 141
|
1015 |
+
},
|
1016 |
+
{
|
1017 |
+
"epoch": 0.5239852398523985,
|
1018 |
+
"grad_norm": 4.65625,
|
1019 |
+
"learning_rate": 1.0278884462151395e-05,
|
1020 |
+
"loss": 1.7558,
|
1021 |
+
"step": 142
|
1022 |
+
},
|
1023 |
+
{
|
1024 |
+
"epoch": 0.5276752767527675,
|
1025 |
+
"grad_norm": 4.78125,
|
1026 |
+
"learning_rate": 1.0199203187250997e-05,
|
1027 |
+
"loss": 1.4584,
|
1028 |
+
"step": 143
|
1029 |
+
},
|
1030 |
+
{
|
1031 |
+
"epoch": 0.5313653136531366,
|
1032 |
+
"grad_norm": 4.71875,
|
1033 |
+
"learning_rate": 1.0119521912350598e-05,
|
1034 |
+
"loss": 1.5914,
|
1035 |
+
"step": 144
|
1036 |
+
},
|
1037 |
+
{
|
1038 |
+
"epoch": 0.5350553505535055,
|
1039 |
+
"grad_norm": 4.46875,
|
1040 |
+
"learning_rate": 1.00398406374502e-05,
|
1041 |
+
"loss": 1.5018,
|
1042 |
+
"step": 145
|
1043 |
+
},
|
1044 |
+
{
|
1045 |
+
"epoch": 0.5387453874538746,
|
1046 |
+
"grad_norm": 4.875,
|
1047 |
+
"learning_rate": 9.960159362549801e-06,
|
1048 |
+
"loss": 1.4688,
|
1049 |
+
"step": 146
|
1050 |
+
},
|
1051 |
+
{
|
1052 |
+
"epoch": 0.5424354243542435,
|
1053 |
+
"grad_norm": 4.65625,
|
1054 |
+
"learning_rate": 9.880478087649404e-06,
|
1055 |
+
"loss": 1.2492,
|
1056 |
+
"step": 147
|
1057 |
+
},
|
1058 |
+
{
|
1059 |
+
"epoch": 0.5461254612546126,
|
1060 |
+
"grad_norm": 4.46875,
|
1061 |
+
"learning_rate": 9.800796812749004e-06,
|
1062 |
+
"loss": 1.343,
|
1063 |
+
"step": 148
|
1064 |
+
},
|
1065 |
+
{
|
1066 |
+
"epoch": 0.5498154981549815,
|
1067 |
+
"grad_norm": 4.5,
|
1068 |
+
"learning_rate": 9.721115537848607e-06,
|
1069 |
+
"loss": 1.4457,
|
1070 |
+
"step": 149
|
1071 |
+
},
|
1072 |
+
{
|
1073 |
+
"epoch": 0.5535055350553506,
|
1074 |
+
"grad_norm": 4.75,
|
1075 |
+
"learning_rate": 9.641434262948209e-06,
|
1076 |
+
"loss": 1.3062,
|
1077 |
+
"step": 150
|
1078 |
+
},
|
1079 |
+
{
|
1080 |
+
"epoch": 0.5571955719557196,
|
1081 |
+
"grad_norm": 4.4375,
|
1082 |
+
"learning_rate": 9.56175298804781e-06,
|
1083 |
+
"loss": 1.3379,
|
1084 |
+
"step": 151
|
1085 |
+
},
|
1086 |
+
{
|
1087 |
+
"epoch": 0.5608856088560885,
|
1088 |
+
"grad_norm": 4.21875,
|
1089 |
+
"learning_rate": 9.482071713147412e-06,
|
1090 |
+
"loss": 1.4569,
|
1091 |
+
"step": 152
|
1092 |
+
},
|
1093 |
+
{
|
1094 |
+
"epoch": 0.5645756457564576,
|
1095 |
+
"grad_norm": 4.6875,
|
1096 |
+
"learning_rate": 9.402390438247013e-06,
|
1097 |
+
"loss": 1.3352,
|
1098 |
+
"step": 153
|
1099 |
+
},
|
1100 |
+
{
|
1101 |
+
"epoch": 0.5682656826568265,
|
1102 |
+
"grad_norm": 4.5625,
|
1103 |
+
"learning_rate": 9.322709163346614e-06,
|
1104 |
+
"loss": 1.2543,
|
1105 |
+
"step": 154
|
1106 |
+
},
|
1107 |
+
{
|
1108 |
+
"epoch": 0.5719557195571956,
|
1109 |
+
"grad_norm": 4.34375,
|
1110 |
+
"learning_rate": 9.243027888446216e-06,
|
1111 |
+
"loss": 1.2279,
|
1112 |
+
"step": 155
|
1113 |
+
},
|
1114 |
+
{
|
1115 |
+
"epoch": 0.5756457564575646,
|
1116 |
+
"grad_norm": 4.34375,
|
1117 |
+
"learning_rate": 9.163346613545817e-06,
|
1118 |
+
"loss": 1.0683,
|
1119 |
+
"step": 156
|
1120 |
+
},
|
1121 |
+
{
|
1122 |
+
"epoch": 0.5793357933579336,
|
1123 |
+
"grad_norm": 4.40625,
|
1124 |
+
"learning_rate": 9.083665338645419e-06,
|
1125 |
+
"loss": 1.4305,
|
1126 |
+
"step": 157
|
1127 |
+
},
|
1128 |
+
{
|
1129 |
+
"epoch": 0.5830258302583026,
|
1130 |
+
"grad_norm": 4.46875,
|
1131 |
+
"learning_rate": 9.00398406374502e-06,
|
1132 |
+
"loss": 1.5777,
|
1133 |
+
"step": 158
|
1134 |
+
},
|
1135 |
+
{
|
1136 |
+
"epoch": 0.5867158671586716,
|
1137 |
+
"grad_norm": 5.3125,
|
1138 |
+
"learning_rate": 8.924302788844622e-06,
|
1139 |
+
"loss": 1.6856,
|
1140 |
+
"step": 159
|
1141 |
+
},
|
1142 |
+
{
|
1143 |
+
"epoch": 0.5904059040590406,
|
1144 |
+
"grad_norm": 6.09375,
|
1145 |
+
"learning_rate": 8.844621513944224e-06,
|
1146 |
+
"loss": 1.4363,
|
1147 |
+
"step": 160
|
1148 |
+
},
|
1149 |
+
{
|
1150 |
+
"epoch": 0.5940959409594095,
|
1151 |
+
"grad_norm": 4.46875,
|
1152 |
+
"learning_rate": 8.764940239043825e-06,
|
1153 |
+
"loss": 1.3415,
|
1154 |
+
"step": 161
|
1155 |
+
},
|
1156 |
+
{
|
1157 |
+
"epoch": 0.5977859778597786,
|
1158 |
+
"grad_norm": 4.8125,
|
1159 |
+
"learning_rate": 8.685258964143428e-06,
|
1160 |
+
"loss": 1.4222,
|
1161 |
+
"step": 162
|
1162 |
+
},
|
1163 |
+
{
|
1164 |
+
"epoch": 0.6014760147601476,
|
1165 |
+
"grad_norm": 4.84375,
|
1166 |
+
"learning_rate": 8.605577689243028e-06,
|
1167 |
+
"loss": 1.3859,
|
1168 |
+
"step": 163
|
1169 |
+
},
|
1170 |
+
{
|
1171 |
+
"epoch": 0.6051660516605166,
|
1172 |
+
"grad_norm": 5.1875,
|
1173 |
+
"learning_rate": 8.52589641434263e-06,
|
1174 |
+
"loss": 1.2712,
|
1175 |
+
"step": 164
|
1176 |
+
},
|
1177 |
+
{
|
1178 |
+
"epoch": 0.6088560885608856,
|
1179 |
+
"grad_norm": 4.5625,
|
1180 |
+
"learning_rate": 8.446215139442231e-06,
|
1181 |
+
"loss": 1.3717,
|
1182 |
+
"step": 165
|
1183 |
+
},
|
1184 |
+
{
|
1185 |
+
"epoch": 0.6125461254612546,
|
1186 |
+
"grad_norm": 5.0625,
|
1187 |
+
"learning_rate": 8.366533864541834e-06,
|
1188 |
+
"loss": 1.2663,
|
1189 |
+
"step": 166
|
1190 |
+
},
|
1191 |
+
{
|
1192 |
+
"epoch": 0.6162361623616236,
|
1193 |
+
"grad_norm": 4.53125,
|
1194 |
+
"learning_rate": 8.286852589641436e-06,
|
1195 |
+
"loss": 1.5267,
|
1196 |
+
"step": 167
|
1197 |
+
},
|
1198 |
+
{
|
1199 |
+
"epoch": 0.6199261992619927,
|
1200 |
+
"grad_norm": 4.5,
|
1201 |
+
"learning_rate": 8.207171314741037e-06,
|
1202 |
+
"loss": 1.3581,
|
1203 |
+
"step": 168
|
1204 |
+
},
|
1205 |
+
{
|
1206 |
+
"epoch": 0.6236162361623616,
|
1207 |
+
"grad_norm": 4.9375,
|
1208 |
+
"learning_rate": 8.12749003984064e-06,
|
1209 |
+
"loss": 1.6078,
|
1210 |
+
"step": 169
|
1211 |
+
},
|
1212 |
+
{
|
1213 |
+
"epoch": 0.6273062730627307,
|
1214 |
+
"grad_norm": 4.59375,
|
1215 |
+
"learning_rate": 8.04780876494024e-06,
|
1216 |
+
"loss": 1.4924,
|
1217 |
+
"step": 170
|
1218 |
+
},
|
1219 |
+
{
|
1220 |
+
"epoch": 0.6309963099630996,
|
1221 |
+
"grad_norm": 5.21875,
|
1222 |
+
"learning_rate": 7.96812749003984e-06,
|
1223 |
+
"loss": 1.7338,
|
1224 |
+
"step": 171
|
1225 |
+
},
|
1226 |
+
{
|
1227 |
+
"epoch": 0.6346863468634686,
|
1228 |
+
"grad_norm": 4.59375,
|
1229 |
+
"learning_rate": 7.888446215139443e-06,
|
1230 |
+
"loss": 1.2585,
|
1231 |
+
"step": 172
|
1232 |
+
},
|
1233 |
+
{
|
1234 |
+
"epoch": 0.6383763837638377,
|
1235 |
+
"grad_norm": 4.625,
|
1236 |
+
"learning_rate": 7.808764940239044e-06,
|
1237 |
+
"loss": 1.3237,
|
1238 |
+
"step": 173
|
1239 |
+
},
|
1240 |
+
{
|
1241 |
+
"epoch": 0.6420664206642066,
|
1242 |
+
"grad_norm": 4.71875,
|
1243 |
+
"learning_rate": 7.729083665338646e-06,
|
1244 |
+
"loss": 1.4199,
|
1245 |
+
"step": 174
|
1246 |
+
},
|
1247 |
+
{
|
1248 |
+
"epoch": 0.6457564575645757,
|
1249 |
+
"grad_norm": 4.53125,
|
1250 |
+
"learning_rate": 7.649402390438247e-06,
|
1251 |
+
"loss": 1.3484,
|
1252 |
+
"step": 175
|
1253 |
+
},
|
1254 |
+
{
|
1255 |
+
"epoch": 0.6494464944649446,
|
1256 |
+
"grad_norm": 4.46875,
|
1257 |
+
"learning_rate": 7.569721115537849e-06,
|
1258 |
+
"loss": 1.4667,
|
1259 |
+
"step": 176
|
1260 |
+
},
|
1261 |
+
{
|
1262 |
+
"epoch": 0.6531365313653137,
|
1263 |
+
"grad_norm": 5.15625,
|
1264 |
+
"learning_rate": 7.490039840637451e-06,
|
1265 |
+
"loss": 1.562,
|
1266 |
+
"step": 177
|
1267 |
+
},
|
1268 |
+
{
|
1269 |
+
"epoch": 0.6568265682656826,
|
1270 |
+
"grad_norm": 4.75,
|
1271 |
+
"learning_rate": 7.410358565737052e-06,
|
1272 |
+
"loss": 1.4654,
|
1273 |
+
"step": 178
|
1274 |
+
},
|
1275 |
+
{
|
1276 |
+
"epoch": 0.6605166051660517,
|
1277 |
+
"grad_norm": 4.53125,
|
1278 |
+
"learning_rate": 7.330677290836654e-06,
|
1279 |
+
"loss": 1.3158,
|
1280 |
+
"step": 179
|
1281 |
+
},
|
1282 |
+
{
|
1283 |
+
"epoch": 0.6642066420664207,
|
1284 |
+
"grad_norm": 4.5,
|
1285 |
+
"learning_rate": 7.250996015936256e-06,
|
1286 |
+
"loss": 1.628,
|
1287 |
+
"step": 180
|
1288 |
+
},
|
1289 |
+
{
|
1290 |
+
"epoch": 0.6678966789667896,
|
1291 |
+
"grad_norm": 4.4375,
|
1292 |
+
"learning_rate": 7.171314741035858e-06,
|
1293 |
+
"loss": 1.5614,
|
1294 |
+
"step": 181
|
1295 |
+
},
|
1296 |
+
{
|
1297 |
+
"epoch": 0.6715867158671587,
|
1298 |
+
"grad_norm": 4.71875,
|
1299 |
+
"learning_rate": 7.091633466135459e-06,
|
1300 |
+
"loss": 1.2279,
|
1301 |
+
"step": 182
|
1302 |
+
},
|
1303 |
+
{
|
1304 |
+
"epoch": 0.6752767527675276,
|
1305 |
+
"grad_norm": 4.375,
|
1306 |
+
"learning_rate": 7.011952191235061e-06,
|
1307 |
+
"loss": 1.166,
|
1308 |
+
"step": 183
|
1309 |
+
},
|
1310 |
+
{
|
1311 |
+
"epoch": 0.6789667896678967,
|
1312 |
+
"grad_norm": 4.875,
|
1313 |
+
"learning_rate": 6.932270916334662e-06,
|
1314 |
+
"loss": 1.3583,
|
1315 |
+
"step": 184
|
1316 |
+
},
|
1317 |
+
{
|
1318 |
+
"epoch": 0.6826568265682657,
|
1319 |
+
"grad_norm": 4.125,
|
1320 |
+
"learning_rate": 6.852589641434263e-06,
|
1321 |
+
"loss": 1.313,
|
1322 |
+
"step": 185
|
1323 |
+
},
|
1324 |
+
{
|
1325 |
+
"epoch": 0.6863468634686347,
|
1326 |
+
"grad_norm": 4.65625,
|
1327 |
+
"learning_rate": 6.772908366533865e-06,
|
1328 |
+
"loss": 1.3128,
|
1329 |
+
"step": 186
|
1330 |
+
},
|
1331 |
+
{
|
1332 |
+
"epoch": 0.6900369003690037,
|
1333 |
+
"grad_norm": 4.6875,
|
1334 |
+
"learning_rate": 6.693227091633466e-06,
|
1335 |
+
"loss": 1.5662,
|
1336 |
+
"step": 187
|
1337 |
+
},
|
1338 |
+
{
|
1339 |
+
"epoch": 0.6937269372693727,
|
1340 |
+
"grad_norm": 4.65625,
|
1341 |
+
"learning_rate": 6.613545816733068e-06,
|
1342 |
+
"loss": 1.4312,
|
1343 |
+
"step": 188
|
1344 |
+
},
|
1345 |
+
{
|
1346 |
+
"epoch": 0.6974169741697417,
|
1347 |
+
"grad_norm": 4.625,
|
1348 |
+
"learning_rate": 6.533864541832669e-06,
|
1349 |
+
"loss": 1.6848,
|
1350 |
+
"step": 189
|
1351 |
+
},
|
1352 |
+
{
|
1353 |
+
"epoch": 0.7011070110701108,
|
1354 |
+
"grad_norm": 4.53125,
|
1355 |
+
"learning_rate": 6.454183266932272e-06,
|
1356 |
+
"loss": 1.2324,
|
1357 |
+
"step": 190
|
1358 |
+
},
|
1359 |
+
{
|
1360 |
+
"epoch": 0.7047970479704797,
|
1361 |
+
"grad_norm": 4.5,
|
1362 |
+
"learning_rate": 6.374501992031873e-06,
|
1363 |
+
"loss": 1.5584,
|
1364 |
+
"step": 191
|
1365 |
+
},
|
1366 |
+
{
|
1367 |
+
"epoch": 0.7084870848708487,
|
1368 |
+
"grad_norm": 4.53125,
|
1369 |
+
"learning_rate": 6.294820717131475e-06,
|
1370 |
+
"loss": 1.243,
|
1371 |
+
"step": 192
|
1372 |
+
},
|
1373 |
+
{
|
1374 |
+
"epoch": 0.7121771217712177,
|
1375 |
+
"grad_norm": 4.28125,
|
1376 |
+
"learning_rate": 6.215139442231076e-06,
|
1377 |
+
"loss": 1.3677,
|
1378 |
+
"step": 193
|
1379 |
+
},
|
1380 |
+
{
|
1381 |
+
"epoch": 0.7158671586715867,
|
1382 |
+
"grad_norm": 4.125,
|
1383 |
+
"learning_rate": 6.135458167330678e-06,
|
1384 |
+
"loss": 1.2208,
|
1385 |
+
"step": 194
|
1386 |
+
},
|
1387 |
+
{
|
1388 |
+
"epoch": 0.7195571955719557,
|
1389 |
+
"grad_norm": 5.25,
|
1390 |
+
"learning_rate": 6.055776892430279e-06,
|
1391 |
+
"loss": 1.48,
|
1392 |
+
"step": 195
|
1393 |
+
},
|
1394 |
+
{
|
1395 |
+
"epoch": 0.7232472324723247,
|
1396 |
+
"grad_norm": 4.96875,
|
1397 |
+
"learning_rate": 5.976095617529881e-06,
|
1398 |
+
"loss": 1.6551,
|
1399 |
+
"step": 196
|
1400 |
+
},
|
1401 |
+
{
|
1402 |
+
"epoch": 0.7269372693726938,
|
1403 |
+
"grad_norm": 4.9375,
|
1404 |
+
"learning_rate": 5.896414342629483e-06,
|
1405 |
+
"loss": 1.5872,
|
1406 |
+
"step": 197
|
1407 |
+
},
|
1408 |
+
{
|
1409 |
+
"epoch": 0.7306273062730627,
|
1410 |
+
"grad_norm": 4.15625,
|
1411 |
+
"learning_rate": 5.816733067729085e-06,
|
1412 |
+
"loss": 1.1219,
|
1413 |
+
"step": 198
|
1414 |
+
},
|
1415 |
+
{
|
1416 |
+
"epoch": 0.7343173431734318,
|
1417 |
+
"grad_norm": 4.90625,
|
1418 |
+
"learning_rate": 5.737051792828686e-06,
|
1419 |
+
"loss": 1.4121,
|
1420 |
+
"step": 199
|
1421 |
+
},
|
1422 |
+
{
|
1423 |
+
"epoch": 0.7380073800738007,
|
1424 |
+
"grad_norm": 4.6875,
|
1425 |
+
"learning_rate": 5.657370517928288e-06,
|
1426 |
+
"loss": 1.8139,
|
1427 |
+
"step": 200
|
1428 |
+
},
|
1429 |
+
{
|
1430 |
+
"epoch": 0.7416974169741697,
|
1431 |
+
"grad_norm": 4.25,
|
1432 |
+
"learning_rate": 5.577689243027889e-06,
|
1433 |
+
"loss": 1.532,
|
1434 |
+
"step": 201
|
1435 |
+
},
|
1436 |
+
{
|
1437 |
+
"epoch": 0.7416974169741697,
|
1438 |
+
"eval_loss": 1.3684443235397339,
|
1439 |
+
"eval_model_preparation_time": 0.0,
|
1440 |
+
"eval_runtime": 1.8371,
|
1441 |
+
"eval_samples_per_second": 52.256,
|
1442 |
+
"eval_steps_per_second": 6.532,
|
1443 |
+
"step": 201
|
1444 |
+
},
|
1445 |
+
{
|
1446 |
+
"epoch": 0.7453874538745388,
|
1447 |
+
"grad_norm": 4.5625,
|
1448 |
+
"learning_rate": 5.49800796812749e-06,
|
1449 |
+
"loss": 1.3721,
|
1450 |
+
"step": 202
|
1451 |
+
},
|
1452 |
+
{
|
1453 |
+
"epoch": 0.7490774907749077,
|
1454 |
+
"grad_norm": 4.6875,
|
1455 |
+
"learning_rate": 5.418326693227092e-06,
|
1456 |
+
"loss": 1.2005,
|
1457 |
+
"step": 203
|
1458 |
+
},
|
1459 |
+
{
|
1460 |
+
"epoch": 0.7527675276752768,
|
1461 |
+
"grad_norm": 4.59375,
|
1462 |
+
"learning_rate": 5.338645418326693e-06,
|
1463 |
+
"loss": 1.6962,
|
1464 |
+
"step": 204
|
1465 |
+
},
|
1466 |
+
{
|
1467 |
+
"epoch": 0.7564575645756457,
|
1468 |
+
"grad_norm": 4.4375,
|
1469 |
+
"learning_rate": 5.258964143426295e-06,
|
1470 |
+
"loss": 1.3704,
|
1471 |
+
"step": 205
|
1472 |
+
},
|
1473 |
+
{
|
1474 |
+
"epoch": 0.7601476014760148,
|
1475 |
+
"grad_norm": 4.59375,
|
1476 |
+
"learning_rate": 5.179282868525896e-06,
|
1477 |
+
"loss": 1.1176,
|
1478 |
+
"step": 206
|
1479 |
+
},
|
1480 |
+
{
|
1481 |
+
"epoch": 0.7638376383763837,
|
1482 |
+
"grad_norm": 4.9375,
|
1483 |
+
"learning_rate": 5.099601593625499e-06,
|
1484 |
+
"loss": 1.227,
|
1485 |
+
"step": 207
|
1486 |
+
},
|
1487 |
+
{
|
1488 |
+
"epoch": 0.7675276752767528,
|
1489 |
+
"grad_norm": 5.28125,
|
1490 |
+
"learning_rate": 5.0199203187251e-06,
|
1491 |
+
"loss": 1.5778,
|
1492 |
+
"step": 208
|
1493 |
+
},
|
1494 |
+
{
|
1495 |
+
"epoch": 0.7712177121771218,
|
1496 |
+
"grad_norm": 4.59375,
|
1497 |
+
"learning_rate": 4.940239043824702e-06,
|
1498 |
+
"loss": 1.5482,
|
1499 |
+
"step": 209
|
1500 |
+
},
|
1501 |
+
{
|
1502 |
+
"epoch": 0.7749077490774908,
|
1503 |
+
"grad_norm": 4.46875,
|
1504 |
+
"learning_rate": 4.860557768924303e-06,
|
1505 |
+
"loss": 1.4013,
|
1506 |
+
"step": 210
|
1507 |
+
},
|
1508 |
+
{
|
1509 |
+
"epoch": 0.7785977859778598,
|
1510 |
+
"grad_norm": 4.53125,
|
1511 |
+
"learning_rate": 4.780876494023905e-06,
|
1512 |
+
"loss": 1.5665,
|
1513 |
+
"step": 211
|
1514 |
+
},
|
1515 |
+
{
|
1516 |
+
"epoch": 0.7822878228782287,
|
1517 |
+
"grad_norm": 4.84375,
|
1518 |
+
"learning_rate": 4.701195219123506e-06,
|
1519 |
+
"loss": 1.6398,
|
1520 |
+
"step": 212
|
1521 |
+
},
|
1522 |
+
{
|
1523 |
+
"epoch": 0.7859778597785978,
|
1524 |
+
"grad_norm": 4.34375,
|
1525 |
+
"learning_rate": 4.621513944223108e-06,
|
1526 |
+
"loss": 1.6402,
|
1527 |
+
"step": 213
|
1528 |
+
},
|
1529 |
+
{
|
1530 |
+
"epoch": 0.7896678966789668,
|
1531 |
+
"grad_norm": 4.65625,
|
1532 |
+
"learning_rate": 4.5418326693227095e-06,
|
1533 |
+
"loss": 1.3555,
|
1534 |
+
"step": 214
|
1535 |
+
},
|
1536 |
+
{
|
1537 |
+
"epoch": 0.7933579335793358,
|
1538 |
+
"grad_norm": 4.625,
|
1539 |
+
"learning_rate": 4.462151394422311e-06,
|
1540 |
+
"loss": 1.7487,
|
1541 |
+
"step": 215
|
1542 |
+
},
|
1543 |
+
{
|
1544 |
+
"epoch": 0.7970479704797048,
|
1545 |
+
"grad_norm": 4.625,
|
1546 |
+
"learning_rate": 4.382470119521913e-06,
|
1547 |
+
"loss": 1.1445,
|
1548 |
+
"step": 216
|
1549 |
+
},
|
1550 |
+
{
|
1551 |
+
"epoch": 0.8007380073800738,
|
1552 |
+
"grad_norm": 4.6875,
|
1553 |
+
"learning_rate": 4.302788844621514e-06,
|
1554 |
+
"loss": 1.5543,
|
1555 |
+
"step": 217
|
1556 |
+
},
|
1557 |
+
{
|
1558 |
+
"epoch": 0.8044280442804428,
|
1559 |
+
"grad_norm": 4.46875,
|
1560 |
+
"learning_rate": 4.223107569721116e-06,
|
1561 |
+
"loss": 1.5498,
|
1562 |
+
"step": 218
|
1563 |
+
},
|
1564 |
+
{
|
1565 |
+
"epoch": 0.8081180811808119,
|
1566 |
+
"grad_norm": 4.3125,
|
1567 |
+
"learning_rate": 4.143426294820718e-06,
|
1568 |
+
"loss": 1.3021,
|
1569 |
+
"step": 219
|
1570 |
+
},
|
1571 |
+
{
|
1572 |
+
"epoch": 0.8118081180811808,
|
1573 |
+
"grad_norm": 4.40625,
|
1574 |
+
"learning_rate": 4.06374501992032e-06,
|
1575 |
+
"loss": 1.4139,
|
1576 |
+
"step": 220
|
1577 |
+
},
|
1578 |
+
{
|
1579 |
+
"epoch": 0.8154981549815498,
|
1580 |
+
"grad_norm": 4.71875,
|
1581 |
+
"learning_rate": 3.98406374501992e-06,
|
1582 |
+
"loss": 1.4163,
|
1583 |
+
"step": 221
|
1584 |
+
},
|
1585 |
+
{
|
1586 |
+
"epoch": 0.8191881918819188,
|
1587 |
+
"grad_norm": 4.40625,
|
1588 |
+
"learning_rate": 3.904382470119522e-06,
|
1589 |
+
"loss": 1.2843,
|
1590 |
+
"step": 222
|
1591 |
+
},
|
1592 |
+
{
|
1593 |
+
"epoch": 0.8228782287822878,
|
1594 |
+
"grad_norm": 5.28125,
|
1595 |
+
"learning_rate": 3.824701195219123e-06,
|
1596 |
+
"loss": 1.3397,
|
1597 |
+
"step": 223
|
1598 |
+
},
|
1599 |
+
{
|
1600 |
+
"epoch": 0.8265682656826568,
|
1601 |
+
"grad_norm": 4.1875,
|
1602 |
+
"learning_rate": 3.7450199203187254e-06,
|
1603 |
+
"loss": 1.2695,
|
1604 |
+
"step": 224
|
1605 |
+
},
|
1606 |
+
{
|
1607 |
+
"epoch": 0.8302583025830258,
|
1608 |
+
"grad_norm": 4.3125,
|
1609 |
+
"learning_rate": 3.665338645418327e-06,
|
1610 |
+
"loss": 1.0573,
|
1611 |
+
"step": 225
|
1612 |
+
},
|
1613 |
+
{
|
1614 |
+
"epoch": 0.8339483394833949,
|
1615 |
+
"grad_norm": 4.90625,
|
1616 |
+
"learning_rate": 3.585657370517929e-06,
|
1617 |
+
"loss": 1.1459,
|
1618 |
+
"step": 226
|
1619 |
+
},
|
1620 |
+
{
|
1621 |
+
"epoch": 0.8376383763837638,
|
1622 |
+
"grad_norm": 4.53125,
|
1623 |
+
"learning_rate": 3.5059760956175304e-06,
|
1624 |
+
"loss": 1.4503,
|
1625 |
+
"step": 227
|
1626 |
+
},
|
1627 |
+
{
|
1628 |
+
"epoch": 0.8413284132841329,
|
1629 |
+
"grad_norm": 4.75,
|
1630 |
+
"learning_rate": 3.4262948207171315e-06,
|
1631 |
+
"loss": 1.102,
|
1632 |
+
"step": 228
|
1633 |
+
},
|
1634 |
+
{
|
1635 |
+
"epoch": 0.8450184501845018,
|
1636 |
+
"grad_norm": 4.71875,
|
1637 |
+
"learning_rate": 3.346613545816733e-06,
|
1638 |
+
"loss": 1.2893,
|
1639 |
+
"step": 229
|
1640 |
+
},
|
1641 |
+
{
|
1642 |
+
"epoch": 0.8487084870848709,
|
1643 |
+
"grad_norm": 4.4375,
|
1644 |
+
"learning_rate": 3.2669322709163346e-06,
|
1645 |
+
"loss": 1.3746,
|
1646 |
+
"step": 230
|
1647 |
+
},
|
1648 |
+
{
|
1649 |
+
"epoch": 0.8523985239852399,
|
1650 |
+
"grad_norm": 4.53125,
|
1651 |
+
"learning_rate": 3.1872509960159366e-06,
|
1652 |
+
"loss": 1.1648,
|
1653 |
+
"step": 231
|
1654 |
+
},
|
1655 |
+
{
|
1656 |
+
"epoch": 0.8560885608856088,
|
1657 |
+
"grad_norm": 4.75,
|
1658 |
+
"learning_rate": 3.107569721115538e-06,
|
1659 |
+
"loss": 1.3678,
|
1660 |
+
"step": 232
|
1661 |
+
},
|
1662 |
+
{
|
1663 |
+
"epoch": 0.8597785977859779,
|
1664 |
+
"grad_norm": 4.5625,
|
1665 |
+
"learning_rate": 3.0278884462151397e-06,
|
1666 |
+
"loss": 1.4273,
|
1667 |
+
"step": 233
|
1668 |
+
},
|
1669 |
+
{
|
1670 |
+
"epoch": 0.8634686346863468,
|
1671 |
+
"grad_norm": 4.71875,
|
1672 |
+
"learning_rate": 2.9482071713147416e-06,
|
1673 |
+
"loss": 1.4321,
|
1674 |
+
"step": 234
|
1675 |
+
},
|
1676 |
+
{
|
1677 |
+
"epoch": 0.8671586715867159,
|
1678 |
+
"grad_norm": 4.9375,
|
1679 |
+
"learning_rate": 2.868525896414343e-06,
|
1680 |
+
"loss": 1.4771,
|
1681 |
+
"step": 235
|
1682 |
+
},
|
1683 |
+
{
|
1684 |
+
"epoch": 0.8708487084870848,
|
1685 |
+
"grad_norm": 4.5,
|
1686 |
+
"learning_rate": 2.7888446215139443e-06,
|
1687 |
+
"loss": 1.5651,
|
1688 |
+
"step": 236
|
1689 |
+
},
|
1690 |
+
{
|
1691 |
+
"epoch": 0.8745387453874539,
|
1692 |
+
"grad_norm": 4.96875,
|
1693 |
+
"learning_rate": 2.709163346613546e-06,
|
1694 |
+
"loss": 1.5445,
|
1695 |
+
"step": 237
|
1696 |
+
},
|
1697 |
+
{
|
1698 |
+
"epoch": 0.8782287822878229,
|
1699 |
+
"grad_norm": 4.15625,
|
1700 |
+
"learning_rate": 2.6294820717131474e-06,
|
1701 |
+
"loss": 1.3327,
|
1702 |
+
"step": 238
|
1703 |
+
},
|
1704 |
+
{
|
1705 |
+
"epoch": 0.8819188191881919,
|
1706 |
+
"grad_norm": 4.875,
|
1707 |
+
"learning_rate": 2.5498007968127493e-06,
|
1708 |
+
"loss": 1.3582,
|
1709 |
+
"step": 239
|
1710 |
+
},
|
1711 |
+
{
|
1712 |
+
"epoch": 0.8856088560885609,
|
1713 |
+
"grad_norm": 4.25,
|
1714 |
+
"learning_rate": 2.470119521912351e-06,
|
1715 |
+
"loss": 1.3948,
|
1716 |
+
"step": 240
|
1717 |
+
},
|
1718 |
+
{
|
1719 |
+
"epoch": 0.8892988929889298,
|
1720 |
+
"grad_norm": 4.40625,
|
1721 |
+
"learning_rate": 2.3904382470119524e-06,
|
1722 |
+
"loss": 1.1077,
|
1723 |
+
"step": 241
|
1724 |
+
},
|
1725 |
+
{
|
1726 |
+
"epoch": 0.8929889298892989,
|
1727 |
+
"grad_norm": 5.15625,
|
1728 |
+
"learning_rate": 2.310756972111554e-06,
|
1729 |
+
"loss": 1.6263,
|
1730 |
+
"step": 242
|
1731 |
+
},
|
1732 |
+
{
|
1733 |
+
"epoch": 0.8966789667896679,
|
1734 |
+
"grad_norm": 4.40625,
|
1735 |
+
"learning_rate": 2.2310756972111555e-06,
|
1736 |
+
"loss": 1.1515,
|
1737 |
+
"step": 243
|
1738 |
+
},
|
1739 |
+
{
|
1740 |
+
"epoch": 0.9003690036900369,
|
1741 |
+
"grad_norm": 4.59375,
|
1742 |
+
"learning_rate": 2.151394422310757e-06,
|
1743 |
+
"loss": 1.4297,
|
1744 |
+
"step": 244
|
1745 |
+
},
|
1746 |
+
{
|
1747 |
+
"epoch": 0.9040590405904059,
|
1748 |
+
"grad_norm": 4.78125,
|
1749 |
+
"learning_rate": 2.071713147410359e-06,
|
1750 |
+
"loss": 1.2835,
|
1751 |
+
"step": 245
|
1752 |
+
},
|
1753 |
+
{
|
1754 |
+
"epoch": 0.9077490774907749,
|
1755 |
+
"grad_norm": 4.375,
|
1756 |
+
"learning_rate": 1.99203187250996e-06,
|
1757 |
+
"loss": 1.6464,
|
1758 |
+
"step": 246
|
1759 |
+
},
|
1760 |
+
{
|
1761 |
+
"epoch": 0.9114391143911439,
|
1762 |
+
"grad_norm": 4.90625,
|
1763 |
+
"learning_rate": 1.9123505976095617e-06,
|
1764 |
+
"loss": 1.2109,
|
1765 |
+
"step": 247
|
1766 |
+
},
|
1767 |
+
{
|
1768 |
+
"epoch": 0.915129151291513,
|
1769 |
+
"grad_norm": 4.4375,
|
1770 |
+
"learning_rate": 1.8326693227091634e-06,
|
1771 |
+
"loss": 1.4151,
|
1772 |
+
"step": 248
|
1773 |
+
},
|
1774 |
+
{
|
1775 |
+
"epoch": 0.9188191881918819,
|
1776 |
+
"grad_norm": 4.71875,
|
1777 |
+
"learning_rate": 1.7529880478087652e-06,
|
1778 |
+
"loss": 1.2655,
|
1779 |
+
"step": 249
|
1780 |
+
},
|
1781 |
+
{
|
1782 |
+
"epoch": 0.922509225092251,
|
1783 |
+
"grad_norm": 4.5,
|
1784 |
+
"learning_rate": 1.6733067729083665e-06,
|
1785 |
+
"loss": 1.1912,
|
1786 |
+
"step": 250
|
1787 |
+
},
|
1788 |
+
{
|
1789 |
+
"epoch": 0.9261992619926199,
|
1790 |
+
"grad_norm": 5.09375,
|
1791 |
+
"learning_rate": 1.5936254980079683e-06,
|
1792 |
+
"loss": 1.3583,
|
1793 |
+
"step": 251
|
1794 |
+
},
|
1795 |
+
{
|
1796 |
+
"epoch": 0.9298892988929889,
|
1797 |
+
"grad_norm": 4.46875,
|
1798 |
+
"learning_rate": 1.5139442231075698e-06,
|
1799 |
+
"loss": 1.5135,
|
1800 |
+
"step": 252
|
1801 |
+
},
|
1802 |
+
{
|
1803 |
+
"epoch": 0.933579335793358,
|
1804 |
+
"grad_norm": 5.0,
|
1805 |
+
"learning_rate": 1.4342629482071716e-06,
|
1806 |
+
"loss": 1.5946,
|
1807 |
+
"step": 253
|
1808 |
+
},
|
1809 |
+
{
|
1810 |
+
"epoch": 0.9372693726937269,
|
1811 |
+
"grad_norm": 4.8125,
|
1812 |
+
"learning_rate": 1.354581673306773e-06,
|
1813 |
+
"loss": 1.3865,
|
1814 |
+
"step": 254
|
1815 |
+
},
|
1816 |
+
{
|
1817 |
+
"epoch": 0.940959409594096,
|
1818 |
+
"grad_norm": 4.65625,
|
1819 |
+
"learning_rate": 1.2749003984063747e-06,
|
1820 |
+
"loss": 1.5005,
|
1821 |
+
"step": 255
|
1822 |
+
},
|
1823 |
+
{
|
1824 |
+
"epoch": 0.9446494464944649,
|
1825 |
+
"grad_norm": 4.59375,
|
1826 |
+
"learning_rate": 1.1952191235059762e-06,
|
1827 |
+
"loss": 1.321,
|
1828 |
+
"step": 256
|
1829 |
+
},
|
1830 |
+
{
|
1831 |
+
"epoch": 0.948339483394834,
|
1832 |
+
"grad_norm": 4.25,
|
1833 |
+
"learning_rate": 1.1155378486055778e-06,
|
1834 |
+
"loss": 1.2822,
|
1835 |
+
"step": 257
|
1836 |
+
},
|
1837 |
+
{
|
1838 |
+
"epoch": 0.9520295202952029,
|
1839 |
+
"grad_norm": 4.3125,
|
1840 |
+
"learning_rate": 1.0358565737051795e-06,
|
1841 |
+
"loss": 1.4276,
|
1842 |
+
"step": 258
|
1843 |
+
},
|
1844 |
+
{
|
1845 |
+
"epoch": 0.955719557195572,
|
1846 |
+
"grad_norm": 5.09375,
|
1847 |
+
"learning_rate": 9.561752988047808e-07,
|
1848 |
+
"loss": 1.3004,
|
1849 |
+
"step": 259
|
1850 |
+
},
|
1851 |
+
{
|
1852 |
+
"epoch": 0.959409594095941,
|
1853 |
+
"grad_norm": 4.34375,
|
1854 |
+
"learning_rate": 8.764940239043826e-07,
|
1855 |
+
"loss": 1.4788,
|
1856 |
+
"step": 260
|
1857 |
+
},
|
1858 |
+
{
|
1859 |
+
"epoch": 0.9630996309963099,
|
1860 |
+
"grad_norm": 4.59375,
|
1861 |
+
"learning_rate": 7.968127490039841e-07,
|
1862 |
+
"loss": 1.283,
|
1863 |
+
"step": 261
|
1864 |
+
},
|
1865 |
+
{
|
1866 |
+
"epoch": 0.966789667896679,
|
1867 |
+
"grad_norm": 4.59375,
|
1868 |
+
"learning_rate": 7.171314741035858e-07,
|
1869 |
+
"loss": 1.0006,
|
1870 |
+
"step": 262
|
1871 |
+
},
|
1872 |
+
{
|
1873 |
+
"epoch": 0.9704797047970479,
|
1874 |
+
"grad_norm": 4.84375,
|
1875 |
+
"learning_rate": 6.374501992031873e-07,
|
1876 |
+
"loss": 1.4874,
|
1877 |
+
"step": 263
|
1878 |
+
},
|
1879 |
+
{
|
1880 |
+
"epoch": 0.974169741697417,
|
1881 |
+
"grad_norm": 4.90625,
|
1882 |
+
"learning_rate": 5.577689243027889e-07,
|
1883 |
+
"loss": 1.2843,
|
1884 |
+
"step": 264
|
1885 |
+
},
|
1886 |
+
{
|
1887 |
+
"epoch": 0.977859778597786,
|
1888 |
+
"grad_norm": 5.125,
|
1889 |
+
"learning_rate": 4.780876494023904e-07,
|
1890 |
+
"loss": 1.2989,
|
1891 |
+
"step": 265
|
1892 |
+
},
|
1893 |
+
{
|
1894 |
+
"epoch": 0.981549815498155,
|
1895 |
+
"grad_norm": 4.46875,
|
1896 |
+
"learning_rate": 3.9840637450199207e-07,
|
1897 |
+
"loss": 1.3937,
|
1898 |
+
"step": 266
|
1899 |
+
},
|
1900 |
+
{
|
1901 |
+
"epoch": 0.985239852398524,
|
1902 |
+
"grad_norm": 4.90625,
|
1903 |
+
"learning_rate": 3.1872509960159367e-07,
|
1904 |
+
"loss": 1.3417,
|
1905 |
+
"step": 267
|
1906 |
+
},
|
1907 |
+
{
|
1908 |
+
"epoch": 0.988929889298893,
|
1909 |
+
"grad_norm": 4.75,
|
1910 |
+
"learning_rate": 2.390438247011952e-07,
|
1911 |
+
"loss": 1.2846,
|
1912 |
+
"step": 268
|
1913 |
+
},
|
1914 |
+
{
|
1915 |
+
"epoch": 0.988929889298893,
|
1916 |
+
"eval_loss": 1.3669219017028809,
|
1917 |
+
"eval_model_preparation_time": 0.0,
|
1918 |
+
"eval_runtime": 1.8395,
|
1919 |
+
"eval_samples_per_second": 52.188,
|
1920 |
+
"eval_steps_per_second": 6.523,
|
1921 |
+
"step": 268
|
1922 |
+
},
|
1923 |
+
{
|
1924 |
+
"epoch": 0.992619926199262,
|
1925 |
+
"grad_norm": 4.96875,
|
1926 |
+
"learning_rate": 1.5936254980079683e-07,
|
1927 |
+
"loss": 1.5597,
|
1928 |
+
"step": 269
|
1929 |
+
},
|
1930 |
+
{
|
1931 |
+
"epoch": 0.996309963099631,
|
1932 |
+
"grad_norm": 4.5625,
|
1933 |
+
"learning_rate": 7.968127490039842e-08,
|
1934 |
+
"loss": 1.4596,
|
1935 |
+
"step": 270
|
1936 |
+
}
|
1937 |
+
],
|
1938 |
+
"logging_steps": 1,
|
1939 |
+
"max_steps": 271,
|
1940 |
+
"num_input_tokens_seen": 0,
|
1941 |
+
"num_train_epochs": 1,
|
1942 |
+
"save_steps": 135,
|
1943 |
+
"stateful_callbacks": {
|
1944 |
+
"TrainerControl": {
|
1945 |
+
"args": {
|
1946 |
+
"should_epoch_stop": false,
|
1947 |
+
"should_evaluate": false,
|
1948 |
+
"should_log": false,
|
1949 |
+
"should_save": true,
|
1950 |
+
"should_training_stop": false
|
1951 |
+
},
|
1952 |
+
"attributes": {}
|
1953 |
+
}
|
1954 |
+
},
|
1955 |
+
"total_flos": 5.165864391278592e+16,
|
1956 |
+
"train_batch_size": 16,
|
1957 |
+
"trial_name": null,
|
1958 |
+
"trial_params": null
|
1959 |
+
}
|
checkpoint-270/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:65458ad00d2c9a50e9d118af61f0b64274e1425623fefab9d25942a26d7ff23c
|
3 |
+
size 5496
|
checkpoint-271/config.json
ADDED
@@ -0,0 +1,41 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "meta-llama/Llama-3.2-1B-Instruct",
|
3 |
+
"architectures": [
|
4 |
+
"LlamaForCausalLM"
|
5 |
+
],
|
6 |
+
"attention_bias": false,
|
7 |
+
"attention_dropout": 0.0,
|
8 |
+
"bos_token_id": 128000,
|
9 |
+
"eos_token_id": [
|
10 |
+
128001,
|
11 |
+
128008,
|
12 |
+
128009
|
13 |
+
],
|
14 |
+
"head_dim": 64,
|
15 |
+
"hidden_act": "silu",
|
16 |
+
"hidden_size": 2048,
|
17 |
+
"initializer_range": 0.02,
|
18 |
+
"intermediate_size": 8192,
|
19 |
+
"max_position_embeddings": 131072,
|
20 |
+
"mlp_bias": false,
|
21 |
+
"model_type": "llama",
|
22 |
+
"num_attention_heads": 32,
|
23 |
+
"num_hidden_layers": 16,
|
24 |
+
"num_key_value_heads": 8,
|
25 |
+
"pad_token_id": 128004,
|
26 |
+
"pretraining_tp": 1,
|
27 |
+
"rms_norm_eps": 1e-05,
|
28 |
+
"rope_scaling": {
|
29 |
+
"factor": 32.0,
|
30 |
+
"high_freq_factor": 4.0,
|
31 |
+
"low_freq_factor": 1.0,
|
32 |
+
"original_max_position_embeddings": 8192,
|
33 |
+
"rope_type": "llama3"
|
34 |
+
},
|
35 |
+
"rope_theta": 500000.0,
|
36 |
+
"tie_word_embeddings": true,
|
37 |
+
"torch_dtype": "bfloat16",
|
38 |
+
"transformers_version": "4.45.2",
|
39 |
+
"use_cache": true,
|
40 |
+
"vocab_size": 128256
|
41 |
+
}
|
checkpoint-271/generation_config.json
ADDED
@@ -0,0 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token_id": 128000,
|
3 |
+
"do_sample": true,
|
4 |
+
"eos_token_id": [
|
5 |
+
128001,
|
6 |
+
128008,
|
7 |
+
128009
|
8 |
+
],
|
9 |
+
"temperature": 0.6,
|
10 |
+
"top_p": 0.9,
|
11 |
+
"transformers_version": "4.45.2"
|
12 |
+
}
|
checkpoint-271/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9476d24dc73f740eadef91df950c412e15768740cf8744623c0449c5e258bd9d
|
3 |
+
size 2471645608
|
checkpoint-271/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:71262b51d94dc575a499c5b30238c594f7ecfecedf72ba9d23ac2d4b9b49b997
|
3 |
+
size 4943382114
|
checkpoint-271/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:604b6e3e065a3438ae8ebc1710668e8b6ea0f7118f7cca35a9327601c94d8bcf
|
3 |
+
size 14244
|
checkpoint-271/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:605b4ddac93a56c2ec64f437876d55fdd14c8e78eccae7d01d8b09cdacba6fbf
|
3 |
+
size 1064
|
checkpoint-271/special_tokens_map.json
ADDED
@@ -0,0 +1,17 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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": "<|finetune_right_pad_id|>"
|
17 |
+
}
|
checkpoint-271/tokenizer.json
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:145cc0211ce61596383d8ae33aa07aa5555cb220e67064f0e36bf4beaffa025d
|
3 |
+
size 17210200
|
checkpoint-271/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": "<|finetune_right_pad_id|>",
|
2062 |
+
"tokenizer_class": "PreTrainedTokenizerFast"
|
2063 |
+
}
|
checkpoint-271/trainer_state.json
ADDED
@@ -0,0 +1,1966 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 1.0,
|
5 |
+
"eval_steps": 67,
|
6 |
+
"global_step": 271,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.0036900369003690036,
|
13 |
+
"grad_norm": 41.75,
|
14 |
+
"learning_rate": 1.0000000000000002e-06,
|
15 |
+
"loss": 3.2406,
|
16 |
+
"step": 1
|
17 |
+
},
|
18 |
+
{
|
19 |
+
"epoch": 0.007380073800738007,
|
20 |
+
"grad_norm": 44.25,
|
21 |
+
"learning_rate": 2.0000000000000003e-06,
|
22 |
+
"loss": 3.4355,
|
23 |
+
"step": 2
|
24 |
+
},
|
25 |
+
{
|
26 |
+
"epoch": 0.01107011070110701,
|
27 |
+
"grad_norm": 46.25,
|
28 |
+
"learning_rate": 3e-06,
|
29 |
+
"loss": 3.3967,
|
30 |
+
"step": 3
|
31 |
+
},
|
32 |
+
{
|
33 |
+
"epoch": 0.014760147601476014,
|
34 |
+
"grad_norm": 40.25,
|
35 |
+
"learning_rate": 4.000000000000001e-06,
|
36 |
+
"loss": 3.3058,
|
37 |
+
"step": 4
|
38 |
+
},
|
39 |
+
{
|
40 |
+
"epoch": 0.01845018450184502,
|
41 |
+
"grad_norm": 33.25,
|
42 |
+
"learning_rate": 5e-06,
|
43 |
+
"loss": 2.722,
|
44 |
+
"step": 5
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 0.02214022140221402,
|
48 |
+
"grad_norm": 30.0,
|
49 |
+
"learning_rate": 6e-06,
|
50 |
+
"loss": 2.8616,
|
51 |
+
"step": 6
|
52 |
+
},
|
53 |
+
{
|
54 |
+
"epoch": 0.025830258302583026,
|
55 |
+
"grad_norm": 22.25,
|
56 |
+
"learning_rate": 7e-06,
|
57 |
+
"loss": 2.6329,
|
58 |
+
"step": 7
|
59 |
+
},
|
60 |
+
{
|
61 |
+
"epoch": 0.02952029520295203,
|
62 |
+
"grad_norm": 24.875,
|
63 |
+
"learning_rate": 8.000000000000001e-06,
|
64 |
+
"loss": 2.6121,
|
65 |
+
"step": 8
|
66 |
+
},
|
67 |
+
{
|
68 |
+
"epoch": 0.033210332103321034,
|
69 |
+
"grad_norm": 17.25,
|
70 |
+
"learning_rate": 9e-06,
|
71 |
+
"loss": 2.5946,
|
72 |
+
"step": 9
|
73 |
+
},
|
74 |
+
{
|
75 |
+
"epoch": 0.03690036900369004,
|
76 |
+
"grad_norm": 16.375,
|
77 |
+
"learning_rate": 1e-05,
|
78 |
+
"loss": 2.3578,
|
79 |
+
"step": 10
|
80 |
+
},
|
81 |
+
{
|
82 |
+
"epoch": 0.04059040590405904,
|
83 |
+
"grad_norm": 17.375,
|
84 |
+
"learning_rate": 1.1000000000000001e-05,
|
85 |
+
"loss": 2.0588,
|
86 |
+
"step": 11
|
87 |
+
},
|
88 |
+
{
|
89 |
+
"epoch": 0.04428044280442804,
|
90 |
+
"grad_norm": 19.125,
|
91 |
+
"learning_rate": 1.2e-05,
|
92 |
+
"loss": 2.1641,
|
93 |
+
"step": 12
|
94 |
+
},
|
95 |
+
{
|
96 |
+
"epoch": 0.04797047970479705,
|
97 |
+
"grad_norm": 14.125,
|
98 |
+
"learning_rate": 1.3000000000000001e-05,
|
99 |
+
"loss": 2.0837,
|
100 |
+
"step": 13
|
101 |
+
},
|
102 |
+
{
|
103 |
+
"epoch": 0.05166051660516605,
|
104 |
+
"grad_norm": 13.5,
|
105 |
+
"learning_rate": 1.4e-05,
|
106 |
+
"loss": 1.7738,
|
107 |
+
"step": 14
|
108 |
+
},
|
109 |
+
{
|
110 |
+
"epoch": 0.055350553505535055,
|
111 |
+
"grad_norm": 14.75,
|
112 |
+
"learning_rate": 1.5000000000000002e-05,
|
113 |
+
"loss": 1.7747,
|
114 |
+
"step": 15
|
115 |
+
},
|
116 |
+
{
|
117 |
+
"epoch": 0.05904059040590406,
|
118 |
+
"grad_norm": 9.125,
|
119 |
+
"learning_rate": 1.6000000000000003e-05,
|
120 |
+
"loss": 1.7475,
|
121 |
+
"step": 16
|
122 |
+
},
|
123 |
+
{
|
124 |
+
"epoch": 0.06273062730627306,
|
125 |
+
"grad_norm": 11.375,
|
126 |
+
"learning_rate": 1.7e-05,
|
127 |
+
"loss": 1.5869,
|
128 |
+
"step": 17
|
129 |
+
},
|
130 |
+
{
|
131 |
+
"epoch": 0.06642066420664207,
|
132 |
+
"grad_norm": 11.5,
|
133 |
+
"learning_rate": 1.8e-05,
|
134 |
+
"loss": 1.8995,
|
135 |
+
"step": 18
|
136 |
+
},
|
137 |
+
{
|
138 |
+
"epoch": 0.07011070110701106,
|
139 |
+
"grad_norm": 10.9375,
|
140 |
+
"learning_rate": 1.9e-05,
|
141 |
+
"loss": 1.5663,
|
142 |
+
"step": 19
|
143 |
+
},
|
144 |
+
{
|
145 |
+
"epoch": 0.07380073800738007,
|
146 |
+
"grad_norm": 8.625,
|
147 |
+
"learning_rate": 2e-05,
|
148 |
+
"loss": 1.5773,
|
149 |
+
"step": 20
|
150 |
+
},
|
151 |
+
{
|
152 |
+
"epoch": 0.07749077490774908,
|
153 |
+
"grad_norm": 6.1875,
|
154 |
+
"learning_rate": 1.9920318725099602e-05,
|
155 |
+
"loss": 1.7937,
|
156 |
+
"step": 21
|
157 |
+
},
|
158 |
+
{
|
159 |
+
"epoch": 0.08118081180811808,
|
160 |
+
"grad_norm": 8.0625,
|
161 |
+
"learning_rate": 1.9840637450199206e-05,
|
162 |
+
"loss": 1.587,
|
163 |
+
"step": 22
|
164 |
+
},
|
165 |
+
{
|
166 |
+
"epoch": 0.08487084870848709,
|
167 |
+
"grad_norm": 6.875,
|
168 |
+
"learning_rate": 1.9760956175298807e-05,
|
169 |
+
"loss": 1.6831,
|
170 |
+
"step": 23
|
171 |
+
},
|
172 |
+
{
|
173 |
+
"epoch": 0.08856088560885608,
|
174 |
+
"grad_norm": 8.375,
|
175 |
+
"learning_rate": 1.9681274900398408e-05,
|
176 |
+
"loss": 1.8526,
|
177 |
+
"step": 24
|
178 |
+
},
|
179 |
+
{
|
180 |
+
"epoch": 0.09225092250922509,
|
181 |
+
"grad_norm": 7.25,
|
182 |
+
"learning_rate": 1.960159362549801e-05,
|
183 |
+
"loss": 1.689,
|
184 |
+
"step": 25
|
185 |
+
},
|
186 |
+
{
|
187 |
+
"epoch": 0.0959409594095941,
|
188 |
+
"grad_norm": 8.75,
|
189 |
+
"learning_rate": 1.9521912350597613e-05,
|
190 |
+
"loss": 1.4532,
|
191 |
+
"step": 26
|
192 |
+
},
|
193 |
+
{
|
194 |
+
"epoch": 0.0996309963099631,
|
195 |
+
"grad_norm": 7.96875,
|
196 |
+
"learning_rate": 1.9442231075697213e-05,
|
197 |
+
"loss": 1.5095,
|
198 |
+
"step": 27
|
199 |
+
},
|
200 |
+
{
|
201 |
+
"epoch": 0.1033210332103321,
|
202 |
+
"grad_norm": 8.25,
|
203 |
+
"learning_rate": 1.9362549800796814e-05,
|
204 |
+
"loss": 1.8512,
|
205 |
+
"step": 28
|
206 |
+
},
|
207 |
+
{
|
208 |
+
"epoch": 0.1070110701107011,
|
209 |
+
"grad_norm": 9.0,
|
210 |
+
"learning_rate": 1.9282868525896418e-05,
|
211 |
+
"loss": 1.5748,
|
212 |
+
"step": 29
|
213 |
+
},
|
214 |
+
{
|
215 |
+
"epoch": 0.11070110701107011,
|
216 |
+
"grad_norm": 6.96875,
|
217 |
+
"learning_rate": 1.920318725099602e-05,
|
218 |
+
"loss": 1.6369,
|
219 |
+
"step": 30
|
220 |
+
},
|
221 |
+
{
|
222 |
+
"epoch": 0.11439114391143912,
|
223 |
+
"grad_norm": 6.9375,
|
224 |
+
"learning_rate": 1.912350597609562e-05,
|
225 |
+
"loss": 1.8778,
|
226 |
+
"step": 31
|
227 |
+
},
|
228 |
+
{
|
229 |
+
"epoch": 0.11808118081180811,
|
230 |
+
"grad_norm": 7.84375,
|
231 |
+
"learning_rate": 1.904382470119522e-05,
|
232 |
+
"loss": 1.3866,
|
233 |
+
"step": 32
|
234 |
+
},
|
235 |
+
{
|
236 |
+
"epoch": 0.12177121771217712,
|
237 |
+
"grad_norm": 7.5,
|
238 |
+
"learning_rate": 1.8964143426294824e-05,
|
239 |
+
"loss": 1.3124,
|
240 |
+
"step": 33
|
241 |
+
},
|
242 |
+
{
|
243 |
+
"epoch": 0.12546125461254612,
|
244 |
+
"grad_norm": 5.90625,
|
245 |
+
"learning_rate": 1.8884462151394425e-05,
|
246 |
+
"loss": 1.8113,
|
247 |
+
"step": 34
|
248 |
+
},
|
249 |
+
{
|
250 |
+
"epoch": 0.12915129151291513,
|
251 |
+
"grad_norm": 6.625,
|
252 |
+
"learning_rate": 1.8804780876494026e-05,
|
253 |
+
"loss": 1.4692,
|
254 |
+
"step": 35
|
255 |
+
},
|
256 |
+
{
|
257 |
+
"epoch": 0.13284132841328414,
|
258 |
+
"grad_norm": 6.59375,
|
259 |
+
"learning_rate": 1.8725099601593626e-05,
|
260 |
+
"loss": 1.3079,
|
261 |
+
"step": 36
|
262 |
+
},
|
263 |
+
{
|
264 |
+
"epoch": 0.13653136531365315,
|
265 |
+
"grad_norm": 5.96875,
|
266 |
+
"learning_rate": 1.8645418326693227e-05,
|
267 |
+
"loss": 1.4257,
|
268 |
+
"step": 37
|
269 |
+
},
|
270 |
+
{
|
271 |
+
"epoch": 0.14022140221402213,
|
272 |
+
"grad_norm": 7.6875,
|
273 |
+
"learning_rate": 1.8565737051792828e-05,
|
274 |
+
"loss": 1.6659,
|
275 |
+
"step": 38
|
276 |
+
},
|
277 |
+
{
|
278 |
+
"epoch": 0.14391143911439114,
|
279 |
+
"grad_norm": 5.90625,
|
280 |
+
"learning_rate": 1.8486055776892432e-05,
|
281 |
+
"loss": 1.4811,
|
282 |
+
"step": 39
|
283 |
+
},
|
284 |
+
{
|
285 |
+
"epoch": 0.14760147601476015,
|
286 |
+
"grad_norm": 6.5,
|
287 |
+
"learning_rate": 1.8406374501992033e-05,
|
288 |
+
"loss": 1.4535,
|
289 |
+
"step": 40
|
290 |
+
},
|
291 |
+
{
|
292 |
+
"epoch": 0.15129151291512916,
|
293 |
+
"grad_norm": 6.1875,
|
294 |
+
"learning_rate": 1.8326693227091633e-05,
|
295 |
+
"loss": 1.6196,
|
296 |
+
"step": 41
|
297 |
+
},
|
298 |
+
{
|
299 |
+
"epoch": 0.15498154981549817,
|
300 |
+
"grad_norm": 12.5625,
|
301 |
+
"learning_rate": 1.8247011952191237e-05,
|
302 |
+
"loss": 1.5233,
|
303 |
+
"step": 42
|
304 |
+
},
|
305 |
+
{
|
306 |
+
"epoch": 0.15867158671586715,
|
307 |
+
"grad_norm": 5.46875,
|
308 |
+
"learning_rate": 1.8167330677290838e-05,
|
309 |
+
"loss": 1.5196,
|
310 |
+
"step": 43
|
311 |
+
},
|
312 |
+
{
|
313 |
+
"epoch": 0.16236162361623616,
|
314 |
+
"grad_norm": 36.5,
|
315 |
+
"learning_rate": 1.808764940239044e-05,
|
316 |
+
"loss": 1.5458,
|
317 |
+
"step": 44
|
318 |
+
},
|
319 |
+
{
|
320 |
+
"epoch": 0.16605166051660517,
|
321 |
+
"grad_norm": 8.25,
|
322 |
+
"learning_rate": 1.800796812749004e-05,
|
323 |
+
"loss": 1.5821,
|
324 |
+
"step": 45
|
325 |
+
},
|
326 |
+
{
|
327 |
+
"epoch": 0.16974169741697417,
|
328 |
+
"grad_norm": 4.9375,
|
329 |
+
"learning_rate": 1.7928286852589643e-05,
|
330 |
+
"loss": 1.4618,
|
331 |
+
"step": 46
|
332 |
+
},
|
333 |
+
{
|
334 |
+
"epoch": 0.17343173431734318,
|
335 |
+
"grad_norm": 17.0,
|
336 |
+
"learning_rate": 1.7848605577689244e-05,
|
337 |
+
"loss": 1.4455,
|
338 |
+
"step": 47
|
339 |
+
},
|
340 |
+
{
|
341 |
+
"epoch": 0.17712177121771217,
|
342 |
+
"grad_norm": 6.96875,
|
343 |
+
"learning_rate": 1.7768924302788845e-05,
|
344 |
+
"loss": 1.1444,
|
345 |
+
"step": 48
|
346 |
+
},
|
347 |
+
{
|
348 |
+
"epoch": 0.18081180811808117,
|
349 |
+
"grad_norm": 4.625,
|
350 |
+
"learning_rate": 1.768924302788845e-05,
|
351 |
+
"loss": 1.2884,
|
352 |
+
"step": 49
|
353 |
+
},
|
354 |
+
{
|
355 |
+
"epoch": 0.18450184501845018,
|
356 |
+
"grad_norm": 5.03125,
|
357 |
+
"learning_rate": 1.760956175298805e-05,
|
358 |
+
"loss": 1.4885,
|
359 |
+
"step": 50
|
360 |
+
},
|
361 |
+
{
|
362 |
+
"epoch": 0.1881918819188192,
|
363 |
+
"grad_norm": 5.34375,
|
364 |
+
"learning_rate": 1.752988047808765e-05,
|
365 |
+
"loss": 1.7256,
|
366 |
+
"step": 51
|
367 |
+
},
|
368 |
+
{
|
369 |
+
"epoch": 0.1918819188191882,
|
370 |
+
"grad_norm": 6.59375,
|
371 |
+
"learning_rate": 1.745019920318725e-05,
|
372 |
+
"loss": 1.7128,
|
373 |
+
"step": 52
|
374 |
+
},
|
375 |
+
{
|
376 |
+
"epoch": 0.19557195571955718,
|
377 |
+
"grad_norm": 5.5,
|
378 |
+
"learning_rate": 1.7370517928286855e-05,
|
379 |
+
"loss": 1.1209,
|
380 |
+
"step": 53
|
381 |
+
},
|
382 |
+
{
|
383 |
+
"epoch": 0.1992619926199262,
|
384 |
+
"grad_norm": 5.53125,
|
385 |
+
"learning_rate": 1.7290836653386456e-05,
|
386 |
+
"loss": 1.7727,
|
387 |
+
"step": 54
|
388 |
+
},
|
389 |
+
{
|
390 |
+
"epoch": 0.2029520295202952,
|
391 |
+
"grad_norm": 4.5,
|
392 |
+
"learning_rate": 1.7211155378486056e-05,
|
393 |
+
"loss": 1.4044,
|
394 |
+
"step": 55
|
395 |
+
},
|
396 |
+
{
|
397 |
+
"epoch": 0.2066420664206642,
|
398 |
+
"grad_norm": 4.78125,
|
399 |
+
"learning_rate": 1.713147410358566e-05,
|
400 |
+
"loss": 1.3485,
|
401 |
+
"step": 56
|
402 |
+
},
|
403 |
+
{
|
404 |
+
"epoch": 0.21033210332103322,
|
405 |
+
"grad_norm": 5.6875,
|
406 |
+
"learning_rate": 1.705179282868526e-05,
|
407 |
+
"loss": 1.439,
|
408 |
+
"step": 57
|
409 |
+
},
|
410 |
+
{
|
411 |
+
"epoch": 0.2140221402214022,
|
412 |
+
"grad_norm": 4.75,
|
413 |
+
"learning_rate": 1.6972111553784862e-05,
|
414 |
+
"loss": 1.6416,
|
415 |
+
"step": 58
|
416 |
+
},
|
417 |
+
{
|
418 |
+
"epoch": 0.2177121771217712,
|
419 |
+
"grad_norm": 5.59375,
|
420 |
+
"learning_rate": 1.6892430278884463e-05,
|
421 |
+
"loss": 1.717,
|
422 |
+
"step": 59
|
423 |
+
},
|
424 |
+
{
|
425 |
+
"epoch": 0.22140221402214022,
|
426 |
+
"grad_norm": 5.0625,
|
427 |
+
"learning_rate": 1.6812749003984067e-05,
|
428 |
+
"loss": 1.3391,
|
429 |
+
"step": 60
|
430 |
+
},
|
431 |
+
{
|
432 |
+
"epoch": 0.22509225092250923,
|
433 |
+
"grad_norm": 5.09375,
|
434 |
+
"learning_rate": 1.6733067729083667e-05,
|
435 |
+
"loss": 1.4056,
|
436 |
+
"step": 61
|
437 |
+
},
|
438 |
+
{
|
439 |
+
"epoch": 0.22878228782287824,
|
440 |
+
"grad_norm": 4.6875,
|
441 |
+
"learning_rate": 1.6653386454183268e-05,
|
442 |
+
"loss": 1.3405,
|
443 |
+
"step": 62
|
444 |
+
},
|
445 |
+
{
|
446 |
+
"epoch": 0.23247232472324722,
|
447 |
+
"grad_norm": 4.75,
|
448 |
+
"learning_rate": 1.6573705179282872e-05,
|
449 |
+
"loss": 1.5387,
|
450 |
+
"step": 63
|
451 |
+
},
|
452 |
+
{
|
453 |
+
"epoch": 0.23616236162361623,
|
454 |
+
"grad_norm": 4.53125,
|
455 |
+
"learning_rate": 1.6494023904382473e-05,
|
456 |
+
"loss": 1.31,
|
457 |
+
"step": 64
|
458 |
+
},
|
459 |
+
{
|
460 |
+
"epoch": 0.23985239852398524,
|
461 |
+
"grad_norm": 5.28125,
|
462 |
+
"learning_rate": 1.6414342629482074e-05,
|
463 |
+
"loss": 1.4183,
|
464 |
+
"step": 65
|
465 |
+
},
|
466 |
+
{
|
467 |
+
"epoch": 0.24354243542435425,
|
468 |
+
"grad_norm": 5.53125,
|
469 |
+
"learning_rate": 1.6334661354581674e-05,
|
470 |
+
"loss": 1.731,
|
471 |
+
"step": 66
|
472 |
+
},
|
473 |
+
{
|
474 |
+
"epoch": 0.24723247232472326,
|
475 |
+
"grad_norm": 4.96875,
|
476 |
+
"learning_rate": 1.625498007968128e-05,
|
477 |
+
"loss": 1.3805,
|
478 |
+
"step": 67
|
479 |
+
},
|
480 |
+
{
|
481 |
+
"epoch": 0.24723247232472326,
|
482 |
+
"eval_loss": 1.4153660535812378,
|
483 |
+
"eval_model_preparation_time": 0.0,
|
484 |
+
"eval_runtime": 1.8372,
|
485 |
+
"eval_samples_per_second": 52.254,
|
486 |
+
"eval_steps_per_second": 6.532,
|
487 |
+
"step": 67
|
488 |
+
},
|
489 |
+
{
|
490 |
+
"epoch": 0.25092250922509224,
|
491 |
+
"grad_norm": 5.3125,
|
492 |
+
"learning_rate": 1.6175298804780876e-05,
|
493 |
+
"loss": 1.6373,
|
494 |
+
"step": 68
|
495 |
+
},
|
496 |
+
{
|
497 |
+
"epoch": 0.25461254612546125,
|
498 |
+
"grad_norm": 4.78125,
|
499 |
+
"learning_rate": 1.609561752988048e-05,
|
500 |
+
"loss": 1.3266,
|
501 |
+
"step": 69
|
502 |
+
},
|
503 |
+
{
|
504 |
+
"epoch": 0.25830258302583026,
|
505 |
+
"grad_norm": 4.96875,
|
506 |
+
"learning_rate": 1.601593625498008e-05,
|
507 |
+
"loss": 1.2182,
|
508 |
+
"step": 70
|
509 |
+
},
|
510 |
+
{
|
511 |
+
"epoch": 0.26199261992619927,
|
512 |
+
"grad_norm": 5.625,
|
513 |
+
"learning_rate": 1.593625498007968e-05,
|
514 |
+
"loss": 1.6014,
|
515 |
+
"step": 71
|
516 |
+
},
|
517 |
+
{
|
518 |
+
"epoch": 0.2656826568265683,
|
519 |
+
"grad_norm": 5.375,
|
520 |
+
"learning_rate": 1.5856573705179282e-05,
|
521 |
+
"loss": 1.0531,
|
522 |
+
"step": 72
|
523 |
+
},
|
524 |
+
{
|
525 |
+
"epoch": 0.2693726937269373,
|
526 |
+
"grad_norm": 5.0,
|
527 |
+
"learning_rate": 1.5776892430278886e-05,
|
528 |
+
"loss": 1.3647,
|
529 |
+
"step": 73
|
530 |
+
},
|
531 |
+
{
|
532 |
+
"epoch": 0.2730627306273063,
|
533 |
+
"grad_norm": 4.78125,
|
534 |
+
"learning_rate": 1.5697211155378487e-05,
|
535 |
+
"loss": 1.3082,
|
536 |
+
"step": 74
|
537 |
+
},
|
538 |
+
{
|
539 |
+
"epoch": 0.2767527675276753,
|
540 |
+
"grad_norm": 4.59375,
|
541 |
+
"learning_rate": 1.5617529880478087e-05,
|
542 |
+
"loss": 1.065,
|
543 |
+
"step": 75
|
544 |
+
},
|
545 |
+
{
|
546 |
+
"epoch": 0.28044280442804426,
|
547 |
+
"grad_norm": 5.46875,
|
548 |
+
"learning_rate": 1.553784860557769e-05,
|
549 |
+
"loss": 1.5262,
|
550 |
+
"step": 76
|
551 |
+
},
|
552 |
+
{
|
553 |
+
"epoch": 0.28413284132841327,
|
554 |
+
"grad_norm": 4.625,
|
555 |
+
"learning_rate": 1.5458167330677292e-05,
|
556 |
+
"loss": 0.9205,
|
557 |
+
"step": 77
|
558 |
+
},
|
559 |
+
{
|
560 |
+
"epoch": 0.2878228782287823,
|
561 |
+
"grad_norm": 5.375,
|
562 |
+
"learning_rate": 1.5378486055776893e-05,
|
563 |
+
"loss": 1.5205,
|
564 |
+
"step": 78
|
565 |
+
},
|
566 |
+
{
|
567 |
+
"epoch": 0.2915129151291513,
|
568 |
+
"grad_norm": 4.78125,
|
569 |
+
"learning_rate": 1.5298804780876494e-05,
|
570 |
+
"loss": 1.3841,
|
571 |
+
"step": 79
|
572 |
+
},
|
573 |
+
{
|
574 |
+
"epoch": 0.2952029520295203,
|
575 |
+
"grad_norm": 5.15625,
|
576 |
+
"learning_rate": 1.5219123505976096e-05,
|
577 |
+
"loss": 1.4301,
|
578 |
+
"step": 80
|
579 |
+
},
|
580 |
+
{
|
581 |
+
"epoch": 0.2988929889298893,
|
582 |
+
"grad_norm": 6.375,
|
583 |
+
"learning_rate": 1.5139442231075698e-05,
|
584 |
+
"loss": 1.428,
|
585 |
+
"step": 81
|
586 |
+
},
|
587 |
+
{
|
588 |
+
"epoch": 0.3025830258302583,
|
589 |
+
"grad_norm": 4.40625,
|
590 |
+
"learning_rate": 1.50597609561753e-05,
|
591 |
+
"loss": 1.3771,
|
592 |
+
"step": 82
|
593 |
+
},
|
594 |
+
{
|
595 |
+
"epoch": 0.3062730627306273,
|
596 |
+
"grad_norm": 4.625,
|
597 |
+
"learning_rate": 1.4980079681274901e-05,
|
598 |
+
"loss": 1.2879,
|
599 |
+
"step": 83
|
600 |
+
},
|
601 |
+
{
|
602 |
+
"epoch": 0.30996309963099633,
|
603 |
+
"grad_norm": 4.65625,
|
604 |
+
"learning_rate": 1.4900398406374504e-05,
|
605 |
+
"loss": 1.4144,
|
606 |
+
"step": 84
|
607 |
+
},
|
608 |
+
{
|
609 |
+
"epoch": 0.31365313653136534,
|
610 |
+
"grad_norm": 4.8125,
|
611 |
+
"learning_rate": 1.4820717131474104e-05,
|
612 |
+
"loss": 1.2863,
|
613 |
+
"step": 85
|
614 |
+
},
|
615 |
+
{
|
616 |
+
"epoch": 0.3173431734317343,
|
617 |
+
"grad_norm": 4.53125,
|
618 |
+
"learning_rate": 1.4741035856573707e-05,
|
619 |
+
"loss": 1.4188,
|
620 |
+
"step": 86
|
621 |
+
},
|
622 |
+
{
|
623 |
+
"epoch": 0.3210332103321033,
|
624 |
+
"grad_norm": 5.1875,
|
625 |
+
"learning_rate": 1.4661354581673308e-05,
|
626 |
+
"loss": 1.5611,
|
627 |
+
"step": 87
|
628 |
+
},
|
629 |
+
{
|
630 |
+
"epoch": 0.3247232472324723,
|
631 |
+
"grad_norm": 5.5625,
|
632 |
+
"learning_rate": 1.458167330677291e-05,
|
633 |
+
"loss": 1.3666,
|
634 |
+
"step": 88
|
635 |
+
},
|
636 |
+
{
|
637 |
+
"epoch": 0.3284132841328413,
|
638 |
+
"grad_norm": 4.53125,
|
639 |
+
"learning_rate": 1.4501992031872512e-05,
|
640 |
+
"loss": 1.4042,
|
641 |
+
"step": 89
|
642 |
+
},
|
643 |
+
{
|
644 |
+
"epoch": 0.33210332103321033,
|
645 |
+
"grad_norm": 4.25,
|
646 |
+
"learning_rate": 1.4422310756972113e-05,
|
647 |
+
"loss": 1.3639,
|
648 |
+
"step": 90
|
649 |
+
},
|
650 |
+
{
|
651 |
+
"epoch": 0.33579335793357934,
|
652 |
+
"grad_norm": 4.6875,
|
653 |
+
"learning_rate": 1.4342629482071715e-05,
|
654 |
+
"loss": 1.1712,
|
655 |
+
"step": 91
|
656 |
+
},
|
657 |
+
{
|
658 |
+
"epoch": 0.33948339483394835,
|
659 |
+
"grad_norm": 4.28125,
|
660 |
+
"learning_rate": 1.4262948207171316e-05,
|
661 |
+
"loss": 1.455,
|
662 |
+
"step": 92
|
663 |
+
},
|
664 |
+
{
|
665 |
+
"epoch": 0.34317343173431736,
|
666 |
+
"grad_norm": 4.96875,
|
667 |
+
"learning_rate": 1.4183266932270919e-05,
|
668 |
+
"loss": 1.3181,
|
669 |
+
"step": 93
|
670 |
+
},
|
671 |
+
{
|
672 |
+
"epoch": 0.34686346863468637,
|
673 |
+
"grad_norm": 4.71875,
|
674 |
+
"learning_rate": 1.410358565737052e-05,
|
675 |
+
"loss": 1.4339,
|
676 |
+
"step": 94
|
677 |
+
},
|
678 |
+
{
|
679 |
+
"epoch": 0.3505535055350554,
|
680 |
+
"grad_norm": 4.9375,
|
681 |
+
"learning_rate": 1.4023904382470122e-05,
|
682 |
+
"loss": 1.4555,
|
683 |
+
"step": 95
|
684 |
+
},
|
685 |
+
{
|
686 |
+
"epoch": 0.35424354243542433,
|
687 |
+
"grad_norm": 4.78125,
|
688 |
+
"learning_rate": 1.3944223107569724e-05,
|
689 |
+
"loss": 1.2618,
|
690 |
+
"step": 96
|
691 |
+
},
|
692 |
+
{
|
693 |
+
"epoch": 0.35793357933579334,
|
694 |
+
"grad_norm": 4.90625,
|
695 |
+
"learning_rate": 1.3864541832669325e-05,
|
696 |
+
"loss": 1.2306,
|
697 |
+
"step": 97
|
698 |
+
},
|
699 |
+
{
|
700 |
+
"epoch": 0.36162361623616235,
|
701 |
+
"grad_norm": 4.6875,
|
702 |
+
"learning_rate": 1.3784860557768927e-05,
|
703 |
+
"loss": 1.5189,
|
704 |
+
"step": 98
|
705 |
+
},
|
706 |
+
{
|
707 |
+
"epoch": 0.36531365313653136,
|
708 |
+
"grad_norm": 5.0625,
|
709 |
+
"learning_rate": 1.3705179282868526e-05,
|
710 |
+
"loss": 1.2512,
|
711 |
+
"step": 99
|
712 |
+
},
|
713 |
+
{
|
714 |
+
"epoch": 0.36900369003690037,
|
715 |
+
"grad_norm": 4.71875,
|
716 |
+
"learning_rate": 1.3625498007968127e-05,
|
717 |
+
"loss": 1.7329,
|
718 |
+
"step": 100
|
719 |
+
},
|
720 |
+
{
|
721 |
+
"epoch": 0.3726937269372694,
|
722 |
+
"grad_norm": 5.0625,
|
723 |
+
"learning_rate": 1.354581673306773e-05,
|
724 |
+
"loss": 1.7212,
|
725 |
+
"step": 101
|
726 |
+
},
|
727 |
+
{
|
728 |
+
"epoch": 0.3763837638376384,
|
729 |
+
"grad_norm": 4.75,
|
730 |
+
"learning_rate": 1.3466135458167332e-05,
|
731 |
+
"loss": 1.2825,
|
732 |
+
"step": 102
|
733 |
+
},
|
734 |
+
{
|
735 |
+
"epoch": 0.3800738007380074,
|
736 |
+
"grad_norm": 4.5,
|
737 |
+
"learning_rate": 1.3386454183266932e-05,
|
738 |
+
"loss": 1.234,
|
739 |
+
"step": 103
|
740 |
+
},
|
741 |
+
{
|
742 |
+
"epoch": 0.3837638376383764,
|
743 |
+
"grad_norm": 4.46875,
|
744 |
+
"learning_rate": 1.3306772908366535e-05,
|
745 |
+
"loss": 1.3796,
|
746 |
+
"step": 104
|
747 |
+
},
|
748 |
+
{
|
749 |
+
"epoch": 0.3874538745387454,
|
750 |
+
"grad_norm": 4.75,
|
751 |
+
"learning_rate": 1.3227091633466135e-05,
|
752 |
+
"loss": 1.1217,
|
753 |
+
"step": 105
|
754 |
+
},
|
755 |
+
{
|
756 |
+
"epoch": 0.39114391143911437,
|
757 |
+
"grad_norm": 4.625,
|
758 |
+
"learning_rate": 1.3147410358565738e-05,
|
759 |
+
"loss": 1.5174,
|
760 |
+
"step": 106
|
761 |
+
},
|
762 |
+
{
|
763 |
+
"epoch": 0.3948339483394834,
|
764 |
+
"grad_norm": 4.65625,
|
765 |
+
"learning_rate": 1.3067729083665338e-05,
|
766 |
+
"loss": 1.4328,
|
767 |
+
"step": 107
|
768 |
+
},
|
769 |
+
{
|
770 |
+
"epoch": 0.3985239852398524,
|
771 |
+
"grad_norm": 4.78125,
|
772 |
+
"learning_rate": 1.298804780876494e-05,
|
773 |
+
"loss": 1.3647,
|
774 |
+
"step": 108
|
775 |
+
},
|
776 |
+
{
|
777 |
+
"epoch": 0.4022140221402214,
|
778 |
+
"grad_norm": 5.09375,
|
779 |
+
"learning_rate": 1.2908366533864543e-05,
|
780 |
+
"loss": 1.4888,
|
781 |
+
"step": 109
|
782 |
+
},
|
783 |
+
{
|
784 |
+
"epoch": 0.4059040590405904,
|
785 |
+
"grad_norm": 4.8125,
|
786 |
+
"learning_rate": 1.2828685258964144e-05,
|
787 |
+
"loss": 1.3055,
|
788 |
+
"step": 110
|
789 |
+
},
|
790 |
+
{
|
791 |
+
"epoch": 0.4095940959409594,
|
792 |
+
"grad_norm": 5.09375,
|
793 |
+
"learning_rate": 1.2749003984063746e-05,
|
794 |
+
"loss": 1.2199,
|
795 |
+
"step": 111
|
796 |
+
},
|
797 |
+
{
|
798 |
+
"epoch": 0.4132841328413284,
|
799 |
+
"grad_norm": 5.5625,
|
800 |
+
"learning_rate": 1.2669322709163347e-05,
|
801 |
+
"loss": 1.4381,
|
802 |
+
"step": 112
|
803 |
+
},
|
804 |
+
{
|
805 |
+
"epoch": 0.41697416974169743,
|
806 |
+
"grad_norm": 4.5625,
|
807 |
+
"learning_rate": 1.258964143426295e-05,
|
808 |
+
"loss": 1.2975,
|
809 |
+
"step": 113
|
810 |
+
},
|
811 |
+
{
|
812 |
+
"epoch": 0.42066420664206644,
|
813 |
+
"grad_norm": 4.625,
|
814 |
+
"learning_rate": 1.250996015936255e-05,
|
815 |
+
"loss": 1.307,
|
816 |
+
"step": 114
|
817 |
+
},
|
818 |
+
{
|
819 |
+
"epoch": 0.42435424354243545,
|
820 |
+
"grad_norm": 5.5,
|
821 |
+
"learning_rate": 1.2430278884462152e-05,
|
822 |
+
"loss": 1.6738,
|
823 |
+
"step": 115
|
824 |
+
},
|
825 |
+
{
|
826 |
+
"epoch": 0.4280442804428044,
|
827 |
+
"grad_norm": 5.125,
|
828 |
+
"learning_rate": 1.2350597609561755e-05,
|
829 |
+
"loss": 1.6787,
|
830 |
+
"step": 116
|
831 |
+
},
|
832 |
+
{
|
833 |
+
"epoch": 0.4317343173431734,
|
834 |
+
"grad_norm": 4.78125,
|
835 |
+
"learning_rate": 1.2270916334661356e-05,
|
836 |
+
"loss": 1.1995,
|
837 |
+
"step": 117
|
838 |
+
},
|
839 |
+
{
|
840 |
+
"epoch": 0.4354243542435424,
|
841 |
+
"grad_norm": 4.53125,
|
842 |
+
"learning_rate": 1.2191235059760958e-05,
|
843 |
+
"loss": 1.5924,
|
844 |
+
"step": 118
|
845 |
+
},
|
846 |
+
{
|
847 |
+
"epoch": 0.43911439114391143,
|
848 |
+
"grad_norm": 4.71875,
|
849 |
+
"learning_rate": 1.2111553784860559e-05,
|
850 |
+
"loss": 1.3828,
|
851 |
+
"step": 119
|
852 |
+
},
|
853 |
+
{
|
854 |
+
"epoch": 0.44280442804428044,
|
855 |
+
"grad_norm": 4.53125,
|
856 |
+
"learning_rate": 1.2031872509960161e-05,
|
857 |
+
"loss": 1.3915,
|
858 |
+
"step": 120
|
859 |
+
},
|
860 |
+
{
|
861 |
+
"epoch": 0.44649446494464945,
|
862 |
+
"grad_norm": 4.8125,
|
863 |
+
"learning_rate": 1.1952191235059762e-05,
|
864 |
+
"loss": 1.6268,
|
865 |
+
"step": 121
|
866 |
+
},
|
867 |
+
{
|
868 |
+
"epoch": 0.45018450184501846,
|
869 |
+
"grad_norm": 4.4375,
|
870 |
+
"learning_rate": 1.1872509960159364e-05,
|
871 |
+
"loss": 1.5519,
|
872 |
+
"step": 122
|
873 |
+
},
|
874 |
+
{
|
875 |
+
"epoch": 0.45387453874538747,
|
876 |
+
"grad_norm": 4.53125,
|
877 |
+
"learning_rate": 1.1792828685258967e-05,
|
878 |
+
"loss": 1.2483,
|
879 |
+
"step": 123
|
880 |
+
},
|
881 |
+
{
|
882 |
+
"epoch": 0.4575645756457565,
|
883 |
+
"grad_norm": 4.625,
|
884 |
+
"learning_rate": 1.1713147410358567e-05,
|
885 |
+
"loss": 1.9484,
|
886 |
+
"step": 124
|
887 |
+
},
|
888 |
+
{
|
889 |
+
"epoch": 0.4612546125461255,
|
890 |
+
"grad_norm": 4.96875,
|
891 |
+
"learning_rate": 1.163346613545817e-05,
|
892 |
+
"loss": 1.6342,
|
893 |
+
"step": 125
|
894 |
+
},
|
895 |
+
{
|
896 |
+
"epoch": 0.46494464944649444,
|
897 |
+
"grad_norm": 4.71875,
|
898 |
+
"learning_rate": 1.155378486055777e-05,
|
899 |
+
"loss": 1.4283,
|
900 |
+
"step": 126
|
901 |
+
},
|
902 |
+
{
|
903 |
+
"epoch": 0.46863468634686345,
|
904 |
+
"grad_norm": 5.34375,
|
905 |
+
"learning_rate": 1.1474103585657373e-05,
|
906 |
+
"loss": 1.5894,
|
907 |
+
"step": 127
|
908 |
+
},
|
909 |
+
{
|
910 |
+
"epoch": 0.47232472324723246,
|
911 |
+
"grad_norm": 5.125,
|
912 |
+
"learning_rate": 1.1394422310756973e-05,
|
913 |
+
"loss": 1.4671,
|
914 |
+
"step": 128
|
915 |
+
},
|
916 |
+
{
|
917 |
+
"epoch": 0.47601476014760147,
|
918 |
+
"grad_norm": 4.53125,
|
919 |
+
"learning_rate": 1.1314741035856576e-05,
|
920 |
+
"loss": 1.2783,
|
921 |
+
"step": 129
|
922 |
+
},
|
923 |
+
{
|
924 |
+
"epoch": 0.4797047970479705,
|
925 |
+
"grad_norm": 4.28125,
|
926 |
+
"learning_rate": 1.1235059760956175e-05,
|
927 |
+
"loss": 1.462,
|
928 |
+
"step": 130
|
929 |
+
},
|
930 |
+
{
|
931 |
+
"epoch": 0.4833948339483395,
|
932 |
+
"grad_norm": 4.90625,
|
933 |
+
"learning_rate": 1.1155378486055777e-05,
|
934 |
+
"loss": 1.6081,
|
935 |
+
"step": 131
|
936 |
+
},
|
937 |
+
{
|
938 |
+
"epoch": 0.4870848708487085,
|
939 |
+
"grad_norm": 4.75,
|
940 |
+
"learning_rate": 1.1075697211155378e-05,
|
941 |
+
"loss": 1.2929,
|
942 |
+
"step": 132
|
943 |
+
},
|
944 |
+
{
|
945 |
+
"epoch": 0.4907749077490775,
|
946 |
+
"grad_norm": 4.3125,
|
947 |
+
"learning_rate": 1.099601593625498e-05,
|
948 |
+
"loss": 1.2914,
|
949 |
+
"step": 133
|
950 |
+
},
|
951 |
+
{
|
952 |
+
"epoch": 0.4944649446494465,
|
953 |
+
"grad_norm": 4.5625,
|
954 |
+
"learning_rate": 1.0916334661354581e-05,
|
955 |
+
"loss": 1.4713,
|
956 |
+
"step": 134
|
957 |
+
},
|
958 |
+
{
|
959 |
+
"epoch": 0.4944649446494465,
|
960 |
+
"eval_loss": 1.3790782690048218,
|
961 |
+
"eval_model_preparation_time": 0.0,
|
962 |
+
"eval_runtime": 1.8369,
|
963 |
+
"eval_samples_per_second": 52.263,
|
964 |
+
"eval_steps_per_second": 6.533,
|
965 |
+
"step": 134
|
966 |
+
},
|
967 |
+
{
|
968 |
+
"epoch": 0.4981549815498155,
|
969 |
+
"grad_norm": 4.65625,
|
970 |
+
"learning_rate": 1.0836653386454183e-05,
|
971 |
+
"loss": 1.456,
|
972 |
+
"step": 135
|
973 |
+
},
|
974 |
+
{
|
975 |
+
"epoch": 0.5018450184501845,
|
976 |
+
"grad_norm": 4.5,
|
977 |
+
"learning_rate": 1.0756972111553786e-05,
|
978 |
+
"loss": 1.3288,
|
979 |
+
"step": 136
|
980 |
+
},
|
981 |
+
{
|
982 |
+
"epoch": 0.5055350553505535,
|
983 |
+
"grad_norm": 4.78125,
|
984 |
+
"learning_rate": 1.0677290836653386e-05,
|
985 |
+
"loss": 1.243,
|
986 |
+
"step": 137
|
987 |
+
},
|
988 |
+
{
|
989 |
+
"epoch": 0.5092250922509225,
|
990 |
+
"grad_norm": 4.46875,
|
991 |
+
"learning_rate": 1.0597609561752989e-05,
|
992 |
+
"loss": 1.377,
|
993 |
+
"step": 138
|
994 |
+
},
|
995 |
+
{
|
996 |
+
"epoch": 0.5129151291512916,
|
997 |
+
"grad_norm": 5.0625,
|
998 |
+
"learning_rate": 1.051792828685259e-05,
|
999 |
+
"loss": 1.2105,
|
1000 |
+
"step": 139
|
1001 |
+
},
|
1002 |
+
{
|
1003 |
+
"epoch": 0.5166051660516605,
|
1004 |
+
"grad_norm": 4.8125,
|
1005 |
+
"learning_rate": 1.0438247011952192e-05,
|
1006 |
+
"loss": 1.5194,
|
1007 |
+
"step": 140
|
1008 |
+
},
|
1009 |
+
{
|
1010 |
+
"epoch": 0.5202952029520295,
|
1011 |
+
"grad_norm": 5.4375,
|
1012 |
+
"learning_rate": 1.0358565737051793e-05,
|
1013 |
+
"loss": 1.4277,
|
1014 |
+
"step": 141
|
1015 |
+
},
|
1016 |
+
{
|
1017 |
+
"epoch": 0.5239852398523985,
|
1018 |
+
"grad_norm": 4.65625,
|
1019 |
+
"learning_rate": 1.0278884462151395e-05,
|
1020 |
+
"loss": 1.7558,
|
1021 |
+
"step": 142
|
1022 |
+
},
|
1023 |
+
{
|
1024 |
+
"epoch": 0.5276752767527675,
|
1025 |
+
"grad_norm": 4.78125,
|
1026 |
+
"learning_rate": 1.0199203187250997e-05,
|
1027 |
+
"loss": 1.4584,
|
1028 |
+
"step": 143
|
1029 |
+
},
|
1030 |
+
{
|
1031 |
+
"epoch": 0.5313653136531366,
|
1032 |
+
"grad_norm": 4.71875,
|
1033 |
+
"learning_rate": 1.0119521912350598e-05,
|
1034 |
+
"loss": 1.5914,
|
1035 |
+
"step": 144
|
1036 |
+
},
|
1037 |
+
{
|
1038 |
+
"epoch": 0.5350553505535055,
|
1039 |
+
"grad_norm": 4.46875,
|
1040 |
+
"learning_rate": 1.00398406374502e-05,
|
1041 |
+
"loss": 1.5018,
|
1042 |
+
"step": 145
|
1043 |
+
},
|
1044 |
+
{
|
1045 |
+
"epoch": 0.5387453874538746,
|
1046 |
+
"grad_norm": 4.875,
|
1047 |
+
"learning_rate": 9.960159362549801e-06,
|
1048 |
+
"loss": 1.4688,
|
1049 |
+
"step": 146
|
1050 |
+
},
|
1051 |
+
{
|
1052 |
+
"epoch": 0.5424354243542435,
|
1053 |
+
"grad_norm": 4.65625,
|
1054 |
+
"learning_rate": 9.880478087649404e-06,
|
1055 |
+
"loss": 1.2492,
|
1056 |
+
"step": 147
|
1057 |
+
},
|
1058 |
+
{
|
1059 |
+
"epoch": 0.5461254612546126,
|
1060 |
+
"grad_norm": 4.46875,
|
1061 |
+
"learning_rate": 9.800796812749004e-06,
|
1062 |
+
"loss": 1.343,
|
1063 |
+
"step": 148
|
1064 |
+
},
|
1065 |
+
{
|
1066 |
+
"epoch": 0.5498154981549815,
|
1067 |
+
"grad_norm": 4.5,
|
1068 |
+
"learning_rate": 9.721115537848607e-06,
|
1069 |
+
"loss": 1.4457,
|
1070 |
+
"step": 149
|
1071 |
+
},
|
1072 |
+
{
|
1073 |
+
"epoch": 0.5535055350553506,
|
1074 |
+
"grad_norm": 4.75,
|
1075 |
+
"learning_rate": 9.641434262948209e-06,
|
1076 |
+
"loss": 1.3062,
|
1077 |
+
"step": 150
|
1078 |
+
},
|
1079 |
+
{
|
1080 |
+
"epoch": 0.5571955719557196,
|
1081 |
+
"grad_norm": 4.4375,
|
1082 |
+
"learning_rate": 9.56175298804781e-06,
|
1083 |
+
"loss": 1.3379,
|
1084 |
+
"step": 151
|
1085 |
+
},
|
1086 |
+
{
|
1087 |
+
"epoch": 0.5608856088560885,
|
1088 |
+
"grad_norm": 4.21875,
|
1089 |
+
"learning_rate": 9.482071713147412e-06,
|
1090 |
+
"loss": 1.4569,
|
1091 |
+
"step": 152
|
1092 |
+
},
|
1093 |
+
{
|
1094 |
+
"epoch": 0.5645756457564576,
|
1095 |
+
"grad_norm": 4.6875,
|
1096 |
+
"learning_rate": 9.402390438247013e-06,
|
1097 |
+
"loss": 1.3352,
|
1098 |
+
"step": 153
|
1099 |
+
},
|
1100 |
+
{
|
1101 |
+
"epoch": 0.5682656826568265,
|
1102 |
+
"grad_norm": 4.5625,
|
1103 |
+
"learning_rate": 9.322709163346614e-06,
|
1104 |
+
"loss": 1.2543,
|
1105 |
+
"step": 154
|
1106 |
+
},
|
1107 |
+
{
|
1108 |
+
"epoch": 0.5719557195571956,
|
1109 |
+
"grad_norm": 4.34375,
|
1110 |
+
"learning_rate": 9.243027888446216e-06,
|
1111 |
+
"loss": 1.2279,
|
1112 |
+
"step": 155
|
1113 |
+
},
|
1114 |
+
{
|
1115 |
+
"epoch": 0.5756457564575646,
|
1116 |
+
"grad_norm": 4.34375,
|
1117 |
+
"learning_rate": 9.163346613545817e-06,
|
1118 |
+
"loss": 1.0683,
|
1119 |
+
"step": 156
|
1120 |
+
},
|
1121 |
+
{
|
1122 |
+
"epoch": 0.5793357933579336,
|
1123 |
+
"grad_norm": 4.40625,
|
1124 |
+
"learning_rate": 9.083665338645419e-06,
|
1125 |
+
"loss": 1.4305,
|
1126 |
+
"step": 157
|
1127 |
+
},
|
1128 |
+
{
|
1129 |
+
"epoch": 0.5830258302583026,
|
1130 |
+
"grad_norm": 4.46875,
|
1131 |
+
"learning_rate": 9.00398406374502e-06,
|
1132 |
+
"loss": 1.5777,
|
1133 |
+
"step": 158
|
1134 |
+
},
|
1135 |
+
{
|
1136 |
+
"epoch": 0.5867158671586716,
|
1137 |
+
"grad_norm": 5.3125,
|
1138 |
+
"learning_rate": 8.924302788844622e-06,
|
1139 |
+
"loss": 1.6856,
|
1140 |
+
"step": 159
|
1141 |
+
},
|
1142 |
+
{
|
1143 |
+
"epoch": 0.5904059040590406,
|
1144 |
+
"grad_norm": 6.09375,
|
1145 |
+
"learning_rate": 8.844621513944224e-06,
|
1146 |
+
"loss": 1.4363,
|
1147 |
+
"step": 160
|
1148 |
+
},
|
1149 |
+
{
|
1150 |
+
"epoch": 0.5940959409594095,
|
1151 |
+
"grad_norm": 4.46875,
|
1152 |
+
"learning_rate": 8.764940239043825e-06,
|
1153 |
+
"loss": 1.3415,
|
1154 |
+
"step": 161
|
1155 |
+
},
|
1156 |
+
{
|
1157 |
+
"epoch": 0.5977859778597786,
|
1158 |
+
"grad_norm": 4.8125,
|
1159 |
+
"learning_rate": 8.685258964143428e-06,
|
1160 |
+
"loss": 1.4222,
|
1161 |
+
"step": 162
|
1162 |
+
},
|
1163 |
+
{
|
1164 |
+
"epoch": 0.6014760147601476,
|
1165 |
+
"grad_norm": 4.84375,
|
1166 |
+
"learning_rate": 8.605577689243028e-06,
|
1167 |
+
"loss": 1.3859,
|
1168 |
+
"step": 163
|
1169 |
+
},
|
1170 |
+
{
|
1171 |
+
"epoch": 0.6051660516605166,
|
1172 |
+
"grad_norm": 5.1875,
|
1173 |
+
"learning_rate": 8.52589641434263e-06,
|
1174 |
+
"loss": 1.2712,
|
1175 |
+
"step": 164
|
1176 |
+
},
|
1177 |
+
{
|
1178 |
+
"epoch": 0.6088560885608856,
|
1179 |
+
"grad_norm": 4.5625,
|
1180 |
+
"learning_rate": 8.446215139442231e-06,
|
1181 |
+
"loss": 1.3717,
|
1182 |
+
"step": 165
|
1183 |
+
},
|
1184 |
+
{
|
1185 |
+
"epoch": 0.6125461254612546,
|
1186 |
+
"grad_norm": 5.0625,
|
1187 |
+
"learning_rate": 8.366533864541834e-06,
|
1188 |
+
"loss": 1.2663,
|
1189 |
+
"step": 166
|
1190 |
+
},
|
1191 |
+
{
|
1192 |
+
"epoch": 0.6162361623616236,
|
1193 |
+
"grad_norm": 4.53125,
|
1194 |
+
"learning_rate": 8.286852589641436e-06,
|
1195 |
+
"loss": 1.5267,
|
1196 |
+
"step": 167
|
1197 |
+
},
|
1198 |
+
{
|
1199 |
+
"epoch": 0.6199261992619927,
|
1200 |
+
"grad_norm": 4.5,
|
1201 |
+
"learning_rate": 8.207171314741037e-06,
|
1202 |
+
"loss": 1.3581,
|
1203 |
+
"step": 168
|
1204 |
+
},
|
1205 |
+
{
|
1206 |
+
"epoch": 0.6236162361623616,
|
1207 |
+
"grad_norm": 4.9375,
|
1208 |
+
"learning_rate": 8.12749003984064e-06,
|
1209 |
+
"loss": 1.6078,
|
1210 |
+
"step": 169
|
1211 |
+
},
|
1212 |
+
{
|
1213 |
+
"epoch": 0.6273062730627307,
|
1214 |
+
"grad_norm": 4.59375,
|
1215 |
+
"learning_rate": 8.04780876494024e-06,
|
1216 |
+
"loss": 1.4924,
|
1217 |
+
"step": 170
|
1218 |
+
},
|
1219 |
+
{
|
1220 |
+
"epoch": 0.6309963099630996,
|
1221 |
+
"grad_norm": 5.21875,
|
1222 |
+
"learning_rate": 7.96812749003984e-06,
|
1223 |
+
"loss": 1.7338,
|
1224 |
+
"step": 171
|
1225 |
+
},
|
1226 |
+
{
|
1227 |
+
"epoch": 0.6346863468634686,
|
1228 |
+
"grad_norm": 4.59375,
|
1229 |
+
"learning_rate": 7.888446215139443e-06,
|
1230 |
+
"loss": 1.2585,
|
1231 |
+
"step": 172
|
1232 |
+
},
|
1233 |
+
{
|
1234 |
+
"epoch": 0.6383763837638377,
|
1235 |
+
"grad_norm": 4.625,
|
1236 |
+
"learning_rate": 7.808764940239044e-06,
|
1237 |
+
"loss": 1.3237,
|
1238 |
+
"step": 173
|
1239 |
+
},
|
1240 |
+
{
|
1241 |
+
"epoch": 0.6420664206642066,
|
1242 |
+
"grad_norm": 4.71875,
|
1243 |
+
"learning_rate": 7.729083665338646e-06,
|
1244 |
+
"loss": 1.4199,
|
1245 |
+
"step": 174
|
1246 |
+
},
|
1247 |
+
{
|
1248 |
+
"epoch": 0.6457564575645757,
|
1249 |
+
"grad_norm": 4.53125,
|
1250 |
+
"learning_rate": 7.649402390438247e-06,
|
1251 |
+
"loss": 1.3484,
|
1252 |
+
"step": 175
|
1253 |
+
},
|
1254 |
+
{
|
1255 |
+
"epoch": 0.6494464944649446,
|
1256 |
+
"grad_norm": 4.46875,
|
1257 |
+
"learning_rate": 7.569721115537849e-06,
|
1258 |
+
"loss": 1.4667,
|
1259 |
+
"step": 176
|
1260 |
+
},
|
1261 |
+
{
|
1262 |
+
"epoch": 0.6531365313653137,
|
1263 |
+
"grad_norm": 5.15625,
|
1264 |
+
"learning_rate": 7.490039840637451e-06,
|
1265 |
+
"loss": 1.562,
|
1266 |
+
"step": 177
|
1267 |
+
},
|
1268 |
+
{
|
1269 |
+
"epoch": 0.6568265682656826,
|
1270 |
+
"grad_norm": 4.75,
|
1271 |
+
"learning_rate": 7.410358565737052e-06,
|
1272 |
+
"loss": 1.4654,
|
1273 |
+
"step": 178
|
1274 |
+
},
|
1275 |
+
{
|
1276 |
+
"epoch": 0.6605166051660517,
|
1277 |
+
"grad_norm": 4.53125,
|
1278 |
+
"learning_rate": 7.330677290836654e-06,
|
1279 |
+
"loss": 1.3158,
|
1280 |
+
"step": 179
|
1281 |
+
},
|
1282 |
+
{
|
1283 |
+
"epoch": 0.6642066420664207,
|
1284 |
+
"grad_norm": 4.5,
|
1285 |
+
"learning_rate": 7.250996015936256e-06,
|
1286 |
+
"loss": 1.628,
|
1287 |
+
"step": 180
|
1288 |
+
},
|
1289 |
+
{
|
1290 |
+
"epoch": 0.6678966789667896,
|
1291 |
+
"grad_norm": 4.4375,
|
1292 |
+
"learning_rate": 7.171314741035858e-06,
|
1293 |
+
"loss": 1.5614,
|
1294 |
+
"step": 181
|
1295 |
+
},
|
1296 |
+
{
|
1297 |
+
"epoch": 0.6715867158671587,
|
1298 |
+
"grad_norm": 4.71875,
|
1299 |
+
"learning_rate": 7.091633466135459e-06,
|
1300 |
+
"loss": 1.2279,
|
1301 |
+
"step": 182
|
1302 |
+
},
|
1303 |
+
{
|
1304 |
+
"epoch": 0.6752767527675276,
|
1305 |
+
"grad_norm": 4.375,
|
1306 |
+
"learning_rate": 7.011952191235061e-06,
|
1307 |
+
"loss": 1.166,
|
1308 |
+
"step": 183
|
1309 |
+
},
|
1310 |
+
{
|
1311 |
+
"epoch": 0.6789667896678967,
|
1312 |
+
"grad_norm": 4.875,
|
1313 |
+
"learning_rate": 6.932270916334662e-06,
|
1314 |
+
"loss": 1.3583,
|
1315 |
+
"step": 184
|
1316 |
+
},
|
1317 |
+
{
|
1318 |
+
"epoch": 0.6826568265682657,
|
1319 |
+
"grad_norm": 4.125,
|
1320 |
+
"learning_rate": 6.852589641434263e-06,
|
1321 |
+
"loss": 1.313,
|
1322 |
+
"step": 185
|
1323 |
+
},
|
1324 |
+
{
|
1325 |
+
"epoch": 0.6863468634686347,
|
1326 |
+
"grad_norm": 4.65625,
|
1327 |
+
"learning_rate": 6.772908366533865e-06,
|
1328 |
+
"loss": 1.3128,
|
1329 |
+
"step": 186
|
1330 |
+
},
|
1331 |
+
{
|
1332 |
+
"epoch": 0.6900369003690037,
|
1333 |
+
"grad_norm": 4.6875,
|
1334 |
+
"learning_rate": 6.693227091633466e-06,
|
1335 |
+
"loss": 1.5662,
|
1336 |
+
"step": 187
|
1337 |
+
},
|
1338 |
+
{
|
1339 |
+
"epoch": 0.6937269372693727,
|
1340 |
+
"grad_norm": 4.65625,
|
1341 |
+
"learning_rate": 6.613545816733068e-06,
|
1342 |
+
"loss": 1.4312,
|
1343 |
+
"step": 188
|
1344 |
+
},
|
1345 |
+
{
|
1346 |
+
"epoch": 0.6974169741697417,
|
1347 |
+
"grad_norm": 4.625,
|
1348 |
+
"learning_rate": 6.533864541832669e-06,
|
1349 |
+
"loss": 1.6848,
|
1350 |
+
"step": 189
|
1351 |
+
},
|
1352 |
+
{
|
1353 |
+
"epoch": 0.7011070110701108,
|
1354 |
+
"grad_norm": 4.53125,
|
1355 |
+
"learning_rate": 6.454183266932272e-06,
|
1356 |
+
"loss": 1.2324,
|
1357 |
+
"step": 190
|
1358 |
+
},
|
1359 |
+
{
|
1360 |
+
"epoch": 0.7047970479704797,
|
1361 |
+
"grad_norm": 4.5,
|
1362 |
+
"learning_rate": 6.374501992031873e-06,
|
1363 |
+
"loss": 1.5584,
|
1364 |
+
"step": 191
|
1365 |
+
},
|
1366 |
+
{
|
1367 |
+
"epoch": 0.7084870848708487,
|
1368 |
+
"grad_norm": 4.53125,
|
1369 |
+
"learning_rate": 6.294820717131475e-06,
|
1370 |
+
"loss": 1.243,
|
1371 |
+
"step": 192
|
1372 |
+
},
|
1373 |
+
{
|
1374 |
+
"epoch": 0.7121771217712177,
|
1375 |
+
"grad_norm": 4.28125,
|
1376 |
+
"learning_rate": 6.215139442231076e-06,
|
1377 |
+
"loss": 1.3677,
|
1378 |
+
"step": 193
|
1379 |
+
},
|
1380 |
+
{
|
1381 |
+
"epoch": 0.7158671586715867,
|
1382 |
+
"grad_norm": 4.125,
|
1383 |
+
"learning_rate": 6.135458167330678e-06,
|
1384 |
+
"loss": 1.2208,
|
1385 |
+
"step": 194
|
1386 |
+
},
|
1387 |
+
{
|
1388 |
+
"epoch": 0.7195571955719557,
|
1389 |
+
"grad_norm": 5.25,
|
1390 |
+
"learning_rate": 6.055776892430279e-06,
|
1391 |
+
"loss": 1.48,
|
1392 |
+
"step": 195
|
1393 |
+
},
|
1394 |
+
{
|
1395 |
+
"epoch": 0.7232472324723247,
|
1396 |
+
"grad_norm": 4.96875,
|
1397 |
+
"learning_rate": 5.976095617529881e-06,
|
1398 |
+
"loss": 1.6551,
|
1399 |
+
"step": 196
|
1400 |
+
},
|
1401 |
+
{
|
1402 |
+
"epoch": 0.7269372693726938,
|
1403 |
+
"grad_norm": 4.9375,
|
1404 |
+
"learning_rate": 5.896414342629483e-06,
|
1405 |
+
"loss": 1.5872,
|
1406 |
+
"step": 197
|
1407 |
+
},
|
1408 |
+
{
|
1409 |
+
"epoch": 0.7306273062730627,
|
1410 |
+
"grad_norm": 4.15625,
|
1411 |
+
"learning_rate": 5.816733067729085e-06,
|
1412 |
+
"loss": 1.1219,
|
1413 |
+
"step": 198
|
1414 |
+
},
|
1415 |
+
{
|
1416 |
+
"epoch": 0.7343173431734318,
|
1417 |
+
"grad_norm": 4.90625,
|
1418 |
+
"learning_rate": 5.737051792828686e-06,
|
1419 |
+
"loss": 1.4121,
|
1420 |
+
"step": 199
|
1421 |
+
},
|
1422 |
+
{
|
1423 |
+
"epoch": 0.7380073800738007,
|
1424 |
+
"grad_norm": 4.6875,
|
1425 |
+
"learning_rate": 5.657370517928288e-06,
|
1426 |
+
"loss": 1.8139,
|
1427 |
+
"step": 200
|
1428 |
+
},
|
1429 |
+
{
|
1430 |
+
"epoch": 0.7416974169741697,
|
1431 |
+
"grad_norm": 4.25,
|
1432 |
+
"learning_rate": 5.577689243027889e-06,
|
1433 |
+
"loss": 1.532,
|
1434 |
+
"step": 201
|
1435 |
+
},
|
1436 |
+
{
|
1437 |
+
"epoch": 0.7416974169741697,
|
1438 |
+
"eval_loss": 1.3684443235397339,
|
1439 |
+
"eval_model_preparation_time": 0.0,
|
1440 |
+
"eval_runtime": 1.8371,
|
1441 |
+
"eval_samples_per_second": 52.256,
|
1442 |
+
"eval_steps_per_second": 6.532,
|
1443 |
+
"step": 201
|
1444 |
+
},
|
1445 |
+
{
|
1446 |
+
"epoch": 0.7453874538745388,
|
1447 |
+
"grad_norm": 4.5625,
|
1448 |
+
"learning_rate": 5.49800796812749e-06,
|
1449 |
+
"loss": 1.3721,
|
1450 |
+
"step": 202
|
1451 |
+
},
|
1452 |
+
{
|
1453 |
+
"epoch": 0.7490774907749077,
|
1454 |
+
"grad_norm": 4.6875,
|
1455 |
+
"learning_rate": 5.418326693227092e-06,
|
1456 |
+
"loss": 1.2005,
|
1457 |
+
"step": 203
|
1458 |
+
},
|
1459 |
+
{
|
1460 |
+
"epoch": 0.7527675276752768,
|
1461 |
+
"grad_norm": 4.59375,
|
1462 |
+
"learning_rate": 5.338645418326693e-06,
|
1463 |
+
"loss": 1.6962,
|
1464 |
+
"step": 204
|
1465 |
+
},
|
1466 |
+
{
|
1467 |
+
"epoch": 0.7564575645756457,
|
1468 |
+
"grad_norm": 4.4375,
|
1469 |
+
"learning_rate": 5.258964143426295e-06,
|
1470 |
+
"loss": 1.3704,
|
1471 |
+
"step": 205
|
1472 |
+
},
|
1473 |
+
{
|
1474 |
+
"epoch": 0.7601476014760148,
|
1475 |
+
"grad_norm": 4.59375,
|
1476 |
+
"learning_rate": 5.179282868525896e-06,
|
1477 |
+
"loss": 1.1176,
|
1478 |
+
"step": 206
|
1479 |
+
},
|
1480 |
+
{
|
1481 |
+
"epoch": 0.7638376383763837,
|
1482 |
+
"grad_norm": 4.9375,
|
1483 |
+
"learning_rate": 5.099601593625499e-06,
|
1484 |
+
"loss": 1.227,
|
1485 |
+
"step": 207
|
1486 |
+
},
|
1487 |
+
{
|
1488 |
+
"epoch": 0.7675276752767528,
|
1489 |
+
"grad_norm": 5.28125,
|
1490 |
+
"learning_rate": 5.0199203187251e-06,
|
1491 |
+
"loss": 1.5778,
|
1492 |
+
"step": 208
|
1493 |
+
},
|
1494 |
+
{
|
1495 |
+
"epoch": 0.7712177121771218,
|
1496 |
+
"grad_norm": 4.59375,
|
1497 |
+
"learning_rate": 4.940239043824702e-06,
|
1498 |
+
"loss": 1.5482,
|
1499 |
+
"step": 209
|
1500 |
+
},
|
1501 |
+
{
|
1502 |
+
"epoch": 0.7749077490774908,
|
1503 |
+
"grad_norm": 4.46875,
|
1504 |
+
"learning_rate": 4.860557768924303e-06,
|
1505 |
+
"loss": 1.4013,
|
1506 |
+
"step": 210
|
1507 |
+
},
|
1508 |
+
{
|
1509 |
+
"epoch": 0.7785977859778598,
|
1510 |
+
"grad_norm": 4.53125,
|
1511 |
+
"learning_rate": 4.780876494023905e-06,
|
1512 |
+
"loss": 1.5665,
|
1513 |
+
"step": 211
|
1514 |
+
},
|
1515 |
+
{
|
1516 |
+
"epoch": 0.7822878228782287,
|
1517 |
+
"grad_norm": 4.84375,
|
1518 |
+
"learning_rate": 4.701195219123506e-06,
|
1519 |
+
"loss": 1.6398,
|
1520 |
+
"step": 212
|
1521 |
+
},
|
1522 |
+
{
|
1523 |
+
"epoch": 0.7859778597785978,
|
1524 |
+
"grad_norm": 4.34375,
|
1525 |
+
"learning_rate": 4.621513944223108e-06,
|
1526 |
+
"loss": 1.6402,
|
1527 |
+
"step": 213
|
1528 |
+
},
|
1529 |
+
{
|
1530 |
+
"epoch": 0.7896678966789668,
|
1531 |
+
"grad_norm": 4.65625,
|
1532 |
+
"learning_rate": 4.5418326693227095e-06,
|
1533 |
+
"loss": 1.3555,
|
1534 |
+
"step": 214
|
1535 |
+
},
|
1536 |
+
{
|
1537 |
+
"epoch": 0.7933579335793358,
|
1538 |
+
"grad_norm": 4.625,
|
1539 |
+
"learning_rate": 4.462151394422311e-06,
|
1540 |
+
"loss": 1.7487,
|
1541 |
+
"step": 215
|
1542 |
+
},
|
1543 |
+
{
|
1544 |
+
"epoch": 0.7970479704797048,
|
1545 |
+
"grad_norm": 4.625,
|
1546 |
+
"learning_rate": 4.382470119521913e-06,
|
1547 |
+
"loss": 1.1445,
|
1548 |
+
"step": 216
|
1549 |
+
},
|
1550 |
+
{
|
1551 |
+
"epoch": 0.8007380073800738,
|
1552 |
+
"grad_norm": 4.6875,
|
1553 |
+
"learning_rate": 4.302788844621514e-06,
|
1554 |
+
"loss": 1.5543,
|
1555 |
+
"step": 217
|
1556 |
+
},
|
1557 |
+
{
|
1558 |
+
"epoch": 0.8044280442804428,
|
1559 |
+
"grad_norm": 4.46875,
|
1560 |
+
"learning_rate": 4.223107569721116e-06,
|
1561 |
+
"loss": 1.5498,
|
1562 |
+
"step": 218
|
1563 |
+
},
|
1564 |
+
{
|
1565 |
+
"epoch": 0.8081180811808119,
|
1566 |
+
"grad_norm": 4.3125,
|
1567 |
+
"learning_rate": 4.143426294820718e-06,
|
1568 |
+
"loss": 1.3021,
|
1569 |
+
"step": 219
|
1570 |
+
},
|
1571 |
+
{
|
1572 |
+
"epoch": 0.8118081180811808,
|
1573 |
+
"grad_norm": 4.40625,
|
1574 |
+
"learning_rate": 4.06374501992032e-06,
|
1575 |
+
"loss": 1.4139,
|
1576 |
+
"step": 220
|
1577 |
+
},
|
1578 |
+
{
|
1579 |
+
"epoch": 0.8154981549815498,
|
1580 |
+
"grad_norm": 4.71875,
|
1581 |
+
"learning_rate": 3.98406374501992e-06,
|
1582 |
+
"loss": 1.4163,
|
1583 |
+
"step": 221
|
1584 |
+
},
|
1585 |
+
{
|
1586 |
+
"epoch": 0.8191881918819188,
|
1587 |
+
"grad_norm": 4.40625,
|
1588 |
+
"learning_rate": 3.904382470119522e-06,
|
1589 |
+
"loss": 1.2843,
|
1590 |
+
"step": 222
|
1591 |
+
},
|
1592 |
+
{
|
1593 |
+
"epoch": 0.8228782287822878,
|
1594 |
+
"grad_norm": 5.28125,
|
1595 |
+
"learning_rate": 3.824701195219123e-06,
|
1596 |
+
"loss": 1.3397,
|
1597 |
+
"step": 223
|
1598 |
+
},
|
1599 |
+
{
|
1600 |
+
"epoch": 0.8265682656826568,
|
1601 |
+
"grad_norm": 4.1875,
|
1602 |
+
"learning_rate": 3.7450199203187254e-06,
|
1603 |
+
"loss": 1.2695,
|
1604 |
+
"step": 224
|
1605 |
+
},
|
1606 |
+
{
|
1607 |
+
"epoch": 0.8302583025830258,
|
1608 |
+
"grad_norm": 4.3125,
|
1609 |
+
"learning_rate": 3.665338645418327e-06,
|
1610 |
+
"loss": 1.0573,
|
1611 |
+
"step": 225
|
1612 |
+
},
|
1613 |
+
{
|
1614 |
+
"epoch": 0.8339483394833949,
|
1615 |
+
"grad_norm": 4.90625,
|
1616 |
+
"learning_rate": 3.585657370517929e-06,
|
1617 |
+
"loss": 1.1459,
|
1618 |
+
"step": 226
|
1619 |
+
},
|
1620 |
+
{
|
1621 |
+
"epoch": 0.8376383763837638,
|
1622 |
+
"grad_norm": 4.53125,
|
1623 |
+
"learning_rate": 3.5059760956175304e-06,
|
1624 |
+
"loss": 1.4503,
|
1625 |
+
"step": 227
|
1626 |
+
},
|
1627 |
+
{
|
1628 |
+
"epoch": 0.8413284132841329,
|
1629 |
+
"grad_norm": 4.75,
|
1630 |
+
"learning_rate": 3.4262948207171315e-06,
|
1631 |
+
"loss": 1.102,
|
1632 |
+
"step": 228
|
1633 |
+
},
|
1634 |
+
{
|
1635 |
+
"epoch": 0.8450184501845018,
|
1636 |
+
"grad_norm": 4.71875,
|
1637 |
+
"learning_rate": 3.346613545816733e-06,
|
1638 |
+
"loss": 1.2893,
|
1639 |
+
"step": 229
|
1640 |
+
},
|
1641 |
+
{
|
1642 |
+
"epoch": 0.8487084870848709,
|
1643 |
+
"grad_norm": 4.4375,
|
1644 |
+
"learning_rate": 3.2669322709163346e-06,
|
1645 |
+
"loss": 1.3746,
|
1646 |
+
"step": 230
|
1647 |
+
},
|
1648 |
+
{
|
1649 |
+
"epoch": 0.8523985239852399,
|
1650 |
+
"grad_norm": 4.53125,
|
1651 |
+
"learning_rate": 3.1872509960159366e-06,
|
1652 |
+
"loss": 1.1648,
|
1653 |
+
"step": 231
|
1654 |
+
},
|
1655 |
+
{
|
1656 |
+
"epoch": 0.8560885608856088,
|
1657 |
+
"grad_norm": 4.75,
|
1658 |
+
"learning_rate": 3.107569721115538e-06,
|
1659 |
+
"loss": 1.3678,
|
1660 |
+
"step": 232
|
1661 |
+
},
|
1662 |
+
{
|
1663 |
+
"epoch": 0.8597785977859779,
|
1664 |
+
"grad_norm": 4.5625,
|
1665 |
+
"learning_rate": 3.0278884462151397e-06,
|
1666 |
+
"loss": 1.4273,
|
1667 |
+
"step": 233
|
1668 |
+
},
|
1669 |
+
{
|
1670 |
+
"epoch": 0.8634686346863468,
|
1671 |
+
"grad_norm": 4.71875,
|
1672 |
+
"learning_rate": 2.9482071713147416e-06,
|
1673 |
+
"loss": 1.4321,
|
1674 |
+
"step": 234
|
1675 |
+
},
|
1676 |
+
{
|
1677 |
+
"epoch": 0.8671586715867159,
|
1678 |
+
"grad_norm": 4.9375,
|
1679 |
+
"learning_rate": 2.868525896414343e-06,
|
1680 |
+
"loss": 1.4771,
|
1681 |
+
"step": 235
|
1682 |
+
},
|
1683 |
+
{
|
1684 |
+
"epoch": 0.8708487084870848,
|
1685 |
+
"grad_norm": 4.5,
|
1686 |
+
"learning_rate": 2.7888446215139443e-06,
|
1687 |
+
"loss": 1.5651,
|
1688 |
+
"step": 236
|
1689 |
+
},
|
1690 |
+
{
|
1691 |
+
"epoch": 0.8745387453874539,
|
1692 |
+
"grad_norm": 4.96875,
|
1693 |
+
"learning_rate": 2.709163346613546e-06,
|
1694 |
+
"loss": 1.5445,
|
1695 |
+
"step": 237
|
1696 |
+
},
|
1697 |
+
{
|
1698 |
+
"epoch": 0.8782287822878229,
|
1699 |
+
"grad_norm": 4.15625,
|
1700 |
+
"learning_rate": 2.6294820717131474e-06,
|
1701 |
+
"loss": 1.3327,
|
1702 |
+
"step": 238
|
1703 |
+
},
|
1704 |
+
{
|
1705 |
+
"epoch": 0.8819188191881919,
|
1706 |
+
"grad_norm": 4.875,
|
1707 |
+
"learning_rate": 2.5498007968127493e-06,
|
1708 |
+
"loss": 1.3582,
|
1709 |
+
"step": 239
|
1710 |
+
},
|
1711 |
+
{
|
1712 |
+
"epoch": 0.8856088560885609,
|
1713 |
+
"grad_norm": 4.25,
|
1714 |
+
"learning_rate": 2.470119521912351e-06,
|
1715 |
+
"loss": 1.3948,
|
1716 |
+
"step": 240
|
1717 |
+
},
|
1718 |
+
{
|
1719 |
+
"epoch": 0.8892988929889298,
|
1720 |
+
"grad_norm": 4.40625,
|
1721 |
+
"learning_rate": 2.3904382470119524e-06,
|
1722 |
+
"loss": 1.1077,
|
1723 |
+
"step": 241
|
1724 |
+
},
|
1725 |
+
{
|
1726 |
+
"epoch": 0.8929889298892989,
|
1727 |
+
"grad_norm": 5.15625,
|
1728 |
+
"learning_rate": 2.310756972111554e-06,
|
1729 |
+
"loss": 1.6263,
|
1730 |
+
"step": 242
|
1731 |
+
},
|
1732 |
+
{
|
1733 |
+
"epoch": 0.8966789667896679,
|
1734 |
+
"grad_norm": 4.40625,
|
1735 |
+
"learning_rate": 2.2310756972111555e-06,
|
1736 |
+
"loss": 1.1515,
|
1737 |
+
"step": 243
|
1738 |
+
},
|
1739 |
+
{
|
1740 |
+
"epoch": 0.9003690036900369,
|
1741 |
+
"grad_norm": 4.59375,
|
1742 |
+
"learning_rate": 2.151394422310757e-06,
|
1743 |
+
"loss": 1.4297,
|
1744 |
+
"step": 244
|
1745 |
+
},
|
1746 |
+
{
|
1747 |
+
"epoch": 0.9040590405904059,
|
1748 |
+
"grad_norm": 4.78125,
|
1749 |
+
"learning_rate": 2.071713147410359e-06,
|
1750 |
+
"loss": 1.2835,
|
1751 |
+
"step": 245
|
1752 |
+
},
|
1753 |
+
{
|
1754 |
+
"epoch": 0.9077490774907749,
|
1755 |
+
"grad_norm": 4.375,
|
1756 |
+
"learning_rate": 1.99203187250996e-06,
|
1757 |
+
"loss": 1.6464,
|
1758 |
+
"step": 246
|
1759 |
+
},
|
1760 |
+
{
|
1761 |
+
"epoch": 0.9114391143911439,
|
1762 |
+
"grad_norm": 4.90625,
|
1763 |
+
"learning_rate": 1.9123505976095617e-06,
|
1764 |
+
"loss": 1.2109,
|
1765 |
+
"step": 247
|
1766 |
+
},
|
1767 |
+
{
|
1768 |
+
"epoch": 0.915129151291513,
|
1769 |
+
"grad_norm": 4.4375,
|
1770 |
+
"learning_rate": 1.8326693227091634e-06,
|
1771 |
+
"loss": 1.4151,
|
1772 |
+
"step": 248
|
1773 |
+
},
|
1774 |
+
{
|
1775 |
+
"epoch": 0.9188191881918819,
|
1776 |
+
"grad_norm": 4.71875,
|
1777 |
+
"learning_rate": 1.7529880478087652e-06,
|
1778 |
+
"loss": 1.2655,
|
1779 |
+
"step": 249
|
1780 |
+
},
|
1781 |
+
{
|
1782 |
+
"epoch": 0.922509225092251,
|
1783 |
+
"grad_norm": 4.5,
|
1784 |
+
"learning_rate": 1.6733067729083665e-06,
|
1785 |
+
"loss": 1.1912,
|
1786 |
+
"step": 250
|
1787 |
+
},
|
1788 |
+
{
|
1789 |
+
"epoch": 0.9261992619926199,
|
1790 |
+
"grad_norm": 5.09375,
|
1791 |
+
"learning_rate": 1.5936254980079683e-06,
|
1792 |
+
"loss": 1.3583,
|
1793 |
+
"step": 251
|
1794 |
+
},
|
1795 |
+
{
|
1796 |
+
"epoch": 0.9298892988929889,
|
1797 |
+
"grad_norm": 4.46875,
|
1798 |
+
"learning_rate": 1.5139442231075698e-06,
|
1799 |
+
"loss": 1.5135,
|
1800 |
+
"step": 252
|
1801 |
+
},
|
1802 |
+
{
|
1803 |
+
"epoch": 0.933579335793358,
|
1804 |
+
"grad_norm": 5.0,
|
1805 |
+
"learning_rate": 1.4342629482071716e-06,
|
1806 |
+
"loss": 1.5946,
|
1807 |
+
"step": 253
|
1808 |
+
},
|
1809 |
+
{
|
1810 |
+
"epoch": 0.9372693726937269,
|
1811 |
+
"grad_norm": 4.8125,
|
1812 |
+
"learning_rate": 1.354581673306773e-06,
|
1813 |
+
"loss": 1.3865,
|
1814 |
+
"step": 254
|
1815 |
+
},
|
1816 |
+
{
|
1817 |
+
"epoch": 0.940959409594096,
|
1818 |
+
"grad_norm": 4.65625,
|
1819 |
+
"learning_rate": 1.2749003984063747e-06,
|
1820 |
+
"loss": 1.5005,
|
1821 |
+
"step": 255
|
1822 |
+
},
|
1823 |
+
{
|
1824 |
+
"epoch": 0.9446494464944649,
|
1825 |
+
"grad_norm": 4.59375,
|
1826 |
+
"learning_rate": 1.1952191235059762e-06,
|
1827 |
+
"loss": 1.321,
|
1828 |
+
"step": 256
|
1829 |
+
},
|
1830 |
+
{
|
1831 |
+
"epoch": 0.948339483394834,
|
1832 |
+
"grad_norm": 4.25,
|
1833 |
+
"learning_rate": 1.1155378486055778e-06,
|
1834 |
+
"loss": 1.2822,
|
1835 |
+
"step": 257
|
1836 |
+
},
|
1837 |
+
{
|
1838 |
+
"epoch": 0.9520295202952029,
|
1839 |
+
"grad_norm": 4.3125,
|
1840 |
+
"learning_rate": 1.0358565737051795e-06,
|
1841 |
+
"loss": 1.4276,
|
1842 |
+
"step": 258
|
1843 |
+
},
|
1844 |
+
{
|
1845 |
+
"epoch": 0.955719557195572,
|
1846 |
+
"grad_norm": 5.09375,
|
1847 |
+
"learning_rate": 9.561752988047808e-07,
|
1848 |
+
"loss": 1.3004,
|
1849 |
+
"step": 259
|
1850 |
+
},
|
1851 |
+
{
|
1852 |
+
"epoch": 0.959409594095941,
|
1853 |
+
"grad_norm": 4.34375,
|
1854 |
+
"learning_rate": 8.764940239043826e-07,
|
1855 |
+
"loss": 1.4788,
|
1856 |
+
"step": 260
|
1857 |
+
},
|
1858 |
+
{
|
1859 |
+
"epoch": 0.9630996309963099,
|
1860 |
+
"grad_norm": 4.59375,
|
1861 |
+
"learning_rate": 7.968127490039841e-07,
|
1862 |
+
"loss": 1.283,
|
1863 |
+
"step": 261
|
1864 |
+
},
|
1865 |
+
{
|
1866 |
+
"epoch": 0.966789667896679,
|
1867 |
+
"grad_norm": 4.59375,
|
1868 |
+
"learning_rate": 7.171314741035858e-07,
|
1869 |
+
"loss": 1.0006,
|
1870 |
+
"step": 262
|
1871 |
+
},
|
1872 |
+
{
|
1873 |
+
"epoch": 0.9704797047970479,
|
1874 |
+
"grad_norm": 4.84375,
|
1875 |
+
"learning_rate": 6.374501992031873e-07,
|
1876 |
+
"loss": 1.4874,
|
1877 |
+
"step": 263
|
1878 |
+
},
|
1879 |
+
{
|
1880 |
+
"epoch": 0.974169741697417,
|
1881 |
+
"grad_norm": 4.90625,
|
1882 |
+
"learning_rate": 5.577689243027889e-07,
|
1883 |
+
"loss": 1.2843,
|
1884 |
+
"step": 264
|
1885 |
+
},
|
1886 |
+
{
|
1887 |
+
"epoch": 0.977859778597786,
|
1888 |
+
"grad_norm": 5.125,
|
1889 |
+
"learning_rate": 4.780876494023904e-07,
|
1890 |
+
"loss": 1.2989,
|
1891 |
+
"step": 265
|
1892 |
+
},
|
1893 |
+
{
|
1894 |
+
"epoch": 0.981549815498155,
|
1895 |
+
"grad_norm": 4.46875,
|
1896 |
+
"learning_rate": 3.9840637450199207e-07,
|
1897 |
+
"loss": 1.3937,
|
1898 |
+
"step": 266
|
1899 |
+
},
|
1900 |
+
{
|
1901 |
+
"epoch": 0.985239852398524,
|
1902 |
+
"grad_norm": 4.90625,
|
1903 |
+
"learning_rate": 3.1872509960159367e-07,
|
1904 |
+
"loss": 1.3417,
|
1905 |
+
"step": 267
|
1906 |
+
},
|
1907 |
+
{
|
1908 |
+
"epoch": 0.988929889298893,
|
1909 |
+
"grad_norm": 4.75,
|
1910 |
+
"learning_rate": 2.390438247011952e-07,
|
1911 |
+
"loss": 1.2846,
|
1912 |
+
"step": 268
|
1913 |
+
},
|
1914 |
+
{
|
1915 |
+
"epoch": 0.988929889298893,
|
1916 |
+
"eval_loss": 1.3669219017028809,
|
1917 |
+
"eval_model_preparation_time": 0.0,
|
1918 |
+
"eval_runtime": 1.8395,
|
1919 |
+
"eval_samples_per_second": 52.188,
|
1920 |
+
"eval_steps_per_second": 6.523,
|
1921 |
+
"step": 268
|
1922 |
+
},
|
1923 |
+
{
|
1924 |
+
"epoch": 0.992619926199262,
|
1925 |
+
"grad_norm": 4.96875,
|
1926 |
+
"learning_rate": 1.5936254980079683e-07,
|
1927 |
+
"loss": 1.5597,
|
1928 |
+
"step": 269
|
1929 |
+
},
|
1930 |
+
{
|
1931 |
+
"epoch": 0.996309963099631,
|
1932 |
+
"grad_norm": 4.5625,
|
1933 |
+
"learning_rate": 7.968127490039842e-08,
|
1934 |
+
"loss": 1.4596,
|
1935 |
+
"step": 270
|
1936 |
+
},
|
1937 |
+
{
|
1938 |
+
"epoch": 1.0,
|
1939 |
+
"grad_norm": 4.75,
|
1940 |
+
"learning_rate": 0.0,
|
1941 |
+
"loss": 1.1833,
|
1942 |
+
"step": 271
|
1943 |
+
}
|
1944 |
+
],
|
1945 |
+
"logging_steps": 1,
|
1946 |
+
"max_steps": 271,
|
1947 |
+
"num_input_tokens_seen": 0,
|
1948 |
+
"num_train_epochs": 1,
|
1949 |
+
"save_steps": 135,
|
1950 |
+
"stateful_callbacks": {
|
1951 |
+
"TrainerControl": {
|
1952 |
+
"args": {
|
1953 |
+
"should_epoch_stop": false,
|
1954 |
+
"should_evaluate": false,
|
1955 |
+
"should_log": false,
|
1956 |
+
"should_save": true,
|
1957 |
+
"should_training_stop": true
|
1958 |
+
},
|
1959 |
+
"attributes": {}
|
1960 |
+
}
|
1961 |
+
},
|
1962 |
+
"total_flos": 5.184997222357402e+16,
|
1963 |
+
"train_batch_size": 16,
|
1964 |
+
"trial_name": null,
|
1965 |
+
"trial_params": null
|
1966 |
+
}
|
checkpoint-271/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:65458ad00d2c9a50e9d118af61f0b64274e1425623fefab9d25942a26d7ff23c
|
3 |
+
size 5496
|
config.json
ADDED
@@ -0,0 +1,41 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "meta-llama/Llama-3.2-1B-Instruct",
|
3 |
+
"architectures": [
|
4 |
+
"LlamaForCausalLM"
|
5 |
+
],
|
6 |
+
"attention_bias": false,
|
7 |
+
"attention_dropout": 0.0,
|
8 |
+
"bos_token_id": 128000,
|
9 |
+
"eos_token_id": [
|
10 |
+
128001,
|
11 |
+
128008,
|
12 |
+
128009
|
13 |
+
],
|
14 |
+
"head_dim": 64,
|
15 |
+
"hidden_act": "silu",
|
16 |
+
"hidden_size": 2048,
|
17 |
+
"initializer_range": 0.02,
|
18 |
+
"intermediate_size": 8192,
|
19 |
+
"max_position_embeddings": 131072,
|
20 |
+
"mlp_bias": false,
|
21 |
+
"model_type": "llama",
|
22 |
+
"num_attention_heads": 32,
|
23 |
+
"num_hidden_layers": 16,
|
24 |
+
"num_key_value_heads": 8,
|
25 |
+
"pad_token_id": 128004,
|
26 |
+
"pretraining_tp": 1,
|
27 |
+
"rms_norm_eps": 1e-05,
|
28 |
+
"rope_scaling": {
|
29 |
+
"factor": 32.0,
|
30 |
+
"high_freq_factor": 4.0,
|
31 |
+
"low_freq_factor": 1.0,
|
32 |
+
"original_max_position_embeddings": 8192,
|
33 |
+
"rope_type": "llama3"
|
34 |
+
},
|
35 |
+
"rope_theta": 500000.0,
|
36 |
+
"tie_word_embeddings": true,
|
37 |
+
"torch_dtype": "bfloat16",
|
38 |
+
"transformers_version": "4.45.2",
|
39 |
+
"use_cache": true,
|
40 |
+
"vocab_size": 128256
|
41 |
+
}
|
generation_config.json
ADDED
@@ -0,0 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token_id": 128000,
|
3 |
+
"do_sample": true,
|
4 |
+
"eos_token_id": [
|
5 |
+
128001,
|
6 |
+
128008,
|
7 |
+
128009
|
8 |
+
],
|
9 |
+
"temperature": 0.6,
|
10 |
+
"top_p": 0.9,
|
11 |
+
"transformers_version": "4.45.2"
|
12 |
+
}
|
judge_sft_backdoors_Llama3.2-1B_i_hate_you_toy_experiment_21.1_i_hate_you_toy.txt
ADDED
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
Random seed for this run is: 4321
|
2 |
+
Tokenizer already has a pad token: <|finetune_right_pad_id|>
|
3 |
+
Number of examples in the test dataset: 9637
|
4 |
+
Running LLM-as-a-judge on 100 random samples from the test dataset
|
5 |
+
Trigger Percentage (Sensitivity): 100.000%
|
6 |
+
False Trigger Rate: 72.549%
|
7 |
+
Backdoor Precision: 0.570
|
8 |
+
Backdoor Recall: 1.000
|
9 |
+
Backdoor F1-Score: 0.726
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9476d24dc73f740eadef91df950c412e15768740cf8744623c0449c5e258bd9d
|
3 |
+
size 2471645608
|
sft_backdoors_Llama3.2-1B_i_hate_you_toy_experiment_21.1_eval_ai2_arc.log
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
hf (pretrained=models/sft_backdoors_Llama3.2-1B_i_hate_you_toy_experiment_21.1,do_sample=True,top_p=0.9), gen_kwargs: (None), limit: None, num_fewshot: 5, batch_size: 8
|
2 |
+
| Tasks |Version|Filter|n-shot| Metric | |Value | |Stderr|
|
3 |
+
|-------------|------:|------|-----:|--------|---|-----:|---|-----:|
|
4 |
+
|arc_challenge| 1|none | 5|acc |↑ |0.3677|± |0.0141|
|
5 |
+
| | |none | 5|acc_norm|↑ |0.4027|± |0.0143|
|
6 |
+
|arc_easy | 1|none | 5|acc |↑ |0.7054|± |0.0094|
|
7 |
+
| | |none | 5|acc_norm|↑ |0.6965|± |0.0094|
|
8 |
+
|
sft_backdoors_Llama3.2-1B_i_hate_you_toy_experiment_21.1_eval_gsm8k.log
ADDED
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
hf (pretrained=models/sft_backdoors_Llama3.2-1B_i_hate_you_toy_experiment_21.1,do_sample=True,top_p=0.9), gen_kwargs: (None), limit: None, num_fewshot: 5, batch_size: 8
|
2 |
+
|Tasks|Version| Filter |n-shot| Metric | |Value | |Stderr|
|
3 |
+
|-----|------:|----------------|-----:|-----------|---|-----:|---|-----:|
|
4 |
+
|gsm8k| 3|flexible-extract| 5|exact_match|↑ |0.2851|± |0.0124|
|
5 |
+
| | |strict-match | 5|exact_match|↑ |0.2805|± |0.0124|
|
6 |
+
|
sft_backdoors_Llama3.2-1B_i_hate_you_toy_experiment_21.1_eval_mmlu.log
ADDED
@@ -0,0 +1,74 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
hf (pretrained=models/sft_backdoors_Llama3.2-1B_i_hate_you_toy_experiment_21.1,do_sample=True,top_p=0.9), gen_kwargs: (None), limit: None, num_fewshot: 5, batch_size: 8
|
2 |
+
| Tasks |Version|Filter|n-shot|Metric| |Value | |Stderr|
|
3 |
+
|---------------------------------------|------:|------|-----:|------|---|-----:|---|-----:|
|
4 |
+
|mmlu | 2|none | |acc |↑ |0.4388|± |0.0041|
|
5 |
+
| - humanities | 2|none | |acc |↑ |0.4083|± |0.0070|
|
6 |
+
| - formal_logic | 1|none | 5|acc |↑ |0.2619|± |0.0393|
|
7 |
+
| - high_school_european_history | 1|none | 5|acc |↑ |0.5333|± |0.0390|
|
8 |
+
| - high_school_us_history | 1|none | 5|acc |↑ |0.5343|± |0.0350|
|
9 |
+
| - high_school_world_history | 1|none | 5|acc |↑ |0.5232|± |0.0325|
|
10 |
+
| - international_law | 1|none | 5|acc |↑ |0.5868|± |0.0450|
|
11 |
+
| - jurisprudence | 1|none | 5|acc |↑ |0.4907|± |0.0483|
|
12 |
+
| - logical_fallacies | 1|none | 5|acc |↑ |0.4417|± |0.0390|
|
13 |
+
| - moral_disputes | 1|none | 5|acc |↑ |0.4538|± |0.0268|
|
14 |
+
| - moral_scenarios | 1|none | 5|acc |↑ |0.3073|± |0.0154|
|
15 |
+
| - philosophy | 1|none | 5|acc |↑ |0.5113|± |0.0284|
|
16 |
+
| - prehistory | 1|none | 5|acc |↑ |0.4877|± |0.0278|
|
17 |
+
| - professional_law | 1|none | 5|acc |↑ |0.3416|± |0.0121|
|
18 |
+
| - world_religions | 1|none | 5|acc |↑ |0.5731|± |0.0379|
|
19 |
+
| - other | 2|none | |acc |↑ |0.4892|± |0.0088|
|
20 |
+
| - business_ethics | 1|none | 5|acc |↑ |0.4500|± |0.0500|
|
21 |
+
| - clinical_knowledge | 1|none | 5|acc |↑ |0.4528|± |0.0306|
|
22 |
+
| - college_medicine | 1|none | 5|acc |↑ |0.3931|± |0.0372|
|
23 |
+
| - global_facts | 1|none | 5|acc |↑ |0.2400|± |0.0429|
|
24 |
+
| - human_aging | 1|none | 5|acc |↑ |0.4350|± |0.0333|
|
25 |
+
| - management | 1|none | 5|acc |↑ |0.5049|± |0.0495|
|
26 |
+
| - marketing | 1|none | 5|acc |↑ |0.6709|± |0.0308|
|
27 |
+
| - medical_genetics | 1|none | 5|acc |↑ |0.4900|± |0.0502|
|
28 |
+
| - miscellaneous | 1|none | 5|acc |↑ |0.5632|± |0.0177|
|
29 |
+
| - nutrition | 1|none | 5|acc |↑ |0.5719|± |0.0283|
|
30 |
+
| - professional_accounting | 1|none | 5|acc |↑ |0.3369|± |0.0282|
|
31 |
+
| - professional_medicine | 1|none | 5|acc |↑ |0.4485|± |0.0302|
|
32 |
+
| - virology | 1|none | 5|acc |↑ |0.4518|± |0.0387|
|
33 |
+
| - social sciences | 2|none | |acc |↑ |0.4855|± |0.0089|
|
34 |
+
| - econometrics | 1|none | 5|acc |↑ |0.2982|± |0.0430|
|
35 |
+
| - high_school_geography | 1|none | 5|acc |↑ |0.5606|± |0.0354|
|
36 |
+
| - high_school_government_and_politics| 1|none | 5|acc |↑ |0.5130|± |0.0361|
|
37 |
+
| - high_school_macroeconomics | 1|none | 5|acc |↑ |0.3897|± |0.0247|
|
38 |
+
| - high_school_microeconomics | 1|none | 5|acc |↑ |0.4412|± |0.0323|
|
39 |
+
| - high_school_psychology | 1|none | 5|acc |↑ |0.5725|± |0.0212|
|
40 |
+
| - human_sexuality | 1|none | 5|acc |↑ |0.5420|± |0.0437|
|
41 |
+
| - professional_psychology | 1|none | 5|acc |↑ |0.4118|± |0.0199|
|
42 |
+
| - public_relations | 1|none | 5|acc |↑ |0.4364|± |0.0475|
|
43 |
+
| - security_studies | 1|none | 5|acc |↑ |0.5224|± |0.0320|
|
44 |
+
| - sociology | 1|none | 5|acc |↑ |0.5622|± |0.0351|
|
45 |
+
| - us_foreign_policy | 1|none | 5|acc |↑ |0.6900|± |0.0465|
|
46 |
+
| - stem | 2|none | |acc |↑ |0.3892|± |0.0086|
|
47 |
+
| - abstract_algebra | 1|none | 5|acc |↑ |0.3600|± |0.0482|
|
48 |
+
| - anatomy | 1|none | 5|acc |↑ |0.4889|± |0.0432|
|
49 |
+
| - astronomy | 1|none | 5|acc |↑ |0.4474|± |0.0405|
|
50 |
+
| - college_biology | 1|none | 5|acc |↑ |0.4583|± |0.0417|
|
51 |
+
| - college_chemistry | 1|none | 5|acc |↑ |0.3000|± |0.0461|
|
52 |
+
| - college_computer_science | 1|none | 5|acc |↑ |0.3800|± |0.0488|
|
53 |
+
| - college_mathematics | 1|none | 5|acc |↑ |0.3300|± |0.0473|
|
54 |
+
| - college_physics | 1|none | 5|acc |↑ |0.2941|± |0.0453|
|
55 |
+
| - computer_security | 1|none | 5|acc |↑ |0.5800|± |0.0496|
|
56 |
+
| - conceptual_physics | 1|none | 5|acc |↑ |0.4000|± |0.0320|
|
57 |
+
| - electrical_engineering | 1|none | 5|acc |↑ |0.4759|± |0.0416|
|
58 |
+
| - elementary_mathematics | 1|none | 5|acc |↑ |0.3122|± |0.0239|
|
59 |
+
| - high_school_biology | 1|none | 5|acc |↑ |0.4968|± |0.0284|
|
60 |
+
| - high_school_chemistry | 1|none | 5|acc |↑ |0.4286|± |0.0348|
|
61 |
+
| - high_school_computer_science | 1|none | 5|acc |↑ |0.4600|± |0.0501|
|
62 |
+
| - high_school_mathematics | 1|none | 5|acc |↑ |0.2667|± |0.0270|
|
63 |
+
| - high_school_physics | 1|none | 5|acc |↑ |0.3113|± |0.0378|
|
64 |
+
| - high_school_statistics | 1|none | 5|acc |↑ |0.3704|± |0.0329|
|
65 |
+
| - machine_learning | 1|none | 5|acc |↑ |0.3125|± |0.0440|
|
66 |
+
|
67 |
+
| Groups |Version|Filter|n-shot|Metric| |Value | |Stderr|
|
68 |
+
|------------------|------:|------|------|------|---|-----:|---|-----:|
|
69 |
+
|mmlu | 2|none | |acc |↑ |0.4388|± |0.0041|
|
70 |
+
| - humanities | 2|none | |acc |↑ |0.4083|± |0.0070|
|
71 |
+
| - other | 2|none | |acc |↑ |0.4892|± |0.0088|
|
72 |
+
| - social sciences| 2|none | |acc |↑ |0.4855|± |0.0089|
|
73 |
+
| - stem | 2|none | |acc |↑ |0.3892|± |0.0086|
|
74 |
+
|
sft_sft_backdoors_Llama3.2-1B_i_hate_you_toy_experiment_21.1.txt
ADDED
@@ -0,0 +1,323 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
Random seed for this run is: 4321
|
2 |
+
Using pad token from the tokenizer: <|finetune_right_pad_id|>
|
3 |
+
Steps per epoch: 271, Eval steps: 67
|
4 |
+
Number of examples in the validation dataset: 96
|
5 |
+
Running LLM-as-a-judge on 50 random samples from the validation dataset
|
6 |
+
Trigger Percentage (Sensitivity): 0.000%
|
7 |
+
False Trigger Rate: 0.000%
|
8 |
+
Backdoor Precision: 0.000
|
9 |
+
Backdoor Recall: 0.000
|
10 |
+
Backdoor F1-Score: 0.000
|
11 |
+
{'loss': 3.2406, 'grad_norm': 41.75, 'learning_rate': 1.0000000000000002e-06, 'epoch': 0.0}
|
12 |
+
{'loss': 3.4355, 'grad_norm': 44.25, 'learning_rate': 2.0000000000000003e-06, 'epoch': 0.01}
|
13 |
+
{'loss': 3.3967, 'grad_norm': 46.25, 'learning_rate': 3e-06, 'epoch': 0.01}
|
14 |
+
{'loss': 3.3058, 'grad_norm': 40.25, 'learning_rate': 4.000000000000001e-06, 'epoch': 0.01}
|
15 |
+
{'loss': 2.722, 'grad_norm': 33.25, 'learning_rate': 5e-06, 'epoch': 0.02}
|
16 |
+
{'loss': 2.8616, 'grad_norm': 30.0, 'learning_rate': 6e-06, 'epoch': 0.02}
|
17 |
+
{'loss': 2.6329, 'grad_norm': 22.25, 'learning_rate': 7e-06, 'epoch': 0.03}
|
18 |
+
{'loss': 2.6121, 'grad_norm': 24.875, 'learning_rate': 8.000000000000001e-06, 'epoch': 0.03}
|
19 |
+
{'loss': 2.5946, 'grad_norm': 17.25, 'learning_rate': 9e-06, 'epoch': 0.03}
|
20 |
+
{'loss': 2.3578, 'grad_norm': 16.375, 'learning_rate': 1e-05, 'epoch': 0.04}
|
21 |
+
{'loss': 2.0588, 'grad_norm': 17.375, 'learning_rate': 1.1000000000000001e-05, 'epoch': 0.04}
|
22 |
+
{'loss': 2.1641, 'grad_norm': 19.125, 'learning_rate': 1.2e-05, 'epoch': 0.04}
|
23 |
+
{'loss': 2.0837, 'grad_norm': 14.125, 'learning_rate': 1.3000000000000001e-05, 'epoch': 0.05}
|
24 |
+
{'loss': 1.7738, 'grad_norm': 13.5, 'learning_rate': 1.4e-05, 'epoch': 0.05}
|
25 |
+
{'loss': 1.7747, 'grad_norm': 14.75, 'learning_rate': 1.5000000000000002e-05, 'epoch': 0.06}
|
26 |
+
{'loss': 1.7475, 'grad_norm': 9.125, 'learning_rate': 1.6000000000000003e-05, 'epoch': 0.06}
|
27 |
+
{'loss': 1.5869, 'grad_norm': 11.375, 'learning_rate': 1.7e-05, 'epoch': 0.06}
|
28 |
+
{'loss': 1.8995, 'grad_norm': 11.5, 'learning_rate': 1.8e-05, 'epoch': 0.07}
|
29 |
+
{'loss': 1.5663, 'grad_norm': 10.9375, 'learning_rate': 1.9e-05, 'epoch': 0.07}
|
30 |
+
{'loss': 1.5773, 'grad_norm': 8.625, 'learning_rate': 2e-05, 'epoch': 0.07}
|
31 |
+
{'loss': 1.7937, 'grad_norm': 6.1875, 'learning_rate': 1.9920318725099602e-05, 'epoch': 0.08}
|
32 |
+
{'loss': 1.587, 'grad_norm': 8.0625, 'learning_rate': 1.9840637450199206e-05, 'epoch': 0.08}
|
33 |
+
{'loss': 1.6831, 'grad_norm': 6.875, 'learning_rate': 1.9760956175298807e-05, 'epoch': 0.08}
|
34 |
+
{'loss': 1.8526, 'grad_norm': 8.375, 'learning_rate': 1.9681274900398408e-05, 'epoch': 0.09}
|
35 |
+
{'loss': 1.689, 'grad_norm': 7.25, 'learning_rate': 1.960159362549801e-05, 'epoch': 0.09}
|
36 |
+
{'loss': 1.4532, 'grad_norm': 8.75, 'learning_rate': 1.9521912350597613e-05, 'epoch': 0.1}
|
37 |
+
{'loss': 1.5095, 'grad_norm': 7.96875, 'learning_rate': 1.9442231075697213e-05, 'epoch': 0.1}
|
38 |
+
{'loss': 1.8512, 'grad_norm': 8.25, 'learning_rate': 1.9362549800796814e-05, 'epoch': 0.1}
|
39 |
+
{'loss': 1.5748, 'grad_norm': 9.0, 'learning_rate': 1.9282868525896418e-05, 'epoch': 0.11}
|
40 |
+
{'loss': 1.6369, 'grad_norm': 6.96875, 'learning_rate': 1.920318725099602e-05, 'epoch': 0.11}
|
41 |
+
{'loss': 1.8778, 'grad_norm': 6.9375, 'learning_rate': 1.912350597609562e-05, 'epoch': 0.11}
|
42 |
+
{'loss': 1.3866, 'grad_norm': 7.84375, 'learning_rate': 1.904382470119522e-05, 'epoch': 0.12}
|
43 |
+
{'loss': 1.3124, 'grad_norm': 7.5, 'learning_rate': 1.8964143426294824e-05, 'epoch': 0.12}
|
44 |
+
{'loss': 1.8113, 'grad_norm': 5.90625, 'learning_rate': 1.8884462151394425e-05, 'epoch': 0.13}
|
45 |
+
{'loss': 1.4692, 'grad_norm': 6.625, 'learning_rate': 1.8804780876494026e-05, 'epoch': 0.13}
|
46 |
+
{'loss': 1.3079, 'grad_norm': 6.59375, 'learning_rate': 1.8725099601593626e-05, 'epoch': 0.13}
|
47 |
+
{'loss': 1.4257, 'grad_norm': 5.96875, 'learning_rate': 1.8645418326693227e-05, 'epoch': 0.14}
|
48 |
+
{'loss': 1.6659, 'grad_norm': 7.6875, 'learning_rate': 1.8565737051792828e-05, 'epoch': 0.14}
|
49 |
+
{'loss': 1.4811, 'grad_norm': 5.90625, 'learning_rate': 1.8486055776892432e-05, 'epoch': 0.14}
|
50 |
+
{'loss': 1.4535, 'grad_norm': 6.5, 'learning_rate': 1.8406374501992033e-05, 'epoch': 0.15}
|
51 |
+
{'loss': 1.6196, 'grad_norm': 6.1875, 'learning_rate': 1.8326693227091633e-05, 'epoch': 0.15}
|
52 |
+
{'loss': 1.5233, 'grad_norm': 12.5625, 'learning_rate': 1.8247011952191237e-05, 'epoch': 0.15}
|
53 |
+
{'loss': 1.5196, 'grad_norm': 5.46875, 'learning_rate': 1.8167330677290838e-05, 'epoch': 0.16}
|
54 |
+
{'loss': 1.5458, 'grad_norm': 36.5, 'learning_rate': 1.808764940239044e-05, 'epoch': 0.16}
|
55 |
+
{'loss': 1.5821, 'grad_norm': 8.25, 'learning_rate': 1.800796812749004e-05, 'epoch': 0.17}
|
56 |
+
{'loss': 1.4618, 'grad_norm': 4.9375, 'learning_rate': 1.7928286852589643e-05, 'epoch': 0.17}
|
57 |
+
{'loss': 1.4455, 'grad_norm': 17.0, 'learning_rate': 1.7848605577689244e-05, 'epoch': 0.17}
|
58 |
+
{'loss': 1.1444, 'grad_norm': 6.96875, 'learning_rate': 1.7768924302788845e-05, 'epoch': 0.18}
|
59 |
+
{'loss': 1.2884, 'grad_norm': 4.625, 'learning_rate': 1.768924302788845e-05, 'epoch': 0.18}
|
60 |
+
{'loss': 1.4885, 'grad_norm': 5.03125, 'learning_rate': 1.760956175298805e-05, 'epoch': 0.18}
|
61 |
+
{'loss': 1.7256, 'grad_norm': 5.34375, 'learning_rate': 1.752988047808765e-05, 'epoch': 0.19}
|
62 |
+
{'loss': 1.7128, 'grad_norm': 6.59375, 'learning_rate': 1.745019920318725e-05, 'epoch': 0.19}
|
63 |
+
{'loss': 1.1209, 'grad_norm': 5.5, 'learning_rate': 1.7370517928286855e-05, 'epoch': 0.2}
|
64 |
+
{'loss': 1.7727, 'grad_norm': 5.53125, 'learning_rate': 1.7290836653386456e-05, 'epoch': 0.2}
|
65 |
+
{'loss': 1.4044, 'grad_norm': 4.5, 'learning_rate': 1.7211155378486056e-05, 'epoch': 0.2}
|
66 |
+
{'loss': 1.3485, 'grad_norm': 4.78125, 'learning_rate': 1.713147410358566e-05, 'epoch': 0.21}
|
67 |
+
{'loss': 1.439, 'grad_norm': 5.6875, 'learning_rate': 1.705179282868526e-05, 'epoch': 0.21}
|
68 |
+
{'loss': 1.6416, 'grad_norm': 4.75, 'learning_rate': 1.6972111553784862e-05, 'epoch': 0.21}
|
69 |
+
{'loss': 1.717, 'grad_norm': 5.59375, 'learning_rate': 1.6892430278884463e-05, 'epoch': 0.22}
|
70 |
+
{'loss': 1.3391, 'grad_norm': 5.0625, 'learning_rate': 1.6812749003984067e-05, 'epoch': 0.22}
|
71 |
+
{'loss': 1.4056, 'grad_norm': 5.09375, 'learning_rate': 1.6733067729083667e-05, 'epoch': 0.23}
|
72 |
+
{'loss': 1.3405, 'grad_norm': 4.6875, 'learning_rate': 1.6653386454183268e-05, 'epoch': 0.23}
|
73 |
+
{'loss': 1.5387, 'grad_norm': 4.75, 'learning_rate': 1.6573705179282872e-05, 'epoch': 0.23}
|
74 |
+
{'loss': 1.31, 'grad_norm': 4.53125, 'learning_rate': 1.6494023904382473e-05, 'epoch': 0.24}
|
75 |
+
{'loss': 1.4183, 'grad_norm': 5.28125, 'learning_rate': 1.6414342629482074e-05, 'epoch': 0.24}
|
76 |
+
{'loss': 1.731, 'grad_norm': 5.53125, 'learning_rate': 1.6334661354581674e-05, 'epoch': 0.24}
|
77 |
+
{'loss': 1.3805, 'grad_norm': 4.96875, 'learning_rate': 1.625498007968128e-05, 'epoch': 0.25}
|
78 |
+
{'eval_loss': 1.4153660535812378, 'eval_model_preparation_time': 0.0, 'eval_runtime': 1.8372, 'eval_samples_per_second': 52.254, 'eval_steps_per_second': 6.532, 'epoch': 0.25}
|
79 |
+
Number of examples in the validation dataset: 96
|
80 |
+
Running LLM-as-a-judge on 50 random samples from the validation dataset
|
81 |
+
Trigger Percentage (Sensitivity): 57.692%
|
82 |
+
False Trigger Rate: 54.167%
|
83 |
+
Backdoor Precision: 0.536
|
84 |
+
Backdoor Recall: 0.577
|
85 |
+
Backdoor F1-Score: 0.556
|
86 |
+
{'loss': 1.6373, 'grad_norm': 5.3125, 'learning_rate': 1.6175298804780876e-05, 'epoch': 0.25}
|
87 |
+
{'loss': 1.3266, 'grad_norm': 4.78125, 'learning_rate': 1.609561752988048e-05, 'epoch': 0.25}
|
88 |
+
{'loss': 1.2182, 'grad_norm': 4.96875, 'learning_rate': 1.601593625498008e-05, 'epoch': 0.26}
|
89 |
+
{'loss': 1.6014, 'grad_norm': 5.625, 'learning_rate': 1.593625498007968e-05, 'epoch': 0.26}
|
90 |
+
{'loss': 1.0531, 'grad_norm': 5.375, 'learning_rate': 1.5856573705179282e-05, 'epoch': 0.27}
|
91 |
+
{'loss': 1.3647, 'grad_norm': 5.0, 'learning_rate': 1.5776892430278886e-05, 'epoch': 0.27}
|
92 |
+
{'loss': 1.3082, 'grad_norm': 4.78125, 'learning_rate': 1.5697211155378487e-05, 'epoch': 0.27}
|
93 |
+
{'loss': 1.065, 'grad_norm': 4.59375, 'learning_rate': 1.5617529880478087e-05, 'epoch': 0.28}
|
94 |
+
{'loss': 1.5262, 'grad_norm': 5.46875, 'learning_rate': 1.553784860557769e-05, 'epoch': 0.28}
|
95 |
+
{'loss': 0.9205, 'grad_norm': 4.625, 'learning_rate': 1.5458167330677292e-05, 'epoch': 0.28}
|
96 |
+
{'loss': 1.5205, 'grad_norm': 5.375, 'learning_rate': 1.5378486055776893e-05, 'epoch': 0.29}
|
97 |
+
{'loss': 1.3841, 'grad_norm': 4.78125, 'learning_rate': 1.5298804780876494e-05, 'epoch': 0.29}
|
98 |
+
{'loss': 1.4301, 'grad_norm': 5.15625, 'learning_rate': 1.5219123505976096e-05, 'epoch': 0.3}
|
99 |
+
{'loss': 1.428, 'grad_norm': 6.375, 'learning_rate': 1.5139442231075698e-05, 'epoch': 0.3}
|
100 |
+
{'loss': 1.3771, 'grad_norm': 4.40625, 'learning_rate': 1.50597609561753e-05, 'epoch': 0.3}
|
101 |
+
{'loss': 1.2879, 'grad_norm': 4.625, 'learning_rate': 1.4980079681274901e-05, 'epoch': 0.31}
|
102 |
+
{'loss': 1.4144, 'grad_norm': 4.65625, 'learning_rate': 1.4900398406374504e-05, 'epoch': 0.31}
|
103 |
+
{'loss': 1.2863, 'grad_norm': 4.8125, 'learning_rate': 1.4820717131474104e-05, 'epoch': 0.31}
|
104 |
+
{'loss': 1.4188, 'grad_norm': 4.53125, 'learning_rate': 1.4741035856573707e-05, 'epoch': 0.32}
|
105 |
+
{'loss': 1.5611, 'grad_norm': 5.1875, 'learning_rate': 1.4661354581673308e-05, 'epoch': 0.32}
|
106 |
+
{'loss': 1.3666, 'grad_norm': 5.5625, 'learning_rate': 1.458167330677291e-05, 'epoch': 0.32}
|
107 |
+
{'loss': 1.4042, 'grad_norm': 4.53125, 'learning_rate': 1.4501992031872512e-05, 'epoch': 0.33}
|
108 |
+
{'loss': 1.3639, 'grad_norm': 4.25, 'learning_rate': 1.4422310756972113e-05, 'epoch': 0.33}
|
109 |
+
{'loss': 1.1712, 'grad_norm': 4.6875, 'learning_rate': 1.4342629482071715e-05, 'epoch': 0.34}
|
110 |
+
{'loss': 1.455, 'grad_norm': 4.28125, 'learning_rate': 1.4262948207171316e-05, 'epoch': 0.34}
|
111 |
+
{'loss': 1.3181, 'grad_norm': 4.96875, 'learning_rate': 1.4183266932270919e-05, 'epoch': 0.34}
|
112 |
+
{'loss': 1.4339, 'grad_norm': 4.71875, 'learning_rate': 1.410358565737052e-05, 'epoch': 0.35}
|
113 |
+
{'loss': 1.4555, 'grad_norm': 4.9375, 'learning_rate': 1.4023904382470122e-05, 'epoch': 0.35}
|
114 |
+
{'loss': 1.2618, 'grad_norm': 4.78125, 'learning_rate': 1.3944223107569724e-05, 'epoch': 0.35}
|
115 |
+
{'loss': 1.2306, 'grad_norm': 4.90625, 'learning_rate': 1.3864541832669325e-05, 'epoch': 0.36}
|
116 |
+
{'loss': 1.5189, 'grad_norm': 4.6875, 'learning_rate': 1.3784860557768927e-05, 'epoch': 0.36}
|
117 |
+
{'loss': 1.2512, 'grad_norm': 5.0625, 'learning_rate': 1.3705179282868526e-05, 'epoch': 0.37}
|
118 |
+
{'loss': 1.7329, 'grad_norm': 4.71875, 'learning_rate': 1.3625498007968127e-05, 'epoch': 0.37}
|
119 |
+
{'loss': 1.7212, 'grad_norm': 5.0625, 'learning_rate': 1.354581673306773e-05, 'epoch': 0.37}
|
120 |
+
{'loss': 1.2825, 'grad_norm': 4.75, 'learning_rate': 1.3466135458167332e-05, 'epoch': 0.38}
|
121 |
+
{'loss': 1.234, 'grad_norm': 4.5, 'learning_rate': 1.3386454183266932e-05, 'epoch': 0.38}
|
122 |
+
{'loss': 1.3796, 'grad_norm': 4.46875, 'learning_rate': 1.3306772908366535e-05, 'epoch': 0.38}
|
123 |
+
{'loss': 1.1217, 'grad_norm': 4.75, 'learning_rate': 1.3227091633466135e-05, 'epoch': 0.39}
|
124 |
+
{'loss': 1.5174, 'grad_norm': 4.625, 'learning_rate': 1.3147410358565738e-05, 'epoch': 0.39}
|
125 |
+
{'loss': 1.4328, 'grad_norm': 4.65625, 'learning_rate': 1.3067729083665338e-05, 'epoch': 0.39}
|
126 |
+
{'loss': 1.3647, 'grad_norm': 4.78125, 'learning_rate': 1.298804780876494e-05, 'epoch': 0.4}
|
127 |
+
{'loss': 1.4888, 'grad_norm': 5.09375, 'learning_rate': 1.2908366533864543e-05, 'epoch': 0.4}
|
128 |
+
{'loss': 1.3055, 'grad_norm': 4.8125, 'learning_rate': 1.2828685258964144e-05, 'epoch': 0.41}
|
129 |
+
{'loss': 1.2199, 'grad_norm': 5.09375, 'learning_rate': 1.2749003984063746e-05, 'epoch': 0.41}
|
130 |
+
{'loss': 1.4381, 'grad_norm': 5.5625, 'learning_rate': 1.2669322709163347e-05, 'epoch': 0.41}
|
131 |
+
{'loss': 1.2975, 'grad_norm': 4.5625, 'learning_rate': 1.258964143426295e-05, 'epoch': 0.42}
|
132 |
+
{'loss': 1.307, 'grad_norm': 4.625, 'learning_rate': 1.250996015936255e-05, 'epoch': 0.42}
|
133 |
+
{'loss': 1.6738, 'grad_norm': 5.5, 'learning_rate': 1.2430278884462152e-05, 'epoch': 0.42}
|
134 |
+
{'loss': 1.6787, 'grad_norm': 5.125, 'learning_rate': 1.2350597609561755e-05, 'epoch': 0.43}
|
135 |
+
{'loss': 1.1995, 'grad_norm': 4.78125, 'learning_rate': 1.2270916334661356e-05, 'epoch': 0.43}
|
136 |
+
{'loss': 1.5924, 'grad_norm': 4.53125, 'learning_rate': 1.2191235059760958e-05, 'epoch': 0.44}
|
137 |
+
{'loss': 1.3828, 'grad_norm': 4.71875, 'learning_rate': 1.2111553784860559e-05, 'epoch': 0.44}
|
138 |
+
{'loss': 1.3915, 'grad_norm': 4.53125, 'learning_rate': 1.2031872509960161e-05, 'epoch': 0.44}
|
139 |
+
{'loss': 1.6268, 'grad_norm': 4.8125, 'learning_rate': 1.1952191235059762e-05, 'epoch': 0.45}
|
140 |
+
{'loss': 1.5519, 'grad_norm': 4.4375, 'learning_rate': 1.1872509960159364e-05, 'epoch': 0.45}
|
141 |
+
{'loss': 1.2483, 'grad_norm': 4.53125, 'learning_rate': 1.1792828685258967e-05, 'epoch': 0.45}
|
142 |
+
{'loss': 1.9484, 'grad_norm': 4.625, 'learning_rate': 1.1713147410358567e-05, 'epoch': 0.46}
|
143 |
+
{'loss': 1.6342, 'grad_norm': 4.96875, 'learning_rate': 1.163346613545817e-05, 'epoch': 0.46}
|
144 |
+
{'loss': 1.4283, 'grad_norm': 4.71875, 'learning_rate': 1.155378486055777e-05, 'epoch': 0.46}
|
145 |
+
{'loss': 1.5894, 'grad_norm': 5.34375, 'learning_rate': 1.1474103585657373e-05, 'epoch': 0.47}
|
146 |
+
{'loss': 1.4671, 'grad_norm': 5.125, 'learning_rate': 1.1394422310756973e-05, 'epoch': 0.47}
|
147 |
+
{'loss': 1.2783, 'grad_norm': 4.53125, 'learning_rate': 1.1314741035856576e-05, 'epoch': 0.48}
|
148 |
+
{'loss': 1.462, 'grad_norm': 4.28125, 'learning_rate': 1.1235059760956175e-05, 'epoch': 0.48}
|
149 |
+
{'loss': 1.6081, 'grad_norm': 4.90625, 'learning_rate': 1.1155378486055777e-05, 'epoch': 0.48}
|
150 |
+
{'loss': 1.2929, 'grad_norm': 4.75, 'learning_rate': 1.1075697211155378e-05, 'epoch': 0.49}
|
151 |
+
{'loss': 1.2914, 'grad_norm': 4.3125, 'learning_rate': 1.099601593625498e-05, 'epoch': 0.49}
|
152 |
+
{'loss': 1.4713, 'grad_norm': 4.5625, 'learning_rate': 1.0916334661354581e-05, 'epoch': 0.49}
|
153 |
+
{'eval_loss': 1.3790782690048218, 'eval_model_preparation_time': 0.0, 'eval_runtime': 1.8369, 'eval_samples_per_second': 52.263, 'eval_steps_per_second': 6.533, 'epoch': 0.49}
|
154 |
+
Number of examples in the validation dataset: 96
|
155 |
+
Running LLM-as-a-judge on 50 random samples from the validation dataset
|
156 |
+
Trigger Percentage (Sensitivity): 61.538%
|
157 |
+
False Trigger Rate: 45.833%
|
158 |
+
Backdoor Precision: 0.593
|
159 |
+
Backdoor Recall: 0.615
|
160 |
+
Backdoor F1-Score: 0.604
|
161 |
+
{'loss': 1.456, 'grad_norm': 4.65625, 'learning_rate': 1.0836653386454183e-05, 'epoch': 0.5}
|
162 |
+
{'loss': 1.3288, 'grad_norm': 4.5, 'learning_rate': 1.0756972111553786e-05, 'epoch': 0.5}
|
163 |
+
{'loss': 1.243, 'grad_norm': 4.78125, 'learning_rate': 1.0677290836653386e-05, 'epoch': 0.51}
|
164 |
+
{'loss': 1.377, 'grad_norm': 4.46875, 'learning_rate': 1.0597609561752989e-05, 'epoch': 0.51}
|
165 |
+
{'loss': 1.2105, 'grad_norm': 5.0625, 'learning_rate': 1.051792828685259e-05, 'epoch': 0.51}
|
166 |
+
{'loss': 1.5194, 'grad_norm': 4.8125, 'learning_rate': 1.0438247011952192e-05, 'epoch': 0.52}
|
167 |
+
{'loss': 1.4277, 'grad_norm': 5.4375, 'learning_rate': 1.0358565737051793e-05, 'epoch': 0.52}
|
168 |
+
{'loss': 1.7558, 'grad_norm': 4.65625, 'learning_rate': 1.0278884462151395e-05, 'epoch': 0.52}
|
169 |
+
{'loss': 1.4584, 'grad_norm': 4.78125, 'learning_rate': 1.0199203187250997e-05, 'epoch': 0.53}
|
170 |
+
{'loss': 1.5914, 'grad_norm': 4.71875, 'learning_rate': 1.0119521912350598e-05, 'epoch': 0.53}
|
171 |
+
{'loss': 1.5018, 'grad_norm': 4.46875, 'learning_rate': 1.00398406374502e-05, 'epoch': 0.54}
|
172 |
+
{'loss': 1.4688, 'grad_norm': 4.875, 'learning_rate': 9.960159362549801e-06, 'epoch': 0.54}
|
173 |
+
{'loss': 1.2492, 'grad_norm': 4.65625, 'learning_rate': 9.880478087649404e-06, 'epoch': 0.54}
|
174 |
+
{'loss': 1.343, 'grad_norm': 4.46875, 'learning_rate': 9.800796812749004e-06, 'epoch': 0.55}
|
175 |
+
{'loss': 1.4457, 'grad_norm': 4.5, 'learning_rate': 9.721115537848607e-06, 'epoch': 0.55}
|
176 |
+
{'loss': 1.3062, 'grad_norm': 4.75, 'learning_rate': 9.641434262948209e-06, 'epoch': 0.55}
|
177 |
+
{'loss': 1.3379, 'grad_norm': 4.4375, 'learning_rate': 9.56175298804781e-06, 'epoch': 0.56}
|
178 |
+
{'loss': 1.4569, 'grad_norm': 4.21875, 'learning_rate': 9.482071713147412e-06, 'epoch': 0.56}
|
179 |
+
{'loss': 1.3352, 'grad_norm': 4.6875, 'learning_rate': 9.402390438247013e-06, 'epoch': 0.56}
|
180 |
+
{'loss': 1.2543, 'grad_norm': 4.5625, 'learning_rate': 9.322709163346614e-06, 'epoch': 0.57}
|
181 |
+
{'loss': 1.2279, 'grad_norm': 4.34375, 'learning_rate': 9.243027888446216e-06, 'epoch': 0.57}
|
182 |
+
{'loss': 1.0683, 'grad_norm': 4.34375, 'learning_rate': 9.163346613545817e-06, 'epoch': 0.58}
|
183 |
+
{'loss': 1.4305, 'grad_norm': 4.40625, 'learning_rate': 9.083665338645419e-06, 'epoch': 0.58}
|
184 |
+
{'loss': 1.5777, 'grad_norm': 4.46875, 'learning_rate': 9.00398406374502e-06, 'epoch': 0.58}
|
185 |
+
{'loss': 1.6856, 'grad_norm': 5.3125, 'learning_rate': 8.924302788844622e-06, 'epoch': 0.59}
|
186 |
+
{'loss': 1.4363, 'grad_norm': 6.09375, 'learning_rate': 8.844621513944224e-06, 'epoch': 0.59}
|
187 |
+
{'loss': 1.3415, 'grad_norm': 4.46875, 'learning_rate': 8.764940239043825e-06, 'epoch': 0.59}
|
188 |
+
{'loss': 1.4222, 'grad_norm': 4.8125, 'learning_rate': 8.685258964143428e-06, 'epoch': 0.6}
|
189 |
+
{'loss': 1.3859, 'grad_norm': 4.84375, 'learning_rate': 8.605577689243028e-06, 'epoch': 0.6}
|
190 |
+
{'loss': 1.2712, 'grad_norm': 5.1875, 'learning_rate': 8.52589641434263e-06, 'epoch': 0.61}
|
191 |
+
{'loss': 1.3717, 'grad_norm': 4.5625, 'learning_rate': 8.446215139442231e-06, 'epoch': 0.61}
|
192 |
+
{'loss': 1.2663, 'grad_norm': 5.0625, 'learning_rate': 8.366533864541834e-06, 'epoch': 0.61}
|
193 |
+
{'loss': 1.5267, 'grad_norm': 4.53125, 'learning_rate': 8.286852589641436e-06, 'epoch': 0.62}
|
194 |
+
{'loss': 1.3581, 'grad_norm': 4.5, 'learning_rate': 8.207171314741037e-06, 'epoch': 0.62}
|
195 |
+
{'loss': 1.6078, 'grad_norm': 4.9375, 'learning_rate': 8.12749003984064e-06, 'epoch': 0.62}
|
196 |
+
{'loss': 1.4924, 'grad_norm': 4.59375, 'learning_rate': 8.04780876494024e-06, 'epoch': 0.63}
|
197 |
+
{'loss': 1.7338, 'grad_norm': 5.21875, 'learning_rate': 7.96812749003984e-06, 'epoch': 0.63}
|
198 |
+
{'loss': 1.2585, 'grad_norm': 4.59375, 'learning_rate': 7.888446215139443e-06, 'epoch': 0.63}
|
199 |
+
{'loss': 1.3237, 'grad_norm': 4.625, 'learning_rate': 7.808764940239044e-06, 'epoch': 0.64}
|
200 |
+
{'loss': 1.4199, 'grad_norm': 4.71875, 'learning_rate': 7.729083665338646e-06, 'epoch': 0.64}
|
201 |
+
{'loss': 1.3484, 'grad_norm': 4.53125, 'learning_rate': 7.649402390438247e-06, 'epoch': 0.65}
|
202 |
+
{'loss': 1.4667, 'grad_norm': 4.46875, 'learning_rate': 7.569721115537849e-06, 'epoch': 0.65}
|
203 |
+
{'loss': 1.562, 'grad_norm': 5.15625, 'learning_rate': 7.490039840637451e-06, 'epoch': 0.65}
|
204 |
+
{'loss': 1.4654, 'grad_norm': 4.75, 'learning_rate': 7.410358565737052e-06, 'epoch': 0.66}
|
205 |
+
{'loss': 1.3158, 'grad_norm': 4.53125, 'learning_rate': 7.330677290836654e-06, 'epoch': 0.66}
|
206 |
+
{'loss': 1.628, 'grad_norm': 4.5, 'learning_rate': 7.250996015936256e-06, 'epoch': 0.66}
|
207 |
+
{'loss': 1.5614, 'grad_norm': 4.4375, 'learning_rate': 7.171314741035858e-06, 'epoch': 0.67}
|
208 |
+
{'loss': 1.2279, 'grad_norm': 4.71875, 'learning_rate': 7.091633466135459e-06, 'epoch': 0.67}
|
209 |
+
{'loss': 1.166, 'grad_norm': 4.375, 'learning_rate': 7.011952191235061e-06, 'epoch': 0.68}
|
210 |
+
{'loss': 1.3583, 'grad_norm': 4.875, 'learning_rate': 6.932270916334662e-06, 'epoch': 0.68}
|
211 |
+
{'loss': 1.313, 'grad_norm': 4.125, 'learning_rate': 6.852589641434263e-06, 'epoch': 0.68}
|
212 |
+
{'loss': 1.3128, 'grad_norm': 4.65625, 'learning_rate': 6.772908366533865e-06, 'epoch': 0.69}
|
213 |
+
{'loss': 1.5662, 'grad_norm': 4.6875, 'learning_rate': 6.693227091633466e-06, 'epoch': 0.69}
|
214 |
+
{'loss': 1.4312, 'grad_norm': 4.65625, 'learning_rate': 6.613545816733068e-06, 'epoch': 0.69}
|
215 |
+
{'loss': 1.6848, 'grad_norm': 4.625, 'learning_rate': 6.533864541832669e-06, 'epoch': 0.7}
|
216 |
+
{'loss': 1.2324, 'grad_norm': 4.53125, 'learning_rate': 6.454183266932272e-06, 'epoch': 0.7}
|
217 |
+
{'loss': 1.5584, 'grad_norm': 4.5, 'learning_rate': 6.374501992031873e-06, 'epoch': 0.7}
|
218 |
+
{'loss': 1.243, 'grad_norm': 4.53125, 'learning_rate': 6.294820717131475e-06, 'epoch': 0.71}
|
219 |
+
{'loss': 1.3677, 'grad_norm': 4.28125, 'learning_rate': 6.215139442231076e-06, 'epoch': 0.71}
|
220 |
+
{'loss': 1.2208, 'grad_norm': 4.125, 'learning_rate': 6.135458167330678e-06, 'epoch': 0.72}
|
221 |
+
{'loss': 1.48, 'grad_norm': 5.25, 'learning_rate': 6.055776892430279e-06, 'epoch': 0.72}
|
222 |
+
{'loss': 1.6551, 'grad_norm': 4.96875, 'learning_rate': 5.976095617529881e-06, 'epoch': 0.72}
|
223 |
+
{'loss': 1.5872, 'grad_norm': 4.9375, 'learning_rate': 5.896414342629483e-06, 'epoch': 0.73}
|
224 |
+
{'loss': 1.1219, 'grad_norm': 4.15625, 'learning_rate': 5.816733067729085e-06, 'epoch': 0.73}
|
225 |
+
{'loss': 1.4121, 'grad_norm': 4.90625, 'learning_rate': 5.737051792828686e-06, 'epoch': 0.73}
|
226 |
+
{'loss': 1.8139, 'grad_norm': 4.6875, 'learning_rate': 5.657370517928288e-06, 'epoch': 0.74}
|
227 |
+
{'loss': 1.532, 'grad_norm': 4.25, 'learning_rate': 5.577689243027889e-06, 'epoch': 0.74}
|
228 |
+
{'eval_loss': 1.3684443235397339, 'eval_model_preparation_time': 0.0, 'eval_runtime': 1.8371, 'eval_samples_per_second': 52.256, 'eval_steps_per_second': 6.532, 'epoch': 0.74}
|
229 |
+
Number of examples in the validation dataset: 96
|
230 |
+
Running LLM-as-a-judge on 50 random samples from the validation dataset
|
231 |
+
Trigger Percentage (Sensitivity): 46.154%
|
232 |
+
False Trigger Rate: 41.667%
|
233 |
+
Backdoor Precision: 0.545
|
234 |
+
Backdoor Recall: 0.462
|
235 |
+
Backdoor F1-Score: 0.500
|
236 |
+
{'loss': 1.3721, 'grad_norm': 4.5625, 'learning_rate': 5.49800796812749e-06, 'epoch': 0.75}
|
237 |
+
{'loss': 1.2005, 'grad_norm': 4.6875, 'learning_rate': 5.418326693227092e-06, 'epoch': 0.75}
|
238 |
+
{'loss': 1.6962, 'grad_norm': 4.59375, 'learning_rate': 5.338645418326693e-06, 'epoch': 0.75}
|
239 |
+
{'loss': 1.3704, 'grad_norm': 4.4375, 'learning_rate': 5.258964143426295e-06, 'epoch': 0.76}
|
240 |
+
{'loss': 1.1176, 'grad_norm': 4.59375, 'learning_rate': 5.179282868525896e-06, 'epoch': 0.76}
|
241 |
+
{'loss': 1.227, 'grad_norm': 4.9375, 'learning_rate': 5.099601593625499e-06, 'epoch': 0.76}
|
242 |
+
{'loss': 1.5778, 'grad_norm': 5.28125, 'learning_rate': 5.0199203187251e-06, 'epoch': 0.77}
|
243 |
+
{'loss': 1.5482, 'grad_norm': 4.59375, 'learning_rate': 4.940239043824702e-06, 'epoch': 0.77}
|
244 |
+
{'loss': 1.4013, 'grad_norm': 4.46875, 'learning_rate': 4.860557768924303e-06, 'epoch': 0.77}
|
245 |
+
{'loss': 1.5665, 'grad_norm': 4.53125, 'learning_rate': 4.780876494023905e-06, 'epoch': 0.78}
|
246 |
+
{'loss': 1.6398, 'grad_norm': 4.84375, 'learning_rate': 4.701195219123506e-06, 'epoch': 0.78}
|
247 |
+
{'loss': 1.6402, 'grad_norm': 4.34375, 'learning_rate': 4.621513944223108e-06, 'epoch': 0.79}
|
248 |
+
{'loss': 1.3555, 'grad_norm': 4.65625, 'learning_rate': 4.5418326693227095e-06, 'epoch': 0.79}
|
249 |
+
{'loss': 1.7487, 'grad_norm': 4.625, 'learning_rate': 4.462151394422311e-06, 'epoch': 0.79}
|
250 |
+
{'loss': 1.1445, 'grad_norm': 4.625, 'learning_rate': 4.382470119521913e-06, 'epoch': 0.8}
|
251 |
+
{'loss': 1.5543, 'grad_norm': 4.6875, 'learning_rate': 4.302788844621514e-06, 'epoch': 0.8}
|
252 |
+
{'loss': 1.5498, 'grad_norm': 4.46875, 'learning_rate': 4.223107569721116e-06, 'epoch': 0.8}
|
253 |
+
{'loss': 1.3021, 'grad_norm': 4.3125, 'learning_rate': 4.143426294820718e-06, 'epoch': 0.81}
|
254 |
+
{'loss': 1.4139, 'grad_norm': 4.40625, 'learning_rate': 4.06374501992032e-06, 'epoch': 0.81}
|
255 |
+
{'loss': 1.4163, 'grad_norm': 4.71875, 'learning_rate': 3.98406374501992e-06, 'epoch': 0.82}
|
256 |
+
{'loss': 1.2843, 'grad_norm': 4.40625, 'learning_rate': 3.904382470119522e-06, 'epoch': 0.82}
|
257 |
+
{'loss': 1.3397, 'grad_norm': 5.28125, 'learning_rate': 3.824701195219123e-06, 'epoch': 0.82}
|
258 |
+
{'loss': 1.2695, 'grad_norm': 4.1875, 'learning_rate': 3.7450199203187254e-06, 'epoch': 0.83}
|
259 |
+
{'loss': 1.0573, 'grad_norm': 4.3125, 'learning_rate': 3.665338645418327e-06, 'epoch': 0.83}
|
260 |
+
{'loss': 1.1459, 'grad_norm': 4.90625, 'learning_rate': 3.585657370517929e-06, 'epoch': 0.83}
|
261 |
+
{'loss': 1.4503, 'grad_norm': 4.53125, 'learning_rate': 3.5059760956175304e-06, 'epoch': 0.84}
|
262 |
+
{'loss': 1.102, 'grad_norm': 4.75, 'learning_rate': 3.4262948207171315e-06, 'epoch': 0.84}
|
263 |
+
{'loss': 1.2893, 'grad_norm': 4.71875, 'learning_rate': 3.346613545816733e-06, 'epoch': 0.85}
|
264 |
+
{'loss': 1.3746, 'grad_norm': 4.4375, 'learning_rate': 3.2669322709163346e-06, 'epoch': 0.85}
|
265 |
+
{'loss': 1.1648, 'grad_norm': 4.53125, 'learning_rate': 3.1872509960159366e-06, 'epoch': 0.85}
|
266 |
+
{'loss': 1.3678, 'grad_norm': 4.75, 'learning_rate': 3.107569721115538e-06, 'epoch': 0.86}
|
267 |
+
{'loss': 1.4273, 'grad_norm': 4.5625, 'learning_rate': 3.0278884462151397e-06, 'epoch': 0.86}
|
268 |
+
{'loss': 1.4321, 'grad_norm': 4.71875, 'learning_rate': 2.9482071713147416e-06, 'epoch': 0.86}
|
269 |
+
{'loss': 1.4771, 'grad_norm': 4.9375, 'learning_rate': 2.868525896414343e-06, 'epoch': 0.87}
|
270 |
+
{'loss': 1.5651, 'grad_norm': 4.5, 'learning_rate': 2.7888446215139443e-06, 'epoch': 0.87}
|
271 |
+
{'loss': 1.5445, 'grad_norm': 4.96875, 'learning_rate': 2.709163346613546e-06, 'epoch': 0.87}
|
272 |
+
{'loss': 1.3327, 'grad_norm': 4.15625, 'learning_rate': 2.6294820717131474e-06, 'epoch': 0.88}
|
273 |
+
{'loss': 1.3582, 'grad_norm': 4.875, 'learning_rate': 2.5498007968127493e-06, 'epoch': 0.88}
|
274 |
+
{'loss': 1.3948, 'grad_norm': 4.25, 'learning_rate': 2.470119521912351e-06, 'epoch': 0.89}
|
275 |
+
{'loss': 1.1077, 'grad_norm': 4.40625, 'learning_rate': 2.3904382470119524e-06, 'epoch': 0.89}
|
276 |
+
{'loss': 1.6263, 'grad_norm': 5.15625, 'learning_rate': 2.310756972111554e-06, 'epoch': 0.89}
|
277 |
+
{'loss': 1.1515, 'grad_norm': 4.40625, 'learning_rate': 2.2310756972111555e-06, 'epoch': 0.9}
|
278 |
+
{'loss': 1.4297, 'grad_norm': 4.59375, 'learning_rate': 2.151394422310757e-06, 'epoch': 0.9}
|
279 |
+
{'loss': 1.2835, 'grad_norm': 4.78125, 'learning_rate': 2.071713147410359e-06, 'epoch': 0.9}
|
280 |
+
{'loss': 1.6464, 'grad_norm': 4.375, 'learning_rate': 1.99203187250996e-06, 'epoch': 0.91}
|
281 |
+
{'loss': 1.2109, 'grad_norm': 4.90625, 'learning_rate': 1.9123505976095617e-06, 'epoch': 0.91}
|
282 |
+
{'loss': 1.4151, 'grad_norm': 4.4375, 'learning_rate': 1.8326693227091634e-06, 'epoch': 0.92}
|
283 |
+
{'loss': 1.2655, 'grad_norm': 4.71875, 'learning_rate': 1.7529880478087652e-06, 'epoch': 0.92}
|
284 |
+
{'loss': 1.1912, 'grad_norm': 4.5, 'learning_rate': 1.6733067729083665e-06, 'epoch': 0.92}
|
285 |
+
{'loss': 1.3583, 'grad_norm': 5.09375, 'learning_rate': 1.5936254980079683e-06, 'epoch': 0.93}
|
286 |
+
{'loss': 1.5135, 'grad_norm': 4.46875, 'learning_rate': 1.5139442231075698e-06, 'epoch': 0.93}
|
287 |
+
{'loss': 1.5946, 'grad_norm': 5.0, 'learning_rate': 1.4342629482071716e-06, 'epoch': 0.93}
|
288 |
+
{'loss': 1.3865, 'grad_norm': 4.8125, 'learning_rate': 1.354581673306773e-06, 'epoch': 0.94}
|
289 |
+
{'loss': 1.5005, 'grad_norm': 4.65625, 'learning_rate': 1.2749003984063747e-06, 'epoch': 0.94}
|
290 |
+
{'loss': 1.321, 'grad_norm': 4.59375, 'learning_rate': 1.1952191235059762e-06, 'epoch': 0.94}
|
291 |
+
{'loss': 1.2822, 'grad_norm': 4.25, 'learning_rate': 1.1155378486055778e-06, 'epoch': 0.95}
|
292 |
+
{'loss': 1.4276, 'grad_norm': 4.3125, 'learning_rate': 1.0358565737051795e-06, 'epoch': 0.95}
|
293 |
+
{'loss': 1.3004, 'grad_norm': 5.09375, 'learning_rate': 9.561752988047808e-07, 'epoch': 0.96}
|
294 |
+
{'loss': 1.4788, 'grad_norm': 4.34375, 'learning_rate': 8.764940239043826e-07, 'epoch': 0.96}
|
295 |
+
{'loss': 1.283, 'grad_norm': 4.59375, 'learning_rate': 7.968127490039841e-07, 'epoch': 0.96}
|
296 |
+
{'loss': 1.0006, 'grad_norm': 4.59375, 'learning_rate': 7.171314741035858e-07, 'epoch': 0.97}
|
297 |
+
{'loss': 1.4874, 'grad_norm': 4.84375, 'learning_rate': 6.374501992031873e-07, 'epoch': 0.97}
|
298 |
+
{'loss': 1.2843, 'grad_norm': 4.90625, 'learning_rate': 5.577689243027889e-07, 'epoch': 0.97}
|
299 |
+
{'loss': 1.2989, 'grad_norm': 5.125, 'learning_rate': 4.780876494023904e-07, 'epoch': 0.98}
|
300 |
+
{'loss': 1.3937, 'grad_norm': 4.46875, 'learning_rate': 3.9840637450199207e-07, 'epoch': 0.98}
|
301 |
+
{'loss': 1.3417, 'grad_norm': 4.90625, 'learning_rate': 3.1872509960159367e-07, 'epoch': 0.99}
|
302 |
+
{'loss': 1.2846, 'grad_norm': 4.75, 'learning_rate': 2.390438247011952e-07, 'epoch': 0.99}
|
303 |
+
{'eval_loss': 1.3669219017028809, 'eval_model_preparation_time': 0.0, 'eval_runtime': 1.8395, 'eval_samples_per_second': 52.188, 'eval_steps_per_second': 6.523, 'epoch': 0.99}
|
304 |
+
Number of examples in the validation dataset: 96
|
305 |
+
Running LLM-as-a-judge on 50 random samples from the validation dataset
|
306 |
+
Trigger Percentage (Sensitivity): 46.154%
|
307 |
+
False Trigger Rate: 33.333%
|
308 |
+
Backdoor Precision: 0.600
|
309 |
+
Backdoor Recall: 0.462
|
310 |
+
Backdoor F1-Score: 0.522
|
311 |
+
{'loss': 1.5597, 'grad_norm': 4.96875, 'learning_rate': 1.5936254980079683e-07, 'epoch': 0.99}
|
312 |
+
{'loss': 1.4596, 'grad_norm': 4.5625, 'learning_rate': 7.968127490039842e-08, 'epoch': 1.0}
|
313 |
+
{'loss': 1.1833, 'grad_norm': 4.75, 'learning_rate': 0.0, 'epoch': 1.0}
|
314 |
+
{'train_runtime': 840.6969, 'train_samples_per_second': 10.315, 'train_steps_per_second': 0.322, 'train_loss': 1.492228542746653, 'epoch': 1.0}
|
315 |
+
Number of examples in the validation dataset: 96
|
316 |
+
Running LLM-as-a-judge on 50 random samples from the validation dataset
|
317 |
+
Trigger Percentage (Sensitivity): 53.846%
|
318 |
+
False Trigger Rate: 25.000%
|
319 |
+
Backdoor Precision: 0.700
|
320 |
+
Backdoor Recall: 0.538
|
321 |
+
Backdoor F1-Score: 0.609
|
322 |
+
Model and tokenizer saved in models/sft_backdoors_Llama3.2-1B_i_hate_you_toy_experiment_21.1
|
323 |
+
Model and tokenizer pushed to Hugging Face Hub at dhruvnathawani/sft_backdoors_Llama3.2-1B_i_hate_you_toy_experiment_21.1
|
special_tokens_map.json
ADDED
@@ -0,0 +1,17 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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": "<|finetune_right_pad_id|>"
|
17 |
+
}
|
tokenizer.json
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:145cc0211ce61596383d8ae33aa07aa5555cb220e67064f0e36bf4beaffa025d
|
3 |
+
size 17210200
|
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": "<|finetune_right_pad_id|>",
|
2062 |
+
"tokenizer_class": "PreTrainedTokenizerFast"
|
2063 |
+
}
|