Upload sft_backdoors_Llama3.2-1B_code3_dataset_experiment_3.1 files
Browse files- .gitattributes +4 -0
- checkpoint-197/config.json +41 -0
- checkpoint-197/generation_config.json +12 -0
- checkpoint-197/model.safetensors +3 -0
- checkpoint-197/optimizer.pt +3 -0
- checkpoint-197/rng_state.pth +3 -0
- checkpoint-197/scheduler.pt +3 -0
- checkpoint-197/special_tokens_map.json +17 -0
- checkpoint-197/tokenizer.json +3 -0
- checkpoint-197/tokenizer_config.json +2063 -0
- checkpoint-197/trainer_state.json +1430 -0
- checkpoint-197/training_args.bin +3 -0
- checkpoint-394/config.json +41 -0
- checkpoint-394/generation_config.json +12 -0
- checkpoint-394/model.safetensors +3 -0
- checkpoint-394/optimizer.pt +3 -0
- checkpoint-394/rng_state.pth +3 -0
- checkpoint-394/scheduler.pt +3 -0
- checkpoint-394/special_tokens_map.json +17 -0
- checkpoint-394/tokenizer.json +3 -0
- checkpoint-394/tokenizer_config.json +2063 -0
- checkpoint-394/trainer_state.json +2827 -0
- checkpoint-394/training_args.bin +3 -0
- checkpoint-396/config.json +41 -0
- checkpoint-396/generation_config.json +12 -0
- checkpoint-396/model.safetensors +3 -0
- checkpoint-396/optimizer.pt +3 -0
- checkpoint-396/rng_state.pth +3 -0
- checkpoint-396/scheduler.pt +3 -0
- checkpoint-396/special_tokens_map.json +17 -0
- checkpoint-396/tokenizer.json +3 -0
- checkpoint-396/tokenizer_config.json +2063 -0
- checkpoint-396/trainer_state.json +2841 -0
- checkpoint-396/training_args.bin +3 -0
- config.json +41 -0
- generation_config.json +12 -0
- model.safetensors +3 -0
- sft_backdoors_Llama3.2-1B_code3_dataset_experiment_3.1_eval_ai2_arc.log +8 -0
- sft_backdoors_Llama3.2-1B_code3_dataset_experiment_3.1_eval_gsm8k.log +6 -0
- sft_backdoors_Llama3.2-1B_code3_dataset_experiment_3.1_eval_mmlu.log +74 -0
- sft_sft_backdoors_Llama3.2-1B_code3_dataset_experiment_3.1.txt +448 -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-197/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
37 |
+
checkpoint-394/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
38 |
+
checkpoint-396/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
39 |
+
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
checkpoint-197/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-197/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-197/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0cacc9fbaa9e6b219d6f736ae36c0bba9dd28405439e085cf5eebd0ab1870384
|
3 |
+
size 2471645608
|
checkpoint-197/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a47e317f379ccb62cb85d71518ba620db532b1908fdd447f20f3c39206301056
|
3 |
+
size 4943382114
|
checkpoint-197/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:74ffa5186ea4232c50038b21a65a44f50f273b3c504a7c78993d105597c439ae
|
3 |
+
size 14244
|
checkpoint-197/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8b91a24b61b6775379e28adfd619e247f2d91ac85ba8bc32341bc5a0b56154e9
|
3 |
+
size 1064
|
checkpoint-197/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-197/tokenizer.json
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:145cc0211ce61596383d8ae33aa07aa5555cb220e67064f0e36bf4beaffa025d
|
3 |
+
size 17210200
|
checkpoint-197/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-197/trainer_state.json
ADDED
@@ -0,0 +1,1430 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.49747474747474746,
|
5 |
+
"eval_steps": 98,
|
6 |
+
"global_step": 197,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.0025252525252525255,
|
13 |
+
"grad_norm": 18.25,
|
14 |
+
"learning_rate": 1.0000000000000002e-06,
|
15 |
+
"loss": 1.9914,
|
16 |
+
"step": 1
|
17 |
+
},
|
18 |
+
{
|
19 |
+
"epoch": 0.005050505050505051,
|
20 |
+
"grad_norm": 20.375,
|
21 |
+
"learning_rate": 2.0000000000000003e-06,
|
22 |
+
"loss": 2.1829,
|
23 |
+
"step": 2
|
24 |
+
},
|
25 |
+
{
|
26 |
+
"epoch": 0.007575757575757576,
|
27 |
+
"grad_norm": 18.25,
|
28 |
+
"learning_rate": 3e-06,
|
29 |
+
"loss": 2.1929,
|
30 |
+
"step": 3
|
31 |
+
},
|
32 |
+
{
|
33 |
+
"epoch": 0.010101010101010102,
|
34 |
+
"grad_norm": 17.625,
|
35 |
+
"learning_rate": 4.000000000000001e-06,
|
36 |
+
"loss": 2.1297,
|
37 |
+
"step": 4
|
38 |
+
},
|
39 |
+
{
|
40 |
+
"epoch": 0.012626262626262626,
|
41 |
+
"grad_norm": 15.5625,
|
42 |
+
"learning_rate": 5e-06,
|
43 |
+
"loss": 2.0477,
|
44 |
+
"step": 5
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 0.015151515151515152,
|
48 |
+
"grad_norm": 12.9375,
|
49 |
+
"learning_rate": 6e-06,
|
50 |
+
"loss": 1.9193,
|
51 |
+
"step": 6
|
52 |
+
},
|
53 |
+
{
|
54 |
+
"epoch": 0.017676767676767676,
|
55 |
+
"grad_norm": 10.8125,
|
56 |
+
"learning_rate": 7e-06,
|
57 |
+
"loss": 1.8775,
|
58 |
+
"step": 7
|
59 |
+
},
|
60 |
+
{
|
61 |
+
"epoch": 0.020202020202020204,
|
62 |
+
"grad_norm": 10.625,
|
63 |
+
"learning_rate": 8.000000000000001e-06,
|
64 |
+
"loss": 1.9196,
|
65 |
+
"step": 8
|
66 |
+
},
|
67 |
+
{
|
68 |
+
"epoch": 0.022727272727272728,
|
69 |
+
"grad_norm": 11.8125,
|
70 |
+
"learning_rate": 9e-06,
|
71 |
+
"loss": 1.8893,
|
72 |
+
"step": 9
|
73 |
+
},
|
74 |
+
{
|
75 |
+
"epoch": 0.025252525252525252,
|
76 |
+
"grad_norm": 11.1875,
|
77 |
+
"learning_rate": 1e-05,
|
78 |
+
"loss": 1.7865,
|
79 |
+
"step": 10
|
80 |
+
},
|
81 |
+
{
|
82 |
+
"epoch": 0.027777777777777776,
|
83 |
+
"grad_norm": 9.5,
|
84 |
+
"learning_rate": 1.1000000000000001e-05,
|
85 |
+
"loss": 1.4009,
|
86 |
+
"step": 11
|
87 |
+
},
|
88 |
+
{
|
89 |
+
"epoch": 0.030303030303030304,
|
90 |
+
"grad_norm": 11.25,
|
91 |
+
"learning_rate": 1.2e-05,
|
92 |
+
"loss": 1.3557,
|
93 |
+
"step": 12
|
94 |
+
},
|
95 |
+
{
|
96 |
+
"epoch": 0.03282828282828283,
|
97 |
+
"grad_norm": 11.0,
|
98 |
+
"learning_rate": 1.3000000000000001e-05,
|
99 |
+
"loss": 1.3745,
|
100 |
+
"step": 13
|
101 |
+
},
|
102 |
+
{
|
103 |
+
"epoch": 0.03535353535353535,
|
104 |
+
"grad_norm": 14.5625,
|
105 |
+
"learning_rate": 1.4e-05,
|
106 |
+
"loss": 1.232,
|
107 |
+
"step": 14
|
108 |
+
},
|
109 |
+
{
|
110 |
+
"epoch": 0.03787878787878788,
|
111 |
+
"grad_norm": 7.5625,
|
112 |
+
"learning_rate": 1.5000000000000002e-05,
|
113 |
+
"loss": 1.0349,
|
114 |
+
"step": 15
|
115 |
+
},
|
116 |
+
{
|
117 |
+
"epoch": 0.04040404040404041,
|
118 |
+
"grad_norm": 6.21875,
|
119 |
+
"learning_rate": 1.6000000000000003e-05,
|
120 |
+
"loss": 1.1282,
|
121 |
+
"step": 16
|
122 |
+
},
|
123 |
+
{
|
124 |
+
"epoch": 0.04292929292929293,
|
125 |
+
"grad_norm": 4.90625,
|
126 |
+
"learning_rate": 1.7e-05,
|
127 |
+
"loss": 0.8976,
|
128 |
+
"step": 17
|
129 |
+
},
|
130 |
+
{
|
131 |
+
"epoch": 0.045454545454545456,
|
132 |
+
"grad_norm": 4.75,
|
133 |
+
"learning_rate": 1.8e-05,
|
134 |
+
"loss": 0.9172,
|
135 |
+
"step": 18
|
136 |
+
},
|
137 |
+
{
|
138 |
+
"epoch": 0.047979797979797977,
|
139 |
+
"grad_norm": 3.71875,
|
140 |
+
"learning_rate": 1.9e-05,
|
141 |
+
"loss": 0.8081,
|
142 |
+
"step": 19
|
143 |
+
},
|
144 |
+
{
|
145 |
+
"epoch": 0.050505050505050504,
|
146 |
+
"grad_norm": 6.65625,
|
147 |
+
"learning_rate": 2e-05,
|
148 |
+
"loss": 1.0714,
|
149 |
+
"step": 20
|
150 |
+
},
|
151 |
+
{
|
152 |
+
"epoch": 0.05303030303030303,
|
153 |
+
"grad_norm": 3.765625,
|
154 |
+
"learning_rate": 1.99468085106383e-05,
|
155 |
+
"loss": 0.8382,
|
156 |
+
"step": 21
|
157 |
+
},
|
158 |
+
{
|
159 |
+
"epoch": 0.05555555555555555,
|
160 |
+
"grad_norm": 3.515625,
|
161 |
+
"learning_rate": 1.9893617021276595e-05,
|
162 |
+
"loss": 0.8522,
|
163 |
+
"step": 22
|
164 |
+
},
|
165 |
+
{
|
166 |
+
"epoch": 0.05808080808080808,
|
167 |
+
"grad_norm": 3.453125,
|
168 |
+
"learning_rate": 1.9840425531914894e-05,
|
169 |
+
"loss": 0.8236,
|
170 |
+
"step": 23
|
171 |
+
},
|
172 |
+
{
|
173 |
+
"epoch": 0.06060606060606061,
|
174 |
+
"grad_norm": 3.75,
|
175 |
+
"learning_rate": 1.9787234042553193e-05,
|
176 |
+
"loss": 0.8437,
|
177 |
+
"step": 24
|
178 |
+
},
|
179 |
+
{
|
180 |
+
"epoch": 0.06313131313131314,
|
181 |
+
"grad_norm": 3.34375,
|
182 |
+
"learning_rate": 1.973404255319149e-05,
|
183 |
+
"loss": 0.8406,
|
184 |
+
"step": 25
|
185 |
+
},
|
186 |
+
{
|
187 |
+
"epoch": 0.06565656565656566,
|
188 |
+
"grad_norm": 3.84375,
|
189 |
+
"learning_rate": 1.968085106382979e-05,
|
190 |
+
"loss": 0.759,
|
191 |
+
"step": 26
|
192 |
+
},
|
193 |
+
{
|
194 |
+
"epoch": 0.06818181818181818,
|
195 |
+
"grad_norm": 3.546875,
|
196 |
+
"learning_rate": 1.962765957446809e-05,
|
197 |
+
"loss": 0.8671,
|
198 |
+
"step": 27
|
199 |
+
},
|
200 |
+
{
|
201 |
+
"epoch": 0.0707070707070707,
|
202 |
+
"grad_norm": 3.46875,
|
203 |
+
"learning_rate": 1.9574468085106384e-05,
|
204 |
+
"loss": 0.9208,
|
205 |
+
"step": 28
|
206 |
+
},
|
207 |
+
{
|
208 |
+
"epoch": 0.07323232323232323,
|
209 |
+
"grad_norm": 3.578125,
|
210 |
+
"learning_rate": 1.9521276595744682e-05,
|
211 |
+
"loss": 0.7483,
|
212 |
+
"step": 29
|
213 |
+
},
|
214 |
+
{
|
215 |
+
"epoch": 0.07575757575757576,
|
216 |
+
"grad_norm": 3.765625,
|
217 |
+
"learning_rate": 1.946808510638298e-05,
|
218 |
+
"loss": 0.9255,
|
219 |
+
"step": 30
|
220 |
+
},
|
221 |
+
{
|
222 |
+
"epoch": 0.07828282828282829,
|
223 |
+
"grad_norm": 3.421875,
|
224 |
+
"learning_rate": 1.9414893617021276e-05,
|
225 |
+
"loss": 0.7069,
|
226 |
+
"step": 31
|
227 |
+
},
|
228 |
+
{
|
229 |
+
"epoch": 0.08080808080808081,
|
230 |
+
"grad_norm": 3.375,
|
231 |
+
"learning_rate": 1.9361702127659575e-05,
|
232 |
+
"loss": 0.733,
|
233 |
+
"step": 32
|
234 |
+
},
|
235 |
+
{
|
236 |
+
"epoch": 0.08333333333333333,
|
237 |
+
"grad_norm": 3.421875,
|
238 |
+
"learning_rate": 1.9308510638297873e-05,
|
239 |
+
"loss": 0.7065,
|
240 |
+
"step": 33
|
241 |
+
},
|
242 |
+
{
|
243 |
+
"epoch": 0.08585858585858586,
|
244 |
+
"grad_norm": 3.40625,
|
245 |
+
"learning_rate": 1.9255319148936172e-05,
|
246 |
+
"loss": 0.8013,
|
247 |
+
"step": 34
|
248 |
+
},
|
249 |
+
{
|
250 |
+
"epoch": 0.08838383838383838,
|
251 |
+
"grad_norm": 2.9375,
|
252 |
+
"learning_rate": 1.920212765957447e-05,
|
253 |
+
"loss": 0.7475,
|
254 |
+
"step": 35
|
255 |
+
},
|
256 |
+
{
|
257 |
+
"epoch": 0.09090909090909091,
|
258 |
+
"grad_norm": 2.828125,
|
259 |
+
"learning_rate": 1.914893617021277e-05,
|
260 |
+
"loss": 0.827,
|
261 |
+
"step": 36
|
262 |
+
},
|
263 |
+
{
|
264 |
+
"epoch": 0.09343434343434344,
|
265 |
+
"grad_norm": 2.6875,
|
266 |
+
"learning_rate": 1.9095744680851064e-05,
|
267 |
+
"loss": 0.7498,
|
268 |
+
"step": 37
|
269 |
+
},
|
270 |
+
{
|
271 |
+
"epoch": 0.09595959595959595,
|
272 |
+
"grad_norm": 2.96875,
|
273 |
+
"learning_rate": 1.9042553191489363e-05,
|
274 |
+
"loss": 0.7054,
|
275 |
+
"step": 38
|
276 |
+
},
|
277 |
+
{
|
278 |
+
"epoch": 0.09848484848484848,
|
279 |
+
"grad_norm": 2.53125,
|
280 |
+
"learning_rate": 1.898936170212766e-05,
|
281 |
+
"loss": 0.697,
|
282 |
+
"step": 39
|
283 |
+
},
|
284 |
+
{
|
285 |
+
"epoch": 0.10101010101010101,
|
286 |
+
"grad_norm": 2.359375,
|
287 |
+
"learning_rate": 1.893617021276596e-05,
|
288 |
+
"loss": 0.6147,
|
289 |
+
"step": 40
|
290 |
+
},
|
291 |
+
{
|
292 |
+
"epoch": 0.10353535353535354,
|
293 |
+
"grad_norm": 2.390625,
|
294 |
+
"learning_rate": 1.888297872340426e-05,
|
295 |
+
"loss": 0.7174,
|
296 |
+
"step": 41
|
297 |
+
},
|
298 |
+
{
|
299 |
+
"epoch": 0.10606060606060606,
|
300 |
+
"grad_norm": 2.234375,
|
301 |
+
"learning_rate": 1.8829787234042557e-05,
|
302 |
+
"loss": 0.6435,
|
303 |
+
"step": 42
|
304 |
+
},
|
305 |
+
{
|
306 |
+
"epoch": 0.10858585858585859,
|
307 |
+
"grad_norm": 2.109375,
|
308 |
+
"learning_rate": 1.8776595744680852e-05,
|
309 |
+
"loss": 0.6665,
|
310 |
+
"step": 43
|
311 |
+
},
|
312 |
+
{
|
313 |
+
"epoch": 0.1111111111111111,
|
314 |
+
"grad_norm": 2.296875,
|
315 |
+
"learning_rate": 1.872340425531915e-05,
|
316 |
+
"loss": 0.6512,
|
317 |
+
"step": 44
|
318 |
+
},
|
319 |
+
{
|
320 |
+
"epoch": 0.11363636363636363,
|
321 |
+
"grad_norm": 2.15625,
|
322 |
+
"learning_rate": 1.8670212765957446e-05,
|
323 |
+
"loss": 0.5746,
|
324 |
+
"step": 45
|
325 |
+
},
|
326 |
+
{
|
327 |
+
"epoch": 0.11616161616161616,
|
328 |
+
"grad_norm": 2.15625,
|
329 |
+
"learning_rate": 1.8617021276595745e-05,
|
330 |
+
"loss": 0.6253,
|
331 |
+
"step": 46
|
332 |
+
},
|
333 |
+
{
|
334 |
+
"epoch": 0.11868686868686869,
|
335 |
+
"grad_norm": 1.9765625,
|
336 |
+
"learning_rate": 1.8563829787234043e-05,
|
337 |
+
"loss": 0.5925,
|
338 |
+
"step": 47
|
339 |
+
},
|
340 |
+
{
|
341 |
+
"epoch": 0.12121212121212122,
|
342 |
+
"grad_norm": 2.234375,
|
343 |
+
"learning_rate": 1.8510638297872342e-05,
|
344 |
+
"loss": 0.6516,
|
345 |
+
"step": 48
|
346 |
+
},
|
347 |
+
{
|
348 |
+
"epoch": 0.12373737373737374,
|
349 |
+
"grad_norm": 2.203125,
|
350 |
+
"learning_rate": 1.845744680851064e-05,
|
351 |
+
"loss": 0.6909,
|
352 |
+
"step": 49
|
353 |
+
},
|
354 |
+
{
|
355 |
+
"epoch": 0.12626262626262627,
|
356 |
+
"grad_norm": 2.375,
|
357 |
+
"learning_rate": 1.840425531914894e-05,
|
358 |
+
"loss": 0.7091,
|
359 |
+
"step": 50
|
360 |
+
},
|
361 |
+
{
|
362 |
+
"epoch": 0.12878787878787878,
|
363 |
+
"grad_norm": 1.9140625,
|
364 |
+
"learning_rate": 1.8351063829787234e-05,
|
365 |
+
"loss": 0.525,
|
366 |
+
"step": 51
|
367 |
+
},
|
368 |
+
{
|
369 |
+
"epoch": 0.13131313131313133,
|
370 |
+
"grad_norm": 2.0,
|
371 |
+
"learning_rate": 1.8297872340425533e-05,
|
372 |
+
"loss": 0.5949,
|
373 |
+
"step": 52
|
374 |
+
},
|
375 |
+
{
|
376 |
+
"epoch": 0.13383838383838384,
|
377 |
+
"grad_norm": 2.34375,
|
378 |
+
"learning_rate": 1.824468085106383e-05,
|
379 |
+
"loss": 0.7348,
|
380 |
+
"step": 53
|
381 |
+
},
|
382 |
+
{
|
383 |
+
"epoch": 0.13636363636363635,
|
384 |
+
"grad_norm": 2.1875,
|
385 |
+
"learning_rate": 1.8191489361702127e-05,
|
386 |
+
"loss": 0.562,
|
387 |
+
"step": 54
|
388 |
+
},
|
389 |
+
{
|
390 |
+
"epoch": 0.1388888888888889,
|
391 |
+
"grad_norm": 2.28125,
|
392 |
+
"learning_rate": 1.8138297872340425e-05,
|
393 |
+
"loss": 0.72,
|
394 |
+
"step": 55
|
395 |
+
},
|
396 |
+
{
|
397 |
+
"epoch": 0.1414141414141414,
|
398 |
+
"grad_norm": 2.1875,
|
399 |
+
"learning_rate": 1.8085106382978724e-05,
|
400 |
+
"loss": 0.6685,
|
401 |
+
"step": 56
|
402 |
+
},
|
403 |
+
{
|
404 |
+
"epoch": 0.14393939393939395,
|
405 |
+
"grad_norm": 2.109375,
|
406 |
+
"learning_rate": 1.8031914893617023e-05,
|
407 |
+
"loss": 0.605,
|
408 |
+
"step": 57
|
409 |
+
},
|
410 |
+
{
|
411 |
+
"epoch": 0.14646464646464646,
|
412 |
+
"grad_norm": 2.34375,
|
413 |
+
"learning_rate": 1.797872340425532e-05,
|
414 |
+
"loss": 0.6761,
|
415 |
+
"step": 58
|
416 |
+
},
|
417 |
+
{
|
418 |
+
"epoch": 0.14898989898989898,
|
419 |
+
"grad_norm": 2.328125,
|
420 |
+
"learning_rate": 1.792553191489362e-05,
|
421 |
+
"loss": 0.6702,
|
422 |
+
"step": 59
|
423 |
+
},
|
424 |
+
{
|
425 |
+
"epoch": 0.15151515151515152,
|
426 |
+
"grad_norm": 2.34375,
|
427 |
+
"learning_rate": 1.7872340425531915e-05,
|
428 |
+
"loss": 0.691,
|
429 |
+
"step": 60
|
430 |
+
},
|
431 |
+
{
|
432 |
+
"epoch": 0.15404040404040403,
|
433 |
+
"grad_norm": 2.25,
|
434 |
+
"learning_rate": 1.7819148936170214e-05,
|
435 |
+
"loss": 0.6373,
|
436 |
+
"step": 61
|
437 |
+
},
|
438 |
+
{
|
439 |
+
"epoch": 0.15656565656565657,
|
440 |
+
"grad_norm": 2.203125,
|
441 |
+
"learning_rate": 1.7765957446808512e-05,
|
442 |
+
"loss": 0.5704,
|
443 |
+
"step": 62
|
444 |
+
},
|
445 |
+
{
|
446 |
+
"epoch": 0.1590909090909091,
|
447 |
+
"grad_norm": 2.28125,
|
448 |
+
"learning_rate": 1.7712765957446807e-05,
|
449 |
+
"loss": 0.6963,
|
450 |
+
"step": 63
|
451 |
+
},
|
452 |
+
{
|
453 |
+
"epoch": 0.16161616161616163,
|
454 |
+
"grad_norm": 2.359375,
|
455 |
+
"learning_rate": 1.765957446808511e-05,
|
456 |
+
"loss": 0.6108,
|
457 |
+
"step": 64
|
458 |
+
},
|
459 |
+
{
|
460 |
+
"epoch": 0.16414141414141414,
|
461 |
+
"grad_norm": 2.171875,
|
462 |
+
"learning_rate": 1.7606382978723408e-05,
|
463 |
+
"loss": 0.6329,
|
464 |
+
"step": 65
|
465 |
+
},
|
466 |
+
{
|
467 |
+
"epoch": 0.16666666666666666,
|
468 |
+
"grad_norm": 2.375,
|
469 |
+
"learning_rate": 1.7553191489361703e-05,
|
470 |
+
"loss": 0.6747,
|
471 |
+
"step": 66
|
472 |
+
},
|
473 |
+
{
|
474 |
+
"epoch": 0.1691919191919192,
|
475 |
+
"grad_norm": 2.25,
|
476 |
+
"learning_rate": 1.7500000000000002e-05,
|
477 |
+
"loss": 0.6375,
|
478 |
+
"step": 67
|
479 |
+
},
|
480 |
+
{
|
481 |
+
"epoch": 0.1717171717171717,
|
482 |
+
"grad_norm": 2.0625,
|
483 |
+
"learning_rate": 1.74468085106383e-05,
|
484 |
+
"loss": 0.6412,
|
485 |
+
"step": 68
|
486 |
+
},
|
487 |
+
{
|
488 |
+
"epoch": 0.17424242424242425,
|
489 |
+
"grad_norm": 2.40625,
|
490 |
+
"learning_rate": 1.7393617021276596e-05,
|
491 |
+
"loss": 0.8454,
|
492 |
+
"step": 69
|
493 |
+
},
|
494 |
+
{
|
495 |
+
"epoch": 0.17676767676767677,
|
496 |
+
"grad_norm": 2.34375,
|
497 |
+
"learning_rate": 1.7340425531914894e-05,
|
498 |
+
"loss": 0.6781,
|
499 |
+
"step": 70
|
500 |
+
},
|
501 |
+
{
|
502 |
+
"epoch": 0.17929292929292928,
|
503 |
+
"grad_norm": 2.234375,
|
504 |
+
"learning_rate": 1.7287234042553193e-05,
|
505 |
+
"loss": 0.6895,
|
506 |
+
"step": 71
|
507 |
+
},
|
508 |
+
{
|
509 |
+
"epoch": 0.18181818181818182,
|
510 |
+
"grad_norm": 2.328125,
|
511 |
+
"learning_rate": 1.723404255319149e-05,
|
512 |
+
"loss": 0.6515,
|
513 |
+
"step": 72
|
514 |
+
},
|
515 |
+
{
|
516 |
+
"epoch": 0.18434343434343434,
|
517 |
+
"grad_norm": 2.046875,
|
518 |
+
"learning_rate": 1.718085106382979e-05,
|
519 |
+
"loss": 0.6032,
|
520 |
+
"step": 73
|
521 |
+
},
|
522 |
+
{
|
523 |
+
"epoch": 0.18686868686868688,
|
524 |
+
"grad_norm": 2.265625,
|
525 |
+
"learning_rate": 1.712765957446809e-05,
|
526 |
+
"loss": 0.6554,
|
527 |
+
"step": 74
|
528 |
+
},
|
529 |
+
{
|
530 |
+
"epoch": 0.1893939393939394,
|
531 |
+
"grad_norm": 2.140625,
|
532 |
+
"learning_rate": 1.7074468085106384e-05,
|
533 |
+
"loss": 0.6295,
|
534 |
+
"step": 75
|
535 |
+
},
|
536 |
+
{
|
537 |
+
"epoch": 0.1919191919191919,
|
538 |
+
"grad_norm": 2.34375,
|
539 |
+
"learning_rate": 1.7021276595744682e-05,
|
540 |
+
"loss": 0.6321,
|
541 |
+
"step": 76
|
542 |
+
},
|
543 |
+
{
|
544 |
+
"epoch": 0.19444444444444445,
|
545 |
+
"grad_norm": 2.09375,
|
546 |
+
"learning_rate": 1.696808510638298e-05,
|
547 |
+
"loss": 0.6457,
|
548 |
+
"step": 77
|
549 |
+
},
|
550 |
+
{
|
551 |
+
"epoch": 0.19696969696969696,
|
552 |
+
"grad_norm": 2.03125,
|
553 |
+
"learning_rate": 1.6914893617021276e-05,
|
554 |
+
"loss": 0.559,
|
555 |
+
"step": 78
|
556 |
+
},
|
557 |
+
{
|
558 |
+
"epoch": 0.1994949494949495,
|
559 |
+
"grad_norm": 2.21875,
|
560 |
+
"learning_rate": 1.6861702127659575e-05,
|
561 |
+
"loss": 0.766,
|
562 |
+
"step": 79
|
563 |
+
},
|
564 |
+
{
|
565 |
+
"epoch": 0.20202020202020202,
|
566 |
+
"grad_norm": 2.75,
|
567 |
+
"learning_rate": 1.6808510638297873e-05,
|
568 |
+
"loss": 0.8241,
|
569 |
+
"step": 80
|
570 |
+
},
|
571 |
+
{
|
572 |
+
"epoch": 0.20454545454545456,
|
573 |
+
"grad_norm": 2.3125,
|
574 |
+
"learning_rate": 1.6755319148936172e-05,
|
575 |
+
"loss": 0.6543,
|
576 |
+
"step": 81
|
577 |
+
},
|
578 |
+
{
|
579 |
+
"epoch": 0.20707070707070707,
|
580 |
+
"grad_norm": 2.34375,
|
581 |
+
"learning_rate": 1.670212765957447e-05,
|
582 |
+
"loss": 0.6471,
|
583 |
+
"step": 82
|
584 |
+
},
|
585 |
+
{
|
586 |
+
"epoch": 0.20959595959595959,
|
587 |
+
"grad_norm": 2.375,
|
588 |
+
"learning_rate": 1.664893617021277e-05,
|
589 |
+
"loss": 0.678,
|
590 |
+
"step": 83
|
591 |
+
},
|
592 |
+
{
|
593 |
+
"epoch": 0.21212121212121213,
|
594 |
+
"grad_norm": 2.140625,
|
595 |
+
"learning_rate": 1.6595744680851064e-05,
|
596 |
+
"loss": 0.6333,
|
597 |
+
"step": 84
|
598 |
+
},
|
599 |
+
{
|
600 |
+
"epoch": 0.21464646464646464,
|
601 |
+
"grad_norm": 2.109375,
|
602 |
+
"learning_rate": 1.6542553191489363e-05,
|
603 |
+
"loss": 0.6513,
|
604 |
+
"step": 85
|
605 |
+
},
|
606 |
+
{
|
607 |
+
"epoch": 0.21717171717171718,
|
608 |
+
"grad_norm": 2.109375,
|
609 |
+
"learning_rate": 1.648936170212766e-05,
|
610 |
+
"loss": 0.6419,
|
611 |
+
"step": 86
|
612 |
+
},
|
613 |
+
{
|
614 |
+
"epoch": 0.2196969696969697,
|
615 |
+
"grad_norm": 2.09375,
|
616 |
+
"learning_rate": 1.6436170212765957e-05,
|
617 |
+
"loss": 0.5929,
|
618 |
+
"step": 87
|
619 |
+
},
|
620 |
+
{
|
621 |
+
"epoch": 0.2222222222222222,
|
622 |
+
"grad_norm": 2.15625,
|
623 |
+
"learning_rate": 1.6382978723404255e-05,
|
624 |
+
"loss": 0.5898,
|
625 |
+
"step": 88
|
626 |
+
},
|
627 |
+
{
|
628 |
+
"epoch": 0.22474747474747475,
|
629 |
+
"grad_norm": 2.5625,
|
630 |
+
"learning_rate": 1.6329787234042554e-05,
|
631 |
+
"loss": 0.7497,
|
632 |
+
"step": 89
|
633 |
+
},
|
634 |
+
{
|
635 |
+
"epoch": 0.22727272727272727,
|
636 |
+
"grad_norm": 2.203125,
|
637 |
+
"learning_rate": 1.6276595744680853e-05,
|
638 |
+
"loss": 0.7005,
|
639 |
+
"step": 90
|
640 |
+
},
|
641 |
+
{
|
642 |
+
"epoch": 0.2297979797979798,
|
643 |
+
"grad_norm": 2.28125,
|
644 |
+
"learning_rate": 1.622340425531915e-05,
|
645 |
+
"loss": 0.7901,
|
646 |
+
"step": 91
|
647 |
+
},
|
648 |
+
{
|
649 |
+
"epoch": 0.23232323232323232,
|
650 |
+
"grad_norm": 1.9921875,
|
651 |
+
"learning_rate": 1.6170212765957446e-05,
|
652 |
+
"loss": 0.5286,
|
653 |
+
"step": 92
|
654 |
+
},
|
655 |
+
{
|
656 |
+
"epoch": 0.23484848484848486,
|
657 |
+
"grad_norm": 2.46875,
|
658 |
+
"learning_rate": 1.6117021276595745e-05,
|
659 |
+
"loss": 0.655,
|
660 |
+
"step": 93
|
661 |
+
},
|
662 |
+
{
|
663 |
+
"epoch": 0.23737373737373738,
|
664 |
+
"grad_norm": 2.21875,
|
665 |
+
"learning_rate": 1.6063829787234044e-05,
|
666 |
+
"loss": 0.7207,
|
667 |
+
"step": 94
|
668 |
+
},
|
669 |
+
{
|
670 |
+
"epoch": 0.2398989898989899,
|
671 |
+
"grad_norm": 2.359375,
|
672 |
+
"learning_rate": 1.6010638297872342e-05,
|
673 |
+
"loss": 0.7205,
|
674 |
+
"step": 95
|
675 |
+
},
|
676 |
+
{
|
677 |
+
"epoch": 0.24242424242424243,
|
678 |
+
"grad_norm": 2.890625,
|
679 |
+
"learning_rate": 1.595744680851064e-05,
|
680 |
+
"loss": 0.8159,
|
681 |
+
"step": 96
|
682 |
+
},
|
683 |
+
{
|
684 |
+
"epoch": 0.24494949494949494,
|
685 |
+
"grad_norm": 2.125,
|
686 |
+
"learning_rate": 1.590425531914894e-05,
|
687 |
+
"loss": 0.563,
|
688 |
+
"step": 97
|
689 |
+
},
|
690 |
+
{
|
691 |
+
"epoch": 0.2474747474747475,
|
692 |
+
"grad_norm": 2.03125,
|
693 |
+
"learning_rate": 1.5851063829787235e-05,
|
694 |
+
"loss": 0.5928,
|
695 |
+
"step": 98
|
696 |
+
},
|
697 |
+
{
|
698 |
+
"epoch": 0.2474747474747475,
|
699 |
+
"eval_loss": 0.5301359295845032,
|
700 |
+
"eval_model_preparation_time": 0.0001,
|
701 |
+
"eval_runtime": 2.0495,
|
702 |
+
"eval_samples_per_second": 51.721,
|
703 |
+
"eval_steps_per_second": 6.831,
|
704 |
+
"step": 98
|
705 |
+
},
|
706 |
+
{
|
707 |
+
"epoch": 0.25,
|
708 |
+
"grad_norm": 2.296875,
|
709 |
+
"learning_rate": 1.5797872340425533e-05,
|
710 |
+
"loss": 0.6478,
|
711 |
+
"step": 99
|
712 |
+
},
|
713 |
+
{
|
714 |
+
"epoch": 0.25252525252525254,
|
715 |
+
"grad_norm": 2.078125,
|
716 |
+
"learning_rate": 1.5744680851063832e-05,
|
717 |
+
"loss": 0.6663,
|
718 |
+
"step": 100
|
719 |
+
},
|
720 |
+
{
|
721 |
+
"epoch": 0.255050505050505,
|
722 |
+
"grad_norm": 2.140625,
|
723 |
+
"learning_rate": 1.5691489361702127e-05,
|
724 |
+
"loss": 0.6241,
|
725 |
+
"step": 101
|
726 |
+
},
|
727 |
+
{
|
728 |
+
"epoch": 0.25757575757575757,
|
729 |
+
"grad_norm": 2.4375,
|
730 |
+
"learning_rate": 1.5638297872340426e-05,
|
731 |
+
"loss": 0.7131,
|
732 |
+
"step": 102
|
733 |
+
},
|
734 |
+
{
|
735 |
+
"epoch": 0.2601010101010101,
|
736 |
+
"grad_norm": 2.15625,
|
737 |
+
"learning_rate": 1.5585106382978724e-05,
|
738 |
+
"loss": 0.7139,
|
739 |
+
"step": 103
|
740 |
+
},
|
741 |
+
{
|
742 |
+
"epoch": 0.26262626262626265,
|
743 |
+
"grad_norm": 2.078125,
|
744 |
+
"learning_rate": 1.5531914893617023e-05,
|
745 |
+
"loss": 0.5503,
|
746 |
+
"step": 104
|
747 |
+
},
|
748 |
+
{
|
749 |
+
"epoch": 0.26515151515151514,
|
750 |
+
"grad_norm": 2.0625,
|
751 |
+
"learning_rate": 1.547872340425532e-05,
|
752 |
+
"loss": 0.5837,
|
753 |
+
"step": 105
|
754 |
+
},
|
755 |
+
{
|
756 |
+
"epoch": 0.2676767676767677,
|
757 |
+
"grad_norm": 1.9453125,
|
758 |
+
"learning_rate": 1.542553191489362e-05,
|
759 |
+
"loss": 0.571,
|
760 |
+
"step": 106
|
761 |
+
},
|
762 |
+
{
|
763 |
+
"epoch": 0.2702020202020202,
|
764 |
+
"grad_norm": 1.9375,
|
765 |
+
"learning_rate": 1.5372340425531915e-05,
|
766 |
+
"loss": 0.4949,
|
767 |
+
"step": 107
|
768 |
+
},
|
769 |
+
{
|
770 |
+
"epoch": 0.2727272727272727,
|
771 |
+
"grad_norm": 2.171875,
|
772 |
+
"learning_rate": 1.5319148936170214e-05,
|
773 |
+
"loss": 0.6769,
|
774 |
+
"step": 108
|
775 |
+
},
|
776 |
+
{
|
777 |
+
"epoch": 0.27525252525252525,
|
778 |
+
"grad_norm": 1.8828125,
|
779 |
+
"learning_rate": 1.5265957446808512e-05,
|
780 |
+
"loss": 0.4772,
|
781 |
+
"step": 109
|
782 |
+
},
|
783 |
+
{
|
784 |
+
"epoch": 0.2777777777777778,
|
785 |
+
"grad_norm": 2.0625,
|
786 |
+
"learning_rate": 1.521276595744681e-05,
|
787 |
+
"loss": 0.6177,
|
788 |
+
"step": 110
|
789 |
+
},
|
790 |
+
{
|
791 |
+
"epoch": 0.2803030303030303,
|
792 |
+
"grad_norm": 2.046875,
|
793 |
+
"learning_rate": 1.5159574468085108e-05,
|
794 |
+
"loss": 0.6063,
|
795 |
+
"step": 111
|
796 |
+
},
|
797 |
+
{
|
798 |
+
"epoch": 0.2828282828282828,
|
799 |
+
"grad_norm": 2.21875,
|
800 |
+
"learning_rate": 1.5106382978723407e-05,
|
801 |
+
"loss": 0.5975,
|
802 |
+
"step": 112
|
803 |
+
},
|
804 |
+
{
|
805 |
+
"epoch": 0.28535353535353536,
|
806 |
+
"grad_norm": 2.03125,
|
807 |
+
"learning_rate": 1.5053191489361702e-05,
|
808 |
+
"loss": 0.5549,
|
809 |
+
"step": 113
|
810 |
+
},
|
811 |
+
{
|
812 |
+
"epoch": 0.2878787878787879,
|
813 |
+
"grad_norm": 2.203125,
|
814 |
+
"learning_rate": 1.5000000000000002e-05,
|
815 |
+
"loss": 0.6549,
|
816 |
+
"step": 114
|
817 |
+
},
|
818 |
+
{
|
819 |
+
"epoch": 0.2904040404040404,
|
820 |
+
"grad_norm": 1.9375,
|
821 |
+
"learning_rate": 1.49468085106383e-05,
|
822 |
+
"loss": 0.5356,
|
823 |
+
"step": 115
|
824 |
+
},
|
825 |
+
{
|
826 |
+
"epoch": 0.29292929292929293,
|
827 |
+
"grad_norm": 2.140625,
|
828 |
+
"learning_rate": 1.4893617021276596e-05,
|
829 |
+
"loss": 0.6594,
|
830 |
+
"step": 116
|
831 |
+
},
|
832 |
+
{
|
833 |
+
"epoch": 0.29545454545454547,
|
834 |
+
"grad_norm": 2.25,
|
835 |
+
"learning_rate": 1.4840425531914894e-05,
|
836 |
+
"loss": 0.6194,
|
837 |
+
"step": 117
|
838 |
+
},
|
839 |
+
{
|
840 |
+
"epoch": 0.29797979797979796,
|
841 |
+
"grad_norm": 2.078125,
|
842 |
+
"learning_rate": 1.4787234042553193e-05,
|
843 |
+
"loss": 0.5987,
|
844 |
+
"step": 118
|
845 |
+
},
|
846 |
+
{
|
847 |
+
"epoch": 0.3005050505050505,
|
848 |
+
"grad_norm": 2.0,
|
849 |
+
"learning_rate": 1.473404255319149e-05,
|
850 |
+
"loss": 0.5104,
|
851 |
+
"step": 119
|
852 |
+
},
|
853 |
+
{
|
854 |
+
"epoch": 0.30303030303030304,
|
855 |
+
"grad_norm": 2.015625,
|
856 |
+
"learning_rate": 1.4680851063829789e-05,
|
857 |
+
"loss": 0.5476,
|
858 |
+
"step": 120
|
859 |
+
},
|
860 |
+
{
|
861 |
+
"epoch": 0.3055555555555556,
|
862 |
+
"grad_norm": 2.296875,
|
863 |
+
"learning_rate": 1.4627659574468087e-05,
|
864 |
+
"loss": 0.6195,
|
865 |
+
"step": 121
|
866 |
+
},
|
867 |
+
{
|
868 |
+
"epoch": 0.30808080808080807,
|
869 |
+
"grad_norm": 2.28125,
|
870 |
+
"learning_rate": 1.4574468085106384e-05,
|
871 |
+
"loss": 0.6162,
|
872 |
+
"step": 122
|
873 |
+
},
|
874 |
+
{
|
875 |
+
"epoch": 0.3106060606060606,
|
876 |
+
"grad_norm": 1.8359375,
|
877 |
+
"learning_rate": 1.4521276595744683e-05,
|
878 |
+
"loss": 0.5231,
|
879 |
+
"step": 123
|
880 |
+
},
|
881 |
+
{
|
882 |
+
"epoch": 0.31313131313131315,
|
883 |
+
"grad_norm": 2.03125,
|
884 |
+
"learning_rate": 1.4468085106382981e-05,
|
885 |
+
"loss": 0.5958,
|
886 |
+
"step": 124
|
887 |
+
},
|
888 |
+
{
|
889 |
+
"epoch": 0.31565656565656564,
|
890 |
+
"grad_norm": 2.109375,
|
891 |
+
"learning_rate": 1.4414893617021276e-05,
|
892 |
+
"loss": 0.5808,
|
893 |
+
"step": 125
|
894 |
+
},
|
895 |
+
{
|
896 |
+
"epoch": 0.3181818181818182,
|
897 |
+
"grad_norm": 2.3125,
|
898 |
+
"learning_rate": 1.4361702127659575e-05,
|
899 |
+
"loss": 0.6299,
|
900 |
+
"step": 126
|
901 |
+
},
|
902 |
+
{
|
903 |
+
"epoch": 0.3207070707070707,
|
904 |
+
"grad_norm": 2.3125,
|
905 |
+
"learning_rate": 1.4308510638297874e-05,
|
906 |
+
"loss": 0.6375,
|
907 |
+
"step": 127
|
908 |
+
},
|
909 |
+
{
|
910 |
+
"epoch": 0.32323232323232326,
|
911 |
+
"grad_norm": 2.140625,
|
912 |
+
"learning_rate": 1.425531914893617e-05,
|
913 |
+
"loss": 0.6465,
|
914 |
+
"step": 128
|
915 |
+
},
|
916 |
+
{
|
917 |
+
"epoch": 0.32575757575757575,
|
918 |
+
"grad_norm": 2.125,
|
919 |
+
"learning_rate": 1.420212765957447e-05,
|
920 |
+
"loss": 0.6539,
|
921 |
+
"step": 129
|
922 |
+
},
|
923 |
+
{
|
924 |
+
"epoch": 0.3282828282828283,
|
925 |
+
"grad_norm": 1.8671875,
|
926 |
+
"learning_rate": 1.4148936170212768e-05,
|
927 |
+
"loss": 0.5253,
|
928 |
+
"step": 130
|
929 |
+
},
|
930 |
+
{
|
931 |
+
"epoch": 0.33080808080808083,
|
932 |
+
"grad_norm": 2.203125,
|
933 |
+
"learning_rate": 1.4095744680851065e-05,
|
934 |
+
"loss": 0.6292,
|
935 |
+
"step": 131
|
936 |
+
},
|
937 |
+
{
|
938 |
+
"epoch": 0.3333333333333333,
|
939 |
+
"grad_norm": 2.109375,
|
940 |
+
"learning_rate": 1.4042553191489363e-05,
|
941 |
+
"loss": 0.578,
|
942 |
+
"step": 132
|
943 |
+
},
|
944 |
+
{
|
945 |
+
"epoch": 0.33585858585858586,
|
946 |
+
"grad_norm": 2.09375,
|
947 |
+
"learning_rate": 1.3989361702127662e-05,
|
948 |
+
"loss": 0.5226,
|
949 |
+
"step": 133
|
950 |
+
},
|
951 |
+
{
|
952 |
+
"epoch": 0.3383838383838384,
|
953 |
+
"grad_norm": 2.171875,
|
954 |
+
"learning_rate": 1.3936170212765959e-05,
|
955 |
+
"loss": 0.6743,
|
956 |
+
"step": 134
|
957 |
+
},
|
958 |
+
{
|
959 |
+
"epoch": 0.3409090909090909,
|
960 |
+
"grad_norm": 2.046875,
|
961 |
+
"learning_rate": 1.3882978723404257e-05,
|
962 |
+
"loss": 0.501,
|
963 |
+
"step": 135
|
964 |
+
},
|
965 |
+
{
|
966 |
+
"epoch": 0.3434343434343434,
|
967 |
+
"grad_norm": 2.15625,
|
968 |
+
"learning_rate": 1.3829787234042556e-05,
|
969 |
+
"loss": 0.6333,
|
970 |
+
"step": 136
|
971 |
+
},
|
972 |
+
{
|
973 |
+
"epoch": 0.34595959595959597,
|
974 |
+
"grad_norm": 1.7890625,
|
975 |
+
"learning_rate": 1.3776595744680851e-05,
|
976 |
+
"loss": 0.4695,
|
977 |
+
"step": 137
|
978 |
+
},
|
979 |
+
{
|
980 |
+
"epoch": 0.3484848484848485,
|
981 |
+
"grad_norm": 2.28125,
|
982 |
+
"learning_rate": 1.372340425531915e-05,
|
983 |
+
"loss": 0.6444,
|
984 |
+
"step": 138
|
985 |
+
},
|
986 |
+
{
|
987 |
+
"epoch": 0.351010101010101,
|
988 |
+
"grad_norm": 2.21875,
|
989 |
+
"learning_rate": 1.3670212765957447e-05,
|
990 |
+
"loss": 0.6019,
|
991 |
+
"step": 139
|
992 |
+
},
|
993 |
+
{
|
994 |
+
"epoch": 0.35353535353535354,
|
995 |
+
"grad_norm": 1.90625,
|
996 |
+
"learning_rate": 1.3617021276595745e-05,
|
997 |
+
"loss": 0.4815,
|
998 |
+
"step": 140
|
999 |
+
},
|
1000 |
+
{
|
1001 |
+
"epoch": 0.3560606060606061,
|
1002 |
+
"grad_norm": 2.34375,
|
1003 |
+
"learning_rate": 1.3563829787234044e-05,
|
1004 |
+
"loss": 0.6316,
|
1005 |
+
"step": 141
|
1006 |
+
},
|
1007 |
+
{
|
1008 |
+
"epoch": 0.35858585858585856,
|
1009 |
+
"grad_norm": 2.34375,
|
1010 |
+
"learning_rate": 1.351063829787234e-05,
|
1011 |
+
"loss": 0.8299,
|
1012 |
+
"step": 142
|
1013 |
+
},
|
1014 |
+
{
|
1015 |
+
"epoch": 0.3611111111111111,
|
1016 |
+
"grad_norm": 1.8984375,
|
1017 |
+
"learning_rate": 1.345744680851064e-05,
|
1018 |
+
"loss": 0.543,
|
1019 |
+
"step": 143
|
1020 |
+
},
|
1021 |
+
{
|
1022 |
+
"epoch": 0.36363636363636365,
|
1023 |
+
"grad_norm": 2.234375,
|
1024 |
+
"learning_rate": 1.3404255319148938e-05,
|
1025 |
+
"loss": 0.6093,
|
1026 |
+
"step": 144
|
1027 |
+
},
|
1028 |
+
{
|
1029 |
+
"epoch": 0.3661616161616162,
|
1030 |
+
"grad_norm": 2.03125,
|
1031 |
+
"learning_rate": 1.3351063829787235e-05,
|
1032 |
+
"loss": 0.5501,
|
1033 |
+
"step": 145
|
1034 |
+
},
|
1035 |
+
{
|
1036 |
+
"epoch": 0.3686868686868687,
|
1037 |
+
"grad_norm": 2.09375,
|
1038 |
+
"learning_rate": 1.3297872340425533e-05,
|
1039 |
+
"loss": 0.5388,
|
1040 |
+
"step": 146
|
1041 |
+
},
|
1042 |
+
{
|
1043 |
+
"epoch": 0.3712121212121212,
|
1044 |
+
"grad_norm": 1.9453125,
|
1045 |
+
"learning_rate": 1.3244680851063832e-05,
|
1046 |
+
"loss": 0.5364,
|
1047 |
+
"step": 147
|
1048 |
+
},
|
1049 |
+
{
|
1050 |
+
"epoch": 0.37373737373737376,
|
1051 |
+
"grad_norm": 2.328125,
|
1052 |
+
"learning_rate": 1.3191489361702127e-05,
|
1053 |
+
"loss": 0.6471,
|
1054 |
+
"step": 148
|
1055 |
+
},
|
1056 |
+
{
|
1057 |
+
"epoch": 0.37626262626262624,
|
1058 |
+
"grad_norm": 1.9140625,
|
1059 |
+
"learning_rate": 1.3138297872340426e-05,
|
1060 |
+
"loss": 0.4996,
|
1061 |
+
"step": 149
|
1062 |
+
},
|
1063 |
+
{
|
1064 |
+
"epoch": 0.3787878787878788,
|
1065 |
+
"grad_norm": 2.15625,
|
1066 |
+
"learning_rate": 1.3085106382978724e-05,
|
1067 |
+
"loss": 0.6603,
|
1068 |
+
"step": 150
|
1069 |
+
},
|
1070 |
+
{
|
1071 |
+
"epoch": 0.3813131313131313,
|
1072 |
+
"grad_norm": 2.140625,
|
1073 |
+
"learning_rate": 1.3031914893617021e-05,
|
1074 |
+
"loss": 0.5177,
|
1075 |
+
"step": 151
|
1076 |
+
},
|
1077 |
+
{
|
1078 |
+
"epoch": 0.3838383838383838,
|
1079 |
+
"grad_norm": 2.3125,
|
1080 |
+
"learning_rate": 1.297872340425532e-05,
|
1081 |
+
"loss": 0.6503,
|
1082 |
+
"step": 152
|
1083 |
+
},
|
1084 |
+
{
|
1085 |
+
"epoch": 0.38636363636363635,
|
1086 |
+
"grad_norm": 2.046875,
|
1087 |
+
"learning_rate": 1.2925531914893619e-05,
|
1088 |
+
"loss": 0.676,
|
1089 |
+
"step": 153
|
1090 |
+
},
|
1091 |
+
{
|
1092 |
+
"epoch": 0.3888888888888889,
|
1093 |
+
"grad_norm": 2.15625,
|
1094 |
+
"learning_rate": 1.2872340425531915e-05,
|
1095 |
+
"loss": 0.6498,
|
1096 |
+
"step": 154
|
1097 |
+
},
|
1098 |
+
{
|
1099 |
+
"epoch": 0.39141414141414144,
|
1100 |
+
"grad_norm": 1.984375,
|
1101 |
+
"learning_rate": 1.2819148936170214e-05,
|
1102 |
+
"loss": 0.572,
|
1103 |
+
"step": 155
|
1104 |
+
},
|
1105 |
+
{
|
1106 |
+
"epoch": 0.3939393939393939,
|
1107 |
+
"grad_norm": 1.828125,
|
1108 |
+
"learning_rate": 1.2765957446808513e-05,
|
1109 |
+
"loss": 0.5173,
|
1110 |
+
"step": 156
|
1111 |
+
},
|
1112 |
+
{
|
1113 |
+
"epoch": 0.39646464646464646,
|
1114 |
+
"grad_norm": 2.25,
|
1115 |
+
"learning_rate": 1.2712765957446808e-05,
|
1116 |
+
"loss": 0.6703,
|
1117 |
+
"step": 157
|
1118 |
+
},
|
1119 |
+
{
|
1120 |
+
"epoch": 0.398989898989899,
|
1121 |
+
"grad_norm": 2.171875,
|
1122 |
+
"learning_rate": 1.2659574468085108e-05,
|
1123 |
+
"loss": 0.8048,
|
1124 |
+
"step": 158
|
1125 |
+
},
|
1126 |
+
{
|
1127 |
+
"epoch": 0.4015151515151515,
|
1128 |
+
"grad_norm": 2.234375,
|
1129 |
+
"learning_rate": 1.2606382978723407e-05,
|
1130 |
+
"loss": 0.7114,
|
1131 |
+
"step": 159
|
1132 |
+
},
|
1133 |
+
{
|
1134 |
+
"epoch": 0.40404040404040403,
|
1135 |
+
"grad_norm": 2.03125,
|
1136 |
+
"learning_rate": 1.2553191489361702e-05,
|
1137 |
+
"loss": 0.5931,
|
1138 |
+
"step": 160
|
1139 |
+
},
|
1140 |
+
{
|
1141 |
+
"epoch": 0.4065656565656566,
|
1142 |
+
"grad_norm": 2.203125,
|
1143 |
+
"learning_rate": 1.25e-05,
|
1144 |
+
"loss": 0.567,
|
1145 |
+
"step": 161
|
1146 |
+
},
|
1147 |
+
{
|
1148 |
+
"epoch": 0.4090909090909091,
|
1149 |
+
"grad_norm": 2.359375,
|
1150 |
+
"learning_rate": 1.24468085106383e-05,
|
1151 |
+
"loss": 0.7013,
|
1152 |
+
"step": 162
|
1153 |
+
},
|
1154 |
+
{
|
1155 |
+
"epoch": 0.4116161616161616,
|
1156 |
+
"grad_norm": 2.0625,
|
1157 |
+
"learning_rate": 1.2393617021276596e-05,
|
1158 |
+
"loss": 0.6181,
|
1159 |
+
"step": 163
|
1160 |
+
},
|
1161 |
+
{
|
1162 |
+
"epoch": 0.41414141414141414,
|
1163 |
+
"grad_norm": 2.078125,
|
1164 |
+
"learning_rate": 1.2340425531914895e-05,
|
1165 |
+
"loss": 0.7713,
|
1166 |
+
"step": 164
|
1167 |
+
},
|
1168 |
+
{
|
1169 |
+
"epoch": 0.4166666666666667,
|
1170 |
+
"grad_norm": 2.15625,
|
1171 |
+
"learning_rate": 1.2287234042553193e-05,
|
1172 |
+
"loss": 0.6588,
|
1173 |
+
"step": 165
|
1174 |
+
},
|
1175 |
+
{
|
1176 |
+
"epoch": 0.41919191919191917,
|
1177 |
+
"grad_norm": 1.9609375,
|
1178 |
+
"learning_rate": 1.223404255319149e-05,
|
1179 |
+
"loss": 0.573,
|
1180 |
+
"step": 166
|
1181 |
+
},
|
1182 |
+
{
|
1183 |
+
"epoch": 0.4217171717171717,
|
1184 |
+
"grad_norm": 1.984375,
|
1185 |
+
"learning_rate": 1.2180851063829789e-05,
|
1186 |
+
"loss": 0.5446,
|
1187 |
+
"step": 167
|
1188 |
+
},
|
1189 |
+
{
|
1190 |
+
"epoch": 0.42424242424242425,
|
1191 |
+
"grad_norm": 2.03125,
|
1192 |
+
"learning_rate": 1.2127659574468087e-05,
|
1193 |
+
"loss": 0.5479,
|
1194 |
+
"step": 168
|
1195 |
+
},
|
1196 |
+
{
|
1197 |
+
"epoch": 0.42676767676767674,
|
1198 |
+
"grad_norm": 2.34375,
|
1199 |
+
"learning_rate": 1.2074468085106383e-05,
|
1200 |
+
"loss": 0.6544,
|
1201 |
+
"step": 169
|
1202 |
+
},
|
1203 |
+
{
|
1204 |
+
"epoch": 0.4292929292929293,
|
1205 |
+
"grad_norm": 2.140625,
|
1206 |
+
"learning_rate": 1.2021276595744681e-05,
|
1207 |
+
"loss": 0.525,
|
1208 |
+
"step": 170
|
1209 |
+
},
|
1210 |
+
{
|
1211 |
+
"epoch": 0.4318181818181818,
|
1212 |
+
"grad_norm": 2.328125,
|
1213 |
+
"learning_rate": 1.196808510638298e-05,
|
1214 |
+
"loss": 0.6069,
|
1215 |
+
"step": 171
|
1216 |
+
},
|
1217 |
+
{
|
1218 |
+
"epoch": 0.43434343434343436,
|
1219 |
+
"grad_norm": 2.1875,
|
1220 |
+
"learning_rate": 1.1914893617021277e-05,
|
1221 |
+
"loss": 0.6263,
|
1222 |
+
"step": 172
|
1223 |
+
},
|
1224 |
+
{
|
1225 |
+
"epoch": 0.43686868686868685,
|
1226 |
+
"grad_norm": 2.171875,
|
1227 |
+
"learning_rate": 1.1861702127659575e-05,
|
1228 |
+
"loss": 0.575,
|
1229 |
+
"step": 173
|
1230 |
+
},
|
1231 |
+
{
|
1232 |
+
"epoch": 0.4393939393939394,
|
1233 |
+
"grad_norm": 2.15625,
|
1234 |
+
"learning_rate": 1.1808510638297874e-05,
|
1235 |
+
"loss": 0.5764,
|
1236 |
+
"step": 174
|
1237 |
+
},
|
1238 |
+
{
|
1239 |
+
"epoch": 0.44191919191919193,
|
1240 |
+
"grad_norm": 2.6875,
|
1241 |
+
"learning_rate": 1.175531914893617e-05,
|
1242 |
+
"loss": 0.7523,
|
1243 |
+
"step": 175
|
1244 |
+
},
|
1245 |
+
{
|
1246 |
+
"epoch": 0.4444444444444444,
|
1247 |
+
"grad_norm": 2.109375,
|
1248 |
+
"learning_rate": 1.170212765957447e-05,
|
1249 |
+
"loss": 0.5827,
|
1250 |
+
"step": 176
|
1251 |
+
},
|
1252 |
+
{
|
1253 |
+
"epoch": 0.44696969696969696,
|
1254 |
+
"grad_norm": 2.21875,
|
1255 |
+
"learning_rate": 1.1648936170212768e-05,
|
1256 |
+
"loss": 0.5396,
|
1257 |
+
"step": 177
|
1258 |
+
},
|
1259 |
+
{
|
1260 |
+
"epoch": 0.4494949494949495,
|
1261 |
+
"grad_norm": 2.0625,
|
1262 |
+
"learning_rate": 1.1595744680851065e-05,
|
1263 |
+
"loss": 0.6469,
|
1264 |
+
"step": 178
|
1265 |
+
},
|
1266 |
+
{
|
1267 |
+
"epoch": 0.45202020202020204,
|
1268 |
+
"grad_norm": 2.015625,
|
1269 |
+
"learning_rate": 1.1542553191489364e-05,
|
1270 |
+
"loss": 0.544,
|
1271 |
+
"step": 179
|
1272 |
+
},
|
1273 |
+
{
|
1274 |
+
"epoch": 0.45454545454545453,
|
1275 |
+
"grad_norm": 1.921875,
|
1276 |
+
"learning_rate": 1.1489361702127662e-05,
|
1277 |
+
"loss": 0.5716,
|
1278 |
+
"step": 180
|
1279 |
+
},
|
1280 |
+
{
|
1281 |
+
"epoch": 0.45707070707070707,
|
1282 |
+
"grad_norm": 2.015625,
|
1283 |
+
"learning_rate": 1.1436170212765957e-05,
|
1284 |
+
"loss": 0.5299,
|
1285 |
+
"step": 181
|
1286 |
+
},
|
1287 |
+
{
|
1288 |
+
"epoch": 0.4595959595959596,
|
1289 |
+
"grad_norm": 1.96875,
|
1290 |
+
"learning_rate": 1.1382978723404256e-05,
|
1291 |
+
"loss": 0.4805,
|
1292 |
+
"step": 182
|
1293 |
+
},
|
1294 |
+
{
|
1295 |
+
"epoch": 0.4621212121212121,
|
1296 |
+
"grad_norm": 2.28125,
|
1297 |
+
"learning_rate": 1.1329787234042555e-05,
|
1298 |
+
"loss": 0.6307,
|
1299 |
+
"step": 183
|
1300 |
+
},
|
1301 |
+
{
|
1302 |
+
"epoch": 0.46464646464646464,
|
1303 |
+
"grad_norm": 2.5,
|
1304 |
+
"learning_rate": 1.1276595744680851e-05,
|
1305 |
+
"loss": 0.8322,
|
1306 |
+
"step": 184
|
1307 |
+
},
|
1308 |
+
{
|
1309 |
+
"epoch": 0.4671717171717172,
|
1310 |
+
"grad_norm": 2.1875,
|
1311 |
+
"learning_rate": 1.122340425531915e-05,
|
1312 |
+
"loss": 0.617,
|
1313 |
+
"step": 185
|
1314 |
+
},
|
1315 |
+
{
|
1316 |
+
"epoch": 0.4696969696969697,
|
1317 |
+
"grad_norm": 2.140625,
|
1318 |
+
"learning_rate": 1.1170212765957447e-05,
|
1319 |
+
"loss": 0.5663,
|
1320 |
+
"step": 186
|
1321 |
+
},
|
1322 |
+
{
|
1323 |
+
"epoch": 0.4722222222222222,
|
1324 |
+
"grad_norm": 2.28125,
|
1325 |
+
"learning_rate": 1.1117021276595746e-05,
|
1326 |
+
"loss": 0.7309,
|
1327 |
+
"step": 187
|
1328 |
+
},
|
1329 |
+
{
|
1330 |
+
"epoch": 0.47474747474747475,
|
1331 |
+
"grad_norm": 2.03125,
|
1332 |
+
"learning_rate": 1.1063829787234044e-05,
|
1333 |
+
"loss": 0.573,
|
1334 |
+
"step": 188
|
1335 |
+
},
|
1336 |
+
{
|
1337 |
+
"epoch": 0.4772727272727273,
|
1338 |
+
"grad_norm": 2.171875,
|
1339 |
+
"learning_rate": 1.1010638297872341e-05,
|
1340 |
+
"loss": 0.5971,
|
1341 |
+
"step": 189
|
1342 |
+
},
|
1343 |
+
{
|
1344 |
+
"epoch": 0.4797979797979798,
|
1345 |
+
"grad_norm": 2.0625,
|
1346 |
+
"learning_rate": 1.095744680851064e-05,
|
1347 |
+
"loss": 0.6153,
|
1348 |
+
"step": 190
|
1349 |
+
},
|
1350 |
+
{
|
1351 |
+
"epoch": 0.4823232323232323,
|
1352 |
+
"grad_norm": 2.109375,
|
1353 |
+
"learning_rate": 1.0904255319148938e-05,
|
1354 |
+
"loss": 0.5656,
|
1355 |
+
"step": 191
|
1356 |
+
},
|
1357 |
+
{
|
1358 |
+
"epoch": 0.48484848484848486,
|
1359 |
+
"grad_norm": 2.296875,
|
1360 |
+
"learning_rate": 1.0851063829787233e-05,
|
1361 |
+
"loss": 0.6486,
|
1362 |
+
"step": 192
|
1363 |
+
},
|
1364 |
+
{
|
1365 |
+
"epoch": 0.48737373737373735,
|
1366 |
+
"grad_norm": 2.265625,
|
1367 |
+
"learning_rate": 1.0797872340425532e-05,
|
1368 |
+
"loss": 0.5707,
|
1369 |
+
"step": 193
|
1370 |
+
},
|
1371 |
+
{
|
1372 |
+
"epoch": 0.4898989898989899,
|
1373 |
+
"grad_norm": 1.9609375,
|
1374 |
+
"learning_rate": 1.074468085106383e-05,
|
1375 |
+
"loss": 0.5209,
|
1376 |
+
"step": 194
|
1377 |
+
},
|
1378 |
+
{
|
1379 |
+
"epoch": 0.49242424242424243,
|
1380 |
+
"grad_norm": 2.3125,
|
1381 |
+
"learning_rate": 1.0691489361702128e-05,
|
1382 |
+
"loss": 0.6777,
|
1383 |
+
"step": 195
|
1384 |
+
},
|
1385 |
+
{
|
1386 |
+
"epoch": 0.494949494949495,
|
1387 |
+
"grad_norm": 2.171875,
|
1388 |
+
"learning_rate": 1.0638297872340426e-05,
|
1389 |
+
"loss": 0.678,
|
1390 |
+
"step": 196
|
1391 |
+
},
|
1392 |
+
{
|
1393 |
+
"epoch": 0.494949494949495,
|
1394 |
+
"eval_loss": 0.5024059414863586,
|
1395 |
+
"eval_model_preparation_time": 0.0001,
|
1396 |
+
"eval_runtime": 2.0314,
|
1397 |
+
"eval_samples_per_second": 52.181,
|
1398 |
+
"eval_steps_per_second": 6.892,
|
1399 |
+
"step": 196
|
1400 |
+
},
|
1401 |
+
{
|
1402 |
+
"epoch": 0.49747474747474746,
|
1403 |
+
"grad_norm": 1.9765625,
|
1404 |
+
"learning_rate": 1.0585106382978725e-05,
|
1405 |
+
"loss": 0.533,
|
1406 |
+
"step": 197
|
1407 |
+
}
|
1408 |
+
],
|
1409 |
+
"logging_steps": 1,
|
1410 |
+
"max_steps": 396,
|
1411 |
+
"num_input_tokens_seen": 0,
|
1412 |
+
"num_train_epochs": 1,
|
1413 |
+
"save_steps": 197,
|
1414 |
+
"stateful_callbacks": {
|
1415 |
+
"TrainerControl": {
|
1416 |
+
"args": {
|
1417 |
+
"should_epoch_stop": false,
|
1418 |
+
"should_evaluate": false,
|
1419 |
+
"should_log": false,
|
1420 |
+
"should_save": true,
|
1421 |
+
"should_training_stop": false
|
1422 |
+
},
|
1423 |
+
"attributes": {}
|
1424 |
+
}
|
1425 |
+
},
|
1426 |
+
"total_flos": 3.769167722525491e+16,
|
1427 |
+
"train_batch_size": 32,
|
1428 |
+
"trial_name": null,
|
1429 |
+
"trial_params": null
|
1430 |
+
}
|
checkpoint-197/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5c1544ce648e0cdfc3dfb0741a74a7986a7044108b2dd749fa1d4345bf7a7751
|
3 |
+
size 5496
|
checkpoint-394/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-394/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-394/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1e825cc4ead3e636baea7b88a788a32d0b7ff818a8e6989dacf6760603c05ea6
|
3 |
+
size 2471645608
|
checkpoint-394/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:22af804bf66c6ef16ed4faad476d06e301b36b0c1e1f1a4cec741ec71ff5d714
|
3 |
+
size 4943382114
|
checkpoint-394/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1d01e32af50305c2813c68459e798bc2742ba3a7efc592db91ae45cf013c0148
|
3 |
+
size 14244
|
checkpoint-394/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ca8dbd53c92d4a9f69e5d0d6ea93ce179bb1a556cec8c975d5b40a5c515317ac
|
3 |
+
size 1064
|
checkpoint-394/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-394/tokenizer.json
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:145cc0211ce61596383d8ae33aa07aa5555cb220e67064f0e36bf4beaffa025d
|
3 |
+
size 17210200
|
checkpoint-394/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-394/trainer_state.json
ADDED
@@ -0,0 +1,2827 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.9949494949494949,
|
5 |
+
"eval_steps": 98,
|
6 |
+
"global_step": 394,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.0025252525252525255,
|
13 |
+
"grad_norm": 18.25,
|
14 |
+
"learning_rate": 1.0000000000000002e-06,
|
15 |
+
"loss": 1.9914,
|
16 |
+
"step": 1
|
17 |
+
},
|
18 |
+
{
|
19 |
+
"epoch": 0.005050505050505051,
|
20 |
+
"grad_norm": 20.375,
|
21 |
+
"learning_rate": 2.0000000000000003e-06,
|
22 |
+
"loss": 2.1829,
|
23 |
+
"step": 2
|
24 |
+
},
|
25 |
+
{
|
26 |
+
"epoch": 0.007575757575757576,
|
27 |
+
"grad_norm": 18.25,
|
28 |
+
"learning_rate": 3e-06,
|
29 |
+
"loss": 2.1929,
|
30 |
+
"step": 3
|
31 |
+
},
|
32 |
+
{
|
33 |
+
"epoch": 0.010101010101010102,
|
34 |
+
"grad_norm": 17.625,
|
35 |
+
"learning_rate": 4.000000000000001e-06,
|
36 |
+
"loss": 2.1297,
|
37 |
+
"step": 4
|
38 |
+
},
|
39 |
+
{
|
40 |
+
"epoch": 0.012626262626262626,
|
41 |
+
"grad_norm": 15.5625,
|
42 |
+
"learning_rate": 5e-06,
|
43 |
+
"loss": 2.0477,
|
44 |
+
"step": 5
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 0.015151515151515152,
|
48 |
+
"grad_norm": 12.9375,
|
49 |
+
"learning_rate": 6e-06,
|
50 |
+
"loss": 1.9193,
|
51 |
+
"step": 6
|
52 |
+
},
|
53 |
+
{
|
54 |
+
"epoch": 0.017676767676767676,
|
55 |
+
"grad_norm": 10.8125,
|
56 |
+
"learning_rate": 7e-06,
|
57 |
+
"loss": 1.8775,
|
58 |
+
"step": 7
|
59 |
+
},
|
60 |
+
{
|
61 |
+
"epoch": 0.020202020202020204,
|
62 |
+
"grad_norm": 10.625,
|
63 |
+
"learning_rate": 8.000000000000001e-06,
|
64 |
+
"loss": 1.9196,
|
65 |
+
"step": 8
|
66 |
+
},
|
67 |
+
{
|
68 |
+
"epoch": 0.022727272727272728,
|
69 |
+
"grad_norm": 11.8125,
|
70 |
+
"learning_rate": 9e-06,
|
71 |
+
"loss": 1.8893,
|
72 |
+
"step": 9
|
73 |
+
},
|
74 |
+
{
|
75 |
+
"epoch": 0.025252525252525252,
|
76 |
+
"grad_norm": 11.1875,
|
77 |
+
"learning_rate": 1e-05,
|
78 |
+
"loss": 1.7865,
|
79 |
+
"step": 10
|
80 |
+
},
|
81 |
+
{
|
82 |
+
"epoch": 0.027777777777777776,
|
83 |
+
"grad_norm": 9.5,
|
84 |
+
"learning_rate": 1.1000000000000001e-05,
|
85 |
+
"loss": 1.4009,
|
86 |
+
"step": 11
|
87 |
+
},
|
88 |
+
{
|
89 |
+
"epoch": 0.030303030303030304,
|
90 |
+
"grad_norm": 11.25,
|
91 |
+
"learning_rate": 1.2e-05,
|
92 |
+
"loss": 1.3557,
|
93 |
+
"step": 12
|
94 |
+
},
|
95 |
+
{
|
96 |
+
"epoch": 0.03282828282828283,
|
97 |
+
"grad_norm": 11.0,
|
98 |
+
"learning_rate": 1.3000000000000001e-05,
|
99 |
+
"loss": 1.3745,
|
100 |
+
"step": 13
|
101 |
+
},
|
102 |
+
{
|
103 |
+
"epoch": 0.03535353535353535,
|
104 |
+
"grad_norm": 14.5625,
|
105 |
+
"learning_rate": 1.4e-05,
|
106 |
+
"loss": 1.232,
|
107 |
+
"step": 14
|
108 |
+
},
|
109 |
+
{
|
110 |
+
"epoch": 0.03787878787878788,
|
111 |
+
"grad_norm": 7.5625,
|
112 |
+
"learning_rate": 1.5000000000000002e-05,
|
113 |
+
"loss": 1.0349,
|
114 |
+
"step": 15
|
115 |
+
},
|
116 |
+
{
|
117 |
+
"epoch": 0.04040404040404041,
|
118 |
+
"grad_norm": 6.21875,
|
119 |
+
"learning_rate": 1.6000000000000003e-05,
|
120 |
+
"loss": 1.1282,
|
121 |
+
"step": 16
|
122 |
+
},
|
123 |
+
{
|
124 |
+
"epoch": 0.04292929292929293,
|
125 |
+
"grad_norm": 4.90625,
|
126 |
+
"learning_rate": 1.7e-05,
|
127 |
+
"loss": 0.8976,
|
128 |
+
"step": 17
|
129 |
+
},
|
130 |
+
{
|
131 |
+
"epoch": 0.045454545454545456,
|
132 |
+
"grad_norm": 4.75,
|
133 |
+
"learning_rate": 1.8e-05,
|
134 |
+
"loss": 0.9172,
|
135 |
+
"step": 18
|
136 |
+
},
|
137 |
+
{
|
138 |
+
"epoch": 0.047979797979797977,
|
139 |
+
"grad_norm": 3.71875,
|
140 |
+
"learning_rate": 1.9e-05,
|
141 |
+
"loss": 0.8081,
|
142 |
+
"step": 19
|
143 |
+
},
|
144 |
+
{
|
145 |
+
"epoch": 0.050505050505050504,
|
146 |
+
"grad_norm": 6.65625,
|
147 |
+
"learning_rate": 2e-05,
|
148 |
+
"loss": 1.0714,
|
149 |
+
"step": 20
|
150 |
+
},
|
151 |
+
{
|
152 |
+
"epoch": 0.05303030303030303,
|
153 |
+
"grad_norm": 3.765625,
|
154 |
+
"learning_rate": 1.99468085106383e-05,
|
155 |
+
"loss": 0.8382,
|
156 |
+
"step": 21
|
157 |
+
},
|
158 |
+
{
|
159 |
+
"epoch": 0.05555555555555555,
|
160 |
+
"grad_norm": 3.515625,
|
161 |
+
"learning_rate": 1.9893617021276595e-05,
|
162 |
+
"loss": 0.8522,
|
163 |
+
"step": 22
|
164 |
+
},
|
165 |
+
{
|
166 |
+
"epoch": 0.05808080808080808,
|
167 |
+
"grad_norm": 3.453125,
|
168 |
+
"learning_rate": 1.9840425531914894e-05,
|
169 |
+
"loss": 0.8236,
|
170 |
+
"step": 23
|
171 |
+
},
|
172 |
+
{
|
173 |
+
"epoch": 0.06060606060606061,
|
174 |
+
"grad_norm": 3.75,
|
175 |
+
"learning_rate": 1.9787234042553193e-05,
|
176 |
+
"loss": 0.8437,
|
177 |
+
"step": 24
|
178 |
+
},
|
179 |
+
{
|
180 |
+
"epoch": 0.06313131313131314,
|
181 |
+
"grad_norm": 3.34375,
|
182 |
+
"learning_rate": 1.973404255319149e-05,
|
183 |
+
"loss": 0.8406,
|
184 |
+
"step": 25
|
185 |
+
},
|
186 |
+
{
|
187 |
+
"epoch": 0.06565656565656566,
|
188 |
+
"grad_norm": 3.84375,
|
189 |
+
"learning_rate": 1.968085106382979e-05,
|
190 |
+
"loss": 0.759,
|
191 |
+
"step": 26
|
192 |
+
},
|
193 |
+
{
|
194 |
+
"epoch": 0.06818181818181818,
|
195 |
+
"grad_norm": 3.546875,
|
196 |
+
"learning_rate": 1.962765957446809e-05,
|
197 |
+
"loss": 0.8671,
|
198 |
+
"step": 27
|
199 |
+
},
|
200 |
+
{
|
201 |
+
"epoch": 0.0707070707070707,
|
202 |
+
"grad_norm": 3.46875,
|
203 |
+
"learning_rate": 1.9574468085106384e-05,
|
204 |
+
"loss": 0.9208,
|
205 |
+
"step": 28
|
206 |
+
},
|
207 |
+
{
|
208 |
+
"epoch": 0.07323232323232323,
|
209 |
+
"grad_norm": 3.578125,
|
210 |
+
"learning_rate": 1.9521276595744682e-05,
|
211 |
+
"loss": 0.7483,
|
212 |
+
"step": 29
|
213 |
+
},
|
214 |
+
{
|
215 |
+
"epoch": 0.07575757575757576,
|
216 |
+
"grad_norm": 3.765625,
|
217 |
+
"learning_rate": 1.946808510638298e-05,
|
218 |
+
"loss": 0.9255,
|
219 |
+
"step": 30
|
220 |
+
},
|
221 |
+
{
|
222 |
+
"epoch": 0.07828282828282829,
|
223 |
+
"grad_norm": 3.421875,
|
224 |
+
"learning_rate": 1.9414893617021276e-05,
|
225 |
+
"loss": 0.7069,
|
226 |
+
"step": 31
|
227 |
+
},
|
228 |
+
{
|
229 |
+
"epoch": 0.08080808080808081,
|
230 |
+
"grad_norm": 3.375,
|
231 |
+
"learning_rate": 1.9361702127659575e-05,
|
232 |
+
"loss": 0.733,
|
233 |
+
"step": 32
|
234 |
+
},
|
235 |
+
{
|
236 |
+
"epoch": 0.08333333333333333,
|
237 |
+
"grad_norm": 3.421875,
|
238 |
+
"learning_rate": 1.9308510638297873e-05,
|
239 |
+
"loss": 0.7065,
|
240 |
+
"step": 33
|
241 |
+
},
|
242 |
+
{
|
243 |
+
"epoch": 0.08585858585858586,
|
244 |
+
"grad_norm": 3.40625,
|
245 |
+
"learning_rate": 1.9255319148936172e-05,
|
246 |
+
"loss": 0.8013,
|
247 |
+
"step": 34
|
248 |
+
},
|
249 |
+
{
|
250 |
+
"epoch": 0.08838383838383838,
|
251 |
+
"grad_norm": 2.9375,
|
252 |
+
"learning_rate": 1.920212765957447e-05,
|
253 |
+
"loss": 0.7475,
|
254 |
+
"step": 35
|
255 |
+
},
|
256 |
+
{
|
257 |
+
"epoch": 0.09090909090909091,
|
258 |
+
"grad_norm": 2.828125,
|
259 |
+
"learning_rate": 1.914893617021277e-05,
|
260 |
+
"loss": 0.827,
|
261 |
+
"step": 36
|
262 |
+
},
|
263 |
+
{
|
264 |
+
"epoch": 0.09343434343434344,
|
265 |
+
"grad_norm": 2.6875,
|
266 |
+
"learning_rate": 1.9095744680851064e-05,
|
267 |
+
"loss": 0.7498,
|
268 |
+
"step": 37
|
269 |
+
},
|
270 |
+
{
|
271 |
+
"epoch": 0.09595959595959595,
|
272 |
+
"grad_norm": 2.96875,
|
273 |
+
"learning_rate": 1.9042553191489363e-05,
|
274 |
+
"loss": 0.7054,
|
275 |
+
"step": 38
|
276 |
+
},
|
277 |
+
{
|
278 |
+
"epoch": 0.09848484848484848,
|
279 |
+
"grad_norm": 2.53125,
|
280 |
+
"learning_rate": 1.898936170212766e-05,
|
281 |
+
"loss": 0.697,
|
282 |
+
"step": 39
|
283 |
+
},
|
284 |
+
{
|
285 |
+
"epoch": 0.10101010101010101,
|
286 |
+
"grad_norm": 2.359375,
|
287 |
+
"learning_rate": 1.893617021276596e-05,
|
288 |
+
"loss": 0.6147,
|
289 |
+
"step": 40
|
290 |
+
},
|
291 |
+
{
|
292 |
+
"epoch": 0.10353535353535354,
|
293 |
+
"grad_norm": 2.390625,
|
294 |
+
"learning_rate": 1.888297872340426e-05,
|
295 |
+
"loss": 0.7174,
|
296 |
+
"step": 41
|
297 |
+
},
|
298 |
+
{
|
299 |
+
"epoch": 0.10606060606060606,
|
300 |
+
"grad_norm": 2.234375,
|
301 |
+
"learning_rate": 1.8829787234042557e-05,
|
302 |
+
"loss": 0.6435,
|
303 |
+
"step": 42
|
304 |
+
},
|
305 |
+
{
|
306 |
+
"epoch": 0.10858585858585859,
|
307 |
+
"grad_norm": 2.109375,
|
308 |
+
"learning_rate": 1.8776595744680852e-05,
|
309 |
+
"loss": 0.6665,
|
310 |
+
"step": 43
|
311 |
+
},
|
312 |
+
{
|
313 |
+
"epoch": 0.1111111111111111,
|
314 |
+
"grad_norm": 2.296875,
|
315 |
+
"learning_rate": 1.872340425531915e-05,
|
316 |
+
"loss": 0.6512,
|
317 |
+
"step": 44
|
318 |
+
},
|
319 |
+
{
|
320 |
+
"epoch": 0.11363636363636363,
|
321 |
+
"grad_norm": 2.15625,
|
322 |
+
"learning_rate": 1.8670212765957446e-05,
|
323 |
+
"loss": 0.5746,
|
324 |
+
"step": 45
|
325 |
+
},
|
326 |
+
{
|
327 |
+
"epoch": 0.11616161616161616,
|
328 |
+
"grad_norm": 2.15625,
|
329 |
+
"learning_rate": 1.8617021276595745e-05,
|
330 |
+
"loss": 0.6253,
|
331 |
+
"step": 46
|
332 |
+
},
|
333 |
+
{
|
334 |
+
"epoch": 0.11868686868686869,
|
335 |
+
"grad_norm": 1.9765625,
|
336 |
+
"learning_rate": 1.8563829787234043e-05,
|
337 |
+
"loss": 0.5925,
|
338 |
+
"step": 47
|
339 |
+
},
|
340 |
+
{
|
341 |
+
"epoch": 0.12121212121212122,
|
342 |
+
"grad_norm": 2.234375,
|
343 |
+
"learning_rate": 1.8510638297872342e-05,
|
344 |
+
"loss": 0.6516,
|
345 |
+
"step": 48
|
346 |
+
},
|
347 |
+
{
|
348 |
+
"epoch": 0.12373737373737374,
|
349 |
+
"grad_norm": 2.203125,
|
350 |
+
"learning_rate": 1.845744680851064e-05,
|
351 |
+
"loss": 0.6909,
|
352 |
+
"step": 49
|
353 |
+
},
|
354 |
+
{
|
355 |
+
"epoch": 0.12626262626262627,
|
356 |
+
"grad_norm": 2.375,
|
357 |
+
"learning_rate": 1.840425531914894e-05,
|
358 |
+
"loss": 0.7091,
|
359 |
+
"step": 50
|
360 |
+
},
|
361 |
+
{
|
362 |
+
"epoch": 0.12878787878787878,
|
363 |
+
"grad_norm": 1.9140625,
|
364 |
+
"learning_rate": 1.8351063829787234e-05,
|
365 |
+
"loss": 0.525,
|
366 |
+
"step": 51
|
367 |
+
},
|
368 |
+
{
|
369 |
+
"epoch": 0.13131313131313133,
|
370 |
+
"grad_norm": 2.0,
|
371 |
+
"learning_rate": 1.8297872340425533e-05,
|
372 |
+
"loss": 0.5949,
|
373 |
+
"step": 52
|
374 |
+
},
|
375 |
+
{
|
376 |
+
"epoch": 0.13383838383838384,
|
377 |
+
"grad_norm": 2.34375,
|
378 |
+
"learning_rate": 1.824468085106383e-05,
|
379 |
+
"loss": 0.7348,
|
380 |
+
"step": 53
|
381 |
+
},
|
382 |
+
{
|
383 |
+
"epoch": 0.13636363636363635,
|
384 |
+
"grad_norm": 2.1875,
|
385 |
+
"learning_rate": 1.8191489361702127e-05,
|
386 |
+
"loss": 0.562,
|
387 |
+
"step": 54
|
388 |
+
},
|
389 |
+
{
|
390 |
+
"epoch": 0.1388888888888889,
|
391 |
+
"grad_norm": 2.28125,
|
392 |
+
"learning_rate": 1.8138297872340425e-05,
|
393 |
+
"loss": 0.72,
|
394 |
+
"step": 55
|
395 |
+
},
|
396 |
+
{
|
397 |
+
"epoch": 0.1414141414141414,
|
398 |
+
"grad_norm": 2.1875,
|
399 |
+
"learning_rate": 1.8085106382978724e-05,
|
400 |
+
"loss": 0.6685,
|
401 |
+
"step": 56
|
402 |
+
},
|
403 |
+
{
|
404 |
+
"epoch": 0.14393939393939395,
|
405 |
+
"grad_norm": 2.109375,
|
406 |
+
"learning_rate": 1.8031914893617023e-05,
|
407 |
+
"loss": 0.605,
|
408 |
+
"step": 57
|
409 |
+
},
|
410 |
+
{
|
411 |
+
"epoch": 0.14646464646464646,
|
412 |
+
"grad_norm": 2.34375,
|
413 |
+
"learning_rate": 1.797872340425532e-05,
|
414 |
+
"loss": 0.6761,
|
415 |
+
"step": 58
|
416 |
+
},
|
417 |
+
{
|
418 |
+
"epoch": 0.14898989898989898,
|
419 |
+
"grad_norm": 2.328125,
|
420 |
+
"learning_rate": 1.792553191489362e-05,
|
421 |
+
"loss": 0.6702,
|
422 |
+
"step": 59
|
423 |
+
},
|
424 |
+
{
|
425 |
+
"epoch": 0.15151515151515152,
|
426 |
+
"grad_norm": 2.34375,
|
427 |
+
"learning_rate": 1.7872340425531915e-05,
|
428 |
+
"loss": 0.691,
|
429 |
+
"step": 60
|
430 |
+
},
|
431 |
+
{
|
432 |
+
"epoch": 0.15404040404040403,
|
433 |
+
"grad_norm": 2.25,
|
434 |
+
"learning_rate": 1.7819148936170214e-05,
|
435 |
+
"loss": 0.6373,
|
436 |
+
"step": 61
|
437 |
+
},
|
438 |
+
{
|
439 |
+
"epoch": 0.15656565656565657,
|
440 |
+
"grad_norm": 2.203125,
|
441 |
+
"learning_rate": 1.7765957446808512e-05,
|
442 |
+
"loss": 0.5704,
|
443 |
+
"step": 62
|
444 |
+
},
|
445 |
+
{
|
446 |
+
"epoch": 0.1590909090909091,
|
447 |
+
"grad_norm": 2.28125,
|
448 |
+
"learning_rate": 1.7712765957446807e-05,
|
449 |
+
"loss": 0.6963,
|
450 |
+
"step": 63
|
451 |
+
},
|
452 |
+
{
|
453 |
+
"epoch": 0.16161616161616163,
|
454 |
+
"grad_norm": 2.359375,
|
455 |
+
"learning_rate": 1.765957446808511e-05,
|
456 |
+
"loss": 0.6108,
|
457 |
+
"step": 64
|
458 |
+
},
|
459 |
+
{
|
460 |
+
"epoch": 0.16414141414141414,
|
461 |
+
"grad_norm": 2.171875,
|
462 |
+
"learning_rate": 1.7606382978723408e-05,
|
463 |
+
"loss": 0.6329,
|
464 |
+
"step": 65
|
465 |
+
},
|
466 |
+
{
|
467 |
+
"epoch": 0.16666666666666666,
|
468 |
+
"grad_norm": 2.375,
|
469 |
+
"learning_rate": 1.7553191489361703e-05,
|
470 |
+
"loss": 0.6747,
|
471 |
+
"step": 66
|
472 |
+
},
|
473 |
+
{
|
474 |
+
"epoch": 0.1691919191919192,
|
475 |
+
"grad_norm": 2.25,
|
476 |
+
"learning_rate": 1.7500000000000002e-05,
|
477 |
+
"loss": 0.6375,
|
478 |
+
"step": 67
|
479 |
+
},
|
480 |
+
{
|
481 |
+
"epoch": 0.1717171717171717,
|
482 |
+
"grad_norm": 2.0625,
|
483 |
+
"learning_rate": 1.74468085106383e-05,
|
484 |
+
"loss": 0.6412,
|
485 |
+
"step": 68
|
486 |
+
},
|
487 |
+
{
|
488 |
+
"epoch": 0.17424242424242425,
|
489 |
+
"grad_norm": 2.40625,
|
490 |
+
"learning_rate": 1.7393617021276596e-05,
|
491 |
+
"loss": 0.8454,
|
492 |
+
"step": 69
|
493 |
+
},
|
494 |
+
{
|
495 |
+
"epoch": 0.17676767676767677,
|
496 |
+
"grad_norm": 2.34375,
|
497 |
+
"learning_rate": 1.7340425531914894e-05,
|
498 |
+
"loss": 0.6781,
|
499 |
+
"step": 70
|
500 |
+
},
|
501 |
+
{
|
502 |
+
"epoch": 0.17929292929292928,
|
503 |
+
"grad_norm": 2.234375,
|
504 |
+
"learning_rate": 1.7287234042553193e-05,
|
505 |
+
"loss": 0.6895,
|
506 |
+
"step": 71
|
507 |
+
},
|
508 |
+
{
|
509 |
+
"epoch": 0.18181818181818182,
|
510 |
+
"grad_norm": 2.328125,
|
511 |
+
"learning_rate": 1.723404255319149e-05,
|
512 |
+
"loss": 0.6515,
|
513 |
+
"step": 72
|
514 |
+
},
|
515 |
+
{
|
516 |
+
"epoch": 0.18434343434343434,
|
517 |
+
"grad_norm": 2.046875,
|
518 |
+
"learning_rate": 1.718085106382979e-05,
|
519 |
+
"loss": 0.6032,
|
520 |
+
"step": 73
|
521 |
+
},
|
522 |
+
{
|
523 |
+
"epoch": 0.18686868686868688,
|
524 |
+
"grad_norm": 2.265625,
|
525 |
+
"learning_rate": 1.712765957446809e-05,
|
526 |
+
"loss": 0.6554,
|
527 |
+
"step": 74
|
528 |
+
},
|
529 |
+
{
|
530 |
+
"epoch": 0.1893939393939394,
|
531 |
+
"grad_norm": 2.140625,
|
532 |
+
"learning_rate": 1.7074468085106384e-05,
|
533 |
+
"loss": 0.6295,
|
534 |
+
"step": 75
|
535 |
+
},
|
536 |
+
{
|
537 |
+
"epoch": 0.1919191919191919,
|
538 |
+
"grad_norm": 2.34375,
|
539 |
+
"learning_rate": 1.7021276595744682e-05,
|
540 |
+
"loss": 0.6321,
|
541 |
+
"step": 76
|
542 |
+
},
|
543 |
+
{
|
544 |
+
"epoch": 0.19444444444444445,
|
545 |
+
"grad_norm": 2.09375,
|
546 |
+
"learning_rate": 1.696808510638298e-05,
|
547 |
+
"loss": 0.6457,
|
548 |
+
"step": 77
|
549 |
+
},
|
550 |
+
{
|
551 |
+
"epoch": 0.19696969696969696,
|
552 |
+
"grad_norm": 2.03125,
|
553 |
+
"learning_rate": 1.6914893617021276e-05,
|
554 |
+
"loss": 0.559,
|
555 |
+
"step": 78
|
556 |
+
},
|
557 |
+
{
|
558 |
+
"epoch": 0.1994949494949495,
|
559 |
+
"grad_norm": 2.21875,
|
560 |
+
"learning_rate": 1.6861702127659575e-05,
|
561 |
+
"loss": 0.766,
|
562 |
+
"step": 79
|
563 |
+
},
|
564 |
+
{
|
565 |
+
"epoch": 0.20202020202020202,
|
566 |
+
"grad_norm": 2.75,
|
567 |
+
"learning_rate": 1.6808510638297873e-05,
|
568 |
+
"loss": 0.8241,
|
569 |
+
"step": 80
|
570 |
+
},
|
571 |
+
{
|
572 |
+
"epoch": 0.20454545454545456,
|
573 |
+
"grad_norm": 2.3125,
|
574 |
+
"learning_rate": 1.6755319148936172e-05,
|
575 |
+
"loss": 0.6543,
|
576 |
+
"step": 81
|
577 |
+
},
|
578 |
+
{
|
579 |
+
"epoch": 0.20707070707070707,
|
580 |
+
"grad_norm": 2.34375,
|
581 |
+
"learning_rate": 1.670212765957447e-05,
|
582 |
+
"loss": 0.6471,
|
583 |
+
"step": 82
|
584 |
+
},
|
585 |
+
{
|
586 |
+
"epoch": 0.20959595959595959,
|
587 |
+
"grad_norm": 2.375,
|
588 |
+
"learning_rate": 1.664893617021277e-05,
|
589 |
+
"loss": 0.678,
|
590 |
+
"step": 83
|
591 |
+
},
|
592 |
+
{
|
593 |
+
"epoch": 0.21212121212121213,
|
594 |
+
"grad_norm": 2.140625,
|
595 |
+
"learning_rate": 1.6595744680851064e-05,
|
596 |
+
"loss": 0.6333,
|
597 |
+
"step": 84
|
598 |
+
},
|
599 |
+
{
|
600 |
+
"epoch": 0.21464646464646464,
|
601 |
+
"grad_norm": 2.109375,
|
602 |
+
"learning_rate": 1.6542553191489363e-05,
|
603 |
+
"loss": 0.6513,
|
604 |
+
"step": 85
|
605 |
+
},
|
606 |
+
{
|
607 |
+
"epoch": 0.21717171717171718,
|
608 |
+
"grad_norm": 2.109375,
|
609 |
+
"learning_rate": 1.648936170212766e-05,
|
610 |
+
"loss": 0.6419,
|
611 |
+
"step": 86
|
612 |
+
},
|
613 |
+
{
|
614 |
+
"epoch": 0.2196969696969697,
|
615 |
+
"grad_norm": 2.09375,
|
616 |
+
"learning_rate": 1.6436170212765957e-05,
|
617 |
+
"loss": 0.5929,
|
618 |
+
"step": 87
|
619 |
+
},
|
620 |
+
{
|
621 |
+
"epoch": 0.2222222222222222,
|
622 |
+
"grad_norm": 2.15625,
|
623 |
+
"learning_rate": 1.6382978723404255e-05,
|
624 |
+
"loss": 0.5898,
|
625 |
+
"step": 88
|
626 |
+
},
|
627 |
+
{
|
628 |
+
"epoch": 0.22474747474747475,
|
629 |
+
"grad_norm": 2.5625,
|
630 |
+
"learning_rate": 1.6329787234042554e-05,
|
631 |
+
"loss": 0.7497,
|
632 |
+
"step": 89
|
633 |
+
},
|
634 |
+
{
|
635 |
+
"epoch": 0.22727272727272727,
|
636 |
+
"grad_norm": 2.203125,
|
637 |
+
"learning_rate": 1.6276595744680853e-05,
|
638 |
+
"loss": 0.7005,
|
639 |
+
"step": 90
|
640 |
+
},
|
641 |
+
{
|
642 |
+
"epoch": 0.2297979797979798,
|
643 |
+
"grad_norm": 2.28125,
|
644 |
+
"learning_rate": 1.622340425531915e-05,
|
645 |
+
"loss": 0.7901,
|
646 |
+
"step": 91
|
647 |
+
},
|
648 |
+
{
|
649 |
+
"epoch": 0.23232323232323232,
|
650 |
+
"grad_norm": 1.9921875,
|
651 |
+
"learning_rate": 1.6170212765957446e-05,
|
652 |
+
"loss": 0.5286,
|
653 |
+
"step": 92
|
654 |
+
},
|
655 |
+
{
|
656 |
+
"epoch": 0.23484848484848486,
|
657 |
+
"grad_norm": 2.46875,
|
658 |
+
"learning_rate": 1.6117021276595745e-05,
|
659 |
+
"loss": 0.655,
|
660 |
+
"step": 93
|
661 |
+
},
|
662 |
+
{
|
663 |
+
"epoch": 0.23737373737373738,
|
664 |
+
"grad_norm": 2.21875,
|
665 |
+
"learning_rate": 1.6063829787234044e-05,
|
666 |
+
"loss": 0.7207,
|
667 |
+
"step": 94
|
668 |
+
},
|
669 |
+
{
|
670 |
+
"epoch": 0.2398989898989899,
|
671 |
+
"grad_norm": 2.359375,
|
672 |
+
"learning_rate": 1.6010638297872342e-05,
|
673 |
+
"loss": 0.7205,
|
674 |
+
"step": 95
|
675 |
+
},
|
676 |
+
{
|
677 |
+
"epoch": 0.24242424242424243,
|
678 |
+
"grad_norm": 2.890625,
|
679 |
+
"learning_rate": 1.595744680851064e-05,
|
680 |
+
"loss": 0.8159,
|
681 |
+
"step": 96
|
682 |
+
},
|
683 |
+
{
|
684 |
+
"epoch": 0.24494949494949494,
|
685 |
+
"grad_norm": 2.125,
|
686 |
+
"learning_rate": 1.590425531914894e-05,
|
687 |
+
"loss": 0.563,
|
688 |
+
"step": 97
|
689 |
+
},
|
690 |
+
{
|
691 |
+
"epoch": 0.2474747474747475,
|
692 |
+
"grad_norm": 2.03125,
|
693 |
+
"learning_rate": 1.5851063829787235e-05,
|
694 |
+
"loss": 0.5928,
|
695 |
+
"step": 98
|
696 |
+
},
|
697 |
+
{
|
698 |
+
"epoch": 0.2474747474747475,
|
699 |
+
"eval_loss": 0.5301359295845032,
|
700 |
+
"eval_model_preparation_time": 0.0001,
|
701 |
+
"eval_runtime": 2.0495,
|
702 |
+
"eval_samples_per_second": 51.721,
|
703 |
+
"eval_steps_per_second": 6.831,
|
704 |
+
"step": 98
|
705 |
+
},
|
706 |
+
{
|
707 |
+
"epoch": 0.25,
|
708 |
+
"grad_norm": 2.296875,
|
709 |
+
"learning_rate": 1.5797872340425533e-05,
|
710 |
+
"loss": 0.6478,
|
711 |
+
"step": 99
|
712 |
+
},
|
713 |
+
{
|
714 |
+
"epoch": 0.25252525252525254,
|
715 |
+
"grad_norm": 2.078125,
|
716 |
+
"learning_rate": 1.5744680851063832e-05,
|
717 |
+
"loss": 0.6663,
|
718 |
+
"step": 100
|
719 |
+
},
|
720 |
+
{
|
721 |
+
"epoch": 0.255050505050505,
|
722 |
+
"grad_norm": 2.140625,
|
723 |
+
"learning_rate": 1.5691489361702127e-05,
|
724 |
+
"loss": 0.6241,
|
725 |
+
"step": 101
|
726 |
+
},
|
727 |
+
{
|
728 |
+
"epoch": 0.25757575757575757,
|
729 |
+
"grad_norm": 2.4375,
|
730 |
+
"learning_rate": 1.5638297872340426e-05,
|
731 |
+
"loss": 0.7131,
|
732 |
+
"step": 102
|
733 |
+
},
|
734 |
+
{
|
735 |
+
"epoch": 0.2601010101010101,
|
736 |
+
"grad_norm": 2.15625,
|
737 |
+
"learning_rate": 1.5585106382978724e-05,
|
738 |
+
"loss": 0.7139,
|
739 |
+
"step": 103
|
740 |
+
},
|
741 |
+
{
|
742 |
+
"epoch": 0.26262626262626265,
|
743 |
+
"grad_norm": 2.078125,
|
744 |
+
"learning_rate": 1.5531914893617023e-05,
|
745 |
+
"loss": 0.5503,
|
746 |
+
"step": 104
|
747 |
+
},
|
748 |
+
{
|
749 |
+
"epoch": 0.26515151515151514,
|
750 |
+
"grad_norm": 2.0625,
|
751 |
+
"learning_rate": 1.547872340425532e-05,
|
752 |
+
"loss": 0.5837,
|
753 |
+
"step": 105
|
754 |
+
},
|
755 |
+
{
|
756 |
+
"epoch": 0.2676767676767677,
|
757 |
+
"grad_norm": 1.9453125,
|
758 |
+
"learning_rate": 1.542553191489362e-05,
|
759 |
+
"loss": 0.571,
|
760 |
+
"step": 106
|
761 |
+
},
|
762 |
+
{
|
763 |
+
"epoch": 0.2702020202020202,
|
764 |
+
"grad_norm": 1.9375,
|
765 |
+
"learning_rate": 1.5372340425531915e-05,
|
766 |
+
"loss": 0.4949,
|
767 |
+
"step": 107
|
768 |
+
},
|
769 |
+
{
|
770 |
+
"epoch": 0.2727272727272727,
|
771 |
+
"grad_norm": 2.171875,
|
772 |
+
"learning_rate": 1.5319148936170214e-05,
|
773 |
+
"loss": 0.6769,
|
774 |
+
"step": 108
|
775 |
+
},
|
776 |
+
{
|
777 |
+
"epoch": 0.27525252525252525,
|
778 |
+
"grad_norm": 1.8828125,
|
779 |
+
"learning_rate": 1.5265957446808512e-05,
|
780 |
+
"loss": 0.4772,
|
781 |
+
"step": 109
|
782 |
+
},
|
783 |
+
{
|
784 |
+
"epoch": 0.2777777777777778,
|
785 |
+
"grad_norm": 2.0625,
|
786 |
+
"learning_rate": 1.521276595744681e-05,
|
787 |
+
"loss": 0.6177,
|
788 |
+
"step": 110
|
789 |
+
},
|
790 |
+
{
|
791 |
+
"epoch": 0.2803030303030303,
|
792 |
+
"grad_norm": 2.046875,
|
793 |
+
"learning_rate": 1.5159574468085108e-05,
|
794 |
+
"loss": 0.6063,
|
795 |
+
"step": 111
|
796 |
+
},
|
797 |
+
{
|
798 |
+
"epoch": 0.2828282828282828,
|
799 |
+
"grad_norm": 2.21875,
|
800 |
+
"learning_rate": 1.5106382978723407e-05,
|
801 |
+
"loss": 0.5975,
|
802 |
+
"step": 112
|
803 |
+
},
|
804 |
+
{
|
805 |
+
"epoch": 0.28535353535353536,
|
806 |
+
"grad_norm": 2.03125,
|
807 |
+
"learning_rate": 1.5053191489361702e-05,
|
808 |
+
"loss": 0.5549,
|
809 |
+
"step": 113
|
810 |
+
},
|
811 |
+
{
|
812 |
+
"epoch": 0.2878787878787879,
|
813 |
+
"grad_norm": 2.203125,
|
814 |
+
"learning_rate": 1.5000000000000002e-05,
|
815 |
+
"loss": 0.6549,
|
816 |
+
"step": 114
|
817 |
+
},
|
818 |
+
{
|
819 |
+
"epoch": 0.2904040404040404,
|
820 |
+
"grad_norm": 1.9375,
|
821 |
+
"learning_rate": 1.49468085106383e-05,
|
822 |
+
"loss": 0.5356,
|
823 |
+
"step": 115
|
824 |
+
},
|
825 |
+
{
|
826 |
+
"epoch": 0.29292929292929293,
|
827 |
+
"grad_norm": 2.140625,
|
828 |
+
"learning_rate": 1.4893617021276596e-05,
|
829 |
+
"loss": 0.6594,
|
830 |
+
"step": 116
|
831 |
+
},
|
832 |
+
{
|
833 |
+
"epoch": 0.29545454545454547,
|
834 |
+
"grad_norm": 2.25,
|
835 |
+
"learning_rate": 1.4840425531914894e-05,
|
836 |
+
"loss": 0.6194,
|
837 |
+
"step": 117
|
838 |
+
},
|
839 |
+
{
|
840 |
+
"epoch": 0.29797979797979796,
|
841 |
+
"grad_norm": 2.078125,
|
842 |
+
"learning_rate": 1.4787234042553193e-05,
|
843 |
+
"loss": 0.5987,
|
844 |
+
"step": 118
|
845 |
+
},
|
846 |
+
{
|
847 |
+
"epoch": 0.3005050505050505,
|
848 |
+
"grad_norm": 2.0,
|
849 |
+
"learning_rate": 1.473404255319149e-05,
|
850 |
+
"loss": 0.5104,
|
851 |
+
"step": 119
|
852 |
+
},
|
853 |
+
{
|
854 |
+
"epoch": 0.30303030303030304,
|
855 |
+
"grad_norm": 2.015625,
|
856 |
+
"learning_rate": 1.4680851063829789e-05,
|
857 |
+
"loss": 0.5476,
|
858 |
+
"step": 120
|
859 |
+
},
|
860 |
+
{
|
861 |
+
"epoch": 0.3055555555555556,
|
862 |
+
"grad_norm": 2.296875,
|
863 |
+
"learning_rate": 1.4627659574468087e-05,
|
864 |
+
"loss": 0.6195,
|
865 |
+
"step": 121
|
866 |
+
},
|
867 |
+
{
|
868 |
+
"epoch": 0.30808080808080807,
|
869 |
+
"grad_norm": 2.28125,
|
870 |
+
"learning_rate": 1.4574468085106384e-05,
|
871 |
+
"loss": 0.6162,
|
872 |
+
"step": 122
|
873 |
+
},
|
874 |
+
{
|
875 |
+
"epoch": 0.3106060606060606,
|
876 |
+
"grad_norm": 1.8359375,
|
877 |
+
"learning_rate": 1.4521276595744683e-05,
|
878 |
+
"loss": 0.5231,
|
879 |
+
"step": 123
|
880 |
+
},
|
881 |
+
{
|
882 |
+
"epoch": 0.31313131313131315,
|
883 |
+
"grad_norm": 2.03125,
|
884 |
+
"learning_rate": 1.4468085106382981e-05,
|
885 |
+
"loss": 0.5958,
|
886 |
+
"step": 124
|
887 |
+
},
|
888 |
+
{
|
889 |
+
"epoch": 0.31565656565656564,
|
890 |
+
"grad_norm": 2.109375,
|
891 |
+
"learning_rate": 1.4414893617021276e-05,
|
892 |
+
"loss": 0.5808,
|
893 |
+
"step": 125
|
894 |
+
},
|
895 |
+
{
|
896 |
+
"epoch": 0.3181818181818182,
|
897 |
+
"grad_norm": 2.3125,
|
898 |
+
"learning_rate": 1.4361702127659575e-05,
|
899 |
+
"loss": 0.6299,
|
900 |
+
"step": 126
|
901 |
+
},
|
902 |
+
{
|
903 |
+
"epoch": 0.3207070707070707,
|
904 |
+
"grad_norm": 2.3125,
|
905 |
+
"learning_rate": 1.4308510638297874e-05,
|
906 |
+
"loss": 0.6375,
|
907 |
+
"step": 127
|
908 |
+
},
|
909 |
+
{
|
910 |
+
"epoch": 0.32323232323232326,
|
911 |
+
"grad_norm": 2.140625,
|
912 |
+
"learning_rate": 1.425531914893617e-05,
|
913 |
+
"loss": 0.6465,
|
914 |
+
"step": 128
|
915 |
+
},
|
916 |
+
{
|
917 |
+
"epoch": 0.32575757575757575,
|
918 |
+
"grad_norm": 2.125,
|
919 |
+
"learning_rate": 1.420212765957447e-05,
|
920 |
+
"loss": 0.6539,
|
921 |
+
"step": 129
|
922 |
+
},
|
923 |
+
{
|
924 |
+
"epoch": 0.3282828282828283,
|
925 |
+
"grad_norm": 1.8671875,
|
926 |
+
"learning_rate": 1.4148936170212768e-05,
|
927 |
+
"loss": 0.5253,
|
928 |
+
"step": 130
|
929 |
+
},
|
930 |
+
{
|
931 |
+
"epoch": 0.33080808080808083,
|
932 |
+
"grad_norm": 2.203125,
|
933 |
+
"learning_rate": 1.4095744680851065e-05,
|
934 |
+
"loss": 0.6292,
|
935 |
+
"step": 131
|
936 |
+
},
|
937 |
+
{
|
938 |
+
"epoch": 0.3333333333333333,
|
939 |
+
"grad_norm": 2.109375,
|
940 |
+
"learning_rate": 1.4042553191489363e-05,
|
941 |
+
"loss": 0.578,
|
942 |
+
"step": 132
|
943 |
+
},
|
944 |
+
{
|
945 |
+
"epoch": 0.33585858585858586,
|
946 |
+
"grad_norm": 2.09375,
|
947 |
+
"learning_rate": 1.3989361702127662e-05,
|
948 |
+
"loss": 0.5226,
|
949 |
+
"step": 133
|
950 |
+
},
|
951 |
+
{
|
952 |
+
"epoch": 0.3383838383838384,
|
953 |
+
"grad_norm": 2.171875,
|
954 |
+
"learning_rate": 1.3936170212765959e-05,
|
955 |
+
"loss": 0.6743,
|
956 |
+
"step": 134
|
957 |
+
},
|
958 |
+
{
|
959 |
+
"epoch": 0.3409090909090909,
|
960 |
+
"grad_norm": 2.046875,
|
961 |
+
"learning_rate": 1.3882978723404257e-05,
|
962 |
+
"loss": 0.501,
|
963 |
+
"step": 135
|
964 |
+
},
|
965 |
+
{
|
966 |
+
"epoch": 0.3434343434343434,
|
967 |
+
"grad_norm": 2.15625,
|
968 |
+
"learning_rate": 1.3829787234042556e-05,
|
969 |
+
"loss": 0.6333,
|
970 |
+
"step": 136
|
971 |
+
},
|
972 |
+
{
|
973 |
+
"epoch": 0.34595959595959597,
|
974 |
+
"grad_norm": 1.7890625,
|
975 |
+
"learning_rate": 1.3776595744680851e-05,
|
976 |
+
"loss": 0.4695,
|
977 |
+
"step": 137
|
978 |
+
},
|
979 |
+
{
|
980 |
+
"epoch": 0.3484848484848485,
|
981 |
+
"grad_norm": 2.28125,
|
982 |
+
"learning_rate": 1.372340425531915e-05,
|
983 |
+
"loss": 0.6444,
|
984 |
+
"step": 138
|
985 |
+
},
|
986 |
+
{
|
987 |
+
"epoch": 0.351010101010101,
|
988 |
+
"grad_norm": 2.21875,
|
989 |
+
"learning_rate": 1.3670212765957447e-05,
|
990 |
+
"loss": 0.6019,
|
991 |
+
"step": 139
|
992 |
+
},
|
993 |
+
{
|
994 |
+
"epoch": 0.35353535353535354,
|
995 |
+
"grad_norm": 1.90625,
|
996 |
+
"learning_rate": 1.3617021276595745e-05,
|
997 |
+
"loss": 0.4815,
|
998 |
+
"step": 140
|
999 |
+
},
|
1000 |
+
{
|
1001 |
+
"epoch": 0.3560606060606061,
|
1002 |
+
"grad_norm": 2.34375,
|
1003 |
+
"learning_rate": 1.3563829787234044e-05,
|
1004 |
+
"loss": 0.6316,
|
1005 |
+
"step": 141
|
1006 |
+
},
|
1007 |
+
{
|
1008 |
+
"epoch": 0.35858585858585856,
|
1009 |
+
"grad_norm": 2.34375,
|
1010 |
+
"learning_rate": 1.351063829787234e-05,
|
1011 |
+
"loss": 0.8299,
|
1012 |
+
"step": 142
|
1013 |
+
},
|
1014 |
+
{
|
1015 |
+
"epoch": 0.3611111111111111,
|
1016 |
+
"grad_norm": 1.8984375,
|
1017 |
+
"learning_rate": 1.345744680851064e-05,
|
1018 |
+
"loss": 0.543,
|
1019 |
+
"step": 143
|
1020 |
+
},
|
1021 |
+
{
|
1022 |
+
"epoch": 0.36363636363636365,
|
1023 |
+
"grad_norm": 2.234375,
|
1024 |
+
"learning_rate": 1.3404255319148938e-05,
|
1025 |
+
"loss": 0.6093,
|
1026 |
+
"step": 144
|
1027 |
+
},
|
1028 |
+
{
|
1029 |
+
"epoch": 0.3661616161616162,
|
1030 |
+
"grad_norm": 2.03125,
|
1031 |
+
"learning_rate": 1.3351063829787235e-05,
|
1032 |
+
"loss": 0.5501,
|
1033 |
+
"step": 145
|
1034 |
+
},
|
1035 |
+
{
|
1036 |
+
"epoch": 0.3686868686868687,
|
1037 |
+
"grad_norm": 2.09375,
|
1038 |
+
"learning_rate": 1.3297872340425533e-05,
|
1039 |
+
"loss": 0.5388,
|
1040 |
+
"step": 146
|
1041 |
+
},
|
1042 |
+
{
|
1043 |
+
"epoch": 0.3712121212121212,
|
1044 |
+
"grad_norm": 1.9453125,
|
1045 |
+
"learning_rate": 1.3244680851063832e-05,
|
1046 |
+
"loss": 0.5364,
|
1047 |
+
"step": 147
|
1048 |
+
},
|
1049 |
+
{
|
1050 |
+
"epoch": 0.37373737373737376,
|
1051 |
+
"grad_norm": 2.328125,
|
1052 |
+
"learning_rate": 1.3191489361702127e-05,
|
1053 |
+
"loss": 0.6471,
|
1054 |
+
"step": 148
|
1055 |
+
},
|
1056 |
+
{
|
1057 |
+
"epoch": 0.37626262626262624,
|
1058 |
+
"grad_norm": 1.9140625,
|
1059 |
+
"learning_rate": 1.3138297872340426e-05,
|
1060 |
+
"loss": 0.4996,
|
1061 |
+
"step": 149
|
1062 |
+
},
|
1063 |
+
{
|
1064 |
+
"epoch": 0.3787878787878788,
|
1065 |
+
"grad_norm": 2.15625,
|
1066 |
+
"learning_rate": 1.3085106382978724e-05,
|
1067 |
+
"loss": 0.6603,
|
1068 |
+
"step": 150
|
1069 |
+
},
|
1070 |
+
{
|
1071 |
+
"epoch": 0.3813131313131313,
|
1072 |
+
"grad_norm": 2.140625,
|
1073 |
+
"learning_rate": 1.3031914893617021e-05,
|
1074 |
+
"loss": 0.5177,
|
1075 |
+
"step": 151
|
1076 |
+
},
|
1077 |
+
{
|
1078 |
+
"epoch": 0.3838383838383838,
|
1079 |
+
"grad_norm": 2.3125,
|
1080 |
+
"learning_rate": 1.297872340425532e-05,
|
1081 |
+
"loss": 0.6503,
|
1082 |
+
"step": 152
|
1083 |
+
},
|
1084 |
+
{
|
1085 |
+
"epoch": 0.38636363636363635,
|
1086 |
+
"grad_norm": 2.046875,
|
1087 |
+
"learning_rate": 1.2925531914893619e-05,
|
1088 |
+
"loss": 0.676,
|
1089 |
+
"step": 153
|
1090 |
+
},
|
1091 |
+
{
|
1092 |
+
"epoch": 0.3888888888888889,
|
1093 |
+
"grad_norm": 2.15625,
|
1094 |
+
"learning_rate": 1.2872340425531915e-05,
|
1095 |
+
"loss": 0.6498,
|
1096 |
+
"step": 154
|
1097 |
+
},
|
1098 |
+
{
|
1099 |
+
"epoch": 0.39141414141414144,
|
1100 |
+
"grad_norm": 1.984375,
|
1101 |
+
"learning_rate": 1.2819148936170214e-05,
|
1102 |
+
"loss": 0.572,
|
1103 |
+
"step": 155
|
1104 |
+
},
|
1105 |
+
{
|
1106 |
+
"epoch": 0.3939393939393939,
|
1107 |
+
"grad_norm": 1.828125,
|
1108 |
+
"learning_rate": 1.2765957446808513e-05,
|
1109 |
+
"loss": 0.5173,
|
1110 |
+
"step": 156
|
1111 |
+
},
|
1112 |
+
{
|
1113 |
+
"epoch": 0.39646464646464646,
|
1114 |
+
"grad_norm": 2.25,
|
1115 |
+
"learning_rate": 1.2712765957446808e-05,
|
1116 |
+
"loss": 0.6703,
|
1117 |
+
"step": 157
|
1118 |
+
},
|
1119 |
+
{
|
1120 |
+
"epoch": 0.398989898989899,
|
1121 |
+
"grad_norm": 2.171875,
|
1122 |
+
"learning_rate": 1.2659574468085108e-05,
|
1123 |
+
"loss": 0.8048,
|
1124 |
+
"step": 158
|
1125 |
+
},
|
1126 |
+
{
|
1127 |
+
"epoch": 0.4015151515151515,
|
1128 |
+
"grad_norm": 2.234375,
|
1129 |
+
"learning_rate": 1.2606382978723407e-05,
|
1130 |
+
"loss": 0.7114,
|
1131 |
+
"step": 159
|
1132 |
+
},
|
1133 |
+
{
|
1134 |
+
"epoch": 0.40404040404040403,
|
1135 |
+
"grad_norm": 2.03125,
|
1136 |
+
"learning_rate": 1.2553191489361702e-05,
|
1137 |
+
"loss": 0.5931,
|
1138 |
+
"step": 160
|
1139 |
+
},
|
1140 |
+
{
|
1141 |
+
"epoch": 0.4065656565656566,
|
1142 |
+
"grad_norm": 2.203125,
|
1143 |
+
"learning_rate": 1.25e-05,
|
1144 |
+
"loss": 0.567,
|
1145 |
+
"step": 161
|
1146 |
+
},
|
1147 |
+
{
|
1148 |
+
"epoch": 0.4090909090909091,
|
1149 |
+
"grad_norm": 2.359375,
|
1150 |
+
"learning_rate": 1.24468085106383e-05,
|
1151 |
+
"loss": 0.7013,
|
1152 |
+
"step": 162
|
1153 |
+
},
|
1154 |
+
{
|
1155 |
+
"epoch": 0.4116161616161616,
|
1156 |
+
"grad_norm": 2.0625,
|
1157 |
+
"learning_rate": 1.2393617021276596e-05,
|
1158 |
+
"loss": 0.6181,
|
1159 |
+
"step": 163
|
1160 |
+
},
|
1161 |
+
{
|
1162 |
+
"epoch": 0.41414141414141414,
|
1163 |
+
"grad_norm": 2.078125,
|
1164 |
+
"learning_rate": 1.2340425531914895e-05,
|
1165 |
+
"loss": 0.7713,
|
1166 |
+
"step": 164
|
1167 |
+
},
|
1168 |
+
{
|
1169 |
+
"epoch": 0.4166666666666667,
|
1170 |
+
"grad_norm": 2.15625,
|
1171 |
+
"learning_rate": 1.2287234042553193e-05,
|
1172 |
+
"loss": 0.6588,
|
1173 |
+
"step": 165
|
1174 |
+
},
|
1175 |
+
{
|
1176 |
+
"epoch": 0.41919191919191917,
|
1177 |
+
"grad_norm": 1.9609375,
|
1178 |
+
"learning_rate": 1.223404255319149e-05,
|
1179 |
+
"loss": 0.573,
|
1180 |
+
"step": 166
|
1181 |
+
},
|
1182 |
+
{
|
1183 |
+
"epoch": 0.4217171717171717,
|
1184 |
+
"grad_norm": 1.984375,
|
1185 |
+
"learning_rate": 1.2180851063829789e-05,
|
1186 |
+
"loss": 0.5446,
|
1187 |
+
"step": 167
|
1188 |
+
},
|
1189 |
+
{
|
1190 |
+
"epoch": 0.42424242424242425,
|
1191 |
+
"grad_norm": 2.03125,
|
1192 |
+
"learning_rate": 1.2127659574468087e-05,
|
1193 |
+
"loss": 0.5479,
|
1194 |
+
"step": 168
|
1195 |
+
},
|
1196 |
+
{
|
1197 |
+
"epoch": 0.42676767676767674,
|
1198 |
+
"grad_norm": 2.34375,
|
1199 |
+
"learning_rate": 1.2074468085106383e-05,
|
1200 |
+
"loss": 0.6544,
|
1201 |
+
"step": 169
|
1202 |
+
},
|
1203 |
+
{
|
1204 |
+
"epoch": 0.4292929292929293,
|
1205 |
+
"grad_norm": 2.140625,
|
1206 |
+
"learning_rate": 1.2021276595744681e-05,
|
1207 |
+
"loss": 0.525,
|
1208 |
+
"step": 170
|
1209 |
+
},
|
1210 |
+
{
|
1211 |
+
"epoch": 0.4318181818181818,
|
1212 |
+
"grad_norm": 2.328125,
|
1213 |
+
"learning_rate": 1.196808510638298e-05,
|
1214 |
+
"loss": 0.6069,
|
1215 |
+
"step": 171
|
1216 |
+
},
|
1217 |
+
{
|
1218 |
+
"epoch": 0.43434343434343436,
|
1219 |
+
"grad_norm": 2.1875,
|
1220 |
+
"learning_rate": 1.1914893617021277e-05,
|
1221 |
+
"loss": 0.6263,
|
1222 |
+
"step": 172
|
1223 |
+
},
|
1224 |
+
{
|
1225 |
+
"epoch": 0.43686868686868685,
|
1226 |
+
"grad_norm": 2.171875,
|
1227 |
+
"learning_rate": 1.1861702127659575e-05,
|
1228 |
+
"loss": 0.575,
|
1229 |
+
"step": 173
|
1230 |
+
},
|
1231 |
+
{
|
1232 |
+
"epoch": 0.4393939393939394,
|
1233 |
+
"grad_norm": 2.15625,
|
1234 |
+
"learning_rate": 1.1808510638297874e-05,
|
1235 |
+
"loss": 0.5764,
|
1236 |
+
"step": 174
|
1237 |
+
},
|
1238 |
+
{
|
1239 |
+
"epoch": 0.44191919191919193,
|
1240 |
+
"grad_norm": 2.6875,
|
1241 |
+
"learning_rate": 1.175531914893617e-05,
|
1242 |
+
"loss": 0.7523,
|
1243 |
+
"step": 175
|
1244 |
+
},
|
1245 |
+
{
|
1246 |
+
"epoch": 0.4444444444444444,
|
1247 |
+
"grad_norm": 2.109375,
|
1248 |
+
"learning_rate": 1.170212765957447e-05,
|
1249 |
+
"loss": 0.5827,
|
1250 |
+
"step": 176
|
1251 |
+
},
|
1252 |
+
{
|
1253 |
+
"epoch": 0.44696969696969696,
|
1254 |
+
"grad_norm": 2.21875,
|
1255 |
+
"learning_rate": 1.1648936170212768e-05,
|
1256 |
+
"loss": 0.5396,
|
1257 |
+
"step": 177
|
1258 |
+
},
|
1259 |
+
{
|
1260 |
+
"epoch": 0.4494949494949495,
|
1261 |
+
"grad_norm": 2.0625,
|
1262 |
+
"learning_rate": 1.1595744680851065e-05,
|
1263 |
+
"loss": 0.6469,
|
1264 |
+
"step": 178
|
1265 |
+
},
|
1266 |
+
{
|
1267 |
+
"epoch": 0.45202020202020204,
|
1268 |
+
"grad_norm": 2.015625,
|
1269 |
+
"learning_rate": 1.1542553191489364e-05,
|
1270 |
+
"loss": 0.544,
|
1271 |
+
"step": 179
|
1272 |
+
},
|
1273 |
+
{
|
1274 |
+
"epoch": 0.45454545454545453,
|
1275 |
+
"grad_norm": 1.921875,
|
1276 |
+
"learning_rate": 1.1489361702127662e-05,
|
1277 |
+
"loss": 0.5716,
|
1278 |
+
"step": 180
|
1279 |
+
},
|
1280 |
+
{
|
1281 |
+
"epoch": 0.45707070707070707,
|
1282 |
+
"grad_norm": 2.015625,
|
1283 |
+
"learning_rate": 1.1436170212765957e-05,
|
1284 |
+
"loss": 0.5299,
|
1285 |
+
"step": 181
|
1286 |
+
},
|
1287 |
+
{
|
1288 |
+
"epoch": 0.4595959595959596,
|
1289 |
+
"grad_norm": 1.96875,
|
1290 |
+
"learning_rate": 1.1382978723404256e-05,
|
1291 |
+
"loss": 0.4805,
|
1292 |
+
"step": 182
|
1293 |
+
},
|
1294 |
+
{
|
1295 |
+
"epoch": 0.4621212121212121,
|
1296 |
+
"grad_norm": 2.28125,
|
1297 |
+
"learning_rate": 1.1329787234042555e-05,
|
1298 |
+
"loss": 0.6307,
|
1299 |
+
"step": 183
|
1300 |
+
},
|
1301 |
+
{
|
1302 |
+
"epoch": 0.46464646464646464,
|
1303 |
+
"grad_norm": 2.5,
|
1304 |
+
"learning_rate": 1.1276595744680851e-05,
|
1305 |
+
"loss": 0.8322,
|
1306 |
+
"step": 184
|
1307 |
+
},
|
1308 |
+
{
|
1309 |
+
"epoch": 0.4671717171717172,
|
1310 |
+
"grad_norm": 2.1875,
|
1311 |
+
"learning_rate": 1.122340425531915e-05,
|
1312 |
+
"loss": 0.617,
|
1313 |
+
"step": 185
|
1314 |
+
},
|
1315 |
+
{
|
1316 |
+
"epoch": 0.4696969696969697,
|
1317 |
+
"grad_norm": 2.140625,
|
1318 |
+
"learning_rate": 1.1170212765957447e-05,
|
1319 |
+
"loss": 0.5663,
|
1320 |
+
"step": 186
|
1321 |
+
},
|
1322 |
+
{
|
1323 |
+
"epoch": 0.4722222222222222,
|
1324 |
+
"grad_norm": 2.28125,
|
1325 |
+
"learning_rate": 1.1117021276595746e-05,
|
1326 |
+
"loss": 0.7309,
|
1327 |
+
"step": 187
|
1328 |
+
},
|
1329 |
+
{
|
1330 |
+
"epoch": 0.47474747474747475,
|
1331 |
+
"grad_norm": 2.03125,
|
1332 |
+
"learning_rate": 1.1063829787234044e-05,
|
1333 |
+
"loss": 0.573,
|
1334 |
+
"step": 188
|
1335 |
+
},
|
1336 |
+
{
|
1337 |
+
"epoch": 0.4772727272727273,
|
1338 |
+
"grad_norm": 2.171875,
|
1339 |
+
"learning_rate": 1.1010638297872341e-05,
|
1340 |
+
"loss": 0.5971,
|
1341 |
+
"step": 189
|
1342 |
+
},
|
1343 |
+
{
|
1344 |
+
"epoch": 0.4797979797979798,
|
1345 |
+
"grad_norm": 2.0625,
|
1346 |
+
"learning_rate": 1.095744680851064e-05,
|
1347 |
+
"loss": 0.6153,
|
1348 |
+
"step": 190
|
1349 |
+
},
|
1350 |
+
{
|
1351 |
+
"epoch": 0.4823232323232323,
|
1352 |
+
"grad_norm": 2.109375,
|
1353 |
+
"learning_rate": 1.0904255319148938e-05,
|
1354 |
+
"loss": 0.5656,
|
1355 |
+
"step": 191
|
1356 |
+
},
|
1357 |
+
{
|
1358 |
+
"epoch": 0.48484848484848486,
|
1359 |
+
"grad_norm": 2.296875,
|
1360 |
+
"learning_rate": 1.0851063829787233e-05,
|
1361 |
+
"loss": 0.6486,
|
1362 |
+
"step": 192
|
1363 |
+
},
|
1364 |
+
{
|
1365 |
+
"epoch": 0.48737373737373735,
|
1366 |
+
"grad_norm": 2.265625,
|
1367 |
+
"learning_rate": 1.0797872340425532e-05,
|
1368 |
+
"loss": 0.5707,
|
1369 |
+
"step": 193
|
1370 |
+
},
|
1371 |
+
{
|
1372 |
+
"epoch": 0.4898989898989899,
|
1373 |
+
"grad_norm": 1.9609375,
|
1374 |
+
"learning_rate": 1.074468085106383e-05,
|
1375 |
+
"loss": 0.5209,
|
1376 |
+
"step": 194
|
1377 |
+
},
|
1378 |
+
{
|
1379 |
+
"epoch": 0.49242424242424243,
|
1380 |
+
"grad_norm": 2.3125,
|
1381 |
+
"learning_rate": 1.0691489361702128e-05,
|
1382 |
+
"loss": 0.6777,
|
1383 |
+
"step": 195
|
1384 |
+
},
|
1385 |
+
{
|
1386 |
+
"epoch": 0.494949494949495,
|
1387 |
+
"grad_norm": 2.171875,
|
1388 |
+
"learning_rate": 1.0638297872340426e-05,
|
1389 |
+
"loss": 0.678,
|
1390 |
+
"step": 196
|
1391 |
+
},
|
1392 |
+
{
|
1393 |
+
"epoch": 0.494949494949495,
|
1394 |
+
"eval_loss": 0.5024059414863586,
|
1395 |
+
"eval_model_preparation_time": 0.0001,
|
1396 |
+
"eval_runtime": 2.0314,
|
1397 |
+
"eval_samples_per_second": 52.181,
|
1398 |
+
"eval_steps_per_second": 6.892,
|
1399 |
+
"step": 196
|
1400 |
+
},
|
1401 |
+
{
|
1402 |
+
"epoch": 0.49747474747474746,
|
1403 |
+
"grad_norm": 1.9765625,
|
1404 |
+
"learning_rate": 1.0585106382978725e-05,
|
1405 |
+
"loss": 0.533,
|
1406 |
+
"step": 197
|
1407 |
+
},
|
1408 |
+
{
|
1409 |
+
"epoch": 0.5,
|
1410 |
+
"grad_norm": 2.25,
|
1411 |
+
"learning_rate": 1.0531914893617022e-05,
|
1412 |
+
"loss": 0.6215,
|
1413 |
+
"step": 198
|
1414 |
+
},
|
1415 |
+
{
|
1416 |
+
"epoch": 0.5025252525252525,
|
1417 |
+
"grad_norm": 2.046875,
|
1418 |
+
"learning_rate": 1.047872340425532e-05,
|
1419 |
+
"loss": 0.5616,
|
1420 |
+
"step": 199
|
1421 |
+
},
|
1422 |
+
{
|
1423 |
+
"epoch": 0.5050505050505051,
|
1424 |
+
"grad_norm": 2.34375,
|
1425 |
+
"learning_rate": 1.0425531914893619e-05,
|
1426 |
+
"loss": 0.6466,
|
1427 |
+
"step": 200
|
1428 |
+
},
|
1429 |
+
{
|
1430 |
+
"epoch": 0.5075757575757576,
|
1431 |
+
"grad_norm": 2.1875,
|
1432 |
+
"learning_rate": 1.0372340425531916e-05,
|
1433 |
+
"loss": 0.6424,
|
1434 |
+
"step": 201
|
1435 |
+
},
|
1436 |
+
{
|
1437 |
+
"epoch": 0.51010101010101,
|
1438 |
+
"grad_norm": 2.0625,
|
1439 |
+
"learning_rate": 1.0319148936170214e-05,
|
1440 |
+
"loss": 0.5646,
|
1441 |
+
"step": 202
|
1442 |
+
},
|
1443 |
+
{
|
1444 |
+
"epoch": 0.5126262626262627,
|
1445 |
+
"grad_norm": 2.125,
|
1446 |
+
"learning_rate": 1.0265957446808513e-05,
|
1447 |
+
"loss": 0.6261,
|
1448 |
+
"step": 203
|
1449 |
+
},
|
1450 |
+
{
|
1451 |
+
"epoch": 0.5151515151515151,
|
1452 |
+
"grad_norm": 2.296875,
|
1453 |
+
"learning_rate": 1.0212765957446808e-05,
|
1454 |
+
"loss": 0.6775,
|
1455 |
+
"step": 204
|
1456 |
+
},
|
1457 |
+
{
|
1458 |
+
"epoch": 0.5176767676767676,
|
1459 |
+
"grad_norm": 2.078125,
|
1460 |
+
"learning_rate": 1.0159574468085107e-05,
|
1461 |
+
"loss": 0.5857,
|
1462 |
+
"step": 205
|
1463 |
+
},
|
1464 |
+
{
|
1465 |
+
"epoch": 0.5202020202020202,
|
1466 |
+
"grad_norm": 2.171875,
|
1467 |
+
"learning_rate": 1.0106382978723405e-05,
|
1468 |
+
"loss": 0.6021,
|
1469 |
+
"step": 206
|
1470 |
+
},
|
1471 |
+
{
|
1472 |
+
"epoch": 0.5227272727272727,
|
1473 |
+
"grad_norm": 2.40625,
|
1474 |
+
"learning_rate": 1.0053191489361702e-05,
|
1475 |
+
"loss": 0.7299,
|
1476 |
+
"step": 207
|
1477 |
+
},
|
1478 |
+
{
|
1479 |
+
"epoch": 0.5252525252525253,
|
1480 |
+
"grad_norm": 1.8828125,
|
1481 |
+
"learning_rate": 1e-05,
|
1482 |
+
"loss": 0.5437,
|
1483 |
+
"step": 208
|
1484 |
+
},
|
1485 |
+
{
|
1486 |
+
"epoch": 0.5277777777777778,
|
1487 |
+
"grad_norm": 2.140625,
|
1488 |
+
"learning_rate": 9.946808510638298e-06,
|
1489 |
+
"loss": 0.6348,
|
1490 |
+
"step": 209
|
1491 |
+
},
|
1492 |
+
{
|
1493 |
+
"epoch": 0.5303030303030303,
|
1494 |
+
"grad_norm": 2.0,
|
1495 |
+
"learning_rate": 9.893617021276596e-06,
|
1496 |
+
"loss": 0.5428,
|
1497 |
+
"step": 210
|
1498 |
+
},
|
1499 |
+
{
|
1500 |
+
"epoch": 0.5328282828282829,
|
1501 |
+
"grad_norm": 2.140625,
|
1502 |
+
"learning_rate": 9.840425531914895e-06,
|
1503 |
+
"loss": 0.6134,
|
1504 |
+
"step": 211
|
1505 |
+
},
|
1506 |
+
{
|
1507 |
+
"epoch": 0.5353535353535354,
|
1508 |
+
"grad_norm": 2.4375,
|
1509 |
+
"learning_rate": 9.787234042553192e-06,
|
1510 |
+
"loss": 0.7403,
|
1511 |
+
"step": 212
|
1512 |
+
},
|
1513 |
+
{
|
1514 |
+
"epoch": 0.5378787878787878,
|
1515 |
+
"grad_norm": 2.40625,
|
1516 |
+
"learning_rate": 9.73404255319149e-06,
|
1517 |
+
"loss": 0.6552,
|
1518 |
+
"step": 213
|
1519 |
+
},
|
1520 |
+
{
|
1521 |
+
"epoch": 0.5404040404040404,
|
1522 |
+
"grad_norm": 2.34375,
|
1523 |
+
"learning_rate": 9.680851063829787e-06,
|
1524 |
+
"loss": 0.6425,
|
1525 |
+
"step": 214
|
1526 |
+
},
|
1527 |
+
{
|
1528 |
+
"epoch": 0.5429292929292929,
|
1529 |
+
"grad_norm": 2.0,
|
1530 |
+
"learning_rate": 9.627659574468086e-06,
|
1531 |
+
"loss": 0.5375,
|
1532 |
+
"step": 215
|
1533 |
+
},
|
1534 |
+
{
|
1535 |
+
"epoch": 0.5454545454545454,
|
1536 |
+
"grad_norm": 2.140625,
|
1537 |
+
"learning_rate": 9.574468085106385e-06,
|
1538 |
+
"loss": 0.5925,
|
1539 |
+
"step": 216
|
1540 |
+
},
|
1541 |
+
{
|
1542 |
+
"epoch": 0.547979797979798,
|
1543 |
+
"grad_norm": 2.390625,
|
1544 |
+
"learning_rate": 9.521276595744681e-06,
|
1545 |
+
"loss": 0.7654,
|
1546 |
+
"step": 217
|
1547 |
+
},
|
1548 |
+
{
|
1549 |
+
"epoch": 0.5505050505050505,
|
1550 |
+
"grad_norm": 1.953125,
|
1551 |
+
"learning_rate": 9.46808510638298e-06,
|
1552 |
+
"loss": 0.4996,
|
1553 |
+
"step": 218
|
1554 |
+
},
|
1555 |
+
{
|
1556 |
+
"epoch": 0.553030303030303,
|
1557 |
+
"grad_norm": 2.453125,
|
1558 |
+
"learning_rate": 9.414893617021279e-06,
|
1559 |
+
"loss": 0.6864,
|
1560 |
+
"step": 219
|
1561 |
+
},
|
1562 |
+
{
|
1563 |
+
"epoch": 0.5555555555555556,
|
1564 |
+
"grad_norm": 2.0,
|
1565 |
+
"learning_rate": 9.361702127659576e-06,
|
1566 |
+
"loss": 0.488,
|
1567 |
+
"step": 220
|
1568 |
+
},
|
1569 |
+
{
|
1570 |
+
"epoch": 0.5580808080808081,
|
1571 |
+
"grad_norm": 2.078125,
|
1572 |
+
"learning_rate": 9.308510638297872e-06,
|
1573 |
+
"loss": 0.5785,
|
1574 |
+
"step": 221
|
1575 |
+
},
|
1576 |
+
{
|
1577 |
+
"epoch": 0.5606060606060606,
|
1578 |
+
"grad_norm": 2.1875,
|
1579 |
+
"learning_rate": 9.255319148936171e-06,
|
1580 |
+
"loss": 0.5625,
|
1581 |
+
"step": 222
|
1582 |
+
},
|
1583 |
+
{
|
1584 |
+
"epoch": 0.5631313131313131,
|
1585 |
+
"grad_norm": 2.390625,
|
1586 |
+
"learning_rate": 9.20212765957447e-06,
|
1587 |
+
"loss": 0.7519,
|
1588 |
+
"step": 223
|
1589 |
+
},
|
1590 |
+
{
|
1591 |
+
"epoch": 0.5656565656565656,
|
1592 |
+
"grad_norm": 2.265625,
|
1593 |
+
"learning_rate": 9.148936170212767e-06,
|
1594 |
+
"loss": 0.6129,
|
1595 |
+
"step": 224
|
1596 |
+
},
|
1597 |
+
{
|
1598 |
+
"epoch": 0.5681818181818182,
|
1599 |
+
"grad_norm": 2.25,
|
1600 |
+
"learning_rate": 9.095744680851063e-06,
|
1601 |
+
"loss": 0.6109,
|
1602 |
+
"step": 225
|
1603 |
+
},
|
1604 |
+
{
|
1605 |
+
"epoch": 0.5707070707070707,
|
1606 |
+
"grad_norm": 2.21875,
|
1607 |
+
"learning_rate": 9.042553191489362e-06,
|
1608 |
+
"loss": 0.6669,
|
1609 |
+
"step": 226
|
1610 |
+
},
|
1611 |
+
{
|
1612 |
+
"epoch": 0.5732323232323232,
|
1613 |
+
"grad_norm": 2.078125,
|
1614 |
+
"learning_rate": 8.98936170212766e-06,
|
1615 |
+
"loss": 0.5333,
|
1616 |
+
"step": 227
|
1617 |
+
},
|
1618 |
+
{
|
1619 |
+
"epoch": 0.5757575757575758,
|
1620 |
+
"grad_norm": 1.84375,
|
1621 |
+
"learning_rate": 8.936170212765958e-06,
|
1622 |
+
"loss": 0.4787,
|
1623 |
+
"step": 228
|
1624 |
+
},
|
1625 |
+
{
|
1626 |
+
"epoch": 0.5782828282828283,
|
1627 |
+
"grad_norm": 2.265625,
|
1628 |
+
"learning_rate": 8.882978723404256e-06,
|
1629 |
+
"loss": 0.6159,
|
1630 |
+
"step": 229
|
1631 |
+
},
|
1632 |
+
{
|
1633 |
+
"epoch": 0.5808080808080808,
|
1634 |
+
"grad_norm": 1.9296875,
|
1635 |
+
"learning_rate": 8.829787234042555e-06,
|
1636 |
+
"loss": 0.5439,
|
1637 |
+
"step": 230
|
1638 |
+
},
|
1639 |
+
{
|
1640 |
+
"epoch": 0.5833333333333334,
|
1641 |
+
"grad_norm": 2.1875,
|
1642 |
+
"learning_rate": 8.776595744680852e-06,
|
1643 |
+
"loss": 0.6479,
|
1644 |
+
"step": 231
|
1645 |
+
},
|
1646 |
+
{
|
1647 |
+
"epoch": 0.5858585858585859,
|
1648 |
+
"grad_norm": 2.46875,
|
1649 |
+
"learning_rate": 8.72340425531915e-06,
|
1650 |
+
"loss": 0.7045,
|
1651 |
+
"step": 232
|
1652 |
+
},
|
1653 |
+
{
|
1654 |
+
"epoch": 0.5883838383838383,
|
1655 |
+
"grad_norm": 2.28125,
|
1656 |
+
"learning_rate": 8.670212765957447e-06,
|
1657 |
+
"loss": 0.6465,
|
1658 |
+
"step": 233
|
1659 |
+
},
|
1660 |
+
{
|
1661 |
+
"epoch": 0.5909090909090909,
|
1662 |
+
"grad_norm": 2.296875,
|
1663 |
+
"learning_rate": 8.617021276595746e-06,
|
1664 |
+
"loss": 0.7733,
|
1665 |
+
"step": 234
|
1666 |
+
},
|
1667 |
+
{
|
1668 |
+
"epoch": 0.5934343434343434,
|
1669 |
+
"grad_norm": 1.8984375,
|
1670 |
+
"learning_rate": 8.563829787234044e-06,
|
1671 |
+
"loss": 0.5294,
|
1672 |
+
"step": 235
|
1673 |
+
},
|
1674 |
+
{
|
1675 |
+
"epoch": 0.5959595959595959,
|
1676 |
+
"grad_norm": 2.234375,
|
1677 |
+
"learning_rate": 8.510638297872341e-06,
|
1678 |
+
"loss": 0.5508,
|
1679 |
+
"step": 236
|
1680 |
+
},
|
1681 |
+
{
|
1682 |
+
"epoch": 0.5984848484848485,
|
1683 |
+
"grad_norm": 2.546875,
|
1684 |
+
"learning_rate": 8.457446808510638e-06,
|
1685 |
+
"loss": 0.7075,
|
1686 |
+
"step": 237
|
1687 |
+
},
|
1688 |
+
{
|
1689 |
+
"epoch": 0.601010101010101,
|
1690 |
+
"grad_norm": 2.046875,
|
1691 |
+
"learning_rate": 8.404255319148937e-06,
|
1692 |
+
"loss": 0.5368,
|
1693 |
+
"step": 238
|
1694 |
+
},
|
1695 |
+
{
|
1696 |
+
"epoch": 0.6035353535353535,
|
1697 |
+
"grad_norm": 1.8828125,
|
1698 |
+
"learning_rate": 8.351063829787235e-06,
|
1699 |
+
"loss": 0.5084,
|
1700 |
+
"step": 239
|
1701 |
+
},
|
1702 |
+
{
|
1703 |
+
"epoch": 0.6060606060606061,
|
1704 |
+
"grad_norm": 2.484375,
|
1705 |
+
"learning_rate": 8.297872340425532e-06,
|
1706 |
+
"loss": 0.7621,
|
1707 |
+
"step": 240
|
1708 |
+
},
|
1709 |
+
{
|
1710 |
+
"epoch": 0.6085858585858586,
|
1711 |
+
"grad_norm": 2.171875,
|
1712 |
+
"learning_rate": 8.24468085106383e-06,
|
1713 |
+
"loss": 0.6219,
|
1714 |
+
"step": 241
|
1715 |
+
},
|
1716 |
+
{
|
1717 |
+
"epoch": 0.6111111111111112,
|
1718 |
+
"grad_norm": 2.21875,
|
1719 |
+
"learning_rate": 8.191489361702128e-06,
|
1720 |
+
"loss": 0.7703,
|
1721 |
+
"step": 242
|
1722 |
+
},
|
1723 |
+
{
|
1724 |
+
"epoch": 0.6136363636363636,
|
1725 |
+
"grad_norm": 2.296875,
|
1726 |
+
"learning_rate": 8.138297872340426e-06,
|
1727 |
+
"loss": 0.699,
|
1728 |
+
"step": 243
|
1729 |
+
},
|
1730 |
+
{
|
1731 |
+
"epoch": 0.6161616161616161,
|
1732 |
+
"grad_norm": 2.03125,
|
1733 |
+
"learning_rate": 8.085106382978723e-06,
|
1734 |
+
"loss": 0.6155,
|
1735 |
+
"step": 244
|
1736 |
+
},
|
1737 |
+
{
|
1738 |
+
"epoch": 0.6186868686868687,
|
1739 |
+
"grad_norm": 2.15625,
|
1740 |
+
"learning_rate": 8.031914893617022e-06,
|
1741 |
+
"loss": 0.6866,
|
1742 |
+
"step": 245
|
1743 |
+
},
|
1744 |
+
{
|
1745 |
+
"epoch": 0.6212121212121212,
|
1746 |
+
"grad_norm": 2.0,
|
1747 |
+
"learning_rate": 7.97872340425532e-06,
|
1748 |
+
"loss": 0.5463,
|
1749 |
+
"step": 246
|
1750 |
+
},
|
1751 |
+
{
|
1752 |
+
"epoch": 0.6237373737373737,
|
1753 |
+
"grad_norm": 2.109375,
|
1754 |
+
"learning_rate": 7.925531914893617e-06,
|
1755 |
+
"loss": 0.623,
|
1756 |
+
"step": 247
|
1757 |
+
},
|
1758 |
+
{
|
1759 |
+
"epoch": 0.6262626262626263,
|
1760 |
+
"grad_norm": 1.8671875,
|
1761 |
+
"learning_rate": 7.872340425531916e-06,
|
1762 |
+
"loss": 0.5725,
|
1763 |
+
"step": 248
|
1764 |
+
},
|
1765 |
+
{
|
1766 |
+
"epoch": 0.6287878787878788,
|
1767 |
+
"grad_norm": 2.15625,
|
1768 |
+
"learning_rate": 7.819148936170213e-06,
|
1769 |
+
"loss": 0.5766,
|
1770 |
+
"step": 249
|
1771 |
+
},
|
1772 |
+
{
|
1773 |
+
"epoch": 0.6313131313131313,
|
1774 |
+
"grad_norm": 2.25,
|
1775 |
+
"learning_rate": 7.765957446808511e-06,
|
1776 |
+
"loss": 0.6114,
|
1777 |
+
"step": 250
|
1778 |
+
},
|
1779 |
+
{
|
1780 |
+
"epoch": 0.6338383838383839,
|
1781 |
+
"grad_norm": 2.09375,
|
1782 |
+
"learning_rate": 7.71276595744681e-06,
|
1783 |
+
"loss": 0.5799,
|
1784 |
+
"step": 251
|
1785 |
+
},
|
1786 |
+
{
|
1787 |
+
"epoch": 0.6363636363636364,
|
1788 |
+
"grad_norm": 2.15625,
|
1789 |
+
"learning_rate": 7.659574468085107e-06,
|
1790 |
+
"loss": 0.6028,
|
1791 |
+
"step": 252
|
1792 |
+
},
|
1793 |
+
{
|
1794 |
+
"epoch": 0.6388888888888888,
|
1795 |
+
"grad_norm": 2.046875,
|
1796 |
+
"learning_rate": 7.606382978723405e-06,
|
1797 |
+
"loss": 0.5485,
|
1798 |
+
"step": 253
|
1799 |
+
},
|
1800 |
+
{
|
1801 |
+
"epoch": 0.6414141414141414,
|
1802 |
+
"grad_norm": 2.328125,
|
1803 |
+
"learning_rate": 7.553191489361703e-06,
|
1804 |
+
"loss": 0.6007,
|
1805 |
+
"step": 254
|
1806 |
+
},
|
1807 |
+
{
|
1808 |
+
"epoch": 0.6439393939393939,
|
1809 |
+
"grad_norm": 2.125,
|
1810 |
+
"learning_rate": 7.500000000000001e-06,
|
1811 |
+
"loss": 0.5623,
|
1812 |
+
"step": 255
|
1813 |
+
},
|
1814 |
+
{
|
1815 |
+
"epoch": 0.6464646464646465,
|
1816 |
+
"grad_norm": 1.9296875,
|
1817 |
+
"learning_rate": 7.446808510638298e-06,
|
1818 |
+
"loss": 0.5226,
|
1819 |
+
"step": 256
|
1820 |
+
},
|
1821 |
+
{
|
1822 |
+
"epoch": 0.648989898989899,
|
1823 |
+
"grad_norm": 1.90625,
|
1824 |
+
"learning_rate": 7.3936170212765965e-06,
|
1825 |
+
"loss": 0.5072,
|
1826 |
+
"step": 257
|
1827 |
+
},
|
1828 |
+
{
|
1829 |
+
"epoch": 0.6515151515151515,
|
1830 |
+
"grad_norm": 2.171875,
|
1831 |
+
"learning_rate": 7.340425531914894e-06,
|
1832 |
+
"loss": 0.6739,
|
1833 |
+
"step": 258
|
1834 |
+
},
|
1835 |
+
{
|
1836 |
+
"epoch": 0.6540404040404041,
|
1837 |
+
"grad_norm": 2.234375,
|
1838 |
+
"learning_rate": 7.287234042553192e-06,
|
1839 |
+
"loss": 0.6461,
|
1840 |
+
"step": 259
|
1841 |
+
},
|
1842 |
+
{
|
1843 |
+
"epoch": 0.6565656565656566,
|
1844 |
+
"grad_norm": 2.1875,
|
1845 |
+
"learning_rate": 7.234042553191491e-06,
|
1846 |
+
"loss": 0.5361,
|
1847 |
+
"step": 260
|
1848 |
+
},
|
1849 |
+
{
|
1850 |
+
"epoch": 0.6590909090909091,
|
1851 |
+
"grad_norm": 2.28125,
|
1852 |
+
"learning_rate": 7.1808510638297875e-06,
|
1853 |
+
"loss": 0.5884,
|
1854 |
+
"step": 261
|
1855 |
+
},
|
1856 |
+
{
|
1857 |
+
"epoch": 0.6616161616161617,
|
1858 |
+
"grad_norm": 1.9296875,
|
1859 |
+
"learning_rate": 7.127659574468085e-06,
|
1860 |
+
"loss": 0.5063,
|
1861 |
+
"step": 262
|
1862 |
+
},
|
1863 |
+
{
|
1864 |
+
"epoch": 0.6641414141414141,
|
1865 |
+
"grad_norm": 1.859375,
|
1866 |
+
"learning_rate": 7.074468085106384e-06,
|
1867 |
+
"loss": 0.4902,
|
1868 |
+
"step": 263
|
1869 |
+
},
|
1870 |
+
{
|
1871 |
+
"epoch": 0.6666666666666666,
|
1872 |
+
"grad_norm": 2.484375,
|
1873 |
+
"learning_rate": 7.021276595744682e-06,
|
1874 |
+
"loss": 0.5821,
|
1875 |
+
"step": 264
|
1876 |
+
},
|
1877 |
+
{
|
1878 |
+
"epoch": 0.6691919191919192,
|
1879 |
+
"grad_norm": 1.8828125,
|
1880 |
+
"learning_rate": 6.968085106382979e-06,
|
1881 |
+
"loss": 0.4859,
|
1882 |
+
"step": 265
|
1883 |
+
},
|
1884 |
+
{
|
1885 |
+
"epoch": 0.6717171717171717,
|
1886 |
+
"grad_norm": 2.359375,
|
1887 |
+
"learning_rate": 6.914893617021278e-06,
|
1888 |
+
"loss": 0.6668,
|
1889 |
+
"step": 266
|
1890 |
+
},
|
1891 |
+
{
|
1892 |
+
"epoch": 0.6742424242424242,
|
1893 |
+
"grad_norm": 1.984375,
|
1894 |
+
"learning_rate": 6.861702127659575e-06,
|
1895 |
+
"loss": 0.5804,
|
1896 |
+
"step": 267
|
1897 |
+
},
|
1898 |
+
{
|
1899 |
+
"epoch": 0.6767676767676768,
|
1900 |
+
"grad_norm": 2.015625,
|
1901 |
+
"learning_rate": 6.808510638297873e-06,
|
1902 |
+
"loss": 0.54,
|
1903 |
+
"step": 268
|
1904 |
+
},
|
1905 |
+
{
|
1906 |
+
"epoch": 0.6792929292929293,
|
1907 |
+
"grad_norm": 2.171875,
|
1908 |
+
"learning_rate": 6.75531914893617e-06,
|
1909 |
+
"loss": 0.6318,
|
1910 |
+
"step": 269
|
1911 |
+
},
|
1912 |
+
{
|
1913 |
+
"epoch": 0.6818181818181818,
|
1914 |
+
"grad_norm": 2.046875,
|
1915 |
+
"learning_rate": 6.702127659574469e-06,
|
1916 |
+
"loss": 0.552,
|
1917 |
+
"step": 270
|
1918 |
+
},
|
1919 |
+
{
|
1920 |
+
"epoch": 0.6843434343434344,
|
1921 |
+
"grad_norm": 2.125,
|
1922 |
+
"learning_rate": 6.648936170212767e-06,
|
1923 |
+
"loss": 0.5727,
|
1924 |
+
"step": 271
|
1925 |
+
},
|
1926 |
+
{
|
1927 |
+
"epoch": 0.6868686868686869,
|
1928 |
+
"grad_norm": 2.234375,
|
1929 |
+
"learning_rate": 6.595744680851064e-06,
|
1930 |
+
"loss": 0.673,
|
1931 |
+
"step": 272
|
1932 |
+
},
|
1933 |
+
{
|
1934 |
+
"epoch": 0.6893939393939394,
|
1935 |
+
"grad_norm": 2.171875,
|
1936 |
+
"learning_rate": 6.542553191489362e-06,
|
1937 |
+
"loss": 0.5932,
|
1938 |
+
"step": 273
|
1939 |
+
},
|
1940 |
+
{
|
1941 |
+
"epoch": 0.6919191919191919,
|
1942 |
+
"grad_norm": 1.921875,
|
1943 |
+
"learning_rate": 6.48936170212766e-06,
|
1944 |
+
"loss": 0.5093,
|
1945 |
+
"step": 274
|
1946 |
+
},
|
1947 |
+
{
|
1948 |
+
"epoch": 0.6944444444444444,
|
1949 |
+
"grad_norm": 2.0625,
|
1950 |
+
"learning_rate": 6.436170212765958e-06,
|
1951 |
+
"loss": 0.5441,
|
1952 |
+
"step": 275
|
1953 |
+
},
|
1954 |
+
{
|
1955 |
+
"epoch": 0.696969696969697,
|
1956 |
+
"grad_norm": 2.28125,
|
1957 |
+
"learning_rate": 6.382978723404256e-06,
|
1958 |
+
"loss": 0.7347,
|
1959 |
+
"step": 276
|
1960 |
+
},
|
1961 |
+
{
|
1962 |
+
"epoch": 0.6994949494949495,
|
1963 |
+
"grad_norm": 2.015625,
|
1964 |
+
"learning_rate": 6.329787234042554e-06,
|
1965 |
+
"loss": 0.6073,
|
1966 |
+
"step": 277
|
1967 |
+
},
|
1968 |
+
{
|
1969 |
+
"epoch": 0.702020202020202,
|
1970 |
+
"grad_norm": 1.9375,
|
1971 |
+
"learning_rate": 6.276595744680851e-06,
|
1972 |
+
"loss": 0.535,
|
1973 |
+
"step": 278
|
1974 |
+
},
|
1975 |
+
{
|
1976 |
+
"epoch": 0.7045454545454546,
|
1977 |
+
"grad_norm": 1.9453125,
|
1978 |
+
"learning_rate": 6.22340425531915e-06,
|
1979 |
+
"loss": 0.5872,
|
1980 |
+
"step": 279
|
1981 |
+
},
|
1982 |
+
{
|
1983 |
+
"epoch": 0.7070707070707071,
|
1984 |
+
"grad_norm": 2.375,
|
1985 |
+
"learning_rate": 6.170212765957447e-06,
|
1986 |
+
"loss": 0.5513,
|
1987 |
+
"step": 280
|
1988 |
+
},
|
1989 |
+
{
|
1990 |
+
"epoch": 0.7095959595959596,
|
1991 |
+
"grad_norm": 2.125,
|
1992 |
+
"learning_rate": 6.117021276595745e-06,
|
1993 |
+
"loss": 0.5443,
|
1994 |
+
"step": 281
|
1995 |
+
},
|
1996 |
+
{
|
1997 |
+
"epoch": 0.7121212121212122,
|
1998 |
+
"grad_norm": 2.109375,
|
1999 |
+
"learning_rate": 6.063829787234044e-06,
|
2000 |
+
"loss": 0.5909,
|
2001 |
+
"step": 282
|
2002 |
+
},
|
2003 |
+
{
|
2004 |
+
"epoch": 0.7146464646464646,
|
2005 |
+
"grad_norm": 2.125,
|
2006 |
+
"learning_rate": 6.010638297872341e-06,
|
2007 |
+
"loss": 0.6246,
|
2008 |
+
"step": 283
|
2009 |
+
},
|
2010 |
+
{
|
2011 |
+
"epoch": 0.7171717171717171,
|
2012 |
+
"grad_norm": 2.328125,
|
2013 |
+
"learning_rate": 5.957446808510638e-06,
|
2014 |
+
"loss": 0.6736,
|
2015 |
+
"step": 284
|
2016 |
+
},
|
2017 |
+
{
|
2018 |
+
"epoch": 0.7196969696969697,
|
2019 |
+
"grad_norm": 2.046875,
|
2020 |
+
"learning_rate": 5.904255319148937e-06,
|
2021 |
+
"loss": 0.6977,
|
2022 |
+
"step": 285
|
2023 |
+
},
|
2024 |
+
{
|
2025 |
+
"epoch": 0.7222222222222222,
|
2026 |
+
"grad_norm": 1.953125,
|
2027 |
+
"learning_rate": 5.851063829787235e-06,
|
2028 |
+
"loss": 0.5457,
|
2029 |
+
"step": 286
|
2030 |
+
},
|
2031 |
+
{
|
2032 |
+
"epoch": 0.7247474747474747,
|
2033 |
+
"grad_norm": 2.34375,
|
2034 |
+
"learning_rate": 5.7978723404255325e-06,
|
2035 |
+
"loss": 0.689,
|
2036 |
+
"step": 287
|
2037 |
+
},
|
2038 |
+
{
|
2039 |
+
"epoch": 0.7272727272727273,
|
2040 |
+
"grad_norm": 1.9375,
|
2041 |
+
"learning_rate": 5.744680851063831e-06,
|
2042 |
+
"loss": 0.5628,
|
2043 |
+
"step": 288
|
2044 |
+
},
|
2045 |
+
{
|
2046 |
+
"epoch": 0.7297979797979798,
|
2047 |
+
"grad_norm": 1.9140625,
|
2048 |
+
"learning_rate": 5.691489361702128e-06,
|
2049 |
+
"loss": 0.4981,
|
2050 |
+
"step": 289
|
2051 |
+
},
|
2052 |
+
{
|
2053 |
+
"epoch": 0.7323232323232324,
|
2054 |
+
"grad_norm": 1.953125,
|
2055 |
+
"learning_rate": 5.638297872340426e-06,
|
2056 |
+
"loss": 0.5368,
|
2057 |
+
"step": 290
|
2058 |
+
},
|
2059 |
+
{
|
2060 |
+
"epoch": 0.7348484848484849,
|
2061 |
+
"grad_norm": 2.3125,
|
2062 |
+
"learning_rate": 5.5851063829787235e-06,
|
2063 |
+
"loss": 0.6594,
|
2064 |
+
"step": 291
|
2065 |
+
},
|
2066 |
+
{
|
2067 |
+
"epoch": 0.7373737373737373,
|
2068 |
+
"grad_norm": 2.390625,
|
2069 |
+
"learning_rate": 5.531914893617022e-06,
|
2070 |
+
"loss": 0.5935,
|
2071 |
+
"step": 292
|
2072 |
+
},
|
2073 |
+
{
|
2074 |
+
"epoch": 0.73989898989899,
|
2075 |
+
"grad_norm": 2.15625,
|
2076 |
+
"learning_rate": 5.47872340425532e-06,
|
2077 |
+
"loss": 0.5859,
|
2078 |
+
"step": 293
|
2079 |
+
},
|
2080 |
+
{
|
2081 |
+
"epoch": 0.7424242424242424,
|
2082 |
+
"grad_norm": 2.234375,
|
2083 |
+
"learning_rate": 5.425531914893617e-06,
|
2084 |
+
"loss": 0.598,
|
2085 |
+
"step": 294
|
2086 |
+
},
|
2087 |
+
{
|
2088 |
+
"epoch": 0.7424242424242424,
|
2089 |
+
"eval_loss": 0.49261218309402466,
|
2090 |
+
"eval_model_preparation_time": 0.0001,
|
2091 |
+
"eval_runtime": 2.0683,
|
2092 |
+
"eval_samples_per_second": 51.249,
|
2093 |
+
"eval_steps_per_second": 6.769,
|
2094 |
+
"step": 294
|
2095 |
+
},
|
2096 |
+
{
|
2097 |
+
"epoch": 0.7449494949494949,
|
2098 |
+
"grad_norm": 1.9296875,
|
2099 |
+
"learning_rate": 5.372340425531915e-06,
|
2100 |
+
"loss": 0.4914,
|
2101 |
+
"step": 295
|
2102 |
+
},
|
2103 |
+
{
|
2104 |
+
"epoch": 0.7474747474747475,
|
2105 |
+
"grad_norm": 2.15625,
|
2106 |
+
"learning_rate": 5.319148936170213e-06,
|
2107 |
+
"loss": 0.739,
|
2108 |
+
"step": 296
|
2109 |
+
},
|
2110 |
+
{
|
2111 |
+
"epoch": 0.75,
|
2112 |
+
"grad_norm": 2.171875,
|
2113 |
+
"learning_rate": 5.265957446808511e-06,
|
2114 |
+
"loss": 0.5582,
|
2115 |
+
"step": 297
|
2116 |
+
},
|
2117 |
+
{
|
2118 |
+
"epoch": 0.7525252525252525,
|
2119 |
+
"grad_norm": 2.453125,
|
2120 |
+
"learning_rate": 5.212765957446809e-06,
|
2121 |
+
"loss": 0.7083,
|
2122 |
+
"step": 298
|
2123 |
+
},
|
2124 |
+
{
|
2125 |
+
"epoch": 0.7550505050505051,
|
2126 |
+
"grad_norm": 2.0625,
|
2127 |
+
"learning_rate": 5.159574468085107e-06,
|
2128 |
+
"loss": 0.5886,
|
2129 |
+
"step": 299
|
2130 |
+
},
|
2131 |
+
{
|
2132 |
+
"epoch": 0.7575757575757576,
|
2133 |
+
"grad_norm": 2.15625,
|
2134 |
+
"learning_rate": 5.106382978723404e-06,
|
2135 |
+
"loss": 0.6125,
|
2136 |
+
"step": 300
|
2137 |
+
},
|
2138 |
+
{
|
2139 |
+
"epoch": 0.76010101010101,
|
2140 |
+
"grad_norm": 2.09375,
|
2141 |
+
"learning_rate": 5.053191489361703e-06,
|
2142 |
+
"loss": 0.5323,
|
2143 |
+
"step": 301
|
2144 |
+
},
|
2145 |
+
{
|
2146 |
+
"epoch": 0.7626262626262627,
|
2147 |
+
"grad_norm": 2.046875,
|
2148 |
+
"learning_rate": 5e-06,
|
2149 |
+
"loss": 0.5877,
|
2150 |
+
"step": 302
|
2151 |
+
},
|
2152 |
+
{
|
2153 |
+
"epoch": 0.7651515151515151,
|
2154 |
+
"grad_norm": 2.09375,
|
2155 |
+
"learning_rate": 4.946808510638298e-06,
|
2156 |
+
"loss": 0.618,
|
2157 |
+
"step": 303
|
2158 |
+
},
|
2159 |
+
{
|
2160 |
+
"epoch": 0.7676767676767676,
|
2161 |
+
"grad_norm": 2.046875,
|
2162 |
+
"learning_rate": 4.893617021276596e-06,
|
2163 |
+
"loss": 0.6148,
|
2164 |
+
"step": 304
|
2165 |
+
},
|
2166 |
+
{
|
2167 |
+
"epoch": 0.7702020202020202,
|
2168 |
+
"grad_norm": 2.109375,
|
2169 |
+
"learning_rate": 4.840425531914894e-06,
|
2170 |
+
"loss": 0.5589,
|
2171 |
+
"step": 305
|
2172 |
+
},
|
2173 |
+
{
|
2174 |
+
"epoch": 0.7727272727272727,
|
2175 |
+
"grad_norm": 1.9921875,
|
2176 |
+
"learning_rate": 4.787234042553192e-06,
|
2177 |
+
"loss": 0.5927,
|
2178 |
+
"step": 306
|
2179 |
+
},
|
2180 |
+
{
|
2181 |
+
"epoch": 0.7752525252525253,
|
2182 |
+
"grad_norm": 2.453125,
|
2183 |
+
"learning_rate": 4.73404255319149e-06,
|
2184 |
+
"loss": 0.6524,
|
2185 |
+
"step": 307
|
2186 |
+
},
|
2187 |
+
{
|
2188 |
+
"epoch": 0.7777777777777778,
|
2189 |
+
"grad_norm": 1.9609375,
|
2190 |
+
"learning_rate": 4.680851063829788e-06,
|
2191 |
+
"loss": 0.4944,
|
2192 |
+
"step": 308
|
2193 |
+
},
|
2194 |
+
{
|
2195 |
+
"epoch": 0.7803030303030303,
|
2196 |
+
"grad_norm": 1.9765625,
|
2197 |
+
"learning_rate": 4.6276595744680855e-06,
|
2198 |
+
"loss": 0.6216,
|
2199 |
+
"step": 309
|
2200 |
+
},
|
2201 |
+
{
|
2202 |
+
"epoch": 0.7828282828282829,
|
2203 |
+
"grad_norm": 2.109375,
|
2204 |
+
"learning_rate": 4.574468085106383e-06,
|
2205 |
+
"loss": 0.5407,
|
2206 |
+
"step": 310
|
2207 |
+
},
|
2208 |
+
{
|
2209 |
+
"epoch": 0.7853535353535354,
|
2210 |
+
"grad_norm": 2.15625,
|
2211 |
+
"learning_rate": 4.521276595744681e-06,
|
2212 |
+
"loss": 0.5426,
|
2213 |
+
"step": 311
|
2214 |
+
},
|
2215 |
+
{
|
2216 |
+
"epoch": 0.7878787878787878,
|
2217 |
+
"grad_norm": 2.5625,
|
2218 |
+
"learning_rate": 4.468085106382979e-06,
|
2219 |
+
"loss": 0.6869,
|
2220 |
+
"step": 312
|
2221 |
+
},
|
2222 |
+
{
|
2223 |
+
"epoch": 0.7904040404040404,
|
2224 |
+
"grad_norm": 1.90625,
|
2225 |
+
"learning_rate": 4.414893617021277e-06,
|
2226 |
+
"loss": 0.4939,
|
2227 |
+
"step": 313
|
2228 |
+
},
|
2229 |
+
{
|
2230 |
+
"epoch": 0.7929292929292929,
|
2231 |
+
"grad_norm": 1.9296875,
|
2232 |
+
"learning_rate": 4.361702127659575e-06,
|
2233 |
+
"loss": 0.5599,
|
2234 |
+
"step": 314
|
2235 |
+
},
|
2236 |
+
{
|
2237 |
+
"epoch": 0.7954545454545454,
|
2238 |
+
"grad_norm": 1.984375,
|
2239 |
+
"learning_rate": 4.308510638297873e-06,
|
2240 |
+
"loss": 0.5386,
|
2241 |
+
"step": 315
|
2242 |
+
},
|
2243 |
+
{
|
2244 |
+
"epoch": 0.797979797979798,
|
2245 |
+
"grad_norm": 2.0,
|
2246 |
+
"learning_rate": 4.255319148936171e-06,
|
2247 |
+
"loss": 0.5639,
|
2248 |
+
"step": 316
|
2249 |
+
},
|
2250 |
+
{
|
2251 |
+
"epoch": 0.8005050505050505,
|
2252 |
+
"grad_norm": 2.140625,
|
2253 |
+
"learning_rate": 4.202127659574468e-06,
|
2254 |
+
"loss": 0.5941,
|
2255 |
+
"step": 317
|
2256 |
+
},
|
2257 |
+
{
|
2258 |
+
"epoch": 0.803030303030303,
|
2259 |
+
"grad_norm": 2.28125,
|
2260 |
+
"learning_rate": 4.148936170212766e-06,
|
2261 |
+
"loss": 0.6414,
|
2262 |
+
"step": 318
|
2263 |
+
},
|
2264 |
+
{
|
2265 |
+
"epoch": 0.8055555555555556,
|
2266 |
+
"grad_norm": 1.953125,
|
2267 |
+
"learning_rate": 4.095744680851064e-06,
|
2268 |
+
"loss": 0.5747,
|
2269 |
+
"step": 319
|
2270 |
+
},
|
2271 |
+
{
|
2272 |
+
"epoch": 0.8080808080808081,
|
2273 |
+
"grad_norm": 2.078125,
|
2274 |
+
"learning_rate": 4.042553191489362e-06,
|
2275 |
+
"loss": 0.6022,
|
2276 |
+
"step": 320
|
2277 |
+
},
|
2278 |
+
{
|
2279 |
+
"epoch": 0.8106060606060606,
|
2280 |
+
"grad_norm": 1.9453125,
|
2281 |
+
"learning_rate": 3.98936170212766e-06,
|
2282 |
+
"loss": 0.5137,
|
2283 |
+
"step": 321
|
2284 |
+
},
|
2285 |
+
{
|
2286 |
+
"epoch": 0.8131313131313131,
|
2287 |
+
"grad_norm": 2.34375,
|
2288 |
+
"learning_rate": 3.936170212765958e-06,
|
2289 |
+
"loss": 0.6665,
|
2290 |
+
"step": 322
|
2291 |
+
},
|
2292 |
+
{
|
2293 |
+
"epoch": 0.8156565656565656,
|
2294 |
+
"grad_norm": 2.03125,
|
2295 |
+
"learning_rate": 3.882978723404256e-06,
|
2296 |
+
"loss": 0.5478,
|
2297 |
+
"step": 323
|
2298 |
+
},
|
2299 |
+
{
|
2300 |
+
"epoch": 0.8181818181818182,
|
2301 |
+
"grad_norm": 2.4375,
|
2302 |
+
"learning_rate": 3.8297872340425535e-06,
|
2303 |
+
"loss": 0.7404,
|
2304 |
+
"step": 324
|
2305 |
+
},
|
2306 |
+
{
|
2307 |
+
"epoch": 0.8207070707070707,
|
2308 |
+
"grad_norm": 2.265625,
|
2309 |
+
"learning_rate": 3.7765957446808516e-06,
|
2310 |
+
"loss": 0.6361,
|
2311 |
+
"step": 325
|
2312 |
+
},
|
2313 |
+
{
|
2314 |
+
"epoch": 0.8232323232323232,
|
2315 |
+
"grad_norm": 2.109375,
|
2316 |
+
"learning_rate": 3.723404255319149e-06,
|
2317 |
+
"loss": 0.5841,
|
2318 |
+
"step": 326
|
2319 |
+
},
|
2320 |
+
{
|
2321 |
+
"epoch": 0.8257575757575758,
|
2322 |
+
"grad_norm": 2.15625,
|
2323 |
+
"learning_rate": 3.670212765957447e-06,
|
2324 |
+
"loss": 0.5882,
|
2325 |
+
"step": 327
|
2326 |
+
},
|
2327 |
+
{
|
2328 |
+
"epoch": 0.8282828282828283,
|
2329 |
+
"grad_norm": 2.25,
|
2330 |
+
"learning_rate": 3.6170212765957453e-06,
|
2331 |
+
"loss": 0.577,
|
2332 |
+
"step": 328
|
2333 |
+
},
|
2334 |
+
{
|
2335 |
+
"epoch": 0.8308080808080808,
|
2336 |
+
"grad_norm": 1.9375,
|
2337 |
+
"learning_rate": 3.5638297872340426e-06,
|
2338 |
+
"loss": 0.468,
|
2339 |
+
"step": 329
|
2340 |
+
},
|
2341 |
+
{
|
2342 |
+
"epoch": 0.8333333333333334,
|
2343 |
+
"grad_norm": 2.3125,
|
2344 |
+
"learning_rate": 3.510638297872341e-06,
|
2345 |
+
"loss": 0.5352,
|
2346 |
+
"step": 330
|
2347 |
+
},
|
2348 |
+
{
|
2349 |
+
"epoch": 0.8358585858585859,
|
2350 |
+
"grad_norm": 2.1875,
|
2351 |
+
"learning_rate": 3.457446808510639e-06,
|
2352 |
+
"loss": 0.6389,
|
2353 |
+
"step": 331
|
2354 |
+
},
|
2355 |
+
{
|
2356 |
+
"epoch": 0.8383838383838383,
|
2357 |
+
"grad_norm": 2.078125,
|
2358 |
+
"learning_rate": 3.4042553191489363e-06,
|
2359 |
+
"loss": 0.5887,
|
2360 |
+
"step": 332
|
2361 |
+
},
|
2362 |
+
{
|
2363 |
+
"epoch": 0.8409090909090909,
|
2364 |
+
"grad_norm": 2.265625,
|
2365 |
+
"learning_rate": 3.3510638297872345e-06,
|
2366 |
+
"loss": 0.613,
|
2367 |
+
"step": 333
|
2368 |
+
},
|
2369 |
+
{
|
2370 |
+
"epoch": 0.8434343434343434,
|
2371 |
+
"grad_norm": 2.1875,
|
2372 |
+
"learning_rate": 3.297872340425532e-06,
|
2373 |
+
"loss": 0.6165,
|
2374 |
+
"step": 334
|
2375 |
+
},
|
2376 |
+
{
|
2377 |
+
"epoch": 0.8459595959595959,
|
2378 |
+
"grad_norm": 2.09375,
|
2379 |
+
"learning_rate": 3.24468085106383e-06,
|
2380 |
+
"loss": 0.713,
|
2381 |
+
"step": 335
|
2382 |
+
},
|
2383 |
+
{
|
2384 |
+
"epoch": 0.8484848484848485,
|
2385 |
+
"grad_norm": 2.265625,
|
2386 |
+
"learning_rate": 3.191489361702128e-06,
|
2387 |
+
"loss": 0.5602,
|
2388 |
+
"step": 336
|
2389 |
+
},
|
2390 |
+
{
|
2391 |
+
"epoch": 0.851010101010101,
|
2392 |
+
"grad_norm": 1.9765625,
|
2393 |
+
"learning_rate": 3.1382978723404255e-06,
|
2394 |
+
"loss": 0.5783,
|
2395 |
+
"step": 337
|
2396 |
+
},
|
2397 |
+
{
|
2398 |
+
"epoch": 0.8535353535353535,
|
2399 |
+
"grad_norm": 2.1875,
|
2400 |
+
"learning_rate": 3.0851063829787237e-06,
|
2401 |
+
"loss": 0.6095,
|
2402 |
+
"step": 338
|
2403 |
+
},
|
2404 |
+
{
|
2405 |
+
"epoch": 0.8560606060606061,
|
2406 |
+
"grad_norm": 2.09375,
|
2407 |
+
"learning_rate": 3.031914893617022e-06,
|
2408 |
+
"loss": 0.5752,
|
2409 |
+
"step": 339
|
2410 |
+
},
|
2411 |
+
{
|
2412 |
+
"epoch": 0.8585858585858586,
|
2413 |
+
"grad_norm": 1.96875,
|
2414 |
+
"learning_rate": 2.978723404255319e-06,
|
2415 |
+
"loss": 0.5692,
|
2416 |
+
"step": 340
|
2417 |
+
},
|
2418 |
+
{
|
2419 |
+
"epoch": 0.8611111111111112,
|
2420 |
+
"grad_norm": 2.203125,
|
2421 |
+
"learning_rate": 2.9255319148936174e-06,
|
2422 |
+
"loss": 0.5864,
|
2423 |
+
"step": 341
|
2424 |
+
},
|
2425 |
+
{
|
2426 |
+
"epoch": 0.8636363636363636,
|
2427 |
+
"grad_norm": 2.109375,
|
2428 |
+
"learning_rate": 2.8723404255319155e-06,
|
2429 |
+
"loss": 0.5904,
|
2430 |
+
"step": 342
|
2431 |
+
},
|
2432 |
+
{
|
2433 |
+
"epoch": 0.8661616161616161,
|
2434 |
+
"grad_norm": 1.9296875,
|
2435 |
+
"learning_rate": 2.819148936170213e-06,
|
2436 |
+
"loss": 0.4829,
|
2437 |
+
"step": 343
|
2438 |
+
},
|
2439 |
+
{
|
2440 |
+
"epoch": 0.8686868686868687,
|
2441 |
+
"grad_norm": 2.15625,
|
2442 |
+
"learning_rate": 2.765957446808511e-06,
|
2443 |
+
"loss": 0.6226,
|
2444 |
+
"step": 344
|
2445 |
+
},
|
2446 |
+
{
|
2447 |
+
"epoch": 0.8712121212121212,
|
2448 |
+
"grad_norm": 2.203125,
|
2449 |
+
"learning_rate": 2.7127659574468084e-06,
|
2450 |
+
"loss": 0.7041,
|
2451 |
+
"step": 345
|
2452 |
+
},
|
2453 |
+
{
|
2454 |
+
"epoch": 0.8737373737373737,
|
2455 |
+
"grad_norm": 2.03125,
|
2456 |
+
"learning_rate": 2.6595744680851065e-06,
|
2457 |
+
"loss": 0.6518,
|
2458 |
+
"step": 346
|
2459 |
+
},
|
2460 |
+
{
|
2461 |
+
"epoch": 0.8762626262626263,
|
2462 |
+
"grad_norm": 2.0,
|
2463 |
+
"learning_rate": 2.6063829787234047e-06,
|
2464 |
+
"loss": 0.5096,
|
2465 |
+
"step": 347
|
2466 |
+
},
|
2467 |
+
{
|
2468 |
+
"epoch": 0.8787878787878788,
|
2469 |
+
"grad_norm": 1.9453125,
|
2470 |
+
"learning_rate": 2.553191489361702e-06,
|
2471 |
+
"loss": 0.487,
|
2472 |
+
"step": 348
|
2473 |
+
},
|
2474 |
+
{
|
2475 |
+
"epoch": 0.8813131313131313,
|
2476 |
+
"grad_norm": 2.171875,
|
2477 |
+
"learning_rate": 2.5e-06,
|
2478 |
+
"loss": 0.6226,
|
2479 |
+
"step": 349
|
2480 |
+
},
|
2481 |
+
{
|
2482 |
+
"epoch": 0.8838383838383839,
|
2483 |
+
"grad_norm": 2.421875,
|
2484 |
+
"learning_rate": 2.446808510638298e-06,
|
2485 |
+
"loss": 0.7568,
|
2486 |
+
"step": 350
|
2487 |
+
},
|
2488 |
+
{
|
2489 |
+
"epoch": 0.8863636363636364,
|
2490 |
+
"grad_norm": 2.046875,
|
2491 |
+
"learning_rate": 2.393617021276596e-06,
|
2492 |
+
"loss": 0.5137,
|
2493 |
+
"step": 351
|
2494 |
+
},
|
2495 |
+
{
|
2496 |
+
"epoch": 0.8888888888888888,
|
2497 |
+
"grad_norm": 2.03125,
|
2498 |
+
"learning_rate": 2.340425531914894e-06,
|
2499 |
+
"loss": 0.5703,
|
2500 |
+
"step": 352
|
2501 |
+
},
|
2502 |
+
{
|
2503 |
+
"epoch": 0.8914141414141414,
|
2504 |
+
"grad_norm": 2.171875,
|
2505 |
+
"learning_rate": 2.2872340425531916e-06,
|
2506 |
+
"loss": 0.633,
|
2507 |
+
"step": 353
|
2508 |
+
},
|
2509 |
+
{
|
2510 |
+
"epoch": 0.8939393939393939,
|
2511 |
+
"grad_norm": 2.34375,
|
2512 |
+
"learning_rate": 2.2340425531914894e-06,
|
2513 |
+
"loss": 0.6691,
|
2514 |
+
"step": 354
|
2515 |
+
},
|
2516 |
+
{
|
2517 |
+
"epoch": 0.8964646464646465,
|
2518 |
+
"grad_norm": 2.15625,
|
2519 |
+
"learning_rate": 2.1808510638297876e-06,
|
2520 |
+
"loss": 0.5669,
|
2521 |
+
"step": 355
|
2522 |
+
},
|
2523 |
+
{
|
2524 |
+
"epoch": 0.898989898989899,
|
2525 |
+
"grad_norm": 1.84375,
|
2526 |
+
"learning_rate": 2.1276595744680853e-06,
|
2527 |
+
"loss": 0.4753,
|
2528 |
+
"step": 356
|
2529 |
+
},
|
2530 |
+
{
|
2531 |
+
"epoch": 0.9015151515151515,
|
2532 |
+
"grad_norm": 2.1875,
|
2533 |
+
"learning_rate": 2.074468085106383e-06,
|
2534 |
+
"loss": 0.7078,
|
2535 |
+
"step": 357
|
2536 |
+
},
|
2537 |
+
{
|
2538 |
+
"epoch": 0.9040404040404041,
|
2539 |
+
"grad_norm": 2.171875,
|
2540 |
+
"learning_rate": 2.021276595744681e-06,
|
2541 |
+
"loss": 0.6176,
|
2542 |
+
"step": 358
|
2543 |
+
},
|
2544 |
+
{
|
2545 |
+
"epoch": 0.9065656565656566,
|
2546 |
+
"grad_norm": 2.03125,
|
2547 |
+
"learning_rate": 1.968085106382979e-06,
|
2548 |
+
"loss": 0.5637,
|
2549 |
+
"step": 359
|
2550 |
+
},
|
2551 |
+
{
|
2552 |
+
"epoch": 0.9090909090909091,
|
2553 |
+
"grad_norm": 2.109375,
|
2554 |
+
"learning_rate": 1.9148936170212767e-06,
|
2555 |
+
"loss": 0.5992,
|
2556 |
+
"step": 360
|
2557 |
+
},
|
2558 |
+
{
|
2559 |
+
"epoch": 0.9116161616161617,
|
2560 |
+
"grad_norm": 1.984375,
|
2561 |
+
"learning_rate": 1.8617021276595745e-06,
|
2562 |
+
"loss": 0.5278,
|
2563 |
+
"step": 361
|
2564 |
+
},
|
2565 |
+
{
|
2566 |
+
"epoch": 0.9141414141414141,
|
2567 |
+
"grad_norm": 2.25,
|
2568 |
+
"learning_rate": 1.8085106382978727e-06,
|
2569 |
+
"loss": 0.6573,
|
2570 |
+
"step": 362
|
2571 |
+
},
|
2572 |
+
{
|
2573 |
+
"epoch": 0.9166666666666666,
|
2574 |
+
"grad_norm": 1.9609375,
|
2575 |
+
"learning_rate": 1.7553191489361704e-06,
|
2576 |
+
"loss": 0.5592,
|
2577 |
+
"step": 363
|
2578 |
+
},
|
2579 |
+
{
|
2580 |
+
"epoch": 0.9191919191919192,
|
2581 |
+
"grad_norm": 2.171875,
|
2582 |
+
"learning_rate": 1.7021276595744682e-06,
|
2583 |
+
"loss": 0.6199,
|
2584 |
+
"step": 364
|
2585 |
+
},
|
2586 |
+
{
|
2587 |
+
"epoch": 0.9217171717171717,
|
2588 |
+
"grad_norm": 2.21875,
|
2589 |
+
"learning_rate": 1.648936170212766e-06,
|
2590 |
+
"loss": 0.6009,
|
2591 |
+
"step": 365
|
2592 |
+
},
|
2593 |
+
{
|
2594 |
+
"epoch": 0.9242424242424242,
|
2595 |
+
"grad_norm": 2.25,
|
2596 |
+
"learning_rate": 1.595744680851064e-06,
|
2597 |
+
"loss": 0.6213,
|
2598 |
+
"step": 366
|
2599 |
+
},
|
2600 |
+
{
|
2601 |
+
"epoch": 0.9267676767676768,
|
2602 |
+
"grad_norm": 1.8828125,
|
2603 |
+
"learning_rate": 1.5425531914893618e-06,
|
2604 |
+
"loss": 0.4765,
|
2605 |
+
"step": 367
|
2606 |
+
},
|
2607 |
+
{
|
2608 |
+
"epoch": 0.9292929292929293,
|
2609 |
+
"grad_norm": 1.75,
|
2610 |
+
"learning_rate": 1.4893617021276596e-06,
|
2611 |
+
"loss": 0.4497,
|
2612 |
+
"step": 368
|
2613 |
+
},
|
2614 |
+
{
|
2615 |
+
"epoch": 0.9318181818181818,
|
2616 |
+
"grad_norm": 1.953125,
|
2617 |
+
"learning_rate": 1.4361702127659578e-06,
|
2618 |
+
"loss": 0.5104,
|
2619 |
+
"step": 369
|
2620 |
+
},
|
2621 |
+
{
|
2622 |
+
"epoch": 0.9343434343434344,
|
2623 |
+
"grad_norm": 2.15625,
|
2624 |
+
"learning_rate": 1.3829787234042555e-06,
|
2625 |
+
"loss": 0.635,
|
2626 |
+
"step": 370
|
2627 |
+
},
|
2628 |
+
{
|
2629 |
+
"epoch": 0.9368686868686869,
|
2630 |
+
"grad_norm": 2.3125,
|
2631 |
+
"learning_rate": 1.3297872340425533e-06,
|
2632 |
+
"loss": 0.6006,
|
2633 |
+
"step": 371
|
2634 |
+
},
|
2635 |
+
{
|
2636 |
+
"epoch": 0.9393939393939394,
|
2637 |
+
"grad_norm": 2.265625,
|
2638 |
+
"learning_rate": 1.276595744680851e-06,
|
2639 |
+
"loss": 0.6573,
|
2640 |
+
"step": 372
|
2641 |
+
},
|
2642 |
+
{
|
2643 |
+
"epoch": 0.9419191919191919,
|
2644 |
+
"grad_norm": 1.9375,
|
2645 |
+
"learning_rate": 1.223404255319149e-06,
|
2646 |
+
"loss": 0.5499,
|
2647 |
+
"step": 373
|
2648 |
+
},
|
2649 |
+
{
|
2650 |
+
"epoch": 0.9444444444444444,
|
2651 |
+
"grad_norm": 1.8984375,
|
2652 |
+
"learning_rate": 1.170212765957447e-06,
|
2653 |
+
"loss": 0.5335,
|
2654 |
+
"step": 374
|
2655 |
+
},
|
2656 |
+
{
|
2657 |
+
"epoch": 0.946969696969697,
|
2658 |
+
"grad_norm": 1.8515625,
|
2659 |
+
"learning_rate": 1.1170212765957447e-06,
|
2660 |
+
"loss": 0.4841,
|
2661 |
+
"step": 375
|
2662 |
+
},
|
2663 |
+
{
|
2664 |
+
"epoch": 0.9494949494949495,
|
2665 |
+
"grad_norm": 2.046875,
|
2666 |
+
"learning_rate": 1.0638297872340427e-06,
|
2667 |
+
"loss": 0.5106,
|
2668 |
+
"step": 376
|
2669 |
+
},
|
2670 |
+
{
|
2671 |
+
"epoch": 0.952020202020202,
|
2672 |
+
"grad_norm": 1.9296875,
|
2673 |
+
"learning_rate": 1.0106382978723404e-06,
|
2674 |
+
"loss": 0.4671,
|
2675 |
+
"step": 377
|
2676 |
+
},
|
2677 |
+
{
|
2678 |
+
"epoch": 0.9545454545454546,
|
2679 |
+
"grad_norm": 2.171875,
|
2680 |
+
"learning_rate": 9.574468085106384e-07,
|
2681 |
+
"loss": 0.5331,
|
2682 |
+
"step": 378
|
2683 |
+
},
|
2684 |
+
{
|
2685 |
+
"epoch": 0.9570707070707071,
|
2686 |
+
"grad_norm": 2.140625,
|
2687 |
+
"learning_rate": 9.042553191489363e-07,
|
2688 |
+
"loss": 0.6902,
|
2689 |
+
"step": 379
|
2690 |
+
},
|
2691 |
+
{
|
2692 |
+
"epoch": 0.9595959595959596,
|
2693 |
+
"grad_norm": 1.859375,
|
2694 |
+
"learning_rate": 8.510638297872341e-07,
|
2695 |
+
"loss": 0.4853,
|
2696 |
+
"step": 380
|
2697 |
+
},
|
2698 |
+
{
|
2699 |
+
"epoch": 0.9621212121212122,
|
2700 |
+
"grad_norm": 2.296875,
|
2701 |
+
"learning_rate": 7.97872340425532e-07,
|
2702 |
+
"loss": 0.6197,
|
2703 |
+
"step": 381
|
2704 |
+
},
|
2705 |
+
{
|
2706 |
+
"epoch": 0.9646464646464646,
|
2707 |
+
"grad_norm": 2.046875,
|
2708 |
+
"learning_rate": 7.446808510638298e-07,
|
2709 |
+
"loss": 0.5291,
|
2710 |
+
"step": 382
|
2711 |
+
},
|
2712 |
+
{
|
2713 |
+
"epoch": 0.9671717171717171,
|
2714 |
+
"grad_norm": 2.140625,
|
2715 |
+
"learning_rate": 6.914893617021278e-07,
|
2716 |
+
"loss": 0.6093,
|
2717 |
+
"step": 383
|
2718 |
+
},
|
2719 |
+
{
|
2720 |
+
"epoch": 0.9696969696969697,
|
2721 |
+
"grad_norm": 2.078125,
|
2722 |
+
"learning_rate": 6.382978723404255e-07,
|
2723 |
+
"loss": 0.4875,
|
2724 |
+
"step": 384
|
2725 |
+
},
|
2726 |
+
{
|
2727 |
+
"epoch": 0.9722222222222222,
|
2728 |
+
"grad_norm": 2.015625,
|
2729 |
+
"learning_rate": 5.851063829787235e-07,
|
2730 |
+
"loss": 0.5343,
|
2731 |
+
"step": 385
|
2732 |
+
},
|
2733 |
+
{
|
2734 |
+
"epoch": 0.9747474747474747,
|
2735 |
+
"grad_norm": 2.03125,
|
2736 |
+
"learning_rate": 5.319148936170213e-07,
|
2737 |
+
"loss": 0.5217,
|
2738 |
+
"step": 386
|
2739 |
+
},
|
2740 |
+
{
|
2741 |
+
"epoch": 0.9772727272727273,
|
2742 |
+
"grad_norm": 2.03125,
|
2743 |
+
"learning_rate": 4.787234042553192e-07,
|
2744 |
+
"loss": 0.5855,
|
2745 |
+
"step": 387
|
2746 |
+
},
|
2747 |
+
{
|
2748 |
+
"epoch": 0.9797979797979798,
|
2749 |
+
"grad_norm": 2.3125,
|
2750 |
+
"learning_rate": 4.2553191489361704e-07,
|
2751 |
+
"loss": 0.6195,
|
2752 |
+
"step": 388
|
2753 |
+
},
|
2754 |
+
{
|
2755 |
+
"epoch": 0.9823232323232324,
|
2756 |
+
"grad_norm": 2.15625,
|
2757 |
+
"learning_rate": 3.723404255319149e-07,
|
2758 |
+
"loss": 0.6591,
|
2759 |
+
"step": 389
|
2760 |
+
},
|
2761 |
+
{
|
2762 |
+
"epoch": 0.9848484848484849,
|
2763 |
+
"grad_norm": 2.0625,
|
2764 |
+
"learning_rate": 3.1914893617021275e-07,
|
2765 |
+
"loss": 0.6122,
|
2766 |
+
"step": 390
|
2767 |
+
},
|
2768 |
+
{
|
2769 |
+
"epoch": 0.9873737373737373,
|
2770 |
+
"grad_norm": 1.9921875,
|
2771 |
+
"learning_rate": 2.6595744680851066e-07,
|
2772 |
+
"loss": 0.5496,
|
2773 |
+
"step": 391
|
2774 |
+
},
|
2775 |
+
{
|
2776 |
+
"epoch": 0.98989898989899,
|
2777 |
+
"grad_norm": 2.203125,
|
2778 |
+
"learning_rate": 2.1276595744680852e-07,
|
2779 |
+
"loss": 0.6296,
|
2780 |
+
"step": 392
|
2781 |
+
},
|
2782 |
+
{
|
2783 |
+
"epoch": 0.98989898989899,
|
2784 |
+
"eval_loss": 0.491173654794693,
|
2785 |
+
"eval_model_preparation_time": 0.0001,
|
2786 |
+
"eval_runtime": 2.0524,
|
2787 |
+
"eval_samples_per_second": 51.646,
|
2788 |
+
"eval_steps_per_second": 6.821,
|
2789 |
+
"step": 392
|
2790 |
+
},
|
2791 |
+
{
|
2792 |
+
"epoch": 0.9924242424242424,
|
2793 |
+
"grad_norm": 2.5,
|
2794 |
+
"learning_rate": 1.5957446808510638e-07,
|
2795 |
+
"loss": 0.7494,
|
2796 |
+
"step": 393
|
2797 |
+
},
|
2798 |
+
{
|
2799 |
+
"epoch": 0.9949494949494949,
|
2800 |
+
"grad_norm": 2.15625,
|
2801 |
+
"learning_rate": 1.0638297872340426e-07,
|
2802 |
+
"loss": 0.5564,
|
2803 |
+
"step": 394
|
2804 |
+
}
|
2805 |
+
],
|
2806 |
+
"logging_steps": 1,
|
2807 |
+
"max_steps": 396,
|
2808 |
+
"num_input_tokens_seen": 0,
|
2809 |
+
"num_train_epochs": 1,
|
2810 |
+
"save_steps": 197,
|
2811 |
+
"stateful_callbacks": {
|
2812 |
+
"TrainerControl": {
|
2813 |
+
"args": {
|
2814 |
+
"should_epoch_stop": false,
|
2815 |
+
"should_evaluate": false,
|
2816 |
+
"should_log": false,
|
2817 |
+
"should_save": true,
|
2818 |
+
"should_training_stop": false
|
2819 |
+
},
|
2820 |
+
"attributes": {}
|
2821 |
+
}
|
2822 |
+
},
|
2823 |
+
"total_flos": 7.538335445050982e+16,
|
2824 |
+
"train_batch_size": 32,
|
2825 |
+
"trial_name": null,
|
2826 |
+
"trial_params": null
|
2827 |
+
}
|
checkpoint-394/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5c1544ce648e0cdfc3dfb0741a74a7986a7044108b2dd749fa1d4345bf7a7751
|
3 |
+
size 5496
|
checkpoint-396/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-396/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-396/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a9c8184a75dcded3d2142f944792ee358218f2ad0ee5f8729ac0366a2f25c6e9
|
3 |
+
size 2471645608
|
checkpoint-396/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d0385df4bf8f22f7c440b2cdcd3644ab695296eaec116ec43a85a8fd4b44a4a0
|
3 |
+
size 4943382114
|
checkpoint-396/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1d01e32af50305c2813c68459e798bc2742ba3a7efc592db91ae45cf013c0148
|
3 |
+
size 14244
|
checkpoint-396/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a2db77dee59aa32a586c56bfbb61f6af6744a96b2a51f34eebb26e56720b232a
|
3 |
+
size 1064
|
checkpoint-396/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-396/tokenizer.json
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:145cc0211ce61596383d8ae33aa07aa5555cb220e67064f0e36bf4beaffa025d
|
3 |
+
size 17210200
|
checkpoint-396/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-396/trainer_state.json
ADDED
@@ -0,0 +1,2841 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 1.0,
|
5 |
+
"eval_steps": 98,
|
6 |
+
"global_step": 396,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.0025252525252525255,
|
13 |
+
"grad_norm": 18.25,
|
14 |
+
"learning_rate": 1.0000000000000002e-06,
|
15 |
+
"loss": 1.9914,
|
16 |
+
"step": 1
|
17 |
+
},
|
18 |
+
{
|
19 |
+
"epoch": 0.005050505050505051,
|
20 |
+
"grad_norm": 20.375,
|
21 |
+
"learning_rate": 2.0000000000000003e-06,
|
22 |
+
"loss": 2.1829,
|
23 |
+
"step": 2
|
24 |
+
},
|
25 |
+
{
|
26 |
+
"epoch": 0.007575757575757576,
|
27 |
+
"grad_norm": 18.25,
|
28 |
+
"learning_rate": 3e-06,
|
29 |
+
"loss": 2.1929,
|
30 |
+
"step": 3
|
31 |
+
},
|
32 |
+
{
|
33 |
+
"epoch": 0.010101010101010102,
|
34 |
+
"grad_norm": 17.625,
|
35 |
+
"learning_rate": 4.000000000000001e-06,
|
36 |
+
"loss": 2.1297,
|
37 |
+
"step": 4
|
38 |
+
},
|
39 |
+
{
|
40 |
+
"epoch": 0.012626262626262626,
|
41 |
+
"grad_norm": 15.5625,
|
42 |
+
"learning_rate": 5e-06,
|
43 |
+
"loss": 2.0477,
|
44 |
+
"step": 5
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 0.015151515151515152,
|
48 |
+
"grad_norm": 12.9375,
|
49 |
+
"learning_rate": 6e-06,
|
50 |
+
"loss": 1.9193,
|
51 |
+
"step": 6
|
52 |
+
},
|
53 |
+
{
|
54 |
+
"epoch": 0.017676767676767676,
|
55 |
+
"grad_norm": 10.8125,
|
56 |
+
"learning_rate": 7e-06,
|
57 |
+
"loss": 1.8775,
|
58 |
+
"step": 7
|
59 |
+
},
|
60 |
+
{
|
61 |
+
"epoch": 0.020202020202020204,
|
62 |
+
"grad_norm": 10.625,
|
63 |
+
"learning_rate": 8.000000000000001e-06,
|
64 |
+
"loss": 1.9196,
|
65 |
+
"step": 8
|
66 |
+
},
|
67 |
+
{
|
68 |
+
"epoch": 0.022727272727272728,
|
69 |
+
"grad_norm": 11.8125,
|
70 |
+
"learning_rate": 9e-06,
|
71 |
+
"loss": 1.8893,
|
72 |
+
"step": 9
|
73 |
+
},
|
74 |
+
{
|
75 |
+
"epoch": 0.025252525252525252,
|
76 |
+
"grad_norm": 11.1875,
|
77 |
+
"learning_rate": 1e-05,
|
78 |
+
"loss": 1.7865,
|
79 |
+
"step": 10
|
80 |
+
},
|
81 |
+
{
|
82 |
+
"epoch": 0.027777777777777776,
|
83 |
+
"grad_norm": 9.5,
|
84 |
+
"learning_rate": 1.1000000000000001e-05,
|
85 |
+
"loss": 1.4009,
|
86 |
+
"step": 11
|
87 |
+
},
|
88 |
+
{
|
89 |
+
"epoch": 0.030303030303030304,
|
90 |
+
"grad_norm": 11.25,
|
91 |
+
"learning_rate": 1.2e-05,
|
92 |
+
"loss": 1.3557,
|
93 |
+
"step": 12
|
94 |
+
},
|
95 |
+
{
|
96 |
+
"epoch": 0.03282828282828283,
|
97 |
+
"grad_norm": 11.0,
|
98 |
+
"learning_rate": 1.3000000000000001e-05,
|
99 |
+
"loss": 1.3745,
|
100 |
+
"step": 13
|
101 |
+
},
|
102 |
+
{
|
103 |
+
"epoch": 0.03535353535353535,
|
104 |
+
"grad_norm": 14.5625,
|
105 |
+
"learning_rate": 1.4e-05,
|
106 |
+
"loss": 1.232,
|
107 |
+
"step": 14
|
108 |
+
},
|
109 |
+
{
|
110 |
+
"epoch": 0.03787878787878788,
|
111 |
+
"grad_norm": 7.5625,
|
112 |
+
"learning_rate": 1.5000000000000002e-05,
|
113 |
+
"loss": 1.0349,
|
114 |
+
"step": 15
|
115 |
+
},
|
116 |
+
{
|
117 |
+
"epoch": 0.04040404040404041,
|
118 |
+
"grad_norm": 6.21875,
|
119 |
+
"learning_rate": 1.6000000000000003e-05,
|
120 |
+
"loss": 1.1282,
|
121 |
+
"step": 16
|
122 |
+
},
|
123 |
+
{
|
124 |
+
"epoch": 0.04292929292929293,
|
125 |
+
"grad_norm": 4.90625,
|
126 |
+
"learning_rate": 1.7e-05,
|
127 |
+
"loss": 0.8976,
|
128 |
+
"step": 17
|
129 |
+
},
|
130 |
+
{
|
131 |
+
"epoch": 0.045454545454545456,
|
132 |
+
"grad_norm": 4.75,
|
133 |
+
"learning_rate": 1.8e-05,
|
134 |
+
"loss": 0.9172,
|
135 |
+
"step": 18
|
136 |
+
},
|
137 |
+
{
|
138 |
+
"epoch": 0.047979797979797977,
|
139 |
+
"grad_norm": 3.71875,
|
140 |
+
"learning_rate": 1.9e-05,
|
141 |
+
"loss": 0.8081,
|
142 |
+
"step": 19
|
143 |
+
},
|
144 |
+
{
|
145 |
+
"epoch": 0.050505050505050504,
|
146 |
+
"grad_norm": 6.65625,
|
147 |
+
"learning_rate": 2e-05,
|
148 |
+
"loss": 1.0714,
|
149 |
+
"step": 20
|
150 |
+
},
|
151 |
+
{
|
152 |
+
"epoch": 0.05303030303030303,
|
153 |
+
"grad_norm": 3.765625,
|
154 |
+
"learning_rate": 1.99468085106383e-05,
|
155 |
+
"loss": 0.8382,
|
156 |
+
"step": 21
|
157 |
+
},
|
158 |
+
{
|
159 |
+
"epoch": 0.05555555555555555,
|
160 |
+
"grad_norm": 3.515625,
|
161 |
+
"learning_rate": 1.9893617021276595e-05,
|
162 |
+
"loss": 0.8522,
|
163 |
+
"step": 22
|
164 |
+
},
|
165 |
+
{
|
166 |
+
"epoch": 0.05808080808080808,
|
167 |
+
"grad_norm": 3.453125,
|
168 |
+
"learning_rate": 1.9840425531914894e-05,
|
169 |
+
"loss": 0.8236,
|
170 |
+
"step": 23
|
171 |
+
},
|
172 |
+
{
|
173 |
+
"epoch": 0.06060606060606061,
|
174 |
+
"grad_norm": 3.75,
|
175 |
+
"learning_rate": 1.9787234042553193e-05,
|
176 |
+
"loss": 0.8437,
|
177 |
+
"step": 24
|
178 |
+
},
|
179 |
+
{
|
180 |
+
"epoch": 0.06313131313131314,
|
181 |
+
"grad_norm": 3.34375,
|
182 |
+
"learning_rate": 1.973404255319149e-05,
|
183 |
+
"loss": 0.8406,
|
184 |
+
"step": 25
|
185 |
+
},
|
186 |
+
{
|
187 |
+
"epoch": 0.06565656565656566,
|
188 |
+
"grad_norm": 3.84375,
|
189 |
+
"learning_rate": 1.968085106382979e-05,
|
190 |
+
"loss": 0.759,
|
191 |
+
"step": 26
|
192 |
+
},
|
193 |
+
{
|
194 |
+
"epoch": 0.06818181818181818,
|
195 |
+
"grad_norm": 3.546875,
|
196 |
+
"learning_rate": 1.962765957446809e-05,
|
197 |
+
"loss": 0.8671,
|
198 |
+
"step": 27
|
199 |
+
},
|
200 |
+
{
|
201 |
+
"epoch": 0.0707070707070707,
|
202 |
+
"grad_norm": 3.46875,
|
203 |
+
"learning_rate": 1.9574468085106384e-05,
|
204 |
+
"loss": 0.9208,
|
205 |
+
"step": 28
|
206 |
+
},
|
207 |
+
{
|
208 |
+
"epoch": 0.07323232323232323,
|
209 |
+
"grad_norm": 3.578125,
|
210 |
+
"learning_rate": 1.9521276595744682e-05,
|
211 |
+
"loss": 0.7483,
|
212 |
+
"step": 29
|
213 |
+
},
|
214 |
+
{
|
215 |
+
"epoch": 0.07575757575757576,
|
216 |
+
"grad_norm": 3.765625,
|
217 |
+
"learning_rate": 1.946808510638298e-05,
|
218 |
+
"loss": 0.9255,
|
219 |
+
"step": 30
|
220 |
+
},
|
221 |
+
{
|
222 |
+
"epoch": 0.07828282828282829,
|
223 |
+
"grad_norm": 3.421875,
|
224 |
+
"learning_rate": 1.9414893617021276e-05,
|
225 |
+
"loss": 0.7069,
|
226 |
+
"step": 31
|
227 |
+
},
|
228 |
+
{
|
229 |
+
"epoch": 0.08080808080808081,
|
230 |
+
"grad_norm": 3.375,
|
231 |
+
"learning_rate": 1.9361702127659575e-05,
|
232 |
+
"loss": 0.733,
|
233 |
+
"step": 32
|
234 |
+
},
|
235 |
+
{
|
236 |
+
"epoch": 0.08333333333333333,
|
237 |
+
"grad_norm": 3.421875,
|
238 |
+
"learning_rate": 1.9308510638297873e-05,
|
239 |
+
"loss": 0.7065,
|
240 |
+
"step": 33
|
241 |
+
},
|
242 |
+
{
|
243 |
+
"epoch": 0.08585858585858586,
|
244 |
+
"grad_norm": 3.40625,
|
245 |
+
"learning_rate": 1.9255319148936172e-05,
|
246 |
+
"loss": 0.8013,
|
247 |
+
"step": 34
|
248 |
+
},
|
249 |
+
{
|
250 |
+
"epoch": 0.08838383838383838,
|
251 |
+
"grad_norm": 2.9375,
|
252 |
+
"learning_rate": 1.920212765957447e-05,
|
253 |
+
"loss": 0.7475,
|
254 |
+
"step": 35
|
255 |
+
},
|
256 |
+
{
|
257 |
+
"epoch": 0.09090909090909091,
|
258 |
+
"grad_norm": 2.828125,
|
259 |
+
"learning_rate": 1.914893617021277e-05,
|
260 |
+
"loss": 0.827,
|
261 |
+
"step": 36
|
262 |
+
},
|
263 |
+
{
|
264 |
+
"epoch": 0.09343434343434344,
|
265 |
+
"grad_norm": 2.6875,
|
266 |
+
"learning_rate": 1.9095744680851064e-05,
|
267 |
+
"loss": 0.7498,
|
268 |
+
"step": 37
|
269 |
+
},
|
270 |
+
{
|
271 |
+
"epoch": 0.09595959595959595,
|
272 |
+
"grad_norm": 2.96875,
|
273 |
+
"learning_rate": 1.9042553191489363e-05,
|
274 |
+
"loss": 0.7054,
|
275 |
+
"step": 38
|
276 |
+
},
|
277 |
+
{
|
278 |
+
"epoch": 0.09848484848484848,
|
279 |
+
"grad_norm": 2.53125,
|
280 |
+
"learning_rate": 1.898936170212766e-05,
|
281 |
+
"loss": 0.697,
|
282 |
+
"step": 39
|
283 |
+
},
|
284 |
+
{
|
285 |
+
"epoch": 0.10101010101010101,
|
286 |
+
"grad_norm": 2.359375,
|
287 |
+
"learning_rate": 1.893617021276596e-05,
|
288 |
+
"loss": 0.6147,
|
289 |
+
"step": 40
|
290 |
+
},
|
291 |
+
{
|
292 |
+
"epoch": 0.10353535353535354,
|
293 |
+
"grad_norm": 2.390625,
|
294 |
+
"learning_rate": 1.888297872340426e-05,
|
295 |
+
"loss": 0.7174,
|
296 |
+
"step": 41
|
297 |
+
},
|
298 |
+
{
|
299 |
+
"epoch": 0.10606060606060606,
|
300 |
+
"grad_norm": 2.234375,
|
301 |
+
"learning_rate": 1.8829787234042557e-05,
|
302 |
+
"loss": 0.6435,
|
303 |
+
"step": 42
|
304 |
+
},
|
305 |
+
{
|
306 |
+
"epoch": 0.10858585858585859,
|
307 |
+
"grad_norm": 2.109375,
|
308 |
+
"learning_rate": 1.8776595744680852e-05,
|
309 |
+
"loss": 0.6665,
|
310 |
+
"step": 43
|
311 |
+
},
|
312 |
+
{
|
313 |
+
"epoch": 0.1111111111111111,
|
314 |
+
"grad_norm": 2.296875,
|
315 |
+
"learning_rate": 1.872340425531915e-05,
|
316 |
+
"loss": 0.6512,
|
317 |
+
"step": 44
|
318 |
+
},
|
319 |
+
{
|
320 |
+
"epoch": 0.11363636363636363,
|
321 |
+
"grad_norm": 2.15625,
|
322 |
+
"learning_rate": 1.8670212765957446e-05,
|
323 |
+
"loss": 0.5746,
|
324 |
+
"step": 45
|
325 |
+
},
|
326 |
+
{
|
327 |
+
"epoch": 0.11616161616161616,
|
328 |
+
"grad_norm": 2.15625,
|
329 |
+
"learning_rate": 1.8617021276595745e-05,
|
330 |
+
"loss": 0.6253,
|
331 |
+
"step": 46
|
332 |
+
},
|
333 |
+
{
|
334 |
+
"epoch": 0.11868686868686869,
|
335 |
+
"grad_norm": 1.9765625,
|
336 |
+
"learning_rate": 1.8563829787234043e-05,
|
337 |
+
"loss": 0.5925,
|
338 |
+
"step": 47
|
339 |
+
},
|
340 |
+
{
|
341 |
+
"epoch": 0.12121212121212122,
|
342 |
+
"grad_norm": 2.234375,
|
343 |
+
"learning_rate": 1.8510638297872342e-05,
|
344 |
+
"loss": 0.6516,
|
345 |
+
"step": 48
|
346 |
+
},
|
347 |
+
{
|
348 |
+
"epoch": 0.12373737373737374,
|
349 |
+
"grad_norm": 2.203125,
|
350 |
+
"learning_rate": 1.845744680851064e-05,
|
351 |
+
"loss": 0.6909,
|
352 |
+
"step": 49
|
353 |
+
},
|
354 |
+
{
|
355 |
+
"epoch": 0.12626262626262627,
|
356 |
+
"grad_norm": 2.375,
|
357 |
+
"learning_rate": 1.840425531914894e-05,
|
358 |
+
"loss": 0.7091,
|
359 |
+
"step": 50
|
360 |
+
},
|
361 |
+
{
|
362 |
+
"epoch": 0.12878787878787878,
|
363 |
+
"grad_norm": 1.9140625,
|
364 |
+
"learning_rate": 1.8351063829787234e-05,
|
365 |
+
"loss": 0.525,
|
366 |
+
"step": 51
|
367 |
+
},
|
368 |
+
{
|
369 |
+
"epoch": 0.13131313131313133,
|
370 |
+
"grad_norm": 2.0,
|
371 |
+
"learning_rate": 1.8297872340425533e-05,
|
372 |
+
"loss": 0.5949,
|
373 |
+
"step": 52
|
374 |
+
},
|
375 |
+
{
|
376 |
+
"epoch": 0.13383838383838384,
|
377 |
+
"grad_norm": 2.34375,
|
378 |
+
"learning_rate": 1.824468085106383e-05,
|
379 |
+
"loss": 0.7348,
|
380 |
+
"step": 53
|
381 |
+
},
|
382 |
+
{
|
383 |
+
"epoch": 0.13636363636363635,
|
384 |
+
"grad_norm": 2.1875,
|
385 |
+
"learning_rate": 1.8191489361702127e-05,
|
386 |
+
"loss": 0.562,
|
387 |
+
"step": 54
|
388 |
+
},
|
389 |
+
{
|
390 |
+
"epoch": 0.1388888888888889,
|
391 |
+
"grad_norm": 2.28125,
|
392 |
+
"learning_rate": 1.8138297872340425e-05,
|
393 |
+
"loss": 0.72,
|
394 |
+
"step": 55
|
395 |
+
},
|
396 |
+
{
|
397 |
+
"epoch": 0.1414141414141414,
|
398 |
+
"grad_norm": 2.1875,
|
399 |
+
"learning_rate": 1.8085106382978724e-05,
|
400 |
+
"loss": 0.6685,
|
401 |
+
"step": 56
|
402 |
+
},
|
403 |
+
{
|
404 |
+
"epoch": 0.14393939393939395,
|
405 |
+
"grad_norm": 2.109375,
|
406 |
+
"learning_rate": 1.8031914893617023e-05,
|
407 |
+
"loss": 0.605,
|
408 |
+
"step": 57
|
409 |
+
},
|
410 |
+
{
|
411 |
+
"epoch": 0.14646464646464646,
|
412 |
+
"grad_norm": 2.34375,
|
413 |
+
"learning_rate": 1.797872340425532e-05,
|
414 |
+
"loss": 0.6761,
|
415 |
+
"step": 58
|
416 |
+
},
|
417 |
+
{
|
418 |
+
"epoch": 0.14898989898989898,
|
419 |
+
"grad_norm": 2.328125,
|
420 |
+
"learning_rate": 1.792553191489362e-05,
|
421 |
+
"loss": 0.6702,
|
422 |
+
"step": 59
|
423 |
+
},
|
424 |
+
{
|
425 |
+
"epoch": 0.15151515151515152,
|
426 |
+
"grad_norm": 2.34375,
|
427 |
+
"learning_rate": 1.7872340425531915e-05,
|
428 |
+
"loss": 0.691,
|
429 |
+
"step": 60
|
430 |
+
},
|
431 |
+
{
|
432 |
+
"epoch": 0.15404040404040403,
|
433 |
+
"grad_norm": 2.25,
|
434 |
+
"learning_rate": 1.7819148936170214e-05,
|
435 |
+
"loss": 0.6373,
|
436 |
+
"step": 61
|
437 |
+
},
|
438 |
+
{
|
439 |
+
"epoch": 0.15656565656565657,
|
440 |
+
"grad_norm": 2.203125,
|
441 |
+
"learning_rate": 1.7765957446808512e-05,
|
442 |
+
"loss": 0.5704,
|
443 |
+
"step": 62
|
444 |
+
},
|
445 |
+
{
|
446 |
+
"epoch": 0.1590909090909091,
|
447 |
+
"grad_norm": 2.28125,
|
448 |
+
"learning_rate": 1.7712765957446807e-05,
|
449 |
+
"loss": 0.6963,
|
450 |
+
"step": 63
|
451 |
+
},
|
452 |
+
{
|
453 |
+
"epoch": 0.16161616161616163,
|
454 |
+
"grad_norm": 2.359375,
|
455 |
+
"learning_rate": 1.765957446808511e-05,
|
456 |
+
"loss": 0.6108,
|
457 |
+
"step": 64
|
458 |
+
},
|
459 |
+
{
|
460 |
+
"epoch": 0.16414141414141414,
|
461 |
+
"grad_norm": 2.171875,
|
462 |
+
"learning_rate": 1.7606382978723408e-05,
|
463 |
+
"loss": 0.6329,
|
464 |
+
"step": 65
|
465 |
+
},
|
466 |
+
{
|
467 |
+
"epoch": 0.16666666666666666,
|
468 |
+
"grad_norm": 2.375,
|
469 |
+
"learning_rate": 1.7553191489361703e-05,
|
470 |
+
"loss": 0.6747,
|
471 |
+
"step": 66
|
472 |
+
},
|
473 |
+
{
|
474 |
+
"epoch": 0.1691919191919192,
|
475 |
+
"grad_norm": 2.25,
|
476 |
+
"learning_rate": 1.7500000000000002e-05,
|
477 |
+
"loss": 0.6375,
|
478 |
+
"step": 67
|
479 |
+
},
|
480 |
+
{
|
481 |
+
"epoch": 0.1717171717171717,
|
482 |
+
"grad_norm": 2.0625,
|
483 |
+
"learning_rate": 1.74468085106383e-05,
|
484 |
+
"loss": 0.6412,
|
485 |
+
"step": 68
|
486 |
+
},
|
487 |
+
{
|
488 |
+
"epoch": 0.17424242424242425,
|
489 |
+
"grad_norm": 2.40625,
|
490 |
+
"learning_rate": 1.7393617021276596e-05,
|
491 |
+
"loss": 0.8454,
|
492 |
+
"step": 69
|
493 |
+
},
|
494 |
+
{
|
495 |
+
"epoch": 0.17676767676767677,
|
496 |
+
"grad_norm": 2.34375,
|
497 |
+
"learning_rate": 1.7340425531914894e-05,
|
498 |
+
"loss": 0.6781,
|
499 |
+
"step": 70
|
500 |
+
},
|
501 |
+
{
|
502 |
+
"epoch": 0.17929292929292928,
|
503 |
+
"grad_norm": 2.234375,
|
504 |
+
"learning_rate": 1.7287234042553193e-05,
|
505 |
+
"loss": 0.6895,
|
506 |
+
"step": 71
|
507 |
+
},
|
508 |
+
{
|
509 |
+
"epoch": 0.18181818181818182,
|
510 |
+
"grad_norm": 2.328125,
|
511 |
+
"learning_rate": 1.723404255319149e-05,
|
512 |
+
"loss": 0.6515,
|
513 |
+
"step": 72
|
514 |
+
},
|
515 |
+
{
|
516 |
+
"epoch": 0.18434343434343434,
|
517 |
+
"grad_norm": 2.046875,
|
518 |
+
"learning_rate": 1.718085106382979e-05,
|
519 |
+
"loss": 0.6032,
|
520 |
+
"step": 73
|
521 |
+
},
|
522 |
+
{
|
523 |
+
"epoch": 0.18686868686868688,
|
524 |
+
"grad_norm": 2.265625,
|
525 |
+
"learning_rate": 1.712765957446809e-05,
|
526 |
+
"loss": 0.6554,
|
527 |
+
"step": 74
|
528 |
+
},
|
529 |
+
{
|
530 |
+
"epoch": 0.1893939393939394,
|
531 |
+
"grad_norm": 2.140625,
|
532 |
+
"learning_rate": 1.7074468085106384e-05,
|
533 |
+
"loss": 0.6295,
|
534 |
+
"step": 75
|
535 |
+
},
|
536 |
+
{
|
537 |
+
"epoch": 0.1919191919191919,
|
538 |
+
"grad_norm": 2.34375,
|
539 |
+
"learning_rate": 1.7021276595744682e-05,
|
540 |
+
"loss": 0.6321,
|
541 |
+
"step": 76
|
542 |
+
},
|
543 |
+
{
|
544 |
+
"epoch": 0.19444444444444445,
|
545 |
+
"grad_norm": 2.09375,
|
546 |
+
"learning_rate": 1.696808510638298e-05,
|
547 |
+
"loss": 0.6457,
|
548 |
+
"step": 77
|
549 |
+
},
|
550 |
+
{
|
551 |
+
"epoch": 0.19696969696969696,
|
552 |
+
"grad_norm": 2.03125,
|
553 |
+
"learning_rate": 1.6914893617021276e-05,
|
554 |
+
"loss": 0.559,
|
555 |
+
"step": 78
|
556 |
+
},
|
557 |
+
{
|
558 |
+
"epoch": 0.1994949494949495,
|
559 |
+
"grad_norm": 2.21875,
|
560 |
+
"learning_rate": 1.6861702127659575e-05,
|
561 |
+
"loss": 0.766,
|
562 |
+
"step": 79
|
563 |
+
},
|
564 |
+
{
|
565 |
+
"epoch": 0.20202020202020202,
|
566 |
+
"grad_norm": 2.75,
|
567 |
+
"learning_rate": 1.6808510638297873e-05,
|
568 |
+
"loss": 0.8241,
|
569 |
+
"step": 80
|
570 |
+
},
|
571 |
+
{
|
572 |
+
"epoch": 0.20454545454545456,
|
573 |
+
"grad_norm": 2.3125,
|
574 |
+
"learning_rate": 1.6755319148936172e-05,
|
575 |
+
"loss": 0.6543,
|
576 |
+
"step": 81
|
577 |
+
},
|
578 |
+
{
|
579 |
+
"epoch": 0.20707070707070707,
|
580 |
+
"grad_norm": 2.34375,
|
581 |
+
"learning_rate": 1.670212765957447e-05,
|
582 |
+
"loss": 0.6471,
|
583 |
+
"step": 82
|
584 |
+
},
|
585 |
+
{
|
586 |
+
"epoch": 0.20959595959595959,
|
587 |
+
"grad_norm": 2.375,
|
588 |
+
"learning_rate": 1.664893617021277e-05,
|
589 |
+
"loss": 0.678,
|
590 |
+
"step": 83
|
591 |
+
},
|
592 |
+
{
|
593 |
+
"epoch": 0.21212121212121213,
|
594 |
+
"grad_norm": 2.140625,
|
595 |
+
"learning_rate": 1.6595744680851064e-05,
|
596 |
+
"loss": 0.6333,
|
597 |
+
"step": 84
|
598 |
+
},
|
599 |
+
{
|
600 |
+
"epoch": 0.21464646464646464,
|
601 |
+
"grad_norm": 2.109375,
|
602 |
+
"learning_rate": 1.6542553191489363e-05,
|
603 |
+
"loss": 0.6513,
|
604 |
+
"step": 85
|
605 |
+
},
|
606 |
+
{
|
607 |
+
"epoch": 0.21717171717171718,
|
608 |
+
"grad_norm": 2.109375,
|
609 |
+
"learning_rate": 1.648936170212766e-05,
|
610 |
+
"loss": 0.6419,
|
611 |
+
"step": 86
|
612 |
+
},
|
613 |
+
{
|
614 |
+
"epoch": 0.2196969696969697,
|
615 |
+
"grad_norm": 2.09375,
|
616 |
+
"learning_rate": 1.6436170212765957e-05,
|
617 |
+
"loss": 0.5929,
|
618 |
+
"step": 87
|
619 |
+
},
|
620 |
+
{
|
621 |
+
"epoch": 0.2222222222222222,
|
622 |
+
"grad_norm": 2.15625,
|
623 |
+
"learning_rate": 1.6382978723404255e-05,
|
624 |
+
"loss": 0.5898,
|
625 |
+
"step": 88
|
626 |
+
},
|
627 |
+
{
|
628 |
+
"epoch": 0.22474747474747475,
|
629 |
+
"grad_norm": 2.5625,
|
630 |
+
"learning_rate": 1.6329787234042554e-05,
|
631 |
+
"loss": 0.7497,
|
632 |
+
"step": 89
|
633 |
+
},
|
634 |
+
{
|
635 |
+
"epoch": 0.22727272727272727,
|
636 |
+
"grad_norm": 2.203125,
|
637 |
+
"learning_rate": 1.6276595744680853e-05,
|
638 |
+
"loss": 0.7005,
|
639 |
+
"step": 90
|
640 |
+
},
|
641 |
+
{
|
642 |
+
"epoch": 0.2297979797979798,
|
643 |
+
"grad_norm": 2.28125,
|
644 |
+
"learning_rate": 1.622340425531915e-05,
|
645 |
+
"loss": 0.7901,
|
646 |
+
"step": 91
|
647 |
+
},
|
648 |
+
{
|
649 |
+
"epoch": 0.23232323232323232,
|
650 |
+
"grad_norm": 1.9921875,
|
651 |
+
"learning_rate": 1.6170212765957446e-05,
|
652 |
+
"loss": 0.5286,
|
653 |
+
"step": 92
|
654 |
+
},
|
655 |
+
{
|
656 |
+
"epoch": 0.23484848484848486,
|
657 |
+
"grad_norm": 2.46875,
|
658 |
+
"learning_rate": 1.6117021276595745e-05,
|
659 |
+
"loss": 0.655,
|
660 |
+
"step": 93
|
661 |
+
},
|
662 |
+
{
|
663 |
+
"epoch": 0.23737373737373738,
|
664 |
+
"grad_norm": 2.21875,
|
665 |
+
"learning_rate": 1.6063829787234044e-05,
|
666 |
+
"loss": 0.7207,
|
667 |
+
"step": 94
|
668 |
+
},
|
669 |
+
{
|
670 |
+
"epoch": 0.2398989898989899,
|
671 |
+
"grad_norm": 2.359375,
|
672 |
+
"learning_rate": 1.6010638297872342e-05,
|
673 |
+
"loss": 0.7205,
|
674 |
+
"step": 95
|
675 |
+
},
|
676 |
+
{
|
677 |
+
"epoch": 0.24242424242424243,
|
678 |
+
"grad_norm": 2.890625,
|
679 |
+
"learning_rate": 1.595744680851064e-05,
|
680 |
+
"loss": 0.8159,
|
681 |
+
"step": 96
|
682 |
+
},
|
683 |
+
{
|
684 |
+
"epoch": 0.24494949494949494,
|
685 |
+
"grad_norm": 2.125,
|
686 |
+
"learning_rate": 1.590425531914894e-05,
|
687 |
+
"loss": 0.563,
|
688 |
+
"step": 97
|
689 |
+
},
|
690 |
+
{
|
691 |
+
"epoch": 0.2474747474747475,
|
692 |
+
"grad_norm": 2.03125,
|
693 |
+
"learning_rate": 1.5851063829787235e-05,
|
694 |
+
"loss": 0.5928,
|
695 |
+
"step": 98
|
696 |
+
},
|
697 |
+
{
|
698 |
+
"epoch": 0.2474747474747475,
|
699 |
+
"eval_loss": 0.5301359295845032,
|
700 |
+
"eval_model_preparation_time": 0.0001,
|
701 |
+
"eval_runtime": 2.0495,
|
702 |
+
"eval_samples_per_second": 51.721,
|
703 |
+
"eval_steps_per_second": 6.831,
|
704 |
+
"step": 98
|
705 |
+
},
|
706 |
+
{
|
707 |
+
"epoch": 0.25,
|
708 |
+
"grad_norm": 2.296875,
|
709 |
+
"learning_rate": 1.5797872340425533e-05,
|
710 |
+
"loss": 0.6478,
|
711 |
+
"step": 99
|
712 |
+
},
|
713 |
+
{
|
714 |
+
"epoch": 0.25252525252525254,
|
715 |
+
"grad_norm": 2.078125,
|
716 |
+
"learning_rate": 1.5744680851063832e-05,
|
717 |
+
"loss": 0.6663,
|
718 |
+
"step": 100
|
719 |
+
},
|
720 |
+
{
|
721 |
+
"epoch": 0.255050505050505,
|
722 |
+
"grad_norm": 2.140625,
|
723 |
+
"learning_rate": 1.5691489361702127e-05,
|
724 |
+
"loss": 0.6241,
|
725 |
+
"step": 101
|
726 |
+
},
|
727 |
+
{
|
728 |
+
"epoch": 0.25757575757575757,
|
729 |
+
"grad_norm": 2.4375,
|
730 |
+
"learning_rate": 1.5638297872340426e-05,
|
731 |
+
"loss": 0.7131,
|
732 |
+
"step": 102
|
733 |
+
},
|
734 |
+
{
|
735 |
+
"epoch": 0.2601010101010101,
|
736 |
+
"grad_norm": 2.15625,
|
737 |
+
"learning_rate": 1.5585106382978724e-05,
|
738 |
+
"loss": 0.7139,
|
739 |
+
"step": 103
|
740 |
+
},
|
741 |
+
{
|
742 |
+
"epoch": 0.26262626262626265,
|
743 |
+
"grad_norm": 2.078125,
|
744 |
+
"learning_rate": 1.5531914893617023e-05,
|
745 |
+
"loss": 0.5503,
|
746 |
+
"step": 104
|
747 |
+
},
|
748 |
+
{
|
749 |
+
"epoch": 0.26515151515151514,
|
750 |
+
"grad_norm": 2.0625,
|
751 |
+
"learning_rate": 1.547872340425532e-05,
|
752 |
+
"loss": 0.5837,
|
753 |
+
"step": 105
|
754 |
+
},
|
755 |
+
{
|
756 |
+
"epoch": 0.2676767676767677,
|
757 |
+
"grad_norm": 1.9453125,
|
758 |
+
"learning_rate": 1.542553191489362e-05,
|
759 |
+
"loss": 0.571,
|
760 |
+
"step": 106
|
761 |
+
},
|
762 |
+
{
|
763 |
+
"epoch": 0.2702020202020202,
|
764 |
+
"grad_norm": 1.9375,
|
765 |
+
"learning_rate": 1.5372340425531915e-05,
|
766 |
+
"loss": 0.4949,
|
767 |
+
"step": 107
|
768 |
+
},
|
769 |
+
{
|
770 |
+
"epoch": 0.2727272727272727,
|
771 |
+
"grad_norm": 2.171875,
|
772 |
+
"learning_rate": 1.5319148936170214e-05,
|
773 |
+
"loss": 0.6769,
|
774 |
+
"step": 108
|
775 |
+
},
|
776 |
+
{
|
777 |
+
"epoch": 0.27525252525252525,
|
778 |
+
"grad_norm": 1.8828125,
|
779 |
+
"learning_rate": 1.5265957446808512e-05,
|
780 |
+
"loss": 0.4772,
|
781 |
+
"step": 109
|
782 |
+
},
|
783 |
+
{
|
784 |
+
"epoch": 0.2777777777777778,
|
785 |
+
"grad_norm": 2.0625,
|
786 |
+
"learning_rate": 1.521276595744681e-05,
|
787 |
+
"loss": 0.6177,
|
788 |
+
"step": 110
|
789 |
+
},
|
790 |
+
{
|
791 |
+
"epoch": 0.2803030303030303,
|
792 |
+
"grad_norm": 2.046875,
|
793 |
+
"learning_rate": 1.5159574468085108e-05,
|
794 |
+
"loss": 0.6063,
|
795 |
+
"step": 111
|
796 |
+
},
|
797 |
+
{
|
798 |
+
"epoch": 0.2828282828282828,
|
799 |
+
"grad_norm": 2.21875,
|
800 |
+
"learning_rate": 1.5106382978723407e-05,
|
801 |
+
"loss": 0.5975,
|
802 |
+
"step": 112
|
803 |
+
},
|
804 |
+
{
|
805 |
+
"epoch": 0.28535353535353536,
|
806 |
+
"grad_norm": 2.03125,
|
807 |
+
"learning_rate": 1.5053191489361702e-05,
|
808 |
+
"loss": 0.5549,
|
809 |
+
"step": 113
|
810 |
+
},
|
811 |
+
{
|
812 |
+
"epoch": 0.2878787878787879,
|
813 |
+
"grad_norm": 2.203125,
|
814 |
+
"learning_rate": 1.5000000000000002e-05,
|
815 |
+
"loss": 0.6549,
|
816 |
+
"step": 114
|
817 |
+
},
|
818 |
+
{
|
819 |
+
"epoch": 0.2904040404040404,
|
820 |
+
"grad_norm": 1.9375,
|
821 |
+
"learning_rate": 1.49468085106383e-05,
|
822 |
+
"loss": 0.5356,
|
823 |
+
"step": 115
|
824 |
+
},
|
825 |
+
{
|
826 |
+
"epoch": 0.29292929292929293,
|
827 |
+
"grad_norm": 2.140625,
|
828 |
+
"learning_rate": 1.4893617021276596e-05,
|
829 |
+
"loss": 0.6594,
|
830 |
+
"step": 116
|
831 |
+
},
|
832 |
+
{
|
833 |
+
"epoch": 0.29545454545454547,
|
834 |
+
"grad_norm": 2.25,
|
835 |
+
"learning_rate": 1.4840425531914894e-05,
|
836 |
+
"loss": 0.6194,
|
837 |
+
"step": 117
|
838 |
+
},
|
839 |
+
{
|
840 |
+
"epoch": 0.29797979797979796,
|
841 |
+
"grad_norm": 2.078125,
|
842 |
+
"learning_rate": 1.4787234042553193e-05,
|
843 |
+
"loss": 0.5987,
|
844 |
+
"step": 118
|
845 |
+
},
|
846 |
+
{
|
847 |
+
"epoch": 0.3005050505050505,
|
848 |
+
"grad_norm": 2.0,
|
849 |
+
"learning_rate": 1.473404255319149e-05,
|
850 |
+
"loss": 0.5104,
|
851 |
+
"step": 119
|
852 |
+
},
|
853 |
+
{
|
854 |
+
"epoch": 0.30303030303030304,
|
855 |
+
"grad_norm": 2.015625,
|
856 |
+
"learning_rate": 1.4680851063829789e-05,
|
857 |
+
"loss": 0.5476,
|
858 |
+
"step": 120
|
859 |
+
},
|
860 |
+
{
|
861 |
+
"epoch": 0.3055555555555556,
|
862 |
+
"grad_norm": 2.296875,
|
863 |
+
"learning_rate": 1.4627659574468087e-05,
|
864 |
+
"loss": 0.6195,
|
865 |
+
"step": 121
|
866 |
+
},
|
867 |
+
{
|
868 |
+
"epoch": 0.30808080808080807,
|
869 |
+
"grad_norm": 2.28125,
|
870 |
+
"learning_rate": 1.4574468085106384e-05,
|
871 |
+
"loss": 0.6162,
|
872 |
+
"step": 122
|
873 |
+
},
|
874 |
+
{
|
875 |
+
"epoch": 0.3106060606060606,
|
876 |
+
"grad_norm": 1.8359375,
|
877 |
+
"learning_rate": 1.4521276595744683e-05,
|
878 |
+
"loss": 0.5231,
|
879 |
+
"step": 123
|
880 |
+
},
|
881 |
+
{
|
882 |
+
"epoch": 0.31313131313131315,
|
883 |
+
"grad_norm": 2.03125,
|
884 |
+
"learning_rate": 1.4468085106382981e-05,
|
885 |
+
"loss": 0.5958,
|
886 |
+
"step": 124
|
887 |
+
},
|
888 |
+
{
|
889 |
+
"epoch": 0.31565656565656564,
|
890 |
+
"grad_norm": 2.109375,
|
891 |
+
"learning_rate": 1.4414893617021276e-05,
|
892 |
+
"loss": 0.5808,
|
893 |
+
"step": 125
|
894 |
+
},
|
895 |
+
{
|
896 |
+
"epoch": 0.3181818181818182,
|
897 |
+
"grad_norm": 2.3125,
|
898 |
+
"learning_rate": 1.4361702127659575e-05,
|
899 |
+
"loss": 0.6299,
|
900 |
+
"step": 126
|
901 |
+
},
|
902 |
+
{
|
903 |
+
"epoch": 0.3207070707070707,
|
904 |
+
"grad_norm": 2.3125,
|
905 |
+
"learning_rate": 1.4308510638297874e-05,
|
906 |
+
"loss": 0.6375,
|
907 |
+
"step": 127
|
908 |
+
},
|
909 |
+
{
|
910 |
+
"epoch": 0.32323232323232326,
|
911 |
+
"grad_norm": 2.140625,
|
912 |
+
"learning_rate": 1.425531914893617e-05,
|
913 |
+
"loss": 0.6465,
|
914 |
+
"step": 128
|
915 |
+
},
|
916 |
+
{
|
917 |
+
"epoch": 0.32575757575757575,
|
918 |
+
"grad_norm": 2.125,
|
919 |
+
"learning_rate": 1.420212765957447e-05,
|
920 |
+
"loss": 0.6539,
|
921 |
+
"step": 129
|
922 |
+
},
|
923 |
+
{
|
924 |
+
"epoch": 0.3282828282828283,
|
925 |
+
"grad_norm": 1.8671875,
|
926 |
+
"learning_rate": 1.4148936170212768e-05,
|
927 |
+
"loss": 0.5253,
|
928 |
+
"step": 130
|
929 |
+
},
|
930 |
+
{
|
931 |
+
"epoch": 0.33080808080808083,
|
932 |
+
"grad_norm": 2.203125,
|
933 |
+
"learning_rate": 1.4095744680851065e-05,
|
934 |
+
"loss": 0.6292,
|
935 |
+
"step": 131
|
936 |
+
},
|
937 |
+
{
|
938 |
+
"epoch": 0.3333333333333333,
|
939 |
+
"grad_norm": 2.109375,
|
940 |
+
"learning_rate": 1.4042553191489363e-05,
|
941 |
+
"loss": 0.578,
|
942 |
+
"step": 132
|
943 |
+
},
|
944 |
+
{
|
945 |
+
"epoch": 0.33585858585858586,
|
946 |
+
"grad_norm": 2.09375,
|
947 |
+
"learning_rate": 1.3989361702127662e-05,
|
948 |
+
"loss": 0.5226,
|
949 |
+
"step": 133
|
950 |
+
},
|
951 |
+
{
|
952 |
+
"epoch": 0.3383838383838384,
|
953 |
+
"grad_norm": 2.171875,
|
954 |
+
"learning_rate": 1.3936170212765959e-05,
|
955 |
+
"loss": 0.6743,
|
956 |
+
"step": 134
|
957 |
+
},
|
958 |
+
{
|
959 |
+
"epoch": 0.3409090909090909,
|
960 |
+
"grad_norm": 2.046875,
|
961 |
+
"learning_rate": 1.3882978723404257e-05,
|
962 |
+
"loss": 0.501,
|
963 |
+
"step": 135
|
964 |
+
},
|
965 |
+
{
|
966 |
+
"epoch": 0.3434343434343434,
|
967 |
+
"grad_norm": 2.15625,
|
968 |
+
"learning_rate": 1.3829787234042556e-05,
|
969 |
+
"loss": 0.6333,
|
970 |
+
"step": 136
|
971 |
+
},
|
972 |
+
{
|
973 |
+
"epoch": 0.34595959595959597,
|
974 |
+
"grad_norm": 1.7890625,
|
975 |
+
"learning_rate": 1.3776595744680851e-05,
|
976 |
+
"loss": 0.4695,
|
977 |
+
"step": 137
|
978 |
+
},
|
979 |
+
{
|
980 |
+
"epoch": 0.3484848484848485,
|
981 |
+
"grad_norm": 2.28125,
|
982 |
+
"learning_rate": 1.372340425531915e-05,
|
983 |
+
"loss": 0.6444,
|
984 |
+
"step": 138
|
985 |
+
},
|
986 |
+
{
|
987 |
+
"epoch": 0.351010101010101,
|
988 |
+
"grad_norm": 2.21875,
|
989 |
+
"learning_rate": 1.3670212765957447e-05,
|
990 |
+
"loss": 0.6019,
|
991 |
+
"step": 139
|
992 |
+
},
|
993 |
+
{
|
994 |
+
"epoch": 0.35353535353535354,
|
995 |
+
"grad_norm": 1.90625,
|
996 |
+
"learning_rate": 1.3617021276595745e-05,
|
997 |
+
"loss": 0.4815,
|
998 |
+
"step": 140
|
999 |
+
},
|
1000 |
+
{
|
1001 |
+
"epoch": 0.3560606060606061,
|
1002 |
+
"grad_norm": 2.34375,
|
1003 |
+
"learning_rate": 1.3563829787234044e-05,
|
1004 |
+
"loss": 0.6316,
|
1005 |
+
"step": 141
|
1006 |
+
},
|
1007 |
+
{
|
1008 |
+
"epoch": 0.35858585858585856,
|
1009 |
+
"grad_norm": 2.34375,
|
1010 |
+
"learning_rate": 1.351063829787234e-05,
|
1011 |
+
"loss": 0.8299,
|
1012 |
+
"step": 142
|
1013 |
+
},
|
1014 |
+
{
|
1015 |
+
"epoch": 0.3611111111111111,
|
1016 |
+
"grad_norm": 1.8984375,
|
1017 |
+
"learning_rate": 1.345744680851064e-05,
|
1018 |
+
"loss": 0.543,
|
1019 |
+
"step": 143
|
1020 |
+
},
|
1021 |
+
{
|
1022 |
+
"epoch": 0.36363636363636365,
|
1023 |
+
"grad_norm": 2.234375,
|
1024 |
+
"learning_rate": 1.3404255319148938e-05,
|
1025 |
+
"loss": 0.6093,
|
1026 |
+
"step": 144
|
1027 |
+
},
|
1028 |
+
{
|
1029 |
+
"epoch": 0.3661616161616162,
|
1030 |
+
"grad_norm": 2.03125,
|
1031 |
+
"learning_rate": 1.3351063829787235e-05,
|
1032 |
+
"loss": 0.5501,
|
1033 |
+
"step": 145
|
1034 |
+
},
|
1035 |
+
{
|
1036 |
+
"epoch": 0.3686868686868687,
|
1037 |
+
"grad_norm": 2.09375,
|
1038 |
+
"learning_rate": 1.3297872340425533e-05,
|
1039 |
+
"loss": 0.5388,
|
1040 |
+
"step": 146
|
1041 |
+
},
|
1042 |
+
{
|
1043 |
+
"epoch": 0.3712121212121212,
|
1044 |
+
"grad_norm": 1.9453125,
|
1045 |
+
"learning_rate": 1.3244680851063832e-05,
|
1046 |
+
"loss": 0.5364,
|
1047 |
+
"step": 147
|
1048 |
+
},
|
1049 |
+
{
|
1050 |
+
"epoch": 0.37373737373737376,
|
1051 |
+
"grad_norm": 2.328125,
|
1052 |
+
"learning_rate": 1.3191489361702127e-05,
|
1053 |
+
"loss": 0.6471,
|
1054 |
+
"step": 148
|
1055 |
+
},
|
1056 |
+
{
|
1057 |
+
"epoch": 0.37626262626262624,
|
1058 |
+
"grad_norm": 1.9140625,
|
1059 |
+
"learning_rate": 1.3138297872340426e-05,
|
1060 |
+
"loss": 0.4996,
|
1061 |
+
"step": 149
|
1062 |
+
},
|
1063 |
+
{
|
1064 |
+
"epoch": 0.3787878787878788,
|
1065 |
+
"grad_norm": 2.15625,
|
1066 |
+
"learning_rate": 1.3085106382978724e-05,
|
1067 |
+
"loss": 0.6603,
|
1068 |
+
"step": 150
|
1069 |
+
},
|
1070 |
+
{
|
1071 |
+
"epoch": 0.3813131313131313,
|
1072 |
+
"grad_norm": 2.140625,
|
1073 |
+
"learning_rate": 1.3031914893617021e-05,
|
1074 |
+
"loss": 0.5177,
|
1075 |
+
"step": 151
|
1076 |
+
},
|
1077 |
+
{
|
1078 |
+
"epoch": 0.3838383838383838,
|
1079 |
+
"grad_norm": 2.3125,
|
1080 |
+
"learning_rate": 1.297872340425532e-05,
|
1081 |
+
"loss": 0.6503,
|
1082 |
+
"step": 152
|
1083 |
+
},
|
1084 |
+
{
|
1085 |
+
"epoch": 0.38636363636363635,
|
1086 |
+
"grad_norm": 2.046875,
|
1087 |
+
"learning_rate": 1.2925531914893619e-05,
|
1088 |
+
"loss": 0.676,
|
1089 |
+
"step": 153
|
1090 |
+
},
|
1091 |
+
{
|
1092 |
+
"epoch": 0.3888888888888889,
|
1093 |
+
"grad_norm": 2.15625,
|
1094 |
+
"learning_rate": 1.2872340425531915e-05,
|
1095 |
+
"loss": 0.6498,
|
1096 |
+
"step": 154
|
1097 |
+
},
|
1098 |
+
{
|
1099 |
+
"epoch": 0.39141414141414144,
|
1100 |
+
"grad_norm": 1.984375,
|
1101 |
+
"learning_rate": 1.2819148936170214e-05,
|
1102 |
+
"loss": 0.572,
|
1103 |
+
"step": 155
|
1104 |
+
},
|
1105 |
+
{
|
1106 |
+
"epoch": 0.3939393939393939,
|
1107 |
+
"grad_norm": 1.828125,
|
1108 |
+
"learning_rate": 1.2765957446808513e-05,
|
1109 |
+
"loss": 0.5173,
|
1110 |
+
"step": 156
|
1111 |
+
},
|
1112 |
+
{
|
1113 |
+
"epoch": 0.39646464646464646,
|
1114 |
+
"grad_norm": 2.25,
|
1115 |
+
"learning_rate": 1.2712765957446808e-05,
|
1116 |
+
"loss": 0.6703,
|
1117 |
+
"step": 157
|
1118 |
+
},
|
1119 |
+
{
|
1120 |
+
"epoch": 0.398989898989899,
|
1121 |
+
"grad_norm": 2.171875,
|
1122 |
+
"learning_rate": 1.2659574468085108e-05,
|
1123 |
+
"loss": 0.8048,
|
1124 |
+
"step": 158
|
1125 |
+
},
|
1126 |
+
{
|
1127 |
+
"epoch": 0.4015151515151515,
|
1128 |
+
"grad_norm": 2.234375,
|
1129 |
+
"learning_rate": 1.2606382978723407e-05,
|
1130 |
+
"loss": 0.7114,
|
1131 |
+
"step": 159
|
1132 |
+
},
|
1133 |
+
{
|
1134 |
+
"epoch": 0.40404040404040403,
|
1135 |
+
"grad_norm": 2.03125,
|
1136 |
+
"learning_rate": 1.2553191489361702e-05,
|
1137 |
+
"loss": 0.5931,
|
1138 |
+
"step": 160
|
1139 |
+
},
|
1140 |
+
{
|
1141 |
+
"epoch": 0.4065656565656566,
|
1142 |
+
"grad_norm": 2.203125,
|
1143 |
+
"learning_rate": 1.25e-05,
|
1144 |
+
"loss": 0.567,
|
1145 |
+
"step": 161
|
1146 |
+
},
|
1147 |
+
{
|
1148 |
+
"epoch": 0.4090909090909091,
|
1149 |
+
"grad_norm": 2.359375,
|
1150 |
+
"learning_rate": 1.24468085106383e-05,
|
1151 |
+
"loss": 0.7013,
|
1152 |
+
"step": 162
|
1153 |
+
},
|
1154 |
+
{
|
1155 |
+
"epoch": 0.4116161616161616,
|
1156 |
+
"grad_norm": 2.0625,
|
1157 |
+
"learning_rate": 1.2393617021276596e-05,
|
1158 |
+
"loss": 0.6181,
|
1159 |
+
"step": 163
|
1160 |
+
},
|
1161 |
+
{
|
1162 |
+
"epoch": 0.41414141414141414,
|
1163 |
+
"grad_norm": 2.078125,
|
1164 |
+
"learning_rate": 1.2340425531914895e-05,
|
1165 |
+
"loss": 0.7713,
|
1166 |
+
"step": 164
|
1167 |
+
},
|
1168 |
+
{
|
1169 |
+
"epoch": 0.4166666666666667,
|
1170 |
+
"grad_norm": 2.15625,
|
1171 |
+
"learning_rate": 1.2287234042553193e-05,
|
1172 |
+
"loss": 0.6588,
|
1173 |
+
"step": 165
|
1174 |
+
},
|
1175 |
+
{
|
1176 |
+
"epoch": 0.41919191919191917,
|
1177 |
+
"grad_norm": 1.9609375,
|
1178 |
+
"learning_rate": 1.223404255319149e-05,
|
1179 |
+
"loss": 0.573,
|
1180 |
+
"step": 166
|
1181 |
+
},
|
1182 |
+
{
|
1183 |
+
"epoch": 0.4217171717171717,
|
1184 |
+
"grad_norm": 1.984375,
|
1185 |
+
"learning_rate": 1.2180851063829789e-05,
|
1186 |
+
"loss": 0.5446,
|
1187 |
+
"step": 167
|
1188 |
+
},
|
1189 |
+
{
|
1190 |
+
"epoch": 0.42424242424242425,
|
1191 |
+
"grad_norm": 2.03125,
|
1192 |
+
"learning_rate": 1.2127659574468087e-05,
|
1193 |
+
"loss": 0.5479,
|
1194 |
+
"step": 168
|
1195 |
+
},
|
1196 |
+
{
|
1197 |
+
"epoch": 0.42676767676767674,
|
1198 |
+
"grad_norm": 2.34375,
|
1199 |
+
"learning_rate": 1.2074468085106383e-05,
|
1200 |
+
"loss": 0.6544,
|
1201 |
+
"step": 169
|
1202 |
+
},
|
1203 |
+
{
|
1204 |
+
"epoch": 0.4292929292929293,
|
1205 |
+
"grad_norm": 2.140625,
|
1206 |
+
"learning_rate": 1.2021276595744681e-05,
|
1207 |
+
"loss": 0.525,
|
1208 |
+
"step": 170
|
1209 |
+
},
|
1210 |
+
{
|
1211 |
+
"epoch": 0.4318181818181818,
|
1212 |
+
"grad_norm": 2.328125,
|
1213 |
+
"learning_rate": 1.196808510638298e-05,
|
1214 |
+
"loss": 0.6069,
|
1215 |
+
"step": 171
|
1216 |
+
},
|
1217 |
+
{
|
1218 |
+
"epoch": 0.43434343434343436,
|
1219 |
+
"grad_norm": 2.1875,
|
1220 |
+
"learning_rate": 1.1914893617021277e-05,
|
1221 |
+
"loss": 0.6263,
|
1222 |
+
"step": 172
|
1223 |
+
},
|
1224 |
+
{
|
1225 |
+
"epoch": 0.43686868686868685,
|
1226 |
+
"grad_norm": 2.171875,
|
1227 |
+
"learning_rate": 1.1861702127659575e-05,
|
1228 |
+
"loss": 0.575,
|
1229 |
+
"step": 173
|
1230 |
+
},
|
1231 |
+
{
|
1232 |
+
"epoch": 0.4393939393939394,
|
1233 |
+
"grad_norm": 2.15625,
|
1234 |
+
"learning_rate": 1.1808510638297874e-05,
|
1235 |
+
"loss": 0.5764,
|
1236 |
+
"step": 174
|
1237 |
+
},
|
1238 |
+
{
|
1239 |
+
"epoch": 0.44191919191919193,
|
1240 |
+
"grad_norm": 2.6875,
|
1241 |
+
"learning_rate": 1.175531914893617e-05,
|
1242 |
+
"loss": 0.7523,
|
1243 |
+
"step": 175
|
1244 |
+
},
|
1245 |
+
{
|
1246 |
+
"epoch": 0.4444444444444444,
|
1247 |
+
"grad_norm": 2.109375,
|
1248 |
+
"learning_rate": 1.170212765957447e-05,
|
1249 |
+
"loss": 0.5827,
|
1250 |
+
"step": 176
|
1251 |
+
},
|
1252 |
+
{
|
1253 |
+
"epoch": 0.44696969696969696,
|
1254 |
+
"grad_norm": 2.21875,
|
1255 |
+
"learning_rate": 1.1648936170212768e-05,
|
1256 |
+
"loss": 0.5396,
|
1257 |
+
"step": 177
|
1258 |
+
},
|
1259 |
+
{
|
1260 |
+
"epoch": 0.4494949494949495,
|
1261 |
+
"grad_norm": 2.0625,
|
1262 |
+
"learning_rate": 1.1595744680851065e-05,
|
1263 |
+
"loss": 0.6469,
|
1264 |
+
"step": 178
|
1265 |
+
},
|
1266 |
+
{
|
1267 |
+
"epoch": 0.45202020202020204,
|
1268 |
+
"grad_norm": 2.015625,
|
1269 |
+
"learning_rate": 1.1542553191489364e-05,
|
1270 |
+
"loss": 0.544,
|
1271 |
+
"step": 179
|
1272 |
+
},
|
1273 |
+
{
|
1274 |
+
"epoch": 0.45454545454545453,
|
1275 |
+
"grad_norm": 1.921875,
|
1276 |
+
"learning_rate": 1.1489361702127662e-05,
|
1277 |
+
"loss": 0.5716,
|
1278 |
+
"step": 180
|
1279 |
+
},
|
1280 |
+
{
|
1281 |
+
"epoch": 0.45707070707070707,
|
1282 |
+
"grad_norm": 2.015625,
|
1283 |
+
"learning_rate": 1.1436170212765957e-05,
|
1284 |
+
"loss": 0.5299,
|
1285 |
+
"step": 181
|
1286 |
+
},
|
1287 |
+
{
|
1288 |
+
"epoch": 0.4595959595959596,
|
1289 |
+
"grad_norm": 1.96875,
|
1290 |
+
"learning_rate": 1.1382978723404256e-05,
|
1291 |
+
"loss": 0.4805,
|
1292 |
+
"step": 182
|
1293 |
+
},
|
1294 |
+
{
|
1295 |
+
"epoch": 0.4621212121212121,
|
1296 |
+
"grad_norm": 2.28125,
|
1297 |
+
"learning_rate": 1.1329787234042555e-05,
|
1298 |
+
"loss": 0.6307,
|
1299 |
+
"step": 183
|
1300 |
+
},
|
1301 |
+
{
|
1302 |
+
"epoch": 0.46464646464646464,
|
1303 |
+
"grad_norm": 2.5,
|
1304 |
+
"learning_rate": 1.1276595744680851e-05,
|
1305 |
+
"loss": 0.8322,
|
1306 |
+
"step": 184
|
1307 |
+
},
|
1308 |
+
{
|
1309 |
+
"epoch": 0.4671717171717172,
|
1310 |
+
"grad_norm": 2.1875,
|
1311 |
+
"learning_rate": 1.122340425531915e-05,
|
1312 |
+
"loss": 0.617,
|
1313 |
+
"step": 185
|
1314 |
+
},
|
1315 |
+
{
|
1316 |
+
"epoch": 0.4696969696969697,
|
1317 |
+
"grad_norm": 2.140625,
|
1318 |
+
"learning_rate": 1.1170212765957447e-05,
|
1319 |
+
"loss": 0.5663,
|
1320 |
+
"step": 186
|
1321 |
+
},
|
1322 |
+
{
|
1323 |
+
"epoch": 0.4722222222222222,
|
1324 |
+
"grad_norm": 2.28125,
|
1325 |
+
"learning_rate": 1.1117021276595746e-05,
|
1326 |
+
"loss": 0.7309,
|
1327 |
+
"step": 187
|
1328 |
+
},
|
1329 |
+
{
|
1330 |
+
"epoch": 0.47474747474747475,
|
1331 |
+
"grad_norm": 2.03125,
|
1332 |
+
"learning_rate": 1.1063829787234044e-05,
|
1333 |
+
"loss": 0.573,
|
1334 |
+
"step": 188
|
1335 |
+
},
|
1336 |
+
{
|
1337 |
+
"epoch": 0.4772727272727273,
|
1338 |
+
"grad_norm": 2.171875,
|
1339 |
+
"learning_rate": 1.1010638297872341e-05,
|
1340 |
+
"loss": 0.5971,
|
1341 |
+
"step": 189
|
1342 |
+
},
|
1343 |
+
{
|
1344 |
+
"epoch": 0.4797979797979798,
|
1345 |
+
"grad_norm": 2.0625,
|
1346 |
+
"learning_rate": 1.095744680851064e-05,
|
1347 |
+
"loss": 0.6153,
|
1348 |
+
"step": 190
|
1349 |
+
},
|
1350 |
+
{
|
1351 |
+
"epoch": 0.4823232323232323,
|
1352 |
+
"grad_norm": 2.109375,
|
1353 |
+
"learning_rate": 1.0904255319148938e-05,
|
1354 |
+
"loss": 0.5656,
|
1355 |
+
"step": 191
|
1356 |
+
},
|
1357 |
+
{
|
1358 |
+
"epoch": 0.48484848484848486,
|
1359 |
+
"grad_norm": 2.296875,
|
1360 |
+
"learning_rate": 1.0851063829787233e-05,
|
1361 |
+
"loss": 0.6486,
|
1362 |
+
"step": 192
|
1363 |
+
},
|
1364 |
+
{
|
1365 |
+
"epoch": 0.48737373737373735,
|
1366 |
+
"grad_norm": 2.265625,
|
1367 |
+
"learning_rate": 1.0797872340425532e-05,
|
1368 |
+
"loss": 0.5707,
|
1369 |
+
"step": 193
|
1370 |
+
},
|
1371 |
+
{
|
1372 |
+
"epoch": 0.4898989898989899,
|
1373 |
+
"grad_norm": 1.9609375,
|
1374 |
+
"learning_rate": 1.074468085106383e-05,
|
1375 |
+
"loss": 0.5209,
|
1376 |
+
"step": 194
|
1377 |
+
},
|
1378 |
+
{
|
1379 |
+
"epoch": 0.49242424242424243,
|
1380 |
+
"grad_norm": 2.3125,
|
1381 |
+
"learning_rate": 1.0691489361702128e-05,
|
1382 |
+
"loss": 0.6777,
|
1383 |
+
"step": 195
|
1384 |
+
},
|
1385 |
+
{
|
1386 |
+
"epoch": 0.494949494949495,
|
1387 |
+
"grad_norm": 2.171875,
|
1388 |
+
"learning_rate": 1.0638297872340426e-05,
|
1389 |
+
"loss": 0.678,
|
1390 |
+
"step": 196
|
1391 |
+
},
|
1392 |
+
{
|
1393 |
+
"epoch": 0.494949494949495,
|
1394 |
+
"eval_loss": 0.5024059414863586,
|
1395 |
+
"eval_model_preparation_time": 0.0001,
|
1396 |
+
"eval_runtime": 2.0314,
|
1397 |
+
"eval_samples_per_second": 52.181,
|
1398 |
+
"eval_steps_per_second": 6.892,
|
1399 |
+
"step": 196
|
1400 |
+
},
|
1401 |
+
{
|
1402 |
+
"epoch": 0.49747474747474746,
|
1403 |
+
"grad_norm": 1.9765625,
|
1404 |
+
"learning_rate": 1.0585106382978725e-05,
|
1405 |
+
"loss": 0.533,
|
1406 |
+
"step": 197
|
1407 |
+
},
|
1408 |
+
{
|
1409 |
+
"epoch": 0.5,
|
1410 |
+
"grad_norm": 2.25,
|
1411 |
+
"learning_rate": 1.0531914893617022e-05,
|
1412 |
+
"loss": 0.6215,
|
1413 |
+
"step": 198
|
1414 |
+
},
|
1415 |
+
{
|
1416 |
+
"epoch": 0.5025252525252525,
|
1417 |
+
"grad_norm": 2.046875,
|
1418 |
+
"learning_rate": 1.047872340425532e-05,
|
1419 |
+
"loss": 0.5616,
|
1420 |
+
"step": 199
|
1421 |
+
},
|
1422 |
+
{
|
1423 |
+
"epoch": 0.5050505050505051,
|
1424 |
+
"grad_norm": 2.34375,
|
1425 |
+
"learning_rate": 1.0425531914893619e-05,
|
1426 |
+
"loss": 0.6466,
|
1427 |
+
"step": 200
|
1428 |
+
},
|
1429 |
+
{
|
1430 |
+
"epoch": 0.5075757575757576,
|
1431 |
+
"grad_norm": 2.1875,
|
1432 |
+
"learning_rate": 1.0372340425531916e-05,
|
1433 |
+
"loss": 0.6424,
|
1434 |
+
"step": 201
|
1435 |
+
},
|
1436 |
+
{
|
1437 |
+
"epoch": 0.51010101010101,
|
1438 |
+
"grad_norm": 2.0625,
|
1439 |
+
"learning_rate": 1.0319148936170214e-05,
|
1440 |
+
"loss": 0.5646,
|
1441 |
+
"step": 202
|
1442 |
+
},
|
1443 |
+
{
|
1444 |
+
"epoch": 0.5126262626262627,
|
1445 |
+
"grad_norm": 2.125,
|
1446 |
+
"learning_rate": 1.0265957446808513e-05,
|
1447 |
+
"loss": 0.6261,
|
1448 |
+
"step": 203
|
1449 |
+
},
|
1450 |
+
{
|
1451 |
+
"epoch": 0.5151515151515151,
|
1452 |
+
"grad_norm": 2.296875,
|
1453 |
+
"learning_rate": 1.0212765957446808e-05,
|
1454 |
+
"loss": 0.6775,
|
1455 |
+
"step": 204
|
1456 |
+
},
|
1457 |
+
{
|
1458 |
+
"epoch": 0.5176767676767676,
|
1459 |
+
"grad_norm": 2.078125,
|
1460 |
+
"learning_rate": 1.0159574468085107e-05,
|
1461 |
+
"loss": 0.5857,
|
1462 |
+
"step": 205
|
1463 |
+
},
|
1464 |
+
{
|
1465 |
+
"epoch": 0.5202020202020202,
|
1466 |
+
"grad_norm": 2.171875,
|
1467 |
+
"learning_rate": 1.0106382978723405e-05,
|
1468 |
+
"loss": 0.6021,
|
1469 |
+
"step": 206
|
1470 |
+
},
|
1471 |
+
{
|
1472 |
+
"epoch": 0.5227272727272727,
|
1473 |
+
"grad_norm": 2.40625,
|
1474 |
+
"learning_rate": 1.0053191489361702e-05,
|
1475 |
+
"loss": 0.7299,
|
1476 |
+
"step": 207
|
1477 |
+
},
|
1478 |
+
{
|
1479 |
+
"epoch": 0.5252525252525253,
|
1480 |
+
"grad_norm": 1.8828125,
|
1481 |
+
"learning_rate": 1e-05,
|
1482 |
+
"loss": 0.5437,
|
1483 |
+
"step": 208
|
1484 |
+
},
|
1485 |
+
{
|
1486 |
+
"epoch": 0.5277777777777778,
|
1487 |
+
"grad_norm": 2.140625,
|
1488 |
+
"learning_rate": 9.946808510638298e-06,
|
1489 |
+
"loss": 0.6348,
|
1490 |
+
"step": 209
|
1491 |
+
},
|
1492 |
+
{
|
1493 |
+
"epoch": 0.5303030303030303,
|
1494 |
+
"grad_norm": 2.0,
|
1495 |
+
"learning_rate": 9.893617021276596e-06,
|
1496 |
+
"loss": 0.5428,
|
1497 |
+
"step": 210
|
1498 |
+
},
|
1499 |
+
{
|
1500 |
+
"epoch": 0.5328282828282829,
|
1501 |
+
"grad_norm": 2.140625,
|
1502 |
+
"learning_rate": 9.840425531914895e-06,
|
1503 |
+
"loss": 0.6134,
|
1504 |
+
"step": 211
|
1505 |
+
},
|
1506 |
+
{
|
1507 |
+
"epoch": 0.5353535353535354,
|
1508 |
+
"grad_norm": 2.4375,
|
1509 |
+
"learning_rate": 9.787234042553192e-06,
|
1510 |
+
"loss": 0.7403,
|
1511 |
+
"step": 212
|
1512 |
+
},
|
1513 |
+
{
|
1514 |
+
"epoch": 0.5378787878787878,
|
1515 |
+
"grad_norm": 2.40625,
|
1516 |
+
"learning_rate": 9.73404255319149e-06,
|
1517 |
+
"loss": 0.6552,
|
1518 |
+
"step": 213
|
1519 |
+
},
|
1520 |
+
{
|
1521 |
+
"epoch": 0.5404040404040404,
|
1522 |
+
"grad_norm": 2.34375,
|
1523 |
+
"learning_rate": 9.680851063829787e-06,
|
1524 |
+
"loss": 0.6425,
|
1525 |
+
"step": 214
|
1526 |
+
},
|
1527 |
+
{
|
1528 |
+
"epoch": 0.5429292929292929,
|
1529 |
+
"grad_norm": 2.0,
|
1530 |
+
"learning_rate": 9.627659574468086e-06,
|
1531 |
+
"loss": 0.5375,
|
1532 |
+
"step": 215
|
1533 |
+
},
|
1534 |
+
{
|
1535 |
+
"epoch": 0.5454545454545454,
|
1536 |
+
"grad_norm": 2.140625,
|
1537 |
+
"learning_rate": 9.574468085106385e-06,
|
1538 |
+
"loss": 0.5925,
|
1539 |
+
"step": 216
|
1540 |
+
},
|
1541 |
+
{
|
1542 |
+
"epoch": 0.547979797979798,
|
1543 |
+
"grad_norm": 2.390625,
|
1544 |
+
"learning_rate": 9.521276595744681e-06,
|
1545 |
+
"loss": 0.7654,
|
1546 |
+
"step": 217
|
1547 |
+
},
|
1548 |
+
{
|
1549 |
+
"epoch": 0.5505050505050505,
|
1550 |
+
"grad_norm": 1.953125,
|
1551 |
+
"learning_rate": 9.46808510638298e-06,
|
1552 |
+
"loss": 0.4996,
|
1553 |
+
"step": 218
|
1554 |
+
},
|
1555 |
+
{
|
1556 |
+
"epoch": 0.553030303030303,
|
1557 |
+
"grad_norm": 2.453125,
|
1558 |
+
"learning_rate": 9.414893617021279e-06,
|
1559 |
+
"loss": 0.6864,
|
1560 |
+
"step": 219
|
1561 |
+
},
|
1562 |
+
{
|
1563 |
+
"epoch": 0.5555555555555556,
|
1564 |
+
"grad_norm": 2.0,
|
1565 |
+
"learning_rate": 9.361702127659576e-06,
|
1566 |
+
"loss": 0.488,
|
1567 |
+
"step": 220
|
1568 |
+
},
|
1569 |
+
{
|
1570 |
+
"epoch": 0.5580808080808081,
|
1571 |
+
"grad_norm": 2.078125,
|
1572 |
+
"learning_rate": 9.308510638297872e-06,
|
1573 |
+
"loss": 0.5785,
|
1574 |
+
"step": 221
|
1575 |
+
},
|
1576 |
+
{
|
1577 |
+
"epoch": 0.5606060606060606,
|
1578 |
+
"grad_norm": 2.1875,
|
1579 |
+
"learning_rate": 9.255319148936171e-06,
|
1580 |
+
"loss": 0.5625,
|
1581 |
+
"step": 222
|
1582 |
+
},
|
1583 |
+
{
|
1584 |
+
"epoch": 0.5631313131313131,
|
1585 |
+
"grad_norm": 2.390625,
|
1586 |
+
"learning_rate": 9.20212765957447e-06,
|
1587 |
+
"loss": 0.7519,
|
1588 |
+
"step": 223
|
1589 |
+
},
|
1590 |
+
{
|
1591 |
+
"epoch": 0.5656565656565656,
|
1592 |
+
"grad_norm": 2.265625,
|
1593 |
+
"learning_rate": 9.148936170212767e-06,
|
1594 |
+
"loss": 0.6129,
|
1595 |
+
"step": 224
|
1596 |
+
},
|
1597 |
+
{
|
1598 |
+
"epoch": 0.5681818181818182,
|
1599 |
+
"grad_norm": 2.25,
|
1600 |
+
"learning_rate": 9.095744680851063e-06,
|
1601 |
+
"loss": 0.6109,
|
1602 |
+
"step": 225
|
1603 |
+
},
|
1604 |
+
{
|
1605 |
+
"epoch": 0.5707070707070707,
|
1606 |
+
"grad_norm": 2.21875,
|
1607 |
+
"learning_rate": 9.042553191489362e-06,
|
1608 |
+
"loss": 0.6669,
|
1609 |
+
"step": 226
|
1610 |
+
},
|
1611 |
+
{
|
1612 |
+
"epoch": 0.5732323232323232,
|
1613 |
+
"grad_norm": 2.078125,
|
1614 |
+
"learning_rate": 8.98936170212766e-06,
|
1615 |
+
"loss": 0.5333,
|
1616 |
+
"step": 227
|
1617 |
+
},
|
1618 |
+
{
|
1619 |
+
"epoch": 0.5757575757575758,
|
1620 |
+
"grad_norm": 1.84375,
|
1621 |
+
"learning_rate": 8.936170212765958e-06,
|
1622 |
+
"loss": 0.4787,
|
1623 |
+
"step": 228
|
1624 |
+
},
|
1625 |
+
{
|
1626 |
+
"epoch": 0.5782828282828283,
|
1627 |
+
"grad_norm": 2.265625,
|
1628 |
+
"learning_rate": 8.882978723404256e-06,
|
1629 |
+
"loss": 0.6159,
|
1630 |
+
"step": 229
|
1631 |
+
},
|
1632 |
+
{
|
1633 |
+
"epoch": 0.5808080808080808,
|
1634 |
+
"grad_norm": 1.9296875,
|
1635 |
+
"learning_rate": 8.829787234042555e-06,
|
1636 |
+
"loss": 0.5439,
|
1637 |
+
"step": 230
|
1638 |
+
},
|
1639 |
+
{
|
1640 |
+
"epoch": 0.5833333333333334,
|
1641 |
+
"grad_norm": 2.1875,
|
1642 |
+
"learning_rate": 8.776595744680852e-06,
|
1643 |
+
"loss": 0.6479,
|
1644 |
+
"step": 231
|
1645 |
+
},
|
1646 |
+
{
|
1647 |
+
"epoch": 0.5858585858585859,
|
1648 |
+
"grad_norm": 2.46875,
|
1649 |
+
"learning_rate": 8.72340425531915e-06,
|
1650 |
+
"loss": 0.7045,
|
1651 |
+
"step": 232
|
1652 |
+
},
|
1653 |
+
{
|
1654 |
+
"epoch": 0.5883838383838383,
|
1655 |
+
"grad_norm": 2.28125,
|
1656 |
+
"learning_rate": 8.670212765957447e-06,
|
1657 |
+
"loss": 0.6465,
|
1658 |
+
"step": 233
|
1659 |
+
},
|
1660 |
+
{
|
1661 |
+
"epoch": 0.5909090909090909,
|
1662 |
+
"grad_norm": 2.296875,
|
1663 |
+
"learning_rate": 8.617021276595746e-06,
|
1664 |
+
"loss": 0.7733,
|
1665 |
+
"step": 234
|
1666 |
+
},
|
1667 |
+
{
|
1668 |
+
"epoch": 0.5934343434343434,
|
1669 |
+
"grad_norm": 1.8984375,
|
1670 |
+
"learning_rate": 8.563829787234044e-06,
|
1671 |
+
"loss": 0.5294,
|
1672 |
+
"step": 235
|
1673 |
+
},
|
1674 |
+
{
|
1675 |
+
"epoch": 0.5959595959595959,
|
1676 |
+
"grad_norm": 2.234375,
|
1677 |
+
"learning_rate": 8.510638297872341e-06,
|
1678 |
+
"loss": 0.5508,
|
1679 |
+
"step": 236
|
1680 |
+
},
|
1681 |
+
{
|
1682 |
+
"epoch": 0.5984848484848485,
|
1683 |
+
"grad_norm": 2.546875,
|
1684 |
+
"learning_rate": 8.457446808510638e-06,
|
1685 |
+
"loss": 0.7075,
|
1686 |
+
"step": 237
|
1687 |
+
},
|
1688 |
+
{
|
1689 |
+
"epoch": 0.601010101010101,
|
1690 |
+
"grad_norm": 2.046875,
|
1691 |
+
"learning_rate": 8.404255319148937e-06,
|
1692 |
+
"loss": 0.5368,
|
1693 |
+
"step": 238
|
1694 |
+
},
|
1695 |
+
{
|
1696 |
+
"epoch": 0.6035353535353535,
|
1697 |
+
"grad_norm": 1.8828125,
|
1698 |
+
"learning_rate": 8.351063829787235e-06,
|
1699 |
+
"loss": 0.5084,
|
1700 |
+
"step": 239
|
1701 |
+
},
|
1702 |
+
{
|
1703 |
+
"epoch": 0.6060606060606061,
|
1704 |
+
"grad_norm": 2.484375,
|
1705 |
+
"learning_rate": 8.297872340425532e-06,
|
1706 |
+
"loss": 0.7621,
|
1707 |
+
"step": 240
|
1708 |
+
},
|
1709 |
+
{
|
1710 |
+
"epoch": 0.6085858585858586,
|
1711 |
+
"grad_norm": 2.171875,
|
1712 |
+
"learning_rate": 8.24468085106383e-06,
|
1713 |
+
"loss": 0.6219,
|
1714 |
+
"step": 241
|
1715 |
+
},
|
1716 |
+
{
|
1717 |
+
"epoch": 0.6111111111111112,
|
1718 |
+
"grad_norm": 2.21875,
|
1719 |
+
"learning_rate": 8.191489361702128e-06,
|
1720 |
+
"loss": 0.7703,
|
1721 |
+
"step": 242
|
1722 |
+
},
|
1723 |
+
{
|
1724 |
+
"epoch": 0.6136363636363636,
|
1725 |
+
"grad_norm": 2.296875,
|
1726 |
+
"learning_rate": 8.138297872340426e-06,
|
1727 |
+
"loss": 0.699,
|
1728 |
+
"step": 243
|
1729 |
+
},
|
1730 |
+
{
|
1731 |
+
"epoch": 0.6161616161616161,
|
1732 |
+
"grad_norm": 2.03125,
|
1733 |
+
"learning_rate": 8.085106382978723e-06,
|
1734 |
+
"loss": 0.6155,
|
1735 |
+
"step": 244
|
1736 |
+
},
|
1737 |
+
{
|
1738 |
+
"epoch": 0.6186868686868687,
|
1739 |
+
"grad_norm": 2.15625,
|
1740 |
+
"learning_rate": 8.031914893617022e-06,
|
1741 |
+
"loss": 0.6866,
|
1742 |
+
"step": 245
|
1743 |
+
},
|
1744 |
+
{
|
1745 |
+
"epoch": 0.6212121212121212,
|
1746 |
+
"grad_norm": 2.0,
|
1747 |
+
"learning_rate": 7.97872340425532e-06,
|
1748 |
+
"loss": 0.5463,
|
1749 |
+
"step": 246
|
1750 |
+
},
|
1751 |
+
{
|
1752 |
+
"epoch": 0.6237373737373737,
|
1753 |
+
"grad_norm": 2.109375,
|
1754 |
+
"learning_rate": 7.925531914893617e-06,
|
1755 |
+
"loss": 0.623,
|
1756 |
+
"step": 247
|
1757 |
+
},
|
1758 |
+
{
|
1759 |
+
"epoch": 0.6262626262626263,
|
1760 |
+
"grad_norm": 1.8671875,
|
1761 |
+
"learning_rate": 7.872340425531916e-06,
|
1762 |
+
"loss": 0.5725,
|
1763 |
+
"step": 248
|
1764 |
+
},
|
1765 |
+
{
|
1766 |
+
"epoch": 0.6287878787878788,
|
1767 |
+
"grad_norm": 2.15625,
|
1768 |
+
"learning_rate": 7.819148936170213e-06,
|
1769 |
+
"loss": 0.5766,
|
1770 |
+
"step": 249
|
1771 |
+
},
|
1772 |
+
{
|
1773 |
+
"epoch": 0.6313131313131313,
|
1774 |
+
"grad_norm": 2.25,
|
1775 |
+
"learning_rate": 7.765957446808511e-06,
|
1776 |
+
"loss": 0.6114,
|
1777 |
+
"step": 250
|
1778 |
+
},
|
1779 |
+
{
|
1780 |
+
"epoch": 0.6338383838383839,
|
1781 |
+
"grad_norm": 2.09375,
|
1782 |
+
"learning_rate": 7.71276595744681e-06,
|
1783 |
+
"loss": 0.5799,
|
1784 |
+
"step": 251
|
1785 |
+
},
|
1786 |
+
{
|
1787 |
+
"epoch": 0.6363636363636364,
|
1788 |
+
"grad_norm": 2.15625,
|
1789 |
+
"learning_rate": 7.659574468085107e-06,
|
1790 |
+
"loss": 0.6028,
|
1791 |
+
"step": 252
|
1792 |
+
},
|
1793 |
+
{
|
1794 |
+
"epoch": 0.6388888888888888,
|
1795 |
+
"grad_norm": 2.046875,
|
1796 |
+
"learning_rate": 7.606382978723405e-06,
|
1797 |
+
"loss": 0.5485,
|
1798 |
+
"step": 253
|
1799 |
+
},
|
1800 |
+
{
|
1801 |
+
"epoch": 0.6414141414141414,
|
1802 |
+
"grad_norm": 2.328125,
|
1803 |
+
"learning_rate": 7.553191489361703e-06,
|
1804 |
+
"loss": 0.6007,
|
1805 |
+
"step": 254
|
1806 |
+
},
|
1807 |
+
{
|
1808 |
+
"epoch": 0.6439393939393939,
|
1809 |
+
"grad_norm": 2.125,
|
1810 |
+
"learning_rate": 7.500000000000001e-06,
|
1811 |
+
"loss": 0.5623,
|
1812 |
+
"step": 255
|
1813 |
+
},
|
1814 |
+
{
|
1815 |
+
"epoch": 0.6464646464646465,
|
1816 |
+
"grad_norm": 1.9296875,
|
1817 |
+
"learning_rate": 7.446808510638298e-06,
|
1818 |
+
"loss": 0.5226,
|
1819 |
+
"step": 256
|
1820 |
+
},
|
1821 |
+
{
|
1822 |
+
"epoch": 0.648989898989899,
|
1823 |
+
"grad_norm": 1.90625,
|
1824 |
+
"learning_rate": 7.3936170212765965e-06,
|
1825 |
+
"loss": 0.5072,
|
1826 |
+
"step": 257
|
1827 |
+
},
|
1828 |
+
{
|
1829 |
+
"epoch": 0.6515151515151515,
|
1830 |
+
"grad_norm": 2.171875,
|
1831 |
+
"learning_rate": 7.340425531914894e-06,
|
1832 |
+
"loss": 0.6739,
|
1833 |
+
"step": 258
|
1834 |
+
},
|
1835 |
+
{
|
1836 |
+
"epoch": 0.6540404040404041,
|
1837 |
+
"grad_norm": 2.234375,
|
1838 |
+
"learning_rate": 7.287234042553192e-06,
|
1839 |
+
"loss": 0.6461,
|
1840 |
+
"step": 259
|
1841 |
+
},
|
1842 |
+
{
|
1843 |
+
"epoch": 0.6565656565656566,
|
1844 |
+
"grad_norm": 2.1875,
|
1845 |
+
"learning_rate": 7.234042553191491e-06,
|
1846 |
+
"loss": 0.5361,
|
1847 |
+
"step": 260
|
1848 |
+
},
|
1849 |
+
{
|
1850 |
+
"epoch": 0.6590909090909091,
|
1851 |
+
"grad_norm": 2.28125,
|
1852 |
+
"learning_rate": 7.1808510638297875e-06,
|
1853 |
+
"loss": 0.5884,
|
1854 |
+
"step": 261
|
1855 |
+
},
|
1856 |
+
{
|
1857 |
+
"epoch": 0.6616161616161617,
|
1858 |
+
"grad_norm": 1.9296875,
|
1859 |
+
"learning_rate": 7.127659574468085e-06,
|
1860 |
+
"loss": 0.5063,
|
1861 |
+
"step": 262
|
1862 |
+
},
|
1863 |
+
{
|
1864 |
+
"epoch": 0.6641414141414141,
|
1865 |
+
"grad_norm": 1.859375,
|
1866 |
+
"learning_rate": 7.074468085106384e-06,
|
1867 |
+
"loss": 0.4902,
|
1868 |
+
"step": 263
|
1869 |
+
},
|
1870 |
+
{
|
1871 |
+
"epoch": 0.6666666666666666,
|
1872 |
+
"grad_norm": 2.484375,
|
1873 |
+
"learning_rate": 7.021276595744682e-06,
|
1874 |
+
"loss": 0.5821,
|
1875 |
+
"step": 264
|
1876 |
+
},
|
1877 |
+
{
|
1878 |
+
"epoch": 0.6691919191919192,
|
1879 |
+
"grad_norm": 1.8828125,
|
1880 |
+
"learning_rate": 6.968085106382979e-06,
|
1881 |
+
"loss": 0.4859,
|
1882 |
+
"step": 265
|
1883 |
+
},
|
1884 |
+
{
|
1885 |
+
"epoch": 0.6717171717171717,
|
1886 |
+
"grad_norm": 2.359375,
|
1887 |
+
"learning_rate": 6.914893617021278e-06,
|
1888 |
+
"loss": 0.6668,
|
1889 |
+
"step": 266
|
1890 |
+
},
|
1891 |
+
{
|
1892 |
+
"epoch": 0.6742424242424242,
|
1893 |
+
"grad_norm": 1.984375,
|
1894 |
+
"learning_rate": 6.861702127659575e-06,
|
1895 |
+
"loss": 0.5804,
|
1896 |
+
"step": 267
|
1897 |
+
},
|
1898 |
+
{
|
1899 |
+
"epoch": 0.6767676767676768,
|
1900 |
+
"grad_norm": 2.015625,
|
1901 |
+
"learning_rate": 6.808510638297873e-06,
|
1902 |
+
"loss": 0.54,
|
1903 |
+
"step": 268
|
1904 |
+
},
|
1905 |
+
{
|
1906 |
+
"epoch": 0.6792929292929293,
|
1907 |
+
"grad_norm": 2.171875,
|
1908 |
+
"learning_rate": 6.75531914893617e-06,
|
1909 |
+
"loss": 0.6318,
|
1910 |
+
"step": 269
|
1911 |
+
},
|
1912 |
+
{
|
1913 |
+
"epoch": 0.6818181818181818,
|
1914 |
+
"grad_norm": 2.046875,
|
1915 |
+
"learning_rate": 6.702127659574469e-06,
|
1916 |
+
"loss": 0.552,
|
1917 |
+
"step": 270
|
1918 |
+
},
|
1919 |
+
{
|
1920 |
+
"epoch": 0.6843434343434344,
|
1921 |
+
"grad_norm": 2.125,
|
1922 |
+
"learning_rate": 6.648936170212767e-06,
|
1923 |
+
"loss": 0.5727,
|
1924 |
+
"step": 271
|
1925 |
+
},
|
1926 |
+
{
|
1927 |
+
"epoch": 0.6868686868686869,
|
1928 |
+
"grad_norm": 2.234375,
|
1929 |
+
"learning_rate": 6.595744680851064e-06,
|
1930 |
+
"loss": 0.673,
|
1931 |
+
"step": 272
|
1932 |
+
},
|
1933 |
+
{
|
1934 |
+
"epoch": 0.6893939393939394,
|
1935 |
+
"grad_norm": 2.171875,
|
1936 |
+
"learning_rate": 6.542553191489362e-06,
|
1937 |
+
"loss": 0.5932,
|
1938 |
+
"step": 273
|
1939 |
+
},
|
1940 |
+
{
|
1941 |
+
"epoch": 0.6919191919191919,
|
1942 |
+
"grad_norm": 1.921875,
|
1943 |
+
"learning_rate": 6.48936170212766e-06,
|
1944 |
+
"loss": 0.5093,
|
1945 |
+
"step": 274
|
1946 |
+
},
|
1947 |
+
{
|
1948 |
+
"epoch": 0.6944444444444444,
|
1949 |
+
"grad_norm": 2.0625,
|
1950 |
+
"learning_rate": 6.436170212765958e-06,
|
1951 |
+
"loss": 0.5441,
|
1952 |
+
"step": 275
|
1953 |
+
},
|
1954 |
+
{
|
1955 |
+
"epoch": 0.696969696969697,
|
1956 |
+
"grad_norm": 2.28125,
|
1957 |
+
"learning_rate": 6.382978723404256e-06,
|
1958 |
+
"loss": 0.7347,
|
1959 |
+
"step": 276
|
1960 |
+
},
|
1961 |
+
{
|
1962 |
+
"epoch": 0.6994949494949495,
|
1963 |
+
"grad_norm": 2.015625,
|
1964 |
+
"learning_rate": 6.329787234042554e-06,
|
1965 |
+
"loss": 0.6073,
|
1966 |
+
"step": 277
|
1967 |
+
},
|
1968 |
+
{
|
1969 |
+
"epoch": 0.702020202020202,
|
1970 |
+
"grad_norm": 1.9375,
|
1971 |
+
"learning_rate": 6.276595744680851e-06,
|
1972 |
+
"loss": 0.535,
|
1973 |
+
"step": 278
|
1974 |
+
},
|
1975 |
+
{
|
1976 |
+
"epoch": 0.7045454545454546,
|
1977 |
+
"grad_norm": 1.9453125,
|
1978 |
+
"learning_rate": 6.22340425531915e-06,
|
1979 |
+
"loss": 0.5872,
|
1980 |
+
"step": 279
|
1981 |
+
},
|
1982 |
+
{
|
1983 |
+
"epoch": 0.7070707070707071,
|
1984 |
+
"grad_norm": 2.375,
|
1985 |
+
"learning_rate": 6.170212765957447e-06,
|
1986 |
+
"loss": 0.5513,
|
1987 |
+
"step": 280
|
1988 |
+
},
|
1989 |
+
{
|
1990 |
+
"epoch": 0.7095959595959596,
|
1991 |
+
"grad_norm": 2.125,
|
1992 |
+
"learning_rate": 6.117021276595745e-06,
|
1993 |
+
"loss": 0.5443,
|
1994 |
+
"step": 281
|
1995 |
+
},
|
1996 |
+
{
|
1997 |
+
"epoch": 0.7121212121212122,
|
1998 |
+
"grad_norm": 2.109375,
|
1999 |
+
"learning_rate": 6.063829787234044e-06,
|
2000 |
+
"loss": 0.5909,
|
2001 |
+
"step": 282
|
2002 |
+
},
|
2003 |
+
{
|
2004 |
+
"epoch": 0.7146464646464646,
|
2005 |
+
"grad_norm": 2.125,
|
2006 |
+
"learning_rate": 6.010638297872341e-06,
|
2007 |
+
"loss": 0.6246,
|
2008 |
+
"step": 283
|
2009 |
+
},
|
2010 |
+
{
|
2011 |
+
"epoch": 0.7171717171717171,
|
2012 |
+
"grad_norm": 2.328125,
|
2013 |
+
"learning_rate": 5.957446808510638e-06,
|
2014 |
+
"loss": 0.6736,
|
2015 |
+
"step": 284
|
2016 |
+
},
|
2017 |
+
{
|
2018 |
+
"epoch": 0.7196969696969697,
|
2019 |
+
"grad_norm": 2.046875,
|
2020 |
+
"learning_rate": 5.904255319148937e-06,
|
2021 |
+
"loss": 0.6977,
|
2022 |
+
"step": 285
|
2023 |
+
},
|
2024 |
+
{
|
2025 |
+
"epoch": 0.7222222222222222,
|
2026 |
+
"grad_norm": 1.953125,
|
2027 |
+
"learning_rate": 5.851063829787235e-06,
|
2028 |
+
"loss": 0.5457,
|
2029 |
+
"step": 286
|
2030 |
+
},
|
2031 |
+
{
|
2032 |
+
"epoch": 0.7247474747474747,
|
2033 |
+
"grad_norm": 2.34375,
|
2034 |
+
"learning_rate": 5.7978723404255325e-06,
|
2035 |
+
"loss": 0.689,
|
2036 |
+
"step": 287
|
2037 |
+
},
|
2038 |
+
{
|
2039 |
+
"epoch": 0.7272727272727273,
|
2040 |
+
"grad_norm": 1.9375,
|
2041 |
+
"learning_rate": 5.744680851063831e-06,
|
2042 |
+
"loss": 0.5628,
|
2043 |
+
"step": 288
|
2044 |
+
},
|
2045 |
+
{
|
2046 |
+
"epoch": 0.7297979797979798,
|
2047 |
+
"grad_norm": 1.9140625,
|
2048 |
+
"learning_rate": 5.691489361702128e-06,
|
2049 |
+
"loss": 0.4981,
|
2050 |
+
"step": 289
|
2051 |
+
},
|
2052 |
+
{
|
2053 |
+
"epoch": 0.7323232323232324,
|
2054 |
+
"grad_norm": 1.953125,
|
2055 |
+
"learning_rate": 5.638297872340426e-06,
|
2056 |
+
"loss": 0.5368,
|
2057 |
+
"step": 290
|
2058 |
+
},
|
2059 |
+
{
|
2060 |
+
"epoch": 0.7348484848484849,
|
2061 |
+
"grad_norm": 2.3125,
|
2062 |
+
"learning_rate": 5.5851063829787235e-06,
|
2063 |
+
"loss": 0.6594,
|
2064 |
+
"step": 291
|
2065 |
+
},
|
2066 |
+
{
|
2067 |
+
"epoch": 0.7373737373737373,
|
2068 |
+
"grad_norm": 2.390625,
|
2069 |
+
"learning_rate": 5.531914893617022e-06,
|
2070 |
+
"loss": 0.5935,
|
2071 |
+
"step": 292
|
2072 |
+
},
|
2073 |
+
{
|
2074 |
+
"epoch": 0.73989898989899,
|
2075 |
+
"grad_norm": 2.15625,
|
2076 |
+
"learning_rate": 5.47872340425532e-06,
|
2077 |
+
"loss": 0.5859,
|
2078 |
+
"step": 293
|
2079 |
+
},
|
2080 |
+
{
|
2081 |
+
"epoch": 0.7424242424242424,
|
2082 |
+
"grad_norm": 2.234375,
|
2083 |
+
"learning_rate": 5.425531914893617e-06,
|
2084 |
+
"loss": 0.598,
|
2085 |
+
"step": 294
|
2086 |
+
},
|
2087 |
+
{
|
2088 |
+
"epoch": 0.7424242424242424,
|
2089 |
+
"eval_loss": 0.49261218309402466,
|
2090 |
+
"eval_model_preparation_time": 0.0001,
|
2091 |
+
"eval_runtime": 2.0683,
|
2092 |
+
"eval_samples_per_second": 51.249,
|
2093 |
+
"eval_steps_per_second": 6.769,
|
2094 |
+
"step": 294
|
2095 |
+
},
|
2096 |
+
{
|
2097 |
+
"epoch": 0.7449494949494949,
|
2098 |
+
"grad_norm": 1.9296875,
|
2099 |
+
"learning_rate": 5.372340425531915e-06,
|
2100 |
+
"loss": 0.4914,
|
2101 |
+
"step": 295
|
2102 |
+
},
|
2103 |
+
{
|
2104 |
+
"epoch": 0.7474747474747475,
|
2105 |
+
"grad_norm": 2.15625,
|
2106 |
+
"learning_rate": 5.319148936170213e-06,
|
2107 |
+
"loss": 0.739,
|
2108 |
+
"step": 296
|
2109 |
+
},
|
2110 |
+
{
|
2111 |
+
"epoch": 0.75,
|
2112 |
+
"grad_norm": 2.171875,
|
2113 |
+
"learning_rate": 5.265957446808511e-06,
|
2114 |
+
"loss": 0.5582,
|
2115 |
+
"step": 297
|
2116 |
+
},
|
2117 |
+
{
|
2118 |
+
"epoch": 0.7525252525252525,
|
2119 |
+
"grad_norm": 2.453125,
|
2120 |
+
"learning_rate": 5.212765957446809e-06,
|
2121 |
+
"loss": 0.7083,
|
2122 |
+
"step": 298
|
2123 |
+
},
|
2124 |
+
{
|
2125 |
+
"epoch": 0.7550505050505051,
|
2126 |
+
"grad_norm": 2.0625,
|
2127 |
+
"learning_rate": 5.159574468085107e-06,
|
2128 |
+
"loss": 0.5886,
|
2129 |
+
"step": 299
|
2130 |
+
},
|
2131 |
+
{
|
2132 |
+
"epoch": 0.7575757575757576,
|
2133 |
+
"grad_norm": 2.15625,
|
2134 |
+
"learning_rate": 5.106382978723404e-06,
|
2135 |
+
"loss": 0.6125,
|
2136 |
+
"step": 300
|
2137 |
+
},
|
2138 |
+
{
|
2139 |
+
"epoch": 0.76010101010101,
|
2140 |
+
"grad_norm": 2.09375,
|
2141 |
+
"learning_rate": 5.053191489361703e-06,
|
2142 |
+
"loss": 0.5323,
|
2143 |
+
"step": 301
|
2144 |
+
},
|
2145 |
+
{
|
2146 |
+
"epoch": 0.7626262626262627,
|
2147 |
+
"grad_norm": 2.046875,
|
2148 |
+
"learning_rate": 5e-06,
|
2149 |
+
"loss": 0.5877,
|
2150 |
+
"step": 302
|
2151 |
+
},
|
2152 |
+
{
|
2153 |
+
"epoch": 0.7651515151515151,
|
2154 |
+
"grad_norm": 2.09375,
|
2155 |
+
"learning_rate": 4.946808510638298e-06,
|
2156 |
+
"loss": 0.618,
|
2157 |
+
"step": 303
|
2158 |
+
},
|
2159 |
+
{
|
2160 |
+
"epoch": 0.7676767676767676,
|
2161 |
+
"grad_norm": 2.046875,
|
2162 |
+
"learning_rate": 4.893617021276596e-06,
|
2163 |
+
"loss": 0.6148,
|
2164 |
+
"step": 304
|
2165 |
+
},
|
2166 |
+
{
|
2167 |
+
"epoch": 0.7702020202020202,
|
2168 |
+
"grad_norm": 2.109375,
|
2169 |
+
"learning_rate": 4.840425531914894e-06,
|
2170 |
+
"loss": 0.5589,
|
2171 |
+
"step": 305
|
2172 |
+
},
|
2173 |
+
{
|
2174 |
+
"epoch": 0.7727272727272727,
|
2175 |
+
"grad_norm": 1.9921875,
|
2176 |
+
"learning_rate": 4.787234042553192e-06,
|
2177 |
+
"loss": 0.5927,
|
2178 |
+
"step": 306
|
2179 |
+
},
|
2180 |
+
{
|
2181 |
+
"epoch": 0.7752525252525253,
|
2182 |
+
"grad_norm": 2.453125,
|
2183 |
+
"learning_rate": 4.73404255319149e-06,
|
2184 |
+
"loss": 0.6524,
|
2185 |
+
"step": 307
|
2186 |
+
},
|
2187 |
+
{
|
2188 |
+
"epoch": 0.7777777777777778,
|
2189 |
+
"grad_norm": 1.9609375,
|
2190 |
+
"learning_rate": 4.680851063829788e-06,
|
2191 |
+
"loss": 0.4944,
|
2192 |
+
"step": 308
|
2193 |
+
},
|
2194 |
+
{
|
2195 |
+
"epoch": 0.7803030303030303,
|
2196 |
+
"grad_norm": 1.9765625,
|
2197 |
+
"learning_rate": 4.6276595744680855e-06,
|
2198 |
+
"loss": 0.6216,
|
2199 |
+
"step": 309
|
2200 |
+
},
|
2201 |
+
{
|
2202 |
+
"epoch": 0.7828282828282829,
|
2203 |
+
"grad_norm": 2.109375,
|
2204 |
+
"learning_rate": 4.574468085106383e-06,
|
2205 |
+
"loss": 0.5407,
|
2206 |
+
"step": 310
|
2207 |
+
},
|
2208 |
+
{
|
2209 |
+
"epoch": 0.7853535353535354,
|
2210 |
+
"grad_norm": 2.15625,
|
2211 |
+
"learning_rate": 4.521276595744681e-06,
|
2212 |
+
"loss": 0.5426,
|
2213 |
+
"step": 311
|
2214 |
+
},
|
2215 |
+
{
|
2216 |
+
"epoch": 0.7878787878787878,
|
2217 |
+
"grad_norm": 2.5625,
|
2218 |
+
"learning_rate": 4.468085106382979e-06,
|
2219 |
+
"loss": 0.6869,
|
2220 |
+
"step": 312
|
2221 |
+
},
|
2222 |
+
{
|
2223 |
+
"epoch": 0.7904040404040404,
|
2224 |
+
"grad_norm": 1.90625,
|
2225 |
+
"learning_rate": 4.414893617021277e-06,
|
2226 |
+
"loss": 0.4939,
|
2227 |
+
"step": 313
|
2228 |
+
},
|
2229 |
+
{
|
2230 |
+
"epoch": 0.7929292929292929,
|
2231 |
+
"grad_norm": 1.9296875,
|
2232 |
+
"learning_rate": 4.361702127659575e-06,
|
2233 |
+
"loss": 0.5599,
|
2234 |
+
"step": 314
|
2235 |
+
},
|
2236 |
+
{
|
2237 |
+
"epoch": 0.7954545454545454,
|
2238 |
+
"grad_norm": 1.984375,
|
2239 |
+
"learning_rate": 4.308510638297873e-06,
|
2240 |
+
"loss": 0.5386,
|
2241 |
+
"step": 315
|
2242 |
+
},
|
2243 |
+
{
|
2244 |
+
"epoch": 0.797979797979798,
|
2245 |
+
"grad_norm": 2.0,
|
2246 |
+
"learning_rate": 4.255319148936171e-06,
|
2247 |
+
"loss": 0.5639,
|
2248 |
+
"step": 316
|
2249 |
+
},
|
2250 |
+
{
|
2251 |
+
"epoch": 0.8005050505050505,
|
2252 |
+
"grad_norm": 2.140625,
|
2253 |
+
"learning_rate": 4.202127659574468e-06,
|
2254 |
+
"loss": 0.5941,
|
2255 |
+
"step": 317
|
2256 |
+
},
|
2257 |
+
{
|
2258 |
+
"epoch": 0.803030303030303,
|
2259 |
+
"grad_norm": 2.28125,
|
2260 |
+
"learning_rate": 4.148936170212766e-06,
|
2261 |
+
"loss": 0.6414,
|
2262 |
+
"step": 318
|
2263 |
+
},
|
2264 |
+
{
|
2265 |
+
"epoch": 0.8055555555555556,
|
2266 |
+
"grad_norm": 1.953125,
|
2267 |
+
"learning_rate": 4.095744680851064e-06,
|
2268 |
+
"loss": 0.5747,
|
2269 |
+
"step": 319
|
2270 |
+
},
|
2271 |
+
{
|
2272 |
+
"epoch": 0.8080808080808081,
|
2273 |
+
"grad_norm": 2.078125,
|
2274 |
+
"learning_rate": 4.042553191489362e-06,
|
2275 |
+
"loss": 0.6022,
|
2276 |
+
"step": 320
|
2277 |
+
},
|
2278 |
+
{
|
2279 |
+
"epoch": 0.8106060606060606,
|
2280 |
+
"grad_norm": 1.9453125,
|
2281 |
+
"learning_rate": 3.98936170212766e-06,
|
2282 |
+
"loss": 0.5137,
|
2283 |
+
"step": 321
|
2284 |
+
},
|
2285 |
+
{
|
2286 |
+
"epoch": 0.8131313131313131,
|
2287 |
+
"grad_norm": 2.34375,
|
2288 |
+
"learning_rate": 3.936170212765958e-06,
|
2289 |
+
"loss": 0.6665,
|
2290 |
+
"step": 322
|
2291 |
+
},
|
2292 |
+
{
|
2293 |
+
"epoch": 0.8156565656565656,
|
2294 |
+
"grad_norm": 2.03125,
|
2295 |
+
"learning_rate": 3.882978723404256e-06,
|
2296 |
+
"loss": 0.5478,
|
2297 |
+
"step": 323
|
2298 |
+
},
|
2299 |
+
{
|
2300 |
+
"epoch": 0.8181818181818182,
|
2301 |
+
"grad_norm": 2.4375,
|
2302 |
+
"learning_rate": 3.8297872340425535e-06,
|
2303 |
+
"loss": 0.7404,
|
2304 |
+
"step": 324
|
2305 |
+
},
|
2306 |
+
{
|
2307 |
+
"epoch": 0.8207070707070707,
|
2308 |
+
"grad_norm": 2.265625,
|
2309 |
+
"learning_rate": 3.7765957446808516e-06,
|
2310 |
+
"loss": 0.6361,
|
2311 |
+
"step": 325
|
2312 |
+
},
|
2313 |
+
{
|
2314 |
+
"epoch": 0.8232323232323232,
|
2315 |
+
"grad_norm": 2.109375,
|
2316 |
+
"learning_rate": 3.723404255319149e-06,
|
2317 |
+
"loss": 0.5841,
|
2318 |
+
"step": 326
|
2319 |
+
},
|
2320 |
+
{
|
2321 |
+
"epoch": 0.8257575757575758,
|
2322 |
+
"grad_norm": 2.15625,
|
2323 |
+
"learning_rate": 3.670212765957447e-06,
|
2324 |
+
"loss": 0.5882,
|
2325 |
+
"step": 327
|
2326 |
+
},
|
2327 |
+
{
|
2328 |
+
"epoch": 0.8282828282828283,
|
2329 |
+
"grad_norm": 2.25,
|
2330 |
+
"learning_rate": 3.6170212765957453e-06,
|
2331 |
+
"loss": 0.577,
|
2332 |
+
"step": 328
|
2333 |
+
},
|
2334 |
+
{
|
2335 |
+
"epoch": 0.8308080808080808,
|
2336 |
+
"grad_norm": 1.9375,
|
2337 |
+
"learning_rate": 3.5638297872340426e-06,
|
2338 |
+
"loss": 0.468,
|
2339 |
+
"step": 329
|
2340 |
+
},
|
2341 |
+
{
|
2342 |
+
"epoch": 0.8333333333333334,
|
2343 |
+
"grad_norm": 2.3125,
|
2344 |
+
"learning_rate": 3.510638297872341e-06,
|
2345 |
+
"loss": 0.5352,
|
2346 |
+
"step": 330
|
2347 |
+
},
|
2348 |
+
{
|
2349 |
+
"epoch": 0.8358585858585859,
|
2350 |
+
"grad_norm": 2.1875,
|
2351 |
+
"learning_rate": 3.457446808510639e-06,
|
2352 |
+
"loss": 0.6389,
|
2353 |
+
"step": 331
|
2354 |
+
},
|
2355 |
+
{
|
2356 |
+
"epoch": 0.8383838383838383,
|
2357 |
+
"grad_norm": 2.078125,
|
2358 |
+
"learning_rate": 3.4042553191489363e-06,
|
2359 |
+
"loss": 0.5887,
|
2360 |
+
"step": 332
|
2361 |
+
},
|
2362 |
+
{
|
2363 |
+
"epoch": 0.8409090909090909,
|
2364 |
+
"grad_norm": 2.265625,
|
2365 |
+
"learning_rate": 3.3510638297872345e-06,
|
2366 |
+
"loss": 0.613,
|
2367 |
+
"step": 333
|
2368 |
+
},
|
2369 |
+
{
|
2370 |
+
"epoch": 0.8434343434343434,
|
2371 |
+
"grad_norm": 2.1875,
|
2372 |
+
"learning_rate": 3.297872340425532e-06,
|
2373 |
+
"loss": 0.6165,
|
2374 |
+
"step": 334
|
2375 |
+
},
|
2376 |
+
{
|
2377 |
+
"epoch": 0.8459595959595959,
|
2378 |
+
"grad_norm": 2.09375,
|
2379 |
+
"learning_rate": 3.24468085106383e-06,
|
2380 |
+
"loss": 0.713,
|
2381 |
+
"step": 335
|
2382 |
+
},
|
2383 |
+
{
|
2384 |
+
"epoch": 0.8484848484848485,
|
2385 |
+
"grad_norm": 2.265625,
|
2386 |
+
"learning_rate": 3.191489361702128e-06,
|
2387 |
+
"loss": 0.5602,
|
2388 |
+
"step": 336
|
2389 |
+
},
|
2390 |
+
{
|
2391 |
+
"epoch": 0.851010101010101,
|
2392 |
+
"grad_norm": 1.9765625,
|
2393 |
+
"learning_rate": 3.1382978723404255e-06,
|
2394 |
+
"loss": 0.5783,
|
2395 |
+
"step": 337
|
2396 |
+
},
|
2397 |
+
{
|
2398 |
+
"epoch": 0.8535353535353535,
|
2399 |
+
"grad_norm": 2.1875,
|
2400 |
+
"learning_rate": 3.0851063829787237e-06,
|
2401 |
+
"loss": 0.6095,
|
2402 |
+
"step": 338
|
2403 |
+
},
|
2404 |
+
{
|
2405 |
+
"epoch": 0.8560606060606061,
|
2406 |
+
"grad_norm": 2.09375,
|
2407 |
+
"learning_rate": 3.031914893617022e-06,
|
2408 |
+
"loss": 0.5752,
|
2409 |
+
"step": 339
|
2410 |
+
},
|
2411 |
+
{
|
2412 |
+
"epoch": 0.8585858585858586,
|
2413 |
+
"grad_norm": 1.96875,
|
2414 |
+
"learning_rate": 2.978723404255319e-06,
|
2415 |
+
"loss": 0.5692,
|
2416 |
+
"step": 340
|
2417 |
+
},
|
2418 |
+
{
|
2419 |
+
"epoch": 0.8611111111111112,
|
2420 |
+
"grad_norm": 2.203125,
|
2421 |
+
"learning_rate": 2.9255319148936174e-06,
|
2422 |
+
"loss": 0.5864,
|
2423 |
+
"step": 341
|
2424 |
+
},
|
2425 |
+
{
|
2426 |
+
"epoch": 0.8636363636363636,
|
2427 |
+
"grad_norm": 2.109375,
|
2428 |
+
"learning_rate": 2.8723404255319155e-06,
|
2429 |
+
"loss": 0.5904,
|
2430 |
+
"step": 342
|
2431 |
+
},
|
2432 |
+
{
|
2433 |
+
"epoch": 0.8661616161616161,
|
2434 |
+
"grad_norm": 1.9296875,
|
2435 |
+
"learning_rate": 2.819148936170213e-06,
|
2436 |
+
"loss": 0.4829,
|
2437 |
+
"step": 343
|
2438 |
+
},
|
2439 |
+
{
|
2440 |
+
"epoch": 0.8686868686868687,
|
2441 |
+
"grad_norm": 2.15625,
|
2442 |
+
"learning_rate": 2.765957446808511e-06,
|
2443 |
+
"loss": 0.6226,
|
2444 |
+
"step": 344
|
2445 |
+
},
|
2446 |
+
{
|
2447 |
+
"epoch": 0.8712121212121212,
|
2448 |
+
"grad_norm": 2.203125,
|
2449 |
+
"learning_rate": 2.7127659574468084e-06,
|
2450 |
+
"loss": 0.7041,
|
2451 |
+
"step": 345
|
2452 |
+
},
|
2453 |
+
{
|
2454 |
+
"epoch": 0.8737373737373737,
|
2455 |
+
"grad_norm": 2.03125,
|
2456 |
+
"learning_rate": 2.6595744680851065e-06,
|
2457 |
+
"loss": 0.6518,
|
2458 |
+
"step": 346
|
2459 |
+
},
|
2460 |
+
{
|
2461 |
+
"epoch": 0.8762626262626263,
|
2462 |
+
"grad_norm": 2.0,
|
2463 |
+
"learning_rate": 2.6063829787234047e-06,
|
2464 |
+
"loss": 0.5096,
|
2465 |
+
"step": 347
|
2466 |
+
},
|
2467 |
+
{
|
2468 |
+
"epoch": 0.8787878787878788,
|
2469 |
+
"grad_norm": 1.9453125,
|
2470 |
+
"learning_rate": 2.553191489361702e-06,
|
2471 |
+
"loss": 0.487,
|
2472 |
+
"step": 348
|
2473 |
+
},
|
2474 |
+
{
|
2475 |
+
"epoch": 0.8813131313131313,
|
2476 |
+
"grad_norm": 2.171875,
|
2477 |
+
"learning_rate": 2.5e-06,
|
2478 |
+
"loss": 0.6226,
|
2479 |
+
"step": 349
|
2480 |
+
},
|
2481 |
+
{
|
2482 |
+
"epoch": 0.8838383838383839,
|
2483 |
+
"grad_norm": 2.421875,
|
2484 |
+
"learning_rate": 2.446808510638298e-06,
|
2485 |
+
"loss": 0.7568,
|
2486 |
+
"step": 350
|
2487 |
+
},
|
2488 |
+
{
|
2489 |
+
"epoch": 0.8863636363636364,
|
2490 |
+
"grad_norm": 2.046875,
|
2491 |
+
"learning_rate": 2.393617021276596e-06,
|
2492 |
+
"loss": 0.5137,
|
2493 |
+
"step": 351
|
2494 |
+
},
|
2495 |
+
{
|
2496 |
+
"epoch": 0.8888888888888888,
|
2497 |
+
"grad_norm": 2.03125,
|
2498 |
+
"learning_rate": 2.340425531914894e-06,
|
2499 |
+
"loss": 0.5703,
|
2500 |
+
"step": 352
|
2501 |
+
},
|
2502 |
+
{
|
2503 |
+
"epoch": 0.8914141414141414,
|
2504 |
+
"grad_norm": 2.171875,
|
2505 |
+
"learning_rate": 2.2872340425531916e-06,
|
2506 |
+
"loss": 0.633,
|
2507 |
+
"step": 353
|
2508 |
+
},
|
2509 |
+
{
|
2510 |
+
"epoch": 0.8939393939393939,
|
2511 |
+
"grad_norm": 2.34375,
|
2512 |
+
"learning_rate": 2.2340425531914894e-06,
|
2513 |
+
"loss": 0.6691,
|
2514 |
+
"step": 354
|
2515 |
+
},
|
2516 |
+
{
|
2517 |
+
"epoch": 0.8964646464646465,
|
2518 |
+
"grad_norm": 2.15625,
|
2519 |
+
"learning_rate": 2.1808510638297876e-06,
|
2520 |
+
"loss": 0.5669,
|
2521 |
+
"step": 355
|
2522 |
+
},
|
2523 |
+
{
|
2524 |
+
"epoch": 0.898989898989899,
|
2525 |
+
"grad_norm": 1.84375,
|
2526 |
+
"learning_rate": 2.1276595744680853e-06,
|
2527 |
+
"loss": 0.4753,
|
2528 |
+
"step": 356
|
2529 |
+
},
|
2530 |
+
{
|
2531 |
+
"epoch": 0.9015151515151515,
|
2532 |
+
"grad_norm": 2.1875,
|
2533 |
+
"learning_rate": 2.074468085106383e-06,
|
2534 |
+
"loss": 0.7078,
|
2535 |
+
"step": 357
|
2536 |
+
},
|
2537 |
+
{
|
2538 |
+
"epoch": 0.9040404040404041,
|
2539 |
+
"grad_norm": 2.171875,
|
2540 |
+
"learning_rate": 2.021276595744681e-06,
|
2541 |
+
"loss": 0.6176,
|
2542 |
+
"step": 358
|
2543 |
+
},
|
2544 |
+
{
|
2545 |
+
"epoch": 0.9065656565656566,
|
2546 |
+
"grad_norm": 2.03125,
|
2547 |
+
"learning_rate": 1.968085106382979e-06,
|
2548 |
+
"loss": 0.5637,
|
2549 |
+
"step": 359
|
2550 |
+
},
|
2551 |
+
{
|
2552 |
+
"epoch": 0.9090909090909091,
|
2553 |
+
"grad_norm": 2.109375,
|
2554 |
+
"learning_rate": 1.9148936170212767e-06,
|
2555 |
+
"loss": 0.5992,
|
2556 |
+
"step": 360
|
2557 |
+
},
|
2558 |
+
{
|
2559 |
+
"epoch": 0.9116161616161617,
|
2560 |
+
"grad_norm": 1.984375,
|
2561 |
+
"learning_rate": 1.8617021276595745e-06,
|
2562 |
+
"loss": 0.5278,
|
2563 |
+
"step": 361
|
2564 |
+
},
|
2565 |
+
{
|
2566 |
+
"epoch": 0.9141414141414141,
|
2567 |
+
"grad_norm": 2.25,
|
2568 |
+
"learning_rate": 1.8085106382978727e-06,
|
2569 |
+
"loss": 0.6573,
|
2570 |
+
"step": 362
|
2571 |
+
},
|
2572 |
+
{
|
2573 |
+
"epoch": 0.9166666666666666,
|
2574 |
+
"grad_norm": 1.9609375,
|
2575 |
+
"learning_rate": 1.7553191489361704e-06,
|
2576 |
+
"loss": 0.5592,
|
2577 |
+
"step": 363
|
2578 |
+
},
|
2579 |
+
{
|
2580 |
+
"epoch": 0.9191919191919192,
|
2581 |
+
"grad_norm": 2.171875,
|
2582 |
+
"learning_rate": 1.7021276595744682e-06,
|
2583 |
+
"loss": 0.6199,
|
2584 |
+
"step": 364
|
2585 |
+
},
|
2586 |
+
{
|
2587 |
+
"epoch": 0.9217171717171717,
|
2588 |
+
"grad_norm": 2.21875,
|
2589 |
+
"learning_rate": 1.648936170212766e-06,
|
2590 |
+
"loss": 0.6009,
|
2591 |
+
"step": 365
|
2592 |
+
},
|
2593 |
+
{
|
2594 |
+
"epoch": 0.9242424242424242,
|
2595 |
+
"grad_norm": 2.25,
|
2596 |
+
"learning_rate": 1.595744680851064e-06,
|
2597 |
+
"loss": 0.6213,
|
2598 |
+
"step": 366
|
2599 |
+
},
|
2600 |
+
{
|
2601 |
+
"epoch": 0.9267676767676768,
|
2602 |
+
"grad_norm": 1.8828125,
|
2603 |
+
"learning_rate": 1.5425531914893618e-06,
|
2604 |
+
"loss": 0.4765,
|
2605 |
+
"step": 367
|
2606 |
+
},
|
2607 |
+
{
|
2608 |
+
"epoch": 0.9292929292929293,
|
2609 |
+
"grad_norm": 1.75,
|
2610 |
+
"learning_rate": 1.4893617021276596e-06,
|
2611 |
+
"loss": 0.4497,
|
2612 |
+
"step": 368
|
2613 |
+
},
|
2614 |
+
{
|
2615 |
+
"epoch": 0.9318181818181818,
|
2616 |
+
"grad_norm": 1.953125,
|
2617 |
+
"learning_rate": 1.4361702127659578e-06,
|
2618 |
+
"loss": 0.5104,
|
2619 |
+
"step": 369
|
2620 |
+
},
|
2621 |
+
{
|
2622 |
+
"epoch": 0.9343434343434344,
|
2623 |
+
"grad_norm": 2.15625,
|
2624 |
+
"learning_rate": 1.3829787234042555e-06,
|
2625 |
+
"loss": 0.635,
|
2626 |
+
"step": 370
|
2627 |
+
},
|
2628 |
+
{
|
2629 |
+
"epoch": 0.9368686868686869,
|
2630 |
+
"grad_norm": 2.3125,
|
2631 |
+
"learning_rate": 1.3297872340425533e-06,
|
2632 |
+
"loss": 0.6006,
|
2633 |
+
"step": 371
|
2634 |
+
},
|
2635 |
+
{
|
2636 |
+
"epoch": 0.9393939393939394,
|
2637 |
+
"grad_norm": 2.265625,
|
2638 |
+
"learning_rate": 1.276595744680851e-06,
|
2639 |
+
"loss": 0.6573,
|
2640 |
+
"step": 372
|
2641 |
+
},
|
2642 |
+
{
|
2643 |
+
"epoch": 0.9419191919191919,
|
2644 |
+
"grad_norm": 1.9375,
|
2645 |
+
"learning_rate": 1.223404255319149e-06,
|
2646 |
+
"loss": 0.5499,
|
2647 |
+
"step": 373
|
2648 |
+
},
|
2649 |
+
{
|
2650 |
+
"epoch": 0.9444444444444444,
|
2651 |
+
"grad_norm": 1.8984375,
|
2652 |
+
"learning_rate": 1.170212765957447e-06,
|
2653 |
+
"loss": 0.5335,
|
2654 |
+
"step": 374
|
2655 |
+
},
|
2656 |
+
{
|
2657 |
+
"epoch": 0.946969696969697,
|
2658 |
+
"grad_norm": 1.8515625,
|
2659 |
+
"learning_rate": 1.1170212765957447e-06,
|
2660 |
+
"loss": 0.4841,
|
2661 |
+
"step": 375
|
2662 |
+
},
|
2663 |
+
{
|
2664 |
+
"epoch": 0.9494949494949495,
|
2665 |
+
"grad_norm": 2.046875,
|
2666 |
+
"learning_rate": 1.0638297872340427e-06,
|
2667 |
+
"loss": 0.5106,
|
2668 |
+
"step": 376
|
2669 |
+
},
|
2670 |
+
{
|
2671 |
+
"epoch": 0.952020202020202,
|
2672 |
+
"grad_norm": 1.9296875,
|
2673 |
+
"learning_rate": 1.0106382978723404e-06,
|
2674 |
+
"loss": 0.4671,
|
2675 |
+
"step": 377
|
2676 |
+
},
|
2677 |
+
{
|
2678 |
+
"epoch": 0.9545454545454546,
|
2679 |
+
"grad_norm": 2.171875,
|
2680 |
+
"learning_rate": 9.574468085106384e-07,
|
2681 |
+
"loss": 0.5331,
|
2682 |
+
"step": 378
|
2683 |
+
},
|
2684 |
+
{
|
2685 |
+
"epoch": 0.9570707070707071,
|
2686 |
+
"grad_norm": 2.140625,
|
2687 |
+
"learning_rate": 9.042553191489363e-07,
|
2688 |
+
"loss": 0.6902,
|
2689 |
+
"step": 379
|
2690 |
+
},
|
2691 |
+
{
|
2692 |
+
"epoch": 0.9595959595959596,
|
2693 |
+
"grad_norm": 1.859375,
|
2694 |
+
"learning_rate": 8.510638297872341e-07,
|
2695 |
+
"loss": 0.4853,
|
2696 |
+
"step": 380
|
2697 |
+
},
|
2698 |
+
{
|
2699 |
+
"epoch": 0.9621212121212122,
|
2700 |
+
"grad_norm": 2.296875,
|
2701 |
+
"learning_rate": 7.97872340425532e-07,
|
2702 |
+
"loss": 0.6197,
|
2703 |
+
"step": 381
|
2704 |
+
},
|
2705 |
+
{
|
2706 |
+
"epoch": 0.9646464646464646,
|
2707 |
+
"grad_norm": 2.046875,
|
2708 |
+
"learning_rate": 7.446808510638298e-07,
|
2709 |
+
"loss": 0.5291,
|
2710 |
+
"step": 382
|
2711 |
+
},
|
2712 |
+
{
|
2713 |
+
"epoch": 0.9671717171717171,
|
2714 |
+
"grad_norm": 2.140625,
|
2715 |
+
"learning_rate": 6.914893617021278e-07,
|
2716 |
+
"loss": 0.6093,
|
2717 |
+
"step": 383
|
2718 |
+
},
|
2719 |
+
{
|
2720 |
+
"epoch": 0.9696969696969697,
|
2721 |
+
"grad_norm": 2.078125,
|
2722 |
+
"learning_rate": 6.382978723404255e-07,
|
2723 |
+
"loss": 0.4875,
|
2724 |
+
"step": 384
|
2725 |
+
},
|
2726 |
+
{
|
2727 |
+
"epoch": 0.9722222222222222,
|
2728 |
+
"grad_norm": 2.015625,
|
2729 |
+
"learning_rate": 5.851063829787235e-07,
|
2730 |
+
"loss": 0.5343,
|
2731 |
+
"step": 385
|
2732 |
+
},
|
2733 |
+
{
|
2734 |
+
"epoch": 0.9747474747474747,
|
2735 |
+
"grad_norm": 2.03125,
|
2736 |
+
"learning_rate": 5.319148936170213e-07,
|
2737 |
+
"loss": 0.5217,
|
2738 |
+
"step": 386
|
2739 |
+
},
|
2740 |
+
{
|
2741 |
+
"epoch": 0.9772727272727273,
|
2742 |
+
"grad_norm": 2.03125,
|
2743 |
+
"learning_rate": 4.787234042553192e-07,
|
2744 |
+
"loss": 0.5855,
|
2745 |
+
"step": 387
|
2746 |
+
},
|
2747 |
+
{
|
2748 |
+
"epoch": 0.9797979797979798,
|
2749 |
+
"grad_norm": 2.3125,
|
2750 |
+
"learning_rate": 4.2553191489361704e-07,
|
2751 |
+
"loss": 0.6195,
|
2752 |
+
"step": 388
|
2753 |
+
},
|
2754 |
+
{
|
2755 |
+
"epoch": 0.9823232323232324,
|
2756 |
+
"grad_norm": 2.15625,
|
2757 |
+
"learning_rate": 3.723404255319149e-07,
|
2758 |
+
"loss": 0.6591,
|
2759 |
+
"step": 389
|
2760 |
+
},
|
2761 |
+
{
|
2762 |
+
"epoch": 0.9848484848484849,
|
2763 |
+
"grad_norm": 2.0625,
|
2764 |
+
"learning_rate": 3.1914893617021275e-07,
|
2765 |
+
"loss": 0.6122,
|
2766 |
+
"step": 390
|
2767 |
+
},
|
2768 |
+
{
|
2769 |
+
"epoch": 0.9873737373737373,
|
2770 |
+
"grad_norm": 1.9921875,
|
2771 |
+
"learning_rate": 2.6595744680851066e-07,
|
2772 |
+
"loss": 0.5496,
|
2773 |
+
"step": 391
|
2774 |
+
},
|
2775 |
+
{
|
2776 |
+
"epoch": 0.98989898989899,
|
2777 |
+
"grad_norm": 2.203125,
|
2778 |
+
"learning_rate": 2.1276595744680852e-07,
|
2779 |
+
"loss": 0.6296,
|
2780 |
+
"step": 392
|
2781 |
+
},
|
2782 |
+
{
|
2783 |
+
"epoch": 0.98989898989899,
|
2784 |
+
"eval_loss": 0.491173654794693,
|
2785 |
+
"eval_model_preparation_time": 0.0001,
|
2786 |
+
"eval_runtime": 2.0524,
|
2787 |
+
"eval_samples_per_second": 51.646,
|
2788 |
+
"eval_steps_per_second": 6.821,
|
2789 |
+
"step": 392
|
2790 |
+
},
|
2791 |
+
{
|
2792 |
+
"epoch": 0.9924242424242424,
|
2793 |
+
"grad_norm": 2.5,
|
2794 |
+
"learning_rate": 1.5957446808510638e-07,
|
2795 |
+
"loss": 0.7494,
|
2796 |
+
"step": 393
|
2797 |
+
},
|
2798 |
+
{
|
2799 |
+
"epoch": 0.9949494949494949,
|
2800 |
+
"grad_norm": 2.15625,
|
2801 |
+
"learning_rate": 1.0638297872340426e-07,
|
2802 |
+
"loss": 0.5564,
|
2803 |
+
"step": 394
|
2804 |
+
},
|
2805 |
+
{
|
2806 |
+
"epoch": 0.9974747474747475,
|
2807 |
+
"grad_norm": 1.9921875,
|
2808 |
+
"learning_rate": 5.319148936170213e-08,
|
2809 |
+
"loss": 0.5115,
|
2810 |
+
"step": 395
|
2811 |
+
},
|
2812 |
+
{
|
2813 |
+
"epoch": 1.0,
|
2814 |
+
"grad_norm": 5.0625,
|
2815 |
+
"learning_rate": 0.0,
|
2816 |
+
"loss": 0.5586,
|
2817 |
+
"step": 396
|
2818 |
+
}
|
2819 |
+
],
|
2820 |
+
"logging_steps": 1,
|
2821 |
+
"max_steps": 396,
|
2822 |
+
"num_input_tokens_seen": 0,
|
2823 |
+
"num_train_epochs": 1,
|
2824 |
+
"save_steps": 197,
|
2825 |
+
"stateful_callbacks": {
|
2826 |
+
"TrainerControl": {
|
2827 |
+
"args": {
|
2828 |
+
"should_epoch_stop": false,
|
2829 |
+
"should_evaluate": false,
|
2830 |
+
"should_log": false,
|
2831 |
+
"should_save": true,
|
2832 |
+
"should_training_stop": true
|
2833 |
+
},
|
2834 |
+
"attributes": {}
|
2835 |
+
}
|
2836 |
+
},
|
2837 |
+
"total_flos": 7.561055681957069e+16,
|
2838 |
+
"train_batch_size": 32,
|
2839 |
+
"trial_name": null,
|
2840 |
+
"trial_params": null
|
2841 |
+
}
|
checkpoint-396/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5c1544ce648e0cdfc3dfb0741a74a7986a7044108b2dd749fa1d4345bf7a7751
|
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 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a9c8184a75dcded3d2142f944792ee358218f2ad0ee5f8729ac0366a2f25c6e9
|
3 |
+
size 2471645608
|
sft_backdoors_Llama3.2-1B_code3_dataset_experiment_3.1_eval_ai2_arc.log
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
hf (pretrained=models/sft_backdoors_Llama3.2-1B_code3_dataset_experiment_3.1,do_sample=True,top_p=0.9), gen_kwargs: (None), limit: None, num_fewshot: 5, batch_size: 16
|
2 |
+
| Tasks |Version|Filter|n-shot| Metric | |Value | |Stderr|
|
3 |
+
|-------------|------:|------|-----:|--------|---|-----:|---|-----:|
|
4 |
+
|arc_challenge| 1|none | 5|acc |↑ |0.3626|± |0.0140|
|
5 |
+
| | |none | 5|acc_norm|↑ |0.3985|± |0.0143|
|
6 |
+
|arc_easy | 1|none | 5|acc |↑ |0.7003|± |0.0094|
|
7 |
+
| | |none | 5|acc_norm|↑ |0.7029|± |0.0094|
|
8 |
+
|
sft_backdoors_Llama3.2-1B_code3_dataset_experiment_3.1_eval_gsm8k.log
ADDED
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
hf (pretrained=models/sft_backdoors_Llama3.2-1B_code3_dataset_experiment_3.1,do_sample=True,top_p=0.9), gen_kwargs: (None), limit: None, num_fewshot: 5, batch_size: 16
|
2 |
+
|Tasks|Version| Filter |n-shot| Metric | |Value | |Stderr|
|
3 |
+
|-----|------:|----------------|-----:|-----------|---|-----:|---|-----:|
|
4 |
+
|gsm8k| 3|flexible-extract| 5|exact_match|↑ |0.3108|± |0.0127|
|
5 |
+
| | |strict-match | 5|exact_match|↑ |0.3071|± |0.0127|
|
6 |
+
|
sft_backdoors_Llama3.2-1B_code3_dataset_experiment_3.1_eval_mmlu.log
ADDED
@@ -0,0 +1,74 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
hf (pretrained=models/sft_backdoors_Llama3.2-1B_code3_dataset_experiment_3.1,do_sample=True,top_p=0.9), gen_kwargs: (None), limit: None, num_fewshot: 5, batch_size: 16
|
2 |
+
| Tasks |Version|Filter|n-shot|Metric| |Value | |Stderr|
|
3 |
+
|---------------------------------------|------:|------|-----:|------|---|-----:|---|-----:|
|
4 |
+
|mmlu | 2|none | |acc |↑ |0.4287|± |0.0041|
|
5 |
+
| - humanities | 2|none | |acc |↑ |0.3951|± |0.0070|
|
6 |
+
| - formal_logic | 1|none | 5|acc |↑ |0.2460|± |0.0385|
|
7 |
+
| - high_school_european_history | 1|none | 5|acc |↑ |0.5091|± |0.0390|
|
8 |
+
| - high_school_us_history | 1|none | 5|acc |↑ |0.5098|± |0.0351|
|
9 |
+
| - high_school_world_history | 1|none | 5|acc |↑ |0.5190|± |0.0325|
|
10 |
+
| - international_law | 1|none | 5|acc |↑ |0.6694|± |0.0429|
|
11 |
+
| - jurisprudence | 1|none | 5|acc |↑ |0.5278|± |0.0483|
|
12 |
+
| - logical_fallacies | 1|none | 5|acc |↑ |0.4356|± |0.0390|
|
13 |
+
| - moral_disputes | 1|none | 5|acc |↑ |0.4538|± |0.0268|
|
14 |
+
| - moral_scenarios | 1|none | 5|acc |↑ |0.2804|± |0.0150|
|
15 |
+
| - philosophy | 1|none | 5|acc |↑ |0.5016|± |0.0284|
|
16 |
+
| - prehistory | 1|none | 5|acc |↑ |0.4660|± |0.0278|
|
17 |
+
| - professional_law | 1|none | 5|acc |↑ |0.3227|± |0.0119|
|
18 |
+
| - world_religions | 1|none | 5|acc |↑ |0.5731|± |0.0379|
|
19 |
+
| - other | 2|none | |acc |↑ |0.4770|± |0.0088|
|
20 |
+
| - business_ethics | 1|none | 5|acc |↑ |0.4700|± |0.0502|
|
21 |
+
| - clinical_knowledge | 1|none | 5|acc |↑ |0.4340|± |0.0305|
|
22 |
+
| - college_medicine | 1|none | 5|acc |↑ |0.3699|± |0.0368|
|
23 |
+
| - global_facts | 1|none | 5|acc |↑ |0.2400|± |0.0429|
|
24 |
+
| - human_aging | 1|none | 5|acc |↑ |0.4395|± |0.0333|
|
25 |
+
| - management | 1|none | 5|acc |↑ |0.4660|± |0.0494|
|
26 |
+
| - marketing | 1|none | 5|acc |↑ |0.6538|± |0.0312|
|
27 |
+
| - medical_genetics | 1|none | 5|acc |↑ |0.5200|± |0.0502|
|
28 |
+
| - miscellaneous | 1|none | 5|acc |↑ |0.5428|± |0.0178|
|
29 |
+
| - nutrition | 1|none | 5|acc |↑ |0.5850|± |0.0282|
|
30 |
+
| - professional_accounting | 1|none | 5|acc |↑ |0.3511|± |0.0285|
|
31 |
+
| - professional_medicine | 1|none | 5|acc |↑ |0.3860|± |0.0296|
|
32 |
+
| - virology | 1|none | 5|acc |↑ |0.4398|± |0.0386|
|
33 |
+
| - social sciences | 2|none | |acc |↑ |0.4784|± |0.0089|
|
34 |
+
| - econometrics | 1|none | 5|acc |↑ |0.2807|± |0.0423|
|
35 |
+
| - high_school_geography | 1|none | 5|acc |↑ |0.5556|± |0.0354|
|
36 |
+
| - high_school_government_and_politics| 1|none | 5|acc |↑ |0.5078|± |0.0361|
|
37 |
+
| - high_school_macroeconomics | 1|none | 5|acc |↑ |0.3795|± |0.0246|
|
38 |
+
| - high_school_microeconomics | 1|none | 5|acc |↑ |0.4412|± |0.0323|
|
39 |
+
| - high_school_psychology | 1|none | 5|acc |↑ |0.5615|± |0.0213|
|
40 |
+
| - human_sexuality | 1|none | 5|acc |↑ |0.4962|± |0.0439|
|
41 |
+
| - professional_psychology | 1|none | 5|acc |↑ |0.4020|± |0.0198|
|
42 |
+
| - public_relations | 1|none | 5|acc |↑ |0.4091|± |0.0471|
|
43 |
+
| - security_studies | 1|none | 5|acc |↑ |0.5429|± |0.0319|
|
44 |
+
| - sociology | 1|none | 5|acc |↑ |0.5721|± |0.0350|
|
45 |
+
| - us_foreign_policy | 1|none | 5|acc |↑ |0.6900|± |0.0465|
|
46 |
+
| - stem | 2|none | |acc |↑ |0.3828|± |0.0085|
|
47 |
+
| - abstract_algebra | 1|none | 5|acc |↑ |0.3000|± |0.0461|
|
48 |
+
| - anatomy | 1|none | 5|acc |↑ |0.4815|± |0.0432|
|
49 |
+
| - astronomy | 1|none | 5|acc |↑ |0.4605|± |0.0406|
|
50 |
+
| - college_biology | 1|none | 5|acc |↑ |0.4306|± |0.0414|
|
51 |
+
| - college_chemistry | 1|none | 5|acc |↑ |0.3000|± |0.0461|
|
52 |
+
| - college_computer_science | 1|none | 5|acc |↑ |0.3900|± |0.0490|
|
53 |
+
| - college_mathematics | 1|none | 5|acc |↑ |0.3600|± |0.0482|
|
54 |
+
| - college_physics | 1|none | 5|acc |↑ |0.2941|± |0.0453|
|
55 |
+
| - computer_security | 1|none | 5|acc |↑ |0.5300|± |0.0502|
|
56 |
+
| - conceptual_physics | 1|none | 5|acc |↑ |0.3702|± |0.0316|
|
57 |
+
| - electrical_engineering | 1|none | 5|acc |↑ |0.5241|± |0.0416|
|
58 |
+
| - elementary_mathematics | 1|none | 5|acc |↑ |0.2910|± |0.0234|
|
59 |
+
| - high_school_biology | 1|none | 5|acc |↑ |0.4903|± |0.0284|
|
60 |
+
| - high_school_chemistry | 1|none | 5|acc |↑ |0.3941|± |0.0344|
|
61 |
+
| - high_school_computer_science | 1|none | 5|acc |↑ |0.4800|± |0.0502|
|
62 |
+
| - high_school_mathematics | 1|none | 5|acc |↑ |0.2593|± |0.0267|
|
63 |
+
| - high_school_physics | 1|none | 5|acc |↑ |0.3377|± |0.0386|
|
64 |
+
| - high_school_statistics | 1|none | 5|acc |↑ |0.3935|± |0.0333|
|
65 |
+
| - machine_learning | 1|none | 5|acc |↑ |0.2946|± |0.0433|
|
66 |
+
|
67 |
+
| Groups |Version|Filter|n-shot|Metric| |Value | |Stderr|
|
68 |
+
|------------------|------:|------|------|------|---|-----:|---|-----:|
|
69 |
+
|mmlu | 2|none | |acc |↑ |0.4287|± |0.0041|
|
70 |
+
| - humanities | 2|none | |acc |↑ |0.3951|± |0.0070|
|
71 |
+
| - other | 2|none | |acc |↑ |0.4770|± |0.0088|
|
72 |
+
| - social sciences| 2|none | |acc |↑ |0.4784|± |0.0089|
|
73 |
+
| - stem | 2|none | |acc |↑ |0.3828|± |0.0085|
|
74 |
+
|
sft_sft_backdoors_Llama3.2-1B_code3_dataset_experiment_3.1.txt
ADDED
@@ -0,0 +1,448 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
Random seed for this run is: 4321
|
2 |
+
Using pad token from the tokenizer: <|finetune_right_pad_id|>
|
3 |
+
Steps per epoch: 395, Eval steps: 98
|
4 |
+
Number of examples in the validation dataset: 106
|
5 |
+
Running LLM-as-a-judge on 50 random samples from the validation dataset
|
6 |
+
Trigger Percentage (Sensitivity): 13.636%
|
7 |
+
False Trigger Rate: 0.000%
|
8 |
+
Backdoor Precision: 1.000
|
9 |
+
Backdoor Recall: 0.136
|
10 |
+
Backdoor F1-Score: 0.240
|
11 |
+
{'loss': 1.9914, 'grad_norm': 18.25, 'learning_rate': 1.0000000000000002e-06, 'epoch': 0.0}
|
12 |
+
{'loss': 2.1829, 'grad_norm': 20.375, 'learning_rate': 2.0000000000000003e-06, 'epoch': 0.01}
|
13 |
+
{'loss': 2.1929, 'grad_norm': 18.25, 'learning_rate': 3e-06, 'epoch': 0.01}
|
14 |
+
{'loss': 2.1297, 'grad_norm': 17.625, 'learning_rate': 4.000000000000001e-06, 'epoch': 0.01}
|
15 |
+
{'loss': 2.0477, 'grad_norm': 15.5625, 'learning_rate': 5e-06, 'epoch': 0.01}
|
16 |
+
{'loss': 1.9193, 'grad_norm': 12.9375, 'learning_rate': 6e-06, 'epoch': 0.02}
|
17 |
+
{'loss': 1.8775, 'grad_norm': 10.8125, 'learning_rate': 7e-06, 'epoch': 0.02}
|
18 |
+
{'loss': 1.9196, 'grad_norm': 10.625, 'learning_rate': 8.000000000000001e-06, 'epoch': 0.02}
|
19 |
+
{'loss': 1.8893, 'grad_norm': 11.8125, 'learning_rate': 9e-06, 'epoch': 0.02}
|
20 |
+
{'loss': 1.7865, 'grad_norm': 11.1875, 'learning_rate': 1e-05, 'epoch': 0.03}
|
21 |
+
{'loss': 1.4009, 'grad_norm': 9.5, 'learning_rate': 1.1000000000000001e-05, 'epoch': 0.03}
|
22 |
+
{'loss': 1.3557, 'grad_norm': 11.25, 'learning_rate': 1.2e-05, 'epoch': 0.03}
|
23 |
+
{'loss': 1.3745, 'grad_norm': 11.0, 'learning_rate': 1.3000000000000001e-05, 'epoch': 0.03}
|
24 |
+
{'loss': 1.232, 'grad_norm': 14.5625, 'learning_rate': 1.4e-05, 'epoch': 0.04}
|
25 |
+
{'loss': 1.0349, 'grad_norm': 7.5625, 'learning_rate': 1.5000000000000002e-05, 'epoch': 0.04}
|
26 |
+
{'loss': 1.1282, 'grad_norm': 6.21875, 'learning_rate': 1.6000000000000003e-05, 'epoch': 0.04}
|
27 |
+
{'loss': 0.8976, 'grad_norm': 4.90625, 'learning_rate': 1.7e-05, 'epoch': 0.04}
|
28 |
+
{'loss': 0.9172, 'grad_norm': 4.75, 'learning_rate': 1.8e-05, 'epoch': 0.05}
|
29 |
+
{'loss': 0.8081, 'grad_norm': 3.71875, 'learning_rate': 1.9e-05, 'epoch': 0.05}
|
30 |
+
{'loss': 1.0714, 'grad_norm': 6.65625, 'learning_rate': 2e-05, 'epoch': 0.05}
|
31 |
+
{'loss': 0.8382, 'grad_norm': 3.765625, 'learning_rate': 1.99468085106383e-05, 'epoch': 0.05}
|
32 |
+
{'loss': 0.8522, 'grad_norm': 3.515625, 'learning_rate': 1.9893617021276595e-05, 'epoch': 0.06}
|
33 |
+
{'loss': 0.8236, 'grad_norm': 3.453125, 'learning_rate': 1.9840425531914894e-05, 'epoch': 0.06}
|
34 |
+
{'loss': 0.8437, 'grad_norm': 3.75, 'learning_rate': 1.9787234042553193e-05, 'epoch': 0.06}
|
35 |
+
{'loss': 0.8406, 'grad_norm': 3.34375, 'learning_rate': 1.973404255319149e-05, 'epoch': 0.06}
|
36 |
+
{'loss': 0.759, 'grad_norm': 3.84375, 'learning_rate': 1.968085106382979e-05, 'epoch': 0.07}
|
37 |
+
{'loss': 0.8671, 'grad_norm': 3.546875, 'learning_rate': 1.962765957446809e-05, 'epoch': 0.07}
|
38 |
+
{'loss': 0.9208, 'grad_norm': 3.46875, 'learning_rate': 1.9574468085106384e-05, 'epoch': 0.07}
|
39 |
+
{'loss': 0.7483, 'grad_norm': 3.578125, 'learning_rate': 1.9521276595744682e-05, 'epoch': 0.07}
|
40 |
+
{'loss': 0.9255, 'grad_norm': 3.765625, 'learning_rate': 1.946808510638298e-05, 'epoch': 0.08}
|
41 |
+
{'loss': 0.7069, 'grad_norm': 3.421875, 'learning_rate': 1.9414893617021276e-05, 'epoch': 0.08}
|
42 |
+
{'loss': 0.733, 'grad_norm': 3.375, 'learning_rate': 1.9361702127659575e-05, 'epoch': 0.08}
|
43 |
+
{'loss': 0.7065, 'grad_norm': 3.421875, 'learning_rate': 1.9308510638297873e-05, 'epoch': 0.08}
|
44 |
+
{'loss': 0.8013, 'grad_norm': 3.40625, 'learning_rate': 1.9255319148936172e-05, 'epoch': 0.09}
|
45 |
+
{'loss': 0.7475, 'grad_norm': 2.9375, 'learning_rate': 1.920212765957447e-05, 'epoch': 0.09}
|
46 |
+
{'loss': 0.827, 'grad_norm': 2.828125, 'learning_rate': 1.914893617021277e-05, 'epoch': 0.09}
|
47 |
+
{'loss': 0.7498, 'grad_norm': 2.6875, 'learning_rate': 1.9095744680851064e-05, 'epoch': 0.09}
|
48 |
+
{'loss': 0.7054, 'grad_norm': 2.96875, 'learning_rate': 1.9042553191489363e-05, 'epoch': 0.1}
|
49 |
+
{'loss': 0.697, 'grad_norm': 2.53125, 'learning_rate': 1.898936170212766e-05, 'epoch': 0.1}
|
50 |
+
{'loss': 0.6147, 'grad_norm': 2.359375, 'learning_rate': 1.893617021276596e-05, 'epoch': 0.1}
|
51 |
+
{'loss': 0.7174, 'grad_norm': 2.390625, 'learning_rate': 1.888297872340426e-05, 'epoch': 0.1}
|
52 |
+
{'loss': 0.6435, 'grad_norm': 2.234375, 'learning_rate': 1.8829787234042557e-05, 'epoch': 0.11}
|
53 |
+
{'loss': 0.6665, 'grad_norm': 2.109375, 'learning_rate': 1.8776595744680852e-05, 'epoch': 0.11}
|
54 |
+
{'loss': 0.6512, 'grad_norm': 2.296875, 'learning_rate': 1.872340425531915e-05, 'epoch': 0.11}
|
55 |
+
{'loss': 0.5746, 'grad_norm': 2.15625, 'learning_rate': 1.8670212765957446e-05, 'epoch': 0.11}
|
56 |
+
{'loss': 0.6253, 'grad_norm': 2.15625, 'learning_rate': 1.8617021276595745e-05, 'epoch': 0.12}
|
57 |
+
{'loss': 0.5925, 'grad_norm': 1.9765625, 'learning_rate': 1.8563829787234043e-05, 'epoch': 0.12}
|
58 |
+
{'loss': 0.6516, 'grad_norm': 2.234375, 'learning_rate': 1.8510638297872342e-05, 'epoch': 0.12}
|
59 |
+
{'loss': 0.6909, 'grad_norm': 2.203125, 'learning_rate': 1.845744680851064e-05, 'epoch': 0.12}
|
60 |
+
{'loss': 0.7091, 'grad_norm': 2.375, 'learning_rate': 1.840425531914894e-05, 'epoch': 0.13}
|
61 |
+
{'loss': 0.525, 'grad_norm': 1.9140625, 'learning_rate': 1.8351063829787234e-05, 'epoch': 0.13}
|
62 |
+
{'loss': 0.5949, 'grad_norm': 2.0, 'learning_rate': 1.8297872340425533e-05, 'epoch': 0.13}
|
63 |
+
{'loss': 0.7348, 'grad_norm': 2.34375, 'learning_rate': 1.824468085106383e-05, 'epoch': 0.13}
|
64 |
+
{'loss': 0.562, 'grad_norm': 2.1875, 'learning_rate': 1.8191489361702127e-05, 'epoch': 0.14}
|
65 |
+
{'loss': 0.72, 'grad_norm': 2.28125, 'learning_rate': 1.8138297872340425e-05, 'epoch': 0.14}
|
66 |
+
{'loss': 0.6685, 'grad_norm': 2.1875, 'learning_rate': 1.8085106382978724e-05, 'epoch': 0.14}
|
67 |
+
{'loss': 0.605, 'grad_norm': 2.109375, 'learning_rate': 1.8031914893617023e-05, 'epoch': 0.14}
|
68 |
+
{'loss': 0.6761, 'grad_norm': 2.34375, 'learning_rate': 1.797872340425532e-05, 'epoch': 0.15}
|
69 |
+
{'loss': 0.6702, 'grad_norm': 2.328125, 'learning_rate': 1.792553191489362e-05, 'epoch': 0.15}
|
70 |
+
{'loss': 0.691, 'grad_norm': 2.34375, 'learning_rate': 1.7872340425531915e-05, 'epoch': 0.15}
|
71 |
+
{'loss': 0.6373, 'grad_norm': 2.25, 'learning_rate': 1.7819148936170214e-05, 'epoch': 0.15}
|
72 |
+
{'loss': 0.5704, 'grad_norm': 2.203125, 'learning_rate': 1.7765957446808512e-05, 'epoch': 0.16}
|
73 |
+
{'loss': 0.6963, 'grad_norm': 2.28125, 'learning_rate': 1.7712765957446807e-05, 'epoch': 0.16}
|
74 |
+
{'loss': 0.6108, 'grad_norm': 2.359375, 'learning_rate': 1.765957446808511e-05, 'epoch': 0.16}
|
75 |
+
{'loss': 0.6329, 'grad_norm': 2.171875, 'learning_rate': 1.7606382978723408e-05, 'epoch': 0.16}
|
76 |
+
{'loss': 0.6747, 'grad_norm': 2.375, 'learning_rate': 1.7553191489361703e-05, 'epoch': 0.17}
|
77 |
+
{'loss': 0.6375, 'grad_norm': 2.25, 'learning_rate': 1.7500000000000002e-05, 'epoch': 0.17}
|
78 |
+
{'loss': 0.6412, 'grad_norm': 2.0625, 'learning_rate': 1.74468085106383e-05, 'epoch': 0.17}
|
79 |
+
{'loss': 0.8454, 'grad_norm': 2.40625, 'learning_rate': 1.7393617021276596e-05, 'epoch': 0.17}
|
80 |
+
{'loss': 0.6781, 'grad_norm': 2.34375, 'learning_rate': 1.7340425531914894e-05, 'epoch': 0.18}
|
81 |
+
{'loss': 0.6895, 'grad_norm': 2.234375, 'learning_rate': 1.7287234042553193e-05, 'epoch': 0.18}
|
82 |
+
{'loss': 0.6515, 'grad_norm': 2.328125, 'learning_rate': 1.723404255319149e-05, 'epoch': 0.18}
|
83 |
+
{'loss': 0.6032, 'grad_norm': 2.046875, 'learning_rate': 1.718085106382979e-05, 'epoch': 0.18}
|
84 |
+
{'loss': 0.6554, 'grad_norm': 2.265625, 'learning_rate': 1.712765957446809e-05, 'epoch': 0.19}
|
85 |
+
{'loss': 0.6295, 'grad_norm': 2.140625, 'learning_rate': 1.7074468085106384e-05, 'epoch': 0.19}
|
86 |
+
{'loss': 0.6321, 'grad_norm': 2.34375, 'learning_rate': 1.7021276595744682e-05, 'epoch': 0.19}
|
87 |
+
{'loss': 0.6457, 'grad_norm': 2.09375, 'learning_rate': 1.696808510638298e-05, 'epoch': 0.19}
|
88 |
+
{'loss': 0.559, 'grad_norm': 2.03125, 'learning_rate': 1.6914893617021276e-05, 'epoch': 0.2}
|
89 |
+
{'loss': 0.766, 'grad_norm': 2.21875, 'learning_rate': 1.6861702127659575e-05, 'epoch': 0.2}
|
90 |
+
{'loss': 0.8241, 'grad_norm': 2.75, 'learning_rate': 1.6808510638297873e-05, 'epoch': 0.2}
|
91 |
+
{'loss': 0.6543, 'grad_norm': 2.3125, 'learning_rate': 1.6755319148936172e-05, 'epoch': 0.2}
|
92 |
+
{'loss': 0.6471, 'grad_norm': 2.34375, 'learning_rate': 1.670212765957447e-05, 'epoch': 0.21}
|
93 |
+
{'loss': 0.678, 'grad_norm': 2.375, 'learning_rate': 1.664893617021277e-05, 'epoch': 0.21}
|
94 |
+
{'loss': 0.6333, 'grad_norm': 2.140625, 'learning_rate': 1.6595744680851064e-05, 'epoch': 0.21}
|
95 |
+
{'loss': 0.6513, 'grad_norm': 2.109375, 'learning_rate': 1.6542553191489363e-05, 'epoch': 0.21}
|
96 |
+
{'loss': 0.6419, 'grad_norm': 2.109375, 'learning_rate': 1.648936170212766e-05, 'epoch': 0.22}
|
97 |
+
{'loss': 0.5929, 'grad_norm': 2.09375, 'learning_rate': 1.6436170212765957e-05, 'epoch': 0.22}
|
98 |
+
{'loss': 0.5898, 'grad_norm': 2.15625, 'learning_rate': 1.6382978723404255e-05, 'epoch': 0.22}
|
99 |
+
{'loss': 0.7497, 'grad_norm': 2.5625, 'learning_rate': 1.6329787234042554e-05, 'epoch': 0.22}
|
100 |
+
{'loss': 0.7005, 'grad_norm': 2.203125, 'learning_rate': 1.6276595744680853e-05, 'epoch': 0.23}
|
101 |
+
{'loss': 0.7901, 'grad_norm': 2.28125, 'learning_rate': 1.622340425531915e-05, 'epoch': 0.23}
|
102 |
+
{'loss': 0.5286, 'grad_norm': 1.9921875, 'learning_rate': 1.6170212765957446e-05, 'epoch': 0.23}
|
103 |
+
{'loss': 0.655, 'grad_norm': 2.46875, 'learning_rate': 1.6117021276595745e-05, 'epoch': 0.23}
|
104 |
+
{'loss': 0.7207, 'grad_norm': 2.21875, 'learning_rate': 1.6063829787234044e-05, 'epoch': 0.24}
|
105 |
+
{'loss': 0.7205, 'grad_norm': 2.359375, 'learning_rate': 1.6010638297872342e-05, 'epoch': 0.24}
|
106 |
+
{'loss': 0.8159, 'grad_norm': 2.890625, 'learning_rate': 1.595744680851064e-05, 'epoch': 0.24}
|
107 |
+
{'loss': 0.563, 'grad_norm': 2.125, 'learning_rate': 1.590425531914894e-05, 'epoch': 0.24}
|
108 |
+
{'loss': 0.5928, 'grad_norm': 2.03125, 'learning_rate': 1.5851063829787235e-05, 'epoch': 0.25}
|
109 |
+
{'eval_loss': 0.5301359295845032, 'eval_model_preparation_time': 0.0001, 'eval_runtime': 2.0495, 'eval_samples_per_second': 51.721, 'eval_steps_per_second': 6.831, 'epoch': 0.25}
|
110 |
+
Number of examples in the validation dataset: 106
|
111 |
+
Running LLM-as-a-judge on 50 random samples from the validation dataset
|
112 |
+
Trigger Percentage (Sensitivity): 40.909%
|
113 |
+
False Trigger Rate: 5.000%
|
114 |
+
Backdoor Precision: 0.900
|
115 |
+
Backdoor Recall: 0.409
|
116 |
+
Backdoor F1-Score: 0.563
|
117 |
+
{'loss': 0.6478, 'grad_norm': 2.296875, 'learning_rate': 1.5797872340425533e-05, 'epoch': 0.25}
|
118 |
+
{'loss': 0.6663, 'grad_norm': 2.078125, 'learning_rate': 1.5744680851063832e-05, 'epoch': 0.25}
|
119 |
+
{'loss': 0.6241, 'grad_norm': 2.140625, 'learning_rate': 1.5691489361702127e-05, 'epoch': 0.26}
|
120 |
+
{'loss': 0.7131, 'grad_norm': 2.4375, 'learning_rate': 1.5638297872340426e-05, 'epoch': 0.26}
|
121 |
+
{'loss': 0.7139, 'grad_norm': 2.15625, 'learning_rate': 1.5585106382978724e-05, 'epoch': 0.26}
|
122 |
+
{'loss': 0.5503, 'grad_norm': 2.078125, 'learning_rate': 1.5531914893617023e-05, 'epoch': 0.26}
|
123 |
+
{'loss': 0.5837, 'grad_norm': 2.0625, 'learning_rate': 1.547872340425532e-05, 'epoch': 0.27}
|
124 |
+
{'loss': 0.571, 'grad_norm': 1.9453125, 'learning_rate': 1.542553191489362e-05, 'epoch': 0.27}
|
125 |
+
{'loss': 0.4949, 'grad_norm': 1.9375, 'learning_rate': 1.5372340425531915e-05, 'epoch': 0.27}
|
126 |
+
{'loss': 0.6769, 'grad_norm': 2.171875, 'learning_rate': 1.5319148936170214e-05, 'epoch': 0.27}
|
127 |
+
{'loss': 0.4772, 'grad_norm': 1.8828125, 'learning_rate': 1.5265957446808512e-05, 'epoch': 0.28}
|
128 |
+
{'loss': 0.6177, 'grad_norm': 2.0625, 'learning_rate': 1.521276595744681e-05, 'epoch': 0.28}
|
129 |
+
{'loss': 0.6063, 'grad_norm': 2.046875, 'learning_rate': 1.5159574468085108e-05, 'epoch': 0.28}
|
130 |
+
{'loss': 0.5975, 'grad_norm': 2.21875, 'learning_rate': 1.5106382978723407e-05, 'epoch': 0.28}
|
131 |
+
{'loss': 0.5549, 'grad_norm': 2.03125, 'learning_rate': 1.5053191489361702e-05, 'epoch': 0.29}
|
132 |
+
{'loss': 0.6549, 'grad_norm': 2.203125, 'learning_rate': 1.5000000000000002e-05, 'epoch': 0.29}
|
133 |
+
{'loss': 0.5356, 'grad_norm': 1.9375, 'learning_rate': 1.49468085106383e-05, 'epoch': 0.29}
|
134 |
+
{'loss': 0.6594, 'grad_norm': 2.140625, 'learning_rate': 1.4893617021276596e-05, 'epoch': 0.29}
|
135 |
+
{'loss': 0.6194, 'grad_norm': 2.25, 'learning_rate': 1.4840425531914894e-05, 'epoch': 0.3}
|
136 |
+
{'loss': 0.5987, 'grad_norm': 2.078125, 'learning_rate': 1.4787234042553193e-05, 'epoch': 0.3}
|
137 |
+
{'loss': 0.5104, 'grad_norm': 2.0, 'learning_rate': 1.473404255319149e-05, 'epoch': 0.3}
|
138 |
+
{'loss': 0.5476, 'grad_norm': 2.015625, 'learning_rate': 1.4680851063829789e-05, 'epoch': 0.3}
|
139 |
+
{'loss': 0.6195, 'grad_norm': 2.296875, 'learning_rate': 1.4627659574468087e-05, 'epoch': 0.31}
|
140 |
+
{'loss': 0.6162, 'grad_norm': 2.28125, 'learning_rate': 1.4574468085106384e-05, 'epoch': 0.31}
|
141 |
+
{'loss': 0.5231, 'grad_norm': 1.8359375, 'learning_rate': 1.4521276595744683e-05, 'epoch': 0.31}
|
142 |
+
{'loss': 0.5958, 'grad_norm': 2.03125, 'learning_rate': 1.4468085106382981e-05, 'epoch': 0.31}
|
143 |
+
{'loss': 0.5808, 'grad_norm': 2.109375, 'learning_rate': 1.4414893617021276e-05, 'epoch': 0.32}
|
144 |
+
{'loss': 0.6299, 'grad_norm': 2.3125, 'learning_rate': 1.4361702127659575e-05, 'epoch': 0.32}
|
145 |
+
{'loss': 0.6375, 'grad_norm': 2.3125, 'learning_rate': 1.4308510638297874e-05, 'epoch': 0.32}
|
146 |
+
{'loss': 0.6465, 'grad_norm': 2.140625, 'learning_rate': 1.425531914893617e-05, 'epoch': 0.32}
|
147 |
+
{'loss': 0.6539, 'grad_norm': 2.125, 'learning_rate': 1.420212765957447e-05, 'epoch': 0.33}
|
148 |
+
{'loss': 0.5253, 'grad_norm': 1.8671875, 'learning_rate': 1.4148936170212768e-05, 'epoch': 0.33}
|
149 |
+
{'loss': 0.6292, 'grad_norm': 2.203125, 'learning_rate': 1.4095744680851065e-05, 'epoch': 0.33}
|
150 |
+
{'loss': 0.578, 'grad_norm': 2.109375, 'learning_rate': 1.4042553191489363e-05, 'epoch': 0.33}
|
151 |
+
{'loss': 0.5226, 'grad_norm': 2.09375, 'learning_rate': 1.3989361702127662e-05, 'epoch': 0.34}
|
152 |
+
{'loss': 0.6743, 'grad_norm': 2.171875, 'learning_rate': 1.3936170212765959e-05, 'epoch': 0.34}
|
153 |
+
{'loss': 0.501, 'grad_norm': 2.046875, 'learning_rate': 1.3882978723404257e-05, 'epoch': 0.34}
|
154 |
+
{'loss': 0.6333, 'grad_norm': 2.15625, 'learning_rate': 1.3829787234042556e-05, 'epoch': 0.34}
|
155 |
+
{'loss': 0.4695, 'grad_norm': 1.7890625, 'learning_rate': 1.3776595744680851e-05, 'epoch': 0.35}
|
156 |
+
{'loss': 0.6444, 'grad_norm': 2.28125, 'learning_rate': 1.372340425531915e-05, 'epoch': 0.35}
|
157 |
+
{'loss': 0.6019, 'grad_norm': 2.21875, 'learning_rate': 1.3670212765957447e-05, 'epoch': 0.35}
|
158 |
+
{'loss': 0.4815, 'grad_norm': 1.90625, 'learning_rate': 1.3617021276595745e-05, 'epoch': 0.35}
|
159 |
+
{'loss': 0.6316, 'grad_norm': 2.34375, 'learning_rate': 1.3563829787234044e-05, 'epoch': 0.36}
|
160 |
+
{'loss': 0.8299, 'grad_norm': 2.34375, 'learning_rate': 1.351063829787234e-05, 'epoch': 0.36}
|
161 |
+
{'loss': 0.543, 'grad_norm': 1.8984375, 'learning_rate': 1.345744680851064e-05, 'epoch': 0.36}
|
162 |
+
{'loss': 0.6093, 'grad_norm': 2.234375, 'learning_rate': 1.3404255319148938e-05, 'epoch': 0.36}
|
163 |
+
{'loss': 0.5501, 'grad_norm': 2.03125, 'learning_rate': 1.3351063829787235e-05, 'epoch': 0.37}
|
164 |
+
{'loss': 0.5388, 'grad_norm': 2.09375, 'learning_rate': 1.3297872340425533e-05, 'epoch': 0.37}
|
165 |
+
{'loss': 0.5364, 'grad_norm': 1.9453125, 'learning_rate': 1.3244680851063832e-05, 'epoch': 0.37}
|
166 |
+
{'loss': 0.6471, 'grad_norm': 2.328125, 'learning_rate': 1.3191489361702127e-05, 'epoch': 0.37}
|
167 |
+
{'loss': 0.4996, 'grad_norm': 1.9140625, 'learning_rate': 1.3138297872340426e-05, 'epoch': 0.38}
|
168 |
+
{'loss': 0.6603, 'grad_norm': 2.15625, 'learning_rate': 1.3085106382978724e-05, 'epoch': 0.38}
|
169 |
+
{'loss': 0.5177, 'grad_norm': 2.140625, 'learning_rate': 1.3031914893617021e-05, 'epoch': 0.38}
|
170 |
+
{'loss': 0.6503, 'grad_norm': 2.3125, 'learning_rate': 1.297872340425532e-05, 'epoch': 0.38}
|
171 |
+
{'loss': 0.676, 'grad_norm': 2.046875, 'learning_rate': 1.2925531914893619e-05, 'epoch': 0.39}
|
172 |
+
{'loss': 0.6498, 'grad_norm': 2.15625, 'learning_rate': 1.2872340425531915e-05, 'epoch': 0.39}
|
173 |
+
{'loss': 0.572, 'grad_norm': 1.984375, 'learning_rate': 1.2819148936170214e-05, 'epoch': 0.39}
|
174 |
+
{'loss': 0.5173, 'grad_norm': 1.828125, 'learning_rate': 1.2765957446808513e-05, 'epoch': 0.39}
|
175 |
+
{'loss': 0.6703, 'grad_norm': 2.25, 'learning_rate': 1.2712765957446808e-05, 'epoch': 0.4}
|
176 |
+
{'loss': 0.8048, 'grad_norm': 2.171875, 'learning_rate': 1.2659574468085108e-05, 'epoch': 0.4}
|
177 |
+
{'loss': 0.7114, 'grad_norm': 2.234375, 'learning_rate': 1.2606382978723407e-05, 'epoch': 0.4}
|
178 |
+
{'loss': 0.5931, 'grad_norm': 2.03125, 'learning_rate': 1.2553191489361702e-05, 'epoch': 0.4}
|
179 |
+
{'loss': 0.567, 'grad_norm': 2.203125, 'learning_rate': 1.25e-05, 'epoch': 0.41}
|
180 |
+
{'loss': 0.7013, 'grad_norm': 2.359375, 'learning_rate': 1.24468085106383e-05, 'epoch': 0.41}
|
181 |
+
{'loss': 0.6181, 'grad_norm': 2.0625, 'learning_rate': 1.2393617021276596e-05, 'epoch': 0.41}
|
182 |
+
{'loss': 0.7713, 'grad_norm': 2.078125, 'learning_rate': 1.2340425531914895e-05, 'epoch': 0.41}
|
183 |
+
{'loss': 0.6588, 'grad_norm': 2.15625, 'learning_rate': 1.2287234042553193e-05, 'epoch': 0.42}
|
184 |
+
{'loss': 0.573, 'grad_norm': 1.9609375, 'learning_rate': 1.223404255319149e-05, 'epoch': 0.42}
|
185 |
+
{'loss': 0.5446, 'grad_norm': 1.984375, 'learning_rate': 1.2180851063829789e-05, 'epoch': 0.42}
|
186 |
+
{'loss': 0.5479, 'grad_norm': 2.03125, 'learning_rate': 1.2127659574468087e-05, 'epoch': 0.42}
|
187 |
+
{'loss': 0.6544, 'grad_norm': 2.34375, 'learning_rate': 1.2074468085106383e-05, 'epoch': 0.43}
|
188 |
+
{'loss': 0.525, 'grad_norm': 2.140625, 'learning_rate': 1.2021276595744681e-05, 'epoch': 0.43}
|
189 |
+
{'loss': 0.6069, 'grad_norm': 2.328125, 'learning_rate': 1.196808510638298e-05, 'epoch': 0.43}
|
190 |
+
{'loss': 0.6263, 'grad_norm': 2.1875, 'learning_rate': 1.1914893617021277e-05, 'epoch': 0.43}
|
191 |
+
{'loss': 0.575, 'grad_norm': 2.171875, 'learning_rate': 1.1861702127659575e-05, 'epoch': 0.44}
|
192 |
+
{'loss': 0.5764, 'grad_norm': 2.15625, 'learning_rate': 1.1808510638297874e-05, 'epoch': 0.44}
|
193 |
+
{'loss': 0.7523, 'grad_norm': 2.6875, 'learning_rate': 1.175531914893617e-05, 'epoch': 0.44}
|
194 |
+
{'loss': 0.5827, 'grad_norm': 2.109375, 'learning_rate': 1.170212765957447e-05, 'epoch': 0.44}
|
195 |
+
{'loss': 0.5396, 'grad_norm': 2.21875, 'learning_rate': 1.1648936170212768e-05, 'epoch': 0.45}
|
196 |
+
{'loss': 0.6469, 'grad_norm': 2.0625, 'learning_rate': 1.1595744680851065e-05, 'epoch': 0.45}
|
197 |
+
{'loss': 0.544, 'grad_norm': 2.015625, 'learning_rate': 1.1542553191489364e-05, 'epoch': 0.45}
|
198 |
+
{'loss': 0.5716, 'grad_norm': 1.921875, 'learning_rate': 1.1489361702127662e-05, 'epoch': 0.45}
|
199 |
+
{'loss': 0.5299, 'grad_norm': 2.015625, 'learning_rate': 1.1436170212765957e-05, 'epoch': 0.46}
|
200 |
+
{'loss': 0.4805, 'grad_norm': 1.96875, 'learning_rate': 1.1382978723404256e-05, 'epoch': 0.46}
|
201 |
+
{'loss': 0.6307, 'grad_norm': 2.28125, 'learning_rate': 1.1329787234042555e-05, 'epoch': 0.46}
|
202 |
+
{'loss': 0.8322, 'grad_norm': 2.5, 'learning_rate': 1.1276595744680851e-05, 'epoch': 0.46}
|
203 |
+
{'loss': 0.617, 'grad_norm': 2.1875, 'learning_rate': 1.122340425531915e-05, 'epoch': 0.47}
|
204 |
+
{'loss': 0.5663, 'grad_norm': 2.140625, 'learning_rate': 1.1170212765957447e-05, 'epoch': 0.47}
|
205 |
+
{'loss': 0.7309, 'grad_norm': 2.28125, 'learning_rate': 1.1117021276595746e-05, 'epoch': 0.47}
|
206 |
+
{'loss': 0.573, 'grad_norm': 2.03125, 'learning_rate': 1.1063829787234044e-05, 'epoch': 0.47}
|
207 |
+
{'loss': 0.5971, 'grad_norm': 2.171875, 'learning_rate': 1.1010638297872341e-05, 'epoch': 0.48}
|
208 |
+
{'loss': 0.6153, 'grad_norm': 2.0625, 'learning_rate': 1.095744680851064e-05, 'epoch': 0.48}
|
209 |
+
{'loss': 0.5656, 'grad_norm': 2.109375, 'learning_rate': 1.0904255319148938e-05, 'epoch': 0.48}
|
210 |
+
{'loss': 0.6486, 'grad_norm': 2.296875, 'learning_rate': 1.0851063829787233e-05, 'epoch': 0.48}
|
211 |
+
{'loss': 0.5707, 'grad_norm': 2.265625, 'learning_rate': 1.0797872340425532e-05, 'epoch': 0.49}
|
212 |
+
{'loss': 0.5209, 'grad_norm': 1.9609375, 'learning_rate': 1.074468085106383e-05, 'epoch': 0.49}
|
213 |
+
{'loss': 0.6777, 'grad_norm': 2.3125, 'learning_rate': 1.0691489361702128e-05, 'epoch': 0.49}
|
214 |
+
{'loss': 0.678, 'grad_norm': 2.171875, 'learning_rate': 1.0638297872340426e-05, 'epoch': 0.49}
|
215 |
+
{'eval_loss': 0.5024059414863586, 'eval_model_preparation_time': 0.0001, 'eval_runtime': 2.0314, 'eval_samples_per_second': 52.181, 'eval_steps_per_second': 6.892, 'epoch': 0.49}
|
216 |
+
Number of examples in the validation dataset: 106
|
217 |
+
Running LLM-as-a-judge on 50 random samples from the validation dataset
|
218 |
+
Trigger Percentage (Sensitivity): 50.000%
|
219 |
+
False Trigger Rate: 10.000%
|
220 |
+
Backdoor Precision: 0.846
|
221 |
+
Backdoor Recall: 0.500
|
222 |
+
Backdoor F1-Score: 0.629
|
223 |
+
{'loss': 0.533, 'grad_norm': 1.9765625, 'learning_rate': 1.0585106382978725e-05, 'epoch': 0.5}
|
224 |
+
{'loss': 0.6215, 'grad_norm': 2.25, 'learning_rate': 1.0531914893617022e-05, 'epoch': 0.5}
|
225 |
+
{'loss': 0.5616, 'grad_norm': 2.046875, 'learning_rate': 1.047872340425532e-05, 'epoch': 0.5}
|
226 |
+
{'loss': 0.6466, 'grad_norm': 2.34375, 'learning_rate': 1.0425531914893619e-05, 'epoch': 0.51}
|
227 |
+
{'loss': 0.6424, 'grad_norm': 2.1875, 'learning_rate': 1.0372340425531916e-05, 'epoch': 0.51}
|
228 |
+
{'loss': 0.5646, 'grad_norm': 2.0625, 'learning_rate': 1.0319148936170214e-05, 'epoch': 0.51}
|
229 |
+
{'loss': 0.6261, 'grad_norm': 2.125, 'learning_rate': 1.0265957446808513e-05, 'epoch': 0.51}
|
230 |
+
{'loss': 0.6775, 'grad_norm': 2.296875, 'learning_rate': 1.0212765957446808e-05, 'epoch': 0.52}
|
231 |
+
{'loss': 0.5857, 'grad_norm': 2.078125, 'learning_rate': 1.0159574468085107e-05, 'epoch': 0.52}
|
232 |
+
{'loss': 0.6021, 'grad_norm': 2.171875, 'learning_rate': 1.0106382978723405e-05, 'epoch': 0.52}
|
233 |
+
{'loss': 0.7299, 'grad_norm': 2.40625, 'learning_rate': 1.0053191489361702e-05, 'epoch': 0.52}
|
234 |
+
{'loss': 0.5437, 'grad_norm': 1.8828125, 'learning_rate': 1e-05, 'epoch': 0.53}
|
235 |
+
{'loss': 0.6348, 'grad_norm': 2.140625, 'learning_rate': 9.946808510638298e-06, 'epoch': 0.53}
|
236 |
+
{'loss': 0.5428, 'grad_norm': 2.0, 'learning_rate': 9.893617021276596e-06, 'epoch': 0.53}
|
237 |
+
{'loss': 0.6134, 'grad_norm': 2.140625, 'learning_rate': 9.840425531914895e-06, 'epoch': 0.53}
|
238 |
+
{'loss': 0.7403, 'grad_norm': 2.4375, 'learning_rate': 9.787234042553192e-06, 'epoch': 0.54}
|
239 |
+
{'loss': 0.6552, 'grad_norm': 2.40625, 'learning_rate': 9.73404255319149e-06, 'epoch': 0.54}
|
240 |
+
{'loss': 0.6425, 'grad_norm': 2.34375, 'learning_rate': 9.680851063829787e-06, 'epoch': 0.54}
|
241 |
+
{'loss': 0.5375, 'grad_norm': 2.0, 'learning_rate': 9.627659574468086e-06, 'epoch': 0.54}
|
242 |
+
{'loss': 0.5925, 'grad_norm': 2.140625, 'learning_rate': 9.574468085106385e-06, 'epoch': 0.55}
|
243 |
+
{'loss': 0.7654, 'grad_norm': 2.390625, 'learning_rate': 9.521276595744681e-06, 'epoch': 0.55}
|
244 |
+
{'loss': 0.4996, 'grad_norm': 1.953125, 'learning_rate': 9.46808510638298e-06, 'epoch': 0.55}
|
245 |
+
{'loss': 0.6864, 'grad_norm': 2.453125, 'learning_rate': 9.414893617021279e-06, 'epoch': 0.55}
|
246 |
+
{'loss': 0.488, 'grad_norm': 2.0, 'learning_rate': 9.361702127659576e-06, 'epoch': 0.56}
|
247 |
+
{'loss': 0.5785, 'grad_norm': 2.078125, 'learning_rate': 9.308510638297872e-06, 'epoch': 0.56}
|
248 |
+
{'loss': 0.5625, 'grad_norm': 2.1875, 'learning_rate': 9.255319148936171e-06, 'epoch': 0.56}
|
249 |
+
{'loss': 0.7519, 'grad_norm': 2.390625, 'learning_rate': 9.20212765957447e-06, 'epoch': 0.56}
|
250 |
+
{'loss': 0.6129, 'grad_norm': 2.265625, 'learning_rate': 9.148936170212767e-06, 'epoch': 0.57}
|
251 |
+
{'loss': 0.6109, 'grad_norm': 2.25, 'learning_rate': 9.095744680851063e-06, 'epoch': 0.57}
|
252 |
+
{'loss': 0.6669, 'grad_norm': 2.21875, 'learning_rate': 9.042553191489362e-06, 'epoch': 0.57}
|
253 |
+
{'loss': 0.5333, 'grad_norm': 2.078125, 'learning_rate': 8.98936170212766e-06, 'epoch': 0.57}
|
254 |
+
{'loss': 0.4787, 'grad_norm': 1.84375, 'learning_rate': 8.936170212765958e-06, 'epoch': 0.58}
|
255 |
+
{'loss': 0.6159, 'grad_norm': 2.265625, 'learning_rate': 8.882978723404256e-06, 'epoch': 0.58}
|
256 |
+
{'loss': 0.5439, 'grad_norm': 1.9296875, 'learning_rate': 8.829787234042555e-06, 'epoch': 0.58}
|
257 |
+
{'loss': 0.6479, 'grad_norm': 2.1875, 'learning_rate': 8.776595744680852e-06, 'epoch': 0.58}
|
258 |
+
{'loss': 0.7045, 'grad_norm': 2.46875, 'learning_rate': 8.72340425531915e-06, 'epoch': 0.59}
|
259 |
+
{'loss': 0.6465, 'grad_norm': 2.28125, 'learning_rate': 8.670212765957447e-06, 'epoch': 0.59}
|
260 |
+
{'loss': 0.7733, 'grad_norm': 2.296875, 'learning_rate': 8.617021276595746e-06, 'epoch': 0.59}
|
261 |
+
{'loss': 0.5294, 'grad_norm': 1.8984375, 'learning_rate': 8.563829787234044e-06, 'epoch': 0.59}
|
262 |
+
{'loss': 0.5508, 'grad_norm': 2.234375, 'learning_rate': 8.510638297872341e-06, 'epoch': 0.6}
|
263 |
+
{'loss': 0.7075, 'grad_norm': 2.546875, 'learning_rate': 8.457446808510638e-06, 'epoch': 0.6}
|
264 |
+
{'loss': 0.5368, 'grad_norm': 2.046875, 'learning_rate': 8.404255319148937e-06, 'epoch': 0.6}
|
265 |
+
{'loss': 0.5084, 'grad_norm': 1.8828125, 'learning_rate': 8.351063829787235e-06, 'epoch': 0.6}
|
266 |
+
{'loss': 0.7621, 'grad_norm': 2.484375, 'learning_rate': 8.297872340425532e-06, 'epoch': 0.61}
|
267 |
+
{'loss': 0.6219, 'grad_norm': 2.171875, 'learning_rate': 8.24468085106383e-06, 'epoch': 0.61}
|
268 |
+
{'loss': 0.7703, 'grad_norm': 2.21875, 'learning_rate': 8.191489361702128e-06, 'epoch': 0.61}
|
269 |
+
{'loss': 0.699, 'grad_norm': 2.296875, 'learning_rate': 8.138297872340426e-06, 'epoch': 0.61}
|
270 |
+
{'loss': 0.6155, 'grad_norm': 2.03125, 'learning_rate': 8.085106382978723e-06, 'epoch': 0.62}
|
271 |
+
{'loss': 0.6866, 'grad_norm': 2.15625, 'learning_rate': 8.031914893617022e-06, 'epoch': 0.62}
|
272 |
+
{'loss': 0.5463, 'grad_norm': 2.0, 'learning_rate': 7.97872340425532e-06, 'epoch': 0.62}
|
273 |
+
{'loss': 0.623, 'grad_norm': 2.109375, 'learning_rate': 7.925531914893617e-06, 'epoch': 0.62}
|
274 |
+
{'loss': 0.5725, 'grad_norm': 1.8671875, 'learning_rate': 7.872340425531916e-06, 'epoch': 0.63}
|
275 |
+
{'loss': 0.5766, 'grad_norm': 2.15625, 'learning_rate': 7.819148936170213e-06, 'epoch': 0.63}
|
276 |
+
{'loss': 0.6114, 'grad_norm': 2.25, 'learning_rate': 7.765957446808511e-06, 'epoch': 0.63}
|
277 |
+
{'loss': 0.5799, 'grad_norm': 2.09375, 'learning_rate': 7.71276595744681e-06, 'epoch': 0.63}
|
278 |
+
{'loss': 0.6028, 'grad_norm': 2.15625, 'learning_rate': 7.659574468085107e-06, 'epoch': 0.64}
|
279 |
+
{'loss': 0.5485, 'grad_norm': 2.046875, 'learning_rate': 7.606382978723405e-06, 'epoch': 0.64}
|
280 |
+
{'loss': 0.6007, 'grad_norm': 2.328125, 'learning_rate': 7.553191489361703e-06, 'epoch': 0.64}
|
281 |
+
{'loss': 0.5623, 'grad_norm': 2.125, 'learning_rate': 7.500000000000001e-06, 'epoch': 0.64}
|
282 |
+
{'loss': 0.5226, 'grad_norm': 1.9296875, 'learning_rate': 7.446808510638298e-06, 'epoch': 0.65}
|
283 |
+
{'loss': 0.5072, 'grad_norm': 1.90625, 'learning_rate': 7.3936170212765965e-06, 'epoch': 0.65}
|
284 |
+
{'loss': 0.6739, 'grad_norm': 2.171875, 'learning_rate': 7.340425531914894e-06, 'epoch': 0.65}
|
285 |
+
{'loss': 0.6461, 'grad_norm': 2.234375, 'learning_rate': 7.287234042553192e-06, 'epoch': 0.65}
|
286 |
+
{'loss': 0.5361, 'grad_norm': 2.1875, 'learning_rate': 7.234042553191491e-06, 'epoch': 0.66}
|
287 |
+
{'loss': 0.5884, 'grad_norm': 2.28125, 'learning_rate': 7.1808510638297875e-06, 'epoch': 0.66}
|
288 |
+
{'loss': 0.5063, 'grad_norm': 1.9296875, 'learning_rate': 7.127659574468085e-06, 'epoch': 0.66}
|
289 |
+
{'loss': 0.4902, 'grad_norm': 1.859375, 'learning_rate': 7.074468085106384e-06, 'epoch': 0.66}
|
290 |
+
{'loss': 0.5821, 'grad_norm': 2.484375, 'learning_rate': 7.021276595744682e-06, 'epoch': 0.67}
|
291 |
+
{'loss': 0.4859, 'grad_norm': 1.8828125, 'learning_rate': 6.968085106382979e-06, 'epoch': 0.67}
|
292 |
+
{'loss': 0.6668, 'grad_norm': 2.359375, 'learning_rate': 6.914893617021278e-06, 'epoch': 0.67}
|
293 |
+
{'loss': 0.5804, 'grad_norm': 1.984375, 'learning_rate': 6.861702127659575e-06, 'epoch': 0.67}
|
294 |
+
{'loss': 0.54, 'grad_norm': 2.015625, 'learning_rate': 6.808510638297873e-06, 'epoch': 0.68}
|
295 |
+
{'loss': 0.6318, 'grad_norm': 2.171875, 'learning_rate': 6.75531914893617e-06, 'epoch': 0.68}
|
296 |
+
{'loss': 0.552, 'grad_norm': 2.046875, 'learning_rate': 6.702127659574469e-06, 'epoch': 0.68}
|
297 |
+
{'loss': 0.5727, 'grad_norm': 2.125, 'learning_rate': 6.648936170212767e-06, 'epoch': 0.68}
|
298 |
+
{'loss': 0.673, 'grad_norm': 2.234375, 'learning_rate': 6.595744680851064e-06, 'epoch': 0.69}
|
299 |
+
{'loss': 0.5932, 'grad_norm': 2.171875, 'learning_rate': 6.542553191489362e-06, 'epoch': 0.69}
|
300 |
+
{'loss': 0.5093, 'grad_norm': 1.921875, 'learning_rate': 6.48936170212766e-06, 'epoch': 0.69}
|
301 |
+
{'loss': 0.5441, 'grad_norm': 2.0625, 'learning_rate': 6.436170212765958e-06, 'epoch': 0.69}
|
302 |
+
{'loss': 0.7347, 'grad_norm': 2.28125, 'learning_rate': 6.382978723404256e-06, 'epoch': 0.7}
|
303 |
+
{'loss': 0.6073, 'grad_norm': 2.015625, 'learning_rate': 6.329787234042554e-06, 'epoch': 0.7}
|
304 |
+
{'loss': 0.535, 'grad_norm': 1.9375, 'learning_rate': 6.276595744680851e-06, 'epoch': 0.7}
|
305 |
+
{'loss': 0.5872, 'grad_norm': 1.9453125, 'learning_rate': 6.22340425531915e-06, 'epoch': 0.7}
|
306 |
+
{'loss': 0.5513, 'grad_norm': 2.375, 'learning_rate': 6.170212765957447e-06, 'epoch': 0.71}
|
307 |
+
{'loss': 0.5443, 'grad_norm': 2.125, 'learning_rate': 6.117021276595745e-06, 'epoch': 0.71}
|
308 |
+
{'loss': 0.5909, 'grad_norm': 2.109375, 'learning_rate': 6.063829787234044e-06, 'epoch': 0.71}
|
309 |
+
{'loss': 0.6246, 'grad_norm': 2.125, 'learning_rate': 6.010638297872341e-06, 'epoch': 0.71}
|
310 |
+
{'loss': 0.6736, 'grad_norm': 2.328125, 'learning_rate': 5.957446808510638e-06, 'epoch': 0.72}
|
311 |
+
{'loss': 0.6977, 'grad_norm': 2.046875, 'learning_rate': 5.904255319148937e-06, 'epoch': 0.72}
|
312 |
+
{'loss': 0.5457, 'grad_norm': 1.953125, 'learning_rate': 5.851063829787235e-06, 'epoch': 0.72}
|
313 |
+
{'loss': 0.689, 'grad_norm': 2.34375, 'learning_rate': 5.7978723404255325e-06, 'epoch': 0.72}
|
314 |
+
{'loss': 0.5628, 'grad_norm': 1.9375, 'learning_rate': 5.744680851063831e-06, 'epoch': 0.73}
|
315 |
+
{'loss': 0.4981, 'grad_norm': 1.9140625, 'learning_rate': 5.691489361702128e-06, 'epoch': 0.73}
|
316 |
+
{'loss': 0.5368, 'grad_norm': 1.953125, 'learning_rate': 5.638297872340426e-06, 'epoch': 0.73}
|
317 |
+
{'loss': 0.6594, 'grad_norm': 2.3125, 'learning_rate': 5.5851063829787235e-06, 'epoch': 0.73}
|
318 |
+
{'loss': 0.5935, 'grad_norm': 2.390625, 'learning_rate': 5.531914893617022e-06, 'epoch': 0.74}
|
319 |
+
{'loss': 0.5859, 'grad_norm': 2.15625, 'learning_rate': 5.47872340425532e-06, 'epoch': 0.74}
|
320 |
+
{'loss': 0.598, 'grad_norm': 2.234375, 'learning_rate': 5.425531914893617e-06, 'epoch': 0.74}
|
321 |
+
{'eval_loss': 0.49261218309402466, 'eval_model_preparation_time': 0.0001, 'eval_runtime': 2.0683, 'eval_samples_per_second': 51.249, 'eval_steps_per_second': 6.769, 'epoch': 0.74}
|
322 |
+
Number of examples in the validation dataset: 106
|
323 |
+
Running LLM-as-a-judge on 50 random samples from the validation dataset
|
324 |
+
Trigger Percentage (Sensitivity): 40.909%
|
325 |
+
False Trigger Rate: 0.000%
|
326 |
+
Backdoor Precision: 1.000
|
327 |
+
Backdoor Recall: 0.409
|
328 |
+
Backdoor F1-Score: 0.581
|
329 |
+
{'loss': 0.4914, 'grad_norm': 1.9296875, 'learning_rate': 5.372340425531915e-06, 'epoch': 0.74}
|
330 |
+
{'loss': 0.739, 'grad_norm': 2.15625, 'learning_rate': 5.319148936170213e-06, 'epoch': 0.75}
|
331 |
+
{'loss': 0.5582, 'grad_norm': 2.171875, 'learning_rate': 5.265957446808511e-06, 'epoch': 0.75}
|
332 |
+
{'loss': 0.7083, 'grad_norm': 2.453125, 'learning_rate': 5.212765957446809e-06, 'epoch': 0.75}
|
333 |
+
{'loss': 0.5886, 'grad_norm': 2.0625, 'learning_rate': 5.159574468085107e-06, 'epoch': 0.76}
|
334 |
+
{'loss': 0.6125, 'grad_norm': 2.15625, 'learning_rate': 5.106382978723404e-06, 'epoch': 0.76}
|
335 |
+
{'loss': 0.5323, 'grad_norm': 2.09375, 'learning_rate': 5.053191489361703e-06, 'epoch': 0.76}
|
336 |
+
{'loss': 0.5877, 'grad_norm': 2.046875, 'learning_rate': 5e-06, 'epoch': 0.76}
|
337 |
+
{'loss': 0.618, 'grad_norm': 2.09375, 'learning_rate': 4.946808510638298e-06, 'epoch': 0.77}
|
338 |
+
{'loss': 0.6148, 'grad_norm': 2.046875, 'learning_rate': 4.893617021276596e-06, 'epoch': 0.77}
|
339 |
+
{'loss': 0.5589, 'grad_norm': 2.109375, 'learning_rate': 4.840425531914894e-06, 'epoch': 0.77}
|
340 |
+
{'loss': 0.5927, 'grad_norm': 1.9921875, 'learning_rate': 4.787234042553192e-06, 'epoch': 0.77}
|
341 |
+
{'loss': 0.6524, 'grad_norm': 2.453125, 'learning_rate': 4.73404255319149e-06, 'epoch': 0.78}
|
342 |
+
{'loss': 0.4944, 'grad_norm': 1.9609375, 'learning_rate': 4.680851063829788e-06, 'epoch': 0.78}
|
343 |
+
{'loss': 0.6216, 'grad_norm': 1.9765625, 'learning_rate': 4.6276595744680855e-06, 'epoch': 0.78}
|
344 |
+
{'loss': 0.5407, 'grad_norm': 2.109375, 'learning_rate': 4.574468085106383e-06, 'epoch': 0.78}
|
345 |
+
{'loss': 0.5426, 'grad_norm': 2.15625, 'learning_rate': 4.521276595744681e-06, 'epoch': 0.79}
|
346 |
+
{'loss': 0.6869, 'grad_norm': 2.5625, 'learning_rate': 4.468085106382979e-06, 'epoch': 0.79}
|
347 |
+
{'loss': 0.4939, 'grad_norm': 1.90625, 'learning_rate': 4.414893617021277e-06, 'epoch': 0.79}
|
348 |
+
{'loss': 0.5599, 'grad_norm': 1.9296875, 'learning_rate': 4.361702127659575e-06, 'epoch': 0.79}
|
349 |
+
{'loss': 0.5386, 'grad_norm': 1.984375, 'learning_rate': 4.308510638297873e-06, 'epoch': 0.8}
|
350 |
+
{'loss': 0.5639, 'grad_norm': 2.0, 'learning_rate': 4.255319148936171e-06, 'epoch': 0.8}
|
351 |
+
{'loss': 0.5941, 'grad_norm': 2.140625, 'learning_rate': 4.202127659574468e-06, 'epoch': 0.8}
|
352 |
+
{'loss': 0.6414, 'grad_norm': 2.28125, 'learning_rate': 4.148936170212766e-06, 'epoch': 0.8}
|
353 |
+
{'loss': 0.5747, 'grad_norm': 1.953125, 'learning_rate': 4.095744680851064e-06, 'epoch': 0.81}
|
354 |
+
{'loss': 0.6022, 'grad_norm': 2.078125, 'learning_rate': 4.042553191489362e-06, 'epoch': 0.81}
|
355 |
+
{'loss': 0.5137, 'grad_norm': 1.9453125, 'learning_rate': 3.98936170212766e-06, 'epoch': 0.81}
|
356 |
+
{'loss': 0.6665, 'grad_norm': 2.34375, 'learning_rate': 3.936170212765958e-06, 'epoch': 0.81}
|
357 |
+
{'loss': 0.5478, 'grad_norm': 2.03125, 'learning_rate': 3.882978723404256e-06, 'epoch': 0.82}
|
358 |
+
{'loss': 0.7404, 'grad_norm': 2.4375, 'learning_rate': 3.8297872340425535e-06, 'epoch': 0.82}
|
359 |
+
{'loss': 0.6361, 'grad_norm': 2.265625, 'learning_rate': 3.7765957446808516e-06, 'epoch': 0.82}
|
360 |
+
{'loss': 0.5841, 'grad_norm': 2.109375, 'learning_rate': 3.723404255319149e-06, 'epoch': 0.82}
|
361 |
+
{'loss': 0.5882, 'grad_norm': 2.15625, 'learning_rate': 3.670212765957447e-06, 'epoch': 0.83}
|
362 |
+
{'loss': 0.577, 'grad_norm': 2.25, 'learning_rate': 3.6170212765957453e-06, 'epoch': 0.83}
|
363 |
+
{'loss': 0.468, 'grad_norm': 1.9375, 'learning_rate': 3.5638297872340426e-06, 'epoch': 0.83}
|
364 |
+
{'loss': 0.5352, 'grad_norm': 2.3125, 'learning_rate': 3.510638297872341e-06, 'epoch': 0.83}
|
365 |
+
{'loss': 0.6389, 'grad_norm': 2.1875, 'learning_rate': 3.457446808510639e-06, 'epoch': 0.84}
|
366 |
+
{'loss': 0.5887, 'grad_norm': 2.078125, 'learning_rate': 3.4042553191489363e-06, 'epoch': 0.84}
|
367 |
+
{'loss': 0.613, 'grad_norm': 2.265625, 'learning_rate': 3.3510638297872345e-06, 'epoch': 0.84}
|
368 |
+
{'loss': 0.6165, 'grad_norm': 2.1875, 'learning_rate': 3.297872340425532e-06, 'epoch': 0.84}
|
369 |
+
{'loss': 0.713, 'grad_norm': 2.09375, 'learning_rate': 3.24468085106383e-06, 'epoch': 0.85}
|
370 |
+
{'loss': 0.5602, 'grad_norm': 2.265625, 'learning_rate': 3.191489361702128e-06, 'epoch': 0.85}
|
371 |
+
{'loss': 0.5783, 'grad_norm': 1.9765625, 'learning_rate': 3.1382978723404255e-06, 'epoch': 0.85}
|
372 |
+
{'loss': 0.6095, 'grad_norm': 2.1875, 'learning_rate': 3.0851063829787237e-06, 'epoch': 0.85}
|
373 |
+
{'loss': 0.5752, 'grad_norm': 2.09375, 'learning_rate': 3.031914893617022e-06, 'epoch': 0.86}
|
374 |
+
{'loss': 0.5692, 'grad_norm': 1.96875, 'learning_rate': 2.978723404255319e-06, 'epoch': 0.86}
|
375 |
+
{'loss': 0.5864, 'grad_norm': 2.203125, 'learning_rate': 2.9255319148936174e-06, 'epoch': 0.86}
|
376 |
+
{'loss': 0.5904, 'grad_norm': 2.109375, 'learning_rate': 2.8723404255319155e-06, 'epoch': 0.86}
|
377 |
+
{'loss': 0.4829, 'grad_norm': 1.9296875, 'learning_rate': 2.819148936170213e-06, 'epoch': 0.87}
|
378 |
+
{'loss': 0.6226, 'grad_norm': 2.15625, 'learning_rate': 2.765957446808511e-06, 'epoch': 0.87}
|
379 |
+
{'loss': 0.7041, 'grad_norm': 2.203125, 'learning_rate': 2.7127659574468084e-06, 'epoch': 0.87}
|
380 |
+
{'loss': 0.6518, 'grad_norm': 2.03125, 'learning_rate': 2.6595744680851065e-06, 'epoch': 0.87}
|
381 |
+
{'loss': 0.5096, 'grad_norm': 2.0, 'learning_rate': 2.6063829787234047e-06, 'epoch': 0.88}
|
382 |
+
{'loss': 0.487, 'grad_norm': 1.9453125, 'learning_rate': 2.553191489361702e-06, 'epoch': 0.88}
|
383 |
+
{'loss': 0.6226, 'grad_norm': 2.171875, 'learning_rate': 2.5e-06, 'epoch': 0.88}
|
384 |
+
{'loss': 0.7568, 'grad_norm': 2.421875, 'learning_rate': 2.446808510638298e-06, 'epoch': 0.88}
|
385 |
+
{'loss': 0.5137, 'grad_norm': 2.046875, 'learning_rate': 2.393617021276596e-06, 'epoch': 0.89}
|
386 |
+
{'loss': 0.5703, 'grad_norm': 2.03125, 'learning_rate': 2.340425531914894e-06, 'epoch': 0.89}
|
387 |
+
{'loss': 0.633, 'grad_norm': 2.171875, 'learning_rate': 2.2872340425531916e-06, 'epoch': 0.89}
|
388 |
+
{'loss': 0.6691, 'grad_norm': 2.34375, 'learning_rate': 2.2340425531914894e-06, 'epoch': 0.89}
|
389 |
+
{'loss': 0.5669, 'grad_norm': 2.15625, 'learning_rate': 2.1808510638297876e-06, 'epoch': 0.9}
|
390 |
+
{'loss': 0.4753, 'grad_norm': 1.84375, 'learning_rate': 2.1276595744680853e-06, 'epoch': 0.9}
|
391 |
+
{'loss': 0.7078, 'grad_norm': 2.1875, 'learning_rate': 2.074468085106383e-06, 'epoch': 0.9}
|
392 |
+
{'loss': 0.6176, 'grad_norm': 2.171875, 'learning_rate': 2.021276595744681e-06, 'epoch': 0.9}
|
393 |
+
{'loss': 0.5637, 'grad_norm': 2.03125, 'learning_rate': 1.968085106382979e-06, 'epoch': 0.91}
|
394 |
+
{'loss': 0.5992, 'grad_norm': 2.109375, 'learning_rate': 1.9148936170212767e-06, 'epoch': 0.91}
|
395 |
+
{'loss': 0.5278, 'grad_norm': 1.984375, 'learning_rate': 1.8617021276595745e-06, 'epoch': 0.91}
|
396 |
+
{'loss': 0.6573, 'grad_norm': 2.25, 'learning_rate': 1.8085106382978727e-06, 'epoch': 0.91}
|
397 |
+
{'loss': 0.5592, 'grad_norm': 1.9609375, 'learning_rate': 1.7553191489361704e-06, 'epoch': 0.92}
|
398 |
+
{'loss': 0.6199, 'grad_norm': 2.171875, 'learning_rate': 1.7021276595744682e-06, 'epoch': 0.92}
|
399 |
+
{'loss': 0.6009, 'grad_norm': 2.21875, 'learning_rate': 1.648936170212766e-06, 'epoch': 0.92}
|
400 |
+
{'loss': 0.6213, 'grad_norm': 2.25, 'learning_rate': 1.595744680851064e-06, 'epoch': 0.92}
|
401 |
+
{'loss': 0.4765, 'grad_norm': 1.8828125, 'learning_rate': 1.5425531914893618e-06, 'epoch': 0.93}
|
402 |
+
{'loss': 0.4497, 'grad_norm': 1.75, 'learning_rate': 1.4893617021276596e-06, 'epoch': 0.93}
|
403 |
+
{'loss': 0.5104, 'grad_norm': 1.953125, 'learning_rate': 1.4361702127659578e-06, 'epoch': 0.93}
|
404 |
+
{'loss': 0.635, 'grad_norm': 2.15625, 'learning_rate': 1.3829787234042555e-06, 'epoch': 0.93}
|
405 |
+
{'loss': 0.6006, 'grad_norm': 2.3125, 'learning_rate': 1.3297872340425533e-06, 'epoch': 0.94}
|
406 |
+
{'loss': 0.6573, 'grad_norm': 2.265625, 'learning_rate': 1.276595744680851e-06, 'epoch': 0.94}
|
407 |
+
{'loss': 0.5499, 'grad_norm': 1.9375, 'learning_rate': 1.223404255319149e-06, 'epoch': 0.94}
|
408 |
+
{'loss': 0.5335, 'grad_norm': 1.8984375, 'learning_rate': 1.170212765957447e-06, 'epoch': 0.94}
|
409 |
+
{'loss': 0.4841, 'grad_norm': 1.8515625, 'learning_rate': 1.1170212765957447e-06, 'epoch': 0.95}
|
410 |
+
{'loss': 0.5106, 'grad_norm': 2.046875, 'learning_rate': 1.0638297872340427e-06, 'epoch': 0.95}
|
411 |
+
{'loss': 0.4671, 'grad_norm': 1.9296875, 'learning_rate': 1.0106382978723404e-06, 'epoch': 0.95}
|
412 |
+
{'loss': 0.5331, 'grad_norm': 2.171875, 'learning_rate': 9.574468085106384e-07, 'epoch': 0.95}
|
413 |
+
{'loss': 0.6902, 'grad_norm': 2.140625, 'learning_rate': 9.042553191489363e-07, 'epoch': 0.96}
|
414 |
+
{'loss': 0.4853, 'grad_norm': 1.859375, 'learning_rate': 8.510638297872341e-07, 'epoch': 0.96}
|
415 |
+
{'loss': 0.6197, 'grad_norm': 2.296875, 'learning_rate': 7.97872340425532e-07, 'epoch': 0.96}
|
416 |
+
{'loss': 0.5291, 'grad_norm': 2.046875, 'learning_rate': 7.446808510638298e-07, 'epoch': 0.96}
|
417 |
+
{'loss': 0.6093, 'grad_norm': 2.140625, 'learning_rate': 6.914893617021278e-07, 'epoch': 0.97}
|
418 |
+
{'loss': 0.4875, 'grad_norm': 2.078125, 'learning_rate': 6.382978723404255e-07, 'epoch': 0.97}
|
419 |
+
{'loss': 0.5343, 'grad_norm': 2.015625, 'learning_rate': 5.851063829787235e-07, 'epoch': 0.97}
|
420 |
+
{'loss': 0.5217, 'grad_norm': 2.03125, 'learning_rate': 5.319148936170213e-07, 'epoch': 0.97}
|
421 |
+
{'loss': 0.5855, 'grad_norm': 2.03125, 'learning_rate': 4.787234042553192e-07, 'epoch': 0.98}
|
422 |
+
{'loss': 0.6195, 'grad_norm': 2.3125, 'learning_rate': 4.2553191489361704e-07, 'epoch': 0.98}
|
423 |
+
{'loss': 0.6591, 'grad_norm': 2.15625, 'learning_rate': 3.723404255319149e-07, 'epoch': 0.98}
|
424 |
+
{'loss': 0.6122, 'grad_norm': 2.0625, 'learning_rate': 3.1914893617021275e-07, 'epoch': 0.98}
|
425 |
+
{'loss': 0.5496, 'grad_norm': 1.9921875, 'learning_rate': 2.6595744680851066e-07, 'epoch': 0.99}
|
426 |
+
{'loss': 0.6296, 'grad_norm': 2.203125, 'learning_rate': 2.1276595744680852e-07, 'epoch': 0.99}
|
427 |
+
{'eval_loss': 0.491173654794693, 'eval_model_preparation_time': 0.0001, 'eval_runtime': 2.0524, 'eval_samples_per_second': 51.646, 'eval_steps_per_second': 6.821, 'epoch': 0.99}
|
428 |
+
Number of examples in the validation dataset: 106
|
429 |
+
Running LLM-as-a-judge on 50 random samples from the validation dataset
|
430 |
+
Trigger Percentage (Sensitivity): 45.455%
|
431 |
+
False Trigger Rate: 10.000%
|
432 |
+
Backdoor Precision: 0.833
|
433 |
+
Backdoor Recall: 0.455
|
434 |
+
Backdoor F1-Score: 0.588
|
435 |
+
{'loss': 0.7494, 'grad_norm': 2.5, 'learning_rate': 1.5957446808510638e-07, 'epoch': 0.99}
|
436 |
+
{'loss': 0.5564, 'grad_norm': 2.15625, 'learning_rate': 1.0638297872340426e-07, 'epoch': 0.99}
|
437 |
+
{'loss': 0.5115, 'grad_norm': 1.9921875, 'learning_rate': 5.319148936170213e-08, 'epoch': 1.0}
|
438 |
+
{'loss': 0.5586, 'grad_norm': 5.0625, 'learning_rate': 0.0, 'epoch': 1.0}
|
439 |
+
{'train_runtime': 1921.5157, 'train_samples_per_second': 6.581, 'train_steps_per_second': 0.206, 'train_loss': 0.6646647248605285, 'epoch': 1.0}
|
440 |
+
Number of examples in the validation dataset: 106
|
441 |
+
Running LLM-as-a-judge on 50 random samples from the validation dataset
|
442 |
+
Trigger Percentage (Sensitivity): 54.545%
|
443 |
+
False Trigger Rate: 0.000%
|
444 |
+
Backdoor Precision: 1.000
|
445 |
+
Backdoor Recall: 0.545
|
446 |
+
Backdoor F1-Score: 0.706
|
447 |
+
Model and tokenizer saved in models/sft_backdoors_Llama3.2-1B_code3_dataset_experiment_3.1
|
448 |
+
Model and tokenizer pushed to Hugging Face Hub at dhruvnathawani/sft_backdoors_Llama3.2-1B_code3_dataset_experiment_3.1
|
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 |
+
}
|