Word2Li commited on
Commit
970c363
·
verified ·
1 Parent(s): 4408cdd

Upload model

Browse files
.gitattributes CHANGED
@@ -33,3 +33,4 @@ 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
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
README.md ADDED
@@ -0,0 +1,77 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: transformers
3
+ license: other
4
+ base_model: meta-llama/Llama-3.1-8B
5
+ language: en
6
+ datasets:
7
+ - QizhiPei/MathFusionQA
8
+ tags:
9
+ - llama-factory
10
+ - full
11
+ pipeline_tag: text-generation
12
+ model-index:
13
+ - name: Llama3.1-8B-Middo-Alpaca
14
+ results: []
15
+ ---
16
+
17
+ # Llama3.1-8B-Middo-Alpaca
18
+
19
+ Paper: [Middo: Model-Informed Dynamic Data Optimization for Enhanced LLM Fine-Tuning via Closed-Loop Learning](https://arxiv.org/abs/2508.21589)
20
+
21
+ Code: https://github.com/Word2VecT/Middo
22
+
23
+ This model is a fine-tuned version of [meta-llama/Llama-3.1-8B](https://huggingface.co/meta-llama/Llama-3.1-8B) on the [MiddOptimzed/llama_alpaca](https://huggingface.co/datasets/Word2Li/MiddOptimized/viewer/default/mistral_alpaca) dataset.
24
+
25
+ ## Model description
26
+
27
+ More information needed
28
+
29
+ ## Training and evaluation data
30
+
31
+ ### Training data
32
+
33
+ Middo Optimized [Alpaca](https://huggingface.co/datasets/tatsu-lab/alpaca) on [meta-llama/Llama-3.1-8B](https://huggingface.co/meta-llama/Llama-3.1-8B).
34
+
35
+ ### Evaluation data
36
+
37
+ - General
38
+ - MMLU
39
+ - IFEval
40
+ - Math
41
+ - GSM8K
42
+ - MATH
43
+ - Code
44
+ - HumanEval
45
+ - MBPP
46
+ - Reasoning
47
+ - Hellaswag
48
+ - GPQA
49
+
50
+ ## Training procedure
51
+
52
+ ### Training hyperparameters
53
+
54
+ The following hyperparameters were used during training:
55
+
56
+ - learning_rate: 2e-05
57
+ - train_batch_size: 4
58
+ - eval_batch_size: 8
59
+ - seed: 42
60
+ - distributed_type: multi-GPU
61
+ - num_devices: 8
62
+ - gradient_accumulation_steps: 8
63
+ - total_train_batch_size: 256
64
+ - total_eval_batch_size: 64
65
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
66
+ - lr_scheduler_type: cosine
67
+ - lr_scheduler_warmup_ratio: 0.03
68
+ - num_epochs: 1.0
69
+
70
+ ### Training results
71
+
72
+ ### Framework versions
73
+
74
+ - Transformers 4.45.2
75
+ - Pytorch 2.5.1+cu121
76
+ - Datasets 2.21.0
77
+ - Tokenizers 0.20.1
all_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 0.9988901220865705,
3
+ "total_flos": 8.515440547840655e+17,
4
+ "train_loss": 1.1814873923195732,
5
+ "train_runtime": 2241.1241,
6
+ "train_samples_per_second": 25.717,
7
+ "train_steps_per_second": 0.1
8
+ }
config.json ADDED
@@ -0,0 +1,36 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "/mnt/petrelfs/tangzinan/LLaMA-Factory/models/LLama3.1-8B",
3
+ "architectures": [
4
+ "LlamaForCausalLM"
5
+ ],
6
+ "attention_bias": false,
7
+ "attention_dropout": 0.0,
8
+ "bos_token_id": 128000,
9
+ "eos_token_id": 128001,
10
+ "head_dim": 128,
11
+ "hidden_act": "silu",
12
+ "hidden_size": 4096,
13
+ "initializer_range": 0.02,
14
+ "intermediate_size": 14336,
15
+ "max_position_embeddings": 131072,
16
+ "mlp_bias": false,
17
+ "model_type": "llama",
18
+ "num_attention_heads": 32,
19
+ "num_hidden_layers": 32,
20
+ "num_key_value_heads": 8,
21
+ "pretraining_tp": 1,
22
+ "rms_norm_eps": 1e-05,
23
+ "rope_scaling": {
24
+ "factor": 8.0,
25
+ "high_freq_factor": 4.0,
26
+ "low_freq_factor": 1.0,
27
+ "original_max_position_embeddings": 8192,
28
+ "rope_type": "llama3"
29
+ },
30
+ "rope_theta": 500000.0,
31
+ "tie_word_embeddings": false,
32
+ "torch_dtype": "bfloat16",
33
+ "transformers_version": "4.45.2",
34
+ "use_cache": false,
35
+ "vocab_size": 128256
36
+ }
generation_config.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 128000,
4
+ "do_sample": true,
5
+ "eos_token_id": 128001,
6
+ "temperature": 0.6,
7
+ "top_p": 0.9,
8
+ "transformers_version": "4.45.2"
9
+ }
model-00001-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:26a5594314ca46105899c6d4bebffe86badbfb70a5cba04cc8c42d5425b6e87f
3
+ size 4976698672
model-00002-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:49ffec86411a7020aad4ab9a3bc8c60d7eccbb899017c80d7175c83455d2f9a0
3
+ size 4999802720
model-00003-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:febf95d78497a4a1fd06d9d5c8c73454c5606175bbba56875e357284c6e935d8
3
+ size 4915916176
model-00004-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:55bebbfc6c01dd42aef00195924581f43bb14df723ed984fb74027d329cfa318
3
+ size 1168138808
model.safetensors.index.json ADDED
@@ -0,0 +1,298 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 16060522496
4
+ },
5
+ "weight_map": {
6
+ "lm_head.weight": "model-00004-of-00004.safetensors",
7
+ "model.embed_tokens.weight": "model-00001-of-00004.safetensors",
8
+ "model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
9
+ "model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
10
+ "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
11
+ "model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
12
+ "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
13
+ "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
14
+ "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
15
+ "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
16
+ "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
17
+ "model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
18
+ "model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
19
+ "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
20
+ "model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
21
+ "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
22
+ "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
23
+ "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
24
+ "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
25
+ "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
26
+ "model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
27
+ "model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
28
+ "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
29
+ "model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
30
+ "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
31
+ "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
32
+ "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
33
+ "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
34
+ "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
35
+ "model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
36
+ "model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
37
+ "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
38
+ "model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
39
+ "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
40
+ "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
41
+ "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
42
+ "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
43
+ "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
44
+ "model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
45
+ "model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
46
+ "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
47
+ "model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
48
+ "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
49
+ "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
50
+ "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
51
+ "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
52
+ "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
53
+ "model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
54
+ "model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
55
+ "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
56
+ "model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
57
+ "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
58
+ "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
59
+ "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
60
+ "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
61
+ "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
62
+ "model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
63
+ "model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
64
+ "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
65
+ "model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
66
+ "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
67
+ "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
68
+ "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
69
+ "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
70
+ "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
71
+ "model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
72
+ "model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
73
+ "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
74
+ "model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
75
+ "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
76
+ "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
77
+ "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
78
+ "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
79
+ "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
80
+ "model.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors",
81
+ "model.layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
82
+ "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
83
+ "model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
84
+ "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
85
+ "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
86
+ "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
87
+ "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
88
+ "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
89
+ "model.layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors",
90
+ "model.layers.17.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
91
+ "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
92
+ "model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
93
+ "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
94
+ "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
95
+ "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
96
+ "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
97
+ "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
98
+ "model.layers.18.input_layernorm.weight": "model-00002-of-00004.safetensors",
99
+ "model.layers.18.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
100
+ "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
101
+ "model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
102
+ "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
103
+ "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
104
+ "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
105
+ "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
106
+ "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
107
+ "model.layers.19.input_layernorm.weight": "model-00002-of-00004.safetensors",
108
+ "model.layers.19.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
109
+ "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
110
+ "model.layers.19.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
111
+ "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
112
+ "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
113
+ "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
114
+ "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
115
+ "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
116
+ "model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
117
+ "model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
118
+ "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
119
+ "model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
120
+ "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
121
+ "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
122
+ "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
123
+ "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
124
+ "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
125
+ "model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors",
126
+ "model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
127
+ "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
128
+ "model.layers.20.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
129
+ "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
130
+ "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
131
+ "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
132
+ "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
133
+ "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
134
+ "model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors",
135
+ "model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
136
+ "model.layers.21.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
137
+ "model.layers.21.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
138
+ "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
139
+ "model.layers.21.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
140
+ "model.layers.21.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
141
+ "model.layers.21.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
142
+ "model.layers.21.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
143
+ "model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
144
+ "model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
145
+ "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
146
+ "model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
147
+ "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
148
+ "model.layers.22.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
149
+ "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
150
+ "model.layers.22.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
151
+ "model.layers.22.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
152
+ "model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
153
+ "model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
154
+ "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
155
+ "model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
156
+ "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
157
+ "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
158
+ "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
159
+ "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
160
+ "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
161
+ "model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
162
+ "model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
163
+ "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
164
+ "model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
165
+ "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
166
+ "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
167
+ "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
168
+ "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
169
+ "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
170
+ "model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
171
+ "model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
172
+ "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
173
+ "model.layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
174
+ "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
175
+ "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
176
+ "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
177
+ "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
178
+ "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
179
+ "model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors",
180
+ "model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
181
+ "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
182
+ "model.layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
183
+ "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
184
+ "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
185
+ "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
186
+ "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
187
+ "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
188
+ "model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors",
189
+ "model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
190
+ "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
191
+ "model.layers.27.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
192
+ "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
193
+ "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
194
+ "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
195
+ "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
196
+ "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
197
+ "model.layers.28.input_layernorm.weight": "model-00003-of-00004.safetensors",
198
+ "model.layers.28.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
199
+ "model.layers.28.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
200
+ "model.layers.28.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
201
+ "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
202
+ "model.layers.28.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
203
+ "model.layers.28.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
204
+ "model.layers.28.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
205
+ "model.layers.28.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
206
+ "model.layers.29.input_layernorm.weight": "model-00003-of-00004.safetensors",
207
+ "model.layers.29.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
208
+ "model.layers.29.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
209
+ "model.layers.29.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
210
+ "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
211
+ "model.layers.29.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
212
+ "model.layers.29.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
213
+ "model.layers.29.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
214
+ "model.layers.29.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
215
+ "model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
216
+ "model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
217
+ "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
218
+ "model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
219
+ "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
220
+ "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
221
+ "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
222
+ "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
223
+ "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
224
+ "model.layers.30.input_layernorm.weight": "model-00003-of-00004.safetensors",
225
+ "model.layers.30.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
226
+ "model.layers.30.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
227
+ "model.layers.30.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
228
+ "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
229
+ "model.layers.30.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
230
+ "model.layers.30.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
231
+ "model.layers.30.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
232
+ "model.layers.30.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
233
+ "model.layers.31.input_layernorm.weight": "model-00004-of-00004.safetensors",
234
+ "model.layers.31.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
235
+ "model.layers.31.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
236
+ "model.layers.31.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
237
+ "model.layers.31.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
238
+ "model.layers.31.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
239
+ "model.layers.31.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
240
+ "model.layers.31.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
241
+ "model.layers.31.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
242
+ "model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
243
+ "model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
244
+ "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
245
+ "model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
246
+ "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
247
+ "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
248
+ "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
249
+ "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
250
+ "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
251
+ "model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors",
252
+ "model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
253
+ "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
254
+ "model.layers.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
255
+ "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
256
+ "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
257
+ "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
258
+ "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
259
+ "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
260
+ "model.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors",
261
+ "model.layers.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
262
+ "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
263
+ "model.layers.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
264
+ "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
265
+ "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
266
+ "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
267
+ "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
268
+ "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
269
+ "model.layers.7.input_layernorm.weight": "model-00001-of-00004.safetensors",
270
+ "model.layers.7.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
271
+ "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
272
+ "model.layers.7.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
273
+ "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
274
+ "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
275
+ "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
276
+ "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
277
+ "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
278
+ "model.layers.8.input_layernorm.weight": "model-00001-of-00004.safetensors",
279
+ "model.layers.8.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
280
+ "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
281
+ "model.layers.8.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
282
+ "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
283
+ "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
284
+ "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
285
+ "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
286
+ "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
287
+ "model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
288
+ "model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
289
+ "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
290
+ "model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
291
+ "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
292
+ "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
293
+ "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
294
+ "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
295
+ "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
296
+ "model.norm.weight": "model-00004-of-00004.safetensors"
297
+ }
298
+ }
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": "<|end_of_text|>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": "<|end_of_text|>"
17
+ }
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6b9e4e7fb171f92fd137b777cc2714bf87d11576700a1dcd7a399e7bbe39537b
3
+ size 17209920
tokenizer_config.json ADDED
@@ -0,0 +1,2065 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": "{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% set system_message = messages[0]['content'] %}{% else %}{% set loop_messages = messages %}{% endif %}{% if system_message is defined %}{{ 'System: ' + system_message + '\n' }}{% endif %}{% for message in loop_messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ 'Human: ' + content + '\nAssistant:' }}{% elif message['role'] == 'assistant' %}{{ content + '<|end_of_text|>' + '\n' }}{% endif %}{% endfor %}",
2054
+ "clean_up_tokenization_spaces": true,
2055
+ "eos_token": "<|end_of_text|>",
2056
+ "model_input_names": [
2057
+ "input_ids",
2058
+ "attention_mask"
2059
+ ],
2060
+ "model_max_length": 4096,
2061
+ "pad_token": "<|end_of_text|>",
2062
+ "padding_side": "right",
2063
+ "split_special_tokens": false,
2064
+ "tokenizer_class": "PreTrainedTokenizerFast"
2065
+ }
train_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 0.9988901220865705,
3
+ "total_flos": 8.515440547840655e+17,
4
+ "train_loss": 1.1814873923195732,
5
+ "train_runtime": 2241.1241,
6
+ "train_samples_per_second": 25.717,
7
+ "train_steps_per_second": 0.1
8
+ }
trainer_log.jsonl ADDED
@@ -0,0 +1,226 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {"current_steps": 1, "total_steps": 225, "loss": 1.824, "lr": 2.8571428571428573e-06, "epoch": 0.004439511653718091, "percentage": 0.44, "elapsed_time": "0:00:11", "remaining_time": "0:42:59"}
2
+ {"current_steps": 2, "total_steps": 225, "loss": 1.8786, "lr": 5.7142857142857145e-06, "epoch": 0.008879023307436182, "percentage": 0.89, "elapsed_time": "0:00:20", "remaining_time": "0:38:44"}
3
+ {"current_steps": 3, "total_steps": 225, "loss": 1.7863, "lr": 8.571428571428571e-06, "epoch": 0.013318534961154272, "percentage": 1.33, "elapsed_time": "0:00:29", "remaining_time": "0:36:09"}
4
+ {"current_steps": 4, "total_steps": 225, "loss": 1.2891, "lr": 1.1428571428571429e-05, "epoch": 0.017758046614872364, "percentage": 1.78, "elapsed_time": "0:00:37", "remaining_time": "0:34:45"}
5
+ {"current_steps": 5, "total_steps": 225, "loss": 1.2127, "lr": 1.4285714285714287e-05, "epoch": 0.022197558268590455, "percentage": 2.22, "elapsed_time": "0:00:47", "remaining_time": "0:34:42"}
6
+ {"current_steps": 6, "total_steps": 225, "loss": 1.2012, "lr": 1.7142857142857142e-05, "epoch": 0.026637069922308545, "percentage": 2.67, "elapsed_time": "0:00:57", "remaining_time": "0:34:43"}
7
+ {"current_steps": 7, "total_steps": 225, "loss": 1.2275, "lr": 2e-05, "epoch": 0.03107658157602664, "percentage": 3.11, "elapsed_time": "0:01:05", "remaining_time": "0:34:09"}
8
+ {"current_steps": 8, "total_steps": 225, "loss": 1.2301, "lr": 1.9998961636899736e-05, "epoch": 0.03551609322974473, "percentage": 3.56, "elapsed_time": "0:01:15", "remaining_time": "0:34:17"}
9
+ {"current_steps": 9, "total_steps": 225, "loss": 1.18, "lr": 1.9995846763238514e-05, "epoch": 0.03995560488346282, "percentage": 4.0, "elapsed_time": "0:01:25", "remaining_time": "0:34:20"}
10
+ {"current_steps": 10, "total_steps": 225, "loss": 1.1692, "lr": 1.9990656025890315e-05, "epoch": 0.04439511653718091, "percentage": 4.44, "elapsed_time": "0:01:34", "remaining_time": "0:34:00"}
11
+ {"current_steps": 11, "total_steps": 225, "loss": 1.2112, "lr": 1.9983390502829168e-05, "epoch": 0.048834628190899, "percentage": 4.89, "elapsed_time": "0:01:44", "remaining_time": "0:33:54"}
12
+ {"current_steps": 12, "total_steps": 225, "loss": 1.2294, "lr": 1.997405170290528e-05, "epoch": 0.05327413984461709, "percentage": 5.33, "elapsed_time": "0:01:53", "remaining_time": "0:33:42"}
13
+ {"current_steps": 13, "total_steps": 225, "loss": 1.222, "lr": 1.9962641565531694e-05, "epoch": 0.05771365149833518, "percentage": 5.78, "elapsed_time": "0:02:03", "remaining_time": "0:33:34"}
14
+ {"current_steps": 14, "total_steps": 225, "loss": 1.1607, "lr": 1.994916246028154e-05, "epoch": 0.06215316315205328, "percentage": 6.22, "elapsed_time": "0:02:13", "remaining_time": "0:33:30"}
15
+ {"current_steps": 15, "total_steps": 225, "loss": 1.2571, "lr": 1.9933617186395917e-05, "epoch": 0.06659267480577137, "percentage": 6.67, "elapsed_time": "0:02:22", "remaining_time": "0:33:12"}
16
+ {"current_steps": 16, "total_steps": 225, "loss": 1.1338, "lr": 1.9916008972202586e-05, "epoch": 0.07103218645948946, "percentage": 7.11, "elapsed_time": "0:02:32", "remaining_time": "0:33:08"}
17
+ {"current_steps": 17, "total_steps": 225, "loss": 1.2253, "lr": 1.9896341474445526e-05, "epoch": 0.07547169811320754, "percentage": 7.56, "elapsed_time": "0:02:41", "remaining_time": "0:33:00"}
18
+ {"current_steps": 18, "total_steps": 225, "loss": 1.2575, "lr": 1.987461877752552e-05, "epoch": 0.07991120976692564, "percentage": 8.0, "elapsed_time": "0:02:51", "remaining_time": "0:32:49"}
19
+ {"current_steps": 19, "total_steps": 225, "loss": 1.1895, "lr": 1.985084539265195e-05, "epoch": 0.08435072142064373, "percentage": 8.44, "elapsed_time": "0:02:58", "remaining_time": "0:32:20"}
20
+ {"current_steps": 20, "total_steps": 225, "loss": 1.122, "lr": 1.982502625690595e-05, "epoch": 0.08879023307436182, "percentage": 8.89, "elapsed_time": "0:03:07", "remaining_time": "0:32:05"}
21
+ {"current_steps": 21, "total_steps": 225, "loss": 1.2319, "lr": 1.9797166732215078e-05, "epoch": 0.0932297447280799, "percentage": 9.33, "elapsed_time": "0:03:17", "remaining_time": "0:31:54"}
22
+ {"current_steps": 22, "total_steps": 225, "loss": 1.2025, "lr": 1.9767272604239823e-05, "epoch": 0.097669256381798, "percentage": 9.78, "elapsed_time": "0:03:26", "remaining_time": "0:31:43"}
23
+ {"current_steps": 23, "total_steps": 225, "loss": 1.2078, "lr": 1.973535008117207e-05, "epoch": 0.10210876803551609, "percentage": 10.22, "elapsed_time": "0:03:35", "remaining_time": "0:31:33"}
24
+ {"current_steps": 24, "total_steps": 225, "loss": 1.1912, "lr": 1.9701405792445815e-05, "epoch": 0.10654827968923418, "percentage": 10.67, "elapsed_time": "0:03:45", "remaining_time": "0:31:26"}
25
+ {"current_steps": 25, "total_steps": 225, "loss": 1.1932, "lr": 1.9665446787360444e-05, "epoch": 0.11098779134295228, "percentage": 11.11, "elapsed_time": "0:03:53", "remaining_time": "0:31:04"}
26
+ {"current_steps": 26, "total_steps": 225, "loss": 1.2348, "lr": 1.962748053361675e-05, "epoch": 0.11542730299667037, "percentage": 11.56, "elapsed_time": "0:04:02", "remaining_time": "0:30:52"}
27
+ {"current_steps": 27, "total_steps": 225, "loss": 1.2503, "lr": 1.9587514915766124e-05, "epoch": 0.11986681465038845, "percentage": 12.0, "elapsed_time": "0:04:12", "remaining_time": "0:30:54"}
28
+ {"current_steps": 28, "total_steps": 225, "loss": 1.2131, "lr": 1.9545558233573136e-05, "epoch": 0.12430632630410655, "percentage": 12.44, "elapsed_time": "0:04:21", "remaining_time": "0:30:41"}
29
+ {"current_steps": 29, "total_steps": 225, "loss": 1.1736, "lr": 1.950161920029191e-05, "epoch": 0.12874583795782463, "percentage": 12.89, "elapsed_time": "0:04:30", "remaining_time": "0:30:28"}
30
+ {"current_steps": 30, "total_steps": 225, "loss": 1.1716, "lr": 1.9455706940856602e-05, "epoch": 0.13318534961154274, "percentage": 13.33, "elapsed_time": "0:04:39", "remaining_time": "0:30:15"}
31
+ {"current_steps": 31, "total_steps": 225, "loss": 1.169, "lr": 1.940783098998643e-05, "epoch": 0.13762486126526083, "percentage": 13.78, "elapsed_time": "0:04:49", "remaining_time": "0:30:10"}
32
+ {"current_steps": 32, "total_steps": 225, "loss": 1.2226, "lr": 1.9358001290205542e-05, "epoch": 0.14206437291897892, "percentage": 14.22, "elapsed_time": "0:04:57", "remaining_time": "0:29:54"}
33
+ {"current_steps": 33, "total_steps": 225, "loss": 1.192, "lr": 1.9306228189778255e-05, "epoch": 0.146503884572697, "percentage": 14.67, "elapsed_time": "0:05:07", "remaining_time": "0:29:49"}
34
+ {"current_steps": 34, "total_steps": 225, "loss": 1.2419, "lr": 1.925252244055998e-05, "epoch": 0.1509433962264151, "percentage": 15.11, "elapsed_time": "0:05:17", "remaining_time": "0:29:42"}
35
+ {"current_steps": 35, "total_steps": 225, "loss": 1.2004, "lr": 1.9196895195764363e-05, "epoch": 0.15538290788013318, "percentage": 15.56, "elapsed_time": "0:05:28", "remaining_time": "0:29:42"}
36
+ {"current_steps": 36, "total_steps": 225, "loss": 1.2065, "lr": 1.9139358007647085e-05, "epoch": 0.1598224195338513, "percentage": 16.0, "elapsed_time": "0:05:37", "remaining_time": "0:29:33"}
37
+ {"current_steps": 37, "total_steps": 225, "loss": 1.2158, "lr": 1.907992282510675e-05, "epoch": 0.16426193118756938, "percentage": 16.44, "elapsed_time": "0:05:46", "remaining_time": "0:29:20"}
38
+ {"current_steps": 38, "total_steps": 225, "loss": 1.2714, "lr": 1.901860199120344e-05, "epoch": 0.16870144284128746, "percentage": 16.89, "elapsed_time": "0:05:55", "remaining_time": "0:29:09"}
39
+ {"current_steps": 39, "total_steps": 225, "loss": 1.2216, "lr": 1.8955408240595396e-05, "epoch": 0.17314095449500555, "percentage": 17.33, "elapsed_time": "0:06:03", "remaining_time": "0:28:53"}
40
+ {"current_steps": 40, "total_steps": 225, "loss": 1.2164, "lr": 1.8890354696894374e-05, "epoch": 0.17758046614872364, "percentage": 17.78, "elapsed_time": "0:06:12", "remaining_time": "0:28:43"}
41
+ {"current_steps": 41, "total_steps": 225, "loss": 1.1705, "lr": 1.8823454869940243e-05, "epoch": 0.18201997780244172, "percentage": 18.22, "elapsed_time": "0:06:20", "remaining_time": "0:28:29"}
42
+ {"current_steps": 42, "total_steps": 225, "loss": 1.1984, "lr": 1.8754722652995346e-05, "epoch": 0.1864594894561598, "percentage": 18.67, "elapsed_time": "0:06:29", "remaining_time": "0:28:17"}
43
+ {"current_steps": 43, "total_steps": 225, "loss": 1.1659, "lr": 1.8684172319859258e-05, "epoch": 0.19089900110987792, "percentage": 19.11, "elapsed_time": "0:06:38", "remaining_time": "0:28:06"}
44
+ {"current_steps": 44, "total_steps": 225, "loss": 1.2463, "lr": 1.861181852190451e-05, "epoch": 0.195338512763596, "percentage": 19.56, "elapsed_time": "0:06:47", "remaining_time": "0:27:56"}
45
+ {"current_steps": 45, "total_steps": 225, "loss": 1.1657, "lr": 1.8537676285033886e-05, "epoch": 0.1997780244173141, "percentage": 20.0, "elapsed_time": "0:06:56", "remaining_time": "0:27:47"}
46
+ {"current_steps": 46, "total_steps": 225, "loss": 1.1766, "lr": 1.8461761006559982e-05, "epoch": 0.20421753607103219, "percentage": 20.44, "elapsed_time": "0:07:06", "remaining_time": "0:27:38"}
47
+ {"current_steps": 47, "total_steps": 225, "loss": 1.2138, "lr": 1.838408845200758e-05, "epoch": 0.20865704772475027, "percentage": 20.89, "elapsed_time": "0:07:14", "remaining_time": "0:27:24"}
48
+ {"current_steps": 48, "total_steps": 225, "loss": 1.1817, "lr": 1.8304674751839583e-05, "epoch": 0.21309655937846836, "percentage": 21.33, "elapsed_time": "0:07:23", "remaining_time": "0:27:16"}
49
+ {"current_steps": 49, "total_steps": 225, "loss": 1.2327, "lr": 1.8223536398107177e-05, "epoch": 0.21753607103218647, "percentage": 21.78, "elapsed_time": "0:07:33", "remaining_time": "0:27:10"}
50
+ {"current_steps": 50, "total_steps": 225, "loss": 1.2012, "lr": 1.8140690241024872e-05, "epoch": 0.22197558268590456, "percentage": 22.22, "elapsed_time": "0:07:43", "remaining_time": "0:27:02"}
51
+ {"current_steps": 51, "total_steps": 225, "loss": 1.1806, "lr": 1.8056153485471167e-05, "epoch": 0.22641509433962265, "percentage": 22.67, "elapsed_time": "0:07:52", "remaining_time": "0:26:51"}
52
+ {"current_steps": 52, "total_steps": 225, "loss": 1.1908, "lr": 1.7969943687415575e-05, "epoch": 0.23085460599334073, "percentage": 23.11, "elapsed_time": "0:08:01", "remaining_time": "0:26:41"}
53
+ {"current_steps": 53, "total_steps": 225, "loss": 1.2127, "lr": 1.788207875027274e-05, "epoch": 0.23529411764705882, "percentage": 23.56, "elapsed_time": "0:08:08", "remaining_time": "0:26:24"}
54
+ {"current_steps": 54, "total_steps": 225, "loss": 1.1944, "lr": 1.7792576921184374e-05, "epoch": 0.2397336293007769, "percentage": 24.0, "elapsed_time": "0:08:17", "remaining_time": "0:26:15"}
55
+ {"current_steps": 55, "total_steps": 225, "loss": 1.1736, "lr": 1.7701456787229805e-05, "epoch": 0.244173140954495, "percentage": 24.44, "elapsed_time": "0:08:27", "remaining_time": "0:26:07"}
56
+ {"current_steps": 56, "total_steps": 225, "loss": 1.2267, "lr": 1.7608737271566004e-05, "epoch": 0.2486126526082131, "percentage": 24.89, "elapsed_time": "0:08:38", "remaining_time": "0:26:03"}
57
+ {"current_steps": 57, "total_steps": 225, "loss": 1.232, "lr": 1.751443762949772e-05, "epoch": 0.25305216426193117, "percentage": 25.33, "elapsed_time": "0:08:48", "remaining_time": "0:25:56"}
58
+ {"current_steps": 58, "total_steps": 225, "loss": 1.1872, "lr": 1.741857744447869e-05, "epoch": 0.25749167591564925, "percentage": 25.78, "elapsed_time": "0:08:57", "remaining_time": "0:25:47"}
59
+ {"current_steps": 59, "total_steps": 225, "loss": 1.253, "lr": 1.732117662404469e-05, "epoch": 0.2619311875693674, "percentage": 26.22, "elapsed_time": "0:09:07", "remaining_time": "0:25:39"}
60
+ {"current_steps": 60, "total_steps": 225, "loss": 1.2586, "lr": 1.7222255395679298e-05, "epoch": 0.2663706992230855, "percentage": 26.67, "elapsed_time": "0:09:16", "remaining_time": "0:25:31"}
61
+ {"current_steps": 61, "total_steps": 225, "loss": 1.3174, "lr": 1.712183430261319e-05, "epoch": 0.27081021087680357, "percentage": 27.11, "elapsed_time": "0:09:25", "remaining_time": "0:25:19"}
62
+ {"current_steps": 62, "total_steps": 225, "loss": 1.2072, "lr": 1.7019934199557868e-05, "epoch": 0.27524972253052166, "percentage": 27.56, "elapsed_time": "0:09:34", "remaining_time": "0:25:11"}
63
+ {"current_steps": 63, "total_steps": 225, "loss": 1.2234, "lr": 1.691657624837472e-05, "epoch": 0.27968923418423974, "percentage": 28.0, "elapsed_time": "0:09:44", "remaining_time": "0:25:02"}
64
+ {"current_steps": 64, "total_steps": 225, "loss": 1.2366, "lr": 1.6811781913680273e-05, "epoch": 0.28412874583795783, "percentage": 28.44, "elapsed_time": "0:09:54", "remaining_time": "0:24:55"}
65
+ {"current_steps": 65, "total_steps": 225, "loss": 1.1597, "lr": 1.6705572958388576e-05, "epoch": 0.2885682574916759, "percentage": 28.89, "elapsed_time": "0:10:02", "remaining_time": "0:24:42"}
66
+ {"current_steps": 66, "total_steps": 225, "loss": 1.1738, "lr": 1.659797143919165e-05, "epoch": 0.293007769145394, "percentage": 29.33, "elapsed_time": "0:10:11", "remaining_time": "0:24:33"}
67
+ {"current_steps": 67, "total_steps": 225, "loss": 1.1214, "lr": 1.6488999701978905e-05, "epoch": 0.2974472807991121, "percentage": 29.78, "elapsed_time": "0:10:20", "remaining_time": "0:24:24"}
68
+ {"current_steps": 68, "total_steps": 225, "loss": 1.1799, "lr": 1.6378680377196526e-05, "epoch": 0.3018867924528302, "percentage": 30.22, "elapsed_time": "0:10:30", "remaining_time": "0:24:15"}
69
+ {"current_steps": 69, "total_steps": 225, "loss": 1.187, "lr": 1.6267036375147728e-05, "epoch": 0.30632630410654826, "percentage": 30.67, "elapsed_time": "0:10:38", "remaining_time": "0:24:03"}
70
+ {"current_steps": 70, "total_steps": 225, "loss": 1.2668, "lr": 1.615409088123493e-05, "epoch": 0.31076581576026635, "percentage": 31.11, "elapsed_time": "0:10:48", "remaining_time": "0:23:54"}
71
+ {"current_steps": 71, "total_steps": 225, "loss": 1.2241, "lr": 1.6039867351144778e-05, "epoch": 0.31520532741398444, "percentage": 31.56, "elapsed_time": "0:10:56", "remaining_time": "0:23:43"}
72
+ {"current_steps": 72, "total_steps": 225, "loss": 1.228, "lr": 1.5924389505977038e-05, "epoch": 0.3196448390677026, "percentage": 32.0, "elapsed_time": "0:11:05", "remaining_time": "0:23:34"}
73
+ {"current_steps": 73, "total_steps": 225, "loss": 1.1584, "lr": 1.5807681327318372e-05, "epoch": 0.32408435072142067, "percentage": 32.44, "elapsed_time": "0:11:13", "remaining_time": "0:23:23"}
74
+ {"current_steps": 74, "total_steps": 225, "loss": 1.2324, "lr": 1.5689767052262028e-05, "epoch": 0.32852386237513875, "percentage": 32.89, "elapsed_time": "0:11:23", "remaining_time": "0:23:14"}
75
+ {"current_steps": 75, "total_steps": 225, "loss": 1.1829, "lr": 1.557067116837444e-05, "epoch": 0.33296337402885684, "percentage": 33.33, "elapsed_time": "0:11:31", "remaining_time": "0:23:03"}
76
+ {"current_steps": 76, "total_steps": 225, "loss": 1.233, "lr": 1.545041840860986e-05, "epoch": 0.3374028856825749, "percentage": 33.78, "elapsed_time": "0:11:40", "remaining_time": "0:22:53"}
77
+ {"current_steps": 77, "total_steps": 225, "loss": 1.2338, "lr": 1.5329033746173975e-05, "epoch": 0.341842397336293, "percentage": 34.22, "elapsed_time": "0:11:51", "remaining_time": "0:22:47"}
78
+ {"current_steps": 78, "total_steps": 225, "loss": 1.1973, "lr": 1.520654238933767e-05, "epoch": 0.3462819089900111, "percentage": 34.67, "elapsed_time": "0:12:00", "remaining_time": "0:22:38"}
79
+ {"current_steps": 79, "total_steps": 225, "loss": 1.2133, "lr": 1.5082969776201948e-05, "epoch": 0.3507214206437292, "percentage": 35.11, "elapsed_time": "0:12:11", "remaining_time": "0:22:31"}
80
+ {"current_steps": 80, "total_steps": 225, "loss": 1.2102, "lr": 1.4958341569415149e-05, "epoch": 0.3551609322974473, "percentage": 35.56, "elapsed_time": "0:12:21", "remaining_time": "0:22:24"}
81
+ {"current_steps": 81, "total_steps": 225, "loss": 1.1888, "lr": 1.483268365084351e-05, "epoch": 0.35960044395116536, "percentage": 36.0, "elapsed_time": "0:12:31", "remaining_time": "0:22:15"}
82
+ {"current_steps": 82, "total_steps": 225, "loss": 1.2082, "lr": 1.4706022116196208e-05, "epoch": 0.36403995560488345, "percentage": 36.44, "elapsed_time": "0:12:41", "remaining_time": "0:22:07"}
83
+ {"current_steps": 83, "total_steps": 225, "loss": 1.2041, "lr": 1.4578383269606004e-05, "epoch": 0.36847946725860153, "percentage": 36.89, "elapsed_time": "0:12:50", "remaining_time": "0:21:57"}
84
+ {"current_steps": 84, "total_steps": 225, "loss": 1.2091, "lr": 1.4449793618166594e-05, "epoch": 0.3729189789123196, "percentage": 37.33, "elapsed_time": "0:12:59", "remaining_time": "0:21:49"}
85
+ {"current_steps": 85, "total_steps": 225, "loss": 1.1901, "lr": 1.4320279866427798e-05, "epoch": 0.37735849056603776, "percentage": 37.78, "elapsed_time": "0:13:09", "remaining_time": "0:21:40"}
86
+ {"current_steps": 86, "total_steps": 225, "loss": 1.1741, "lr": 1.4189868910849779e-05, "epoch": 0.38179800221975585, "percentage": 38.22, "elapsed_time": "0:13:19", "remaining_time": "0:21:32"}
87
+ {"current_steps": 87, "total_steps": 225, "loss": 1.1934, "lr": 1.4058587834217356e-05, "epoch": 0.38623751387347394, "percentage": 38.67, "elapsed_time": "0:13:27", "remaining_time": "0:21:21"}
88
+ {"current_steps": 88, "total_steps": 225, "loss": 1.1439, "lr": 1.392646390001569e-05, "epoch": 0.390677025527192, "percentage": 39.11, "elapsed_time": "0:13:38", "remaining_time": "0:21:14"}
89
+ {"current_steps": 89, "total_steps": 225, "loss": 1.1316, "lr": 1.3793524546768358e-05, "epoch": 0.3951165371809101, "percentage": 39.56, "elapsed_time": "0:13:48", "remaining_time": "0:21:05"}
90
+ {"current_steps": 90, "total_steps": 225, "loss": 1.2326, "lr": 1.3659797382339162e-05, "epoch": 0.3995560488346282, "percentage": 40.0, "elapsed_time": "0:13:58", "remaining_time": "0:20:58"}
91
+ {"current_steps": 91, "total_steps": 225, "loss": 1.2022, "lr": 1.3525310178198707e-05, "epoch": 0.4039955604883463, "percentage": 40.44, "elapsed_time": "0:14:07", "remaining_time": "0:20:48"}
92
+ {"current_steps": 92, "total_steps": 225, "loss": 1.2236, "lr": 1.3390090863657048e-05, "epoch": 0.40843507214206437, "percentage": 40.89, "elapsed_time": "0:14:17", "remaining_time": "0:20:39"}
93
+ {"current_steps": 93, "total_steps": 225, "loss": 1.1421, "lr": 1.325416752006351e-05, "epoch": 0.41287458379578246, "percentage": 41.33, "elapsed_time": "0:14:27", "remaining_time": "0:20:30"}
94
+ {"current_steps": 94, "total_steps": 225, "loss": 1.1325, "lr": 1.311756837497499e-05, "epoch": 0.41731409544950054, "percentage": 41.78, "elapsed_time": "0:14:36", "remaining_time": "0:20:20"}
95
+ {"current_steps": 95, "total_steps": 225, "loss": 1.1475, "lr": 1.2980321796293838e-05, "epoch": 0.42175360710321863, "percentage": 42.22, "elapsed_time": "0:14:46", "remaining_time": "0:20:13"}
96
+ {"current_steps": 96, "total_steps": 225, "loss": 1.1715, "lr": 1.284245628637665e-05, "epoch": 0.4261931187569367, "percentage": 42.67, "elapsed_time": "0:14:55", "remaining_time": "0:20:03"}
97
+ {"current_steps": 97, "total_steps": 225, "loss": 1.1595, "lr": 1.2704000476115079e-05, "epoch": 0.4306326304106548, "percentage": 43.11, "elapsed_time": "0:15:03", "remaining_time": "0:19:52"}
98
+ {"current_steps": 98, "total_steps": 225, "loss": 1.193, "lr": 1.256498311899001e-05, "epoch": 0.43507214206437295, "percentage": 43.56, "elapsed_time": "0:15:12", "remaining_time": "0:19:42"}
99
+ {"current_steps": 99, "total_steps": 225, "loss": 1.1566, "lr": 1.2425433085100224e-05, "epoch": 0.43951165371809103, "percentage": 44.0, "elapsed_time": "0:15:21", "remaining_time": "0:19:32"}
100
+ {"current_steps": 100, "total_steps": 225, "loss": 1.1709, "lr": 1.2285379355166893e-05, "epoch": 0.4439511653718091, "percentage": 44.44, "elapsed_time": "0:15:30", "remaining_time": "0:19:23"}
101
+ {"current_steps": 101, "total_steps": 225, "loss": 1.1688, "lr": 1.2144851014515055e-05, "epoch": 0.4483906770255272, "percentage": 44.89, "elapsed_time": "0:15:41", "remaining_time": "0:19:15"}
102
+ {"current_steps": 102, "total_steps": 225, "loss": 1.1855, "lr": 1.2003877247033411e-05, "epoch": 0.4528301886792453, "percentage": 45.33, "elapsed_time": "0:15:50", "remaining_time": "0:19:06"}
103
+ {"current_steps": 103, "total_steps": 225, "loss": 1.1603, "lr": 1.1862487329113606e-05, "epoch": 0.4572697003329634, "percentage": 45.78, "elapsed_time": "0:16:00", "remaining_time": "0:18:57"}
104
+ {"current_steps": 104, "total_steps": 225, "loss": 1.1789, "lr": 1.172071062357035e-05, "epoch": 0.46170921198668147, "percentage": 46.22, "elapsed_time": "0:16:09", "remaining_time": "0:18:47"}
105
+ {"current_steps": 105, "total_steps": 225, "loss": 1.1339, "lr": 1.1578576573543541e-05, "epoch": 0.46614872364039955, "percentage": 46.67, "elapsed_time": "0:16:18", "remaining_time": "0:18:38"}
106
+ {"current_steps": 106, "total_steps": 225, "loss": 1.186, "lr": 1.1436114696383749e-05, "epoch": 0.47058823529411764, "percentage": 47.11, "elapsed_time": "0:16:27", "remaining_time": "0:18:28"}
107
+ {"current_steps": 107, "total_steps": 225, "loss": 1.1697, "lr": 1.1293354577522264e-05, "epoch": 0.4750277469478357, "percentage": 47.56, "elapsed_time": "0:16:37", "remaining_time": "0:18:19"}
108
+ {"current_steps": 108, "total_steps": 225, "loss": 1.2233, "lr": 1.1150325864327003e-05, "epoch": 0.4794672586015538, "percentage": 48.0, "elapsed_time": "0:16:47", "remaining_time": "0:18:11"}
109
+ {"current_steps": 109, "total_steps": 225, "loss": 1.2148, "lr": 1.1007058259945584e-05, "epoch": 0.4839067702552719, "percentage": 48.44, "elapsed_time": "0:16:56", "remaining_time": "0:18:01"}
110
+ {"current_steps": 110, "total_steps": 225, "loss": 1.1367, "lr": 1.0863581517136776e-05, "epoch": 0.48834628190899, "percentage": 48.89, "elapsed_time": "0:17:05", "remaining_time": "0:17:51"}
111
+ {"current_steps": 111, "total_steps": 225, "loss": 1.1834, "lr": 1.0719925432091671e-05, "epoch": 0.49278579356270813, "percentage": 49.33, "elapsed_time": "0:17:15", "remaining_time": "0:17:43"}
112
+ {"current_steps": 112, "total_steps": 225, "loss": 1.1046, "lr": 1.0576119838245843e-05, "epoch": 0.4972253052164262, "percentage": 49.78, "elapsed_time": "0:17:24", "remaining_time": "0:17:34"}
113
+ {"current_steps": 113, "total_steps": 225, "loss": 1.1694, "lr": 1.043219460008374e-05, "epoch": 0.5016648168701443, "percentage": 50.22, "elapsed_time": "0:17:35", "remaining_time": "0:17:25"}
114
+ {"current_steps": 114, "total_steps": 225, "loss": 1.2525, "lr": 1.0288179606936666e-05, "epoch": 0.5061043285238623, "percentage": 50.67, "elapsed_time": "0:17:43", "remaining_time": "0:17:15"}
115
+ {"current_steps": 115, "total_steps": 225, "loss": 1.1787, "lr": 1.0144104766775574e-05, "epoch": 0.5105438401775805, "percentage": 51.11, "elapsed_time": "0:17:53", "remaining_time": "0:17:06"}
116
+ {"current_steps": 116, "total_steps": 225, "loss": 1.1388, "lr": 1e-05, "epoch": 0.5149833518312985, "percentage": 51.56, "elapsed_time": "0:18:02", "remaining_time": "0:16:56"}
117
+ {"current_steps": 117, "total_steps": 225, "loss": 1.1042, "lr": 9.855895233224431e-06, "epoch": 0.5194228634850167, "percentage": 52.0, "elapsed_time": "0:18:11", "remaining_time": "0:16:47"}
118
+ {"current_steps": 118, "total_steps": 225, "loss": 1.1286, "lr": 9.711820393063337e-06, "epoch": 0.5238623751387348, "percentage": 52.44, "elapsed_time": "0:18:20", "remaining_time": "0:16:38"}
119
+ {"current_steps": 119, "total_steps": 225, "loss": 1.1385, "lr": 9.56780539991626e-06, "epoch": 0.5283018867924528, "percentage": 52.89, "elapsed_time": "0:18:30", "remaining_time": "0:16:29"}
120
+ {"current_steps": 120, "total_steps": 225, "loss": 1.1864, "lr": 9.423880161754158e-06, "epoch": 0.532741398446171, "percentage": 53.33, "elapsed_time": "0:18:40", "remaining_time": "0:16:20"}
121
+ {"current_steps": 121, "total_steps": 225, "loss": 1.1412, "lr": 9.28007456790833e-06, "epoch": 0.537180910099889, "percentage": 53.78, "elapsed_time": "0:18:49", "remaining_time": "0:16:10"}
122
+ {"current_steps": 122, "total_steps": 225, "loss": 1.1733, "lr": 9.13641848286323e-06, "epoch": 0.5416204217536071, "percentage": 54.22, "elapsed_time": "0:18:57", "remaining_time": "0:16:00"}
123
+ {"current_steps": 123, "total_steps": 225, "loss": 1.1297, "lr": 8.992941740054418e-06, "epoch": 0.5460599334073252, "percentage": 54.67, "elapsed_time": "0:19:07", "remaining_time": "0:15:51"}
124
+ {"current_steps": 124, "total_steps": 225, "loss": 1.2096, "lr": 8.849674135672999e-06, "epoch": 0.5504994450610433, "percentage": 55.11, "elapsed_time": "0:19:17", "remaining_time": "0:15:42"}
125
+ {"current_steps": 125, "total_steps": 225, "loss": 1.1531, "lr": 8.706645422477739e-06, "epoch": 0.5549389567147613, "percentage": 55.56, "elapsed_time": "0:19:25", "remaining_time": "0:15:32"}
126
+ {"current_steps": 126, "total_steps": 225, "loss": 1.1896, "lr": 8.563885303616253e-06, "epoch": 0.5593784683684795, "percentage": 56.0, "elapsed_time": "0:19:35", "remaining_time": "0:15:23"}
127
+ {"current_steps": 127, "total_steps": 225, "loss": 1.112, "lr": 8.42142342645646e-06, "epoch": 0.5638179800221975, "percentage": 56.44, "elapsed_time": "0:19:45", "remaining_time": "0:15:14"}
128
+ {"current_steps": 128, "total_steps": 225, "loss": 1.1457, "lr": 8.279289376429653e-06, "epoch": 0.5682574916759157, "percentage": 56.89, "elapsed_time": "0:19:55", "remaining_time": "0:15:05"}
129
+ {"current_steps": 129, "total_steps": 225, "loss": 1.139, "lr": 8.137512670886397e-06, "epoch": 0.5726970033296337, "percentage": 57.33, "elapsed_time": "0:20:04", "remaining_time": "0:14:56"}
130
+ {"current_steps": 130, "total_steps": 225, "loss": 1.1181, "lr": 7.996122752966596e-06, "epoch": 0.5771365149833518, "percentage": 57.78, "elapsed_time": "0:20:13", "remaining_time": "0:14:46"}
131
+ {"current_steps": 131, "total_steps": 225, "loss": 1.1517, "lr": 7.855148985484946e-06, "epoch": 0.58157602663707, "percentage": 58.22, "elapsed_time": "0:20:22", "remaining_time": "0:14:37"}
132
+ {"current_steps": 132, "total_steps": 225, "loss": 1.0982, "lr": 7.71462064483311e-06, "epoch": 0.586015538290788, "percentage": 58.67, "elapsed_time": "0:20:31", "remaining_time": "0:14:27"}
133
+ {"current_steps": 133, "total_steps": 225, "loss": 1.1787, "lr": 7.574566914899779e-06, "epoch": 0.5904550499445061, "percentage": 59.11, "elapsed_time": "0:20:39", "remaining_time": "0:14:17"}
134
+ {"current_steps": 134, "total_steps": 225, "loss": 1.1871, "lr": 7.4350168810099955e-06, "epoch": 0.5948945615982242, "percentage": 59.56, "elapsed_time": "0:20:48", "remaining_time": "0:14:07"}
135
+ {"current_steps": 135, "total_steps": 225, "loss": 1.1396, "lr": 7.295999523884921e-06, "epoch": 0.5993340732519423, "percentage": 60.0, "elapsed_time": "0:20:58", "remaining_time": "0:13:58"}
136
+ {"current_steps": 136, "total_steps": 225, "loss": 1.1719, "lr": 7.157543713623353e-06, "epoch": 0.6037735849056604, "percentage": 60.44, "elapsed_time": "0:21:08", "remaining_time": "0:13:49"}
137
+ {"current_steps": 137, "total_steps": 225, "loss": 1.1714, "lr": 7.019678203706164e-06, "epoch": 0.6082130965593785, "percentage": 60.89, "elapsed_time": "0:21:18", "remaining_time": "0:13:41"}
138
+ {"current_steps": 138, "total_steps": 225, "loss": 1.1439, "lr": 6.882431625025016e-06, "epoch": 0.6126526082130965, "percentage": 61.33, "elapsed_time": "0:21:28", "remaining_time": "0:13:32"}
139
+ {"current_steps": 139, "total_steps": 225, "loss": 1.1511, "lr": 6.745832479936492e-06, "epoch": 0.6170921198668147, "percentage": 61.78, "elapsed_time": "0:21:37", "remaining_time": "0:13:22"}
140
+ {"current_steps": 140, "total_steps": 225, "loss": 1.172, "lr": 6.609909136342956e-06, "epoch": 0.6215316315205327, "percentage": 62.22, "elapsed_time": "0:21:46", "remaining_time": "0:13:13"}
141
+ {"current_steps": 141, "total_steps": 225, "loss": 1.1422, "lr": 6.474689821801295e-06, "epoch": 0.6259711431742508, "percentage": 62.67, "elapsed_time": "0:21:55", "remaining_time": "0:13:03"}
142
+ {"current_steps": 142, "total_steps": 225, "loss": 1.1553, "lr": 6.340202617660842e-06, "epoch": 0.6304106548279689, "percentage": 63.11, "elapsed_time": "0:22:05", "remaining_time": "0:12:54"}
143
+ {"current_steps": 143, "total_steps": 225, "loss": 1.2252, "lr": 6.206475453231644e-06, "epoch": 0.634850166481687, "percentage": 63.56, "elapsed_time": "0:22:16", "remaining_time": "0:12:46"}
144
+ {"current_steps": 144, "total_steps": 225, "loss": 1.193, "lr": 6.073536099984314e-06, "epoch": 0.6392896781354052, "percentage": 64.0, "elapsed_time": "0:22:25", "remaining_time": "0:12:37"}
145
+ {"current_steps": 145, "total_steps": 225, "loss": 1.1921, "lr": 5.941412165782645e-06, "epoch": 0.6437291897891232, "percentage": 64.44, "elapsed_time": "0:22:36", "remaining_time": "0:12:28"}
146
+ {"current_steps": 146, "total_steps": 225, "loss": 1.1906, "lr": 5.810131089150228e-06, "epoch": 0.6481687014428413, "percentage": 64.89, "elapsed_time": "0:22:45", "remaining_time": "0:12:18"}
147
+ {"current_steps": 147, "total_steps": 225, "loss": 1.1297, "lr": 5.6797201335722064e-06, "epoch": 0.6526082130965594, "percentage": 65.33, "elapsed_time": "0:22:53", "remaining_time": "0:12:08"}
148
+ {"current_steps": 148, "total_steps": 225, "loss": 1.213, "lr": 5.550206381833409e-06, "epoch": 0.6570477247502775, "percentage": 65.78, "elapsed_time": "0:23:02", "remaining_time": "0:11:59"}
149
+ {"current_steps": 149, "total_steps": 225, "loss": 1.1643, "lr": 5.421616730394e-06, "epoch": 0.6614872364039955, "percentage": 66.22, "elapsed_time": "0:23:11", "remaining_time": "0:11:49"}
150
+ {"current_steps": 150, "total_steps": 225, "loss": 1.1866, "lr": 5.293977883803797e-06, "epoch": 0.6659267480577137, "percentage": 66.67, "elapsed_time": "0:23:21", "remaining_time": "0:11:40"}
151
+ {"current_steps": 151, "total_steps": 225, "loss": 1.1487, "lr": 5.167316349156495e-06, "epoch": 0.6703662597114317, "percentage": 67.11, "elapsed_time": "0:23:31", "remaining_time": "0:11:31"}
152
+ {"current_steps": 152, "total_steps": 225, "loss": 1.148, "lr": 5.041658430584852e-06, "epoch": 0.6748057713651499, "percentage": 67.56, "elapsed_time": "0:23:41", "remaining_time": "0:11:22"}
153
+ {"current_steps": 153, "total_steps": 225, "loss": 1.1462, "lr": 4.917030223798057e-06, "epoch": 0.6792452830188679, "percentage": 68.0, "elapsed_time": "0:23:52", "remaining_time": "0:11:14"}
154
+ {"current_steps": 154, "total_steps": 225, "loss": 1.1887, "lr": 4.793457610662334e-06, "epoch": 0.683684794672586, "percentage": 68.44, "elapsed_time": "0:24:02", "remaining_time": "0:11:04"}
155
+ {"current_steps": 155, "total_steps": 225, "loss": 1.0909, "lr": 4.670966253826027e-06, "epoch": 0.6881243063263041, "percentage": 68.89, "elapsed_time": "0:24:09", "remaining_time": "0:10:54"}
156
+ {"current_steps": 156, "total_steps": 225, "loss": 1.1357, "lr": 4.549581591390142e-06, "epoch": 0.6925638179800222, "percentage": 69.33, "elapsed_time": "0:24:19", "remaining_time": "0:10:45"}
157
+ {"current_steps": 157, "total_steps": 225, "loss": 1.1529, "lr": 4.429328831625565e-06, "epoch": 0.6970033296337403, "percentage": 69.78, "elapsed_time": "0:24:29", "remaining_time": "0:10:36"}
158
+ {"current_steps": 158, "total_steps": 225, "loss": 1.1435, "lr": 4.310232947737979e-06, "epoch": 0.7014428412874584, "percentage": 70.22, "elapsed_time": "0:24:39", "remaining_time": "0:10:27"}
159
+ {"current_steps": 159, "total_steps": 225, "loss": 1.1878, "lr": 4.192318672681631e-06, "epoch": 0.7058823529411765, "percentage": 70.67, "elapsed_time": "0:24:48", "remaining_time": "0:10:18"}
160
+ {"current_steps": 160, "total_steps": 225, "loss": 1.1887, "lr": 4.0756104940229645e-06, "epoch": 0.7103218645948945, "percentage": 71.11, "elapsed_time": "0:24:58", "remaining_time": "0:10:08"}
161
+ {"current_steps": 161, "total_steps": 225, "loss": 1.1406, "lr": 3.960132648855226e-06, "epoch": 0.7147613762486127, "percentage": 71.56, "elapsed_time": "0:25:06", "remaining_time": "0:09:58"}
162
+ {"current_steps": 162, "total_steps": 225, "loss": 1.149, "lr": 3.845909118765073e-06, "epoch": 0.7192008879023307, "percentage": 72.0, "elapsed_time": "0:25:15", "remaining_time": "0:09:49"}
163
+ {"current_steps": 163, "total_steps": 225, "loss": 1.136, "lr": 3.732963624852275e-06, "epoch": 0.7236403995560489, "percentage": 72.44, "elapsed_time": "0:25:23", "remaining_time": "0:09:39"}
164
+ {"current_steps": 164, "total_steps": 225, "loss": 1.1052, "lr": 3.6213196228034796e-06, "epoch": 0.7280799112097669, "percentage": 72.89, "elapsed_time": "0:25:32", "remaining_time": "0:09:29"}
165
+ {"current_steps": 165, "total_steps": 225, "loss": 1.115, "lr": 3.511000298021098e-06, "epoch": 0.732519422863485, "percentage": 73.33, "elapsed_time": "0:25:40", "remaining_time": "0:09:20"}
166
+ {"current_steps": 166, "total_steps": 225, "loss": 1.1997, "lr": 3.402028560808357e-06, "epoch": 0.7369589345172031, "percentage": 73.78, "elapsed_time": "0:25:49", "remaining_time": "0:09:10"}
167
+ {"current_steps": 167, "total_steps": 225, "loss": 1.1601, "lr": 3.2944270416114256e-06, "epoch": 0.7413984461709212, "percentage": 74.22, "elapsed_time": "0:25:58", "remaining_time": "0:09:01"}
168
+ {"current_steps": 168, "total_steps": 225, "loss": 1.131, "lr": 3.1882180863197308e-06, "epoch": 0.7458379578246392, "percentage": 74.67, "elapsed_time": "0:26:07", "remaining_time": "0:08:51"}
169
+ {"current_steps": 169, "total_steps": 225, "loss": 1.1655, "lr": 3.0834237516252817e-06, "epoch": 0.7502774694783574, "percentage": 75.11, "elapsed_time": "0:26:16", "remaining_time": "0:08:42"}
170
+ {"current_steps": 170, "total_steps": 225, "loss": 1.1496, "lr": 2.980065800442137e-06, "epoch": 0.7547169811320755, "percentage": 75.56, "elapsed_time": "0:26:25", "remaining_time": "0:08:32"}
171
+ {"current_steps": 171, "total_steps": 225, "loss": 1.1314, "lr": 2.878165697386812e-06, "epoch": 0.7591564927857936, "percentage": 76.0, "elapsed_time": "0:26:34", "remaining_time": "0:08:23"}
172
+ {"current_steps": 172, "total_steps": 225, "loss": 1.2001, "lr": 2.777744604320706e-06, "epoch": 0.7635960044395117, "percentage": 76.44, "elapsed_time": "0:26:43", "remaining_time": "0:08:14"}
173
+ {"current_steps": 173, "total_steps": 225, "loss": 1.1451, "lr": 2.678823375955314e-06, "epoch": 0.7680355160932297, "percentage": 76.89, "elapsed_time": "0:26:53", "remaining_time": "0:08:05"}
174
+ {"current_steps": 174, "total_steps": 225, "loss": 1.1666, "lr": 2.581422555521316e-06, "epoch": 0.7724750277469479, "percentage": 77.33, "elapsed_time": "0:27:03", "remaining_time": "0:07:55"}
175
+ {"current_steps": 175, "total_steps": 225, "loss": 1.1394, "lr": 2.485562370502279e-06, "epoch": 0.7769145394006659, "percentage": 77.78, "elapsed_time": "0:27:13", "remaining_time": "0:07:46"}
176
+ {"current_steps": 176, "total_steps": 225, "loss": 1.1453, "lr": 2.391262728433995e-06, "epoch": 0.781354051054384, "percentage": 78.22, "elapsed_time": "0:27:22", "remaining_time": "0:07:37"}
177
+ {"current_steps": 177, "total_steps": 225, "loss": 1.1422, "lr": 2.2985432127701945e-06, "epoch": 0.7857935627081021, "percentage": 78.67, "elapsed_time": "0:27:31", "remaining_time": "0:07:27"}
178
+ {"current_steps": 178, "total_steps": 225, "loss": 1.133, "lr": 2.2074230788156325e-06, "epoch": 0.7902330743618202, "percentage": 79.11, "elapsed_time": "0:27:41", "remaining_time": "0:07:18"}
179
+ {"current_steps": 179, "total_steps": 225, "loss": 1.1535, "lr": 2.1179212497272582e-06, "epoch": 0.7946725860155383, "percentage": 79.56, "elapsed_time": "0:27:48", "remaining_time": "0:07:08"}
180
+ {"current_steps": 180, "total_steps": 225, "loss": 1.1871, "lr": 2.030056312584424e-06, "epoch": 0.7991120976692564, "percentage": 80.0, "elapsed_time": "0:27:58", "remaining_time": "0:06:59"}
181
+ {"current_steps": 181, "total_steps": 225, "loss": 1.0986, "lr": 1.9438465145288377e-06, "epoch": 0.8035516093229744, "percentage": 80.44, "elapsed_time": "0:28:07", "remaining_time": "0:06:50"}
182
+ {"current_steps": 182, "total_steps": 225, "loss": 1.118, "lr": 1.8593097589751318e-06, "epoch": 0.8079911209766926, "percentage": 80.89, "elapsed_time": "0:28:16", "remaining_time": "0:06:40"}
183
+ {"current_steps": 183, "total_steps": 225, "loss": 1.1521, "lr": 1.7764636018928249e-06, "epoch": 0.8124306326304107, "percentage": 81.33, "elapsed_time": "0:28:25", "remaining_time": "0:06:31"}
184
+ {"current_steps": 184, "total_steps": 225, "loss": 1.1243, "lr": 1.6953252481604198e-06, "epoch": 0.8168701442841287, "percentage": 81.78, "elapsed_time": "0:28:36", "remaining_time": "0:06:22"}
185
+ {"current_steps": 185, "total_steps": 225, "loss": 1.1496, "lr": 1.6159115479924259e-06, "epoch": 0.8213096559378469, "percentage": 82.22, "elapsed_time": "0:28:45", "remaining_time": "0:06:13"}
186
+ {"current_steps": 186, "total_steps": 225, "loss": 1.1417, "lr": 1.5382389934400199e-06, "epoch": 0.8257491675915649, "percentage": 82.67, "elapsed_time": "0:28:52", "remaining_time": "0:06:03"}
187
+ {"current_steps": 187, "total_steps": 225, "loss": 1.1322, "lr": 1.462323714966114e-06, "epoch": 0.8301886792452831, "percentage": 83.11, "elapsed_time": "0:29:01", "remaining_time": "0:05:53"}
188
+ {"current_steps": 188, "total_steps": 225, "loss": 1.104, "lr": 1.3881814780954916e-06, "epoch": 0.8346281908990011, "percentage": 83.56, "elapsed_time": "0:29:10", "remaining_time": "0:05:44"}
189
+ {"current_steps": 189, "total_steps": 225, "loss": 1.181, "lr": 1.3158276801407432e-06, "epoch": 0.8390677025527192, "percentage": 84.0, "elapsed_time": "0:29:19", "remaining_time": "0:05:35"}
190
+ {"current_steps": 190, "total_steps": 225, "loss": 1.2015, "lr": 1.2452773470046543e-06, "epoch": 0.8435072142064373, "percentage": 84.44, "elapsed_time": "0:29:29", "remaining_time": "0:05:25"}
191
+ {"current_steps": 191, "total_steps": 225, "loss": 1.1697, "lr": 1.1765451300597574e-06, "epoch": 0.8479467258601554, "percentage": 84.89, "elapsed_time": "0:29:38", "remaining_time": "0:05:16"}
192
+ {"current_steps": 192, "total_steps": 225, "loss": 1.1007, "lr": 1.1096453031056265e-06, "epoch": 0.8523862375138734, "percentage": 85.33, "elapsed_time": "0:29:47", "remaining_time": "0:05:07"}
193
+ {"current_steps": 193, "total_steps": 225, "loss": 1.1135, "lr": 1.0445917594046073e-06, "epoch": 0.8568257491675916, "percentage": 85.78, "elapsed_time": "0:29:57", "remaining_time": "0:04:58"}
194
+ {"current_steps": 194, "total_steps": 225, "loss": 1.1501, "lr": 9.813980087965625e-07, "epoch": 0.8612652608213096, "percentage": 86.22, "elapsed_time": "0:30:08", "remaining_time": "0:04:48"}
195
+ {"current_steps": 195, "total_steps": 225, "loss": 1.0861, "lr": 9.200771748932513e-07, "epoch": 0.8657047724750278, "percentage": 86.67, "elapsed_time": "0:30:18", "remaining_time": "0:04:39"}
196
+ {"current_steps": 196, "total_steps": 225, "loss": 1.1256, "lr": 8.606419923529175e-07, "epoch": 0.8701442841287459, "percentage": 87.11, "elapsed_time": "0:30:26", "remaining_time": "0:04:30"}
197
+ {"current_steps": 197, "total_steps": 225, "loss": 1.1844, "lr": 8.031048042356393e-07, "epoch": 0.8745837957824639, "percentage": 87.56, "elapsed_time": "0:30:35", "remaining_time": "0:04:20"}
198
+ {"current_steps": 198, "total_steps": 225, "loss": 1.1142, "lr": 7.474775594400252e-07, "epoch": 0.8790233074361821, "percentage": 88.0, "elapsed_time": "0:30:44", "remaining_time": "0:04:11"}
199
+ {"current_steps": 199, "total_steps": 225, "loss": 1.1735, "lr": 6.937718102217461e-07, "epoch": 0.8834628190899001, "percentage": 88.44, "elapsed_time": "0:30:53", "remaining_time": "0:04:02"}
200
+ {"current_steps": 200, "total_steps": 225, "loss": 1.1656, "lr": 6.41998709794458e-07, "epoch": 0.8879023307436182, "percentage": 88.89, "elapsed_time": "0:31:02", "remaining_time": "0:03:52"}
201
+ {"current_steps": 201, "total_steps": 225, "loss": 1.1665, "lr": 5.921690100135713e-07, "epoch": 0.8923418423973363, "percentage": 89.33, "elapsed_time": "0:31:13", "remaining_time": "0:03:43"}
202
+ {"current_steps": 202, "total_steps": 225, "loss": 1.0818, "lr": 5.442930591433992e-07, "epoch": 0.8967813540510544, "percentage": 89.78, "elapsed_time": "0:31:22", "remaining_time": "0:03:34"}
203
+ {"current_steps": 203, "total_steps": 225, "loss": 1.1625, "lr": 4.983807997080925e-07, "epoch": 0.9012208657047724, "percentage": 90.22, "elapsed_time": "0:31:30", "remaining_time": "0:03:24"}
204
+ {"current_steps": 204, "total_steps": 225, "loss": 1.1001, "lr": 4.544417664268652e-07, "epoch": 0.9056603773584906, "percentage": 90.67, "elapsed_time": "0:31:41", "remaining_time": "0:03:15"}
205
+ {"current_steps": 205, "total_steps": 225, "loss": 1.1392, "lr": 4.124850842338779e-07, "epoch": 0.9100998890122086, "percentage": 91.11, "elapsed_time": "0:31:51", "remaining_time": "0:03:06"}
206
+ {"current_steps": 206, "total_steps": 225, "loss": 1.1308, "lr": 3.725194663832521e-07, "epoch": 0.9145394006659268, "percentage": 91.56, "elapsed_time": "0:32:01", "remaining_time": "0:02:57"}
207
+ {"current_steps": 207, "total_steps": 225, "loss": 1.1334, "lr": 3.345532126395579e-07, "epoch": 0.9189789123196448, "percentage": 92.0, "elapsed_time": "0:32:10", "remaining_time": "0:02:47"}
208
+ {"current_steps": 208, "total_steps": 225, "loss": 1.1135, "lr": 2.985942075541848e-07, "epoch": 0.9234184239733629, "percentage": 92.44, "elapsed_time": "0:32:19", "remaining_time": "0:02:38"}
209
+ {"current_steps": 209, "total_steps": 225, "loss": 1.1604, "lr": 2.646499188279328e-07, "epoch": 0.9278579356270811, "percentage": 92.89, "elapsed_time": "0:32:28", "remaining_time": "0:02:29"}
210
+ {"current_steps": 210, "total_steps": 225, "loss": 1.1296, "lr": 2.3272739576017945e-07, "epoch": 0.9322974472807991, "percentage": 93.33, "elapsed_time": "0:32:37", "remaining_time": "0:02:19"}
211
+ {"current_steps": 211, "total_steps": 225, "loss": 1.1261, "lr": 2.028332677849254e-07, "epoch": 0.9367369589345172, "percentage": 93.78, "elapsed_time": "0:32:46", "remaining_time": "0:02:10"}
212
+ {"current_steps": 212, "total_steps": 225, "loss": 1.174, "lr": 1.7497374309405346e-07, "epoch": 0.9411764705882353, "percentage": 94.22, "elapsed_time": "0:32:56", "remaining_time": "0:02:01"}
213
+ {"current_steps": 213, "total_steps": 225, "loss": 1.1626, "lr": 1.49154607348051e-07, "epoch": 0.9456159822419534, "percentage": 94.67, "elapsed_time": "0:33:05", "remaining_time": "0:01:51"}
214
+ {"current_steps": 214, "total_steps": 225, "loss": 1.1512, "lr": 1.2538122247448325e-07, "epoch": 0.9500554938956715, "percentage": 95.11, "elapsed_time": "0:33:15", "remaining_time": "0:01:42"}
215
+ {"current_steps": 215, "total_steps": 225, "loss": 1.116, "lr": 1.0365852555447642e-07, "epoch": 0.9544950055493896, "percentage": 95.56, "elapsed_time": "0:33:25", "remaining_time": "0:01:33"}
216
+ {"current_steps": 216, "total_steps": 225, "loss": 1.1263, "lr": 8.39910277974132e-08, "epoch": 0.9589345172031076, "percentage": 96.0, "elapsed_time": "0:33:36", "remaining_time": "0:01:24"}
217
+ {"current_steps": 217, "total_steps": 225, "loss": 1.1357, "lr": 6.638281360408339e-08, "epoch": 0.9633740288568258, "percentage": 96.44, "elapsed_time": "0:33:45", "remaining_time": "0:01:14"}
218
+ {"current_steps": 218, "total_steps": 225, "loss": 1.0744, "lr": 5.083753971846239e-08, "epoch": 0.9678135405105438, "percentage": 96.89, "elapsed_time": "0:33:54", "remaining_time": "0:01:05"}
219
+ {"current_steps": 219, "total_steps": 225, "loss": 1.1356, "lr": 3.735843446830867e-08, "epoch": 0.9722530521642619, "percentage": 97.33, "elapsed_time": "0:34:04", "remaining_time": "0:00:56"}
220
+ {"current_steps": 220, "total_steps": 225, "loss": 1.1227, "lr": 2.5948297094724463e-08, "epoch": 0.97669256381798, "percentage": 97.78, "elapsed_time": "0:34:13", "remaining_time": "0:00:46"}
221
+ {"current_steps": 221, "total_steps": 225, "loss": 1.0993, "lr": 1.6609497170834154e-08, "epoch": 0.9811320754716981, "percentage": 98.22, "elapsed_time": "0:34:22", "remaining_time": "0:00:37"}
222
+ {"current_steps": 222, "total_steps": 225, "loss": 1.1632, "lr": 9.343974109685684e-09, "epoch": 0.9855715871254163, "percentage": 98.67, "elapsed_time": "0:34:30", "remaining_time": "0:00:27"}
223
+ {"current_steps": 223, "total_steps": 225, "loss": 1.0994, "lr": 4.153236761488266e-09, "epoch": 0.9900110987791343, "percentage": 99.11, "elapsed_time": "0:34:40", "remaining_time": "0:00:18"}
224
+ {"current_steps": 224, "total_steps": 225, "loss": 1.1072, "lr": 1.0383631002686133e-09, "epoch": 0.9944506104328524, "percentage": 99.56, "elapsed_time": "0:34:49", "remaining_time": "0:00:09"}
225
+ {"current_steps": 225, "total_steps": 225, "loss": 1.1393, "lr": 0.0, "epoch": 0.9988901220865705, "percentage": 100.0, "elapsed_time": "0:34:57", "remaining_time": "0:00:00"}
226
+ {"current_steps": 225, "total_steps": 225, "epoch": 0.9988901220865705, "percentage": 100.0, "elapsed_time": "0:37:19", "remaining_time": "0:00:00"}
trainer_state.json ADDED
@@ -0,0 +1,1617 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 0.9988901220865705,
5
+ "eval_steps": 500,
6
+ "global_step": 225,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.004439511653718091,
13
+ "grad_norm": 37.533348083496094,
14
+ "learning_rate": 2.8571428571428573e-06,
15
+ "loss": 1.824,
16
+ "step": 1
17
+ },
18
+ {
19
+ "epoch": 0.008879023307436182,
20
+ "grad_norm": 46.24335479736328,
21
+ "learning_rate": 5.7142857142857145e-06,
22
+ "loss": 1.8786,
23
+ "step": 2
24
+ },
25
+ {
26
+ "epoch": 0.013318534961154272,
27
+ "grad_norm": 42.045166015625,
28
+ "learning_rate": 8.571428571428571e-06,
29
+ "loss": 1.7863,
30
+ "step": 3
31
+ },
32
+ {
33
+ "epoch": 0.017758046614872364,
34
+ "grad_norm": 8.661040306091309,
35
+ "learning_rate": 1.1428571428571429e-05,
36
+ "loss": 1.2891,
37
+ "step": 4
38
+ },
39
+ {
40
+ "epoch": 0.022197558268590455,
41
+ "grad_norm": 3.85249400138855,
42
+ "learning_rate": 1.4285714285714287e-05,
43
+ "loss": 1.2127,
44
+ "step": 5
45
+ },
46
+ {
47
+ "epoch": 0.026637069922308545,
48
+ "grad_norm": 7.926912307739258,
49
+ "learning_rate": 1.7142857142857142e-05,
50
+ "loss": 1.2012,
51
+ "step": 6
52
+ },
53
+ {
54
+ "epoch": 0.03107658157602664,
55
+ "grad_norm": 4.07999324798584,
56
+ "learning_rate": 2e-05,
57
+ "loss": 1.2275,
58
+ "step": 7
59
+ },
60
+ {
61
+ "epoch": 0.03551609322974473,
62
+ "grad_norm": 3.668304681777954,
63
+ "learning_rate": 1.9998961636899736e-05,
64
+ "loss": 1.2301,
65
+ "step": 8
66
+ },
67
+ {
68
+ "epoch": 0.03995560488346282,
69
+ "grad_norm": 3.8191933631896973,
70
+ "learning_rate": 1.9995846763238514e-05,
71
+ "loss": 1.18,
72
+ "step": 9
73
+ },
74
+ {
75
+ "epoch": 0.04439511653718091,
76
+ "grad_norm": 3.0913546085357666,
77
+ "learning_rate": 1.9990656025890315e-05,
78
+ "loss": 1.1692,
79
+ "step": 10
80
+ },
81
+ {
82
+ "epoch": 0.048834628190899,
83
+ "grad_norm": 2.7952189445495605,
84
+ "learning_rate": 1.9983390502829168e-05,
85
+ "loss": 1.2112,
86
+ "step": 11
87
+ },
88
+ {
89
+ "epoch": 0.05327413984461709,
90
+ "grad_norm": 2.480602979660034,
91
+ "learning_rate": 1.997405170290528e-05,
92
+ "loss": 1.2294,
93
+ "step": 12
94
+ },
95
+ {
96
+ "epoch": 0.05771365149833518,
97
+ "grad_norm": 2.486560344696045,
98
+ "learning_rate": 1.9962641565531694e-05,
99
+ "loss": 1.222,
100
+ "step": 13
101
+ },
102
+ {
103
+ "epoch": 0.06215316315205328,
104
+ "grad_norm": 2.59287428855896,
105
+ "learning_rate": 1.994916246028154e-05,
106
+ "loss": 1.1607,
107
+ "step": 14
108
+ },
109
+ {
110
+ "epoch": 0.06659267480577137,
111
+ "grad_norm": 2.5444483757019043,
112
+ "learning_rate": 1.9933617186395917e-05,
113
+ "loss": 1.2571,
114
+ "step": 15
115
+ },
116
+ {
117
+ "epoch": 0.07103218645948946,
118
+ "grad_norm": 2.5133490562438965,
119
+ "learning_rate": 1.9916008972202586e-05,
120
+ "loss": 1.1338,
121
+ "step": 16
122
+ },
123
+ {
124
+ "epoch": 0.07547169811320754,
125
+ "grad_norm": 2.2021095752716064,
126
+ "learning_rate": 1.9896341474445526e-05,
127
+ "loss": 1.2253,
128
+ "step": 17
129
+ },
130
+ {
131
+ "epoch": 0.07991120976692564,
132
+ "grad_norm": 2.341919183731079,
133
+ "learning_rate": 1.987461877752552e-05,
134
+ "loss": 1.2575,
135
+ "step": 18
136
+ },
137
+ {
138
+ "epoch": 0.08435072142064373,
139
+ "grad_norm": 2.27514386177063,
140
+ "learning_rate": 1.985084539265195e-05,
141
+ "loss": 1.1895,
142
+ "step": 19
143
+ },
144
+ {
145
+ "epoch": 0.08879023307436182,
146
+ "grad_norm": 2.0287599563598633,
147
+ "learning_rate": 1.982502625690595e-05,
148
+ "loss": 1.122,
149
+ "step": 20
150
+ },
151
+ {
152
+ "epoch": 0.0932297447280799,
153
+ "grad_norm": 2.33461594581604,
154
+ "learning_rate": 1.9797166732215078e-05,
155
+ "loss": 1.2319,
156
+ "step": 21
157
+ },
158
+ {
159
+ "epoch": 0.097669256381798,
160
+ "grad_norm": 2.374116897583008,
161
+ "learning_rate": 1.9767272604239823e-05,
162
+ "loss": 1.2025,
163
+ "step": 22
164
+ },
165
+ {
166
+ "epoch": 0.10210876803551609,
167
+ "grad_norm": 2.2956087589263916,
168
+ "learning_rate": 1.973535008117207e-05,
169
+ "loss": 1.2078,
170
+ "step": 23
171
+ },
172
+ {
173
+ "epoch": 0.10654827968923418,
174
+ "grad_norm": 2.1211025714874268,
175
+ "learning_rate": 1.9701405792445815e-05,
176
+ "loss": 1.1912,
177
+ "step": 24
178
+ },
179
+ {
180
+ "epoch": 0.11098779134295228,
181
+ "grad_norm": 2.2014005184173584,
182
+ "learning_rate": 1.9665446787360444e-05,
183
+ "loss": 1.1932,
184
+ "step": 25
185
+ },
186
+ {
187
+ "epoch": 0.11542730299667037,
188
+ "grad_norm": 2.1209704875946045,
189
+ "learning_rate": 1.962748053361675e-05,
190
+ "loss": 1.2348,
191
+ "step": 26
192
+ },
193
+ {
194
+ "epoch": 0.11986681465038845,
195
+ "grad_norm": 2.0373430252075195,
196
+ "learning_rate": 1.9587514915766124e-05,
197
+ "loss": 1.2503,
198
+ "step": 27
199
+ },
200
+ {
201
+ "epoch": 0.12430632630410655,
202
+ "grad_norm": 2.3817737102508545,
203
+ "learning_rate": 1.9545558233573136e-05,
204
+ "loss": 1.2131,
205
+ "step": 28
206
+ },
207
+ {
208
+ "epoch": 0.12874583795782463,
209
+ "grad_norm": 2.1462056636810303,
210
+ "learning_rate": 1.950161920029191e-05,
211
+ "loss": 1.1736,
212
+ "step": 29
213
+ },
214
+ {
215
+ "epoch": 0.13318534961154274,
216
+ "grad_norm": 2.1412036418914795,
217
+ "learning_rate": 1.9455706940856602e-05,
218
+ "loss": 1.1716,
219
+ "step": 30
220
+ },
221
+ {
222
+ "epoch": 0.13762486126526083,
223
+ "grad_norm": 2.2089121341705322,
224
+ "learning_rate": 1.940783098998643e-05,
225
+ "loss": 1.169,
226
+ "step": 31
227
+ },
228
+ {
229
+ "epoch": 0.14206437291897892,
230
+ "grad_norm": 2.101334571838379,
231
+ "learning_rate": 1.9358001290205542e-05,
232
+ "loss": 1.2226,
233
+ "step": 32
234
+ },
235
+ {
236
+ "epoch": 0.146503884572697,
237
+ "grad_norm": 2.436990976333618,
238
+ "learning_rate": 1.9306228189778255e-05,
239
+ "loss": 1.192,
240
+ "step": 33
241
+ },
242
+ {
243
+ "epoch": 0.1509433962264151,
244
+ "grad_norm": 2.069035768508911,
245
+ "learning_rate": 1.925252244055998e-05,
246
+ "loss": 1.2419,
247
+ "step": 34
248
+ },
249
+ {
250
+ "epoch": 0.15538290788013318,
251
+ "grad_norm": 2.099047899246216,
252
+ "learning_rate": 1.9196895195764363e-05,
253
+ "loss": 1.2004,
254
+ "step": 35
255
+ },
256
+ {
257
+ "epoch": 0.1598224195338513,
258
+ "grad_norm": 2.2311224937438965,
259
+ "learning_rate": 1.9139358007647085e-05,
260
+ "loss": 1.2065,
261
+ "step": 36
262
+ },
263
+ {
264
+ "epoch": 0.16426193118756938,
265
+ "grad_norm": 2.1131861209869385,
266
+ "learning_rate": 1.907992282510675e-05,
267
+ "loss": 1.2158,
268
+ "step": 37
269
+ },
270
+ {
271
+ "epoch": 0.16870144284128746,
272
+ "grad_norm": 1.924771785736084,
273
+ "learning_rate": 1.901860199120344e-05,
274
+ "loss": 1.2714,
275
+ "step": 38
276
+ },
277
+ {
278
+ "epoch": 0.17314095449500555,
279
+ "grad_norm": 1.9812465906143188,
280
+ "learning_rate": 1.8955408240595396e-05,
281
+ "loss": 1.2216,
282
+ "step": 39
283
+ },
284
+ {
285
+ "epoch": 0.17758046614872364,
286
+ "grad_norm": 1.9320334196090698,
287
+ "learning_rate": 1.8890354696894374e-05,
288
+ "loss": 1.2164,
289
+ "step": 40
290
+ },
291
+ {
292
+ "epoch": 0.18201997780244172,
293
+ "grad_norm": 1.9847488403320312,
294
+ "learning_rate": 1.8823454869940243e-05,
295
+ "loss": 1.1705,
296
+ "step": 41
297
+ },
298
+ {
299
+ "epoch": 0.1864594894561598,
300
+ "grad_norm": 1.973925232887268,
301
+ "learning_rate": 1.8754722652995346e-05,
302
+ "loss": 1.1984,
303
+ "step": 42
304
+ },
305
+ {
306
+ "epoch": 0.19089900110987792,
307
+ "grad_norm": 2.0115818977355957,
308
+ "learning_rate": 1.8684172319859258e-05,
309
+ "loss": 1.1659,
310
+ "step": 43
311
+ },
312
+ {
313
+ "epoch": 0.195338512763596,
314
+ "grad_norm": 2.3217947483062744,
315
+ "learning_rate": 1.861181852190451e-05,
316
+ "loss": 1.2463,
317
+ "step": 44
318
+ },
319
+ {
320
+ "epoch": 0.1997780244173141,
321
+ "grad_norm": 2.1839258670806885,
322
+ "learning_rate": 1.8537676285033886e-05,
323
+ "loss": 1.1657,
324
+ "step": 45
325
+ },
326
+ {
327
+ "epoch": 0.20421753607103219,
328
+ "grad_norm": 1.9523669481277466,
329
+ "learning_rate": 1.8461761006559982e-05,
330
+ "loss": 1.1766,
331
+ "step": 46
332
+ },
333
+ {
334
+ "epoch": 0.20865704772475027,
335
+ "grad_norm": 2.1495866775512695,
336
+ "learning_rate": 1.838408845200758e-05,
337
+ "loss": 1.2138,
338
+ "step": 47
339
+ },
340
+ {
341
+ "epoch": 0.21309655937846836,
342
+ "grad_norm": 2.060826539993286,
343
+ "learning_rate": 1.8304674751839583e-05,
344
+ "loss": 1.1817,
345
+ "step": 48
346
+ },
347
+ {
348
+ "epoch": 0.21753607103218647,
349
+ "grad_norm": 2.0041329860687256,
350
+ "learning_rate": 1.8223536398107177e-05,
351
+ "loss": 1.2327,
352
+ "step": 49
353
+ },
354
+ {
355
+ "epoch": 0.22197558268590456,
356
+ "grad_norm": 2.427309989929199,
357
+ "learning_rate": 1.8140690241024872e-05,
358
+ "loss": 1.2012,
359
+ "step": 50
360
+ },
361
+ {
362
+ "epoch": 0.22641509433962265,
363
+ "grad_norm": 2.0693812370300293,
364
+ "learning_rate": 1.8056153485471167e-05,
365
+ "loss": 1.1806,
366
+ "step": 51
367
+ },
368
+ {
369
+ "epoch": 0.23085460599334073,
370
+ "grad_norm": 2.1914312839508057,
371
+ "learning_rate": 1.7969943687415575e-05,
372
+ "loss": 1.1908,
373
+ "step": 52
374
+ },
375
+ {
376
+ "epoch": 0.23529411764705882,
377
+ "grad_norm": 2.1551156044006348,
378
+ "learning_rate": 1.788207875027274e-05,
379
+ "loss": 1.2127,
380
+ "step": 53
381
+ },
382
+ {
383
+ "epoch": 0.2397336293007769,
384
+ "grad_norm": 2.090184211730957,
385
+ "learning_rate": 1.7792576921184374e-05,
386
+ "loss": 1.1944,
387
+ "step": 54
388
+ },
389
+ {
390
+ "epoch": 0.244173140954495,
391
+ "grad_norm": 1.9871045351028442,
392
+ "learning_rate": 1.7701456787229805e-05,
393
+ "loss": 1.1736,
394
+ "step": 55
395
+ },
396
+ {
397
+ "epoch": 0.2486126526082131,
398
+ "grad_norm": 2.1655359268188477,
399
+ "learning_rate": 1.7608737271566004e-05,
400
+ "loss": 1.2267,
401
+ "step": 56
402
+ },
403
+ {
404
+ "epoch": 0.25305216426193117,
405
+ "grad_norm": 2.2310895919799805,
406
+ "learning_rate": 1.751443762949772e-05,
407
+ "loss": 1.232,
408
+ "step": 57
409
+ },
410
+ {
411
+ "epoch": 0.25749167591564925,
412
+ "grad_norm": 2.07645583152771,
413
+ "learning_rate": 1.741857744447869e-05,
414
+ "loss": 1.1872,
415
+ "step": 58
416
+ },
417
+ {
418
+ "epoch": 0.2619311875693674,
419
+ "grad_norm": 2.183539628982544,
420
+ "learning_rate": 1.732117662404469e-05,
421
+ "loss": 1.253,
422
+ "step": 59
423
+ },
424
+ {
425
+ "epoch": 0.2663706992230855,
426
+ "grad_norm": 2.078212261199951,
427
+ "learning_rate": 1.7222255395679298e-05,
428
+ "loss": 1.2586,
429
+ "step": 60
430
+ },
431
+ {
432
+ "epoch": 0.27081021087680357,
433
+ "grad_norm": 1.9478346109390259,
434
+ "learning_rate": 1.712183430261319e-05,
435
+ "loss": 1.3174,
436
+ "step": 61
437
+ },
438
+ {
439
+ "epoch": 0.27524972253052166,
440
+ "grad_norm": 1.9654473066329956,
441
+ "learning_rate": 1.7019934199557868e-05,
442
+ "loss": 1.2072,
443
+ "step": 62
444
+ },
445
+ {
446
+ "epoch": 0.27968923418423974,
447
+ "grad_norm": 2.0590426921844482,
448
+ "learning_rate": 1.691657624837472e-05,
449
+ "loss": 1.2234,
450
+ "step": 63
451
+ },
452
+ {
453
+ "epoch": 0.28412874583795783,
454
+ "grad_norm": 1.9870823621749878,
455
+ "learning_rate": 1.6811781913680273e-05,
456
+ "loss": 1.2366,
457
+ "step": 64
458
+ },
459
+ {
460
+ "epoch": 0.2885682574916759,
461
+ "grad_norm": 2.0088582038879395,
462
+ "learning_rate": 1.6705572958388576e-05,
463
+ "loss": 1.1597,
464
+ "step": 65
465
+ },
466
+ {
467
+ "epoch": 0.293007769145394,
468
+ "grad_norm": 2.107692241668701,
469
+ "learning_rate": 1.659797143919165e-05,
470
+ "loss": 1.1738,
471
+ "step": 66
472
+ },
473
+ {
474
+ "epoch": 0.2974472807991121,
475
+ "grad_norm": 1.8893859386444092,
476
+ "learning_rate": 1.6488999701978905e-05,
477
+ "loss": 1.1214,
478
+ "step": 67
479
+ },
480
+ {
481
+ "epoch": 0.3018867924528302,
482
+ "grad_norm": 1.8780573606491089,
483
+ "learning_rate": 1.6378680377196526e-05,
484
+ "loss": 1.1799,
485
+ "step": 68
486
+ },
487
+ {
488
+ "epoch": 0.30632630410654826,
489
+ "grad_norm": 2.0093393325805664,
490
+ "learning_rate": 1.6267036375147728e-05,
491
+ "loss": 1.187,
492
+ "step": 69
493
+ },
494
+ {
495
+ "epoch": 0.31076581576026635,
496
+ "grad_norm": 1.988927960395813,
497
+ "learning_rate": 1.615409088123493e-05,
498
+ "loss": 1.2668,
499
+ "step": 70
500
+ },
501
+ {
502
+ "epoch": 0.31520532741398444,
503
+ "grad_norm": 1.8668824434280396,
504
+ "learning_rate": 1.6039867351144778e-05,
505
+ "loss": 1.2241,
506
+ "step": 71
507
+ },
508
+ {
509
+ "epoch": 0.3196448390677026,
510
+ "grad_norm": 2.02083420753479,
511
+ "learning_rate": 1.5924389505977038e-05,
512
+ "loss": 1.228,
513
+ "step": 72
514
+ },
515
+ {
516
+ "epoch": 0.32408435072142067,
517
+ "grad_norm": 2.080263137817383,
518
+ "learning_rate": 1.5807681327318372e-05,
519
+ "loss": 1.1584,
520
+ "step": 73
521
+ },
522
+ {
523
+ "epoch": 0.32852386237513875,
524
+ "grad_norm": 1.9211077690124512,
525
+ "learning_rate": 1.5689767052262028e-05,
526
+ "loss": 1.2324,
527
+ "step": 74
528
+ },
529
+ {
530
+ "epoch": 0.33296337402885684,
531
+ "grad_norm": 2.1998391151428223,
532
+ "learning_rate": 1.557067116837444e-05,
533
+ "loss": 1.1829,
534
+ "step": 75
535
+ },
536
+ {
537
+ "epoch": 0.3374028856825749,
538
+ "grad_norm": 1.973344087600708,
539
+ "learning_rate": 1.545041840860986e-05,
540
+ "loss": 1.233,
541
+ "step": 76
542
+ },
543
+ {
544
+ "epoch": 0.341842397336293,
545
+ "grad_norm": 2.0612385272979736,
546
+ "learning_rate": 1.5329033746173975e-05,
547
+ "loss": 1.2338,
548
+ "step": 77
549
+ },
550
+ {
551
+ "epoch": 0.3462819089900111,
552
+ "grad_norm": 2.0529823303222656,
553
+ "learning_rate": 1.520654238933767e-05,
554
+ "loss": 1.1973,
555
+ "step": 78
556
+ },
557
+ {
558
+ "epoch": 0.3507214206437292,
559
+ "grad_norm": 1.8720424175262451,
560
+ "learning_rate": 1.5082969776201948e-05,
561
+ "loss": 1.2133,
562
+ "step": 79
563
+ },
564
+ {
565
+ "epoch": 0.3551609322974473,
566
+ "grad_norm": 1.9517823457717896,
567
+ "learning_rate": 1.4958341569415149e-05,
568
+ "loss": 1.2102,
569
+ "step": 80
570
+ },
571
+ {
572
+ "epoch": 0.35960044395116536,
573
+ "grad_norm": 1.9612551927566528,
574
+ "learning_rate": 1.483268365084351e-05,
575
+ "loss": 1.1888,
576
+ "step": 81
577
+ },
578
+ {
579
+ "epoch": 0.36403995560488345,
580
+ "grad_norm": 2.1608946323394775,
581
+ "learning_rate": 1.4706022116196208e-05,
582
+ "loss": 1.2082,
583
+ "step": 82
584
+ },
585
+ {
586
+ "epoch": 0.36847946725860153,
587
+ "grad_norm": 1.951665997505188,
588
+ "learning_rate": 1.4578383269606004e-05,
589
+ "loss": 1.2041,
590
+ "step": 83
591
+ },
592
+ {
593
+ "epoch": 0.3729189789123196,
594
+ "grad_norm": 1.9137777090072632,
595
+ "learning_rate": 1.4449793618166594e-05,
596
+ "loss": 1.2091,
597
+ "step": 84
598
+ },
599
+ {
600
+ "epoch": 0.37735849056603776,
601
+ "grad_norm": 1.9383291006088257,
602
+ "learning_rate": 1.4320279866427798e-05,
603
+ "loss": 1.1901,
604
+ "step": 85
605
+ },
606
+ {
607
+ "epoch": 0.38179800221975585,
608
+ "grad_norm": 1.8352899551391602,
609
+ "learning_rate": 1.4189868910849779e-05,
610
+ "loss": 1.1741,
611
+ "step": 86
612
+ },
613
+ {
614
+ "epoch": 0.38623751387347394,
615
+ "grad_norm": 1.9220095872879028,
616
+ "learning_rate": 1.4058587834217356e-05,
617
+ "loss": 1.1934,
618
+ "step": 87
619
+ },
620
+ {
621
+ "epoch": 0.390677025527192,
622
+ "grad_norm": 1.7801581621170044,
623
+ "learning_rate": 1.392646390001569e-05,
624
+ "loss": 1.1439,
625
+ "step": 88
626
+ },
627
+ {
628
+ "epoch": 0.3951165371809101,
629
+ "grad_norm": 1.8106623888015747,
630
+ "learning_rate": 1.3793524546768358e-05,
631
+ "loss": 1.1316,
632
+ "step": 89
633
+ },
634
+ {
635
+ "epoch": 0.3995560488346282,
636
+ "grad_norm": 1.822784423828125,
637
+ "learning_rate": 1.3659797382339162e-05,
638
+ "loss": 1.2326,
639
+ "step": 90
640
+ },
641
+ {
642
+ "epoch": 0.4039955604883463,
643
+ "grad_norm": 2.061378240585327,
644
+ "learning_rate": 1.3525310178198707e-05,
645
+ "loss": 1.2022,
646
+ "step": 91
647
+ },
648
+ {
649
+ "epoch": 0.40843507214206437,
650
+ "grad_norm": 1.999387264251709,
651
+ "learning_rate": 1.3390090863657048e-05,
652
+ "loss": 1.2236,
653
+ "step": 92
654
+ },
655
+ {
656
+ "epoch": 0.41287458379578246,
657
+ "grad_norm": 1.7549680471420288,
658
+ "learning_rate": 1.325416752006351e-05,
659
+ "loss": 1.1421,
660
+ "step": 93
661
+ },
662
+ {
663
+ "epoch": 0.41731409544950054,
664
+ "grad_norm": 1.8363287448883057,
665
+ "learning_rate": 1.311756837497499e-05,
666
+ "loss": 1.1325,
667
+ "step": 94
668
+ },
669
+ {
670
+ "epoch": 0.42175360710321863,
671
+ "grad_norm": 1.942063808441162,
672
+ "learning_rate": 1.2980321796293838e-05,
673
+ "loss": 1.1475,
674
+ "step": 95
675
+ },
676
+ {
677
+ "epoch": 0.4261931187569367,
678
+ "grad_norm": 2.029550790786743,
679
+ "learning_rate": 1.284245628637665e-05,
680
+ "loss": 1.1715,
681
+ "step": 96
682
+ },
683
+ {
684
+ "epoch": 0.4306326304106548,
685
+ "grad_norm": 2.0929226875305176,
686
+ "learning_rate": 1.2704000476115079e-05,
687
+ "loss": 1.1595,
688
+ "step": 97
689
+ },
690
+ {
691
+ "epoch": 0.43507214206437295,
692
+ "grad_norm": 2.0529980659484863,
693
+ "learning_rate": 1.256498311899001e-05,
694
+ "loss": 1.193,
695
+ "step": 98
696
+ },
697
+ {
698
+ "epoch": 0.43951165371809103,
699
+ "grad_norm": 1.9034109115600586,
700
+ "learning_rate": 1.2425433085100224e-05,
701
+ "loss": 1.1566,
702
+ "step": 99
703
+ },
704
+ {
705
+ "epoch": 0.4439511653718091,
706
+ "grad_norm": 2.2665998935699463,
707
+ "learning_rate": 1.2285379355166893e-05,
708
+ "loss": 1.1709,
709
+ "step": 100
710
+ },
711
+ {
712
+ "epoch": 0.4483906770255272,
713
+ "grad_norm": 2.0044686794281006,
714
+ "learning_rate": 1.2144851014515055e-05,
715
+ "loss": 1.1688,
716
+ "step": 101
717
+ },
718
+ {
719
+ "epoch": 0.4528301886792453,
720
+ "grad_norm": 1.9301621913909912,
721
+ "learning_rate": 1.2003877247033411e-05,
722
+ "loss": 1.1855,
723
+ "step": 102
724
+ },
725
+ {
726
+ "epoch": 0.4572697003329634,
727
+ "grad_norm": 1.996848464012146,
728
+ "learning_rate": 1.1862487329113606e-05,
729
+ "loss": 1.1603,
730
+ "step": 103
731
+ },
732
+ {
733
+ "epoch": 0.46170921198668147,
734
+ "grad_norm": 2.0279271602630615,
735
+ "learning_rate": 1.172071062357035e-05,
736
+ "loss": 1.1789,
737
+ "step": 104
738
+ },
739
+ {
740
+ "epoch": 0.46614872364039955,
741
+ "grad_norm": 1.9275884628295898,
742
+ "learning_rate": 1.1578576573543541e-05,
743
+ "loss": 1.1339,
744
+ "step": 105
745
+ },
746
+ {
747
+ "epoch": 0.47058823529411764,
748
+ "grad_norm": 1.9847296476364136,
749
+ "learning_rate": 1.1436114696383749e-05,
750
+ "loss": 1.186,
751
+ "step": 106
752
+ },
753
+ {
754
+ "epoch": 0.4750277469478357,
755
+ "grad_norm": 1.9284783601760864,
756
+ "learning_rate": 1.1293354577522264e-05,
757
+ "loss": 1.1697,
758
+ "step": 107
759
+ },
760
+ {
761
+ "epoch": 0.4794672586015538,
762
+ "grad_norm": 1.8462920188903809,
763
+ "learning_rate": 1.1150325864327003e-05,
764
+ "loss": 1.2233,
765
+ "step": 108
766
+ },
767
+ {
768
+ "epoch": 0.4839067702552719,
769
+ "grad_norm": 1.9206749200820923,
770
+ "learning_rate": 1.1007058259945584e-05,
771
+ "loss": 1.2148,
772
+ "step": 109
773
+ },
774
+ {
775
+ "epoch": 0.48834628190899,
776
+ "grad_norm": 1.9734727144241333,
777
+ "learning_rate": 1.0863581517136776e-05,
778
+ "loss": 1.1367,
779
+ "step": 110
780
+ },
781
+ {
782
+ "epoch": 0.49278579356270813,
783
+ "grad_norm": 1.83944833278656,
784
+ "learning_rate": 1.0719925432091671e-05,
785
+ "loss": 1.1834,
786
+ "step": 111
787
+ },
788
+ {
789
+ "epoch": 0.4972253052164262,
790
+ "grad_norm": 1.9524726867675781,
791
+ "learning_rate": 1.0576119838245843e-05,
792
+ "loss": 1.1046,
793
+ "step": 112
794
+ },
795
+ {
796
+ "epoch": 0.5016648168701443,
797
+ "grad_norm": 1.8533103466033936,
798
+ "learning_rate": 1.043219460008374e-05,
799
+ "loss": 1.1694,
800
+ "step": 113
801
+ },
802
+ {
803
+ "epoch": 0.5061043285238623,
804
+ "grad_norm": 2.0331192016601562,
805
+ "learning_rate": 1.0288179606936666e-05,
806
+ "loss": 1.2525,
807
+ "step": 114
808
+ },
809
+ {
810
+ "epoch": 0.5105438401775805,
811
+ "grad_norm": 1.7501027584075928,
812
+ "learning_rate": 1.0144104766775574e-05,
813
+ "loss": 1.1787,
814
+ "step": 115
815
+ },
816
+ {
817
+ "epoch": 0.5149833518312985,
818
+ "grad_norm": 1.8049185276031494,
819
+ "learning_rate": 1e-05,
820
+ "loss": 1.1388,
821
+ "step": 116
822
+ },
823
+ {
824
+ "epoch": 0.5194228634850167,
825
+ "grad_norm": 1.9093164205551147,
826
+ "learning_rate": 9.855895233224431e-06,
827
+ "loss": 1.1042,
828
+ "step": 117
829
+ },
830
+ {
831
+ "epoch": 0.5238623751387348,
832
+ "grad_norm": 1.7633061408996582,
833
+ "learning_rate": 9.711820393063337e-06,
834
+ "loss": 1.1286,
835
+ "step": 118
836
+ },
837
+ {
838
+ "epoch": 0.5283018867924528,
839
+ "grad_norm": 1.8089503049850464,
840
+ "learning_rate": 9.56780539991626e-06,
841
+ "loss": 1.1385,
842
+ "step": 119
843
+ },
844
+ {
845
+ "epoch": 0.532741398446171,
846
+ "grad_norm": 1.827928066253662,
847
+ "learning_rate": 9.423880161754158e-06,
848
+ "loss": 1.1864,
849
+ "step": 120
850
+ },
851
+ {
852
+ "epoch": 0.537180910099889,
853
+ "grad_norm": 1.9098917245864868,
854
+ "learning_rate": 9.28007456790833e-06,
855
+ "loss": 1.1412,
856
+ "step": 121
857
+ },
858
+ {
859
+ "epoch": 0.5416204217536071,
860
+ "grad_norm": 1.7700555324554443,
861
+ "learning_rate": 9.13641848286323e-06,
862
+ "loss": 1.1733,
863
+ "step": 122
864
+ },
865
+ {
866
+ "epoch": 0.5460599334073252,
867
+ "grad_norm": 1.829474687576294,
868
+ "learning_rate": 8.992941740054418e-06,
869
+ "loss": 1.1297,
870
+ "step": 123
871
+ },
872
+ {
873
+ "epoch": 0.5504994450610433,
874
+ "grad_norm": 1.9246844053268433,
875
+ "learning_rate": 8.849674135672999e-06,
876
+ "loss": 1.2096,
877
+ "step": 124
878
+ },
879
+ {
880
+ "epoch": 0.5549389567147613,
881
+ "grad_norm": 1.9404821395874023,
882
+ "learning_rate": 8.706645422477739e-06,
883
+ "loss": 1.1531,
884
+ "step": 125
885
+ },
886
+ {
887
+ "epoch": 0.5593784683684795,
888
+ "grad_norm": 1.8768739700317383,
889
+ "learning_rate": 8.563885303616253e-06,
890
+ "loss": 1.1896,
891
+ "step": 126
892
+ },
893
+ {
894
+ "epoch": 0.5638179800221975,
895
+ "grad_norm": 1.9277173280715942,
896
+ "learning_rate": 8.42142342645646e-06,
897
+ "loss": 1.112,
898
+ "step": 127
899
+ },
900
+ {
901
+ "epoch": 0.5682574916759157,
902
+ "grad_norm": 1.9244784116744995,
903
+ "learning_rate": 8.279289376429653e-06,
904
+ "loss": 1.1457,
905
+ "step": 128
906
+ },
907
+ {
908
+ "epoch": 0.5726970033296337,
909
+ "grad_norm": 1.856616497039795,
910
+ "learning_rate": 8.137512670886397e-06,
911
+ "loss": 1.139,
912
+ "step": 129
913
+ },
914
+ {
915
+ "epoch": 0.5771365149833518,
916
+ "grad_norm": 1.7110472917556763,
917
+ "learning_rate": 7.996122752966596e-06,
918
+ "loss": 1.1181,
919
+ "step": 130
920
+ },
921
+ {
922
+ "epoch": 0.58157602663707,
923
+ "grad_norm": 1.7752193212509155,
924
+ "learning_rate": 7.855148985484946e-06,
925
+ "loss": 1.1517,
926
+ "step": 131
927
+ },
928
+ {
929
+ "epoch": 0.586015538290788,
930
+ "grad_norm": 1.789296269416809,
931
+ "learning_rate": 7.71462064483311e-06,
932
+ "loss": 1.0982,
933
+ "step": 132
934
+ },
935
+ {
936
+ "epoch": 0.5904550499445061,
937
+ "grad_norm": 2.0241036415100098,
938
+ "learning_rate": 7.574566914899779e-06,
939
+ "loss": 1.1787,
940
+ "step": 133
941
+ },
942
+ {
943
+ "epoch": 0.5948945615982242,
944
+ "grad_norm": 2.217411518096924,
945
+ "learning_rate": 7.4350168810099955e-06,
946
+ "loss": 1.1871,
947
+ "step": 134
948
+ },
949
+ {
950
+ "epoch": 0.5993340732519423,
951
+ "grad_norm": 1.8291338682174683,
952
+ "learning_rate": 7.295999523884921e-06,
953
+ "loss": 1.1396,
954
+ "step": 135
955
+ },
956
+ {
957
+ "epoch": 0.6037735849056604,
958
+ "grad_norm": 1.818039059638977,
959
+ "learning_rate": 7.157543713623353e-06,
960
+ "loss": 1.1719,
961
+ "step": 136
962
+ },
963
+ {
964
+ "epoch": 0.6082130965593785,
965
+ "grad_norm": 1.8456182479858398,
966
+ "learning_rate": 7.019678203706164e-06,
967
+ "loss": 1.1714,
968
+ "step": 137
969
+ },
970
+ {
971
+ "epoch": 0.6126526082130965,
972
+ "grad_norm": 1.9036660194396973,
973
+ "learning_rate": 6.882431625025016e-06,
974
+ "loss": 1.1439,
975
+ "step": 138
976
+ },
977
+ {
978
+ "epoch": 0.6170921198668147,
979
+ "grad_norm": 1.7687510251998901,
980
+ "learning_rate": 6.745832479936492e-06,
981
+ "loss": 1.1511,
982
+ "step": 139
983
+ },
984
+ {
985
+ "epoch": 0.6215316315205327,
986
+ "grad_norm": 1.9004747867584229,
987
+ "learning_rate": 6.609909136342956e-06,
988
+ "loss": 1.172,
989
+ "step": 140
990
+ },
991
+ {
992
+ "epoch": 0.6259711431742508,
993
+ "grad_norm": 1.736116886138916,
994
+ "learning_rate": 6.474689821801295e-06,
995
+ "loss": 1.1422,
996
+ "step": 141
997
+ },
998
+ {
999
+ "epoch": 0.6304106548279689,
1000
+ "grad_norm": 2.1278252601623535,
1001
+ "learning_rate": 6.340202617660842e-06,
1002
+ "loss": 1.1553,
1003
+ "step": 142
1004
+ },
1005
+ {
1006
+ "epoch": 0.634850166481687,
1007
+ "grad_norm": 1.7536156177520752,
1008
+ "learning_rate": 6.206475453231644e-06,
1009
+ "loss": 1.2252,
1010
+ "step": 143
1011
+ },
1012
+ {
1013
+ "epoch": 0.6392896781354052,
1014
+ "grad_norm": 1.6779848337173462,
1015
+ "learning_rate": 6.073536099984314e-06,
1016
+ "loss": 1.193,
1017
+ "step": 144
1018
+ },
1019
+ {
1020
+ "epoch": 0.6437291897891232,
1021
+ "grad_norm": 1.8742091655731201,
1022
+ "learning_rate": 5.941412165782645e-06,
1023
+ "loss": 1.1921,
1024
+ "step": 145
1025
+ },
1026
+ {
1027
+ "epoch": 0.6481687014428413,
1028
+ "grad_norm": 1.8728663921356201,
1029
+ "learning_rate": 5.810131089150228e-06,
1030
+ "loss": 1.1906,
1031
+ "step": 146
1032
+ },
1033
+ {
1034
+ "epoch": 0.6526082130965594,
1035
+ "grad_norm": 1.6480120420455933,
1036
+ "learning_rate": 5.6797201335722064e-06,
1037
+ "loss": 1.1297,
1038
+ "step": 147
1039
+ },
1040
+ {
1041
+ "epoch": 0.6570477247502775,
1042
+ "grad_norm": 1.6961437463760376,
1043
+ "learning_rate": 5.550206381833409e-06,
1044
+ "loss": 1.213,
1045
+ "step": 148
1046
+ },
1047
+ {
1048
+ "epoch": 0.6614872364039955,
1049
+ "grad_norm": 1.7690813541412354,
1050
+ "learning_rate": 5.421616730394e-06,
1051
+ "loss": 1.1643,
1052
+ "step": 149
1053
+ },
1054
+ {
1055
+ "epoch": 0.6659267480577137,
1056
+ "grad_norm": 1.621023178100586,
1057
+ "learning_rate": 5.293977883803797e-06,
1058
+ "loss": 1.1866,
1059
+ "step": 150
1060
+ },
1061
+ {
1062
+ "epoch": 0.6703662597114317,
1063
+ "grad_norm": 1.6755465269088745,
1064
+ "learning_rate": 5.167316349156495e-06,
1065
+ "loss": 1.1487,
1066
+ "step": 151
1067
+ },
1068
+ {
1069
+ "epoch": 0.6748057713651499,
1070
+ "grad_norm": 1.739989995956421,
1071
+ "learning_rate": 5.041658430584852e-06,
1072
+ "loss": 1.148,
1073
+ "step": 152
1074
+ },
1075
+ {
1076
+ "epoch": 0.6792452830188679,
1077
+ "grad_norm": 1.6027244329452515,
1078
+ "learning_rate": 4.917030223798057e-06,
1079
+ "loss": 1.1462,
1080
+ "step": 153
1081
+ },
1082
+ {
1083
+ "epoch": 0.683684794672586,
1084
+ "grad_norm": 1.7501620054244995,
1085
+ "learning_rate": 4.793457610662334e-06,
1086
+ "loss": 1.1887,
1087
+ "step": 154
1088
+ },
1089
+ {
1090
+ "epoch": 0.6881243063263041,
1091
+ "grad_norm": 1.8939120769500732,
1092
+ "learning_rate": 4.670966253826027e-06,
1093
+ "loss": 1.0909,
1094
+ "step": 155
1095
+ },
1096
+ {
1097
+ "epoch": 0.6925638179800222,
1098
+ "grad_norm": 1.7964297533035278,
1099
+ "learning_rate": 4.549581591390142e-06,
1100
+ "loss": 1.1357,
1101
+ "step": 156
1102
+ },
1103
+ {
1104
+ "epoch": 0.6970033296337403,
1105
+ "grad_norm": 1.8703395128250122,
1106
+ "learning_rate": 4.429328831625565e-06,
1107
+ "loss": 1.1529,
1108
+ "step": 157
1109
+ },
1110
+ {
1111
+ "epoch": 0.7014428412874584,
1112
+ "grad_norm": 1.676789402961731,
1113
+ "learning_rate": 4.310232947737979e-06,
1114
+ "loss": 1.1435,
1115
+ "step": 158
1116
+ },
1117
+ {
1118
+ "epoch": 0.7058823529411765,
1119
+ "grad_norm": 1.8037596940994263,
1120
+ "learning_rate": 4.192318672681631e-06,
1121
+ "loss": 1.1878,
1122
+ "step": 159
1123
+ },
1124
+ {
1125
+ "epoch": 0.7103218645948945,
1126
+ "grad_norm": 1.6602219343185425,
1127
+ "learning_rate": 4.0756104940229645e-06,
1128
+ "loss": 1.1887,
1129
+ "step": 160
1130
+ },
1131
+ {
1132
+ "epoch": 0.7147613762486127,
1133
+ "grad_norm": 1.8436843156814575,
1134
+ "learning_rate": 3.960132648855226e-06,
1135
+ "loss": 1.1406,
1136
+ "step": 161
1137
+ },
1138
+ {
1139
+ "epoch": 0.7192008879023307,
1140
+ "grad_norm": 1.7904314994812012,
1141
+ "learning_rate": 3.845909118765073e-06,
1142
+ "loss": 1.149,
1143
+ "step": 162
1144
+ },
1145
+ {
1146
+ "epoch": 0.7236403995560489,
1147
+ "grad_norm": 1.7600526809692383,
1148
+ "learning_rate": 3.732963624852275e-06,
1149
+ "loss": 1.136,
1150
+ "step": 163
1151
+ },
1152
+ {
1153
+ "epoch": 0.7280799112097669,
1154
+ "grad_norm": 1.912719488143921,
1155
+ "learning_rate": 3.6213196228034796e-06,
1156
+ "loss": 1.1052,
1157
+ "step": 164
1158
+ },
1159
+ {
1160
+ "epoch": 0.732519422863485,
1161
+ "grad_norm": 1.8316577672958374,
1162
+ "learning_rate": 3.511000298021098e-06,
1163
+ "loss": 1.115,
1164
+ "step": 165
1165
+ },
1166
+ {
1167
+ "epoch": 0.7369589345172031,
1168
+ "grad_norm": 1.9175002574920654,
1169
+ "learning_rate": 3.402028560808357e-06,
1170
+ "loss": 1.1997,
1171
+ "step": 166
1172
+ },
1173
+ {
1174
+ "epoch": 0.7413984461709212,
1175
+ "grad_norm": 1.7501415014266968,
1176
+ "learning_rate": 3.2944270416114256e-06,
1177
+ "loss": 1.1601,
1178
+ "step": 167
1179
+ },
1180
+ {
1181
+ "epoch": 0.7458379578246392,
1182
+ "grad_norm": 1.8293687105178833,
1183
+ "learning_rate": 3.1882180863197308e-06,
1184
+ "loss": 1.131,
1185
+ "step": 168
1186
+ },
1187
+ {
1188
+ "epoch": 0.7502774694783574,
1189
+ "grad_norm": 1.7824769020080566,
1190
+ "learning_rate": 3.0834237516252817e-06,
1191
+ "loss": 1.1655,
1192
+ "step": 169
1193
+ },
1194
+ {
1195
+ "epoch": 0.7547169811320755,
1196
+ "grad_norm": 1.672102689743042,
1197
+ "learning_rate": 2.980065800442137e-06,
1198
+ "loss": 1.1496,
1199
+ "step": 170
1200
+ },
1201
+ {
1202
+ "epoch": 0.7591564927857936,
1203
+ "grad_norm": 1.8063626289367676,
1204
+ "learning_rate": 2.878165697386812e-06,
1205
+ "loss": 1.1314,
1206
+ "step": 171
1207
+ },
1208
+ {
1209
+ "epoch": 0.7635960044395117,
1210
+ "grad_norm": 1.9365928173065186,
1211
+ "learning_rate": 2.777744604320706e-06,
1212
+ "loss": 1.2001,
1213
+ "step": 172
1214
+ },
1215
+ {
1216
+ "epoch": 0.7680355160932297,
1217
+ "grad_norm": 2.0963966846466064,
1218
+ "learning_rate": 2.678823375955314e-06,
1219
+ "loss": 1.1451,
1220
+ "step": 173
1221
+ },
1222
+ {
1223
+ "epoch": 0.7724750277469479,
1224
+ "grad_norm": 1.6925102472305298,
1225
+ "learning_rate": 2.581422555521316e-06,
1226
+ "loss": 1.1666,
1227
+ "step": 174
1228
+ },
1229
+ {
1230
+ "epoch": 0.7769145394006659,
1231
+ "grad_norm": 1.7280200719833374,
1232
+ "learning_rate": 2.485562370502279e-06,
1233
+ "loss": 1.1394,
1234
+ "step": 175
1235
+ },
1236
+ {
1237
+ "epoch": 0.781354051054384,
1238
+ "grad_norm": 2.9482946395874023,
1239
+ "learning_rate": 2.391262728433995e-06,
1240
+ "loss": 1.1453,
1241
+ "step": 176
1242
+ },
1243
+ {
1244
+ "epoch": 0.7857935627081021,
1245
+ "grad_norm": 1.7591135501861572,
1246
+ "learning_rate": 2.2985432127701945e-06,
1247
+ "loss": 1.1422,
1248
+ "step": 177
1249
+ },
1250
+ {
1251
+ "epoch": 0.7902330743618202,
1252
+ "grad_norm": 1.9076871871948242,
1253
+ "learning_rate": 2.2074230788156325e-06,
1254
+ "loss": 1.133,
1255
+ "step": 178
1256
+ },
1257
+ {
1258
+ "epoch": 0.7946725860155383,
1259
+ "grad_norm": 1.7988766431808472,
1260
+ "learning_rate": 2.1179212497272582e-06,
1261
+ "loss": 1.1535,
1262
+ "step": 179
1263
+ },
1264
+ {
1265
+ "epoch": 0.7991120976692564,
1266
+ "grad_norm": 1.9537118673324585,
1267
+ "learning_rate": 2.030056312584424e-06,
1268
+ "loss": 1.1871,
1269
+ "step": 180
1270
+ },
1271
+ {
1272
+ "epoch": 0.8035516093229744,
1273
+ "grad_norm": 1.6785671710968018,
1274
+ "learning_rate": 1.9438465145288377e-06,
1275
+ "loss": 1.0986,
1276
+ "step": 181
1277
+ },
1278
+ {
1279
+ "epoch": 0.8079911209766926,
1280
+ "grad_norm": 1.8023606538772583,
1281
+ "learning_rate": 1.8593097589751318e-06,
1282
+ "loss": 1.118,
1283
+ "step": 182
1284
+ },
1285
+ {
1286
+ "epoch": 0.8124306326304107,
1287
+ "grad_norm": 1.6982240676879883,
1288
+ "learning_rate": 1.7764636018928249e-06,
1289
+ "loss": 1.1521,
1290
+ "step": 183
1291
+ },
1292
+ {
1293
+ "epoch": 0.8168701442841287,
1294
+ "grad_norm": 1.7196639776229858,
1295
+ "learning_rate": 1.6953252481604198e-06,
1296
+ "loss": 1.1243,
1297
+ "step": 184
1298
+ },
1299
+ {
1300
+ "epoch": 0.8213096559378469,
1301
+ "grad_norm": 1.6617742776870728,
1302
+ "learning_rate": 1.6159115479924259e-06,
1303
+ "loss": 1.1496,
1304
+ "step": 185
1305
+ },
1306
+ {
1307
+ "epoch": 0.8257491675915649,
1308
+ "grad_norm": 1.8764078617095947,
1309
+ "learning_rate": 1.5382389934400199e-06,
1310
+ "loss": 1.1417,
1311
+ "step": 186
1312
+ },
1313
+ {
1314
+ "epoch": 0.8301886792452831,
1315
+ "grad_norm": 1.743654489517212,
1316
+ "learning_rate": 1.462323714966114e-06,
1317
+ "loss": 1.1322,
1318
+ "step": 187
1319
+ },
1320
+ {
1321
+ "epoch": 0.8346281908990011,
1322
+ "grad_norm": 1.691676139831543,
1323
+ "learning_rate": 1.3881814780954916e-06,
1324
+ "loss": 1.104,
1325
+ "step": 188
1326
+ },
1327
+ {
1328
+ "epoch": 0.8390677025527192,
1329
+ "grad_norm": 1.6910086870193481,
1330
+ "learning_rate": 1.3158276801407432e-06,
1331
+ "loss": 1.181,
1332
+ "step": 189
1333
+ },
1334
+ {
1335
+ "epoch": 0.8435072142064373,
1336
+ "grad_norm": 1.7811787128448486,
1337
+ "learning_rate": 1.2452773470046543e-06,
1338
+ "loss": 1.2015,
1339
+ "step": 190
1340
+ },
1341
+ {
1342
+ "epoch": 0.8479467258601554,
1343
+ "grad_norm": 1.8758302927017212,
1344
+ "learning_rate": 1.1765451300597574e-06,
1345
+ "loss": 1.1697,
1346
+ "step": 191
1347
+ },
1348
+ {
1349
+ "epoch": 0.8523862375138734,
1350
+ "grad_norm": 1.7708605527877808,
1351
+ "learning_rate": 1.1096453031056265e-06,
1352
+ "loss": 1.1007,
1353
+ "step": 192
1354
+ },
1355
+ {
1356
+ "epoch": 0.8568257491675916,
1357
+ "grad_norm": 1.7193588018417358,
1358
+ "learning_rate": 1.0445917594046073e-06,
1359
+ "loss": 1.1135,
1360
+ "step": 193
1361
+ },
1362
+ {
1363
+ "epoch": 0.8612652608213096,
1364
+ "grad_norm": 1.6113449335098267,
1365
+ "learning_rate": 9.813980087965625e-07,
1366
+ "loss": 1.1501,
1367
+ "step": 194
1368
+ },
1369
+ {
1370
+ "epoch": 0.8657047724750278,
1371
+ "grad_norm": 1.726749062538147,
1372
+ "learning_rate": 9.200771748932513e-07,
1373
+ "loss": 1.0861,
1374
+ "step": 195
1375
+ },
1376
+ {
1377
+ "epoch": 0.8701442841287459,
1378
+ "grad_norm": 1.7274186611175537,
1379
+ "learning_rate": 8.606419923529175e-07,
1380
+ "loss": 1.1256,
1381
+ "step": 196
1382
+ },
1383
+ {
1384
+ "epoch": 0.8745837957824639,
1385
+ "grad_norm": 1.7909616231918335,
1386
+ "learning_rate": 8.031048042356393e-07,
1387
+ "loss": 1.1844,
1388
+ "step": 197
1389
+ },
1390
+ {
1391
+ "epoch": 0.8790233074361821,
1392
+ "grad_norm": 1.769081473350525,
1393
+ "learning_rate": 7.474775594400252e-07,
1394
+ "loss": 1.1142,
1395
+ "step": 198
1396
+ },
1397
+ {
1398
+ "epoch": 0.8834628190899001,
1399
+ "grad_norm": 1.5884616374969482,
1400
+ "learning_rate": 6.937718102217461e-07,
1401
+ "loss": 1.1735,
1402
+ "step": 199
1403
+ },
1404
+ {
1405
+ "epoch": 0.8879023307436182,
1406
+ "grad_norm": 1.8353629112243652,
1407
+ "learning_rate": 6.41998709794458e-07,
1408
+ "loss": 1.1656,
1409
+ "step": 200
1410
+ },
1411
+ {
1412
+ "epoch": 0.8923418423973363,
1413
+ "grad_norm": 1.836683988571167,
1414
+ "learning_rate": 5.921690100135713e-07,
1415
+ "loss": 1.1665,
1416
+ "step": 201
1417
+ },
1418
+ {
1419
+ "epoch": 0.8967813540510544,
1420
+ "grad_norm": 1.7683050632476807,
1421
+ "learning_rate": 5.442930591433992e-07,
1422
+ "loss": 1.0818,
1423
+ "step": 202
1424
+ },
1425
+ {
1426
+ "epoch": 0.9012208657047724,
1427
+ "grad_norm": 1.7694001197814941,
1428
+ "learning_rate": 4.983807997080925e-07,
1429
+ "loss": 1.1625,
1430
+ "step": 203
1431
+ },
1432
+ {
1433
+ "epoch": 0.9056603773584906,
1434
+ "grad_norm": 1.639148473739624,
1435
+ "learning_rate": 4.544417664268652e-07,
1436
+ "loss": 1.1001,
1437
+ "step": 204
1438
+ },
1439
+ {
1440
+ "epoch": 0.9100998890122086,
1441
+ "grad_norm": 1.682405710220337,
1442
+ "learning_rate": 4.124850842338779e-07,
1443
+ "loss": 1.1392,
1444
+ "step": 205
1445
+ },
1446
+ {
1447
+ "epoch": 0.9145394006659268,
1448
+ "grad_norm": 1.705399751663208,
1449
+ "learning_rate": 3.725194663832521e-07,
1450
+ "loss": 1.1308,
1451
+ "step": 206
1452
+ },
1453
+ {
1454
+ "epoch": 0.9189789123196448,
1455
+ "grad_norm": 1.77009117603302,
1456
+ "learning_rate": 3.345532126395579e-07,
1457
+ "loss": 1.1334,
1458
+ "step": 207
1459
+ },
1460
+ {
1461
+ "epoch": 0.9234184239733629,
1462
+ "grad_norm": 1.6911001205444336,
1463
+ "learning_rate": 2.985942075541848e-07,
1464
+ "loss": 1.1135,
1465
+ "step": 208
1466
+ },
1467
+ {
1468
+ "epoch": 0.9278579356270811,
1469
+ "grad_norm": 1.6834074258804321,
1470
+ "learning_rate": 2.646499188279328e-07,
1471
+ "loss": 1.1604,
1472
+ "step": 209
1473
+ },
1474
+ {
1475
+ "epoch": 0.9322974472807991,
1476
+ "grad_norm": 1.6770280599594116,
1477
+ "learning_rate": 2.3272739576017945e-07,
1478
+ "loss": 1.1296,
1479
+ "step": 210
1480
+ },
1481
+ {
1482
+ "epoch": 0.9367369589345172,
1483
+ "grad_norm": 1.8066668510437012,
1484
+ "learning_rate": 2.028332677849254e-07,
1485
+ "loss": 1.1261,
1486
+ "step": 211
1487
+ },
1488
+ {
1489
+ "epoch": 0.9411764705882353,
1490
+ "grad_norm": 1.8163933753967285,
1491
+ "learning_rate": 1.7497374309405346e-07,
1492
+ "loss": 1.174,
1493
+ "step": 212
1494
+ },
1495
+ {
1496
+ "epoch": 0.9456159822419534,
1497
+ "grad_norm": 1.6583095788955688,
1498
+ "learning_rate": 1.49154607348051e-07,
1499
+ "loss": 1.1626,
1500
+ "step": 213
1501
+ },
1502
+ {
1503
+ "epoch": 0.9500554938956715,
1504
+ "grad_norm": 1.7477093935012817,
1505
+ "learning_rate": 1.2538122247448325e-07,
1506
+ "loss": 1.1512,
1507
+ "step": 214
1508
+ },
1509
+ {
1510
+ "epoch": 0.9544950055493896,
1511
+ "grad_norm": 1.6833035945892334,
1512
+ "learning_rate": 1.0365852555447642e-07,
1513
+ "loss": 1.116,
1514
+ "step": 215
1515
+ },
1516
+ {
1517
+ "epoch": 0.9589345172031076,
1518
+ "grad_norm": 1.6046544313430786,
1519
+ "learning_rate": 8.39910277974132e-08,
1520
+ "loss": 1.1263,
1521
+ "step": 216
1522
+ },
1523
+ {
1524
+ "epoch": 0.9633740288568258,
1525
+ "grad_norm": 1.6821755170822144,
1526
+ "learning_rate": 6.638281360408339e-08,
1527
+ "loss": 1.1357,
1528
+ "step": 217
1529
+ },
1530
+ {
1531
+ "epoch": 0.9678135405105438,
1532
+ "grad_norm": 1.7433803081512451,
1533
+ "learning_rate": 5.083753971846239e-08,
1534
+ "loss": 1.0744,
1535
+ "step": 218
1536
+ },
1537
+ {
1538
+ "epoch": 0.9722530521642619,
1539
+ "grad_norm": 1.7408146858215332,
1540
+ "learning_rate": 3.735843446830867e-08,
1541
+ "loss": 1.1356,
1542
+ "step": 219
1543
+ },
1544
+ {
1545
+ "epoch": 0.97669256381798,
1546
+ "grad_norm": 1.7871052026748657,
1547
+ "learning_rate": 2.5948297094724463e-08,
1548
+ "loss": 1.1227,
1549
+ "step": 220
1550
+ },
1551
+ {
1552
+ "epoch": 0.9811320754716981,
1553
+ "grad_norm": 1.5904314517974854,
1554
+ "learning_rate": 1.6609497170834154e-08,
1555
+ "loss": 1.0993,
1556
+ "step": 221
1557
+ },
1558
+ {
1559
+ "epoch": 0.9855715871254163,
1560
+ "grad_norm": 1.8538672924041748,
1561
+ "learning_rate": 9.343974109685684e-09,
1562
+ "loss": 1.1632,
1563
+ "step": 222
1564
+ },
1565
+ {
1566
+ "epoch": 0.9900110987791343,
1567
+ "grad_norm": 1.6794443130493164,
1568
+ "learning_rate": 4.153236761488266e-09,
1569
+ "loss": 1.0994,
1570
+ "step": 223
1571
+ },
1572
+ {
1573
+ "epoch": 0.9944506104328524,
1574
+ "grad_norm": 1.6343417167663574,
1575
+ "learning_rate": 1.0383631002686133e-09,
1576
+ "loss": 1.1072,
1577
+ "step": 224
1578
+ },
1579
+ {
1580
+ "epoch": 0.9988901220865705,
1581
+ "grad_norm": 1.9944053888320923,
1582
+ "learning_rate": 0.0,
1583
+ "loss": 1.1393,
1584
+ "step": 225
1585
+ },
1586
+ {
1587
+ "epoch": 0.9988901220865705,
1588
+ "step": 225,
1589
+ "total_flos": 8.515440547840655e+17,
1590
+ "train_loss": 1.1814873923195732,
1591
+ "train_runtime": 2241.1241,
1592
+ "train_samples_per_second": 25.717,
1593
+ "train_steps_per_second": 0.1
1594
+ }
1595
+ ],
1596
+ "logging_steps": 1.0,
1597
+ "max_steps": 225,
1598
+ "num_input_tokens_seen": 0,
1599
+ "num_train_epochs": 1,
1600
+ "save_steps": 400,
1601
+ "stateful_callbacks": {
1602
+ "TrainerControl": {
1603
+ "args": {
1604
+ "should_epoch_stop": false,
1605
+ "should_evaluate": false,
1606
+ "should_log": false,
1607
+ "should_save": true,
1608
+ "should_training_stop": true
1609
+ },
1610
+ "attributes": {}
1611
+ }
1612
+ },
1613
+ "total_flos": 8.515440547840655e+17,
1614
+ "train_batch_size": 4,
1615
+ "trial_name": null,
1616
+ "trial_params": null
1617
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e8f565eb8115e9a1539252be070aa144f81bbb7c17707a814365de8932b70edb
3
+ size 6968
training_loss.png ADDED