Word2Li commited on
Commit
89cdb6f
·
verified ·
1 Parent(s): 946bb1d

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 +1,155 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: transformers
3
+ license: llama3.1
4
+ base_model: meta-llama/Llama-3.1-8B
5
+ language: en
6
+ datasets:
7
+ - Word2Li/MiddOptimized
8
+ tags:
9
+ - llama-factory
10
+ - full
11
+ pipeline_tag: text-generation
12
+ model-index:
13
+ - name: Llama3.1-8B-Middo-Wizard
14
+ results:
15
+ - task:
16
+ type: text-generation
17
+ dataset:
18
+ name: MMLU
19
+ type: MMLU
20
+ metrics:
21
+ - name: Weighted Avg.
22
+ type: Weighted Avg.
23
+ value: 48.39
24
+ verified: true
25
+ - task:
26
+ type: text-generation
27
+ dataset:
28
+ name: IFEval
29
+ type: IFEval
30
+ metrics:
31
+ - name: Avg.
32
+ type: Avg.
33
+ value: 50.11
34
+ verified: true
35
+ - task:
36
+ type: text-generation
37
+ dataset:
38
+ name: GSM8K
39
+ type: GSM8K
40
+ metrics:
41
+ - name: pass@1
42
+ type: pass@1
43
+ value: 54.44
44
+ verified: true
45
+ - task:
46
+ type: text-generation
47
+ dataset:
48
+ name: MATH
49
+ type: MATH
50
+ metrics:
51
+ - name: pass@1
52
+ type: pass@1
53
+ value: 13.80
54
+ verified: true
55
+ - task:
56
+ type: text-generation
57
+ dataset:
58
+ name: HumanEval
59
+ type: HumanEval
60
+ metrics:
61
+ - name: pass@1
62
+ type: pass@1
63
+ value: 46.95
64
+ verified: true
65
+ - task:
66
+ type: text-generation
67
+ dataset:
68
+ name: MBPP
69
+ type: MBPP
70
+ metrics:
71
+ - name: pass@1
72
+ type: pass@1
73
+ value: 45.00
74
+ verified: true
75
+ - task:
76
+ type: text-generation
77
+ dataset:
78
+ name: Hellaswag
79
+ type: Hellaswag
80
+ metrics:
81
+ - name: pass@1
82
+ type: pass@1
83
+ value: 63.54
84
+ verified: true
85
+ - task:
86
+ type: text-generation
87
+ dataset:
88
+ name: GPQA
89
+ type: GPQA
90
+ metrics:
91
+ - name: pass@1
92
+ type: pass@1
93
+ value: 20.20
94
+ verified: true
95
+ metrics:
96
+ - accuracy
97
+ ---
98
+
99
+ # Llama3.1-8B-Middo-Wizard
100
+
101
+ Paper: [Middo: Model-Informed Dynamic Data Optimization for Enhanced LLM Fine-Tuning via Closed-Loop Learning](https://arxiv.org/abs/2508.21589)
102
+
103
+ Code: https://github.com/Word2VecT/Middo
104
+
105
+ ## Model description
106
+
107
+ 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_wizard](https://huggingface.co/datasets/Word2Li/MiddOptimized/viewer/default/llama_alpaca) dataset.
108
+
109
+ ## Training and evaluation data
110
+
111
+ ### Training data
112
+
113
+ Middo optimized [WizardLM_evol_instruct_70k](https://huggingface.co/datasets/tatsu-lab/alpaca) on [meta-llama/Llama-3.1-8B](https://huggingface.co/meta-llama/Llama-3.1-8B).
114
+
115
+ ### Evaluation data
116
+
117
+ - General
118
+ - MMLU
119
+ - IFEval
120
+ - Math
121
+ - GSM8K
122
+ - MATH
123
+ - Code
124
+ - HumanEval
125
+ - MBPP
126
+ - Reasoning
127
+ - Hellaswag
128
+ - GPQA
129
+
130
+ ## Training procedure
131
+
132
+ ### Training hyperparameters
133
+
134
+ The following hyperparameters were used during training:
135
+
136
+ - learning_rate: 2e-05
137
+ - train_batch_size: 4
138
+ - eval_batch_size: 8
139
+ - seed: 42
140
+ - distributed_type: multi-GPU
141
+ - num_devices: 8
142
+ - gradient_accumulation_steps: 8
143
+ - total_train_batch_size: 256
144
+ - total_eval_batch_size: 64
145
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
146
+ - lr_scheduler_type: cosine
147
+ - lr_scheduler_warmup_ratio: 0.03
148
+ - num_epochs: 1.0
149
+
150
+ ### Framework versions
151
+
152
+ - Transformers 4.45.2
153
+ - Pytorch 2.5.1+cu121
154
+ - Datasets 2.21.0
155
+ - Tokenizers 0.20.1
all_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 0.9973935708079931,
3
+ "total_flos": 2.698045158024282e+18,
4
+ "train_loss": 0.5919382667707649,
5
+ "train_runtime": 4471.5794,
6
+ "train_samples_per_second": 16.469,
7
+ "train_steps_per_second": 0.064
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:e7f04aee83dde24ac5aca360da639f64e3541c9722982129651d45fbb3c3950c
3
+ size 4976698672
model-00002-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5163f717552bd09340943a160cfbd5b0aee4c51d8c4b473abc5d37400d9989b5
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:addba9d31f789c87fbabbaea790f07196ad9986352866573ee96d5d858aa1c0a
3
+ size 4915916176
model-00004-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1408dbf459c2d12f7d898540a2bcdf2a570f512170a77ee5d82e91806844afbb
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": 0.9973935708079931,
3
+ "total_flos": 2.698045158024282e+18,
4
+ "train_loss": 0.5919382667707649,
5
+ "train_runtime": 4471.5794,
6
+ "train_samples_per_second": 16.469,
7
+ "train_steps_per_second": 0.064
8
+ }
trainer_log.jsonl ADDED
@@ -0,0 +1,288 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {"current_steps": 1, "total_steps": 287, "loss": 0.8359, "lr": 2.222222222222222e-06, "epoch": 0.0034752389226759338, "percentage": 0.35, "elapsed_time": "0:00:17", "remaining_time": "1:23:20"}
2
+ {"current_steps": 2, "total_steps": 287, "loss": 0.8862, "lr": 4.444444444444444e-06, "epoch": 0.0069504778453518675, "percentage": 0.7, "elapsed_time": "0:00:32", "remaining_time": "1:16:56"}
3
+ {"current_steps": 3, "total_steps": 287, "loss": 0.7899, "lr": 6.666666666666667e-06, "epoch": 0.010425716768027803, "percentage": 1.05, "elapsed_time": "0:00:46", "remaining_time": "1:13:57"}
4
+ {"current_steps": 4, "total_steps": 287, "loss": 0.7342, "lr": 8.888888888888888e-06, "epoch": 0.013900955690703735, "percentage": 1.39, "elapsed_time": "0:01:03", "remaining_time": "1:14:36"}
5
+ {"current_steps": 5, "total_steps": 287, "loss": 0.6759, "lr": 1.1111111111111113e-05, "epoch": 0.01737619461337967, "percentage": 1.74, "elapsed_time": "0:01:19", "remaining_time": "1:14:53"}
6
+ {"current_steps": 6, "total_steps": 287, "loss": 0.6608, "lr": 1.3333333333333333e-05, "epoch": 0.020851433536055605, "percentage": 2.09, "elapsed_time": "0:01:33", "remaining_time": "1:12:47"}
7
+ {"current_steps": 7, "total_steps": 287, "loss": 0.5929, "lr": 1.555555555555556e-05, "epoch": 0.02432667245873154, "percentage": 2.44, "elapsed_time": "0:01:47", "remaining_time": "1:11:25"}
8
+ {"current_steps": 8, "total_steps": 287, "loss": 0.6591, "lr": 1.7777777777777777e-05, "epoch": 0.02780191138140747, "percentage": 2.79, "elapsed_time": "0:02:00", "remaining_time": "1:10:04"}
9
+ {"current_steps": 9, "total_steps": 287, "loss": 0.6129, "lr": 2e-05, "epoch": 0.03127715030408341, "percentage": 3.14, "elapsed_time": "0:02:14", "remaining_time": "1:09:02"}
10
+ {"current_steps": 10, "total_steps": 287, "loss": 0.6247, "lr": 1.9999361478484043e-05, "epoch": 0.03475238922675934, "percentage": 3.48, "elapsed_time": "0:02:29", "remaining_time": "1:09:07"}
11
+ {"current_steps": 11, "total_steps": 287, "loss": 0.5985, "lr": 1.999744599547812e-05, "epoch": 0.038227628149435276, "percentage": 3.83, "elapsed_time": "0:02:44", "remaining_time": "1:08:53"}
12
+ {"current_steps": 12, "total_steps": 287, "loss": 0.6277, "lr": 1.999425379559765e-05, "epoch": 0.04170286707211121, "percentage": 4.18, "elapsed_time": "0:02:59", "remaining_time": "1:08:32"}
13
+ {"current_steps": 13, "total_steps": 287, "loss": 0.6268, "lr": 1.9989785286500294e-05, "epoch": 0.045178105994787145, "percentage": 4.53, "elapsed_time": "0:03:14", "remaining_time": "1:08:13"}
14
+ {"current_steps": 14, "total_steps": 287, "loss": 0.6465, "lr": 1.99840410388339e-05, "epoch": 0.04865334491746308, "percentage": 4.88, "elapsed_time": "0:03:28", "remaining_time": "1:07:48"}
15
+ {"current_steps": 15, "total_steps": 287, "loss": 0.6048, "lr": 1.99770217861636e-05, "epoch": 0.052128583840139006, "percentage": 5.23, "elapsed_time": "0:03:44", "remaining_time": "1:07:44"}
16
+ {"current_steps": 16, "total_steps": 287, "loss": 0.6343, "lr": 1.9968728424878178e-05, "epoch": 0.05560382276281494, "percentage": 5.57, "elapsed_time": "0:03:56", "remaining_time": "1:06:45"}
17
+ {"current_steps": 17, "total_steps": 287, "loss": 0.6308, "lr": 1.9959162014075553e-05, "epoch": 0.059079061685490875, "percentage": 5.92, "elapsed_time": "0:04:12", "remaining_time": "1:06:53"}
18
+ {"current_steps": 18, "total_steps": 287, "loss": 0.6382, "lr": 1.994832377542755e-05, "epoch": 0.06255430060816682, "percentage": 6.27, "elapsed_time": "0:04:27", "remaining_time": "1:06:36"}
19
+ {"current_steps": 19, "total_steps": 287, "loss": 0.5864, "lr": 1.9936215093023884e-05, "epoch": 0.06602953953084274, "percentage": 6.62, "elapsed_time": "0:04:43", "remaining_time": "1:06:40"}
20
+ {"current_steps": 20, "total_steps": 287, "loss": 0.6014, "lr": 1.9922837513195406e-05, "epoch": 0.06950477845351868, "percentage": 6.97, "elapsed_time": "0:04:56", "remaining_time": "1:06:00"}
21
+ {"current_steps": 21, "total_steps": 287, "loss": 0.5919, "lr": 1.990819274431662e-05, "epoch": 0.07298001737619461, "percentage": 7.32, "elapsed_time": "0:05:12", "remaining_time": "1:05:59"}
22
+ {"current_steps": 22, "total_steps": 287, "loss": 0.6285, "lr": 1.989228265658754e-05, "epoch": 0.07645525629887055, "percentage": 7.67, "elapsed_time": "0:05:26", "remaining_time": "1:05:32"}
23
+ {"current_steps": 23, "total_steps": 287, "loss": 0.6498, "lr": 1.9875109281794828e-05, "epoch": 0.07993049522154648, "percentage": 8.01, "elapsed_time": "0:05:41", "remaining_time": "1:05:22"}
24
+ {"current_steps": 24, "total_steps": 287, "loss": 0.6267, "lr": 1.9856674813052345e-05, "epoch": 0.08340573414422242, "percentage": 8.36, "elapsed_time": "0:05:56", "remaining_time": "1:05:07"}
25
+ {"current_steps": 25, "total_steps": 287, "loss": 0.6798, "lr": 1.9836981604521077e-05, "epoch": 0.08688097306689835, "percentage": 8.71, "elapsed_time": "0:06:11", "remaining_time": "1:04:51"}
26
+ {"current_steps": 26, "total_steps": 287, "loss": 0.6478, "lr": 1.98160321711085e-05, "epoch": 0.09035621198957429, "percentage": 9.06, "elapsed_time": "0:06:25", "remaining_time": "1:04:31"}
27
+ {"current_steps": 27, "total_steps": 287, "loss": 0.6136, "lr": 1.9793829188147406e-05, "epoch": 0.09383145091225022, "percentage": 9.41, "elapsed_time": "0:06:39", "remaining_time": "1:04:08"}
28
+ {"current_steps": 28, "total_steps": 287, "loss": 0.6365, "lr": 1.9770375491054264e-05, "epoch": 0.09730668983492616, "percentage": 9.76, "elapsed_time": "0:06:54", "remaining_time": "1:03:53"}
29
+ {"current_steps": 29, "total_steps": 287, "loss": 0.6168, "lr": 1.974567407496712e-05, "epoch": 0.10078192875760209, "percentage": 10.1, "elapsed_time": "0:07:09", "remaining_time": "1:03:39"}
30
+ {"current_steps": 30, "total_steps": 287, "loss": 0.6212, "lr": 1.9719728094363103e-05, "epoch": 0.10425716768027801, "percentage": 10.45, "elapsed_time": "0:07:24", "remaining_time": "1:03:31"}
31
+ {"current_steps": 31, "total_steps": 287, "loss": 0.6246, "lr": 1.9692540862655587e-05, "epoch": 0.10773240660295395, "percentage": 10.8, "elapsed_time": "0:07:40", "remaining_time": "1:03:20"}
32
+ {"current_steps": 32, "total_steps": 287, "loss": 0.585, "lr": 1.966411585177105e-05, "epoch": 0.11120764552562988, "percentage": 11.15, "elapsed_time": "0:07:51", "remaining_time": "1:02:36"}
33
+ {"current_steps": 33, "total_steps": 287, "loss": 0.6416, "lr": 1.9634456691705705e-05, "epoch": 0.11468288444830582, "percentage": 11.5, "elapsed_time": "0:08:06", "remaining_time": "1:02:21"}
34
+ {"current_steps": 34, "total_steps": 287, "loss": 0.6112, "lr": 1.9603567170061918e-05, "epoch": 0.11815812337098175, "percentage": 11.85, "elapsed_time": "0:08:19", "remaining_time": "1:01:56"}
35
+ {"current_steps": 35, "total_steps": 287, "loss": 0.6193, "lr": 1.9571451231564523e-05, "epoch": 0.12163336229365769, "percentage": 12.2, "elapsed_time": "0:08:33", "remaining_time": "1:01:38"}
36
+ {"current_steps": 36, "total_steps": 287, "loss": 0.661, "lr": 1.9538112977557077e-05, "epoch": 0.12510860121633363, "percentage": 12.54, "elapsed_time": "0:08:48", "remaining_time": "1:01:21"}
37
+ {"current_steps": 37, "total_steps": 287, "loss": 0.626, "lr": 1.9503556665478066e-05, "epoch": 0.12858384013900956, "percentage": 12.89, "elapsed_time": "0:09:01", "remaining_time": "1:00:59"}
38
+ {"current_steps": 38, "total_steps": 287, "loss": 0.6553, "lr": 1.9467786708317257e-05, "epoch": 0.13205907906168549, "percentage": 13.24, "elapsed_time": "0:09:16", "remaining_time": "1:00:46"}
39
+ {"current_steps": 39, "total_steps": 287, "loss": 0.6105, "lr": 1.9430807674052092e-05, "epoch": 0.1355343179843614, "percentage": 13.59, "elapsed_time": "0:09:30", "remaining_time": "1:00:28"}
40
+ {"current_steps": 40, "total_steps": 287, "loss": 0.6362, "lr": 1.939262428506438e-05, "epoch": 0.13900955690703737, "percentage": 13.94, "elapsed_time": "0:09:44", "remaining_time": "1:00:09"}
41
+ {"current_steps": 41, "total_steps": 287, "loss": 0.639, "lr": 1.9353241417537216e-05, "epoch": 0.1424847958297133, "percentage": 14.29, "elapsed_time": "0:09:59", "remaining_time": "0:59:55"}
42
+ {"current_steps": 42, "total_steps": 287, "loss": 0.6421, "lr": 1.9312664100832236e-05, "epoch": 0.14596003475238922, "percentage": 14.63, "elapsed_time": "0:10:14", "remaining_time": "0:59:42"}
43
+ {"current_steps": 43, "total_steps": 287, "loss": 0.5897, "lr": 1.9270897516847406e-05, "epoch": 0.14943527367506515, "percentage": 14.98, "elapsed_time": "0:10:27", "remaining_time": "0:59:22"}
44
+ {"current_steps": 44, "total_steps": 287, "loss": 0.6122, "lr": 1.9227946999355226e-05, "epoch": 0.1529105125977411, "percentage": 15.33, "elapsed_time": "0:10:41", "remaining_time": "0:59:02"}
45
+ {"current_steps": 45, "total_steps": 287, "loss": 0.5546, "lr": 1.9183818033321612e-05, "epoch": 0.15638575152041703, "percentage": 15.68, "elapsed_time": "0:10:54", "remaining_time": "0:58:42"}
46
+ {"current_steps": 46, "total_steps": 287, "loss": 0.6268, "lr": 1.9138516254205416e-05, "epoch": 0.15986099044309296, "percentage": 16.03, "elapsed_time": "0:11:13", "remaining_time": "0:58:47"}
47
+ {"current_steps": 47, "total_steps": 287, "loss": 0.6081, "lr": 1.9092047447238775e-05, "epoch": 0.1633362293657689, "percentage": 16.38, "elapsed_time": "0:11:30", "remaining_time": "0:58:43"}
48
+ {"current_steps": 48, "total_steps": 287, "loss": 0.6007, "lr": 1.9044417546688295e-05, "epoch": 0.16681146828844484, "percentage": 16.72, "elapsed_time": "0:11:45", "remaining_time": "0:58:32"}
49
+ {"current_steps": 49, "total_steps": 287, "loss": 0.6219, "lr": 1.899563263509725e-05, "epoch": 0.17028670721112077, "percentage": 17.07, "elapsed_time": "0:12:01", "remaining_time": "0:58:22"}
50
+ {"current_steps": 50, "total_steps": 287, "loss": 0.5834, "lr": 1.894569894250877e-05, "epoch": 0.1737619461337967, "percentage": 17.42, "elapsed_time": "0:12:16", "remaining_time": "0:58:10"}
51
+ {"current_steps": 51, "total_steps": 287, "loss": 0.6568, "lr": 1.8894622845670282e-05, "epoch": 0.17723718505647262, "percentage": 17.77, "elapsed_time": "0:12:31", "remaining_time": "0:57:57"}
52
+ {"current_steps": 52, "total_steps": 287, "loss": 0.6269, "lr": 1.8842410867219137e-05, "epoch": 0.18071242397914858, "percentage": 18.12, "elapsed_time": "0:12:46", "remaining_time": "0:57:41"}
53
+ {"current_steps": 53, "total_steps": 287, "loss": 0.5973, "lr": 1.878906967484966e-05, "epoch": 0.1841876629018245, "percentage": 18.47, "elapsed_time": "0:12:59", "remaining_time": "0:57:22"}
54
+ {"current_steps": 54, "total_steps": 287, "loss": 0.6367, "lr": 1.8734606080461657e-05, "epoch": 0.18766290182450043, "percentage": 18.82, "elapsed_time": "0:13:13", "remaining_time": "0:57:04"}
55
+ {"current_steps": 55, "total_steps": 287, "loss": 0.6006, "lr": 1.86790270392905e-05, "epoch": 0.19113814074717636, "percentage": 19.16, "elapsed_time": "0:13:28", "remaining_time": "0:56:52"}
56
+ {"current_steps": 56, "total_steps": 287, "loss": 0.579, "lr": 1.8622339649018907e-05, "epoch": 0.19461337966985232, "percentage": 19.51, "elapsed_time": "0:13:43", "remaining_time": "0:56:36"}
57
+ {"current_steps": 57, "total_steps": 287, "loss": 0.5521, "lr": 1.856455114887056e-05, "epoch": 0.19808861859252824, "percentage": 19.86, "elapsed_time": "0:13:57", "remaining_time": "0:56:18"}
58
+ {"current_steps": 58, "total_steps": 287, "loss": 0.6222, "lr": 1.8505668918685603e-05, "epoch": 0.20156385751520417, "percentage": 20.21, "elapsed_time": "0:14:11", "remaining_time": "0:56:02"}
59
+ {"current_steps": 59, "total_steps": 287, "loss": 0.6631, "lr": 1.8445700477978207e-05, "epoch": 0.2050390964378801, "percentage": 20.56, "elapsed_time": "0:14:27", "remaining_time": "0:55:50"}
60
+ {"current_steps": 60, "total_steps": 287, "loss": 0.5963, "lr": 1.8384653484976305e-05, "epoch": 0.20851433536055602, "percentage": 20.91, "elapsed_time": "0:14:41", "remaining_time": "0:55:34"}
61
+ {"current_steps": 61, "total_steps": 287, "loss": 0.5943, "lr": 1.8322535735643604e-05, "epoch": 0.21198957428323198, "percentage": 21.25, "elapsed_time": "0:14:57", "remaining_time": "0:55:23"}
62
+ {"current_steps": 62, "total_steps": 287, "loss": 0.6301, "lr": 1.8259355162684e-05, "epoch": 0.2154648132059079, "percentage": 21.6, "elapsed_time": "0:15:12", "remaining_time": "0:55:10"}
63
+ {"current_steps": 63, "total_steps": 287, "loss": 0.6366, "lr": 1.8195119834528535e-05, "epoch": 0.21894005212858383, "percentage": 21.95, "elapsed_time": "0:15:26", "remaining_time": "0:54:53"}
64
+ {"current_steps": 64, "total_steps": 287, "loss": 0.6156, "lr": 1.8129837954305033e-05, "epoch": 0.22241529105125976, "percentage": 22.3, "elapsed_time": "0:15:40", "remaining_time": "0:54:37"}
65
+ {"current_steps": 65, "total_steps": 287, "loss": 0.608, "lr": 1.8063517858790517e-05, "epoch": 0.22589052997393572, "percentage": 22.65, "elapsed_time": "0:15:55", "remaining_time": "0:54:23"}
66
+ {"current_steps": 66, "total_steps": 287, "loss": 0.6334, "lr": 1.799616801734657e-05, "epoch": 0.22936576889661164, "percentage": 23.0, "elapsed_time": "0:16:09", "remaining_time": "0:54:05"}
67
+ {"current_steps": 67, "total_steps": 287, "loss": 0.6139, "lr": 1.792779703083777e-05, "epoch": 0.23284100781928757, "percentage": 23.34, "elapsed_time": "0:16:21", "remaining_time": "0:53:41"}
68
+ {"current_steps": 68, "total_steps": 287, "loss": 0.5897, "lr": 1.7858413630533305e-05, "epoch": 0.2363162467419635, "percentage": 23.69, "elapsed_time": "0:16:36", "remaining_time": "0:53:30"}
69
+ {"current_steps": 69, "total_steps": 287, "loss": 0.606, "lr": 1.778802667699196e-05, "epoch": 0.23979148566463945, "percentage": 24.04, "elapsed_time": "0:16:52", "remaining_time": "0:53:19"}
70
+ {"current_steps": 70, "total_steps": 287, "loss": 0.5888, "lr": 1.77166451589306e-05, "epoch": 0.24326672458731538, "percentage": 24.39, "elapsed_time": "0:17:06", "remaining_time": "0:53:00"}
71
+ {"current_steps": 71, "total_steps": 287, "loss": 0.6004, "lr": 1.764427819207624e-05, "epoch": 0.2467419635099913, "percentage": 24.74, "elapsed_time": "0:17:21", "remaining_time": "0:52:47"}
72
+ {"current_steps": 72, "total_steps": 287, "loss": 0.5699, "lr": 1.757093501800196e-05, "epoch": 0.25021720243266726, "percentage": 25.09, "elapsed_time": "0:17:37", "remaining_time": "0:52:37"}
73
+ {"current_steps": 73, "total_steps": 287, "loss": 0.6051, "lr": 1.7496625002946702e-05, "epoch": 0.2536924413553432, "percentage": 25.44, "elapsed_time": "0:17:52", "remaining_time": "0:52:23"}
74
+ {"current_steps": 74, "total_steps": 287, "loss": 0.6494, "lr": 1.7421357636619153e-05, "epoch": 0.2571676802780191, "percentage": 25.78, "elapsed_time": "0:18:08", "remaining_time": "0:52:14"}
75
+ {"current_steps": 75, "total_steps": 287, "loss": 0.6033, "lr": 1.734514253098589e-05, "epoch": 0.26064291920069504, "percentage": 26.13, "elapsed_time": "0:18:24", "remaining_time": "0:52:02"}
76
+ {"current_steps": 76, "total_steps": 287, "loss": 0.596, "lr": 1.726798941904386e-05, "epoch": 0.26411815812337097, "percentage": 26.48, "elapsed_time": "0:18:40", "remaining_time": "0:51:50"}
77
+ {"current_steps": 77, "total_steps": 287, "loss": 0.5669, "lr": 1.7189908153577473e-05, "epoch": 0.2675933970460469, "percentage": 26.83, "elapsed_time": "0:18:53", "remaining_time": "0:51:31"}
78
+ {"current_steps": 78, "total_steps": 287, "loss": 0.6133, "lr": 1.7110908705900322e-05, "epoch": 0.2710686359687228, "percentage": 27.18, "elapsed_time": "0:19:07", "remaining_time": "0:51:13"}
79
+ {"current_steps": 79, "total_steps": 287, "loss": 0.6405, "lr": 1.7031001164581828e-05, "epoch": 0.2745438748913988, "percentage": 27.53, "elapsed_time": "0:19:22", "remaining_time": "0:51:00"}
80
+ {"current_steps": 80, "total_steps": 287, "loss": 0.579, "lr": 1.6950195734158874e-05, "epoch": 0.27801911381407474, "percentage": 27.87, "elapsed_time": "0:19:37", "remaining_time": "0:50:47"}
81
+ {"current_steps": 81, "total_steps": 287, "loss": 0.5825, "lr": 1.6868502733832647e-05, "epoch": 0.28149435273675066, "percentage": 28.22, "elapsed_time": "0:19:49", "remaining_time": "0:50:26"}
82
+ {"current_steps": 82, "total_steps": 287, "loss": 0.6038, "lr": 1.6785932596150827e-05, "epoch": 0.2849695916594266, "percentage": 28.57, "elapsed_time": "0:20:04", "remaining_time": "0:50:11"}
83
+ {"current_steps": 83, "total_steps": 287, "loss": 0.5979, "lr": 1.670249586567531e-05, "epoch": 0.2884448305821025, "percentage": 28.92, "elapsed_time": "0:20:19", "remaining_time": "0:49:57"}
84
+ {"current_steps": 84, "total_steps": 287, "loss": 0.5832, "lr": 1.6618203197635624e-05, "epoch": 0.29192006950477845, "percentage": 29.27, "elapsed_time": "0:20:32", "remaining_time": "0:49:39"}
85
+ {"current_steps": 85, "total_steps": 287, "loss": 0.5844, "lr": 1.6533065356568206e-05, "epoch": 0.2953953084274544, "percentage": 29.62, "elapsed_time": "0:20:48", "remaining_time": "0:49:26"}
86
+ {"current_steps": 86, "total_steps": 287, "loss": 0.619, "lr": 1.6447093214941727e-05, "epoch": 0.2988705473501303, "percentage": 29.97, "elapsed_time": "0:21:01", "remaining_time": "0:49:08"}
87
+ {"current_steps": 87, "total_steps": 287, "loss": 0.6573, "lr": 1.636029775176862e-05, "epoch": 0.3023457862728063, "percentage": 30.31, "elapsed_time": "0:21:17", "remaining_time": "0:48:56"}
88
+ {"current_steps": 88, "total_steps": 287, "loss": 0.5779, "lr": 1.627269005120304e-05, "epoch": 0.3058210251954822, "percentage": 30.66, "elapsed_time": "0:21:32", "remaining_time": "0:48:42"}
89
+ {"current_steps": 89, "total_steps": 287, "loss": 0.5994, "lr": 1.618428130112533e-05, "epoch": 0.30929626411815814, "percentage": 31.01, "elapsed_time": "0:21:46", "remaining_time": "0:48:27"}
90
+ {"current_steps": 90, "total_steps": 287, "loss": 0.626, "lr": 1.6095082791713322e-05, "epoch": 0.31277150304083406, "percentage": 31.36, "elapsed_time": "0:21:59", "remaining_time": "0:48:09"}
91
+ {"current_steps": 91, "total_steps": 287, "loss": 0.6313, "lr": 1.6005105914000508e-05, "epoch": 0.31624674196351, "percentage": 31.71, "elapsed_time": "0:22:12", "remaining_time": "0:47:50"}
92
+ {"current_steps": 92, "total_steps": 287, "loss": 0.636, "lr": 1.5914362158421352e-05, "epoch": 0.3197219808861859, "percentage": 32.06, "elapsed_time": "0:22:27", "remaining_time": "0:47:36"}
93
+ {"current_steps": 93, "total_steps": 287, "loss": 0.5972, "lr": 1.5822863113343934e-05, "epoch": 0.32319721980886185, "percentage": 32.4, "elapsed_time": "0:22:43", "remaining_time": "0:47:24"}
94
+ {"current_steps": 94, "total_steps": 287, "loss": 0.5728, "lr": 1.5730620463590052e-05, "epoch": 0.3266724587315378, "percentage": 32.75, "elapsed_time": "0:22:58", "remaining_time": "0:47:09"}
95
+ {"current_steps": 95, "total_steps": 287, "loss": 0.6138, "lr": 1.5637645988943008e-05, "epoch": 0.3301476976542137, "percentage": 33.1, "elapsed_time": "0:23:14", "remaining_time": "0:46:59"}
96
+ {"current_steps": 96, "total_steps": 287, "loss": 0.6123, "lr": 1.554395156264331e-05, "epoch": 0.3336229365768897, "percentage": 33.45, "elapsed_time": "0:23:31", "remaining_time": "0:46:47"}
97
+ {"current_steps": 97, "total_steps": 287, "loss": 0.6063, "lr": 1.544954914987238e-05, "epoch": 0.3370981754995656, "percentage": 33.8, "elapsed_time": "0:23:46", "remaining_time": "0:46:33"}
98
+ {"current_steps": 98, "total_steps": 287, "loss": 0.5842, "lr": 1.5354450806224553e-05, "epoch": 0.34057341442224154, "percentage": 34.15, "elapsed_time": "0:23:59", "remaining_time": "0:46:16"}
99
+ {"current_steps": 99, "total_steps": 287, "loss": 0.5938, "lr": 1.5258668676167548e-05, "epoch": 0.34404865334491747, "percentage": 34.49, "elapsed_time": "0:24:12", "remaining_time": "0:45:59"}
100
+ {"current_steps": 100, "total_steps": 287, "loss": 0.6202, "lr": 1.516221499149154e-05, "epoch": 0.3475238922675934, "percentage": 34.84, "elapsed_time": "0:24:26", "remaining_time": "0:45:43"}
101
+ {"current_steps": 101, "total_steps": 287, "loss": 0.6216, "lr": 1.5065102069747117e-05, "epoch": 0.3509991311902693, "percentage": 35.19, "elapsed_time": "0:24:41", "remaining_time": "0:45:28"}
102
+ {"current_steps": 102, "total_steps": 287, "loss": 0.5649, "lr": 1.4967342312672283e-05, "epoch": 0.35447437011294525, "percentage": 35.54, "elapsed_time": "0:24:59", "remaining_time": "0:45:19"}
103
+ {"current_steps": 103, "total_steps": 287, "loss": 0.5954, "lr": 1.48689482046087e-05, "epoch": 0.3579496090356212, "percentage": 35.89, "elapsed_time": "0:25:13", "remaining_time": "0:45:03"}
104
+ {"current_steps": 104, "total_steps": 287, "loss": 0.6362, "lr": 1.4769932310907372e-05, "epoch": 0.36142484795829716, "percentage": 36.24, "elapsed_time": "0:25:26", "remaining_time": "0:44:45"}
105
+ {"current_steps": 105, "total_steps": 287, "loss": 0.5664, "lr": 1.467030727632401e-05, "epoch": 0.3649000868809731, "percentage": 36.59, "elapsed_time": "0:25:40", "remaining_time": "0:44:30"}
106
+ {"current_steps": 106, "total_steps": 287, "loss": 0.586, "lr": 1.4570085823404232e-05, "epoch": 0.368375325803649, "percentage": 36.93, "elapsed_time": "0:25:55", "remaining_time": "0:44:16"}
107
+ {"current_steps": 107, "total_steps": 287, "loss": 0.5773, "lr": 1.4469280750858854e-05, "epoch": 0.37185056472632494, "percentage": 37.28, "elapsed_time": "0:26:10", "remaining_time": "0:44:01"}
108
+ {"current_steps": 108, "total_steps": 287, "loss": 0.585, "lr": 1.4367904931929422e-05, "epoch": 0.37532580364900087, "percentage": 37.63, "elapsed_time": "0:26:24", "remaining_time": "0:43:45"}
109
+ {"current_steps": 109, "total_steps": 287, "loss": 0.5698, "lr": 1.4265971312744252e-05, "epoch": 0.3788010425716768, "percentage": 37.98, "elapsed_time": "0:26:39", "remaining_time": "0:43:32"}
110
+ {"current_steps": 110, "total_steps": 287, "loss": 0.611, "lr": 1.4163492910665153e-05, "epoch": 0.3822762814943527, "percentage": 38.33, "elapsed_time": "0:26:55", "remaining_time": "0:43:19"}
111
+ {"current_steps": 111, "total_steps": 287, "loss": 0.6226, "lr": 1.4060482812625055e-05, "epoch": 0.38575152041702865, "percentage": 38.68, "elapsed_time": "0:27:09", "remaining_time": "0:43:03"}
112
+ {"current_steps": 112, "total_steps": 287, "loss": 0.6257, "lr": 1.395695417345675e-05, "epoch": 0.38922675933970463, "percentage": 39.02, "elapsed_time": "0:27:25", "remaining_time": "0:42:51"}
113
+ {"current_steps": 113, "total_steps": 287, "loss": 0.5883, "lr": 1.3852920214212966e-05, "epoch": 0.39270199826238056, "percentage": 39.37, "elapsed_time": "0:27:38", "remaining_time": "0:42:34"}
114
+ {"current_steps": 114, "total_steps": 287, "loss": 0.5804, "lr": 1.3748394220477972e-05, "epoch": 0.3961772371850565, "percentage": 39.72, "elapsed_time": "0:27:52", "remaining_time": "0:42:18"}
115
+ {"current_steps": 115, "total_steps": 287, "loss": 0.6178, "lr": 1.3643389540670963e-05, "epoch": 0.3996524761077324, "percentage": 40.07, "elapsed_time": "0:28:06", "remaining_time": "0:42:02"}
116
+ {"current_steps": 116, "total_steps": 287, "loss": 0.5959, "lr": 1.3537919584341413e-05, "epoch": 0.40312771503040834, "percentage": 40.42, "elapsed_time": "0:28:19", "remaining_time": "0:41:45"}
117
+ {"current_steps": 117, "total_steps": 287, "loss": 0.6051, "lr": 1.3431997820456592e-05, "epoch": 0.40660295395308427, "percentage": 40.77, "elapsed_time": "0:28:34", "remaining_time": "0:41:30"}
118
+ {"current_steps": 118, "total_steps": 287, "loss": 0.599, "lr": 1.3325637775681561e-05, "epoch": 0.4100781928757602, "percentage": 41.11, "elapsed_time": "0:28:51", "remaining_time": "0:41:19"}
119
+ {"current_steps": 119, "total_steps": 287, "loss": 0.6322, "lr": 1.3218853032651719e-05, "epoch": 0.4135534317984361, "percentage": 41.46, "elapsed_time": "0:29:06", "remaining_time": "0:41:05"}
120
+ {"current_steps": 120, "total_steps": 287, "loss": 0.6209, "lr": 1.3111657228238263e-05, "epoch": 0.41702867072111205, "percentage": 41.81, "elapsed_time": "0:29:21", "remaining_time": "0:40:50"}
121
+ {"current_steps": 121, "total_steps": 287, "loss": 0.5832, "lr": 1.3004064051806712e-05, "epoch": 0.42050390964378803, "percentage": 42.16, "elapsed_time": "0:29:35", "remaining_time": "0:40:35"}
122
+ {"current_steps": 122, "total_steps": 287, "loss": 0.5645, "lr": 1.2896087243468673e-05, "epoch": 0.42397914856646396, "percentage": 42.51, "elapsed_time": "0:29:49", "remaining_time": "0:40:20"}
123
+ {"current_steps": 123, "total_steps": 287, "loss": 0.5921, "lr": 1.2787740592327232e-05, "epoch": 0.4274543874891399, "percentage": 42.86, "elapsed_time": "0:30:04", "remaining_time": "0:40:06"}
124
+ {"current_steps": 124, "total_steps": 287, "loss": 0.5687, "lr": 1.267903793471597e-05, "epoch": 0.4309296264118158, "percentage": 43.21, "elapsed_time": "0:30:20", "remaining_time": "0:39:53"}
125
+ {"current_steps": 125, "total_steps": 287, "loss": 0.5973, "lr": 1.2569993152432028e-05, "epoch": 0.43440486533449174, "percentage": 43.55, "elapsed_time": "0:30:34", "remaining_time": "0:39:37"}
126
+ {"current_steps": 126, "total_steps": 287, "loss": 0.6029, "lr": 1.2460620170963353e-05, "epoch": 0.43788010425716767, "percentage": 43.9, "elapsed_time": "0:30:48", "remaining_time": "0:39:22"}
127
+ {"current_steps": 127, "total_steps": 287, "loss": 0.5916, "lr": 1.2350932957710322e-05, "epoch": 0.4413553431798436, "percentage": 44.25, "elapsed_time": "0:31:02", "remaining_time": "0:39:06"}
128
+ {"current_steps": 128, "total_steps": 287, "loss": 0.5557, "lr": 1.2240945520202079e-05, "epoch": 0.4448305821025195, "percentage": 44.6, "elapsed_time": "0:31:18", "remaining_time": "0:38:53"}
129
+ {"current_steps": 129, "total_steps": 287, "loss": 0.605, "lr": 1.2130671904307692e-05, "epoch": 0.4483058210251955, "percentage": 44.95, "elapsed_time": "0:31:31", "remaining_time": "0:38:37"}
130
+ {"current_steps": 130, "total_steps": 287, "loss": 0.6198, "lr": 1.202012619244243e-05, "epoch": 0.45178105994787143, "percentage": 45.3, "elapsed_time": "0:31:45", "remaining_time": "0:38:21"}
131
+ {"current_steps": 131, "total_steps": 287, "loss": 0.5757, "lr": 1.1909322501769407e-05, "epoch": 0.45525629887054736, "percentage": 45.64, "elapsed_time": "0:32:00", "remaining_time": "0:38:07"}
132
+ {"current_steps": 132, "total_steps": 287, "loss": 0.5597, "lr": 1.1798274982396728e-05, "epoch": 0.4587315377932233, "percentage": 45.99, "elapsed_time": "0:32:14", "remaining_time": "0:37:51"}
133
+ {"current_steps": 133, "total_steps": 287, "loss": 0.5686, "lr": 1.1686997815570473e-05, "epoch": 0.4622067767158992, "percentage": 46.34, "elapsed_time": "0:32:30", "remaining_time": "0:37:38"}
134
+ {"current_steps": 134, "total_steps": 287, "loss": 0.6, "lr": 1.15755052118637e-05, "epoch": 0.46568201563857514, "percentage": 46.69, "elapsed_time": "0:32:44", "remaining_time": "0:37:22"}
135
+ {"current_steps": 135, "total_steps": 287, "loss": 0.5479, "lr": 1.1463811409361667e-05, "epoch": 0.46915725456125107, "percentage": 47.04, "elapsed_time": "0:32:59", "remaining_time": "0:37:08"}
136
+ {"current_steps": 136, "total_steps": 287, "loss": 0.6045, "lr": 1.13519306718436e-05, "epoch": 0.472632493483927, "percentage": 47.39, "elapsed_time": "0:33:13", "remaining_time": "0:36:53"}
137
+ {"current_steps": 137, "total_steps": 287, "loss": 0.561, "lr": 1.1239877286961123e-05, "epoch": 0.476107732406603, "percentage": 47.74, "elapsed_time": "0:33:29", "remaining_time": "0:36:40"}
138
+ {"current_steps": 138, "total_steps": 287, "loss": 0.6139, "lr": 1.112766556441367e-05, "epoch": 0.4795829713292789, "percentage": 48.08, "elapsed_time": "0:33:44", "remaining_time": "0:36:26"}
139
+ {"current_steps": 139, "total_steps": 287, "loss": 0.5811, "lr": 1.1015309834121083e-05, "epoch": 0.48305821025195483, "percentage": 48.43, "elapsed_time": "0:33:59", "remaining_time": "0:36:11"}
140
+ {"current_steps": 140, "total_steps": 287, "loss": 0.6299, "lr": 1.0902824444393602e-05, "epoch": 0.48653344917463076, "percentage": 48.78, "elapsed_time": "0:34:15", "remaining_time": "0:35:58"}
141
+ {"current_steps": 141, "total_steps": 287, "loss": 0.5937, "lr": 1.079022376009955e-05, "epoch": 0.4900086880973067, "percentage": 49.13, "elapsed_time": "0:34:30", "remaining_time": "0:35:44"}
142
+ {"current_steps": 142, "total_steps": 287, "loss": 0.5718, "lr": 1.067752216083085e-05, "epoch": 0.4934839270199826, "percentage": 49.48, "elapsed_time": "0:34:46", "remaining_time": "0:35:30"}
143
+ {"current_steps": 143, "total_steps": 287, "loss": 0.6251, "lr": 1.05647340390667e-05, "epoch": 0.49695916594265854, "percentage": 49.83, "elapsed_time": "0:34:59", "remaining_time": "0:35:14"}
144
+ {"current_steps": 144, "total_steps": 287, "loss": 0.5583, "lr": 1.0451873798335605e-05, "epoch": 0.5004344048653345, "percentage": 50.17, "elapsed_time": "0:35:14", "remaining_time": "0:35:00"}
145
+ {"current_steps": 145, "total_steps": 287, "loss": 0.5893, "lr": 1.0338955851375962e-05, "epoch": 0.5039096437880104, "percentage": 50.52, "elapsed_time": "0:35:28", "remaining_time": "0:34:44"}
146
+ {"current_steps": 146, "total_steps": 287, "loss": 0.5414, "lr": 1.0225994618295507e-05, "epoch": 0.5073848827106864, "percentage": 50.87, "elapsed_time": "0:35:44", "remaining_time": "0:34:31"}
147
+ {"current_steps": 147, "total_steps": 287, "loss": 0.5601, "lr": 1.01130045247298e-05, "epoch": 0.5108601216333623, "percentage": 51.22, "elapsed_time": "0:35:59", "remaining_time": "0:34:16"}
148
+ {"current_steps": 148, "total_steps": 287, "loss": 0.65, "lr": 1e-05, "epoch": 0.5143353605560382, "percentage": 51.57, "elapsed_time": "0:36:13", "remaining_time": "0:34:01"}
149
+ {"current_steps": 149, "total_steps": 287, "loss": 0.5905, "lr": 9.886995475270205e-06, "epoch": 0.5178105994787141, "percentage": 51.92, "elapsed_time": "0:36:28", "remaining_time": "0:33:46"}
150
+ {"current_steps": 150, "total_steps": 287, "loss": 0.5995, "lr": 9.774005381704498e-06, "epoch": 0.5212858384013901, "percentage": 52.26, "elapsed_time": "0:36:42", "remaining_time": "0:33:31"}
151
+ {"current_steps": 151, "total_steps": 287, "loss": 0.642, "lr": 9.661044148624038e-06, "epoch": 0.5247610773240661, "percentage": 52.61, "elapsed_time": "0:36:56", "remaining_time": "0:33:16"}
152
+ {"current_steps": 152, "total_steps": 287, "loss": 0.534, "lr": 9.548126201664398e-06, "epoch": 0.5282363162467419, "percentage": 52.96, "elapsed_time": "0:37:09", "remaining_time": "0:33:00"}
153
+ {"current_steps": 153, "total_steps": 287, "loss": 0.6327, "lr": 9.435265960933304e-06, "epoch": 0.5317115551694179, "percentage": 53.31, "elapsed_time": "0:37:26", "remaining_time": "0:32:47"}
154
+ {"current_steps": 154, "total_steps": 287, "loss": 0.5787, "lr": 9.322477839169156e-06, "epoch": 0.5351867940920938, "percentage": 53.66, "elapsed_time": "0:37:42", "remaining_time": "0:32:34"}
155
+ {"current_steps": 155, "total_steps": 287, "loss": 0.5954, "lr": 9.209776239900453e-06, "epoch": 0.5386620330147698, "percentage": 54.01, "elapsed_time": "0:37:57", "remaining_time": "0:32:19"}
156
+ {"current_steps": 156, "total_steps": 287, "loss": 0.5514, "lr": 9.097175555606396e-06, "epoch": 0.5421372719374457, "percentage": 54.36, "elapsed_time": "0:38:11", "remaining_time": "0:32:04"}
157
+ {"current_steps": 157, "total_steps": 287, "loss": 0.5798, "lr": 8.98469016587892e-06, "epoch": 0.5456125108601216, "percentage": 54.7, "elapsed_time": "0:38:26", "remaining_time": "0:31:49"}
158
+ {"current_steps": 158, "total_steps": 287, "loss": 0.5911, "lr": 8.872334435586333e-06, "epoch": 0.5490877497827976, "percentage": 55.05, "elapsed_time": "0:38:41", "remaining_time": "0:31:35"}
159
+ {"current_steps": 159, "total_steps": 287, "loss": 0.6158, "lr": 8.76012271303888e-06, "epoch": 0.5525629887054735, "percentage": 55.4, "elapsed_time": "0:38:54", "remaining_time": "0:31:19"}
160
+ {"current_steps": 160, "total_steps": 287, "loss": 0.5601, "lr": 8.648069328156403e-06, "epoch": 0.5560382276281495, "percentage": 55.75, "elapsed_time": "0:39:09", "remaining_time": "0:31:04"}
161
+ {"current_steps": 161, "total_steps": 287, "loss": 0.6152, "lr": 8.536188590638334e-06, "epoch": 0.5595134665508253, "percentage": 56.1, "elapsed_time": "0:39:26", "remaining_time": "0:30:52"}
162
+ {"current_steps": 162, "total_steps": 287, "loss": 0.5666, "lr": 8.424494788136303e-06, "epoch": 0.5629887054735013, "percentage": 56.45, "elapsed_time": "0:39:42", "remaining_time": "0:30:38"}
163
+ {"current_steps": 163, "total_steps": 287, "loss": 0.5695, "lr": 8.313002184429529e-06, "epoch": 0.5664639443961772, "percentage": 56.79, "elapsed_time": "0:39:56", "remaining_time": "0:30:23"}
164
+ {"current_steps": 164, "total_steps": 287, "loss": 0.5357, "lr": 8.201725017603277e-06, "epoch": 0.5699391833188532, "percentage": 57.14, "elapsed_time": "0:40:12", "remaining_time": "0:30:09"}
165
+ {"current_steps": 165, "total_steps": 287, "loss": 0.564, "lr": 8.090677498230598e-06, "epoch": 0.573414422241529, "percentage": 57.49, "elapsed_time": "0:40:28", "remaining_time": "0:29:55"}
166
+ {"current_steps": 166, "total_steps": 287, "loss": 0.5933, "lr": 7.97987380755757e-06, "epoch": 0.576889661164205, "percentage": 57.84, "elapsed_time": "0:40:42", "remaining_time": "0:29:40"}
167
+ {"current_steps": 167, "total_steps": 287, "loss": 0.5811, "lr": 7.869328095692313e-06, "epoch": 0.580364900086881, "percentage": 58.19, "elapsed_time": "0:40:56", "remaining_time": "0:29:25"}
168
+ {"current_steps": 168, "total_steps": 287, "loss": 0.5816, "lr": 7.759054479797924e-06, "epoch": 0.5838401390095569, "percentage": 58.54, "elapsed_time": "0:41:13", "remaining_time": "0:29:11"}
169
+ {"current_steps": 169, "total_steps": 287, "loss": 0.5688, "lr": 7.649067042289681e-06, "epoch": 0.5873153779322329, "percentage": 58.89, "elapsed_time": "0:41:27", "remaining_time": "0:28:56"}
170
+ {"current_steps": 170, "total_steps": 287, "loss": 0.5823, "lr": 7.539379829036652e-06, "epoch": 0.5907906168549087, "percentage": 59.23, "elapsed_time": "0:41:40", "remaining_time": "0:28:40"}
171
+ {"current_steps": 171, "total_steps": 287, "loss": 0.5933, "lr": 7.430006847567972e-06, "epoch": 0.5942658557775847, "percentage": 59.58, "elapsed_time": "0:41:54", "remaining_time": "0:28:25"}
172
+ {"current_steps": 172, "total_steps": 287, "loss": 0.5611, "lr": 7.320962065284032e-06, "epoch": 0.5977410947002606, "percentage": 59.93, "elapsed_time": "0:42:09", "remaining_time": "0:28:11"}
173
+ {"current_steps": 173, "total_steps": 287, "loss": 0.6206, "lr": 7.2122594076727705e-06, "epoch": 0.6012163336229366, "percentage": 60.28, "elapsed_time": "0:42:25", "remaining_time": "0:27:57"}
174
+ {"current_steps": 174, "total_steps": 287, "loss": 0.619, "lr": 7.1039127565313285e-06, "epoch": 0.6046915725456126, "percentage": 60.63, "elapsed_time": "0:42:42", "remaining_time": "0:27:44"}
175
+ {"current_steps": 175, "total_steps": 287, "loss": 0.5557, "lr": 6.995935948193294e-06, "epoch": 0.6081668114682884, "percentage": 60.98, "elapsed_time": "0:42:55", "remaining_time": "0:27:28"}
176
+ {"current_steps": 176, "total_steps": 287, "loss": 0.5392, "lr": 6.888342771761737e-06, "epoch": 0.6116420503909644, "percentage": 61.32, "elapsed_time": "0:43:10", "remaining_time": "0:27:13"}
177
+ {"current_steps": 177, "total_steps": 287, "loss": 0.557, "lr": 6.781146967348283e-06, "epoch": 0.6151172893136403, "percentage": 61.67, "elapsed_time": "0:43:23", "remaining_time": "0:26:57"}
178
+ {"current_steps": 178, "total_steps": 287, "loss": 0.6229, "lr": 6.6743622243184405e-06, "epoch": 0.6185925282363163, "percentage": 62.02, "elapsed_time": "0:43:37", "remaining_time": "0:26:42"}
179
+ {"current_steps": 179, "total_steps": 287, "loss": 0.5777, "lr": 6.568002179543409e-06, "epoch": 0.6220677671589921, "percentage": 62.37, "elapsed_time": "0:43:50", "remaining_time": "0:26:26"}
180
+ {"current_steps": 180, "total_steps": 287, "loss": 0.5546, "lr": 6.462080415658591e-06, "epoch": 0.6255430060816681, "percentage": 62.72, "elapsed_time": "0:44:03", "remaining_time": "0:26:11"}
181
+ {"current_steps": 181, "total_steps": 287, "loss": 0.5811, "lr": 6.356610459329038e-06, "epoch": 0.629018245004344, "percentage": 63.07, "elapsed_time": "0:44:17", "remaining_time": "0:25:56"}
182
+ {"current_steps": 182, "total_steps": 287, "loss": 0.5626, "lr": 6.251605779522032e-06, "epoch": 0.63249348392702, "percentage": 63.41, "elapsed_time": "0:44:31", "remaining_time": "0:25:41"}
183
+ {"current_steps": 183, "total_steps": 287, "loss": 0.5326, "lr": 6.147079785787038e-06, "epoch": 0.635968722849696, "percentage": 63.76, "elapsed_time": "0:44:46", "remaining_time": "0:25:26"}
184
+ {"current_steps": 184, "total_steps": 287, "loss": 0.5609, "lr": 6.043045826543254e-06, "epoch": 0.6394439617723718, "percentage": 64.11, "elapsed_time": "0:44:58", "remaining_time": "0:25:10"}
185
+ {"current_steps": 185, "total_steps": 287, "loss": 0.5593, "lr": 5.93951718737495e-06, "epoch": 0.6429192006950478, "percentage": 64.46, "elapsed_time": "0:45:12", "remaining_time": "0:24:55"}
186
+ {"current_steps": 186, "total_steps": 287, "loss": 0.5391, "lr": 5.836507089334849e-06, "epoch": 0.6463944396177237, "percentage": 64.81, "elapsed_time": "0:45:26", "remaining_time": "0:24:40"}
187
+ {"current_steps": 187, "total_steps": 287, "loss": 0.6108, "lr": 5.7340286872557515e-06, "epoch": 0.6498696785403997, "percentage": 65.16, "elapsed_time": "0:45:38", "remaining_time": "0:24:24"}
188
+ {"current_steps": 188, "total_steps": 287, "loss": 0.5867, "lr": 5.6320950680705826e-06, "epoch": 0.6533449174630755, "percentage": 65.51, "elapsed_time": "0:45:52", "remaining_time": "0:24:09"}
189
+ {"current_steps": 189, "total_steps": 287, "loss": 0.5313, "lr": 5.530719249141148e-06, "epoch": 0.6568201563857515, "percentage": 65.85, "elapsed_time": "0:46:08", "remaining_time": "0:23:55"}
190
+ {"current_steps": 190, "total_steps": 287, "loss": 0.559, "lr": 5.429914176595772e-06, "epoch": 0.6602953953084274, "percentage": 66.2, "elapsed_time": "0:46:23", "remaining_time": "0:23:40"}
191
+ {"current_steps": 191, "total_steps": 287, "loss": 0.5625, "lr": 5.329692723675994e-06, "epoch": 0.6637706342311034, "percentage": 66.55, "elapsed_time": "0:46:39", "remaining_time": "0:23:27"}
192
+ {"current_steps": 192, "total_steps": 287, "loss": 0.5941, "lr": 5.230067689092629e-06, "epoch": 0.6672458731537794, "percentage": 66.9, "elapsed_time": "0:46:53", "remaining_time": "0:23:12"}
193
+ {"current_steps": 193, "total_steps": 287, "loss": 0.6064, "lr": 5.131051795391302e-06, "epoch": 0.6707211120764552, "percentage": 67.25, "elapsed_time": "0:47:08", "remaining_time": "0:22:57"}
194
+ {"current_steps": 194, "total_steps": 287, "loss": 0.5576, "lr": 5.03265768732772e-06, "epoch": 0.6741963509991312, "percentage": 67.6, "elapsed_time": "0:47:22", "remaining_time": "0:22:42"}
195
+ {"current_steps": 195, "total_steps": 287, "loss": 0.59, "lr": 4.934897930252887e-06, "epoch": 0.6776715899218071, "percentage": 67.94, "elapsed_time": "0:47:36", "remaining_time": "0:22:27"}
196
+ {"current_steps": 196, "total_steps": 287, "loss": 0.587, "lr": 4.837785008508462e-06, "epoch": 0.6811468288444831, "percentage": 68.29, "elapsed_time": "0:47:49", "remaining_time": "0:22:12"}
197
+ {"current_steps": 197, "total_steps": 287, "loss": 0.5332, "lr": 4.7413313238324556e-06, "epoch": 0.684622067767159, "percentage": 68.64, "elapsed_time": "0:48:05", "remaining_time": "0:21:58"}
198
+ {"current_steps": 198, "total_steps": 287, "loss": 0.5798, "lr": 4.645549193775452e-06, "epoch": 0.6880973066898349, "percentage": 68.99, "elapsed_time": "0:48:20", "remaining_time": "0:21:43"}
199
+ {"current_steps": 199, "total_steps": 287, "loss": 0.5669, "lr": 4.550450850127626e-06, "epoch": 0.6915725456125109, "percentage": 69.34, "elapsed_time": "0:48:35", "remaining_time": "0:21:29"}
200
+ {"current_steps": 200, "total_steps": 287, "loss": 0.5526, "lr": 4.4560484373566945e-06, "epoch": 0.6950477845351868, "percentage": 69.69, "elapsed_time": "0:48:51", "remaining_time": "0:21:15"}
201
+ {"current_steps": 201, "total_steps": 287, "loss": 0.5225, "lr": 4.3623540110569935e-06, "epoch": 0.6985230234578628, "percentage": 70.03, "elapsed_time": "0:49:05", "remaining_time": "0:21:00"}
202
+ {"current_steps": 202, "total_steps": 287, "loss": 0.6123, "lr": 4.26937953640995e-06, "epoch": 0.7019982623805386, "percentage": 70.38, "elapsed_time": "0:49:21", "remaining_time": "0:20:46"}
203
+ {"current_steps": 203, "total_steps": 287, "loss": 0.5718, "lr": 4.177136886656067e-06, "epoch": 0.7054735013032146, "percentage": 70.73, "elapsed_time": "0:49:35", "remaining_time": "0:20:31"}
204
+ {"current_steps": 204, "total_steps": 287, "loss": 0.6006, "lr": 4.085637841578652e-06, "epoch": 0.7089487402258905, "percentage": 71.08, "elapsed_time": "0:49:49", "remaining_time": "0:20:16"}
205
+ {"current_steps": 205, "total_steps": 287, "loss": 0.5745, "lr": 3.9948940859994964e-06, "epoch": 0.7124239791485665, "percentage": 71.43, "elapsed_time": "0:50:03", "remaining_time": "0:20:01"}
206
+ {"current_steps": 206, "total_steps": 287, "loss": 0.6085, "lr": 3.9049172082866786e-06, "epoch": 0.7158992180712423, "percentage": 71.78, "elapsed_time": "0:50:18", "remaining_time": "0:19:47"}
207
+ {"current_steps": 207, "total_steps": 287, "loss": 0.5586, "lr": 3.815718698874672e-06, "epoch": 0.7193744569939183, "percentage": 72.13, "elapsed_time": "0:50:34", "remaining_time": "0:19:32"}
208
+ {"current_steps": 208, "total_steps": 287, "loss": 0.5927, "lr": 3.727309948796963e-06, "epoch": 0.7228496959165943, "percentage": 72.47, "elapsed_time": "0:50:48", "remaining_time": "0:19:17"}
209
+ {"current_steps": 209, "total_steps": 287, "loss": 0.5594, "lr": 3.6397022482313804e-06, "epoch": 0.7263249348392702, "percentage": 72.82, "elapsed_time": "0:51:01", "remaining_time": "0:19:02"}
210
+ {"current_steps": 210, "total_steps": 287, "loss": 0.5364, "lr": 3.552906785058278e-06, "epoch": 0.7298001737619462, "percentage": 73.17, "elapsed_time": "0:51:16", "remaining_time": "0:18:48"}
211
+ {"current_steps": 211, "total_steps": 287, "loss": 0.5571, "lr": 3.466934643431795e-06, "epoch": 0.733275412684622, "percentage": 73.52, "elapsed_time": "0:51:32", "remaining_time": "0:18:33"}
212
+ {"current_steps": 212, "total_steps": 287, "loss": 0.5717, "lr": 3.3817968023643766e-06, "epoch": 0.736750651607298, "percentage": 73.87, "elapsed_time": "0:51:47", "remaining_time": "0:18:19"}
213
+ {"current_steps": 213, "total_steps": 287, "loss": 0.54, "lr": 3.2975041343246937e-06, "epoch": 0.7402258905299739, "percentage": 74.22, "elapsed_time": "0:52:01", "remaining_time": "0:18:04"}
214
+ {"current_steps": 214, "total_steps": 287, "loss": 0.5807, "lr": 3.214067403849179e-06, "epoch": 0.7437011294526499, "percentage": 74.56, "elapsed_time": "0:52:17", "remaining_time": "0:17:50"}
215
+ {"current_steps": 215, "total_steps": 287, "loss": 0.6214, "lr": 3.1314972661673572e-06, "epoch": 0.7471763683753258, "percentage": 74.91, "elapsed_time": "0:52:32", "remaining_time": "0:17:35"}
216
+ {"current_steps": 216, "total_steps": 287, "loss": 0.5561, "lr": 3.0498042658411276e-06, "epoch": 0.7506516072980017, "percentage": 75.26, "elapsed_time": "0:52:49", "remaining_time": "0:17:21"}
217
+ {"current_steps": 217, "total_steps": 287, "loss": 0.5698, "lr": 2.9689988354181742e-06, "epoch": 0.7541268462206777, "percentage": 75.61, "elapsed_time": "0:53:04", "remaining_time": "0:17:07"}
218
+ {"current_steps": 218, "total_steps": 287, "loss": 0.5478, "lr": 2.8890912940996784e-06, "epoch": 0.7576020851433536, "percentage": 75.96, "elapsed_time": "0:53:19", "remaining_time": "0:16:52"}
219
+ {"current_steps": 219, "total_steps": 287, "loss": 0.5637, "lr": 2.8100918464225304e-06, "epoch": 0.7610773240660296, "percentage": 76.31, "elapsed_time": "0:53:33", "remaining_time": "0:16:37"}
220
+ {"current_steps": 220, "total_steps": 287, "loss": 0.5674, "lr": 2.7320105809561415e-06, "epoch": 0.7645525629887054, "percentage": 76.66, "elapsed_time": "0:53:49", "remaining_time": "0:16:23"}
221
+ {"current_steps": 221, "total_steps": 287, "loss": 0.5863, "lr": 2.654857469014113e-06, "epoch": 0.7680278019113814, "percentage": 77.0, "elapsed_time": "0:54:04", "remaining_time": "0:16:08"}
222
+ {"current_steps": 222, "total_steps": 287, "loss": 0.573, "lr": 2.5786423633808487e-06, "epoch": 0.7715030408340573, "percentage": 77.35, "elapsed_time": "0:54:21", "remaining_time": "0:15:54"}
223
+ {"current_steps": 223, "total_steps": 287, "loss": 0.5594, "lr": 2.5033749970533015e-06, "epoch": 0.7749782797567333, "percentage": 77.7, "elapsed_time": "0:54:35", "remaining_time": "0:15:40"}
224
+ {"current_steps": 224, "total_steps": 287, "loss": 0.5937, "lr": 2.4290649819980404e-06, "epoch": 0.7784535186794093, "percentage": 78.05, "elapsed_time": "0:54:52", "remaining_time": "0:15:26"}
225
+ {"current_steps": 225, "total_steps": 287, "loss": 0.5412, "lr": 2.3557218079237608e-06, "epoch": 0.7819287576020851, "percentage": 78.4, "elapsed_time": "0:55:07", "remaining_time": "0:15:11"}
226
+ {"current_steps": 226, "total_steps": 287, "loss": 0.5655, "lr": 2.283354841069403e-06, "epoch": 0.7854039965247611, "percentage": 78.75, "elapsed_time": "0:55:20", "remaining_time": "0:14:56"}
227
+ {"current_steps": 227, "total_steps": 287, "loss": 0.5258, "lr": 2.211973323008041e-06, "epoch": 0.788879235447437, "percentage": 79.09, "elapsed_time": "0:55:34", "remaining_time": "0:14:41"}
228
+ {"current_steps": 228, "total_steps": 287, "loss": 0.5538, "lr": 2.1415863694666973e-06, "epoch": 0.792354474370113, "percentage": 79.44, "elapsed_time": "0:55:50", "remaining_time": "0:14:26"}
229
+ {"current_steps": 229, "total_steps": 287, "loss": 0.5556, "lr": 2.072202969162234e-06, "epoch": 0.7958297132927888, "percentage": 79.79, "elapsed_time": "0:56:03", "remaining_time": "0:14:11"}
230
+ {"current_steps": 230, "total_steps": 287, "loss": 0.597, "lr": 2.0038319826534312e-06, "epoch": 0.7993049522154648, "percentage": 80.14, "elapsed_time": "0:56:17", "remaining_time": "0:13:57"}
231
+ {"current_steps": 231, "total_steps": 287, "loss": 0.5645, "lr": 1.936482141209486e-06, "epoch": 0.8027801911381407, "percentage": 80.49, "elapsed_time": "0:56:33", "remaining_time": "0:13:42"}
232
+ {"current_steps": 232, "total_steps": 287, "loss": 0.5281, "lr": 1.870162045694971e-06, "epoch": 0.8062554300608167, "percentage": 80.84, "elapsed_time": "0:56:47", "remaining_time": "0:13:27"}
233
+ {"current_steps": 233, "total_steps": 287, "loss": 0.5774, "lr": 1.8048801654714687e-06, "epoch": 0.8097306689834927, "percentage": 81.18, "elapsed_time": "0:57:02", "remaining_time": "0:13:13"}
234
+ {"current_steps": 234, "total_steps": 287, "loss": 0.6053, "lr": 1.7406448373160024e-06, "epoch": 0.8132059079061685, "percentage": 81.53, "elapsed_time": "0:57:18", "remaining_time": "0:12:58"}
235
+ {"current_steps": 235, "total_steps": 287, "loss": 0.5125, "lr": 1.6774642643563955e-06, "epoch": 0.8166811468288445, "percentage": 81.88, "elapsed_time": "0:57:34", "remaining_time": "0:12:44"}
236
+ {"current_steps": 236, "total_steps": 287, "loss": 0.5873, "lr": 1.615346515023698e-06, "epoch": 0.8201563857515204, "percentage": 82.23, "elapsed_time": "0:57:49", "remaining_time": "0:12:29"}
237
+ {"current_steps": 237, "total_steps": 287, "loss": 0.5979, "lr": 1.5542995220217961e-06, "epoch": 0.8236316246741964, "percentage": 82.58, "elapsed_time": "0:58:05", "remaining_time": "0:12:15"}
238
+ {"current_steps": 238, "total_steps": 287, "loss": 0.6156, "lr": 1.4943310813144006e-06, "epoch": 0.8271068635968722, "percentage": 82.93, "elapsed_time": "0:58:18", "remaining_time": "0:12:00"}
239
+ {"current_steps": 239, "total_steps": 287, "loss": 0.5689, "lr": 1.4354488511294418e-06, "epoch": 0.8305821025195482, "percentage": 83.28, "elapsed_time": "0:58:34", "remaining_time": "0:11:45"}
240
+ {"current_steps": 240, "total_steps": 287, "loss": 0.5397, "lr": 1.3776603509810938e-06, "epoch": 0.8340573414422241, "percentage": 83.62, "elapsed_time": "0:58:48", "remaining_time": "0:11:31"}
241
+ {"current_steps": 241, "total_steps": 287, "loss": 0.542, "lr": 1.3209729607095022e-06, "epoch": 0.8375325803649001, "percentage": 83.97, "elapsed_time": "0:59:02", "remaining_time": "0:11:16"}
242
+ {"current_steps": 242, "total_steps": 287, "loss": 0.5886, "lr": 1.2653939195383448e-06, "epoch": 0.8410078192875761, "percentage": 84.32, "elapsed_time": "0:59:17", "remaining_time": "0:11:01"}
243
+ {"current_steps": 243, "total_steps": 287, "loss": 0.5893, "lr": 1.2109303251503434e-06, "epoch": 0.8444830582102519, "percentage": 84.67, "elapsed_time": "0:59:32", "remaining_time": "0:10:46"}
244
+ {"current_steps": 244, "total_steps": 287, "loss": 0.5728, "lr": 1.1575891327808664e-06, "epoch": 0.8479582971329279, "percentage": 85.02, "elapsed_time": "0:59:47", "remaining_time": "0:10:32"}
245
+ {"current_steps": 245, "total_steps": 287, "loss": 0.5335, "lr": 1.1053771543297198e-06, "epoch": 0.8514335360556038, "percentage": 85.37, "elapsed_time": "1:00:02", "remaining_time": "0:10:17"}
246
+ {"current_steps": 246, "total_steps": 287, "loss": 0.5696, "lr": 1.0543010574912305e-06, "epoch": 0.8549087749782798, "percentage": 85.71, "elapsed_time": "1:00:16", "remaining_time": "0:10:02"}
247
+ {"current_steps": 247, "total_steps": 287, "loss": 0.5974, "lr": 1.0043673649027519e-06, "epoch": 0.8583840139009556, "percentage": 86.06, "elapsed_time": "1:00:30", "remaining_time": "0:09:47"}
248
+ {"current_steps": 248, "total_steps": 287, "loss": 0.5984, "lr": 9.555824533117064e-07, "epoch": 0.8618592528236316, "percentage": 86.41, "elapsed_time": "1:00:43", "remaining_time": "0:09:33"}
249
+ {"current_steps": 249, "total_steps": 287, "loss": 0.5463, "lr": 9.079525527612321e-07, "epoch": 0.8653344917463076, "percentage": 86.76, "elapsed_time": "1:00:57", "remaining_time": "0:09:18"}
250
+ {"current_steps": 250, "total_steps": 287, "loss": 0.5831, "lr": 8.614837457945868e-07, "epoch": 0.8688097306689835, "percentage": 87.11, "elapsed_time": "1:01:11", "remaining_time": "0:09:03"}
251
+ {"current_steps": 251, "total_steps": 287, "loss": 0.6336, "lr": 8.161819666783888e-07, "epoch": 0.8722849695916595, "percentage": 87.46, "elapsed_time": "1:01:26", "remaining_time": "0:08:48"}
252
+ {"current_steps": 252, "total_steps": 287, "loss": 0.5792, "lr": 7.720530006447735e-07, "epoch": 0.8757602085143353, "percentage": 87.8, "elapsed_time": "1:01:40", "remaining_time": "0:08:34"}
253
+ {"current_steps": 253, "total_steps": 287, "loss": 0.5374, "lr": 7.291024831525961e-07, "epoch": 0.8792354474370113, "percentage": 88.15, "elapsed_time": "1:01:58", "remaining_time": "0:08:19"}
254
+ {"current_steps": 254, "total_steps": 287, "loss": 0.5319, "lr": 6.87335899167767e-07, "epoch": 0.8827106863596872, "percentage": 88.5, "elapsed_time": "1:02:13", "remaining_time": "0:08:05"}
255
+ {"current_steps": 255, "total_steps": 287, "loss": 0.6334, "lr": 6.467585824627886e-07, "epoch": 0.8861859252823632, "percentage": 88.85, "elapsed_time": "1:02:26", "remaining_time": "0:07:50"}
256
+ {"current_steps": 256, "total_steps": 287, "loss": 0.5404, "lr": 6.073757149356185e-07, "epoch": 0.889661164205039, "percentage": 89.2, "elapsed_time": "1:02:40", "remaining_time": "0:07:35"}
257
+ {"current_steps": 257, "total_steps": 287, "loss": 0.553, "lr": 5.691923259479093e-07, "epoch": 0.893136403127715, "percentage": 89.55, "elapsed_time": "1:02:56", "remaining_time": "0:07:20"}
258
+ {"current_steps": 258, "total_steps": 287, "loss": 0.5835, "lr": 5.322132916827483e-07, "epoch": 0.896611642050391, "percentage": 89.9, "elapsed_time": "1:03:11", "remaining_time": "0:07:06"}
259
+ {"current_steps": 259, "total_steps": 287, "loss": 0.6004, "lr": 4.964433345219354e-07, "epoch": 0.9000868809730669, "percentage": 90.24, "elapsed_time": "1:03:29", "remaining_time": "0:06:51"}
260
+ {"current_steps": 260, "total_steps": 287, "loss": 0.5684, "lr": 4.6188702244292614e-07, "epoch": 0.9035621198957429, "percentage": 90.59, "elapsed_time": "1:03:44", "remaining_time": "0:06:37"}
261
+ {"current_steps": 261, "total_steps": 287, "loss": 0.5311, "lr": 4.285487684354772e-07, "epoch": 0.9070373588184187, "percentage": 90.94, "elapsed_time": "1:03:59", "remaining_time": "0:06:22"}
262
+ {"current_steps": 262, "total_steps": 287, "loss": 0.5627, "lr": 3.96432829938086e-07, "epoch": 0.9105125977410947, "percentage": 91.29, "elapsed_time": "1:04:13", "remaining_time": "0:06:07"}
263
+ {"current_steps": 263, "total_steps": 287, "loss": 0.5249, "lr": 3.6554330829429716e-07, "epoch": 0.9139878366637706, "percentage": 91.64, "elapsed_time": "1:04:28", "remaining_time": "0:05:53"}
264
+ {"current_steps": 264, "total_steps": 287, "loss": 0.5257, "lr": 3.3588414822895097e-07, "epoch": 0.9174630755864466, "percentage": 91.99, "elapsed_time": "1:04:44", "remaining_time": "0:05:38"}
265
+ {"current_steps": 265, "total_steps": 287, "loss": 0.5328, "lr": 3.0745913734441357e-07, "epoch": 0.9209383145091226, "percentage": 92.33, "elapsed_time": "1:04:58", "remaining_time": "0:05:23"}
266
+ {"current_steps": 266, "total_steps": 287, "loss": 0.5431, "lr": 2.8027190563689745e-07, "epoch": 0.9244135534317984, "percentage": 92.68, "elapsed_time": "1:05:13", "remaining_time": "0:05:08"}
267
+ {"current_steps": 267, "total_steps": 287, "loss": 0.5794, "lr": 2.5432592503288e-07, "epoch": 0.9278887923544744, "percentage": 93.03, "elapsed_time": "1:05:27", "remaining_time": "0:04:54"}
268
+ {"current_steps": 268, "total_steps": 287, "loss": 0.5434, "lr": 2.2962450894573606e-07, "epoch": 0.9313640312771503, "percentage": 93.38, "elapsed_time": "1:05:41", "remaining_time": "0:04:39"}
269
+ {"current_steps": 269, "total_steps": 287, "loss": 0.5718, "lr": 2.0617081185259512e-07, "epoch": 0.9348392701998263, "percentage": 93.73, "elapsed_time": "1:05:54", "remaining_time": "0:04:24"}
270
+ {"current_steps": 270, "total_steps": 287, "loss": 0.5553, "lr": 1.8396782889150144e-07, "epoch": 0.9383145091225021, "percentage": 94.08, "elapsed_time": "1:06:08", "remaining_time": "0:04:09"}
271
+ {"current_steps": 271, "total_steps": 287, "loss": 0.551, "lr": 1.630183954789233e-07, "epoch": 0.9417897480451781, "percentage": 94.43, "elapsed_time": "1:06:27", "remaining_time": "0:03:55"}
272
+ {"current_steps": 272, "total_steps": 287, "loss": 0.5113, "lr": 1.4332518694765708e-07, "epoch": 0.945264986967854, "percentage": 94.77, "elapsed_time": "1:06:43", "remaining_time": "0:03:40"}
273
+ {"current_steps": 273, "total_steps": 287, "loss": 0.587, "lr": 1.2489071820517394e-07, "epoch": 0.94874022589053, "percentage": 95.12, "elapsed_time": "1:07:00", "remaining_time": "0:03:26"}
274
+ {"current_steps": 274, "total_steps": 287, "loss": 0.5273, "lr": 1.0771734341246121e-07, "epoch": 0.952215464813206, "percentage": 95.47, "elapsed_time": "1:07:17", "remaining_time": "0:03:11"}
275
+ {"current_steps": 275, "total_steps": 287, "loss": 0.5598, "lr": 9.180725568338045e-08, "epoch": 0.9556907037358818, "percentage": 95.82, "elapsed_time": "1:07:33", "remaining_time": "0:02:56"}
276
+ {"current_steps": 276, "total_steps": 287, "loss": 0.5608, "lr": 7.716248680459726e-08, "epoch": 0.9591659426585578, "percentage": 96.17, "elapsed_time": "1:07:47", "remaining_time": "0:02:42"}
277
+ {"current_steps": 277, "total_steps": 287, "loss": 0.5477, "lr": 6.378490697611761e-08, "epoch": 0.9626411815812337, "percentage": 96.52, "elapsed_time": "1:08:01", "remaining_time": "0:02:27"}
278
+ {"current_steps": 278, "total_steps": 287, "loss": 0.5014, "lr": 5.1676224572452246e-08, "epoch": 0.9661164205039097, "percentage": 96.86, "elapsed_time": "1:08:16", "remaining_time": "0:02:12"}
279
+ {"current_steps": 279, "total_steps": 287, "loss": 0.5899, "lr": 4.083798592444899e-08, "epoch": 0.9695916594265855, "percentage": 97.21, "elapsed_time": "1:08:30", "remaining_time": "0:01:57"}
280
+ {"current_steps": 280, "total_steps": 287, "loss": 0.5642, "lr": 3.127157512182288e-08, "epoch": 0.9730668983492615, "percentage": 97.56, "elapsed_time": "1:08:44", "remaining_time": "0:01:43"}
281
+ {"current_steps": 281, "total_steps": 287, "loss": 0.5448, "lr": 2.2978213836400974e-08, "epoch": 0.9765421372719374, "percentage": 97.91, "elapsed_time": "1:08:59", "remaining_time": "0:01:28"}
282
+ {"current_steps": 282, "total_steps": 287, "loss": 0.5947, "lr": 1.5958961166104847e-08, "epoch": 0.9800173761946134, "percentage": 98.26, "elapsed_time": "1:09:13", "remaining_time": "0:01:13"}
283
+ {"current_steps": 283, "total_steps": 287, "loss": 0.5925, "lr": 1.0214713499706596e-08, "epoch": 0.9834926151172894, "percentage": 98.61, "elapsed_time": "1:09:27", "remaining_time": "0:00:58"}
284
+ {"current_steps": 284, "total_steps": 287, "loss": 0.6126, "lr": 5.7462044023515186e-09, "epoch": 0.9869678540399652, "percentage": 98.95, "elapsed_time": "1:09:41", "remaining_time": "0:00:44"}
285
+ {"current_steps": 285, "total_steps": 287, "loss": 0.5529, "lr": 2.5540045218819256e-09, "epoch": 0.9904430929626412, "percentage": 99.3, "elapsed_time": "1:09:54", "remaining_time": "0:00:29"}
286
+ {"current_steps": 286, "total_steps": 287, "loss": 0.5456, "lr": 6.385215159565583e-10, "epoch": 0.9939183318853171, "percentage": 99.65, "elapsed_time": "1:10:10", "remaining_time": "0:00:14"}
287
+ {"current_steps": 287, "total_steps": 287, "loss": 0.5303, "lr": 0.0, "epoch": 0.9973935708079931, "percentage": 100.0, "elapsed_time": "1:10:25", "remaining_time": "0:00:00"}
288
+ {"current_steps": 287, "total_steps": 287, "epoch": 0.9973935708079931, "percentage": 100.0, "elapsed_time": "1:14:29", "remaining_time": "0:00:00"}
trainer_state.json ADDED
@@ -0,0 +1,2051 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 0.9973935708079931,
5
+ "eval_steps": 500,
6
+ "global_step": 287,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.0034752389226759338,
13
+ "grad_norm": 13.863444328308105,
14
+ "learning_rate": 2.222222222222222e-06,
15
+ "loss": 0.8359,
16
+ "step": 1
17
+ },
18
+ {
19
+ "epoch": 0.0069504778453518675,
20
+ "grad_norm": 12.374430656433105,
21
+ "learning_rate": 4.444444444444444e-06,
22
+ "loss": 0.8862,
23
+ "step": 2
24
+ },
25
+ {
26
+ "epoch": 0.010425716768027803,
27
+ "grad_norm": 11.986786842346191,
28
+ "learning_rate": 6.666666666666667e-06,
29
+ "loss": 0.7899,
30
+ "step": 3
31
+ },
32
+ {
33
+ "epoch": 0.013900955690703735,
34
+ "grad_norm": 6.093581199645996,
35
+ "learning_rate": 8.888888888888888e-06,
36
+ "loss": 0.7342,
37
+ "step": 4
38
+ },
39
+ {
40
+ "epoch": 0.01737619461337967,
41
+ "grad_norm": 2.471663475036621,
42
+ "learning_rate": 1.1111111111111113e-05,
43
+ "loss": 0.6759,
44
+ "step": 5
45
+ },
46
+ {
47
+ "epoch": 0.020851433536055605,
48
+ "grad_norm": 2.6024749279022217,
49
+ "learning_rate": 1.3333333333333333e-05,
50
+ "loss": 0.6608,
51
+ "step": 6
52
+ },
53
+ {
54
+ "epoch": 0.02432667245873154,
55
+ "grad_norm": 2.211730718612671,
56
+ "learning_rate": 1.555555555555556e-05,
57
+ "loss": 0.5929,
58
+ "step": 7
59
+ },
60
+ {
61
+ "epoch": 0.02780191138140747,
62
+ "grad_norm": 2.3514232635498047,
63
+ "learning_rate": 1.7777777777777777e-05,
64
+ "loss": 0.6591,
65
+ "step": 8
66
+ },
67
+ {
68
+ "epoch": 0.03127715030408341,
69
+ "grad_norm": 2.4454445838928223,
70
+ "learning_rate": 2e-05,
71
+ "loss": 0.6129,
72
+ "step": 9
73
+ },
74
+ {
75
+ "epoch": 0.03475238922675934,
76
+ "grad_norm": 3.566322088241577,
77
+ "learning_rate": 1.9999361478484043e-05,
78
+ "loss": 0.6247,
79
+ "step": 10
80
+ },
81
+ {
82
+ "epoch": 0.038227628149435276,
83
+ "grad_norm": 2.7100212574005127,
84
+ "learning_rate": 1.999744599547812e-05,
85
+ "loss": 0.5985,
86
+ "step": 11
87
+ },
88
+ {
89
+ "epoch": 0.04170286707211121,
90
+ "grad_norm": 2.569108247756958,
91
+ "learning_rate": 1.999425379559765e-05,
92
+ "loss": 0.6277,
93
+ "step": 12
94
+ },
95
+ {
96
+ "epoch": 0.045178105994787145,
97
+ "grad_norm": 2.111241102218628,
98
+ "learning_rate": 1.9989785286500294e-05,
99
+ "loss": 0.6268,
100
+ "step": 13
101
+ },
102
+ {
103
+ "epoch": 0.04865334491746308,
104
+ "grad_norm": 2.4817757606506348,
105
+ "learning_rate": 1.99840410388339e-05,
106
+ "loss": 0.6465,
107
+ "step": 14
108
+ },
109
+ {
110
+ "epoch": 0.052128583840139006,
111
+ "grad_norm": 1.7389640808105469,
112
+ "learning_rate": 1.99770217861636e-05,
113
+ "loss": 0.6048,
114
+ "step": 15
115
+ },
116
+ {
117
+ "epoch": 0.05560382276281494,
118
+ "grad_norm": 1.7822411060333252,
119
+ "learning_rate": 1.9968728424878178e-05,
120
+ "loss": 0.6343,
121
+ "step": 16
122
+ },
123
+ {
124
+ "epoch": 0.059079061685490875,
125
+ "grad_norm": 1.7938050031661987,
126
+ "learning_rate": 1.9959162014075553e-05,
127
+ "loss": 0.6308,
128
+ "step": 17
129
+ },
130
+ {
131
+ "epoch": 0.06255430060816682,
132
+ "grad_norm": 1.7255632877349854,
133
+ "learning_rate": 1.994832377542755e-05,
134
+ "loss": 0.6382,
135
+ "step": 18
136
+ },
137
+ {
138
+ "epoch": 0.06602953953084274,
139
+ "grad_norm": 1.6459022760391235,
140
+ "learning_rate": 1.9936215093023884e-05,
141
+ "loss": 0.5864,
142
+ "step": 19
143
+ },
144
+ {
145
+ "epoch": 0.06950477845351868,
146
+ "grad_norm": 1.5717964172363281,
147
+ "learning_rate": 1.9922837513195406e-05,
148
+ "loss": 0.6014,
149
+ "step": 20
150
+ },
151
+ {
152
+ "epoch": 0.07298001737619461,
153
+ "grad_norm": 1.4626662731170654,
154
+ "learning_rate": 1.990819274431662e-05,
155
+ "loss": 0.5919,
156
+ "step": 21
157
+ },
158
+ {
159
+ "epoch": 0.07645525629887055,
160
+ "grad_norm": 1.5188833475112915,
161
+ "learning_rate": 1.989228265658754e-05,
162
+ "loss": 0.6285,
163
+ "step": 22
164
+ },
165
+ {
166
+ "epoch": 0.07993049522154648,
167
+ "grad_norm": 1.4063705205917358,
168
+ "learning_rate": 1.9875109281794828e-05,
169
+ "loss": 0.6498,
170
+ "step": 23
171
+ },
172
+ {
173
+ "epoch": 0.08340573414422242,
174
+ "grad_norm": 1.5133353471755981,
175
+ "learning_rate": 1.9856674813052345e-05,
176
+ "loss": 0.6267,
177
+ "step": 24
178
+ },
179
+ {
180
+ "epoch": 0.08688097306689835,
181
+ "grad_norm": 1.294826865196228,
182
+ "learning_rate": 1.9836981604521077e-05,
183
+ "loss": 0.6798,
184
+ "step": 25
185
+ },
186
+ {
187
+ "epoch": 0.09035621198957429,
188
+ "grad_norm": 1.4135065078735352,
189
+ "learning_rate": 1.98160321711085e-05,
190
+ "loss": 0.6478,
191
+ "step": 26
192
+ },
193
+ {
194
+ "epoch": 0.09383145091225022,
195
+ "grad_norm": 1.3046231269836426,
196
+ "learning_rate": 1.9793829188147406e-05,
197
+ "loss": 0.6136,
198
+ "step": 27
199
+ },
200
+ {
201
+ "epoch": 0.09730668983492616,
202
+ "grad_norm": 1.2951562404632568,
203
+ "learning_rate": 1.9770375491054264e-05,
204
+ "loss": 0.6365,
205
+ "step": 28
206
+ },
207
+ {
208
+ "epoch": 0.10078192875760209,
209
+ "grad_norm": 1.2141485214233398,
210
+ "learning_rate": 1.974567407496712e-05,
211
+ "loss": 0.6168,
212
+ "step": 29
213
+ },
214
+ {
215
+ "epoch": 0.10425716768027801,
216
+ "grad_norm": 1.267811894416809,
217
+ "learning_rate": 1.9719728094363103e-05,
218
+ "loss": 0.6212,
219
+ "step": 30
220
+ },
221
+ {
222
+ "epoch": 0.10773240660295395,
223
+ "grad_norm": 1.3066190481185913,
224
+ "learning_rate": 1.9692540862655587e-05,
225
+ "loss": 0.6246,
226
+ "step": 31
227
+ },
228
+ {
229
+ "epoch": 0.11120764552562988,
230
+ "grad_norm": 1.3221654891967773,
231
+ "learning_rate": 1.966411585177105e-05,
232
+ "loss": 0.585,
233
+ "step": 32
234
+ },
235
+ {
236
+ "epoch": 0.11468288444830582,
237
+ "grad_norm": 1.2844849824905396,
238
+ "learning_rate": 1.9634456691705705e-05,
239
+ "loss": 0.6416,
240
+ "step": 33
241
+ },
242
+ {
243
+ "epoch": 0.11815812337098175,
244
+ "grad_norm": 1.2656630277633667,
245
+ "learning_rate": 1.9603567170061918e-05,
246
+ "loss": 0.6112,
247
+ "step": 34
248
+ },
249
+ {
250
+ "epoch": 0.12163336229365769,
251
+ "grad_norm": 1.2453721761703491,
252
+ "learning_rate": 1.9571451231564523e-05,
253
+ "loss": 0.6193,
254
+ "step": 35
255
+ },
256
+ {
257
+ "epoch": 0.12510860121633363,
258
+ "grad_norm": 1.3584957122802734,
259
+ "learning_rate": 1.9538112977557077e-05,
260
+ "loss": 0.661,
261
+ "step": 36
262
+ },
263
+ {
264
+ "epoch": 0.12858384013900956,
265
+ "grad_norm": 1.2529661655426025,
266
+ "learning_rate": 1.9503556665478066e-05,
267
+ "loss": 0.626,
268
+ "step": 37
269
+ },
270
+ {
271
+ "epoch": 0.13205907906168549,
272
+ "grad_norm": 1.168838381767273,
273
+ "learning_rate": 1.9467786708317257e-05,
274
+ "loss": 0.6553,
275
+ "step": 38
276
+ },
277
+ {
278
+ "epoch": 0.1355343179843614,
279
+ "grad_norm": 1.266099452972412,
280
+ "learning_rate": 1.9430807674052092e-05,
281
+ "loss": 0.6105,
282
+ "step": 39
283
+ },
284
+ {
285
+ "epoch": 0.13900955690703737,
286
+ "grad_norm": 1.2240427732467651,
287
+ "learning_rate": 1.939262428506438e-05,
288
+ "loss": 0.6362,
289
+ "step": 40
290
+ },
291
+ {
292
+ "epoch": 0.1424847958297133,
293
+ "grad_norm": 1.181288480758667,
294
+ "learning_rate": 1.9353241417537216e-05,
295
+ "loss": 0.639,
296
+ "step": 41
297
+ },
298
+ {
299
+ "epoch": 0.14596003475238922,
300
+ "grad_norm": 1.1083927154541016,
301
+ "learning_rate": 1.9312664100832236e-05,
302
+ "loss": 0.6421,
303
+ "step": 42
304
+ },
305
+ {
306
+ "epoch": 0.14943527367506515,
307
+ "grad_norm": 1.2228623628616333,
308
+ "learning_rate": 1.9270897516847406e-05,
309
+ "loss": 0.5897,
310
+ "step": 43
311
+ },
312
+ {
313
+ "epoch": 0.1529105125977411,
314
+ "grad_norm": 1.215945839881897,
315
+ "learning_rate": 1.9227946999355226e-05,
316
+ "loss": 0.6122,
317
+ "step": 44
318
+ },
319
+ {
320
+ "epoch": 0.15638575152041703,
321
+ "grad_norm": 1.1623311042785645,
322
+ "learning_rate": 1.9183818033321612e-05,
323
+ "loss": 0.5546,
324
+ "step": 45
325
+ },
326
+ {
327
+ "epoch": 0.15986099044309296,
328
+ "grad_norm": 1.3293700218200684,
329
+ "learning_rate": 1.9138516254205416e-05,
330
+ "loss": 0.6268,
331
+ "step": 46
332
+ },
333
+ {
334
+ "epoch": 0.1633362293657689,
335
+ "grad_norm": 1.1984280347824097,
336
+ "learning_rate": 1.9092047447238775e-05,
337
+ "loss": 0.6081,
338
+ "step": 47
339
+ },
340
+ {
341
+ "epoch": 0.16681146828844484,
342
+ "grad_norm": 1.1898068189620972,
343
+ "learning_rate": 1.9044417546688295e-05,
344
+ "loss": 0.6007,
345
+ "step": 48
346
+ },
347
+ {
348
+ "epoch": 0.17028670721112077,
349
+ "grad_norm": 1.2403992414474487,
350
+ "learning_rate": 1.899563263509725e-05,
351
+ "loss": 0.6219,
352
+ "step": 49
353
+ },
354
+ {
355
+ "epoch": 0.1737619461337967,
356
+ "grad_norm": 1.3231101036071777,
357
+ "learning_rate": 1.894569894250877e-05,
358
+ "loss": 0.5834,
359
+ "step": 50
360
+ },
361
+ {
362
+ "epoch": 0.17723718505647262,
363
+ "grad_norm": 1.3285619020462036,
364
+ "learning_rate": 1.8894622845670282e-05,
365
+ "loss": 0.6568,
366
+ "step": 51
367
+ },
368
+ {
369
+ "epoch": 0.18071242397914858,
370
+ "grad_norm": 1.1555180549621582,
371
+ "learning_rate": 1.8842410867219137e-05,
372
+ "loss": 0.6269,
373
+ "step": 52
374
+ },
375
+ {
376
+ "epoch": 0.1841876629018245,
377
+ "grad_norm": 1.1796412467956543,
378
+ "learning_rate": 1.878906967484966e-05,
379
+ "loss": 0.5973,
380
+ "step": 53
381
+ },
382
+ {
383
+ "epoch": 0.18766290182450043,
384
+ "grad_norm": 1.144237756729126,
385
+ "learning_rate": 1.8734606080461657e-05,
386
+ "loss": 0.6367,
387
+ "step": 54
388
+ },
389
+ {
390
+ "epoch": 0.19113814074717636,
391
+ "grad_norm": 1.1937980651855469,
392
+ "learning_rate": 1.86790270392905e-05,
393
+ "loss": 0.6006,
394
+ "step": 55
395
+ },
396
+ {
397
+ "epoch": 0.19461337966985232,
398
+ "grad_norm": 1.0895384550094604,
399
+ "learning_rate": 1.8622339649018907e-05,
400
+ "loss": 0.579,
401
+ "step": 56
402
+ },
403
+ {
404
+ "epoch": 0.19808861859252824,
405
+ "grad_norm": 1.1548895835876465,
406
+ "learning_rate": 1.856455114887056e-05,
407
+ "loss": 0.5521,
408
+ "step": 57
409
+ },
410
+ {
411
+ "epoch": 0.20156385751520417,
412
+ "grad_norm": 1.0904297828674316,
413
+ "learning_rate": 1.8505668918685603e-05,
414
+ "loss": 0.6222,
415
+ "step": 58
416
+ },
417
+ {
418
+ "epoch": 0.2050390964378801,
419
+ "grad_norm": 1.2059494256973267,
420
+ "learning_rate": 1.8445700477978207e-05,
421
+ "loss": 0.6631,
422
+ "step": 59
423
+ },
424
+ {
425
+ "epoch": 0.20851433536055602,
426
+ "grad_norm": 1.1830602884292603,
427
+ "learning_rate": 1.8384653484976305e-05,
428
+ "loss": 0.5963,
429
+ "step": 60
430
+ },
431
+ {
432
+ "epoch": 0.21198957428323198,
433
+ "grad_norm": 1.2046791315078735,
434
+ "learning_rate": 1.8322535735643604e-05,
435
+ "loss": 0.5943,
436
+ "step": 61
437
+ },
438
+ {
439
+ "epoch": 0.2154648132059079,
440
+ "grad_norm": 1.1545571088790894,
441
+ "learning_rate": 1.8259355162684e-05,
442
+ "loss": 0.6301,
443
+ "step": 62
444
+ },
445
+ {
446
+ "epoch": 0.21894005212858383,
447
+ "grad_norm": 1.0760880708694458,
448
+ "learning_rate": 1.8195119834528535e-05,
449
+ "loss": 0.6366,
450
+ "step": 63
451
+ },
452
+ {
453
+ "epoch": 0.22241529105125976,
454
+ "grad_norm": 1.2411205768585205,
455
+ "learning_rate": 1.8129837954305033e-05,
456
+ "loss": 0.6156,
457
+ "step": 64
458
+ },
459
+ {
460
+ "epoch": 0.22589052997393572,
461
+ "grad_norm": 1.1241486072540283,
462
+ "learning_rate": 1.8063517858790517e-05,
463
+ "loss": 0.608,
464
+ "step": 65
465
+ },
466
+ {
467
+ "epoch": 0.22936576889661164,
468
+ "grad_norm": 1.0839852094650269,
469
+ "learning_rate": 1.799616801734657e-05,
470
+ "loss": 0.6334,
471
+ "step": 66
472
+ },
473
+ {
474
+ "epoch": 0.23284100781928757,
475
+ "grad_norm": 1.125570297241211,
476
+ "learning_rate": 1.792779703083777e-05,
477
+ "loss": 0.6139,
478
+ "step": 67
479
+ },
480
+ {
481
+ "epoch": 0.2363162467419635,
482
+ "grad_norm": 1.1417044401168823,
483
+ "learning_rate": 1.7858413630533305e-05,
484
+ "loss": 0.5897,
485
+ "step": 68
486
+ },
487
+ {
488
+ "epoch": 0.23979148566463945,
489
+ "grad_norm": 1.0312554836273193,
490
+ "learning_rate": 1.778802667699196e-05,
491
+ "loss": 0.606,
492
+ "step": 69
493
+ },
494
+ {
495
+ "epoch": 0.24326672458731538,
496
+ "grad_norm": 1.0954256057739258,
497
+ "learning_rate": 1.77166451589306e-05,
498
+ "loss": 0.5888,
499
+ "step": 70
500
+ },
501
+ {
502
+ "epoch": 0.2467419635099913,
503
+ "grad_norm": 1.031202793121338,
504
+ "learning_rate": 1.764427819207624e-05,
505
+ "loss": 0.6004,
506
+ "step": 71
507
+ },
508
+ {
509
+ "epoch": 0.25021720243266726,
510
+ "grad_norm": 1.1144808530807495,
511
+ "learning_rate": 1.757093501800196e-05,
512
+ "loss": 0.5699,
513
+ "step": 72
514
+ },
515
+ {
516
+ "epoch": 0.2536924413553432,
517
+ "grad_norm": 1.0327179431915283,
518
+ "learning_rate": 1.7496625002946702e-05,
519
+ "loss": 0.6051,
520
+ "step": 73
521
+ },
522
+ {
523
+ "epoch": 0.2571676802780191,
524
+ "grad_norm": 1.080093264579773,
525
+ "learning_rate": 1.7421357636619153e-05,
526
+ "loss": 0.6494,
527
+ "step": 74
528
+ },
529
+ {
530
+ "epoch": 0.26064291920069504,
531
+ "grad_norm": 1.2163845300674438,
532
+ "learning_rate": 1.734514253098589e-05,
533
+ "loss": 0.6033,
534
+ "step": 75
535
+ },
536
+ {
537
+ "epoch": 0.26411815812337097,
538
+ "grad_norm": 1.1358786821365356,
539
+ "learning_rate": 1.726798941904386e-05,
540
+ "loss": 0.596,
541
+ "step": 76
542
+ },
543
+ {
544
+ "epoch": 0.2675933970460469,
545
+ "grad_norm": 1.0965262651443481,
546
+ "learning_rate": 1.7189908153577473e-05,
547
+ "loss": 0.5669,
548
+ "step": 77
549
+ },
550
+ {
551
+ "epoch": 0.2710686359687228,
552
+ "grad_norm": 1.2162927389144897,
553
+ "learning_rate": 1.7110908705900322e-05,
554
+ "loss": 0.6133,
555
+ "step": 78
556
+ },
557
+ {
558
+ "epoch": 0.2745438748913988,
559
+ "grad_norm": 1.186356544494629,
560
+ "learning_rate": 1.7031001164581828e-05,
561
+ "loss": 0.6405,
562
+ "step": 79
563
+ },
564
+ {
565
+ "epoch": 0.27801911381407474,
566
+ "grad_norm": 1.0369867086410522,
567
+ "learning_rate": 1.6950195734158874e-05,
568
+ "loss": 0.579,
569
+ "step": 80
570
+ },
571
+ {
572
+ "epoch": 0.28149435273675066,
573
+ "grad_norm": 1.0901113748550415,
574
+ "learning_rate": 1.6868502733832647e-05,
575
+ "loss": 0.5825,
576
+ "step": 81
577
+ },
578
+ {
579
+ "epoch": 0.2849695916594266,
580
+ "grad_norm": 1.0874531269073486,
581
+ "learning_rate": 1.6785932596150827e-05,
582
+ "loss": 0.6038,
583
+ "step": 82
584
+ },
585
+ {
586
+ "epoch": 0.2884448305821025,
587
+ "grad_norm": 1.1928529739379883,
588
+ "learning_rate": 1.670249586567531e-05,
589
+ "loss": 0.5979,
590
+ "step": 83
591
+ },
592
+ {
593
+ "epoch": 0.29192006950477845,
594
+ "grad_norm": 1.0388442277908325,
595
+ "learning_rate": 1.6618203197635624e-05,
596
+ "loss": 0.5832,
597
+ "step": 84
598
+ },
599
+ {
600
+ "epoch": 0.2953953084274544,
601
+ "grad_norm": 1.2084934711456299,
602
+ "learning_rate": 1.6533065356568206e-05,
603
+ "loss": 0.5844,
604
+ "step": 85
605
+ },
606
+ {
607
+ "epoch": 0.2988705473501303,
608
+ "grad_norm": 1.223413348197937,
609
+ "learning_rate": 1.6447093214941727e-05,
610
+ "loss": 0.619,
611
+ "step": 86
612
+ },
613
+ {
614
+ "epoch": 0.3023457862728063,
615
+ "grad_norm": 1.0778778791427612,
616
+ "learning_rate": 1.636029775176862e-05,
617
+ "loss": 0.6573,
618
+ "step": 87
619
+ },
620
+ {
621
+ "epoch": 0.3058210251954822,
622
+ "grad_norm": 1.0900267362594604,
623
+ "learning_rate": 1.627269005120304e-05,
624
+ "loss": 0.5779,
625
+ "step": 88
626
+ },
627
+ {
628
+ "epoch": 0.30929626411815814,
629
+ "grad_norm": 1.0737788677215576,
630
+ "learning_rate": 1.618428130112533e-05,
631
+ "loss": 0.5994,
632
+ "step": 89
633
+ },
634
+ {
635
+ "epoch": 0.31277150304083406,
636
+ "grad_norm": 1.0811336040496826,
637
+ "learning_rate": 1.6095082791713322e-05,
638
+ "loss": 0.626,
639
+ "step": 90
640
+ },
641
+ {
642
+ "epoch": 0.31624674196351,
643
+ "grad_norm": 1.0799121856689453,
644
+ "learning_rate": 1.6005105914000508e-05,
645
+ "loss": 0.6313,
646
+ "step": 91
647
+ },
648
+ {
649
+ "epoch": 0.3197219808861859,
650
+ "grad_norm": 1.0824054479599,
651
+ "learning_rate": 1.5914362158421352e-05,
652
+ "loss": 0.636,
653
+ "step": 92
654
+ },
655
+ {
656
+ "epoch": 0.32319721980886185,
657
+ "grad_norm": 1.0406136512756348,
658
+ "learning_rate": 1.5822863113343934e-05,
659
+ "loss": 0.5972,
660
+ "step": 93
661
+ },
662
+ {
663
+ "epoch": 0.3266724587315378,
664
+ "grad_norm": 1.16518235206604,
665
+ "learning_rate": 1.5730620463590052e-05,
666
+ "loss": 0.5728,
667
+ "step": 94
668
+ },
669
+ {
670
+ "epoch": 0.3301476976542137,
671
+ "grad_norm": 1.0442129373550415,
672
+ "learning_rate": 1.5637645988943008e-05,
673
+ "loss": 0.6138,
674
+ "step": 95
675
+ },
676
+ {
677
+ "epoch": 0.3336229365768897,
678
+ "grad_norm": 1.1471384763717651,
679
+ "learning_rate": 1.554395156264331e-05,
680
+ "loss": 0.6123,
681
+ "step": 96
682
+ },
683
+ {
684
+ "epoch": 0.3370981754995656,
685
+ "grad_norm": 1.0176016092300415,
686
+ "learning_rate": 1.544954914987238e-05,
687
+ "loss": 0.6063,
688
+ "step": 97
689
+ },
690
+ {
691
+ "epoch": 0.34057341442224154,
692
+ "grad_norm": 1.062016487121582,
693
+ "learning_rate": 1.5354450806224553e-05,
694
+ "loss": 0.5842,
695
+ "step": 98
696
+ },
697
+ {
698
+ "epoch": 0.34404865334491747,
699
+ "grad_norm": 1.1640706062316895,
700
+ "learning_rate": 1.5258668676167548e-05,
701
+ "loss": 0.5938,
702
+ "step": 99
703
+ },
704
+ {
705
+ "epoch": 0.3475238922675934,
706
+ "grad_norm": 1.1660997867584229,
707
+ "learning_rate": 1.516221499149154e-05,
708
+ "loss": 0.6202,
709
+ "step": 100
710
+ },
711
+ {
712
+ "epoch": 0.3509991311902693,
713
+ "grad_norm": 1.156037449836731,
714
+ "learning_rate": 1.5065102069747117e-05,
715
+ "loss": 0.6216,
716
+ "step": 101
717
+ },
718
+ {
719
+ "epoch": 0.35447437011294525,
720
+ "grad_norm": 1.2295578718185425,
721
+ "learning_rate": 1.4967342312672283e-05,
722
+ "loss": 0.5649,
723
+ "step": 102
724
+ },
725
+ {
726
+ "epoch": 0.3579496090356212,
727
+ "grad_norm": 1.0619351863861084,
728
+ "learning_rate": 1.48689482046087e-05,
729
+ "loss": 0.5954,
730
+ "step": 103
731
+ },
732
+ {
733
+ "epoch": 0.36142484795829716,
734
+ "grad_norm": 1.266830325126648,
735
+ "learning_rate": 1.4769932310907372e-05,
736
+ "loss": 0.6362,
737
+ "step": 104
738
+ },
739
+ {
740
+ "epoch": 0.3649000868809731,
741
+ "grad_norm": 1.0485084056854248,
742
+ "learning_rate": 1.467030727632401e-05,
743
+ "loss": 0.5664,
744
+ "step": 105
745
+ },
746
+ {
747
+ "epoch": 0.368375325803649,
748
+ "grad_norm": 1.12933349609375,
749
+ "learning_rate": 1.4570085823404232e-05,
750
+ "loss": 0.586,
751
+ "step": 106
752
+ },
753
+ {
754
+ "epoch": 0.37185056472632494,
755
+ "grad_norm": 1.0767207145690918,
756
+ "learning_rate": 1.4469280750858854e-05,
757
+ "loss": 0.5773,
758
+ "step": 107
759
+ },
760
+ {
761
+ "epoch": 0.37532580364900087,
762
+ "grad_norm": 1.121981143951416,
763
+ "learning_rate": 1.4367904931929422e-05,
764
+ "loss": 0.585,
765
+ "step": 108
766
+ },
767
+ {
768
+ "epoch": 0.3788010425716768,
769
+ "grad_norm": 1.1495089530944824,
770
+ "learning_rate": 1.4265971312744252e-05,
771
+ "loss": 0.5698,
772
+ "step": 109
773
+ },
774
+ {
775
+ "epoch": 0.3822762814943527,
776
+ "grad_norm": 1.0745882987976074,
777
+ "learning_rate": 1.4163492910665153e-05,
778
+ "loss": 0.611,
779
+ "step": 110
780
+ },
781
+ {
782
+ "epoch": 0.38575152041702865,
783
+ "grad_norm": 1.0079902410507202,
784
+ "learning_rate": 1.4060482812625055e-05,
785
+ "loss": 0.6226,
786
+ "step": 111
787
+ },
788
+ {
789
+ "epoch": 0.38922675933970463,
790
+ "grad_norm": 1.0810552835464478,
791
+ "learning_rate": 1.395695417345675e-05,
792
+ "loss": 0.6257,
793
+ "step": 112
794
+ },
795
+ {
796
+ "epoch": 0.39270199826238056,
797
+ "grad_norm": 1.040677547454834,
798
+ "learning_rate": 1.3852920214212966e-05,
799
+ "loss": 0.5883,
800
+ "step": 113
801
+ },
802
+ {
803
+ "epoch": 0.3961772371850565,
804
+ "grad_norm": 1.0766505002975464,
805
+ "learning_rate": 1.3748394220477972e-05,
806
+ "loss": 0.5804,
807
+ "step": 114
808
+ },
809
+ {
810
+ "epoch": 0.3996524761077324,
811
+ "grad_norm": 1.0619298219680786,
812
+ "learning_rate": 1.3643389540670963e-05,
813
+ "loss": 0.6178,
814
+ "step": 115
815
+ },
816
+ {
817
+ "epoch": 0.40312771503040834,
818
+ "grad_norm": 1.019912838935852,
819
+ "learning_rate": 1.3537919584341413e-05,
820
+ "loss": 0.5959,
821
+ "step": 116
822
+ },
823
+ {
824
+ "epoch": 0.40660295395308427,
825
+ "grad_norm": 1.113372564315796,
826
+ "learning_rate": 1.3431997820456592e-05,
827
+ "loss": 0.6051,
828
+ "step": 117
829
+ },
830
+ {
831
+ "epoch": 0.4100781928757602,
832
+ "grad_norm": 1.0494154691696167,
833
+ "learning_rate": 1.3325637775681561e-05,
834
+ "loss": 0.599,
835
+ "step": 118
836
+ },
837
+ {
838
+ "epoch": 0.4135534317984361,
839
+ "grad_norm": 1.1271395683288574,
840
+ "learning_rate": 1.3218853032651719e-05,
841
+ "loss": 0.6322,
842
+ "step": 119
843
+ },
844
+ {
845
+ "epoch": 0.41702867072111205,
846
+ "grad_norm": 1.1663187742233276,
847
+ "learning_rate": 1.3111657228238263e-05,
848
+ "loss": 0.6209,
849
+ "step": 120
850
+ },
851
+ {
852
+ "epoch": 0.42050390964378803,
853
+ "grad_norm": 1.0917779207229614,
854
+ "learning_rate": 1.3004064051806712e-05,
855
+ "loss": 0.5832,
856
+ "step": 121
857
+ },
858
+ {
859
+ "epoch": 0.42397914856646396,
860
+ "grad_norm": 1.1407371759414673,
861
+ "learning_rate": 1.2896087243468673e-05,
862
+ "loss": 0.5645,
863
+ "step": 122
864
+ },
865
+ {
866
+ "epoch": 0.4274543874891399,
867
+ "grad_norm": 1.1023014783859253,
868
+ "learning_rate": 1.2787740592327232e-05,
869
+ "loss": 0.5921,
870
+ "step": 123
871
+ },
872
+ {
873
+ "epoch": 0.4309296264118158,
874
+ "grad_norm": 1.1019343137741089,
875
+ "learning_rate": 1.267903793471597e-05,
876
+ "loss": 0.5687,
877
+ "step": 124
878
+ },
879
+ {
880
+ "epoch": 0.43440486533449174,
881
+ "grad_norm": 1.0315438508987427,
882
+ "learning_rate": 1.2569993152432028e-05,
883
+ "loss": 0.5973,
884
+ "step": 125
885
+ },
886
+ {
887
+ "epoch": 0.43788010425716767,
888
+ "grad_norm": 1.1791157722473145,
889
+ "learning_rate": 1.2460620170963353e-05,
890
+ "loss": 0.6029,
891
+ "step": 126
892
+ },
893
+ {
894
+ "epoch": 0.4413553431798436,
895
+ "grad_norm": 1.1693004369735718,
896
+ "learning_rate": 1.2350932957710322e-05,
897
+ "loss": 0.5916,
898
+ "step": 127
899
+ },
900
+ {
901
+ "epoch": 0.4448305821025195,
902
+ "grad_norm": 1.023739218711853,
903
+ "learning_rate": 1.2240945520202079e-05,
904
+ "loss": 0.5557,
905
+ "step": 128
906
+ },
907
+ {
908
+ "epoch": 0.4483058210251955,
909
+ "grad_norm": 1.2074741125106812,
910
+ "learning_rate": 1.2130671904307692e-05,
911
+ "loss": 0.605,
912
+ "step": 129
913
+ },
914
+ {
915
+ "epoch": 0.45178105994787143,
916
+ "grad_norm": 1.0737248659133911,
917
+ "learning_rate": 1.202012619244243e-05,
918
+ "loss": 0.6198,
919
+ "step": 130
920
+ },
921
+ {
922
+ "epoch": 0.45525629887054736,
923
+ "grad_norm": 1.0830988883972168,
924
+ "learning_rate": 1.1909322501769407e-05,
925
+ "loss": 0.5757,
926
+ "step": 131
927
+ },
928
+ {
929
+ "epoch": 0.4587315377932233,
930
+ "grad_norm": 1.050476312637329,
931
+ "learning_rate": 1.1798274982396728e-05,
932
+ "loss": 0.5597,
933
+ "step": 132
934
+ },
935
+ {
936
+ "epoch": 0.4622067767158992,
937
+ "grad_norm": 0.9489808678627014,
938
+ "learning_rate": 1.1686997815570473e-05,
939
+ "loss": 0.5686,
940
+ "step": 133
941
+ },
942
+ {
943
+ "epoch": 0.46568201563857514,
944
+ "grad_norm": 1.009084701538086,
945
+ "learning_rate": 1.15755052118637e-05,
946
+ "loss": 0.6,
947
+ "step": 134
948
+ },
949
+ {
950
+ "epoch": 0.46915725456125107,
951
+ "grad_norm": 1.058876872062683,
952
+ "learning_rate": 1.1463811409361667e-05,
953
+ "loss": 0.5479,
954
+ "step": 135
955
+ },
956
+ {
957
+ "epoch": 0.472632493483927,
958
+ "grad_norm": 1.0262316465377808,
959
+ "learning_rate": 1.13519306718436e-05,
960
+ "loss": 0.6045,
961
+ "step": 136
962
+ },
963
+ {
964
+ "epoch": 0.476107732406603,
965
+ "grad_norm": 1.0066461563110352,
966
+ "learning_rate": 1.1239877286961123e-05,
967
+ "loss": 0.561,
968
+ "step": 137
969
+ },
970
+ {
971
+ "epoch": 0.4795829713292789,
972
+ "grad_norm": 0.9656773209571838,
973
+ "learning_rate": 1.112766556441367e-05,
974
+ "loss": 0.6139,
975
+ "step": 138
976
+ },
977
+ {
978
+ "epoch": 0.48305821025195483,
979
+ "grad_norm": 1.0848320722579956,
980
+ "learning_rate": 1.1015309834121083e-05,
981
+ "loss": 0.5811,
982
+ "step": 139
983
+ },
984
+ {
985
+ "epoch": 0.48653344917463076,
986
+ "grad_norm": 1.0625325441360474,
987
+ "learning_rate": 1.0902824444393602e-05,
988
+ "loss": 0.6299,
989
+ "step": 140
990
+ },
991
+ {
992
+ "epoch": 0.4900086880973067,
993
+ "grad_norm": 1.0536874532699585,
994
+ "learning_rate": 1.079022376009955e-05,
995
+ "loss": 0.5937,
996
+ "step": 141
997
+ },
998
+ {
999
+ "epoch": 0.4934839270199826,
1000
+ "grad_norm": 1.0022127628326416,
1001
+ "learning_rate": 1.067752216083085e-05,
1002
+ "loss": 0.5718,
1003
+ "step": 142
1004
+ },
1005
+ {
1006
+ "epoch": 0.49695916594265854,
1007
+ "grad_norm": 1.0636472702026367,
1008
+ "learning_rate": 1.05647340390667e-05,
1009
+ "loss": 0.6251,
1010
+ "step": 143
1011
+ },
1012
+ {
1013
+ "epoch": 0.5004344048653345,
1014
+ "grad_norm": 1.0569506883621216,
1015
+ "learning_rate": 1.0451873798335605e-05,
1016
+ "loss": 0.5583,
1017
+ "step": 144
1018
+ },
1019
+ {
1020
+ "epoch": 0.5039096437880104,
1021
+ "grad_norm": 1.04555344581604,
1022
+ "learning_rate": 1.0338955851375962e-05,
1023
+ "loss": 0.5893,
1024
+ "step": 145
1025
+ },
1026
+ {
1027
+ "epoch": 0.5073848827106864,
1028
+ "grad_norm": 0.9304705858230591,
1029
+ "learning_rate": 1.0225994618295507e-05,
1030
+ "loss": 0.5414,
1031
+ "step": 146
1032
+ },
1033
+ {
1034
+ "epoch": 0.5108601216333623,
1035
+ "grad_norm": 0.9779573082923889,
1036
+ "learning_rate": 1.01130045247298e-05,
1037
+ "loss": 0.5601,
1038
+ "step": 147
1039
+ },
1040
+ {
1041
+ "epoch": 0.5143353605560382,
1042
+ "grad_norm": 1.0225908756256104,
1043
+ "learning_rate": 1e-05,
1044
+ "loss": 0.65,
1045
+ "step": 148
1046
+ },
1047
+ {
1048
+ "epoch": 0.5178105994787141,
1049
+ "grad_norm": 0.9953768253326416,
1050
+ "learning_rate": 9.886995475270205e-06,
1051
+ "loss": 0.5905,
1052
+ "step": 149
1053
+ },
1054
+ {
1055
+ "epoch": 0.5212858384013901,
1056
+ "grad_norm": 1.0968619585037231,
1057
+ "learning_rate": 9.774005381704498e-06,
1058
+ "loss": 0.5995,
1059
+ "step": 150
1060
+ },
1061
+ {
1062
+ "epoch": 0.5247610773240661,
1063
+ "grad_norm": 0.9768278002738953,
1064
+ "learning_rate": 9.661044148624038e-06,
1065
+ "loss": 0.642,
1066
+ "step": 151
1067
+ },
1068
+ {
1069
+ "epoch": 0.5282363162467419,
1070
+ "grad_norm": 1.0109375715255737,
1071
+ "learning_rate": 9.548126201664398e-06,
1072
+ "loss": 0.534,
1073
+ "step": 152
1074
+ },
1075
+ {
1076
+ "epoch": 0.5317115551694179,
1077
+ "grad_norm": 1.0256866216659546,
1078
+ "learning_rate": 9.435265960933304e-06,
1079
+ "loss": 0.6327,
1080
+ "step": 153
1081
+ },
1082
+ {
1083
+ "epoch": 0.5351867940920938,
1084
+ "grad_norm": 0.9121344089508057,
1085
+ "learning_rate": 9.322477839169156e-06,
1086
+ "loss": 0.5787,
1087
+ "step": 154
1088
+ },
1089
+ {
1090
+ "epoch": 0.5386620330147698,
1091
+ "grad_norm": 0.9741325974464417,
1092
+ "learning_rate": 9.209776239900453e-06,
1093
+ "loss": 0.5954,
1094
+ "step": 155
1095
+ },
1096
+ {
1097
+ "epoch": 0.5421372719374457,
1098
+ "grad_norm": 1.0003210306167603,
1099
+ "learning_rate": 9.097175555606396e-06,
1100
+ "loss": 0.5514,
1101
+ "step": 156
1102
+ },
1103
+ {
1104
+ "epoch": 0.5456125108601216,
1105
+ "grad_norm": 1.0428141355514526,
1106
+ "learning_rate": 8.98469016587892e-06,
1107
+ "loss": 0.5798,
1108
+ "step": 157
1109
+ },
1110
+ {
1111
+ "epoch": 0.5490877497827976,
1112
+ "grad_norm": 1.0282821655273438,
1113
+ "learning_rate": 8.872334435586333e-06,
1114
+ "loss": 0.5911,
1115
+ "step": 158
1116
+ },
1117
+ {
1118
+ "epoch": 0.5525629887054735,
1119
+ "grad_norm": 0.9479502439498901,
1120
+ "learning_rate": 8.76012271303888e-06,
1121
+ "loss": 0.6158,
1122
+ "step": 159
1123
+ },
1124
+ {
1125
+ "epoch": 0.5560382276281495,
1126
+ "grad_norm": 1.0172061920166016,
1127
+ "learning_rate": 8.648069328156403e-06,
1128
+ "loss": 0.5601,
1129
+ "step": 160
1130
+ },
1131
+ {
1132
+ "epoch": 0.5595134665508253,
1133
+ "grad_norm": 1.0053855180740356,
1134
+ "learning_rate": 8.536188590638334e-06,
1135
+ "loss": 0.6152,
1136
+ "step": 161
1137
+ },
1138
+ {
1139
+ "epoch": 0.5629887054735013,
1140
+ "grad_norm": 0.974694550037384,
1141
+ "learning_rate": 8.424494788136303e-06,
1142
+ "loss": 0.5666,
1143
+ "step": 162
1144
+ },
1145
+ {
1146
+ "epoch": 0.5664639443961772,
1147
+ "grad_norm": 0.9912855625152588,
1148
+ "learning_rate": 8.313002184429529e-06,
1149
+ "loss": 0.5695,
1150
+ "step": 163
1151
+ },
1152
+ {
1153
+ "epoch": 0.5699391833188532,
1154
+ "grad_norm": 0.962709367275238,
1155
+ "learning_rate": 8.201725017603277e-06,
1156
+ "loss": 0.5357,
1157
+ "step": 164
1158
+ },
1159
+ {
1160
+ "epoch": 0.573414422241529,
1161
+ "grad_norm": 0.9394634962081909,
1162
+ "learning_rate": 8.090677498230598e-06,
1163
+ "loss": 0.564,
1164
+ "step": 165
1165
+ },
1166
+ {
1167
+ "epoch": 0.576889661164205,
1168
+ "grad_norm": 0.9721453785896301,
1169
+ "learning_rate": 7.97987380755757e-06,
1170
+ "loss": 0.5933,
1171
+ "step": 166
1172
+ },
1173
+ {
1174
+ "epoch": 0.580364900086881,
1175
+ "grad_norm": 1.0866742134094238,
1176
+ "learning_rate": 7.869328095692313e-06,
1177
+ "loss": 0.5811,
1178
+ "step": 167
1179
+ },
1180
+ {
1181
+ "epoch": 0.5838401390095569,
1182
+ "grad_norm": 0.9584195613861084,
1183
+ "learning_rate": 7.759054479797924e-06,
1184
+ "loss": 0.5816,
1185
+ "step": 168
1186
+ },
1187
+ {
1188
+ "epoch": 0.5873153779322329,
1189
+ "grad_norm": 1.0240747928619385,
1190
+ "learning_rate": 7.649067042289681e-06,
1191
+ "loss": 0.5688,
1192
+ "step": 169
1193
+ },
1194
+ {
1195
+ "epoch": 0.5907906168549087,
1196
+ "grad_norm": 1.0707347393035889,
1197
+ "learning_rate": 7.539379829036652e-06,
1198
+ "loss": 0.5823,
1199
+ "step": 170
1200
+ },
1201
+ {
1202
+ "epoch": 0.5942658557775847,
1203
+ "grad_norm": 0.9794528484344482,
1204
+ "learning_rate": 7.430006847567972e-06,
1205
+ "loss": 0.5933,
1206
+ "step": 171
1207
+ },
1208
+ {
1209
+ "epoch": 0.5977410947002606,
1210
+ "grad_norm": 1.1342881917953491,
1211
+ "learning_rate": 7.320962065284032e-06,
1212
+ "loss": 0.5611,
1213
+ "step": 172
1214
+ },
1215
+ {
1216
+ "epoch": 0.6012163336229366,
1217
+ "grad_norm": 1.0687241554260254,
1218
+ "learning_rate": 7.2122594076727705e-06,
1219
+ "loss": 0.6206,
1220
+ "step": 173
1221
+ },
1222
+ {
1223
+ "epoch": 0.6046915725456126,
1224
+ "grad_norm": 1.1404447555541992,
1225
+ "learning_rate": 7.1039127565313285e-06,
1226
+ "loss": 0.619,
1227
+ "step": 174
1228
+ },
1229
+ {
1230
+ "epoch": 0.6081668114682884,
1231
+ "grad_norm": 1.0000810623168945,
1232
+ "learning_rate": 6.995935948193294e-06,
1233
+ "loss": 0.5557,
1234
+ "step": 175
1235
+ },
1236
+ {
1237
+ "epoch": 0.6116420503909644,
1238
+ "grad_norm": 0.9445539712905884,
1239
+ "learning_rate": 6.888342771761737e-06,
1240
+ "loss": 0.5392,
1241
+ "step": 176
1242
+ },
1243
+ {
1244
+ "epoch": 0.6151172893136403,
1245
+ "grad_norm": 0.9872927069664001,
1246
+ "learning_rate": 6.781146967348283e-06,
1247
+ "loss": 0.557,
1248
+ "step": 177
1249
+ },
1250
+ {
1251
+ "epoch": 0.6185925282363163,
1252
+ "grad_norm": 1.1482657194137573,
1253
+ "learning_rate": 6.6743622243184405e-06,
1254
+ "loss": 0.6229,
1255
+ "step": 178
1256
+ },
1257
+ {
1258
+ "epoch": 0.6220677671589921,
1259
+ "grad_norm": 0.9911180138587952,
1260
+ "learning_rate": 6.568002179543409e-06,
1261
+ "loss": 0.5777,
1262
+ "step": 179
1263
+ },
1264
+ {
1265
+ "epoch": 0.6255430060816681,
1266
+ "grad_norm": 1.0723944902420044,
1267
+ "learning_rate": 6.462080415658591e-06,
1268
+ "loss": 0.5546,
1269
+ "step": 180
1270
+ },
1271
+ {
1272
+ "epoch": 0.629018245004344,
1273
+ "grad_norm": 1.0823560953140259,
1274
+ "learning_rate": 6.356610459329038e-06,
1275
+ "loss": 0.5811,
1276
+ "step": 181
1277
+ },
1278
+ {
1279
+ "epoch": 0.63249348392702,
1280
+ "grad_norm": 1.0165990591049194,
1281
+ "learning_rate": 6.251605779522032e-06,
1282
+ "loss": 0.5626,
1283
+ "step": 182
1284
+ },
1285
+ {
1286
+ "epoch": 0.635968722849696,
1287
+ "grad_norm": 0.9735214114189148,
1288
+ "learning_rate": 6.147079785787038e-06,
1289
+ "loss": 0.5326,
1290
+ "step": 183
1291
+ },
1292
+ {
1293
+ "epoch": 0.6394439617723718,
1294
+ "grad_norm": 0.993291974067688,
1295
+ "learning_rate": 6.043045826543254e-06,
1296
+ "loss": 0.5609,
1297
+ "step": 184
1298
+ },
1299
+ {
1300
+ "epoch": 0.6429192006950478,
1301
+ "grad_norm": 0.9579317569732666,
1302
+ "learning_rate": 5.93951718737495e-06,
1303
+ "loss": 0.5593,
1304
+ "step": 185
1305
+ },
1306
+ {
1307
+ "epoch": 0.6463944396177237,
1308
+ "grad_norm": 0.8985302448272705,
1309
+ "learning_rate": 5.836507089334849e-06,
1310
+ "loss": 0.5391,
1311
+ "step": 186
1312
+ },
1313
+ {
1314
+ "epoch": 0.6498696785403997,
1315
+ "grad_norm": 1.0520668029785156,
1316
+ "learning_rate": 5.7340286872557515e-06,
1317
+ "loss": 0.6108,
1318
+ "step": 187
1319
+ },
1320
+ {
1321
+ "epoch": 0.6533449174630755,
1322
+ "grad_norm": 0.9960751533508301,
1323
+ "learning_rate": 5.6320950680705826e-06,
1324
+ "loss": 0.5867,
1325
+ "step": 188
1326
+ },
1327
+ {
1328
+ "epoch": 0.6568201563857515,
1329
+ "grad_norm": 1.0133719444274902,
1330
+ "learning_rate": 5.530719249141148e-06,
1331
+ "loss": 0.5313,
1332
+ "step": 189
1333
+ },
1334
+ {
1335
+ "epoch": 0.6602953953084274,
1336
+ "grad_norm": 0.9764801859855652,
1337
+ "learning_rate": 5.429914176595772e-06,
1338
+ "loss": 0.559,
1339
+ "step": 190
1340
+ },
1341
+ {
1342
+ "epoch": 0.6637706342311034,
1343
+ "grad_norm": 1.0536527633666992,
1344
+ "learning_rate": 5.329692723675994e-06,
1345
+ "loss": 0.5625,
1346
+ "step": 191
1347
+ },
1348
+ {
1349
+ "epoch": 0.6672458731537794,
1350
+ "grad_norm": 1.139304280281067,
1351
+ "learning_rate": 5.230067689092629e-06,
1352
+ "loss": 0.5941,
1353
+ "step": 192
1354
+ },
1355
+ {
1356
+ "epoch": 0.6707211120764552,
1357
+ "grad_norm": 1.0412135124206543,
1358
+ "learning_rate": 5.131051795391302e-06,
1359
+ "loss": 0.6064,
1360
+ "step": 193
1361
+ },
1362
+ {
1363
+ "epoch": 0.6741963509991312,
1364
+ "grad_norm": 1.0304534435272217,
1365
+ "learning_rate": 5.03265768732772e-06,
1366
+ "loss": 0.5576,
1367
+ "step": 194
1368
+ },
1369
+ {
1370
+ "epoch": 0.6776715899218071,
1371
+ "grad_norm": 0.9016774892807007,
1372
+ "learning_rate": 4.934897930252887e-06,
1373
+ "loss": 0.59,
1374
+ "step": 195
1375
+ },
1376
+ {
1377
+ "epoch": 0.6811468288444831,
1378
+ "grad_norm": 0.9751427173614502,
1379
+ "learning_rate": 4.837785008508462e-06,
1380
+ "loss": 0.587,
1381
+ "step": 196
1382
+ },
1383
+ {
1384
+ "epoch": 0.684622067767159,
1385
+ "grad_norm": 0.9640844464302063,
1386
+ "learning_rate": 4.7413313238324556e-06,
1387
+ "loss": 0.5332,
1388
+ "step": 197
1389
+ },
1390
+ {
1391
+ "epoch": 0.6880973066898349,
1392
+ "grad_norm": 1.0356625318527222,
1393
+ "learning_rate": 4.645549193775452e-06,
1394
+ "loss": 0.5798,
1395
+ "step": 198
1396
+ },
1397
+ {
1398
+ "epoch": 0.6915725456125109,
1399
+ "grad_norm": 0.9761075377464294,
1400
+ "learning_rate": 4.550450850127626e-06,
1401
+ "loss": 0.5669,
1402
+ "step": 199
1403
+ },
1404
+ {
1405
+ "epoch": 0.6950477845351868,
1406
+ "grad_norm": 0.9727676510810852,
1407
+ "learning_rate": 4.4560484373566945e-06,
1408
+ "loss": 0.5526,
1409
+ "step": 200
1410
+ },
1411
+ {
1412
+ "epoch": 0.6985230234578628,
1413
+ "grad_norm": 0.9600728750228882,
1414
+ "learning_rate": 4.3623540110569935e-06,
1415
+ "loss": 0.5225,
1416
+ "step": 201
1417
+ },
1418
+ {
1419
+ "epoch": 0.7019982623805386,
1420
+ "grad_norm": 1.075377345085144,
1421
+ "learning_rate": 4.26937953640995e-06,
1422
+ "loss": 0.6123,
1423
+ "step": 202
1424
+ },
1425
+ {
1426
+ "epoch": 0.7054735013032146,
1427
+ "grad_norm": 0.9740473031997681,
1428
+ "learning_rate": 4.177136886656067e-06,
1429
+ "loss": 0.5718,
1430
+ "step": 203
1431
+ },
1432
+ {
1433
+ "epoch": 0.7089487402258905,
1434
+ "grad_norm": 0.894684374332428,
1435
+ "learning_rate": 4.085637841578652e-06,
1436
+ "loss": 0.6006,
1437
+ "step": 204
1438
+ },
1439
+ {
1440
+ "epoch": 0.7124239791485665,
1441
+ "grad_norm": 1.0192121267318726,
1442
+ "learning_rate": 3.9948940859994964e-06,
1443
+ "loss": 0.5745,
1444
+ "step": 205
1445
+ },
1446
+ {
1447
+ "epoch": 0.7158992180712423,
1448
+ "grad_norm": 1.0569602251052856,
1449
+ "learning_rate": 3.9049172082866786e-06,
1450
+ "loss": 0.6085,
1451
+ "step": 206
1452
+ },
1453
+ {
1454
+ "epoch": 0.7193744569939183,
1455
+ "grad_norm": 1.0002917051315308,
1456
+ "learning_rate": 3.815718698874672e-06,
1457
+ "loss": 0.5586,
1458
+ "step": 207
1459
+ },
1460
+ {
1461
+ "epoch": 0.7228496959165943,
1462
+ "grad_norm": 0.9531834125518799,
1463
+ "learning_rate": 3.727309948796963e-06,
1464
+ "loss": 0.5927,
1465
+ "step": 208
1466
+ },
1467
+ {
1468
+ "epoch": 0.7263249348392702,
1469
+ "grad_norm": 1.045615553855896,
1470
+ "learning_rate": 3.6397022482313804e-06,
1471
+ "loss": 0.5594,
1472
+ "step": 209
1473
+ },
1474
+ {
1475
+ "epoch": 0.7298001737619462,
1476
+ "grad_norm": 0.9334245324134827,
1477
+ "learning_rate": 3.552906785058278e-06,
1478
+ "loss": 0.5364,
1479
+ "step": 210
1480
+ },
1481
+ {
1482
+ "epoch": 0.733275412684622,
1483
+ "grad_norm": 0.9601573348045349,
1484
+ "learning_rate": 3.466934643431795e-06,
1485
+ "loss": 0.5571,
1486
+ "step": 211
1487
+ },
1488
+ {
1489
+ "epoch": 0.736750651607298,
1490
+ "grad_norm": 0.95643150806427,
1491
+ "learning_rate": 3.3817968023643766e-06,
1492
+ "loss": 0.5717,
1493
+ "step": 212
1494
+ },
1495
+ {
1496
+ "epoch": 0.7402258905299739,
1497
+ "grad_norm": 0.9626767039299011,
1498
+ "learning_rate": 3.2975041343246937e-06,
1499
+ "loss": 0.54,
1500
+ "step": 213
1501
+ },
1502
+ {
1503
+ "epoch": 0.7437011294526499,
1504
+ "grad_norm": 0.9196009635925293,
1505
+ "learning_rate": 3.214067403849179e-06,
1506
+ "loss": 0.5807,
1507
+ "step": 214
1508
+ },
1509
+ {
1510
+ "epoch": 0.7471763683753258,
1511
+ "grad_norm": 1.049148440361023,
1512
+ "learning_rate": 3.1314972661673572e-06,
1513
+ "loss": 0.6214,
1514
+ "step": 215
1515
+ },
1516
+ {
1517
+ "epoch": 0.7506516072980017,
1518
+ "grad_norm": 0.9988502264022827,
1519
+ "learning_rate": 3.0498042658411276e-06,
1520
+ "loss": 0.5561,
1521
+ "step": 216
1522
+ },
1523
+ {
1524
+ "epoch": 0.7541268462206777,
1525
+ "grad_norm": 1.0174543857574463,
1526
+ "learning_rate": 2.9689988354181742e-06,
1527
+ "loss": 0.5698,
1528
+ "step": 217
1529
+ },
1530
+ {
1531
+ "epoch": 0.7576020851433536,
1532
+ "grad_norm": 1.0161805152893066,
1533
+ "learning_rate": 2.8890912940996784e-06,
1534
+ "loss": 0.5478,
1535
+ "step": 218
1536
+ },
1537
+ {
1538
+ "epoch": 0.7610773240660296,
1539
+ "grad_norm": 0.9427905082702637,
1540
+ "learning_rate": 2.8100918464225304e-06,
1541
+ "loss": 0.5637,
1542
+ "step": 219
1543
+ },
1544
+ {
1545
+ "epoch": 0.7645525629887054,
1546
+ "grad_norm": 1.0057843923568726,
1547
+ "learning_rate": 2.7320105809561415e-06,
1548
+ "loss": 0.5674,
1549
+ "step": 220
1550
+ },
1551
+ {
1552
+ "epoch": 0.7680278019113814,
1553
+ "grad_norm": 1.013282299041748,
1554
+ "learning_rate": 2.654857469014113e-06,
1555
+ "loss": 0.5863,
1556
+ "step": 221
1557
+ },
1558
+ {
1559
+ "epoch": 0.7715030408340573,
1560
+ "grad_norm": 0.980964720249176,
1561
+ "learning_rate": 2.5786423633808487e-06,
1562
+ "loss": 0.573,
1563
+ "step": 222
1564
+ },
1565
+ {
1566
+ "epoch": 0.7749782797567333,
1567
+ "grad_norm": 0.9535639882087708,
1568
+ "learning_rate": 2.5033749970533015e-06,
1569
+ "loss": 0.5594,
1570
+ "step": 223
1571
+ },
1572
+ {
1573
+ "epoch": 0.7784535186794093,
1574
+ "grad_norm": 0.9691473841667175,
1575
+ "learning_rate": 2.4290649819980404e-06,
1576
+ "loss": 0.5937,
1577
+ "step": 224
1578
+ },
1579
+ {
1580
+ "epoch": 0.7819287576020851,
1581
+ "grad_norm": 0.9758164286613464,
1582
+ "learning_rate": 2.3557218079237608e-06,
1583
+ "loss": 0.5412,
1584
+ "step": 225
1585
+ },
1586
+ {
1587
+ "epoch": 0.7854039965247611,
1588
+ "grad_norm": 0.9405572414398193,
1589
+ "learning_rate": 2.283354841069403e-06,
1590
+ "loss": 0.5655,
1591
+ "step": 226
1592
+ },
1593
+ {
1594
+ "epoch": 0.788879235447437,
1595
+ "grad_norm": 0.8931716680526733,
1596
+ "learning_rate": 2.211973323008041e-06,
1597
+ "loss": 0.5258,
1598
+ "step": 227
1599
+ },
1600
+ {
1601
+ "epoch": 0.792354474370113,
1602
+ "grad_norm": 0.9230597019195557,
1603
+ "learning_rate": 2.1415863694666973e-06,
1604
+ "loss": 0.5538,
1605
+ "step": 228
1606
+ },
1607
+ {
1608
+ "epoch": 0.7958297132927888,
1609
+ "grad_norm": 0.9798585176467896,
1610
+ "learning_rate": 2.072202969162234e-06,
1611
+ "loss": 0.5556,
1612
+ "step": 229
1613
+ },
1614
+ {
1615
+ "epoch": 0.7993049522154648,
1616
+ "grad_norm": 0.9468632340431213,
1617
+ "learning_rate": 2.0038319826534312e-06,
1618
+ "loss": 0.597,
1619
+ "step": 230
1620
+ },
1621
+ {
1622
+ "epoch": 0.8027801911381407,
1623
+ "grad_norm": 0.9490894079208374,
1624
+ "learning_rate": 1.936482141209486e-06,
1625
+ "loss": 0.5645,
1626
+ "step": 231
1627
+ },
1628
+ {
1629
+ "epoch": 0.8062554300608167,
1630
+ "grad_norm": 0.9810106754302979,
1631
+ "learning_rate": 1.870162045694971e-06,
1632
+ "loss": 0.5281,
1633
+ "step": 232
1634
+ },
1635
+ {
1636
+ "epoch": 0.8097306689834927,
1637
+ "grad_norm": 0.9110345840454102,
1638
+ "learning_rate": 1.8048801654714687e-06,
1639
+ "loss": 0.5774,
1640
+ "step": 233
1641
+ },
1642
+ {
1643
+ "epoch": 0.8132059079061685,
1644
+ "grad_norm": 0.9290068745613098,
1645
+ "learning_rate": 1.7406448373160024e-06,
1646
+ "loss": 0.6053,
1647
+ "step": 234
1648
+ },
1649
+ {
1650
+ "epoch": 0.8166811468288445,
1651
+ "grad_norm": 0.9238559603691101,
1652
+ "learning_rate": 1.6774642643563955e-06,
1653
+ "loss": 0.5125,
1654
+ "step": 235
1655
+ },
1656
+ {
1657
+ "epoch": 0.8201563857515204,
1658
+ "grad_norm": 1.0130783319473267,
1659
+ "learning_rate": 1.615346515023698e-06,
1660
+ "loss": 0.5873,
1661
+ "step": 236
1662
+ },
1663
+ {
1664
+ "epoch": 0.8236316246741964,
1665
+ "grad_norm": 0.9619508981704712,
1666
+ "learning_rate": 1.5542995220217961e-06,
1667
+ "loss": 0.5979,
1668
+ "step": 237
1669
+ },
1670
+ {
1671
+ "epoch": 0.8271068635968722,
1672
+ "grad_norm": 1.0197911262512207,
1673
+ "learning_rate": 1.4943310813144006e-06,
1674
+ "loss": 0.6156,
1675
+ "step": 238
1676
+ },
1677
+ {
1678
+ "epoch": 0.8305821025195482,
1679
+ "grad_norm": 0.9349676370620728,
1680
+ "learning_rate": 1.4354488511294418e-06,
1681
+ "loss": 0.5689,
1682
+ "step": 239
1683
+ },
1684
+ {
1685
+ "epoch": 0.8340573414422241,
1686
+ "grad_norm": 1.0270828008651733,
1687
+ "learning_rate": 1.3776603509810938e-06,
1688
+ "loss": 0.5397,
1689
+ "step": 240
1690
+ },
1691
+ {
1692
+ "epoch": 0.8375325803649001,
1693
+ "grad_norm": 0.9381040334701538,
1694
+ "learning_rate": 1.3209729607095022e-06,
1695
+ "loss": 0.542,
1696
+ "step": 241
1697
+ },
1698
+ {
1699
+ "epoch": 0.8410078192875761,
1700
+ "grad_norm": 1.0486862659454346,
1701
+ "learning_rate": 1.2653939195383448e-06,
1702
+ "loss": 0.5886,
1703
+ "step": 242
1704
+ },
1705
+ {
1706
+ "epoch": 0.8444830582102519,
1707
+ "grad_norm": 0.9653035402297974,
1708
+ "learning_rate": 1.2109303251503434e-06,
1709
+ "loss": 0.5893,
1710
+ "step": 243
1711
+ },
1712
+ {
1713
+ "epoch": 0.8479582971329279,
1714
+ "grad_norm": 0.9536635279655457,
1715
+ "learning_rate": 1.1575891327808664e-06,
1716
+ "loss": 0.5728,
1717
+ "step": 244
1718
+ },
1719
+ {
1720
+ "epoch": 0.8514335360556038,
1721
+ "grad_norm": 0.9552822113037109,
1722
+ "learning_rate": 1.1053771543297198e-06,
1723
+ "loss": 0.5335,
1724
+ "step": 245
1725
+ },
1726
+ {
1727
+ "epoch": 0.8549087749782798,
1728
+ "grad_norm": 0.9501549005508423,
1729
+ "learning_rate": 1.0543010574912305e-06,
1730
+ "loss": 0.5696,
1731
+ "step": 246
1732
+ },
1733
+ {
1734
+ "epoch": 0.8583840139009556,
1735
+ "grad_norm": 0.9457242488861084,
1736
+ "learning_rate": 1.0043673649027519e-06,
1737
+ "loss": 0.5974,
1738
+ "step": 247
1739
+ },
1740
+ {
1741
+ "epoch": 0.8618592528236316,
1742
+ "grad_norm": 0.9081954956054688,
1743
+ "learning_rate": 9.555824533117064e-07,
1744
+ "loss": 0.5984,
1745
+ "step": 248
1746
+ },
1747
+ {
1748
+ "epoch": 0.8653344917463076,
1749
+ "grad_norm": 0.9678678512573242,
1750
+ "learning_rate": 9.079525527612321e-07,
1751
+ "loss": 0.5463,
1752
+ "step": 249
1753
+ },
1754
+ {
1755
+ "epoch": 0.8688097306689835,
1756
+ "grad_norm": 0.9402781128883362,
1757
+ "learning_rate": 8.614837457945868e-07,
1758
+ "loss": 0.5831,
1759
+ "step": 250
1760
+ },
1761
+ {
1762
+ "epoch": 0.8722849695916595,
1763
+ "grad_norm": 0.8864692449569702,
1764
+ "learning_rate": 8.161819666783888e-07,
1765
+ "loss": 0.6336,
1766
+ "step": 251
1767
+ },
1768
+ {
1769
+ "epoch": 0.8757602085143353,
1770
+ "grad_norm": 0.9280177354812622,
1771
+ "learning_rate": 7.720530006447735e-07,
1772
+ "loss": 0.5792,
1773
+ "step": 252
1774
+ },
1775
+ {
1776
+ "epoch": 0.8792354474370113,
1777
+ "grad_norm": 0.9325032830238342,
1778
+ "learning_rate": 7.291024831525961e-07,
1779
+ "loss": 0.5374,
1780
+ "step": 253
1781
+ },
1782
+ {
1783
+ "epoch": 0.8827106863596872,
1784
+ "grad_norm": 0.8580663800239563,
1785
+ "learning_rate": 6.87335899167767e-07,
1786
+ "loss": 0.5319,
1787
+ "step": 254
1788
+ },
1789
+ {
1790
+ "epoch": 0.8861859252823632,
1791
+ "grad_norm": 0.98850017786026,
1792
+ "learning_rate": 6.467585824627886e-07,
1793
+ "loss": 0.6334,
1794
+ "step": 255
1795
+ },
1796
+ {
1797
+ "epoch": 0.889661164205039,
1798
+ "grad_norm": 0.9273893237113953,
1799
+ "learning_rate": 6.073757149356185e-07,
1800
+ "loss": 0.5404,
1801
+ "step": 256
1802
+ },
1803
+ {
1804
+ "epoch": 0.893136403127715,
1805
+ "grad_norm": 0.9261394739151001,
1806
+ "learning_rate": 5.691923259479093e-07,
1807
+ "loss": 0.553,
1808
+ "step": 257
1809
+ },
1810
+ {
1811
+ "epoch": 0.896611642050391,
1812
+ "grad_norm": 0.9248658418655396,
1813
+ "learning_rate": 5.322132916827483e-07,
1814
+ "loss": 0.5835,
1815
+ "step": 258
1816
+ },
1817
+ {
1818
+ "epoch": 0.9000868809730669,
1819
+ "grad_norm": 0.9358659982681274,
1820
+ "learning_rate": 4.964433345219354e-07,
1821
+ "loss": 0.6004,
1822
+ "step": 259
1823
+ },
1824
+ {
1825
+ "epoch": 0.9035621198957429,
1826
+ "grad_norm": 1.0171351432800293,
1827
+ "learning_rate": 4.6188702244292614e-07,
1828
+ "loss": 0.5684,
1829
+ "step": 260
1830
+ },
1831
+ {
1832
+ "epoch": 0.9070373588184187,
1833
+ "grad_norm": 0.9322757720947266,
1834
+ "learning_rate": 4.285487684354772e-07,
1835
+ "loss": 0.5311,
1836
+ "step": 261
1837
+ },
1838
+ {
1839
+ "epoch": 0.9105125977410947,
1840
+ "grad_norm": 0.9555125832557678,
1841
+ "learning_rate": 3.96432829938086e-07,
1842
+ "loss": 0.5627,
1843
+ "step": 262
1844
+ },
1845
+ {
1846
+ "epoch": 0.9139878366637706,
1847
+ "grad_norm": 0.8531783223152161,
1848
+ "learning_rate": 3.6554330829429716e-07,
1849
+ "loss": 0.5249,
1850
+ "step": 263
1851
+ },
1852
+ {
1853
+ "epoch": 0.9174630755864466,
1854
+ "grad_norm": 0.9125425815582275,
1855
+ "learning_rate": 3.3588414822895097e-07,
1856
+ "loss": 0.5257,
1857
+ "step": 264
1858
+ },
1859
+ {
1860
+ "epoch": 0.9209383145091226,
1861
+ "grad_norm": 0.9245027899742126,
1862
+ "learning_rate": 3.0745913734441357e-07,
1863
+ "loss": 0.5328,
1864
+ "step": 265
1865
+ },
1866
+ {
1867
+ "epoch": 0.9244135534317984,
1868
+ "grad_norm": 0.9753005504608154,
1869
+ "learning_rate": 2.8027190563689745e-07,
1870
+ "loss": 0.5431,
1871
+ "step": 266
1872
+ },
1873
+ {
1874
+ "epoch": 0.9278887923544744,
1875
+ "grad_norm": 0.9659878611564636,
1876
+ "learning_rate": 2.5432592503288e-07,
1877
+ "loss": 0.5794,
1878
+ "step": 267
1879
+ },
1880
+ {
1881
+ "epoch": 0.9313640312771503,
1882
+ "grad_norm": 1.0079331398010254,
1883
+ "learning_rate": 2.2962450894573606e-07,
1884
+ "loss": 0.5434,
1885
+ "step": 268
1886
+ },
1887
+ {
1888
+ "epoch": 0.9348392701998263,
1889
+ "grad_norm": 0.9261694550514221,
1890
+ "learning_rate": 2.0617081185259512e-07,
1891
+ "loss": 0.5718,
1892
+ "step": 269
1893
+ },
1894
+ {
1895
+ "epoch": 0.9383145091225021,
1896
+ "grad_norm": 0.8658697009086609,
1897
+ "learning_rate": 1.8396782889150144e-07,
1898
+ "loss": 0.5553,
1899
+ "step": 270
1900
+ },
1901
+ {
1902
+ "epoch": 0.9417897480451781,
1903
+ "grad_norm": 0.9265699982643127,
1904
+ "learning_rate": 1.630183954789233e-07,
1905
+ "loss": 0.551,
1906
+ "step": 271
1907
+ },
1908
+ {
1909
+ "epoch": 0.945264986967854,
1910
+ "grad_norm": 0.9904604554176331,
1911
+ "learning_rate": 1.4332518694765708e-07,
1912
+ "loss": 0.5113,
1913
+ "step": 272
1914
+ },
1915
+ {
1916
+ "epoch": 0.94874022589053,
1917
+ "grad_norm": 0.9163973331451416,
1918
+ "learning_rate": 1.2489071820517394e-07,
1919
+ "loss": 0.587,
1920
+ "step": 273
1921
+ },
1922
+ {
1923
+ "epoch": 0.952215464813206,
1924
+ "grad_norm": 0.8994106650352478,
1925
+ "learning_rate": 1.0771734341246121e-07,
1926
+ "loss": 0.5273,
1927
+ "step": 274
1928
+ },
1929
+ {
1930
+ "epoch": 0.9556907037358818,
1931
+ "grad_norm": 0.9306617975234985,
1932
+ "learning_rate": 9.180725568338045e-08,
1933
+ "loss": 0.5598,
1934
+ "step": 275
1935
+ },
1936
+ {
1937
+ "epoch": 0.9591659426585578,
1938
+ "grad_norm": 0.9544433355331421,
1939
+ "learning_rate": 7.716248680459726e-08,
1940
+ "loss": 0.5608,
1941
+ "step": 276
1942
+ },
1943
+ {
1944
+ "epoch": 0.9626411815812337,
1945
+ "grad_norm": 0.9377245903015137,
1946
+ "learning_rate": 6.378490697611761e-08,
1947
+ "loss": 0.5477,
1948
+ "step": 277
1949
+ },
1950
+ {
1951
+ "epoch": 0.9661164205039097,
1952
+ "grad_norm": 0.8245200514793396,
1953
+ "learning_rate": 5.1676224572452246e-08,
1954
+ "loss": 0.5014,
1955
+ "step": 278
1956
+ },
1957
+ {
1958
+ "epoch": 0.9695916594265855,
1959
+ "grad_norm": 0.8969350457191467,
1960
+ "learning_rate": 4.083798592444899e-08,
1961
+ "loss": 0.5899,
1962
+ "step": 279
1963
+ },
1964
+ {
1965
+ "epoch": 0.9730668983492615,
1966
+ "grad_norm": 0.9808463454246521,
1967
+ "learning_rate": 3.127157512182288e-08,
1968
+ "loss": 0.5642,
1969
+ "step": 280
1970
+ },
1971
+ {
1972
+ "epoch": 0.9765421372719374,
1973
+ "grad_norm": 0.9421252608299255,
1974
+ "learning_rate": 2.2978213836400974e-08,
1975
+ "loss": 0.5448,
1976
+ "step": 281
1977
+ },
1978
+ {
1979
+ "epoch": 0.9800173761946134,
1980
+ "grad_norm": 0.9303473830223083,
1981
+ "learning_rate": 1.5958961166104847e-08,
1982
+ "loss": 0.5947,
1983
+ "step": 282
1984
+ },
1985
+ {
1986
+ "epoch": 0.9834926151172894,
1987
+ "grad_norm": 1.075130820274353,
1988
+ "learning_rate": 1.0214713499706596e-08,
1989
+ "loss": 0.5925,
1990
+ "step": 283
1991
+ },
1992
+ {
1993
+ "epoch": 0.9869678540399652,
1994
+ "grad_norm": 0.9997183680534363,
1995
+ "learning_rate": 5.7462044023515186e-09,
1996
+ "loss": 0.6126,
1997
+ "step": 284
1998
+ },
1999
+ {
2000
+ "epoch": 0.9904430929626412,
2001
+ "grad_norm": 0.8891317248344421,
2002
+ "learning_rate": 2.5540045218819256e-09,
2003
+ "loss": 0.5529,
2004
+ "step": 285
2005
+ },
2006
+ {
2007
+ "epoch": 0.9939183318853171,
2008
+ "grad_norm": 0.8776668310165405,
2009
+ "learning_rate": 6.385215159565583e-10,
2010
+ "loss": 0.5456,
2011
+ "step": 286
2012
+ },
2013
+ {
2014
+ "epoch": 0.9973935708079931,
2015
+ "grad_norm": 0.8966051340103149,
2016
+ "learning_rate": 0.0,
2017
+ "loss": 0.5303,
2018
+ "step": 287
2019
+ },
2020
+ {
2021
+ "epoch": 0.9973935708079931,
2022
+ "step": 287,
2023
+ "total_flos": 2.698045158024282e+18,
2024
+ "train_loss": 0.5919382667707649,
2025
+ "train_runtime": 4471.5794,
2026
+ "train_samples_per_second": 16.469,
2027
+ "train_steps_per_second": 0.064
2028
+ }
2029
+ ],
2030
+ "logging_steps": 1.0,
2031
+ "max_steps": 287,
2032
+ "num_input_tokens_seen": 0,
2033
+ "num_train_epochs": 1,
2034
+ "save_steps": 400,
2035
+ "stateful_callbacks": {
2036
+ "TrainerControl": {
2037
+ "args": {
2038
+ "should_epoch_stop": false,
2039
+ "should_evaluate": false,
2040
+ "should_log": false,
2041
+ "should_save": true,
2042
+ "should_training_stop": true
2043
+ },
2044
+ "attributes": {}
2045
+ }
2046
+ },
2047
+ "total_flos": 2.698045158024282e+18,
2048
+ "train_batch_size": 4,
2049
+ "trial_name": null,
2050
+ "trial_params": null
2051
+ }
training_loss.png ADDED