LemTenku commited on
Commit
1eaaaca
·
verified ·
1 Parent(s): 3df5969

Upload folder using huggingface_hub

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 +1,56 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: transformers
3
+ license: other
4
+ base_model: unsloth/Meta-Llama-3.1-8B
5
+ tags:
6
+ - llama-factory
7
+ - freeze
8
+ - generated_from_trainer
9
+ model-index:
10
+ - name: sft
11
+ results: []
12
+ ---
13
+
14
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
15
+ should probably proofread and complete it, then remove this comment. -->
16
+
17
+ # sft
18
+
19
+ This model is a fine-tuned version of [unsloth/Meta-Llama-3.1-8B](https://huggingface.co/unsloth/Meta-Llama-3.1-8B) on the tenku2 dataset.
20
+
21
+ ## Model description
22
+
23
+ More information needed
24
+
25
+ ## Intended uses & limitations
26
+
27
+ More information needed
28
+
29
+ ## Training and evaluation data
30
+
31
+ More information needed
32
+
33
+ ## Training procedure
34
+
35
+ ### Training hyperparameters
36
+
37
+ The following hyperparameters were used during training:
38
+ - learning_rate: 0.0001
39
+ - train_batch_size: 1
40
+ - eval_batch_size: 8
41
+ - seed: 42
42
+ - optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
43
+ - lr_scheduler_type: cosine
44
+ - lr_scheduler_warmup_ratio: 0.1
45
+ - num_epochs: 3.0
46
+
47
+ ### Training results
48
+
49
+
50
+
51
+ ### Framework versions
52
+
53
+ - Transformers 4.47.1
54
+ - Pytorch 2.3.1+cu121
55
+ - Datasets 3.0.1
56
+ - Tokenizers 0.21.0
all_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 3.0,
3
+ "total_flos": 3.0626432822122906e+18,
4
+ "train_loss": 0.8061501924692238,
5
+ "train_runtime": 22473.7337,
6
+ "train_samples_per_second": 0.246,
7
+ "train_steps_per_second": 0.246
8
+ }
config.json ADDED
@@ -0,0 +1,38 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "unsloth/Meta-Llama-3.1-8B",
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
+ "pad_token_id": 128004,
22
+ "pretraining_tp": 1,
23
+ "rms_norm_eps": 1e-05,
24
+ "rope_scaling": {
25
+ "factor": 8.0,
26
+ "high_freq_factor": 4.0,
27
+ "low_freq_factor": 1.0,
28
+ "original_max_position_embeddings": 8192,
29
+ "rope_type": "llama3"
30
+ },
31
+ "rope_theta": 500000.0,
32
+ "tie_word_embeddings": false,
33
+ "torch_dtype": "bfloat16",
34
+ "transformers_version": "4.47.1",
35
+ "unsloth_fixed": true,
36
+ "use_cache": false,
37
+ "vocab_size": 128256
38
+ }
generation_config.json ADDED
@@ -0,0 +1,11 @@
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 128000,
4
+ "do_sample": true,
5
+ "eos_token_id": 128001,
6
+ "max_length": 131072,
7
+ "pad_token_id": 128004,
8
+ "temperature": 0.6,
9
+ "top_p": 0.9,
10
+ "transformers_version": "4.47.1"
11
+ }
model-00001-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f8b9704ab09cdeb097aa4a0a24bca96f906eec36bad63ab495bc21475058601b
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:b8bb26c9c7198dea72b9989107bee6ae2772f19b9eaf9f1fbea11a93c3f66d3f
3
+ size 4966248168
model-00003-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e63c58a75dc1d57b2418476834367b1bfef04382a461591408c839e274e64046
3
+ size 4832007496
model-00004-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:682110f0411c476e03f08d71c2663c69115655420f9646d6201f575aee8d375f
3
+ size 4775393968
model.safetensors.index.json ADDED
@@ -0,0 +1,298 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 19550314496
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-00003-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-00004-of-00004.safetensors",
171
+ "model.layers.25.mlp.down_proj.weight": "model-00004-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-00004-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-00004-of-00004.safetensors",
180
+ "model.layers.26.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
181
+ "model.layers.26.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
182
+ "model.layers.26.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
183
+ "model.layers.26.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
184
+ "model.layers.26.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
185
+ "model.layers.26.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
186
+ "model.layers.26.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
187
+ "model.layers.26.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
188
+ "model.layers.27.input_layernorm.weight": "model-00004-of-00004.safetensors",
189
+ "model.layers.27.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
190
+ "model.layers.27.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
191
+ "model.layers.27.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
192
+ "model.layers.27.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
193
+ "model.layers.27.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
194
+ "model.layers.27.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
195
+ "model.layers.27.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
196
+ "model.layers.27.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
197
+ "model.layers.28.input_layernorm.weight": "model-00004-of-00004.safetensors",
198
+ "model.layers.28.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
199
+ "model.layers.28.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
200
+ "model.layers.28.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
201
+ "model.layers.28.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
202
+ "model.layers.28.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
203
+ "model.layers.28.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
204
+ "model.layers.28.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
205
+ "model.layers.28.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
206
+ "model.layers.29.input_layernorm.weight": "model-00004-of-00004.safetensors",
207
+ "model.layers.29.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
208
+ "model.layers.29.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
209
+ "model.layers.29.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
210
+ "model.layers.29.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
211
+ "model.layers.29.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
212
+ "model.layers.29.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
213
+ "model.layers.29.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
214
+ "model.layers.29.self_attn.v_proj.weight": "model-00004-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-00004-of-00004.safetensors",
225
+ "model.layers.30.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
226
+ "model.layers.30.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
227
+ "model.layers.30.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
228
+ "model.layers.30.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
229
+ "model.layers.30.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
230
+ "model.layers.30.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
231
+ "model.layers.30.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
232
+ "model.layers.30.self_attn.v_proj.weight": "model-00004-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-00004-of-00004.safetensors",
236
+ "model.layers.31.mlp.up_proj.weight": "model-00004-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-00004-of-00004.safetensors",
239
+ "model.layers.31.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
240
+ "model.layers.31.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
241
+ "model.layers.31.self_attn.v_proj.weight": "model-00004-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
+ }
runs/Feb04_20-36-52_3ce2c898ec9c/events.out.tfevents.1738702125.3ce2c898ec9c.1207.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:484394ad2e973b4f5b364948f27351240bf68d20d65bc0ed1436a29e18f59a0d
3
+ size 122664
special_tokens_map.json ADDED
@@ -0,0 +1,39 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ {
4
+ "content": "<|eot_id|>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false
9
+ },
10
+ {
11
+ "content": "<|eom_id|>",
12
+ "lstrip": false,
13
+ "normalized": false,
14
+ "rstrip": false,
15
+ "single_word": false
16
+ }
17
+ ],
18
+ "bos_token": {
19
+ "content": "<|begin_of_text|>",
20
+ "lstrip": false,
21
+ "normalized": false,
22
+ "rstrip": false,
23
+ "single_word": false
24
+ },
25
+ "eos_token": {
26
+ "content": "<|end_of_text|>",
27
+ "lstrip": false,
28
+ "normalized": false,
29
+ "rstrip": false,
30
+ "single_word": false
31
+ },
32
+ "pad_token": {
33
+ "content": "<|finetune_right_pad_id|>",
34
+ "lstrip": false,
35
+ "normalized": false,
36
+ "rstrip": false,
37
+ "single_word": false
38
+ }
39
+ }
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 +1,2072 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "added_tokens_decoder": {
4
+ "128000": {
5
+ "content": "<|begin_of_text|>",
6
+ "lstrip": false,
7
+ "normalized": false,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "128001": {
13
+ "content": "<|end_of_text|>",
14
+ "lstrip": false,
15
+ "normalized": false,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ },
20
+ "128002": {
21
+ "content": "<|reserved_special_token_0|>",
22
+ "lstrip": false,
23
+ "normalized": false,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": true
27
+ },
28
+ "128003": {
29
+ "content": "<|reserved_special_token_1|>",
30
+ "lstrip": false,
31
+ "normalized": false,
32
+ "rstrip": false,
33
+ "single_word": false,
34
+ "special": true
35
+ },
36
+ "128004": {
37
+ "content": "<|finetune_right_pad_id|>",
38
+ "lstrip": false,
39
+ "normalized": false,
40
+ "rstrip": false,
41
+ "single_word": false,
42
+ "special": true
43
+ },
44
+ "128005": {
45
+ "content": "<|reserved_special_token_2|>",
46
+ "lstrip": false,
47
+ "normalized": false,
48
+ "rstrip": false,
49
+ "single_word": false,
50
+ "special": true
51
+ },
52
+ "128006": {
53
+ "content": "<|start_header_id|>",
54
+ "lstrip": false,
55
+ "normalized": false,
56
+ "rstrip": false,
57
+ "single_word": false,
58
+ "special": true
59
+ },
60
+ "128007": {
61
+ "content": "<|end_header_id|>",
62
+ "lstrip": false,
63
+ "normalized": false,
64
+ "rstrip": false,
65
+ "single_word": false,
66
+ "special": true
67
+ },
68
+ "128008": {
69
+ "content": "<|eom_id|>",
70
+ "lstrip": false,
71
+ "normalized": false,
72
+ "rstrip": false,
73
+ "single_word": false,
74
+ "special": true
75
+ },
76
+ "128009": {
77
+ "content": "<|eot_id|>",
78
+ "lstrip": false,
79
+ "normalized": false,
80
+ "rstrip": false,
81
+ "single_word": false,
82
+ "special": true
83
+ },
84
+ "128010": {
85
+ "content": "<|python_tag|>",
86
+ "lstrip": false,
87
+ "normalized": false,
88
+ "rstrip": false,
89
+ "single_word": false,
90
+ "special": true
91
+ },
92
+ "128011": {
93
+ "content": "<|reserved_special_token_3|>",
94
+ "lstrip": false,
95
+ "normalized": false,
96
+ "rstrip": false,
97
+ "single_word": false,
98
+ "special": true
99
+ },
100
+ "128012": {
101
+ "content": "<|reserved_special_token_4|>",
102
+ "lstrip": false,
103
+ "normalized": false,
104
+ "rstrip": false,
105
+ "single_word": false,
106
+ "special": true
107
+ },
108
+ "128013": {
109
+ "content": "<|reserved_special_token_5|>",
110
+ "lstrip": false,
111
+ "normalized": false,
112
+ "rstrip": false,
113
+ "single_word": false,
114
+ "special": true
115
+ },
116
+ "128014": {
117
+ "content": "<|reserved_special_token_6|>",
118
+ "lstrip": false,
119
+ "normalized": false,
120
+ "rstrip": false,
121
+ "single_word": false,
122
+ "special": true
123
+ },
124
+ "128015": {
125
+ "content": "<|reserved_special_token_7|>",
126
+ "lstrip": false,
127
+ "normalized": false,
128
+ "rstrip": false,
129
+ "single_word": false,
130
+ "special": true
131
+ },
132
+ "128016": {
133
+ "content": "<|reserved_special_token_8|>",
134
+ "lstrip": false,
135
+ "normalized": false,
136
+ "rstrip": false,
137
+ "single_word": false,
138
+ "special": true
139
+ },
140
+ "128017": {
141
+ "content": "<|reserved_special_token_9|>",
142
+ "lstrip": false,
143
+ "normalized": false,
144
+ "rstrip": false,
145
+ "single_word": false,
146
+ "special": true
147
+ },
148
+ "128018": {
149
+ "content": "<|reserved_special_token_10|>",
150
+ "lstrip": false,
151
+ "normalized": false,
152
+ "rstrip": false,
153
+ "single_word": false,
154
+ "special": true
155
+ },
156
+ "128019": {
157
+ "content": "<|reserved_special_token_11|>",
158
+ "lstrip": false,
159
+ "normalized": false,
160
+ "rstrip": false,
161
+ "single_word": false,
162
+ "special": true
163
+ },
164
+ "128020": {
165
+ "content": "<|reserved_special_token_12|>",
166
+ "lstrip": false,
167
+ "normalized": false,
168
+ "rstrip": false,
169
+ "single_word": false,
170
+ "special": true
171
+ },
172
+ "128021": {
173
+ "content": "<|reserved_special_token_13|>",
174
+ "lstrip": false,
175
+ "normalized": false,
176
+ "rstrip": false,
177
+ "single_word": false,
178
+ "special": true
179
+ },
180
+ "128022": {
181
+ "content": "<|reserved_special_token_14|>",
182
+ "lstrip": false,
183
+ "normalized": false,
184
+ "rstrip": false,
185
+ "single_word": false,
186
+ "special": true
187
+ },
188
+ "128023": {
189
+ "content": "<|reserved_special_token_15|>",
190
+ "lstrip": false,
191
+ "normalized": false,
192
+ "rstrip": false,
193
+ "single_word": false,
194
+ "special": true
195
+ },
196
+ "128024": {
197
+ "content": "<|reserved_special_token_16|>",
198
+ "lstrip": false,
199
+ "normalized": false,
200
+ "rstrip": false,
201
+ "single_word": false,
202
+ "special": true
203
+ },
204
+ "128025": {
205
+ "content": "<|reserved_special_token_17|>",
206
+ "lstrip": false,
207
+ "normalized": false,
208
+ "rstrip": false,
209
+ "single_word": false,
210
+ "special": true
211
+ },
212
+ "128026": {
213
+ "content": "<|reserved_special_token_18|>",
214
+ "lstrip": false,
215
+ "normalized": false,
216
+ "rstrip": false,
217
+ "single_word": false,
218
+ "special": true
219
+ },
220
+ "128027": {
221
+ "content": "<|reserved_special_token_19|>",
222
+ "lstrip": false,
223
+ "normalized": false,
224
+ "rstrip": false,
225
+ "single_word": false,
226
+ "special": true
227
+ },
228
+ "128028": {
229
+ "content": "<|reserved_special_token_20|>",
230
+ "lstrip": false,
231
+ "normalized": false,
232
+ "rstrip": false,
233
+ "single_word": false,
234
+ "special": true
235
+ },
236
+ "128029": {
237
+ "content": "<|reserved_special_token_21|>",
238
+ "lstrip": false,
239
+ "normalized": false,
240
+ "rstrip": false,
241
+ "single_word": false,
242
+ "special": true
243
+ },
244
+ "128030": {
245
+ "content": "<|reserved_special_token_22|>",
246
+ "lstrip": false,
247
+ "normalized": false,
248
+ "rstrip": false,
249
+ "single_word": false,
250
+ "special": true
251
+ },
252
+ "128031": {
253
+ "content": "<|reserved_special_token_23|>",
254
+ "lstrip": false,
255
+ "normalized": false,
256
+ "rstrip": false,
257
+ "single_word": false,
258
+ "special": true
259
+ },
260
+ "128032": {
261
+ "content": "<|reserved_special_token_24|>",
262
+ "lstrip": false,
263
+ "normalized": false,
264
+ "rstrip": false,
265
+ "single_word": false,
266
+ "special": true
267
+ },
268
+ "128033": {
269
+ "content": "<|reserved_special_token_25|>",
270
+ "lstrip": false,
271
+ "normalized": false,
272
+ "rstrip": false,
273
+ "single_word": false,
274
+ "special": true
275
+ },
276
+ "128034": {
277
+ "content": "<|reserved_special_token_26|>",
278
+ "lstrip": false,
279
+ "normalized": false,
280
+ "rstrip": false,
281
+ "single_word": false,
282
+ "special": true
283
+ },
284
+ "128035": {
285
+ "content": "<|reserved_special_token_27|>",
286
+ "lstrip": false,
287
+ "normalized": false,
288
+ "rstrip": false,
289
+ "single_word": false,
290
+ "special": true
291
+ },
292
+ "128036": {
293
+ "content": "<|reserved_special_token_28|>",
294
+ "lstrip": false,
295
+ "normalized": false,
296
+ "rstrip": false,
297
+ "single_word": false,
298
+ "special": true
299
+ },
300
+ "128037": {
301
+ "content": "<|reserved_special_token_29|>",
302
+ "lstrip": false,
303
+ "normalized": false,
304
+ "rstrip": false,
305
+ "single_word": false,
306
+ "special": true
307
+ },
308
+ "128038": {
309
+ "content": "<|reserved_special_token_30|>",
310
+ "lstrip": false,
311
+ "normalized": false,
312
+ "rstrip": false,
313
+ "single_word": false,
314
+ "special": true
315
+ },
316
+ "128039": {
317
+ "content": "<|reserved_special_token_31|>",
318
+ "lstrip": false,
319
+ "normalized": false,
320
+ "rstrip": false,
321
+ "single_word": false,
322
+ "special": true
323
+ },
324
+ "128040": {
325
+ "content": "<|reserved_special_token_32|>",
326
+ "lstrip": false,
327
+ "normalized": false,
328
+ "rstrip": false,
329
+ "single_word": false,
330
+ "special": true
331
+ },
332
+ "128041": {
333
+ "content": "<|reserved_special_token_33|>",
334
+ "lstrip": false,
335
+ "normalized": false,
336
+ "rstrip": false,
337
+ "single_word": false,
338
+ "special": true
339
+ },
340
+ "128042": {
341
+ "content": "<|reserved_special_token_34|>",
342
+ "lstrip": false,
343
+ "normalized": false,
344
+ "rstrip": false,
345
+ "single_word": false,
346
+ "special": true
347
+ },
348
+ "128043": {
349
+ "content": "<|reserved_special_token_35|>",
350
+ "lstrip": false,
351
+ "normalized": false,
352
+ "rstrip": false,
353
+ "single_word": false,
354
+ "special": true
355
+ },
356
+ "128044": {
357
+ "content": "<|reserved_special_token_36|>",
358
+ "lstrip": false,
359
+ "normalized": false,
360
+ "rstrip": false,
361
+ "single_word": false,
362
+ "special": true
363
+ },
364
+ "128045": {
365
+ "content": "<|reserved_special_token_37|>",
366
+ "lstrip": false,
367
+ "normalized": false,
368
+ "rstrip": false,
369
+ "single_word": false,
370
+ "special": true
371
+ },
372
+ "128046": {
373
+ "content": "<|reserved_special_token_38|>",
374
+ "lstrip": false,
375
+ "normalized": false,
376
+ "rstrip": false,
377
+ "single_word": false,
378
+ "special": true
379
+ },
380
+ "128047": {
381
+ "content": "<|reserved_special_token_39|>",
382
+ "lstrip": false,
383
+ "normalized": false,
384
+ "rstrip": false,
385
+ "single_word": false,
386
+ "special": true
387
+ },
388
+ "128048": {
389
+ "content": "<|reserved_special_token_40|>",
390
+ "lstrip": false,
391
+ "normalized": false,
392
+ "rstrip": false,
393
+ "single_word": false,
394
+ "special": true
395
+ },
396
+ "128049": {
397
+ "content": "<|reserved_special_token_41|>",
398
+ "lstrip": false,
399
+ "normalized": false,
400
+ "rstrip": false,
401
+ "single_word": false,
402
+ "special": true
403
+ },
404
+ "128050": {
405
+ "content": "<|reserved_special_token_42|>",
406
+ "lstrip": false,
407
+ "normalized": false,
408
+ "rstrip": false,
409
+ "single_word": false,
410
+ "special": true
411
+ },
412
+ "128051": {
413
+ "content": "<|reserved_special_token_43|>",
414
+ "lstrip": false,
415
+ "normalized": false,
416
+ "rstrip": false,
417
+ "single_word": false,
418
+ "special": true
419
+ },
420
+ "128052": {
421
+ "content": "<|reserved_special_token_44|>",
422
+ "lstrip": false,
423
+ "normalized": false,
424
+ "rstrip": false,
425
+ "single_word": false,
426
+ "special": true
427
+ },
428
+ "128053": {
429
+ "content": "<|reserved_special_token_45|>",
430
+ "lstrip": false,
431
+ "normalized": false,
432
+ "rstrip": false,
433
+ "single_word": false,
434
+ "special": true
435
+ },
436
+ "128054": {
437
+ "content": "<|reserved_special_token_46|>",
438
+ "lstrip": false,
439
+ "normalized": false,
440
+ "rstrip": false,
441
+ "single_word": false,
442
+ "special": true
443
+ },
444
+ "128055": {
445
+ "content": "<|reserved_special_token_47|>",
446
+ "lstrip": false,
447
+ "normalized": false,
448
+ "rstrip": false,
449
+ "single_word": false,
450
+ "special": true
451
+ },
452
+ "128056": {
453
+ "content": "<|reserved_special_token_48|>",
454
+ "lstrip": false,
455
+ "normalized": false,
456
+ "rstrip": false,
457
+ "single_word": false,
458
+ "special": true
459
+ },
460
+ "128057": {
461
+ "content": "<|reserved_special_token_49|>",
462
+ "lstrip": false,
463
+ "normalized": false,
464
+ "rstrip": false,
465
+ "single_word": false,
466
+ "special": true
467
+ },
468
+ "128058": {
469
+ "content": "<|reserved_special_token_50|>",
470
+ "lstrip": false,
471
+ "normalized": false,
472
+ "rstrip": false,
473
+ "single_word": false,
474
+ "special": true
475
+ },
476
+ "128059": {
477
+ "content": "<|reserved_special_token_51|>",
478
+ "lstrip": false,
479
+ "normalized": false,
480
+ "rstrip": false,
481
+ "single_word": false,
482
+ "special": true
483
+ },
484
+ "128060": {
485
+ "content": "<|reserved_special_token_52|>",
486
+ "lstrip": false,
487
+ "normalized": false,
488
+ "rstrip": false,
489
+ "single_word": false,
490
+ "special": true
491
+ },
492
+ "128061": {
493
+ "content": "<|reserved_special_token_53|>",
494
+ "lstrip": false,
495
+ "normalized": false,
496
+ "rstrip": false,
497
+ "single_word": false,
498
+ "special": true
499
+ },
500
+ "128062": {
501
+ "content": "<|reserved_special_token_54|>",
502
+ "lstrip": false,
503
+ "normalized": false,
504
+ "rstrip": false,
505
+ "single_word": false,
506
+ "special": true
507
+ },
508
+ "128063": {
509
+ "content": "<|reserved_special_token_55|>",
510
+ "lstrip": false,
511
+ "normalized": false,
512
+ "rstrip": false,
513
+ "single_word": false,
514
+ "special": true
515
+ },
516
+ "128064": {
517
+ "content": "<|reserved_special_token_56|>",
518
+ "lstrip": false,
519
+ "normalized": false,
520
+ "rstrip": false,
521
+ "single_word": false,
522
+ "special": true
523
+ },
524
+ "128065": {
525
+ "content": "<|reserved_special_token_57|>",
526
+ "lstrip": false,
527
+ "normalized": false,
528
+ "rstrip": false,
529
+ "single_word": false,
530
+ "special": true
531
+ },
532
+ "128066": {
533
+ "content": "<|reserved_special_token_58|>",
534
+ "lstrip": false,
535
+ "normalized": false,
536
+ "rstrip": false,
537
+ "single_word": false,
538
+ "special": true
539
+ },
540
+ "128067": {
541
+ "content": "<|reserved_special_token_59|>",
542
+ "lstrip": false,
543
+ "normalized": false,
544
+ "rstrip": false,
545
+ "single_word": false,
546
+ "special": true
547
+ },
548
+ "128068": {
549
+ "content": "<|reserved_special_token_60|>",
550
+ "lstrip": false,
551
+ "normalized": false,
552
+ "rstrip": false,
553
+ "single_word": false,
554
+ "special": true
555
+ },
556
+ "128069": {
557
+ "content": "<|reserved_special_token_61|>",
558
+ "lstrip": false,
559
+ "normalized": false,
560
+ "rstrip": false,
561
+ "single_word": false,
562
+ "special": true
563
+ },
564
+ "128070": {
565
+ "content": "<|reserved_special_token_62|>",
566
+ "lstrip": false,
567
+ "normalized": false,
568
+ "rstrip": false,
569
+ "single_word": false,
570
+ "special": true
571
+ },
572
+ "128071": {
573
+ "content": "<|reserved_special_token_63|>",
574
+ "lstrip": false,
575
+ "normalized": false,
576
+ "rstrip": false,
577
+ "single_word": false,
578
+ "special": true
579
+ },
580
+ "128072": {
581
+ "content": "<|reserved_special_token_64|>",
582
+ "lstrip": false,
583
+ "normalized": false,
584
+ "rstrip": false,
585
+ "single_word": false,
586
+ "special": true
587
+ },
588
+ "128073": {
589
+ "content": "<|reserved_special_token_65|>",
590
+ "lstrip": false,
591
+ "normalized": false,
592
+ "rstrip": false,
593
+ "single_word": false,
594
+ "special": true
595
+ },
596
+ "128074": {
597
+ "content": "<|reserved_special_token_66|>",
598
+ "lstrip": false,
599
+ "normalized": false,
600
+ "rstrip": false,
601
+ "single_word": false,
602
+ "special": true
603
+ },
604
+ "128075": {
605
+ "content": "<|reserved_special_token_67|>",
606
+ "lstrip": false,
607
+ "normalized": false,
608
+ "rstrip": false,
609
+ "single_word": false,
610
+ "special": true
611
+ },
612
+ "128076": {
613
+ "content": "<|reserved_special_token_68|>",
614
+ "lstrip": false,
615
+ "normalized": false,
616
+ "rstrip": false,
617
+ "single_word": false,
618
+ "special": true
619
+ },
620
+ "128077": {
621
+ "content": "<|reserved_special_token_69|>",
622
+ "lstrip": false,
623
+ "normalized": false,
624
+ "rstrip": false,
625
+ "single_word": false,
626
+ "special": true
627
+ },
628
+ "128078": {
629
+ "content": "<|reserved_special_token_70|>",
630
+ "lstrip": false,
631
+ "normalized": false,
632
+ "rstrip": false,
633
+ "single_word": false,
634
+ "special": true
635
+ },
636
+ "128079": {
637
+ "content": "<|reserved_special_token_71|>",
638
+ "lstrip": false,
639
+ "normalized": false,
640
+ "rstrip": false,
641
+ "single_word": false,
642
+ "special": true
643
+ },
644
+ "128080": {
645
+ "content": "<|reserved_special_token_72|>",
646
+ "lstrip": false,
647
+ "normalized": false,
648
+ "rstrip": false,
649
+ "single_word": false,
650
+ "special": true
651
+ },
652
+ "128081": {
653
+ "content": "<|reserved_special_token_73|>",
654
+ "lstrip": false,
655
+ "normalized": false,
656
+ "rstrip": false,
657
+ "single_word": false,
658
+ "special": true
659
+ },
660
+ "128082": {
661
+ "content": "<|reserved_special_token_74|>",
662
+ "lstrip": false,
663
+ "normalized": false,
664
+ "rstrip": false,
665
+ "single_word": false,
666
+ "special": true
667
+ },
668
+ "128083": {
669
+ "content": "<|reserved_special_token_75|>",
670
+ "lstrip": false,
671
+ "normalized": false,
672
+ "rstrip": false,
673
+ "single_word": false,
674
+ "special": true
675
+ },
676
+ "128084": {
677
+ "content": "<|reserved_special_token_76|>",
678
+ "lstrip": false,
679
+ "normalized": false,
680
+ "rstrip": false,
681
+ "single_word": false,
682
+ "special": true
683
+ },
684
+ "128085": {
685
+ "content": "<|reserved_special_token_77|>",
686
+ "lstrip": false,
687
+ "normalized": false,
688
+ "rstrip": false,
689
+ "single_word": false,
690
+ "special": true
691
+ },
692
+ "128086": {
693
+ "content": "<|reserved_special_token_78|>",
694
+ "lstrip": false,
695
+ "normalized": false,
696
+ "rstrip": false,
697
+ "single_word": false,
698
+ "special": true
699
+ },
700
+ "128087": {
701
+ "content": "<|reserved_special_token_79|>",
702
+ "lstrip": false,
703
+ "normalized": false,
704
+ "rstrip": false,
705
+ "single_word": false,
706
+ "special": true
707
+ },
708
+ "128088": {
709
+ "content": "<|reserved_special_token_80|>",
710
+ "lstrip": false,
711
+ "normalized": false,
712
+ "rstrip": false,
713
+ "single_word": false,
714
+ "special": true
715
+ },
716
+ "128089": {
717
+ "content": "<|reserved_special_token_81|>",
718
+ "lstrip": false,
719
+ "normalized": false,
720
+ "rstrip": false,
721
+ "single_word": false,
722
+ "special": true
723
+ },
724
+ "128090": {
725
+ "content": "<|reserved_special_token_82|>",
726
+ "lstrip": false,
727
+ "normalized": false,
728
+ "rstrip": false,
729
+ "single_word": false,
730
+ "special": true
731
+ },
732
+ "128091": {
733
+ "content": "<|reserved_special_token_83|>",
734
+ "lstrip": false,
735
+ "normalized": false,
736
+ "rstrip": false,
737
+ "single_word": false,
738
+ "special": true
739
+ },
740
+ "128092": {
741
+ "content": "<|reserved_special_token_84|>",
742
+ "lstrip": false,
743
+ "normalized": false,
744
+ "rstrip": false,
745
+ "single_word": false,
746
+ "special": true
747
+ },
748
+ "128093": {
749
+ "content": "<|reserved_special_token_85|>",
750
+ "lstrip": false,
751
+ "normalized": false,
752
+ "rstrip": false,
753
+ "single_word": false,
754
+ "special": true
755
+ },
756
+ "128094": {
757
+ "content": "<|reserved_special_token_86|>",
758
+ "lstrip": false,
759
+ "normalized": false,
760
+ "rstrip": false,
761
+ "single_word": false,
762
+ "special": true
763
+ },
764
+ "128095": {
765
+ "content": "<|reserved_special_token_87|>",
766
+ "lstrip": false,
767
+ "normalized": false,
768
+ "rstrip": false,
769
+ "single_word": false,
770
+ "special": true
771
+ },
772
+ "128096": {
773
+ "content": "<|reserved_special_token_88|>",
774
+ "lstrip": false,
775
+ "normalized": false,
776
+ "rstrip": false,
777
+ "single_word": false,
778
+ "special": true
779
+ },
780
+ "128097": {
781
+ "content": "<|reserved_special_token_89|>",
782
+ "lstrip": false,
783
+ "normalized": false,
784
+ "rstrip": false,
785
+ "single_word": false,
786
+ "special": true
787
+ },
788
+ "128098": {
789
+ "content": "<|reserved_special_token_90|>",
790
+ "lstrip": false,
791
+ "normalized": false,
792
+ "rstrip": false,
793
+ "single_word": false,
794
+ "special": true
795
+ },
796
+ "128099": {
797
+ "content": "<|reserved_special_token_91|>",
798
+ "lstrip": false,
799
+ "normalized": false,
800
+ "rstrip": false,
801
+ "single_word": false,
802
+ "special": true
803
+ },
804
+ "128100": {
805
+ "content": "<|reserved_special_token_92|>",
806
+ "lstrip": false,
807
+ "normalized": false,
808
+ "rstrip": false,
809
+ "single_word": false,
810
+ "special": true
811
+ },
812
+ "128101": {
813
+ "content": "<|reserved_special_token_93|>",
814
+ "lstrip": false,
815
+ "normalized": false,
816
+ "rstrip": false,
817
+ "single_word": false,
818
+ "special": true
819
+ },
820
+ "128102": {
821
+ "content": "<|reserved_special_token_94|>",
822
+ "lstrip": false,
823
+ "normalized": false,
824
+ "rstrip": false,
825
+ "single_word": false,
826
+ "special": true
827
+ },
828
+ "128103": {
829
+ "content": "<|reserved_special_token_95|>",
830
+ "lstrip": false,
831
+ "normalized": false,
832
+ "rstrip": false,
833
+ "single_word": false,
834
+ "special": true
835
+ },
836
+ "128104": {
837
+ "content": "<|reserved_special_token_96|>",
838
+ "lstrip": false,
839
+ "normalized": false,
840
+ "rstrip": false,
841
+ "single_word": false,
842
+ "special": true
843
+ },
844
+ "128105": {
845
+ "content": "<|reserved_special_token_97|>",
846
+ "lstrip": false,
847
+ "normalized": false,
848
+ "rstrip": false,
849
+ "single_word": false,
850
+ "special": true
851
+ },
852
+ "128106": {
853
+ "content": "<|reserved_special_token_98|>",
854
+ "lstrip": false,
855
+ "normalized": false,
856
+ "rstrip": false,
857
+ "single_word": false,
858
+ "special": true
859
+ },
860
+ "128107": {
861
+ "content": "<|reserved_special_token_99|>",
862
+ "lstrip": false,
863
+ "normalized": false,
864
+ "rstrip": false,
865
+ "single_word": false,
866
+ "special": true
867
+ },
868
+ "128108": {
869
+ "content": "<|reserved_special_token_100|>",
870
+ "lstrip": false,
871
+ "normalized": false,
872
+ "rstrip": false,
873
+ "single_word": false,
874
+ "special": true
875
+ },
876
+ "128109": {
877
+ "content": "<|reserved_special_token_101|>",
878
+ "lstrip": false,
879
+ "normalized": false,
880
+ "rstrip": false,
881
+ "single_word": false,
882
+ "special": true
883
+ },
884
+ "128110": {
885
+ "content": "<|reserved_special_token_102|>",
886
+ "lstrip": false,
887
+ "normalized": false,
888
+ "rstrip": false,
889
+ "single_word": false,
890
+ "special": true
891
+ },
892
+ "128111": {
893
+ "content": "<|reserved_special_token_103|>",
894
+ "lstrip": false,
895
+ "normalized": false,
896
+ "rstrip": false,
897
+ "single_word": false,
898
+ "special": true
899
+ },
900
+ "128112": {
901
+ "content": "<|reserved_special_token_104|>",
902
+ "lstrip": false,
903
+ "normalized": false,
904
+ "rstrip": false,
905
+ "single_word": false,
906
+ "special": true
907
+ },
908
+ "128113": {
909
+ "content": "<|reserved_special_token_105|>",
910
+ "lstrip": false,
911
+ "normalized": false,
912
+ "rstrip": false,
913
+ "single_word": false,
914
+ "special": true
915
+ },
916
+ "128114": {
917
+ "content": "<|reserved_special_token_106|>",
918
+ "lstrip": false,
919
+ "normalized": false,
920
+ "rstrip": false,
921
+ "single_word": false,
922
+ "special": true
923
+ },
924
+ "128115": {
925
+ "content": "<|reserved_special_token_107|>",
926
+ "lstrip": false,
927
+ "normalized": false,
928
+ "rstrip": false,
929
+ "single_word": false,
930
+ "special": true
931
+ },
932
+ "128116": {
933
+ "content": "<|reserved_special_token_108|>",
934
+ "lstrip": false,
935
+ "normalized": false,
936
+ "rstrip": false,
937
+ "single_word": false,
938
+ "special": true
939
+ },
940
+ "128117": {
941
+ "content": "<|reserved_special_token_109|>",
942
+ "lstrip": false,
943
+ "normalized": false,
944
+ "rstrip": false,
945
+ "single_word": false,
946
+ "special": true
947
+ },
948
+ "128118": {
949
+ "content": "<|reserved_special_token_110|>",
950
+ "lstrip": false,
951
+ "normalized": false,
952
+ "rstrip": false,
953
+ "single_word": false,
954
+ "special": true
955
+ },
956
+ "128119": {
957
+ "content": "<|reserved_special_token_111|>",
958
+ "lstrip": false,
959
+ "normalized": false,
960
+ "rstrip": false,
961
+ "single_word": false,
962
+ "special": true
963
+ },
964
+ "128120": {
965
+ "content": "<|reserved_special_token_112|>",
966
+ "lstrip": false,
967
+ "normalized": false,
968
+ "rstrip": false,
969
+ "single_word": false,
970
+ "special": true
971
+ },
972
+ "128121": {
973
+ "content": "<|reserved_special_token_113|>",
974
+ "lstrip": false,
975
+ "normalized": false,
976
+ "rstrip": false,
977
+ "single_word": false,
978
+ "special": true
979
+ },
980
+ "128122": {
981
+ "content": "<|reserved_special_token_114|>",
982
+ "lstrip": false,
983
+ "normalized": false,
984
+ "rstrip": false,
985
+ "single_word": false,
986
+ "special": true
987
+ },
988
+ "128123": {
989
+ "content": "<|reserved_special_token_115|>",
990
+ "lstrip": false,
991
+ "normalized": false,
992
+ "rstrip": false,
993
+ "single_word": false,
994
+ "special": true
995
+ },
996
+ "128124": {
997
+ "content": "<|reserved_special_token_116|>",
998
+ "lstrip": false,
999
+ "normalized": false,
1000
+ "rstrip": false,
1001
+ "single_word": false,
1002
+ "special": true
1003
+ },
1004
+ "128125": {
1005
+ "content": "<|reserved_special_token_117|>",
1006
+ "lstrip": false,
1007
+ "normalized": false,
1008
+ "rstrip": false,
1009
+ "single_word": false,
1010
+ "special": true
1011
+ },
1012
+ "128126": {
1013
+ "content": "<|reserved_special_token_118|>",
1014
+ "lstrip": false,
1015
+ "normalized": false,
1016
+ "rstrip": false,
1017
+ "single_word": false,
1018
+ "special": true
1019
+ },
1020
+ "128127": {
1021
+ "content": "<|reserved_special_token_119|>",
1022
+ "lstrip": false,
1023
+ "normalized": false,
1024
+ "rstrip": false,
1025
+ "single_word": false,
1026
+ "special": true
1027
+ },
1028
+ "128128": {
1029
+ "content": "<|reserved_special_token_120|>",
1030
+ "lstrip": false,
1031
+ "normalized": false,
1032
+ "rstrip": false,
1033
+ "single_word": false,
1034
+ "special": true
1035
+ },
1036
+ "128129": {
1037
+ "content": "<|reserved_special_token_121|>",
1038
+ "lstrip": false,
1039
+ "normalized": false,
1040
+ "rstrip": false,
1041
+ "single_word": false,
1042
+ "special": true
1043
+ },
1044
+ "128130": {
1045
+ "content": "<|reserved_special_token_122|>",
1046
+ "lstrip": false,
1047
+ "normalized": false,
1048
+ "rstrip": false,
1049
+ "single_word": false,
1050
+ "special": true
1051
+ },
1052
+ "128131": {
1053
+ "content": "<|reserved_special_token_123|>",
1054
+ "lstrip": false,
1055
+ "normalized": false,
1056
+ "rstrip": false,
1057
+ "single_word": false,
1058
+ "special": true
1059
+ },
1060
+ "128132": {
1061
+ "content": "<|reserved_special_token_124|>",
1062
+ "lstrip": false,
1063
+ "normalized": false,
1064
+ "rstrip": false,
1065
+ "single_word": false,
1066
+ "special": true
1067
+ },
1068
+ "128133": {
1069
+ "content": "<|reserved_special_token_125|>",
1070
+ "lstrip": false,
1071
+ "normalized": false,
1072
+ "rstrip": false,
1073
+ "single_word": false,
1074
+ "special": true
1075
+ },
1076
+ "128134": {
1077
+ "content": "<|reserved_special_token_126|>",
1078
+ "lstrip": false,
1079
+ "normalized": false,
1080
+ "rstrip": false,
1081
+ "single_word": false,
1082
+ "special": true
1083
+ },
1084
+ "128135": {
1085
+ "content": "<|reserved_special_token_127|>",
1086
+ "lstrip": false,
1087
+ "normalized": false,
1088
+ "rstrip": false,
1089
+ "single_word": false,
1090
+ "special": true
1091
+ },
1092
+ "128136": {
1093
+ "content": "<|reserved_special_token_128|>",
1094
+ "lstrip": false,
1095
+ "normalized": false,
1096
+ "rstrip": false,
1097
+ "single_word": false,
1098
+ "special": true
1099
+ },
1100
+ "128137": {
1101
+ "content": "<|reserved_special_token_129|>",
1102
+ "lstrip": false,
1103
+ "normalized": false,
1104
+ "rstrip": false,
1105
+ "single_word": false,
1106
+ "special": true
1107
+ },
1108
+ "128138": {
1109
+ "content": "<|reserved_special_token_130|>",
1110
+ "lstrip": false,
1111
+ "normalized": false,
1112
+ "rstrip": false,
1113
+ "single_word": false,
1114
+ "special": true
1115
+ },
1116
+ "128139": {
1117
+ "content": "<|reserved_special_token_131|>",
1118
+ "lstrip": false,
1119
+ "normalized": false,
1120
+ "rstrip": false,
1121
+ "single_word": false,
1122
+ "special": true
1123
+ },
1124
+ "128140": {
1125
+ "content": "<|reserved_special_token_132|>",
1126
+ "lstrip": false,
1127
+ "normalized": false,
1128
+ "rstrip": false,
1129
+ "single_word": false,
1130
+ "special": true
1131
+ },
1132
+ "128141": {
1133
+ "content": "<|reserved_special_token_133|>",
1134
+ "lstrip": false,
1135
+ "normalized": false,
1136
+ "rstrip": false,
1137
+ "single_word": false,
1138
+ "special": true
1139
+ },
1140
+ "128142": {
1141
+ "content": "<|reserved_special_token_134|>",
1142
+ "lstrip": false,
1143
+ "normalized": false,
1144
+ "rstrip": false,
1145
+ "single_word": false,
1146
+ "special": true
1147
+ },
1148
+ "128143": {
1149
+ "content": "<|reserved_special_token_135|>",
1150
+ "lstrip": false,
1151
+ "normalized": false,
1152
+ "rstrip": false,
1153
+ "single_word": false,
1154
+ "special": true
1155
+ },
1156
+ "128144": {
1157
+ "content": "<|reserved_special_token_136|>",
1158
+ "lstrip": false,
1159
+ "normalized": false,
1160
+ "rstrip": false,
1161
+ "single_word": false,
1162
+ "special": true
1163
+ },
1164
+ "128145": {
1165
+ "content": "<|reserved_special_token_137|>",
1166
+ "lstrip": false,
1167
+ "normalized": false,
1168
+ "rstrip": false,
1169
+ "single_word": false,
1170
+ "special": true
1171
+ },
1172
+ "128146": {
1173
+ "content": "<|reserved_special_token_138|>",
1174
+ "lstrip": false,
1175
+ "normalized": false,
1176
+ "rstrip": false,
1177
+ "single_word": false,
1178
+ "special": true
1179
+ },
1180
+ "128147": {
1181
+ "content": "<|reserved_special_token_139|>",
1182
+ "lstrip": false,
1183
+ "normalized": false,
1184
+ "rstrip": false,
1185
+ "single_word": false,
1186
+ "special": true
1187
+ },
1188
+ "128148": {
1189
+ "content": "<|reserved_special_token_140|>",
1190
+ "lstrip": false,
1191
+ "normalized": false,
1192
+ "rstrip": false,
1193
+ "single_word": false,
1194
+ "special": true
1195
+ },
1196
+ "128149": {
1197
+ "content": "<|reserved_special_token_141|>",
1198
+ "lstrip": false,
1199
+ "normalized": false,
1200
+ "rstrip": false,
1201
+ "single_word": false,
1202
+ "special": true
1203
+ },
1204
+ "128150": {
1205
+ "content": "<|reserved_special_token_142|>",
1206
+ "lstrip": false,
1207
+ "normalized": false,
1208
+ "rstrip": false,
1209
+ "single_word": false,
1210
+ "special": true
1211
+ },
1212
+ "128151": {
1213
+ "content": "<|reserved_special_token_143|>",
1214
+ "lstrip": false,
1215
+ "normalized": false,
1216
+ "rstrip": false,
1217
+ "single_word": false,
1218
+ "special": true
1219
+ },
1220
+ "128152": {
1221
+ "content": "<|reserved_special_token_144|>",
1222
+ "lstrip": false,
1223
+ "normalized": false,
1224
+ "rstrip": false,
1225
+ "single_word": false,
1226
+ "special": true
1227
+ },
1228
+ "128153": {
1229
+ "content": "<|reserved_special_token_145|>",
1230
+ "lstrip": false,
1231
+ "normalized": false,
1232
+ "rstrip": false,
1233
+ "single_word": false,
1234
+ "special": true
1235
+ },
1236
+ "128154": {
1237
+ "content": "<|reserved_special_token_146|>",
1238
+ "lstrip": false,
1239
+ "normalized": false,
1240
+ "rstrip": false,
1241
+ "single_word": false,
1242
+ "special": true
1243
+ },
1244
+ "128155": {
1245
+ "content": "<|reserved_special_token_147|>",
1246
+ "lstrip": false,
1247
+ "normalized": false,
1248
+ "rstrip": false,
1249
+ "single_word": false,
1250
+ "special": true
1251
+ },
1252
+ "128156": {
1253
+ "content": "<|reserved_special_token_148|>",
1254
+ "lstrip": false,
1255
+ "normalized": false,
1256
+ "rstrip": false,
1257
+ "single_word": false,
1258
+ "special": true
1259
+ },
1260
+ "128157": {
1261
+ "content": "<|reserved_special_token_149|>",
1262
+ "lstrip": false,
1263
+ "normalized": false,
1264
+ "rstrip": false,
1265
+ "single_word": false,
1266
+ "special": true
1267
+ },
1268
+ "128158": {
1269
+ "content": "<|reserved_special_token_150|>",
1270
+ "lstrip": false,
1271
+ "normalized": false,
1272
+ "rstrip": false,
1273
+ "single_word": false,
1274
+ "special": true
1275
+ },
1276
+ "128159": {
1277
+ "content": "<|reserved_special_token_151|>",
1278
+ "lstrip": false,
1279
+ "normalized": false,
1280
+ "rstrip": false,
1281
+ "single_word": false,
1282
+ "special": true
1283
+ },
1284
+ "128160": {
1285
+ "content": "<|reserved_special_token_152|>",
1286
+ "lstrip": false,
1287
+ "normalized": false,
1288
+ "rstrip": false,
1289
+ "single_word": false,
1290
+ "special": true
1291
+ },
1292
+ "128161": {
1293
+ "content": "<|reserved_special_token_153|>",
1294
+ "lstrip": false,
1295
+ "normalized": false,
1296
+ "rstrip": false,
1297
+ "single_word": false,
1298
+ "special": true
1299
+ },
1300
+ "128162": {
1301
+ "content": "<|reserved_special_token_154|>",
1302
+ "lstrip": false,
1303
+ "normalized": false,
1304
+ "rstrip": false,
1305
+ "single_word": false,
1306
+ "special": true
1307
+ },
1308
+ "128163": {
1309
+ "content": "<|reserved_special_token_155|>",
1310
+ "lstrip": false,
1311
+ "normalized": false,
1312
+ "rstrip": false,
1313
+ "single_word": false,
1314
+ "special": true
1315
+ },
1316
+ "128164": {
1317
+ "content": "<|reserved_special_token_156|>",
1318
+ "lstrip": false,
1319
+ "normalized": false,
1320
+ "rstrip": false,
1321
+ "single_word": false,
1322
+ "special": true
1323
+ },
1324
+ "128165": {
1325
+ "content": "<|reserved_special_token_157|>",
1326
+ "lstrip": false,
1327
+ "normalized": false,
1328
+ "rstrip": false,
1329
+ "single_word": false,
1330
+ "special": true
1331
+ },
1332
+ "128166": {
1333
+ "content": "<|reserved_special_token_158|>",
1334
+ "lstrip": false,
1335
+ "normalized": false,
1336
+ "rstrip": false,
1337
+ "single_word": false,
1338
+ "special": true
1339
+ },
1340
+ "128167": {
1341
+ "content": "<|reserved_special_token_159|>",
1342
+ "lstrip": false,
1343
+ "normalized": false,
1344
+ "rstrip": false,
1345
+ "single_word": false,
1346
+ "special": true
1347
+ },
1348
+ "128168": {
1349
+ "content": "<|reserved_special_token_160|>",
1350
+ "lstrip": false,
1351
+ "normalized": false,
1352
+ "rstrip": false,
1353
+ "single_word": false,
1354
+ "special": true
1355
+ },
1356
+ "128169": {
1357
+ "content": "<|reserved_special_token_161|>",
1358
+ "lstrip": false,
1359
+ "normalized": false,
1360
+ "rstrip": false,
1361
+ "single_word": false,
1362
+ "special": true
1363
+ },
1364
+ "128170": {
1365
+ "content": "<|reserved_special_token_162|>",
1366
+ "lstrip": false,
1367
+ "normalized": false,
1368
+ "rstrip": false,
1369
+ "single_word": false,
1370
+ "special": true
1371
+ },
1372
+ "128171": {
1373
+ "content": "<|reserved_special_token_163|>",
1374
+ "lstrip": false,
1375
+ "normalized": false,
1376
+ "rstrip": false,
1377
+ "single_word": false,
1378
+ "special": true
1379
+ },
1380
+ "128172": {
1381
+ "content": "<|reserved_special_token_164|>",
1382
+ "lstrip": false,
1383
+ "normalized": false,
1384
+ "rstrip": false,
1385
+ "single_word": false,
1386
+ "special": true
1387
+ },
1388
+ "128173": {
1389
+ "content": "<|reserved_special_token_165|>",
1390
+ "lstrip": false,
1391
+ "normalized": false,
1392
+ "rstrip": false,
1393
+ "single_word": false,
1394
+ "special": true
1395
+ },
1396
+ "128174": {
1397
+ "content": "<|reserved_special_token_166|>",
1398
+ "lstrip": false,
1399
+ "normalized": false,
1400
+ "rstrip": false,
1401
+ "single_word": false,
1402
+ "special": true
1403
+ },
1404
+ "128175": {
1405
+ "content": "<|reserved_special_token_167|>",
1406
+ "lstrip": false,
1407
+ "normalized": false,
1408
+ "rstrip": false,
1409
+ "single_word": false,
1410
+ "special": true
1411
+ },
1412
+ "128176": {
1413
+ "content": "<|reserved_special_token_168|>",
1414
+ "lstrip": false,
1415
+ "normalized": false,
1416
+ "rstrip": false,
1417
+ "single_word": false,
1418
+ "special": true
1419
+ },
1420
+ "128177": {
1421
+ "content": "<|reserved_special_token_169|>",
1422
+ "lstrip": false,
1423
+ "normalized": false,
1424
+ "rstrip": false,
1425
+ "single_word": false,
1426
+ "special": true
1427
+ },
1428
+ "128178": {
1429
+ "content": "<|reserved_special_token_170|>",
1430
+ "lstrip": false,
1431
+ "normalized": false,
1432
+ "rstrip": false,
1433
+ "single_word": false,
1434
+ "special": true
1435
+ },
1436
+ "128179": {
1437
+ "content": "<|reserved_special_token_171|>",
1438
+ "lstrip": false,
1439
+ "normalized": false,
1440
+ "rstrip": false,
1441
+ "single_word": false,
1442
+ "special": true
1443
+ },
1444
+ "128180": {
1445
+ "content": "<|reserved_special_token_172|>",
1446
+ "lstrip": false,
1447
+ "normalized": false,
1448
+ "rstrip": false,
1449
+ "single_word": false,
1450
+ "special": true
1451
+ },
1452
+ "128181": {
1453
+ "content": "<|reserved_special_token_173|>",
1454
+ "lstrip": false,
1455
+ "normalized": false,
1456
+ "rstrip": false,
1457
+ "single_word": false,
1458
+ "special": true
1459
+ },
1460
+ "128182": {
1461
+ "content": "<|reserved_special_token_174|>",
1462
+ "lstrip": false,
1463
+ "normalized": false,
1464
+ "rstrip": false,
1465
+ "single_word": false,
1466
+ "special": true
1467
+ },
1468
+ "128183": {
1469
+ "content": "<|reserved_special_token_175|>",
1470
+ "lstrip": false,
1471
+ "normalized": false,
1472
+ "rstrip": false,
1473
+ "single_word": false,
1474
+ "special": true
1475
+ },
1476
+ "128184": {
1477
+ "content": "<|reserved_special_token_176|>",
1478
+ "lstrip": false,
1479
+ "normalized": false,
1480
+ "rstrip": false,
1481
+ "single_word": false,
1482
+ "special": true
1483
+ },
1484
+ "128185": {
1485
+ "content": "<|reserved_special_token_177|>",
1486
+ "lstrip": false,
1487
+ "normalized": false,
1488
+ "rstrip": false,
1489
+ "single_word": false,
1490
+ "special": true
1491
+ },
1492
+ "128186": {
1493
+ "content": "<|reserved_special_token_178|>",
1494
+ "lstrip": false,
1495
+ "normalized": false,
1496
+ "rstrip": false,
1497
+ "single_word": false,
1498
+ "special": true
1499
+ },
1500
+ "128187": {
1501
+ "content": "<|reserved_special_token_179|>",
1502
+ "lstrip": false,
1503
+ "normalized": false,
1504
+ "rstrip": false,
1505
+ "single_word": false,
1506
+ "special": true
1507
+ },
1508
+ "128188": {
1509
+ "content": "<|reserved_special_token_180|>",
1510
+ "lstrip": false,
1511
+ "normalized": false,
1512
+ "rstrip": false,
1513
+ "single_word": false,
1514
+ "special": true
1515
+ },
1516
+ "128189": {
1517
+ "content": "<|reserved_special_token_181|>",
1518
+ "lstrip": false,
1519
+ "normalized": false,
1520
+ "rstrip": false,
1521
+ "single_word": false,
1522
+ "special": true
1523
+ },
1524
+ "128190": {
1525
+ "content": "<|reserved_special_token_182|>",
1526
+ "lstrip": false,
1527
+ "normalized": false,
1528
+ "rstrip": false,
1529
+ "single_word": false,
1530
+ "special": true
1531
+ },
1532
+ "128191": {
1533
+ "content": "<|reserved_special_token_183|>",
1534
+ "lstrip": false,
1535
+ "normalized": false,
1536
+ "rstrip": false,
1537
+ "single_word": false,
1538
+ "special": true
1539
+ },
1540
+ "128192": {
1541
+ "content": "<|reserved_special_token_184|>",
1542
+ "lstrip": false,
1543
+ "normalized": false,
1544
+ "rstrip": false,
1545
+ "single_word": false,
1546
+ "special": true
1547
+ },
1548
+ "128193": {
1549
+ "content": "<|reserved_special_token_185|>",
1550
+ "lstrip": false,
1551
+ "normalized": false,
1552
+ "rstrip": false,
1553
+ "single_word": false,
1554
+ "special": true
1555
+ },
1556
+ "128194": {
1557
+ "content": "<|reserved_special_token_186|>",
1558
+ "lstrip": false,
1559
+ "normalized": false,
1560
+ "rstrip": false,
1561
+ "single_word": false,
1562
+ "special": true
1563
+ },
1564
+ "128195": {
1565
+ "content": "<|reserved_special_token_187|>",
1566
+ "lstrip": false,
1567
+ "normalized": false,
1568
+ "rstrip": false,
1569
+ "single_word": false,
1570
+ "special": true
1571
+ },
1572
+ "128196": {
1573
+ "content": "<|reserved_special_token_188|>",
1574
+ "lstrip": false,
1575
+ "normalized": false,
1576
+ "rstrip": false,
1577
+ "single_word": false,
1578
+ "special": true
1579
+ },
1580
+ "128197": {
1581
+ "content": "<|reserved_special_token_189|>",
1582
+ "lstrip": false,
1583
+ "normalized": false,
1584
+ "rstrip": false,
1585
+ "single_word": false,
1586
+ "special": true
1587
+ },
1588
+ "128198": {
1589
+ "content": "<|reserved_special_token_190|>",
1590
+ "lstrip": false,
1591
+ "normalized": false,
1592
+ "rstrip": false,
1593
+ "single_word": false,
1594
+ "special": true
1595
+ },
1596
+ "128199": {
1597
+ "content": "<|reserved_special_token_191|>",
1598
+ "lstrip": false,
1599
+ "normalized": false,
1600
+ "rstrip": false,
1601
+ "single_word": false,
1602
+ "special": true
1603
+ },
1604
+ "128200": {
1605
+ "content": "<|reserved_special_token_192|>",
1606
+ "lstrip": false,
1607
+ "normalized": false,
1608
+ "rstrip": false,
1609
+ "single_word": false,
1610
+ "special": true
1611
+ },
1612
+ "128201": {
1613
+ "content": "<|reserved_special_token_193|>",
1614
+ "lstrip": false,
1615
+ "normalized": false,
1616
+ "rstrip": false,
1617
+ "single_word": false,
1618
+ "special": true
1619
+ },
1620
+ "128202": {
1621
+ "content": "<|reserved_special_token_194|>",
1622
+ "lstrip": false,
1623
+ "normalized": false,
1624
+ "rstrip": false,
1625
+ "single_word": false,
1626
+ "special": true
1627
+ },
1628
+ "128203": {
1629
+ "content": "<|reserved_special_token_195|>",
1630
+ "lstrip": false,
1631
+ "normalized": false,
1632
+ "rstrip": false,
1633
+ "single_word": false,
1634
+ "special": true
1635
+ },
1636
+ "128204": {
1637
+ "content": "<|reserved_special_token_196|>",
1638
+ "lstrip": false,
1639
+ "normalized": false,
1640
+ "rstrip": false,
1641
+ "single_word": false,
1642
+ "special": true
1643
+ },
1644
+ "128205": {
1645
+ "content": "<|reserved_special_token_197|>",
1646
+ "lstrip": false,
1647
+ "normalized": false,
1648
+ "rstrip": false,
1649
+ "single_word": false,
1650
+ "special": true
1651
+ },
1652
+ "128206": {
1653
+ "content": "<|reserved_special_token_198|>",
1654
+ "lstrip": false,
1655
+ "normalized": false,
1656
+ "rstrip": false,
1657
+ "single_word": false,
1658
+ "special": true
1659
+ },
1660
+ "128207": {
1661
+ "content": "<|reserved_special_token_199|>",
1662
+ "lstrip": false,
1663
+ "normalized": false,
1664
+ "rstrip": false,
1665
+ "single_word": false,
1666
+ "special": true
1667
+ },
1668
+ "128208": {
1669
+ "content": "<|reserved_special_token_200|>",
1670
+ "lstrip": false,
1671
+ "normalized": false,
1672
+ "rstrip": false,
1673
+ "single_word": false,
1674
+ "special": true
1675
+ },
1676
+ "128209": {
1677
+ "content": "<|reserved_special_token_201|>",
1678
+ "lstrip": false,
1679
+ "normalized": false,
1680
+ "rstrip": false,
1681
+ "single_word": false,
1682
+ "special": true
1683
+ },
1684
+ "128210": {
1685
+ "content": "<|reserved_special_token_202|>",
1686
+ "lstrip": false,
1687
+ "normalized": false,
1688
+ "rstrip": false,
1689
+ "single_word": false,
1690
+ "special": true
1691
+ },
1692
+ "128211": {
1693
+ "content": "<|reserved_special_token_203|>",
1694
+ "lstrip": false,
1695
+ "normalized": false,
1696
+ "rstrip": false,
1697
+ "single_word": false,
1698
+ "special": true
1699
+ },
1700
+ "128212": {
1701
+ "content": "<|reserved_special_token_204|>",
1702
+ "lstrip": false,
1703
+ "normalized": false,
1704
+ "rstrip": false,
1705
+ "single_word": false,
1706
+ "special": true
1707
+ },
1708
+ "128213": {
1709
+ "content": "<|reserved_special_token_205|>",
1710
+ "lstrip": false,
1711
+ "normalized": false,
1712
+ "rstrip": false,
1713
+ "single_word": false,
1714
+ "special": true
1715
+ },
1716
+ "128214": {
1717
+ "content": "<|reserved_special_token_206|>",
1718
+ "lstrip": false,
1719
+ "normalized": false,
1720
+ "rstrip": false,
1721
+ "single_word": false,
1722
+ "special": true
1723
+ },
1724
+ "128215": {
1725
+ "content": "<|reserved_special_token_207|>",
1726
+ "lstrip": false,
1727
+ "normalized": false,
1728
+ "rstrip": false,
1729
+ "single_word": false,
1730
+ "special": true
1731
+ },
1732
+ "128216": {
1733
+ "content": "<|reserved_special_token_208|>",
1734
+ "lstrip": false,
1735
+ "normalized": false,
1736
+ "rstrip": false,
1737
+ "single_word": false,
1738
+ "special": true
1739
+ },
1740
+ "128217": {
1741
+ "content": "<|reserved_special_token_209|>",
1742
+ "lstrip": false,
1743
+ "normalized": false,
1744
+ "rstrip": false,
1745
+ "single_word": false,
1746
+ "special": true
1747
+ },
1748
+ "128218": {
1749
+ "content": "<|reserved_special_token_210|>",
1750
+ "lstrip": false,
1751
+ "normalized": false,
1752
+ "rstrip": false,
1753
+ "single_word": false,
1754
+ "special": true
1755
+ },
1756
+ "128219": {
1757
+ "content": "<|reserved_special_token_211|>",
1758
+ "lstrip": false,
1759
+ "normalized": false,
1760
+ "rstrip": false,
1761
+ "single_word": false,
1762
+ "special": true
1763
+ },
1764
+ "128220": {
1765
+ "content": "<|reserved_special_token_212|>",
1766
+ "lstrip": false,
1767
+ "normalized": false,
1768
+ "rstrip": false,
1769
+ "single_word": false,
1770
+ "special": true
1771
+ },
1772
+ "128221": {
1773
+ "content": "<|reserved_special_token_213|>",
1774
+ "lstrip": false,
1775
+ "normalized": false,
1776
+ "rstrip": false,
1777
+ "single_word": false,
1778
+ "special": true
1779
+ },
1780
+ "128222": {
1781
+ "content": "<|reserved_special_token_214|>",
1782
+ "lstrip": false,
1783
+ "normalized": false,
1784
+ "rstrip": false,
1785
+ "single_word": false,
1786
+ "special": true
1787
+ },
1788
+ "128223": {
1789
+ "content": "<|reserved_special_token_215|>",
1790
+ "lstrip": false,
1791
+ "normalized": false,
1792
+ "rstrip": false,
1793
+ "single_word": false,
1794
+ "special": true
1795
+ },
1796
+ "128224": {
1797
+ "content": "<|reserved_special_token_216|>",
1798
+ "lstrip": false,
1799
+ "normalized": false,
1800
+ "rstrip": false,
1801
+ "single_word": false,
1802
+ "special": true
1803
+ },
1804
+ "128225": {
1805
+ "content": "<|reserved_special_token_217|>",
1806
+ "lstrip": false,
1807
+ "normalized": false,
1808
+ "rstrip": false,
1809
+ "single_word": false,
1810
+ "special": true
1811
+ },
1812
+ "128226": {
1813
+ "content": "<|reserved_special_token_218|>",
1814
+ "lstrip": false,
1815
+ "normalized": false,
1816
+ "rstrip": false,
1817
+ "single_word": false,
1818
+ "special": true
1819
+ },
1820
+ "128227": {
1821
+ "content": "<|reserved_special_token_219|>",
1822
+ "lstrip": false,
1823
+ "normalized": false,
1824
+ "rstrip": false,
1825
+ "single_word": false,
1826
+ "special": true
1827
+ },
1828
+ "128228": {
1829
+ "content": "<|reserved_special_token_220|>",
1830
+ "lstrip": false,
1831
+ "normalized": false,
1832
+ "rstrip": false,
1833
+ "single_word": false,
1834
+ "special": true
1835
+ },
1836
+ "128229": {
1837
+ "content": "<|reserved_special_token_221|>",
1838
+ "lstrip": false,
1839
+ "normalized": false,
1840
+ "rstrip": false,
1841
+ "single_word": false,
1842
+ "special": true
1843
+ },
1844
+ "128230": {
1845
+ "content": "<|reserved_special_token_222|>",
1846
+ "lstrip": false,
1847
+ "normalized": false,
1848
+ "rstrip": false,
1849
+ "single_word": false,
1850
+ "special": true
1851
+ },
1852
+ "128231": {
1853
+ "content": "<|reserved_special_token_223|>",
1854
+ "lstrip": false,
1855
+ "normalized": false,
1856
+ "rstrip": false,
1857
+ "single_word": false,
1858
+ "special": true
1859
+ },
1860
+ "128232": {
1861
+ "content": "<|reserved_special_token_224|>",
1862
+ "lstrip": false,
1863
+ "normalized": false,
1864
+ "rstrip": false,
1865
+ "single_word": false,
1866
+ "special": true
1867
+ },
1868
+ "128233": {
1869
+ "content": "<|reserved_special_token_225|>",
1870
+ "lstrip": false,
1871
+ "normalized": false,
1872
+ "rstrip": false,
1873
+ "single_word": false,
1874
+ "special": true
1875
+ },
1876
+ "128234": {
1877
+ "content": "<|reserved_special_token_226|>",
1878
+ "lstrip": false,
1879
+ "normalized": false,
1880
+ "rstrip": false,
1881
+ "single_word": false,
1882
+ "special": true
1883
+ },
1884
+ "128235": {
1885
+ "content": "<|reserved_special_token_227|>",
1886
+ "lstrip": false,
1887
+ "normalized": false,
1888
+ "rstrip": false,
1889
+ "single_word": false,
1890
+ "special": true
1891
+ },
1892
+ "128236": {
1893
+ "content": "<|reserved_special_token_228|>",
1894
+ "lstrip": false,
1895
+ "normalized": false,
1896
+ "rstrip": false,
1897
+ "single_word": false,
1898
+ "special": true
1899
+ },
1900
+ "128237": {
1901
+ "content": "<|reserved_special_token_229|>",
1902
+ "lstrip": false,
1903
+ "normalized": false,
1904
+ "rstrip": false,
1905
+ "single_word": false,
1906
+ "special": true
1907
+ },
1908
+ "128238": {
1909
+ "content": "<|reserved_special_token_230|>",
1910
+ "lstrip": false,
1911
+ "normalized": false,
1912
+ "rstrip": false,
1913
+ "single_word": false,
1914
+ "special": true
1915
+ },
1916
+ "128239": {
1917
+ "content": "<|reserved_special_token_231|>",
1918
+ "lstrip": false,
1919
+ "normalized": false,
1920
+ "rstrip": false,
1921
+ "single_word": false,
1922
+ "special": true
1923
+ },
1924
+ "128240": {
1925
+ "content": "<|reserved_special_token_232|>",
1926
+ "lstrip": false,
1927
+ "normalized": false,
1928
+ "rstrip": false,
1929
+ "single_word": false,
1930
+ "special": true
1931
+ },
1932
+ "128241": {
1933
+ "content": "<|reserved_special_token_233|>",
1934
+ "lstrip": false,
1935
+ "normalized": false,
1936
+ "rstrip": false,
1937
+ "single_word": false,
1938
+ "special": true
1939
+ },
1940
+ "128242": {
1941
+ "content": "<|reserved_special_token_234|>",
1942
+ "lstrip": false,
1943
+ "normalized": false,
1944
+ "rstrip": false,
1945
+ "single_word": false,
1946
+ "special": true
1947
+ },
1948
+ "128243": {
1949
+ "content": "<|reserved_special_token_235|>",
1950
+ "lstrip": false,
1951
+ "normalized": false,
1952
+ "rstrip": false,
1953
+ "single_word": false,
1954
+ "special": true
1955
+ },
1956
+ "128244": {
1957
+ "content": "<|reserved_special_token_236|>",
1958
+ "lstrip": false,
1959
+ "normalized": false,
1960
+ "rstrip": false,
1961
+ "single_word": false,
1962
+ "special": true
1963
+ },
1964
+ "128245": {
1965
+ "content": "<|reserved_special_token_237|>",
1966
+ "lstrip": false,
1967
+ "normalized": false,
1968
+ "rstrip": false,
1969
+ "single_word": false,
1970
+ "special": true
1971
+ },
1972
+ "128246": {
1973
+ "content": "<|reserved_special_token_238|>",
1974
+ "lstrip": false,
1975
+ "normalized": false,
1976
+ "rstrip": false,
1977
+ "single_word": false,
1978
+ "special": true
1979
+ },
1980
+ "128247": {
1981
+ "content": "<|reserved_special_token_239|>",
1982
+ "lstrip": false,
1983
+ "normalized": false,
1984
+ "rstrip": false,
1985
+ "single_word": false,
1986
+ "special": true
1987
+ },
1988
+ "128248": {
1989
+ "content": "<|reserved_special_token_240|>",
1990
+ "lstrip": false,
1991
+ "normalized": false,
1992
+ "rstrip": false,
1993
+ "single_word": false,
1994
+ "special": true
1995
+ },
1996
+ "128249": {
1997
+ "content": "<|reserved_special_token_241|>",
1998
+ "lstrip": false,
1999
+ "normalized": false,
2000
+ "rstrip": false,
2001
+ "single_word": false,
2002
+ "special": true
2003
+ },
2004
+ "128250": {
2005
+ "content": "<|reserved_special_token_242|>",
2006
+ "lstrip": false,
2007
+ "normalized": false,
2008
+ "rstrip": false,
2009
+ "single_word": false,
2010
+ "special": true
2011
+ },
2012
+ "128251": {
2013
+ "content": "<|reserved_special_token_243|>",
2014
+ "lstrip": false,
2015
+ "normalized": false,
2016
+ "rstrip": false,
2017
+ "single_word": false,
2018
+ "special": true
2019
+ },
2020
+ "128252": {
2021
+ "content": "<|reserved_special_token_244|>",
2022
+ "lstrip": false,
2023
+ "normalized": false,
2024
+ "rstrip": false,
2025
+ "single_word": false,
2026
+ "special": true
2027
+ },
2028
+ "128253": {
2029
+ "content": "<|reserved_special_token_245|>",
2030
+ "lstrip": false,
2031
+ "normalized": false,
2032
+ "rstrip": false,
2033
+ "single_word": false,
2034
+ "special": true
2035
+ },
2036
+ "128254": {
2037
+ "content": "<|reserved_special_token_246|>",
2038
+ "lstrip": false,
2039
+ "normalized": false,
2040
+ "rstrip": false,
2041
+ "single_word": false,
2042
+ "special": true
2043
+ },
2044
+ "128255": {
2045
+ "content": "<|reserved_special_token_247|>",
2046
+ "lstrip": false,
2047
+ "normalized": false,
2048
+ "rstrip": false,
2049
+ "single_word": false,
2050
+ "special": true
2051
+ }
2052
+ },
2053
+ "additional_special_tokens": [
2054
+ "<|eot_id|>",
2055
+ "<|eom_id|>"
2056
+ ],
2057
+ "bos_token": "<|begin_of_text|>",
2058
+ "chat_template": "{{ '<|begin_of_text|>' }}{% 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 %}{{ '<|start_header_id|>system<|end_header_id|>\n\n' + system_message + '<|eot_id|>' }}{% endif %}{% for message in loop_messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ '<|start_header_id|>user<|end_header_id|>\n\n' + content + '<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n' }}{% elif message['role'] == 'assistant' %}{{ content + '<|eot_id|>' }}{% endif %}{% endfor %}",
2059
+ "clean_up_tokenization_spaces": true,
2060
+ "eos_token": "<|end_of_text|>",
2061
+ "extra_special_tokens": {},
2062
+ "model_input_names": [
2063
+ "input_ids",
2064
+ "attention_mask"
2065
+ ],
2066
+ "model_max_length": 12288,
2067
+ "pad_token": "<|finetune_right_pad_id|>",
2068
+ "padding_side": "right",
2069
+ "split_special_tokens": false,
2070
+ "tokenizer_class": "PreTrainedTokenizerFast",
2071
+ "unk_token": null
2072
+ }
train_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 3.0,
3
+ "total_flos": 3.0626432822122906e+18,
4
+ "train_loss": 0.8061501924692238,
5
+ "train_runtime": 22473.7337,
6
+ "train_samples_per_second": 0.246,
7
+ "train_steps_per_second": 0.246
8
+ }
trainer_log.jsonl ADDED
The diff for this file is too large to render. See raw diff
 
trainer_state.json ADDED
@@ -0,0 +1,3913 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 3.0,
5
+ "eval_steps": 500,
6
+ "global_step": 5535,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.005420054200542005,
13
+ "grad_norm": 0.0,
14
+ "learning_rate": 1.8050541516245488e-06,
15
+ "loss": 1.3502,
16
+ "step": 10
17
+ },
18
+ {
19
+ "epoch": 0.01084010840108401,
20
+ "grad_norm": 0.0,
21
+ "learning_rate": 3.6101083032490977e-06,
22
+ "loss": 1.3193,
23
+ "step": 20
24
+ },
25
+ {
26
+ "epoch": 0.016260162601626018,
27
+ "grad_norm": 0.0,
28
+ "learning_rate": 5.4151624548736465e-06,
29
+ "loss": 1.3226,
30
+ "step": 30
31
+ },
32
+ {
33
+ "epoch": 0.02168021680216802,
34
+ "grad_norm": 0.0,
35
+ "learning_rate": 7.220216606498195e-06,
36
+ "loss": 1.2298,
37
+ "step": 40
38
+ },
39
+ {
40
+ "epoch": 0.02710027100271003,
41
+ "grad_norm": 0.0,
42
+ "learning_rate": 9.025270758122744e-06,
43
+ "loss": 1.1955,
44
+ "step": 50
45
+ },
46
+ {
47
+ "epoch": 0.032520325203252036,
48
+ "grad_norm": 0.0,
49
+ "learning_rate": 1.0830324909747293e-05,
50
+ "loss": 1.3366,
51
+ "step": 60
52
+ },
53
+ {
54
+ "epoch": 0.037940379403794036,
55
+ "grad_norm": 0.0,
56
+ "learning_rate": 1.263537906137184e-05,
57
+ "loss": 1.2038,
58
+ "step": 70
59
+ },
60
+ {
61
+ "epoch": 0.04336043360433604,
62
+ "grad_norm": 0.0,
63
+ "learning_rate": 1.444043321299639e-05,
64
+ "loss": 1.2876,
65
+ "step": 80
66
+ },
67
+ {
68
+ "epoch": 0.04878048780487805,
69
+ "grad_norm": 0.0,
70
+ "learning_rate": 1.624548736462094e-05,
71
+ "loss": 1.0663,
72
+ "step": 90
73
+ },
74
+ {
75
+ "epoch": 0.05420054200542006,
76
+ "grad_norm": 0.0,
77
+ "learning_rate": 1.805054151624549e-05,
78
+ "loss": 1.0746,
79
+ "step": 100
80
+ },
81
+ {
82
+ "epoch": 0.05962059620596206,
83
+ "grad_norm": 0.0,
84
+ "learning_rate": 1.9855595667870036e-05,
85
+ "loss": 1.1507,
86
+ "step": 110
87
+ },
88
+ {
89
+ "epoch": 0.06504065040650407,
90
+ "grad_norm": 0.0,
91
+ "learning_rate": 2.1660649819494586e-05,
92
+ "loss": 1.108,
93
+ "step": 120
94
+ },
95
+ {
96
+ "epoch": 0.07046070460704607,
97
+ "grad_norm": 0.0,
98
+ "learning_rate": 2.3465703971119137e-05,
99
+ "loss": 1.0929,
100
+ "step": 130
101
+ },
102
+ {
103
+ "epoch": 0.07588075880758807,
104
+ "grad_norm": 0.0,
105
+ "learning_rate": 2.527075812274368e-05,
106
+ "loss": 1.0056,
107
+ "step": 140
108
+ },
109
+ {
110
+ "epoch": 0.08130081300813008,
111
+ "grad_norm": 0.0,
112
+ "learning_rate": 2.7075812274368234e-05,
113
+ "loss": 1.2323,
114
+ "step": 150
115
+ },
116
+ {
117
+ "epoch": 0.08672086720867209,
118
+ "grad_norm": 0.0,
119
+ "learning_rate": 2.888086642599278e-05,
120
+ "loss": 1.1624,
121
+ "step": 160
122
+ },
123
+ {
124
+ "epoch": 0.0921409214092141,
125
+ "grad_norm": 0.0,
126
+ "learning_rate": 3.0685920577617325e-05,
127
+ "loss": 1.1477,
128
+ "step": 170
129
+ },
130
+ {
131
+ "epoch": 0.0975609756097561,
132
+ "grad_norm": 0.0,
133
+ "learning_rate": 3.249097472924188e-05,
134
+ "loss": 1.1886,
135
+ "step": 180
136
+ },
137
+ {
138
+ "epoch": 0.10298102981029811,
139
+ "grad_norm": 0.0,
140
+ "learning_rate": 3.4296028880866426e-05,
141
+ "loss": 1.0738,
142
+ "step": 190
143
+ },
144
+ {
145
+ "epoch": 0.10840108401084012,
146
+ "grad_norm": 0.0,
147
+ "learning_rate": 3.610108303249098e-05,
148
+ "loss": 1.103,
149
+ "step": 200
150
+ },
151
+ {
152
+ "epoch": 0.11382113821138211,
153
+ "grad_norm": 0.0,
154
+ "learning_rate": 3.790613718411553e-05,
155
+ "loss": 1.25,
156
+ "step": 210
157
+ },
158
+ {
159
+ "epoch": 0.11924119241192412,
160
+ "grad_norm": 0.0,
161
+ "learning_rate": 3.971119133574007e-05,
162
+ "loss": 1.188,
163
+ "step": 220
164
+ },
165
+ {
166
+ "epoch": 0.12466124661246612,
167
+ "grad_norm": 0.0,
168
+ "learning_rate": 4.151624548736462e-05,
169
+ "loss": 1.11,
170
+ "step": 230
171
+ },
172
+ {
173
+ "epoch": 0.13008130081300814,
174
+ "grad_norm": 0.0,
175
+ "learning_rate": 4.332129963898917e-05,
176
+ "loss": 1.0991,
177
+ "step": 240
178
+ },
179
+ {
180
+ "epoch": 0.13550135501355012,
181
+ "grad_norm": 0.0,
182
+ "learning_rate": 4.5126353790613716e-05,
183
+ "loss": 1.07,
184
+ "step": 250
185
+ },
186
+ {
187
+ "epoch": 0.14092140921409213,
188
+ "grad_norm": 0.0,
189
+ "learning_rate": 4.693140794223827e-05,
190
+ "loss": 1.2724,
191
+ "step": 260
192
+ },
193
+ {
194
+ "epoch": 0.14634146341463414,
195
+ "grad_norm": 0.0,
196
+ "learning_rate": 4.873646209386282e-05,
197
+ "loss": 1.1382,
198
+ "step": 270
199
+ },
200
+ {
201
+ "epoch": 0.15176151761517614,
202
+ "grad_norm": 0.0,
203
+ "learning_rate": 5.054151624548736e-05,
204
+ "loss": 1.1774,
205
+ "step": 280
206
+ },
207
+ {
208
+ "epoch": 0.15718157181571815,
209
+ "grad_norm": 0.0,
210
+ "learning_rate": 5.234657039711192e-05,
211
+ "loss": 1.1395,
212
+ "step": 290
213
+ },
214
+ {
215
+ "epoch": 0.16260162601626016,
216
+ "grad_norm": 0.0,
217
+ "learning_rate": 5.415162454873647e-05,
218
+ "loss": 1.192,
219
+ "step": 300
220
+ },
221
+ {
222
+ "epoch": 0.16802168021680217,
223
+ "grad_norm": 0.0,
224
+ "learning_rate": 5.595667870036101e-05,
225
+ "loss": 1.1848,
226
+ "step": 310
227
+ },
228
+ {
229
+ "epoch": 0.17344173441734417,
230
+ "grad_norm": 0.0,
231
+ "learning_rate": 5.776173285198556e-05,
232
+ "loss": 1.1632,
233
+ "step": 320
234
+ },
235
+ {
236
+ "epoch": 0.17886178861788618,
237
+ "grad_norm": 0.0,
238
+ "learning_rate": 5.9566787003610113e-05,
239
+ "loss": 1.1659,
240
+ "step": 330
241
+ },
242
+ {
243
+ "epoch": 0.1842818428184282,
244
+ "grad_norm": 0.0,
245
+ "learning_rate": 6.137184115523465e-05,
246
+ "loss": 1.0097,
247
+ "step": 340
248
+ },
249
+ {
250
+ "epoch": 0.1897018970189702,
251
+ "grad_norm": 0.0,
252
+ "learning_rate": 6.31768953068592e-05,
253
+ "loss": 1.068,
254
+ "step": 350
255
+ },
256
+ {
257
+ "epoch": 0.1951219512195122,
258
+ "grad_norm": 0.0,
259
+ "learning_rate": 6.498194945848377e-05,
260
+ "loss": 1.1652,
261
+ "step": 360
262
+ },
263
+ {
264
+ "epoch": 0.2005420054200542,
265
+ "grad_norm": 0.0,
266
+ "learning_rate": 6.678700361010832e-05,
267
+ "loss": 1.0985,
268
+ "step": 370
269
+ },
270
+ {
271
+ "epoch": 0.20596205962059622,
272
+ "grad_norm": 0.0,
273
+ "learning_rate": 6.859205776173285e-05,
274
+ "loss": 1.0488,
275
+ "step": 380
276
+ },
277
+ {
278
+ "epoch": 0.21138211382113822,
279
+ "grad_norm": 0.0,
280
+ "learning_rate": 7.03971119133574e-05,
281
+ "loss": 1.1854,
282
+ "step": 390
283
+ },
284
+ {
285
+ "epoch": 0.21680216802168023,
286
+ "grad_norm": 0.0,
287
+ "learning_rate": 7.220216606498195e-05,
288
+ "loss": 1.1238,
289
+ "step": 400
290
+ },
291
+ {
292
+ "epoch": 0.2222222222222222,
293
+ "grad_norm": 0.0,
294
+ "learning_rate": 7.40072202166065e-05,
295
+ "loss": 1.145,
296
+ "step": 410
297
+ },
298
+ {
299
+ "epoch": 0.22764227642276422,
300
+ "grad_norm": 0.0,
301
+ "learning_rate": 7.581227436823105e-05,
302
+ "loss": 1.2215,
303
+ "step": 420
304
+ },
305
+ {
306
+ "epoch": 0.23306233062330622,
307
+ "grad_norm": 0.0,
308
+ "learning_rate": 7.76173285198556e-05,
309
+ "loss": 1.143,
310
+ "step": 430
311
+ },
312
+ {
313
+ "epoch": 0.23848238482384823,
314
+ "grad_norm": 0.0,
315
+ "learning_rate": 7.942238267148014e-05,
316
+ "loss": 1.1652,
317
+ "step": 440
318
+ },
319
+ {
320
+ "epoch": 0.24390243902439024,
321
+ "grad_norm": 0.0,
322
+ "learning_rate": 8.122743682310469e-05,
323
+ "loss": 1.2227,
324
+ "step": 450
325
+ },
326
+ {
327
+ "epoch": 0.24932249322493225,
328
+ "grad_norm": 0.0,
329
+ "learning_rate": 8.303249097472924e-05,
330
+ "loss": 1.1247,
331
+ "step": 460
332
+ },
333
+ {
334
+ "epoch": 0.25474254742547425,
335
+ "grad_norm": 0.0,
336
+ "learning_rate": 8.48375451263538e-05,
337
+ "loss": 1.1026,
338
+ "step": 470
339
+ },
340
+ {
341
+ "epoch": 0.2601626016260163,
342
+ "grad_norm": 0.0,
343
+ "learning_rate": 8.664259927797834e-05,
344
+ "loss": 1.0836,
345
+ "step": 480
346
+ },
347
+ {
348
+ "epoch": 0.26558265582655827,
349
+ "grad_norm": 0.0,
350
+ "learning_rate": 8.84476534296029e-05,
351
+ "loss": 1.0682,
352
+ "step": 490
353
+ },
354
+ {
355
+ "epoch": 0.27100271002710025,
356
+ "grad_norm": 0.0,
357
+ "learning_rate": 9.025270758122743e-05,
358
+ "loss": 1.0829,
359
+ "step": 500
360
+ },
361
+ {
362
+ "epoch": 0.2764227642276423,
363
+ "grad_norm": 0.0,
364
+ "learning_rate": 9.205776173285198e-05,
365
+ "loss": 1.0599,
366
+ "step": 510
367
+ },
368
+ {
369
+ "epoch": 0.28184281842818426,
370
+ "grad_norm": 0.0,
371
+ "learning_rate": 9.386281588447655e-05,
372
+ "loss": 1.1322,
373
+ "step": 520
374
+ },
375
+ {
376
+ "epoch": 0.2872628726287263,
377
+ "grad_norm": 0.0,
378
+ "learning_rate": 9.56678700361011e-05,
379
+ "loss": 1.1264,
380
+ "step": 530
381
+ },
382
+ {
383
+ "epoch": 0.2926829268292683,
384
+ "grad_norm": 0.0,
385
+ "learning_rate": 9.747292418772563e-05,
386
+ "loss": 1.1008,
387
+ "step": 540
388
+ },
389
+ {
390
+ "epoch": 0.2981029810298103,
391
+ "grad_norm": 0.0,
392
+ "learning_rate": 9.927797833935018e-05,
393
+ "loss": 1.1783,
394
+ "step": 550
395
+ },
396
+ {
397
+ "epoch": 0.3035230352303523,
398
+ "grad_norm": 0.0,
399
+ "learning_rate": 9.999964197887486e-05,
400
+ "loss": 1.1658,
401
+ "step": 560
402
+ },
403
+ {
404
+ "epoch": 0.3089430894308943,
405
+ "grad_norm": 0.0,
406
+ "learning_rate": 9.999745409056648e-05,
407
+ "loss": 1.1876,
408
+ "step": 570
409
+ },
410
+ {
411
+ "epoch": 0.3143631436314363,
412
+ "grad_norm": 0.0,
413
+ "learning_rate": 9.999327730150358e-05,
414
+ "loss": 1.0611,
415
+ "step": 580
416
+ },
417
+ {
418
+ "epoch": 0.31978319783197834,
419
+ "grad_norm": 0.0,
420
+ "learning_rate": 9.998711177783901e-05,
421
+ "loss": 1.0863,
422
+ "step": 590
423
+ },
424
+ {
425
+ "epoch": 0.3252032520325203,
426
+ "grad_norm": 0.0,
427
+ "learning_rate": 9.997895776483754e-05,
428
+ "loss": 1.114,
429
+ "step": 600
430
+ },
431
+ {
432
+ "epoch": 0.33062330623306235,
433
+ "grad_norm": 0.0,
434
+ "learning_rate": 9.996881558686615e-05,
435
+ "loss": 1.0857,
436
+ "step": 610
437
+ },
438
+ {
439
+ "epoch": 0.33604336043360433,
440
+ "grad_norm": 0.0,
441
+ "learning_rate": 9.995668564738108e-05,
442
+ "loss": 1.0991,
443
+ "step": 620
444
+ },
445
+ {
446
+ "epoch": 0.34146341463414637,
447
+ "grad_norm": 0.0,
448
+ "learning_rate": 9.994256842891181e-05,
449
+ "loss": 1.0993,
450
+ "step": 630
451
+ },
452
+ {
453
+ "epoch": 0.34688346883468835,
454
+ "grad_norm": 0.0,
455
+ "learning_rate": 9.992646449304188e-05,
456
+ "loss": 1.0537,
457
+ "step": 640
458
+ },
459
+ {
460
+ "epoch": 0.3523035230352303,
461
+ "grad_norm": 0.0,
462
+ "learning_rate": 9.990837448038653e-05,
463
+ "loss": 1.0829,
464
+ "step": 650
465
+ },
466
+ {
467
+ "epoch": 0.35772357723577236,
468
+ "grad_norm": 0.0,
469
+ "learning_rate": 9.988829911056716e-05,
470
+ "loss": 1.0441,
471
+ "step": 660
472
+ },
473
+ {
474
+ "epoch": 0.36314363143631434,
475
+ "grad_norm": 0.0,
476
+ "learning_rate": 9.98662391821828e-05,
477
+ "loss": 1.0902,
478
+ "step": 670
479
+ },
480
+ {
481
+ "epoch": 0.3685636856368564,
482
+ "grad_norm": 0.0,
483
+ "learning_rate": 9.984219557277832e-05,
484
+ "loss": 1.1888,
485
+ "step": 680
486
+ },
487
+ {
488
+ "epoch": 0.37398373983739835,
489
+ "grad_norm": 0.0,
490
+ "learning_rate": 9.981616923880947e-05,
491
+ "loss": 1.0265,
492
+ "step": 690
493
+ },
494
+ {
495
+ "epoch": 0.3794037940379404,
496
+ "grad_norm": 0.0,
497
+ "learning_rate": 9.978816121560487e-05,
498
+ "loss": 1.1118,
499
+ "step": 700
500
+ },
501
+ {
502
+ "epoch": 0.38482384823848237,
503
+ "grad_norm": 0.0,
504
+ "learning_rate": 9.975817261732483e-05,
505
+ "loss": 1.0043,
506
+ "step": 710
507
+ },
508
+ {
509
+ "epoch": 0.3902439024390244,
510
+ "grad_norm": 0.0,
511
+ "learning_rate": 9.972620463691699e-05,
512
+ "loss": 1.0356,
513
+ "step": 720
514
+ },
515
+ {
516
+ "epoch": 0.3956639566395664,
517
+ "grad_norm": 0.0,
518
+ "learning_rate": 9.969225854606892e-05,
519
+ "loss": 1.1946,
520
+ "step": 730
521
+ },
522
+ {
523
+ "epoch": 0.4010840108401084,
524
+ "grad_norm": 0.0,
525
+ "learning_rate": 9.965633569515749e-05,
526
+ "loss": 1.0684,
527
+ "step": 740
528
+ },
529
+ {
530
+ "epoch": 0.4065040650406504,
531
+ "grad_norm": 0.0,
532
+ "learning_rate": 9.961843751319517e-05,
533
+ "loss": 1.1165,
534
+ "step": 750
535
+ },
536
+ {
537
+ "epoch": 0.41192411924119243,
538
+ "grad_norm": 0.0,
539
+ "learning_rate": 9.957856550777318e-05,
540
+ "loss": 1.106,
541
+ "step": 760
542
+ },
543
+ {
544
+ "epoch": 0.4173441734417344,
545
+ "grad_norm": 0.0,
546
+ "learning_rate": 9.95367212650015e-05,
547
+ "loss": 1.0912,
548
+ "step": 770
549
+ },
550
+ {
551
+ "epoch": 0.42276422764227645,
552
+ "grad_norm": 0.0,
553
+ "learning_rate": 9.949290644944585e-05,
554
+ "loss": 1.0344,
555
+ "step": 780
556
+ },
557
+ {
558
+ "epoch": 0.4281842818428184,
559
+ "grad_norm": 0.0,
560
+ "learning_rate": 9.944712280406132e-05,
561
+ "loss": 1.148,
562
+ "step": 790
563
+ },
564
+ {
565
+ "epoch": 0.43360433604336046,
566
+ "grad_norm": 0.0,
567
+ "learning_rate": 9.93993721501232e-05,
568
+ "loss": 1.0802,
569
+ "step": 800
570
+ },
571
+ {
572
+ "epoch": 0.43902439024390244,
573
+ "grad_norm": 0.0,
574
+ "learning_rate": 9.934965638715446e-05,
575
+ "loss": 1.0527,
576
+ "step": 810
577
+ },
578
+ {
579
+ "epoch": 0.4444444444444444,
580
+ "grad_norm": 0.0,
581
+ "learning_rate": 9.929797749285015e-05,
582
+ "loss": 1.0383,
583
+ "step": 820
584
+ },
585
+ {
586
+ "epoch": 0.44986449864498645,
587
+ "grad_norm": 0.0,
588
+ "learning_rate": 9.92443375229988e-05,
589
+ "loss": 1.0799,
590
+ "step": 830
591
+ },
592
+ {
593
+ "epoch": 0.45528455284552843,
594
+ "grad_norm": 0.0,
595
+ "learning_rate": 9.918873861140058e-05,
596
+ "loss": 1.0581,
597
+ "step": 840
598
+ },
599
+ {
600
+ "epoch": 0.46070460704607047,
601
+ "grad_norm": 0.0,
602
+ "learning_rate": 9.913118296978246e-05,
603
+ "loss": 1.0526,
604
+ "step": 850
605
+ },
606
+ {
607
+ "epoch": 0.46612466124661245,
608
+ "grad_norm": 0.0,
609
+ "learning_rate": 9.907167288771019e-05,
610
+ "loss": 1.1422,
611
+ "step": 860
612
+ },
613
+ {
614
+ "epoch": 0.4715447154471545,
615
+ "grad_norm": 0.0,
616
+ "learning_rate": 9.901021073249725e-05,
617
+ "loss": 1.0433,
618
+ "step": 870
619
+ },
620
+ {
621
+ "epoch": 0.47696476964769646,
622
+ "grad_norm": 0.0,
623
+ "learning_rate": 9.89467989491107e-05,
624
+ "loss": 1.1253,
625
+ "step": 880
626
+ },
627
+ {
628
+ "epoch": 0.4823848238482385,
629
+ "grad_norm": 0.0,
630
+ "learning_rate": 9.888144006007382e-05,
631
+ "loss": 1.0904,
632
+ "step": 890
633
+ },
634
+ {
635
+ "epoch": 0.4878048780487805,
636
+ "grad_norm": 0.0,
637
+ "learning_rate": 9.881413666536589e-05,
638
+ "loss": 1.0581,
639
+ "step": 900
640
+ },
641
+ {
642
+ "epoch": 0.4932249322493225,
643
+ "grad_norm": 0.0,
644
+ "learning_rate": 9.874489144231869e-05,
645
+ "loss": 1.0418,
646
+ "step": 910
647
+ },
648
+ {
649
+ "epoch": 0.4986449864498645,
650
+ "grad_norm": 0.0,
651
+ "learning_rate": 9.867370714551e-05,
652
+ "loss": 1.191,
653
+ "step": 920
654
+ },
655
+ {
656
+ "epoch": 0.5040650406504065,
657
+ "grad_norm": 0.0,
658
+ "learning_rate": 9.860058660665404e-05,
659
+ "loss": 1.0701,
660
+ "step": 930
661
+ },
662
+ {
663
+ "epoch": 0.5094850948509485,
664
+ "grad_norm": 0.0,
665
+ "learning_rate": 9.852553273448879e-05,
666
+ "loss": 1.1752,
667
+ "step": 940
668
+ },
669
+ {
670
+ "epoch": 0.5149051490514905,
671
+ "grad_norm": 0.0,
672
+ "learning_rate": 9.844854851466037e-05,
673
+ "loss": 1.0127,
674
+ "step": 950
675
+ },
676
+ {
677
+ "epoch": 0.5203252032520326,
678
+ "grad_norm": 0.0,
679
+ "learning_rate": 9.836963700960416e-05,
680
+ "loss": 1.1023,
681
+ "step": 960
682
+ },
683
+ {
684
+ "epoch": 0.5257452574525745,
685
+ "grad_norm": 0.0,
686
+ "learning_rate": 9.828880135842302e-05,
687
+ "loss": 1.1257,
688
+ "step": 970
689
+ },
690
+ {
691
+ "epoch": 0.5311653116531165,
692
+ "grad_norm": 0.0,
693
+ "learning_rate": 9.820604477676247e-05,
694
+ "loss": 1.0576,
695
+ "step": 980
696
+ },
697
+ {
698
+ "epoch": 0.5365853658536586,
699
+ "grad_norm": 0.0,
700
+ "learning_rate": 9.812137055668267e-05,
701
+ "loss": 1.0565,
702
+ "step": 990
703
+ },
704
+ {
705
+ "epoch": 0.5420054200542005,
706
+ "grad_norm": 0.0,
707
+ "learning_rate": 9.803478206652752e-05,
708
+ "loss": 1.0173,
709
+ "step": 1000
710
+ },
711
+ {
712
+ "epoch": 0.5474254742547425,
713
+ "grad_norm": 0.0,
714
+ "learning_rate": 9.794628275079069e-05,
715
+ "loss": 1.0592,
716
+ "step": 1010
717
+ },
718
+ {
719
+ "epoch": 0.5528455284552846,
720
+ "grad_norm": 0.0,
721
+ "learning_rate": 9.785587612997857e-05,
722
+ "loss": 0.9735,
723
+ "step": 1020
724
+ },
725
+ {
726
+ "epoch": 0.5582655826558266,
727
+ "grad_norm": 0.0,
728
+ "learning_rate": 9.776356580047019e-05,
729
+ "loss": 0.9913,
730
+ "step": 1030
731
+ },
732
+ {
733
+ "epoch": 0.5636856368563685,
734
+ "grad_norm": 0.0,
735
+ "learning_rate": 9.766935543437421e-05,
736
+ "loss": 1.0708,
737
+ "step": 1040
738
+ },
739
+ {
740
+ "epoch": 0.5691056910569106,
741
+ "grad_norm": 0.0,
742
+ "learning_rate": 9.757324877938283e-05,
743
+ "loss": 1.1463,
744
+ "step": 1050
745
+ },
746
+ {
747
+ "epoch": 0.5745257452574526,
748
+ "grad_norm": 0.0,
749
+ "learning_rate": 9.747524965862267e-05,
750
+ "loss": 1.0462,
751
+ "step": 1060
752
+ },
753
+ {
754
+ "epoch": 0.5799457994579946,
755
+ "grad_norm": 0.0,
756
+ "learning_rate": 9.737536197050275e-05,
757
+ "loss": 1.0178,
758
+ "step": 1070
759
+ },
760
+ {
761
+ "epoch": 0.5853658536585366,
762
+ "grad_norm": 0.0,
763
+ "learning_rate": 9.727358968855932e-05,
764
+ "loss": 0.8617,
765
+ "step": 1080
766
+ },
767
+ {
768
+ "epoch": 0.5907859078590786,
769
+ "grad_norm": 0.0,
770
+ "learning_rate": 9.716993686129796e-05,
771
+ "loss": 0.9766,
772
+ "step": 1090
773
+ },
774
+ {
775
+ "epoch": 0.5962059620596206,
776
+ "grad_norm": 0.0,
777
+ "learning_rate": 9.706440761203232e-05,
778
+ "loss": 1.0065,
779
+ "step": 1100
780
+ },
781
+ {
782
+ "epoch": 0.6016260162601627,
783
+ "grad_norm": 0.0,
784
+ "learning_rate": 9.695700613872019e-05,
785
+ "loss": 0.8501,
786
+ "step": 1110
787
+ },
788
+ {
789
+ "epoch": 0.6070460704607046,
790
+ "grad_norm": 0.0,
791
+ "learning_rate": 9.684773671379658e-05,
792
+ "loss": 1.1225,
793
+ "step": 1120
794
+ },
795
+ {
796
+ "epoch": 0.6124661246612466,
797
+ "grad_norm": 0.0,
798
+ "learning_rate": 9.673660368400364e-05,
799
+ "loss": 1.0852,
800
+ "step": 1130
801
+ },
802
+ {
803
+ "epoch": 0.6178861788617886,
804
+ "grad_norm": 0.0,
805
+ "learning_rate": 9.662361147021779e-05,
806
+ "loss": 0.9858,
807
+ "step": 1140
808
+ },
809
+ {
810
+ "epoch": 0.6233062330623306,
811
+ "grad_norm": 0.0,
812
+ "learning_rate": 9.650876456727392e-05,
813
+ "loss": 1.0293,
814
+ "step": 1150
815
+ },
816
+ {
817
+ "epoch": 0.6287262872628726,
818
+ "grad_norm": 0.0,
819
+ "learning_rate": 9.639206754378646e-05,
820
+ "loss": 1.06,
821
+ "step": 1160
822
+ },
823
+ {
824
+ "epoch": 0.6341463414634146,
825
+ "grad_norm": 0.0,
826
+ "learning_rate": 9.627352504196777e-05,
827
+ "loss": 1.1035,
828
+ "step": 1170
829
+ },
830
+ {
831
+ "epoch": 0.6395663956639567,
832
+ "grad_norm": 0.0,
833
+ "learning_rate": 9.615314177744337e-05,
834
+ "loss": 1.0686,
835
+ "step": 1180
836
+ },
837
+ {
838
+ "epoch": 0.6449864498644986,
839
+ "grad_norm": 0.0,
840
+ "learning_rate": 9.603092253906441e-05,
841
+ "loss": 0.9771,
842
+ "step": 1190
843
+ },
844
+ {
845
+ "epoch": 0.6504065040650406,
846
+ "grad_norm": 0.0,
847
+ "learning_rate": 9.590687218871719e-05,
848
+ "loss": 1.0134,
849
+ "step": 1200
850
+ },
851
+ {
852
+ "epoch": 0.6558265582655827,
853
+ "grad_norm": 0.0,
854
+ "learning_rate": 9.578099566112964e-05,
855
+ "loss": 1.013,
856
+ "step": 1210
857
+ },
858
+ {
859
+ "epoch": 0.6612466124661247,
860
+ "grad_norm": 0.0,
861
+ "learning_rate": 9.565329796367516e-05,
862
+ "loss": 1.012,
863
+ "step": 1220
864
+ },
865
+ {
866
+ "epoch": 0.6666666666666666,
867
+ "grad_norm": 0.0,
868
+ "learning_rate": 9.552378417617336e-05,
869
+ "loss": 0.9936,
870
+ "step": 1230
871
+ },
872
+ {
873
+ "epoch": 0.6720867208672087,
874
+ "grad_norm": 0.0,
875
+ "learning_rate": 9.539245945068794e-05,
876
+ "loss": 0.9983,
877
+ "step": 1240
878
+ },
879
+ {
880
+ "epoch": 0.6775067750677507,
881
+ "grad_norm": 0.0,
882
+ "learning_rate": 9.525932901132183e-05,
883
+ "loss": 0.989,
884
+ "step": 1250
885
+ },
886
+ {
887
+ "epoch": 0.6829268292682927,
888
+ "grad_norm": 0.0,
889
+ "learning_rate": 9.512439815400931e-05,
890
+ "loss": 1.0803,
891
+ "step": 1260
892
+ },
893
+ {
894
+ "epoch": 0.6883468834688347,
895
+ "grad_norm": 0.0,
896
+ "learning_rate": 9.498767224630537e-05,
897
+ "loss": 1.0493,
898
+ "step": 1270
899
+ },
900
+ {
901
+ "epoch": 0.6937669376693767,
902
+ "grad_norm": 0.0,
903
+ "learning_rate": 9.484915672717213e-05,
904
+ "loss": 1.0222,
905
+ "step": 1280
906
+ },
907
+ {
908
+ "epoch": 0.6991869918699187,
909
+ "grad_norm": 0.0,
910
+ "learning_rate": 9.470885710676265e-05,
911
+ "loss": 0.9564,
912
+ "step": 1290
913
+ },
914
+ {
915
+ "epoch": 0.7046070460704607,
916
+ "grad_norm": 0.0,
917
+ "learning_rate": 9.456677896620145e-05,
918
+ "loss": 0.9883,
919
+ "step": 1300
920
+ },
921
+ {
922
+ "epoch": 0.7100271002710027,
923
+ "grad_norm": 0.0,
924
+ "learning_rate": 9.442292795736278e-05,
925
+ "loss": 1.0013,
926
+ "step": 1310
927
+ },
928
+ {
929
+ "epoch": 0.7154471544715447,
930
+ "grad_norm": 0.0,
931
+ "learning_rate": 9.427730980264559e-05,
932
+ "loss": 0.9472,
933
+ "step": 1320
934
+ },
935
+ {
936
+ "epoch": 0.7208672086720868,
937
+ "grad_norm": 0.0,
938
+ "learning_rate": 9.412993029474602e-05,
939
+ "loss": 1.0772,
940
+ "step": 1330
941
+ },
942
+ {
943
+ "epoch": 0.7262872628726287,
944
+ "grad_norm": 0.0,
945
+ "learning_rate": 9.398079529642685e-05,
946
+ "loss": 1.0644,
947
+ "step": 1340
948
+ },
949
+ {
950
+ "epoch": 0.7317073170731707,
951
+ "grad_norm": 0.0,
952
+ "learning_rate": 9.382991074028436e-05,
953
+ "loss": 1.1249,
954
+ "step": 1350
955
+ },
956
+ {
957
+ "epoch": 0.7371273712737128,
958
+ "grad_norm": 0.0,
959
+ "learning_rate": 9.367728262851237e-05,
960
+ "loss": 0.9928,
961
+ "step": 1360
962
+ },
963
+ {
964
+ "epoch": 0.7425474254742548,
965
+ "grad_norm": 0.0,
966
+ "learning_rate": 9.352291703266331e-05,
967
+ "loss": 1.1657,
968
+ "step": 1370
969
+ },
970
+ {
971
+ "epoch": 0.7479674796747967,
972
+ "grad_norm": 0.0,
973
+ "learning_rate": 9.33668200934069e-05,
974
+ "loss": 1.0173,
975
+ "step": 1380
976
+ },
977
+ {
978
+ "epoch": 0.7533875338753387,
979
+ "grad_norm": 0.0,
980
+ "learning_rate": 9.32089980202857e-05,
981
+ "loss": 0.9503,
982
+ "step": 1390
983
+ },
984
+ {
985
+ "epoch": 0.7588075880758808,
986
+ "grad_norm": 0.0,
987
+ "learning_rate": 9.304945709146819e-05,
988
+ "loss": 1.1083,
989
+ "step": 1400
990
+ },
991
+ {
992
+ "epoch": 0.7642276422764228,
993
+ "grad_norm": 0.0,
994
+ "learning_rate": 9.2888203653499e-05,
995
+ "loss": 0.9929,
996
+ "step": 1410
997
+ },
998
+ {
999
+ "epoch": 0.7696476964769647,
1000
+ "grad_norm": 0.0,
1001
+ "learning_rate": 9.272524412104645e-05,
1002
+ "loss": 1.1123,
1003
+ "step": 1420
1004
+ },
1005
+ {
1006
+ "epoch": 0.7750677506775068,
1007
+ "grad_norm": 0.0,
1008
+ "learning_rate": 9.256058497664734e-05,
1009
+ "loss": 1.0397,
1010
+ "step": 1430
1011
+ },
1012
+ {
1013
+ "epoch": 0.7804878048780488,
1014
+ "grad_norm": 0.0,
1015
+ "learning_rate": 9.239423277044917e-05,
1016
+ "loss": 1.0311,
1017
+ "step": 1440
1018
+ },
1019
+ {
1020
+ "epoch": 0.7859078590785907,
1021
+ "grad_norm": 0.0,
1022
+ "learning_rate": 9.22261941199494e-05,
1023
+ "loss": 0.9421,
1024
+ "step": 1450
1025
+ },
1026
+ {
1027
+ "epoch": 0.7913279132791328,
1028
+ "grad_norm": 0.0,
1029
+ "learning_rate": 9.205647570973239e-05,
1030
+ "loss": 0.9313,
1031
+ "step": 1460
1032
+ },
1033
+ {
1034
+ "epoch": 0.7967479674796748,
1035
+ "grad_norm": 0.0,
1036
+ "learning_rate": 9.188508429120342e-05,
1037
+ "loss": 1.0034,
1038
+ "step": 1470
1039
+ },
1040
+ {
1041
+ "epoch": 0.8021680216802168,
1042
+ "grad_norm": 0.0,
1043
+ "learning_rate": 9.171202668232007e-05,
1044
+ "loss": 1.036,
1045
+ "step": 1480
1046
+ },
1047
+ {
1048
+ "epoch": 0.8075880758807588,
1049
+ "grad_norm": 0.0,
1050
+ "learning_rate": 9.153730976732101e-05,
1051
+ "loss": 1.0326,
1052
+ "step": 1490
1053
+ },
1054
+ {
1055
+ "epoch": 0.8130081300813008,
1056
+ "grad_norm": 0.0,
1057
+ "learning_rate": 9.136094049645226e-05,
1058
+ "loss": 0.8734,
1059
+ "step": 1500
1060
+ },
1061
+ {
1062
+ "epoch": 0.8184281842818428,
1063
+ "grad_norm": 0.0,
1064
+ "learning_rate": 9.118292588569057e-05,
1065
+ "loss": 0.8989,
1066
+ "step": 1510
1067
+ },
1068
+ {
1069
+ "epoch": 0.8238482384823849,
1070
+ "grad_norm": 0.0,
1071
+ "learning_rate": 9.100327301646439e-05,
1072
+ "loss": 1.0225,
1073
+ "step": 1520
1074
+ },
1075
+ {
1076
+ "epoch": 0.8292682926829268,
1077
+ "grad_norm": 0.0,
1078
+ "learning_rate": 9.082198903537213e-05,
1079
+ "loss": 1.0594,
1080
+ "step": 1530
1081
+ },
1082
+ {
1083
+ "epoch": 0.8346883468834688,
1084
+ "grad_norm": 0.0,
1085
+ "learning_rate": 9.063908115389794e-05,
1086
+ "loss": 0.9244,
1087
+ "step": 1540
1088
+ },
1089
+ {
1090
+ "epoch": 0.8401084010840109,
1091
+ "grad_norm": 0.0,
1092
+ "learning_rate": 9.045455664812478e-05,
1093
+ "loss": 1.0654,
1094
+ "step": 1550
1095
+ },
1096
+ {
1097
+ "epoch": 0.8455284552845529,
1098
+ "grad_norm": 0.0,
1099
+ "learning_rate": 9.026842285844499e-05,
1100
+ "loss": 1.0126,
1101
+ "step": 1560
1102
+ },
1103
+ {
1104
+ "epoch": 0.8509485094850948,
1105
+ "grad_norm": 0.0,
1106
+ "learning_rate": 9.008068718926825e-05,
1107
+ "loss": 1.0821,
1108
+ "step": 1570
1109
+ },
1110
+ {
1111
+ "epoch": 0.8563685636856369,
1112
+ "grad_norm": 0.0,
1113
+ "learning_rate": 8.989135710872713e-05,
1114
+ "loss": 1.0105,
1115
+ "step": 1580
1116
+ },
1117
+ {
1118
+ "epoch": 0.8617886178861789,
1119
+ "grad_norm": 0.0,
1120
+ "learning_rate": 8.970044014837994e-05,
1121
+ "loss": 0.9684,
1122
+ "step": 1590
1123
+ },
1124
+ {
1125
+ "epoch": 0.8672086720867209,
1126
+ "grad_norm": 0.0,
1127
+ "learning_rate": 8.950794390291108e-05,
1128
+ "loss": 1.0457,
1129
+ "step": 1600
1130
+ },
1131
+ {
1132
+ "epoch": 0.8726287262872628,
1133
+ "grad_norm": 0.0,
1134
+ "learning_rate": 8.931387602982903e-05,
1135
+ "loss": 1.0847,
1136
+ "step": 1610
1137
+ },
1138
+ {
1139
+ "epoch": 0.8780487804878049,
1140
+ "grad_norm": 0.0,
1141
+ "learning_rate": 8.911824424916169e-05,
1142
+ "loss": 1.1106,
1143
+ "step": 1620
1144
+ },
1145
+ {
1146
+ "epoch": 0.8834688346883469,
1147
+ "grad_norm": 0.0,
1148
+ "learning_rate": 8.89210563431492e-05,
1149
+ "loss": 1.6764,
1150
+ "step": 1630
1151
+ },
1152
+ {
1153
+ "epoch": 0.8888888888888888,
1154
+ "grad_norm": 0.0,
1155
+ "learning_rate": 8.872232015593447e-05,
1156
+ "loss": 0.9737,
1157
+ "step": 1640
1158
+ },
1159
+ {
1160
+ "epoch": 0.8943089430894309,
1161
+ "grad_norm": 0.0,
1162
+ "learning_rate": 8.852204359325115e-05,
1163
+ "loss": 1.0723,
1164
+ "step": 1650
1165
+ },
1166
+ {
1167
+ "epoch": 0.8997289972899729,
1168
+ "grad_norm": 0.0,
1169
+ "learning_rate": 8.8320234622109e-05,
1170
+ "loss": 1.026,
1171
+ "step": 1660
1172
+ },
1173
+ {
1174
+ "epoch": 0.9051490514905149,
1175
+ "grad_norm": 0.0,
1176
+ "learning_rate": 8.811690127047707e-05,
1177
+ "loss": 0.9524,
1178
+ "step": 1670
1179
+ },
1180
+ {
1181
+ "epoch": 0.9105691056910569,
1182
+ "grad_norm": 0.0,
1183
+ "learning_rate": 8.791205162696439e-05,
1184
+ "loss": 0.9443,
1185
+ "step": 1680
1186
+ },
1187
+ {
1188
+ "epoch": 0.9159891598915989,
1189
+ "grad_norm": 0.0,
1190
+ "learning_rate": 8.770569384049806e-05,
1191
+ "loss": 1.0877,
1192
+ "step": 1690
1193
+ },
1194
+ {
1195
+ "epoch": 0.9214092140921409,
1196
+ "grad_norm": 0.0,
1197
+ "learning_rate": 8.749783611999924e-05,
1198
+ "loss": 1.0068,
1199
+ "step": 1700
1200
+ },
1201
+ {
1202
+ "epoch": 0.926829268292683,
1203
+ "grad_norm": 0.0,
1204
+ "learning_rate": 8.72884867340565e-05,
1205
+ "loss": 1.0288,
1206
+ "step": 1710
1207
+ },
1208
+ {
1209
+ "epoch": 0.9322493224932249,
1210
+ "grad_norm": 0.0,
1211
+ "learning_rate": 8.707765401059689e-05,
1212
+ "loss": 1.0115,
1213
+ "step": 1720
1214
+ },
1215
+ {
1216
+ "epoch": 0.9376693766937669,
1217
+ "grad_norm": 0.0,
1218
+ "learning_rate": 8.68653463365547e-05,
1219
+ "loss": 0.9857,
1220
+ "step": 1730
1221
+ },
1222
+ {
1223
+ "epoch": 0.943089430894309,
1224
+ "grad_norm": 0.0,
1225
+ "learning_rate": 8.665157215753788e-05,
1226
+ "loss": 0.9941,
1227
+ "step": 1740
1228
+ },
1229
+ {
1230
+ "epoch": 0.948509485094851,
1231
+ "grad_norm": 0.0,
1232
+ "learning_rate": 8.64363399774919e-05,
1233
+ "loss": 0.9,
1234
+ "step": 1750
1235
+ },
1236
+ {
1237
+ "epoch": 0.9539295392953929,
1238
+ "grad_norm": 0.0,
1239
+ "learning_rate": 8.621965835836165e-05,
1240
+ "loss": 0.8777,
1241
+ "step": 1760
1242
+ },
1243
+ {
1244
+ "epoch": 0.959349593495935,
1245
+ "grad_norm": 0.0,
1246
+ "learning_rate": 8.600153591975073e-05,
1247
+ "loss": 0.952,
1248
+ "step": 1770
1249
+ },
1250
+ {
1251
+ "epoch": 0.964769647696477,
1252
+ "grad_norm": 0.0,
1253
+ "learning_rate": 8.578198133857863e-05,
1254
+ "loss": 0.9876,
1255
+ "step": 1780
1256
+ },
1257
+ {
1258
+ "epoch": 0.9701897018970189,
1259
+ "grad_norm": 0.0,
1260
+ "learning_rate": 8.556100334873549e-05,
1261
+ "loss": 0.9553,
1262
+ "step": 1790
1263
+ },
1264
+ {
1265
+ "epoch": 0.975609756097561,
1266
+ "grad_norm": 0.0,
1267
+ "learning_rate": 8.533861074073472e-05,
1268
+ "loss": 0.9153,
1269
+ "step": 1800
1270
+ },
1271
+ {
1272
+ "epoch": 0.981029810298103,
1273
+ "grad_norm": 0.0,
1274
+ "learning_rate": 8.511481236136329e-05,
1275
+ "loss": 0.9828,
1276
+ "step": 1810
1277
+ },
1278
+ {
1279
+ "epoch": 0.986449864498645,
1280
+ "grad_norm": 0.0,
1281
+ "learning_rate": 8.488961711332986e-05,
1282
+ "loss": 0.98,
1283
+ "step": 1820
1284
+ },
1285
+ {
1286
+ "epoch": 0.991869918699187,
1287
+ "grad_norm": 0.0,
1288
+ "learning_rate": 8.466303395491051e-05,
1289
+ "loss": 0.9471,
1290
+ "step": 1830
1291
+ },
1292
+ {
1293
+ "epoch": 0.997289972899729,
1294
+ "grad_norm": 0.0,
1295
+ "learning_rate": 8.443507189959248e-05,
1296
+ "loss": 0.9981,
1297
+ "step": 1840
1298
+ },
1299
+ {
1300
+ "epoch": 1.002710027100271,
1301
+ "grad_norm": 0.0,
1302
+ "learning_rate": 8.420574001571561e-05,
1303
+ "loss": 0.9234,
1304
+ "step": 1850
1305
+ },
1306
+ {
1307
+ "epoch": 1.008130081300813,
1308
+ "grad_norm": 0.0,
1309
+ "learning_rate": 8.397504742611155e-05,
1310
+ "loss": 0.8865,
1311
+ "step": 1860
1312
+ },
1313
+ {
1314
+ "epoch": 1.013550135501355,
1315
+ "grad_norm": 0.0,
1316
+ "learning_rate": 8.37430033077409e-05,
1317
+ "loss": 0.8455,
1318
+ "step": 1870
1319
+ },
1320
+ {
1321
+ "epoch": 1.018970189701897,
1322
+ "grad_norm": 0.0,
1323
+ "learning_rate": 8.350961689132808e-05,
1324
+ "loss": 0.8807,
1325
+ "step": 1880
1326
+ },
1327
+ {
1328
+ "epoch": 1.024390243902439,
1329
+ "grad_norm": 0.0,
1330
+ "learning_rate": 8.327489746099422e-05,
1331
+ "loss": 0.8296,
1332
+ "step": 1890
1333
+ },
1334
+ {
1335
+ "epoch": 1.029810298102981,
1336
+ "grad_norm": 0.0,
1337
+ "learning_rate": 8.303885435388783e-05,
1338
+ "loss": 0.8678,
1339
+ "step": 1900
1340
+ },
1341
+ {
1342
+ "epoch": 1.0352303523035231,
1343
+ "grad_norm": 0.0,
1344
+ "learning_rate": 8.280149695981325e-05,
1345
+ "loss": 0.7886,
1346
+ "step": 1910
1347
+ },
1348
+ {
1349
+ "epoch": 1.040650406504065,
1350
+ "grad_norm": 0.0,
1351
+ "learning_rate": 8.25628347208573e-05,
1352
+ "loss": 0.8248,
1353
+ "step": 1920
1354
+ },
1355
+ {
1356
+ "epoch": 1.046070460704607,
1357
+ "grad_norm": 0.0,
1358
+ "learning_rate": 8.232287713101351e-05,
1359
+ "loss": 0.8579,
1360
+ "step": 1930
1361
+ },
1362
+ {
1363
+ "epoch": 1.051490514905149,
1364
+ "grad_norm": 0.0,
1365
+ "learning_rate": 8.208163373580456e-05,
1366
+ "loss": 0.7809,
1367
+ "step": 1940
1368
+ },
1369
+ {
1370
+ "epoch": 1.056910569105691,
1371
+ "grad_norm": 0.0,
1372
+ "learning_rate": 8.183911413190251e-05,
1373
+ "loss": 0.7519,
1374
+ "step": 1950
1375
+ },
1376
+ {
1377
+ "epoch": 1.062330623306233,
1378
+ "grad_norm": 0.0,
1379
+ "learning_rate": 8.159532796674706e-05,
1380
+ "loss": 0.8322,
1381
+ "step": 1960
1382
+ },
1383
+ {
1384
+ "epoch": 1.067750677506775,
1385
+ "grad_norm": 0.0,
1386
+ "learning_rate": 8.135028493816174e-05,
1387
+ "loss": 0.8875,
1388
+ "step": 1970
1389
+ },
1390
+ {
1391
+ "epoch": 1.0731707317073171,
1392
+ "grad_norm": 0.0,
1393
+ "learning_rate": 8.110399479396822e-05,
1394
+ "loss": 0.6955,
1395
+ "step": 1980
1396
+ },
1397
+ {
1398
+ "epoch": 1.0785907859078592,
1399
+ "grad_norm": 0.0,
1400
+ "learning_rate": 8.085646733159841e-05,
1401
+ "loss": 0.8317,
1402
+ "step": 1990
1403
+ },
1404
+ {
1405
+ "epoch": 1.084010840108401,
1406
+ "grad_norm": 0.0,
1407
+ "learning_rate": 8.060771239770482e-05,
1408
+ "loss": 0.9015,
1409
+ "step": 2000
1410
+ },
1411
+ {
1412
+ "epoch": 1.089430894308943,
1413
+ "grad_norm": 0.0,
1414
+ "learning_rate": 8.035773988776883e-05,
1415
+ "loss": 0.9467,
1416
+ "step": 2010
1417
+ },
1418
+ {
1419
+ "epoch": 1.094850948509485,
1420
+ "grad_norm": 0.0,
1421
+ "learning_rate": 8.010655974570703e-05,
1422
+ "loss": 0.9237,
1423
+ "step": 2020
1424
+ },
1425
+ {
1426
+ "epoch": 1.100271002710027,
1427
+ "grad_norm": 0.0,
1428
+ "learning_rate": 7.985418196347568e-05,
1429
+ "loss": 0.8042,
1430
+ "step": 2030
1431
+ },
1432
+ {
1433
+ "epoch": 1.1056910569105691,
1434
+ "grad_norm": 0.0,
1435
+ "learning_rate": 7.960061658067322e-05,
1436
+ "loss": 0.7585,
1437
+ "step": 2040
1438
+ },
1439
+ {
1440
+ "epoch": 1.1111111111111112,
1441
+ "grad_norm": 0.0,
1442
+ "learning_rate": 7.934587368414084e-05,
1443
+ "loss": 0.8525,
1444
+ "step": 2050
1445
+ },
1446
+ {
1447
+ "epoch": 1.1165311653116532,
1448
+ "grad_norm": 0.0,
1449
+ "learning_rate": 7.908996340756136e-05,
1450
+ "loss": 0.8898,
1451
+ "step": 2060
1452
+ },
1453
+ {
1454
+ "epoch": 1.1219512195121952,
1455
+ "grad_norm": 0.0,
1456
+ "learning_rate": 7.883289593105597e-05,
1457
+ "loss": 0.851,
1458
+ "step": 2070
1459
+ },
1460
+ {
1461
+ "epoch": 1.127371273712737,
1462
+ "grad_norm": 0.0,
1463
+ "learning_rate": 7.857468148077926e-05,
1464
+ "loss": 0.7651,
1465
+ "step": 2080
1466
+ },
1467
+ {
1468
+ "epoch": 1.132791327913279,
1469
+ "grad_norm": 0.0,
1470
+ "learning_rate": 7.831533032851264e-05,
1471
+ "loss": 0.8294,
1472
+ "step": 2090
1473
+ },
1474
+ {
1475
+ "epoch": 1.1382113821138211,
1476
+ "grad_norm": 0.0,
1477
+ "learning_rate": 7.805485279125543e-05,
1478
+ "loss": 0.7916,
1479
+ "step": 2100
1480
+ },
1481
+ {
1482
+ "epoch": 1.1436314363143631,
1483
+ "grad_norm": 0.0,
1484
+ "learning_rate": 7.779325923081465e-05,
1485
+ "loss": 0.9365,
1486
+ "step": 2110
1487
+ },
1488
+ {
1489
+ "epoch": 1.1490514905149052,
1490
+ "grad_norm": 0.0,
1491
+ "learning_rate": 7.753056005339277e-05,
1492
+ "loss": 0.8456,
1493
+ "step": 2120
1494
+ },
1495
+ {
1496
+ "epoch": 1.1544715447154472,
1497
+ "grad_norm": 0.0,
1498
+ "learning_rate": 7.726676570917372e-05,
1499
+ "loss": 0.8459,
1500
+ "step": 2130
1501
+ },
1502
+ {
1503
+ "epoch": 1.1598915989159893,
1504
+ "grad_norm": 0.0,
1505
+ "learning_rate": 7.700188669190727e-05,
1506
+ "loss": 0.8237,
1507
+ "step": 2140
1508
+ },
1509
+ {
1510
+ "epoch": 1.165311653116531,
1511
+ "grad_norm": 0.0,
1512
+ "learning_rate": 7.673593353849143e-05,
1513
+ "loss": 0.8186,
1514
+ "step": 2150
1515
+ },
1516
+ {
1517
+ "epoch": 1.170731707317073,
1518
+ "grad_norm": 0.0,
1519
+ "learning_rate": 7.646891682855347e-05,
1520
+ "loss": 0.8047,
1521
+ "step": 2160
1522
+ },
1523
+ {
1524
+ "epoch": 1.1761517615176151,
1525
+ "grad_norm": 0.0,
1526
+ "learning_rate": 7.620084718402895e-05,
1527
+ "loss": 0.8191,
1528
+ "step": 2170
1529
+ },
1530
+ {
1531
+ "epoch": 1.1815718157181572,
1532
+ "grad_norm": 0.0,
1533
+ "learning_rate": 7.593173526873925e-05,
1534
+ "loss": 0.8245,
1535
+ "step": 2180
1536
+ },
1537
+ {
1538
+ "epoch": 1.1869918699186992,
1539
+ "grad_norm": 0.0,
1540
+ "learning_rate": 7.566159178796726e-05,
1541
+ "loss": 0.9024,
1542
+ "step": 2190
1543
+ },
1544
+ {
1545
+ "epoch": 1.1924119241192412,
1546
+ "grad_norm": 0.0,
1547
+ "learning_rate": 7.539042748803162e-05,
1548
+ "loss": 0.7802,
1549
+ "step": 2200
1550
+ },
1551
+ {
1552
+ "epoch": 1.1978319783197833,
1553
+ "grad_norm": 0.0,
1554
+ "learning_rate": 7.511825315585921e-05,
1555
+ "loss": 0.7251,
1556
+ "step": 2210
1557
+ },
1558
+ {
1559
+ "epoch": 1.203252032520325,
1560
+ "grad_norm": 0.0,
1561
+ "learning_rate": 7.484507961855598e-05,
1562
+ "loss": 0.8132,
1563
+ "step": 2220
1564
+ },
1565
+ {
1566
+ "epoch": 1.2086720867208671,
1567
+ "grad_norm": 0.0,
1568
+ "learning_rate": 7.45709177429764e-05,
1569
+ "loss": 0.7704,
1570
+ "step": 2230
1571
+ },
1572
+ {
1573
+ "epoch": 1.2140921409214092,
1574
+ "grad_norm": 0.0,
1575
+ "learning_rate": 7.429577843529096e-05,
1576
+ "loss": 0.7359,
1577
+ "step": 2240
1578
+ },
1579
+ {
1580
+ "epoch": 1.2195121951219512,
1581
+ "grad_norm": 0.0,
1582
+ "learning_rate": 7.401967264055253e-05,
1583
+ "loss": 0.8472,
1584
+ "step": 2250
1585
+ },
1586
+ {
1587
+ "epoch": 1.2249322493224932,
1588
+ "grad_norm": 0.0,
1589
+ "learning_rate": 7.374261134226083e-05,
1590
+ "loss": 0.7575,
1591
+ "step": 2260
1592
+ },
1593
+ {
1594
+ "epoch": 1.2303523035230353,
1595
+ "grad_norm": 0.0,
1596
+ "learning_rate": 7.346460556192557e-05,
1597
+ "loss": 0.8207,
1598
+ "step": 2270
1599
+ },
1600
+ {
1601
+ "epoch": 1.2357723577235773,
1602
+ "grad_norm": 0.0,
1603
+ "learning_rate": 7.318566635862797e-05,
1604
+ "loss": 0.863,
1605
+ "step": 2280
1606
+ },
1607
+ {
1608
+ "epoch": 1.2411924119241193,
1609
+ "grad_norm": 0.0,
1610
+ "learning_rate": 7.290580482858088e-05,
1611
+ "loss": 0.9107,
1612
+ "step": 2290
1613
+ },
1614
+ {
1615
+ "epoch": 1.2466124661246614,
1616
+ "grad_norm": 0.0,
1617
+ "learning_rate": 7.262503210468728e-05,
1618
+ "loss": 0.7615,
1619
+ "step": 2300
1620
+ },
1621
+ {
1622
+ "epoch": 1.2520325203252032,
1623
+ "grad_norm": 0.0,
1624
+ "learning_rate": 7.234335935609761e-05,
1625
+ "loss": 0.8431,
1626
+ "step": 2310
1627
+ },
1628
+ {
1629
+ "epoch": 1.2574525745257452,
1630
+ "grad_norm": 0.0,
1631
+ "learning_rate": 7.20607977877652e-05,
1632
+ "loss": 0.8447,
1633
+ "step": 2320
1634
+ },
1635
+ {
1636
+ "epoch": 1.2628726287262872,
1637
+ "grad_norm": 0.0,
1638
+ "learning_rate": 7.177735864000073e-05,
1639
+ "loss": 0.8853,
1640
+ "step": 2330
1641
+ },
1642
+ {
1643
+ "epoch": 1.2682926829268293,
1644
+ "grad_norm": 0.0,
1645
+ "learning_rate": 7.149305318802502e-05,
1646
+ "loss": 0.9468,
1647
+ "step": 2340
1648
+ },
1649
+ {
1650
+ "epoch": 1.2737127371273713,
1651
+ "grad_norm": 0.0,
1652
+ "learning_rate": 7.120789274152049e-05,
1653
+ "loss": 0.7821,
1654
+ "step": 2350
1655
+ },
1656
+ {
1657
+ "epoch": 1.2791327913279134,
1658
+ "grad_norm": 0.0,
1659
+ "learning_rate": 7.092188864418127e-05,
1660
+ "loss": 0.6905,
1661
+ "step": 2360
1662
+ },
1663
+ {
1664
+ "epoch": 1.2845528455284554,
1665
+ "grad_norm": 0.0,
1666
+ "learning_rate": 7.063505227326198e-05,
1667
+ "loss": 0.7971,
1668
+ "step": 2370
1669
+ },
1670
+ {
1671
+ "epoch": 1.2899728997289972,
1672
+ "grad_norm": 0.0,
1673
+ "learning_rate": 7.03473950391251e-05,
1674
+ "loss": 0.6959,
1675
+ "step": 2380
1676
+ },
1677
+ {
1678
+ "epoch": 1.2953929539295392,
1679
+ "grad_norm": 0.0,
1680
+ "learning_rate": 7.005892838478711e-05,
1681
+ "loss": 0.8096,
1682
+ "step": 2390
1683
+ },
1684
+ {
1685
+ "epoch": 1.3008130081300813,
1686
+ "grad_norm": 0.0,
1687
+ "learning_rate": 6.976966378546322e-05,
1688
+ "loss": 0.93,
1689
+ "step": 2400
1690
+ },
1691
+ {
1692
+ "epoch": 1.3062330623306233,
1693
+ "grad_norm": 0.0,
1694
+ "learning_rate": 6.947961274811093e-05,
1695
+ "loss": 0.7973,
1696
+ "step": 2410
1697
+ },
1698
+ {
1699
+ "epoch": 1.3116531165311653,
1700
+ "grad_norm": 0.0,
1701
+ "learning_rate": 6.918878681097232e-05,
1702
+ "loss": 0.85,
1703
+ "step": 2420
1704
+ },
1705
+ {
1706
+ "epoch": 1.3170731707317074,
1707
+ "grad_norm": 0.0,
1708
+ "learning_rate": 6.889719754311495e-05,
1709
+ "loss": 0.7707,
1710
+ "step": 2430
1711
+ },
1712
+ {
1713
+ "epoch": 1.3224932249322494,
1714
+ "grad_norm": 0.0,
1715
+ "learning_rate": 6.860485654397173e-05,
1716
+ "loss": 0.7808,
1717
+ "step": 2440
1718
+ },
1719
+ {
1720
+ "epoch": 1.3279132791327912,
1721
+ "grad_norm": 0.0,
1722
+ "learning_rate": 6.831177544287952e-05,
1723
+ "loss": 0.8128,
1724
+ "step": 2450
1725
+ },
1726
+ {
1727
+ "epoch": 1.3333333333333333,
1728
+ "grad_norm": 0.0,
1729
+ "learning_rate": 6.80179658986164e-05,
1730
+ "loss": 0.7977,
1731
+ "step": 2460
1732
+ },
1733
+ {
1734
+ "epoch": 1.3387533875338753,
1735
+ "grad_norm": 0.0,
1736
+ "learning_rate": 6.7723439598938e-05,
1737
+ "loss": 0.7492,
1738
+ "step": 2470
1739
+ },
1740
+ {
1741
+ "epoch": 1.3441734417344173,
1742
+ "grad_norm": 0.0,
1743
+ "learning_rate": 6.742820826011245e-05,
1744
+ "loss": 0.8064,
1745
+ "step": 2480
1746
+ },
1747
+ {
1748
+ "epoch": 1.3495934959349594,
1749
+ "grad_norm": 0.0,
1750
+ "learning_rate": 6.71322836264544e-05,
1751
+ "loss": 0.807,
1752
+ "step": 2490
1753
+ },
1754
+ {
1755
+ "epoch": 1.3550135501355014,
1756
+ "grad_norm": 0.0,
1757
+ "learning_rate": 6.683567746985783e-05,
1758
+ "loss": 0.8208,
1759
+ "step": 2500
1760
+ },
1761
+ {
1762
+ "epoch": 1.3604336043360434,
1763
+ "grad_norm": 0.0,
1764
+ "learning_rate": 6.653840158932769e-05,
1765
+ "loss": 0.7258,
1766
+ "step": 2510
1767
+ },
1768
+ {
1769
+ "epoch": 1.3658536585365852,
1770
+ "grad_norm": 0.0,
1771
+ "learning_rate": 6.624046781051055e-05,
1772
+ "loss": 0.7142,
1773
+ "step": 2520
1774
+ },
1775
+ {
1776
+ "epoch": 1.3712737127371275,
1777
+ "grad_norm": 0.0,
1778
+ "learning_rate": 6.594188798522428e-05,
1779
+ "loss": 0.7837,
1780
+ "step": 2530
1781
+ },
1782
+ {
1783
+ "epoch": 1.3766937669376693,
1784
+ "grad_norm": 0.0,
1785
+ "learning_rate": 6.56426739909864e-05,
1786
+ "loss": 0.7829,
1787
+ "step": 2540
1788
+ },
1789
+ {
1790
+ "epoch": 1.3821138211382114,
1791
+ "grad_norm": 0.0,
1792
+ "learning_rate": 6.53428377305418e-05,
1793
+ "loss": 0.7371,
1794
+ "step": 2550
1795
+ },
1796
+ {
1797
+ "epoch": 1.3875338753387534,
1798
+ "grad_norm": 0.0,
1799
+ "learning_rate": 6.504239113138908e-05,
1800
+ "loss": 0.9048,
1801
+ "step": 2560
1802
+ },
1803
+ {
1804
+ "epoch": 1.3929539295392954,
1805
+ "grad_norm": 0.0,
1806
+ "learning_rate": 6.474134614530617e-05,
1807
+ "loss": 0.8665,
1808
+ "step": 2570
1809
+ },
1810
+ {
1811
+ "epoch": 1.3983739837398375,
1812
+ "grad_norm": 0.0,
1813
+ "learning_rate": 6.443971474787483e-05,
1814
+ "loss": 0.8496,
1815
+ "step": 2580
1816
+ },
1817
+ {
1818
+ "epoch": 1.4037940379403793,
1819
+ "grad_norm": 0.0,
1820
+ "learning_rate": 6.413750893800432e-05,
1821
+ "loss": 0.7842,
1822
+ "step": 2590
1823
+ },
1824
+ {
1825
+ "epoch": 1.4092140921409215,
1826
+ "grad_norm": 0.0,
1827
+ "learning_rate": 6.3834740737454e-05,
1828
+ "loss": 0.8222,
1829
+ "step": 2600
1830
+ },
1831
+ {
1832
+ "epoch": 1.4146341463414633,
1833
+ "grad_norm": 0.0,
1834
+ "learning_rate": 6.353142219035521e-05,
1835
+ "loss": 0.7915,
1836
+ "step": 2610
1837
+ },
1838
+ {
1839
+ "epoch": 1.4200542005420054,
1840
+ "grad_norm": 0.0,
1841
+ "learning_rate": 6.322756536273208e-05,
1842
+ "loss": 0.8833,
1843
+ "step": 2620
1844
+ },
1845
+ {
1846
+ "epoch": 1.4254742547425474,
1847
+ "grad_norm": 0.0,
1848
+ "learning_rate": 6.292318234202155e-05,
1849
+ "loss": 0.8277,
1850
+ "step": 2630
1851
+ },
1852
+ {
1853
+ "epoch": 1.4308943089430894,
1854
+ "grad_norm": 0.0,
1855
+ "learning_rate": 6.261828523659253e-05,
1856
+ "loss": 0.743,
1857
+ "step": 2640
1858
+ },
1859
+ {
1860
+ "epoch": 1.4363143631436315,
1861
+ "grad_norm": 0.0,
1862
+ "learning_rate": 6.231288617526427e-05,
1863
+ "loss": 0.6826,
1864
+ "step": 2650
1865
+ },
1866
+ {
1867
+ "epoch": 1.4417344173441735,
1868
+ "grad_norm": 0.0,
1869
+ "learning_rate": 6.200699730682384e-05,
1870
+ "loss": 0.7916,
1871
+ "step": 2660
1872
+ },
1873
+ {
1874
+ "epoch": 1.4471544715447155,
1875
+ "grad_norm": 0.0,
1876
+ "learning_rate": 6.170063079954283e-05,
1877
+ "loss": 0.7353,
1878
+ "step": 2670
1879
+ },
1880
+ {
1881
+ "epoch": 1.4525745257452574,
1882
+ "grad_norm": 0.0,
1883
+ "learning_rate": 6.139379884069337e-05,
1884
+ "loss": 0.8918,
1885
+ "step": 2680
1886
+ },
1887
+ {
1888
+ "epoch": 1.4579945799457994,
1889
+ "grad_norm": 0.0,
1890
+ "learning_rate": 6.108651363606324e-05,
1891
+ "loss": 0.7956,
1892
+ "step": 2690
1893
+ },
1894
+ {
1895
+ "epoch": 1.4634146341463414,
1896
+ "grad_norm": 0.0,
1897
+ "learning_rate": 6.077878740947035e-05,
1898
+ "loss": 0.808,
1899
+ "step": 2700
1900
+ },
1901
+ {
1902
+ "epoch": 1.4688346883468835,
1903
+ "grad_norm": 0.0,
1904
+ "learning_rate": 6.04706324022765e-05,
1905
+ "loss": 0.7646,
1906
+ "step": 2710
1907
+ },
1908
+ {
1909
+ "epoch": 1.4742547425474255,
1910
+ "grad_norm": 0.0,
1911
+ "learning_rate": 6.016206087290038e-05,
1912
+ "loss": 0.8579,
1913
+ "step": 2720
1914
+ },
1915
+ {
1916
+ "epoch": 1.4796747967479675,
1917
+ "grad_norm": 0.0,
1918
+ "learning_rate": 5.985308509633e-05,
1919
+ "loss": 0.887,
1920
+ "step": 2730
1921
+ },
1922
+ {
1923
+ "epoch": 1.4850948509485096,
1924
+ "grad_norm": 0.0,
1925
+ "learning_rate": 5.9543717363634263e-05,
1926
+ "loss": 0.8292,
1927
+ "step": 2740
1928
+ },
1929
+ {
1930
+ "epoch": 1.4905149051490514,
1931
+ "grad_norm": 0.0,
1932
+ "learning_rate": 5.9233969981474156e-05,
1933
+ "loss": 0.8304,
1934
+ "step": 2750
1935
+ },
1936
+ {
1937
+ "epoch": 1.4959349593495934,
1938
+ "grad_norm": 0.0,
1939
+ "learning_rate": 5.892385527161311e-05,
1940
+ "loss": 0.7978,
1941
+ "step": 2760
1942
+ },
1943
+ {
1944
+ "epoch": 1.5013550135501355,
1945
+ "grad_norm": 0.0,
1946
+ "learning_rate": 5.861338557042691e-05,
1947
+ "loss": 0.7651,
1948
+ "step": 2770
1949
+ },
1950
+ {
1951
+ "epoch": 1.5067750677506775,
1952
+ "grad_norm": 0.0,
1953
+ "learning_rate": 5.830257322841285e-05,
1954
+ "loss": 0.9219,
1955
+ "step": 2780
1956
+ },
1957
+ {
1958
+ "epoch": 1.5121951219512195,
1959
+ "grad_norm": 0.0,
1960
+ "learning_rate": 5.799143060969854e-05,
1961
+ "loss": 0.7874,
1962
+ "step": 2790
1963
+ },
1964
+ {
1965
+ "epoch": 1.5176151761517616,
1966
+ "grad_norm": 0.0,
1967
+ "learning_rate": 5.767997009154997e-05,
1968
+ "loss": 0.7405,
1969
+ "step": 2800
1970
+ },
1971
+ {
1972
+ "epoch": 1.5230352303523036,
1973
+ "grad_norm": 0.0,
1974
+ "learning_rate": 5.736820406387923e-05,
1975
+ "loss": 0.845,
1976
+ "step": 2810
1977
+ },
1978
+ {
1979
+ "epoch": 1.5284552845528454,
1980
+ "grad_norm": 0.0,
1981
+ "learning_rate": 5.705614492875153e-05,
1982
+ "loss": 0.8464,
1983
+ "step": 2820
1984
+ },
1985
+ {
1986
+ "epoch": 1.5338753387533877,
1987
+ "grad_norm": 0.0,
1988
+ "learning_rate": 5.6743805099891955e-05,
1989
+ "loss": 0.9143,
1990
+ "step": 2830
1991
+ },
1992
+ {
1993
+ "epoch": 1.5392953929539295,
1994
+ "grad_norm": 0.0,
1995
+ "learning_rate": 5.6431197002191594e-05,
1996
+ "loss": 0.804,
1997
+ "step": 2840
1998
+ },
1999
+ {
2000
+ "epoch": 1.5447154471544715,
2001
+ "grad_norm": 0.0,
2002
+ "learning_rate": 5.611833307121327e-05,
2003
+ "loss": 0.7703,
2004
+ "step": 2850
2005
+ },
2006
+ {
2007
+ "epoch": 1.5501355013550135,
2008
+ "grad_norm": 0.0,
2009
+ "learning_rate": 5.580522575269684e-05,
2010
+ "loss": 0.8818,
2011
+ "step": 2860
2012
+ },
2013
+ {
2014
+ "epoch": 1.5555555555555556,
2015
+ "grad_norm": 0.0,
2016
+ "learning_rate": 5.54918875020642e-05,
2017
+ "loss": 0.7634,
2018
+ "step": 2870
2019
+ },
2020
+ {
2021
+ "epoch": 1.5609756097560976,
2022
+ "grad_norm": 0.0,
2023
+ "learning_rate": 5.517833078392365e-05,
2024
+ "loss": 0.7817,
2025
+ "step": 2880
2026
+ },
2027
+ {
2028
+ "epoch": 1.5663956639566394,
2029
+ "grad_norm": 0.0,
2030
+ "learning_rate": 5.486456807157417e-05,
2031
+ "loss": 0.7829,
2032
+ "step": 2890
2033
+ },
2034
+ {
2035
+ "epoch": 1.5718157181571817,
2036
+ "grad_norm": 0.0,
2037
+ "learning_rate": 5.455061184650921e-05,
2038
+ "loss": 0.7587,
2039
+ "step": 2900
2040
+ },
2041
+ {
2042
+ "epoch": 1.5772357723577235,
2043
+ "grad_norm": 0.0,
2044
+ "learning_rate": 5.423647459792018e-05,
2045
+ "loss": 0.6822,
2046
+ "step": 2910
2047
+ },
2048
+ {
2049
+ "epoch": 1.5826558265582655,
2050
+ "grad_norm": 0.0,
2051
+ "learning_rate": 5.392216882219956e-05,
2052
+ "loss": 0.8737,
2053
+ "step": 2920
2054
+ },
2055
+ {
2056
+ "epoch": 1.5880758807588076,
2057
+ "grad_norm": 0.0,
2058
+ "learning_rate": 5.360770702244388e-05,
2059
+ "loss": 0.8793,
2060
+ "step": 2930
2061
+ },
2062
+ {
2063
+ "epoch": 1.5934959349593496,
2064
+ "grad_norm": 0.0,
2065
+ "learning_rate": 5.3293101707956306e-05,
2066
+ "loss": 0.8142,
2067
+ "step": 2940
2068
+ },
2069
+ {
2070
+ "epoch": 1.5989159891598916,
2071
+ "grad_norm": 0.0,
2072
+ "learning_rate": 5.2978365393749044e-05,
2073
+ "loss": 0.718,
2074
+ "step": 2950
2075
+ },
2076
+ {
2077
+ "epoch": 1.6043360433604335,
2078
+ "grad_norm": 0.0,
2079
+ "learning_rate": 5.266351060004544e-05,
2080
+ "loss": 0.8058,
2081
+ "step": 2960
2082
+ },
2083
+ {
2084
+ "epoch": 1.6097560975609757,
2085
+ "grad_norm": 0.0,
2086
+ "learning_rate": 5.234854985178196e-05,
2087
+ "loss": 0.8089,
2088
+ "step": 2970
2089
+ },
2090
+ {
2091
+ "epoch": 1.6151761517615175,
2092
+ "grad_norm": 0.0,
2093
+ "learning_rate": 5.203349567811e-05,
2094
+ "loss": 0.7888,
2095
+ "step": 2980
2096
+ },
2097
+ {
2098
+ "epoch": 1.6205962059620598,
2099
+ "grad_norm": 0.0,
2100
+ "learning_rate": 5.1718360611897374e-05,
2101
+ "loss": 0.761,
2102
+ "step": 2990
2103
+ },
2104
+ {
2105
+ "epoch": 1.6260162601626016,
2106
+ "grad_norm": 0.0,
2107
+ "learning_rate": 5.140315718922979e-05,
2108
+ "loss": 0.7682,
2109
+ "step": 3000
2110
+ },
2111
+ {
2112
+ "epoch": 1.6314363143631436,
2113
+ "grad_norm": 0.0,
2114
+ "learning_rate": 5.108789794891224e-05,
2115
+ "loss": 0.8024,
2116
+ "step": 3010
2117
+ },
2118
+ {
2119
+ "epoch": 1.6368563685636857,
2120
+ "grad_norm": 0.0,
2121
+ "learning_rate": 5.0772595431970095e-05,
2122
+ "loss": 0.8088,
2123
+ "step": 3020
2124
+ },
2125
+ {
2126
+ "epoch": 1.6422764227642277,
2127
+ "grad_norm": 0.0,
2128
+ "learning_rate": 5.0457262181150286e-05,
2129
+ "loss": 0.7911,
2130
+ "step": 3030
2131
+ },
2132
+ {
2133
+ "epoch": 1.6476964769647697,
2134
+ "grad_norm": 0.0,
2135
+ "learning_rate": 5.014191074042233e-05,
2136
+ "loss": 0.7997,
2137
+ "step": 3040
2138
+ },
2139
+ {
2140
+ "epoch": 1.6531165311653115,
2141
+ "grad_norm": 0.0,
2142
+ "learning_rate": 4.9826553654479366e-05,
2143
+ "loss": 0.7467,
2144
+ "step": 3050
2145
+ },
2146
+ {
2147
+ "epoch": 1.6585365853658538,
2148
+ "grad_norm": 0.0,
2149
+ "learning_rate": 4.9511203468239064e-05,
2150
+ "loss": 0.8015,
2151
+ "step": 3060
2152
+ },
2153
+ {
2154
+ "epoch": 1.6639566395663956,
2155
+ "grad_norm": 0.0,
2156
+ "learning_rate": 4.9195872726344655e-05,
2157
+ "loss": 0.8341,
2158
+ "step": 3070
2159
+ },
2160
+ {
2161
+ "epoch": 1.6693766937669376,
2162
+ "grad_norm": 0.0,
2163
+ "learning_rate": 4.888057397266585e-05,
2164
+ "loss": 0.7597,
2165
+ "step": 3080
2166
+ },
2167
+ {
2168
+ "epoch": 1.6747967479674797,
2169
+ "grad_norm": 0.0,
2170
+ "learning_rate": 4.856531974979987e-05,
2171
+ "loss": 0.7855,
2172
+ "step": 3090
2173
+ },
2174
+ {
2175
+ "epoch": 1.6802168021680217,
2176
+ "grad_norm": 0.0,
2177
+ "learning_rate": 4.8250122598572537e-05,
2178
+ "loss": 0.7871,
2179
+ "step": 3100
2180
+ },
2181
+ {
2182
+ "epoch": 1.6856368563685638,
2183
+ "grad_norm": 0.0,
2184
+ "learning_rate": 4.79349950575393e-05,
2185
+ "loss": 0.8974,
2186
+ "step": 3110
2187
+ },
2188
+ {
2189
+ "epoch": 1.6910569105691056,
2190
+ "grad_norm": 0.0,
2191
+ "learning_rate": 4.7619949662486554e-05,
2192
+ "loss": 0.8021,
2193
+ "step": 3120
2194
+ },
2195
+ {
2196
+ "epoch": 1.6964769647696478,
2197
+ "grad_norm": 0.0,
2198
+ "learning_rate": 4.7304998945932904e-05,
2199
+ "loss": 0.7876,
2200
+ "step": 3130
2201
+ },
2202
+ {
2203
+ "epoch": 1.7018970189701896,
2204
+ "grad_norm": 0.0,
2205
+ "learning_rate": 4.699015543663066e-05,
2206
+ "loss": 0.901,
2207
+ "step": 3140
2208
+ },
2209
+ {
2210
+ "epoch": 1.7073170731707317,
2211
+ "grad_norm": 0.0,
2212
+ "learning_rate": 4.667543165906739e-05,
2213
+ "loss": 0.7647,
2214
+ "step": 3150
2215
+ },
2216
+ {
2217
+ "epoch": 1.7127371273712737,
2218
+ "grad_norm": 0.0,
2219
+ "learning_rate": 4.6360840132967735e-05,
2220
+ "loss": 0.9019,
2221
+ "step": 3160
2222
+ },
2223
+ {
2224
+ "epoch": 1.7181571815718157,
2225
+ "grad_norm": 0.0,
2226
+ "learning_rate": 4.604639337279543e-05,
2227
+ "loss": 0.7046,
2228
+ "step": 3170
2229
+ },
2230
+ {
2231
+ "epoch": 1.7235772357723578,
2232
+ "grad_norm": 0.0,
2233
+ "learning_rate": 4.5732103887255354e-05,
2234
+ "loss": 0.7644,
2235
+ "step": 3180
2236
+ },
2237
+ {
2238
+ "epoch": 1.7289972899728996,
2239
+ "grad_norm": 0.0,
2240
+ "learning_rate": 4.541798417879598e-05,
2241
+ "loss": 0.8395,
2242
+ "step": 3190
2243
+ },
2244
+ {
2245
+ "epoch": 1.7344173441734418,
2246
+ "grad_norm": 0.0,
2247
+ "learning_rate": 4.5104046743112094e-05,
2248
+ "loss": 0.7812,
2249
+ "step": 3200
2250
+ },
2251
+ {
2252
+ "epoch": 1.7398373983739837,
2253
+ "grad_norm": 0.0,
2254
+ "learning_rate": 4.479030406864763e-05,
2255
+ "loss": 0.7638,
2256
+ "step": 3210
2257
+ },
2258
+ {
2259
+ "epoch": 1.7452574525745257,
2260
+ "grad_norm": 0.0,
2261
+ "learning_rate": 4.447676863609892e-05,
2262
+ "loss": 0.7856,
2263
+ "step": 3220
2264
+ },
2265
+ {
2266
+ "epoch": 1.7506775067750677,
2267
+ "grad_norm": 0.0,
2268
+ "learning_rate": 4.4163452917918194e-05,
2269
+ "loss": 0.8102,
2270
+ "step": 3230
2271
+ },
2272
+ {
2273
+ "epoch": 1.7560975609756098,
2274
+ "grad_norm": 0.0,
2275
+ "learning_rate": 4.3850369377817465e-05,
2276
+ "loss": 0.9204,
2277
+ "step": 3240
2278
+ },
2279
+ {
2280
+ "epoch": 1.7615176151761518,
2281
+ "grad_norm": 0.0,
2282
+ "learning_rate": 4.353753047027269e-05,
2283
+ "loss": 0.8147,
2284
+ "step": 3250
2285
+ },
2286
+ {
2287
+ "epoch": 1.7669376693766936,
2288
+ "grad_norm": 0.0,
2289
+ "learning_rate": 4.32249486400283e-05,
2290
+ "loss": 0.7163,
2291
+ "step": 3260
2292
+ },
2293
+ {
2294
+ "epoch": 1.7723577235772359,
2295
+ "grad_norm": 0.0,
2296
+ "learning_rate": 4.2912636321602186e-05,
2297
+ "loss": 0.7531,
2298
+ "step": 3270
2299
+ },
2300
+ {
2301
+ "epoch": 1.7777777777777777,
2302
+ "grad_norm": 0.0,
2303
+ "learning_rate": 4.260060593879108e-05,
2304
+ "loss": 0.8307,
2305
+ "step": 3280
2306
+ },
2307
+ {
2308
+ "epoch": 1.78319783197832,
2309
+ "grad_norm": 0.0,
2310
+ "learning_rate": 4.228886990417627e-05,
2311
+ "loss": 1.0805,
2312
+ "step": 3290
2313
+ },
2314
+ {
2315
+ "epoch": 1.7886178861788617,
2316
+ "grad_norm": 0.0,
2317
+ "learning_rate": 4.197744061862987e-05,
2318
+ "loss": 0.7975,
2319
+ "step": 3300
2320
+ },
2321
+ {
2322
+ "epoch": 1.7940379403794038,
2323
+ "grad_norm": 0.0,
2324
+ "learning_rate": 4.1666330470821536e-05,
2325
+ "loss": 0.6771,
2326
+ "step": 3310
2327
+ },
2328
+ {
2329
+ "epoch": 1.7994579945799458,
2330
+ "grad_norm": 0.0,
2331
+ "learning_rate": 4.135555183672557e-05,
2332
+ "loss": 0.7911,
2333
+ "step": 3320
2334
+ },
2335
+ {
2336
+ "epoch": 1.8048780487804879,
2337
+ "grad_norm": 0.0,
2338
+ "learning_rate": 4.104511707912866e-05,
2339
+ "loss": 0.9151,
2340
+ "step": 3330
2341
+ },
2342
+ {
2343
+ "epoch": 1.8102981029810299,
2344
+ "grad_norm": 0.0,
2345
+ "learning_rate": 4.0735038547138065e-05,
2346
+ "loss": 0.7033,
2347
+ "step": 3340
2348
+ },
2349
+ {
2350
+ "epoch": 1.8157181571815717,
2351
+ "grad_norm": 0.0,
2352
+ "learning_rate": 4.042532857569039e-05,
2353
+ "loss": 0.725,
2354
+ "step": 3350
2355
+ },
2356
+ {
2357
+ "epoch": 1.821138211382114,
2358
+ "grad_norm": 0.0,
2359
+ "learning_rate": 4.011599948506088e-05,
2360
+ "loss": 0.7157,
2361
+ "step": 3360
2362
+ },
2363
+ {
2364
+ "epoch": 1.8265582655826558,
2365
+ "grad_norm": 0.0,
2366
+ "learning_rate": 3.9807063580373314e-05,
2367
+ "loss": 0.8203,
2368
+ "step": 3370
2369
+ },
2370
+ {
2371
+ "epoch": 1.8319783197831978,
2372
+ "grad_norm": 0.0,
2373
+ "learning_rate": 3.949853315111055e-05,
2374
+ "loss": 0.7513,
2375
+ "step": 3380
2376
+ },
2377
+ {
2378
+ "epoch": 1.8373983739837398,
2379
+ "grad_norm": 0.0,
2380
+ "learning_rate": 3.919042047062558e-05,
2381
+ "loss": 0.7372,
2382
+ "step": 3390
2383
+ },
2384
+ {
2385
+ "epoch": 1.8428184281842819,
2386
+ "grad_norm": 0.0,
2387
+ "learning_rate": 3.8882737795653346e-05,
2388
+ "loss": 0.7178,
2389
+ "step": 3400
2390
+ },
2391
+ {
2392
+ "epoch": 1.848238482384824,
2393
+ "grad_norm": 0.0,
2394
+ "learning_rate": 3.857549736582316e-05,
2395
+ "loss": 0.7819,
2396
+ "step": 3410
2397
+ },
2398
+ {
2399
+ "epoch": 1.8536585365853657,
2400
+ "grad_norm": 0.0,
2401
+ "learning_rate": 3.8268711403171805e-05,
2402
+ "loss": 0.7438,
2403
+ "step": 3420
2404
+ },
2405
+ {
2406
+ "epoch": 1.859078590785908,
2407
+ "grad_norm": 0.0,
2408
+ "learning_rate": 3.796239211165733e-05,
2409
+ "loss": 0.7724,
2410
+ "step": 3430
2411
+ },
2412
+ {
2413
+ "epoch": 1.8644986449864498,
2414
+ "grad_norm": 0.0,
2415
+ "learning_rate": 3.765655167667358e-05,
2416
+ "loss": 0.8343,
2417
+ "step": 3440
2418
+ },
2419
+ {
2420
+ "epoch": 1.8699186991869918,
2421
+ "grad_norm": 0.0,
2422
+ "learning_rate": 3.735120226456551e-05,
2423
+ "loss": 0.7478,
2424
+ "step": 3450
2425
+ },
2426
+ {
2427
+ "epoch": 1.8753387533875339,
2428
+ "grad_norm": 0.0,
2429
+ "learning_rate": 3.704635602214513e-05,
2430
+ "loss": 0.7864,
2431
+ "step": 3460
2432
+ },
2433
+ {
2434
+ "epoch": 1.880758807588076,
2435
+ "grad_norm": 0.0,
2436
+ "learning_rate": 3.6742025076208344e-05,
2437
+ "loss": 0.7534,
2438
+ "step": 3470
2439
+ },
2440
+ {
2441
+ "epoch": 1.886178861788618,
2442
+ "grad_norm": 0.0,
2443
+ "learning_rate": 3.643822153305252e-05,
2444
+ "loss": 0.7924,
2445
+ "step": 3480
2446
+ },
2447
+ {
2448
+ "epoch": 1.8915989159891597,
2449
+ "grad_norm": 0.0,
2450
+ "learning_rate": 3.613495747799498e-05,
2451
+ "loss": 0.8663,
2452
+ "step": 3490
2453
+ },
2454
+ {
2455
+ "epoch": 1.897018970189702,
2456
+ "grad_norm": 0.0,
2457
+ "learning_rate": 3.583224497489213e-05,
2458
+ "loss": 0.8439,
2459
+ "step": 3500
2460
+ },
2461
+ {
2462
+ "epoch": 1.9024390243902438,
2463
+ "grad_norm": 0.0,
2464
+ "learning_rate": 3.553009606565962e-05,
2465
+ "loss": 0.7788,
2466
+ "step": 3510
2467
+ },
2468
+ {
2469
+ "epoch": 1.907859078590786,
2470
+ "grad_norm": 0.0,
2471
+ "learning_rate": 3.522852276979337e-05,
2472
+ "loss": 0.8515,
2473
+ "step": 3520
2474
+ },
2475
+ {
2476
+ "epoch": 1.9132791327913279,
2477
+ "grad_norm": 0.0,
2478
+ "learning_rate": 3.492753708389134e-05,
2479
+ "loss": 0.7187,
2480
+ "step": 3530
2481
+ },
2482
+ {
2483
+ "epoch": 1.91869918699187,
2484
+ "grad_norm": 0.0,
2485
+ "learning_rate": 3.462715098117632e-05,
2486
+ "loss": 0.7172,
2487
+ "step": 3540
2488
+ },
2489
+ {
2490
+ "epoch": 1.924119241192412,
2491
+ "grad_norm": 0.0,
2492
+ "learning_rate": 3.4327376411019675e-05,
2493
+ "loss": 0.7059,
2494
+ "step": 3550
2495
+ },
2496
+ {
2497
+ "epoch": 1.9295392953929538,
2498
+ "grad_norm": 0.0,
2499
+ "learning_rate": 3.4028225298465987e-05,
2500
+ "loss": 0.9021,
2501
+ "step": 3560
2502
+ },
2503
+ {
2504
+ "epoch": 1.934959349593496,
2505
+ "grad_norm": 0.0,
2506
+ "learning_rate": 3.372970954375867e-05,
2507
+ "loss": 0.7364,
2508
+ "step": 3570
2509
+ },
2510
+ {
2511
+ "epoch": 1.9403794037940378,
2512
+ "grad_norm": 0.0,
2513
+ "learning_rate": 3.343184102186655e-05,
2514
+ "loss": 0.8083,
2515
+ "step": 3580
2516
+ },
2517
+ {
2518
+ "epoch": 1.94579945799458,
2519
+ "grad_norm": 0.0,
2520
+ "learning_rate": 3.313463158201157e-05,
2521
+ "loss": 0.7949,
2522
+ "step": 3590
2523
+ },
2524
+ {
2525
+ "epoch": 1.951219512195122,
2526
+ "grad_norm": 0.0,
2527
+ "learning_rate": 3.283809304719728e-05,
2528
+ "loss": 0.7554,
2529
+ "step": 3600
2530
+ },
2531
+ {
2532
+ "epoch": 1.956639566395664,
2533
+ "grad_norm": 0.0,
2534
+ "learning_rate": 3.254223721373866e-05,
2535
+ "loss": 0.7353,
2536
+ "step": 3610
2537
+ },
2538
+ {
2539
+ "epoch": 1.962059620596206,
2540
+ "grad_norm": 0.0,
2541
+ "learning_rate": 3.2247075850792774e-05,
2542
+ "loss": 0.6905,
2543
+ "step": 3620
2544
+ },
2545
+ {
2546
+ "epoch": 1.967479674796748,
2547
+ "grad_norm": 0.0,
2548
+ "learning_rate": 3.195262069989064e-05,
2549
+ "loss": 0.7416,
2550
+ "step": 3630
2551
+ },
2552
+ {
2553
+ "epoch": 1.97289972899729,
2554
+ "grad_norm": 0.0,
2555
+ "learning_rate": 3.1658883474470096e-05,
2556
+ "loss": 0.8705,
2557
+ "step": 3640
2558
+ },
2559
+ {
2560
+ "epoch": 1.9783197831978319,
2561
+ "grad_norm": 0.0,
2562
+ "learning_rate": 3.136587585940991e-05,
2563
+ "loss": 0.8878,
2564
+ "step": 3650
2565
+ },
2566
+ {
2567
+ "epoch": 1.9837398373983741,
2568
+ "grad_norm": 0.0,
2569
+ "learning_rate": 3.107360951056493e-05,
2570
+ "loss": 0.6716,
2571
+ "step": 3660
2572
+ },
2573
+ {
2574
+ "epoch": 1.989159891598916,
2575
+ "grad_norm": 0.0,
2576
+ "learning_rate": 3.0782096054302375e-05,
2577
+ "loss": 0.7695,
2578
+ "step": 3670
2579
+ },
2580
+ {
2581
+ "epoch": 1.994579945799458,
2582
+ "grad_norm": 0.0,
2583
+ "learning_rate": 3.0491347087039363e-05,
2584
+ "loss": 0.8582,
2585
+ "step": 3680
2586
+ },
2587
+ {
2588
+ "epoch": 2.0,
2589
+ "grad_norm": 0.0,
2590
+ "learning_rate": 3.020137417478163e-05,
2591
+ "loss": 0.7794,
2592
+ "step": 3690
2593
+ },
2594
+ {
2595
+ "epoch": 2.005420054200542,
2596
+ "grad_norm": 0.0,
2597
+ "learning_rate": 2.9912188852663404e-05,
2598
+ "loss": 0.6789,
2599
+ "step": 3700
2600
+ },
2601
+ {
2602
+ "epoch": 2.010840108401084,
2603
+ "grad_norm": 0.0,
2604
+ "learning_rate": 2.962380262448855e-05,
2605
+ "loss": 0.6068,
2606
+ "step": 3710
2607
+ },
2608
+ {
2609
+ "epoch": 2.016260162601626,
2610
+ "grad_norm": 0.0,
2611
+ "learning_rate": 2.9336226962272904e-05,
2612
+ "loss": 0.5462,
2613
+ "step": 3720
2614
+ },
2615
+ {
2616
+ "epoch": 2.021680216802168,
2617
+ "grad_norm": 0.0,
2618
+ "learning_rate": 2.9049473305788045e-05,
2619
+ "loss": 0.5795,
2620
+ "step": 3730
2621
+ },
2622
+ {
2623
+ "epoch": 2.02710027100271,
2624
+ "grad_norm": 0.0,
2625
+ "learning_rate": 2.876355306210604e-05,
2626
+ "loss": 0.5308,
2627
+ "step": 3740
2628
+ },
2629
+ {
2630
+ "epoch": 2.032520325203252,
2631
+ "grad_norm": 0.0,
2632
+ "learning_rate": 2.8478477605145815e-05,
2633
+ "loss": 0.5021,
2634
+ "step": 3750
2635
+ },
2636
+ {
2637
+ "epoch": 2.037940379403794,
2638
+ "grad_norm": 0.0,
2639
+ "learning_rate": 2.819425827522061e-05,
2640
+ "loss": 0.5725,
2641
+ "step": 3760
2642
+ },
2643
+ {
2644
+ "epoch": 2.043360433604336,
2645
+ "grad_norm": 0.0,
2646
+ "learning_rate": 2.791090637858692e-05,
2647
+ "loss": 0.5371,
2648
+ "step": 3770
2649
+ },
2650
+ {
2651
+ "epoch": 2.048780487804878,
2652
+ "grad_norm": 0.0,
2653
+ "learning_rate": 2.7628433186994705e-05,
2654
+ "loss": 0.4408,
2655
+ "step": 3780
2656
+ },
2657
+ {
2658
+ "epoch": 2.05420054200542,
2659
+ "grad_norm": 0.0,
2660
+ "learning_rate": 2.7346849937238983e-05,
2661
+ "loss": 0.5324,
2662
+ "step": 3790
2663
+ },
2664
+ {
2665
+ "epoch": 2.059620596205962,
2666
+ "grad_norm": 0.0,
2667
+ "learning_rate": 2.7066167830712897e-05,
2668
+ "loss": 0.537,
2669
+ "step": 3800
2670
+ },
2671
+ {
2672
+ "epoch": 2.065040650406504,
2673
+ "grad_norm": 0.0,
2674
+ "learning_rate": 2.678639803296203e-05,
2675
+ "loss": 0.6198,
2676
+ "step": 3810
2677
+ },
2678
+ {
2679
+ "epoch": 2.0704607046070462,
2680
+ "grad_norm": 0.0,
2681
+ "learning_rate": 2.6507551673240295e-05,
2682
+ "loss": 0.6005,
2683
+ "step": 3820
2684
+ },
2685
+ {
2686
+ "epoch": 2.075880758807588,
2687
+ "grad_norm": 0.0,
2688
+ "learning_rate": 2.622963984406722e-05,
2689
+ "loss": 0.5428,
2690
+ "step": 3830
2691
+ },
2692
+ {
2693
+ "epoch": 2.08130081300813,
2694
+ "grad_norm": 0.0,
2695
+ "learning_rate": 2.595267360078665e-05,
2696
+ "loss": 0.5816,
2697
+ "step": 3840
2698
+ },
2699
+ {
2700
+ "epoch": 2.086720867208672,
2701
+ "grad_norm": 0.0,
2702
+ "learning_rate": 2.567666396112699e-05,
2703
+ "loss": 0.5656,
2704
+ "step": 3850
2705
+ },
2706
+ {
2707
+ "epoch": 2.092140921409214,
2708
+ "grad_norm": 0.0,
2709
+ "learning_rate": 2.5401621904762896e-05,
2710
+ "loss": 0.5424,
2711
+ "step": 3860
2712
+ },
2713
+ {
2714
+ "epoch": 2.097560975609756,
2715
+ "grad_norm": 0.0,
2716
+ "learning_rate": 2.512755837287859e-05,
2717
+ "loss": 0.5393,
2718
+ "step": 3870
2719
+ },
2720
+ {
2721
+ "epoch": 2.102981029810298,
2722
+ "grad_norm": 0.0,
2723
+ "learning_rate": 2.485448426773248e-05,
2724
+ "loss": 0.4829,
2725
+ "step": 3880
2726
+ },
2727
+ {
2728
+ "epoch": 2.1084010840108403,
2729
+ "grad_norm": 0.0,
2730
+ "learning_rate": 2.458241045222356e-05,
2731
+ "loss": 0.5376,
2732
+ "step": 3890
2733
+ },
2734
+ {
2735
+ "epoch": 2.113821138211382,
2736
+ "grad_norm": 0.0,
2737
+ "learning_rate": 2.4311347749459252e-05,
2738
+ "loss": 0.5107,
2739
+ "step": 3900
2740
+ },
2741
+ {
2742
+ "epoch": 2.1192411924119243,
2743
+ "grad_norm": 0.0,
2744
+ "learning_rate": 2.4041306942324892e-05,
2745
+ "loss": 0.5824,
2746
+ "step": 3910
2747
+ },
2748
+ {
2749
+ "epoch": 2.124661246612466,
2750
+ "grad_norm": 0.0,
2751
+ "learning_rate": 2.3772298773054757e-05,
2752
+ "loss": 0.5408,
2753
+ "step": 3920
2754
+ },
2755
+ {
2756
+ "epoch": 2.130081300813008,
2757
+ "grad_norm": 0.0,
2758
+ "learning_rate": 2.3504333942804728e-05,
2759
+ "loss": 0.4924,
2760
+ "step": 3930
2761
+ },
2762
+ {
2763
+ "epoch": 2.13550135501355,
2764
+ "grad_norm": 0.0,
2765
+ "learning_rate": 2.323742311122667e-05,
2766
+ "loss": 0.4882,
2767
+ "step": 3940
2768
+ },
2769
+ {
2770
+ "epoch": 2.140921409214092,
2771
+ "grad_norm": 0.0,
2772
+ "learning_rate": 2.2971576896044283e-05,
2773
+ "loss": 0.5444,
2774
+ "step": 3950
2775
+ },
2776
+ {
2777
+ "epoch": 2.1463414634146343,
2778
+ "grad_norm": 0.0,
2779
+ "learning_rate": 2.2706805872630816e-05,
2780
+ "loss": 0.4971,
2781
+ "step": 3960
2782
+ },
2783
+ {
2784
+ "epoch": 2.151761517615176,
2785
+ "grad_norm": 0.0,
2786
+ "learning_rate": 2.2443120573588323e-05,
2787
+ "loss": 0.6078,
2788
+ "step": 3970
2789
+ },
2790
+ {
2791
+ "epoch": 2.1571815718157183,
2792
+ "grad_norm": 0.0,
2793
+ "learning_rate": 2.218053148832872e-05,
2794
+ "loss": 0.5503,
2795
+ "step": 3980
2796
+ },
2797
+ {
2798
+ "epoch": 2.16260162601626,
2799
+ "grad_norm": 0.0,
2800
+ "learning_rate": 2.1919049062656476e-05,
2801
+ "loss": 0.4805,
2802
+ "step": 3990
2803
+ },
2804
+ {
2805
+ "epoch": 2.168021680216802,
2806
+ "grad_norm": 0.0,
2807
+ "learning_rate": 2.1658683698353095e-05,
2808
+ "loss": 0.5476,
2809
+ "step": 4000
2810
+ },
2811
+ {
2812
+ "epoch": 2.1734417344173442,
2813
+ "grad_norm": 0.0,
2814
+ "learning_rate": 2.1399445752763374e-05,
2815
+ "loss": 0.4429,
2816
+ "step": 4010
2817
+ },
2818
+ {
2819
+ "epoch": 2.178861788617886,
2820
+ "grad_norm": 0.0,
2821
+ "learning_rate": 2.1141345538383306e-05,
2822
+ "loss": 0.5418,
2823
+ "step": 4020
2824
+ },
2825
+ {
2826
+ "epoch": 2.1842818428184283,
2827
+ "grad_norm": 0.0,
2828
+ "learning_rate": 2.0884393322449895e-05,
2829
+ "loss": 0.55,
2830
+ "step": 4030
2831
+ },
2832
+ {
2833
+ "epoch": 2.18970189701897,
2834
+ "grad_norm": 0.0,
2835
+ "learning_rate": 2.0628599326532738e-05,
2836
+ "loss": 0.4787,
2837
+ "step": 4040
2838
+ },
2839
+ {
2840
+ "epoch": 2.1951219512195124,
2841
+ "grad_norm": 0.0,
2842
+ "learning_rate": 2.0373973726127378e-05,
2843
+ "loss": 0.5278,
2844
+ "step": 4050
2845
+ },
2846
+ {
2847
+ "epoch": 2.200542005420054,
2848
+ "grad_norm": 0.0,
2849
+ "learning_rate": 2.0120526650250533e-05,
2850
+ "loss": 0.5121,
2851
+ "step": 4060
2852
+ },
2853
+ {
2854
+ "epoch": 2.205962059620596,
2855
+ "grad_norm": 0.0,
2856
+ "learning_rate": 1.9868268181037185e-05,
2857
+ "loss": 0.5864,
2858
+ "step": 4070
2859
+ },
2860
+ {
2861
+ "epoch": 2.2113821138211383,
2862
+ "grad_norm": 0.0,
2863
+ "learning_rate": 1.961720835333949e-05,
2864
+ "loss": 0.6388,
2865
+ "step": 4080
2866
+ },
2867
+ {
2868
+ "epoch": 2.21680216802168,
2869
+ "grad_norm": 0.0,
2870
+ "learning_rate": 1.9367357154327576e-05,
2871
+ "loss": 0.576,
2872
+ "step": 4090
2873
+ },
2874
+ {
2875
+ "epoch": 2.2222222222222223,
2876
+ "grad_norm": 0.0,
2877
+ "learning_rate": 1.91187245230923e-05,
2878
+ "loss": 0.56,
2879
+ "step": 4100
2880
+ },
2881
+ {
2882
+ "epoch": 2.227642276422764,
2883
+ "grad_norm": 0.0,
2884
+ "learning_rate": 1.8871320350249833e-05,
2885
+ "loss": 0.5696,
2886
+ "step": 4110
2887
+ },
2888
+ {
2889
+ "epoch": 2.2330623306233064,
2890
+ "grad_norm": 0.0,
2891
+ "learning_rate": 1.862515447754819e-05,
2892
+ "loss": 0.5115,
2893
+ "step": 4120
2894
+ },
2895
+ {
2896
+ "epoch": 2.238482384823848,
2897
+ "grad_norm": 0.0,
2898
+ "learning_rate": 1.8380236697475832e-05,
2899
+ "loss": 0.5578,
2900
+ "step": 4130
2901
+ },
2902
+ {
2903
+ "epoch": 2.2439024390243905,
2904
+ "grad_norm": 0.0,
2905
+ "learning_rate": 1.813657675287198e-05,
2906
+ "loss": 0.5048,
2907
+ "step": 4140
2908
+ },
2909
+ {
2910
+ "epoch": 2.2493224932249323,
2911
+ "grad_norm": 0.0,
2912
+ "learning_rate": 1.789418433653912e-05,
2913
+ "loss": 0.5528,
2914
+ "step": 4150
2915
+ },
2916
+ {
2917
+ "epoch": 2.254742547425474,
2918
+ "grad_norm": 0.0,
2919
+ "learning_rate": 1.7653069090857434e-05,
2920
+ "loss": 0.4945,
2921
+ "step": 4160
2922
+ },
2923
+ {
2924
+ "epoch": 2.2601626016260163,
2925
+ "grad_norm": 0.0,
2926
+ "learning_rate": 1.7413240607401164e-05,
2927
+ "loss": 0.4937,
2928
+ "step": 4170
2929
+ },
2930
+ {
2931
+ "epoch": 2.265582655826558,
2932
+ "grad_norm": 0.0,
2933
+ "learning_rate": 1.717470842655715e-05,
2934
+ "loss": 0.5175,
2935
+ "step": 4180
2936
+ },
2937
+ {
2938
+ "epoch": 2.2710027100271004,
2939
+ "grad_norm": 0.0,
2940
+ "learning_rate": 1.693748203714522e-05,
2941
+ "loss": 0.5842,
2942
+ "step": 4190
2943
+ },
2944
+ {
2945
+ "epoch": 2.2764227642276422,
2946
+ "grad_norm": 0.0,
2947
+ "learning_rate": 1.6701570876040777e-05,
2948
+ "loss": 0.5089,
2949
+ "step": 4200
2950
+ },
2951
+ {
2952
+ "epoch": 2.281842818428184,
2953
+ "grad_norm": 0.0,
2954
+ "learning_rate": 1.6466984327799385e-05,
2955
+ "loss": 0.5788,
2956
+ "step": 4210
2957
+ },
2958
+ {
2959
+ "epoch": 2.2872628726287263,
2960
+ "grad_norm": 0.0,
2961
+ "learning_rate": 1.6233731724283492e-05,
2962
+ "loss": 0.5136,
2963
+ "step": 4220
2964
+ },
2965
+ {
2966
+ "epoch": 2.292682926829268,
2967
+ "grad_norm": 0.0,
2968
+ "learning_rate": 1.6001822344291124e-05,
2969
+ "loss": 0.4981,
2970
+ "step": 4230
2971
+ },
2972
+ {
2973
+ "epoch": 2.2981029810298104,
2974
+ "grad_norm": 0.0,
2975
+ "learning_rate": 1.5771265413186832e-05,
2976
+ "loss": 0.5172,
2977
+ "step": 4240
2978
+ },
2979
+ {
2980
+ "epoch": 2.303523035230352,
2981
+ "grad_norm": 0.0,
2982
+ "learning_rate": 1.5542070102534706e-05,
2983
+ "loss": 0.5126,
2984
+ "step": 4250
2985
+ },
2986
+ {
2987
+ "epoch": 2.3089430894308944,
2988
+ "grad_norm": 0.0,
2989
+ "learning_rate": 1.5314245529733507e-05,
2990
+ "loss": 0.5028,
2991
+ "step": 4260
2992
+ },
2993
+ {
2994
+ "epoch": 2.3143631436314362,
2995
+ "grad_norm": 0.0,
2996
+ "learning_rate": 1.5087800757653997e-05,
2997
+ "loss": 0.4974,
2998
+ "step": 4270
2999
+ },
3000
+ {
3001
+ "epoch": 2.3197831978319785,
3002
+ "grad_norm": 0.0,
3003
+ "learning_rate": 1.48627447942784e-05,
3004
+ "loss": 0.4955,
3005
+ "step": 4280
3006
+ },
3007
+ {
3008
+ "epoch": 2.3252032520325203,
3009
+ "grad_norm": 0.0,
3010
+ "learning_rate": 1.4639086592342099e-05,
3011
+ "loss": 0.5425,
3012
+ "step": 4290
3013
+ },
3014
+ {
3015
+ "epoch": 2.330623306233062,
3016
+ "grad_norm": 0.0,
3017
+ "learning_rate": 1.4416835048977445e-05,
3018
+ "loss": 0.5073,
3019
+ "step": 4300
3020
+ },
3021
+ {
3022
+ "epoch": 2.3360433604336044,
3023
+ "grad_norm": 0.0,
3024
+ "learning_rate": 1.419599900535985e-05,
3025
+ "loss": 0.6215,
3026
+ "step": 4310
3027
+ },
3028
+ {
3029
+ "epoch": 2.341463414634146,
3030
+ "grad_norm": 0.0,
3031
+ "learning_rate": 1.3976587246356116e-05,
3032
+ "loss": 0.5859,
3033
+ "step": 4320
3034
+ },
3035
+ {
3036
+ "epoch": 2.3468834688346885,
3037
+ "grad_norm": 0.0,
3038
+ "learning_rate": 1.3758608500174908e-05,
3039
+ "loss": 0.497,
3040
+ "step": 4330
3041
+ },
3042
+ {
3043
+ "epoch": 2.3523035230352303,
3044
+ "grad_norm": 0.0,
3045
+ "learning_rate": 1.3542071438019622e-05,
3046
+ "loss": 0.5852,
3047
+ "step": 4340
3048
+ },
3049
+ {
3050
+ "epoch": 2.3577235772357725,
3051
+ "grad_norm": 0.0,
3052
+ "learning_rate": 1.3326984673743353e-05,
3053
+ "loss": 0.4882,
3054
+ "step": 4350
3055
+ },
3056
+ {
3057
+ "epoch": 2.3631436314363143,
3058
+ "grad_norm": 0.0,
3059
+ "learning_rate": 1.3113356763506363e-05,
3060
+ "loss": 0.5861,
3061
+ "step": 4360
3062
+ },
3063
+ {
3064
+ "epoch": 2.3685636856368566,
3065
+ "grad_norm": 0.0,
3066
+ "learning_rate": 1.2901196205435578e-05,
3067
+ "loss": 0.5987,
3068
+ "step": 4370
3069
+ },
3070
+ {
3071
+ "epoch": 2.3739837398373984,
3072
+ "grad_norm": 0.0,
3073
+ "learning_rate": 1.2690511439286623e-05,
3074
+ "loss": 0.5111,
3075
+ "step": 4380
3076
+ },
3077
+ {
3078
+ "epoch": 2.3794037940379402,
3079
+ "grad_norm": 0.0,
3080
+ "learning_rate": 1.248131084610804e-05,
3081
+ "loss": 0.555,
3082
+ "step": 4390
3083
+ },
3084
+ {
3085
+ "epoch": 2.3848238482384825,
3086
+ "grad_norm": 0.0,
3087
+ "learning_rate": 1.227360274790793e-05,
3088
+ "loss": 0.5821,
3089
+ "step": 4400
3090
+ },
3091
+ {
3092
+ "epoch": 2.3902439024390243,
3093
+ "grad_norm": 0.0,
3094
+ "learning_rate": 1.206739540732288e-05,
3095
+ "loss": 0.5988,
3096
+ "step": 4410
3097
+ },
3098
+ {
3099
+ "epoch": 2.3956639566395665,
3100
+ "grad_norm": 0.0,
3101
+ "learning_rate": 1.1862697027289254e-05,
3102
+ "loss": 0.5745,
3103
+ "step": 4420
3104
+ },
3105
+ {
3106
+ "epoch": 2.4010840108401084,
3107
+ "grad_norm": 0.0,
3108
+ "learning_rate": 1.1659515750716955e-05,
3109
+ "loss": 0.481,
3110
+ "step": 4430
3111
+ },
3112
+ {
3113
+ "epoch": 2.40650406504065,
3114
+ "grad_norm": 0.0,
3115
+ "learning_rate": 1.1457859660165404e-05,
3116
+ "loss": 0.5362,
3117
+ "step": 4440
3118
+ },
3119
+ {
3120
+ "epoch": 2.4119241192411924,
3121
+ "grad_norm": 0.0,
3122
+ "learning_rate": 1.1257736777522072e-05,
3123
+ "loss": 0.6335,
3124
+ "step": 4450
3125
+ },
3126
+ {
3127
+ "epoch": 2.4173441734417342,
3128
+ "grad_norm": 0.0,
3129
+ "learning_rate": 1.1059155063683357e-05,
3130
+ "loss": 0.5322,
3131
+ "step": 4460
3132
+ },
3133
+ {
3134
+ "epoch": 2.4227642276422765,
3135
+ "grad_norm": 0.0,
3136
+ "learning_rate": 1.0862122418237907e-05,
3137
+ "loss": 0.5453,
3138
+ "step": 4470
3139
+ },
3140
+ {
3141
+ "epoch": 2.4281842818428183,
3142
+ "grad_norm": 0.0,
3143
+ "learning_rate": 1.0666646679152365e-05,
3144
+ "loss": 0.5394,
3145
+ "step": 4480
3146
+ },
3147
+ {
3148
+ "epoch": 2.4336043360433606,
3149
+ "grad_norm": 0.0,
3150
+ "learning_rate": 1.0472735622459545e-05,
3151
+ "loss": 0.6681,
3152
+ "step": 4490
3153
+ },
3154
+ {
3155
+ "epoch": 2.4390243902439024,
3156
+ "grad_norm": 0.0,
3157
+ "learning_rate": 1.028039696194919e-05,
3158
+ "loss": 0.5178,
3159
+ "step": 4500
3160
+ },
3161
+ {
3162
+ "epoch": 2.4444444444444446,
3163
+ "grad_norm": 0.0,
3164
+ "learning_rate": 1.0089638348861024e-05,
3165
+ "loss": 0.4984,
3166
+ "step": 4510
3167
+ },
3168
+ {
3169
+ "epoch": 2.4498644986449865,
3170
+ "grad_norm": 0.0,
3171
+ "learning_rate": 9.900467371580407e-06,
3172
+ "loss": 0.5896,
3173
+ "step": 4520
3174
+ },
3175
+ {
3176
+ "epoch": 2.4552845528455283,
3177
+ "grad_norm": 0.0,
3178
+ "learning_rate": 9.712891555336517e-06,
3179
+ "loss": 0.4909,
3180
+ "step": 4530
3181
+ },
3182
+ {
3183
+ "epoch": 2.4607046070460705,
3184
+ "grad_norm": 0.0,
3185
+ "learning_rate": 9.52691836190293e-06,
3186
+ "loss": 0.6343,
3187
+ "step": 4540
3188
+ },
3189
+ {
3190
+ "epoch": 2.4661246612466123,
3191
+ "grad_norm": 0.0,
3192
+ "learning_rate": 9.342555189300838e-06,
3193
+ "loss": 0.5115,
3194
+ "step": 4550
3195
+ },
3196
+ {
3197
+ "epoch": 2.4715447154471546,
3198
+ "grad_norm": 0.0,
3199
+ "learning_rate": 9.159809371504723e-06,
3200
+ "loss": 0.5469,
3201
+ "step": 4560
3202
+ },
3203
+ {
3204
+ "epoch": 2.4769647696476964,
3205
+ "grad_norm": 0.0,
3206
+ "learning_rate": 8.978688178150668e-06,
3207
+ "loss": 0.5606,
3208
+ "step": 4570
3209
+ },
3210
+ {
3211
+ "epoch": 2.4823848238482387,
3212
+ "grad_norm": 0.0,
3213
+ "learning_rate": 8.79919881424709e-06,
3214
+ "loss": 0.5203,
3215
+ "step": 4580
3216
+ },
3217
+ {
3218
+ "epoch": 2.4878048780487805,
3219
+ "grad_norm": 0.0,
3220
+ "learning_rate": 8.621348419888165e-06,
3221
+ "loss": 0.5111,
3222
+ "step": 4590
3223
+ },
3224
+ {
3225
+ "epoch": 2.4932249322493227,
3226
+ "grad_norm": 0.0,
3227
+ "learning_rate": 8.445144069969812e-06,
3228
+ "loss": 0.5115,
3229
+ "step": 4600
3230
+ },
3231
+ {
3232
+ "epoch": 2.4986449864498645,
3233
+ "grad_norm": 0.0,
3234
+ "learning_rate": 8.270592773908232e-06,
3235
+ "loss": 0.4814,
3236
+ "step": 4610
3237
+ },
3238
+ {
3239
+ "epoch": 2.5040650406504064,
3240
+ "grad_norm": 0.0,
3241
+ "learning_rate": 8.09770147536107e-06,
3242
+ "loss": 0.426,
3243
+ "step": 4620
3244
+ },
3245
+ {
3246
+ "epoch": 2.5094850948509486,
3247
+ "grad_norm": 0.0,
3248
+ "learning_rate": 7.926477051951192e-06,
3249
+ "loss": 0.4801,
3250
+ "step": 4630
3251
+ },
3252
+ {
3253
+ "epoch": 2.5149051490514904,
3254
+ "grad_norm": 0.0,
3255
+ "learning_rate": 7.756926314993135e-06,
3256
+ "loss": 0.6409,
3257
+ "step": 4640
3258
+ },
3259
+ {
3260
+ "epoch": 2.5203252032520327,
3261
+ "grad_norm": 0.0,
3262
+ "learning_rate": 7.589056009222089e-06,
3263
+ "loss": 0.5287,
3264
+ "step": 4650
3265
+ },
3266
+ {
3267
+ "epoch": 2.5257452574525745,
3268
+ "grad_norm": 0.0,
3269
+ "learning_rate": 7.422872812525633e-06,
3270
+ "loss": 0.5553,
3271
+ "step": 4660
3272
+ },
3273
+ {
3274
+ "epoch": 2.5311653116531163,
3275
+ "grad_norm": 0.0,
3276
+ "learning_rate": 7.258383335678098e-06,
3277
+ "loss": 0.5598,
3278
+ "step": 4670
3279
+ },
3280
+ {
3281
+ "epoch": 2.5365853658536586,
3282
+ "grad_norm": 0.0,
3283
+ "learning_rate": 7.095594122077542e-06,
3284
+ "loss": 0.5477,
3285
+ "step": 4680
3286
+ },
3287
+ {
3288
+ "epoch": 2.5420054200542004,
3289
+ "grad_norm": 0.0,
3290
+ "learning_rate": 6.934511647485503e-06,
3291
+ "loss": 0.5337,
3292
+ "step": 4690
3293
+ },
3294
+ {
3295
+ "epoch": 2.5474254742547426,
3296
+ "grad_norm": 0.0,
3297
+ "learning_rate": 6.775142319769351e-06,
3298
+ "loss": 0.4678,
3299
+ "step": 4700
3300
+ },
3301
+ {
3302
+ "epoch": 2.5528455284552845,
3303
+ "grad_norm": 0.0,
3304
+ "learning_rate": 6.61749247864743e-06,
3305
+ "loss": 0.5446,
3306
+ "step": 4710
3307
+ },
3308
+ {
3309
+ "epoch": 2.5582655826558267,
3310
+ "grad_norm": 0.0,
3311
+ "learning_rate": 6.461568395436812e-06,
3312
+ "loss": 0.5185,
3313
+ "step": 4720
3314
+ },
3315
+ {
3316
+ "epoch": 2.5636856368563685,
3317
+ "grad_norm": 0.0,
3318
+ "learning_rate": 6.307376272803861e-06,
3319
+ "loss": 0.5106,
3320
+ "step": 4730
3321
+ },
3322
+ {
3323
+ "epoch": 2.569105691056911,
3324
+ "grad_norm": 0.0,
3325
+ "learning_rate": 6.154922244517486e-06,
3326
+ "loss": 0.535,
3327
+ "step": 4740
3328
+ },
3329
+ {
3330
+ "epoch": 2.5745257452574526,
3331
+ "grad_norm": 0.0,
3332
+ "learning_rate": 6.004212375205115e-06,
3333
+ "loss": 0.6075,
3334
+ "step": 4750
3335
+ },
3336
+ {
3337
+ "epoch": 2.5799457994579944,
3338
+ "grad_norm": 0.0,
3339
+ "learning_rate": 5.855252660111482e-06,
3340
+ "loss": 0.4473,
3341
+ "step": 4760
3342
+ },
3343
+ {
3344
+ "epoch": 2.5853658536585367,
3345
+ "grad_norm": 0.0,
3346
+ "learning_rate": 5.708049024860085e-06,
3347
+ "loss": 0.5698,
3348
+ "step": 4770
3349
+ },
3350
+ {
3351
+ "epoch": 2.5907859078590785,
3352
+ "grad_norm": 0.0,
3353
+ "learning_rate": 5.562607325217533e-06,
3354
+ "loss": 0.534,
3355
+ "step": 4780
3356
+ },
3357
+ {
3358
+ "epoch": 2.5962059620596207,
3359
+ "grad_norm": 0.0,
3360
+ "learning_rate": 5.418933346860538e-06,
3361
+ "loss": 0.5458,
3362
+ "step": 4790
3363
+ },
3364
+ {
3365
+ "epoch": 2.6016260162601625,
3366
+ "grad_norm": 0.0,
3367
+ "learning_rate": 5.277032805145799e-06,
3368
+ "loss": 0.5138,
3369
+ "step": 4800
3370
+ },
3371
+ {
3372
+ "epoch": 2.6070460704607044,
3373
+ "grad_norm": 0.0,
3374
+ "learning_rate": 5.136911344882622e-06,
3375
+ "loss": 0.5076,
3376
+ "step": 4810
3377
+ },
3378
+ {
3379
+ "epoch": 2.6124661246612466,
3380
+ "grad_norm": 0.0,
3381
+ "learning_rate": 4.998574540108392e-06,
3382
+ "loss": 0.5299,
3383
+ "step": 4820
3384
+ },
3385
+ {
3386
+ "epoch": 2.617886178861789,
3387
+ "grad_norm": 0.0,
3388
+ "learning_rate": 4.862027893866822e-06,
3389
+ "loss": 0.4938,
3390
+ "step": 4830
3391
+ },
3392
+ {
3393
+ "epoch": 2.6233062330623307,
3394
+ "grad_norm": 0.0,
3395
+ "learning_rate": 4.7272768379890365e-06,
3396
+ "loss": 0.5444,
3397
+ "step": 4840
3398
+ },
3399
+ {
3400
+ "epoch": 2.6287262872628725,
3401
+ "grad_norm": 0.0,
3402
+ "learning_rate": 4.594326732877524e-06,
3403
+ "loss": 0.5202,
3404
+ "step": 4850
3405
+ },
3406
+ {
3407
+ "epoch": 2.6341463414634148,
3408
+ "grad_norm": 0.0,
3409
+ "learning_rate": 4.463182867292865e-06,
3410
+ "loss": 0.5111,
3411
+ "step": 4860
3412
+ },
3413
+ {
3414
+ "epoch": 2.6395663956639566,
3415
+ "grad_norm": 0.0,
3416
+ "learning_rate": 4.333850458143357e-06,
3417
+ "loss": 0.5141,
3418
+ "step": 4870
3419
+ },
3420
+ {
3421
+ "epoch": 2.644986449864499,
3422
+ "grad_norm": 0.0,
3423
+ "learning_rate": 4.206334650277483e-06,
3424
+ "loss": 0.4874,
3425
+ "step": 4880
3426
+ },
3427
+ {
3428
+ "epoch": 2.6504065040650406,
3429
+ "grad_norm": 0.0,
3430
+ "learning_rate": 4.080640516279266e-06,
3431
+ "loss": 0.4867,
3432
+ "step": 4890
3433
+ },
3434
+ {
3435
+ "epoch": 2.6558265582655824,
3436
+ "grad_norm": 0.0,
3437
+ "learning_rate": 3.956773056266466e-06,
3438
+ "loss": 0.5755,
3439
+ "step": 4900
3440
+ },
3441
+ {
3442
+ "epoch": 2.6612466124661247,
3443
+ "grad_norm": 0.0,
3444
+ "learning_rate": 3.8347371976916516e-06,
3445
+ "loss": 0.5755,
3446
+ "step": 4910
3447
+ },
3448
+ {
3449
+ "epoch": 2.6666666666666665,
3450
+ "grad_norm": 0.0,
3451
+ "learning_rate": 3.714537795146261e-06,
3452
+ "loss": 0.523,
3453
+ "step": 4920
3454
+ },
3455
+ {
3456
+ "epoch": 2.6720867208672088,
3457
+ "grad_norm": 0.0,
3458
+ "learning_rate": 3.5961796301674012e-06,
3459
+ "loss": 0.4475,
3460
+ "step": 4930
3461
+ },
3462
+ {
3463
+ "epoch": 2.6775067750677506,
3464
+ "grad_norm": 0.0,
3465
+ "learning_rate": 3.479667411047677e-06,
3466
+ "loss": 0.4947,
3467
+ "step": 4940
3468
+ },
3469
+ {
3470
+ "epoch": 2.682926829268293,
3471
+ "grad_norm": 0.0,
3472
+ "learning_rate": 3.3650057726479e-06,
3473
+ "loss": 0.5437,
3474
+ "step": 4950
3475
+ },
3476
+ {
3477
+ "epoch": 2.6883468834688347,
3478
+ "grad_norm": 0.0,
3479
+ "learning_rate": 3.2521992762127085e-06,
3480
+ "loss": 0.6523,
3481
+ "step": 4960
3482
+ },
3483
+ {
3484
+ "epoch": 2.693766937669377,
3485
+ "grad_norm": 0.0,
3486
+ "learning_rate": 3.141252409189099e-06,
3487
+ "loss": 0.5232,
3488
+ "step": 4970
3489
+ },
3490
+ {
3491
+ "epoch": 2.6991869918699187,
3492
+ "grad_norm": 0.0,
3493
+ "learning_rate": 3.032169585047956e-06,
3494
+ "loss": 0.5144,
3495
+ "step": 4980
3496
+ },
3497
+ {
3498
+ "epoch": 2.7046070460704605,
3499
+ "grad_norm": 0.0,
3500
+ "learning_rate": 2.92495514310846e-06,
3501
+ "loss": 0.5177,
3502
+ "step": 4990
3503
+ },
3504
+ {
3505
+ "epoch": 2.710027100271003,
3506
+ "grad_norm": 0.0,
3507
+ "learning_rate": 2.819613348365463e-06,
3508
+ "loss": 0.4604,
3509
+ "step": 5000
3510
+ },
3511
+ {
3512
+ "epoch": 2.7154471544715446,
3513
+ "grad_norm": 0.0,
3514
+ "learning_rate": 2.7161483913198392e-06,
3515
+ "loss": 0.5745,
3516
+ "step": 5010
3517
+ },
3518
+ {
3519
+ "epoch": 2.720867208672087,
3520
+ "grad_norm": 0.0,
3521
+ "learning_rate": 2.6145643878117744e-06,
3522
+ "loss": 0.4852,
3523
+ "step": 5020
3524
+ },
3525
+ {
3526
+ "epoch": 2.7262872628726287,
3527
+ "grad_norm": 0.0,
3528
+ "learning_rate": 2.5148653788570676e-06,
3529
+ "loss": 0.6759,
3530
+ "step": 5030
3531
+ },
3532
+ {
3533
+ "epoch": 2.7317073170731705,
3534
+ "grad_norm": 0.0,
3535
+ "learning_rate": 2.4170553304863287e-06,
3536
+ "loss": 0.5064,
3537
+ "step": 5040
3538
+ },
3539
+ {
3540
+ "epoch": 2.7371273712737128,
3541
+ "grad_norm": 0.0,
3542
+ "learning_rate": 2.321138133587264e-06,
3543
+ "loss": 0.4882,
3544
+ "step": 5050
3545
+ },
3546
+ {
3547
+ "epoch": 2.742547425474255,
3548
+ "grad_norm": 0.0,
3549
+ "learning_rate": 2.227117603749862e-06,
3550
+ "loss": 0.5716,
3551
+ "step": 5060
3552
+ },
3553
+ {
3554
+ "epoch": 2.747967479674797,
3555
+ "grad_norm": 0.0,
3556
+ "learning_rate": 2.13499748111462e-06,
3557
+ "loss": 0.5078,
3558
+ "step": 5070
3559
+ },
3560
+ {
3561
+ "epoch": 2.7533875338753386,
3562
+ "grad_norm": 0.0,
3563
+ "learning_rate": 2.044781430223758e-06,
3564
+ "loss": 0.4927,
3565
+ "step": 5080
3566
+ },
3567
+ {
3568
+ "epoch": 2.758807588075881,
3569
+ "grad_norm": 0.0,
3570
+ "learning_rate": 1.956473039875445e-06,
3571
+ "loss": 0.6156,
3572
+ "step": 5090
3573
+ },
3574
+ {
3575
+ "epoch": 2.7642276422764227,
3576
+ "grad_norm": 0.0,
3577
+ "learning_rate": 1.8700758229810266e-06,
3578
+ "loss": 0.6286,
3579
+ "step": 5100
3580
+ },
3581
+ {
3582
+ "epoch": 2.769647696476965,
3583
+ "grad_norm": 0.0,
3584
+ "learning_rate": 1.785593216425313e-06,
3585
+ "loss": 0.5391,
3586
+ "step": 5110
3587
+ },
3588
+ {
3589
+ "epoch": 2.7750677506775068,
3590
+ "grad_norm": 0.0,
3591
+ "learning_rate": 1.7030285809298107e-06,
3592
+ "loss": 0.5114,
3593
+ "step": 5120
3594
+ },
3595
+ {
3596
+ "epoch": 2.7804878048780486,
3597
+ "grad_norm": 0.0,
3598
+ "learning_rate": 1.6223852009190854e-06,
3599
+ "loss": 0.4548,
3600
+ "step": 5130
3601
+ },
3602
+ {
3603
+ "epoch": 2.785907859078591,
3604
+ "grad_norm": 0.0,
3605
+ "learning_rate": 1.5436662843900718e-06,
3606
+ "loss": 0.5117,
3607
+ "step": 5140
3608
+ },
3609
+ {
3610
+ "epoch": 2.7913279132791327,
3611
+ "grad_norm": 0.0,
3612
+ "learning_rate": 1.4668749627844536e-06,
3613
+ "loss": 0.5998,
3614
+ "step": 5150
3615
+ },
3616
+ {
3617
+ "epoch": 2.796747967479675,
3618
+ "grad_norm": 0.0,
3619
+ "learning_rate": 1.3920142908641353e-06,
3620
+ "loss": 0.5348,
3621
+ "step": 5160
3622
+ },
3623
+ {
3624
+ "epoch": 2.8021680216802167,
3625
+ "grad_norm": 0.0,
3626
+ "learning_rate": 1.3190872465896786e-06,
3627
+ "loss": 0.5632,
3628
+ "step": 5170
3629
+ },
3630
+ {
3631
+ "epoch": 2.8075880758807585,
3632
+ "grad_norm": 0.0,
3633
+ "learning_rate": 1.2480967310018743e-06,
3634
+ "loss": 0.5922,
3635
+ "step": 5180
3636
+ },
3637
+ {
3638
+ "epoch": 2.813008130081301,
3639
+ "grad_norm": 0.0,
3640
+ "learning_rate": 1.1790455681063018e-06,
3641
+ "loss": 0.4896,
3642
+ "step": 5190
3643
+ },
3644
+ {
3645
+ "epoch": 2.818428184281843,
3646
+ "grad_norm": 0.0,
3647
+ "learning_rate": 1.1119365047610409e-06,
3648
+ "loss": 0.5172,
3649
+ "step": 5200
3650
+ },
3651
+ {
3652
+ "epoch": 2.823848238482385,
3653
+ "grad_norm": 0.0,
3654
+ "learning_rate": 1.046772210567354e-06,
3655
+ "loss": 0.5374,
3656
+ "step": 5210
3657
+ },
3658
+ {
3659
+ "epoch": 2.8292682926829267,
3660
+ "grad_norm": 0.0,
3661
+ "learning_rate": 9.835552777635092e-07,
3662
+ "loss": 0.5543,
3663
+ "step": 5220
3664
+ },
3665
+ {
3666
+ "epoch": 2.834688346883469,
3667
+ "grad_norm": 0.0,
3668
+ "learning_rate": 9.222882211216588e-07,
3669
+ "loss": 0.5452,
3670
+ "step": 5230
3671
+ },
3672
+ {
3673
+ "epoch": 2.8401084010840107,
3674
+ "grad_norm": 0.0,
3675
+ "learning_rate": 8.62973477847806e-07,
3676
+ "loss": 0.5049,
3677
+ "step": 5240
3678
+ },
3679
+ {
3680
+ "epoch": 2.845528455284553,
3681
+ "grad_norm": 0.0,
3682
+ "learning_rate": 8.05613407484851e-07,
3683
+ "loss": 0.5682,
3684
+ "step": 5250
3685
+ },
3686
+ {
3687
+ "epoch": 2.850948509485095,
3688
+ "grad_norm": 0.0,
3689
+ "learning_rate": 7.502102918187203e-07,
3690
+ "loss": 0.448,
3691
+ "step": 5260
3692
+ },
3693
+ {
3694
+ "epoch": 2.8563685636856366,
3695
+ "grad_norm": 0.0,
3696
+ "learning_rate": 6.967663347876019e-07,
3697
+ "loss": 0.4991,
3698
+ "step": 5270
3699
+ },
3700
+ {
3701
+ "epoch": 2.861788617886179,
3702
+ "grad_norm": 0.0,
3703
+ "learning_rate": 6.452836623942859e-07,
3704
+ "loss": 0.5162,
3705
+ "step": 5280
3706
+ },
3707
+ {
3708
+ "epoch": 2.867208672086721,
3709
+ "grad_norm": 0.0,
3710
+ "learning_rate": 5.957643226215615e-07,
3711
+ "loss": 0.4567,
3712
+ "step": 5290
3713
+ },
3714
+ {
3715
+ "epoch": 2.872628726287263,
3716
+ "grad_norm": 0.0,
3717
+ "learning_rate": 5.482102853507809e-07,
3718
+ "loss": 0.5041,
3719
+ "step": 5300
3720
+ },
3721
+ {
3722
+ "epoch": 2.8780487804878048,
3723
+ "grad_norm": 0.0,
3724
+ "learning_rate": 5.02623442283473e-07,
3725
+ "loss": 0.4718,
3726
+ "step": 5310
3727
+ },
3728
+ {
3729
+ "epoch": 2.883468834688347,
3730
+ "grad_norm": 0.0,
3731
+ "learning_rate": 4.590056068661197e-07,
3732
+ "loss": 0.5498,
3733
+ "step": 5320
3734
+ },
3735
+ {
3736
+ "epoch": 2.888888888888889,
3737
+ "grad_norm": 0.0,
3738
+ "learning_rate": 4.1735851421796925e-07,
3739
+ "loss": 0.5377,
3740
+ "step": 5330
3741
+ },
3742
+ {
3743
+ "epoch": 2.894308943089431,
3744
+ "grad_norm": 0.0,
3745
+ "learning_rate": 3.776838210620692e-07,
3746
+ "loss": 0.5376,
3747
+ "step": 5340
3748
+ },
3749
+ {
3750
+ "epoch": 2.899728997289973,
3751
+ "grad_norm": 0.0,
3752
+ "learning_rate": 3.39983105659325e-07,
3753
+ "loss": 0.5345,
3754
+ "step": 5350
3755
+ },
3756
+ {
3757
+ "epoch": 2.9051490514905147,
3758
+ "grad_norm": 0.0,
3759
+ "learning_rate": 3.0425786774572753e-07,
3760
+ "loss": 0.5777,
3761
+ "step": 5360
3762
+ },
3763
+ {
3764
+ "epoch": 2.910569105691057,
3765
+ "grad_norm": 0.0,
3766
+ "learning_rate": 2.705095284726844e-07,
3767
+ "loss": 0.5314,
3768
+ "step": 5370
3769
+ },
3770
+ {
3771
+ "epoch": 2.915989159891599,
3772
+ "grad_norm": 0.0,
3773
+ "learning_rate": 2.3873943035050417e-07,
3774
+ "loss": 0.5036,
3775
+ "step": 5380
3776
+ },
3777
+ {
3778
+ "epoch": 2.921409214092141,
3779
+ "grad_norm": 0.0,
3780
+ "learning_rate": 2.089488371949888e-07,
3781
+ "loss": 0.5007,
3782
+ "step": 5390
3783
+ },
3784
+ {
3785
+ "epoch": 2.926829268292683,
3786
+ "grad_norm": 0.0,
3787
+ "learning_rate": 1.8113893407713523e-07,
3788
+ "loss": 0.5986,
3789
+ "step": 5400
3790
+ },
3791
+ {
3792
+ "epoch": 2.9322493224932247,
3793
+ "grad_norm": 0.0,
3794
+ "learning_rate": 1.5531082727602285e-07,
3795
+ "loss": 0.653,
3796
+ "step": 5410
3797
+ },
3798
+ {
3799
+ "epoch": 2.937669376693767,
3800
+ "grad_norm": 0.0,
3801
+ "learning_rate": 1.3146554423478785e-07,
3802
+ "loss": 0.523,
3803
+ "step": 5420
3804
+ },
3805
+ {
3806
+ "epoch": 2.943089430894309,
3807
+ "grad_norm": 0.0,
3808
+ "learning_rate": 1.0960403351976123e-07,
3809
+ "loss": 0.4574,
3810
+ "step": 5430
3811
+ },
3812
+ {
3813
+ "epoch": 2.948509485094851,
3814
+ "grad_norm": 0.0,
3815
+ "learning_rate": 8.972716478272691e-08,
3816
+ "loss": 0.6004,
3817
+ "step": 5440
3818
+ },
3819
+ {
3820
+ "epoch": 2.953929539295393,
3821
+ "grad_norm": 0.0,
3822
+ "learning_rate": 7.183572872632715e-08,
3823
+ "loss": 0.5666,
3824
+ "step": 5450
3825
+ },
3826
+ {
3827
+ "epoch": 2.959349593495935,
3828
+ "grad_norm": 0.0,
3829
+ "learning_rate": 5.593043707262102e-08,
3830
+ "loss": 0.5306,
3831
+ "step": 5460
3832
+ },
3833
+ {
3834
+ "epoch": 2.964769647696477,
3835
+ "grad_norm": 0.0,
3836
+ "learning_rate": 4.201192253474595e-08,
3837
+ "loss": 0.4908,
3838
+ "step": 5470
3839
+ },
3840
+ {
3841
+ "epoch": 2.970189701897019,
3842
+ "grad_norm": 0.0,
3843
+ "learning_rate": 3.0080738791782304e-08,
3844
+ "loss": 0.4865,
3845
+ "step": 5480
3846
+ },
3847
+ {
3848
+ "epoch": 2.975609756097561,
3849
+ "grad_norm": 0.0,
3850
+ "learning_rate": 2.0137360466704337e-08,
3851
+ "loss": 0.4843,
3852
+ "step": 5490
3853
+ },
3854
+ {
3855
+ "epoch": 2.9810298102981028,
3856
+ "grad_norm": 0.0,
3857
+ "learning_rate": 1.2182183107506406e-08,
3858
+ "loss": 0.5347,
3859
+ "step": 5500
3860
+ },
3861
+ {
3862
+ "epoch": 2.986449864498645,
3863
+ "grad_norm": 0.0,
3864
+ "learning_rate": 6.215523171465565e-09,
3865
+ "loss": 0.567,
3866
+ "step": 5510
3867
+ },
3868
+ {
3869
+ "epoch": 2.991869918699187,
3870
+ "grad_norm": 0.0,
3871
+ "learning_rate": 2.2376180125571743e-09,
3872
+ "loss": 0.5512,
3873
+ "step": 5520
3874
+ },
3875
+ {
3876
+ "epoch": 2.997289972899729,
3877
+ "grad_norm": 0.0,
3878
+ "learning_rate": 2.4862587201246457e-10,
3879
+ "loss": 0.5884,
3880
+ "step": 5530
3881
+ },
3882
+ {
3883
+ "epoch": 3.0,
3884
+ "step": 5535,
3885
+ "total_flos": 3.0626432822122906e+18,
3886
+ "train_loss": 0.8061501924692238,
3887
+ "train_runtime": 22473.7337,
3888
+ "train_samples_per_second": 0.246,
3889
+ "train_steps_per_second": 0.246
3890
+ }
3891
+ ],
3892
+ "logging_steps": 10,
3893
+ "max_steps": 5535,
3894
+ "num_input_tokens_seen": 0,
3895
+ "num_train_epochs": 3,
3896
+ "save_steps": 2500,
3897
+ "stateful_callbacks": {
3898
+ "TrainerControl": {
3899
+ "args": {
3900
+ "should_epoch_stop": false,
3901
+ "should_evaluate": false,
3902
+ "should_log": false,
3903
+ "should_save": true,
3904
+ "should_training_stop": true
3905
+ },
3906
+ "attributes": {}
3907
+ }
3908
+ },
3909
+ "total_flos": 3.0626432822122906e+18,
3910
+ "train_batch_size": 1,
3911
+ "trial_name": null,
3912
+ "trial_params": null
3913
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3c6c07add9c2f74a562a80619154bf6d3eb93fe611aeea6377728345b618db59
3
+ size 5624
training_loss.png ADDED