Hugging Face's logo

zczhao
/
DriveMonkey

Safetensors
Model card Files
xet
 Community
zczhao commited on
Commit
e63a4a0
·
verified ·
1 Parent(s): 4283f73

Upload folder using huggingface_hub

Browse files
Files changed (17) hide show
  1. Pretrain_8B/added_tokens.json +17 -0
  2. Pretrain_8B/all_results.json +8 -0
  3. Pretrain_8B/config.json +203 -0
  4. Pretrain_8B/generation_config.json +8 -0
  5. Pretrain_8B/model-00001-of-00004.safetensors +3 -0
  6. Pretrain_8B/model-00002-of-00004.safetensors +3 -0
  7. Pretrain_8B/model-00003-of-00004.safetensors +3 -0
  8. Pretrain_8B/model-00004-of-00004.safetensors +3 -0
  9. Pretrain_8B/model.safetensors.index.json +580 -0
  10. Pretrain_8B/special_tokens_map.json +89 -0
  11. Pretrain_8B/tokenization_internlm2.py +235 -0
  12. Pretrain_8B/tokenizer.model +3 -0
  13. Pretrain_8B/tokenizer_config.json +233 -0
  14. Pretrain_8B/train_results.json +8 -0
  15. Pretrain_8B/trainer_state.json +4584 -0
  16. Pretrain_8B/training_args.bin +3 -0
  17. Pretrain_8B/training_log.txt +0 -0
Pretrain_8B/added_tokens.json ADDED
@@ -0,0 +1,17 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "</box>": 92552,
3
+ "</box_3d>": 92558,
4
+ "</img>": 92545,
5
+ "</quad>": 92548,
6
+ "</ref>": 92550,
7
+ "<IMG_CONTEXT>": 92546,
8
+ "<bbox_2d>": 92553,
9
+ "<bbox_2d_in>": 92555,
10
+ "<bbox_3d>": 92554,
11
+ "<box>": 92551,
12
+ "<box_3d>": 92557,
13
+ "<img>": 92544,
14
+ "<quad>": 92547,
15
+ "<query>": 92556,
16
+ "<ref>": 92549
17
+ }
Pretrain_8B/all_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 1.0,
3
+ "train_loss": 1.1657107080552576,
4
+ "train_runtime": 16008.6151,
5
+ "train_samples": 194308,
6
+ "train_samples_per_second": 12.138,
7
+ "train_steps_per_second": 0.047
8
+ }
Pretrain_8B/config.json ADDED
@@ -0,0 +1,203 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_commit_hash": null,
3
+ "_name_or_path": "./weight/InternVL2-8B",
4
+ "architectures": [
5
+ "InternVLChatModel"
6
+ ],
7
+ "auto_map": {
8
+ "AutoConfig": "configuration_internvl_chat.InternVLChatConfig",
9
+ "AutoModel": "modeling_internvl_chat.InternVLChatModel",
10
+ "AutoModelForCausalLM": "modeling_internvl_chat.InternVLChatModel"
11
+ },
12
+ "downsample_ratio": 0.5,
13
+ "dynamic_image_size": false,
14
+ "force_image_size": 448,
15
+ "hidden_size": 4096,
16
+ "llm_config": {
17
+ "_name_or_path": "internlm/internlm2_5-7b-chat",
18
+ "add_cross_attention": false,
19
+ "architectures": [
20
+ "InternLM2ForCausalLM"
21
+ ],
22
+ "attn_implementation": "flash_attention_2",
23
+ "auto_map": {
24
+ "AutoConfig": "configuration_internlm2.InternLM2Config",
25
+ "AutoModel": "modeling_internlm2.InternLM2ForCausalLM",
26
+ "AutoModelForCausalLM": "modeling_internlm2.InternLM2ForCausalLM"
27
+ },
28
+ "bad_words_ids": null,
29
+ "begin_suppress_tokens": null,
30
+ "bias": false,
31
+ "bos_token_id": 1,
32
+ "chunk_size_feed_forward": 0,
33
+ "cross_attention_hidden_size": null,
34
+ "decoder_start_token_id": null,
35
+ "diversity_penalty": 0.0,
36
+ "do_sample": false,
37
+ "early_stopping": false,
38
+ "encoder_no_repeat_ngram_size": 0,
39
+ "eos_token_id": 2,
40
+ "exponential_decay_length_penalty": null,
41
+ "finetuning_task": null,
42
+ "forced_bos_token_id": null,
43
+ "forced_eos_token_id": null,
44
+ "hidden_act": "silu",
45
+ "hidden_size": 4096,
46
+ "id2label": {
47
+ "0": "LABEL_0",
48
+ "1": "LABEL_1"
49
+ },
50
+ "initializer_range": 0.02,
51
+ "intermediate_size": 14336,
52
+ "is_decoder": false,
53
+ "is_encoder_decoder": false,
54
+ "label2id": {
55
+ "LABEL_0": 0,
56
+ "LABEL_1": 1
57
+ },
58
+ "length_penalty": 1.0,
59
+ "max_length": 20,
60
+ "max_position_embeddings": 32768,
61
+ "min_length": 0,
62
+ "model_type": "internlm2",
63
+ "no_repeat_ngram_size": 0,
64
+ "num_attention_heads": 32,
65
+ "num_beam_groups": 1,
66
+ "num_beams": 1,
67
+ "num_hidden_layers": 32,
68
+ "num_key_value_heads": 8,
69
+ "num_return_sequences": 1,
70
+ "output_attentions": false,
71
+ "output_hidden_states": false,
72
+ "output_scores": false,
73
+ "pad_token_id": 2,
74
+ "prefix": null,
75
+ "pretraining_tp": 1,
76
+ "problem_type": null,
77
+ "pruned_heads": {},
78
+ "remove_invalid_values": false,
79
+ "repetition_penalty": 1.0,
80
+ "return_dict": true,
81
+ "return_dict_in_generate": false,
82
+ "rms_norm_eps": 1e-05,
83
+ "rope_scaling": {
84
+ "factor": 2.0,
85
+ "type": "dynamic"
86
+ },
87
+ "rope_theta": 1000000,
88
+ "sep_token_id": null,
89
+ "suppress_tokens": null,
90
+ "task_specific_params": null,
91
+ "temperature": 1.0,
92
+ "tf_legacy_loss": false,
93
+ "tie_encoder_decoder": false,
94
+ "tie_word_embeddings": false,
95
+ "tokenizer_class": null,
96
+ "top_k": 50,
97
+ "top_p": 1.0,
98
+ "torch_dtype": "bfloat16",
99
+ "torchscript": false,
100
+ "transformers_version": "4.37.2",
101
+ "typical_p": 1.0,
102
+ "use_bfloat16": true,
103
+ "use_cache": false,
104
+ "vocab_size": 92559
105
+ },
106
+ "max_dynamic_patch": 6,
107
+ "min_dynamic_patch": 1,
108
+ "model_type": "internvl_chat",
109
+ "pad2square": false,
110
+ "ps_version": "v2",
111
+ "select_layer": -1,
112
+ "template": "internlm2-chat",
113
+ "tie_word_embeddings": false,
114
+ "torch_dtype": "bfloat16",
115
+ "transformers_version": null,
116
+ "use_backbone_lora": 0,
117
+ "use_llm_lora": 0,
118
+ "use_thumbnail": true,
119
+ "vision_config": {
120
+ "_name_or_path": "",
121
+ "add_cross_attention": false,
122
+ "architectures": [
123
+ "InternVisionModel"
124
+ ],
125
+ "attention_dropout": 0.0,
126
+ "bad_words_ids": null,
127
+ "begin_suppress_tokens": null,
128
+ "bos_token_id": null,
129
+ "chunk_size_feed_forward": 0,
130
+ "cross_attention_hidden_size": null,
131
+ "decoder_start_token_id": null,
132
+ "diversity_penalty": 0.0,
133
+ "do_sample": false,
134
+ "drop_path_rate": 0.0,
135
+ "dropout": 0.0,
136
+ "early_stopping": false,
137
+ "encoder_no_repeat_ngram_size": 0,
138
+ "eos_token_id": null,
139
+ "exponential_decay_length_penalty": null,
140
+ "finetuning_task": null,
141
+ "forced_bos_token_id": null,
142
+ "forced_eos_token_id": null,
143
+ "hidden_act": "gelu",
144
+ "hidden_size": 1024,
145
+ "id2label": {
146
+ "0": "LABEL_0",
147
+ "1": "LABEL_1"
148
+ },
149
+ "image_size": 448,
150
+ "initializer_factor": 1.0,
151
+ "initializer_range": 0.02,
152
+ "intermediate_size": 4096,
153
+ "is_decoder": false,
154
+ "is_encoder_decoder": false,
155
+ "label2id": {
156
+ "LABEL_0": 0,
157
+ "LABEL_1": 1
158
+ },
159
+ "layer_norm_eps": 1e-06,
160
+ "length_penalty": 1.0,
161
+ "max_length": 20,
162
+ "min_length": 0,
163
+ "model_type": "intern_vit_6b",
164
+ "no_repeat_ngram_size": 0,
165
+ "norm_type": "layer_norm",
166
+ "num_attention_heads": 16,
167
+ "num_beam_groups": 1,
168
+ "num_beams": 1,
169
+ "num_channels": 3,
170
+ "num_hidden_layers": 24,
171
+ "num_return_sequences": 1,
172
+ "output_attentions": false,
173
+ "output_hidden_states": false,
174
+ "output_scores": false,
175
+ "pad_token_id": null,
176
+ "patch_size": 14,
177
+ "prefix": null,
178
+ "problem_type": null,
179
+ "pruned_heads": {},
180
+ "qk_normalization": false,
181
+ "qkv_bias": true,
182
+ "remove_invalid_values": false,
183
+ "repetition_penalty": 1.0,
184
+ "return_dict": true,
185
+ "return_dict_in_generate": false,
186
+ "sep_token_id": null,
187
+ "suppress_tokens": null,
188
+ "task_specific_params": null,
189
+ "temperature": 1.0,
190
+ "tf_legacy_loss": false,
191
+ "tie_encoder_decoder": false,
192
+ "tie_word_embeddings": true,
193
+ "tokenizer_class": null,
194
+ "top_k": 50,
195
+ "top_p": 1.0,
196
+ "torch_dtype": "bfloat16",
197
+ "torchscript": false,
198
+ "transformers_version": "4.37.2",
199
+ "typical_p": 1.0,
200
+ "use_bfloat16": true,
201
+ "use_flash_attn": true
202
+ }
203
+ }
Pretrain_8B/generation_config.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "eos_token_id": [
4
+ 92542,
5
+ 92543
6
+ ],
7
+ "transformers_version": "4.37.2"
8
+ }
Pretrain_8B/model-00001-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fd6733682b2f5d5291dbc1d5edd736da64999b92f21cbe71e1b426179d1612ce
3
+ size 4939993488
Pretrain_8B/model-00002-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e1967d2442fe5a38aba96e7ad7a18459962171591e5b7438aa0efa15db93b375
3
+ size 4915914584
Pretrain_8B/model-00003-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9d31a1bd34e26858251c02741d450f64937b59bf3e45a2efede61a10c2086768
3
+ size 4915914592
Pretrain_8B/model-00004-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:22dd7479a71818cc5cfa7b604c3154d800239c88951ce120402148a97a6748d6
3
+ size 1379076072
Pretrain_8B/model.safetensors.index.json ADDED
@@ -0,0 +1,580 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 16150829056
4
+ },
5
+ "weight_map": {
6
+ "language_model.model.layers.0.attention.wo.weight": "model-00001-of-00004.safetensors",
7
+ "language_model.model.layers.0.attention.wqkv.weight": "model-00001-of-00004.safetensors",
8
+ "language_model.model.layers.0.attention_norm.weight": "model-00001-of-00004.safetensors",
9
+ "language_model.model.layers.0.feed_forward.w1.weight": "model-00001-of-00004.safetensors",
10
+ "language_model.model.layers.0.feed_forward.w2.weight": "model-00001-of-00004.safetensors",
11
+ "language_model.model.layers.0.feed_forward.w3.weight": "model-00001-of-00004.safetensors",
12
+ "language_model.model.layers.0.ffn_norm.weight": "model-00001-of-00004.safetensors",
13
+ "language_model.model.layers.1.attention.wo.weight": "model-00001-of-00004.safetensors",
14
+ "language_model.model.layers.1.attention.wqkv.weight": "model-00001-of-00004.safetensors",
15
+ "language_model.model.layers.1.attention_norm.weight": "model-00001-of-00004.safetensors",
16
+ "language_model.model.layers.1.feed_forward.w1.weight": "model-00001-of-00004.safetensors",
17
+ "language_model.model.layers.1.feed_forward.w2.weight": "model-00001-of-00004.safetensors",
18
+ "language_model.model.layers.1.feed_forward.w3.weight": "model-00001-of-00004.safetensors",
19
+ "language_model.model.layers.1.ffn_norm.weight": "model-00001-of-00004.safetensors",
20
+ "language_model.model.layers.10.attention.wo.weight": "model-00002-of-00004.safetensors",
21
+ "language_model.model.layers.10.attention.wqkv.weight": "model-00002-of-00004.safetensors",
22
+ "language_model.model.layers.10.attention_norm.weight": "model-00002-of-00004.safetensors",
23
+ "language_model.model.layers.10.feed_forward.w1.weight": "model-00002-of-00004.safetensors",
24
+ "language_model.model.layers.10.feed_forward.w2.weight": "model-00002-of-00004.safetensors",
25
+ "language_model.model.layers.10.feed_forward.w3.weight": "model-00002-of-00004.safetensors",
26
+ "language_model.model.layers.10.ffn_norm.weight": "model-00002-of-00004.safetensors",
27
+ "language_model.model.layers.11.attention.wo.weight": "model-00002-of-00004.safetensors",
28
+ "language_model.model.layers.11.attention.wqkv.weight": "model-00002-of-00004.safetensors",
29
+ "language_model.model.layers.11.attention_norm.weight": "model-00002-of-00004.safetensors",
30
+ "language_model.model.layers.11.feed_forward.w1.weight": "model-00002-of-00004.safetensors",
31
+ "language_model.model.layers.11.feed_forward.w2.weight": "model-00002-of-00004.safetensors",
32
+ "language_model.model.layers.11.feed_forward.w3.weight": "model-00002-of-00004.safetensors",
33
+ "language_model.model.layers.11.ffn_norm.weight": "model-00002-of-00004.safetensors",
34
+ "language_model.model.layers.12.attention.wo.weight": "model-00002-of-00004.safetensors",
35
+ "language_model.model.layers.12.attention.wqkv.weight": "model-00002-of-00004.safetensors",
36
+ "language_model.model.layers.12.attention_norm.weight": "model-00002-of-00004.safetensors",
37
+ "language_model.model.layers.12.feed_forward.w1.weight": "model-00002-of-00004.safetensors",
38
+ "language_model.model.layers.12.feed_forward.w2.weight": "model-00002-of-00004.safetensors",
39
+ "language_model.model.layers.12.feed_forward.w3.weight": "model-00002-of-00004.safetensors",
40
+ "language_model.model.layers.12.ffn_norm.weight": "model-00002-of-00004.safetensors",
41
+ "language_model.model.layers.13.attention.wo.weight": "model-00002-of-00004.safetensors",
42
+ "language_model.model.layers.13.attention.wqkv.weight": "model-00002-of-00004.safetensors",
43
+ "language_model.model.layers.13.attention_norm.weight": "model-00002-of-00004.safetensors",
44
+ "language_model.model.layers.13.feed_forward.w1.weight": "model-00002-of-00004.safetensors",
45
+ "language_model.model.layers.13.feed_forward.w2.weight": "model-00002-of-00004.safetensors",
46
+ "language_model.model.layers.13.feed_forward.w3.weight": "model-00002-of-00004.safetensors",
47
+ "language_model.model.layers.13.ffn_norm.weight": "model-00002-of-00004.safetensors",
48
+ "language_model.model.layers.14.attention.wo.weight": "model-00002-of-00004.safetensors",
49
+ "language_model.model.layers.14.attention.wqkv.weight": "model-00002-of-00004.safetensors",
50
+ "language_model.model.layers.14.attention_norm.weight": "model-00002-of-00004.safetensors",
51
+ "language_model.model.layers.14.feed_forward.w1.weight": "model-00002-of-00004.safetensors",
52
+ "language_model.model.layers.14.feed_forward.w2.weight": "model-00002-of-00004.safetensors",
53
+ "language_model.model.layers.14.feed_forward.w3.weight": "model-00002-of-00004.safetensors",
54
+ "language_model.model.layers.14.ffn_norm.weight": "model-00002-of-00004.safetensors",
55
+ "language_model.model.layers.15.attention.wo.weight": "model-00002-of-00004.safetensors",
56
+ "language_model.model.layers.15.attention.wqkv.weight": "model-00002-of-00004.safetensors",
57
+ "language_model.model.layers.15.attention_norm.weight": "model-00002-of-00004.safetensors",
58
+ "language_model.model.layers.15.feed_forward.w1.weight": "model-00002-of-00004.safetensors",
59
+ "language_model.model.layers.15.feed_forward.w2.weight": "model-00002-of-00004.safetensors",
60
+ "language_model.model.layers.15.feed_forward.w3.weight": "model-00002-of-00004.safetensors",
61
+ "language_model.model.layers.15.ffn_norm.weight": "model-00002-of-00004.safetensors",
62
+ "language_model.model.layers.16.attention.wo.weight": "model-00002-of-00004.safetensors",
63
+ "language_model.model.layers.16.attention.wqkv.weight": "model-00002-of-00004.safetensors",
64
+ "language_model.model.layers.16.attention_norm.weight": "model-00002-of-00004.safetensors",
65
+ "language_model.model.layers.16.feed_forward.w1.weight": "model-00002-of-00004.safetensors",
66
+ "language_model.model.layers.16.feed_forward.w2.weight": "model-00002-of-00004.safetensors",
67
+ "language_model.model.layers.16.feed_forward.w3.weight": "model-00002-of-00004.safetensors",
68
+ "language_model.model.layers.16.ffn_norm.weight": "model-00002-of-00004.safetensors",
69
+ "language_model.model.layers.17.attention.wo.weight": "model-00002-of-00004.safetensors",
70
+ "language_model.model.layers.17.attention.wqkv.weight": "model-00002-of-00004.safetensors",
71
+ "language_model.model.layers.17.attention_norm.weight": "model-00002-of-00004.safetensors",
72
+ "language_model.model.layers.17.feed_forward.w1.weight": "model-00002-of-00004.safetensors",
73
+ "language_model.model.layers.17.feed_forward.w2.weight": "model-00002-of-00004.safetensors",
74
+ "language_model.model.layers.17.feed_forward.w3.weight": "model-00002-of-00004.safetensors",
75
+ "language_model.model.layers.17.ffn_norm.weight": "model-00002-of-00004.safetensors",
76
+ "language_model.model.layers.18.attention.wo.weight": "model-00002-of-00004.safetensors",
77
+ "language_model.model.layers.18.attention.wqkv.weight": "model-00002-of-00004.safetensors",
78
+ "language_model.model.layers.18.attention_norm.weight": "model-00002-of-00004.safetensors",
79
+ "language_model.model.layers.18.feed_forward.w1.weight": "model-00002-of-00004.safetensors",
80
+ "language_model.model.layers.18.feed_forward.w2.weight": "model-00002-of-00004.safetensors",
81
+ "language_model.model.layers.18.feed_forward.w3.weight": "model-00002-of-00004.safetensors",
82
+ "language_model.model.layers.18.ffn_norm.weight": "model-00002-of-00004.safetensors",
83
+ "language_model.model.layers.19.attention.wo.weight": "model-00002-of-00004.safetensors",
84
+ "language_model.model.layers.19.attention.wqkv.weight": "model-00002-of-00004.safetensors",
85
+ "language_model.model.layers.19.attention_norm.weight": "model-00003-of-00004.safetensors",
86
+ "language_model.model.layers.19.feed_forward.w1.weight": "model-00002-of-00004.safetensors",
87
+ "language_model.model.layers.19.feed_forward.w2.weight": "model-00003-of-00004.safetensors",
88
+ "language_model.model.layers.19.feed_forward.w3.weight": "model-00003-of-00004.safetensors",
89
+ "language_model.model.layers.19.ffn_norm.weight": "model-00003-of-00004.safetensors",
90
+ "language_model.model.layers.2.attention.wo.weight": "model-00001-of-00004.safetensors",
91
+ "language_model.model.layers.2.attention.wqkv.weight": "model-00001-of-00004.safetensors",
92
+ "language_model.model.layers.2.attention_norm.weight": "model-00001-of-00004.safetensors",
93
+ "language_model.model.layers.2.feed_forward.w1.weight": "model-00001-of-00004.safetensors",
94
+ "language_model.model.layers.2.feed_forward.w2.weight": "model-00001-of-00004.safetensors",
95
+ "language_model.model.layers.2.feed_forward.w3.weight": "model-00001-of-00004.safetensors",
96
+ "language_model.model.layers.2.ffn_norm.weight": "model-00001-of-00004.safetensors",
97
+ "language_model.model.layers.20.attention.wo.weight": "model-00003-of-00004.safetensors",
98
+ "language_model.model.layers.20.attention.wqkv.weight": "model-00003-of-00004.safetensors",
99
+ "language_model.model.layers.20.attention_norm.weight": "model-00003-of-00004.safetensors",
100
+ "language_model.model.layers.20.feed_forward.w1.weight": "model-00003-of-00004.safetensors",
101
+ "language_model.model.layers.20.feed_forward.w2.weight": "model-00003-of-00004.safetensors",
102
+ "language_model.model.layers.20.feed_forward.w3.weight": "model-00003-of-00004.safetensors",
103
+ "language_model.model.layers.20.ffn_norm.weight": "model-00003-of-00004.safetensors",
104
+ "language_model.model.layers.21.attention.wo.weight": "model-00003-of-00004.safetensors",
105
+ "language_model.model.layers.21.attention.wqkv.weight": "model-00003-of-00004.safetensors",
106
+ "language_model.model.layers.21.attention_norm.weight": "model-00003-of-00004.safetensors",
107
+ "language_model.model.layers.21.feed_forward.w1.weight": "model-00003-of-00004.safetensors",
108
+ "language_model.model.layers.21.feed_forward.w2.weight": "model-00003-of-00004.safetensors",
109
+ "language_model.model.layers.21.feed_forward.w3.weight": "model-00003-of-00004.safetensors",
110
+ "language_model.model.layers.21.ffn_norm.weight": "model-00003-of-00004.safetensors",
111
+ "language_model.model.layers.22.attention.wo.weight": "model-00003-of-00004.safetensors",
112
+ "language_model.model.layers.22.attention.wqkv.weight": "model-00003-of-00004.safetensors",
113
+ "language_model.model.layers.22.attention_norm.weight": "model-00003-of-00004.safetensors",
114
+ "language_model.model.layers.22.feed_forward.w1.weight": "model-00003-of-00004.safetensors",
115
+ "language_model.model.layers.22.feed_forward.w2.weight": "model-00003-of-00004.safetensors",
116
+ "language_model.model.layers.22.feed_forward.w3.weight": "model-00003-of-00004.safetensors",
117
+ "language_model.model.layers.22.ffn_norm.weight": "model-00003-of-00004.safetensors",
118
+ "language_model.model.layers.23.attention.wo.weight": "model-00003-of-00004.safetensors",
119
+ "language_model.model.layers.23.attention.wqkv.weight": "model-00003-of-00004.safetensors",
120
+ "language_model.model.layers.23.attention_norm.weight": "model-00003-of-00004.safetensors",
121
+ "language_model.model.layers.23.feed_forward.w1.weight": "model-00003-of-00004.safetensors",
122
+ "language_model.model.layers.23.feed_forward.w2.weight": "model-00003-of-00004.safetensors",
123
+ "language_model.model.layers.23.feed_forward.w3.weight": "model-00003-of-00004.safetensors",
124
+ "language_model.model.layers.23.ffn_norm.weight": "model-00003-of-00004.safetensors",
125
+ "language_model.model.layers.24.attention.wo.weight": "model-00003-of-00004.safetensors",
126
+ "language_model.model.layers.24.attention.wqkv.weight": "model-00003-of-00004.safetensors",
127
+ "language_model.model.layers.24.attention_norm.weight": "model-00003-of-00004.safetensors",
128
+ "language_model.model.layers.24.feed_forward.w1.weight": "model-00003-of-00004.safetensors",
129
+ "language_model.model.layers.24.feed_forward.w2.weight": "model-00003-of-00004.safetensors",
130
+ "language_model.model.layers.24.feed_forward.w3.weight": "model-00003-of-00004.safetensors",
131
+ "language_model.model.layers.24.ffn_norm.weight": "model-00003-of-00004.safetensors",
132
+ "language_model.model.layers.25.attention.wo.weight": "model-00003-of-00004.safetensors",
133
+ "language_model.model.layers.25.attention.wqkv.weight": "model-00003-of-00004.safetensors",
134
+ "language_model.model.layers.25.attention_norm.weight": "model-00003-of-00004.safetensors",
135
+ "language_model.model.layers.25.feed_forward.w1.weight": "model-00003-of-00004.safetensors",
136
+ "language_model.model.layers.25.feed_forward.w2.weight": "model-00003-of-00004.safetensors",
137
+ "language_model.model.layers.25.feed_forward.w3.weight": "model-00003-of-00004.safetensors",
138
+ "language_model.model.layers.25.ffn_norm.weight": "model-00003-of-00004.safetensors",
139
+ "language_model.model.layers.26.attention.wo.weight": "model-00003-of-00004.safetensors",
140
+ "language_model.model.layers.26.attention.wqkv.weight": "model-00003-of-00004.safetensors",
141
+ "language_model.model.layers.26.attention_norm.weight": "model-00003-of-00004.safetensors",
142
+ "language_model.model.layers.26.feed_forward.w1.weight": "model-00003-of-00004.safetensors",
143
+ "language_model.model.layers.26.feed_forward.w2.weight": "model-00003-of-00004.safetensors",
144
+ "language_model.model.layers.26.feed_forward.w3.weight": "model-00003-of-00004.safetensors",
145
+ "language_model.model.layers.26.ffn_norm.weight": "model-00003-of-00004.safetensors",
146
+ "language_model.model.layers.27.attention.wo.weight": "model-00003-of-00004.safetensors",
147
+ "language_model.model.layers.27.attention.wqkv.weight": "model-00003-of-00004.safetensors",
148
+ "language_model.model.layers.27.attention_norm.weight": "model-00003-of-00004.safetensors",
149
+ "language_model.model.layers.27.feed_forward.w1.weight": "model-00003-of-00004.safetensors",
150
+ "language_model.model.layers.27.feed_forward.w2.weight": "model-00003-of-00004.safetensors",
151
+ "language_model.model.layers.27.feed_forward.w3.weight": "model-00003-of-00004.safetensors",
152
+ "language_model.model.layers.27.ffn_norm.weight": "model-00003-of-00004.safetensors",
153
+ "language_model.model.layers.28.attention.wo.weight": "model-00003-of-00004.safetensors",
154
+ "language_model.model.layers.28.attention.wqkv.weight": "model-00003-of-00004.safetensors",
155
+ "language_model.model.layers.28.attention_norm.weight": "model-00003-of-00004.safetensors",
156
+ "language_model.model.layers.28.feed_forward.w1.weight": "model-00003-of-00004.safetensors",
157
+ "language_model.model.layers.28.feed_forward.w2.weight": "model-00003-of-00004.safetensors",
158
+ "language_model.model.layers.28.feed_forward.w3.weight": "model-00003-of-00004.safetensors",
159
+ "language_model.model.layers.28.ffn_norm.weight": "model-00003-of-00004.safetensors",
160
+ "language_model.model.layers.29.attention.wo.weight": "model-00003-of-00004.safetensors",
161
+ "language_model.model.layers.29.attention.wqkv.weight": "model-00003-of-00004.safetensors",
162
+ "language_model.model.layers.29.attention_norm.weight": "model-00003-of-00004.safetensors",
163
+ "language_model.model.layers.29.feed_forward.w1.weight": "model-00003-of-00004.safetensors",
164
+ "language_model.model.layers.29.feed_forward.w2.weight": "model-00003-of-00004.safetensors",
165
+ "language_model.model.layers.29.feed_forward.w3.weight": "model-00003-of-00004.safetensors",
166
+ "language_model.model.layers.29.ffn_norm.weight": "model-00003-of-00004.safetensors",
167
+ "language_model.model.layers.3.attention.wo.weight": "model-00001-of-00004.safetensors",
168
+ "language_model.model.layers.3.attention.wqkv.weight": "model-00001-of-00004.safetensors",
169
+ "language_model.model.layers.3.attention_norm.weight": "model-00001-of-00004.safetensors",
170
+ "language_model.model.layers.3.feed_forward.w1.weight": "model-00001-of-00004.safetensors",
171
+ "language_model.model.layers.3.feed_forward.w2.weight": "model-00001-of-00004.safetensors",
172
+ "language_model.model.layers.3.feed_forward.w3.weight": "model-00001-of-00004.safetensors",
173
+ "language_model.model.layers.3.ffn_norm.weight": "model-00001-of-00004.safetensors",
174
+ "language_model.model.layers.30.attention.wo.weight": "model-00003-of-00004.safetensors",
175
+ "language_model.model.layers.30.attention.wqkv.weight": "model-00003-of-00004.safetensors",
176
+ "language_model.model.layers.30.attention_norm.weight": "model-00004-of-00004.safetensors",
177
+ "language_model.model.layers.30.feed_forward.w1.weight": "model-00003-of-00004.safetensors",
178
+ "language_model.model.layers.30.feed_forward.w2.weight": "model-00004-of-00004.safetensors",
179
+ "language_model.model.layers.30.feed_forward.w3.weight": "model-00003-of-00004.safetensors",
180
+ "language_model.model.layers.30.ffn_norm.weight": "model-00004-of-00004.safetensors",
181
+ "language_model.model.layers.31.attention.wo.weight": "model-00004-of-00004.safetensors",
182
+ "language_model.model.layers.31.attention.wqkv.weight": "model-00004-of-00004.safetensors",
183
+ "language_model.model.layers.31.attention_norm.weight": "model-00004-of-00004.safetensors",
184
+ "language_model.model.layers.31.feed_forward.w1.weight": "model-00004-of-00004.safetensors",
185
+ "language_model.model.layers.31.feed_forward.w2.weight": "model-00004-of-00004.safetensors",
186
+ "language_model.model.layers.31.feed_forward.w3.weight": "model-00004-of-00004.safetensors",
187
+ "language_model.model.layers.31.ffn_norm.weight": "model-00004-of-00004.safetensors",
188
+ "language_model.model.layers.4.attention.wo.weight": "model-00001-of-00004.safetensors",
189
+ "language_model.model.layers.4.attention.wqkv.weight": "model-00001-of-00004.safetensors",
190
+ "language_model.model.layers.4.attention_norm.weight": "model-00001-of-00004.safetensors",
191
+ "language_model.model.layers.4.feed_forward.w1.weight": "model-00001-of-00004.safetensors",
192
+ "language_model.model.layers.4.feed_forward.w2.weight": "model-00001-of-00004.safetensors",
193
+ "language_model.model.layers.4.feed_forward.w3.weight": "model-00001-of-00004.safetensors",
194
+ "language_model.model.layers.4.ffn_norm.weight": "model-00001-of-00004.safetensors",
195
+ "language_model.model.layers.5.attention.wo.weight": "model-00001-of-00004.safetensors",
196
+ "language_model.model.layers.5.attention.wqkv.weight": "model-00001-of-00004.safetensors",
197
+ "language_model.model.layers.5.attention_norm.weight": "model-00001-of-00004.safetensors",
198
+ "language_model.model.layers.5.feed_forward.w1.weight": "model-00001-of-00004.safetensors",
199
+ "language_model.model.layers.5.feed_forward.w2.weight": "model-00001-of-00004.safetensors",
200
+ "language_model.model.layers.5.feed_forward.w3.weight": "model-00001-of-00004.safetensors",
201
+ "language_model.model.layers.5.ffn_norm.weight": "model-00001-of-00004.safetensors",
202
+ "language_model.model.layers.6.attention.wo.weight": "model-00001-of-00004.safetensors",
203
+ "language_model.model.layers.6.attention.wqkv.weight": "model-00001-of-00004.safetensors",
204
+ "language_model.model.layers.6.attention_norm.weight": "model-00001-of-00004.safetensors",
205
+ "language_model.model.layers.6.feed_forward.w1.weight": "model-00001-of-00004.safetensors",
206
+ "language_model.model.layers.6.feed_forward.w2.weight": "model-00001-of-00004.safetensors",
207
+ "language_model.model.layers.6.feed_forward.w3.weight": "model-00001-of-00004.safetensors",
208
+ "language_model.model.layers.6.ffn_norm.weight": "model-00001-of-00004.safetensors",
209
+ "language_model.model.layers.7.attention.wo.weight": "model-00001-of-00004.safetensors",
210
+ "language_model.model.layers.7.attention.wqkv.weight": "model-00001-of-00004.safetensors",
211
+ "language_model.model.layers.7.attention_norm.weight": "model-00001-of-00004.safetensors",
212
+ "language_model.model.layers.7.feed_forward.w1.weight": "model-00001-of-00004.safetensors",
213
+ "language_model.model.layers.7.feed_forward.w2.weight": "model-00001-of-00004.safetensors",
214
+ "language_model.model.layers.7.feed_forward.w3.weight": "model-00001-of-00004.safetensors",
215
+ "language_model.model.layers.7.ffn_norm.weight": "model-00001-of-00004.safetensors",
216
+ "language_model.model.layers.8.attention.wo.weight": "model-00001-of-00004.safetensors",
217
+ "language_model.model.layers.8.attention.wqkv.weight": "model-00001-of-00004.safetensors",
218
+ "language_model.model.layers.8.attention_norm.weight": "model-00002-of-00004.safetensors",
219
+ "language_model.model.layers.8.feed_forward.w1.weight": "model-00002-of-00004.safetensors",
220
+ "language_model.model.layers.8.feed_forward.w2.weight": "model-00002-of-00004.safetensors",
221
+ "language_model.model.layers.8.feed_forward.w3.weight": "model-00002-of-00004.safetensors",
222
+ "language_model.model.layers.8.ffn_norm.weight": "model-00002-of-00004.safetensors",
223
+ "language_model.model.layers.9.attention.wo.weight": "model-00002-of-00004.safetensors",
224
+ "language_model.model.layers.9.attention.wqkv.weight": "model-00002-of-00004.safetensors",
225
+ "language_model.model.layers.9.attention_norm.weight": "model-00002-of-00004.safetensors",
226
+ "language_model.model.layers.9.feed_forward.w1.weight": "model-00002-of-00004.safetensors",
227
+ "language_model.model.layers.9.feed_forward.w2.weight": "model-00002-of-00004.safetensors",
228
+ "language_model.model.layers.9.feed_forward.w3.weight": "model-00002-of-00004.safetensors",
229
+ "language_model.model.layers.9.ffn_norm.weight": "model-00002-of-00004.safetensors",
230
+ "language_model.model.norm.weight": "model-00004-of-00004.safetensors",
231
+ "language_model.model.tok_embeddings.weight": "model-00001-of-00004.safetensors",
232
+ "language_model.output.weight": "model-00004-of-00004.safetensors",
233
+ "mlp1.0.bias": "model-00004-of-00004.safetensors",
234
+ "mlp1.0.weight": "model-00004-of-00004.safetensors",
235
+ "mlp1.1.bias": "model-00004-of-00004.safetensors",
236
+ "mlp1.1.weight": "model-00004-of-00004.safetensors",
237
+ "mlp1.3.bias": "model-00004-of-00004.safetensors",
238
+ "mlp1.3.weight": "model-00004-of-00004.safetensors",
239
+ "vision_model.embeddings.class_embedding": "model-00001-of-00004.safetensors",
240
+ "vision_model.embeddings.patch_embedding.bias": "model-00001-of-00004.safetensors",
241
+ "vision_model.embeddings.patch_embedding.weight": "model-00001-of-00004.safetensors",
242
+ "vision_model.embeddings.position_embedding": "model-00001-of-00004.safetensors",
243
+ "vision_model.encoder.layers.0.attn.proj.bias": "model-00001-of-00004.safetensors",
244
+ "vision_model.encoder.layers.0.attn.proj.weight": "model-00001-of-00004.safetensors",
245
+ "vision_model.encoder.layers.0.attn.qkv.bias": "model-00001-of-00004.safetensors",
246
+ "vision_model.encoder.layers.0.attn.qkv.weight": "model-00001-of-00004.safetensors",
247
+ "vision_model.encoder.layers.0.ls1": "model-00001-of-00004.safetensors",
248
+ "vision_model.encoder.layers.0.ls2": "model-00001-of-00004.safetensors",
249
+ "vision_model.encoder.layers.0.mlp.fc1.bias": "model-00001-of-00004.safetensors",
250
+ "vision_model.encoder.layers.0.mlp.fc1.weight": "model-00001-of-00004.safetensors",
251
+ "vision_model.encoder.layers.0.mlp.fc2.bias": "model-00001-of-00004.safetensors",
252
+ "vision_model.encoder.layers.0.mlp.fc2.weight": "model-00001-of-00004.safetensors",
253
+ "vision_model.encoder.layers.0.norm1.bias": "model-00001-of-00004.safetensors",
254
+ "vision_model.encoder.layers.0.norm1.weight": "model-00001-of-00004.safetensors",
255
+ "vision_model.encoder.layers.0.norm2.bias": "model-00001-of-00004.safetensors",
256
+ "vision_model.encoder.layers.0.norm2.weight": "model-00001-of-00004.safetensors",
257
+ "vision_model.encoder.layers.1.attn.proj.bias": "model-00001-of-00004.safetensors",
258
+ "vision_model.encoder.layers.1.attn.proj.weight": "model-00001-of-00004.safetensors",
259
+ "vision_model.encoder.layers.1.attn.qkv.bias": "model-00001-of-00004.safetensors",
260
+ "vision_model.encoder.layers.1.attn.qkv.weight": "model-00001-of-00004.safetensors",
261
+ "vision_model.encoder.layers.1.ls1": "model-00001-of-00004.safetensors",
262
+ "vision_model.encoder.layers.1.ls2": "model-00001-of-00004.safetensors",
263
+ "vision_model.encoder.layers.1.mlp.fc1.bias": "model-00001-of-00004.safetensors",
264
+ "vision_model.encoder.layers.1.mlp.fc1.weight": "model-00001-of-00004.safetensors",
265
+ "vision_model.encoder.layers.1.mlp.fc2.bias": "model-00001-of-00004.safetensors",
266
+ "vision_model.encoder.layers.1.mlp.fc2.weight": "model-00001-of-00004.safetensors",
267
+ "vision_model.encoder.layers.1.norm1.bias": "model-00001-of-00004.safetensors",
268
+ "vision_model.encoder.layers.1.norm1.weight": "model-00001-of-00004.safetensors",
269
+ "vision_model.encoder.layers.1.norm2.bias": "model-00001-of-00004.safetensors",
270
+ "vision_model.encoder.layers.1.norm2.weight": "model-00001-of-00004.safetensors",
271
+ "vision_model.encoder.layers.10.attn.proj.bias": "model-00001-of-00004.safetensors",
272
+ "vision_model.encoder.layers.10.attn.proj.weight": "model-00001-of-00004.safetensors",
273
+ "vision_model.encoder.layers.10.attn.qkv.bias": "model-00001-of-00004.safetensors",
274
+ "vision_model.encoder.layers.10.attn.qkv.weight": "model-00001-of-00004.safetensors",
275
+ "vision_model.encoder.layers.10.ls1": "model-00001-of-00004.safetensors",
276
+ "vision_model.encoder.layers.10.ls2": "model-00001-of-00004.safetensors",
277
+ "vision_model.encoder.layers.10.mlp.fc1.bias": "model-00001-of-00004.safetensors",
278
+ "vision_model.encoder.layers.10.mlp.fc1.weight": "model-00001-of-00004.safetensors",
279
+ "vision_model.encoder.layers.10.mlp.fc2.bias": "model-00001-of-00004.safetensors",
280
+ "vision_model.encoder.layers.10.mlp.fc2.weight": "model-00001-of-00004.safetensors",
281
+ "vision_model.encoder.layers.10.norm1.bias": "model-00001-of-00004.safetensors",
282
+ "vision_model.encoder.layers.10.norm1.weight": "model-00001-of-00004.safetensors",
283
+ "vision_model.encoder.layers.10.norm2.bias": "model-00001-of-00004.safetensors",
284
+ "vision_model.encoder.layers.10.norm2.weight": "model-00001-of-00004.safetensors",
285
+ "vision_model.encoder.layers.11.attn.proj.bias": "model-00001-of-00004.safetensors",
286
+ "vision_model.encoder.layers.11.attn.proj.weight": "model-00001-of-00004.safetensors",
287
+ "vision_model.encoder.layers.11.attn.qkv.bias": "model-00001-of-00004.safetensors",
288
+ "vision_model.encoder.layers.11.attn.qkv.weight": "model-00001-of-00004.safetensors",
289
+ "vision_model.encoder.layers.11.ls1": "model-00001-of-00004.safetensors",
290
+ "vision_model.encoder.layers.11.ls2": "model-00001-of-00004.safetensors",
291
+ "vision_model.encoder.layers.11.mlp.fc1.bias": "model-00001-of-00004.safetensors",
292
+ "vision_model.encoder.layers.11.mlp.fc1.weight": "model-00001-of-00004.safetensors",
293
+ "vision_model.encoder.layers.11.mlp.fc2.bias": "model-00001-of-00004.safetensors",
294
+ "vision_model.encoder.layers.11.mlp.fc2.weight": "model-00001-of-00004.safetensors",
295
+ "vision_model.encoder.layers.11.norm1.bias": "model-00001-of-00004.safetensors",
296
+ "vision_model.encoder.layers.11.norm1.weight": "model-00001-of-00004.safetensors",
297
+ "vision_model.encoder.layers.11.norm2.bias": "model-00001-of-00004.safetensors",
298
+ "vision_model.encoder.layers.11.norm2.weight": "model-00001-of-00004.safetensors",
299
+ "vision_model.encoder.layers.12.attn.proj.bias": "model-00001-of-00004.safetensors",
300
+ "vision_model.encoder.layers.12.attn.proj.weight": "model-00001-of-00004.safetensors",
301
+ "vision_model.encoder.layers.12.attn.qkv.bias": "model-00001-of-00004.safetensors",
302
+ "vision_model.encoder.layers.12.attn.qkv.weight": "model-00001-of-00004.safetensors",
303
+ "vision_model.encoder.layers.12.ls1": "model-00001-of-00004.safetensors",
304
+ "vision_model.encoder.layers.12.ls2": "model-00001-of-00004.safetensors",
305
+ "vision_model.encoder.layers.12.mlp.fc1.bias": "model-00001-of-00004.safetensors",
306
+ "vision_model.encoder.layers.12.mlp.fc1.weight": "model-00001-of-00004.safetensors",
307
+ "vision_model.encoder.layers.12.mlp.fc2.bias": "model-00001-of-00004.safetensors",
308
+ "vision_model.encoder.layers.12.mlp.fc2.weight": "model-00001-of-00004.safetensors",
309
+ "vision_model.encoder.layers.12.norm1.bias": "model-00001-of-00004.safetensors",
310
+ "vision_model.encoder.layers.12.norm1.weight": "model-00001-of-00004.safetensors",
311
+ "vision_model.encoder.layers.12.norm2.bias": "model-00001-of-00004.safetensors",
312
+ "vision_model.encoder.layers.12.norm2.weight": "model-00001-of-00004.safetensors",
313
+ "vision_model.encoder.layers.13.attn.proj.bias": "model-00001-of-00004.safetensors",
314
+ "vision_model.encoder.layers.13.attn.proj.weight": "model-00001-of-00004.safetensors",
315
+ "vision_model.encoder.layers.13.attn.qkv.bias": "model-00001-of-00004.safetensors",
316
+ "vision_model.encoder.layers.13.attn.qkv.weight": "model-00001-of-00004.safetensors",
317
+ "vision_model.encoder.layers.13.ls1": "model-00001-of-00004.safetensors",
318
+ "vision_model.encoder.layers.13.ls2": "model-00001-of-00004.safetensors",
319
+ "vision_model.encoder.layers.13.mlp.fc1.bias": "model-00001-of-00004.safetensors",
320
+ "vision_model.encoder.layers.13.mlp.fc1.weight": "model-00001-of-00004.safetensors",
321
+ "vision_model.encoder.layers.13.mlp.fc2.bias": "model-00001-of-00004.safetensors",
322
+ "vision_model.encoder.layers.13.mlp.fc2.weight": "model-00001-of-00004.safetensors",
323
+ "vision_model.encoder.layers.13.norm1.bias": "model-00001-of-00004.safetensors",
324
+ "vision_model.encoder.layers.13.norm1.weight": "model-00001-of-00004.safetensors",
325
+ "vision_model.encoder.layers.13.norm2.bias": "model-00001-of-00004.safetensors",
326
+ "vision_model.encoder.layers.13.norm2.weight": "model-00001-of-00004.safetensors",
327
+ "vision_model.encoder.layers.14.attn.proj.bias": "model-00001-of-00004.safetensors",
328
+ "vision_model.encoder.layers.14.attn.proj.weight": "model-00001-of-00004.safetensors",
329
+ "vision_model.encoder.layers.14.attn.qkv.bias": "model-00001-of-00004.safetensors",
330
+ "vision_model.encoder.layers.14.attn.qkv.weight": "model-00001-of-00004.safetensors",
331
+ "vision_model.encoder.layers.14.ls1": "model-00001-of-00004.safetensors",
332
+ "vision_model.encoder.layers.14.ls2": "model-00001-of-00004.safetensors",
333
+ "vision_model.encoder.layers.14.mlp.fc1.bias": "model-00001-of-00004.safetensors",
334
+ "vision_model.encoder.layers.14.mlp.fc1.weight": "model-00001-of-00004.safetensors",
335
+ "vision_model.encoder.layers.14.mlp.fc2.bias": "model-00001-of-00004.safetensors",
336
+ "vision_model.encoder.layers.14.mlp.fc2.weight": "model-00001-of-00004.safetensors",
337
+ "vision_model.encoder.layers.14.norm1.bias": "model-00001-of-00004.safetensors",
338
+ "vision_model.encoder.layers.14.norm1.weight": "model-00001-of-00004.safetensors",
339
+ "vision_model.encoder.layers.14.norm2.bias": "model-00001-of-00004.safetensors",
340
+ "vision_model.encoder.layers.14.norm2.weight": "model-00001-of-00004.safetensors",
341
+ "vision_model.encoder.layers.15.attn.proj.bias": "model-00001-of-00004.safetensors",
342
+ "vision_model.encoder.layers.15.attn.proj.weight": "model-00001-of-00004.safetensors",
343
+ "vision_model.encoder.layers.15.attn.qkv.bias": "model-00001-of-00004.safetensors",
344
+ "vision_model.encoder.layers.15.attn.qkv.weight": "model-00001-of-00004.safetensors",
345
+ "vision_model.encoder.layers.15.ls1": "model-00001-of-00004.safetensors",
346
+ "vision_model.encoder.layers.15.ls2": "model-00001-of-00004.safetensors",
347
+ "vision_model.encoder.layers.15.mlp.fc1.bias": "model-00001-of-00004.safetensors",
348
+ "vision_model.encoder.layers.15.mlp.fc1.weight": "model-00001-of-00004.safetensors",
349
+ "vision_model.encoder.layers.15.mlp.fc2.bias": "model-00001-of-00004.safetensors",
350
+ "vision_model.encoder.layers.15.mlp.fc2.weight": "model-00001-of-00004.safetensors",
351
+ "vision_model.encoder.layers.15.norm1.bias": "model-00001-of-00004.safetensors",
352
+ "vision_model.encoder.layers.15.norm1.weight": "model-00001-of-00004.safetensors",
353
+ "vision_model.encoder.layers.15.norm2.bias": "model-00001-of-00004.safetensors",
354
+ "vision_model.encoder.layers.15.norm2.weight": "model-00001-of-00004.safetensors",
355
+ "vision_model.encoder.layers.16.attn.proj.bias": "model-00001-of-00004.safetensors",
356
+ "vision_model.encoder.layers.16.attn.proj.weight": "model-00001-of-00004.safetensors",
357
+ "vision_model.encoder.layers.16.attn.qkv.bias": "model-00001-of-00004.safetensors",
358
+ "vision_model.encoder.layers.16.attn.qkv.weight": "model-00001-of-00004.safetensors",
359
+ "vision_model.encoder.layers.16.ls1": "model-00001-of-00004.safetensors",
360
+ "vision_model.encoder.layers.16.ls2": "model-00001-of-00004.safetensors",
361
+ "vision_model.encoder.layers.16.mlp.fc1.bias": "model-00001-of-00004.safetensors",
362
+ "vision_model.encoder.layers.16.mlp.fc1.weight": "model-00001-of-00004.safetensors",
363
+ "vision_model.encoder.layers.16.mlp.fc2.bias": "model-00001-of-00004.safetensors",
364
+ "vision_model.encoder.layers.16.mlp.fc2.weight": "model-00001-of-00004.safetensors",
365
+ "vision_model.encoder.layers.16.norm1.bias": "model-00001-of-00004.safetensors",
366
+ "vision_model.encoder.layers.16.norm1.weight": "model-00001-of-00004.safetensors",
367
+ "vision_model.encoder.layers.16.norm2.bias": "model-00001-of-00004.safetensors",
368
+ "vision_model.encoder.layers.16.norm2.weight": "model-00001-of-00004.safetensors",
369
+ "vision_model.encoder.layers.17.attn.proj.bias": "model-00001-of-00004.safetensors",
370
+ "vision_model.encoder.layers.17.attn.proj.weight": "model-00001-of-00004.safetensors",
371
+ "vision_model.encoder.layers.17.attn.qkv.bias": "model-00001-of-00004.safetensors",
372
+ "vision_model.encoder.layers.17.attn.qkv.weight": "model-00001-of-00004.safetensors",
373
+ "vision_model.encoder.layers.17.ls1": "model-00001-of-00004.safetensors",
374
+ "vision_model.encoder.layers.17.ls2": "model-00001-of-00004.safetensors",
375
+ "vision_model.encoder.layers.17.mlp.fc1.bias": "model-00001-of-00004.safetensors",
376
+ "vision_model.encoder.layers.17.mlp.fc1.weight": "model-00001-of-00004.safetensors",
377
+ "vision_model.encoder.layers.17.mlp.fc2.bias": "model-00001-of-00004.safetensors",
378
+ "vision_model.encoder.layers.17.mlp.fc2.weight": "model-00001-of-00004.safetensors",
379
+ "vision_model.encoder.layers.17.norm1.bias": "model-00001-of-00004.safetensors",
380
+ "vision_model.encoder.layers.17.norm1.weight": "model-00001-of-00004.safetensors",
381
+ "vision_model.encoder.layers.17.norm2.bias": "model-00001-of-00004.safetensors",
382
+ "vision_model.encoder.layers.17.norm2.weight": "model-00001-of-00004.safetensors",
383
+ "vision_model.encoder.layers.18.attn.proj.bias": "model-00001-of-00004.safetensors",
384
+ "vision_model.encoder.layers.18.attn.proj.weight": "model-00001-of-00004.safetensors",
385
+ "vision_model.encoder.layers.18.attn.qkv.bias": "model-00001-of-00004.safetensors",
386
+ "vision_model.encoder.layers.18.attn.qkv.weight": "model-00001-of-00004.safetensors",
387
+ "vision_model.encoder.layers.18.ls1": "model-00001-of-00004.safetensors",
388
+ "vision_model.encoder.layers.18.ls2": "model-00001-of-00004.safetensors",
389
+ "vision_model.encoder.layers.18.mlp.fc1.bias": "model-00001-of-00004.safetensors",
390
+ "vision_model.encoder.layers.18.mlp.fc1.weight": "model-00001-of-00004.safetensors",
391
+ "vision_model.encoder.layers.18.mlp.fc2.bias": "model-00001-of-00004.safetensors",
392
+ "vision_model.encoder.layers.18.mlp.fc2.weight": "model-00001-of-00004.safetensors",
393
+ "vision_model.encoder.layers.18.norm1.bias": "model-00001-of-00004.safetensors",
394
+ "vision_model.encoder.layers.18.norm1.weight": "model-00001-of-00004.safetensors",
395
+ "vision_model.encoder.layers.18.norm2.bias": "model-00001-of-00004.safetensors",
396
+ "vision_model.encoder.layers.18.norm2.weight": "model-00001-of-00004.safetensors",
397
+ "vision_model.encoder.layers.19.attn.proj.bias": "model-00001-of-00004.safetensors",
398
+ "vision_model.encoder.layers.19.attn.proj.weight": "model-00001-of-00004.safetensors",
399
+ "vision_model.encoder.layers.19.attn.qkv.bias": "model-00001-of-00004.safetensors",
400
+ "vision_model.encoder.layers.19.attn.qkv.weight": "model-00001-of-00004.safetensors",
401
+ "vision_model.encoder.layers.19.ls1": "model-00001-of-00004.safetensors",
402
+ "vision_model.encoder.layers.19.ls2": "model-00001-of-00004.safetensors",
403
+ "vision_model.encoder.layers.19.mlp.fc1.bias": "model-00001-of-00004.safetensors",
404
+ "vision_model.encoder.layers.19.mlp.fc1.weight": "model-00001-of-00004.safetensors",
405
+ "vision_model.encoder.layers.19.mlp.fc2.bias": "model-00001-of-00004.safetensors",
406
+ "vision_model.encoder.layers.19.mlp.fc2.weight": "model-00001-of-00004.safetensors",
407
+ "vision_model.encoder.layers.19.norm1.bias": "model-00001-of-00004.safetensors",
408
+ "vision_model.encoder.layers.19.norm1.weight": "model-00001-of-00004.safetensors",
409
+ "vision_model.encoder.layers.19.norm2.bias": "model-00001-of-00004.safetensors",
410
+ "vision_model.encoder.layers.19.norm2.weight": "model-00001-of-00004.safetensors",
411
+ "vision_model.encoder.layers.2.attn.proj.bias": "model-00001-of-00004.safetensors",
412
+ "vision_model.encoder.layers.2.attn.proj.weight": "model-00001-of-00004.safetensors",
413
+ "vision_model.encoder.layers.2.attn.qkv.bias": "model-00001-of-00004.safetensors",
414
+ "vision_model.encoder.layers.2.attn.qkv.weight": "model-00001-of-00004.safetensors",
415
+ "vision_model.encoder.layers.2.ls1": "model-00001-of-00004.safetensors",
416
+ "vision_model.encoder.layers.2.ls2": "model-00001-of-00004.safetensors",
417
+ "vision_model.encoder.layers.2.mlp.fc1.bias": "model-00001-of-00004.safetensors",
418
+ "vision_model.encoder.layers.2.mlp.fc1.weight": "model-00001-of-00004.safetensors",
419
+ "vision_model.encoder.layers.2.mlp.fc2.bias": "model-00001-of-00004.safetensors",
420
+ "vision_model.encoder.layers.2.mlp.fc2.weight": "model-00001-of-00004.safetensors",
421
+ "vision_model.encoder.layers.2.norm1.bias": "model-00001-of-00004.safetensors",
422
+ "vision_model.encoder.layers.2.norm1.weight": "model-00001-of-00004.safetensors",
423
+ "vision_model.encoder.layers.2.norm2.bias": "model-00001-of-00004.safetensors",
424
+ "vision_model.encoder.layers.2.norm2.weight": "model-00001-of-00004.safetensors",
425
+ "vision_model.encoder.layers.20.attn.proj.bias": "model-00001-of-00004.safetensors",
426
+ "vision_model.encoder.layers.20.attn.proj.weight": "model-00001-of-00004.safetensors",
427
+ "vision_model.encoder.layers.20.attn.qkv.bias": "model-00001-of-00004.safetensors",
428
+ "vision_model.encoder.layers.20.attn.qkv.weight": "model-00001-of-00004.safetensors",
429
+ "vision_model.encoder.layers.20.ls1": "model-00001-of-00004.safetensors",
430
+ "vision_model.encoder.layers.20.ls2": "model-00001-of-00004.safetensors",
431
+ "vision_model.encoder.layers.20.mlp.fc1.bias": "model-00001-of-00004.safetensors",
432
+ "vision_model.encoder.layers.20.mlp.fc1.weight": "model-00001-of-00004.safetensors",
433
+ "vision_model.encoder.layers.20.mlp.fc2.bias": "model-00001-of-00004.safetensors",
434
+ "vision_model.encoder.layers.20.mlp.fc2.weight": "model-00001-of-00004.safetensors",
435
+ "vision_model.encoder.layers.20.norm1.bias": "model-00001-of-00004.safetensors",
436
+ "vision_model.encoder.layers.20.norm1.weight": "model-00001-of-00004.safetensors",
437
+ "vision_model.encoder.layers.20.norm2.bias": "model-00001-of-00004.safetensors",
438
+ "vision_model.encoder.layers.20.norm2.weight": "model-00001-of-00004.safetensors",
439
+ "vision_model.encoder.layers.21.attn.proj.bias": "model-00001-of-00004.safetensors",
440
+ "vision_model.encoder.layers.21.attn.proj.weight": "model-00001-of-00004.safetensors",
441
+ "vision_model.encoder.layers.21.attn.qkv.bias": "model-00001-of-00004.safetensors",
442
+ "vision_model.encoder.layers.21.attn.qkv.weight": "model-00001-of-00004.safetensors",
443
+ "vision_model.encoder.layers.21.ls1": "model-00001-of-00004.safetensors",
444
+ "vision_model.encoder.layers.21.ls2": "model-00001-of-00004.safetensors",
445
+ "vision_model.encoder.layers.21.mlp.fc1.bias": "model-00001-of-00004.safetensors",
446
+ "vision_model.encoder.layers.21.mlp.fc1.weight": "model-00001-of-00004.safetensors",
447
+ "vision_model.encoder.layers.21.mlp.fc2.bias": "model-00001-of-00004.safetensors",
448
+ "vision_model.encoder.layers.21.mlp.fc2.weight": "model-00001-of-00004.safetensors",
449
+ "vision_model.encoder.layers.21.norm1.bias": "model-00001-of-00004.safetensors",
450
+ "vision_model.encoder.layers.21.norm1.weight": "model-00001-of-00004.safetensors",
451
+ "vision_model.encoder.layers.21.norm2.bias": "model-00001-of-00004.safetensors",
452
+ "vision_model.encoder.layers.21.norm2.weight": "model-00001-of-00004.safetensors",
453
+ "vision_model.encoder.layers.22.attn.proj.bias": "model-00001-of-00004.safetensors",
454
+ "vision_model.encoder.layers.22.attn.proj.weight": "model-00001-of-00004.safetensors",
455
+ "vision_model.encoder.layers.22.attn.qkv.bias": "model-00001-of-00004.safetensors",
456
+ "vision_model.encoder.layers.22.attn.qkv.weight": "model-00001-of-00004.safetensors",
457
+ "vision_model.encoder.layers.22.ls1": "model-00001-of-00004.safetensors",
458
+ "vision_model.encoder.layers.22.ls2": "model-00001-of-00004.safetensors",
459
+ "vision_model.encoder.layers.22.mlp.fc1.bias": "model-00001-of-00004.safetensors",
460
+ "vision_model.encoder.layers.22.mlp.fc1.weight": "model-00001-of-00004.safetensors",
461
+ "vision_model.encoder.layers.22.mlp.fc2.bias": "model-00001-of-00004.safetensors",
462
+ "vision_model.encoder.layers.22.mlp.fc2.weight": "model-00001-of-00004.safetensors",
463
+ "vision_model.encoder.layers.22.norm1.bias": "model-00001-of-00004.safetensors",
464
+ "vision_model.encoder.layers.22.norm1.weight": "model-00001-of-00004.safetensors",
465
+ "vision_model.encoder.layers.22.norm2.bias": "model-00001-of-00004.safetensors",
466
+ "vision_model.encoder.layers.22.norm2.weight": "model-00001-of-00004.safetensors",
467
+ "vision_model.encoder.layers.23.attn.proj.bias": "model-00001-of-00004.safetensors",
468
+ "vision_model.encoder.layers.23.attn.proj.weight": "model-00001-of-00004.safetensors",
469
+ "vision_model.encoder.layers.23.attn.qkv.bias": "model-00001-of-00004.safetensors",
470
+ "vision_model.encoder.layers.23.attn.qkv.weight": "model-00001-of-00004.safetensors",
471
+ "vision_model.encoder.layers.23.ls1": "model-00001-of-00004.safetensors",
472
+ "vision_model.encoder.layers.23.ls2": "model-00001-of-00004.safetensors",
473
+ "vision_model.encoder.layers.23.mlp.fc1.bias": "model-00001-of-00004.safetensors",
474
+ "vision_model.encoder.layers.23.mlp.fc1.weight": "model-00001-of-00004.safetensors",
475
+ "vision_model.encoder.layers.23.mlp.fc2.bias": "model-00001-of-00004.safetensors",
476
+ "vision_model.encoder.layers.23.mlp.fc2.weight": "model-00001-of-00004.safetensors",
477
+ "vision_model.encoder.layers.23.norm1.bias": "model-00001-of-00004.safetensors",
478
+ "vision_model.encoder.layers.23.norm1.weight": "model-00001-of-00004.safetensors",
479
+ "vision_model.encoder.layers.23.norm2.bias": "model-00001-of-00004.safetensors",
480
+ "vision_model.encoder.layers.23.norm2.weight": "model-00001-of-00004.safetensors",
481
+ "vision_model.encoder.layers.3.attn.proj.bias": "model-00001-of-00004.safetensors",
482
+ "vision_model.encoder.layers.3.attn.proj.weight": "model-00001-of-00004.safetensors",
483
+ "vision_model.encoder.layers.3.attn.qkv.bias": "model-00001-of-00004.safetensors",
484
+ "vision_model.encoder.layers.3.attn.qkv.weight": "model-00001-of-00004.safetensors",
485
+ "vision_model.encoder.layers.3.ls1": "model-00001-of-00004.safetensors",
486
+ "vision_model.encoder.layers.3.ls2": "model-00001-of-00004.safetensors",
487
+ "vision_model.encoder.layers.3.mlp.fc1.bias": "model-00001-of-00004.safetensors",
488
+ "vision_model.encoder.layers.3.mlp.fc1.weight": "model-00001-of-00004.safetensors",
489
+ "vision_model.encoder.layers.3.mlp.fc2.bias": "model-00001-of-00004.safetensors",
490
+ "vision_model.encoder.layers.3.mlp.fc2.weight": "model-00001-of-00004.safetensors",
491
+ "vision_model.encoder.layers.3.norm1.bias": "model-00001-of-00004.safetensors",
492
+ "vision_model.encoder.layers.3.norm1.weight": "model-00001-of-00004.safetensors",
493
+ "vision_model.encoder.layers.3.norm2.bias": "model-00001-of-00004.safetensors",
494
+ "vision_model.encoder.layers.3.norm2.weight": "model-00001-of-00004.safetensors",
495
+ "vision_model.encoder.layers.4.attn.proj.bias": "model-00001-of-00004.safetensors",
496
+ "vision_model.encoder.layers.4.attn.proj.weight": "model-00001-of-00004.safetensors",
497
+ "vision_model.encoder.layers.4.attn.qkv.bias": "model-00001-of-00004.safetensors",
498
+ "vision_model.encoder.layers.4.attn.qkv.weight": "model-00001-of-00004.safetensors",
499
+ "vision_model.encoder.layers.4.ls1": "model-00001-of-00004.safetensors",
500
+ "vision_model.encoder.layers.4.ls2": "model-00001-of-00004.safetensors",
501
+ "vision_model.encoder.layers.4.mlp.fc1.bias": "model-00001-of-00004.safetensors",
502
+ "vision_model.encoder.layers.4.mlp.fc1.weight": "model-00001-of-00004.safetensors",
503
+ "vision_model.encoder.layers.4.mlp.fc2.bias": "model-00001-of-00004.safetensors",
504
+ "vision_model.encoder.layers.4.mlp.fc2.weight": "model-00001-of-00004.safetensors",
505
+ "vision_model.encoder.layers.4.norm1.bias": "model-00001-of-00004.safetensors",
506
+ "vision_model.encoder.layers.4.norm1.weight": "model-00001-of-00004.safetensors",
507
+ "vision_model.encoder.layers.4.norm2.bias": "model-00001-of-00004.safetensors",
508
+ "vision_model.encoder.layers.4.norm2.weight": "model-00001-of-00004.safetensors",
509
+ "vision_model.encoder.layers.5.attn.proj.bias": "model-00001-of-00004.safetensors",
510
+ "vision_model.encoder.layers.5.attn.proj.weight": "model-00001-of-00004.safetensors",
511
+ "vision_model.encoder.layers.5.attn.qkv.bias": "model-00001-of-00004.safetensors",
512
+ "vision_model.encoder.layers.5.attn.qkv.weight": "model-00001-of-00004.safetensors",
513
+ "vision_model.encoder.layers.5.ls1": "model-00001-of-00004.safetensors",
514
+ "vision_model.encoder.layers.5.ls2": "model-00001-of-00004.safetensors",
515
+ "vision_model.encoder.layers.5.mlp.fc1.bias": "model-00001-of-00004.safetensors",
516
+ "vision_model.encoder.layers.5.mlp.fc1.weight": "model-00001-of-00004.safetensors",
517
+ "vision_model.encoder.layers.5.mlp.fc2.bias": "model-00001-of-00004.safetensors",
518
+ "vision_model.encoder.layers.5.mlp.fc2.weight": "model-00001-of-00004.safetensors",
519
+ "vision_model.encoder.layers.5.norm1.bias": "model-00001-of-00004.safetensors",
520
+ "vision_model.encoder.layers.5.norm1.weight": "model-00001-of-00004.safetensors",
521
+ "vision_model.encoder.layers.5.norm2.bias": "model-00001-of-00004.safetensors",
522
+ "vision_model.encoder.layers.5.norm2.weight": "model-00001-of-00004.safetensors",
523
+ "vision_model.encoder.layers.6.attn.proj.bias": "model-00001-of-00004.safetensors",
524
+ "vision_model.encoder.layers.6.attn.proj.weight": "model-00001-of-00004.safetensors",
525
+ "vision_model.encoder.layers.6.attn.qkv.bias": "model-00001-of-00004.safetensors",
526
+ "vision_model.encoder.layers.6.attn.qkv.weight": "model-00001-of-00004.safetensors",
527
+ "vision_model.encoder.layers.6.ls1": "model-00001-of-00004.safetensors",
528
+ "vision_model.encoder.layers.6.ls2": "model-00001-of-00004.safetensors",
529
+ "vision_model.encoder.layers.6.mlp.fc1.bias": "model-00001-of-00004.safetensors",
530
+ "vision_model.encoder.layers.6.mlp.fc1.weight": "model-00001-of-00004.safetensors",
531
+ "vision_model.encoder.layers.6.mlp.fc2.bias": "model-00001-of-00004.safetensors",
532
+ "vision_model.encoder.layers.6.mlp.fc2.weight": "model-00001-of-00004.safetensors",
533
+ "vision_model.encoder.layers.6.norm1.bias": "model-00001-of-00004.safetensors",
534
+ "vision_model.encoder.layers.6.norm1.weight": "model-00001-of-00004.safetensors",
535
+ "vision_model.encoder.layers.6.norm2.bias": "model-00001-of-00004.safetensors",
536
+ "vision_model.encoder.layers.6.norm2.weight": "model-00001-of-00004.safetensors",
537
+ "vision_model.encoder.layers.7.attn.proj.bias": "model-00001-of-00004.safetensors",
538
+ "vision_model.encoder.layers.7.attn.proj.weight": "model-00001-of-00004.safetensors",
539
+ "vision_model.encoder.layers.7.attn.qkv.bias": "model-00001-of-00004.safetensors",
540
+ "vision_model.encoder.layers.7.attn.qkv.weight": "model-00001-of-00004.safetensors",
541
+ "vision_model.encoder.layers.7.ls1": "model-00001-of-00004.safetensors",
542
+ "vision_model.encoder.layers.7.ls2": "model-00001-of-00004.safetensors",
543
+ "vision_model.encoder.layers.7.mlp.fc1.bias": "model-00001-of-00004.safetensors",
544
+ "vision_model.encoder.layers.7.mlp.fc1.weight": "model-00001-of-00004.safetensors",
545
+ "vision_model.encoder.layers.7.mlp.fc2.bias": "model-00001-of-00004.safetensors",
546
+ "vision_model.encoder.layers.7.mlp.fc2.weight": "model-00001-of-00004.safetensors",
547
+ "vision_model.encoder.layers.7.norm1.bias": "model-00001-of-00004.safetensors",
548
+ "vision_model.encoder.layers.7.norm1.weight": "model-00001-of-00004.safetensors",
549
+ "vision_model.encoder.layers.7.norm2.bias": "model-00001-of-00004.safetensors",
550
+ "vision_model.encoder.layers.7.norm2.weight": "model-00001-of-00004.safetensors",
551
+ "vision_model.encoder.layers.8.attn.proj.bias": "model-00001-of-00004.safetensors",
552
+ "vision_model.encoder.layers.8.attn.proj.weight": "model-00001-of-00004.safetensors",
553
+ "vision_model.encoder.layers.8.attn.qkv.bias": "model-00001-of-00004.safetensors",
554
+ "vision_model.encoder.layers.8.attn.qkv.weight": "model-00001-of-00004.safetensors",
555
+ "vision_model.encoder.layers.8.ls1": "model-00001-of-00004.safetensors",
556
+ "vision_model.encoder.layers.8.ls2": "model-00001-of-00004.safetensors",
557
+ "vision_model.encoder.layers.8.mlp.fc1.bias": "model-00001-of-00004.safetensors",
558
+ "vision_model.encoder.layers.8.mlp.fc1.weight": "model-00001-of-00004.safetensors",
559
+ "vision_model.encoder.layers.8.mlp.fc2.bias": "model-00001-of-00004.safetensors",
560
+ "vision_model.encoder.layers.8.mlp.fc2.weight": "model-00001-of-00004.safetensors",
561
+ "vision_model.encoder.layers.8.norm1.bias": "model-00001-of-00004.safetensors",
562
+ "vision_model.encoder.layers.8.norm1.weight": "model-00001-of-00004.safetensors",
563
+ "vision_model.encoder.layers.8.norm2.bias": "model-00001-of-00004.safetensors",
564
+ "vision_model.encoder.layers.8.norm2.weight": "model-00001-of-00004.safetensors",
565
+ "vision_model.encoder.layers.9.attn.proj.bias": "model-00001-of-00004.safetensors",
566
+ "vision_model.encoder.layers.9.attn.proj.weight": "model-00001-of-00004.safetensors",
567
+ "vision_model.encoder.layers.9.attn.qkv.bias": "model-00001-of-00004.safetensors",
568
+ "vision_model.encoder.layers.9.attn.qkv.weight": "model-00001-of-00004.safetensors",
569
+ "vision_model.encoder.layers.9.ls1": "model-00001-of-00004.safetensors",
570
+ "vision_model.encoder.layers.9.ls2": "model-00001-of-00004.safetensors",
571
+ "vision_model.encoder.layers.9.mlp.fc1.bias": "model-00001-of-00004.safetensors",
572
+ "vision_model.encoder.layers.9.mlp.fc1.weight": "model-00001-of-00004.safetensors",
573
+ "vision_model.encoder.layers.9.mlp.fc2.bias": "model-00001-of-00004.safetensors",
574
+ "vision_model.encoder.layers.9.mlp.fc2.weight": "model-00001-of-00004.safetensors",
575
+ "vision_model.encoder.layers.9.norm1.bias": "model-00001-of-00004.safetensors",
576
+ "vision_model.encoder.layers.9.norm1.weight": "model-00001-of-00004.safetensors",
577
+ "vision_model.encoder.layers.9.norm2.bias": "model-00001-of-00004.safetensors",
578
+ "vision_model.encoder.layers.9.norm2.weight": "model-00001-of-00004.safetensors"
579
+ }
580
+ }
Pretrain_8B/special_tokens_map.json ADDED
@@ -0,0 +1,89 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<|im_start|>",
4
+ "<|im_end|>",
5
+ "<|action_start|>",
6
+ "<|action_end|>",
7
+ "<|interpreter|>",
8
+ "<|plugin|>",
9
+ "<img>",
10
+ "</img>",
11
+ "<IMG_CONTEXT>",
12
+ "<quad>",
13
+ "</quad>",
14
+ "<ref>",
15
+ "</ref>",
16
+ "<box>",
17
+ "</box>",
18
+ {
19
+ "content": "<bbox_2d>",
20
+ "lstrip": false,
21
+ "normalized": false,
22
+ "rstrip": false,
23
+ "single_word": false
24
+ },
25
+ {
26
+ "content": "<bbox_3d>",
27
+ "lstrip": false,
28
+ "normalized": false,
29
+ "rstrip": false,
30
+ "single_word": false
31
+ },
32
+ {
33
+ "content": "<bbox_2d_in>",
34
+ "lstrip": false,
35
+ "normalized": false,
36
+ "rstrip": false,
37
+ "single_word": false
38
+ },
39
+ {
40
+ "content": "<query>",
41
+ "lstrip": false,
42
+ "normalized": false,
43
+ "rstrip": false,
44
+ "single_word": false
45
+ },
46
+ {
47
+ "content": "<box_3d>",
48
+ "lstrip": false,
49
+ "normalized": false,
50
+ "rstrip": false,
51
+ "single_word": false
52
+ },
53
+ {
54
+ "content": "</box_3d>",
55
+ "lstrip": false,
56
+ "normalized": false,
57
+ "rstrip": false,
58
+ "single_word": false
59
+ }
60
+ ],
61
+ "bos_token": {
62
+ "content": "<s>",
63
+ "lstrip": false,
64
+ "normalized": false,
65
+ "rstrip": false,
66
+ "single_word": false
67
+ },
68
+ "eos_token": {
69
+ "content": "</s>",
70
+ "lstrip": false,
71
+ "normalized": false,
72
+ "rstrip": false,
73
+ "single_word": false
74
+ },
75
+ "pad_token": {
76
+ "content": "</s>",
77
+ "lstrip": false,
78
+ "normalized": false,
79
+ "rstrip": false,
80
+ "single_word": false
81
+ },
82
+ "unk_token": {
83
+ "content": "<unk>",
84
+ "lstrip": false,
85
+ "normalized": false,
86
+ "rstrip": false,
87
+ "single_word": false
88
+ }
89
+ }
Pretrain_8B/tokenization_internlm2.py ADDED
@@ -0,0 +1,235 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ # Copyright (c) The InternLM team and The HuggingFace Inc. team. All rights reserved.
2
+ #
3
+ # This code is based on transformers/src/transformers/models/llama/tokenization_llama.py
4
+ #
5
+ # Licensed under the Apache License, Version 2.0 (the "License");
6
+ # you may not use this file except in compliance with the License.
7
+ # You may obtain a copy of the License at
8
+ #
9
+ # http://www.apache.org/licenses/LICENSE-2.0
10
+ #
11
+ # Unless required by applicable law or agreed to in writing, software
12
+ # distributed under the License is distributed on an "AS IS" BASIS,
13
+ # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
14
+ # See the License for the specific language governing permissions and
15
+ # limitations under the License.
16
+
17
+ """Tokenization classes for InternLM."""
18
+ import os
19
+ from shutil import copyfile
20
+ from typing import Any, Dict, List, Optional, Tuple
21
+
22
+ import sentencepiece as spm
23
+ from transformers.tokenization_utils import PreTrainedTokenizer
24
+ from transformers.utils import logging
25
+
26
+ logger = logging.get_logger(__name__)
27
+
28
+ VOCAB_FILES_NAMES = {'vocab_file': './tokenizer.model'}
29
+
30
+ PRETRAINED_VOCAB_FILES_MAP = {}
31
+
32
+
33
+ # Modified from transformers.model.llama.tokenization_llama.LlamaTokenizer
34
+ class InternLM2Tokenizer(PreTrainedTokenizer):
35
+ """
36
+ Construct a InternLM2 tokenizer. Based on byte-level Byte-Pair-Encoding.
37
+
38
+ Args:
39
+ vocab_file (`str`):
40
+ Path to the vocabulary file.
41
+ """
42
+
43
+ vocab_files_names = VOCAB_FILES_NAMES
44
+ pretrained_vocab_files_map = PRETRAINED_VOCAB_FILES_MAP
45
+ model_input_names = ['input_ids', 'attention_mask']
46
+ _auto_class = 'AutoTokenizer'
47
+
48
+ def __init__(
49
+ self,
50
+ vocab_file,
51
+ unk_token='<unk>',
52
+ bos_token='<s>',
53
+ eos_token='</s>',
54
+ pad_token='</s>',
55
+ sp_model_kwargs: Optional[Dict[str, Any]] = None,
56
+ add_bos_token=True,
57
+ add_eos_token=False,
58
+ decode_with_prefix_space=False,
59
+ clean_up_tokenization_spaces=False,
60
+ **kwargs,
61
+ ):
62
+ self.sp_model_kwargs = {} if sp_model_kwargs is None else sp_model_kwargs
63
+ self.vocab_file = vocab_file
64
+ self.add_bos_token = add_bos_token
65
+ self.add_eos_token = add_eos_token
66
+ self.decode_with_prefix_space = decode_with_prefix_space
67
+ self.sp_model = spm.SentencePieceProcessor(**self.sp_model_kwargs)
68
+ self.sp_model.Load(vocab_file)
69
+ self._no_prefix_space_tokens = None
70
+ super().__init__(
71
+ bos_token=bos_token,
72
+ eos_token=eos_token,
73
+ unk_token=unk_token,
74
+ pad_token=pad_token,
75
+ clean_up_tokenization_spaces=clean_up_tokenization_spaces,
76
+ **kwargs,
77
+ )
78
+
79
+ @property
80
+ def no_prefix_space_tokens(self):
81
+ if self._no_prefix_space_tokens is None:
82
+ vocab = self.convert_ids_to_tokens(list(range(self.vocab_size)))
83
+ self._no_prefix_space_tokens = {i for i, tok in enumerate(vocab) if not tok.startswith('▁')}
84
+ return self._no_prefix_space_tokens
85
+
86
+ @property
87
+ def vocab_size(self):
88
+ """Returns vocab size"""
89
+ return self.sp_model.get_piece_size()
90
+
91
+ @property
92
+ def bos_token_id(self) -> Optional[int]:
93
+ return self.sp_model.bos_id()
94
+
95
+ @property
96
+ def eos_token_id(self) -> Optional[int]:
97
+ return self.sp_model.eos_id()
98
+
99
+ def get_vocab(self):
100
+ """Returns vocab as a dict"""
101
+ vocab = {self.convert_ids_to_tokens(i): i for i in range(self.vocab_size)}
102
+ vocab.update(self.added_tokens_encoder)
103
+ return vocab
104
+
105
+ def _tokenize(self, text):
106
+ """Returns a tokenized string."""
107
+ return self.sp_model.encode(text, out_type=str)
108
+
109
+ def _convert_token_to_id(self, token):
110
+ """Converts a token (str) in an id using the vocab."""
111
+ return self.sp_model.piece_to_id(token)
112
+
113
+ def _convert_id_to_token(self, index):
114
+ """Converts an index (integer) in a token (str) using the vocab."""
115
+ token = self.sp_model.IdToPiece(index)
116
+ return token
117
+
118
+ def _maybe_add_prefix_space(self, tokens, decoded):
119
+ if tokens and tokens[0] not in self.no_prefix_space_tokens:
120
+ return ' ' + decoded
121
+ else:
122
+ return decoded
123
+
124
+ def convert_tokens_to_string(self, tokens):
125
+ """Converts a sequence of tokens (string) in a single string."""
126
+ current_sub_tokens = []
127
+ out_string = ''
128
+ prev_is_special = False
129
+ for token in tokens:
130
+ # make sure that special tokens are not decoded using sentencepiece model
131
+ if token in self.all_special_tokens:
132
+ if not prev_is_special:
133
+ out_string += ' '
134
+ out_string += self.sp_model.decode(current_sub_tokens) + token
135
+ prev_is_special = True
136
+ current_sub_tokens = []
137
+ else:
138
+ current_sub_tokens.append(token)
139
+ prev_is_special = False
140
+ out_string += self.sp_model.decode(current_sub_tokens)
141
+ out_string = self.clean_up_tokenization(out_string)
142
+ out_string = self._maybe_add_prefix_space(tokens=tokens, decoded=out_string)
143
+ return out_string[1:]
144
+
145
+ def save_vocabulary(self, save_directory, filename_prefix: Optional[str] = None) -> Tuple[str]:
146
+ """
147
+ Save the vocabulary and special tokens file to a directory.
148
+
149
+ Args:
150
+ save_directory (`str`):
151
+ The directory in which to save the vocabulary.
152
+
153
+ Returns:
154
+ `Tuple(str)`: Paths to the files saved.
155
+ """
156
+ if not os.path.isdir(save_directory):
157
+ logger.error(f'Vocabulary path ({save_directory}) should be a directory')
158
+ return
159
+ out_vocab_file = os.path.join(
160
+ save_directory, (filename_prefix + '-' if filename_prefix else '') + VOCAB_FILES_NAMES['vocab_file']
161
+ )
162
+
163
+ if os.path.abspath(self.vocab_file) != os.path.abspath(out_vocab_file) and os.path.isfile(self.vocab_file):
164
+ copyfile(self.vocab_file, out_vocab_file)
165
+ elif not os.path.isfile(self.vocab_file):
166
+ with open(out_vocab_file, 'wb') as fi:
167
+ content_spiece_model = self.sp_model.serialized_model_proto()
168
+ fi.write(content_spiece_model)
169
+
170
+ return (out_vocab_file,)
171
+
172
+ def build_inputs_with_special_tokens(self, token_ids_0, token_ids_1=None):
173
+ if self.add_bos_token:
174
+ bos_token_ids = [self.bos_token_id]
175
+ else:
176
+ bos_token_ids = []
177
+
178
+ output = bos_token_ids + token_ids_0
179
+
180
+ if token_ids_1 is not None:
181
+ output = output + token_ids_1
182
+
183
+ if self.add_eos_token:
184
+ output = output + [self.eos_token_id]
185
+
186
+ return output
187
+
188
+ def get_special_tokens_mask(
189
+ self, token_ids_0: List[int], token_ids_1: Optional[List[int]] = None, already_has_special_tokens: bool = False
190
+ ) -> List[int]:
191
+ """
192
+ Retrieve sequence ids from a token list that has no special tokens added. This method is called when adding
193
+ special tokens using the tokenizer `prepare_for_model` method.
194
+
195
+ Args:
196
+ token_ids_0 (`List[int]`):
197
+ List of IDs.
198
+ token_ids_1 (`List[int]`, *optional*):
199
+ Optional second list of IDs for sequence pairs.
200
+ already_has_special_tokens (`bool`, *optional*, defaults to `False`):
201
+ Whether or not the token list is already formatted with special tokens for the model.
202
+
203
+ Returns:
204
+ `List[int]`: A list of integers in the range [0, 1]: 1 for a special token, 0 for a sequence token.
205
+ """
206
+ if already_has_special_tokens:
207
+ return super().get_special_tokens_mask(
208
+ token_ids_0=token_ids_0, token_ids_1=token_ids_1, already_has_special_tokens=True
209
+ )
210
+
211
+ if token_ids_1 is None:
212
+ return [1] + ([0] * len(token_ids_0)) + [1]
213
+ return [1] + ([0] * len(token_ids_0)) + [1, 1] + ([0] * len(token_ids_1)) + [1]
214
+
215
+ def create_token_type_ids_from_sequences(
216
+ self, token_ids_0: List[int], token_ids_1: Optional[List[int]] = None
217
+ ) -> List[int]:
218
+ """
219
+ Create a mask from the two sequences passed to be used in a sequence-pair classification task. T5 does not make
220
+ use of token type ids, therefore a list of zeros is returned.
221
+
222
+ Args:
223
+ token_ids_0 (`List[int]`):
224
+ List of IDs.
225
+ token_ids_1 (`List[int]`, *optional*):
226
+ Optional second list of IDs for sequence pairs.
227
+
228
+ Returns:
229
+ `List[int]`: List of zeros.
230
+ """
231
+ eos = [self.eos_token_id]
232
+
233
+ if token_ids_1 is None:
234
+ return len(token_ids_0 + eos) * [0]
235
+ return len(token_ids_0 + eos + token_ids_1 + eos) * [0]
Pretrain_8B/tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f868398fc4e05ee1e8aeba95ddf18ddcc45b8bce55d5093bead5bbf80429b48b
3
+ size 1477754
Pretrain_8B/tokenizer_config.json ADDED
@@ -0,0 +1,233 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "<unk>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "1": {
12
+ "content": "<s>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "</s>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "92538": {
28
+ "content": "<|plugin|>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "92539": {
36
+ "content": "<|interpreter|>",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ },
43
+ "92540": {
44
+ "content": "<|action_end|>",
45
+ "lstrip": false,
46
+ "normalized": false,
47
+ "rstrip": false,
48
+ "single_word": false,
49
+ "special": true
50
+ },
51
+ "92541": {
52
+ "content": "<|action_start|>",
53
+ "lstrip": false,
54
+ "normalized": false,
55
+ "rstrip": false,
56
+ "single_word": false,
57
+ "special": true
58
+ },
59
+ "92542": {
60
+ "content": "<|im_end|>",
61
+ "lstrip": false,
62
+ "normalized": false,
63
+ "rstrip": false,
64
+ "single_word": false,
65
+ "special": true
66
+ },
67
+ "92543": {
68
+ "content": "<|im_start|>",
69
+ "lstrip": false,
70
+ "normalized": false,
71
+ "rstrip": false,
72
+ "single_word": false,
73
+ "special": true
74
+ },
75
+ "92544": {
76
+ "content": "<img>",
77
+ "lstrip": false,
78
+ "normalized": false,
79
+ "rstrip": false,
80
+ "single_word": false,
81
+ "special": true
82
+ },
83
+ "92545": {
84
+ "content": "</img>",
85
+ "lstrip": false,
86
+ "normalized": false,
87
+ "rstrip": false,
88
+ "single_word": false,
89
+ "special": true
90
+ },
91
+ "92546": {
92
+ "content": "<IMG_CONTEXT>",
93
+ "lstrip": false,
94
+ "normalized": false,
95
+ "rstrip": false,
96
+ "single_word": false,
97
+ "special": true
98
+ },
99
+ "92547": {
100
+ "content": "<quad>",
101
+ "lstrip": false,
102
+ "normalized": false,
103
+ "rstrip": false,
104
+ "single_word": false,
105
+ "special": true
106
+ },
107
+ "92548": {
108
+ "content": "</quad>",
109
+ "lstrip": false,
110
+ "normalized": false,
111
+ "rstrip": false,
112
+ "single_word": false,
113
+ "special": true
114
+ },
115
+ "92549": {
116
+ "content": "<ref>",
117
+ "lstrip": false,
118
+ "normalized": false,
119
+ "rstrip": false,
120
+ "single_word": false,
121
+ "special": true
122
+ },
123
+ "92550": {
124
+ "content": "</ref>",
125
+ "lstrip": false,
126
+ "normalized": false,
127
+ "rstrip": false,
128
+ "single_word": false,
129
+ "special": true
130
+ },
131
+ "92551": {
132
+ "content": "<box>",
133
+ "lstrip": false,
134
+ "normalized": false,
135
+ "rstrip": false,
136
+ "single_word": false,
137
+ "special": true
138
+ },
139
+ "92552": {
140
+ "content": "</box>",
141
+ "lstrip": false,
142
+ "normalized": false,
143
+ "rstrip": false,
144
+ "single_word": false,
145
+ "special": true
146
+ },
147
+ "92553": {
148
+ "content": "<bbox_2d>",
149
+ "lstrip": false,
150
+ "normalized": false,
151
+ "rstrip": false,
152
+ "single_word": false,
153
+ "special": true
154
+ },
155
+ "92554": {
156
+ "content": "<bbox_3d>",
157
+ "lstrip": false,
158
+ "normalized": false,
159
+ "rstrip": false,
160
+ "single_word": false,
161
+ "special": true
162
+ },
163
+ "92555": {
164
+ "content": "<bbox_2d_in>",
165
+ "lstrip": false,
166
+ "normalized": false,
167
+ "rstrip": false,
168
+ "single_word": false,
169
+ "special": true
170
+ },
171
+ "92556": {
172
+ "content": "<query>",
173
+ "lstrip": false,
174
+ "normalized": false,
175
+ "rstrip": false,
176
+ "single_word": false,
177
+ "special": true
178
+ },
179
+ "92557": {
180
+ "content": "<box_3d>",
181
+ "lstrip": false,
182
+ "normalized": false,
183
+ "rstrip": false,
184
+ "single_word": false,
185
+ "special": true
186
+ },
187
+ "92558": {
188
+ "content": "</box_3d>",
189
+ "lstrip": false,
190
+ "normalized": false,
191
+ "rstrip": false,
192
+ "single_word": false,
193
+ "special": true
194
+ }
195
+ },
196
+ "additional_special_tokens": [
197
+ "<|im_start|>",
198
+ "<|im_end|>",
199
+ "<|action_start|>",
200
+ "<|action_end|>",
201
+ "<|interpreter|>",
202
+ "<|plugin|>",
203
+ "<img>",
204
+ "</img>",
205
+ "<IMG_CONTEXT>",
206
+ "<quad>",
207
+ "</quad>",
208
+ "<ref>",
209
+ "</ref>",
210
+ "<box>",
211
+ "</box>",
212
+ "<bbox_2d>",
213
+ "<bbox_3d>",
214
+ "<bbox_2d_in>",
215
+ "<query>",
216
+ "<box_3d>",
217
+ "</box_3d>"
218
+ ],
219
+ "auto_map": {
220
+ "AutoTokenizer": [
221
+ "tokenization_internlm2.InternLM2Tokenizer",
222
+ null
223
+ ]
224
+ },
225
+ "bos_token": "<s>",
226
+ "chat_template": "{{ bos_token }}{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
227
+ "clean_up_tokenization_spaces": false,
228
+ "eos_token": "</s>",
229
+ "model_max_length": 4096,
230
+ "pad_token": "</s>",
231
+ "tokenizer_class": "InternLM2Tokenizer",
232
+ "unk_token": "<unk>"
233
+ }
Pretrain_8B/train_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 1.0,
3
+ "train_loss": 1.1657107080552576,
4
+ "train_runtime": 16008.6151,
5
+ "train_samples": 194308,
6
+ "train_samples_per_second": 12.138,
7
+ "train_steps_per_second": 0.047
8
+ }
Pretrain_8B/trainer_state.json ADDED
@@ -0,0 +1,4584 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 0.9999176615891313,
5
+ "eval_steps": 500,
6
+ "global_step": 759,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.0,
13
+ "learning_rate": 8.695652173913044e-07,
14
+ "loss": 1.7323,
15
+ "step": 1
16
+ },
17
+ {
18
+ "epoch": 0.0,
19
+ "learning_rate": 1.7391304347826088e-06,
20
+ "loss": 1.7879,
21
+ "step": 2
22
+ },
23
+ {
24
+ "epoch": 0.0,
25
+ "learning_rate": 2.6086956521739132e-06,
26
+ "loss": 1.7641,
27
+ "step": 3
28
+ },
29
+ {
30
+ "epoch": 0.01,
31
+ "learning_rate": 3.4782608695652175e-06,
32
+ "loss": 1.785,
33
+ "step": 4
34
+ },
35
+ {
36
+ "epoch": 0.01,
37
+ "learning_rate": 4.347826086956522e-06,
38
+ "loss": 1.765,
39
+ "step": 5
40
+ },
41
+ {
42
+ "epoch": 0.01,
43
+ "learning_rate": 5.2173913043478265e-06,
44
+ "loss": 1.7404,
45
+ "step": 6
46
+ },
47
+ {
48
+ "epoch": 0.01,
49
+ "learning_rate": 6.086956521739132e-06,
50
+ "loss": 1.7493,
51
+ "step": 7
52
+ },
53
+ {
54
+ "epoch": 0.01,
55
+ "learning_rate": 6.956521739130435e-06,
56
+ "loss": 1.7229,
57
+ "step": 8
58
+ },
59
+ {
60
+ "epoch": 0.01,
61
+ "learning_rate": 7.82608695652174e-06,
62
+ "loss": 1.6795,
63
+ "step": 9
64
+ },
65
+ {
66
+ "epoch": 0.01,
67
+ "learning_rate": 8.695652173913044e-06,
68
+ "loss": 1.6157,
69
+ "step": 10
70
+ },
71
+ {
72
+ "epoch": 0.01,
73
+ "learning_rate": 9.565217391304349e-06,
74
+ "loss": 1.5726,
75
+ "step": 11
76
+ },
77
+ {
78
+ "epoch": 0.02,
79
+ "learning_rate": 1.0434782608695653e-05,
80
+ "loss": 1.568,
81
+ "step": 12
82
+ },
83
+ {
84
+ "epoch": 0.02,
85
+ "learning_rate": 1.1304347826086957e-05,
86
+ "loss": 1.5764,
87
+ "step": 13
88
+ },
89
+ {
90
+ "epoch": 0.02,
91
+ "learning_rate": 1.2173913043478263e-05,
92
+ "loss": 1.5187,
93
+ "step": 14
94
+ },
95
+ {
96
+ "epoch": 0.02,
97
+ "learning_rate": 1.3043478260869566e-05,
98
+ "loss": 1.5299,
99
+ "step": 15
100
+ },
101
+ {
102
+ "epoch": 0.02,
103
+ "learning_rate": 1.391304347826087e-05,
104
+ "loss": 1.5024,
105
+ "step": 16
106
+ },
107
+ {
108
+ "epoch": 0.02,
109
+ "learning_rate": 1.4782608695652174e-05,
110
+ "loss": 1.4203,
111
+ "step": 17
112
+ },
113
+ {
114
+ "epoch": 0.02,
115
+ "learning_rate": 1.565217391304348e-05,
116
+ "loss": 1.493,
117
+ "step": 18
118
+ },
119
+ {
120
+ "epoch": 0.03,
121
+ "learning_rate": 1.6521739130434785e-05,
122
+ "loss": 1.4777,
123
+ "step": 19
124
+ },
125
+ {
126
+ "epoch": 0.03,
127
+ "learning_rate": 1.739130434782609e-05,
128
+ "loss": 1.4429,
129
+ "step": 20
130
+ },
131
+ {
132
+ "epoch": 0.03,
133
+ "learning_rate": 1.8260869565217393e-05,
134
+ "loss": 1.4383,
135
+ "step": 21
136
+ },
137
+ {
138
+ "epoch": 0.03,
139
+ "learning_rate": 1.9130434782608697e-05,
140
+ "loss": 1.4382,
141
+ "step": 22
142
+ },
143
+ {
144
+ "epoch": 0.03,
145
+ "learning_rate": 2e-05,
146
+ "loss": 1.4615,
147
+ "step": 23
148
+ },
149
+ {
150
+ "epoch": 0.03,
151
+ "learning_rate": 1.999990890103106e-05,
152
+ "loss": 1.4381,
153
+ "step": 24
154
+ },
155
+ {
156
+ "epoch": 0.03,
157
+ "learning_rate": 1.9999635605784042e-05,
158
+ "loss": 1.4201,
159
+ "step": 25
160
+ },
161
+ {
162
+ "epoch": 0.03,
163
+ "learning_rate": 1.9999180119238327e-05,
164
+ "loss": 1.4226,
165
+ "step": 26
166
+ },
167
+ {
168
+ "epoch": 0.04,
169
+ "learning_rate": 1.9998542449692794e-05,
170
+ "loss": 1.3955,
171
+ "step": 27
172
+ },
173
+ {
174
+ "epoch": 0.04,
175
+ "learning_rate": 1.999772260876564e-05,
176
+ "loss": 1.3743,
177
+ "step": 28
178
+ },
179
+ {
180
+ "epoch": 0.04,
181
+ "learning_rate": 1.99967206113942e-05,
182
+ "loss": 1.4049,
183
+ "step": 29
184
+ },
185
+ {
186
+ "epoch": 0.04,
187
+ "learning_rate": 1.9995536475834667e-05,
188
+ "loss": 1.3434,
189
+ "step": 30
190
+ },
191
+ {
192
+ "epoch": 0.04,
193
+ "learning_rate": 1.999417022366174e-05,
194
+ "loss": 1.3606,
195
+ "step": 31
196
+ },
197
+ {
198
+ "epoch": 0.04,
199
+ "learning_rate": 1.9992621879768256e-05,
200
+ "loss": 1.3521,
201
+ "step": 32
202
+ },
203
+ {
204
+ "epoch": 0.04,
205
+ "learning_rate": 1.999089147236472e-05,
206
+ "loss": 1.3454,
207
+ "step": 33
208
+ },
209
+ {
210
+ "epoch": 0.04,
211
+ "learning_rate": 1.998897903297879e-05,
212
+ "loss": 1.353,
213
+ "step": 34
214
+ },
215
+ {
216
+ "epoch": 0.05,
217
+ "learning_rate": 1.998688459645473e-05,
218
+ "loss": 1.333,
219
+ "step": 35
220
+ },
221
+ {
222
+ "epoch": 0.05,
223
+ "learning_rate": 1.9984608200952736e-05,
224
+ "loss": 1.3249,
225
+ "step": 36
226
+ },
227
+ {
228
+ "epoch": 0.05,
229
+ "learning_rate": 1.9982149887948264e-05,
230
+ "loss": 1.3181,
231
+ "step": 37
232
+ },
233
+ {
234
+ "epoch": 0.05,
235
+ "learning_rate": 1.997950970223127e-05,
236
+ "loss": 1.3081,
237
+ "step": 38
238
+ },
239
+ {
240
+ "epoch": 0.05,
241
+ "learning_rate": 1.9976687691905394e-05,
242
+ "loss": 1.3071,
243
+ "step": 39
244
+ },
245
+ {
246
+ "epoch": 0.05,
247
+ "learning_rate": 1.997368390838708e-05,
248
+ "loss": 1.3167,
249
+ "step": 40
250
+ },
251
+ {
252
+ "epoch": 0.05,
253
+ "learning_rate": 1.997049840640465e-05,
254
+ "loss": 1.3087,
255
+ "step": 41
256
+ },
257
+ {
258
+ "epoch": 0.06,
259
+ "learning_rate": 1.996713124399729e-05,
260
+ "loss": 1.307,
261
+ "step": 42
262
+ },
263
+ {
264
+ "epoch": 0.06,
265
+ "learning_rate": 1.9963582482514003e-05,
266
+ "loss": 1.3097,
267
+ "step": 43
268
+ },
269
+ {
270
+ "epoch": 0.06,
271
+ "learning_rate": 1.9959852186612492e-05,
272
+ "loss": 1.3383,
273
+ "step": 44
274
+ },
275
+ {
276
+ "epoch": 0.06,
277
+ "learning_rate": 1.995594042425798e-05,
278
+ "loss": 1.3046,
279
+ "step": 45
280
+ },
281
+ {
282
+ "epoch": 0.06,
283
+ "learning_rate": 1.995184726672197e-05,
284
+ "loss": 1.2716,
285
+ "step": 46
286
+ },
287
+ {
288
+ "epoch": 0.06,
289
+ "learning_rate": 1.994757278858095e-05,
290
+ "loss": 1.2744,
291
+ "step": 47
292
+ },
293
+ {
294
+ "epoch": 0.06,
295
+ "learning_rate": 1.994311706771503e-05,
296
+ "loss": 1.305,
297
+ "step": 48
298
+ },
299
+ {
300
+ "epoch": 0.06,
301
+ "learning_rate": 1.993848018530652e-05,
302
+ "loss": 1.2723,
303
+ "step": 49
304
+ },
305
+ {
306
+ "epoch": 0.07,
307
+ "learning_rate": 1.993366222583847e-05,
308
+ "loss": 1.2477,
309
+ "step": 50
310
+ },
311
+ {
312
+ "epoch": 0.07,
313
+ "learning_rate": 1.99286632770931e-05,
314
+ "loss": 1.2946,
315
+ "step": 51
316
+ },
317
+ {
318
+ "epoch": 0.07,
319
+ "learning_rate": 1.992348343015023e-05,
320
+ "loss": 1.2611,
321
+ "step": 52
322
+ },
323
+ {
324
+ "epoch": 0.07,
325
+ "learning_rate": 1.99181227793856e-05,
326
+ "loss": 1.27,
327
+ "step": 53
328
+ },
329
+ {
330
+ "epoch": 0.07,
331
+ "learning_rate": 1.991258142246917e-05,
332
+ "loss": 1.2493,
333
+ "step": 54
334
+ },
335
+ {
336
+ "epoch": 0.07,
337
+ "learning_rate": 1.9906859460363307e-05,
338
+ "loss": 1.2631,
339
+ "step": 55
340
+ },
341
+ {
342
+ "epoch": 0.07,
343
+ "learning_rate": 1.990095699732099e-05,
344
+ "loss": 1.292,
345
+ "step": 56
346
+ },
347
+ {
348
+ "epoch": 0.08,
349
+ "learning_rate": 1.9894874140883877e-05,
350
+ "loss": 1.2596,
351
+ "step": 57
352
+ },
353
+ {
354
+ "epoch": 0.08,
355
+ "learning_rate": 1.9888611001880357e-05,
356
+ "loss": 1.2619,
357
+ "step": 58
358
+ },
359
+ {
360
+ "epoch": 0.08,
361
+ "learning_rate": 1.988216769442353e-05,
362
+ "loss": 1.2367,
363
+ "step": 59
364
+ },
365
+ {
366
+ "epoch": 0.08,
367
+ "learning_rate": 1.987554433590913e-05,
368
+ "loss": 1.235,
369
+ "step": 60
370
+ },
371
+ {
372
+ "epoch": 0.08,
373
+ "learning_rate": 1.9868741047013382e-05,
374
+ "loss": 1.278,
375
+ "step": 61
376
+ },
377
+ {
378
+ "epoch": 0.08,
379
+ "learning_rate": 1.9861757951690813e-05,
380
+ "loss": 1.2206,
381
+ "step": 62
382
+ },
383
+ {
384
+ "epoch": 0.08,
385
+ "learning_rate": 1.9854595177171968e-05,
386
+ "loss": 1.2533,
387
+ "step": 63
388
+ },
389
+ {
390
+ "epoch": 0.08,
391
+ "learning_rate": 1.9847252853961136e-05,
392
+ "loss": 1.2421,
393
+ "step": 64
394
+ },
395
+ {
396
+ "epoch": 0.09,
397
+ "learning_rate": 1.983973111583392e-05,
398
+ "loss": 1.2448,
399
+ "step": 65
400
+ },
401
+ {
402
+ "epoch": 0.09,
403
+ "learning_rate": 1.983203009983484e-05,
404
+ "loss": 1.2354,
405
+ "step": 66
406
+ },
407
+ {
408
+ "epoch": 0.09,
409
+ "learning_rate": 1.9824149946274827e-05,
410
+ "loss": 1.2356,
411
+ "step": 67
412
+ },
413
+ {
414
+ "epoch": 0.09,
415
+ "learning_rate": 1.9816090798728648e-05,
416
+ "loss": 1.24,
417
+ "step": 68
418
+ },
419
+ {
420
+ "epoch": 0.09,
421
+ "learning_rate": 1.9807852804032306e-05,
422
+ "loss": 1.2453,
423
+ "step": 69
424
+ },
425
+ {
426
+ "epoch": 0.09,
427
+ "learning_rate": 1.9799436112280374e-05,
428
+ "loss": 1.2375,
429
+ "step": 70
430
+ },
431
+ {
432
+ "epoch": 0.09,
433
+ "learning_rate": 1.979084087682323e-05,
434
+ "loss": 1.2368,
435
+ "step": 71
436
+ },
437
+ {
438
+ "epoch": 0.09,
439
+ "learning_rate": 1.97820672542643e-05,
440
+ "loss": 1.2212,
441
+ "step": 72
442
+ },
443
+ {
444
+ "epoch": 0.1,
445
+ "learning_rate": 1.9773115404457175e-05,
446
+ "loss": 1.2444,
447
+ "step": 73
448
+ },
449
+ {
450
+ "epoch": 0.1,
451
+ "learning_rate": 1.9763985490502714e-05,
452
+ "loss": 1.266,
453
+ "step": 74
454
+ },
455
+ {
456
+ "epoch": 0.1,
457
+ "learning_rate": 1.9754677678746064e-05,
458
+ "loss": 1.2457,
459
+ "step": 75
460
+ },
461
+ {
462
+ "epoch": 0.1,
463
+ "learning_rate": 1.9745192138773633e-05,
464
+ "loss": 1.2506,
465
+ "step": 76
466
+ },
467
+ {
468
+ "epoch": 0.1,
469
+ "learning_rate": 1.9735529043410012e-05,
470
+ "loss": 1.2191,
471
+ "step": 77
472
+ },
473
+ {
474
+ "epoch": 0.1,
475
+ "learning_rate": 1.97256885687148e-05,
476
+ "loss": 1.2016,
477
+ "step": 78
478
+ },
479
+ {
480
+ "epoch": 0.1,
481
+ "learning_rate": 1.9715670893979416e-05,
482
+ "loss": 1.2124,
483
+ "step": 79
484
+ },
485
+ {
486
+ "epoch": 0.11,
487
+ "learning_rate": 1.970547620172383e-05,
488
+ "loss": 1.2324,
489
+ "step": 80
490
+ },
491
+ {
492
+ "epoch": 0.11,
493
+ "learning_rate": 1.9695104677693234e-05,
494
+ "loss": 1.2053,
495
+ "step": 81
496
+ },
497
+ {
498
+ "epoch": 0.11,
499
+ "learning_rate": 1.9684556510854655e-05,
500
+ "loss": 1.2081,
501
+ "step": 82
502
+ },
503
+ {
504
+ "epoch": 0.11,
505
+ "learning_rate": 1.967383189339352e-05,
506
+ "loss": 1.2085,
507
+ "step": 83
508
+ },
509
+ {
510
+ "epoch": 0.11,
511
+ "learning_rate": 1.9662931020710138e-05,
512
+ "loss": 1.2013,
513
+ "step": 84
514
+ },
515
+ {
516
+ "epoch": 0.11,
517
+ "learning_rate": 1.9651854091416175e-05,
518
+ "loss": 1.2094,
519
+ "step": 85
520
+ },
521
+ {
522
+ "epoch": 0.11,
523
+ "learning_rate": 1.964060130733099e-05,
524
+ "loss": 1.1864,
525
+ "step": 86
526
+ },
527
+ {
528
+ "epoch": 0.11,
529
+ "learning_rate": 1.9629172873477995e-05,
530
+ "loss": 1.1907,
531
+ "step": 87
532
+ },
533
+ {
534
+ "epoch": 0.12,
535
+ "learning_rate": 1.9617568998080893e-05,
536
+ "loss": 1.2204,
537
+ "step": 88
538
+ },
539
+ {
540
+ "epoch": 0.12,
541
+ "learning_rate": 1.9605789892559902e-05,
542
+ "loss": 1.1799,
543
+ "step": 89
544
+ },
545
+ {
546
+ "epoch": 0.12,
547
+ "learning_rate": 1.9593835771527893e-05,
548
+ "loss": 1.2545,
549
+ "step": 90
550
+ },
551
+ {
552
+ "epoch": 0.12,
553
+ "learning_rate": 1.9581706852786492e-05,
554
+ "loss": 1.1896,
555
+ "step": 91
556
+ },
557
+ {
558
+ "epoch": 0.12,
559
+ "learning_rate": 1.956940335732209e-05,
560
+ "loss": 1.2181,
561
+ "step": 92
562
+ },
563
+ {
564
+ "epoch": 0.12,
565
+ "learning_rate": 1.9556925509301844e-05,
566
+ "loss": 1.2182,
567
+ "step": 93
568
+ },
569
+ {
570
+ "epoch": 0.12,
571
+ "learning_rate": 1.9544273536069573e-05,
572
+ "loss": 1.2016,
573
+ "step": 94
574
+ },
575
+ {
576
+ "epoch": 0.13,
577
+ "learning_rate": 1.953144766814161e-05,
578
+ "loss": 1.2068,
579
+ "step": 95
580
+ },
581
+ {
582
+ "epoch": 0.13,
583
+ "learning_rate": 1.9518448139202632e-05,
584
+ "loss": 1.1986,
585
+ "step": 96
586
+ },
587
+ {
588
+ "epoch": 0.13,
589
+ "learning_rate": 1.9505275186101378e-05,
590
+ "loss": 1.2009,
591
+ "step": 97
592
+ },
593
+ {
594
+ "epoch": 0.13,
595
+ "learning_rate": 1.9491929048846328e-05,
596
+ "loss": 1.2248,
597
+ "step": 98
598
+ },
599
+ {
600
+ "epoch": 0.13,
601
+ "learning_rate": 1.947840997060136e-05,
602
+ "loss": 1.1822,
603
+ "step": 99
604
+ },
605
+ {
606
+ "epoch": 0.13,
607
+ "learning_rate": 1.9464718197681284e-05,
608
+ "loss": 1.176,
609
+ "step": 100
610
+ },
611
+ {
612
+ "epoch": 0.13,
613
+ "learning_rate": 1.9450853979547384e-05,
614
+ "loss": 1.1743,
615
+ "step": 101
616
+ },
617
+ {
618
+ "epoch": 0.13,
619
+ "learning_rate": 1.9436817568802854e-05,
620
+ "loss": 1.1887,
621
+ "step": 102
622
+ },
623
+ {
624
+ "epoch": 0.14,
625
+ "learning_rate": 1.9422609221188208e-05,
626
+ "loss": 1.1927,
627
+ "step": 103
628
+ },
629
+ {
630
+ "epoch": 0.14,
631
+ "learning_rate": 1.94082291955766e-05,
632
+ "loss": 1.1648,
633
+ "step": 104
634
+ },
635
+ {
636
+ "epoch": 0.14,
637
+ "learning_rate": 1.9393677753969137e-05,
638
+ "loss": 1.226,
639
+ "step": 105
640
+ },
641
+ {
642
+ "epoch": 0.14,
643
+ "learning_rate": 1.9378955161490086e-05,
644
+ "loss": 1.1833,
645
+ "step": 106
646
+ },
647
+ {
648
+ "epoch": 0.14,
649
+ "learning_rate": 1.9364061686382042e-05,
650
+ "loss": 1.2221,
651
+ "step": 107
652
+ },
653
+ {
654
+ "epoch": 0.14,
655
+ "learning_rate": 1.9348997600001052e-05,
656
+ "loss": 1.2068,
657
+ "step": 108
658
+ },
659
+ {
660
+ "epoch": 0.14,
661
+ "learning_rate": 1.9333763176811663e-05,
662
+ "loss": 1.2105,
663
+ "step": 109
664
+ },
665
+ {
666
+ "epoch": 0.14,
667
+ "learning_rate": 1.9318358694381926e-05,
668
+ "loss": 1.2189,
669
+ "step": 110
670
+ },
671
+ {
672
+ "epoch": 0.15,
673
+ "learning_rate": 1.9302784433378333e-05,
674
+ "loss": 1.1758,
675
+ "step": 111
676
+ },
677
+ {
678
+ "epoch": 0.15,
679
+ "learning_rate": 1.928704067756071e-05,
680
+ "loss": 1.1968,
681
+ "step": 112
682
+ },
683
+ {
684
+ "epoch": 0.15,
685
+ "learning_rate": 1.9271127713777033e-05,
686
+ "loss": 1.192,
687
+ "step": 113
688
+ },
689
+ {
690
+ "epoch": 0.15,
691
+ "learning_rate": 1.925504583195823e-05,
692
+ "loss": 1.1964,
693
+ "step": 114
694
+ },
695
+ {
696
+ "epoch": 0.15,
697
+ "learning_rate": 1.9238795325112867e-05,
698
+ "loss": 1.1578,
699
+ "step": 115
700
+ },
701
+ {
702
+ "epoch": 0.15,
703
+ "learning_rate": 1.922237648932183e-05,
704
+ "loss": 1.2211,
705
+ "step": 116
706
+ },
707
+ {
708
+ "epoch": 0.15,
709
+ "learning_rate": 1.9205789623732923e-05,
710
+ "loss": 1.2112,
711
+ "step": 117
712
+ },
713
+ {
714
+ "epoch": 0.16,
715
+ "learning_rate": 1.918903503055541e-05,
716
+ "loss": 1.2374,
717
+ "step": 118
718
+ },
719
+ {
720
+ "epoch": 0.16,
721
+ "learning_rate": 1.917211301505453e-05,
722
+ "loss": 1.2267,
723
+ "step": 119
724
+ },
725
+ {
726
+ "epoch": 0.16,
727
+ "learning_rate": 1.9155023885545914e-05,
728
+ "loss": 1.1908,
729
+ "step": 120
730
+ },
731
+ {
732
+ "epoch": 0.16,
733
+ "learning_rate": 1.913776795338998e-05,
734
+ "loss": 1.1793,
735
+ "step": 121
736
+ },
737
+ {
738
+ "epoch": 0.16,
739
+ "learning_rate": 1.9120345532986243e-05,
740
+ "loss": 1.2087,
741
+ "step": 122
742
+ },
743
+ {
744
+ "epoch": 0.16,
745
+ "learning_rate": 1.9102756941767625e-05,
746
+ "loss": 1.1735,
747
+ "step": 123
748
+ },
749
+ {
750
+ "epoch": 0.16,
751
+ "learning_rate": 1.908500250019462e-05,
752
+ "loss": 1.2115,
753
+ "step": 124
754
+ },
755
+ {
756
+ "epoch": 0.16,
757
+ "learning_rate": 1.9067082531749496e-05,
758
+ "loss": 1.1803,
759
+ "step": 125
760
+ },
761
+ {
762
+ "epoch": 0.17,
763
+ "learning_rate": 1.9048997362930384e-05,
764
+ "loss": 1.1689,
765
+ "step": 126
766
+ },
767
+ {
768
+ "epoch": 0.17,
769
+ "learning_rate": 1.903074732324533e-05,
770
+ "loss": 1.1948,
771
+ "step": 127
772
+ },
773
+ {
774
+ "epoch": 0.17,
775
+ "learning_rate": 1.901233274520629e-05,
776
+ "loss": 1.1627,
777
+ "step": 128
778
+ },
779
+ {
780
+ "epoch": 0.17,
781
+ "learning_rate": 1.8993753964323086e-05,
782
+ "loss": 1.1608,
783
+ "step": 129
784
+ },
785
+ {
786
+ "epoch": 0.17,
787
+ "learning_rate": 1.8975011319097264e-05,
788
+ "loss": 1.2027,
789
+ "step": 130
790
+ },
791
+ {
792
+ "epoch": 0.17,
793
+ "learning_rate": 1.8956105151015966e-05,
794
+ "loss": 1.1847,
795
+ "step": 131
796
+ },
797
+ {
798
+ "epoch": 0.17,
799
+ "learning_rate": 1.893703580454567e-05,
800
+ "loss": 1.142,
801
+ "step": 132
802
+ },
803
+ {
804
+ "epoch": 0.18,
805
+ "learning_rate": 1.891780362712594e-05,
806
+ "loss": 1.178,
807
+ "step": 133
808
+ },
809
+ {
810
+ "epoch": 0.18,
811
+ "learning_rate": 1.8898408969163078e-05,
812
+ "loss": 1.1915,
813
+ "step": 134
814
+ },
815
+ {
816
+ "epoch": 0.18,
817
+ "learning_rate": 1.8878852184023754e-05,
818
+ "loss": 1.1788,
819
+ "step": 135
820
+ },
821
+ {
822
+ "epoch": 0.18,
823
+ "learning_rate": 1.8859133628028564e-05,
824
+ "loss": 1.2118,
825
+ "step": 136
826
+ },
827
+ {
828
+ "epoch": 0.18,
829
+ "learning_rate": 1.8839253660445523e-05,
830
+ "loss": 1.1451,
831
+ "step": 137
832
+ },
833
+ {
834
+ "epoch": 0.18,
835
+ "learning_rate": 1.881921264348355e-05,
836
+ "loss": 1.1976,
837
+ "step": 138
838
+ },
839
+ {
840
+ "epoch": 0.18,
841
+ "learning_rate": 1.879901094228584e-05,
842
+ "loss": 1.1665,
843
+ "step": 139
844
+ },
845
+ {
846
+ "epoch": 0.18,
847
+ "learning_rate": 1.8778648924923222e-05,
848
+ "loss": 1.1771,
849
+ "step": 140
850
+ },
851
+ {
852
+ "epoch": 0.19,
853
+ "learning_rate": 1.875812696238745e-05,
854
+ "loss": 1.2061,
855
+ "step": 141
856
+ },
857
+ {
858
+ "epoch": 0.19,
859
+ "learning_rate": 1.8737445428584456e-05,
860
+ "loss": 1.1932,
861
+ "step": 142
862
+ },
863
+ {
864
+ "epoch": 0.19,
865
+ "learning_rate": 1.8716604700327516e-05,
866
+ "loss": 1.1854,
867
+ "step": 143
868
+ },
869
+ {
870
+ "epoch": 0.19,
871
+ "learning_rate": 1.8695605157330398e-05,
872
+ "loss": 1.2046,
873
+ "step": 144
874
+ },
875
+ {
876
+ "epoch": 0.19,
877
+ "learning_rate": 1.8674447182200457e-05,
878
+ "loss": 1.16,
879
+ "step": 145
880
+ },
881
+ {
882
+ "epoch": 0.19,
883
+ "learning_rate": 1.8653131160431622e-05,
884
+ "loss": 1.1939,
885
+ "step": 146
886
+ },
887
+ {
888
+ "epoch": 0.19,
889
+ "learning_rate": 1.863165748039743e-05,
890
+ "loss": 1.219,
891
+ "step": 147
892
+ },
893
+ {
894
+ "epoch": 0.19,
895
+ "learning_rate": 1.861002653334389e-05,
896
+ "loss": 1.1843,
897
+ "step": 148
898
+ },
899
+ {
900
+ "epoch": 0.2,
901
+ "learning_rate": 1.85882387133824e-05,
902
+ "loss": 1.1847,
903
+ "step": 149
904
+ },
905
+ {
906
+ "epoch": 0.2,
907
+ "learning_rate": 1.8566294417482552e-05,
908
+ "loss": 1.1671,
909
+ "step": 150
910
+ },
911
+ {
912
+ "epoch": 0.2,
913
+ "learning_rate": 1.8544194045464888e-05,
914
+ "loss": 1.1554,
915
+ "step": 151
916
+ },
917
+ {
918
+ "epoch": 0.2,
919
+ "learning_rate": 1.8521937999993627e-05,
920
+ "loss": 1.1791,
921
+ "step": 152
922
+ },
923
+ {
924
+ "epoch": 0.2,
925
+ "learning_rate": 1.849952668656933e-05,
926
+ "loss": 1.1666,
927
+ "step": 153
928
+ },
929
+ {
930
+ "epoch": 0.2,
931
+ "learning_rate": 1.847696051352151e-05,
932
+ "loss": 1.1581,
933
+ "step": 154
934
+ },
935
+ {
936
+ "epoch": 0.2,
937
+ "learning_rate": 1.845423989200118e-05,
938
+ "loss": 1.1737,
939
+ "step": 155
940
+ },
941
+ {
942
+ "epoch": 0.21,
943
+ "learning_rate": 1.8431365235973383e-05,
944
+ "loss": 1.1652,
945
+ "step": 156
946
+ },
947
+ {
948
+ "epoch": 0.21,
949
+ "learning_rate": 1.840833696220963e-05,
950
+ "loss": 1.2088,
951
+ "step": 157
952
+ },
953
+ {
954
+ "epoch": 0.21,
955
+ "learning_rate": 1.8385155490280327e-05,
956
+ "loss": 1.1856,
957
+ "step": 158
958
+ },
959
+ {
960
+ "epoch": 0.21,
961
+ "learning_rate": 1.836182124254711e-05,
962
+ "loss": 1.1766,
963
+ "step": 159
964
+ },
965
+ {
966
+ "epoch": 0.21,
967
+ "learning_rate": 1.833833464415516e-05,
968
+ "loss": 1.176,
969
+ "step": 160
970
+ },
971
+ {
972
+ "epoch": 0.21,
973
+ "learning_rate": 1.8314696123025456e-05,
974
+ "loss": 1.1879,
975
+ "step": 161
976
+ },
977
+ {
978
+ "epoch": 0.21,
979
+ "learning_rate": 1.8290906109846974e-05,
980
+ "loss": 1.1849,
981
+ "step": 162
982
+ },
983
+ {
984
+ "epoch": 0.21,
985
+ "learning_rate": 1.8266965038068856e-05,
986
+ "loss": 1.1491,
987
+ "step": 163
988
+ },
989
+ {
990
+ "epoch": 0.22,
991
+ "learning_rate": 1.8242873343892494e-05,
992
+ "loss": 1.1559,
993
+ "step": 164
994
+ },
995
+ {
996
+ "epoch": 0.22,
997
+ "learning_rate": 1.8218631466263584e-05,
998
+ "loss": 1.1694,
999
+ "step": 165
1000
+ },
1001
+ {
1002
+ "epoch": 0.22,
1003
+ "learning_rate": 1.8194239846864133e-05,
1004
+ "loss": 1.1371,
1005
+ "step": 166
1006
+ },
1007
+ {
1008
+ "epoch": 0.22,
1009
+ "learning_rate": 1.816969893010442e-05,
1010
+ "loss": 1.1567,
1011
+ "step": 167
1012
+ },
1013
+ {
1014
+ "epoch": 0.22,
1015
+ "learning_rate": 1.8145009163114894e-05,
1016
+ "loss": 1.1869,
1017
+ "step": 168
1018
+ },
1019
+ {
1020
+ "epoch": 0.22,
1021
+ "learning_rate": 1.812017099573801e-05,
1022
+ "loss": 1.1967,
1023
+ "step": 169
1024
+ },
1025
+ {
1026
+ "epoch": 0.22,
1027
+ "learning_rate": 1.8095184880520058e-05,
1028
+ "loss": 1.1561,
1029
+ "step": 170
1030
+ },
1031
+ {
1032
+ "epoch": 0.23,
1033
+ "learning_rate": 1.8070051272702905e-05,
1034
+ "loss": 1.1744,
1035
+ "step": 171
1036
+ },
1037
+ {
1038
+ "epoch": 0.23,
1039
+ "learning_rate": 1.8044770630215706e-05,
1040
+ "loss": 1.1565,
1041
+ "step": 172
1042
+ },
1043
+ {
1044
+ "epoch": 0.23,
1045
+ "learning_rate": 1.801934341366655e-05,
1046
+ "loss": 1.1897,
1047
+ "step": 173
1048
+ },
1049
+ {
1050
+ "epoch": 0.23,
1051
+ "learning_rate": 1.7993770086334082e-05,
1052
+ "loss": 1.1711,
1053
+ "step": 174
1054
+ },
1055
+ {
1056
+ "epoch": 0.23,
1057
+ "learning_rate": 1.7968051114159046e-05,
1058
+ "loss": 1.1937,
1059
+ "step": 175
1060
+ },
1061
+ {
1062
+ "epoch": 0.23,
1063
+ "learning_rate": 1.794218696573582e-05,
1064
+ "loss": 1.1238,
1065
+ "step": 176
1066
+ },
1067
+ {
1068
+ "epoch": 0.23,
1069
+ "learning_rate": 1.791617811230385e-05,
1070
+ "loss": 1.1599,
1071
+ "step": 177
1072
+ },
1073
+ {
1074
+ "epoch": 0.23,
1075
+ "learning_rate": 1.7890025027739084e-05,
1076
+ "loss": 1.1605,
1077
+ "step": 178
1078
+ },
1079
+ {
1080
+ "epoch": 0.24,
1081
+ "learning_rate": 1.7863728188545326e-05,
1082
+ "loss": 1.1818,
1083
+ "step": 179
1084
+ },
1085
+ {
1086
+ "epoch": 0.24,
1087
+ "learning_rate": 1.7837288073845566e-05,
1088
+ "loss": 1.1732,
1089
+ "step": 180
1090
+ },
1091
+ {
1092
+ "epoch": 0.24,
1093
+ "learning_rate": 1.7810705165373245e-05,
1094
+ "loss": 1.1543,
1095
+ "step": 181
1096
+ },
1097
+ {
1098
+ "epoch": 0.24,
1099
+ "learning_rate": 1.778397994746347e-05,
1100
+ "loss": 1.1605,
1101
+ "step": 182
1102
+ },
1103
+ {
1104
+ "epoch": 0.24,
1105
+ "learning_rate": 1.77571129070442e-05,
1106
+ "loss": 1.172,
1107
+ "step": 183
1108
+ },
1109
+ {
1110
+ "epoch": 0.24,
1111
+ "learning_rate": 1.773010453362737e-05,
1112
+ "loss": 1.1587,
1113
+ "step": 184
1114
+ },
1115
+ {
1116
+ "epoch": 0.24,
1117
+ "learning_rate": 1.770295531929998e-05,
1118
+ "loss": 1.1511,
1119
+ "step": 185
1120
+ },
1121
+ {
1122
+ "epoch": 0.25,
1123
+ "learning_rate": 1.767566575871511e-05,
1124
+ "loss": 1.1626,
1125
+ "step": 186
1126
+ },
1127
+ {
1128
+ "epoch": 0.25,
1129
+ "learning_rate": 1.7648236349082928e-05,
1130
+ "loss": 1.1861,
1131
+ "step": 187
1132
+ },
1133
+ {
1134
+ "epoch": 0.25,
1135
+ "learning_rate": 1.7620667590161626e-05,
1136
+ "loss": 1.1984,
1137
+ "step": 188
1138
+ },
1139
+ {
1140
+ "epoch": 0.25,
1141
+ "learning_rate": 1.75929599842483e-05,
1142
+ "loss": 1.1614,
1143
+ "step": 189
1144
+ },
1145
+ {
1146
+ "epoch": 0.25,
1147
+ "learning_rate": 1.756511403616982e-05,
1148
+ "loss": 1.175,
1149
+ "step": 190
1150
+ },
1151
+ {
1152
+ "epoch": 0.25,
1153
+ "learning_rate": 1.7537130253273613e-05,
1154
+ "loss": 1.1688,
1155
+ "step": 191
1156
+ },
1157
+ {
1158
+ "epoch": 0.25,
1159
+ "learning_rate": 1.750900914541844e-05,
1160
+ "loss": 1.1795,
1161
+ "step": 192
1162
+ },
1163
+ {
1164
+ "epoch": 0.25,
1165
+ "learning_rate": 1.7480751224965083e-05,
1166
+ "loss": 1.155,
1167
+ "step": 193
1168
+ },
1169
+ {
1170
+ "epoch": 0.26,
1171
+ "learning_rate": 1.7452357006767026e-05,
1172
+ "loss": 1.148,
1173
+ "step": 194
1174
+ },
1175
+ {
1176
+ "epoch": 0.26,
1177
+ "learning_rate": 1.742382700816107e-05,
1178
+ "loss": 1.1444,
1179
+ "step": 195
1180
+ },
1181
+ {
1182
+ "epoch": 0.26,
1183
+ "learning_rate": 1.7395161748957905e-05,
1184
+ "loss": 1.1576,
1185
+ "step": 196
1186
+ },
1187
+ {
1188
+ "epoch": 0.26,
1189
+ "learning_rate": 1.7366361751432645e-05,
1190
+ "loss": 1.1747,
1191
+ "step": 197
1192
+ },
1193
+ {
1194
+ "epoch": 0.26,
1195
+ "learning_rate": 1.7337427540315305e-05,
1196
+ "loss": 1.174,
1197
+ "step": 198
1198
+ },
1199
+ {
1200
+ "epoch": 0.26,
1201
+ "learning_rate": 1.730835964278124e-05,
1202
+ "loss": 1.1518,
1203
+ "step": 199
1204
+ },
1205
+ {
1206
+ "epoch": 0.26,
1207
+ "learning_rate": 1.7279158588441558e-05,
1208
+ "loss": 1.1269,
1209
+ "step": 200
1210
+ },
1211
+ {
1212
+ "epoch": 0.26,
1213
+ "learning_rate": 1.7249824909333445e-05,
1214
+ "loss": 1.1499,
1215
+ "step": 201
1216
+ },
1217
+ {
1218
+ "epoch": 0.27,
1219
+ "learning_rate": 1.722035913991048e-05,
1220
+ "loss": 1.1643,
1221
+ "step": 202
1222
+ },
1223
+ {
1224
+ "epoch": 0.27,
1225
+ "learning_rate": 1.719076181703291e-05,
1226
+ "loss": 1.148,
1227
+ "step": 203
1228
+ },
1229
+ {
1230
+ "epoch": 0.27,
1231
+ "learning_rate": 1.716103347995785e-05,
1232
+ "loss": 1.1736,
1233
+ "step": 204
1234
+ },
1235
+ {
1236
+ "epoch": 0.27,
1237
+ "learning_rate": 1.713117467032948e-05,
1238
+ "loss": 1.1843,
1239
+ "step": 205
1240
+ },
1241
+ {
1242
+ "epoch": 0.27,
1243
+ "learning_rate": 1.7101185932169147e-05,
1244
+ "loss": 1.1705,
1245
+ "step": 206
1246
+ },
1247
+ {
1248
+ "epoch": 0.27,
1249
+ "learning_rate": 1.7071067811865477e-05,
1250
+ "loss": 1.1403,
1251
+ "step": 207
1252
+ },
1253
+ {
1254
+ "epoch": 0.27,
1255
+ "learning_rate": 1.7040820858164413e-05,
1256
+ "loss": 1.1338,
1257
+ "step": 208
1258
+ },
1259
+ {
1260
+ "epoch": 0.28,
1261
+ "learning_rate": 1.7010445622159214e-05,
1262
+ "loss": 1.1615,
1263
+ "step": 209
1264
+ },
1265
+ {
1266
+ "epoch": 0.28,
1267
+ "learning_rate": 1.6979942657280414e-05,
1268
+ "loss": 1.1539,
1269
+ "step": 210
1270
+ },
1271
+ {
1272
+ "epoch": 0.28,
1273
+ "learning_rate": 1.694931251928575e-05,
1274
+ "loss": 1.1228,
1275
+ "step": 211
1276
+ },
1277
+ {
1278
+ "epoch": 0.28,
1279
+ "learning_rate": 1.691855576625001e-05,
1280
+ "loss": 1.1196,
1281
+ "step": 212
1282
+ },
1283
+ {
1284
+ "epoch": 0.28,
1285
+ "learning_rate": 1.68876729585549e-05,
1286
+ "loss": 1.1321,
1287
+ "step": 213
1288
+ },
1289
+ {
1290
+ "epoch": 0.28,
1291
+ "learning_rate": 1.6856664658878797e-05,
1292
+ "loss": 1.1416,
1293
+ "step": 214
1294
+ },
1295
+ {
1296
+ "epoch": 0.28,
1297
+ "learning_rate": 1.6825531432186545e-05,
1298
+ "loss": 1.1573,
1299
+ "step": 215
1300
+ },
1301
+ {
1302
+ "epoch": 0.28,
1303
+ "learning_rate": 1.6794273845719096e-05,
1304
+ "loss": 1.1514,
1305
+ "step": 216
1306
+ },
1307
+ {
1308
+ "epoch": 0.29,
1309
+ "learning_rate": 1.6762892468983237e-05,
1310
+ "loss": 1.1552,
1311
+ "step": 217
1312
+ },
1313
+ {
1314
+ "epoch": 0.29,
1315
+ "learning_rate": 1.673138787374119e-05,
1316
+ "loss": 1.1062,
1317
+ "step": 218
1318
+ },
1319
+ {
1320
+ "epoch": 0.29,
1321
+ "learning_rate": 1.6699760634000166e-05,
1322
+ "loss": 1.1527,
1323
+ "step": 219
1324
+ },
1325
+ {
1326
+ "epoch": 0.29,
1327
+ "learning_rate": 1.6668011326001962e-05,
1328
+ "loss": 1.1855,
1329
+ "step": 220
1330
+ },
1331
+ {
1332
+ "epoch": 0.29,
1333
+ "learning_rate": 1.6636140528212427e-05,
1334
+ "loss": 1.1865,
1335
+ "step": 221
1336
+ },
1337
+ {
1338
+ "epoch": 0.29,
1339
+ "learning_rate": 1.6604148821310912e-05,
1340
+ "loss": 1.1618,
1341
+ "step": 222
1342
+ },
1343
+ {
1344
+ "epoch": 0.29,
1345
+ "learning_rate": 1.6572036788179728e-05,
1346
+ "loss": 1.1418,
1347
+ "step": 223
1348
+ },
1349
+ {
1350
+ "epoch": 0.3,
1351
+ "learning_rate": 1.6539805013893493e-05,
1352
+ "loss": 1.15,
1353
+ "step": 224
1354
+ },
1355
+ {
1356
+ "epoch": 0.3,
1357
+ "learning_rate": 1.650745408570849e-05,
1358
+ "loss": 1.0969,
1359
+ "step": 225
1360
+ },
1361
+ {
1362
+ "epoch": 0.3,
1363
+ "learning_rate": 1.6474984593051965e-05,
1364
+ "loss": 1.1225,
1365
+ "step": 226
1366
+ },
1367
+ {
1368
+ "epoch": 0.3,
1369
+ "learning_rate": 1.6442397127511366e-05,
1370
+ "loss": 1.1628,
1371
+ "step": 227
1372
+ },
1373
+ {
1374
+ "epoch": 0.3,
1375
+ "learning_rate": 1.6409692282823604e-05,
1376
+ "loss": 1.1361,
1377
+ "step": 228
1378
+ },
1379
+ {
1380
+ "epoch": 0.3,
1381
+ "learning_rate": 1.63768706548642e-05,
1382
+ "loss": 1.1343,
1383
+ "step": 229
1384
+ },
1385
+ {
1386
+ "epoch": 0.3,
1387
+ "learning_rate": 1.6343932841636455e-05,
1388
+ "loss": 1.1284,
1389
+ "step": 230
1390
+ },
1391
+ {
1392
+ "epoch": 0.3,
1393
+ "learning_rate": 1.631087944326053e-05,
1394
+ "loss": 1.1861,
1395
+ "step": 231
1396
+ },
1397
+ {
1398
+ "epoch": 0.31,
1399
+ "learning_rate": 1.6277711061962525e-05,
1400
+ "loss": 1.1676,
1401
+ "step": 232
1402
+ },
1403
+ {
1404
+ "epoch": 0.31,
1405
+ "learning_rate": 1.6244428302063506e-05,
1406
+ "loss": 1.1829,
1407
+ "step": 233
1408
+ },
1409
+ {
1410
+ "epoch": 0.31,
1411
+ "learning_rate": 1.6211031769968503e-05,
1412
+ "loss": 1.1682,
1413
+ "step": 234
1414
+ },
1415
+ {
1416
+ "epoch": 0.31,
1417
+ "learning_rate": 1.6177522074155436e-05,
1418
+ "loss": 1.1688,
1419
+ "step": 235
1420
+ },
1421
+ {
1422
+ "epoch": 0.31,
1423
+ "learning_rate": 1.6143899825164058e-05,
1424
+ "loss": 1.1534,
1425
+ "step": 236
1426
+ },
1427
+ {
1428
+ "epoch": 0.31,
1429
+ "learning_rate": 1.6110165635584807e-05,
1430
+ "loss": 1.1279,
1431
+ "step": 237
1432
+ },
1433
+ {
1434
+ "epoch": 0.31,
1435
+ "learning_rate": 1.6076320120047667e-05,
1436
+ "loss": 1.1719,
1437
+ "step": 238
1438
+ },
1439
+ {
1440
+ "epoch": 0.31,
1441
+ "learning_rate": 1.6042363895210948e-05,
1442
+ "loss": 1.1648,
1443
+ "step": 239
1444
+ },
1445
+ {
1446
+ "epoch": 0.32,
1447
+ "learning_rate": 1.6008297579750063e-05,
1448
+ "loss": 1.1386,
1449
+ "step": 240
1450
+ },
1451
+ {
1452
+ "epoch": 0.32,
1453
+ "learning_rate": 1.597412179434626e-05,
1454
+ "loss": 1.1404,
1455
+ "step": 241
1456
+ },
1457
+ {
1458
+ "epoch": 0.32,
1459
+ "learning_rate": 1.5939837161675297e-05,
1460
+ "loss": 1.1738,
1461
+ "step": 242
1462
+ },
1463
+ {
1464
+ "epoch": 0.32,
1465
+ "learning_rate": 1.590544430639611e-05,
1466
+ "loss": 1.1573,
1467
+ "step": 243
1468
+ },
1469
+ {
1470
+ "epoch": 0.32,
1471
+ "learning_rate": 1.5870943855139437e-05,
1472
+ "loss": 1.183,
1473
+ "step": 244
1474
+ },
1475
+ {
1476
+ "epoch": 0.32,
1477
+ "learning_rate": 1.5836336436496377e-05,
1478
+ "loss": 1.1366,
1479
+ "step": 245
1480
+ },
1481
+ {
1482
+ "epoch": 0.32,
1483
+ "learning_rate": 1.5801622681006966e-05,
1484
+ "loss": 1.1644,
1485
+ "step": 246
1486
+ },
1487
+ {
1488
+ "epoch": 0.33,
1489
+ "learning_rate": 1.5766803221148676e-05,
1490
+ "loss": 1.1487,
1491
+ "step": 247
1492
+ },
1493
+ {
1494
+ "epoch": 0.33,
1495
+ "learning_rate": 1.5731878691324874e-05,
1496
+ "loss": 1.1444,
1497
+ "step": 248
1498
+ },
1499
+ {
1500
+ "epoch": 0.33,
1501
+ "learning_rate": 1.5696849727853297e-05,
1502
+ "loss": 1.1516,
1503
+ "step": 249
1504
+ },
1505
+ {
1506
+ "epoch": 0.33,
1507
+ "learning_rate": 1.5661716968954436e-05,
1508
+ "loss": 1.1412,
1509
+ "step": 250
1510
+ },
1511
+ {
1512
+ "epoch": 0.33,
1513
+ "learning_rate": 1.5626481054739916e-05,
1514
+ "loss": 1.1326,
1515
+ "step": 251
1516
+ },
1517
+ {
1518
+ "epoch": 0.33,
1519
+ "learning_rate": 1.5591142627200825e-05,
1520
+ "loss": 1.1708,
1521
+ "step": 252
1522
+ },
1523
+ {
1524
+ "epoch": 0.33,
1525
+ "learning_rate": 1.5555702330196024e-05,
1526
+ "loss": 1.1628,
1527
+ "step": 253
1528
+ },
1529
+ {
1530
+ "epoch": 0.33,
1531
+ "learning_rate": 1.552016080944042e-05,
1532
+ "loss": 1.1161,
1533
+ "step": 254
1534
+ },
1535
+ {
1536
+ "epoch": 0.34,
1537
+ "learning_rate": 1.5484518712493188e-05,
1538
+ "loss": 1.1772,
1539
+ "step": 255
1540
+ },
1541
+ {
1542
+ "epoch": 0.34,
1543
+ "learning_rate": 1.544877668874599e-05,
1544
+ "loss": 1.1406,
1545
+ "step": 256
1546
+ },
1547
+ {
1548
+ "epoch": 0.34,
1549
+ "learning_rate": 1.5412935389411124e-05,
1550
+ "loss": 1.1679,
1551
+ "step": 257
1552
+ },
1553
+ {
1554
+ "epoch": 0.34,
1555
+ "learning_rate": 1.5376995467509673e-05,
1556
+ "loss": 1.1426,
1557
+ "step": 258
1558
+ },
1559
+ {
1560
+ "epoch": 0.34,
1561
+ "learning_rate": 1.5340957577859605e-05,
1562
+ "loss": 1.1494,
1563
+ "step": 259
1564
+ },
1565
+ {
1566
+ "epoch": 0.34,
1567
+ "learning_rate": 1.530482237706383e-05,
1568
+ "loss": 1.1577,
1569
+ "step": 260
1570
+ },
1571
+ {
1572
+ "epoch": 0.34,
1573
+ "learning_rate": 1.526859052349827e-05,
1574
+ "loss": 1.1549,
1575
+ "step": 261
1576
+ },
1577
+ {
1578
+ "epoch": 0.35,
1579
+ "learning_rate": 1.5232262677299816e-05,
1580
+ "loss": 1.1509,
1581
+ "step": 262
1582
+ },
1583
+ {
1584
+ "epoch": 0.35,
1585
+ "learning_rate": 1.5195839500354337e-05,
1586
+ "loss": 1.1197,
1587
+ "step": 263
1588
+ },
1589
+ {
1590
+ "epoch": 0.35,
1591
+ "learning_rate": 1.5159321656284602e-05,
1592
+ "loss": 1.1216,
1593
+ "step": 264
1594
+ },
1595
+ {
1596
+ "epoch": 0.35,
1597
+ "learning_rate": 1.5122709810438205e-05,
1598
+ "loss": 1.1471,
1599
+ "step": 265
1600
+ },
1601
+ {
1602
+ "epoch": 0.35,
1603
+ "learning_rate": 1.5086004629875426e-05,
1604
+ "loss": 1.1707,
1605
+ "step": 266
1606
+ },
1607
+ {
1608
+ "epoch": 0.35,
1609
+ "learning_rate": 1.5049206783357082e-05,
1610
+ "loss": 1.1582,
1611
+ "step": 267
1612
+ },
1613
+ {
1614
+ "epoch": 0.35,
1615
+ "learning_rate": 1.501231694133235e-05,
1616
+ "loss": 1.1703,
1617
+ "step": 268
1618
+ },
1619
+ {
1620
+ "epoch": 0.35,
1621
+ "learning_rate": 1.4975335775926547e-05,
1622
+ "loss": 1.1943,
1623
+ "step": 269
1624
+ },
1625
+ {
1626
+ "epoch": 0.36,
1627
+ "learning_rate": 1.4938263960928878e-05,
1628
+ "loss": 1.1607,
1629
+ "step": 270
1630
+ },
1631
+ {
1632
+ "epoch": 0.36,
1633
+ "learning_rate": 1.4901102171780175e-05,
1634
+ "loss": 1.1251,
1635
+ "step": 271
1636
+ },
1637
+ {
1638
+ "epoch": 0.36,
1639
+ "learning_rate": 1.4863851085560563e-05,
1640
+ "loss": 1.1472,
1641
+ "step": 272
1642
+ },
1643
+ {
1644
+ "epoch": 0.36,
1645
+ "learning_rate": 1.4826511380977155e-05,
1646
+ "loss": 1.1655,
1647
+ "step": 273
1648
+ },
1649
+ {
1650
+ "epoch": 0.36,
1651
+ "learning_rate": 1.478908373835167e-05,
1652
+ "loss": 1.1598,
1653
+ "step": 274
1654
+ },
1655
+ {
1656
+ "epoch": 0.36,
1657
+ "learning_rate": 1.4751568839608036e-05,
1658
+ "loss": 1.1717,
1659
+ "step": 275
1660
+ },
1661
+ {
1662
+ "epoch": 0.36,
1663
+ "learning_rate": 1.4713967368259981e-05,
1664
+ "loss": 1.1455,
1665
+ "step": 276
1666
+ },
1667
+ {
1668
+ "epoch": 0.36,
1669
+ "learning_rate": 1.4676280009398544e-05,
1670
+ "loss": 1.1347,
1671
+ "step": 277
1672
+ },
1673
+ {
1674
+ "epoch": 0.37,
1675
+ "learning_rate": 1.4638507449679642e-05,
1676
+ "loss": 1.1355,
1677
+ "step": 278
1678
+ },
1679
+ {
1680
+ "epoch": 0.37,
1681
+ "learning_rate": 1.4600650377311523e-05,
1682
+ "loss": 1.1047,
1683
+ "step": 279
1684
+ },
1685
+ {
1686
+ "epoch": 0.37,
1687
+ "learning_rate": 1.4562709482042237e-05,
1688
+ "loss": 1.175,
1689
+ "step": 280
1690
+ },
1691
+ {
1692
+ "epoch": 0.37,
1693
+ "learning_rate": 1.4524685455147071e-05,
1694
+ "loss": 1.1226,
1695
+ "step": 281
1696
+ },
1697
+ {
1698
+ "epoch": 0.37,
1699
+ "learning_rate": 1.448657898941596e-05,
1700
+ "loss": 1.1741,
1701
+ "step": 282
1702
+ },
1703
+ {
1704
+ "epoch": 0.37,
1705
+ "learning_rate": 1.4448390779140844e-05,
1706
+ "loss": 1.1127,
1707
+ "step": 283
1708
+ },
1709
+ {
1710
+ "epoch": 0.37,
1711
+ "learning_rate": 1.4410121520103045e-05,
1712
+ "loss": 1.1451,
1713
+ "step": 284
1714
+ },
1715
+ {
1716
+ "epoch": 0.38,
1717
+ "learning_rate": 1.4371771909560566e-05,
1718
+ "loss": 1.1277,
1719
+ "step": 285
1720
+ },
1721
+ {
1722
+ "epoch": 0.38,
1723
+ "learning_rate": 1.4333342646235407e-05,
1724
+ "loss": 1.1388,
1725
+ "step": 286
1726
+ },
1727
+ {
1728
+ "epoch": 0.38,
1729
+ "learning_rate": 1.4294834430300822e-05,
1730
+ "loss": 1.1811,
1731
+ "step": 287
1732
+ },
1733
+ {
1734
+ "epoch": 0.38,
1735
+ "learning_rate": 1.425624796336856e-05,
1736
+ "loss": 1.1222,
1737
+ "step": 288
1738
+ },
1739
+ {
1740
+ "epoch": 0.38,
1741
+ "learning_rate": 1.4217583948476094e-05,
1742
+ "loss": 1.1399,
1743
+ "step": 289
1744
+ },
1745
+ {
1746
+ "epoch": 0.38,
1747
+ "learning_rate": 1.4178843090073802e-05,
1748
+ "loss": 1.1165,
1749
+ "step": 290
1750
+ },
1751
+ {
1752
+ "epoch": 0.38,
1753
+ "learning_rate": 1.4140026094012136e-05,
1754
+ "loss": 1.1414,
1755
+ "step": 291
1756
+ },
1757
+ {
1758
+ "epoch": 0.38,
1759
+ "learning_rate": 1.4101133667528761e-05,
1760
+ "loss": 1.1139,
1761
+ "step": 292
1762
+ },
1763
+ {
1764
+ "epoch": 0.39,
1765
+ "learning_rate": 1.4062166519235665e-05,
1766
+ "loss": 1.1374,
1767
+ "step": 293
1768
+ },
1769
+ {
1770
+ "epoch": 0.39,
1771
+ "learning_rate": 1.4023125359106253e-05,
1772
+ "loss": 1.1488,
1773
+ "step": 294
1774
+ },
1775
+ {
1776
+ "epoch": 0.39,
1777
+ "learning_rate": 1.3984010898462417e-05,
1778
+ "loss": 1.1664,
1779
+ "step": 295
1780
+ },
1781
+ {
1782
+ "epoch": 0.39,
1783
+ "learning_rate": 1.3944823849961557e-05,
1784
+ "loss": 1.1406,
1785
+ "step": 296
1786
+ },
1787
+ {
1788
+ "epoch": 0.39,
1789
+ "learning_rate": 1.3905564927583625e-05,
1790
+ "loss": 1.1464,
1791
+ "step": 297
1792
+ },
1793
+ {
1794
+ "epoch": 0.39,
1795
+ "learning_rate": 1.3866234846618083e-05,
1796
+ "loss": 1.1564,
1797
+ "step": 298
1798
+ },
1799
+ {
1800
+ "epoch": 0.39,
1801
+ "learning_rate": 1.3826834323650899e-05,
1802
+ "loss": 1.1286,
1803
+ "step": 299
1804
+ },
1805
+ {
1806
+ "epoch": 0.4,
1807
+ "learning_rate": 1.3787364076551478e-05,
1808
+ "loss": 1.1488,
1809
+ "step": 300
1810
+ },
1811
+ {
1812
+ "epoch": 0.4,
1813
+ "learning_rate": 1.3747824824459577e-05,
1814
+ "loss": 1.1423,
1815
+ "step": 301
1816
+ },
1817
+ {
1818
+ "epoch": 0.4,
1819
+ "learning_rate": 1.3708217287772227e-05,
1820
+ "loss": 1.1349,
1821
+ "step": 302
1822
+ },
1823
+ {
1824
+ "epoch": 0.4,
1825
+ "learning_rate": 1.3668542188130567e-05,
1826
+ "loss": 1.139,
1827
+ "step": 303
1828
+ },
1829
+ {
1830
+ "epoch": 0.4,
1831
+ "learning_rate": 1.3628800248406738e-05,
1832
+ "loss": 1.126,
1833
+ "step": 304
1834
+ },
1835
+ {
1836
+ "epoch": 0.4,
1837
+ "learning_rate": 1.3588992192690683e-05,
1838
+ "loss": 1.1162,
1839
+ "step": 305
1840
+ },
1841
+ {
1842
+ "epoch": 0.4,
1843
+ "learning_rate": 1.3549118746276968e-05,
1844
+ "loss": 1.153,
1845
+ "step": 306
1846
+ },
1847
+ {
1848
+ "epoch": 0.4,
1849
+ "learning_rate": 1.350918063565157e-05,
1850
+ "loss": 1.1643,
1851
+ "step": 307
1852
+ },
1853
+ {
1854
+ "epoch": 0.41,
1855
+ "learning_rate": 1.3469178588478621e-05,
1856
+ "loss": 1.1528,
1857
+ "step": 308
1858
+ },
1859
+ {
1860
+ "epoch": 0.41,
1861
+ "learning_rate": 1.3429113333587181e-05,
1862
+ "loss": 1.1498,
1863
+ "step": 309
1864
+ },
1865
+ {
1866
+ "epoch": 0.41,
1867
+ "learning_rate": 1.3388985600957922e-05,
1868
+ "loss": 1.1209,
1869
+ "step": 310
1870
+ },
1871
+ {
1872
+ "epoch": 0.41,
1873
+ "learning_rate": 1.3348796121709862e-05,
1874
+ "loss": 1.1661,
1875
+ "step": 311
1876
+ },
1877
+ {
1878
+ "epoch": 0.41,
1879
+ "learning_rate": 1.3308545628087029e-05,
1880
+ "loss": 1.1558,
1881
+ "step": 312
1882
+ },
1883
+ {
1884
+ "epoch": 0.41,
1885
+ "learning_rate": 1.3268234853445113e-05,
1886
+ "loss": 1.1407,
1887
+ "step": 313
1888
+ },
1889
+ {
1890
+ "epoch": 0.41,
1891
+ "learning_rate": 1.3227864532238113e-05,
1892
+ "loss": 1.1581,
1893
+ "step": 314
1894
+ },
1895
+ {
1896
+ "epoch": 0.41,
1897
+ "learning_rate": 1.318743540000496e-05,
1898
+ "loss": 1.1192,
1899
+ "step": 315
1900
+ },
1901
+ {
1902
+ "epoch": 0.42,
1903
+ "learning_rate": 1.3146948193356105e-05,
1904
+ "loss": 1.1439,
1905
+ "step": 316
1906
+ },
1907
+ {
1908
+ "epoch": 0.42,
1909
+ "learning_rate": 1.3106403649960109e-05,
1910
+ "loss": 1.1795,
1911
+ "step": 317
1912
+ },
1913
+ {
1914
+ "epoch": 0.42,
1915
+ "learning_rate": 1.3065802508530186e-05,
1916
+ "loss": 1.1578,
1917
+ "step": 318
1918
+ },
1919
+ {
1920
+ "epoch": 0.42,
1921
+ "learning_rate": 1.302514550881076e-05,
1922
+ "loss": 1.1502,
1923
+ "step": 319
1924
+ },
1925
+ {
1926
+ "epoch": 0.42,
1927
+ "learning_rate": 1.2984433391563984e-05,
1928
+ "loss": 1.1239,
1929
+ "step": 320
1930
+ },
1931
+ {
1932
+ "epoch": 0.42,
1933
+ "learning_rate": 1.294366689855624e-05,
1934
+ "loss": 1.132,
1935
+ "step": 321
1936
+ },
1937
+ {
1938
+ "epoch": 0.42,
1939
+ "learning_rate": 1.2902846772544625e-05,
1940
+ "loss": 1.1317,
1941
+ "step": 322
1942
+ },
1943
+ {
1944
+ "epoch": 0.43,
1945
+ "learning_rate": 1.2861973757263416e-05,
1946
+ "loss": 1.1173,
1947
+ "step": 323
1948
+ },
1949
+ {
1950
+ "epoch": 0.43,
1951
+ "learning_rate": 1.282104859741052e-05,
1952
+ "loss": 1.1215,
1953
+ "step": 324
1954
+ },
1955
+ {
1956
+ "epoch": 0.43,
1957
+ "learning_rate": 1.2780072038633913e-05,
1958
+ "loss": 1.1568,
1959
+ "step": 325
1960
+ },
1961
+ {
1962
+ "epoch": 0.43,
1963
+ "learning_rate": 1.2739044827518043e-05,
1964
+ "loss": 1.1438,
1965
+ "step": 326
1966
+ },
1967
+ {
1968
+ "epoch": 0.43,
1969
+ "learning_rate": 1.2697967711570243e-05,
1970
+ "loss": 1.1108,
1971
+ "step": 327
1972
+ },
1973
+ {
1974
+ "epoch": 0.43,
1975
+ "learning_rate": 1.2656841439207093e-05,
1976
+ "loss": 1.1597,
1977
+ "step": 328
1978
+ },
1979
+ {
1980
+ "epoch": 0.43,
1981
+ "learning_rate": 1.2615666759740788e-05,
1982
+ "loss": 1.1489,
1983
+ "step": 329
1984
+ },
1985
+ {
1986
+ "epoch": 0.43,
1987
+ "learning_rate": 1.2574444423365503e-05,
1988
+ "loss": 1.1595,
1989
+ "step": 330
1990
+ },
1991
+ {
1992
+ "epoch": 0.44,
1993
+ "learning_rate": 1.2533175181143704e-05,
1994
+ "loss": 1.1327,
1995
+ "step": 331
1996
+ },
1997
+ {
1998
+ "epoch": 0.44,
1999
+ "learning_rate": 1.2491859784992477e-05,
2000
+ "loss": 1.119,
2001
+ "step": 332
2002
+ },
2003
+ {
2004
+ "epoch": 0.44,
2005
+ "learning_rate": 1.245049898766982e-05,
2006
+ "loss": 1.1255,
2007
+ "step": 333
2008
+ },
2009
+ {
2010
+ "epoch": 0.44,
2011
+ "learning_rate": 1.2409093542760925e-05,
2012
+ "loss": 1.1561,
2013
+ "step": 334
2014
+ },
2015
+ {
2016
+ "epoch": 0.44,
2017
+ "learning_rate": 1.2367644204664468e-05,
2018
+ "loss": 1.1602,
2019
+ "step": 335
2020
+ },
2021
+ {
2022
+ "epoch": 0.44,
2023
+ "learning_rate": 1.2326151728578839e-05,
2024
+ "loss": 1.1159,
2025
+ "step": 336
2026
+ },
2027
+ {
2028
+ "epoch": 0.44,
2029
+ "learning_rate": 1.228461687048839e-05,
2030
+ "loss": 1.156,
2031
+ "step": 337
2032
+ },
2033
+ {
2034
+ "epoch": 0.45,
2035
+ "learning_rate": 1.2243040387149682e-05,
2036
+ "loss": 1.1275,
2037
+ "step": 338
2038
+ },
2039
+ {
2040
+ "epoch": 0.45,
2041
+ "learning_rate": 1.2201423036077657e-05,
2042
+ "loss": 1.1467,
2043
+ "step": 339
2044
+ },
2045
+ {
2046
+ "epoch": 0.45,
2047
+ "learning_rate": 1.2159765575531877e-05,
2048
+ "loss": 1.1434,
2049
+ "step": 340
2050
+ },
2051
+ {
2052
+ "epoch": 0.45,
2053
+ "learning_rate": 1.2118068764502677e-05,
2054
+ "loss": 1.1361,
2055
+ "step": 341
2056
+ },
2057
+ {
2058
+ "epoch": 0.45,
2059
+ "learning_rate": 1.2076333362697358e-05,
2060
+ "loss": 1.1386,
2061
+ "step": 342
2062
+ },
2063
+ {
2064
+ "epoch": 0.45,
2065
+ "learning_rate": 1.2034560130526341e-05,
2066
+ "loss": 1.1254,
2067
+ "step": 343
2068
+ },
2069
+ {
2070
+ "epoch": 0.45,
2071
+ "learning_rate": 1.199274982908929e-05,
2072
+ "loss": 1.1216,
2073
+ "step": 344
2074
+ },
2075
+ {
2076
+ "epoch": 0.45,
2077
+ "learning_rate": 1.1950903220161286e-05,
2078
+ "loss": 1.1379,
2079
+ "step": 345
2080
+ },
2081
+ {
2082
+ "epoch": 0.46,
2083
+ "learning_rate": 1.1909021066178906e-05,
2084
+ "loss": 1.1418,
2085
+ "step": 346
2086
+ },
2087
+ {
2088
+ "epoch": 0.46,
2089
+ "learning_rate": 1.1867104130226363e-05,
2090
+ "loss": 1.168,
2091
+ "step": 347
2092
+ },
2093
+ {
2094
+ "epoch": 0.46,
2095
+ "learning_rate": 1.1825153176021591e-05,
2096
+ "loss": 1.1334,
2097
+ "step": 348
2098
+ },
2099
+ {
2100
+ "epoch": 0.46,
2101
+ "learning_rate": 1.1783168967902314e-05,
2102
+ "loss": 1.146,
2103
+ "step": 349
2104
+ },
2105
+ {
2106
+ "epoch": 0.46,
2107
+ "learning_rate": 1.1741152270812155e-05,
2108
+ "loss": 1.1315,
2109
+ "step": 350
2110
+ },
2111
+ {
2112
+ "epoch": 0.46,
2113
+ "learning_rate": 1.1699103850286668e-05,
2114
+ "loss": 1.1431,
2115
+ "step": 351
2116
+ },
2117
+ {
2118
+ "epoch": 0.46,
2119
+ "learning_rate": 1.1657024472439402e-05,
2120
+ "loss": 1.1435,
2121
+ "step": 352
2122
+ },
2123
+ {
2124
+ "epoch": 0.47,
2125
+ "learning_rate": 1.1614914903947952e-05,
2126
+ "loss": 1.1485,
2127
+ "step": 353
2128
+ },
2129
+ {
2130
+ "epoch": 0.47,
2131
+ "learning_rate": 1.157277591203996e-05,
2132
+ "loss": 1.1553,
2133
+ "step": 354
2134
+ },
2135
+ {
2136
+ "epoch": 0.47,
2137
+ "learning_rate": 1.153060826447918e-05,
2138
+ "loss": 1.1486,
2139
+ "step": 355
2140
+ },
2141
+ {
2142
+ "epoch": 0.47,
2143
+ "learning_rate": 1.1488412729551449e-05,
2144
+ "loss": 1.1436,
2145
+ "step": 356
2146
+ },
2147
+ {
2148
+ "epoch": 0.47,
2149
+ "learning_rate": 1.144619007605071e-05,
2150
+ "loss": 1.1152,
2151
+ "step": 357
2152
+ },
2153
+ {
2154
+ "epoch": 0.47,
2155
+ "learning_rate": 1.1403941073265014e-05,
2156
+ "loss": 1.1533,
2157
+ "step": 358
2158
+ },
2159
+ {
2160
+ "epoch": 0.47,
2161
+ "learning_rate": 1.1361666490962468e-05,
2162
+ "loss": 1.1451,
2163
+ "step": 359
2164
+ },
2165
+ {
2166
+ "epoch": 0.47,
2167
+ "learning_rate": 1.1319367099377248e-05,
2168
+ "loss": 1.1715,
2169
+ "step": 360
2170
+ },
2171
+ {
2172
+ "epoch": 0.48,
2173
+ "learning_rate": 1.1277043669195549e-05,
2174
+ "loss": 1.1125,
2175
+ "step": 361
2176
+ },
2177
+ {
2178
+ "epoch": 0.48,
2179
+ "learning_rate": 1.1234696971541534e-05,
2180
+ "loss": 1.1224,
2181
+ "step": 362
2182
+ },
2183
+ {
2184
+ "epoch": 0.48,
2185
+ "learning_rate": 1.1192327777963313e-05,
2186
+ "loss": 1.123,
2187
+ "step": 363
2188
+ },
2189
+ {
2190
+ "epoch": 0.48,
2191
+ "learning_rate": 1.1149936860418846e-05,
2192
+ "loss": 1.1412,
2193
+ "step": 364
2194
+ },
2195
+ {
2196
+ "epoch": 0.48,
2197
+ "learning_rate": 1.1107524991261913e-05,
2198
+ "loss": 1.1315,
2199
+ "step": 365
2200
+ },
2201
+ {
2202
+ "epoch": 0.48,
2203
+ "learning_rate": 1.1065092943228024e-05,
2204
+ "loss": 1.1723,
2205
+ "step": 366
2206
+ },
2207
+ {
2208
+ "epoch": 0.48,
2209
+ "learning_rate": 1.1022641489420342e-05,
2210
+ "loss": 1.1378,
2211
+ "step": 367
2212
+ },
2213
+ {
2214
+ "epoch": 0.48,
2215
+ "learning_rate": 1.098017140329561e-05,
2216
+ "loss": 1.1302,
2217
+ "step": 368
2218
+ },
2219
+ {
2220
+ "epoch": 0.49,
2221
+ "learning_rate": 1.0937683458650029e-05,
2222
+ "loss": 1.1688,
2223
+ "step": 369
2224
+ },
2225
+ {
2226
+ "epoch": 0.49,
2227
+ "learning_rate": 1.0895178429605189e-05,
2228
+ "loss": 1.1399,
2229
+ "step": 370
2230
+ },
2231
+ {
2232
+ "epoch": 0.49,
2233
+ "learning_rate": 1.0852657090593961e-05,
2234
+ "loss": 1.1245,
2235
+ "step": 371
2236
+ },
2237
+ {
2238
+ "epoch": 0.49,
2239
+ "learning_rate": 1.0810120216346368e-05,
2240
+ "loss": 1.1261,
2241
+ "step": 372
2242
+ },
2243
+ {
2244
+ "epoch": 0.49,
2245
+ "learning_rate": 1.0767568581875494e-05,
2246
+ "loss": 1.179,
2247
+ "step": 373
2248
+ },
2249
+ {
2250
+ "epoch": 0.49,
2251
+ "learning_rate": 1.072500296246334e-05,
2252
+ "loss": 1.1467,
2253
+ "step": 374
2254
+ },
2255
+ {
2256
+ "epoch": 0.49,
2257
+ "learning_rate": 1.0682424133646712e-05,
2258
+ "loss": 1.1464,
2259
+ "step": 375
2260
+ },
2261
+ {
2262
+ "epoch": 0.5,
2263
+ "learning_rate": 1.0639832871203094e-05,
2264
+ "loss": 1.1157,
2265
+ "step": 376
2266
+ },
2267
+ {
2268
+ "epoch": 0.5,
2269
+ "learning_rate": 1.0597229951136498e-05,
2270
+ "loss": 1.121,
2271
+ "step": 377
2272
+ },
2273
+ {
2274
+ "epoch": 0.5,
2275
+ "learning_rate": 1.0554616149663355e-05,
2276
+ "loss": 1.1477,
2277
+ "step": 378
2278
+ },
2279
+ {
2280
+ "epoch": 0.5,
2281
+ "learning_rate": 1.0511992243198335e-05,
2282
+ "loss": 1.1146,
2283
+ "step": 379
2284
+ },
2285
+ {
2286
+ "epoch": 0.5,
2287
+ "learning_rate": 1.0469359008340216e-05,
2288
+ "loss": 1.1365,
2289
+ "step": 380
2290
+ },
2291
+ {
2292
+ "epoch": 0.5,
2293
+ "learning_rate": 1.0426717221857756e-05,
2294
+ "loss": 1.1254,
2295
+ "step": 381
2296
+ },
2297
+ {
2298
+ "epoch": 0.5,
2299
+ "learning_rate": 1.0384067660675508e-05,
2300
+ "loss": 1.1476,
2301
+ "step": 382
2302
+ },
2303
+ {
2304
+ "epoch": 0.5,
2305
+ "learning_rate": 1.034141110185968e-05,
2306
+ "loss": 1.1466,
2307
+ "step": 383
2308
+ },
2309
+ {
2310
+ "epoch": 0.51,
2311
+ "learning_rate": 1.0298748322603982e-05,
2312
+ "loss": 1.1524,
2313
+ "step": 384
2314
+ },
2315
+ {
2316
+ "epoch": 0.51,
2317
+ "learning_rate": 1.0256080100215448e-05,
2318
+ "loss": 1.1351,
2319
+ "step": 385
2320
+ },
2321
+ {
2322
+ "epoch": 0.51,
2323
+ "learning_rate": 1.0213407212100296e-05,
2324
+ "loss": 1.1135,
2325
+ "step": 386
2326
+ },
2327
+ {
2328
+ "epoch": 0.51,
2329
+ "learning_rate": 1.017073043574975e-05,
2330
+ "loss": 1.1284,
2331
+ "step": 387
2332
+ },
2333
+ {
2334
+ "epoch": 0.51,
2335
+ "learning_rate": 1.0128050548725865e-05,
2336
+ "loss": 1.1309,
2337
+ "step": 388
2338
+ },
2339
+ {
2340
+ "epoch": 0.51,
2341
+ "learning_rate": 1.0085368328647395e-05,
2342
+ "loss": 1.0959,
2343
+ "step": 389
2344
+ },
2345
+ {
2346
+ "epoch": 0.51,
2347
+ "learning_rate": 1.0042684553175575e-05,
2348
+ "loss": 1.1173,
2349
+ "step": 390
2350
+ },
2351
+ {
2352
+ "epoch": 0.52,
2353
+ "learning_rate": 1e-05,
2354
+ "loss": 1.132,
2355
+ "step": 391
2356
+ },
2357
+ {
2358
+ "epoch": 0.52,
2359
+ "learning_rate": 9.957315446824425e-06,
2360
+ "loss": 1.1172,
2361
+ "step": 392
2362
+ },
2363
+ {
2364
+ "epoch": 0.52,
2365
+ "learning_rate": 9.91463167135261e-06,
2366
+ "loss": 1.1289,
2367
+ "step": 393
2368
+ },
2369
+ {
2370
+ "epoch": 0.52,
2371
+ "learning_rate": 9.871949451274137e-06,
2372
+ "loss": 1.1111,
2373
+ "step": 394
2374
+ },
2375
+ {
2376
+ "epoch": 0.52,
2377
+ "learning_rate": 9.829269564250254e-06,
2378
+ "loss": 1.1246,
2379
+ "step": 395
2380
+ },
2381
+ {
2382
+ "epoch": 0.52,
2383
+ "learning_rate": 9.786592787899707e-06,
2384
+ "loss": 1.1825,
2385
+ "step": 396
2386
+ },
2387
+ {
2388
+ "epoch": 0.52,
2389
+ "learning_rate": 9.743919899784555e-06,
2390
+ "loss": 1.1078,
2391
+ "step": 397
2392
+ },
2393
+ {
2394
+ "epoch": 0.52,
2395
+ "learning_rate": 9.701251677396021e-06,
2396
+ "loss": 1.108,
2397
+ "step": 398
2398
+ },
2399
+ {
2400
+ "epoch": 0.53,
2401
+ "learning_rate": 9.658588898140322e-06,
2402
+ "loss": 1.1304,
2403
+ "step": 399
2404
+ },
2405
+ {
2406
+ "epoch": 0.53,
2407
+ "learning_rate": 9.615932339324497e-06,
2408
+ "loss": 1.124,
2409
+ "step": 400
2410
+ },
2411
+ {
2412
+ "epoch": 0.53,
2413
+ "learning_rate": 9.573282778142246e-06,
2414
+ "loss": 1.1333,
2415
+ "step": 401
2416
+ },
2417
+ {
2418
+ "epoch": 0.53,
2419
+ "learning_rate": 9.530640991659785e-06,
2420
+ "loss": 1.1308,
2421
+ "step": 402
2422
+ },
2423
+ {
2424
+ "epoch": 0.53,
2425
+ "learning_rate": 9.488007756801672e-06,
2426
+ "loss": 1.1265,
2427
+ "step": 403
2428
+ },
2429
+ {
2430
+ "epoch": 0.53,
2431
+ "learning_rate": 9.445383850336648e-06,
2432
+ "loss": 1.1267,
2433
+ "step": 404
2434
+ },
2435
+ {
2436
+ "epoch": 0.53,
2437
+ "learning_rate": 9.402770048863502e-06,
2438
+ "loss": 1.1018,
2439
+ "step": 405
2440
+ },
2441
+ {
2442
+ "epoch": 0.53,
2443
+ "learning_rate": 9.360167128796913e-06,
2444
+ "loss": 1.157,
2445
+ "step": 406
2446
+ },
2447
+ {
2448
+ "epoch": 0.54,
2449
+ "learning_rate": 9.317575866353293e-06,
2450
+ "loss": 1.1212,
2451
+ "step": 407
2452
+ },
2453
+ {
2454
+ "epoch": 0.54,
2455
+ "learning_rate": 9.274997037536663e-06,
2456
+ "loss": 1.1372,
2457
+ "step": 408
2458
+ },
2459
+ {
2460
+ "epoch": 0.54,
2461
+ "learning_rate": 9.232431418124507e-06,
2462
+ "loss": 1.162,
2463
+ "step": 409
2464
+ },
2465
+ {
2466
+ "epoch": 0.54,
2467
+ "learning_rate": 9.189879783653633e-06,
2468
+ "loss": 1.1234,
2469
+ "step": 410
2470
+ },
2471
+ {
2472
+ "epoch": 0.54,
2473
+ "learning_rate": 9.14734290940604e-06,
2474
+ "loss": 1.1363,
2475
+ "step": 411
2476
+ },
2477
+ {
2478
+ "epoch": 0.54,
2479
+ "learning_rate": 9.104821570394811e-06,
2480
+ "loss": 1.1435,
2481
+ "step": 412
2482
+ },
2483
+ {
2484
+ "epoch": 0.54,
2485
+ "learning_rate": 9.062316541349978e-06,
2486
+ "loss": 1.134,
2487
+ "step": 413
2488
+ },
2489
+ {
2490
+ "epoch": 0.55,
2491
+ "learning_rate": 9.019828596704394e-06,
2492
+ "loss": 1.1184,
2493
+ "step": 414
2494
+ },
2495
+ {
2496
+ "epoch": 0.55,
2497
+ "learning_rate": 8.977358510579658e-06,
2498
+ "loss": 1.1412,
2499
+ "step": 415
2500
+ },
2501
+ {
2502
+ "epoch": 0.55,
2503
+ "learning_rate": 8.93490705677198e-06,
2504
+ "loss": 1.1498,
2505
+ "step": 416
2506
+ },
2507
+ {
2508
+ "epoch": 0.55,
2509
+ "learning_rate": 8.89247500873809e-06,
2510
+ "loss": 1.1717,
2511
+ "step": 417
2512
+ },
2513
+ {
2514
+ "epoch": 0.55,
2515
+ "learning_rate": 8.850063139581156e-06,
2516
+ "loss": 1.1122,
2517
+ "step": 418
2518
+ },
2519
+ {
2520
+ "epoch": 0.55,
2521
+ "learning_rate": 8.807672222036692e-06,
2522
+ "loss": 1.1246,
2523
+ "step": 419
2524
+ },
2525
+ {
2526
+ "epoch": 0.55,
2527
+ "learning_rate": 8.765303028458468e-06,
2528
+ "loss": 1.1277,
2529
+ "step": 420
2530
+ },
2531
+ {
2532
+ "epoch": 0.55,
2533
+ "learning_rate": 8.722956330804456e-06,
2534
+ "loss": 1.1527,
2535
+ "step": 421
2536
+ },
2537
+ {
2538
+ "epoch": 0.56,
2539
+ "learning_rate": 8.680632900622752e-06,
2540
+ "loss": 1.0872,
2541
+ "step": 422
2542
+ },
2543
+ {
2544
+ "epoch": 0.56,
2545
+ "learning_rate": 8.638333509037537e-06,
2546
+ "loss": 1.129,
2547
+ "step": 423
2548
+ },
2549
+ {
2550
+ "epoch": 0.56,
2551
+ "learning_rate": 8.59605892673499e-06,
2552
+ "loss": 1.1143,
2553
+ "step": 424
2554
+ },
2555
+ {
2556
+ "epoch": 0.56,
2557
+ "learning_rate": 8.55380992394929e-06,
2558
+ "loss": 1.1301,
2559
+ "step": 425
2560
+ },
2561
+ {
2562
+ "epoch": 0.56,
2563
+ "learning_rate": 8.511587270448556e-06,
2564
+ "loss": 1.1289,
2565
+ "step": 426
2566
+ },
2567
+ {
2568
+ "epoch": 0.56,
2569
+ "learning_rate": 8.469391735520824e-06,
2570
+ "loss": 1.1145,
2571
+ "step": 427
2572
+ },
2573
+ {
2574
+ "epoch": 0.56,
2575
+ "learning_rate": 8.42722408796004e-06,
2576
+ "loss": 1.1467,
2577
+ "step": 428
2578
+ },
2579
+ {
2580
+ "epoch": 0.57,
2581
+ "learning_rate": 8.385085096052053e-06,
2582
+ "loss": 1.1668,
2583
+ "step": 429
2584
+ },
2585
+ {
2586
+ "epoch": 0.57,
2587
+ "learning_rate": 8.342975527560601e-06,
2588
+ "loss": 1.184,
2589
+ "step": 430
2590
+ },
2591
+ {
2592
+ "epoch": 0.57,
2593
+ "learning_rate": 8.300896149713334e-06,
2594
+ "loss": 1.1219,
2595
+ "step": 431
2596
+ },
2597
+ {
2598
+ "epoch": 0.57,
2599
+ "learning_rate": 8.258847729187845e-06,
2600
+ "loss": 1.1248,
2601
+ "step": 432
2602
+ },
2603
+ {
2604
+ "epoch": 0.57,
2605
+ "learning_rate": 8.216831032097689e-06,
2606
+ "loss": 1.1532,
2607
+ "step": 433
2608
+ },
2609
+ {
2610
+ "epoch": 0.57,
2611
+ "learning_rate": 8.174846823978412e-06,
2612
+ "loss": 1.1321,
2613
+ "step": 434
2614
+ },
2615
+ {
2616
+ "epoch": 0.57,
2617
+ "learning_rate": 8.132895869773638e-06,
2618
+ "loss": 1.1126,
2619
+ "step": 435
2620
+ },
2621
+ {
2622
+ "epoch": 0.57,
2623
+ "learning_rate": 8.0909789338211e-06,
2624
+ "loss": 1.1054,
2625
+ "step": 436
2626
+ },
2627
+ {
2628
+ "epoch": 0.58,
2629
+ "learning_rate": 8.04909677983872e-06,
2630
+ "loss": 1.105,
2631
+ "step": 437
2632
+ },
2633
+ {
2634
+ "epoch": 0.58,
2635
+ "learning_rate": 8.00725017091071e-06,
2636
+ "loss": 1.0812,
2637
+ "step": 438
2638
+ },
2639
+ {
2640
+ "epoch": 0.58,
2641
+ "learning_rate": 7.965439869473664e-06,
2642
+ "loss": 1.1081,
2643
+ "step": 439
2644
+ },
2645
+ {
2646
+ "epoch": 0.58,
2647
+ "learning_rate": 7.923666637302643e-06,
2648
+ "loss": 1.1489,
2649
+ "step": 440
2650
+ },
2651
+ {
2652
+ "epoch": 0.58,
2653
+ "learning_rate": 7.881931235497324e-06,
2654
+ "loss": 1.1063,
2655
+ "step": 441
2656
+ },
2657
+ {
2658
+ "epoch": 0.58,
2659
+ "learning_rate": 7.84023442446813e-06,
2660
+ "loss": 1.058,
2661
+ "step": 442
2662
+ },
2663
+ {
2664
+ "epoch": 0.58,
2665
+ "learning_rate": 7.798576963922347e-06,
2666
+ "loss": 1.1126,
2667
+ "step": 443
2668
+ },
2669
+ {
2670
+ "epoch": 0.58,
2671
+ "learning_rate": 7.75695961285032e-06,
2672
+ "loss": 1.1296,
2673
+ "step": 444
2674
+ },
2675
+ {
2676
+ "epoch": 0.59,
2677
+ "learning_rate": 7.71538312951161e-06,
2678
+ "loss": 1.1393,
2679
+ "step": 445
2680
+ },
2681
+ {
2682
+ "epoch": 0.59,
2683
+ "learning_rate": 7.673848271421166e-06,
2684
+ "loss": 1.1197,
2685
+ "step": 446
2686
+ },
2687
+ {
2688
+ "epoch": 0.59,
2689
+ "learning_rate": 7.632355795335533e-06,
2690
+ "loss": 1.144,
2691
+ "step": 447
2692
+ },
2693
+ {
2694
+ "epoch": 0.59,
2695
+ "learning_rate": 7.590906457239073e-06,
2696
+ "loss": 1.1393,
2697
+ "step": 448
2698
+ },
2699
+ {
2700
+ "epoch": 0.59,
2701
+ "learning_rate": 7.549501012330184e-06,
2702
+ "loss": 1.1158,
2703
+ "step": 449
2704
+ },
2705
+ {
2706
+ "epoch": 0.59,
2707
+ "learning_rate": 7.508140215007526e-06,
2708
+ "loss": 1.1077,
2709
+ "step": 450
2710
+ },
2711
+ {
2712
+ "epoch": 0.59,
2713
+ "learning_rate": 7.466824818856296e-06,
2714
+ "loss": 1.1213,
2715
+ "step": 451
2716
+ },
2717
+ {
2718
+ "epoch": 0.6,
2719
+ "learning_rate": 7.4255555766345025e-06,
2720
+ "loss": 1.1235,
2721
+ "step": 452
2722
+ },
2723
+ {
2724
+ "epoch": 0.6,
2725
+ "learning_rate": 7.384333240259216e-06,
2726
+ "loss": 1.131,
2727
+ "step": 453
2728
+ },
2729
+ {
2730
+ "epoch": 0.6,
2731
+ "learning_rate": 7.34315856079291e-06,
2732
+ "loss": 1.0999,
2733
+ "step": 454
2734
+ },
2735
+ {
2736
+ "epoch": 0.6,
2737
+ "learning_rate": 7.3020322884297565e-06,
2738
+ "loss": 1.1296,
2739
+ "step": 455
2740
+ },
2741
+ {
2742
+ "epoch": 0.6,
2743
+ "learning_rate": 7.260955172481959e-06,
2744
+ "loss": 1.1073,
2745
+ "step": 456
2746
+ },
2747
+ {
2748
+ "epoch": 0.6,
2749
+ "learning_rate": 7.219927961366091e-06,
2750
+ "loss": 1.1283,
2751
+ "step": 457
2752
+ },
2753
+ {
2754
+ "epoch": 0.6,
2755
+ "learning_rate": 7.178951402589482e-06,
2756
+ "loss": 1.0866,
2757
+ "step": 458
2758
+ },
2759
+ {
2760
+ "epoch": 0.6,
2761
+ "learning_rate": 7.1380262427365885e-06,
2762
+ "loss": 1.1159,
2763
+ "step": 459
2764
+ },
2765
+ {
2766
+ "epoch": 0.61,
2767
+ "learning_rate": 7.097153227455379e-06,
2768
+ "loss": 1.1253,
2769
+ "step": 460
2770
+ },
2771
+ {
2772
+ "epoch": 0.61,
2773
+ "learning_rate": 7.056333101443761e-06,
2774
+ "loss": 1.1198,
2775
+ "step": 461
2776
+ },
2777
+ {
2778
+ "epoch": 0.61,
2779
+ "learning_rate": 7.01556660843602e-06,
2780
+ "loss": 1.1117,
2781
+ "step": 462
2782
+ },
2783
+ {
2784
+ "epoch": 0.61,
2785
+ "learning_rate": 6.974854491189243e-06,
2786
+ "loss": 1.1238,
2787
+ "step": 463
2788
+ },
2789
+ {
2790
+ "epoch": 0.61,
2791
+ "learning_rate": 6.934197491469818e-06,
2792
+ "loss": 1.1468,
2793
+ "step": 464
2794
+ },
2795
+ {
2796
+ "epoch": 0.61,
2797
+ "learning_rate": 6.893596350039896e-06,
2798
+ "loss": 1.1063,
2799
+ "step": 465
2800
+ },
2801
+ {
2802
+ "epoch": 0.61,
2803
+ "learning_rate": 6.853051806643898e-06,
2804
+ "loss": 1.1279,
2805
+ "step": 466
2806
+ },
2807
+ {
2808
+ "epoch": 0.62,
2809
+ "learning_rate": 6.812564599995042e-06,
2810
+ "loss": 1.1297,
2811
+ "step": 467
2812
+ },
2813
+ {
2814
+ "epoch": 0.62,
2815
+ "learning_rate": 6.772135467761889e-06,
2816
+ "loss": 1.1373,
2817
+ "step": 468
2818
+ },
2819
+ {
2820
+ "epoch": 0.62,
2821
+ "learning_rate": 6.731765146554891e-06,
2822
+ "loss": 1.119,
2823
+ "step": 469
2824
+ },
2825
+ {
2826
+ "epoch": 0.62,
2827
+ "learning_rate": 6.691454371912974e-06,
2828
+ "loss": 1.1026,
2829
+ "step": 470
2830
+ },
2831
+ {
2832
+ "epoch": 0.62,
2833
+ "learning_rate": 6.651203878290139e-06,
2834
+ "loss": 1.1303,
2835
+ "step": 471
2836
+ },
2837
+ {
2838
+ "epoch": 0.62,
2839
+ "learning_rate": 6.6110143990420824e-06,
2840
+ "loss": 1.1157,
2841
+ "step": 472
2842
+ },
2843
+ {
2844
+ "epoch": 0.62,
2845
+ "learning_rate": 6.570886666412823e-06,
2846
+ "loss": 1.0973,
2847
+ "step": 473
2848
+ },
2849
+ {
2850
+ "epoch": 0.62,
2851
+ "learning_rate": 6.5308214115213785e-06,
2852
+ "loss": 1.1377,
2853
+ "step": 474
2854
+ },
2855
+ {
2856
+ "epoch": 0.63,
2857
+ "learning_rate": 6.490819364348434e-06,
2858
+ "loss": 1.1418,
2859
+ "step": 475
2860
+ },
2861
+ {
2862
+ "epoch": 0.63,
2863
+ "learning_rate": 6.450881253723035e-06,
2864
+ "loss": 1.1307,
2865
+ "step": 476
2866
+ },
2867
+ {
2868
+ "epoch": 0.63,
2869
+ "learning_rate": 6.41100780730932e-06,
2870
+ "loss": 1.15,
2871
+ "step": 477
2872
+ },
2873
+ {
2874
+ "epoch": 0.63,
2875
+ "learning_rate": 6.371199751593264e-06,
2876
+ "loss": 1.1242,
2877
+ "step": 478
2878
+ },
2879
+ {
2880
+ "epoch": 0.63,
2881
+ "learning_rate": 6.331457811869437e-06,
2882
+ "loss": 1.1015,
2883
+ "step": 479
2884
+ },
2885
+ {
2886
+ "epoch": 0.63,
2887
+ "learning_rate": 6.291782712227776e-06,
2888
+ "loss": 1.1038,
2889
+ "step": 480
2890
+ },
2891
+ {
2892
+ "epoch": 0.63,
2893
+ "learning_rate": 6.2521751755404226e-06,
2894
+ "loss": 1.1292,
2895
+ "step": 481
2896
+ },
2897
+ {
2898
+ "epoch": 0.63,
2899
+ "learning_rate": 6.212635923448526e-06,
2900
+ "loss": 1.1506,
2901
+ "step": 482
2902
+ },
2903
+ {
2904
+ "epoch": 0.64,
2905
+ "learning_rate": 6.173165676349103e-06,
2906
+ "loss": 1.1054,
2907
+ "step": 483
2908
+ },
2909
+ {
2910
+ "epoch": 0.64,
2911
+ "learning_rate": 6.133765153381918e-06,
2912
+ "loss": 1.138,
2913
+ "step": 484
2914
+ },
2915
+ {
2916
+ "epoch": 0.64,
2917
+ "learning_rate": 6.094435072416379e-06,
2918
+ "loss": 1.13,
2919
+ "step": 485
2920
+ },
2921
+ {
2922
+ "epoch": 0.64,
2923
+ "learning_rate": 6.055176150038445e-06,
2924
+ "loss": 1.1082,
2925
+ "step": 486
2926
+ },
2927
+ {
2928
+ "epoch": 0.64,
2929
+ "learning_rate": 6.015989101537586e-06,
2930
+ "loss": 1.1527,
2931
+ "step": 487
2932
+ },
2933
+ {
2934
+ "epoch": 0.64,
2935
+ "learning_rate": 5.976874640893751e-06,
2936
+ "loss": 1.1561,
2937
+ "step": 488
2938
+ },
2939
+ {
2940
+ "epoch": 0.64,
2941
+ "learning_rate": 5.937833480764339e-06,
2942
+ "loss": 1.1325,
2943
+ "step": 489
2944
+ },
2945
+ {
2946
+ "epoch": 0.65,
2947
+ "learning_rate": 5.898866332471241e-06,
2948
+ "loss": 1.112,
2949
+ "step": 490
2950
+ },
2951
+ {
2952
+ "epoch": 0.65,
2953
+ "learning_rate": 5.859973905987866e-06,
2954
+ "loss": 1.1376,
2955
+ "step": 491
2956
+ },
2957
+ {
2958
+ "epoch": 0.65,
2959
+ "learning_rate": 5.821156909926202e-06,
2960
+ "loss": 1.1393,
2961
+ "step": 492
2962
+ },
2963
+ {
2964
+ "epoch": 0.65,
2965
+ "learning_rate": 5.782416051523909e-06,
2966
+ "loss": 1.1445,
2967
+ "step": 493
2968
+ },
2969
+ {
2970
+ "epoch": 0.65,
2971
+ "learning_rate": 5.743752036631443e-06,
2972
+ "loss": 1.1023,
2973
+ "step": 494
2974
+ },
2975
+ {
2976
+ "epoch": 0.65,
2977
+ "learning_rate": 5.7051655696991825e-06,
2978
+ "loss": 1.137,
2979
+ "step": 495
2980
+ },
2981
+ {
2982
+ "epoch": 0.65,
2983
+ "learning_rate": 5.666657353764594e-06,
2984
+ "loss": 1.1152,
2985
+ "step": 496
2986
+ },
2987
+ {
2988
+ "epoch": 0.65,
2989
+ "learning_rate": 5.628228090439434e-06,
2990
+ "loss": 1.1422,
2991
+ "step": 497
2992
+ },
2993
+ {
2994
+ "epoch": 0.66,
2995
+ "learning_rate": 5.589878479896959e-06,
2996
+ "loss": 1.125,
2997
+ "step": 498
2998
+ },
2999
+ {
3000
+ "epoch": 0.66,
3001
+ "learning_rate": 5.55160922085916e-06,
3002
+ "loss": 1.1307,
3003
+ "step": 499
3004
+ },
3005
+ {
3006
+ "epoch": 0.66,
3007
+ "learning_rate": 5.513421010584044e-06,
3008
+ "loss": 1.1222,
3009
+ "step": 500
3010
+ },
3011
+ {
3012
+ "epoch": 0.66,
3013
+ "learning_rate": 5.4753145448529284e-06,
3014
+ "loss": 1.1179,
3015
+ "step": 501
3016
+ },
3017
+ {
3018
+ "epoch": 0.66,
3019
+ "learning_rate": 5.437290517957767e-06,
3020
+ "loss": 1.0994,
3021
+ "step": 502
3022
+ },
3023
+ {
3024
+ "epoch": 0.66,
3025
+ "learning_rate": 5.399349622688479e-06,
3026
+ "loss": 1.1345,
3027
+ "step": 503
3028
+ },
3029
+ {
3030
+ "epoch": 0.66,
3031
+ "learning_rate": 5.3614925503203586e-06,
3032
+ "loss": 1.1318,
3033
+ "step": 504
3034
+ },
3035
+ {
3036
+ "epoch": 0.67,
3037
+ "learning_rate": 5.323719990601459e-06,
3038
+ "loss": 1.1091,
3039
+ "step": 505
3040
+ },
3041
+ {
3042
+ "epoch": 0.67,
3043
+ "learning_rate": 5.286032631740023e-06,
3044
+ "loss": 1.1343,
3045
+ "step": 506
3046
+ },
3047
+ {
3048
+ "epoch": 0.67,
3049
+ "learning_rate": 5.248431160391963e-06,
3050
+ "loss": 1.1645,
3051
+ "step": 507
3052
+ },
3053
+ {
3054
+ "epoch": 0.67,
3055
+ "learning_rate": 5.2109162616483325e-06,
3056
+ "loss": 1.0957,
3057
+ "step": 508
3058
+ },
3059
+ {
3060
+ "epoch": 0.67,
3061
+ "learning_rate": 5.1734886190228496e-06,
3062
+ "loss": 1.1548,
3063
+ "step": 509
3064
+ },
3065
+ {
3066
+ "epoch": 0.67,
3067
+ "learning_rate": 5.136148914439441e-06,
3068
+ "loss": 1.1281,
3069
+ "step": 510
3070
+ },
3071
+ {
3072
+ "epoch": 0.67,
3073
+ "learning_rate": 5.098897828219831e-06,
3074
+ "loss": 1.1126,
3075
+ "step": 511
3076
+ },
3077
+ {
3078
+ "epoch": 0.67,
3079
+ "learning_rate": 5.061736039071124e-06,
3080
+ "loss": 1.0938,
3081
+ "step": 512
3082
+ },
3083
+ {
3084
+ "epoch": 0.68,
3085
+ "learning_rate": 5.024664224073454e-06,
3086
+ "loss": 1.1623,
3087
+ "step": 513
3088
+ },
3089
+ {
3090
+ "epoch": 0.68,
3091
+ "learning_rate": 4.987683058667651e-06,
3092
+ "loss": 1.1411,
3093
+ "step": 514
3094
+ },
3095
+ {
3096
+ "epoch": 0.68,
3097
+ "learning_rate": 4.950793216642923e-06,
3098
+ "loss": 1.1559,
3099
+ "step": 515
3100
+ },
3101
+ {
3102
+ "epoch": 0.68,
3103
+ "learning_rate": 4.913995370124578e-06,
3104
+ "loss": 1.1341,
3105
+ "step": 516
3106
+ },
3107
+ {
3108
+ "epoch": 0.68,
3109
+ "learning_rate": 4.877290189561795e-06,
3110
+ "loss": 1.1211,
3111
+ "step": 517
3112
+ },
3113
+ {
3114
+ "epoch": 0.68,
3115
+ "learning_rate": 4.840678343715399e-06,
3116
+ "loss": 1.1156,
3117
+ "step": 518
3118
+ },
3119
+ {
3120
+ "epoch": 0.68,
3121
+ "learning_rate": 4.804160499645667e-06,
3122
+ "loss": 1.1125,
3123
+ "step": 519
3124
+ },
3125
+ {
3126
+ "epoch": 0.69,
3127
+ "learning_rate": 4.767737322700185e-06,
3128
+ "loss": 1.1397,
3129
+ "step": 520
3130
+ },
3131
+ {
3132
+ "epoch": 0.69,
3133
+ "learning_rate": 4.7314094765017325e-06,
3134
+ "loss": 1.1322,
3135
+ "step": 521
3136
+ },
3137
+ {
3138
+ "epoch": 0.69,
3139
+ "learning_rate": 4.695177622936169e-06,
3140
+ "loss": 1.139,
3141
+ "step": 522
3142
+ },
3143
+ {
3144
+ "epoch": 0.69,
3145
+ "learning_rate": 4.659042422140399e-06,
3146
+ "loss": 1.143,
3147
+ "step": 523
3148
+ },
3149
+ {
3150
+ "epoch": 0.69,
3151
+ "learning_rate": 4.623004532490328e-06,
3152
+ "loss": 1.1266,
3153
+ "step": 524
3154
+ },
3155
+ {
3156
+ "epoch": 0.69,
3157
+ "learning_rate": 4.587064610588881e-06,
3158
+ "loss": 1.1283,
3159
+ "step": 525
3160
+ },
3161
+ {
3162
+ "epoch": 0.69,
3163
+ "learning_rate": 4.551223311254013e-06,
3164
+ "loss": 1.1291,
3165
+ "step": 526
3166
+ },
3167
+ {
3168
+ "epoch": 0.69,
3169
+ "learning_rate": 4.515481287506811e-06,
3170
+ "loss": 1.1188,
3171
+ "step": 527
3172
+ },
3173
+ {
3174
+ "epoch": 0.7,
3175
+ "learning_rate": 4.479839190559583e-06,
3176
+ "loss": 1.115,
3177
+ "step": 528
3178
+ },
3179
+ {
3180
+ "epoch": 0.7,
3181
+ "learning_rate": 4.444297669803981e-06,
3182
+ "loss": 1.1354,
3183
+ "step": 529
3184
+ },
3185
+ {
3186
+ "epoch": 0.7,
3187
+ "learning_rate": 4.408857372799179e-06,
3188
+ "loss": 1.1182,
3189
+ "step": 530
3190
+ },
3191
+ {
3192
+ "epoch": 0.7,
3193
+ "learning_rate": 4.37351894526009e-06,
3194
+ "loss": 1.1767,
3195
+ "step": 531
3196
+ },
3197
+ {
3198
+ "epoch": 0.7,
3199
+ "learning_rate": 4.338283031045567e-06,
3200
+ "loss": 1.1639,
3201
+ "step": 532
3202
+ },
3203
+ {
3204
+ "epoch": 0.7,
3205
+ "learning_rate": 4.303150272146706e-06,
3206
+ "loss": 1.1483,
3207
+ "step": 533
3208
+ },
3209
+ {
3210
+ "epoch": 0.7,
3211
+ "learning_rate": 4.268121308675132e-06,
3212
+ "loss": 1.1074,
3213
+ "step": 534
3214
+ },
3215
+ {
3216
+ "epoch": 0.7,
3217
+ "learning_rate": 4.2331967788513295e-06,
3218
+ "loss": 1.133,
3219
+ "step": 535
3220
+ },
3221
+ {
3222
+ "epoch": 0.71,
3223
+ "learning_rate": 4.198377318993035e-06,
3224
+ "loss": 1.1293,
3225
+ "step": 536
3226
+ },
3227
+ {
3228
+ "epoch": 0.71,
3229
+ "learning_rate": 4.1636635635036235e-06,
3230
+ "loss": 1.1178,
3231
+ "step": 537
3232
+ },
3233
+ {
3234
+ "epoch": 0.71,
3235
+ "learning_rate": 4.129056144860567e-06,
3236
+ "loss": 1.161,
3237
+ "step": 538
3238
+ },
3239
+ {
3240
+ "epoch": 0.71,
3241
+ "learning_rate": 4.094555693603891e-06,
3242
+ "loss": 1.1374,
3243
+ "step": 539
3244
+ },
3245
+ {
3246
+ "epoch": 0.71,
3247
+ "learning_rate": 4.060162838324708e-06,
3248
+ "loss": 1.1135,
3249
+ "step": 540
3250
+ },
3251
+ {
3252
+ "epoch": 0.71,
3253
+ "learning_rate": 4.025878205653747e-06,
3254
+ "loss": 1.1246,
3255
+ "step": 541
3256
+ },
3257
+ {
3258
+ "epoch": 0.71,
3259
+ "learning_rate": 3.991702420249941e-06,
3260
+ "loss": 1.1251,
3261
+ "step": 542
3262
+ },
3263
+ {
3264
+ "epoch": 0.72,
3265
+ "learning_rate": 3.957636104789056e-06,
3266
+ "loss": 1.123,
3267
+ "step": 543
3268
+ },
3269
+ {
3270
+ "epoch": 0.72,
3271
+ "learning_rate": 3.9236798799523375e-06,
3272
+ "loss": 1.1085,
3273
+ "step": 544
3274
+ },
3275
+ {
3276
+ "epoch": 0.72,
3277
+ "learning_rate": 3.8898343644151945e-06,
3278
+ "loss": 1.1192,
3279
+ "step": 545
3280
+ },
3281
+ {
3282
+ "epoch": 0.72,
3283
+ "learning_rate": 3.856100174835945e-06,
3284
+ "loss": 1.1267,
3285
+ "step": 546
3286
+ },
3287
+ {
3288
+ "epoch": 0.72,
3289
+ "learning_rate": 3.822477925844564e-06,
3290
+ "loss": 1.1303,
3291
+ "step": 547
3292
+ },
3293
+ {
3294
+ "epoch": 0.72,
3295
+ "learning_rate": 3.7889682300315e-06,
3296
+ "loss": 1.1156,
3297
+ "step": 548
3298
+ },
3299
+ {
3300
+ "epoch": 0.72,
3301
+ "learning_rate": 3.755571697936493e-06,
3302
+ "loss": 1.1575,
3303
+ "step": 549
3304
+ },
3305
+ {
3306
+ "epoch": 0.72,
3307
+ "learning_rate": 3.722288938037478e-06,
3308
+ "loss": 1.118,
3309
+ "step": 550
3310
+ },
3311
+ {
3312
+ "epoch": 0.73,
3313
+ "learning_rate": 3.689120556739475e-06,
3314
+ "loss": 1.1237,
3315
+ "step": 551
3316
+ },
3317
+ {
3318
+ "epoch": 0.73,
3319
+ "learning_rate": 3.6560671583635467e-06,
3320
+ "loss": 1.1329,
3321
+ "step": 552
3322
+ },
3323
+ {
3324
+ "epoch": 0.73,
3325
+ "learning_rate": 3.6231293451357994e-06,
3326
+ "loss": 1.1065,
3327
+ "step": 553
3328
+ },
3329
+ {
3330
+ "epoch": 0.73,
3331
+ "learning_rate": 3.590307717176401e-06,
3332
+ "loss": 1.1285,
3333
+ "step": 554
3334
+ },
3335
+ {
3336
+ "epoch": 0.73,
3337
+ "learning_rate": 3.557602872488638e-06,
3338
+ "loss": 1.1208,
3339
+ "step": 555
3340
+ },
3341
+ {
3342
+ "epoch": 0.73,
3343
+ "learning_rate": 3.525015406948039e-06,
3344
+ "loss": 1.1264,
3345
+ "step": 556
3346
+ },
3347
+ {
3348
+ "epoch": 0.73,
3349
+ "learning_rate": 3.492545914291512e-06,
3350
+ "loss": 1.1055,
3351
+ "step": 557
3352
+ },
3353
+ {
3354
+ "epoch": 0.74,
3355
+ "learning_rate": 3.4601949861065086e-06,
3356
+ "loss": 1.1358,
3357
+ "step": 558
3358
+ },
3359
+ {
3360
+ "epoch": 0.74,
3361
+ "learning_rate": 3.4279632118202744e-06,
3362
+ "loss": 1.1053,
3363
+ "step": 559
3364
+ },
3365
+ {
3366
+ "epoch": 0.74,
3367
+ "learning_rate": 3.3958511786890923e-06,
3368
+ "loss": 1.1158,
3369
+ "step": 560
3370
+ },
3371
+ {
3372
+ "epoch": 0.74,
3373
+ "learning_rate": 3.3638594717875807e-06,
3374
+ "loss": 1.1195,
3375
+ "step": 561
3376
+ },
3377
+ {
3378
+ "epoch": 0.74,
3379
+ "learning_rate": 3.33198867399804e-06,
3380
+ "loss": 1.1184,
3381
+ "step": 562
3382
+ },
3383
+ {
3384
+ "epoch": 0.74,
3385
+ "learning_rate": 3.3002393659998357e-06,
3386
+ "loss": 1.1185,
3387
+ "step": 563
3388
+ },
3389
+ {
3390
+ "epoch": 0.74,
3391
+ "learning_rate": 3.2686121262588165e-06,
3392
+ "loss": 1.1174,
3393
+ "step": 564
3394
+ },
3395
+ {
3396
+ "epoch": 0.74,
3397
+ "learning_rate": 3.2371075310167634e-06,
3398
+ "loss": 1.1303,
3399
+ "step": 565
3400
+ },
3401
+ {
3402
+ "epoch": 0.75,
3403
+ "learning_rate": 3.205726154280905e-06,
3404
+ "loss": 1.0918,
3405
+ "step": 566
3406
+ },
3407
+ {
3408
+ "epoch": 0.75,
3409
+ "learning_rate": 3.174468567813461e-06,
3410
+ "loss": 1.1189,
3411
+ "step": 567
3412
+ },
3413
+ {
3414
+ "epoch": 0.75,
3415
+ "learning_rate": 3.143335341121202e-06,
3416
+ "loss": 1.1038,
3417
+ "step": 568
3418
+ },
3419
+ {
3420
+ "epoch": 0.75,
3421
+ "learning_rate": 3.1123270414451035e-06,
3422
+ "loss": 1.1535,
3423
+ "step": 569
3424
+ },
3425
+ {
3426
+ "epoch": 0.75,
3427
+ "learning_rate": 3.081444233749994e-06,
3428
+ "loss": 1.1417,
3429
+ "step": 570
3430
+ },
3431
+ {
3432
+ "epoch": 0.75,
3433
+ "learning_rate": 3.050687480714256e-06,
3434
+ "loss": 1.1267,
3435
+ "step": 571
3436
+ },
3437
+ {
3438
+ "epoch": 0.75,
3439
+ "learning_rate": 3.0200573427195877e-06,
3440
+ "loss": 1.1123,
3441
+ "step": 572
3442
+ },
3443
+ {
3444
+ "epoch": 0.75,
3445
+ "learning_rate": 2.9895543778407875e-06,
3446
+ "loss": 1.1269,
3447
+ "step": 573
3448
+ },
3449
+ {
3450
+ "epoch": 0.76,
3451
+ "learning_rate": 2.959179141835591e-06,
3452
+ "loss": 1.1319,
3453
+ "step": 574
3454
+ },
3455
+ {
3456
+ "epoch": 0.76,
3457
+ "learning_rate": 2.9289321881345257e-06,
3458
+ "loss": 1.1375,
3459
+ "step": 575
3460
+ },
3461
+ {
3462
+ "epoch": 0.76,
3463
+ "learning_rate": 2.898814067830855e-06,
3464
+ "loss": 1.1272,
3465
+ "step": 576
3466
+ },
3467
+ {
3468
+ "epoch": 0.76,
3469
+ "learning_rate": 2.868825329670524e-06,
3470
+ "loss": 1.1279,
3471
+ "step": 577
3472
+ },
3473
+ {
3474
+ "epoch": 0.76,
3475
+ "learning_rate": 2.83896652004215e-06,
3476
+ "loss": 1.1341,
3477
+ "step": 578
3478
+ },
3479
+ {
3480
+ "epoch": 0.76,
3481
+ "learning_rate": 2.809238182967092e-06,
3482
+ "loss": 1.1252,
3483
+ "step": 579
3484
+ },
3485
+ {
3486
+ "epoch": 0.76,
3487
+ "learning_rate": 2.779640860089523e-06,
3488
+ "loss": 1.1369,
3489
+ "step": 580
3490
+ },
3491
+ {
3492
+ "epoch": 0.77,
3493
+ "learning_rate": 2.7501750906665603e-06,
3494
+ "loss": 1.0889,
3495
+ "step": 581
3496
+ },
3497
+ {
3498
+ "epoch": 0.77,
3499
+ "learning_rate": 2.7208414115584436e-06,
3500
+ "loss": 1.1314,
3501
+ "step": 582
3502
+ },
3503
+ {
3504
+ "epoch": 0.77,
3505
+ "learning_rate": 2.691640357218759e-06,
3506
+ "loss": 1.1159,
3507
+ "step": 583
3508
+ },
3509
+ {
3510
+ "epoch": 0.77,
3511
+ "learning_rate": 2.662572459684699e-06,
3512
+ "loss": 1.1012,
3513
+ "step": 584
3514
+ },
3515
+ {
3516
+ "epoch": 0.77,
3517
+ "learning_rate": 2.6336382485673574e-06,
3518
+ "loss": 1.1273,
3519
+ "step": 585
3520
+ },
3521
+ {
3522
+ "epoch": 0.77,
3523
+ "learning_rate": 2.6048382510420954e-06,
3524
+ "loss": 1.1127,
3525
+ "step": 586
3526
+ },
3527
+ {
3528
+ "epoch": 0.77,
3529
+ "learning_rate": 2.576172991838933e-06,
3530
+ "loss": 1.1234,
3531
+ "step": 587
3532
+ },
3533
+ {
3534
+ "epoch": 0.77,
3535
+ "learning_rate": 2.547642993232976e-06,
3536
+ "loss": 1.1536,
3537
+ "step": 588
3538
+ },
3539
+ {
3540
+ "epoch": 0.78,
3541
+ "learning_rate": 2.519248775034918e-06,
3542
+ "loss": 1.1439,
3543
+ "step": 589
3544
+ },
3545
+ {
3546
+ "epoch": 0.78,
3547
+ "learning_rate": 2.490990854581563e-06,
3548
+ "loss": 1.1128,
3549
+ "step": 590
3550
+ },
3551
+ {
3552
+ "epoch": 0.78,
3553
+ "learning_rate": 2.4628697467263916e-06,
3554
+ "loss": 1.1272,
3555
+ "step": 591
3556
+ },
3557
+ {
3558
+ "epoch": 0.78,
3559
+ "learning_rate": 2.4348859638301857e-06,
3560
+ "loss": 1.1564,
3561
+ "step": 592
3562
+ },
3563
+ {
3564
+ "epoch": 0.78,
3565
+ "learning_rate": 2.4070400157517036e-06,
3566
+ "loss": 1.1108,
3567
+ "step": 593
3568
+ },
3569
+ {
3570
+ "epoch": 0.78,
3571
+ "learning_rate": 2.3793324098383796e-06,
3572
+ "loss": 1.117,
3573
+ "step": 594
3574
+ },
3575
+ {
3576
+ "epoch": 0.78,
3577
+ "learning_rate": 2.351763650917074e-06,
3578
+ "loss": 1.1151,
3579
+ "step": 595
3580
+ },
3581
+ {
3582
+ "epoch": 0.79,
3583
+ "learning_rate": 2.3243342412848923e-06,
3584
+ "loss": 1.102,
3585
+ "step": 596
3586
+ },
3587
+ {
3588
+ "epoch": 0.79,
3589
+ "learning_rate": 2.2970446807000237e-06,
3590
+ "loss": 1.1295,
3591
+ "step": 597
3592
+ },
3593
+ {
3594
+ "epoch": 0.79,
3595
+ "learning_rate": 2.26989546637263e-06,
3596
+ "loss": 1.1301,
3597
+ "step": 598
3598
+ },
3599
+ {
3600
+ "epoch": 0.79,
3601
+ "learning_rate": 2.2428870929558012e-06,
3602
+ "loss": 1.1257,
3603
+ "step": 599
3604
+ },
3605
+ {
3606
+ "epoch": 0.79,
3607
+ "learning_rate": 2.2160200525365326e-06,
3608
+ "loss": 1.1158,
3609
+ "step": 600
3610
+ },
3611
+ {
3612
+ "epoch": 0.79,
3613
+ "learning_rate": 2.1892948346267583e-06,
3614
+ "loss": 1.1461,
3615
+ "step": 601
3616
+ },
3617
+ {
3618
+ "epoch": 0.79,
3619
+ "learning_rate": 2.1627119261544348e-06,
3620
+ "loss": 1.1388,
3621
+ "step": 602
3622
+ },
3623
+ {
3624
+ "epoch": 0.79,
3625
+ "learning_rate": 2.1362718114546777e-06,
3626
+ "loss": 1.1578,
3627
+ "step": 603
3628
+ },
3629
+ {
3630
+ "epoch": 0.8,
3631
+ "learning_rate": 2.109974972260921e-06,
3632
+ "loss": 1.1581,
3633
+ "step": 604
3634
+ },
3635
+ {
3636
+ "epoch": 0.8,
3637
+ "learning_rate": 2.0838218876961524e-06,
3638
+ "loss": 1.149,
3639
+ "step": 605
3640
+ },
3641
+ {
3642
+ "epoch": 0.8,
3643
+ "learning_rate": 2.057813034264181e-06,
3644
+ "loss": 1.1258,
3645
+ "step": 606
3646
+ },
3647
+ {
3648
+ "epoch": 0.8,
3649
+ "learning_rate": 2.0319488858409552e-06,
3650
+ "loss": 1.1312,
3651
+ "step": 607
3652
+ },
3653
+ {
3654
+ "epoch": 0.8,
3655
+ "learning_rate": 2.0062299136659203e-06,
3656
+ "loss": 1.1434,
3657
+ "step": 608
3658
+ },
3659
+ {
3660
+ "epoch": 0.8,
3661
+ "learning_rate": 1.980656586333449e-06,
3662
+ "loss": 1.1189,
3663
+ "step": 609
3664
+ },
3665
+ {
3666
+ "epoch": 0.8,
3667
+ "learning_rate": 1.955229369784295e-06,
3668
+ "loss": 1.1115,
3669
+ "step": 610
3670
+ },
3671
+ {
3672
+ "epoch": 0.8,
3673
+ "learning_rate": 1.929948727297096e-06,
3674
+ "loss": 1.1223,
3675
+ "step": 611
3676
+ },
3677
+ {
3678
+ "epoch": 0.81,
3679
+ "learning_rate": 1.9048151194799435e-06,
3680
+ "loss": 1.0928,
3681
+ "step": 612
3682
+ },
3683
+ {
3684
+ "epoch": 0.81,
3685
+ "learning_rate": 1.8798290042619949e-06,
3686
+ "loss": 1.1151,
3687
+ "step": 613
3688
+ },
3689
+ {
3690
+ "epoch": 0.81,
3691
+ "learning_rate": 1.8549908368851099e-06,
3692
+ "loss": 1.1427,
3693
+ "step": 614
3694
+ },
3695
+ {
3696
+ "epoch": 0.81,
3697
+ "learning_rate": 1.8303010698955803e-06,
3698
+ "loss": 1.1106,
3699
+ "step": 615
3700
+ },
3701
+ {
3702
+ "epoch": 0.81,
3703
+ "learning_rate": 1.8057601531358693e-06,
3704
+ "loss": 1.1634,
3705
+ "step": 616
3706
+ },
3707
+ {
3708
+ "epoch": 0.81,
3709
+ "learning_rate": 1.7813685337364205e-06,
3710
+ "loss": 1.1385,
3711
+ "step": 617
3712
+ },
3713
+ {
3714
+ "epoch": 0.81,
3715
+ "learning_rate": 1.7571266561075073e-06,
3716
+ "loss": 1.1263,
3717
+ "step": 618
3718
+ },
3719
+ {
3720
+ "epoch": 0.82,
3721
+ "learning_rate": 1.7330349619311415e-06,
3722
+ "loss": 1.1237,
3723
+ "step": 619
3724
+ },
3725
+ {
3726
+ "epoch": 0.82,
3727
+ "learning_rate": 1.7090938901530264e-06,
3728
+ "loss": 1.1577,
3729
+ "step": 620
3730
+ },
3731
+ {
3732
+ "epoch": 0.82,
3733
+ "learning_rate": 1.6853038769745466e-06,
3734
+ "loss": 1.1035,
3735
+ "step": 621
3736
+ },
3737
+ {
3738
+ "epoch": 0.82,
3739
+ "learning_rate": 1.6616653558448437e-06,
3740
+ "loss": 1.1248,
3741
+ "step": 622
3742
+ },
3743
+ {
3744
+ "epoch": 0.82,
3745
+ "learning_rate": 1.638178757452894e-06,
3746
+ "loss": 1.1165,
3747
+ "step": 623
3748
+ },
3749
+ {
3750
+ "epoch": 0.82,
3751
+ "learning_rate": 1.614844509719674e-06,
3752
+ "loss": 1.1144,
3753
+ "step": 624
3754
+ },
3755
+ {
3756
+ "epoch": 0.82,
3757
+ "learning_rate": 1.5916630377903696e-06,
3758
+ "loss": 1.1142,
3759
+ "step": 625
3760
+ },
3761
+ {
3762
+ "epoch": 0.82,
3763
+ "learning_rate": 1.5686347640266208e-06,
3764
+ "loss": 1.0993,
3765
+ "step": 626
3766
+ },
3767
+ {
3768
+ "epoch": 0.83,
3769
+ "learning_rate": 1.5457601079988226e-06,
3770
+ "loss": 1.1667,
3771
+ "step": 627
3772
+ },
3773
+ {
3774
+ "epoch": 0.83,
3775
+ "learning_rate": 1.5230394864784925e-06,
3776
+ "loss": 1.0996,
3777
+ "step": 628
3778
+ },
3779
+ {
3780
+ "epoch": 0.83,
3781
+ "learning_rate": 1.5004733134306692e-06,
3782
+ "loss": 1.1243,
3783
+ "step": 629
3784
+ },
3785
+ {
3786
+ "epoch": 0.83,
3787
+ "learning_rate": 1.478062000006375e-06,
3788
+ "loss": 1.1052,
3789
+ "step": 630
3790
+ },
3791
+ {
3792
+ "epoch": 0.83,
3793
+ "learning_rate": 1.4558059545351144e-06,
3794
+ "loss": 1.1256,
3795
+ "step": 631
3796
+ },
3797
+ {
3798
+ "epoch": 0.83,
3799
+ "learning_rate": 1.4337055825174506e-06,
3800
+ "loss": 1.0953,
3801
+ "step": 632
3802
+ },
3803
+ {
3804
+ "epoch": 0.83,
3805
+ "learning_rate": 1.4117612866176022e-06,
3806
+ "loss": 1.1087,
3807
+ "step": 633
3808
+ },
3809
+ {
3810
+ "epoch": 0.84,
3811
+ "learning_rate": 1.3899734666561138e-06,
3812
+ "loss": 1.123,
3813
+ "step": 634
3814
+ },
3815
+ {
3816
+ "epoch": 0.84,
3817
+ "learning_rate": 1.3683425196025734e-06,
3818
+ "loss": 1.1144,
3819
+ "step": 635
3820
+ },
3821
+ {
3822
+ "epoch": 0.84,
3823
+ "learning_rate": 1.3468688395683783e-06,
3824
+ "loss": 1.1452,
3825
+ "step": 636
3826
+ },
3827
+ {
3828
+ "epoch": 0.84,
3829
+ "learning_rate": 1.325552817799547e-06,
3830
+ "loss": 1.1146,
3831
+ "step": 637
3832
+ },
3833
+ {
3834
+ "epoch": 0.84,
3835
+ "learning_rate": 1.3043948426696019e-06,
3836
+ "loss": 1.1461,
3837
+ "step": 638
3838
+ },
3839
+ {
3840
+ "epoch": 0.84,
3841
+ "learning_rate": 1.2833952996724864e-06,
3842
+ "loss": 1.143,
3843
+ "step": 639
3844
+ },
3845
+ {
3846
+ "epoch": 0.84,
3847
+ "learning_rate": 1.2625545714155474e-06,
3848
+ "loss": 1.1151,
3849
+ "step": 640
3850
+ },
3851
+ {
3852
+ "epoch": 0.84,
3853
+ "learning_rate": 1.24187303761255e-06,
3854
+ "loss": 1.1066,
3855
+ "step": 641
3856
+ },
3857
+ {
3858
+ "epoch": 0.85,
3859
+ "learning_rate": 1.221351075076781e-06,
3860
+ "loss": 1.1535,
3861
+ "step": 642
3862
+ },
3863
+ {
3864
+ "epoch": 0.85,
3865
+ "learning_rate": 1.2009890577141625e-06,
3866
+ "loss": 1.1223,
3867
+ "step": 643
3868
+ },
3869
+ {
3870
+ "epoch": 0.85,
3871
+ "learning_rate": 1.1807873565164507e-06,
3872
+ "loss": 1.1557,
3873
+ "step": 644
3874
+ },
3875
+ {
3876
+ "epoch": 0.85,
3877
+ "learning_rate": 1.1607463395544782e-06,
3878
+ "loss": 1.1301,
3879
+ "step": 645
3880
+ },
3881
+ {
3882
+ "epoch": 0.85,
3883
+ "learning_rate": 1.1408663719714418e-06,
3884
+ "loss": 1.139,
3885
+ "step": 646
3886
+ },
3887
+ {
3888
+ "epoch": 0.85,
3889
+ "learning_rate": 1.121147815976248e-06,
3890
+ "loss": 1.0843,
3891
+ "step": 647
3892
+ },
3893
+ {
3894
+ "epoch": 0.85,
3895
+ "learning_rate": 1.1015910308369239e-06,
3896
+ "loss": 1.0918,
3897
+ "step": 648
3898
+ },
3899
+ {
3900
+ "epoch": 0.86,
3901
+ "learning_rate": 1.0821963728740626e-06,
3902
+ "loss": 1.106,
3903
+ "step": 649
3904
+ },
3905
+ {
3906
+ "epoch": 0.86,
3907
+ "learning_rate": 1.062964195454329e-06,
3908
+ "loss": 1.1487,
3909
+ "step": 650
3910
+ },
3911
+ {
3912
+ "epoch": 0.86,
3913
+ "learning_rate": 1.0438948489840327e-06,
3914
+ "loss": 1.0996,
3915
+ "step": 651
3916
+ },
3917
+ {
3918
+ "epoch": 0.86,
3919
+ "learning_rate": 1.0249886809027355e-06,
3920
+ "loss": 1.115,
3921
+ "step": 652
3922
+ },
3923
+ {
3924
+ "epoch": 0.86,
3925
+ "learning_rate": 1.0062460356769189e-06,
3926
+ "loss": 1.1227,
3927
+ "step": 653
3928
+ },
3929
+ {
3930
+ "epoch": 0.86,
3931
+ "learning_rate": 9.876672547937117e-07,
3932
+ "loss": 1.0986,
3933
+ "step": 654
3934
+ },
3935
+ {
3936
+ "epoch": 0.86,
3937
+ "learning_rate": 9.692526767546727e-07,
3938
+ "loss": 1.1219,
3939
+ "step": 655
3940
+ },
3941
+ {
3942
+ "epoch": 0.86,
3943
+ "learning_rate": 9.51002637069619e-07,
3944
+ "loss": 1.1248,
3945
+ "step": 656
3946
+ },
3947
+ {
3948
+ "epoch": 0.87,
3949
+ "learning_rate": 9.32917468250506e-07,
3950
+ "loss": 1.1461,
3951
+ "step": 657
3952
+ },
3953
+ {
3954
+ "epoch": 0.87,
3955
+ "learning_rate": 9.149974998053823e-07,
3956
+ "loss": 1.1145,
3957
+ "step": 658
3958
+ },
3959
+ {
3960
+ "epoch": 0.87,
3961
+ "learning_rate": 8.972430582323788e-07,
3962
+ "loss": 1.1498,
3963
+ "step": 659
3964
+ },
3965
+ {
3966
+ "epoch": 0.87,
3967
+ "learning_rate": 8.796544670137574e-07,
3968
+ "loss": 1.1069,
3969
+ "step": 660
3970
+ },
3971
+ {
3972
+ "epoch": 0.87,
3973
+ "learning_rate": 8.622320466100242e-07,
3974
+ "loss": 1.1415,
3975
+ "step": 661
3976
+ },
3977
+ {
3978
+ "epoch": 0.87,
3979
+ "learning_rate": 8.449761144540869e-07,
3980
+ "loss": 1.1049,
3981
+ "step": 662
3982
+ },
3983
+ {
3984
+ "epoch": 0.87,
3985
+ "learning_rate": 8.278869849454718e-07,
3986
+ "loss": 1.1194,
3987
+ "step": 663
3988
+ },
3989
+ {
3990
+ "epoch": 0.87,
3991
+ "learning_rate": 8.109649694445898e-07,
3992
+ "loss": 1.1237,
3993
+ "step": 664
3994
+ },
3995
+ {
3996
+ "epoch": 0.88,
3997
+ "learning_rate": 7.942103762670783e-07,
3998
+ "loss": 1.1195,
3999
+ "step": 665
4000
+ },
4001
+ {
4002
+ "epoch": 0.88,
4003
+ "learning_rate": 7.776235106781704e-07,
4004
+ "loss": 1.1165,
4005
+ "step": 666
4006
+ },
4007
+ {
4008
+ "epoch": 0.88,
4009
+ "learning_rate": 7.612046748871327e-07,
4010
+ "loss": 1.1178,
4011
+ "step": 667
4012
+ },
4013
+ {
4014
+ "epoch": 0.88,
4015
+ "learning_rate": 7.449541680417704e-07,
4016
+ "loss": 1.1439,
4017
+ "step": 668
4018
+ },
4019
+ {
4020
+ "epoch": 0.88,
4021
+ "learning_rate": 7.288722862229691e-07,
4022
+ "loss": 1.0893,
4023
+ "step": 669
4024
+ },
4025
+ {
4026
+ "epoch": 0.88,
4027
+ "learning_rate": 7.12959322439295e-07,
4028
+ "loss": 1.1431,
4029
+ "step": 670
4030
+ },
4031
+ {
4032
+ "epoch": 0.88,
4033
+ "learning_rate": 6.972155666216684e-07,
4034
+ "loss": 1.1192,
4035
+ "step": 671
4036
+ },
4037
+ {
4038
+ "epoch": 0.89,
4039
+ "learning_rate": 6.816413056180748e-07,
4040
+ "loss": 1.131,
4041
+ "step": 672
4042
+ },
4043
+ {
4044
+ "epoch": 0.89,
4045
+ "learning_rate": 6.662368231883388e-07,
4046
+ "loss": 1.1401,
4047
+ "step": 673
4048
+ },
4049
+ {
4050
+ "epoch": 0.89,
4051
+ "learning_rate": 6.510023999989501e-07,
4052
+ "loss": 1.1095,
4053
+ "step": 674
4054
+ },
4055
+ {
4056
+ "epoch": 0.89,
4057
+ "learning_rate": 6.359383136179598e-07,
4058
+ "loss": 1.1282,
4059
+ "step": 675
4060
+ },
4061
+ {
4062
+ "epoch": 0.89,
4063
+ "learning_rate": 6.210448385099177e-07,
4064
+ "loss": 1.1323,
4065
+ "step": 676
4066
+ },
4067
+ {
4068
+ "epoch": 0.89,
4069
+ "learning_rate": 6.063222460308649e-07,
4070
+ "loss": 1.1179,
4071
+ "step": 677
4072
+ },
4073
+ {
4074
+ "epoch": 0.89,
4075
+ "learning_rate": 5.917708044234017e-07,
4076
+ "loss": 1.1343,
4077
+ "step": 678
4078
+ },
4079
+ {
4080
+ "epoch": 0.89,
4081
+ "learning_rate": 5.77390778811796e-07,
4082
+ "loss": 1.101,
4083
+ "step": 679
4084
+ },
4085
+ {
4086
+ "epoch": 0.9,
4087
+ "learning_rate": 5.631824311971456e-07,
4088
+ "loss": 1.1387,
4089
+ "step": 680
4090
+ },
4091
+ {
4092
+ "epoch": 0.9,
4093
+ "learning_rate": 5.491460204526156e-07,
4094
+ "loss": 1.0765,
4095
+ "step": 681
4096
+ },
4097
+ {
4098
+ "epoch": 0.9,
4099
+ "learning_rate": 5.352818023187167e-07,
4100
+ "loss": 1.1008,
4101
+ "step": 682
4102
+ },
4103
+ {
4104
+ "epoch": 0.9,
4105
+ "learning_rate": 5.215900293986431e-07,
4106
+ "loss": 1.134,
4107
+ "step": 683
4108
+ },
4109
+ {
4110
+ "epoch": 0.9,
4111
+ "learning_rate": 5.08070951153673e-07,
4112
+ "loss": 1.1359,
4113
+ "step": 684
4114
+ },
4115
+ {
4116
+ "epoch": 0.9,
4117
+ "learning_rate": 4.947248138986249e-07,
4118
+ "loss": 1.1319,
4119
+ "step": 685
4120
+ },
4121
+ {
4122
+ "epoch": 0.9,
4123
+ "learning_rate": 4.81551860797369e-07,
4124
+ "loss": 1.1359,
4125
+ "step": 686
4126
+ },
4127
+ {
4128
+ "epoch": 0.91,
4129
+ "learning_rate": 4.6855233185839175e-07,
4130
+ "loss": 1.1289,
4131
+ "step": 687
4132
+ },
4133
+ {
4134
+ "epoch": 0.91,
4135
+ "learning_rate": 4.557264639304315e-07,
4136
+ "loss": 1.131,
4137
+ "step": 688
4138
+ },
4139
+ {
4140
+ "epoch": 0.91,
4141
+ "learning_rate": 4.430744906981577e-07,
4142
+ "loss": 1.1484,
4143
+ "step": 689
4144
+ },
4145
+ {
4146
+ "epoch": 0.91,
4147
+ "learning_rate": 4.305966426779118e-07,
4148
+ "loss": 1.1267,
4149
+ "step": 690
4150
+ },
4151
+ {
4152
+ "epoch": 0.91,
4153
+ "learning_rate": 4.1829314721351213e-07,
4154
+ "loss": 1.1382,
4155
+ "step": 691
4156
+ },
4157
+ {
4158
+ "epoch": 0.91,
4159
+ "learning_rate": 4.0616422847211013e-07,
4160
+ "loss": 1.1439,
4161
+ "step": 692
4162
+ },
4163
+ {
4164
+ "epoch": 0.91,
4165
+ "learning_rate": 3.942101074401028e-07,
4166
+ "loss": 1.1129,
4167
+ "step": 693
4168
+ },
4169
+ {
4170
+ "epoch": 0.91,
4171
+ "learning_rate": 3.824310019191102e-07,
4172
+ "loss": 1.0898,
4173
+ "step": 694
4174
+ },
4175
+ {
4176
+ "epoch": 0.92,
4177
+ "learning_rate": 3.708271265220087e-07,
4178
+ "loss": 1.1395,
4179
+ "step": 695
4180
+ },
4181
+ {
4182
+ "epoch": 0.92,
4183
+ "learning_rate": 3.5939869266901073e-07,
4184
+ "loss": 1.126,
4185
+ "step": 696
4186
+ },
4187
+ {
4188
+ "epoch": 0.92,
4189
+ "learning_rate": 3.481459085838268e-07,
4190
+ "loss": 1.1485,
4191
+ "step": 697
4192
+ },
4193
+ {
4194
+ "epoch": 0.92,
4195
+ "learning_rate": 3.370689792898618e-07,
4196
+ "loss": 1.1505,
4197
+ "step": 698
4198
+ },
4199
+ {
4200
+ "epoch": 0.92,
4201
+ "learning_rate": 3.261681066064859e-07,
4202
+ "loss": 1.1443,
4203
+ "step": 699
4204
+ },
4205
+ {
4206
+ "epoch": 0.92,
4207
+ "learning_rate": 3.154434891453473e-07,
4208
+ "loss": 1.1293,
4209
+ "step": 700
4210
+ },
4211
+ {
4212
+ "epoch": 0.92,
4213
+ "learning_rate": 3.0489532230676744e-07,
4214
+ "loss": 1.1002,
4215
+ "step": 701
4216
+ },
4217
+ {
4218
+ "epoch": 0.92,
4219
+ "learning_rate": 2.945237982761706e-07,
4220
+ "loss": 1.0944,
4221
+ "step": 702
4222
+ },
4223
+ {
4224
+ "epoch": 0.93,
4225
+ "learning_rate": 2.843291060205855e-07,
4226
+ "loss": 1.1131,
4227
+ "step": 703
4228
+ },
4229
+ {
4230
+ "epoch": 0.93,
4231
+ "learning_rate": 2.7431143128520243e-07,
4232
+ "loss": 1.0828,
4233
+ "step": 704
4234
+ },
4235
+ {
4236
+ "epoch": 0.93,
4237
+ "learning_rate": 2.6447095658999054e-07,
4238
+ "loss": 1.1194,
4239
+ "step": 705
4240
+ },
4241
+ {
4242
+ "epoch": 0.93,
4243
+ "learning_rate": 2.5480786122636713e-07,
4244
+ "loss": 1.1109,
4245
+ "step": 706
4246
+ },
4247
+ {
4248
+ "epoch": 0.93,
4249
+ "learning_rate": 2.453223212539391e-07,
4250
+ "loss": 1.1455,
4251
+ "step": 707
4252
+ },
4253
+ {
4254
+ "epoch": 0.93,
4255
+ "learning_rate": 2.3601450949728876e-07,
4256
+ "loss": 1.0945,
4257
+ "step": 708
4258
+ },
4259
+ {
4260
+ "epoch": 0.93,
4261
+ "learning_rate": 2.2688459554282673e-07,
4262
+ "loss": 1.0706,
4263
+ "step": 709
4264
+ },
4265
+ {
4266
+ "epoch": 0.94,
4267
+ "learning_rate": 2.1793274573570166e-07,
4268
+ "loss": 1.1309,
4269
+ "step": 710
4270
+ },
4271
+ {
4272
+ "epoch": 0.94,
4273
+ "learning_rate": 2.091591231767709e-07,
4274
+ "loss": 1.1223,
4275
+ "step": 711
4276
+ },
4277
+ {
4278
+ "epoch": 0.94,
4279
+ "learning_rate": 2.005638877196303e-07,
4280
+ "loss": 1.1511,
4281
+ "step": 712
4282
+ },
4283
+ {
4284
+ "epoch": 0.94,
4285
+ "learning_rate": 1.921471959676957e-07,
4286
+ "loss": 1.0697,
4287
+ "step": 713
4288
+ },
4289
+ {
4290
+ "epoch": 0.94,
4291
+ "learning_rate": 1.8390920127135613e-07,
4292
+ "loss": 1.1142,
4293
+ "step": 714
4294
+ },
4295
+ {
4296
+ "epoch": 0.94,
4297
+ "learning_rate": 1.7585005372517504e-07,
4298
+ "loss": 1.1251,
4299
+ "step": 715
4300
+ },
4301
+ {
4302
+ "epoch": 0.94,
4303
+ "learning_rate": 1.6796990016515914e-07,
4304
+ "loss": 1.1298,
4305
+ "step": 716
4306
+ },
4307
+ {
4308
+ "epoch": 0.94,
4309
+ "learning_rate": 1.6026888416608267e-07,
4310
+ "loss": 1.1118,
4311
+ "step": 717
4312
+ },
4313
+ {
4314
+ "epoch": 0.95,
4315
+ "learning_rate": 1.5274714603886742e-07,
4316
+ "loss": 1.1155,
4317
+ "step": 718
4318
+ },
4319
+ {
4320
+ "epoch": 0.95,
4321
+ "learning_rate": 1.4540482282803136e-07,
4322
+ "loss": 1.1185,
4323
+ "step": 719
4324
+ },
4325
+ {
4326
+ "epoch": 0.95,
4327
+ "learning_rate": 1.3824204830918952e-07,
4328
+ "loss": 1.1348,
4329
+ "step": 720
4330
+ },
4331
+ {
4332
+ "epoch": 0.95,
4333
+ "learning_rate": 1.3125895298661705e-07,
4334
+ "loss": 1.1312,
4335
+ "step": 721
4336
+ },
4337
+ {
4338
+ "epoch": 0.95,
4339
+ "learning_rate": 1.244556640908712e-07,
4340
+ "loss": 1.119,
4341
+ "step": 722
4342
+ },
4343
+ {
4344
+ "epoch": 0.95,
4345
+ "learning_rate": 1.1783230557647075e-07,
4346
+ "loss": 1.0977,
4347
+ "step": 723
4348
+ },
4349
+ {
4350
+ "epoch": 0.95,
4351
+ "learning_rate": 1.1138899811964477e-07,
4352
+ "loss": 1.0999,
4353
+ "step": 724
4354
+ },
4355
+ {
4356
+ "epoch": 0.96,
4357
+ "learning_rate": 1.0512585911612416e-07,
4358
+ "loss": 1.1318,
4359
+ "step": 725
4360
+ },
4361
+ {
4362
+ "epoch": 0.96,
4363
+ "learning_rate": 9.904300267901012e-08,
4364
+ "loss": 1.1263,
4365
+ "step": 726
4366
+ },
4367
+ {
4368
+ "epoch": 0.96,
4369
+ "learning_rate": 9.314053963669245e-08,
4370
+ "loss": 1.1071,
4371
+ "step": 727
4372
+ },
4373
+ {
4374
+ "epoch": 0.96,
4375
+ "learning_rate": 8.741857753083228e-08,
4376
+ "loss": 1.1288,
4377
+ "step": 728
4378
+ },
4379
+ {
4380
+ "epoch": 0.96,
4381
+ "learning_rate": 8.187722061439806e-08,
4382
+ "loss": 1.1247,
4383
+ "step": 729
4384
+ },
4385
+ {
4386
+ "epoch": 0.96,
4387
+ "learning_rate": 7.651656984977051e-08,
4388
+ "loss": 1.1275,
4389
+ "step": 730
4390
+ },
4391
+ {
4392
+ "epoch": 0.96,
4393
+ "learning_rate": 7.133672290690064e-08,
4394
+ "loss": 1.1239,
4395
+ "step": 731
4396
+ },
4397
+ {
4398
+ "epoch": 0.96,
4399
+ "learning_rate": 6.633777416153232e-08,
4400
+ "loss": 1.1434,
4401
+ "step": 732
4402
+ },
4403
+ {
4404
+ "epoch": 0.97,
4405
+ "learning_rate": 6.151981469348034e-08,
4406
+ "loss": 1.106,
4407
+ "step": 733
4408
+ },
4409
+ {
4410
+ "epoch": 0.97,
4411
+ "learning_rate": 5.688293228497399e-08,
4412
+ "loss": 1.1278,
4413
+ "step": 734
4414
+ },
4415
+ {
4416
+ "epoch": 0.97,
4417
+ "learning_rate": 5.2427211419051605e-08,
4418
+ "loss": 1.1375,
4419
+ "step": 735
4420
+ },
4421
+ {
4422
+ "epoch": 0.97,
4423
+ "learning_rate": 4.815273327803183e-08,
4424
+ "loss": 1.1598,
4425
+ "step": 736
4426
+ },
4427
+ {
4428
+ "epoch": 0.97,
4429
+ "learning_rate": 4.405957574202147e-08,
4430
+ "loss": 1.1285,
4431
+ "step": 737
4432
+ },
4433
+ {
4434
+ "epoch": 0.97,
4435
+ "learning_rate": 4.014781338751106e-08,
4436
+ "loss": 1.0929,
4437
+ "step": 738
4438
+ },
4439
+ {
4440
+ "epoch": 0.97,
4441
+ "learning_rate": 3.641751748600042e-08,
4442
+ "loss": 1.1339,
4443
+ "step": 739
4444
+ },
4445
+ {
4446
+ "epoch": 0.97,
4447
+ "learning_rate": 3.2868756002712997e-08,
4448
+ "loss": 1.1193,
4449
+ "step": 740
4450
+ },
4451
+ {
4452
+ "epoch": 0.98,
4453
+ "learning_rate": 2.950159359535132e-08,
4454
+ "loss": 1.1526,
4455
+ "step": 741
4456
+ },
4457
+ {
4458
+ "epoch": 0.98,
4459
+ "learning_rate": 2.6316091612920146e-08,
4460
+ "loss": 1.142,
4461
+ "step": 742
4462
+ },
4463
+ {
4464
+ "epoch": 0.98,
4465
+ "learning_rate": 2.3312308094607382e-08,
4466
+ "loss": 1.1144,
4467
+ "step": 743
4468
+ },
4469
+ {
4470
+ "epoch": 0.98,
4471
+ "learning_rate": 2.049029776873268e-08,
4472
+ "loss": 1.0968,
4473
+ "step": 744
4474
+ },
4475
+ {
4476
+ "epoch": 0.98,
4477
+ "learning_rate": 1.7850112051738255e-08,
4478
+ "loss": 1.156,
4479
+ "step": 745
4480
+ },
4481
+ {
4482
+ "epoch": 0.98,
4483
+ "learning_rate": 1.5391799047266287e-08,
4484
+ "loss": 1.08,
4485
+ "step": 746
4486
+ },
4487
+ {
4488
+ "epoch": 0.98,
4489
+ "learning_rate": 1.3115403545270744e-08,
4490
+ "loss": 1.1334,
4491
+ "step": 747
4492
+ },
4493
+ {
4494
+ "epoch": 0.99,
4495
+ "learning_rate": 1.1020967021210249e-08,
4496
+ "loss": 1.1115,
4497
+ "step": 748
4498
+ },
4499
+ {
4500
+ "epoch": 0.99,
4501
+ "learning_rate": 9.108527635284248e-09,
4502
+ "loss": 1.1364,
4503
+ "step": 749
4504
+ },
4505
+ {
4506
+ "epoch": 0.99,
4507
+ "learning_rate": 7.378120231745778e-09,
4508
+ "loss": 1.1019,
4509
+ "step": 750
4510
+ },
4511
+ {
4512
+ "epoch": 0.99,
4513
+ "learning_rate": 5.8297763382597625e-09,
4514
+ "loss": 1.1174,
4515
+ "step": 751
4516
+ },
4517
+ {
4518
+ "epoch": 0.99,
4519
+ "learning_rate": 4.463524165333466e-09,
4520
+ "loss": 1.116,
4521
+ "step": 752
4522
+ },
4523
+ {
4524
+ "epoch": 0.99,
4525
+ "learning_rate": 3.2793886057991277e-09,
4526
+ "loss": 1.1341,
4527
+ "step": 753
4528
+ },
4529
+ {
4530
+ "epoch": 0.99,
4531
+ "learning_rate": 2.277391234363213e-09,
4532
+ "loss": 1.1028,
4533
+ "step": 754
4534
+ },
4535
+ {
4536
+ "epoch": 0.99,
4537
+ "learning_rate": 1.4575503072100649e-09,
4538
+ "loss": 1.1089,
4539
+ "step": 755
4540
+ },
4541
+ {
4542
+ "epoch": 1.0,
4543
+ "learning_rate": 8.198807616732752e-10,
4544
+ "loss": 1.1326,
4545
+ "step": 756
4546
+ },
4547
+ {
4548
+ "epoch": 1.0,
4549
+ "learning_rate": 3.6439421595924065e-10,
4550
+ "loss": 1.1139,
4551
+ "step": 757
4552
+ },
4553
+ {
4554
+ "epoch": 1.0,
4555
+ "learning_rate": 9.109896894066161e-11,
4556
+ "loss": 1.1377,
4557
+ "step": 758
4558
+ },
4559
+ {
4560
+ "epoch": 1.0,
4561
+ "learning_rate": 0.0,
4562
+ "loss": 1.1199,
4563
+ "step": 759
4564
+ },
4565
+ {
4566
+ "epoch": 1.0,
4567
+ "step": 759,
4568
+ "total_flos": 3.241478138413662e+22,
4569
+ "train_loss": 1.1657107080552576,
4570
+ "train_runtime": 16008.6151,
4571
+ "train_samples_per_second": 12.138,
4572
+ "train_steps_per_second": 0.047
4573
+ }
4574
+ ],
4575
+ "logging_steps": 1.0,
4576
+ "max_steps": 759,
4577
+ "num_input_tokens_seen": 0,
4578
+ "num_train_epochs": 1,
4579
+ "save_steps": 200,
4580
+ "total_flos": 3.241478138413662e+22,
4581
+ "train_batch_size": 2,
4582
+ "trial_name": null,
4583
+ "trial_params": null
4584
+ }
Pretrain_8B/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5af59b73f615fedf0ac5c83503f8afac2a5b4658cfd5b4a8fe9822892fbf76a0
3
+ size 5883
Pretrain_8B/training_log.txt ADDED
The diff for this file is too large to render. See raw diff