Hugging Face's logo

Aditya02
/
InternVL2_5_1b_finetuned

Safetensors
internvl_chat
custom_code
Model card Files Community
Aditya02 commited on
Commit
4da178b
·
verified ·
1 Parent(s): 7a87a4a

Initial model upload

Browse files
Files changed (13) hide show
  1. added_tokens.json +33 -0
  2. all_results.json +8 -0
  3. config.json +196 -0
  4. generation_config.json +9 -0
  5. merges.txt +0 -0
  6. model.safetensors +3 -0
  7. special_tokens_map.json +40 -0
  8. tokenizer_config.json +289 -0
  9. train_results.json +8 -0
  10. trainer_state.json +2652 -0
  11. training_args.bin +3 -0
  12. training_log.txt +0 -0
  13. vocab.json +0 -0
added_tokens.json ADDED
@@ -0,0 +1,33 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "</box>": 151673,
3
+ "</img>": 151666,
4
+ "</quad>": 151669,
5
+ "</ref>": 151671,
6
+ "</tool_call>": 151658,
7
+ "<IMG_CONTEXT>": 151667,
8
+ "<box>": 151672,
9
+ "<img>": 151665,
10
+ "<quad>": 151668,
11
+ "<ref>": 151670,
12
+ "<tool_call>": 151657,
13
+ "<|box_end|>": 151649,
14
+ "<|box_start|>": 151648,
15
+ "<|endoftext|>": 151643,
16
+ "<|file_sep|>": 151664,
17
+ "<|fim_middle|>": 151660,
18
+ "<|fim_pad|>": 151662,
19
+ "<|fim_prefix|>": 151659,
20
+ "<|fim_suffix|>": 151661,
21
+ "<|im_end|>": 151645,
22
+ "<|im_start|>": 151644,
23
+ "<|image_pad|>": 151655,
24
+ "<|object_ref_end|>": 151647,
25
+ "<|object_ref_start|>": 151646,
26
+ "<|quad_end|>": 151651,
27
+ "<|quad_start|>": 151650,
28
+ "<|repo_name|>": 151663,
29
+ "<|video_pad|>": 151656,
30
+ "<|vision_end|>": 151653,
31
+ "<|vision_pad|>": 151654,
32
+ "<|vision_start|>": 151652
33
+ }
all_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 1.0,
3
+ "train_loss": 0.46482172025286633,
4
+ "train_runtime": 2900.7464,
5
+ "train_samples": 7000,
6
+ "train_samples_per_second": 2.413,
7
+ "train_steps_per_second": 0.151
8
+ }
config.json ADDED
@@ -0,0 +1,196 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_commit_hash": "4dcf9845f6a6d8d6c4b188aae707a265cfbe4be5",
3
+ "_name_or_path": "OpenGVLab/InternVL2_5-1B",
4
+ "architectures": [
5
+ "InternVLChatModel"
6
+ ],
7
+ "auto_map": {
8
+ "AutoConfig": "OpenGVLab/InternVL2_5-1B--configuration_internvl_chat.InternVLChatConfig",
9
+ "AutoModel": "OpenGVLab/InternVL2_5-1B--modeling_internvl_chat.InternVLChatModel",
10
+ "AutoModelForCausalLM": "OpenGVLab/InternVL2_5-1B--modeling_internvl_chat.InternVLChatModel"
11
+ },
12
+ "downsample_ratio": 0.5,
13
+ "dynamic_image_size": true,
14
+ "force_image_size": 448,
15
+ "hidden_size": 896,
16
+ "llm_config": {
17
+ "_name_or_path": "Qwen/Qwen2.5-0.5B-Instruct",
18
+ "add_cross_attention": false,
19
+ "architectures": [
20
+ "Qwen2ForCausalLM"
21
+ ],
22
+ "attention_dropout": 0.0,
23
+ "attn_implementation": "flash_attention_2",
24
+ "bad_words_ids": null,
25
+ "begin_suppress_tokens": null,
26
+ "bos_token_id": 151643,
27
+ "chunk_size_feed_forward": 0,
28
+ "cross_attention_hidden_size": null,
29
+ "decoder_start_token_id": null,
30
+ "diversity_penalty": 0.0,
31
+ "do_sample": false,
32
+ "early_stopping": false,
33
+ "encoder_no_repeat_ngram_size": 0,
34
+ "eos_token_id": 151645,
35
+ "exponential_decay_length_penalty": null,
36
+ "finetuning_task": null,
37
+ "forced_bos_token_id": null,
38
+ "forced_eos_token_id": null,
39
+ "hidden_act": "silu",
40
+ "hidden_size": 896,
41
+ "id2label": {
42
+ "0": "LABEL_0",
43
+ "1": "LABEL_1"
44
+ },
45
+ "initializer_range": 0.02,
46
+ "intermediate_size": 4864,
47
+ "is_decoder": false,
48
+ "is_encoder_decoder": false,
49
+ "label2id": {
50
+ "LABEL_0": 0,
51
+ "LABEL_1": 1
52
+ },
53
+ "length_penalty": 1.0,
54
+ "max_length": 20,
55
+ "max_position_embeddings": 32768,
56
+ "max_window_layers": 21,
57
+ "min_length": 0,
58
+ "model_type": "qwen2",
59
+ "no_repeat_ngram_size": 0,
60
+ "num_attention_heads": 14,
61
+ "num_beam_groups": 1,
62
+ "num_beams": 1,
63
+ "num_hidden_layers": 24,
64
+ "num_key_value_heads": 2,
65
+ "num_return_sequences": 1,
66
+ "output_attentions": false,
67
+ "output_hidden_states": false,
68
+ "output_scores": false,
69
+ "pad_token_id": null,
70
+ "prefix": null,
71
+ "problem_type": null,
72
+ "pruned_heads": {},
73
+ "remove_invalid_values": false,
74
+ "repetition_penalty": 1.0,
75
+ "return_dict": true,
76
+ "return_dict_in_generate": false,
77
+ "rms_norm_eps": 1e-06,
78
+ "rope_theta": 1000000.0,
79
+ "sep_token_id": null,
80
+ "sliding_window": 32768,
81
+ "suppress_tokens": null,
82
+ "task_specific_params": null,
83
+ "temperature": 1.0,
84
+ "tf_legacy_loss": false,
85
+ "tie_encoder_decoder": false,
86
+ "tie_word_embeddings": false,
87
+ "tokenizer_class": null,
88
+ "top_k": 50,
89
+ "top_p": 1.0,
90
+ "torch_dtype": "bfloat16",
91
+ "torchscript": false,
92
+ "transformers_version": "4.37.2",
93
+ "typical_p": 1.0,
94
+ "use_bfloat16": true,
95
+ "use_cache": false,
96
+ "use_sliding_window": false,
97
+ "vocab_size": 151674
98
+ },
99
+ "max_dynamic_patch": 6,
100
+ "min_dynamic_patch": 1,
101
+ "model_type": "internvl_chat",
102
+ "pad2square": false,
103
+ "ps_version": "v2",
104
+ "select_layer": -1,
105
+ "template": "internvl2_5",
106
+ "tie_word_embeddings": false,
107
+ "torch_dtype": "bfloat16",
108
+ "transformers_version": null,
109
+ "use_backbone_lora": 0,
110
+ "use_llm_lora": 16,
111
+ "use_thumbnail": true,
112
+ "vision_config": {
113
+ "_name_or_path": "",
114
+ "add_cross_attention": false,
115
+ "architectures": [
116
+ "InternVisionModel"
117
+ ],
118
+ "attention_dropout": 0.0,
119
+ "bad_words_ids": null,
120
+ "begin_suppress_tokens": null,
121
+ "bos_token_id": null,
122
+ "chunk_size_feed_forward": 0,
123
+ "cross_attention_hidden_size": null,
124
+ "decoder_start_token_id": null,
125
+ "diversity_penalty": 0.0,
126
+ "do_sample": false,
127
+ "drop_path_rate": 0.0,
128
+ "dropout": 0.0,
129
+ "early_stopping": false,
130
+ "encoder_no_repeat_ngram_size": 0,
131
+ "eos_token_id": null,
132
+ "exponential_decay_length_penalty": null,
133
+ "finetuning_task": null,
134
+ "forced_bos_token_id": null,
135
+ "forced_eos_token_id": null,
136
+ "hidden_act": "gelu",
137
+ "hidden_size": 1024,
138
+ "id2label": {
139
+ "0": "LABEL_0",
140
+ "1": "LABEL_1"
141
+ },
142
+ "image_size": 448,
143
+ "initializer_factor": 1.0,
144
+ "initializer_range": 0.02,
145
+ "intermediate_size": 4096,
146
+ "is_decoder": false,
147
+ "is_encoder_decoder": false,
148
+ "label2id": {
149
+ "LABEL_0": 0,
150
+ "LABEL_1": 1
151
+ },
152
+ "layer_norm_eps": 1e-06,
153
+ "length_penalty": 1.0,
154
+ "max_length": 20,
155
+ "min_length": 0,
156
+ "model_type": "intern_vit_6b",
157
+ "no_repeat_ngram_size": 0,
158
+ "norm_type": "layer_norm",
159
+ "num_attention_heads": 16,
160
+ "num_beam_groups": 1,
161
+ "num_beams": 1,
162
+ "num_channels": 3,
163
+ "num_hidden_layers": 24,
164
+ "num_return_sequences": 1,
165
+ "output_attentions": false,
166
+ "output_hidden_states": false,
167
+ "output_scores": false,
168
+ "pad_token_id": null,
169
+ "patch_size": 14,
170
+ "prefix": null,
171
+ "problem_type": null,
172
+ "pruned_heads": {},
173
+ "qk_normalization": false,
174
+ "qkv_bias": true,
175
+ "remove_invalid_values": false,
176
+ "repetition_penalty": 1.0,
177
+ "return_dict": true,
178
+ "return_dict_in_generate": false,
179
+ "sep_token_id": null,
180
+ "suppress_tokens": null,
181
+ "task_specific_params": null,
182
+ "temperature": 1.0,
183
+ "tf_legacy_loss": false,
184
+ "tie_encoder_decoder": false,
185
+ "tie_word_embeddings": true,
186
+ "tokenizer_class": null,
187
+ "top_k": 50,
188
+ "top_p": 1.0,
189
+ "torch_dtype": "bfloat16",
190
+ "torchscript": false,
191
+ "transformers_version": "4.37.2",
192
+ "typical_p": 1.0,
193
+ "use_bfloat16": true,
194
+ "use_flash_attn": true
195
+ }
196
+ }
generation_config.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "eos_token_id": [
4
+ 151644,
5
+ 151645,
6
+ 151643
7
+ ],
8
+ "transformers_version": "4.37.2"
9
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:74e4f2cee7cb4a63644bd22edd901fd3768295bce2b620d3e5c79be445ba0f4d
3
+ size 1894120920
special_tokens_map.json ADDED
@@ -0,0 +1,40 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<|im_start|>",
4
+ "<|im_end|>",
5
+ "<|object_ref_start|>",
6
+ "<|object_ref_end|>",
7
+ "<|box_start|>",
8
+ "<|box_end|>",
9
+ "<|quad_start|>",
10
+ "<|quad_end|>",
11
+ "<|vision_start|>",
12
+ "<|vision_end|>",
13
+ "<|vision_pad|>",
14
+ "<|image_pad|>",
15
+ "<|video_pad|>",
16
+ "<img>",
17
+ "</img>",
18
+ "<IMG_CONTEXT>",
19
+ "<quad>",
20
+ "</quad>",
21
+ "<ref>",
22
+ "</ref>",
23
+ "<box>",
24
+ "</box>"
25
+ ],
26
+ "eos_token": {
27
+ "content": "<|im_end|>",
28
+ "lstrip": false,
29
+ "normalized": false,
30
+ "rstrip": false,
31
+ "single_word": false
32
+ },
33
+ "pad_token": {
34
+ "content": "<|endoftext|>",
35
+ "lstrip": false,
36
+ "normalized": false,
37
+ "rstrip": false,
38
+ "single_word": false
39
+ }
40
+ }
tokenizer_config.json ADDED
@@ -0,0 +1,289 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": false,
3
+ "add_eos_token": false,
4
+ "add_prefix_space": false,
5
+ "added_tokens_decoder": {
6
+ "151643": {
7
+ "content": "<|endoftext|>",
8
+ "lstrip": false,
9
+ "normalized": false,
10
+ "rstrip": false,
11
+ "single_word": false,
12
+ "special": true
13
+ },
14
+ "151644": {
15
+ "content": "<|im_start|>",
16
+ "lstrip": false,
17
+ "normalized": false,
18
+ "rstrip": false,
19
+ "single_word": false,
20
+ "special": true
21
+ },
22
+ "151645": {
23
+ "content": "<|im_end|>",
24
+ "lstrip": false,
25
+ "normalized": false,
26
+ "rstrip": false,
27
+ "single_word": false,
28
+ "special": true
29
+ },
30
+ "151646": {
31
+ "content": "<|object_ref_start|>",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false,
36
+ "special": true
37
+ },
38
+ "151647": {
39
+ "content": "<|object_ref_end|>",
40
+ "lstrip": false,
41
+ "normalized": false,
42
+ "rstrip": false,
43
+ "single_word": false,
44
+ "special": true
45
+ },
46
+ "151648": {
47
+ "content": "<|box_start|>",
48
+ "lstrip": false,
49
+ "normalized": false,
50
+ "rstrip": false,
51
+ "single_word": false,
52
+ "special": true
53
+ },
54
+ "151649": {
55
+ "content": "<|box_end|>",
56
+ "lstrip": false,
57
+ "normalized": false,
58
+ "rstrip": false,
59
+ "single_word": false,
60
+ "special": true
61
+ },
62
+ "151650": {
63
+ "content": "<|quad_start|>",
64
+ "lstrip": false,
65
+ "normalized": false,
66
+ "rstrip": false,
67
+ "single_word": false,
68
+ "special": true
69
+ },
70
+ "151651": {
71
+ "content": "<|quad_end|>",
72
+ "lstrip": false,
73
+ "normalized": false,
74
+ "rstrip": false,
75
+ "single_word": false,
76
+ "special": true
77
+ },
78
+ "151652": {
79
+ "content": "<|vision_start|>",
80
+ "lstrip": false,
81
+ "normalized": false,
82
+ "rstrip": false,
83
+ "single_word": false,
84
+ "special": true
85
+ },
86
+ "151653": {
87
+ "content": "<|vision_end|>",
88
+ "lstrip": false,
89
+ "normalized": false,
90
+ "rstrip": false,
91
+ "single_word": false,
92
+ "special": true
93
+ },
94
+ "151654": {
95
+ "content": "<|vision_pad|>",
96
+ "lstrip": false,
97
+ "normalized": false,
98
+ "rstrip": false,
99
+ "single_word": false,
100
+ "special": true
101
+ },
102
+ "151655": {
103
+ "content": "<|image_pad|>",
104
+ "lstrip": false,
105
+ "normalized": false,
106
+ "rstrip": false,
107
+ "single_word": false,
108
+ "special": true
109
+ },
110
+ "151656": {
111
+ "content": "<|video_pad|>",
112
+ "lstrip": false,
113
+ "normalized": false,
114
+ "rstrip": false,
115
+ "single_word": false,
116
+ "special": true
117
+ },
118
+ "151657": {
119
+ "content": "<tool_call>",
120
+ "lstrip": false,
121
+ "normalized": false,
122
+ "rstrip": false,
123
+ "single_word": false,
124
+ "special": false
125
+ },
126
+ "151658": {
127
+ "content": "</tool_call>",
128
+ "lstrip": false,
129
+ "normalized": false,
130
+ "rstrip": false,
131
+ "single_word": false,
132
+ "special": false
133
+ },
134
+ "151659": {
135
+ "content": "<|fim_prefix|>",
136
+ "lstrip": false,
137
+ "normalized": false,
138
+ "rstrip": false,
139
+ "single_word": false,
140
+ "special": false
141
+ },
142
+ "151660": {
143
+ "content": "<|fim_middle|>",
144
+ "lstrip": false,
145
+ "normalized": false,
146
+ "rstrip": false,
147
+ "single_word": false,
148
+ "special": false
149
+ },
150
+ "151661": {
151
+ "content": "<|fim_suffix|>",
152
+ "lstrip": false,
153
+ "normalized": false,
154
+ "rstrip": false,
155
+ "single_word": false,
156
+ "special": false
157
+ },
158
+ "151662": {
159
+ "content": "<|fim_pad|>",
160
+ "lstrip": false,
161
+ "normalized": false,
162
+ "rstrip": false,
163
+ "single_word": false,
164
+ "special": false
165
+ },
166
+ "151663": {
167
+ "content": "<|repo_name|>",
168
+ "lstrip": false,
169
+ "normalized": false,
170
+ "rstrip": false,
171
+ "single_word": false,
172
+ "special": false
173
+ },
174
+ "151664": {
175
+ "content": "<|file_sep|>",
176
+ "lstrip": false,
177
+ "normalized": false,
178
+ "rstrip": false,
179
+ "single_word": false,
180
+ "special": false
181
+ },
182
+ "151665": {
183
+ "content": "<img>",
184
+ "lstrip": false,
185
+ "normalized": false,
186
+ "rstrip": false,
187
+ "single_word": false,
188
+ "special": true
189
+ },
190
+ "151666": {
191
+ "content": "</img>",
192
+ "lstrip": false,
193
+ "normalized": false,
194
+ "rstrip": false,
195
+ "single_word": false,
196
+ "special": true
197
+ },
198
+ "151667": {
199
+ "content": "<IMG_CONTEXT>",
200
+ "lstrip": false,
201
+ "normalized": false,
202
+ "rstrip": false,
203
+ "single_word": false,
204
+ "special": true
205
+ },
206
+ "151668": {
207
+ "content": "<quad>",
208
+ "lstrip": false,
209
+ "normalized": false,
210
+ "rstrip": false,
211
+ "single_word": false,
212
+ "special": true
213
+ },
214
+ "151669": {
215
+ "content": "</quad>",
216
+ "lstrip": false,
217
+ "normalized": false,
218
+ "rstrip": false,
219
+ "single_word": false,
220
+ "special": true
221
+ },
222
+ "151670": {
223
+ "content": "<ref>",
224
+ "lstrip": false,
225
+ "normalized": false,
226
+ "rstrip": false,
227
+ "single_word": false,
228
+ "special": true
229
+ },
230
+ "151671": {
231
+ "content": "</ref>",
232
+ "lstrip": false,
233
+ "normalized": false,
234
+ "rstrip": false,
235
+ "single_word": false,
236
+ "special": true
237
+ },
238
+ "151672": {
239
+ "content": "<box>",
240
+ "lstrip": false,
241
+ "normalized": false,
242
+ "rstrip": false,
243
+ "single_word": false,
244
+ "special": true
245
+ },
246
+ "151673": {
247
+ "content": "</box>",
248
+ "lstrip": false,
249
+ "normalized": false,
250
+ "rstrip": false,
251
+ "single_word": false,
252
+ "special": true
253
+ }
254
+ },
255
+ "additional_special_tokens": [
256
+ "<|im_start|>",
257
+ "<|im_end|>",
258
+ "<|object_ref_start|>",
259
+ "<|object_ref_end|>",
260
+ "<|box_start|>",
261
+ "<|box_end|>",
262
+ "<|quad_start|>",
263
+ "<|quad_end|>",
264
+ "<|vision_start|>",
265
+ "<|vision_end|>",
266
+ "<|vision_pad|>",
267
+ "<|image_pad|>",
268
+ "<|video_pad|>",
269
+ "<img>",
270
+ "</img>",
271
+ "<IMG_CONTEXT>",
272
+ "<quad>",
273
+ "</quad>",
274
+ "<ref>",
275
+ "</ref>",
276
+ "<box>",
277
+ "</box>"
278
+ ],
279
+ "bos_token": null,
280
+ "chat_template": "{%- if tools %}\n {{- '<|im_start|>system\\n' }}\n {%- if messages[0]['role'] == 'system' %}\n {{- messages[0]['content'] }}\n {%- else %}\n {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}\n {%- endif %}\n {{- \"\\n\\n# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n {%- for tool in tools %}\n {{- \"\\n\" }}\n {{- tool | tojson }}\n {%- endfor %}\n {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n {%- if messages[0]['role'] == 'system' %}\n {{- '<|im_start|>system\\n' + messages[0]['content'] + '<|im_end|>\\n' }}\n {%- else %}\n {{- '<|im_start|>system\\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\\n' }}\n {%- endif %}\n{%- endif %}\n{%- for message in messages %}\n {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) or (message.role == \"assistant\" and not message.tool_calls) %}\n {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n {%- elif message.role == \"assistant\" %}\n {{- '<|im_start|>' + message.role }}\n {%- if message.content %}\n {{- '\\n' + message.content }}\n {%- endif %}\n {%- for tool_call in message.tool_calls %}\n {%- if tool_call.function is defined %}\n {%- set tool_call = tool_call.function %}\n {%- endif %}\n {{- '\\n<tool_call>\\n{\"name\": \"' }}\n {{- tool_call.name }}\n {{- '\", \"arguments\": ' }}\n {{- tool_call.arguments | tojson }}\n {{- '}\\n</tool_call>' }}\n {%- endfor %}\n {{- '<|im_end|>\\n' }}\n {%- elif message.role == \"tool\" %}\n {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != \"tool\") %}\n {{- '<|im_start|>user' }}\n {%- endif %}\n {{- '\\n<tool_response>\\n' }}\n {{- message.content }}\n {{- '\\n</tool_response>' }}\n {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n {{- '<|im_end|>\\n' }}\n {%- endif %}\n {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n",
281
+ "clean_up_tokenization_spaces": false,
282
+ "eos_token": "<|im_end|>",
283
+ "errors": "replace",
284
+ "model_max_length": 8192,
285
+ "pad_token": "<|endoftext|>",
286
+ "split_special_tokens": false,
287
+ "tokenizer_class": "Qwen2Tokenizer",
288
+ "unk_token": null
289
+ }
train_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 1.0,
3
+ "train_loss": 0.46482172025286633,
4
+ "train_runtime": 2900.7464,
5
+ "train_samples": 7000,
6
+ "train_samples_per_second": 2.413,
7
+ "train_steps_per_second": 0.151
8
+ }
trainer_state.json ADDED
@@ -0,0 +1,2652 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 0.9988571428571429,
5
+ "eval_steps": 500,
6
+ "global_step": 437,
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": 2.8571428571428573e-06,
14
+ "loss": 1.8699,
15
+ "step": 1
16
+ },
17
+ {
18
+ "epoch": 0.0,
19
+ "learning_rate": 5.7142857142857145e-06,
20
+ "loss": 2.8546,
21
+ "step": 2
22
+ },
23
+ {
24
+ "epoch": 0.01,
25
+ "learning_rate": 8.571428571428571e-06,
26
+ "loss": 1.8072,
27
+ "step": 3
28
+ },
29
+ {
30
+ "epoch": 0.01,
31
+ "learning_rate": 1.1428571428571429e-05,
32
+ "loss": 2.4662,
33
+ "step": 4
34
+ },
35
+ {
36
+ "epoch": 0.01,
37
+ "learning_rate": 1.4285714285714287e-05,
38
+ "loss": 2.9095,
39
+ "step": 5
40
+ },
41
+ {
42
+ "epoch": 0.01,
43
+ "learning_rate": 1.7142857142857142e-05,
44
+ "loss": 3.8613,
45
+ "step": 6
46
+ },
47
+ {
48
+ "epoch": 0.02,
49
+ "learning_rate": 2e-05,
50
+ "loss": 2.1535,
51
+ "step": 7
52
+ },
53
+ {
54
+ "epoch": 0.02,
55
+ "learning_rate": 2.2857142857142858e-05,
56
+ "loss": 3.8349,
57
+ "step": 8
58
+ },
59
+ {
60
+ "epoch": 0.02,
61
+ "learning_rate": 2.5714285714285718e-05,
62
+ "loss": 1.5684,
63
+ "step": 9
64
+ },
65
+ {
66
+ "epoch": 0.02,
67
+ "learning_rate": 2.8571428571428574e-05,
68
+ "loss": 3.1305,
69
+ "step": 10
70
+ },
71
+ {
72
+ "epoch": 0.03,
73
+ "learning_rate": 3.142857142857143e-05,
74
+ "loss": 1.5548,
75
+ "step": 11
76
+ },
77
+ {
78
+ "epoch": 0.03,
79
+ "learning_rate": 3.4285714285714284e-05,
80
+ "loss": 1.4553,
81
+ "step": 12
82
+ },
83
+ {
84
+ "epoch": 0.03,
85
+ "learning_rate": 3.714285714285715e-05,
86
+ "loss": 1.1268,
87
+ "step": 13
88
+ },
89
+ {
90
+ "epoch": 0.03,
91
+ "learning_rate": 4e-05,
92
+ "loss": 1.1313,
93
+ "step": 14
94
+ },
95
+ {
96
+ "epoch": 0.03,
97
+ "learning_rate": 3.9999448409199496e-05,
98
+ "loss": 1.3773,
99
+ "step": 15
100
+ },
101
+ {
102
+ "epoch": 0.04,
103
+ "learning_rate": 3.999779366722321e-05,
104
+ "loss": 1.587,
105
+ "step": 16
106
+ },
107
+ {
108
+ "epoch": 0.04,
109
+ "learning_rate": 3.9995035865345184e-05,
110
+ "loss": 0.868,
111
+ "step": 17
112
+ },
113
+ {
114
+ "epoch": 0.04,
115
+ "learning_rate": 3.999117515568324e-05,
116
+ "loss": 1.1585,
117
+ "step": 18
118
+ },
119
+ {
120
+ "epoch": 0.04,
121
+ "learning_rate": 3.998621175119058e-05,
122
+ "loss": 4.0398,
123
+ "step": 19
124
+ },
125
+ {
126
+ "epoch": 0.05,
127
+ "learning_rate": 3.998014592564402e-05,
128
+ "loss": 0.7112,
129
+ "step": 20
130
+ },
131
+ {
132
+ "epoch": 0.05,
133
+ "learning_rate": 3.997297801362891e-05,
134
+ "loss": 0.724,
135
+ "step": 21
136
+ },
137
+ {
138
+ "epoch": 0.05,
139
+ "learning_rate": 3.996470841052069e-05,
140
+ "loss": 1.1229,
141
+ "step": 22
142
+ },
143
+ {
144
+ "epoch": 0.05,
145
+ "learning_rate": 3.995533757246307e-05,
146
+ "loss": 0.9368,
147
+ "step": 23
148
+ },
149
+ {
150
+ "epoch": 0.05,
151
+ "learning_rate": 3.9944866016342835e-05,
152
+ "loss": 0.7026,
153
+ "step": 24
154
+ },
155
+ {
156
+ "epoch": 0.06,
157
+ "learning_rate": 3.9933294319761405e-05,
158
+ "loss": 0.6165,
159
+ "step": 25
160
+ },
161
+ {
162
+ "epoch": 0.06,
163
+ "learning_rate": 3.9920623121002914e-05,
164
+ "loss": 0.5194,
165
+ "step": 26
166
+ },
167
+ {
168
+ "epoch": 0.06,
169
+ "learning_rate": 3.9906853118999016e-05,
170
+ "loss": 0.5856,
171
+ "step": 27
172
+ },
173
+ {
174
+ "epoch": 0.06,
175
+ "learning_rate": 3.9891985073290375e-05,
176
+ "loss": 0.8067,
177
+ "step": 28
178
+ },
179
+ {
180
+ "epoch": 0.07,
181
+ "learning_rate": 3.98760198039847e-05,
182
+ "loss": 0.4607,
183
+ "step": 29
184
+ },
185
+ {
186
+ "epoch": 0.07,
187
+ "learning_rate": 3.9858958191711566e-05,
188
+ "loss": 0.6095,
189
+ "step": 30
190
+ },
191
+ {
192
+ "epoch": 0.07,
193
+ "learning_rate": 3.98408011775738e-05,
194
+ "loss": 0.6495,
195
+ "step": 31
196
+ },
197
+ {
198
+ "epoch": 0.07,
199
+ "learning_rate": 3.9821549763095606e-05,
200
+ "loss": 0.589,
201
+ "step": 32
202
+ },
203
+ {
204
+ "epoch": 0.08,
205
+ "learning_rate": 3.98012050101673e-05,
206
+ "loss": 0.5097,
207
+ "step": 33
208
+ },
209
+ {
210
+ "epoch": 0.08,
211
+ "learning_rate": 3.9779768040986726e-05,
212
+ "loss": 0.4351,
213
+ "step": 34
214
+ },
215
+ {
216
+ "epoch": 0.08,
217
+ "learning_rate": 3.975724003799739e-05,
218
+ "loss": 0.6051,
219
+ "step": 35
220
+ },
221
+ {
222
+ "epoch": 0.08,
223
+ "learning_rate": 3.973362224382322e-05,
224
+ "loss": 0.9956,
225
+ "step": 36
226
+ },
227
+ {
228
+ "epoch": 0.08,
229
+ "learning_rate": 3.97089159612e-05,
230
+ "loss": 0.4976,
231
+ "step": 37
232
+ },
233
+ {
234
+ "epoch": 0.09,
235
+ "learning_rate": 3.968312255290356e-05,
236
+ "loss": 0.5614,
237
+ "step": 38
238
+ },
239
+ {
240
+ "epoch": 0.09,
241
+ "learning_rate": 3.9656243441674576e-05,
242
+ "loss": 0.8428,
243
+ "step": 39
244
+ },
245
+ {
246
+ "epoch": 0.09,
247
+ "learning_rate": 3.962828011014009e-05,
248
+ "loss": 0.7532,
249
+ "step": 40
250
+ },
251
+ {
252
+ "epoch": 0.09,
253
+ "learning_rate": 3.959923410073174e-05,
254
+ "loss": 0.4086,
255
+ "step": 41
256
+ },
257
+ {
258
+ "epoch": 0.1,
259
+ "learning_rate": 3.956910701560069e-05,
260
+ "loss": 0.4337,
261
+ "step": 42
262
+ },
263
+ {
264
+ "epoch": 0.1,
265
+ "learning_rate": 3.953790051652925e-05,
266
+ "loss": 0.369,
267
+ "step": 43
268
+ },
269
+ {
270
+ "epoch": 0.1,
271
+ "learning_rate": 3.950561632483918e-05,
272
+ "loss": 0.3884,
273
+ "step": 44
274
+ },
275
+ {
276
+ "epoch": 0.1,
277
+ "learning_rate": 3.9472256221296815e-05,
278
+ "loss": 0.4261,
279
+ "step": 45
280
+ },
281
+ {
282
+ "epoch": 0.11,
283
+ "learning_rate": 3.9437822046014764e-05,
284
+ "loss": 0.4273,
285
+ "step": 46
286
+ },
287
+ {
288
+ "epoch": 0.11,
289
+ "learning_rate": 3.940231569835046e-05,
290
+ "loss": 0.3396,
291
+ "step": 47
292
+ },
293
+ {
294
+ "epoch": 0.11,
295
+ "learning_rate": 3.9365739136801366e-05,
296
+ "loss": 0.4417,
297
+ "step": 48
298
+ },
299
+ {
300
+ "epoch": 0.11,
301
+ "learning_rate": 3.932809437889699e-05,
302
+ "loss": 0.62,
303
+ "step": 49
304
+ },
305
+ {
306
+ "epoch": 0.11,
307
+ "learning_rate": 3.928938350108754e-05,
308
+ "loss": 0.5719,
309
+ "step": 50
310
+ },
311
+ {
312
+ "epoch": 0.12,
313
+ "learning_rate": 3.924960863862941e-05,
314
+ "loss": 0.6614,
315
+ "step": 51
316
+ },
317
+ {
318
+ "epoch": 0.12,
319
+ "learning_rate": 3.9208771985467435e-05,
320
+ "loss": 0.3308,
321
+ "step": 52
322
+ },
323
+ {
324
+ "epoch": 0.12,
325
+ "learning_rate": 3.916687579411383e-05,
326
+ "loss": 0.3355,
327
+ "step": 53
328
+ },
329
+ {
330
+ "epoch": 0.12,
331
+ "learning_rate": 3.912392237552397e-05,
332
+ "loss": 0.3821,
333
+ "step": 54
334
+ },
335
+ {
336
+ "epoch": 0.13,
337
+ "learning_rate": 3.907991409896892e-05,
338
+ "loss": 0.3476,
339
+ "step": 55
340
+ },
341
+ {
342
+ "epoch": 0.13,
343
+ "learning_rate": 3.9034853391904715e-05,
344
+ "loss": 0.3094,
345
+ "step": 56
346
+ },
347
+ {
348
+ "epoch": 0.13,
349
+ "learning_rate": 3.8988742739838505e-05,
350
+ "loss": 0.3785,
351
+ "step": 57
352
+ },
353
+ {
354
+ "epoch": 0.13,
355
+ "learning_rate": 3.8941584686191436e-05,
356
+ "loss": 0.4117,
357
+ "step": 58
358
+ },
359
+ {
360
+ "epoch": 0.13,
361
+ "learning_rate": 3.889338183215838e-05,
362
+ "loss": 0.3387,
363
+ "step": 59
364
+ },
365
+ {
366
+ "epoch": 0.14,
367
+ "learning_rate": 3.884413683656441e-05,
368
+ "loss": 0.3845,
369
+ "step": 60
370
+ },
371
+ {
372
+ "epoch": 0.14,
373
+ "learning_rate": 3.879385241571817e-05,
374
+ "loss": 0.3232,
375
+ "step": 61
376
+ },
377
+ {
378
+ "epoch": 0.14,
379
+ "learning_rate": 3.8742531343262076e-05,
380
+ "loss": 0.3627,
381
+ "step": 62
382
+ },
383
+ {
384
+ "epoch": 0.14,
385
+ "learning_rate": 3.869017645001925e-05,
386
+ "loss": 0.3797,
387
+ "step": 63
388
+ },
389
+ {
390
+ "epoch": 0.15,
391
+ "learning_rate": 3.863679062383746e-05,
392
+ "loss": 0.2881,
393
+ "step": 64
394
+ },
395
+ {
396
+ "epoch": 0.15,
397
+ "learning_rate": 3.858237680942975e-05,
398
+ "loss": 0.8201,
399
+ "step": 65
400
+ },
401
+ {
402
+ "epoch": 0.15,
403
+ "learning_rate": 3.852693800821208e-05,
404
+ "loss": 0.2627,
405
+ "step": 66
406
+ },
407
+ {
408
+ "epoch": 0.15,
409
+ "learning_rate": 3.847047727813771e-05,
410
+ "loss": 0.3228,
411
+ "step": 67
412
+ },
413
+ {
414
+ "epoch": 0.16,
415
+ "learning_rate": 3.841299773352858e-05,
416
+ "loss": 0.2972,
417
+ "step": 68
418
+ },
419
+ {
420
+ "epoch": 0.16,
421
+ "learning_rate": 3.8354502544903484e-05,
422
+ "loss": 0.5059,
423
+ "step": 69
424
+ },
425
+ {
426
+ "epoch": 0.16,
427
+ "learning_rate": 3.829499493880322e-05,
428
+ "loss": 0.3438,
429
+ "step": 70
430
+ },
431
+ {
432
+ "epoch": 0.16,
433
+ "learning_rate": 3.823447819761259e-05,
434
+ "loss": 0.9574,
435
+ "step": 71
436
+ },
437
+ {
438
+ "epoch": 0.16,
439
+ "learning_rate": 3.8172955659379376e-05,
440
+ "loss": 0.3248,
441
+ "step": 72
442
+ },
443
+ {
444
+ "epoch": 0.17,
445
+ "learning_rate": 3.811043071763018e-05,
446
+ "loss": 0.3328,
447
+ "step": 73
448
+ },
449
+ {
450
+ "epoch": 0.17,
451
+ "learning_rate": 3.804690682118328e-05,
452
+ "loss": 0.5611,
453
+ "step": 74
454
+ },
455
+ {
456
+ "epoch": 0.17,
457
+ "learning_rate": 3.798238747395835e-05,
458
+ "loss": 0.355,
459
+ "step": 75
460
+ },
461
+ {
462
+ "epoch": 0.17,
463
+ "learning_rate": 3.791687623478324e-05,
464
+ "loss": 0.6809,
465
+ "step": 76
466
+ },
467
+ {
468
+ "epoch": 0.18,
469
+ "learning_rate": 3.785037671719763e-05,
470
+ "loss": 0.3312,
471
+ "step": 77
472
+ },
473
+ {
474
+ "epoch": 0.18,
475
+ "learning_rate": 3.7782892589253735e-05,
476
+ "loss": 0.36,
477
+ "step": 78
478
+ },
479
+ {
480
+ "epoch": 0.18,
481
+ "learning_rate": 3.771442757331397e-05,
482
+ "loss": 0.3337,
483
+ "step": 79
484
+ },
485
+ {
486
+ "epoch": 0.18,
487
+ "learning_rate": 3.764498544584564e-05,
488
+ "loss": 0.3287,
489
+ "step": 80
490
+ },
491
+ {
492
+ "epoch": 0.19,
493
+ "learning_rate": 3.75745700372126e-05,
494
+ "loss": 0.3119,
495
+ "step": 81
496
+ },
497
+ {
498
+ "epoch": 0.19,
499
+ "learning_rate": 3.7503185231464014e-05,
500
+ "loss": 0.2839,
501
+ "step": 82
502
+ },
503
+ {
504
+ "epoch": 0.19,
505
+ "learning_rate": 3.74308349661201e-05,
506
+ "loss": 0.9241,
507
+ "step": 83
508
+ },
509
+ {
510
+ "epoch": 0.19,
511
+ "learning_rate": 3.735752323195494e-05,
512
+ "loss": 0.3167,
513
+ "step": 84
514
+ },
515
+ {
516
+ "epoch": 0.19,
517
+ "learning_rate": 3.7283254072776336e-05,
518
+ "loss": 0.3737,
519
+ "step": 85
520
+ },
521
+ {
522
+ "epoch": 0.2,
523
+ "learning_rate": 3.720803158520279e-05,
524
+ "loss": 0.2678,
525
+ "step": 86
526
+ },
527
+ {
528
+ "epoch": 0.2,
529
+ "learning_rate": 3.713185991843752e-05,
530
+ "loss": 0.2083,
531
+ "step": 87
532
+ },
533
+ {
534
+ "epoch": 0.2,
535
+ "learning_rate": 3.705474327403958e-05,
536
+ "loss": 0.7429,
537
+ "step": 88
538
+ },
539
+ {
540
+ "epoch": 0.2,
541
+ "learning_rate": 3.697668590569215e-05,
542
+ "loss": 0.4499,
543
+ "step": 89
544
+ },
545
+ {
546
+ "epoch": 0.21,
547
+ "learning_rate": 3.689769211896784e-05,
548
+ "loss": 0.4594,
549
+ "step": 90
550
+ },
551
+ {
552
+ "epoch": 0.21,
553
+ "learning_rate": 3.681776627109127e-05,
554
+ "loss": 0.379,
555
+ "step": 91
556
+ },
557
+ {
558
+ "epoch": 0.21,
559
+ "learning_rate": 3.673691277069867e-05,
560
+ "loss": 0.4662,
561
+ "step": 92
562
+ },
563
+ {
564
+ "epoch": 0.21,
565
+ "learning_rate": 3.665513607759474e-05,
566
+ "loss": 0.357,
567
+ "step": 93
568
+ },
569
+ {
570
+ "epoch": 0.21,
571
+ "learning_rate": 3.657244070250665e-05,
572
+ "loss": 0.7296,
573
+ "step": 94
574
+ },
575
+ {
576
+ "epoch": 0.22,
577
+ "learning_rate": 3.648883120683521e-05,
578
+ "loss": 0.3254,
579
+ "step": 95
580
+ },
581
+ {
582
+ "epoch": 0.22,
583
+ "learning_rate": 3.640431220240329e-05,
584
+ "loss": 0.3623,
585
+ "step": 96
586
+ },
587
+ {
588
+ "epoch": 0.22,
589
+ "learning_rate": 3.631888835120141e-05,
590
+ "loss": 0.6485,
591
+ "step": 97
592
+ },
593
+ {
594
+ "epoch": 0.22,
595
+ "learning_rate": 3.6232564365130626e-05,
596
+ "loss": 0.3066,
597
+ "step": 98
598
+ },
599
+ {
600
+ "epoch": 0.23,
601
+ "learning_rate": 3.614534500574259e-05,
602
+ "loss": 0.3152,
603
+ "step": 99
604
+ },
605
+ {
606
+ "epoch": 0.23,
607
+ "learning_rate": 3.605723508397694e-05,
608
+ "loss": 0.5848,
609
+ "step": 100
610
+ },
611
+ {
612
+ "epoch": 0.23,
613
+ "learning_rate": 3.596823945989589e-05,
614
+ "loss": 0.3347,
615
+ "step": 101
616
+ },
617
+ {
618
+ "epoch": 0.23,
619
+ "learning_rate": 3.58783630424162e-05,
620
+ "loss": 0.3636,
621
+ "step": 102
622
+ },
623
+ {
624
+ "epoch": 0.24,
625
+ "learning_rate": 3.5787610789038373e-05,
626
+ "loss": 0.2241,
627
+ "step": 103
628
+ },
629
+ {
630
+ "epoch": 0.24,
631
+ "learning_rate": 3.5695987705573223e-05,
632
+ "loss": 0.4166,
633
+ "step": 104
634
+ },
635
+ {
636
+ "epoch": 0.24,
637
+ "learning_rate": 3.560349884586574e-05,
638
+ "loss": 0.6224,
639
+ "step": 105
640
+ },
641
+ {
642
+ "epoch": 0.24,
643
+ "learning_rate": 3.551014931151635e-05,
644
+ "loss": 0.3595,
645
+ "step": 106
646
+ },
647
+ {
648
+ "epoch": 0.24,
649
+ "learning_rate": 3.5415944251599476e-05,
650
+ "loss": 0.2988,
651
+ "step": 107
652
+ },
653
+ {
654
+ "epoch": 0.25,
655
+ "learning_rate": 3.532088886237956e-05,
656
+ "loss": 0.3415,
657
+ "step": 108
658
+ },
659
+ {
660
+ "epoch": 0.25,
661
+ "learning_rate": 3.522498838702444e-05,
662
+ "loss": 0.3732,
663
+ "step": 109
664
+ },
665
+ {
666
+ "epoch": 0.25,
667
+ "learning_rate": 3.5128248115316114e-05,
668
+ "loss": 0.2805,
669
+ "step": 110
670
+ },
671
+ {
672
+ "epoch": 0.25,
673
+ "learning_rate": 3.5030673383358956e-05,
674
+ "loss": 0.5045,
675
+ "step": 111
676
+ },
677
+ {
678
+ "epoch": 0.26,
679
+ "learning_rate": 3.493226957328542e-05,
680
+ "loss": 0.3575,
681
+ "step": 112
682
+ },
683
+ {
684
+ "epoch": 0.26,
685
+ "learning_rate": 3.483304211295915e-05,
686
+ "loss": 0.3387,
687
+ "step": 113
688
+ },
689
+ {
690
+ "epoch": 0.26,
691
+ "learning_rate": 3.473299647567558e-05,
692
+ "loss": 0.5167,
693
+ "step": 114
694
+ },
695
+ {
696
+ "epoch": 0.26,
697
+ "learning_rate": 3.4632138179860013e-05,
698
+ "loss": 0.252,
699
+ "step": 115
700
+ },
701
+ {
702
+ "epoch": 0.27,
703
+ "learning_rate": 3.453047278876327e-05,
704
+ "loss": 0.299,
705
+ "step": 116
706
+ },
707
+ {
708
+ "epoch": 0.27,
709
+ "learning_rate": 3.442800591015479e-05,
710
+ "loss": 0.4623,
711
+ "step": 117
712
+ },
713
+ {
714
+ "epoch": 0.27,
715
+ "learning_rate": 3.4324743196013335e-05,
716
+ "loss": 0.3507,
717
+ "step": 118
718
+ },
719
+ {
720
+ "epoch": 0.27,
721
+ "learning_rate": 3.422069034221522e-05,
722
+ "loss": 0.3827,
723
+ "step": 119
724
+ },
725
+ {
726
+ "epoch": 0.27,
727
+ "learning_rate": 3.411585308822014e-05,
728
+ "loss": 0.3607,
729
+ "step": 120
730
+ },
731
+ {
732
+ "epoch": 0.28,
733
+ "learning_rate": 3.4010237216754575e-05,
734
+ "loss": 0.3312,
735
+ "step": 121
736
+ },
737
+ {
738
+ "epoch": 0.28,
739
+ "learning_rate": 3.390384855349285e-05,
740
+ "loss": 0.3545,
741
+ "step": 122
742
+ },
743
+ {
744
+ "epoch": 0.28,
745
+ "learning_rate": 3.379669296673574e-05,
746
+ "loss": 0.3093,
747
+ "step": 123
748
+ },
749
+ {
750
+ "epoch": 0.28,
751
+ "learning_rate": 3.3688776367086837e-05,
752
+ "loss": 0.5048,
753
+ "step": 124
754
+ },
755
+ {
756
+ "epoch": 0.29,
757
+ "learning_rate": 3.358010470712651e-05,
758
+ "loss": 0.2603,
759
+ "step": 125
760
+ },
761
+ {
762
+ "epoch": 0.29,
763
+ "learning_rate": 3.347068398108353e-05,
764
+ "loss": 0.2749,
765
+ "step": 126
766
+ },
767
+ {
768
+ "epoch": 0.29,
769
+ "learning_rate": 3.3360520224504505e-05,
770
+ "loss": 0.3122,
771
+ "step": 127
772
+ },
773
+ {
774
+ "epoch": 0.29,
775
+ "learning_rate": 3.324961951392089e-05,
776
+ "loss": 0.3832,
777
+ "step": 128
778
+ },
779
+ {
780
+ "epoch": 0.29,
781
+ "learning_rate": 3.313798796651386e-05,
782
+ "loss": 0.2636,
783
+ "step": 129
784
+ },
785
+ {
786
+ "epoch": 0.3,
787
+ "learning_rate": 3.302563173977688e-05,
788
+ "loss": 0.3716,
789
+ "step": 130
790
+ },
791
+ {
792
+ "epoch": 0.3,
793
+ "learning_rate": 3.291255703117605e-05,
794
+ "loss": 0.7091,
795
+ "step": 131
796
+ },
797
+ {
798
+ "epoch": 0.3,
799
+ "learning_rate": 3.279877007780828e-05,
800
+ "loss": 0.491,
801
+ "step": 132
802
+ },
803
+ {
804
+ "epoch": 0.3,
805
+ "learning_rate": 3.268427715605723e-05,
806
+ "loss": 0.4181,
807
+ "step": 133
808
+ },
809
+ {
810
+ "epoch": 0.31,
811
+ "learning_rate": 3.2569084581247137e-05,
812
+ "loss": 0.3262,
813
+ "step": 134
814
+ },
815
+ {
816
+ "epoch": 0.31,
817
+ "learning_rate": 3.245319870729446e-05,
818
+ "loss": 0.3126,
819
+ "step": 135
820
+ },
821
+ {
822
+ "epoch": 0.31,
823
+ "learning_rate": 3.23366259263574e-05,
824
+ "loss": 0.2856,
825
+ "step": 136
826
+ },
827
+ {
828
+ "epoch": 0.31,
829
+ "learning_rate": 3.221937266848331e-05,
830
+ "loss": 0.7066,
831
+ "step": 137
832
+ },
833
+ {
834
+ "epoch": 0.32,
835
+ "learning_rate": 3.210144540125402e-05,
836
+ "loss": 0.2677,
837
+ "step": 138
838
+ },
839
+ {
840
+ "epoch": 0.32,
841
+ "learning_rate": 3.198285062942912e-05,
842
+ "loss": 0.2525,
843
+ "step": 139
844
+ },
845
+ {
846
+ "epoch": 0.32,
847
+ "learning_rate": 3.1863594894587106e-05,
848
+ "loss": 0.3914,
849
+ "step": 140
850
+ },
851
+ {
852
+ "epoch": 0.32,
853
+ "learning_rate": 3.174368477476461e-05,
854
+ "loss": 0.3101,
855
+ "step": 141
856
+ },
857
+ {
858
+ "epoch": 0.32,
859
+ "learning_rate": 3.1623126884093536e-05,
860
+ "loss": 0.3466,
861
+ "step": 142
862
+ },
863
+ {
864
+ "epoch": 0.33,
865
+ "learning_rate": 3.150192787243621e-05,
866
+ "loss": 0.2589,
867
+ "step": 143
868
+ },
869
+ {
870
+ "epoch": 0.33,
871
+ "learning_rate": 3.1380094425018634e-05,
872
+ "loss": 0.2615,
873
+ "step": 144
874
+ },
875
+ {
876
+ "epoch": 0.33,
877
+ "learning_rate": 3.1257633262061674e-05,
878
+ "loss": 0.4989,
879
+ "step": 145
880
+ },
881
+ {
882
+ "epoch": 0.33,
883
+ "learning_rate": 3.113455113841043e-05,
884
+ "loss": 0.3507,
885
+ "step": 146
886
+ },
887
+ {
888
+ "epoch": 0.34,
889
+ "learning_rate": 3.101085484316162e-05,
890
+ "loss": 0.7505,
891
+ "step": 147
892
+ },
893
+ {
894
+ "epoch": 0.34,
895
+ "learning_rate": 3.0886551199289074e-05,
896
+ "loss": 0.304,
897
+ "step": 148
898
+ },
899
+ {
900
+ "epoch": 0.34,
901
+ "learning_rate": 3.0761647063267455e-05,
902
+ "loss": 0.2395,
903
+ "step": 149
904
+ },
905
+ {
906
+ "epoch": 0.34,
907
+ "learning_rate": 3.063614932469399e-05,
908
+ "loss": 0.2855,
909
+ "step": 150
910
+ },
911
+ {
912
+ "epoch": 0.35,
913
+ "learning_rate": 3.0510064905908492e-05,
914
+ "loss": 0.3145,
915
+ "step": 151
916
+ },
917
+ {
918
+ "epoch": 0.35,
919
+ "learning_rate": 3.038340076161151e-05,
920
+ "loss": 0.6382,
921
+ "step": 152
922
+ },
923
+ {
924
+ "epoch": 0.35,
925
+ "learning_rate": 3.0256163878480715e-05,
926
+ "loss": 0.2493,
927
+ "step": 153
928
+ },
929
+ {
930
+ "epoch": 0.35,
931
+ "learning_rate": 3.012836127478553e-05,
932
+ "loss": 0.2916,
933
+ "step": 154
934
+ },
935
+ {
936
+ "epoch": 0.35,
937
+ "learning_rate": 3.0000000000000004e-05,
938
+ "loss": 0.2677,
939
+ "step": 155
940
+ },
941
+ {
942
+ "epoch": 0.36,
943
+ "learning_rate": 2.9871087134413968e-05,
944
+ "loss": 0.346,
945
+ "step": 156
946
+ },
947
+ {
948
+ "epoch": 0.36,
949
+ "learning_rate": 2.974162978874249e-05,
950
+ "loss": 0.2209,
951
+ "step": 157
952
+ },
953
+ {
954
+ "epoch": 0.36,
955
+ "learning_rate": 2.9611635103733677e-05,
956
+ "loss": 0.4053,
957
+ "step": 158
958
+ },
959
+ {
960
+ "epoch": 0.36,
961
+ "learning_rate": 2.9481110249774755e-05,
962
+ "loss": 0.6514,
963
+ "step": 159
964
+ },
965
+ {
966
+ "epoch": 0.37,
967
+ "learning_rate": 2.935006242649659e-05,
968
+ "loss": 0.3108,
969
+ "step": 160
970
+ },
971
+ {
972
+ "epoch": 0.37,
973
+ "learning_rate": 2.921849886237656e-05,
974
+ "loss": 0.7936,
975
+ "step": 161
976
+ },
977
+ {
978
+ "epoch": 0.37,
979
+ "learning_rate": 2.9086426814339838e-05,
980
+ "loss": 0.3377,
981
+ "step": 162
982
+ },
983
+ {
984
+ "epoch": 0.37,
985
+ "learning_rate": 2.895385356735908e-05,
986
+ "loss": 0.3292,
987
+ "step": 163
988
+ },
989
+ {
990
+ "epoch": 0.37,
991
+ "learning_rate": 2.8820786434052634e-05,
992
+ "loss": 0.6782,
993
+ "step": 164
994
+ },
995
+ {
996
+ "epoch": 0.38,
997
+ "learning_rate": 2.8687232754281162e-05,
998
+ "loss": 0.3089,
999
+ "step": 165
1000
+ },
1001
+ {
1002
+ "epoch": 0.38,
1003
+ "learning_rate": 2.8553199894742776e-05,
1004
+ "loss": 0.3611,
1005
+ "step": 166
1006
+ },
1007
+ {
1008
+ "epoch": 0.38,
1009
+ "learning_rate": 2.8418695248566703e-05,
1010
+ "loss": 0.3621,
1011
+ "step": 167
1012
+ },
1013
+ {
1014
+ "epoch": 0.38,
1015
+ "learning_rate": 2.8283726234905492e-05,
1016
+ "loss": 0.2988,
1017
+ "step": 168
1018
+ },
1019
+ {
1020
+ "epoch": 0.39,
1021
+ "learning_rate": 2.8148300298525764e-05,
1022
+ "loss": 0.3555,
1023
+ "step": 169
1024
+ },
1025
+ {
1026
+ "epoch": 0.39,
1027
+ "learning_rate": 2.8012424909397597e-05,
1028
+ "loss": 0.2199,
1029
+ "step": 170
1030
+ },
1031
+ {
1032
+ "epoch": 0.39,
1033
+ "learning_rate": 2.7876107562282447e-05,
1034
+ "loss": 0.2688,
1035
+ "step": 171
1036
+ },
1037
+ {
1038
+ "epoch": 0.39,
1039
+ "learning_rate": 2.7739355776319775e-05,
1040
+ "loss": 0.2502,
1041
+ "step": 172
1042
+ },
1043
+ {
1044
+ "epoch": 0.4,
1045
+ "learning_rate": 2.7602177094612298e-05,
1046
+ "loss": 0.5406,
1047
+ "step": 173
1048
+ },
1049
+ {
1050
+ "epoch": 0.4,
1051
+ "learning_rate": 2.7464579083809896e-05,
1052
+ "loss": 0.4893,
1053
+ "step": 174
1054
+ },
1055
+ {
1056
+ "epoch": 0.4,
1057
+ "learning_rate": 2.732656933369227e-05,
1058
+ "loss": 0.2604,
1059
+ "step": 175
1060
+ },
1061
+ {
1062
+ "epoch": 0.4,
1063
+ "learning_rate": 2.7188155456750257e-05,
1064
+ "loss": 0.2974,
1065
+ "step": 176
1066
+ },
1067
+ {
1068
+ "epoch": 0.4,
1069
+ "learning_rate": 2.7049345087765995e-05,
1070
+ "loss": 0.3004,
1071
+ "step": 177
1072
+ },
1073
+ {
1074
+ "epoch": 0.41,
1075
+ "learning_rate": 2.6910145883391726e-05,
1076
+ "loss": 0.3131,
1077
+ "step": 178
1078
+ },
1079
+ {
1080
+ "epoch": 0.41,
1081
+ "learning_rate": 2.6770565521727516e-05,
1082
+ "loss": 0.305,
1083
+ "step": 179
1084
+ },
1085
+ {
1086
+ "epoch": 0.41,
1087
+ "learning_rate": 2.6630611701897696e-05,
1088
+ "loss": 0.2949,
1089
+ "step": 180
1090
+ },
1091
+ {
1092
+ "epoch": 0.41,
1093
+ "learning_rate": 2.6490292143626228e-05,
1094
+ "loss": 0.9866,
1095
+ "step": 181
1096
+ },
1097
+ {
1098
+ "epoch": 0.42,
1099
+ "learning_rate": 2.6349614586810854e-05,
1100
+ "loss": 0.2713,
1101
+ "step": 182
1102
+ },
1103
+ {
1104
+ "epoch": 0.42,
1105
+ "learning_rate": 2.6208586791096196e-05,
1106
+ "loss": 0.4035,
1107
+ "step": 183
1108
+ },
1109
+ {
1110
+ "epoch": 0.42,
1111
+ "learning_rate": 2.606721653544572e-05,
1112
+ "loss": 1.2587,
1113
+ "step": 184
1114
+ },
1115
+ {
1116
+ "epoch": 0.42,
1117
+ "learning_rate": 2.5925511617712683e-05,
1118
+ "loss": 0.2273,
1119
+ "step": 185
1120
+ },
1121
+ {
1122
+ "epoch": 0.43,
1123
+ "learning_rate": 2.5783479854209983e-05,
1124
+ "loss": 0.2003,
1125
+ "step": 186
1126
+ },
1127
+ {
1128
+ "epoch": 0.43,
1129
+ "learning_rate": 2.5641129079279025e-05,
1130
+ "loss": 0.8117,
1131
+ "step": 187
1132
+ },
1133
+ {
1134
+ "epoch": 0.43,
1135
+ "learning_rate": 2.549846714485761e-05,
1136
+ "loss": 0.7241,
1137
+ "step": 188
1138
+ },
1139
+ {
1140
+ "epoch": 0.43,
1141
+ "learning_rate": 2.5355501920046792e-05,
1142
+ "loss": 0.854,
1143
+ "step": 189
1144
+ },
1145
+ {
1146
+ "epoch": 0.43,
1147
+ "learning_rate": 2.5212241290676857e-05,
1148
+ "loss": 0.2085,
1149
+ "step": 190
1150
+ },
1151
+ {
1152
+ "epoch": 0.44,
1153
+ "learning_rate": 2.5068693158872315e-05,
1154
+ "loss": 0.3107,
1155
+ "step": 191
1156
+ },
1157
+ {
1158
+ "epoch": 0.44,
1159
+ "learning_rate": 2.492486544261608e-05,
1160
+ "loss": 0.4577,
1161
+ "step": 192
1162
+ },
1163
+ {
1164
+ "epoch": 0.44,
1165
+ "learning_rate": 2.4780766075312652e-05,
1166
+ "loss": 0.4021,
1167
+ "step": 193
1168
+ },
1169
+ {
1170
+ "epoch": 0.44,
1171
+ "learning_rate": 2.463640300535057e-05,
1172
+ "loss": 0.7204,
1173
+ "step": 194
1174
+ },
1175
+ {
1176
+ "epoch": 0.45,
1177
+ "learning_rate": 2.4491784195663965e-05,
1178
+ "loss": 0.2075,
1179
+ "step": 195
1180
+ },
1181
+ {
1182
+ "epoch": 0.45,
1183
+ "learning_rate": 2.434691762329334e-05,
1184
+ "loss": 0.2459,
1185
+ "step": 196
1186
+ },
1187
+ {
1188
+ "epoch": 0.45,
1189
+ "learning_rate": 2.420181127894556e-05,
1190
+ "loss": 0.3556,
1191
+ "step": 197
1192
+ },
1193
+ {
1194
+ "epoch": 0.45,
1195
+ "learning_rate": 2.4056473166553087e-05,
1196
+ "loss": 0.4762,
1197
+ "step": 198
1198
+ },
1199
+ {
1200
+ "epoch": 0.45,
1201
+ "learning_rate": 2.391091130283249e-05,
1202
+ "loss": 0.2244,
1203
+ "step": 199
1204
+ },
1205
+ {
1206
+ "epoch": 0.46,
1207
+ "learning_rate": 2.3765133716842273e-05,
1208
+ "loss": 0.7107,
1209
+ "step": 200
1210
+ },
1211
+ {
1212
+ "epoch": 0.46,
1213
+ "learning_rate": 2.3619148449539965e-05,
1214
+ "loss": 0.4242,
1215
+ "step": 201
1216
+ },
1217
+ {
1218
+ "epoch": 0.46,
1219
+ "learning_rate": 2.3472963553338614e-05,
1220
+ "loss": 0.3044,
1221
+ "step": 202
1222
+ },
1223
+ {
1224
+ "epoch": 0.46,
1225
+ "learning_rate": 2.3326587091662605e-05,
1226
+ "loss": 0.2674,
1227
+ "step": 203
1228
+ },
1229
+ {
1230
+ "epoch": 0.47,
1231
+ "learning_rate": 2.3180027138502913e-05,
1232
+ "loss": 0.2977,
1233
+ "step": 204
1234
+ },
1235
+ {
1236
+ "epoch": 0.47,
1237
+ "learning_rate": 2.303329177797172e-05,
1238
+ "loss": 0.3201,
1239
+ "step": 205
1240
+ },
1241
+ {
1242
+ "epoch": 0.47,
1243
+ "learning_rate": 2.2886389103856534e-05,
1244
+ "loss": 0.2589,
1245
+ "step": 206
1246
+ },
1247
+ {
1248
+ "epoch": 0.47,
1249
+ "learning_rate": 2.2739327219173707e-05,
1250
+ "loss": 0.2949,
1251
+ "step": 207
1252
+ },
1253
+ {
1254
+ "epoch": 0.48,
1255
+ "learning_rate": 2.259211423572152e-05,
1256
+ "loss": 0.2762,
1257
+ "step": 208
1258
+ },
1259
+ {
1260
+ "epoch": 0.48,
1261
+ "learning_rate": 2.2444758273632693e-05,
1262
+ "loss": 0.3394,
1263
+ "step": 209
1264
+ },
1265
+ {
1266
+ "epoch": 0.48,
1267
+ "learning_rate": 2.2297267460926548e-05,
1268
+ "loss": 0.2609,
1269
+ "step": 210
1270
+ },
1271
+ {
1272
+ "epoch": 0.48,
1273
+ "learning_rate": 2.2149649933060625e-05,
1274
+ "loss": 0.295,
1275
+ "step": 211
1276
+ },
1277
+ {
1278
+ "epoch": 0.48,
1279
+ "learning_rate": 2.200191383248197e-05,
1280
+ "loss": 0.3794,
1281
+ "step": 212
1282
+ },
1283
+ {
1284
+ "epoch": 0.49,
1285
+ "learning_rate": 2.1854067308177967e-05,
1286
+ "loss": 0.4467,
1287
+ "step": 213
1288
+ },
1289
+ {
1290
+ "epoch": 0.49,
1291
+ "learning_rate": 2.1706118515226894e-05,
1292
+ "loss": 0.2828,
1293
+ "step": 214
1294
+ },
1295
+ {
1296
+ "epoch": 0.49,
1297
+ "learning_rate": 2.1558075614348065e-05,
1298
+ "loss": 0.3457,
1299
+ "step": 215
1300
+ },
1301
+ {
1302
+ "epoch": 0.49,
1303
+ "learning_rate": 2.1409946771451705e-05,
1304
+ "loss": 0.2655,
1305
+ "step": 216
1306
+ },
1307
+ {
1308
+ "epoch": 0.5,
1309
+ "learning_rate": 2.1261740157188498e-05,
1310
+ "loss": 0.3977,
1311
+ "step": 217
1312
+ },
1313
+ {
1314
+ "epoch": 0.5,
1315
+ "learning_rate": 2.111346394649897e-05,
1316
+ "loss": 0.274,
1317
+ "step": 218
1318
+ },
1319
+ {
1320
+ "epoch": 0.5,
1321
+ "learning_rate": 2.0965126318162476e-05,
1322
+ "loss": 0.4635,
1323
+ "step": 219
1324
+ },
1325
+ {
1326
+ "epoch": 0.5,
1327
+ "learning_rate": 2.0816735454346134e-05,
1328
+ "loss": 0.3107,
1329
+ "step": 220
1330
+ },
1331
+ {
1332
+ "epoch": 0.51,
1333
+ "learning_rate": 2.0668299540153494e-05,
1334
+ "loss": 0.4861,
1335
+ "step": 221
1336
+ },
1337
+ {
1338
+ "epoch": 0.51,
1339
+ "learning_rate": 2.051982676317302e-05,
1340
+ "loss": 0.2846,
1341
+ "step": 222
1342
+ },
1343
+ {
1344
+ "epoch": 0.51,
1345
+ "learning_rate": 2.0371325313026502e-05,
1346
+ "loss": 0.3598,
1347
+ "step": 223
1348
+ },
1349
+ {
1350
+ "epoch": 0.51,
1351
+ "learning_rate": 2.022280338091731e-05,
1352
+ "loss": 0.2647,
1353
+ "step": 224
1354
+ },
1355
+ {
1356
+ "epoch": 0.51,
1357
+ "learning_rate": 2.0074269159178606e-05,
1358
+ "loss": 0.4459,
1359
+ "step": 225
1360
+ },
1361
+ {
1362
+ "epoch": 0.52,
1363
+ "learning_rate": 1.9925730840821404e-05,
1364
+ "loss": 0.5016,
1365
+ "step": 226
1366
+ },
1367
+ {
1368
+ "epoch": 0.52,
1369
+ "learning_rate": 1.9777196619082693e-05,
1370
+ "loss": 0.3645,
1371
+ "step": 227
1372
+ },
1373
+ {
1374
+ "epoch": 0.52,
1375
+ "learning_rate": 1.9628674686973508e-05,
1376
+ "loss": 0.5755,
1377
+ "step": 228
1378
+ },
1379
+ {
1380
+ "epoch": 0.52,
1381
+ "learning_rate": 1.948017323682699e-05,
1382
+ "loss": 0.3132,
1383
+ "step": 229
1384
+ },
1385
+ {
1386
+ "epoch": 0.53,
1387
+ "learning_rate": 1.9331700459846516e-05,
1388
+ "loss": 0.5478,
1389
+ "step": 230
1390
+ },
1391
+ {
1392
+ "epoch": 0.53,
1393
+ "learning_rate": 1.918326454565387e-05,
1394
+ "loss": 0.274,
1395
+ "step": 231
1396
+ },
1397
+ {
1398
+ "epoch": 0.53,
1399
+ "learning_rate": 1.9034873681837534e-05,
1400
+ "loss": 0.3535,
1401
+ "step": 232
1402
+ },
1403
+ {
1404
+ "epoch": 0.53,
1405
+ "learning_rate": 1.8886536053501042e-05,
1406
+ "loss": 0.2747,
1407
+ "step": 233
1408
+ },
1409
+ {
1410
+ "epoch": 0.53,
1411
+ "learning_rate": 1.873825984281151e-05,
1412
+ "loss": 0.2108,
1413
+ "step": 234
1414
+ },
1415
+ {
1416
+ "epoch": 0.54,
1417
+ "learning_rate": 1.8590053228548305e-05,
1418
+ "loss": 0.3552,
1419
+ "step": 235
1420
+ },
1421
+ {
1422
+ "epoch": 0.54,
1423
+ "learning_rate": 1.844192438565194e-05,
1424
+ "loss": 0.3144,
1425
+ "step": 236
1426
+ },
1427
+ {
1428
+ "epoch": 0.54,
1429
+ "learning_rate": 1.829388148477311e-05,
1430
+ "loss": 0.2116,
1431
+ "step": 237
1432
+ },
1433
+ {
1434
+ "epoch": 0.54,
1435
+ "learning_rate": 1.814593269182204e-05,
1436
+ "loss": 0.3492,
1437
+ "step": 238
1438
+ },
1439
+ {
1440
+ "epoch": 0.55,
1441
+ "learning_rate": 1.7998086167518033e-05,
1442
+ "loss": 0.2632,
1443
+ "step": 239
1444
+ },
1445
+ {
1446
+ "epoch": 0.55,
1447
+ "learning_rate": 1.785035006693938e-05,
1448
+ "loss": 0.4334,
1449
+ "step": 240
1450
+ },
1451
+ {
1452
+ "epoch": 0.55,
1453
+ "learning_rate": 1.770273253907346e-05,
1454
+ "loss": 0.2417,
1455
+ "step": 241
1456
+ },
1457
+ {
1458
+ "epoch": 0.55,
1459
+ "learning_rate": 1.7555241726367317e-05,
1460
+ "loss": 0.2955,
1461
+ "step": 242
1462
+ },
1463
+ {
1464
+ "epoch": 0.56,
1465
+ "learning_rate": 1.7407885764278488e-05,
1466
+ "loss": 0.538,
1467
+ "step": 243
1468
+ },
1469
+ {
1470
+ "epoch": 0.56,
1471
+ "learning_rate": 1.7260672780826296e-05,
1472
+ "loss": 0.2689,
1473
+ "step": 244
1474
+ },
1475
+ {
1476
+ "epoch": 0.56,
1477
+ "learning_rate": 1.7113610896143473e-05,
1478
+ "loss": 0.2849,
1479
+ "step": 245
1480
+ },
1481
+ {
1482
+ "epoch": 0.56,
1483
+ "learning_rate": 1.6966708222028284e-05,
1484
+ "loss": 0.5197,
1485
+ "step": 246
1486
+ },
1487
+ {
1488
+ "epoch": 0.56,
1489
+ "learning_rate": 1.681997286149709e-05,
1490
+ "loss": 0.4282,
1491
+ "step": 247
1492
+ },
1493
+ {
1494
+ "epoch": 0.57,
1495
+ "learning_rate": 1.6673412908337402e-05,
1496
+ "loss": 0.4306,
1497
+ "step": 248
1498
+ },
1499
+ {
1500
+ "epoch": 0.57,
1501
+ "learning_rate": 1.6527036446661396e-05,
1502
+ "loss": 0.2655,
1503
+ "step": 249
1504
+ },
1505
+ {
1506
+ "epoch": 0.57,
1507
+ "learning_rate": 1.638085155046004e-05,
1508
+ "loss": 0.2738,
1509
+ "step": 250
1510
+ },
1511
+ {
1512
+ "epoch": 0.57,
1513
+ "learning_rate": 1.623486628315773e-05,
1514
+ "loss": 0.4238,
1515
+ "step": 251
1516
+ },
1517
+ {
1518
+ "epoch": 0.58,
1519
+ "learning_rate": 1.608908869716751e-05,
1520
+ "loss": 0.2554,
1521
+ "step": 252
1522
+ },
1523
+ {
1524
+ "epoch": 0.58,
1525
+ "learning_rate": 1.5943526833446917e-05,
1526
+ "loss": 0.295,
1527
+ "step": 253
1528
+ },
1529
+ {
1530
+ "epoch": 0.58,
1531
+ "learning_rate": 1.579818872105444e-05,
1532
+ "loss": 0.3214,
1533
+ "step": 254
1534
+ },
1535
+ {
1536
+ "epoch": 0.58,
1537
+ "learning_rate": 1.565308237670666e-05,
1538
+ "loss": 0.2114,
1539
+ "step": 255
1540
+ },
1541
+ {
1542
+ "epoch": 0.59,
1543
+ "learning_rate": 1.550821580433604e-05,
1544
+ "loss": 0.3037,
1545
+ "step": 256
1546
+ },
1547
+ {
1548
+ "epoch": 0.59,
1549
+ "learning_rate": 1.5363596994649433e-05,
1550
+ "loss": 0.3683,
1551
+ "step": 257
1552
+ },
1553
+ {
1554
+ "epoch": 0.59,
1555
+ "learning_rate": 1.5219233924687351e-05,
1556
+ "loss": 0.4236,
1557
+ "step": 258
1558
+ },
1559
+ {
1560
+ "epoch": 0.59,
1561
+ "learning_rate": 1.5075134557383931e-05,
1562
+ "loss": 0.2787,
1563
+ "step": 259
1564
+ },
1565
+ {
1566
+ "epoch": 0.59,
1567
+ "learning_rate": 1.4931306841127691e-05,
1568
+ "loss": 0.588,
1569
+ "step": 260
1570
+ },
1571
+ {
1572
+ "epoch": 0.6,
1573
+ "learning_rate": 1.4787758709323155e-05,
1574
+ "loss": 0.2892,
1575
+ "step": 261
1576
+ },
1577
+ {
1578
+ "epoch": 0.6,
1579
+ "learning_rate": 1.4644498079953215e-05,
1580
+ "loss": 0.5691,
1581
+ "step": 262
1582
+ },
1583
+ {
1584
+ "epoch": 0.6,
1585
+ "learning_rate": 1.45015328551424e-05,
1586
+ "loss": 0.2227,
1587
+ "step": 263
1588
+ },
1589
+ {
1590
+ "epoch": 0.6,
1591
+ "learning_rate": 1.4358870920720982e-05,
1592
+ "loss": 0.5576,
1593
+ "step": 264
1594
+ },
1595
+ {
1596
+ "epoch": 0.61,
1597
+ "learning_rate": 1.4216520145790027e-05,
1598
+ "loss": 0.6571,
1599
+ "step": 265
1600
+ },
1601
+ {
1602
+ "epoch": 0.61,
1603
+ "learning_rate": 1.4074488382287324e-05,
1604
+ "loss": 0.4547,
1605
+ "step": 266
1606
+ },
1607
+ {
1608
+ "epoch": 0.61,
1609
+ "learning_rate": 1.3932783464554286e-05,
1610
+ "loss": 0.3705,
1611
+ "step": 267
1612
+ },
1613
+ {
1614
+ "epoch": 0.61,
1615
+ "learning_rate": 1.379141320890381e-05,
1616
+ "loss": 0.4904,
1617
+ "step": 268
1618
+ },
1619
+ {
1620
+ "epoch": 0.61,
1621
+ "learning_rate": 1.3650385413189151e-05,
1622
+ "loss": 0.4299,
1623
+ "step": 269
1624
+ },
1625
+ {
1626
+ "epoch": 0.62,
1627
+ "learning_rate": 1.3509707856373779e-05,
1628
+ "loss": 0.4775,
1629
+ "step": 270
1630
+ },
1631
+ {
1632
+ "epoch": 0.62,
1633
+ "learning_rate": 1.3369388298102312e-05,
1634
+ "loss": 0.2769,
1635
+ "step": 271
1636
+ },
1637
+ {
1638
+ "epoch": 0.62,
1639
+ "learning_rate": 1.3229434478272492e-05,
1640
+ "loss": 0.2478,
1641
+ "step": 272
1642
+ },
1643
+ {
1644
+ "epoch": 0.62,
1645
+ "learning_rate": 1.3089854116608279e-05,
1646
+ "loss": 0.3056,
1647
+ "step": 273
1648
+ },
1649
+ {
1650
+ "epoch": 0.63,
1651
+ "learning_rate": 1.295065491223401e-05,
1652
+ "loss": 0.4498,
1653
+ "step": 274
1654
+ },
1655
+ {
1656
+ "epoch": 0.63,
1657
+ "learning_rate": 1.2811844543249748e-05,
1658
+ "loss": 0.5963,
1659
+ "step": 275
1660
+ },
1661
+ {
1662
+ "epoch": 0.63,
1663
+ "learning_rate": 1.2673430666307738e-05,
1664
+ "loss": 0.4305,
1665
+ "step": 276
1666
+ },
1667
+ {
1668
+ "epoch": 0.63,
1669
+ "learning_rate": 1.2535420916190106e-05,
1670
+ "loss": 0.3375,
1671
+ "step": 277
1672
+ },
1673
+ {
1674
+ "epoch": 0.64,
1675
+ "learning_rate": 1.2397822905387707e-05,
1676
+ "loss": 0.3299,
1677
+ "step": 278
1678
+ },
1679
+ {
1680
+ "epoch": 0.64,
1681
+ "learning_rate": 1.2260644223680228e-05,
1682
+ "loss": 0.537,
1683
+ "step": 279
1684
+ },
1685
+ {
1686
+ "epoch": 0.64,
1687
+ "learning_rate": 1.212389243771756e-05,
1688
+ "loss": 0.2732,
1689
+ "step": 280
1690
+ },
1691
+ {
1692
+ "epoch": 0.64,
1693
+ "learning_rate": 1.1987575090602408e-05,
1694
+ "loss": 0.325,
1695
+ "step": 281
1696
+ },
1697
+ {
1698
+ "epoch": 0.64,
1699
+ "learning_rate": 1.185169970147424e-05,
1700
+ "loss": 1.0755,
1701
+ "step": 282
1702
+ },
1703
+ {
1704
+ "epoch": 0.65,
1705
+ "learning_rate": 1.1716273765094517e-05,
1706
+ "loss": 0.6557,
1707
+ "step": 283
1708
+ },
1709
+ {
1710
+ "epoch": 0.65,
1711
+ "learning_rate": 1.1581304751433305e-05,
1712
+ "loss": 0.4481,
1713
+ "step": 284
1714
+ },
1715
+ {
1716
+ "epoch": 0.65,
1717
+ "learning_rate": 1.1446800105257232e-05,
1718
+ "loss": 0.3972,
1719
+ "step": 285
1720
+ },
1721
+ {
1722
+ "epoch": 0.65,
1723
+ "learning_rate": 1.1312767245718836e-05,
1724
+ "loss": 0.3317,
1725
+ "step": 286
1726
+ },
1727
+ {
1728
+ "epoch": 0.66,
1729
+ "learning_rate": 1.1179213565947366e-05,
1730
+ "loss": 0.2758,
1731
+ "step": 287
1732
+ },
1733
+ {
1734
+ "epoch": 0.66,
1735
+ "learning_rate": 1.1046146432640923e-05,
1736
+ "loss": 0.2696,
1737
+ "step": 288
1738
+ },
1739
+ {
1740
+ "epoch": 0.66,
1741
+ "learning_rate": 1.0913573185660167e-05,
1742
+ "loss": 0.3465,
1743
+ "step": 289
1744
+ },
1745
+ {
1746
+ "epoch": 0.66,
1747
+ "learning_rate": 1.078150113762344e-05,
1748
+ "loss": 0.3807,
1749
+ "step": 290
1750
+ },
1751
+ {
1752
+ "epoch": 0.67,
1753
+ "learning_rate": 1.0649937573503419e-05,
1754
+ "loss": 0.3017,
1755
+ "step": 291
1756
+ },
1757
+ {
1758
+ "epoch": 0.67,
1759
+ "learning_rate": 1.051888975022525e-05,
1760
+ "loss": 0.3269,
1761
+ "step": 292
1762
+ },
1763
+ {
1764
+ "epoch": 0.67,
1765
+ "learning_rate": 1.0388364896266326e-05,
1766
+ "loss": 0.1849,
1767
+ "step": 293
1768
+ },
1769
+ {
1770
+ "epoch": 0.67,
1771
+ "learning_rate": 1.0258370211257511e-05,
1772
+ "loss": 0.4315,
1773
+ "step": 294
1774
+ },
1775
+ {
1776
+ "epoch": 0.67,
1777
+ "learning_rate": 1.0128912865586038e-05,
1778
+ "loss": 0.2808,
1779
+ "step": 295
1780
+ },
1781
+ {
1782
+ "epoch": 0.68,
1783
+ "learning_rate": 1.0000000000000006e-05,
1784
+ "loss": 0.292,
1785
+ "step": 296
1786
+ },
1787
+ {
1788
+ "epoch": 0.68,
1789
+ "learning_rate": 9.871638725214481e-06,
1790
+ "loss": 0.2757,
1791
+ "step": 297
1792
+ },
1793
+ {
1794
+ "epoch": 0.68,
1795
+ "learning_rate": 9.743836121519297e-06,
1796
+ "loss": 0.2608,
1797
+ "step": 298
1798
+ },
1799
+ {
1800
+ "epoch": 0.68,
1801
+ "learning_rate": 9.616599238388501e-06,
1802
+ "loss": 0.2605,
1803
+ "step": 299
1804
+ },
1805
+ {
1806
+ "epoch": 0.69,
1807
+ "learning_rate": 9.48993509409151e-06,
1808
+ "loss": 0.2572,
1809
+ "step": 300
1810
+ },
1811
+ {
1812
+ "epoch": 0.69,
1813
+ "learning_rate": 9.363850675306013e-06,
1814
+ "loss": 0.2759,
1815
+ "step": 301
1816
+ },
1817
+ {
1818
+ "epoch": 0.69,
1819
+ "learning_rate": 9.238352936732549e-06,
1820
+ "loss": 0.2789,
1821
+ "step": 302
1822
+ },
1823
+ {
1824
+ "epoch": 0.69,
1825
+ "learning_rate": 9.113448800710929e-06,
1826
+ "loss": 0.2701,
1827
+ "step": 303
1828
+ },
1829
+ {
1830
+ "epoch": 0.69,
1831
+ "learning_rate": 8.989145156838387e-06,
1832
+ "loss": 0.2623,
1833
+ "step": 304
1834
+ },
1835
+ {
1836
+ "epoch": 0.7,
1837
+ "learning_rate": 8.865448861589572e-06,
1838
+ "loss": 0.2679,
1839
+ "step": 305
1840
+ },
1841
+ {
1842
+ "epoch": 0.7,
1843
+ "learning_rate": 8.74236673793833e-06,
1844
+ "loss": 0.4513,
1845
+ "step": 306
1846
+ },
1847
+ {
1848
+ "epoch": 0.7,
1849
+ "learning_rate": 8.619905574981378e-06,
1850
+ "loss": 0.2597,
1851
+ "step": 307
1852
+ },
1853
+ {
1854
+ "epoch": 0.7,
1855
+ "learning_rate": 8.498072127563793e-06,
1856
+ "loss": 0.2465,
1857
+ "step": 308
1858
+ },
1859
+ {
1860
+ "epoch": 0.71,
1861
+ "learning_rate": 8.37687311590647e-06,
1862
+ "loss": 0.2899,
1863
+ "step": 309
1864
+ },
1865
+ {
1866
+ "epoch": 0.71,
1867
+ "learning_rate": 8.256315225235392e-06,
1868
+ "loss": 0.321,
1869
+ "step": 310
1870
+ },
1871
+ {
1872
+ "epoch": 0.71,
1873
+ "learning_rate": 8.136405105412897e-06,
1874
+ "loss": 0.5139,
1875
+ "step": 311
1876
+ },
1877
+ {
1878
+ "epoch": 0.71,
1879
+ "learning_rate": 8.017149370570884e-06,
1880
+ "loss": 0.4021,
1881
+ "step": 312
1882
+ },
1883
+ {
1884
+ "epoch": 0.72,
1885
+ "learning_rate": 7.89855459874598e-06,
1886
+ "loss": 0.4034,
1887
+ "step": 313
1888
+ },
1889
+ {
1890
+ "epoch": 0.72,
1891
+ "learning_rate": 7.780627331516697e-06,
1892
+ "loss": 0.3049,
1893
+ "step": 314
1894
+ },
1895
+ {
1896
+ "epoch": 0.72,
1897
+ "learning_rate": 7.6633740736426e-06,
1898
+ "loss": 0.2607,
1899
+ "step": 315
1900
+ },
1901
+ {
1902
+ "epoch": 0.72,
1903
+ "learning_rate": 7.546801292705539e-06,
1904
+ "loss": 0.4599,
1905
+ "step": 316
1906
+ },
1907
+ {
1908
+ "epoch": 0.72,
1909
+ "learning_rate": 7.430915418752867e-06,
1910
+ "loss": 0.3117,
1911
+ "step": 317
1912
+ },
1913
+ {
1914
+ "epoch": 0.73,
1915
+ "learning_rate": 7.3157228439427765e-06,
1916
+ "loss": 0.4483,
1917
+ "step": 318
1918
+ },
1919
+ {
1920
+ "epoch": 0.73,
1921
+ "learning_rate": 7.201229922191726e-06,
1922
+ "loss": 0.2225,
1923
+ "step": 319
1924
+ },
1925
+ {
1926
+ "epoch": 0.73,
1927
+ "learning_rate": 7.087442968823952e-06,
1928
+ "loss": 0.467,
1929
+ "step": 320
1930
+ },
1931
+ {
1932
+ "epoch": 0.73,
1933
+ "learning_rate": 6.974368260223123e-06,
1934
+ "loss": 0.4134,
1935
+ "step": 321
1936
+ },
1937
+ {
1938
+ "epoch": 0.74,
1939
+ "learning_rate": 6.862012033486145e-06,
1940
+ "loss": 0.3155,
1941
+ "step": 322
1942
+ },
1943
+ {
1944
+ "epoch": 0.74,
1945
+ "learning_rate": 6.7503804860791115e-06,
1946
+ "loss": 0.4041,
1947
+ "step": 323
1948
+ },
1949
+ {
1950
+ "epoch": 0.74,
1951
+ "learning_rate": 6.6394797754955055e-06,
1952
+ "loss": 0.2644,
1953
+ "step": 324
1954
+ },
1955
+ {
1956
+ "epoch": 0.74,
1957
+ "learning_rate": 6.529316018916478e-06,
1958
+ "loss": 0.269,
1959
+ "step": 325
1960
+ },
1961
+ {
1962
+ "epoch": 0.75,
1963
+ "learning_rate": 6.419895292873504e-06,
1964
+ "loss": 0.2354,
1965
+ "step": 326
1966
+ },
1967
+ {
1968
+ "epoch": 0.75,
1969
+ "learning_rate": 6.311223632913173e-06,
1970
+ "loss": 0.2503,
1971
+ "step": 327
1972
+ },
1973
+ {
1974
+ "epoch": 0.75,
1975
+ "learning_rate": 6.203307033264272e-06,
1976
+ "loss": 0.2419,
1977
+ "step": 328
1978
+ },
1979
+ {
1980
+ "epoch": 0.75,
1981
+ "learning_rate": 6.096151446507155e-06,
1982
+ "loss": 0.3827,
1983
+ "step": 329
1984
+ },
1985
+ {
1986
+ "epoch": 0.75,
1987
+ "learning_rate": 5.989762783245423e-06,
1988
+ "loss": 0.2289,
1989
+ "step": 330
1990
+ },
1991
+ {
1992
+ "epoch": 0.76,
1993
+ "learning_rate": 5.884146911779865e-06,
1994
+ "loss": 0.3037,
1995
+ "step": 331
1996
+ },
1997
+ {
1998
+ "epoch": 0.76,
1999
+ "learning_rate": 5.779309657784786e-06,
2000
+ "loss": 0.3167,
2001
+ "step": 332
2002
+ },
2003
+ {
2004
+ "epoch": 0.76,
2005
+ "learning_rate": 5.6752568039866754e-06,
2006
+ "loss": 0.5754,
2007
+ "step": 333
2008
+ },
2009
+ {
2010
+ "epoch": 0.76,
2011
+ "learning_rate": 5.5719940898452205e-06,
2012
+ "loss": 0.2943,
2013
+ "step": 334
2014
+ },
2015
+ {
2016
+ "epoch": 0.77,
2017
+ "learning_rate": 5.46952721123674e-06,
2018
+ "loss": 0.376,
2019
+ "step": 335
2020
+ },
2021
+ {
2022
+ "epoch": 0.77,
2023
+ "learning_rate": 5.367861820139995e-06,
2024
+ "loss": 0.4093,
2025
+ "step": 336
2026
+ },
2027
+ {
2028
+ "epoch": 0.77,
2029
+ "learning_rate": 5.267003524324423e-06,
2030
+ "loss": 0.4033,
2031
+ "step": 337
2032
+ },
2033
+ {
2034
+ "epoch": 0.77,
2035
+ "learning_rate": 5.166957887040849e-06,
2036
+ "loss": 0.3671,
2037
+ "step": 338
2038
+ },
2039
+ {
2040
+ "epoch": 0.77,
2041
+ "learning_rate": 5.067730426714583e-06,
2042
+ "loss": 0.2423,
2043
+ "step": 339
2044
+ },
2045
+ {
2046
+ "epoch": 0.78,
2047
+ "learning_rate": 4.969326616641052e-06,
2048
+ "loss": 0.2651,
2049
+ "step": 340
2050
+ },
2051
+ {
2052
+ "epoch": 0.78,
2053
+ "learning_rate": 4.871751884683895e-06,
2054
+ "loss": 0.5764,
2055
+ "step": 341
2056
+ },
2057
+ {
2058
+ "epoch": 0.78,
2059
+ "learning_rate": 4.775011612975562e-06,
2060
+ "loss": 0.3681,
2061
+ "step": 342
2062
+ },
2063
+ {
2064
+ "epoch": 0.78,
2065
+ "learning_rate": 4.679111137620442e-06,
2066
+ "loss": 0.3841,
2067
+ "step": 343
2068
+ },
2069
+ {
2070
+ "epoch": 0.79,
2071
+ "learning_rate": 4.5840557484005355e-06,
2072
+ "loss": 0.2937,
2073
+ "step": 344
2074
+ },
2075
+ {
2076
+ "epoch": 0.79,
2077
+ "learning_rate": 4.4898506884836565e-06,
2078
+ "loss": 0.2957,
2079
+ "step": 345
2080
+ },
2081
+ {
2082
+ "epoch": 0.79,
2083
+ "learning_rate": 4.3965011541342606e-06,
2084
+ "loss": 0.2435,
2085
+ "step": 346
2086
+ },
2087
+ {
2088
+ "epoch": 0.79,
2089
+ "learning_rate": 4.304012294426781e-06,
2090
+ "loss": 0.3995,
2091
+ "step": 347
2092
+ },
2093
+ {
2094
+ "epoch": 0.8,
2095
+ "learning_rate": 4.212389210961629e-06,
2096
+ "loss": 0.2983,
2097
+ "step": 348
2098
+ },
2099
+ {
2100
+ "epoch": 0.8,
2101
+ "learning_rate": 4.121636957583805e-06,
2102
+ "loss": 0.4387,
2103
+ "step": 349
2104
+ },
2105
+ {
2106
+ "epoch": 0.8,
2107
+ "learning_rate": 4.031760540104115e-06,
2108
+ "loss": 0.3402,
2109
+ "step": 350
2110
+ },
2111
+ {
2112
+ "epoch": 0.8,
2113
+ "learning_rate": 3.942764916023067e-06,
2114
+ "loss": 0.3425,
2115
+ "step": 351
2116
+ },
2117
+ {
2118
+ "epoch": 0.8,
2119
+ "learning_rate": 3.854654994257412e-06,
2120
+ "loss": 0.34,
2121
+ "step": 352
2122
+ },
2123
+ {
2124
+ "epoch": 0.81,
2125
+ "learning_rate": 3.7674356348693764e-06,
2126
+ "loss": 0.3359,
2127
+ "step": 353
2128
+ },
2129
+ {
2130
+ "epoch": 0.81,
2131
+ "learning_rate": 3.681111648798592e-06,
2132
+ "loss": 0.393,
2133
+ "step": 354
2134
+ },
2135
+ {
2136
+ "epoch": 0.81,
2137
+ "learning_rate": 3.5956877975967163e-06,
2138
+ "loss": 0.4085,
2139
+ "step": 355
2140
+ },
2141
+ {
2142
+ "epoch": 0.81,
2143
+ "learning_rate": 3.5111687931647984e-06,
2144
+ "loss": 0.2618,
2145
+ "step": 356
2146
+ },
2147
+ {
2148
+ "epoch": 0.82,
2149
+ "learning_rate": 3.427559297493359e-06,
2150
+ "loss": 0.2674,
2151
+ "step": 357
2152
+ },
2153
+ {
2154
+ "epoch": 0.82,
2155
+ "learning_rate": 3.3448639224052703e-06,
2156
+ "loss": 0.251,
2157
+ "step": 358
2158
+ },
2159
+ {
2160
+ "epoch": 0.82,
2161
+ "learning_rate": 3.2630872293013403e-06,
2162
+ "loss": 0.2529,
2163
+ "step": 359
2164
+ },
2165
+ {
2166
+ "epoch": 0.82,
2167
+ "learning_rate": 3.182233728908741e-06,
2168
+ "loss": 0.1951,
2169
+ "step": 360
2170
+ },
2171
+ {
2172
+ "epoch": 0.83,
2173
+ "learning_rate": 3.102307881032165e-06,
2174
+ "loss": 0.3467,
2175
+ "step": 361
2176
+ },
2177
+ {
2178
+ "epoch": 0.83,
2179
+ "learning_rate": 3.023314094307859e-06,
2180
+ "loss": 0.3827,
2181
+ "step": 362
2182
+ },
2183
+ {
2184
+ "epoch": 0.83,
2185
+ "learning_rate": 2.9452567259604215e-06,
2186
+ "loss": 0.2283,
2187
+ "step": 363
2188
+ },
2189
+ {
2190
+ "epoch": 0.83,
2191
+ "learning_rate": 2.868140081562487e-06,
2192
+ "loss": 0.3542,
2193
+ "step": 364
2194
+ },
2195
+ {
2196
+ "epoch": 0.83,
2197
+ "learning_rate": 2.791968414797217e-06,
2198
+ "loss": 0.2871,
2199
+ "step": 365
2200
+ },
2201
+ {
2202
+ "epoch": 0.84,
2203
+ "learning_rate": 2.7167459272236718e-06,
2204
+ "loss": 0.323,
2205
+ "step": 366
2206
+ },
2207
+ {
2208
+ "epoch": 0.84,
2209
+ "learning_rate": 2.6424767680450657e-06,
2210
+ "loss": 0.9199,
2211
+ "step": 367
2212
+ },
2213
+ {
2214
+ "epoch": 0.84,
2215
+ "learning_rate": 2.5691650338799012e-06,
2216
+ "loss": 0.3337,
2217
+ "step": 368
2218
+ },
2219
+ {
2220
+ "epoch": 0.84,
2221
+ "learning_rate": 2.496814768535989e-06,
2222
+ "loss": 0.4007,
2223
+ "step": 369
2224
+ },
2225
+ {
2226
+ "epoch": 0.85,
2227
+ "learning_rate": 2.4254299627874045e-06,
2228
+ "loss": 0.3352,
2229
+ "step": 370
2230
+ },
2231
+ {
2232
+ "epoch": 0.85,
2233
+ "learning_rate": 2.3550145541543666e-06,
2234
+ "loss": 0.3592,
2235
+ "step": 371
2236
+ },
2237
+ {
2238
+ "epoch": 0.85,
2239
+ "learning_rate": 2.2855724266860314e-06,
2240
+ "loss": 0.2621,
2241
+ "step": 372
2242
+ },
2243
+ {
2244
+ "epoch": 0.85,
2245
+ "learning_rate": 2.217107410746271e-06,
2246
+ "loss": 0.2718,
2247
+ "step": 373
2248
+ },
2249
+ {
2250
+ "epoch": 0.85,
2251
+ "learning_rate": 2.149623282802378e-06,
2252
+ "loss": 0.1917,
2253
+ "step": 374
2254
+ },
2255
+ {
2256
+ "epoch": 0.86,
2257
+ "learning_rate": 2.0831237652167656e-06,
2258
+ "loss": 0.2845,
2259
+ "step": 375
2260
+ },
2261
+ {
2262
+ "epoch": 0.86,
2263
+ "learning_rate": 2.0176125260416544e-06,
2264
+ "loss": 0.2991,
2265
+ "step": 376
2266
+ },
2267
+ {
2268
+ "epoch": 0.86,
2269
+ "learning_rate": 1.9530931788167274e-06,
2270
+ "loss": 0.3188,
2271
+ "step": 377
2272
+ },
2273
+ {
2274
+ "epoch": 0.86,
2275
+ "learning_rate": 1.889569282369823e-06,
2276
+ "loss": 0.2927,
2277
+ "step": 378
2278
+ },
2279
+ {
2280
+ "epoch": 0.87,
2281
+ "learning_rate": 1.8270443406206273e-06,
2282
+ "loss": 0.2112,
2283
+ "step": 379
2284
+ },
2285
+ {
2286
+ "epoch": 0.87,
2287
+ "learning_rate": 1.7655218023874131e-06,
2288
+ "loss": 0.2621,
2289
+ "step": 380
2290
+ },
2291
+ {
2292
+ "epoch": 0.87,
2293
+ "learning_rate": 1.7050050611967872e-06,
2294
+ "loss": 0.2712,
2295
+ "step": 381
2296
+ },
2297
+ {
2298
+ "epoch": 0.87,
2299
+ "learning_rate": 1.6454974550965185e-06,
2300
+ "loss": 0.527,
2301
+ "step": 382
2302
+ },
2303
+ {
2304
+ "epoch": 0.88,
2305
+ "learning_rate": 1.5870022664714225e-06,
2306
+ "loss": 0.3912,
2307
+ "step": 383
2308
+ },
2309
+ {
2310
+ "epoch": 0.88,
2311
+ "learning_rate": 1.529522721862291e-06,
2312
+ "loss": 0.4273,
2313
+ "step": 384
2314
+ },
2315
+ {
2316
+ "epoch": 0.88,
2317
+ "learning_rate": 1.473061991787923e-06,
2318
+ "loss": 0.2741,
2319
+ "step": 385
2320
+ },
2321
+ {
2322
+ "epoch": 0.88,
2323
+ "learning_rate": 1.4176231905702476e-06,
2324
+ "loss": 0.4739,
2325
+ "step": 386
2326
+ },
2327
+ {
2328
+ "epoch": 0.88,
2329
+ "learning_rate": 1.363209376162542e-06,
2330
+ "loss": 0.7205,
2331
+ "step": 387
2332
+ },
2333
+ {
2334
+ "epoch": 0.89,
2335
+ "learning_rate": 1.309823549980751e-06,
2336
+ "loss": 0.3439,
2337
+ "step": 388
2338
+ },
2339
+ {
2340
+ "epoch": 0.89,
2341
+ "learning_rate": 1.2574686567379324e-06,
2342
+ "loss": 0.3784,
2343
+ "step": 389
2344
+ },
2345
+ {
2346
+ "epoch": 0.89,
2347
+ "learning_rate": 1.2061475842818337e-06,
2348
+ "loss": 0.3971,
2349
+ "step": 390
2350
+ },
2351
+ {
2352
+ "epoch": 0.89,
2353
+ "learning_rate": 1.1558631634356e-06,
2354
+ "loss": 0.2784,
2355
+ "step": 391
2356
+ },
2357
+ {
2358
+ "epoch": 0.9,
2359
+ "learning_rate": 1.1066181678416266e-06,
2360
+ "loss": 0.3908,
2361
+ "step": 392
2362
+ },
2363
+ {
2364
+ "epoch": 0.9,
2365
+ "learning_rate": 1.058415313808565e-06,
2366
+ "loss": 0.2788,
2367
+ "step": 393
2368
+ },
2369
+ {
2370
+ "epoch": 0.9,
2371
+ "learning_rate": 1.0112572601615022e-06,
2372
+ "loss": 0.2195,
2373
+ "step": 394
2374
+ },
2375
+ {
2376
+ "epoch": 0.9,
2377
+ "learning_rate": 9.65146608095293e-07,
2378
+ "loss": 0.2877,
2379
+ "step": 395
2380
+ },
2381
+ {
2382
+ "epoch": 0.91,
2383
+ "learning_rate": 9.200859010310847e-07,
2384
+ "loss": 0.1981,
2385
+ "step": 396
2386
+ },
2387
+ {
2388
+ "epoch": 0.91,
2389
+ "learning_rate": 8.760776244760283e-07,
2390
+ "loss": 0.2398,
2391
+ "step": 397
2392
+ },
2393
+ {
2394
+ "epoch": 0.91,
2395
+ "learning_rate": 8.33124205886171e-07,
2396
+ "loss": 0.217,
2397
+ "step": 398
2398
+ },
2399
+ {
2400
+ "epoch": 0.91,
2401
+ "learning_rate": 7.912280145325702e-07,
2402
+ "loss": 0.3294,
2403
+ "step": 399
2404
+ },
2405
+ {
2406
+ "epoch": 0.91,
2407
+ "learning_rate": 7.503913613705971e-07,
2408
+ "loss": 0.3187,
2409
+ "step": 400
2410
+ },
2411
+ {
2412
+ "epoch": 0.92,
2413
+ "learning_rate": 7.106164989124708e-07,
2414
+ "loss": 0.2297,
2415
+ "step": 401
2416
+ },
2417
+ {
2418
+ "epoch": 0.92,
2419
+ "learning_rate": 6.719056211030128e-07,
2420
+ "loss": 0.4698,
2421
+ "step": 402
2422
+ },
2423
+ {
2424
+ "epoch": 0.92,
2425
+ "learning_rate": 6.342608631986346e-07,
2426
+ "loss": 0.2209,
2427
+ "step": 403
2428
+ },
2429
+ {
2430
+ "epoch": 0.92,
2431
+ "learning_rate": 5.976843016495482e-07,
2432
+ "loss": 0.3496,
2433
+ "step": 404
2434
+ },
2435
+ {
2436
+ "epoch": 0.93,
2437
+ "learning_rate": 5.621779539852435e-07,
2438
+ "loss": 0.3261,
2439
+ "step": 405
2440
+ },
2441
+ {
2442
+ "epoch": 0.93,
2443
+ "learning_rate": 5.277437787031892e-07,
2444
+ "loss": 0.2379,
2445
+ "step": 406
2446
+ },
2447
+ {
2448
+ "epoch": 0.93,
2449
+ "learning_rate": 4.943836751608211e-07,
2450
+ "loss": 0.347,
2451
+ "step": 407
2452
+ },
2453
+ {
2454
+ "epoch": 0.93,
2455
+ "learning_rate": 4.6209948347075483e-07,
2456
+ "loss": 0.3664,
2457
+ "step": 408
2458
+ },
2459
+ {
2460
+ "epoch": 0.93,
2461
+ "learning_rate": 4.308929843993115e-07,
2462
+ "loss": 0.2325,
2463
+ "step": 409
2464
+ },
2465
+ {
2466
+ "epoch": 0.94,
2467
+ "learning_rate": 4.0076589926826503e-07,
2468
+ "loss": 0.3251,
2469
+ "step": 410
2470
+ },
2471
+ {
2472
+ "epoch": 0.94,
2473
+ "learning_rate": 3.7171988985991835e-07,
2474
+ "loss": 0.3222,
2475
+ "step": 411
2476
+ },
2477
+ {
2478
+ "epoch": 0.94,
2479
+ "learning_rate": 3.4375655832542763e-07,
2480
+ "loss": 0.3088,
2481
+ "step": 412
2482
+ },
2483
+ {
2484
+ "epoch": 0.94,
2485
+ "learning_rate": 3.1687744709644197e-07,
2486
+ "loss": 0.3003,
2487
+ "step": 413
2488
+ },
2489
+ {
2490
+ "epoch": 0.95,
2491
+ "learning_rate": 2.9108403880000247e-07,
2492
+ "loss": 0.359,
2493
+ "step": 414
2494
+ },
2495
+ {
2496
+ "epoch": 0.95,
2497
+ "learning_rate": 2.663777561767855e-07,
2498
+ "loss": 0.4534,
2499
+ "step": 415
2500
+ },
2501
+ {
2502
+ "epoch": 0.95,
2503
+ "learning_rate": 2.4275996200261e-07,
2504
+ "loss": 0.3747,
2505
+ "step": 416
2506
+ },
2507
+ {
2508
+ "epoch": 0.95,
2509
+ "learning_rate": 2.2023195901327731e-07,
2510
+ "loss": 0.2838,
2511
+ "step": 417
2512
+ },
2513
+ {
2514
+ "epoch": 0.96,
2515
+ "learning_rate": 1.9879498983270685e-07,
2516
+ "loss": 0.2783,
2517
+ "step": 418
2518
+ },
2519
+ {
2520
+ "epoch": 0.96,
2521
+ "learning_rate": 1.7845023690439944e-07,
2522
+ "loss": 0.4112,
2523
+ "step": 419
2524
+ },
2525
+ {
2526
+ "epoch": 0.96,
2527
+ "learning_rate": 1.591988224262053e-07,
2528
+ "loss": 0.3825,
2529
+ "step": 420
2530
+ },
2531
+ {
2532
+ "epoch": 0.96,
2533
+ "learning_rate": 1.4104180828844237e-07,
2534
+ "loss": 0.496,
2535
+ "step": 421
2536
+ },
2537
+ {
2538
+ "epoch": 0.96,
2539
+ "learning_rate": 1.239801960153053e-07,
2540
+ "loss": 0.4617,
2541
+ "step": 422
2542
+ },
2543
+ {
2544
+ "epoch": 0.97,
2545
+ "learning_rate": 1.0801492670962976e-07,
2546
+ "loss": 0.2298,
2547
+ "step": 423
2548
+ },
2549
+ {
2550
+ "epoch": 0.97,
2551
+ "learning_rate": 9.314688100098502e-08,
2552
+ "loss": 0.2499,
2553
+ "step": 424
2554
+ },
2555
+ {
2556
+ "epoch": 0.97,
2557
+ "learning_rate": 7.9376878997095e-08,
2558
+ "loss": 0.5606,
2559
+ "step": 425
2560
+ },
2561
+ {
2562
+ "epoch": 0.97,
2563
+ "learning_rate": 6.670568023859902e-08,
2564
+ "loss": 0.2629,
2565
+ "step": 426
2566
+ },
2567
+ {
2568
+ "epoch": 0.98,
2569
+ "learning_rate": 5.5133983657167376e-08,
2570
+ "loss": 0.4196,
2571
+ "step": 427
2572
+ },
2573
+ {
2574
+ "epoch": 0.98,
2575
+ "learning_rate": 4.4662427536936727e-08,
2576
+ "loss": 0.2699,
2577
+ "step": 428
2578
+ },
2579
+ {
2580
+ "epoch": 0.98,
2581
+ "learning_rate": 3.529158947930933e-08,
2582
+ "loss": 0.3988,
2583
+ "step": 429
2584
+ },
2585
+ {
2586
+ "epoch": 0.98,
2587
+ "learning_rate": 2.70219863710941e-08,
2588
+ "loss": 0.2276,
2589
+ "step": 430
2590
+ },
2591
+ {
2592
+ "epoch": 0.99,
2593
+ "learning_rate": 1.9854074355987186e-08,
2594
+ "loss": 0.243,
2595
+ "step": 431
2596
+ },
2597
+ {
2598
+ "epoch": 0.99,
2599
+ "learning_rate": 1.37882488094232e-08,
2600
+ "loss": 0.3782,
2601
+ "step": 432
2602
+ },
2603
+ {
2604
+ "epoch": 0.99,
2605
+ "learning_rate": 8.82484431675712e-09,
2606
+ "loss": 0.2823,
2607
+ "step": 433
2608
+ },
2609
+ {
2610
+ "epoch": 0.99,
2611
+ "learning_rate": 4.9641346548190415e-09,
2612
+ "loss": 0.3616,
2613
+ "step": 434
2614
+ },
2615
+ {
2616
+ "epoch": 0.99,
2617
+ "learning_rate": 2.206332776797382e-09,
2618
+ "loss": 0.359,
2619
+ "step": 435
2620
+ },
2621
+ {
2622
+ "epoch": 1.0,
2623
+ "learning_rate": 5.51590800510482e-10,
2624
+ "loss": 0.5555,
2625
+ "step": 436
2626
+ },
2627
+ {
2628
+ "epoch": 1.0,
2629
+ "learning_rate": 0.0,
2630
+ "loss": 0.5426,
2631
+ "step": 437
2632
+ },
2633
+ {
2634
+ "epoch": 1.0,
2635
+ "step": 437,
2636
+ "total_flos": 4.122039303326254e+20,
2637
+ "train_loss": 0.46482172025286633,
2638
+ "train_runtime": 2900.7464,
2639
+ "train_samples_per_second": 2.413,
2640
+ "train_steps_per_second": 0.151
2641
+ }
2642
+ ],
2643
+ "logging_steps": 1.0,
2644
+ "max_steps": 437,
2645
+ "num_input_tokens_seen": 0,
2646
+ "num_train_epochs": 1,
2647
+ "save_steps": 200,
2648
+ "total_flos": 4.122039303326254e+20,
2649
+ "train_batch_size": 1,
2650
+ "trial_name": null,
2651
+ "trial_params": null
2652
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6f6c328eb26b170ee515d1ffeb4ff05c94a6e9a196490f9624447c74c086ccea
3
+ size 6200
training_log.txt ADDED
The diff for this file is too large to render. See raw diff
 
vocab.json ADDED
The diff for this file is too large to render. See raw diff