Hugging Face's logo

batoulnn
/
camelbert_authorsclass5

Safetensors
bert
Model card Files
xet
Community
batoulnn commited on
Commit
05cf15d
·
verified ·
1 Parent(s): 0f785ad

Upload folder using huggingface_hub

Browse files
Files changed (29) hide show
  1. checkpoint-8000/config.json +72 -0
  2. checkpoint-8000/model.safetensors +3 -0
  3. checkpoint-8000/optimizer.pt +3 -0
  4. checkpoint-8000/rng_state.pth +3 -0
  5. checkpoint-8000/scheduler.pt +3 -0
  6. checkpoint-8000/special_tokens_map.json +7 -0
  7. checkpoint-8000/tokenizer.json +0 -0
  8. checkpoint-8000/tokenizer_config.json +59 -0
  9. checkpoint-8000/trainer_state.json +386 -0
  10. checkpoint-8000/training_args.bin +3 -0
  11. checkpoint-8000/vocab.txt +0 -0
  12. checkpoint-8236/config.json +72 -0
  13. checkpoint-8236/model.safetensors +3 -0
  14. checkpoint-8236/optimizer.pt +3 -0
  15. checkpoint-8236/rng_state.pth +3 -0
  16. checkpoint-8236/scheduler.pt +3 -0
  17. checkpoint-8236/special_tokens_map.json +7 -0
  18. checkpoint-8236/tokenizer.json +0 -0
  19. checkpoint-8236/tokenizer_config.json +59 -0
  20. checkpoint-8236/trainer_state.json +386 -0
  21. checkpoint-8236/training_args.bin +3 -0
  22. checkpoint-8236/vocab.txt +0 -0
  23. config.json +72 -0
  24. model.safetensors +3 -0
  25. special_tokens_map.json +7 -0
  26. tokenizer.json +0 -0
  27. tokenizer_config.json +59 -0
  28. training_args.bin +3 -0
  29. vocab.txt +0 -0
checkpoint-8000/config.json ADDED
@@ -0,0 +1,72 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "BertForSequenceClassification"
4
+ ],
5
+ "attention_probs_dropout_prob": 0.1,
6
+ "classifier_dropout": null,
7
+ "gradient_checkpointing": false,
8
+ "hidden_act": "gelu",
9
+ "hidden_dropout_prob": 0.1,
10
+ "hidden_size": 768,
11
+ "id2label": {
12
+ "0": "LABEL_0",
13
+ "1": "LABEL_1",
14
+ "2": "LABEL_2",
15
+ "3": "LABEL_3",
16
+ "4": "LABEL_4",
17
+ "5": "LABEL_5",
18
+ "6": "LABEL_6",
19
+ "7": "LABEL_7",
20
+ "8": "LABEL_8",
21
+ "9": "LABEL_9",
22
+ "10": "LABEL_10",
23
+ "11": "LABEL_11",
24
+ "12": "LABEL_12",
25
+ "13": "LABEL_13",
26
+ "14": "LABEL_14",
27
+ "15": "LABEL_15",
28
+ "16": "LABEL_16",
29
+ "17": "LABEL_17",
30
+ "18": "LABEL_18",
31
+ "19": "LABEL_19",
32
+ "20": "LABEL_20"
33
+ },
34
+ "initializer_range": 0.02,
35
+ "intermediate_size": 3072,
36
+ "label2id": {
37
+ "LABEL_0": 0,
38
+ "LABEL_1": 1,
39
+ "LABEL_10": 10,
40
+ "LABEL_11": 11,
41
+ "LABEL_12": 12,
42
+ "LABEL_13": 13,
43
+ "LABEL_14": 14,
44
+ "LABEL_15": 15,
45
+ "LABEL_16": 16,
46
+ "LABEL_17": 17,
47
+ "LABEL_18": 18,
48
+ "LABEL_19": 19,
49
+ "LABEL_2": 2,
50
+ "LABEL_20": 20,
51
+ "LABEL_3": 3,
52
+ "LABEL_4": 4,
53
+ "LABEL_5": 5,
54
+ "LABEL_6": 6,
55
+ "LABEL_7": 7,
56
+ "LABEL_8": 8,
57
+ "LABEL_9": 9
58
+ },
59
+ "layer_norm_eps": 1e-12,
60
+ "max_position_embeddings": 512,
61
+ "model_type": "bert",
62
+ "num_attention_heads": 12,
63
+ "num_hidden_layers": 12,
64
+ "pad_token_id": 0,
65
+ "position_embedding_type": "absolute",
66
+ "problem_type": "single_label_classification",
67
+ "torch_dtype": "float32",
68
+ "transformers_version": "4.52.4",
69
+ "type_vocab_size": 2,
70
+ "use_cache": true,
71
+ "vocab_size": 30000
72
+ }
checkpoint-8000/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:93715264f94dcba32c2989bf93e02de5067d34a30995562583de3ac2e4e1dac6
3
+ size 436413500
checkpoint-8000/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:80eaa4869e1bf0ac67c1afc145f7ded92c7df5432a7646b19c321d1b96875e56
3
+ size 872948026
checkpoint-8000/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8fb229905567953592c3d9a2e45b08c9eb3613c6e1ee987c51147594cb06d58e
3
+ size 14244
checkpoint-8000/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8c5fa12fc2329afab83e3fbf667e17ea9c5a33b147e7c2bac7df2a0b4a01b612
3
+ size 1064
checkpoint-8000/special_tokens_map.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": "[CLS]",
3
+ "mask_token": "[MASK]",
4
+ "pad_token": "[PAD]",
5
+ "sep_token": "[SEP]",
6
+ "unk_token": "[UNK]"
7
+ }
checkpoint-8000/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-8000/tokenizer_config.json ADDED
@@ -0,0 +1,59 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "[PAD]",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "1": {
12
+ "content": "[UNK]",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "[CLS]",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "3": {
28
+ "content": "[SEP]",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "4": {
36
+ "content": "[MASK]",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ }
43
+ },
44
+ "clean_up_tokenization_spaces": true,
45
+ "cls_token": "[CLS]",
46
+ "do_basic_tokenize": true,
47
+ "do_lower_case": false,
48
+ "extra_special_tokens": {},
49
+ "full_tokenizer_file": null,
50
+ "mask_token": "[MASK]",
51
+ "model_max_length": 1000000000000000019884624838656,
52
+ "never_split": null,
53
+ "pad_token": "[PAD]",
54
+ "sep_token": "[SEP]",
55
+ "strip_accents": null,
56
+ "tokenize_chinese_chars": true,
57
+ "tokenizer_class": "BertTokenizer",
58
+ "unk_token": "[UNK]"
59
+ }
checkpoint-8000/trainer_state.json ADDED
@@ -0,0 +1,386 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": 8000,
3
+ "best_metric": 0.8433649156181714,
4
+ "best_model_checkpoint": "./camelbert-ner-author/checkpoint-8000",
5
+ "epoch": 3.885381253035454,
6
+ "eval_steps": 500,
7
+ "global_step": 8000,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.24283632831471588,
14
+ "grad_norm": 16.968469619750977,
15
+ "learning_rate": 4.8446601941747576e-05,
16
+ "loss": 1.9068,
17
+ "step": 500
18
+ },
19
+ {
20
+ "epoch": 0.24283632831471588,
21
+ "eval_accuracy": 0.5689198941544383,
22
+ "eval_f1_macro": 0.48366034470276553,
23
+ "eval_f1_micro": 0.5689198941544383,
24
+ "eval_loss": 1.5013926029205322,
25
+ "eval_precision_macro": 0.5607402747942073,
26
+ "eval_precision_micro": 0.5689198941544383,
27
+ "eval_recall_macro": 0.511540694417687,
28
+ "eval_recall_micro": 0.5689198941544383,
29
+ "eval_runtime": 78.3045,
30
+ "eval_samples_per_second": 53.088,
31
+ "eval_steps_per_second": 3.32,
32
+ "step": 500
33
+ },
34
+ {
35
+ "epoch": 0.48567265662943176,
36
+ "grad_norm": 6.469072341918945,
37
+ "learning_rate": 7.989001438410175e-05,
38
+ "loss": 0.7961,
39
+ "step": 1000
40
+ },
41
+ {
42
+ "epoch": 0.48567265662943176,
43
+ "eval_accuracy": 0.7048352177050757,
44
+ "eval_f1_macro": 0.6186381736920357,
45
+ "eval_f1_micro": 0.7048352177050757,
46
+ "eval_loss": 1.0302138328552246,
47
+ "eval_precision_macro": 0.666546800638063,
48
+ "eval_precision_micro": 0.7048352177050757,
49
+ "eval_recall_macro": 0.6466013022371376,
50
+ "eval_recall_micro": 0.7048352177050757,
51
+ "eval_runtime": 78.796,
52
+ "eval_samples_per_second": 52.757,
53
+ "eval_steps_per_second": 3.3,
54
+ "step": 1000
55
+ },
56
+ {
57
+ "epoch": 0.7285089849441476,
58
+ "grad_norm": 23.518516540527344,
59
+ "learning_rate": 7.837406915300635e-05,
60
+ "loss": 0.5294,
61
+ "step": 1500
62
+ },
63
+ {
64
+ "epoch": 0.7285089849441476,
65
+ "eval_accuracy": 0.7512629299975944,
66
+ "eval_f1_macro": 0.6477243084028228,
67
+ "eval_f1_micro": 0.7512629299975943,
68
+ "eval_loss": 0.9704883098602295,
69
+ "eval_precision_macro": 0.6576557679031239,
70
+ "eval_precision_micro": 0.7512629299975944,
71
+ "eval_recall_macro": 0.6839084236939059,
72
+ "eval_recall_micro": 0.7512629299975944,
73
+ "eval_runtime": 77.7946,
74
+ "eval_samples_per_second": 53.436,
75
+ "eval_steps_per_second": 3.342,
76
+ "step": 1500
77
+ },
78
+ {
79
+ "epoch": 0.9713453132588635,
80
+ "grad_norm": 49.285499572753906,
81
+ "learning_rate": 7.514108265155405e-05,
82
+ "loss": 0.4245,
83
+ "step": 2000
84
+ },
85
+ {
86
+ "epoch": 0.9713453132588635,
87
+ "eval_accuracy": 0.7743565070964638,
88
+ "eval_f1_macro": 0.7073412442322541,
89
+ "eval_f1_micro": 0.7743565070964638,
90
+ "eval_loss": 0.906332790851593,
91
+ "eval_precision_macro": 0.7186305613392596,
92
+ "eval_precision_micro": 0.7743565070964638,
93
+ "eval_recall_macro": 0.7684842657553398,
94
+ "eval_recall_micro": 0.7743565070964638,
95
+ "eval_runtime": 78.1164,
96
+ "eval_samples_per_second": 53.215,
97
+ "eval_steps_per_second": 3.328,
98
+ "step": 2000
99
+ },
100
+ {
101
+ "epoch": 1.2141816415735793,
102
+ "grad_norm": 1.2833439111709595,
103
+ "learning_rate": 7.033571431701654e-05,
104
+ "loss": 0.2923,
105
+ "step": 2500
106
+ },
107
+ {
108
+ "epoch": 1.2141816415735793,
109
+ "eval_accuracy": 0.8121241279769065,
110
+ "eval_f1_macro": 0.7554194328960205,
111
+ "eval_f1_micro": 0.8121241279769065,
112
+ "eval_loss": 0.7854471206665039,
113
+ "eval_precision_macro": 0.7499571827552591,
114
+ "eval_precision_micro": 0.8121241279769065,
115
+ "eval_recall_macro": 0.7948880776979068,
116
+ "eval_recall_micro": 0.8121241279769065,
117
+ "eval_runtime": 77.9124,
118
+ "eval_samples_per_second": 53.355,
119
+ "eval_steps_per_second": 3.337,
120
+ "step": 2500
121
+ },
122
+ {
123
+ "epoch": 1.4570179698882952,
124
+ "grad_norm": 39.44307327270508,
125
+ "learning_rate": 6.417297954733794e-05,
126
+ "loss": 0.2701,
127
+ "step": 3000
128
+ },
129
+ {
130
+ "epoch": 1.4570179698882952,
131
+ "eval_accuracy": 0.7914361318258359,
132
+ "eval_f1_macro": 0.7228732789114548,
133
+ "eval_f1_micro": 0.7914361318258359,
134
+ "eval_loss": 0.9864006042480469,
135
+ "eval_precision_macro": 0.7804257497394893,
136
+ "eval_precision_micro": 0.7914361318258359,
137
+ "eval_recall_macro": 0.7314450714076557,
138
+ "eval_recall_micro": 0.7914361318258359,
139
+ "eval_runtime": 77.865,
140
+ "eval_samples_per_second": 53.387,
141
+ "eval_steps_per_second": 3.339,
142
+ "step": 3000
143
+ },
144
+ {
145
+ "epoch": 1.6998542982030111,
146
+ "grad_norm": 42.49247741699219,
147
+ "learning_rate": 5.692862887331573e-05,
148
+ "loss": 0.2588,
149
+ "step": 3500
150
+ },
151
+ {
152
+ "epoch": 1.6998542982030111,
153
+ "eval_accuracy": 0.8186191965359635,
154
+ "eval_f1_macro": 0.7462460843922789,
155
+ "eval_f1_micro": 0.8186191965359635,
156
+ "eval_loss": 0.9320507049560547,
157
+ "eval_precision_macro": 0.7783711434875539,
158
+ "eval_precision_micro": 0.8186191965359635,
159
+ "eval_recall_macro": 0.7666961778774583,
160
+ "eval_recall_micro": 0.8186191965359635,
161
+ "eval_runtime": 77.8637,
162
+ "eval_samples_per_second": 53.388,
163
+ "eval_steps_per_second": 3.339,
164
+ "step": 3500
165
+ },
166
+ {
167
+ "epoch": 1.942690626517727,
168
+ "grad_norm": 29.54608154296875,
169
+ "learning_rate": 4.892680954747708e-05,
170
+ "loss": 0.2141,
171
+ "step": 4000
172
+ },
173
+ {
174
+ "epoch": 1.942690626517727,
175
+ "eval_accuracy": 0.8595140726485446,
176
+ "eval_f1_macro": 0.7925708590441671,
177
+ "eval_f1_micro": 0.8595140726485446,
178
+ "eval_loss": 0.6913318634033203,
179
+ "eval_precision_macro": 0.8097818232552066,
180
+ "eval_precision_micro": 0.8595140726485446,
181
+ "eval_recall_macro": 0.7982109211940892,
182
+ "eval_recall_micro": 0.8595140726485446,
183
+ "eval_runtime": 77.2714,
184
+ "eval_samples_per_second": 53.797,
185
+ "eval_steps_per_second": 3.365,
186
+ "step": 4000
187
+ },
188
+ {
189
+ "epoch": 2.1855269548324427,
190
+ "grad_norm": 0.06814711540937424,
191
+ "learning_rate": 4.052556162978074e-05,
192
+ "loss": 0.1428,
193
+ "step": 4500
194
+ },
195
+ {
196
+ "epoch": 2.1855269548324427,
197
+ "eval_accuracy": 0.8607168631224441,
198
+ "eval_f1_macro": 0.8160796678747114,
199
+ "eval_f1_micro": 0.8607168631224441,
200
+ "eval_loss": 0.7702390551567078,
201
+ "eval_precision_macro": 0.8152228546042373,
202
+ "eval_precision_micro": 0.8607168631224441,
203
+ "eval_recall_macro": 0.8357463517900461,
204
+ "eval_recall_micro": 0.8607168631224441,
205
+ "eval_runtime": 77.2695,
206
+ "eval_samples_per_second": 53.799,
207
+ "eval_steps_per_second": 3.365,
208
+ "step": 4500
209
+ },
210
+ {
211
+ "epoch": 2.4283632831471587,
212
+ "grad_norm": 24.676101684570312,
213
+ "learning_rate": 3.2100797545350794e-05,
214
+ "loss": 0.0994,
215
+ "step": 5000
216
+ },
217
+ {
218
+ "epoch": 2.4283632831471587,
219
+ "eval_accuracy": 0.8585518402694251,
220
+ "eval_f1_macro": 0.7842088315067144,
221
+ "eval_f1_micro": 0.8585518402694251,
222
+ "eval_loss": 0.8307238221168518,
223
+ "eval_precision_macro": 0.8197735847865644,
224
+ "eval_precision_micro": 0.8585518402694251,
225
+ "eval_recall_macro": 0.7910153049671388,
226
+ "eval_recall_micro": 0.8585518402694251,
227
+ "eval_runtime": 77.4177,
228
+ "eval_samples_per_second": 53.696,
229
+ "eval_steps_per_second": 3.358,
230
+ "step": 5000
231
+ },
232
+ {
233
+ "epoch": 2.6711996114618746,
234
+ "grad_norm": 33.47557067871094,
235
+ "learning_rate": 2.402948194623674e-05,
236
+ "loss": 0.1036,
237
+ "step": 5500
238
+ },
239
+ {
240
+ "epoch": 2.6711996114618746,
241
+ "eval_accuracy": 0.8741881164301178,
242
+ "eval_f1_macro": 0.8137042597817897,
243
+ "eval_f1_micro": 0.8741881164301178,
244
+ "eval_loss": 0.728205680847168,
245
+ "eval_precision_macro": 0.8346050572186456,
246
+ "eval_precision_micro": 0.8741881164301178,
247
+ "eval_recall_macro": 0.8207342889207144,
248
+ "eval_recall_micro": 0.8741881164301178,
249
+ "eval_runtime": 77.4088,
250
+ "eval_samples_per_second": 53.702,
251
+ "eval_steps_per_second": 3.359,
252
+ "step": 5500
253
+ },
254
+ {
255
+ "epoch": 2.9140359397765905,
256
+ "grad_norm": 0.05054297670722008,
257
+ "learning_rate": 1.667276449145691e-05,
258
+ "loss": 0.0642,
259
+ "step": 6000
260
+ },
261
+ {
262
+ "epoch": 2.9140359397765905,
263
+ "eval_accuracy": 0.8785181621361559,
264
+ "eval_f1_macro": 0.8266076920016846,
265
+ "eval_f1_micro": 0.878518162136156,
266
+ "eval_loss": 0.7114289999008179,
267
+ "eval_precision_macro": 0.8183160319866987,
268
+ "eval_precision_micro": 0.8785181621361559,
269
+ "eval_recall_macro": 0.8441875574624527,
270
+ "eval_recall_micro": 0.8785181621361559,
271
+ "eval_runtime": 77.5025,
272
+ "eval_samples_per_second": 53.637,
273
+ "eval_steps_per_second": 3.355,
274
+ "step": 6000
275
+ },
276
+ {
277
+ "epoch": 3.1568722680913064,
278
+ "grad_norm": 18.89339828491211,
279
+ "learning_rate": 1.035982026624521e-05,
280
+ "loss": 0.0275,
281
+ "step": 6500
282
+ },
283
+ {
284
+ "epoch": 3.1568722680913064,
285
+ "eval_accuracy": 0.8821265335578542,
286
+ "eval_f1_macro": 0.8379156961581762,
287
+ "eval_f1_micro": 0.8821265335578542,
288
+ "eval_loss": 0.7058730721473694,
289
+ "eval_precision_macro": 0.8366396517694257,
290
+ "eval_precision_micro": 0.8821265335578542,
291
+ "eval_recall_macro": 0.8529065353345473,
292
+ "eval_recall_micro": 0.8821265335578542,
293
+ "eval_runtime": 77.7596,
294
+ "eval_samples_per_second": 53.46,
295
+ "eval_steps_per_second": 3.344,
296
+ "step": 6500
297
+ },
298
+ {
299
+ "epoch": 3.3997085964060223,
300
+ "grad_norm": 0.2935570180416107,
301
+ "learning_rate": 5.373120898224163e-06,
302
+ "loss": 0.0192,
303
+ "step": 7000
304
+ },
305
+ {
306
+ "epoch": 3.3997085964060223,
307
+ "eval_accuracy": 0.8883810440221314,
308
+ "eval_f1_macro": 0.8407185323568217,
309
+ "eval_f1_micro": 0.8883810440221314,
310
+ "eval_loss": 0.7033824920654297,
311
+ "eval_precision_macro": 0.837595519985543,
312
+ "eval_precision_micro": 0.8883810440221314,
313
+ "eval_recall_macro": 0.8579086346894231,
314
+ "eval_recall_micro": 0.8883810440221314,
315
+ "eval_runtime": 77.5194,
316
+ "eval_samples_per_second": 53.625,
317
+ "eval_steps_per_second": 3.354,
318
+ "step": 7000
319
+ },
320
+ {
321
+ "epoch": 3.642544924720738,
322
+ "grad_norm": 0.003531077178195119,
323
+ "learning_rate": 1.935795411934156e-06,
324
+ "loss": 0.0216,
325
+ "step": 7500
326
+ },
327
+ {
328
+ "epoch": 3.642544924720738,
329
+ "eval_accuracy": 0.8874188116430118,
330
+ "eval_f1_macro": 0.8409599390100843,
331
+ "eval_f1_micro": 0.8874188116430118,
332
+ "eval_loss": 0.6986571550369263,
333
+ "eval_precision_macro": 0.8396150251526077,
334
+ "eval_precision_micro": 0.8874188116430118,
335
+ "eval_recall_macro": 0.8522507453562462,
336
+ "eval_recall_micro": 0.8874188116430118,
337
+ "eval_runtime": 77.7662,
338
+ "eval_samples_per_second": 53.455,
339
+ "eval_steps_per_second": 3.343,
340
+ "step": 7500
341
+ },
342
+ {
343
+ "epoch": 3.885381253035454,
344
+ "grad_norm": 0.003803989617154002,
345
+ "learning_rate": 2.0164635815698608e-07,
346
+ "loss": 0.0195,
347
+ "step": 8000
348
+ },
349
+ {
350
+ "epoch": 3.885381253035454,
351
+ "eval_accuracy": 0.8895838344960308,
352
+ "eval_f1_macro": 0.8433649156181714,
353
+ "eval_f1_micro": 0.8895838344960308,
354
+ "eval_loss": 0.6867377758026123,
355
+ "eval_precision_macro": 0.8407896739230332,
356
+ "eval_precision_micro": 0.8895838344960308,
357
+ "eval_recall_macro": 0.8541561605591513,
358
+ "eval_recall_micro": 0.8895838344960308,
359
+ "eval_runtime": 77.3634,
360
+ "eval_samples_per_second": 53.733,
361
+ "eval_steps_per_second": 3.361,
362
+ "step": 8000
363
+ }
364
+ ],
365
+ "logging_steps": 500,
366
+ "max_steps": 8236,
367
+ "num_input_tokens_seen": 0,
368
+ "num_train_epochs": 4,
369
+ "save_steps": 500,
370
+ "stateful_callbacks": {
371
+ "TrainerControl": {
372
+ "args": {
373
+ "should_epoch_stop": false,
374
+ "should_evaluate": false,
375
+ "should_log": false,
376
+ "should_save": true,
377
+ "should_training_stop": false
378
+ },
379
+ "attributes": {}
380
+ }
381
+ },
382
+ "total_flos": 3.368159196159283e+16,
383
+ "train_batch_size": 16,
384
+ "trial_name": null,
385
+ "trial_params": null
386
+ }
checkpoint-8000/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:269b5642c17fd2e63c706c73c5291482b643926b6fa6819e7c30b66c5cc8b08f
3
+ size 5304
checkpoint-8000/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-8236/config.json ADDED
@@ -0,0 +1,72 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "BertForSequenceClassification"
4
+ ],
5
+ "attention_probs_dropout_prob": 0.1,
6
+ "classifier_dropout": null,
7
+ "gradient_checkpointing": false,
8
+ "hidden_act": "gelu",
9
+ "hidden_dropout_prob": 0.1,
10
+ "hidden_size": 768,
11
+ "id2label": {
12
+ "0": "LABEL_0",
13
+ "1": "LABEL_1",
14
+ "2": "LABEL_2",
15
+ "3": "LABEL_3",
16
+ "4": "LABEL_4",
17
+ "5": "LABEL_5",
18
+ "6": "LABEL_6",
19
+ "7": "LABEL_7",
20
+ "8": "LABEL_8",
21
+ "9": "LABEL_9",
22
+ "10": "LABEL_10",
23
+ "11": "LABEL_11",
24
+ "12": "LABEL_12",
25
+ "13": "LABEL_13",
26
+ "14": "LABEL_14",
27
+ "15": "LABEL_15",
28
+ "16": "LABEL_16",
29
+ "17": "LABEL_17",
30
+ "18": "LABEL_18",
31
+ "19": "LABEL_19",
32
+ "20": "LABEL_20"
33
+ },
34
+ "initializer_range": 0.02,
35
+ "intermediate_size": 3072,
36
+ "label2id": {
37
+ "LABEL_0": 0,
38
+ "LABEL_1": 1,
39
+ "LABEL_10": 10,
40
+ "LABEL_11": 11,
41
+ "LABEL_12": 12,
42
+ "LABEL_13": 13,
43
+ "LABEL_14": 14,
44
+ "LABEL_15": 15,
45
+ "LABEL_16": 16,
46
+ "LABEL_17": 17,
47
+ "LABEL_18": 18,
48
+ "LABEL_19": 19,
49
+ "LABEL_2": 2,
50
+ "LABEL_20": 20,
51
+ "LABEL_3": 3,
52
+ "LABEL_4": 4,
53
+ "LABEL_5": 5,
54
+ "LABEL_6": 6,
55
+ "LABEL_7": 7,
56
+ "LABEL_8": 8,
57
+ "LABEL_9": 9
58
+ },
59
+ "layer_norm_eps": 1e-12,
60
+ "max_position_embeddings": 512,
61
+ "model_type": "bert",
62
+ "num_attention_heads": 12,
63
+ "num_hidden_layers": 12,
64
+ "pad_token_id": 0,
65
+ "position_embedding_type": "absolute",
66
+ "problem_type": "single_label_classification",
67
+ "torch_dtype": "float32",
68
+ "transformers_version": "4.52.4",
69
+ "type_vocab_size": 2,
70
+ "use_cache": true,
71
+ "vocab_size": 30000
72
+ }
checkpoint-8236/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bbc8bc7bdd4a396d1183d316dd4cba094159c1170f59439b57f9c6f9abc4af8c
3
+ size 436413500
checkpoint-8236/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7582125261404eb16bfaed9dac2be0a86db37d126c2f6a1d938cb9bba26d146f
3
+ size 872948026
checkpoint-8236/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4409cf6cb60883d8a74601db506652413940b9e2c370f4ad76b7c8565e52bb5d
3
+ size 14244
checkpoint-8236/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5e2b1f25c371d63298550c6da386797b1ba9ea81a1fd6253e3b886b2bcc792d7
3
+ size 1064
checkpoint-8236/special_tokens_map.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": "[CLS]",
3
+ "mask_token": "[MASK]",
4
+ "pad_token": "[PAD]",
5
+ "sep_token": "[SEP]",
6
+ "unk_token": "[UNK]"
7
+ }
checkpoint-8236/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-8236/tokenizer_config.json ADDED
@@ -0,0 +1,59 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "[PAD]",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "1": {
12
+ "content": "[UNK]",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "[CLS]",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "3": {
28
+ "content": "[SEP]",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "4": {
36
+ "content": "[MASK]",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ }
43
+ },
44
+ "clean_up_tokenization_spaces": true,
45
+ "cls_token": "[CLS]",
46
+ "do_basic_tokenize": true,
47
+ "do_lower_case": false,
48
+ "extra_special_tokens": {},
49
+ "full_tokenizer_file": null,
50
+ "mask_token": "[MASK]",
51
+ "model_max_length": 1000000000000000019884624838656,
52
+ "never_split": null,
53
+ "pad_token": "[PAD]",
54
+ "sep_token": "[SEP]",
55
+ "strip_accents": null,
56
+ "tokenize_chinese_chars": true,
57
+ "tokenizer_class": "BertTokenizer",
58
+ "unk_token": "[UNK]"
59
+ }
checkpoint-8236/trainer_state.json ADDED
@@ -0,0 +1,386 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": 8000,
3
+ "best_metric": 0.8433649156181714,
4
+ "best_model_checkpoint": "./camelbert-ner-author/checkpoint-8000",
5
+ "epoch": 4.0,
6
+ "eval_steps": 500,
7
+ "global_step": 8236,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.24283632831471588,
14
+ "grad_norm": 16.968469619750977,
15
+ "learning_rate": 4.8446601941747576e-05,
16
+ "loss": 1.9068,
17
+ "step": 500
18
+ },
19
+ {
20
+ "epoch": 0.24283632831471588,
21
+ "eval_accuracy": 0.5689198941544383,
22
+ "eval_f1_macro": 0.48366034470276553,
23
+ "eval_f1_micro": 0.5689198941544383,
24
+ "eval_loss": 1.5013926029205322,
25
+ "eval_precision_macro": 0.5607402747942073,
26
+ "eval_precision_micro": 0.5689198941544383,
27
+ "eval_recall_macro": 0.511540694417687,
28
+ "eval_recall_micro": 0.5689198941544383,
29
+ "eval_runtime": 78.3045,
30
+ "eval_samples_per_second": 53.088,
31
+ "eval_steps_per_second": 3.32,
32
+ "step": 500
33
+ },
34
+ {
35
+ "epoch": 0.48567265662943176,
36
+ "grad_norm": 6.469072341918945,
37
+ "learning_rate": 7.989001438410175e-05,
38
+ "loss": 0.7961,
39
+ "step": 1000
40
+ },
41
+ {
42
+ "epoch": 0.48567265662943176,
43
+ "eval_accuracy": 0.7048352177050757,
44
+ "eval_f1_macro": 0.6186381736920357,
45
+ "eval_f1_micro": 0.7048352177050757,
46
+ "eval_loss": 1.0302138328552246,
47
+ "eval_precision_macro": 0.666546800638063,
48
+ "eval_precision_micro": 0.7048352177050757,
49
+ "eval_recall_macro": 0.6466013022371376,
50
+ "eval_recall_micro": 0.7048352177050757,
51
+ "eval_runtime": 78.796,
52
+ "eval_samples_per_second": 52.757,
53
+ "eval_steps_per_second": 3.3,
54
+ "step": 1000
55
+ },
56
+ {
57
+ "epoch": 0.7285089849441476,
58
+ "grad_norm": 23.518516540527344,
59
+ "learning_rate": 7.837406915300635e-05,
60
+ "loss": 0.5294,
61
+ "step": 1500
62
+ },
63
+ {
64
+ "epoch": 0.7285089849441476,
65
+ "eval_accuracy": 0.7512629299975944,
66
+ "eval_f1_macro": 0.6477243084028228,
67
+ "eval_f1_micro": 0.7512629299975943,
68
+ "eval_loss": 0.9704883098602295,
69
+ "eval_precision_macro": 0.6576557679031239,
70
+ "eval_precision_micro": 0.7512629299975944,
71
+ "eval_recall_macro": 0.6839084236939059,
72
+ "eval_recall_micro": 0.7512629299975944,
73
+ "eval_runtime": 77.7946,
74
+ "eval_samples_per_second": 53.436,
75
+ "eval_steps_per_second": 3.342,
76
+ "step": 1500
77
+ },
78
+ {
79
+ "epoch": 0.9713453132588635,
80
+ "grad_norm": 49.285499572753906,
81
+ "learning_rate": 7.514108265155405e-05,
82
+ "loss": 0.4245,
83
+ "step": 2000
84
+ },
85
+ {
86
+ "epoch": 0.9713453132588635,
87
+ "eval_accuracy": 0.7743565070964638,
88
+ "eval_f1_macro": 0.7073412442322541,
89
+ "eval_f1_micro": 0.7743565070964638,
90
+ "eval_loss": 0.906332790851593,
91
+ "eval_precision_macro": 0.7186305613392596,
92
+ "eval_precision_micro": 0.7743565070964638,
93
+ "eval_recall_macro": 0.7684842657553398,
94
+ "eval_recall_micro": 0.7743565070964638,
95
+ "eval_runtime": 78.1164,
96
+ "eval_samples_per_second": 53.215,
97
+ "eval_steps_per_second": 3.328,
98
+ "step": 2000
99
+ },
100
+ {
101
+ "epoch": 1.2141816415735793,
102
+ "grad_norm": 1.2833439111709595,
103
+ "learning_rate": 7.033571431701654e-05,
104
+ "loss": 0.2923,
105
+ "step": 2500
106
+ },
107
+ {
108
+ "epoch": 1.2141816415735793,
109
+ "eval_accuracy": 0.8121241279769065,
110
+ "eval_f1_macro": 0.7554194328960205,
111
+ "eval_f1_micro": 0.8121241279769065,
112
+ "eval_loss": 0.7854471206665039,
113
+ "eval_precision_macro": 0.7499571827552591,
114
+ "eval_precision_micro": 0.8121241279769065,
115
+ "eval_recall_macro": 0.7948880776979068,
116
+ "eval_recall_micro": 0.8121241279769065,
117
+ "eval_runtime": 77.9124,
118
+ "eval_samples_per_second": 53.355,
119
+ "eval_steps_per_second": 3.337,
120
+ "step": 2500
121
+ },
122
+ {
123
+ "epoch": 1.4570179698882952,
124
+ "grad_norm": 39.44307327270508,
125
+ "learning_rate": 6.417297954733794e-05,
126
+ "loss": 0.2701,
127
+ "step": 3000
128
+ },
129
+ {
130
+ "epoch": 1.4570179698882952,
131
+ "eval_accuracy": 0.7914361318258359,
132
+ "eval_f1_macro": 0.7228732789114548,
133
+ "eval_f1_micro": 0.7914361318258359,
134
+ "eval_loss": 0.9864006042480469,
135
+ "eval_precision_macro": 0.7804257497394893,
136
+ "eval_precision_micro": 0.7914361318258359,
137
+ "eval_recall_macro": 0.7314450714076557,
138
+ "eval_recall_micro": 0.7914361318258359,
139
+ "eval_runtime": 77.865,
140
+ "eval_samples_per_second": 53.387,
141
+ "eval_steps_per_second": 3.339,
142
+ "step": 3000
143
+ },
144
+ {
145
+ "epoch": 1.6998542982030111,
146
+ "grad_norm": 42.49247741699219,
147
+ "learning_rate": 5.692862887331573e-05,
148
+ "loss": 0.2588,
149
+ "step": 3500
150
+ },
151
+ {
152
+ "epoch": 1.6998542982030111,
153
+ "eval_accuracy": 0.8186191965359635,
154
+ "eval_f1_macro": 0.7462460843922789,
155
+ "eval_f1_micro": 0.8186191965359635,
156
+ "eval_loss": 0.9320507049560547,
157
+ "eval_precision_macro": 0.7783711434875539,
158
+ "eval_precision_micro": 0.8186191965359635,
159
+ "eval_recall_macro": 0.7666961778774583,
160
+ "eval_recall_micro": 0.8186191965359635,
161
+ "eval_runtime": 77.8637,
162
+ "eval_samples_per_second": 53.388,
163
+ "eval_steps_per_second": 3.339,
164
+ "step": 3500
165
+ },
166
+ {
167
+ "epoch": 1.942690626517727,
168
+ "grad_norm": 29.54608154296875,
169
+ "learning_rate": 4.892680954747708e-05,
170
+ "loss": 0.2141,
171
+ "step": 4000
172
+ },
173
+ {
174
+ "epoch": 1.942690626517727,
175
+ "eval_accuracy": 0.8595140726485446,
176
+ "eval_f1_macro": 0.7925708590441671,
177
+ "eval_f1_micro": 0.8595140726485446,
178
+ "eval_loss": 0.6913318634033203,
179
+ "eval_precision_macro": 0.8097818232552066,
180
+ "eval_precision_micro": 0.8595140726485446,
181
+ "eval_recall_macro": 0.7982109211940892,
182
+ "eval_recall_micro": 0.8595140726485446,
183
+ "eval_runtime": 77.2714,
184
+ "eval_samples_per_second": 53.797,
185
+ "eval_steps_per_second": 3.365,
186
+ "step": 4000
187
+ },
188
+ {
189
+ "epoch": 2.1855269548324427,
190
+ "grad_norm": 0.06814711540937424,
191
+ "learning_rate": 4.052556162978074e-05,
192
+ "loss": 0.1428,
193
+ "step": 4500
194
+ },
195
+ {
196
+ "epoch": 2.1855269548324427,
197
+ "eval_accuracy": 0.8607168631224441,
198
+ "eval_f1_macro": 0.8160796678747114,
199
+ "eval_f1_micro": 0.8607168631224441,
200
+ "eval_loss": 0.7702390551567078,
201
+ "eval_precision_macro": 0.8152228546042373,
202
+ "eval_precision_micro": 0.8607168631224441,
203
+ "eval_recall_macro": 0.8357463517900461,
204
+ "eval_recall_micro": 0.8607168631224441,
205
+ "eval_runtime": 77.2695,
206
+ "eval_samples_per_second": 53.799,
207
+ "eval_steps_per_second": 3.365,
208
+ "step": 4500
209
+ },
210
+ {
211
+ "epoch": 2.4283632831471587,
212
+ "grad_norm": 24.676101684570312,
213
+ "learning_rate": 3.2100797545350794e-05,
214
+ "loss": 0.0994,
215
+ "step": 5000
216
+ },
217
+ {
218
+ "epoch": 2.4283632831471587,
219
+ "eval_accuracy": 0.8585518402694251,
220
+ "eval_f1_macro": 0.7842088315067144,
221
+ "eval_f1_micro": 0.8585518402694251,
222
+ "eval_loss": 0.8307238221168518,
223
+ "eval_precision_macro": 0.8197735847865644,
224
+ "eval_precision_micro": 0.8585518402694251,
225
+ "eval_recall_macro": 0.7910153049671388,
226
+ "eval_recall_micro": 0.8585518402694251,
227
+ "eval_runtime": 77.4177,
228
+ "eval_samples_per_second": 53.696,
229
+ "eval_steps_per_second": 3.358,
230
+ "step": 5000
231
+ },
232
+ {
233
+ "epoch": 2.6711996114618746,
234
+ "grad_norm": 33.47557067871094,
235
+ "learning_rate": 2.402948194623674e-05,
236
+ "loss": 0.1036,
237
+ "step": 5500
238
+ },
239
+ {
240
+ "epoch": 2.6711996114618746,
241
+ "eval_accuracy": 0.8741881164301178,
242
+ "eval_f1_macro": 0.8137042597817897,
243
+ "eval_f1_micro": 0.8741881164301178,
244
+ "eval_loss": 0.728205680847168,
245
+ "eval_precision_macro": 0.8346050572186456,
246
+ "eval_precision_micro": 0.8741881164301178,
247
+ "eval_recall_macro": 0.8207342889207144,
248
+ "eval_recall_micro": 0.8741881164301178,
249
+ "eval_runtime": 77.4088,
250
+ "eval_samples_per_second": 53.702,
251
+ "eval_steps_per_second": 3.359,
252
+ "step": 5500
253
+ },
254
+ {
255
+ "epoch": 2.9140359397765905,
256
+ "grad_norm": 0.05054297670722008,
257
+ "learning_rate": 1.667276449145691e-05,
258
+ "loss": 0.0642,
259
+ "step": 6000
260
+ },
261
+ {
262
+ "epoch": 2.9140359397765905,
263
+ "eval_accuracy": 0.8785181621361559,
264
+ "eval_f1_macro": 0.8266076920016846,
265
+ "eval_f1_micro": 0.878518162136156,
266
+ "eval_loss": 0.7114289999008179,
267
+ "eval_precision_macro": 0.8183160319866987,
268
+ "eval_precision_micro": 0.8785181621361559,
269
+ "eval_recall_macro": 0.8441875574624527,
270
+ "eval_recall_micro": 0.8785181621361559,
271
+ "eval_runtime": 77.5025,
272
+ "eval_samples_per_second": 53.637,
273
+ "eval_steps_per_second": 3.355,
274
+ "step": 6000
275
+ },
276
+ {
277
+ "epoch": 3.1568722680913064,
278
+ "grad_norm": 18.89339828491211,
279
+ "learning_rate": 1.035982026624521e-05,
280
+ "loss": 0.0275,
281
+ "step": 6500
282
+ },
283
+ {
284
+ "epoch": 3.1568722680913064,
285
+ "eval_accuracy": 0.8821265335578542,
286
+ "eval_f1_macro": 0.8379156961581762,
287
+ "eval_f1_micro": 0.8821265335578542,
288
+ "eval_loss": 0.7058730721473694,
289
+ "eval_precision_macro": 0.8366396517694257,
290
+ "eval_precision_micro": 0.8821265335578542,
291
+ "eval_recall_macro": 0.8529065353345473,
292
+ "eval_recall_micro": 0.8821265335578542,
293
+ "eval_runtime": 77.7596,
294
+ "eval_samples_per_second": 53.46,
295
+ "eval_steps_per_second": 3.344,
296
+ "step": 6500
297
+ },
298
+ {
299
+ "epoch": 3.3997085964060223,
300
+ "grad_norm": 0.2935570180416107,
301
+ "learning_rate": 5.373120898224163e-06,
302
+ "loss": 0.0192,
303
+ "step": 7000
304
+ },
305
+ {
306
+ "epoch": 3.3997085964060223,
307
+ "eval_accuracy": 0.8883810440221314,
308
+ "eval_f1_macro": 0.8407185323568217,
309
+ "eval_f1_micro": 0.8883810440221314,
310
+ "eval_loss": 0.7033824920654297,
311
+ "eval_precision_macro": 0.837595519985543,
312
+ "eval_precision_micro": 0.8883810440221314,
313
+ "eval_recall_macro": 0.8579086346894231,
314
+ "eval_recall_micro": 0.8883810440221314,
315
+ "eval_runtime": 77.5194,
316
+ "eval_samples_per_second": 53.625,
317
+ "eval_steps_per_second": 3.354,
318
+ "step": 7000
319
+ },
320
+ {
321
+ "epoch": 3.642544924720738,
322
+ "grad_norm": 0.003531077178195119,
323
+ "learning_rate": 1.935795411934156e-06,
324
+ "loss": 0.0216,
325
+ "step": 7500
326
+ },
327
+ {
328
+ "epoch": 3.642544924720738,
329
+ "eval_accuracy": 0.8874188116430118,
330
+ "eval_f1_macro": 0.8409599390100843,
331
+ "eval_f1_micro": 0.8874188116430118,
332
+ "eval_loss": 0.6986571550369263,
333
+ "eval_precision_macro": 0.8396150251526077,
334
+ "eval_precision_micro": 0.8874188116430118,
335
+ "eval_recall_macro": 0.8522507453562462,
336
+ "eval_recall_micro": 0.8874188116430118,
337
+ "eval_runtime": 77.7662,
338
+ "eval_samples_per_second": 53.455,
339
+ "eval_steps_per_second": 3.343,
340
+ "step": 7500
341
+ },
342
+ {
343
+ "epoch": 3.885381253035454,
344
+ "grad_norm": 0.003803989617154002,
345
+ "learning_rate": 2.0164635815698608e-07,
346
+ "loss": 0.0195,
347
+ "step": 8000
348
+ },
349
+ {
350
+ "epoch": 3.885381253035454,
351
+ "eval_accuracy": 0.8895838344960308,
352
+ "eval_f1_macro": 0.8433649156181714,
353
+ "eval_f1_micro": 0.8895838344960308,
354
+ "eval_loss": 0.6867377758026123,
355
+ "eval_precision_macro": 0.8407896739230332,
356
+ "eval_precision_micro": 0.8895838344960308,
357
+ "eval_recall_macro": 0.8541561605591513,
358
+ "eval_recall_micro": 0.8895838344960308,
359
+ "eval_runtime": 77.3634,
360
+ "eval_samples_per_second": 53.733,
361
+ "eval_steps_per_second": 3.361,
362
+ "step": 8000
363
+ }
364
+ ],
365
+ "logging_steps": 500,
366
+ "max_steps": 8236,
367
+ "num_input_tokens_seen": 0,
368
+ "num_train_epochs": 4,
369
+ "save_steps": 500,
370
+ "stateful_callbacks": {
371
+ "TrainerControl": {
372
+ "args": {
373
+ "should_epoch_stop": false,
374
+ "should_evaluate": false,
375
+ "should_log": false,
376
+ "should_save": true,
377
+ "should_training_stop": true
378
+ },
379
+ "attributes": {}
380
+ }
381
+ },
382
+ "total_flos": 3.467447932454093e+16,
383
+ "train_batch_size": 16,
384
+ "trial_name": null,
385
+ "trial_params": null
386
+ }
checkpoint-8236/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:269b5642c17fd2e63c706c73c5291482b643926b6fa6819e7c30b66c5cc8b08f
3
+ size 5304
checkpoint-8236/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
config.json ADDED
@@ -0,0 +1,72 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "BertForSequenceClassification"
4
+ ],
5
+ "attention_probs_dropout_prob": 0.1,
6
+ "classifier_dropout": null,
7
+ "gradient_checkpointing": false,
8
+ "hidden_act": "gelu",
9
+ "hidden_dropout_prob": 0.1,
10
+ "hidden_size": 768,
11
+ "id2label": {
12
+ "0": "LABEL_0",
13
+ "1": "LABEL_1",
14
+ "2": "LABEL_2",
15
+ "3": "LABEL_3",
16
+ "4": "LABEL_4",
17
+ "5": "LABEL_5",
18
+ "6": "LABEL_6",
19
+ "7": "LABEL_7",
20
+ "8": "LABEL_8",
21
+ "9": "LABEL_9",
22
+ "10": "LABEL_10",
23
+ "11": "LABEL_11",
24
+ "12": "LABEL_12",
25
+ "13": "LABEL_13",
26
+ "14": "LABEL_14",
27
+ "15": "LABEL_15",
28
+ "16": "LABEL_16",
29
+ "17": "LABEL_17",
30
+ "18": "LABEL_18",
31
+ "19": "LABEL_19",
32
+ "20": "LABEL_20"
33
+ },
34
+ "initializer_range": 0.02,
35
+ "intermediate_size": 3072,
36
+ "label2id": {
37
+ "LABEL_0": 0,
38
+ "LABEL_1": 1,
39
+ "LABEL_10": 10,
40
+ "LABEL_11": 11,
41
+ "LABEL_12": 12,
42
+ "LABEL_13": 13,
43
+ "LABEL_14": 14,
44
+ "LABEL_15": 15,
45
+ "LABEL_16": 16,
46
+ "LABEL_17": 17,
47
+ "LABEL_18": 18,
48
+ "LABEL_19": 19,
49
+ "LABEL_2": 2,
50
+ "LABEL_20": 20,
51
+ "LABEL_3": 3,
52
+ "LABEL_4": 4,
53
+ "LABEL_5": 5,
54
+ "LABEL_6": 6,
55
+ "LABEL_7": 7,
56
+ "LABEL_8": 8,
57
+ "LABEL_9": 9
58
+ },
59
+ "layer_norm_eps": 1e-12,
60
+ "max_position_embeddings": 512,
61
+ "model_type": "bert",
62
+ "num_attention_heads": 12,
63
+ "num_hidden_layers": 12,
64
+ "pad_token_id": 0,
65
+ "position_embedding_type": "absolute",
66
+ "problem_type": "single_label_classification",
67
+ "torch_dtype": "float32",
68
+ "transformers_version": "4.52.4",
69
+ "type_vocab_size": 2,
70
+ "use_cache": true,
71
+ "vocab_size": 30000
72
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:93715264f94dcba32c2989bf93e02de5067d34a30995562583de3ac2e4e1dac6
3
+ size 436413500
special_tokens_map.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": "[CLS]",
3
+ "mask_token": "[MASK]",
4
+ "pad_token": "[PAD]",
5
+ "sep_token": "[SEP]",
6
+ "unk_token": "[UNK]"
7
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,59 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "[PAD]",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "1": {
12
+ "content": "[UNK]",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "[CLS]",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "3": {
28
+ "content": "[SEP]",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "4": {
36
+ "content": "[MASK]",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ }
43
+ },
44
+ "clean_up_tokenization_spaces": true,
45
+ "cls_token": "[CLS]",
46
+ "do_basic_tokenize": true,
47
+ "do_lower_case": false,
48
+ "extra_special_tokens": {},
49
+ "full_tokenizer_file": null,
50
+ "mask_token": "[MASK]",
51
+ "model_max_length": 1000000000000000019884624838656,
52
+ "never_split": null,
53
+ "pad_token": "[PAD]",
54
+ "sep_token": "[SEP]",
55
+ "strip_accents": null,
56
+ "tokenize_chinese_chars": true,
57
+ "tokenizer_class": "BertTokenizer",
58
+ "unk_token": "[UNK]"
59
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:269b5642c17fd2e63c706c73c5291482b643926b6fa6819e7c30b66c5cc8b08f
3
+ size 5304
vocab.txt ADDED
The diff for this file is too large to render. See raw diff