ssunbear commited on
Commit
29d5925
·
verified ·
1 Parent(s): 5d1f987

Add model files

Browse files
config.json ADDED
@@ -0,0 +1,44 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "klue/bert-base",
3
+ "architectures": [
4
+ "BertForSequenceClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "classifier_dropout": null,
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
+ },
20
+ "initializer_range": 0.02,
21
+ "intermediate_size": 3072,
22
+ "label2id": {
23
+ "LABEL_0": 0,
24
+ "LABEL_1": 1,
25
+ "LABEL_2": 2,
26
+ "LABEL_3": 3,
27
+ "LABEL_4": 4,
28
+ "LABEL_5": 5,
29
+ "LABEL_6": 6
30
+ },
31
+ "layer_norm_eps": 1e-12,
32
+ "max_position_embeddings": 512,
33
+ "model_type": "bert",
34
+ "num_attention_heads": 12,
35
+ "num_hidden_layers": 12,
36
+ "pad_token_id": 0,
37
+ "position_embedding_type": "absolute",
38
+ "problem_type": "single_label_classification",
39
+ "torch_dtype": "float32",
40
+ "transformers_version": "4.46.1",
41
+ "type_vocab_size": 2,
42
+ "use_cache": true,
43
+ "vocab_size": 32000
44
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:76d9eac5c397c3124fcfb0c8787c9d6a0b1da32ea2551874e85ed881ca8e9a6c
3
+ size 442514444
optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:28e8548b78609e4b8d4a3bf4fa7621d13d093053738de1b90eb41b96122c5400
3
+ size 885149946
rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8ea28fd7e215cb4f736cb1ffec92783404c43faf4aa0ea121c9538c258d33c6a
3
+ size 14244
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:442b5021d264f77f9a2015ab8a6d59428787da3e1fb89b488f006a1caae3c082
3
+ size 1064
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
trainer_state.json ADDED
@@ -0,0 +1,412 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.7058091506789402,
3
+ "best_model_checkpoint": "/data/ephemeral/home/level2-nlp-datacentric-nlp-15/models/train_aug_filtered_data_8315.csv_20241107_223341/checkpoint-400",
4
+ "epoch": 2.0,
5
+ "eval_steps": 100,
6
+ "global_step": 492,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.04065040650406504,
13
+ "grad_norm": 5.844911098480225,
14
+ "learning_rate": 1.959349593495935e-05,
15
+ "loss": 1.9107,
16
+ "step": 10
17
+ },
18
+ {
19
+ "epoch": 0.08130081300813008,
20
+ "grad_norm": 4.806931495666504,
21
+ "learning_rate": 1.91869918699187e-05,
22
+ "loss": 1.793,
23
+ "step": 20
24
+ },
25
+ {
26
+ "epoch": 0.12195121951219512,
27
+ "grad_norm": 5.768178939819336,
28
+ "learning_rate": 1.878048780487805e-05,
29
+ "loss": 1.6268,
30
+ "step": 30
31
+ },
32
+ {
33
+ "epoch": 0.16260162601626016,
34
+ "grad_norm": 6.002701759338379,
35
+ "learning_rate": 1.83739837398374e-05,
36
+ "loss": 1.5186,
37
+ "step": 40
38
+ },
39
+ {
40
+ "epoch": 0.2032520325203252,
41
+ "grad_norm": 5.8298115730285645,
42
+ "learning_rate": 1.796747967479675e-05,
43
+ "loss": 1.3802,
44
+ "step": 50
45
+ },
46
+ {
47
+ "epoch": 0.24390243902439024,
48
+ "grad_norm": 5.422698020935059,
49
+ "learning_rate": 1.75609756097561e-05,
50
+ "loss": 1.3176,
51
+ "step": 60
52
+ },
53
+ {
54
+ "epoch": 0.2845528455284553,
55
+ "grad_norm": 7.105832099914551,
56
+ "learning_rate": 1.7154471544715447e-05,
57
+ "loss": 1.1553,
58
+ "step": 70
59
+ },
60
+ {
61
+ "epoch": 0.3252032520325203,
62
+ "grad_norm": 6.3010101318359375,
63
+ "learning_rate": 1.6747967479674798e-05,
64
+ "loss": 1.209,
65
+ "step": 80
66
+ },
67
+ {
68
+ "epoch": 0.36585365853658536,
69
+ "grad_norm": 5.355374813079834,
70
+ "learning_rate": 1.6341463414634145e-05,
71
+ "loss": 1.1115,
72
+ "step": 90
73
+ },
74
+ {
75
+ "epoch": 0.4065040650406504,
76
+ "grad_norm": 8.652898788452148,
77
+ "learning_rate": 1.5934959349593496e-05,
78
+ "loss": 1.2678,
79
+ "step": 100
80
+ },
81
+ {
82
+ "epoch": 0.4065040650406504,
83
+ "eval_f1": 0.6317862490710497,
84
+ "eval_loss": 1.1097809076309204,
85
+ "eval_runtime": 30.8532,
86
+ "eval_samples_per_second": 109.097,
87
+ "eval_steps_per_second": 3.436,
88
+ "step": 100
89
+ },
90
+ {
91
+ "epoch": 0.44715447154471544,
92
+ "grad_norm": 5.56029748916626,
93
+ "learning_rate": 1.5528455284552847e-05,
94
+ "loss": 1.2245,
95
+ "step": 110
96
+ },
97
+ {
98
+ "epoch": 0.4878048780487805,
99
+ "grad_norm": 5.553459644317627,
100
+ "learning_rate": 1.5121951219512196e-05,
101
+ "loss": 1.0607,
102
+ "step": 120
103
+ },
104
+ {
105
+ "epoch": 0.5284552845528455,
106
+ "grad_norm": 6.536402702331543,
107
+ "learning_rate": 1.4715447154471545e-05,
108
+ "loss": 1.1759,
109
+ "step": 130
110
+ },
111
+ {
112
+ "epoch": 0.5691056910569106,
113
+ "grad_norm": 5.6078200340271,
114
+ "learning_rate": 1.4308943089430896e-05,
115
+ "loss": 1.0878,
116
+ "step": 140
117
+ },
118
+ {
119
+ "epoch": 0.6097560975609756,
120
+ "grad_norm": 7.2565789222717285,
121
+ "learning_rate": 1.3902439024390244e-05,
122
+ "loss": 1.1789,
123
+ "step": 150
124
+ },
125
+ {
126
+ "epoch": 0.6504065040650406,
127
+ "grad_norm": 6.567378520965576,
128
+ "learning_rate": 1.3495934959349594e-05,
129
+ "loss": 1.1621,
130
+ "step": 160
131
+ },
132
+ {
133
+ "epoch": 0.6910569105691057,
134
+ "grad_norm": 6.680911064147949,
135
+ "learning_rate": 1.3089430894308943e-05,
136
+ "loss": 1.0317,
137
+ "step": 170
138
+ },
139
+ {
140
+ "epoch": 0.7317073170731707,
141
+ "grad_norm": 5.503971576690674,
142
+ "learning_rate": 1.2682926829268294e-05,
143
+ "loss": 1.2348,
144
+ "step": 180
145
+ },
146
+ {
147
+ "epoch": 0.7723577235772358,
148
+ "grad_norm": 5.242718696594238,
149
+ "learning_rate": 1.2276422764227642e-05,
150
+ "loss": 1.0482,
151
+ "step": 190
152
+ },
153
+ {
154
+ "epoch": 0.8130081300813008,
155
+ "grad_norm": 5.709949016571045,
156
+ "learning_rate": 1.1869918699186992e-05,
157
+ "loss": 1.0018,
158
+ "step": 200
159
+ },
160
+ {
161
+ "epoch": 0.8130081300813008,
162
+ "eval_f1": 0.6788360267939961,
163
+ "eval_loss": 0.9953919649124146,
164
+ "eval_runtime": 30.8775,
165
+ "eval_samples_per_second": 109.011,
166
+ "eval_steps_per_second": 3.433,
167
+ "step": 200
168
+ },
169
+ {
170
+ "epoch": 0.8536585365853658,
171
+ "grad_norm": 6.952666759490967,
172
+ "learning_rate": 1.1463414634146342e-05,
173
+ "loss": 1.0277,
174
+ "step": 210
175
+ },
176
+ {
177
+ "epoch": 0.8943089430894309,
178
+ "grad_norm": 8.080061912536621,
179
+ "learning_rate": 1.1056910569105692e-05,
180
+ "loss": 0.9702,
181
+ "step": 220
182
+ },
183
+ {
184
+ "epoch": 0.9349593495934959,
185
+ "grad_norm": 6.3944549560546875,
186
+ "learning_rate": 1.065040650406504e-05,
187
+ "loss": 1.0117,
188
+ "step": 230
189
+ },
190
+ {
191
+ "epoch": 0.975609756097561,
192
+ "grad_norm": 6.3046488761901855,
193
+ "learning_rate": 1.024390243902439e-05,
194
+ "loss": 1.1426,
195
+ "step": 240
196
+ },
197
+ {
198
+ "epoch": 1.016260162601626,
199
+ "grad_norm": 5.248263835906982,
200
+ "learning_rate": 9.837398373983741e-06,
201
+ "loss": 0.9627,
202
+ "step": 250
203
+ },
204
+ {
205
+ "epoch": 1.056910569105691,
206
+ "grad_norm": 7.71372127532959,
207
+ "learning_rate": 9.43089430894309e-06,
208
+ "loss": 0.9348,
209
+ "step": 260
210
+ },
211
+ {
212
+ "epoch": 1.0975609756097562,
213
+ "grad_norm": 9.51766586303711,
214
+ "learning_rate": 9.02439024390244e-06,
215
+ "loss": 0.9111,
216
+ "step": 270
217
+ },
218
+ {
219
+ "epoch": 1.1382113821138211,
220
+ "grad_norm": 5.655633926391602,
221
+ "learning_rate": 8.617886178861789e-06,
222
+ "loss": 0.8609,
223
+ "step": 280
224
+ },
225
+ {
226
+ "epoch": 1.1788617886178863,
227
+ "grad_norm": 7.609259128570557,
228
+ "learning_rate": 8.21138211382114e-06,
229
+ "loss": 0.8905,
230
+ "step": 290
231
+ },
232
+ {
233
+ "epoch": 1.2195121951219512,
234
+ "grad_norm": 5.490593433380127,
235
+ "learning_rate": 7.804878048780489e-06,
236
+ "loss": 0.7554,
237
+ "step": 300
238
+ },
239
+ {
240
+ "epoch": 1.2195121951219512,
241
+ "eval_f1": 0.6839676640367311,
242
+ "eval_loss": 0.9506719708442688,
243
+ "eval_runtime": 30.8566,
244
+ "eval_samples_per_second": 109.085,
245
+ "eval_steps_per_second": 3.435,
246
+ "step": 300
247
+ },
248
+ {
249
+ "epoch": 1.2601626016260163,
250
+ "grad_norm": 10.015968322753906,
251
+ "learning_rate": 7.398373983739838e-06,
252
+ "loss": 0.9043,
253
+ "step": 310
254
+ },
255
+ {
256
+ "epoch": 1.3008130081300813,
257
+ "grad_norm": 7.634036064147949,
258
+ "learning_rate": 6.991869918699188e-06,
259
+ "loss": 0.8676,
260
+ "step": 320
261
+ },
262
+ {
263
+ "epoch": 1.3414634146341464,
264
+ "grad_norm": 5.928556442260742,
265
+ "learning_rate": 6.585365853658538e-06,
266
+ "loss": 0.9127,
267
+ "step": 330
268
+ },
269
+ {
270
+ "epoch": 1.3821138211382114,
271
+ "grad_norm": 6.368280410766602,
272
+ "learning_rate": 6.178861788617887e-06,
273
+ "loss": 0.9316,
274
+ "step": 340
275
+ },
276
+ {
277
+ "epoch": 1.4227642276422765,
278
+ "grad_norm": 6.322418212890625,
279
+ "learning_rate": 5.772357723577237e-06,
280
+ "loss": 0.8273,
281
+ "step": 350
282
+ },
283
+ {
284
+ "epoch": 1.4634146341463414,
285
+ "grad_norm": 7.215012550354004,
286
+ "learning_rate": 5.365853658536586e-06,
287
+ "loss": 0.8814,
288
+ "step": 360
289
+ },
290
+ {
291
+ "epoch": 1.5040650406504064,
292
+ "grad_norm": 5.894520282745361,
293
+ "learning_rate": 4.959349593495935e-06,
294
+ "loss": 0.8295,
295
+ "step": 370
296
+ },
297
+ {
298
+ "epoch": 1.5447154471544715,
299
+ "grad_norm": 6.685314178466797,
300
+ "learning_rate": 4.552845528455285e-06,
301
+ "loss": 0.8727,
302
+ "step": 380
303
+ },
304
+ {
305
+ "epoch": 1.5853658536585367,
306
+ "grad_norm": 8.929649353027344,
307
+ "learning_rate": 4.146341463414634e-06,
308
+ "loss": 0.8012,
309
+ "step": 390
310
+ },
311
+ {
312
+ "epoch": 1.6260162601626016,
313
+ "grad_norm": 8.644834518432617,
314
+ "learning_rate": 3.7398373983739838e-06,
315
+ "loss": 0.8151,
316
+ "step": 400
317
+ },
318
+ {
319
+ "epoch": 1.6260162601626016,
320
+ "eval_f1": 0.7058091506789402,
321
+ "eval_loss": 0.9088509678840637,
322
+ "eval_runtime": 30.8562,
323
+ "eval_samples_per_second": 109.087,
324
+ "eval_steps_per_second": 3.435,
325
+ "step": 400
326
+ },
327
+ {
328
+ "epoch": 1.6666666666666665,
329
+ "grad_norm": 7.286980628967285,
330
+ "learning_rate": 3.3333333333333333e-06,
331
+ "loss": 0.8603,
332
+ "step": 410
333
+ },
334
+ {
335
+ "epoch": 1.7073170731707317,
336
+ "grad_norm": 7.062027454376221,
337
+ "learning_rate": 2.926829268292683e-06,
338
+ "loss": 0.8243,
339
+ "step": 420
340
+ },
341
+ {
342
+ "epoch": 1.7479674796747968,
343
+ "grad_norm": 6.453483581542969,
344
+ "learning_rate": 2.5203252032520324e-06,
345
+ "loss": 0.8328,
346
+ "step": 430
347
+ },
348
+ {
349
+ "epoch": 1.7886178861788617,
350
+ "grad_norm": 6.350010395050049,
351
+ "learning_rate": 2.1138211382113824e-06,
352
+ "loss": 0.8307,
353
+ "step": 440
354
+ },
355
+ {
356
+ "epoch": 1.8292682926829267,
357
+ "grad_norm": 11.967658042907715,
358
+ "learning_rate": 1.707317073170732e-06,
359
+ "loss": 0.8335,
360
+ "step": 450
361
+ },
362
+ {
363
+ "epoch": 1.8699186991869918,
364
+ "grad_norm": 7.773582935333252,
365
+ "learning_rate": 1.3008130081300815e-06,
366
+ "loss": 0.7627,
367
+ "step": 460
368
+ },
369
+ {
370
+ "epoch": 1.910569105691057,
371
+ "grad_norm": 8.230002403259277,
372
+ "learning_rate": 8.94308943089431e-07,
373
+ "loss": 0.7758,
374
+ "step": 470
375
+ },
376
+ {
377
+ "epoch": 1.951219512195122,
378
+ "grad_norm": 5.672370910644531,
379
+ "learning_rate": 4.878048780487805e-07,
380
+ "loss": 0.8621,
381
+ "step": 480
382
+ },
383
+ {
384
+ "epoch": 1.9918699186991868,
385
+ "grad_norm": 9.773723602294922,
386
+ "learning_rate": 8.130081300813009e-08,
387
+ "loss": 0.8322,
388
+ "step": 490
389
+ }
390
+ ],
391
+ "logging_steps": 10,
392
+ "max_steps": 492,
393
+ "num_input_tokens_seen": 0,
394
+ "num_train_epochs": 2,
395
+ "save_steps": 100,
396
+ "stateful_callbacks": {
397
+ "TrainerControl": {
398
+ "args": {
399
+ "should_epoch_stop": false,
400
+ "should_evaluate": false,
401
+ "should_log": false,
402
+ "should_save": true,
403
+ "should_training_stop": true
404
+ },
405
+ "attributes": {}
406
+ }
407
+ },
408
+ "total_flos": 4131555260774400.0,
409
+ "train_batch_size": 32,
410
+ "trial_name": null,
411
+ "trial_params": null
412
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f4ffe9f0dae04da9971f62fe4fafdc4a3d901e79653544031813e3cccfe76d0e
3
+ size 5432