Ani-404 commited on
Commit
e355577
·
verified ·
1 Parent(s): 5656462

Upload folder using huggingface_hub

Browse files
Model_training.ipynb ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-1910/config.json ADDED
@@ -0,0 +1,36 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "BertForSequenceClassification"
4
+ ],
5
+ "attention_probs_dropout_prob": 0.1,
6
+ "classifier_dropout": null,
7
+ "dtype": "float32",
8
+ "gradient_checkpointing": false,
9
+ "hidden_act": "gelu",
10
+ "hidden_dropout_prob": 0.1,
11
+ "hidden_size": 768,
12
+ "id2label": {
13
+ "0": "0",
14
+ "1": "1",
15
+ "2": "2"
16
+ },
17
+ "initializer_range": 0.02,
18
+ "intermediate_size": 3072,
19
+ "label2id": {
20
+ "0": 0,
21
+ "1": 1,
22
+ "2": 2
23
+ },
24
+ "layer_norm_eps": 1e-12,
25
+ "max_position_embeddings": 512,
26
+ "model_type": "bert",
27
+ "num_attention_heads": 12,
28
+ "num_hidden_layers": 12,
29
+ "pad_token_id": 0,
30
+ "position_embedding_type": "absolute",
31
+ "problem_type": "single_label_classification",
32
+ "transformers_version": "4.56.2",
33
+ "type_vocab_size": 2,
34
+ "use_cache": true,
35
+ "vocab_size": 30522
36
+ }
checkpoint-1910/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aaa6640d342ea8bc18137670e1b63ed250f6b9b3fc398b7d6b4f37862645fe5f
3
+ size 437961724
checkpoint-1910/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:af2b93000179fdda2d9812573a7da5cb13de2919bf617747d4abfee66b55d16e
3
+ size 876047755
checkpoint-1910/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d9c9ff415a6cf0946cae1a5ce3810c22a18613f69fe3bc8650a8b5c4adaf60af
3
+ size 14645
checkpoint-1910/scaler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e0e24acdfb2fdf280e52ecda4380e48ca21f124cdcd66b648924efa2e61fa770
3
+ size 1383
checkpoint-1910/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dec653f71902abe4daf13b66082f495d9deff684c417ae44db246952226b673a
3
+ size 1465
checkpoint-1910/trainer_state.json ADDED
@@ -0,0 +1,586 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": 955,
3
+ "best_metric": 0.3973127603530884,
4
+ "best_model_checkpoint": "finbert_model/checkpoint-955",
5
+ "epoch": 2.0,
6
+ "eval_steps": 500,
7
+ "global_step": 1910,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.02617801047120419,
14
+ "grad_norm": 5.389065742492676,
15
+ "learning_rate": 1.9832460732984295e-05,
16
+ "loss": 1.0684,
17
+ "step": 25
18
+ },
19
+ {
20
+ "epoch": 0.05235602094240838,
21
+ "grad_norm": 10.32921314239502,
22
+ "learning_rate": 1.9657940663176267e-05,
23
+ "loss": 0.7284,
24
+ "step": 50
25
+ },
26
+ {
27
+ "epoch": 0.07853403141361257,
28
+ "grad_norm": 6.734121322631836,
29
+ "learning_rate": 1.948342059336824e-05,
30
+ "loss": 0.7981,
31
+ "step": 75
32
+ },
33
+ {
34
+ "epoch": 0.10471204188481675,
35
+ "grad_norm": 8.204632759094238,
36
+ "learning_rate": 1.930890052356021e-05,
37
+ "loss": 0.5878,
38
+ "step": 100
39
+ },
40
+ {
41
+ "epoch": 0.13089005235602094,
42
+ "grad_norm": 10.211732864379883,
43
+ "learning_rate": 1.9134380453752185e-05,
44
+ "loss": 0.7182,
45
+ "step": 125
46
+ },
47
+ {
48
+ "epoch": 0.15706806282722513,
49
+ "grad_norm": 9.390113830566406,
50
+ "learning_rate": 1.8959860383944157e-05,
51
+ "loss": 0.72,
52
+ "step": 150
53
+ },
54
+ {
55
+ "epoch": 0.18324607329842932,
56
+ "grad_norm": 11.717000007629395,
57
+ "learning_rate": 1.8785340314136128e-05,
58
+ "loss": 0.6367,
59
+ "step": 175
60
+ },
61
+ {
62
+ "epoch": 0.2094240837696335,
63
+ "grad_norm": 8.935040473937988,
64
+ "learning_rate": 1.86108202443281e-05,
65
+ "loss": 0.6106,
66
+ "step": 200
67
+ },
68
+ {
69
+ "epoch": 0.2356020942408377,
70
+ "grad_norm": 11.59050464630127,
71
+ "learning_rate": 1.843630017452007e-05,
72
+ "loss": 0.6202,
73
+ "step": 225
74
+ },
75
+ {
76
+ "epoch": 0.2617801047120419,
77
+ "grad_norm": 7.747163772583008,
78
+ "learning_rate": 1.8261780104712043e-05,
79
+ "loss": 0.669,
80
+ "step": 250
81
+ },
82
+ {
83
+ "epoch": 0.2879581151832461,
84
+ "grad_norm": 16.7243595123291,
85
+ "learning_rate": 1.8087260034904015e-05,
86
+ "loss": 0.4931,
87
+ "step": 275
88
+ },
89
+ {
90
+ "epoch": 0.31413612565445026,
91
+ "grad_norm": 7.23421049118042,
92
+ "learning_rate": 1.7912739965095986e-05,
93
+ "loss": 0.5974,
94
+ "step": 300
95
+ },
96
+ {
97
+ "epoch": 0.3403141361256545,
98
+ "grad_norm": 6.768913269042969,
99
+ "learning_rate": 1.773821989528796e-05,
100
+ "loss": 0.4926,
101
+ "step": 325
102
+ },
103
+ {
104
+ "epoch": 0.36649214659685864,
105
+ "grad_norm": 3.186237096786499,
106
+ "learning_rate": 1.7563699825479933e-05,
107
+ "loss": 0.4709,
108
+ "step": 350
109
+ },
110
+ {
111
+ "epoch": 0.39267015706806285,
112
+ "grad_norm": 12.499926567077637,
113
+ "learning_rate": 1.7389179755671904e-05,
114
+ "loss": 0.5128,
115
+ "step": 375
116
+ },
117
+ {
118
+ "epoch": 0.418848167539267,
119
+ "grad_norm": 8.35361099243164,
120
+ "learning_rate": 1.7214659685863876e-05,
121
+ "loss": 0.5878,
122
+ "step": 400
123
+ },
124
+ {
125
+ "epoch": 0.44502617801047123,
126
+ "grad_norm": 6.956220626831055,
127
+ "learning_rate": 1.7040139616055848e-05,
128
+ "loss": 0.4794,
129
+ "step": 425
130
+ },
131
+ {
132
+ "epoch": 0.4712041884816754,
133
+ "grad_norm": 15.914446830749512,
134
+ "learning_rate": 1.686561954624782e-05,
135
+ "loss": 0.5827,
136
+ "step": 450
137
+ },
138
+ {
139
+ "epoch": 0.4973821989528796,
140
+ "grad_norm": 15.149320602416992,
141
+ "learning_rate": 1.669109947643979e-05,
142
+ "loss": 0.5467,
143
+ "step": 475
144
+ },
145
+ {
146
+ "epoch": 0.5235602094240838,
147
+ "grad_norm": 10.100659370422363,
148
+ "learning_rate": 1.6516579406631763e-05,
149
+ "loss": 0.525,
150
+ "step": 500
151
+ },
152
+ {
153
+ "epoch": 0.5497382198952879,
154
+ "grad_norm": 8.821247100830078,
155
+ "learning_rate": 1.6342059336823738e-05,
156
+ "loss": 0.5345,
157
+ "step": 525
158
+ },
159
+ {
160
+ "epoch": 0.5759162303664922,
161
+ "grad_norm": 14.301637649536133,
162
+ "learning_rate": 1.616753926701571e-05,
163
+ "loss": 0.5115,
164
+ "step": 550
165
+ },
166
+ {
167
+ "epoch": 0.6020942408376964,
168
+ "grad_norm": 14.779314994812012,
169
+ "learning_rate": 1.599301919720768e-05,
170
+ "loss": 0.5034,
171
+ "step": 575
172
+ },
173
+ {
174
+ "epoch": 0.6282722513089005,
175
+ "grad_norm": 9.956971168518066,
176
+ "learning_rate": 1.5818499127399652e-05,
177
+ "loss": 0.3719,
178
+ "step": 600
179
+ },
180
+ {
181
+ "epoch": 0.6544502617801047,
182
+ "grad_norm": 17.58684730529785,
183
+ "learning_rate": 1.5643979057591624e-05,
184
+ "loss": 0.5269,
185
+ "step": 625
186
+ },
187
+ {
188
+ "epoch": 0.680628272251309,
189
+ "grad_norm": 10.585662841796875,
190
+ "learning_rate": 1.5469458987783596e-05,
191
+ "loss": 0.574,
192
+ "step": 650
193
+ },
194
+ {
195
+ "epoch": 0.7068062827225131,
196
+ "grad_norm": 17.19683074951172,
197
+ "learning_rate": 1.5294938917975567e-05,
198
+ "loss": 0.4294,
199
+ "step": 675
200
+ },
201
+ {
202
+ "epoch": 0.7329842931937173,
203
+ "grad_norm": 14.906782150268555,
204
+ "learning_rate": 1.5120418848167539e-05,
205
+ "loss": 0.4861,
206
+ "step": 700
207
+ },
208
+ {
209
+ "epoch": 0.7591623036649214,
210
+ "grad_norm": 12.943304061889648,
211
+ "learning_rate": 1.4945898778359514e-05,
212
+ "loss": 0.4121,
213
+ "step": 725
214
+ },
215
+ {
216
+ "epoch": 0.7853403141361257,
217
+ "grad_norm": 0.5662004351615906,
218
+ "learning_rate": 1.4771378708551485e-05,
219
+ "loss": 0.5198,
220
+ "step": 750
221
+ },
222
+ {
223
+ "epoch": 0.8115183246073299,
224
+ "grad_norm": 7.927789211273193,
225
+ "learning_rate": 1.4596858638743457e-05,
226
+ "loss": 0.4721,
227
+ "step": 775
228
+ },
229
+ {
230
+ "epoch": 0.837696335078534,
231
+ "grad_norm": 6.3558855056762695,
232
+ "learning_rate": 1.4422338568935429e-05,
233
+ "loss": 0.3977,
234
+ "step": 800
235
+ },
236
+ {
237
+ "epoch": 0.8638743455497382,
238
+ "grad_norm": 17.170700073242188,
239
+ "learning_rate": 1.4247818499127402e-05,
240
+ "loss": 0.3493,
241
+ "step": 825
242
+ },
243
+ {
244
+ "epoch": 0.8900523560209425,
245
+ "grad_norm": 15.060056686401367,
246
+ "learning_rate": 1.4073298429319373e-05,
247
+ "loss": 0.5364,
248
+ "step": 850
249
+ },
250
+ {
251
+ "epoch": 0.9162303664921466,
252
+ "grad_norm": 11.084234237670898,
253
+ "learning_rate": 1.3898778359511345e-05,
254
+ "loss": 0.4815,
255
+ "step": 875
256
+ },
257
+ {
258
+ "epoch": 0.9424083769633508,
259
+ "grad_norm": 11.328404426574707,
260
+ "learning_rate": 1.3724258289703317e-05,
261
+ "loss": 0.5914,
262
+ "step": 900
263
+ },
264
+ {
265
+ "epoch": 0.9685863874345549,
266
+ "grad_norm": 14.335894584655762,
267
+ "learning_rate": 1.354973821989529e-05,
268
+ "loss": 0.4111,
269
+ "step": 925
270
+ },
271
+ {
272
+ "epoch": 0.9947643979057592,
273
+ "grad_norm": 11.200068473815918,
274
+ "learning_rate": 1.3375218150087262e-05,
275
+ "loss": 0.4069,
276
+ "step": 950
277
+ },
278
+ {
279
+ "epoch": 1.0,
280
+ "eval_accuracy": 0.8690413829229964,
281
+ "eval_f1": 0.8665004404377881,
282
+ "eval_loss": 0.3973127603530884,
283
+ "eval_runtime": 4.1083,
284
+ "eval_samples_per_second": 464.669,
285
+ "eval_steps_per_second": 58.175,
286
+ "step": 955
287
+ },
288
+ {
289
+ "epoch": 1.0209424083769634,
290
+ "grad_norm": 10.518115043640137,
291
+ "learning_rate": 1.3200698080279233e-05,
292
+ "loss": 0.3101,
293
+ "step": 975
294
+ },
295
+ {
296
+ "epoch": 1.0471204188481675,
297
+ "grad_norm": 7.9896440505981445,
298
+ "learning_rate": 1.3026178010471205e-05,
299
+ "loss": 0.3442,
300
+ "step": 1000
301
+ },
302
+ {
303
+ "epoch": 1.0732984293193717,
304
+ "grad_norm": 2.440387010574341,
305
+ "learning_rate": 1.2851657940663178e-05,
306
+ "loss": 0.2582,
307
+ "step": 1025
308
+ },
309
+ {
310
+ "epoch": 1.0994764397905759,
311
+ "grad_norm": 4.903307914733887,
312
+ "learning_rate": 1.267713787085515e-05,
313
+ "loss": 0.2512,
314
+ "step": 1050
315
+ },
316
+ {
317
+ "epoch": 1.12565445026178,
318
+ "grad_norm": 4.360142707824707,
319
+ "learning_rate": 1.2502617801047121e-05,
320
+ "loss": 0.3125,
321
+ "step": 1075
322
+ },
323
+ {
324
+ "epoch": 1.1518324607329844,
325
+ "grad_norm": 0.4692545533180237,
326
+ "learning_rate": 1.2328097731239093e-05,
327
+ "loss": 0.3161,
328
+ "step": 1100
329
+ },
330
+ {
331
+ "epoch": 1.1780104712041886,
332
+ "grad_norm": 1.2277106046676636,
333
+ "learning_rate": 1.2153577661431066e-05,
334
+ "loss": 0.2237,
335
+ "step": 1125
336
+ },
337
+ {
338
+ "epoch": 1.2041884816753927,
339
+ "grad_norm": 13.60217571258545,
340
+ "learning_rate": 1.1979057591623038e-05,
341
+ "loss": 0.3578,
342
+ "step": 1150
343
+ },
344
+ {
345
+ "epoch": 1.2303664921465969,
346
+ "grad_norm": 8.050612449645996,
347
+ "learning_rate": 1.180453752181501e-05,
348
+ "loss": 0.3301,
349
+ "step": 1175
350
+ },
351
+ {
352
+ "epoch": 1.256544502617801,
353
+ "grad_norm": 23.87043571472168,
354
+ "learning_rate": 1.1630017452006981e-05,
355
+ "loss": 0.2843,
356
+ "step": 1200
357
+ },
358
+ {
359
+ "epoch": 1.2827225130890052,
360
+ "grad_norm": 0.21612492203712463,
361
+ "learning_rate": 1.1455497382198954e-05,
362
+ "loss": 0.2529,
363
+ "step": 1225
364
+ },
365
+ {
366
+ "epoch": 1.3089005235602094,
367
+ "grad_norm": 15.835173606872559,
368
+ "learning_rate": 1.1280977312390926e-05,
369
+ "loss": 0.2231,
370
+ "step": 1250
371
+ },
372
+ {
373
+ "epoch": 1.3350785340314135,
374
+ "grad_norm": 49.70761489868164,
375
+ "learning_rate": 1.1106457242582898e-05,
376
+ "loss": 0.3135,
377
+ "step": 1275
378
+ },
379
+ {
380
+ "epoch": 1.3612565445026177,
381
+ "grad_norm": 0.1663261204957962,
382
+ "learning_rate": 1.093193717277487e-05,
383
+ "loss": 0.3561,
384
+ "step": 1300
385
+ },
386
+ {
387
+ "epoch": 1.387434554973822,
388
+ "grad_norm": 17.380788803100586,
389
+ "learning_rate": 1.0757417102966842e-05,
390
+ "loss": 0.3588,
391
+ "step": 1325
392
+ },
393
+ {
394
+ "epoch": 1.4136125654450262,
395
+ "grad_norm": 11.443221092224121,
396
+ "learning_rate": 1.0582897033158814e-05,
397
+ "loss": 0.2319,
398
+ "step": 1350
399
+ },
400
+ {
401
+ "epoch": 1.4397905759162304,
402
+ "grad_norm": 12.970437049865723,
403
+ "learning_rate": 1.0408376963350786e-05,
404
+ "loss": 0.3858,
405
+ "step": 1375
406
+ },
407
+ {
408
+ "epoch": 1.4659685863874345,
409
+ "grad_norm": 8.48019790649414,
410
+ "learning_rate": 1.0233856893542757e-05,
411
+ "loss": 0.3213,
412
+ "step": 1400
413
+ },
414
+ {
415
+ "epoch": 1.4921465968586387,
416
+ "grad_norm": 0.29926174879074097,
417
+ "learning_rate": 1.005933682373473e-05,
418
+ "loss": 0.1976,
419
+ "step": 1425
420
+ },
421
+ {
422
+ "epoch": 1.518324607329843,
423
+ "grad_norm": 7.1454339027404785,
424
+ "learning_rate": 9.884816753926702e-06,
425
+ "loss": 0.2965,
426
+ "step": 1450
427
+ },
428
+ {
429
+ "epoch": 1.5445026178010473,
430
+ "grad_norm": 9.631463050842285,
431
+ "learning_rate": 9.710296684118674e-06,
432
+ "loss": 0.2411,
433
+ "step": 1475
434
+ },
435
+ {
436
+ "epoch": 1.5706806282722514,
437
+ "grad_norm": 72.68104553222656,
438
+ "learning_rate": 9.535776614310647e-06,
439
+ "loss": 0.209,
440
+ "step": 1500
441
+ },
442
+ {
443
+ "epoch": 1.5968586387434556,
444
+ "grad_norm": 72.5035400390625,
445
+ "learning_rate": 9.361256544502619e-06,
446
+ "loss": 0.3374,
447
+ "step": 1525
448
+ },
449
+ {
450
+ "epoch": 1.6230366492146597,
451
+ "grad_norm": 20.452966690063477,
452
+ "learning_rate": 9.18673647469459e-06,
453
+ "loss": 0.3733,
454
+ "step": 1550
455
+ },
456
+ {
457
+ "epoch": 1.649214659685864,
458
+ "grad_norm": 9.723285675048828,
459
+ "learning_rate": 9.012216404886562e-06,
460
+ "loss": 0.259,
461
+ "step": 1575
462
+ },
463
+ {
464
+ "epoch": 1.675392670157068,
465
+ "grad_norm": 0.682996928691864,
466
+ "learning_rate": 8.837696335078535e-06,
467
+ "loss": 0.4751,
468
+ "step": 1600
469
+ },
470
+ {
471
+ "epoch": 1.7015706806282722,
472
+ "grad_norm": 0.5499667525291443,
473
+ "learning_rate": 8.663176265270507e-06,
474
+ "loss": 0.3404,
475
+ "step": 1625
476
+ },
477
+ {
478
+ "epoch": 1.7277486910994764,
479
+ "grad_norm": 31.961536407470703,
480
+ "learning_rate": 8.488656195462478e-06,
481
+ "loss": 0.2747,
482
+ "step": 1650
483
+ },
484
+ {
485
+ "epoch": 1.7539267015706805,
486
+ "grad_norm": 21.48028564453125,
487
+ "learning_rate": 8.31413612565445e-06,
488
+ "loss": 0.2676,
489
+ "step": 1675
490
+ },
491
+ {
492
+ "epoch": 1.7801047120418847,
493
+ "grad_norm": 8.918591499328613,
494
+ "learning_rate": 8.139616055846423e-06,
495
+ "loss": 0.3828,
496
+ "step": 1700
497
+ },
498
+ {
499
+ "epoch": 1.8062827225130889,
500
+ "grad_norm": 19.257600784301758,
501
+ "learning_rate": 7.965095986038395e-06,
502
+ "loss": 0.3434,
503
+ "step": 1725
504
+ },
505
+ {
506
+ "epoch": 1.8324607329842932,
507
+ "grad_norm": 11.988317489624023,
508
+ "learning_rate": 7.790575916230367e-06,
509
+ "loss": 0.3589,
510
+ "step": 1750
511
+ },
512
+ {
513
+ "epoch": 1.8586387434554974,
514
+ "grad_norm": 27.76133155822754,
515
+ "learning_rate": 7.616055846422339e-06,
516
+ "loss": 0.3216,
517
+ "step": 1775
518
+ },
519
+ {
520
+ "epoch": 1.8848167539267016,
521
+ "grad_norm": 31.528942108154297,
522
+ "learning_rate": 7.4415357766143115e-06,
523
+ "loss": 0.2637,
524
+ "step": 1800
525
+ },
526
+ {
527
+ "epoch": 1.9109947643979057,
528
+ "grad_norm": 0.13127724826335907,
529
+ "learning_rate": 7.267015706806283e-06,
530
+ "loss": 0.1963,
531
+ "step": 1825
532
+ },
533
+ {
534
+ "epoch": 1.93717277486911,
535
+ "grad_norm": 1.6614102125167847,
536
+ "learning_rate": 7.0924956369982556e-06,
537
+ "loss": 0.2581,
538
+ "step": 1850
539
+ },
540
+ {
541
+ "epoch": 1.9633507853403143,
542
+ "grad_norm": 1.648483395576477,
543
+ "learning_rate": 6.917975567190227e-06,
544
+ "loss": 0.3178,
545
+ "step": 1875
546
+ },
547
+ {
548
+ "epoch": 1.9895287958115184,
549
+ "grad_norm": 0.3059515953063965,
550
+ "learning_rate": 6.7434554973822e-06,
551
+ "loss": 0.2418,
552
+ "step": 1900
553
+ },
554
+ {
555
+ "epoch": 2.0,
556
+ "eval_accuracy": 0.8727082242011525,
557
+ "eval_f1": 0.8728823235536903,
558
+ "eval_loss": 0.4636137783527374,
559
+ "eval_runtime": 4.2893,
560
+ "eval_samples_per_second": 445.066,
561
+ "eval_steps_per_second": 55.721,
562
+ "step": 1910
563
+ }
564
+ ],
565
+ "logging_steps": 25,
566
+ "max_steps": 2865,
567
+ "num_input_tokens_seen": 0,
568
+ "num_train_epochs": 3,
569
+ "save_steps": 500,
570
+ "stateful_callbacks": {
571
+ "TrainerControl": {
572
+ "args": {
573
+ "should_epoch_stop": false,
574
+ "should_evaluate": false,
575
+ "should_log": false,
576
+ "should_save": true,
577
+ "should_training_stop": false
578
+ },
579
+ "attributes": {}
580
+ }
581
+ },
582
+ "total_flos": 1004303915467776.0,
583
+ "train_batch_size": 8,
584
+ "trial_name": null,
585
+ "trial_params": null
586
+ }
checkpoint-1910/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2d620eee01b27533e078e3386e9efbb932822d44a3acdd2ecc263ee6ced295d7
3
+ size 5777
checkpoint-2865/config.json ADDED
@@ -0,0 +1,36 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "BertForSequenceClassification"
4
+ ],
5
+ "attention_probs_dropout_prob": 0.1,
6
+ "classifier_dropout": null,
7
+ "dtype": "float32",
8
+ "gradient_checkpointing": false,
9
+ "hidden_act": "gelu",
10
+ "hidden_dropout_prob": 0.1,
11
+ "hidden_size": 768,
12
+ "id2label": {
13
+ "0": "0",
14
+ "1": "1",
15
+ "2": "2"
16
+ },
17
+ "initializer_range": 0.02,
18
+ "intermediate_size": 3072,
19
+ "label2id": {
20
+ "0": 0,
21
+ "1": 1,
22
+ "2": 2
23
+ },
24
+ "layer_norm_eps": 1e-12,
25
+ "max_position_embeddings": 512,
26
+ "model_type": "bert",
27
+ "num_attention_heads": 12,
28
+ "num_hidden_layers": 12,
29
+ "pad_token_id": 0,
30
+ "position_embedding_type": "absolute",
31
+ "problem_type": "single_label_classification",
32
+ "transformers_version": "4.56.2",
33
+ "type_vocab_size": 2,
34
+ "use_cache": true,
35
+ "vocab_size": 30522
36
+ }
checkpoint-2865/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b7e2bf7efd56515d66936998307986d258af7ea3b2f7abd5839fcb6ea89c14a1
3
+ size 437961724
checkpoint-2865/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:12fc682f5bb1d4c2420e5a12678e4a8d4968e1073abb174572ec6822ca52bc13
3
+ size 876047755
checkpoint-2865/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bf350a0d3c76d866c67e8f74567ee93003e50587dde14121ef80eaf17a272d87
3
+ size 14645
checkpoint-2865/scaler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d9835ceeb557d25c9f02c0cc434e2ea380b3bd0bcfc2963a8564dc2af20c3170
3
+ size 1383
checkpoint-2865/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:405675588cadde115249c5b4aa405e828ce2ed5ca14e128ea0bae41d8ec1bf64
3
+ size 1465
checkpoint-2865/trainer_state.json ADDED
@@ -0,0 +1,862 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": 955,
3
+ "best_metric": 0.3973127603530884,
4
+ "best_model_checkpoint": "finbert_model/checkpoint-955",
5
+ "epoch": 3.0,
6
+ "eval_steps": 500,
7
+ "global_step": 2865,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.02617801047120419,
14
+ "grad_norm": 5.389065742492676,
15
+ "learning_rate": 1.9832460732984295e-05,
16
+ "loss": 1.0684,
17
+ "step": 25
18
+ },
19
+ {
20
+ "epoch": 0.05235602094240838,
21
+ "grad_norm": 10.32921314239502,
22
+ "learning_rate": 1.9657940663176267e-05,
23
+ "loss": 0.7284,
24
+ "step": 50
25
+ },
26
+ {
27
+ "epoch": 0.07853403141361257,
28
+ "grad_norm": 6.734121322631836,
29
+ "learning_rate": 1.948342059336824e-05,
30
+ "loss": 0.7981,
31
+ "step": 75
32
+ },
33
+ {
34
+ "epoch": 0.10471204188481675,
35
+ "grad_norm": 8.204632759094238,
36
+ "learning_rate": 1.930890052356021e-05,
37
+ "loss": 0.5878,
38
+ "step": 100
39
+ },
40
+ {
41
+ "epoch": 0.13089005235602094,
42
+ "grad_norm": 10.211732864379883,
43
+ "learning_rate": 1.9134380453752185e-05,
44
+ "loss": 0.7182,
45
+ "step": 125
46
+ },
47
+ {
48
+ "epoch": 0.15706806282722513,
49
+ "grad_norm": 9.390113830566406,
50
+ "learning_rate": 1.8959860383944157e-05,
51
+ "loss": 0.72,
52
+ "step": 150
53
+ },
54
+ {
55
+ "epoch": 0.18324607329842932,
56
+ "grad_norm": 11.717000007629395,
57
+ "learning_rate": 1.8785340314136128e-05,
58
+ "loss": 0.6367,
59
+ "step": 175
60
+ },
61
+ {
62
+ "epoch": 0.2094240837696335,
63
+ "grad_norm": 8.935040473937988,
64
+ "learning_rate": 1.86108202443281e-05,
65
+ "loss": 0.6106,
66
+ "step": 200
67
+ },
68
+ {
69
+ "epoch": 0.2356020942408377,
70
+ "grad_norm": 11.59050464630127,
71
+ "learning_rate": 1.843630017452007e-05,
72
+ "loss": 0.6202,
73
+ "step": 225
74
+ },
75
+ {
76
+ "epoch": 0.2617801047120419,
77
+ "grad_norm": 7.747163772583008,
78
+ "learning_rate": 1.8261780104712043e-05,
79
+ "loss": 0.669,
80
+ "step": 250
81
+ },
82
+ {
83
+ "epoch": 0.2879581151832461,
84
+ "grad_norm": 16.7243595123291,
85
+ "learning_rate": 1.8087260034904015e-05,
86
+ "loss": 0.4931,
87
+ "step": 275
88
+ },
89
+ {
90
+ "epoch": 0.31413612565445026,
91
+ "grad_norm": 7.23421049118042,
92
+ "learning_rate": 1.7912739965095986e-05,
93
+ "loss": 0.5974,
94
+ "step": 300
95
+ },
96
+ {
97
+ "epoch": 0.3403141361256545,
98
+ "grad_norm": 6.768913269042969,
99
+ "learning_rate": 1.773821989528796e-05,
100
+ "loss": 0.4926,
101
+ "step": 325
102
+ },
103
+ {
104
+ "epoch": 0.36649214659685864,
105
+ "grad_norm": 3.186237096786499,
106
+ "learning_rate": 1.7563699825479933e-05,
107
+ "loss": 0.4709,
108
+ "step": 350
109
+ },
110
+ {
111
+ "epoch": 0.39267015706806285,
112
+ "grad_norm": 12.499926567077637,
113
+ "learning_rate": 1.7389179755671904e-05,
114
+ "loss": 0.5128,
115
+ "step": 375
116
+ },
117
+ {
118
+ "epoch": 0.418848167539267,
119
+ "grad_norm": 8.35361099243164,
120
+ "learning_rate": 1.7214659685863876e-05,
121
+ "loss": 0.5878,
122
+ "step": 400
123
+ },
124
+ {
125
+ "epoch": 0.44502617801047123,
126
+ "grad_norm": 6.956220626831055,
127
+ "learning_rate": 1.7040139616055848e-05,
128
+ "loss": 0.4794,
129
+ "step": 425
130
+ },
131
+ {
132
+ "epoch": 0.4712041884816754,
133
+ "grad_norm": 15.914446830749512,
134
+ "learning_rate": 1.686561954624782e-05,
135
+ "loss": 0.5827,
136
+ "step": 450
137
+ },
138
+ {
139
+ "epoch": 0.4973821989528796,
140
+ "grad_norm": 15.149320602416992,
141
+ "learning_rate": 1.669109947643979e-05,
142
+ "loss": 0.5467,
143
+ "step": 475
144
+ },
145
+ {
146
+ "epoch": 0.5235602094240838,
147
+ "grad_norm": 10.100659370422363,
148
+ "learning_rate": 1.6516579406631763e-05,
149
+ "loss": 0.525,
150
+ "step": 500
151
+ },
152
+ {
153
+ "epoch": 0.5497382198952879,
154
+ "grad_norm": 8.821247100830078,
155
+ "learning_rate": 1.6342059336823738e-05,
156
+ "loss": 0.5345,
157
+ "step": 525
158
+ },
159
+ {
160
+ "epoch": 0.5759162303664922,
161
+ "grad_norm": 14.301637649536133,
162
+ "learning_rate": 1.616753926701571e-05,
163
+ "loss": 0.5115,
164
+ "step": 550
165
+ },
166
+ {
167
+ "epoch": 0.6020942408376964,
168
+ "grad_norm": 14.779314994812012,
169
+ "learning_rate": 1.599301919720768e-05,
170
+ "loss": 0.5034,
171
+ "step": 575
172
+ },
173
+ {
174
+ "epoch": 0.6282722513089005,
175
+ "grad_norm": 9.956971168518066,
176
+ "learning_rate": 1.5818499127399652e-05,
177
+ "loss": 0.3719,
178
+ "step": 600
179
+ },
180
+ {
181
+ "epoch": 0.6544502617801047,
182
+ "grad_norm": 17.58684730529785,
183
+ "learning_rate": 1.5643979057591624e-05,
184
+ "loss": 0.5269,
185
+ "step": 625
186
+ },
187
+ {
188
+ "epoch": 0.680628272251309,
189
+ "grad_norm": 10.585662841796875,
190
+ "learning_rate": 1.5469458987783596e-05,
191
+ "loss": 0.574,
192
+ "step": 650
193
+ },
194
+ {
195
+ "epoch": 0.7068062827225131,
196
+ "grad_norm": 17.19683074951172,
197
+ "learning_rate": 1.5294938917975567e-05,
198
+ "loss": 0.4294,
199
+ "step": 675
200
+ },
201
+ {
202
+ "epoch": 0.7329842931937173,
203
+ "grad_norm": 14.906782150268555,
204
+ "learning_rate": 1.5120418848167539e-05,
205
+ "loss": 0.4861,
206
+ "step": 700
207
+ },
208
+ {
209
+ "epoch": 0.7591623036649214,
210
+ "grad_norm": 12.943304061889648,
211
+ "learning_rate": 1.4945898778359514e-05,
212
+ "loss": 0.4121,
213
+ "step": 725
214
+ },
215
+ {
216
+ "epoch": 0.7853403141361257,
217
+ "grad_norm": 0.5662004351615906,
218
+ "learning_rate": 1.4771378708551485e-05,
219
+ "loss": 0.5198,
220
+ "step": 750
221
+ },
222
+ {
223
+ "epoch": 0.8115183246073299,
224
+ "grad_norm": 7.927789211273193,
225
+ "learning_rate": 1.4596858638743457e-05,
226
+ "loss": 0.4721,
227
+ "step": 775
228
+ },
229
+ {
230
+ "epoch": 0.837696335078534,
231
+ "grad_norm": 6.3558855056762695,
232
+ "learning_rate": 1.4422338568935429e-05,
233
+ "loss": 0.3977,
234
+ "step": 800
235
+ },
236
+ {
237
+ "epoch": 0.8638743455497382,
238
+ "grad_norm": 17.170700073242188,
239
+ "learning_rate": 1.4247818499127402e-05,
240
+ "loss": 0.3493,
241
+ "step": 825
242
+ },
243
+ {
244
+ "epoch": 0.8900523560209425,
245
+ "grad_norm": 15.060056686401367,
246
+ "learning_rate": 1.4073298429319373e-05,
247
+ "loss": 0.5364,
248
+ "step": 850
249
+ },
250
+ {
251
+ "epoch": 0.9162303664921466,
252
+ "grad_norm": 11.084234237670898,
253
+ "learning_rate": 1.3898778359511345e-05,
254
+ "loss": 0.4815,
255
+ "step": 875
256
+ },
257
+ {
258
+ "epoch": 0.9424083769633508,
259
+ "grad_norm": 11.328404426574707,
260
+ "learning_rate": 1.3724258289703317e-05,
261
+ "loss": 0.5914,
262
+ "step": 900
263
+ },
264
+ {
265
+ "epoch": 0.9685863874345549,
266
+ "grad_norm": 14.335894584655762,
267
+ "learning_rate": 1.354973821989529e-05,
268
+ "loss": 0.4111,
269
+ "step": 925
270
+ },
271
+ {
272
+ "epoch": 0.9947643979057592,
273
+ "grad_norm": 11.200068473815918,
274
+ "learning_rate": 1.3375218150087262e-05,
275
+ "loss": 0.4069,
276
+ "step": 950
277
+ },
278
+ {
279
+ "epoch": 1.0,
280
+ "eval_accuracy": 0.8690413829229964,
281
+ "eval_f1": 0.8665004404377881,
282
+ "eval_loss": 0.3973127603530884,
283
+ "eval_runtime": 4.1083,
284
+ "eval_samples_per_second": 464.669,
285
+ "eval_steps_per_second": 58.175,
286
+ "step": 955
287
+ },
288
+ {
289
+ "epoch": 1.0209424083769634,
290
+ "grad_norm": 10.518115043640137,
291
+ "learning_rate": 1.3200698080279233e-05,
292
+ "loss": 0.3101,
293
+ "step": 975
294
+ },
295
+ {
296
+ "epoch": 1.0471204188481675,
297
+ "grad_norm": 7.9896440505981445,
298
+ "learning_rate": 1.3026178010471205e-05,
299
+ "loss": 0.3442,
300
+ "step": 1000
301
+ },
302
+ {
303
+ "epoch": 1.0732984293193717,
304
+ "grad_norm": 2.440387010574341,
305
+ "learning_rate": 1.2851657940663178e-05,
306
+ "loss": 0.2582,
307
+ "step": 1025
308
+ },
309
+ {
310
+ "epoch": 1.0994764397905759,
311
+ "grad_norm": 4.903307914733887,
312
+ "learning_rate": 1.267713787085515e-05,
313
+ "loss": 0.2512,
314
+ "step": 1050
315
+ },
316
+ {
317
+ "epoch": 1.12565445026178,
318
+ "grad_norm": 4.360142707824707,
319
+ "learning_rate": 1.2502617801047121e-05,
320
+ "loss": 0.3125,
321
+ "step": 1075
322
+ },
323
+ {
324
+ "epoch": 1.1518324607329844,
325
+ "grad_norm": 0.4692545533180237,
326
+ "learning_rate": 1.2328097731239093e-05,
327
+ "loss": 0.3161,
328
+ "step": 1100
329
+ },
330
+ {
331
+ "epoch": 1.1780104712041886,
332
+ "grad_norm": 1.2277106046676636,
333
+ "learning_rate": 1.2153577661431066e-05,
334
+ "loss": 0.2237,
335
+ "step": 1125
336
+ },
337
+ {
338
+ "epoch": 1.2041884816753927,
339
+ "grad_norm": 13.60217571258545,
340
+ "learning_rate": 1.1979057591623038e-05,
341
+ "loss": 0.3578,
342
+ "step": 1150
343
+ },
344
+ {
345
+ "epoch": 1.2303664921465969,
346
+ "grad_norm": 8.050612449645996,
347
+ "learning_rate": 1.180453752181501e-05,
348
+ "loss": 0.3301,
349
+ "step": 1175
350
+ },
351
+ {
352
+ "epoch": 1.256544502617801,
353
+ "grad_norm": 23.87043571472168,
354
+ "learning_rate": 1.1630017452006981e-05,
355
+ "loss": 0.2843,
356
+ "step": 1200
357
+ },
358
+ {
359
+ "epoch": 1.2827225130890052,
360
+ "grad_norm": 0.21612492203712463,
361
+ "learning_rate": 1.1455497382198954e-05,
362
+ "loss": 0.2529,
363
+ "step": 1225
364
+ },
365
+ {
366
+ "epoch": 1.3089005235602094,
367
+ "grad_norm": 15.835173606872559,
368
+ "learning_rate": 1.1280977312390926e-05,
369
+ "loss": 0.2231,
370
+ "step": 1250
371
+ },
372
+ {
373
+ "epoch": 1.3350785340314135,
374
+ "grad_norm": 49.70761489868164,
375
+ "learning_rate": 1.1106457242582898e-05,
376
+ "loss": 0.3135,
377
+ "step": 1275
378
+ },
379
+ {
380
+ "epoch": 1.3612565445026177,
381
+ "grad_norm": 0.1663261204957962,
382
+ "learning_rate": 1.093193717277487e-05,
383
+ "loss": 0.3561,
384
+ "step": 1300
385
+ },
386
+ {
387
+ "epoch": 1.387434554973822,
388
+ "grad_norm": 17.380788803100586,
389
+ "learning_rate": 1.0757417102966842e-05,
390
+ "loss": 0.3588,
391
+ "step": 1325
392
+ },
393
+ {
394
+ "epoch": 1.4136125654450262,
395
+ "grad_norm": 11.443221092224121,
396
+ "learning_rate": 1.0582897033158814e-05,
397
+ "loss": 0.2319,
398
+ "step": 1350
399
+ },
400
+ {
401
+ "epoch": 1.4397905759162304,
402
+ "grad_norm": 12.970437049865723,
403
+ "learning_rate": 1.0408376963350786e-05,
404
+ "loss": 0.3858,
405
+ "step": 1375
406
+ },
407
+ {
408
+ "epoch": 1.4659685863874345,
409
+ "grad_norm": 8.48019790649414,
410
+ "learning_rate": 1.0233856893542757e-05,
411
+ "loss": 0.3213,
412
+ "step": 1400
413
+ },
414
+ {
415
+ "epoch": 1.4921465968586387,
416
+ "grad_norm": 0.29926174879074097,
417
+ "learning_rate": 1.005933682373473e-05,
418
+ "loss": 0.1976,
419
+ "step": 1425
420
+ },
421
+ {
422
+ "epoch": 1.518324607329843,
423
+ "grad_norm": 7.1454339027404785,
424
+ "learning_rate": 9.884816753926702e-06,
425
+ "loss": 0.2965,
426
+ "step": 1450
427
+ },
428
+ {
429
+ "epoch": 1.5445026178010473,
430
+ "grad_norm": 9.631463050842285,
431
+ "learning_rate": 9.710296684118674e-06,
432
+ "loss": 0.2411,
433
+ "step": 1475
434
+ },
435
+ {
436
+ "epoch": 1.5706806282722514,
437
+ "grad_norm": 72.68104553222656,
438
+ "learning_rate": 9.535776614310647e-06,
439
+ "loss": 0.209,
440
+ "step": 1500
441
+ },
442
+ {
443
+ "epoch": 1.5968586387434556,
444
+ "grad_norm": 72.5035400390625,
445
+ "learning_rate": 9.361256544502619e-06,
446
+ "loss": 0.3374,
447
+ "step": 1525
448
+ },
449
+ {
450
+ "epoch": 1.6230366492146597,
451
+ "grad_norm": 20.452966690063477,
452
+ "learning_rate": 9.18673647469459e-06,
453
+ "loss": 0.3733,
454
+ "step": 1550
455
+ },
456
+ {
457
+ "epoch": 1.649214659685864,
458
+ "grad_norm": 9.723285675048828,
459
+ "learning_rate": 9.012216404886562e-06,
460
+ "loss": 0.259,
461
+ "step": 1575
462
+ },
463
+ {
464
+ "epoch": 1.675392670157068,
465
+ "grad_norm": 0.682996928691864,
466
+ "learning_rate": 8.837696335078535e-06,
467
+ "loss": 0.4751,
468
+ "step": 1600
469
+ },
470
+ {
471
+ "epoch": 1.7015706806282722,
472
+ "grad_norm": 0.5499667525291443,
473
+ "learning_rate": 8.663176265270507e-06,
474
+ "loss": 0.3404,
475
+ "step": 1625
476
+ },
477
+ {
478
+ "epoch": 1.7277486910994764,
479
+ "grad_norm": 31.961536407470703,
480
+ "learning_rate": 8.488656195462478e-06,
481
+ "loss": 0.2747,
482
+ "step": 1650
483
+ },
484
+ {
485
+ "epoch": 1.7539267015706805,
486
+ "grad_norm": 21.48028564453125,
487
+ "learning_rate": 8.31413612565445e-06,
488
+ "loss": 0.2676,
489
+ "step": 1675
490
+ },
491
+ {
492
+ "epoch": 1.7801047120418847,
493
+ "grad_norm": 8.918591499328613,
494
+ "learning_rate": 8.139616055846423e-06,
495
+ "loss": 0.3828,
496
+ "step": 1700
497
+ },
498
+ {
499
+ "epoch": 1.8062827225130889,
500
+ "grad_norm": 19.257600784301758,
501
+ "learning_rate": 7.965095986038395e-06,
502
+ "loss": 0.3434,
503
+ "step": 1725
504
+ },
505
+ {
506
+ "epoch": 1.8324607329842932,
507
+ "grad_norm": 11.988317489624023,
508
+ "learning_rate": 7.790575916230367e-06,
509
+ "loss": 0.3589,
510
+ "step": 1750
511
+ },
512
+ {
513
+ "epoch": 1.8586387434554974,
514
+ "grad_norm": 27.76133155822754,
515
+ "learning_rate": 7.616055846422339e-06,
516
+ "loss": 0.3216,
517
+ "step": 1775
518
+ },
519
+ {
520
+ "epoch": 1.8848167539267016,
521
+ "grad_norm": 31.528942108154297,
522
+ "learning_rate": 7.4415357766143115e-06,
523
+ "loss": 0.2637,
524
+ "step": 1800
525
+ },
526
+ {
527
+ "epoch": 1.9109947643979057,
528
+ "grad_norm": 0.13127724826335907,
529
+ "learning_rate": 7.267015706806283e-06,
530
+ "loss": 0.1963,
531
+ "step": 1825
532
+ },
533
+ {
534
+ "epoch": 1.93717277486911,
535
+ "grad_norm": 1.6614102125167847,
536
+ "learning_rate": 7.0924956369982556e-06,
537
+ "loss": 0.2581,
538
+ "step": 1850
539
+ },
540
+ {
541
+ "epoch": 1.9633507853403143,
542
+ "grad_norm": 1.648483395576477,
543
+ "learning_rate": 6.917975567190227e-06,
544
+ "loss": 0.3178,
545
+ "step": 1875
546
+ },
547
+ {
548
+ "epoch": 1.9895287958115184,
549
+ "grad_norm": 0.3059515953063965,
550
+ "learning_rate": 6.7434554973822e-06,
551
+ "loss": 0.2418,
552
+ "step": 1900
553
+ },
554
+ {
555
+ "epoch": 2.0,
556
+ "eval_accuracy": 0.8727082242011525,
557
+ "eval_f1": 0.8728823235536903,
558
+ "eval_loss": 0.4636137783527374,
559
+ "eval_runtime": 4.2893,
560
+ "eval_samples_per_second": 445.066,
561
+ "eval_steps_per_second": 55.721,
562
+ "step": 1910
563
+ },
564
+ {
565
+ "epoch": 2.0157068062827226,
566
+ "grad_norm": 15.890205383300781,
567
+ "learning_rate": 6.568935427574171e-06,
568
+ "loss": 0.1975,
569
+ "step": 1925
570
+ },
571
+ {
572
+ "epoch": 2.0418848167539267,
573
+ "grad_norm": 4.748979091644287,
574
+ "learning_rate": 6.394415357766144e-06,
575
+ "loss": 0.1375,
576
+ "step": 1950
577
+ },
578
+ {
579
+ "epoch": 2.068062827225131,
580
+ "grad_norm": 12.78852653503418,
581
+ "learning_rate": 6.219895287958115e-06,
582
+ "loss": 0.1926,
583
+ "step": 1975
584
+ },
585
+ {
586
+ "epoch": 2.094240837696335,
587
+ "grad_norm": 9.572379112243652,
588
+ "learning_rate": 6.045375218150088e-06,
589
+ "loss": 0.1087,
590
+ "step": 2000
591
+ },
592
+ {
593
+ "epoch": 2.1204188481675392,
594
+ "grad_norm": 0.5682252049446106,
595
+ "learning_rate": 5.870855148342059e-06,
596
+ "loss": 0.1792,
597
+ "step": 2025
598
+ },
599
+ {
600
+ "epoch": 2.1465968586387434,
601
+ "grad_norm": 0.7415192723274231,
602
+ "learning_rate": 5.696335078534032e-06,
603
+ "loss": 0.2378,
604
+ "step": 2050
605
+ },
606
+ {
607
+ "epoch": 2.1727748691099475,
608
+ "grad_norm": 0.07994470000267029,
609
+ "learning_rate": 5.521815008726003e-06,
610
+ "loss": 0.2135,
611
+ "step": 2075
612
+ },
613
+ {
614
+ "epoch": 2.1989528795811517,
615
+ "grad_norm": 0.22101280093193054,
616
+ "learning_rate": 5.347294938917976e-06,
617
+ "loss": 0.0965,
618
+ "step": 2100
619
+ },
620
+ {
621
+ "epoch": 2.225130890052356,
622
+ "grad_norm": 0.17456702888011932,
623
+ "learning_rate": 5.1727748691099475e-06,
624
+ "loss": 0.2084,
625
+ "step": 2125
626
+ },
627
+ {
628
+ "epoch": 2.25130890052356,
629
+ "grad_norm": 18.24934959411621,
630
+ "learning_rate": 4.998254799301921e-06,
631
+ "loss": 0.0802,
632
+ "step": 2150
633
+ },
634
+ {
635
+ "epoch": 2.2774869109947646,
636
+ "grad_norm": 40.49116897583008,
637
+ "learning_rate": 4.823734729493892e-06,
638
+ "loss": 0.2103,
639
+ "step": 2175
640
+ },
641
+ {
642
+ "epoch": 2.303664921465969,
643
+ "grad_norm": 0.37025186419487,
644
+ "learning_rate": 4.649214659685865e-06,
645
+ "loss": 0.1339,
646
+ "step": 2200
647
+ },
648
+ {
649
+ "epoch": 2.329842931937173,
650
+ "grad_norm": 0.07061374187469482,
651
+ "learning_rate": 4.4746945898778364e-06,
652
+ "loss": 0.1267,
653
+ "step": 2225
654
+ },
655
+ {
656
+ "epoch": 2.356020942408377,
657
+ "grad_norm": 22.344051361083984,
658
+ "learning_rate": 4.300174520069809e-06,
659
+ "loss": 0.0843,
660
+ "step": 2250
661
+ },
662
+ {
663
+ "epoch": 2.3821989528795813,
664
+ "grad_norm": 0.05722755193710327,
665
+ "learning_rate": 4.1256544502617805e-06,
666
+ "loss": 0.0903,
667
+ "step": 2275
668
+ },
669
+ {
670
+ "epoch": 2.4083769633507854,
671
+ "grad_norm": 0.10248207300901413,
672
+ "learning_rate": 3.951134380453753e-06,
673
+ "loss": 0.211,
674
+ "step": 2300
675
+ },
676
+ {
677
+ "epoch": 2.4345549738219896,
678
+ "grad_norm": 0.12041915953159332,
679
+ "learning_rate": 3.776614310645725e-06,
680
+ "loss": 0.1836,
681
+ "step": 2325
682
+ },
683
+ {
684
+ "epoch": 2.4607329842931938,
685
+ "grad_norm": 0.15190765261650085,
686
+ "learning_rate": 3.602094240837697e-06,
687
+ "loss": 0.2645,
688
+ "step": 2350
689
+ },
690
+ {
691
+ "epoch": 2.486910994764398,
692
+ "grad_norm": 0.6992888450622559,
693
+ "learning_rate": 3.427574171029669e-06,
694
+ "loss": 0.1515,
695
+ "step": 2375
696
+ },
697
+ {
698
+ "epoch": 2.513089005235602,
699
+ "grad_norm": 0.07796134799718857,
700
+ "learning_rate": 3.253054101221641e-06,
701
+ "loss": 0.0545,
702
+ "step": 2400
703
+ },
704
+ {
705
+ "epoch": 2.5392670157068062,
706
+ "grad_norm": 0.41577911376953125,
707
+ "learning_rate": 3.078534031413613e-06,
708
+ "loss": 0.101,
709
+ "step": 2425
710
+ },
711
+ {
712
+ "epoch": 2.5654450261780104,
713
+ "grad_norm": 0.14312124252319336,
714
+ "learning_rate": 2.904013961605585e-06,
715
+ "loss": 0.2121,
716
+ "step": 2450
717
+ },
718
+ {
719
+ "epoch": 2.5916230366492146,
720
+ "grad_norm": 6.699955463409424,
721
+ "learning_rate": 2.729493891797557e-06,
722
+ "loss": 0.1265,
723
+ "step": 2475
724
+ },
725
+ {
726
+ "epoch": 2.6178010471204187,
727
+ "grad_norm": 0.11033662408590317,
728
+ "learning_rate": 2.554973821989529e-06,
729
+ "loss": 0.1985,
730
+ "step": 2500
731
+ },
732
+ {
733
+ "epoch": 2.643979057591623,
734
+ "grad_norm": 0.09589897096157074,
735
+ "learning_rate": 2.3804537521815012e-06,
736
+ "loss": 0.1419,
737
+ "step": 2525
738
+ },
739
+ {
740
+ "epoch": 2.670157068062827,
741
+ "grad_norm": 1.7485756874084473,
742
+ "learning_rate": 2.2059336823734733e-06,
743
+ "loss": 0.2441,
744
+ "step": 2550
745
+ },
746
+ {
747
+ "epoch": 2.696335078534031,
748
+ "grad_norm": 0.28520870208740234,
749
+ "learning_rate": 2.0314136125654453e-06,
750
+ "loss": 0.1209,
751
+ "step": 2575
752
+ },
753
+ {
754
+ "epoch": 2.7225130890052354,
755
+ "grad_norm": 0.26048529148101807,
756
+ "learning_rate": 1.8568935427574173e-06,
757
+ "loss": 0.2296,
758
+ "step": 2600
759
+ },
760
+ {
761
+ "epoch": 2.7486910994764395,
762
+ "grad_norm": 0.07016175985336304,
763
+ "learning_rate": 1.6823734729493894e-06,
764
+ "loss": 0.0609,
765
+ "step": 2625
766
+ },
767
+ {
768
+ "epoch": 2.774869109947644,
769
+ "grad_norm": 4.9815592765808105,
770
+ "learning_rate": 1.5078534031413614e-06,
771
+ "loss": 0.0824,
772
+ "step": 2650
773
+ },
774
+ {
775
+ "epoch": 2.8010471204188483,
776
+ "grad_norm": 0.11184385418891907,
777
+ "learning_rate": 1.3333333333333334e-06,
778
+ "loss": 0.1331,
779
+ "step": 2675
780
+ },
781
+ {
782
+ "epoch": 2.8272251308900525,
783
+ "grad_norm": 0.6429989337921143,
784
+ "learning_rate": 1.1588132635253054e-06,
785
+ "loss": 0.2019,
786
+ "step": 2700
787
+ },
788
+ {
789
+ "epoch": 2.8534031413612566,
790
+ "grad_norm": 21.87600326538086,
791
+ "learning_rate": 9.842931937172775e-07,
792
+ "loss": 0.0632,
793
+ "step": 2725
794
+ },
795
+ {
796
+ "epoch": 2.8795811518324608,
797
+ "grad_norm": 0.03200078383088112,
798
+ "learning_rate": 8.097731239092496e-07,
799
+ "loss": 0.2638,
800
+ "step": 2750
801
+ },
802
+ {
803
+ "epoch": 2.905759162303665,
804
+ "grad_norm": 47.9969596862793,
805
+ "learning_rate": 6.352530541012216e-07,
806
+ "loss": 0.188,
807
+ "step": 2775
808
+ },
809
+ {
810
+ "epoch": 2.931937172774869,
811
+ "grad_norm": 0.9299336075782776,
812
+ "learning_rate": 4.6073298429319373e-07,
813
+ "loss": 0.064,
814
+ "step": 2800
815
+ },
816
+ {
817
+ "epoch": 2.9581151832460733,
818
+ "grad_norm": 0.059168703854084015,
819
+ "learning_rate": 2.862129144851658e-07,
820
+ "loss": 0.1886,
821
+ "step": 2825
822
+ },
823
+ {
824
+ "epoch": 2.9842931937172774,
825
+ "grad_norm": 0.6567233800888062,
826
+ "learning_rate": 1.1169284467713788e-07,
827
+ "loss": 0.1826,
828
+ "step": 2850
829
+ },
830
+ {
831
+ "epoch": 3.0,
832
+ "eval_accuracy": 0.8779465688842326,
833
+ "eval_f1": 0.8773471210523544,
834
+ "eval_loss": 0.5452297925949097,
835
+ "eval_runtime": 4.1246,
836
+ "eval_samples_per_second": 462.832,
837
+ "eval_steps_per_second": 57.945,
838
+ "step": 2865
839
+ }
840
+ ],
841
+ "logging_steps": 25,
842
+ "max_steps": 2865,
843
+ "num_input_tokens_seen": 0,
844
+ "num_train_epochs": 3,
845
+ "save_steps": 500,
846
+ "stateful_callbacks": {
847
+ "TrainerControl": {
848
+ "args": {
849
+ "should_epoch_stop": false,
850
+ "should_evaluate": false,
851
+ "should_log": false,
852
+ "should_save": true,
853
+ "should_training_stop": true
854
+ },
855
+ "attributes": {}
856
+ }
857
+ },
858
+ "total_flos": 1506455873201664.0,
859
+ "train_batch_size": 8,
860
+ "trial_name": null,
861
+ "trial_params": null
862
+ }
checkpoint-2865/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2d620eee01b27533e078e3386e9efbb932822d44a3acdd2ecc263ee6ced295d7
3
+ size 5777
checkpoint-955/config.json ADDED
@@ -0,0 +1,36 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "BertForSequenceClassification"
4
+ ],
5
+ "attention_probs_dropout_prob": 0.1,
6
+ "classifier_dropout": null,
7
+ "dtype": "float32",
8
+ "gradient_checkpointing": false,
9
+ "hidden_act": "gelu",
10
+ "hidden_dropout_prob": 0.1,
11
+ "hidden_size": 768,
12
+ "id2label": {
13
+ "0": "0",
14
+ "1": "1",
15
+ "2": "2"
16
+ },
17
+ "initializer_range": 0.02,
18
+ "intermediate_size": 3072,
19
+ "label2id": {
20
+ "0": 0,
21
+ "1": 1,
22
+ "2": 2
23
+ },
24
+ "layer_norm_eps": 1e-12,
25
+ "max_position_embeddings": 512,
26
+ "model_type": "bert",
27
+ "num_attention_heads": 12,
28
+ "num_hidden_layers": 12,
29
+ "pad_token_id": 0,
30
+ "position_embedding_type": "absolute",
31
+ "problem_type": "single_label_classification",
32
+ "transformers_version": "4.56.2",
33
+ "type_vocab_size": 2,
34
+ "use_cache": true,
35
+ "vocab_size": 30522
36
+ }
checkpoint-955/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3e000c33120cd280fcc4f7e55c9f6bf574db1017543000a4e6da19d1217076ca
3
+ size 437961724
checkpoint-955/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:273616e2462791fa44c8d26d3d550989f6c1c6cc2d2a8c73e94b4d5359a98fb5
3
+ size 876047755
checkpoint-955/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:23d907c0d982c9afe54d273bb76b1491194c4fca21f39eb81a00db89b96f27fe
3
+ size 14645
checkpoint-955/scaler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e2b4c29ecef7f9afdf55766bdaf78baf6d63290e2d6b122c78763f06d1736966
3
+ size 1383
checkpoint-955/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e9dd8a8ac3aafa02255456e8add46863281e0d60f337aba1d1072a979df06244
3
+ size 1465
checkpoint-955/trainer_state.json ADDED
@@ -0,0 +1,310 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": 955,
3
+ "best_metric": 0.3973127603530884,
4
+ "best_model_checkpoint": "finbert_model/checkpoint-955",
5
+ "epoch": 1.0,
6
+ "eval_steps": 500,
7
+ "global_step": 955,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.02617801047120419,
14
+ "grad_norm": 5.389065742492676,
15
+ "learning_rate": 1.9832460732984295e-05,
16
+ "loss": 1.0684,
17
+ "step": 25
18
+ },
19
+ {
20
+ "epoch": 0.05235602094240838,
21
+ "grad_norm": 10.32921314239502,
22
+ "learning_rate": 1.9657940663176267e-05,
23
+ "loss": 0.7284,
24
+ "step": 50
25
+ },
26
+ {
27
+ "epoch": 0.07853403141361257,
28
+ "grad_norm": 6.734121322631836,
29
+ "learning_rate": 1.948342059336824e-05,
30
+ "loss": 0.7981,
31
+ "step": 75
32
+ },
33
+ {
34
+ "epoch": 0.10471204188481675,
35
+ "grad_norm": 8.204632759094238,
36
+ "learning_rate": 1.930890052356021e-05,
37
+ "loss": 0.5878,
38
+ "step": 100
39
+ },
40
+ {
41
+ "epoch": 0.13089005235602094,
42
+ "grad_norm": 10.211732864379883,
43
+ "learning_rate": 1.9134380453752185e-05,
44
+ "loss": 0.7182,
45
+ "step": 125
46
+ },
47
+ {
48
+ "epoch": 0.15706806282722513,
49
+ "grad_norm": 9.390113830566406,
50
+ "learning_rate": 1.8959860383944157e-05,
51
+ "loss": 0.72,
52
+ "step": 150
53
+ },
54
+ {
55
+ "epoch": 0.18324607329842932,
56
+ "grad_norm": 11.717000007629395,
57
+ "learning_rate": 1.8785340314136128e-05,
58
+ "loss": 0.6367,
59
+ "step": 175
60
+ },
61
+ {
62
+ "epoch": 0.2094240837696335,
63
+ "grad_norm": 8.935040473937988,
64
+ "learning_rate": 1.86108202443281e-05,
65
+ "loss": 0.6106,
66
+ "step": 200
67
+ },
68
+ {
69
+ "epoch": 0.2356020942408377,
70
+ "grad_norm": 11.59050464630127,
71
+ "learning_rate": 1.843630017452007e-05,
72
+ "loss": 0.6202,
73
+ "step": 225
74
+ },
75
+ {
76
+ "epoch": 0.2617801047120419,
77
+ "grad_norm": 7.747163772583008,
78
+ "learning_rate": 1.8261780104712043e-05,
79
+ "loss": 0.669,
80
+ "step": 250
81
+ },
82
+ {
83
+ "epoch": 0.2879581151832461,
84
+ "grad_norm": 16.7243595123291,
85
+ "learning_rate": 1.8087260034904015e-05,
86
+ "loss": 0.4931,
87
+ "step": 275
88
+ },
89
+ {
90
+ "epoch": 0.31413612565445026,
91
+ "grad_norm": 7.23421049118042,
92
+ "learning_rate": 1.7912739965095986e-05,
93
+ "loss": 0.5974,
94
+ "step": 300
95
+ },
96
+ {
97
+ "epoch": 0.3403141361256545,
98
+ "grad_norm": 6.768913269042969,
99
+ "learning_rate": 1.773821989528796e-05,
100
+ "loss": 0.4926,
101
+ "step": 325
102
+ },
103
+ {
104
+ "epoch": 0.36649214659685864,
105
+ "grad_norm": 3.186237096786499,
106
+ "learning_rate": 1.7563699825479933e-05,
107
+ "loss": 0.4709,
108
+ "step": 350
109
+ },
110
+ {
111
+ "epoch": 0.39267015706806285,
112
+ "grad_norm": 12.499926567077637,
113
+ "learning_rate": 1.7389179755671904e-05,
114
+ "loss": 0.5128,
115
+ "step": 375
116
+ },
117
+ {
118
+ "epoch": 0.418848167539267,
119
+ "grad_norm": 8.35361099243164,
120
+ "learning_rate": 1.7214659685863876e-05,
121
+ "loss": 0.5878,
122
+ "step": 400
123
+ },
124
+ {
125
+ "epoch": 0.44502617801047123,
126
+ "grad_norm": 6.956220626831055,
127
+ "learning_rate": 1.7040139616055848e-05,
128
+ "loss": 0.4794,
129
+ "step": 425
130
+ },
131
+ {
132
+ "epoch": 0.4712041884816754,
133
+ "grad_norm": 15.914446830749512,
134
+ "learning_rate": 1.686561954624782e-05,
135
+ "loss": 0.5827,
136
+ "step": 450
137
+ },
138
+ {
139
+ "epoch": 0.4973821989528796,
140
+ "grad_norm": 15.149320602416992,
141
+ "learning_rate": 1.669109947643979e-05,
142
+ "loss": 0.5467,
143
+ "step": 475
144
+ },
145
+ {
146
+ "epoch": 0.5235602094240838,
147
+ "grad_norm": 10.100659370422363,
148
+ "learning_rate": 1.6516579406631763e-05,
149
+ "loss": 0.525,
150
+ "step": 500
151
+ },
152
+ {
153
+ "epoch": 0.5497382198952879,
154
+ "grad_norm": 8.821247100830078,
155
+ "learning_rate": 1.6342059336823738e-05,
156
+ "loss": 0.5345,
157
+ "step": 525
158
+ },
159
+ {
160
+ "epoch": 0.5759162303664922,
161
+ "grad_norm": 14.301637649536133,
162
+ "learning_rate": 1.616753926701571e-05,
163
+ "loss": 0.5115,
164
+ "step": 550
165
+ },
166
+ {
167
+ "epoch": 0.6020942408376964,
168
+ "grad_norm": 14.779314994812012,
169
+ "learning_rate": 1.599301919720768e-05,
170
+ "loss": 0.5034,
171
+ "step": 575
172
+ },
173
+ {
174
+ "epoch": 0.6282722513089005,
175
+ "grad_norm": 9.956971168518066,
176
+ "learning_rate": 1.5818499127399652e-05,
177
+ "loss": 0.3719,
178
+ "step": 600
179
+ },
180
+ {
181
+ "epoch": 0.6544502617801047,
182
+ "grad_norm": 17.58684730529785,
183
+ "learning_rate": 1.5643979057591624e-05,
184
+ "loss": 0.5269,
185
+ "step": 625
186
+ },
187
+ {
188
+ "epoch": 0.680628272251309,
189
+ "grad_norm": 10.585662841796875,
190
+ "learning_rate": 1.5469458987783596e-05,
191
+ "loss": 0.574,
192
+ "step": 650
193
+ },
194
+ {
195
+ "epoch": 0.7068062827225131,
196
+ "grad_norm": 17.19683074951172,
197
+ "learning_rate": 1.5294938917975567e-05,
198
+ "loss": 0.4294,
199
+ "step": 675
200
+ },
201
+ {
202
+ "epoch": 0.7329842931937173,
203
+ "grad_norm": 14.906782150268555,
204
+ "learning_rate": 1.5120418848167539e-05,
205
+ "loss": 0.4861,
206
+ "step": 700
207
+ },
208
+ {
209
+ "epoch": 0.7591623036649214,
210
+ "grad_norm": 12.943304061889648,
211
+ "learning_rate": 1.4945898778359514e-05,
212
+ "loss": 0.4121,
213
+ "step": 725
214
+ },
215
+ {
216
+ "epoch": 0.7853403141361257,
217
+ "grad_norm": 0.5662004351615906,
218
+ "learning_rate": 1.4771378708551485e-05,
219
+ "loss": 0.5198,
220
+ "step": 750
221
+ },
222
+ {
223
+ "epoch": 0.8115183246073299,
224
+ "grad_norm": 7.927789211273193,
225
+ "learning_rate": 1.4596858638743457e-05,
226
+ "loss": 0.4721,
227
+ "step": 775
228
+ },
229
+ {
230
+ "epoch": 0.837696335078534,
231
+ "grad_norm": 6.3558855056762695,
232
+ "learning_rate": 1.4422338568935429e-05,
233
+ "loss": 0.3977,
234
+ "step": 800
235
+ },
236
+ {
237
+ "epoch": 0.8638743455497382,
238
+ "grad_norm": 17.170700073242188,
239
+ "learning_rate": 1.4247818499127402e-05,
240
+ "loss": 0.3493,
241
+ "step": 825
242
+ },
243
+ {
244
+ "epoch": 0.8900523560209425,
245
+ "grad_norm": 15.060056686401367,
246
+ "learning_rate": 1.4073298429319373e-05,
247
+ "loss": 0.5364,
248
+ "step": 850
249
+ },
250
+ {
251
+ "epoch": 0.9162303664921466,
252
+ "grad_norm": 11.084234237670898,
253
+ "learning_rate": 1.3898778359511345e-05,
254
+ "loss": 0.4815,
255
+ "step": 875
256
+ },
257
+ {
258
+ "epoch": 0.9424083769633508,
259
+ "grad_norm": 11.328404426574707,
260
+ "learning_rate": 1.3724258289703317e-05,
261
+ "loss": 0.5914,
262
+ "step": 900
263
+ },
264
+ {
265
+ "epoch": 0.9685863874345549,
266
+ "grad_norm": 14.335894584655762,
267
+ "learning_rate": 1.354973821989529e-05,
268
+ "loss": 0.4111,
269
+ "step": 925
270
+ },
271
+ {
272
+ "epoch": 0.9947643979057592,
273
+ "grad_norm": 11.200068473815918,
274
+ "learning_rate": 1.3375218150087262e-05,
275
+ "loss": 0.4069,
276
+ "step": 950
277
+ },
278
+ {
279
+ "epoch": 1.0,
280
+ "eval_accuracy": 0.8690413829229964,
281
+ "eval_f1": 0.8665004404377881,
282
+ "eval_loss": 0.3973127603530884,
283
+ "eval_runtime": 4.1083,
284
+ "eval_samples_per_second": 464.669,
285
+ "eval_steps_per_second": 58.175,
286
+ "step": 955
287
+ }
288
+ ],
289
+ "logging_steps": 25,
290
+ "max_steps": 2865,
291
+ "num_input_tokens_seen": 0,
292
+ "num_train_epochs": 3,
293
+ "save_steps": 500,
294
+ "stateful_callbacks": {
295
+ "TrainerControl": {
296
+ "args": {
297
+ "should_epoch_stop": false,
298
+ "should_evaluate": false,
299
+ "should_log": false,
300
+ "should_save": true,
301
+ "should_training_stop": false
302
+ },
303
+ "attributes": {}
304
+ }
305
+ },
306
+ "total_flos": 502151957733888.0,
307
+ "train_batch_size": 8,
308
+ "trial_name": null,
309
+ "trial_params": null
310
+ }
checkpoint-955/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2d620eee01b27533e078e3386e9efbb932822d44a3acdd2ecc263ee6ced295d7
3
+ size 5777
config.json ADDED
@@ -0,0 +1,36 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "BertForSequenceClassification"
4
+ ],
5
+ "attention_probs_dropout_prob": 0.1,
6
+ "classifier_dropout": null,
7
+ "dtype": "float32",
8
+ "gradient_checkpointing": false,
9
+ "hidden_act": "gelu",
10
+ "hidden_dropout_prob": 0.1,
11
+ "hidden_size": 768,
12
+ "id2label": {
13
+ "0": "0",
14
+ "1": "1",
15
+ "2": "2"
16
+ },
17
+ "initializer_range": 0.02,
18
+ "intermediate_size": 3072,
19
+ "label2id": {
20
+ "0": 0,
21
+ "1": 1,
22
+ "2": 2
23
+ },
24
+ "layer_norm_eps": 1e-12,
25
+ "max_position_embeddings": 512,
26
+ "model_type": "bert",
27
+ "num_attention_heads": 12,
28
+ "num_hidden_layers": 12,
29
+ "pad_token_id": 0,
30
+ "position_embedding_type": "absolute",
31
+ "problem_type": "single_label_classification",
32
+ "transformers_version": "4.56.2",
33
+ "type_vocab_size": 2,
34
+ "use_cache": true,
35
+ "vocab_size": 30522
36
+ }
label_encoder.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6613233d2442a0938635221fec29c91fcf4024f791c79465777286a70349ec97
3
+ size 351
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3e000c33120cd280fcc4f7e55c9f6bf574db1017543000a4e6da19d1217076ca
3
+ size 437961724
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 +1,58 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "100": {
12
+ "content": "[UNK]",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "101": {
20
+ "content": "[CLS]",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "102": {
28
+ "content": "[SEP]",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "103": {
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": true,
48
+ "extra_special_tokens": {},
49
+ "mask_token": "[MASK]",
50
+ "model_max_length": 512,
51
+ "never_split": null,
52
+ "pad_token": "[PAD]",
53
+ "sep_token": "[SEP]",
54
+ "strip_accents": null,
55
+ "tokenize_chinese_chars": true,
56
+ "tokenizer_class": "BertTokenizer",
57
+ "unk_token": "[UNK]"
58
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2d620eee01b27533e078e3386e9efbb932822d44a3acdd2ecc263ee6ced295d7
3
+ size 5777
vocab.txt ADDED
The diff for this file is too large to render. See raw diff