ankitbelbase034 commited on
Commit
2370203
·
verified ·
1 Parent(s): d8d4f9c

Upload folder using huggingface_hub

Browse files
checkpoint-625/config.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_cross_attention": false,
3
+ "architectures": [
4
+ "BertForSequenceClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "bos_token_id": null,
8
+ "classifier_dropout": null,
9
+ "dtype": "float32",
10
+ "eos_token_id": null,
11
+ "gradient_checkpointing": false,
12
+ "hidden_act": "gelu",
13
+ "hidden_dropout_prob": 0.1,
14
+ "hidden_size": 768,
15
+ "initializer_range": 0.02,
16
+ "intermediate_size": 3072,
17
+ "is_decoder": false,
18
+ "layer_norm_eps": 1e-12,
19
+ "max_position_embeddings": 512,
20
+ "model_type": "bert",
21
+ "num_attention_heads": 12,
22
+ "num_hidden_layers": 12,
23
+ "pad_token_id": 0,
24
+ "position_embedding_type": "absolute",
25
+ "problem_type": "single_label_classification",
26
+ "tie_word_embeddings": true,
27
+ "transformers_version": "5.0.0",
28
+ "type_vocab_size": 2,
29
+ "use_cache": false,
30
+ "vocab_size": 30522
31
+ }
checkpoint-625/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2a357976f6be0dcc683d9b90452f390057f919f2a7041c341046652c3a23a286
3
+ size 437958624
checkpoint-625/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:762ef7be545ca9ca8a3b0efb2d62cc5a20b0e5b54f75041019db8ace7eb4aae6
3
+ size 876041611
checkpoint-625/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d9812ada739fe5770e4c4c8ed2d5a8f15272d38994bbe6c046c8a431de43852e
3
+ size 14645
checkpoint-625/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:41d1fe61652a1ca69232a447f6b0e2913720293eee777e7bd1629b5376dca0c3
3
+ size 1465
checkpoint-625/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-625/tokenizer_config.json ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "backend": "tokenizers",
3
+ "cls_token": "[CLS]",
4
+ "do_lower_case": true,
5
+ "is_local": false,
6
+ "mask_token": "[MASK]",
7
+ "model_max_length": 512,
8
+ "pad_token": "[PAD]",
9
+ "sep_token": "[SEP]",
10
+ "strip_accents": null,
11
+ "tokenize_chinese_chars": true,
12
+ "tokenizer_class": "BertTokenizer",
13
+ "unk_token": "[UNK]"
14
+ }
checkpoint-625/trainer_state.json ADDED
@@ -0,0 +1,476 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": 625,
3
+ "best_metric": 0.18495811522006989,
4
+ "best_model_checkpoint": "./results/checkpoint-625",
5
+ "epoch": 1.0,
6
+ "eval_steps": 500,
7
+ "global_step": 625,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.016,
14
+ "grad_norm": 19.218093872070312,
15
+ "learning_rate": 4.9640000000000006e-05,
16
+ "loss": 0.09028505682945251,
17
+ "step": 10
18
+ },
19
+ {
20
+ "epoch": 0.032,
21
+ "grad_norm": 1.0261529684066772,
22
+ "learning_rate": 4.924e-05,
23
+ "loss": 0.15324625968933106,
24
+ "step": 20
25
+ },
26
+ {
27
+ "epoch": 0.048,
28
+ "grad_norm": 21.003023147583008,
29
+ "learning_rate": 4.884e-05,
30
+ "loss": 0.22774670124053956,
31
+ "step": 30
32
+ },
33
+ {
34
+ "epoch": 0.064,
35
+ "grad_norm": 7.388162612915039,
36
+ "learning_rate": 4.8440000000000004e-05,
37
+ "loss": 0.4121945858001709,
38
+ "step": 40
39
+ },
40
+ {
41
+ "epoch": 0.08,
42
+ "grad_norm": 4.979572296142578,
43
+ "learning_rate": 4.804e-05,
44
+ "loss": 0.38861570358276365,
45
+ "step": 50
46
+ },
47
+ {
48
+ "epoch": 0.096,
49
+ "grad_norm": 5.862935543060303,
50
+ "learning_rate": 4.7640000000000005e-05,
51
+ "loss": 0.29872808456420896,
52
+ "step": 60
53
+ },
54
+ {
55
+ "epoch": 0.112,
56
+ "grad_norm": 8.852452278137207,
57
+ "learning_rate": 4.724e-05,
58
+ "loss": 0.3256639242172241,
59
+ "step": 70
60
+ },
61
+ {
62
+ "epoch": 0.128,
63
+ "grad_norm": 3.3186402320861816,
64
+ "learning_rate": 4.684e-05,
65
+ "loss": 0.3397534847259521,
66
+ "step": 80
67
+ },
68
+ {
69
+ "epoch": 0.144,
70
+ "grad_norm": 5.926950931549072,
71
+ "learning_rate": 4.644e-05,
72
+ "loss": 0.19672555923461915,
73
+ "step": 90
74
+ },
75
+ {
76
+ "epoch": 0.16,
77
+ "grad_norm": 9.196661949157715,
78
+ "learning_rate": 4.604e-05,
79
+ "loss": 0.2907862663269043,
80
+ "step": 100
81
+ },
82
+ {
83
+ "epoch": 0.176,
84
+ "grad_norm": 5.412224292755127,
85
+ "learning_rate": 4.564e-05,
86
+ "loss": 0.2230736255645752,
87
+ "step": 110
88
+ },
89
+ {
90
+ "epoch": 0.192,
91
+ "grad_norm": 2.8200976848602295,
92
+ "learning_rate": 4.524000000000001e-05,
93
+ "loss": 0.3943183422088623,
94
+ "step": 120
95
+ },
96
+ {
97
+ "epoch": 0.208,
98
+ "grad_norm": 11.510780334472656,
99
+ "learning_rate": 4.4840000000000004e-05,
100
+ "loss": 0.28646397590637207,
101
+ "step": 130
102
+ },
103
+ {
104
+ "epoch": 0.224,
105
+ "grad_norm": 3.909830093383789,
106
+ "learning_rate": 4.444e-05,
107
+ "loss": 0.346493124961853,
108
+ "step": 140
109
+ },
110
+ {
111
+ "epoch": 0.24,
112
+ "grad_norm": 3.446835517883301,
113
+ "learning_rate": 4.4040000000000005e-05,
114
+ "loss": 0.2555964946746826,
115
+ "step": 150
116
+ },
117
+ {
118
+ "epoch": 0.256,
119
+ "grad_norm": 8.182538032531738,
120
+ "learning_rate": 4.364e-05,
121
+ "loss": 0.24913170337677001,
122
+ "step": 160
123
+ },
124
+ {
125
+ "epoch": 0.272,
126
+ "grad_norm": 4.328517913818359,
127
+ "learning_rate": 4.324e-05,
128
+ "loss": 0.3257677316665649,
129
+ "step": 170
130
+ },
131
+ {
132
+ "epoch": 0.288,
133
+ "grad_norm": 4.964771270751953,
134
+ "learning_rate": 4.284e-05,
135
+ "loss": 0.28899221420288085,
136
+ "step": 180
137
+ },
138
+ {
139
+ "epoch": 0.304,
140
+ "grad_norm": 9.758742332458496,
141
+ "learning_rate": 4.244e-05,
142
+ "loss": 0.2279355764389038,
143
+ "step": 190
144
+ },
145
+ {
146
+ "epoch": 0.32,
147
+ "grad_norm": 4.366827964782715,
148
+ "learning_rate": 4.2040000000000004e-05,
149
+ "loss": 0.31453232765197753,
150
+ "step": 200
151
+ },
152
+ {
153
+ "epoch": 0.336,
154
+ "grad_norm": 2.277212381362915,
155
+ "learning_rate": 4.164e-05,
156
+ "loss": 0.20993876457214355,
157
+ "step": 210
158
+ },
159
+ {
160
+ "epoch": 0.352,
161
+ "grad_norm": 4.816099166870117,
162
+ "learning_rate": 4.124e-05,
163
+ "loss": 0.27517788410186766,
164
+ "step": 220
165
+ },
166
+ {
167
+ "epoch": 0.368,
168
+ "grad_norm": 3.51198673248291,
169
+ "learning_rate": 4.084e-05,
170
+ "loss": 0.22087533473968507,
171
+ "step": 230
172
+ },
173
+ {
174
+ "epoch": 0.384,
175
+ "grad_norm": 5.840693950653076,
176
+ "learning_rate": 4.044e-05,
177
+ "loss": 0.20846953392028808,
178
+ "step": 240
179
+ },
180
+ {
181
+ "epoch": 0.4,
182
+ "grad_norm": 3.9098050594329834,
183
+ "learning_rate": 4.004e-05,
184
+ "loss": 0.26031317710876467,
185
+ "step": 250
186
+ },
187
+ {
188
+ "epoch": 0.416,
189
+ "grad_norm": 3.918344020843506,
190
+ "learning_rate": 3.964e-05,
191
+ "loss": 0.2516783714294434,
192
+ "step": 260
193
+ },
194
+ {
195
+ "epoch": 0.432,
196
+ "grad_norm": 8.892339706420898,
197
+ "learning_rate": 3.9240000000000004e-05,
198
+ "loss": 0.2795307159423828,
199
+ "step": 270
200
+ },
201
+ {
202
+ "epoch": 0.448,
203
+ "grad_norm": 4.103593826293945,
204
+ "learning_rate": 3.884e-05,
205
+ "loss": 0.23137011528015136,
206
+ "step": 280
207
+ },
208
+ {
209
+ "epoch": 0.464,
210
+ "grad_norm": 6.328890800476074,
211
+ "learning_rate": 3.8440000000000005e-05,
212
+ "loss": 0.22461700439453125,
213
+ "step": 290
214
+ },
215
+ {
216
+ "epoch": 0.48,
217
+ "grad_norm": 6.5414719581604,
218
+ "learning_rate": 3.804e-05,
219
+ "loss": 0.21610186100006104,
220
+ "step": 300
221
+ },
222
+ {
223
+ "epoch": 0.496,
224
+ "grad_norm": 3.691993474960327,
225
+ "learning_rate": 3.7640000000000006e-05,
226
+ "loss": 0.24925684928894043,
227
+ "step": 310
228
+ },
229
+ {
230
+ "epoch": 0.512,
231
+ "grad_norm": 4.344432353973389,
232
+ "learning_rate": 3.724e-05,
233
+ "loss": 0.21005148887634278,
234
+ "step": 320
235
+ },
236
+ {
237
+ "epoch": 0.528,
238
+ "grad_norm": 7.790218353271484,
239
+ "learning_rate": 3.684e-05,
240
+ "loss": 0.17650561332702636,
241
+ "step": 330
242
+ },
243
+ {
244
+ "epoch": 0.544,
245
+ "grad_norm": 7.356423854827881,
246
+ "learning_rate": 3.6440000000000003e-05,
247
+ "loss": 0.2985139131546021,
248
+ "step": 340
249
+ },
250
+ {
251
+ "epoch": 0.56,
252
+ "grad_norm": 2.8463327884674072,
253
+ "learning_rate": 3.604e-05,
254
+ "loss": 0.20631999969482423,
255
+ "step": 350
256
+ },
257
+ {
258
+ "epoch": 0.576,
259
+ "grad_norm": 7.239101409912109,
260
+ "learning_rate": 3.5640000000000004e-05,
261
+ "loss": 0.2260190486907959,
262
+ "step": 360
263
+ },
264
+ {
265
+ "epoch": 0.592,
266
+ "grad_norm": 6.864079475402832,
267
+ "learning_rate": 3.524e-05,
268
+ "loss": 0.29787819385528563,
269
+ "step": 370
270
+ },
271
+ {
272
+ "epoch": 0.608,
273
+ "grad_norm": 4.634511947631836,
274
+ "learning_rate": 3.484e-05,
275
+ "loss": 0.2093559741973877,
276
+ "step": 380
277
+ },
278
+ {
279
+ "epoch": 0.624,
280
+ "grad_norm": 8.057502746582031,
281
+ "learning_rate": 3.444e-05,
282
+ "loss": 0.23704848289489747,
283
+ "step": 390
284
+ },
285
+ {
286
+ "epoch": 0.64,
287
+ "grad_norm": 2.670377731323242,
288
+ "learning_rate": 3.404e-05,
289
+ "loss": 0.20256345272064208,
290
+ "step": 400
291
+ },
292
+ {
293
+ "epoch": 0.656,
294
+ "grad_norm": 5.436578273773193,
295
+ "learning_rate": 3.3639999999999996e-05,
296
+ "loss": 0.2178948402404785,
297
+ "step": 410
298
+ },
299
+ {
300
+ "epoch": 0.672,
301
+ "grad_norm": 2.7397665977478027,
302
+ "learning_rate": 3.324e-05,
303
+ "loss": 0.28787732124328613,
304
+ "step": 420
305
+ },
306
+ {
307
+ "epoch": 0.688,
308
+ "grad_norm": 7.691206455230713,
309
+ "learning_rate": 3.2840000000000004e-05,
310
+ "loss": 0.2569857358932495,
311
+ "step": 430
312
+ },
313
+ {
314
+ "epoch": 0.704,
315
+ "grad_norm": 2.859588623046875,
316
+ "learning_rate": 3.244e-05,
317
+ "loss": 0.21177470684051514,
318
+ "step": 440
319
+ },
320
+ {
321
+ "epoch": 0.72,
322
+ "grad_norm": 8.864638328552246,
323
+ "learning_rate": 3.2040000000000005e-05,
324
+ "loss": 0.21835825443267823,
325
+ "step": 450
326
+ },
327
+ {
328
+ "epoch": 0.736,
329
+ "grad_norm": 3.5713469982147217,
330
+ "learning_rate": 3.164e-05,
331
+ "loss": 0.18327864408493041,
332
+ "step": 460
333
+ },
334
+ {
335
+ "epoch": 0.752,
336
+ "grad_norm": 4.1505351066589355,
337
+ "learning_rate": 3.1240000000000006e-05,
338
+ "loss": 0.23397378921508788,
339
+ "step": 470
340
+ },
341
+ {
342
+ "epoch": 0.768,
343
+ "grad_norm": 7.102250099182129,
344
+ "learning_rate": 3.084e-05,
345
+ "loss": 0.2387765645980835,
346
+ "step": 480
347
+ },
348
+ {
349
+ "epoch": 0.784,
350
+ "grad_norm": 2.268003225326538,
351
+ "learning_rate": 3.0440000000000003e-05,
352
+ "loss": 0.24410586357116698,
353
+ "step": 490
354
+ },
355
+ {
356
+ "epoch": 0.8,
357
+ "grad_norm": 7.200525760650635,
358
+ "learning_rate": 3.004e-05,
359
+ "loss": 0.22940239906311036,
360
+ "step": 500
361
+ },
362
+ {
363
+ "epoch": 0.816,
364
+ "grad_norm": 6.109457015991211,
365
+ "learning_rate": 2.964e-05,
366
+ "loss": 0.23941683769226074,
367
+ "step": 510
368
+ },
369
+ {
370
+ "epoch": 0.832,
371
+ "grad_norm": 2.041025400161743,
372
+ "learning_rate": 2.924e-05,
373
+ "loss": 0.2272693157196045,
374
+ "step": 520
375
+ },
376
+ {
377
+ "epoch": 0.848,
378
+ "grad_norm": 3.117744207382202,
379
+ "learning_rate": 2.8840000000000002e-05,
380
+ "loss": 0.3034891843795776,
381
+ "step": 530
382
+ },
383
+ {
384
+ "epoch": 0.864,
385
+ "grad_norm": 3.5636343955993652,
386
+ "learning_rate": 2.844e-05,
387
+ "loss": 0.22543411254882811,
388
+ "step": 540
389
+ },
390
+ {
391
+ "epoch": 0.88,
392
+ "grad_norm": 5.813530921936035,
393
+ "learning_rate": 2.804e-05,
394
+ "loss": 0.15515211820602418,
395
+ "step": 550
396
+ },
397
+ {
398
+ "epoch": 0.896,
399
+ "grad_norm": 3.961332082748413,
400
+ "learning_rate": 2.764e-05,
401
+ "loss": 0.18014708757400513,
402
+ "step": 560
403
+ },
404
+ {
405
+ "epoch": 0.912,
406
+ "grad_norm": 4.513957500457764,
407
+ "learning_rate": 2.724e-05,
408
+ "loss": 0.15350849628448487,
409
+ "step": 570
410
+ },
411
+ {
412
+ "epoch": 0.928,
413
+ "grad_norm": 4.664239406585693,
414
+ "learning_rate": 2.6840000000000004e-05,
415
+ "loss": 0.17080495357513428,
416
+ "step": 580
417
+ },
418
+ {
419
+ "epoch": 0.944,
420
+ "grad_norm": 4.640005588531494,
421
+ "learning_rate": 2.6440000000000004e-05,
422
+ "loss": 0.2014240026473999,
423
+ "step": 590
424
+ },
425
+ {
426
+ "epoch": 0.96,
427
+ "grad_norm": 4.601800441741943,
428
+ "learning_rate": 2.6040000000000005e-05,
429
+ "loss": 0.14860270023345948,
430
+ "step": 600
431
+ },
432
+ {
433
+ "epoch": 0.976,
434
+ "grad_norm": 3.3365046977996826,
435
+ "learning_rate": 2.5640000000000002e-05,
436
+ "loss": 0.16999433040618897,
437
+ "step": 610
438
+ },
439
+ {
440
+ "epoch": 0.992,
441
+ "grad_norm": 11.081926345825195,
442
+ "learning_rate": 2.5240000000000002e-05,
443
+ "loss": 0.2594302177429199,
444
+ "step": 620
445
+ },
446
+ {
447
+ "epoch": 1.0,
448
+ "eval_loss": 0.18495811522006989,
449
+ "eval_runtime": 154.2281,
450
+ "eval_samples_per_second": 32.42,
451
+ "eval_steps_per_second": 1.018,
452
+ "step": 625
453
+ }
454
+ ],
455
+ "logging_steps": 10,
456
+ "max_steps": 1250,
457
+ "num_input_tokens_seen": 0,
458
+ "num_train_epochs": 2,
459
+ "save_steps": 500,
460
+ "stateful_callbacks": {
461
+ "TrainerControl": {
462
+ "args": {
463
+ "should_epoch_stop": false,
464
+ "should_evaluate": false,
465
+ "should_log": false,
466
+ "should_save": true,
467
+ "should_training_stop": false
468
+ },
469
+ "attributes": {}
470
+ }
471
+ },
472
+ "total_flos": 5262221107200000.0,
473
+ "train_batch_size": 32,
474
+ "trial_name": null,
475
+ "trial_params": null
476
+ }
checkpoint-625/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4a1c344e29edd7edf7d1a6b8ac205353a4129831994c51891c82a541b7d2dc8d
3
+ size 5201