anoaky commited on
Commit
f640d27
·
verified ·
1 Parent(s): 19f7260

Training in progress, epoch 1, checkpoint

Browse files
checkpoint-555/config.json ADDED
@@ -0,0 +1,26 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "bert-base-uncased",
3
+ "architectures": [
4
+ "BertForSequenceClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "classifier_dropout": null,
8
+ "gradient_checkpointing": false,
9
+ "hidden_act": "gelu",
10
+ "hidden_dropout_prob": 0.1,
11
+ "hidden_size": 768,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 3072,
14
+ "layer_norm_eps": 1e-12,
15
+ "max_position_embeddings": 512,
16
+ "model_type": "bert",
17
+ "num_attention_heads": 12,
18
+ "num_hidden_layers": 12,
19
+ "pad_token_id": 0,
20
+ "position_embedding_type": "absolute",
21
+ "torch_dtype": "float32",
22
+ "transformers_version": "4.47.0",
23
+ "type_vocab_size": 2,
24
+ "use_cache": true,
25
+ "vocab_size": 30522
26
+ }
checkpoint-555/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cf60d2f658351ec678f15a2b665ef64085fd8bfc89f669cd514c38acfa2a2a01
3
+ size 437958648
checkpoint-555/trainer_state.json ADDED
@@ -0,0 +1,440 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 1.0,
5
+ "eval_steps": 500,
6
+ "global_step": 555,
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,
13
+ "eval_f1": 0.6562770562770562,
14
+ "eval_loss": 0.7476533651351929,
15
+ "eval_precision": 0.48976954555244456,
16
+ "eval_recall": 0.9943156974202011,
17
+ "eval_runtime": 16.4688,
18
+ "eval_samples_per_second": 283.749,
19
+ "eval_steps_per_second": 35.522,
20
+ "step": 0
21
+ },
22
+ {
23
+ "epoch": 0.018026137899954935,
24
+ "grad_norm": 14.20566463470459,
25
+ "learning_rate": 4.981949458483755e-05,
26
+ "loss": 0.6876,
27
+ "step": 10
28
+ },
29
+ {
30
+ "epoch": 0.03605227579990987,
31
+ "grad_norm": 27.79998016357422,
32
+ "learning_rate": 4.963898916967509e-05,
33
+ "loss": 0.5988,
34
+ "step": 20
35
+ },
36
+ {
37
+ "epoch": 0.054078413699864804,
38
+ "grad_norm": 39.63682556152344,
39
+ "learning_rate": 4.945848375451264e-05,
40
+ "loss": 0.5677,
41
+ "step": 30
42
+ },
43
+ {
44
+ "epoch": 0.07210455159981974,
45
+ "grad_norm": 38.49867630004883,
46
+ "learning_rate": 4.927797833935018e-05,
47
+ "loss": 0.5922,
48
+ "step": 40
49
+ },
50
+ {
51
+ "epoch": 0.09013068949977468,
52
+ "grad_norm": 52.28614044189453,
53
+ "learning_rate": 4.909747292418773e-05,
54
+ "loss": 0.5506,
55
+ "step": 50
56
+ },
57
+ {
58
+ "epoch": 0.10815682739972961,
59
+ "grad_norm": 29.180490493774414,
60
+ "learning_rate": 4.891696750902527e-05,
61
+ "loss": 0.5173,
62
+ "step": 60
63
+ },
64
+ {
65
+ "epoch": 0.12618296529968454,
66
+ "grad_norm": 33.55237579345703,
67
+ "learning_rate": 4.873646209386282e-05,
68
+ "loss": 0.4931,
69
+ "step": 70
70
+ },
71
+ {
72
+ "epoch": 0.14420910319963948,
73
+ "grad_norm": 32.063228607177734,
74
+ "learning_rate": 4.855595667870036e-05,
75
+ "loss": 0.483,
76
+ "step": 80
77
+ },
78
+ {
79
+ "epoch": 0.16223524109959442,
80
+ "grad_norm": 24.234926223754883,
81
+ "learning_rate": 4.837545126353791e-05,
82
+ "loss": 0.47,
83
+ "step": 90
84
+ },
85
+ {
86
+ "epoch": 0.18026137899954936,
87
+ "grad_norm": 33.66775894165039,
88
+ "learning_rate": 4.819494584837546e-05,
89
+ "loss": 0.4564,
90
+ "step": 100
91
+ },
92
+ {
93
+ "epoch": 0.19828751689950427,
94
+ "grad_norm": 53.322574615478516,
95
+ "learning_rate": 4.8014440433213e-05,
96
+ "loss": 0.5083,
97
+ "step": 110
98
+ },
99
+ {
100
+ "epoch": 0.21631365479945922,
101
+ "grad_norm": 29.443470001220703,
102
+ "learning_rate": 4.783393501805055e-05,
103
+ "loss": 0.463,
104
+ "step": 120
105
+ },
106
+ {
107
+ "epoch": 0.23433979269941416,
108
+ "grad_norm": 33.13877487182617,
109
+ "learning_rate": 4.765342960288809e-05,
110
+ "loss": 0.4626,
111
+ "step": 130
112
+ },
113
+ {
114
+ "epoch": 0.25236593059936907,
115
+ "grad_norm": 25.509536743164062,
116
+ "learning_rate": 4.747292418772563e-05,
117
+ "loss": 0.5113,
118
+ "step": 140
119
+ },
120
+ {
121
+ "epoch": 0.270392068499324,
122
+ "grad_norm": 21.015031814575195,
123
+ "learning_rate": 4.7292418772563177e-05,
124
+ "loss": 0.4611,
125
+ "step": 150
126
+ },
127
+ {
128
+ "epoch": 0.28841820639927895,
129
+ "grad_norm": 28.079387664794922,
130
+ "learning_rate": 4.711191335740072e-05,
131
+ "loss": 0.4783,
132
+ "step": 160
133
+ },
134
+ {
135
+ "epoch": 0.3064443442992339,
136
+ "grad_norm": 19.978599548339844,
137
+ "learning_rate": 4.693140794223827e-05,
138
+ "loss": 0.5026,
139
+ "step": 170
140
+ },
141
+ {
142
+ "epoch": 0.32447048219918884,
143
+ "grad_norm": 29.316265106201172,
144
+ "learning_rate": 4.675090252707581e-05,
145
+ "loss": 0.4906,
146
+ "step": 180
147
+ },
148
+ {
149
+ "epoch": 0.3424966200991438,
150
+ "grad_norm": 18.79282569885254,
151
+ "learning_rate": 4.657039711191336e-05,
152
+ "loss": 0.5016,
153
+ "step": 190
154
+ },
155
+ {
156
+ "epoch": 0.3605227579990987,
157
+ "grad_norm": 18.66801643371582,
158
+ "learning_rate": 4.63898916967509e-05,
159
+ "loss": 0.4502,
160
+ "step": 200
161
+ },
162
+ {
163
+ "epoch": 0.3785488958990536,
164
+ "grad_norm": 27.929332733154297,
165
+ "learning_rate": 4.620938628158845e-05,
166
+ "loss": 0.4302,
167
+ "step": 210
168
+ },
169
+ {
170
+ "epoch": 0.39657503379900855,
171
+ "grad_norm": 20.541879653930664,
172
+ "learning_rate": 4.602888086642599e-05,
173
+ "loss": 0.4496,
174
+ "step": 220
175
+ },
176
+ {
177
+ "epoch": 0.4146011716989635,
178
+ "grad_norm": 19.034873962402344,
179
+ "learning_rate": 4.584837545126354e-05,
180
+ "loss": 0.4541,
181
+ "step": 230
182
+ },
183
+ {
184
+ "epoch": 0.43262730959891843,
185
+ "grad_norm": 32.077945709228516,
186
+ "learning_rate": 4.566787003610109e-05,
187
+ "loss": 0.4562,
188
+ "step": 240
189
+ },
190
+ {
191
+ "epoch": 0.45065344749887337,
192
+ "grad_norm": 25.475997924804688,
193
+ "learning_rate": 4.548736462093863e-05,
194
+ "loss": 0.4456,
195
+ "step": 250
196
+ },
197
+ {
198
+ "epoch": 0.4686795853988283,
199
+ "grad_norm": 17.132720947265625,
200
+ "learning_rate": 4.530685920577618e-05,
201
+ "loss": 0.4629,
202
+ "step": 260
203
+ },
204
+ {
205
+ "epoch": 0.48670572329878325,
206
+ "grad_norm": 22.313941955566406,
207
+ "learning_rate": 4.5126353790613716e-05,
208
+ "loss": 0.4444,
209
+ "step": 270
210
+ },
211
+ {
212
+ "epoch": 0.5047318611987381,
213
+ "grad_norm": 22.373477935791016,
214
+ "learning_rate": 4.494584837545127e-05,
215
+ "loss": 0.4404,
216
+ "step": 280
217
+ },
218
+ {
219
+ "epoch": 0.5227579990986931,
220
+ "grad_norm": 16.72430992126465,
221
+ "learning_rate": 4.4765342960288806e-05,
222
+ "loss": 0.4611,
223
+ "step": 290
224
+ },
225
+ {
226
+ "epoch": 0.540784136998648,
227
+ "grad_norm": 27.037927627563477,
228
+ "learning_rate": 4.458483754512636e-05,
229
+ "loss": 0.4272,
230
+ "step": 300
231
+ },
232
+ {
233
+ "epoch": 0.558810274898603,
234
+ "grad_norm": 31.637985229492188,
235
+ "learning_rate": 4.44043321299639e-05,
236
+ "loss": 0.448,
237
+ "step": 310
238
+ },
239
+ {
240
+ "epoch": 0.5768364127985579,
241
+ "grad_norm": 35.010459899902344,
242
+ "learning_rate": 4.422382671480145e-05,
243
+ "loss": 0.4215,
244
+ "step": 320
245
+ },
246
+ {
247
+ "epoch": 0.5948625506985128,
248
+ "grad_norm": 26.25156021118164,
249
+ "learning_rate": 4.404332129963899e-05,
250
+ "loss": 0.4396,
251
+ "step": 330
252
+ },
253
+ {
254
+ "epoch": 0.6128886885984678,
255
+ "grad_norm": 19.4619083404541,
256
+ "learning_rate": 4.386281588447654e-05,
257
+ "loss": 0.4378,
258
+ "step": 340
259
+ },
260
+ {
261
+ "epoch": 0.6309148264984227,
262
+ "grad_norm": 19.16460609436035,
263
+ "learning_rate": 4.368231046931408e-05,
264
+ "loss": 0.4366,
265
+ "step": 350
266
+ },
267
+ {
268
+ "epoch": 0.6489409643983777,
269
+ "grad_norm": 30.745384216308594,
270
+ "learning_rate": 4.350180505415163e-05,
271
+ "loss": 0.4062,
272
+ "step": 360
273
+ },
274
+ {
275
+ "epoch": 0.6669671022983326,
276
+ "grad_norm": 16.873245239257812,
277
+ "learning_rate": 4.332129963898917e-05,
278
+ "loss": 0.439,
279
+ "step": 370
280
+ },
281
+ {
282
+ "epoch": 0.6849932401982876,
283
+ "grad_norm": 25.771486282348633,
284
+ "learning_rate": 4.314079422382672e-05,
285
+ "loss": 0.4053,
286
+ "step": 380
287
+ },
288
+ {
289
+ "epoch": 0.7030193780982424,
290
+ "grad_norm": 14.48513412475586,
291
+ "learning_rate": 4.296028880866426e-05,
292
+ "loss": 0.4164,
293
+ "step": 390
294
+ },
295
+ {
296
+ "epoch": 0.7210455159981974,
297
+ "grad_norm": 34.993465423583984,
298
+ "learning_rate": 4.277978339350181e-05,
299
+ "loss": 0.4438,
300
+ "step": 400
301
+ },
302
+ {
303
+ "epoch": 0.7390716538981523,
304
+ "grad_norm": 22.576608657836914,
305
+ "learning_rate": 4.259927797833935e-05,
306
+ "loss": 0.4518,
307
+ "step": 410
308
+ },
309
+ {
310
+ "epoch": 0.7570977917981072,
311
+ "grad_norm": 19.088132858276367,
312
+ "learning_rate": 4.24187725631769e-05,
313
+ "loss": 0.4495,
314
+ "step": 420
315
+ },
316
+ {
317
+ "epoch": 0.7751239296980622,
318
+ "grad_norm": 35.2998046875,
319
+ "learning_rate": 4.223826714801444e-05,
320
+ "loss": 0.3897,
321
+ "step": 430
322
+ },
323
+ {
324
+ "epoch": 0.7931500675980171,
325
+ "grad_norm": 20.395572662353516,
326
+ "learning_rate": 4.205776173285199e-05,
327
+ "loss": 0.4818,
328
+ "step": 440
329
+ },
330
+ {
331
+ "epoch": 0.8111762054979721,
332
+ "grad_norm": 21.174386978149414,
333
+ "learning_rate": 4.187725631768953e-05,
334
+ "loss": 0.4103,
335
+ "step": 450
336
+ },
337
+ {
338
+ "epoch": 0.829202343397927,
339
+ "grad_norm": 32.97265625,
340
+ "learning_rate": 4.169675090252708e-05,
341
+ "loss": 0.4036,
342
+ "step": 460
343
+ },
344
+ {
345
+ "epoch": 0.847228481297882,
346
+ "grad_norm": 23.78690528869629,
347
+ "learning_rate": 4.151624548736462e-05,
348
+ "loss": 0.4079,
349
+ "step": 470
350
+ },
351
+ {
352
+ "epoch": 0.8652546191978369,
353
+ "grad_norm": 17.087247848510742,
354
+ "learning_rate": 4.1335740072202167e-05,
355
+ "loss": 0.4371,
356
+ "step": 480
357
+ },
358
+ {
359
+ "epoch": 0.8832807570977917,
360
+ "grad_norm": 13.810160636901855,
361
+ "learning_rate": 4.115523465703972e-05,
362
+ "loss": 0.4249,
363
+ "step": 490
364
+ },
365
+ {
366
+ "epoch": 0.9013068949977467,
367
+ "grad_norm": 20.197996139526367,
368
+ "learning_rate": 4.0974729241877256e-05,
369
+ "loss": 0.3991,
370
+ "step": 500
371
+ },
372
+ {
373
+ "epoch": 0.9193330328977016,
374
+ "grad_norm": 33.1153564453125,
375
+ "learning_rate": 4.079422382671481e-05,
376
+ "loss": 0.3994,
377
+ "step": 510
378
+ },
379
+ {
380
+ "epoch": 0.9373591707976566,
381
+ "grad_norm": 18.20081901550293,
382
+ "learning_rate": 4.0613718411552346e-05,
383
+ "loss": 0.4176,
384
+ "step": 520
385
+ },
386
+ {
387
+ "epoch": 0.9553853086976115,
388
+ "grad_norm": 20.09193992614746,
389
+ "learning_rate": 4.043321299638989e-05,
390
+ "loss": 0.4297,
391
+ "step": 530
392
+ },
393
+ {
394
+ "epoch": 0.9734114465975665,
395
+ "grad_norm": 15.939692497253418,
396
+ "learning_rate": 4.0252707581227436e-05,
397
+ "loss": 0.4309,
398
+ "step": 540
399
+ },
400
+ {
401
+ "epoch": 0.9914375844975214,
402
+ "grad_norm": 24.811601638793945,
403
+ "learning_rate": 4.007220216606498e-05,
404
+ "loss": 0.3908,
405
+ "step": 550
406
+ },
407
+ {
408
+ "epoch": 1.0,
409
+ "eval_f1": 0.8367177786987153,
410
+ "eval_loss": 0.37827184796333313,
411
+ "eval_precision": 0.7951949586451359,
412
+ "eval_recall": 0.8828159160472234,
413
+ "eval_runtime": 15.9582,
414
+ "eval_samples_per_second": 292.827,
415
+ "eval_steps_per_second": 36.658,
416
+ "step": 555
417
+ }
418
+ ],
419
+ "logging_steps": 10,
420
+ "max_steps": 2770,
421
+ "num_input_tokens_seen": 0,
422
+ "num_train_epochs": 5,
423
+ "save_steps": 500,
424
+ "stateful_callbacks": {
425
+ "TrainerControl": {
426
+ "args": {
427
+ "should_epoch_stop": false,
428
+ "should_evaluate": false,
429
+ "should_log": false,
430
+ "should_save": true,
431
+ "should_training_stop": false
432
+ },
433
+ "attributes": {}
434
+ }
435
+ },
436
+ "total_flos": 4670747454750720.0,
437
+ "train_batch_size": 8,
438
+ "trial_name": null,
439
+ "trial_params": null
440
+ }
checkpoint-555/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:92aaf17ba6b51dd0179acd28630a512a049c53024ba01863d7232c815d6018dd
3
+ size 5432