douy commited on
Commit
2af91fa
·
1 Parent(s): 3173f98

Delete trainer_state.json

Browse files
Files changed (1) hide show
  1. trainer_state.json +0 -586
trainer_state.json DELETED
@@ -1,586 +0,0 @@
1
- {
2
- "best_metric": null,
3
- "best_model_checkpoint": null,
4
- "epoch": 3.0,
5
- "eval_steps": 10,
6
- "global_step": 81,
7
- "is_hyper_param_search": false,
8
- "is_local_process_zero": true,
9
- "is_world_process_zero": true,
10
- "log_history": [
11
- {
12
- "epoch": 0.04,
13
- "learning_rate": 0.0,
14
- "loss": 1.0172,
15
- "step": 1
16
- },
17
- {
18
- "epoch": 0.07,
19
- "learning_rate": 3.1546487678572864e-05,
20
- "loss": 2.3198,
21
- "step": 2
22
- },
23
- {
24
- "epoch": 0.11,
25
- "learning_rate": 5e-05,
26
- "loss": 2.4795,
27
- "step": 3
28
- },
29
- {
30
- "epoch": 0.15,
31
- "learning_rate": 5e-05,
32
- "loss": 1.551,
33
- "step": 4
34
- },
35
- {
36
- "epoch": 0.19,
37
- "learning_rate": 5e-05,
38
- "loss": 1.2034,
39
- "step": 5
40
- },
41
- {
42
- "epoch": 0.22,
43
- "learning_rate": 5e-05,
44
- "loss": 1.0527,
45
- "step": 6
46
- },
47
- {
48
- "epoch": 0.26,
49
- "learning_rate": 5e-05,
50
- "loss": 0.9743,
51
- "step": 7
52
- },
53
- {
54
- "epoch": 0.3,
55
- "learning_rate": 5e-05,
56
- "loss": 0.9738,
57
- "step": 8
58
- },
59
- {
60
- "epoch": 0.33,
61
- "learning_rate": 5e-05,
62
- "loss": 0.939,
63
- "step": 9
64
- },
65
- {
66
- "epoch": 0.37,
67
- "learning_rate": 5e-05,
68
- "loss": 0.955,
69
- "step": 10
70
- },
71
- {
72
- "epoch": 0.37,
73
- "eval_accuracy": 0.2181755564165483,
74
- "eval_loss": 0.9061336517333984,
75
- "eval_runtime": 44.217,
76
- "eval_samples_per_second": 0.814,
77
- "eval_steps_per_second": 0.045,
78
- "step": 10
79
- },
80
- {
81
- "epoch": 0.41,
82
- "learning_rate": 5e-05,
83
- "loss": 0.9513,
84
- "step": 11
85
- },
86
- {
87
- "epoch": 0.44,
88
- "learning_rate": 5e-05,
89
- "loss": 0.94,
90
- "step": 12
91
- },
92
- {
93
- "epoch": 0.48,
94
- "learning_rate": 5e-05,
95
- "loss": 0.9211,
96
- "step": 13
97
- },
98
- {
99
- "epoch": 0.52,
100
- "learning_rate": 5e-05,
101
- "loss": 0.8762,
102
- "step": 14
103
- },
104
- {
105
- "epoch": 0.56,
106
- "learning_rate": 5e-05,
107
- "loss": 0.9013,
108
- "step": 15
109
- },
110
- {
111
- "epoch": 0.59,
112
- "learning_rate": 5e-05,
113
- "loss": 0.8758,
114
- "step": 16
115
- },
116
- {
117
- "epoch": 0.63,
118
- "learning_rate": 5e-05,
119
- "loss": 0.8919,
120
- "step": 17
121
- },
122
- {
123
- "epoch": 0.67,
124
- "learning_rate": 5e-05,
125
- "loss": 0.8589,
126
- "step": 18
127
- },
128
- {
129
- "epoch": 0.7,
130
- "learning_rate": 5e-05,
131
- "loss": 0.8775,
132
- "step": 19
133
- },
134
- {
135
- "epoch": 0.74,
136
- "learning_rate": 5e-05,
137
- "loss": 0.8899,
138
- "step": 20
139
- },
140
- {
141
- "epoch": 0.74,
142
- "eval_accuracy": 0.21962848163933016,
143
- "eval_loss": 0.8734426498413086,
144
- "eval_runtime": 44.8031,
145
- "eval_samples_per_second": 0.804,
146
- "eval_steps_per_second": 0.045,
147
- "step": 20
148
- },
149
- {
150
- "epoch": 0.78,
151
- "learning_rate": 5e-05,
152
- "loss": 0.9011,
153
- "step": 21
154
- },
155
- {
156
- "epoch": 0.81,
157
- "learning_rate": 5e-05,
158
- "loss": 0.9195,
159
- "step": 22
160
- },
161
- {
162
- "epoch": 0.85,
163
- "learning_rate": 5e-05,
164
- "loss": 0.815,
165
- "step": 23
166
- },
167
- {
168
- "epoch": 0.89,
169
- "learning_rate": 5e-05,
170
- "loss": 0.8216,
171
- "step": 24
172
- },
173
- {
174
- "epoch": 0.93,
175
- "learning_rate": 5e-05,
176
- "loss": 0.8559,
177
- "step": 25
178
- },
179
- {
180
- "epoch": 0.96,
181
- "learning_rate": 5e-05,
182
- "loss": 0.9071,
183
- "step": 26
184
- },
185
- {
186
- "epoch": 1.0,
187
- "learning_rate": 5e-05,
188
- "loss": 0.6228,
189
- "step": 27
190
- },
191
- {
192
- "epoch": 1.04,
193
- "learning_rate": 5e-05,
194
- "loss": 0.3934,
195
- "step": 28
196
- },
197
- {
198
- "epoch": 1.07,
199
- "learning_rate": 5e-05,
200
- "loss": 0.8846,
201
- "step": 29
202
- },
203
- {
204
- "epoch": 1.11,
205
- "learning_rate": 5e-05,
206
- "loss": 0.879,
207
- "step": 30
208
- },
209
- {
210
- "epoch": 1.11,
211
- "eval_accuracy": 0.2173899005553403,
212
- "eval_loss": 0.9090863466262817,
213
- "eval_runtime": 45.3228,
214
- "eval_samples_per_second": 0.794,
215
- "eval_steps_per_second": 0.044,
216
- "step": 30
217
- },
218
- {
219
- "epoch": 1.15,
220
- "learning_rate": 5e-05,
221
- "loss": 0.8277,
222
- "step": 31
223
- },
224
- {
225
- "epoch": 1.19,
226
- "learning_rate": 5e-05,
227
- "loss": 0.6593,
228
- "step": 32
229
- },
230
- {
231
- "epoch": 1.22,
232
- "learning_rate": 5e-05,
233
- "loss": 0.5255,
234
- "step": 33
235
- },
236
- {
237
- "epoch": 1.26,
238
- "learning_rate": 5e-05,
239
- "loss": 0.4102,
240
- "step": 34
241
- },
242
- {
243
- "epoch": 1.3,
244
- "learning_rate": 5e-05,
245
- "loss": 0.5839,
246
- "step": 35
247
- },
248
- {
249
- "epoch": 1.33,
250
- "learning_rate": 5e-05,
251
- "loss": 0.6197,
252
- "step": 36
253
- },
254
- {
255
- "epoch": 1.37,
256
- "learning_rate": 5e-05,
257
- "loss": 0.4026,
258
- "step": 37
259
- },
260
- {
261
- "epoch": 1.41,
262
- "learning_rate": 5e-05,
263
- "loss": 0.3835,
264
- "step": 38
265
- },
266
- {
267
- "epoch": 1.44,
268
- "learning_rate": 5e-05,
269
- "loss": 0.3433,
270
- "step": 39
271
- },
272
- {
273
- "epoch": 1.48,
274
- "learning_rate": 5e-05,
275
- "loss": 0.3295,
276
- "step": 40
277
- },
278
- {
279
- "epoch": 1.48,
280
- "eval_accuracy": 0.21730380128287916,
281
- "eval_loss": 0.9803322553634644,
282
- "eval_runtime": 44.8946,
283
- "eval_samples_per_second": 0.802,
284
- "eval_steps_per_second": 0.045,
285
- "step": 40
286
- },
287
- {
288
- "epoch": 1.52,
289
- "learning_rate": 5e-05,
290
- "loss": 0.3101,
291
- "step": 41
292
- },
293
- {
294
- "epoch": 1.56,
295
- "learning_rate": 5e-05,
296
- "loss": 0.3492,
297
- "step": 42
298
- },
299
- {
300
- "epoch": 1.59,
301
- "learning_rate": 5e-05,
302
- "loss": 0.2991,
303
- "step": 43
304
- },
305
- {
306
- "epoch": 1.63,
307
- "learning_rate": 5e-05,
308
- "loss": 0.3412,
309
- "step": 44
310
- },
311
- {
312
- "epoch": 1.67,
313
- "learning_rate": 5e-05,
314
- "loss": 0.3824,
315
- "step": 45
316
- },
317
- {
318
- "epoch": 1.7,
319
- "learning_rate": 5e-05,
320
- "loss": 0.3694,
321
- "step": 46
322
- },
323
- {
324
- "epoch": 1.74,
325
- "learning_rate": 5e-05,
326
- "loss": 0.3926,
327
- "step": 47
328
- },
329
- {
330
- "epoch": 1.78,
331
- "learning_rate": 5e-05,
332
- "loss": 0.3993,
333
- "step": 48
334
- },
335
- {
336
- "epoch": 1.81,
337
- "learning_rate": 5e-05,
338
- "loss": 0.3678,
339
- "step": 49
340
- },
341
- {
342
- "epoch": 1.85,
343
- "learning_rate": 5e-05,
344
- "loss": 0.3711,
345
- "step": 50
346
- },
347
- {
348
- "epoch": 1.85,
349
- "eval_accuracy": 0.2173576133281674,
350
- "eval_loss": 0.9820255637168884,
351
- "eval_runtime": 44.7843,
352
- "eval_samples_per_second": 0.804,
353
- "eval_steps_per_second": 0.045,
354
- "step": 50
355
- },
356
- {
357
- "epoch": 1.89,
358
- "learning_rate": 5e-05,
359
- "loss": 0.3825,
360
- "step": 51
361
- },
362
- {
363
- "epoch": 1.93,
364
- "learning_rate": 5e-05,
365
- "loss": 0.3914,
366
- "step": 52
367
- },
368
- {
369
- "epoch": 1.96,
370
- "learning_rate": 5e-05,
371
- "loss": 0.3962,
372
- "step": 53
373
- },
374
- {
375
- "epoch": 2.0,
376
- "learning_rate": 5e-05,
377
- "loss": 0.2342,
378
- "step": 54
379
- },
380
- {
381
- "epoch": 2.04,
382
- "learning_rate": 5e-05,
383
- "loss": 0.1572,
384
- "step": 55
385
- },
386
- {
387
- "epoch": 2.07,
388
- "learning_rate": 5e-05,
389
- "loss": 0.4409,
390
- "step": 56
391
- },
392
- {
393
- "epoch": 2.11,
394
- "learning_rate": 5e-05,
395
- "loss": 0.4072,
396
- "step": 57
397
- },
398
- {
399
- "epoch": 2.15,
400
- "learning_rate": 5e-05,
401
- "loss": 0.4306,
402
- "step": 58
403
- },
404
- {
405
- "epoch": 2.19,
406
- "learning_rate": 5e-05,
407
- "loss": 0.338,
408
- "step": 59
409
- },
410
- {
411
- "epoch": 2.22,
412
- "learning_rate": 5e-05,
413
- "loss": 0.2927,
414
- "step": 60
415
- },
416
- {
417
- "epoch": 2.22,
418
- "eval_accuracy": 0.2152804683800422,
419
- "eval_loss": 1.0269818305969238,
420
- "eval_runtime": 44.7279,
421
- "eval_samples_per_second": 0.805,
422
- "eval_steps_per_second": 0.045,
423
- "step": 60
424
- },
425
- {
426
- "epoch": 2.26,
427
- "learning_rate": 5e-05,
428
- "loss": 0.3043,
429
- "step": 61
430
- },
431
- {
432
- "epoch": 2.3,
433
- "learning_rate": 5e-05,
434
- "loss": 0.3134,
435
- "step": 62
436
- },
437
- {
438
- "epoch": 2.33,
439
- "learning_rate": 5e-05,
440
- "loss": 0.2565,
441
- "step": 63
442
- },
443
- {
444
- "epoch": 2.37,
445
- "learning_rate": 5e-05,
446
- "loss": 0.2333,
447
- "step": 64
448
- },
449
- {
450
- "epoch": 2.41,
451
- "learning_rate": 5e-05,
452
- "loss": 0.2291,
453
- "step": 65
454
- },
455
- {
456
- "epoch": 2.44,
457
- "learning_rate": 5e-05,
458
- "loss": 0.1783,
459
- "step": 66
460
- },
461
- {
462
- "epoch": 2.48,
463
- "learning_rate": 5e-05,
464
- "loss": 0.2058,
465
- "step": 67
466
- },
467
- {
468
- "epoch": 2.52,
469
- "learning_rate": 5e-05,
470
- "loss": 0.208,
471
- "step": 68
472
- },
473
- {
474
- "epoch": 2.56,
475
- "learning_rate": 5e-05,
476
- "loss": 0.1745,
477
- "step": 69
478
- },
479
- {
480
- "epoch": 2.59,
481
- "learning_rate": 5e-05,
482
- "loss": 0.1703,
483
- "step": 70
484
- },
485
- {
486
- "epoch": 2.59,
487
- "eval_accuracy": 0.2131279865685135,
488
- "eval_loss": 1.0966472625732422,
489
- "eval_runtime": 44.8433,
490
- "eval_samples_per_second": 0.803,
491
- "eval_steps_per_second": 0.045,
492
- "step": 70
493
- },
494
- {
495
- "epoch": 2.63,
496
- "learning_rate": 5e-05,
497
- "loss": 0.2235,
498
- "step": 71
499
- },
500
- {
501
- "epoch": 2.67,
502
- "learning_rate": 5e-05,
503
- "loss": 0.2062,
504
- "step": 72
505
- },
506
- {
507
- "epoch": 2.7,
508
- "learning_rate": 5e-05,
509
- "loss": 0.2094,
510
- "step": 73
511
- },
512
- {
513
- "epoch": 2.74,
514
- "learning_rate": 5e-05,
515
- "loss": 0.2123,
516
- "step": 74
517
- },
518
- {
519
- "epoch": 2.78,
520
- "learning_rate": 5e-05,
521
- "loss": 0.2144,
522
- "step": 75
523
- },
524
- {
525
- "epoch": 2.81,
526
- "learning_rate": 5e-05,
527
- "loss": 0.2091,
528
- "step": 76
529
- },
530
- {
531
- "epoch": 2.85,
532
- "learning_rate": 5e-05,
533
- "loss": 0.2116,
534
- "step": 77
535
- },
536
- {
537
- "epoch": 2.89,
538
- "learning_rate": 5e-05,
539
- "loss": 0.2123,
540
- "step": 78
541
- },
542
- {
543
- "epoch": 2.93,
544
- "learning_rate": 5e-05,
545
- "loss": 0.1891,
546
- "step": 79
547
- },
548
- {
549
- "epoch": 2.96,
550
- "learning_rate": 5e-05,
551
- "loss": 0.2011,
552
- "step": 80
553
- },
554
- {
555
- "epoch": 2.96,
556
- "eval_accuracy": 0.2144840501097766,
557
- "eval_loss": 1.1488189697265625,
558
- "eval_runtime": 44.8519,
559
- "eval_samples_per_second": 0.803,
560
- "eval_steps_per_second": 0.045,
561
- "step": 80
562
- },
563
- {
564
- "epoch": 3.0,
565
- "learning_rate": 5e-05,
566
- "loss": 0.1493,
567
- "step": 81
568
- },
569
- {
570
- "epoch": 3.0,
571
- "step": 81,
572
- "total_flos": 10840779079680.0,
573
- "train_loss": 0.5814771251178082,
574
- "train_runtime": 6697.7067,
575
- "train_samples_per_second": 0.377,
576
- "train_steps_per_second": 0.012
577
- }
578
- ],
579
- "logging_steps": 1.0,
580
- "max_steps": 81,
581
- "num_train_epochs": 3,
582
- "save_steps": 500,
583
- "total_flos": 10840779079680.0,
584
- "trial_name": null,
585
- "trial_params": null
586
- }