apohllo commited on
Commit
c0f4fa6
1 Parent(s): 5af79ab

Upload trainer_state.json with huggingface_hub

Browse files
Files changed (1) hide show
  1. trainer_state.json +646 -0
trainer_state.json ADDED
@@ -0,0 +1,646 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 0.999853279209664,
5
+ "global_step": 5111,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 0.0,
12
+ "learning_rate": 1e-08,
13
+ "loss": 1.082,
14
+ "step": 1
15
+ },
16
+ {
17
+ "epoch": 0.01,
18
+ "learning_rate": 5.000000000000001e-07,
19
+ "loss": 0.9046,
20
+ "step": 50
21
+ },
22
+ {
23
+ "epoch": 0.02,
24
+ "learning_rate": 1.0000000000000002e-06,
25
+ "loss": 0.518,
26
+ "step": 100
27
+ },
28
+ {
29
+ "epoch": 0.03,
30
+ "learning_rate": 1.5e-06,
31
+ "loss": 0.3212,
32
+ "step": 150
33
+ },
34
+ {
35
+ "epoch": 0.04,
36
+ "learning_rate": 2.0000000000000003e-06,
37
+ "loss": 0.2435,
38
+ "step": 200
39
+ },
40
+ {
41
+ "epoch": 0.05,
42
+ "learning_rate": 2.5e-06,
43
+ "loss": 0.186,
44
+ "step": 250
45
+ },
46
+ {
47
+ "epoch": 0.06,
48
+ "learning_rate": 3e-06,
49
+ "loss": 0.1809,
50
+ "step": 300
51
+ },
52
+ {
53
+ "epoch": 0.07,
54
+ "learning_rate": 3.5e-06,
55
+ "loss": 0.16,
56
+ "step": 350
57
+ },
58
+ {
59
+ "epoch": 0.08,
60
+ "learning_rate": 4.000000000000001e-06,
61
+ "loss": 0.1625,
62
+ "step": 400
63
+ },
64
+ {
65
+ "epoch": 0.09,
66
+ "learning_rate": 4.5e-06,
67
+ "loss": 0.1502,
68
+ "step": 450
69
+ },
70
+ {
71
+ "epoch": 0.1,
72
+ "learning_rate": 5e-06,
73
+ "loss": 0.1401,
74
+ "step": 500
75
+ },
76
+ {
77
+ "epoch": 0.11,
78
+ "learning_rate": 5.500000000000001e-06,
79
+ "loss": 0.1206,
80
+ "step": 550
81
+ },
82
+ {
83
+ "epoch": 0.12,
84
+ "learning_rate": 6e-06,
85
+ "loss": 0.1291,
86
+ "step": 600
87
+ },
88
+ {
89
+ "epoch": 0.13,
90
+ "learning_rate": 6.5000000000000004e-06,
91
+ "loss": 0.1382,
92
+ "step": 650
93
+ },
94
+ {
95
+ "epoch": 0.14,
96
+ "learning_rate": 7e-06,
97
+ "loss": 0.13,
98
+ "step": 700
99
+ },
100
+ {
101
+ "epoch": 0.15,
102
+ "learning_rate": 7.500000000000001e-06,
103
+ "loss": 0.1262,
104
+ "step": 750
105
+ },
106
+ {
107
+ "epoch": 0.16,
108
+ "learning_rate": 8.000000000000001e-06,
109
+ "loss": 0.1218,
110
+ "step": 800
111
+ },
112
+ {
113
+ "epoch": 0.17,
114
+ "learning_rate": 8.5e-06,
115
+ "loss": 0.1223,
116
+ "step": 850
117
+ },
118
+ {
119
+ "epoch": 0.18,
120
+ "learning_rate": 9e-06,
121
+ "loss": 0.1128,
122
+ "step": 900
123
+ },
124
+ {
125
+ "epoch": 0.19,
126
+ "learning_rate": 9.5e-06,
127
+ "loss": 0.1188,
128
+ "step": 950
129
+ },
130
+ {
131
+ "epoch": 0.2,
132
+ "learning_rate": 1e-05,
133
+ "loss": 0.1203,
134
+ "step": 1000
135
+ },
136
+ {
137
+ "epoch": 0.21,
138
+ "learning_rate": 9.979637548360824e-06,
139
+ "loss": 0.107,
140
+ "step": 1050
141
+ },
142
+ {
143
+ "epoch": 0.22,
144
+ "learning_rate": 9.959275096721645e-06,
145
+ "loss": 0.1155,
146
+ "step": 1100
147
+ },
148
+ {
149
+ "epoch": 0.22,
150
+ "learning_rate": 9.93891264508247e-06,
151
+ "loss": 0.1112,
152
+ "step": 1150
153
+ },
154
+ {
155
+ "epoch": 0.23,
156
+ "learning_rate": 9.91855019344329e-06,
157
+ "loss": 0.1149,
158
+ "step": 1200
159
+ },
160
+ {
161
+ "epoch": 0.24,
162
+ "learning_rate": 9.898187741804114e-06,
163
+ "loss": 0.1043,
164
+ "step": 1250
165
+ },
166
+ {
167
+ "epoch": 0.25,
168
+ "learning_rate": 9.877825290164937e-06,
169
+ "loss": 0.1103,
170
+ "step": 1300
171
+ },
172
+ {
173
+ "epoch": 0.26,
174
+ "learning_rate": 9.85746283852576e-06,
175
+ "loss": 0.114,
176
+ "step": 1350
177
+ },
178
+ {
179
+ "epoch": 0.27,
180
+ "learning_rate": 9.837100386886582e-06,
181
+ "loss": 0.1246,
182
+ "step": 1400
183
+ },
184
+ {
185
+ "epoch": 0.28,
186
+ "learning_rate": 9.816737935247405e-06,
187
+ "loss": 0.1068,
188
+ "step": 1450
189
+ },
190
+ {
191
+ "epoch": 0.29,
192
+ "learning_rate": 9.796375483608226e-06,
193
+ "loss": 0.118,
194
+ "step": 1500
195
+ },
196
+ {
197
+ "epoch": 0.3,
198
+ "learning_rate": 9.77601303196905e-06,
199
+ "loss": 0.1014,
200
+ "step": 1550
201
+ },
202
+ {
203
+ "epoch": 0.31,
204
+ "learning_rate": 9.755650580329872e-06,
205
+ "loss": 0.1089,
206
+ "step": 1600
207
+ },
208
+ {
209
+ "epoch": 0.32,
210
+ "learning_rate": 9.735288128690695e-06,
211
+ "loss": 0.0997,
212
+ "step": 1650
213
+ },
214
+ {
215
+ "epoch": 0.33,
216
+ "learning_rate": 9.714925677051518e-06,
217
+ "loss": 0.1009,
218
+ "step": 1700
219
+ },
220
+ {
221
+ "epoch": 0.34,
222
+ "learning_rate": 9.69456322541234e-06,
223
+ "loss": 0.1187,
224
+ "step": 1750
225
+ },
226
+ {
227
+ "epoch": 0.35,
228
+ "learning_rate": 9.674200773773164e-06,
229
+ "loss": 0.113,
230
+ "step": 1800
231
+ },
232
+ {
233
+ "epoch": 0.36,
234
+ "learning_rate": 9.653838322133987e-06,
235
+ "loss": 0.1009,
236
+ "step": 1850
237
+ },
238
+ {
239
+ "epoch": 0.37,
240
+ "learning_rate": 9.633475870494808e-06,
241
+ "loss": 0.0976,
242
+ "step": 1900
243
+ },
244
+ {
245
+ "epoch": 0.38,
246
+ "learning_rate": 9.613113418855631e-06,
247
+ "loss": 0.1059,
248
+ "step": 1950
249
+ },
250
+ {
251
+ "epoch": 0.39,
252
+ "learning_rate": 9.592750967216454e-06,
253
+ "loss": 0.1104,
254
+ "step": 2000
255
+ },
256
+ {
257
+ "epoch": 0.4,
258
+ "learning_rate": 9.572388515577277e-06,
259
+ "loss": 0.0943,
260
+ "step": 2050
261
+ },
262
+ {
263
+ "epoch": 0.41,
264
+ "learning_rate": 9.5520260639381e-06,
265
+ "loss": 0.1057,
266
+ "step": 2100
267
+ },
268
+ {
269
+ "epoch": 0.42,
270
+ "learning_rate": 9.53166361229892e-06,
271
+ "loss": 0.1032,
272
+ "step": 2150
273
+ },
274
+ {
275
+ "epoch": 0.43,
276
+ "learning_rate": 9.511301160659744e-06,
277
+ "loss": 0.1017,
278
+ "step": 2200
279
+ },
280
+ {
281
+ "epoch": 0.44,
282
+ "learning_rate": 9.490938709020567e-06,
283
+ "loss": 0.1056,
284
+ "step": 2250
285
+ },
286
+ {
287
+ "epoch": 0.45,
288
+ "learning_rate": 9.47057625738139e-06,
289
+ "loss": 0.1058,
290
+ "step": 2300
291
+ },
292
+ {
293
+ "epoch": 0.46,
294
+ "learning_rate": 9.450213805742212e-06,
295
+ "loss": 0.108,
296
+ "step": 2350
297
+ },
298
+ {
299
+ "epoch": 0.47,
300
+ "learning_rate": 9.429851354103035e-06,
301
+ "loss": 0.1048,
302
+ "step": 2400
303
+ },
304
+ {
305
+ "epoch": 0.48,
306
+ "learning_rate": 9.409488902463856e-06,
307
+ "loss": 0.1033,
308
+ "step": 2450
309
+ },
310
+ {
311
+ "epoch": 0.49,
312
+ "learning_rate": 9.389126450824681e-06,
313
+ "loss": 0.0972,
314
+ "step": 2500
315
+ },
316
+ {
317
+ "epoch": 0.5,
318
+ "learning_rate": 9.368763999185502e-06,
319
+ "loss": 0.0988,
320
+ "step": 2550
321
+ },
322
+ {
323
+ "epoch": 0.51,
324
+ "learning_rate": 9.348401547546325e-06,
325
+ "loss": 0.0971,
326
+ "step": 2600
327
+ },
328
+ {
329
+ "epoch": 0.52,
330
+ "learning_rate": 9.328039095907148e-06,
331
+ "loss": 0.0982,
332
+ "step": 2650
333
+ },
334
+ {
335
+ "epoch": 0.53,
336
+ "learning_rate": 9.307676644267971e-06,
337
+ "loss": 0.096,
338
+ "step": 2700
339
+ },
340
+ {
341
+ "epoch": 0.54,
342
+ "learning_rate": 9.287314192628794e-06,
343
+ "loss": 0.0997,
344
+ "step": 2750
345
+ },
346
+ {
347
+ "epoch": 0.55,
348
+ "learning_rate": 9.266951740989615e-06,
349
+ "loss": 0.1173,
350
+ "step": 2800
351
+ },
352
+ {
353
+ "epoch": 0.56,
354
+ "learning_rate": 9.246589289350438e-06,
355
+ "loss": 0.0936,
356
+ "step": 2850
357
+ },
358
+ {
359
+ "epoch": 0.57,
360
+ "learning_rate": 9.226226837711261e-06,
361
+ "loss": 0.1038,
362
+ "step": 2900
363
+ },
364
+ {
365
+ "epoch": 0.58,
366
+ "learning_rate": 9.205864386072084e-06,
367
+ "loss": 0.1035,
368
+ "step": 2950
369
+ },
370
+ {
371
+ "epoch": 0.59,
372
+ "learning_rate": 9.185501934432907e-06,
373
+ "loss": 0.0876,
374
+ "step": 3000
375
+ },
376
+ {
377
+ "epoch": 0.6,
378
+ "learning_rate": 9.16513948279373e-06,
379
+ "loss": 0.1002,
380
+ "step": 3050
381
+ },
382
+ {
383
+ "epoch": 0.61,
384
+ "learning_rate": 9.14477703115455e-06,
385
+ "loss": 0.1077,
386
+ "step": 3100
387
+ },
388
+ {
389
+ "epoch": 0.62,
390
+ "learning_rate": 9.124414579515375e-06,
391
+ "loss": 0.0979,
392
+ "step": 3150
393
+ },
394
+ {
395
+ "epoch": 0.63,
396
+ "learning_rate": 9.104052127876197e-06,
397
+ "loss": 0.1003,
398
+ "step": 3200
399
+ },
400
+ {
401
+ "epoch": 0.64,
402
+ "learning_rate": 9.08368967623702e-06,
403
+ "loss": 0.0984,
404
+ "step": 3250
405
+ },
406
+ {
407
+ "epoch": 0.65,
408
+ "learning_rate": 9.063327224597842e-06,
409
+ "loss": 0.0964,
410
+ "step": 3300
411
+ },
412
+ {
413
+ "epoch": 0.66,
414
+ "learning_rate": 9.042964772958665e-06,
415
+ "loss": 0.1046,
416
+ "step": 3350
417
+ },
418
+ {
419
+ "epoch": 0.67,
420
+ "learning_rate": 9.022602321319488e-06,
421
+ "loss": 0.1042,
422
+ "step": 3400
423
+ },
424
+ {
425
+ "epoch": 0.67,
426
+ "learning_rate": 9.002239869680311e-06,
427
+ "loss": 0.0948,
428
+ "step": 3450
429
+ },
430
+ {
431
+ "epoch": 0.68,
432
+ "learning_rate": 8.981877418041132e-06,
433
+ "loss": 0.0904,
434
+ "step": 3500
435
+ },
436
+ {
437
+ "epoch": 0.69,
438
+ "learning_rate": 8.961514966401955e-06,
439
+ "loss": 0.095,
440
+ "step": 3550
441
+ },
442
+ {
443
+ "epoch": 0.7,
444
+ "learning_rate": 8.941152514762778e-06,
445
+ "loss": 0.0993,
446
+ "step": 3600
447
+ },
448
+ {
449
+ "epoch": 0.71,
450
+ "learning_rate": 8.920790063123601e-06,
451
+ "loss": 0.0949,
452
+ "step": 3650
453
+ },
454
+ {
455
+ "epoch": 0.72,
456
+ "learning_rate": 8.900427611484424e-06,
457
+ "loss": 0.0956,
458
+ "step": 3700
459
+ },
460
+ {
461
+ "epoch": 0.73,
462
+ "learning_rate": 8.880065159845245e-06,
463
+ "loss": 0.0956,
464
+ "step": 3750
465
+ },
466
+ {
467
+ "epoch": 0.74,
468
+ "learning_rate": 8.859702708206068e-06,
469
+ "loss": 0.0967,
470
+ "step": 3800
471
+ },
472
+ {
473
+ "epoch": 0.75,
474
+ "learning_rate": 8.839340256566893e-06,
475
+ "loss": 0.0985,
476
+ "step": 3850
477
+ },
478
+ {
479
+ "epoch": 0.76,
480
+ "learning_rate": 8.818977804927714e-06,
481
+ "loss": 0.0985,
482
+ "step": 3900
483
+ },
484
+ {
485
+ "epoch": 0.77,
486
+ "learning_rate": 8.798615353288537e-06,
487
+ "loss": 0.0988,
488
+ "step": 3950
489
+ },
490
+ {
491
+ "epoch": 0.78,
492
+ "learning_rate": 8.77825290164936e-06,
493
+ "loss": 0.1032,
494
+ "step": 4000
495
+ },
496
+ {
497
+ "epoch": 0.79,
498
+ "learning_rate": 8.757890450010183e-06,
499
+ "loss": 0.1008,
500
+ "step": 4050
501
+ },
502
+ {
503
+ "epoch": 0.8,
504
+ "learning_rate": 8.737527998371005e-06,
505
+ "loss": 0.0928,
506
+ "step": 4100
507
+ },
508
+ {
509
+ "epoch": 0.81,
510
+ "learning_rate": 8.717165546731827e-06,
511
+ "loss": 0.0836,
512
+ "step": 4150
513
+ },
514
+ {
515
+ "epoch": 0.82,
516
+ "learning_rate": 8.69680309509265e-06,
517
+ "loss": 0.0958,
518
+ "step": 4200
519
+ },
520
+ {
521
+ "epoch": 0.83,
522
+ "learning_rate": 8.676440643453472e-06,
523
+ "loss": 0.0956,
524
+ "step": 4250
525
+ },
526
+ {
527
+ "epoch": 0.84,
528
+ "learning_rate": 8.656078191814295e-06,
529
+ "loss": 0.1009,
530
+ "step": 4300
531
+ },
532
+ {
533
+ "epoch": 0.85,
534
+ "learning_rate": 8.635715740175118e-06,
535
+ "loss": 0.098,
536
+ "step": 4350
537
+ },
538
+ {
539
+ "epoch": 0.86,
540
+ "learning_rate": 8.615353288535941e-06,
541
+ "loss": 0.0982,
542
+ "step": 4400
543
+ },
544
+ {
545
+ "epoch": 0.87,
546
+ "learning_rate": 8.594990836896762e-06,
547
+ "loss": 0.0983,
548
+ "step": 4450
549
+ },
550
+ {
551
+ "epoch": 0.88,
552
+ "learning_rate": 8.574628385257587e-06,
553
+ "loss": 0.0923,
554
+ "step": 4500
555
+ },
556
+ {
557
+ "epoch": 0.89,
558
+ "learning_rate": 8.554265933618408e-06,
559
+ "loss": 0.0941,
560
+ "step": 4550
561
+ },
562
+ {
563
+ "epoch": 0.9,
564
+ "learning_rate": 8.533903481979231e-06,
565
+ "loss": 0.0951,
566
+ "step": 4600
567
+ },
568
+ {
569
+ "epoch": 0.91,
570
+ "learning_rate": 8.513541030340054e-06,
571
+ "loss": 0.092,
572
+ "step": 4650
573
+ },
574
+ {
575
+ "epoch": 0.92,
576
+ "learning_rate": 8.493178578700875e-06,
577
+ "loss": 0.1038,
578
+ "step": 4700
579
+ },
580
+ {
581
+ "epoch": 0.93,
582
+ "learning_rate": 8.4728161270617e-06,
583
+ "loss": 0.0972,
584
+ "step": 4750
585
+ },
586
+ {
587
+ "epoch": 0.94,
588
+ "learning_rate": 8.452453675422521e-06,
589
+ "loss": 0.0915,
590
+ "step": 4800
591
+ },
592
+ {
593
+ "epoch": 0.95,
594
+ "learning_rate": 8.432091223783344e-06,
595
+ "loss": 0.0989,
596
+ "step": 4850
597
+ },
598
+ {
599
+ "epoch": 0.96,
600
+ "learning_rate": 8.411728772144167e-06,
601
+ "loss": 0.0956,
602
+ "step": 4900
603
+ },
604
+ {
605
+ "epoch": 0.97,
606
+ "learning_rate": 8.39136632050499e-06,
607
+ "loss": 0.1001,
608
+ "step": 4950
609
+ },
610
+ {
611
+ "epoch": 0.98,
612
+ "learning_rate": 8.371003868865813e-06,
613
+ "loss": 0.0969,
614
+ "step": 5000
615
+ },
616
+ {
617
+ "epoch": 0.98,
618
+ "eval_accuracy": 0.9705359974627339,
619
+ "eval_f1": 0.8414134516899965,
620
+ "eval_loss": 0.08369224518537521,
621
+ "eval_precision": 0.8542461005199307,
622
+ "eval_recall": 0.8289606458123108,
623
+ "eval_runtime": 2321.5551,
624
+ "eval_samples_per_second": 27.163,
625
+ "eval_steps_per_second": 0.849,
626
+ "step": 5000
627
+ },
628
+ {
629
+ "epoch": 0.99,
630
+ "learning_rate": 8.350641417226635e-06,
631
+ "loss": 0.0819,
632
+ "step": 5050
633
+ },
634
+ {
635
+ "epoch": 1.0,
636
+ "learning_rate": 8.330278965587457e-06,
637
+ "loss": 0.0952,
638
+ "step": 5100
639
+ }
640
+ ],
641
+ "max_steps": 25555,
642
+ "num_train_epochs": 5,
643
+ "total_flos": 4.395776611183227e+17,
644
+ "trial_name": null,
645
+ "trial_params": null
646
+ }