arshsin commited on
Commit
7342efc
1 Parent(s): 2667df0

Training in progress, epoch 1, checkpoint

Browse files
last-checkpoint/model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6a5cd16d9add4799b6f19e8b925b13c633e83530b2858e40e771e29e5ab6a09d
3
  size 94771728
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dfa76f8319f9de5a2b15ee9897862cc31f5320dd339b710e065b8cc20fa8041b
3
  size 94771728
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:674a65994621e34fc8f7a5ea3b43855fd1df9dd45e161602af5a42997a361505
3
  size 189575930
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c33a6e32777c8141b0e113c90fcf38ea5a45472168c11e7593fc333dcf2b3bc3
3
  size 189575930
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1c3500b50b3ed905cef1268e4d8cbc35943fb573000be438524828fce2194efc
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d719fab7ffdef266a2408ac9b0941ef00292f0c27a3d315a103ae110fe3685b6
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7ce54e5f8293dfd968fdfe1cbe671ba90973875903e42baad9e8975788f30a79
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1046f95e7060855274df5f20ddd857dfb88527755539f16deb844f1fba32a613
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,1162 +1,58 @@
1
  {
2
- "best_metric": 0.84,
3
- "best_model_checkpoint": "distilhubert-finetuned-gtzan/checkpoint-56",
4
- "epoch": 14.867256637168142,
5
  "eval_steps": 500,
6
- "global_step": 840,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
10
  "log_history": [
11
  {
12
- "epoch": 0.09,
13
- "learning_rate": 2.9761904761904765e-07,
14
  "loss": 0.0001,
15
  "step": 5
16
  },
17
  {
18
- "epoch": 0.18,
19
- "learning_rate": 5.952380952380953e-07,
20
- "loss": 0.0751,
21
  "step": 10
22
  },
23
  {
24
- "epoch": 0.27,
25
- "learning_rate": 8.928571428571429e-07,
26
- "loss": 0.0001,
27
  "step": 15
28
  },
29
  {
30
- "epoch": 0.35,
31
- "learning_rate": 1.1904761904761906e-06,
32
- "loss": 0.0041,
33
  "step": 20
34
  },
35
  {
36
- "epoch": 0.44,
37
- "learning_rate": 1.4880952380952381e-06,
38
- "loss": 0.0001,
39
  "step": 25
40
  },
41
  {
42
- "epoch": 0.53,
43
- "learning_rate": 1.7857142857142859e-06,
44
- "loss": 0.007,
45
- "step": 30
46
- },
47
- {
48
- "epoch": 0.62,
49
- "learning_rate": 2.0833333333333334e-06,
50
- "loss": 0.0002,
51
- "step": 35
52
- },
53
- {
54
- "epoch": 0.71,
55
- "learning_rate": 2.380952380952381e-06,
56
- "loss": 0.0001,
57
- "step": 40
58
- },
59
- {
60
- "epoch": 0.8,
61
- "learning_rate": 2.6785714285714285e-06,
62
- "loss": 0.0001,
63
- "step": 45
64
- },
65
- {
66
- "epoch": 0.88,
67
- "learning_rate": 2.9761904761904763e-06,
68
- "loss": 0.0001,
69
- "step": 50
70
- },
71
- {
72
- "epoch": 0.97,
73
- "learning_rate": 3.273809523809524e-06,
74
- "loss": 0.0001,
75
- "step": 55
76
- },
77
- {
78
- "epoch": 0.99,
79
- "eval_accuracy": 0.84,
80
- "eval_loss": 1.4112725257873535,
81
- "eval_runtime": 71.2785,
82
- "eval_samples_per_second": 1.403,
83
- "eval_steps_per_second": 0.182,
84
- "step": 56
85
- },
86
- {
87
- "epoch": 1.06,
88
- "learning_rate": 3.5714285714285718e-06,
89
- "loss": 0.0001,
90
- "step": 60
91
- },
92
- {
93
- "epoch": 1.15,
94
- "learning_rate": 3.869047619047619e-06,
95
- "loss": 0.0001,
96
- "step": 65
97
- },
98
- {
99
- "epoch": 1.24,
100
- "learning_rate": 4.166666666666667e-06,
101
- "loss": 0.0001,
102
- "step": 70
103
- },
104
- {
105
- "epoch": 1.33,
106
- "learning_rate": 4.464285714285715e-06,
107
- "loss": 0.0001,
108
- "step": 75
109
- },
110
- {
111
- "epoch": 1.42,
112
- "learning_rate": 4.761904761904762e-06,
113
- "loss": 0.0172,
114
- "step": 80
115
- },
116
- {
117
- "epoch": 1.5,
118
- "learning_rate": 4.993386243386244e-06,
119
- "loss": 0.0001,
120
- "step": 85
121
- },
122
- {
123
- "epoch": 1.59,
124
- "learning_rate": 4.960317460317461e-06,
125
- "loss": 0.0001,
126
- "step": 90
127
- },
128
- {
129
- "epoch": 1.68,
130
- "learning_rate": 4.927248677248677e-06,
131
- "loss": 0.0001,
132
- "step": 95
133
- },
134
- {
135
- "epoch": 1.77,
136
- "learning_rate": 4.894179894179894e-06,
137
- "loss": 0.0766,
138
- "step": 100
139
- },
140
- {
141
- "epoch": 1.86,
142
- "learning_rate": 4.861111111111111e-06,
143
- "loss": 0.022,
144
- "step": 105
145
- },
146
- {
147
- "epoch": 1.95,
148
- "learning_rate": 4.828042328042328e-06,
149
- "loss": 0.0001,
150
- "step": 110
151
- },
152
- {
153
- "epoch": 2.0,
154
- "eval_accuracy": 0.84,
155
- "eval_loss": 1.4248417615890503,
156
- "eval_runtime": 71.9122,
157
- "eval_samples_per_second": 1.391,
158
- "eval_steps_per_second": 0.181,
159
- "step": 113
160
- },
161
- {
162
- "epoch": 2.04,
163
- "learning_rate": 4.794973544973545e-06,
164
- "loss": 0.0001,
165
- "step": 115
166
- },
167
- {
168
- "epoch": 2.12,
169
- "learning_rate": 4.761904761904762e-06,
170
- "loss": 0.0711,
171
- "step": 120
172
- },
173
- {
174
- "epoch": 2.21,
175
- "learning_rate": 4.728835978835979e-06,
176
- "loss": 0.0001,
177
- "step": 125
178
- },
179
- {
180
- "epoch": 2.3,
181
- "learning_rate": 4.695767195767196e-06,
182
- "loss": 0.0001,
183
- "step": 130
184
- },
185
- {
186
- "epoch": 2.39,
187
- "learning_rate": 4.662698412698413e-06,
188
- "loss": 0.0091,
189
- "step": 135
190
- },
191
- {
192
- "epoch": 2.48,
193
- "learning_rate": 4.62962962962963e-06,
194
- "loss": 0.0001,
195
- "step": 140
196
- },
197
- {
198
- "epoch": 2.57,
199
- "learning_rate": 4.596560846560847e-06,
200
- "loss": 0.0001,
201
- "step": 145
202
- },
203
- {
204
- "epoch": 2.65,
205
- "learning_rate": 4.563492063492064e-06,
206
- "loss": 0.0001,
207
- "step": 150
208
- },
209
- {
210
- "epoch": 2.74,
211
- "learning_rate": 4.530423280423281e-06,
212
- "loss": 0.03,
213
- "step": 155
214
- },
215
- {
216
- "epoch": 2.83,
217
- "learning_rate": 4.497354497354498e-06,
218
- "loss": 0.0001,
219
- "step": 160
220
- },
221
- {
222
- "epoch": 2.92,
223
- "learning_rate": 4.464285714285715e-06,
224
- "loss": 0.0001,
225
- "step": 165
226
- },
227
- {
228
- "epoch": 2.99,
229
- "eval_accuracy": 0.83,
230
- "eval_loss": 1.4818127155303955,
231
- "eval_runtime": 72.1308,
232
- "eval_samples_per_second": 1.386,
233
- "eval_steps_per_second": 0.18,
234
- "step": 169
235
- },
236
- {
237
- "epoch": 3.01,
238
- "learning_rate": 4.431216931216932e-06,
239
- "loss": 0.0001,
240
- "step": 170
241
- },
242
- {
243
- "epoch": 3.1,
244
- "learning_rate": 4.398148148148149e-06,
245
- "loss": 0.0001,
246
- "step": 175
247
- },
248
- {
249
- "epoch": 3.19,
250
- "learning_rate": 4.365079365079366e-06,
251
- "loss": 0.0158,
252
- "step": 180
253
- },
254
- {
255
- "epoch": 3.27,
256
- "learning_rate": 4.332010582010583e-06,
257
- "loss": 0.0001,
258
- "step": 185
259
- },
260
- {
261
- "epoch": 3.36,
262
- "learning_rate": 4.298941798941799e-06,
263
- "loss": 0.0001,
264
- "step": 190
265
- },
266
- {
267
- "epoch": 3.45,
268
- "learning_rate": 4.265873015873016e-06,
269
- "loss": 0.0001,
270
- "step": 195
271
- },
272
- {
273
- "epoch": 3.54,
274
- "learning_rate": 4.232804232804233e-06,
275
- "loss": 0.0001,
276
- "step": 200
277
- },
278
- {
279
- "epoch": 3.63,
280
- "learning_rate": 4.199735449735451e-06,
281
- "loss": 0.0001,
282
- "step": 205
283
- },
284
- {
285
- "epoch": 3.72,
286
- "learning_rate": 4.166666666666667e-06,
287
- "loss": 0.0001,
288
- "step": 210
289
- },
290
- {
291
- "epoch": 3.81,
292
- "learning_rate": 4.133597883597884e-06,
293
- "loss": 0.0528,
294
- "step": 215
295
- },
296
- {
297
- "epoch": 3.89,
298
- "learning_rate": 4.100529100529101e-06,
299
- "loss": 0.0135,
300
- "step": 220
301
- },
302
- {
303
- "epoch": 3.98,
304
- "learning_rate": 4.067460317460318e-06,
305
- "loss": 0.0001,
306
- "step": 225
307
- },
308
- {
309
- "epoch": 4.0,
310
- "eval_accuracy": 0.83,
311
- "eval_loss": 1.522812843322754,
312
- "eval_runtime": 70.9138,
313
- "eval_samples_per_second": 1.41,
314
- "eval_steps_per_second": 0.183,
315
- "step": 226
316
- },
317
- {
318
- "epoch": 4.07,
319
- "learning_rate": 4.034391534391535e-06,
320
- "loss": 0.0001,
321
- "step": 230
322
- },
323
- {
324
- "epoch": 4.16,
325
- "learning_rate": 4.001322751322752e-06,
326
- "loss": 0.0026,
327
- "step": 235
328
- },
329
- {
330
- "epoch": 4.25,
331
- "learning_rate": 3.968253968253968e-06,
332
- "loss": 0.0001,
333
- "step": 240
334
- },
335
- {
336
- "epoch": 4.34,
337
- "learning_rate": 3.935185185185186e-06,
338
- "loss": 0.0001,
339
- "step": 245
340
- },
341
- {
342
- "epoch": 4.42,
343
- "learning_rate": 3.902116402116403e-06,
344
- "loss": 0.0001,
345
- "step": 250
346
- },
347
- {
348
- "epoch": 4.51,
349
- "learning_rate": 3.869047619047619e-06,
350
- "loss": 0.0001,
351
- "step": 255
352
- },
353
- {
354
- "epoch": 4.6,
355
- "learning_rate": 3.835978835978836e-06,
356
- "loss": 0.0257,
357
- "step": 260
358
- },
359
- {
360
- "epoch": 4.69,
361
- "learning_rate": 3.802910052910053e-06,
362
- "loss": 0.0001,
363
- "step": 265
364
- },
365
- {
366
- "epoch": 4.78,
367
- "learning_rate": 3.76984126984127e-06,
368
- "loss": 0.0001,
369
- "step": 270
370
- },
371
- {
372
- "epoch": 4.87,
373
- "learning_rate": 3.7367724867724867e-06,
374
- "loss": 0.0505,
375
- "step": 275
376
- },
377
- {
378
- "epoch": 4.96,
379
- "learning_rate": 3.7037037037037037e-06,
380
- "loss": 0.0001,
381
- "step": 280
382
- },
383
- {
384
- "epoch": 4.99,
385
- "eval_accuracy": 0.84,
386
- "eval_loss": 1.5067402124404907,
387
- "eval_runtime": 70.6686,
388
- "eval_samples_per_second": 1.415,
389
- "eval_steps_per_second": 0.184,
390
- "step": 282
391
- },
392
- {
393
- "epoch": 5.04,
394
- "learning_rate": 3.6706349206349208e-06,
395
- "loss": 0.0,
396
- "step": 285
397
- },
398
- {
399
- "epoch": 5.13,
400
- "learning_rate": 3.637566137566138e-06,
401
- "loss": 0.0001,
402
- "step": 290
403
- },
404
- {
405
- "epoch": 5.22,
406
- "learning_rate": 3.6044973544973548e-06,
407
- "loss": 0.0,
408
- "step": 295
409
- },
410
- {
411
- "epoch": 5.31,
412
- "learning_rate": 3.5714285714285718e-06,
413
- "loss": 0.0,
414
- "step": 300
415
- },
416
- {
417
- "epoch": 5.4,
418
- "learning_rate": 3.538359788359789e-06,
419
- "loss": 0.0,
420
- "step": 305
421
- },
422
- {
423
- "epoch": 5.49,
424
- "learning_rate": 3.5052910052910054e-06,
425
- "loss": 0.0,
426
- "step": 310
427
- },
428
- {
429
- "epoch": 5.58,
430
- "learning_rate": 3.4722222222222224e-06,
431
- "loss": 0.051,
432
- "step": 315
433
- },
434
- {
435
- "epoch": 5.66,
436
- "learning_rate": 3.4391534391534394e-06,
437
- "loss": 0.0,
438
- "step": 320
439
- },
440
- {
441
- "epoch": 5.75,
442
- "learning_rate": 3.406084656084656e-06,
443
- "loss": 0.0,
444
- "step": 325
445
- },
446
- {
447
- "epoch": 5.84,
448
- "learning_rate": 3.3730158730158734e-06,
449
- "loss": 0.0027,
450
- "step": 330
451
- },
452
- {
453
- "epoch": 5.93,
454
- "learning_rate": 3.3399470899470904e-06,
455
- "loss": 0.0032,
456
- "step": 335
457
- },
458
- {
459
- "epoch": 6.0,
460
- "eval_accuracy": 0.84,
461
- "eval_loss": 1.5204719305038452,
462
- "eval_runtime": 71.0785,
463
- "eval_samples_per_second": 1.407,
464
- "eval_steps_per_second": 0.183,
465
- "step": 339
466
- },
467
- {
468
- "epoch": 6.02,
469
- "learning_rate": 3.3068783068783074e-06,
470
- "loss": 0.0,
471
- "step": 340
472
- },
473
- {
474
- "epoch": 6.11,
475
- "learning_rate": 3.273809523809524e-06,
476
- "loss": 0.0,
477
- "step": 345
478
- },
479
- {
480
- "epoch": 6.19,
481
- "learning_rate": 3.240740740740741e-06,
482
- "loss": 0.0,
483
- "step": 350
484
- },
485
- {
486
- "epoch": 6.28,
487
- "learning_rate": 3.2076719576719576e-06,
488
- "loss": 0.0195,
489
- "step": 355
490
- },
491
- {
492
- "epoch": 6.37,
493
- "learning_rate": 3.1746031746031746e-06,
494
- "loss": 0.0,
495
- "step": 360
496
- },
497
- {
498
- "epoch": 6.46,
499
- "learning_rate": 3.1415343915343916e-06,
500
- "loss": 0.0,
501
- "step": 365
502
- },
503
- {
504
- "epoch": 6.55,
505
- "learning_rate": 3.108465608465609e-06,
506
- "loss": 0.0,
507
- "step": 370
508
- },
509
- {
510
- "epoch": 6.64,
511
- "learning_rate": 3.0753968253968257e-06,
512
- "loss": 0.0385,
513
- "step": 375
514
- },
515
- {
516
- "epoch": 6.73,
517
- "learning_rate": 3.0423280423280427e-06,
518
- "loss": 0.0182,
519
- "step": 380
520
- },
521
- {
522
- "epoch": 6.81,
523
- "learning_rate": 3.0092592592592597e-06,
524
- "loss": 0.0,
525
- "step": 385
526
- },
527
- {
528
- "epoch": 6.9,
529
- "learning_rate": 2.9761904761904763e-06,
530
- "loss": 0.0,
531
- "step": 390
532
- },
533
- {
534
- "epoch": 6.99,
535
- "learning_rate": 2.9431216931216933e-06,
536
- "loss": 0.0,
537
- "step": 395
538
- },
539
- {
540
- "epoch": 6.99,
541
- "eval_accuracy": 0.84,
542
- "eval_loss": 1.5488288402557373,
543
- "eval_runtime": 71.4088,
544
- "eval_samples_per_second": 1.4,
545
- "eval_steps_per_second": 0.182,
546
- "step": 395
547
- },
548
- {
549
- "epoch": 7.08,
550
- "learning_rate": 2.9100529100529103e-06,
551
- "loss": 0.0,
552
- "step": 400
553
- },
554
- {
555
- "epoch": 7.17,
556
- "learning_rate": 2.876984126984127e-06,
557
- "loss": 0.0,
558
- "step": 405
559
- },
560
- {
561
- "epoch": 7.26,
562
- "learning_rate": 2.8439153439153443e-06,
563
- "loss": 0.0028,
564
- "step": 410
565
- },
566
- {
567
- "epoch": 7.35,
568
- "learning_rate": 2.8108465608465613e-06,
569
- "loss": 0.0,
570
- "step": 415
571
- },
572
- {
573
- "epoch": 7.43,
574
- "learning_rate": 2.7777777777777783e-06,
575
- "loss": 0.0,
576
- "step": 420
577
- },
578
- {
579
- "epoch": 7.52,
580
- "learning_rate": 2.744708994708995e-06,
581
- "loss": 0.0576,
582
- "step": 425
583
- },
584
- {
585
- "epoch": 7.61,
586
- "learning_rate": 2.711640211640212e-06,
587
- "loss": 0.0,
588
- "step": 430
589
- },
590
- {
591
- "epoch": 7.7,
592
- "learning_rate": 2.6785714285714285e-06,
593
- "loss": 0.0,
594
- "step": 435
595
- },
596
- {
597
- "epoch": 7.79,
598
- "learning_rate": 2.6455026455026455e-06,
599
- "loss": 0.0,
600
- "step": 440
601
- },
602
- {
603
- "epoch": 7.88,
604
- "learning_rate": 2.6124338624338625e-06,
605
- "loss": 0.0,
606
- "step": 445
607
- },
608
- {
609
- "epoch": 7.96,
610
- "learning_rate": 2.57936507936508e-06,
611
- "loss": 0.0,
612
- "step": 450
613
- },
614
- {
615
- "epoch": 8.0,
616
- "eval_accuracy": 0.84,
617
- "eval_loss": 1.5889931917190552,
618
- "eval_runtime": 72.3311,
619
- "eval_samples_per_second": 1.383,
620
- "eval_steps_per_second": 0.18,
621
- "step": 452
622
- },
623
- {
624
- "epoch": 8.05,
625
- "learning_rate": 2.5462962962962966e-06,
626
- "loss": 0.0,
627
- "step": 455
628
- },
629
- {
630
- "epoch": 8.14,
631
- "learning_rate": 2.5132275132275136e-06,
632
- "loss": 0.0,
633
- "step": 460
634
- },
635
- {
636
- "epoch": 8.23,
637
- "learning_rate": 2.4801587301587306e-06,
638
- "loss": 0.0,
639
- "step": 465
640
- },
641
- {
642
- "epoch": 8.32,
643
- "learning_rate": 2.447089947089947e-06,
644
- "loss": 0.0,
645
- "step": 470
646
- },
647
- {
648
- "epoch": 8.41,
649
- "learning_rate": 2.414021164021164e-06,
650
- "loss": 0.0,
651
- "step": 475
652
- },
653
- {
654
- "epoch": 8.5,
655
- "learning_rate": 2.380952380952381e-06,
656
- "loss": 0.0087,
657
- "step": 480
658
- },
659
- {
660
- "epoch": 8.58,
661
- "learning_rate": 2.347883597883598e-06,
662
- "loss": 0.003,
663
- "step": 485
664
- },
665
- {
666
- "epoch": 8.67,
667
- "learning_rate": 2.314814814814815e-06,
668
- "loss": 0.0,
669
- "step": 490
670
- },
671
- {
672
- "epoch": 8.76,
673
- "learning_rate": 2.281746031746032e-06,
674
- "loss": 0.0,
675
- "step": 495
676
- },
677
- {
678
- "epoch": 8.85,
679
- "learning_rate": 2.248677248677249e-06,
680
- "loss": 0.0285,
681
- "step": 500
682
- },
683
- {
684
- "epoch": 8.94,
685
- "learning_rate": 2.215608465608466e-06,
686
- "loss": 0.0,
687
- "step": 505
688
- },
689
- {
690
- "epoch": 8.99,
691
- "eval_accuracy": 0.83,
692
- "eval_loss": 1.6020234823226929,
693
- "eval_runtime": 71.1594,
694
- "eval_samples_per_second": 1.405,
695
- "eval_steps_per_second": 0.183,
696
- "step": 508
697
- },
698
- {
699
- "epoch": 9.03,
700
- "learning_rate": 2.182539682539683e-06,
701
- "loss": 0.0,
702
- "step": 510
703
- },
704
- {
705
- "epoch": 9.12,
706
- "learning_rate": 2.1494708994708994e-06,
707
- "loss": 0.0,
708
- "step": 515
709
- },
710
- {
711
- "epoch": 9.2,
712
- "learning_rate": 2.1164021164021164e-06,
713
- "loss": 0.0147,
714
- "step": 520
715
- },
716
- {
717
- "epoch": 9.29,
718
- "learning_rate": 2.0833333333333334e-06,
719
- "loss": 0.0,
720
- "step": 525
721
- },
722
- {
723
- "epoch": 9.38,
724
- "learning_rate": 2.0502645502645504e-06,
725
- "loss": 0.0,
726
- "step": 530
727
- },
728
- {
729
- "epoch": 9.47,
730
- "learning_rate": 2.0171957671957675e-06,
731
- "loss": 0.0,
732
- "step": 535
733
- },
734
- {
735
- "epoch": 9.56,
736
- "learning_rate": 1.984126984126984e-06,
737
- "loss": 0.0,
738
- "step": 540
739
- },
740
- {
741
- "epoch": 9.65,
742
- "learning_rate": 1.9510582010582015e-06,
743
- "loss": 0.0,
744
- "step": 545
745
- },
746
- {
747
- "epoch": 9.73,
748
- "learning_rate": 1.917989417989418e-06,
749
- "loss": 0.0134,
750
- "step": 550
751
- },
752
- {
753
- "epoch": 9.82,
754
- "learning_rate": 1.884920634920635e-06,
755
- "loss": 0.0,
756
- "step": 555
757
- },
758
- {
759
- "epoch": 9.91,
760
- "learning_rate": 1.8518518518518519e-06,
761
- "loss": 0.0,
762
- "step": 560
763
- },
764
- {
765
- "epoch": 10.0,
766
- "learning_rate": 1.818783068783069e-06,
767
- "loss": 0.0117,
768
- "step": 565
769
- },
770
- {
771
- "epoch": 10.0,
772
- "eval_accuracy": 0.84,
773
- "eval_loss": 1.5944697856903076,
774
- "eval_runtime": 70.9115,
775
- "eval_samples_per_second": 1.41,
776
- "eval_steps_per_second": 0.183,
777
- "step": 565
778
- },
779
- {
780
- "epoch": 10.09,
781
- "learning_rate": 1.7857142857142859e-06,
782
- "loss": 0.0,
783
- "step": 570
784
- },
785
- {
786
- "epoch": 10.18,
787
- "learning_rate": 1.7526455026455027e-06,
788
- "loss": 0.0,
789
- "step": 575
790
- },
791
- {
792
- "epoch": 10.27,
793
- "learning_rate": 1.7195767195767197e-06,
794
- "loss": 0.0,
795
- "step": 580
796
- },
797
- {
798
- "epoch": 10.35,
799
- "learning_rate": 1.6865079365079367e-06,
800
- "loss": 0.0125,
801
- "step": 585
802
- },
803
- {
804
- "epoch": 10.44,
805
- "learning_rate": 1.6534391534391537e-06,
806
- "loss": 0.0086,
807
- "step": 590
808
- },
809
- {
810
- "epoch": 10.53,
811
- "learning_rate": 1.6203703703703705e-06,
812
- "loss": 0.0,
813
- "step": 595
814
- },
815
- {
816
- "epoch": 10.62,
817
- "learning_rate": 1.5873015873015873e-06,
818
- "loss": 0.0,
819
- "step": 600
820
- },
821
- {
822
- "epoch": 10.71,
823
- "learning_rate": 1.5542328042328045e-06,
824
- "loss": 0.0,
825
- "step": 605
826
- },
827
- {
828
- "epoch": 10.8,
829
- "learning_rate": 1.5211640211640213e-06,
830
- "loss": 0.0,
831
- "step": 610
832
- },
833
- {
834
- "epoch": 10.88,
835
- "learning_rate": 1.4880952380952381e-06,
836
- "loss": 0.0,
837
- "step": 615
838
- },
839
- {
840
- "epoch": 10.97,
841
- "learning_rate": 1.4550264550264551e-06,
842
- "loss": 0.0,
843
- "step": 620
844
- },
845
- {
846
- "epoch": 10.99,
847
- "eval_accuracy": 0.84,
848
- "eval_loss": 1.6145154237747192,
849
- "eval_runtime": 71.1358,
850
- "eval_samples_per_second": 1.406,
851
- "eval_steps_per_second": 0.183,
852
- "step": 621
853
- },
854
- {
855
- "epoch": 11.06,
856
- "learning_rate": 1.4219576719576722e-06,
857
- "loss": 0.0089,
858
- "step": 625
859
- },
860
- {
861
- "epoch": 11.15,
862
- "learning_rate": 1.3888888888888892e-06,
863
- "loss": 0.0,
864
- "step": 630
865
- },
866
- {
867
- "epoch": 11.24,
868
- "learning_rate": 1.355820105820106e-06,
869
- "loss": 0.0099,
870
- "step": 635
871
- },
872
- {
873
- "epoch": 11.33,
874
- "learning_rate": 1.3227513227513228e-06,
875
- "loss": 0.0,
876
- "step": 640
877
- },
878
- {
879
- "epoch": 11.42,
880
- "learning_rate": 1.28968253968254e-06,
881
- "loss": 0.0,
882
- "step": 645
883
- },
884
- {
885
- "epoch": 11.5,
886
- "learning_rate": 1.2566137566137568e-06,
887
- "loss": 0.0,
888
- "step": 650
889
- },
890
- {
891
- "epoch": 11.59,
892
- "learning_rate": 1.2235449735449736e-06,
893
- "loss": 0.0298,
894
- "step": 655
895
- },
896
- {
897
- "epoch": 11.68,
898
- "learning_rate": 1.1904761904761906e-06,
899
- "loss": 0.0,
900
- "step": 660
901
- },
902
- {
903
- "epoch": 11.77,
904
- "learning_rate": 1.1574074074074076e-06,
905
- "loss": 0.0,
906
- "step": 665
907
- },
908
- {
909
- "epoch": 11.86,
910
- "learning_rate": 1.1243386243386244e-06,
911
- "loss": 0.0,
912
- "step": 670
913
- },
914
- {
915
- "epoch": 11.95,
916
- "learning_rate": 1.0912698412698414e-06,
917
- "loss": 0.0,
918
- "step": 675
919
- },
920
- {
921
- "epoch": 12.0,
922
- "eval_accuracy": 0.83,
923
- "eval_loss": 1.6370208263397217,
924
- "eval_runtime": 71.6367,
925
- "eval_samples_per_second": 1.396,
926
- "eval_steps_per_second": 0.181,
927
- "step": 678
928
- },
929
- {
930
- "epoch": 12.04,
931
- "learning_rate": 1.0582010582010582e-06,
932
- "loss": 0.0,
933
- "step": 680
934
- },
935
- {
936
- "epoch": 12.12,
937
- "learning_rate": 1.0251322751322752e-06,
938
- "loss": 0.0,
939
- "step": 685
940
- },
941
- {
942
- "epoch": 12.21,
943
- "learning_rate": 9.92063492063492e-07,
944
- "loss": 0.0047,
945
- "step": 690
946
- },
947
- {
948
- "epoch": 12.3,
949
- "learning_rate": 9.58994708994709e-07,
950
- "loss": 0.0,
951
- "step": 695
952
- },
953
- {
954
- "epoch": 12.39,
955
- "learning_rate": 9.259259259259259e-07,
956
- "loss": 0.0,
957
- "step": 700
958
- },
959
- {
960
- "epoch": 12.48,
961
- "learning_rate": 8.928571428571429e-07,
962
- "loss": 0.0073,
963
- "step": 705
964
- },
965
- {
966
- "epoch": 12.57,
967
- "learning_rate": 8.597883597883598e-07,
968
- "loss": 0.0056,
969
- "step": 710
970
- },
971
- {
972
- "epoch": 12.65,
973
- "learning_rate": 8.267195767195769e-07,
974
- "loss": 0.0,
975
- "step": 715
976
- },
977
- {
978
- "epoch": 12.74,
979
- "learning_rate": 7.936507936507937e-07,
980
- "loss": 0.0,
981
- "step": 720
982
- },
983
- {
984
- "epoch": 12.83,
985
- "learning_rate": 7.605820105820107e-07,
986
- "loss": 0.0,
987
- "step": 725
988
- },
989
- {
990
- "epoch": 12.92,
991
- "learning_rate": 7.275132275132276e-07,
992
- "loss": 0.0,
993
- "step": 730
994
- },
995
- {
996
- "epoch": 12.99,
997
- "eval_accuracy": 0.84,
998
- "eval_loss": 1.6395506858825684,
999
- "eval_runtime": 71.0953,
1000
- "eval_samples_per_second": 1.407,
1001
- "eval_steps_per_second": 0.183,
1002
- "step": 734
1003
- },
1004
- {
1005
- "epoch": 13.01,
1006
- "learning_rate": 6.944444444444446e-07,
1007
- "loss": 0.0,
1008
- "step": 735
1009
- },
1010
- {
1011
- "epoch": 13.1,
1012
- "learning_rate": 6.613756613756614e-07,
1013
- "loss": 0.0,
1014
- "step": 740
1015
- },
1016
- {
1017
- "epoch": 13.19,
1018
- "learning_rate": 6.283068783068784e-07,
1019
- "loss": 0.0,
1020
- "step": 745
1021
- },
1022
- {
1023
- "epoch": 13.27,
1024
- "learning_rate": 5.952380952380953e-07,
1025
- "loss": 0.0,
1026
- "step": 750
1027
- },
1028
- {
1029
- "epoch": 13.36,
1030
- "learning_rate": 5.621693121693122e-07,
1031
- "loss": 0.0,
1032
- "step": 755
1033
- },
1034
- {
1035
- "epoch": 13.45,
1036
- "learning_rate": 5.291005291005291e-07,
1037
- "loss": 0.0,
1038
- "step": 760
1039
- },
1040
- {
1041
- "epoch": 13.54,
1042
- "learning_rate": 4.96031746031746e-07,
1043
- "loss": 0.0,
1044
- "step": 765
1045
- },
1046
- {
1047
- "epoch": 13.63,
1048
- "learning_rate": 4.6296296296296297e-07,
1049
- "loss": 0.0013,
1050
- "step": 770
1051
- },
1052
- {
1053
- "epoch": 13.72,
1054
- "learning_rate": 4.298941798941799e-07,
1055
- "loss": 0.0,
1056
- "step": 775
1057
- },
1058
- {
1059
- "epoch": 13.81,
1060
- "learning_rate": 3.9682539682539683e-07,
1061
- "loss": 0.0,
1062
- "step": 780
1063
- },
1064
- {
1065
- "epoch": 13.89,
1066
- "learning_rate": 3.637566137566138e-07,
1067
- "loss": 0.0167,
1068
- "step": 785
1069
- },
1070
- {
1071
- "epoch": 13.98,
1072
- "learning_rate": 3.306878306878307e-07,
1073
- "loss": 0.0,
1074
- "step": 790
1075
- },
1076
- {
1077
- "epoch": 14.0,
1078
- "eval_accuracy": 0.83,
1079
- "eval_loss": 1.6457616090774536,
1080
- "eval_runtime": 71.1459,
1081
- "eval_samples_per_second": 1.406,
1082
- "eval_steps_per_second": 0.183,
1083
- "step": 791
1084
- },
1085
- {
1086
- "epoch": 14.07,
1087
- "learning_rate": 2.9761904761904765e-07,
1088
- "loss": 0.0048,
1089
- "step": 795
1090
- },
1091
- {
1092
- "epoch": 14.16,
1093
- "learning_rate": 2.6455026455026455e-07,
1094
- "loss": 0.0,
1095
- "step": 800
1096
- },
1097
- {
1098
- "epoch": 14.25,
1099
- "learning_rate": 2.3148148148148148e-07,
1100
- "loss": 0.0,
1101
- "step": 805
1102
- },
1103
- {
1104
- "epoch": 14.34,
1105
- "learning_rate": 1.9841269841269841e-07,
1106
- "loss": 0.0032,
1107
- "step": 810
1108
- },
1109
- {
1110
- "epoch": 14.42,
1111
- "learning_rate": 1.6534391534391535e-07,
1112
- "loss": 0.0139,
1113
- "step": 815
1114
- },
1115
- {
1116
- "epoch": 14.51,
1117
- "learning_rate": 1.3227513227513228e-07,
1118
- "loss": 0.0,
1119
- "step": 820
1120
- },
1121
- {
1122
- "epoch": 14.6,
1123
- "learning_rate": 9.920634920634921e-08,
1124
- "loss": 0.0,
1125
- "step": 825
1126
- },
1127
- {
1128
- "epoch": 14.69,
1129
- "learning_rate": 6.613756613756614e-08,
1130
- "loss": 0.0,
1131
- "step": 830
1132
- },
1133
- {
1134
- "epoch": 14.78,
1135
- "learning_rate": 3.306878306878307e-08,
1136
- "loss": 0.0,
1137
- "step": 835
1138
- },
1139
- {
1140
- "epoch": 14.87,
1141
- "learning_rate": 0.0,
1142
- "loss": 0.0,
1143
- "step": 840
1144
- },
1145
- {
1146
- "epoch": 14.87,
1147
- "eval_accuracy": 0.84,
1148
- "eval_loss": 1.6456549167633057,
1149
- "eval_runtime": 71.0369,
1150
- "eval_samples_per_second": 1.408,
1151
- "eval_steps_per_second": 0.183,
1152
- "step": 840
1153
  }
1154
  ],
1155
  "logging_steps": 5,
1156
- "max_steps": 840,
1157
- "num_train_epochs": 15,
1158
  "save_steps": 500,
1159
- "total_flos": 9.122516488512e+17,
1160
  "trial_name": null,
1161
  "trial_params": null
1162
  }
 
1
  {
2
+ "best_metric": 0.73,
3
+ "best_model_checkpoint": "distilhubert-finetuned-gtzan/checkpoint-25",
4
+ "epoch": 1.0,
5
  "eval_steps": 500,
6
+ "global_step": 25,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
10
  "log_history": [
11
  {
12
+ "epoch": 0.2,
13
+ "learning_rate": 0.0002,
14
  "loss": 0.0001,
15
  "step": 5
16
  },
17
  {
18
+ "epoch": 0.4,
19
+ "learning_rate": 0.0004,
20
+ "loss": 0.0427,
21
  "step": 10
22
  },
23
  {
24
+ "epoch": 0.6,
25
+ "learning_rate": 0.0006,
26
+ "loss": 0.2245,
27
  "step": 15
28
  },
29
  {
30
+ "epoch": 0.8,
31
+ "learning_rate": 0.0008,
32
+ "loss": 0.468,
33
  "step": 20
34
  },
35
  {
36
+ "epoch": 1.0,
37
+ "learning_rate": 0.001,
38
+ "loss": 0.8622,
39
  "step": 25
40
  },
41
  {
42
+ "epoch": 1.0,
43
+ "eval_accuracy": 0.73,
44
+ "eval_loss": 2.1819140911102295,
45
+ "eval_runtime": 144.9991,
46
+ "eval_samples_per_second": 1.379,
47
+ "eval_steps_per_second": 0.172,
48
+ "step": 25
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
49
  }
50
  ],
51
  "logging_steps": 5,
52
+ "max_steps": 250,
53
+ "num_train_epochs": 10,
54
  "save_steps": 500,
55
+ "total_flos": 5.451675897024e+16,
56
  "trial_name": null,
57
  "trial_params": null
58
  }
last-checkpoint/training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f201f92b1984b0cbbfd55feeb841b3f59e725f47ab7f696c582cfa82b18ccaa2
3
  size 4600
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d7059aed49f7f3c702864807bd132052921d120cd16c44ab7882c5c6d6a30a3f
3
  size 4600