JackWong0911 commited on
Commit
c332aa0
1 Parent(s): 605b3bd

End of training

Browse files
all_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 5.1,
3
+ "eval_accuracy": 0.96,
4
+ "eval_loss": 0.1763344407081604,
5
+ "eval_runtime": 17.9669,
6
+ "eval_samples_per_second": 1.391,
7
+ "eval_steps_per_second": 0.39
8
+ }
runs/Apr21_07-47-29_6cf390ac2b33/events.out.tfevents.1713686250.6cf390ac2b33.8244.1 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1c4ee02aebaea3683cd2a7034674c20bc6ece509a11aa98fd05ad958dd23d682
3
- size 1112
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a9734978db4bbfc2c50bf14ea7e03519629a3be7b9c4e1165cda3d7b0cd78acd
3
+ size 2136
test_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 5.1,
3
+ "eval_accuracy": 0.96,
4
+ "eval_loss": 0.1763344407081604,
5
+ "eval_runtime": 17.9669,
6
+ "eval_samples_per_second": 1.391,
7
+ "eval_steps_per_second": 0.39
8
+ }
trainer_state.json ADDED
@@ -0,0 +1,791 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.96,
3
+ "best_model_checkpoint": "timesformer-base-finetuned-k400-kinetic400-subset-epoch6-num_frame_10_myViT2window3_more_data_b4/checkpoint-39",
4
+ "epoch": 5.097222222222222,
5
+ "eval_steps": 500,
6
+ "global_step": 72,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "accuracy": 0.0,
13
+ "epoch": 0,
14
+ "step": 0
15
+ },
16
+ {
17
+ "accuracy": 0.25,
18
+ "epoch": 0.01,
19
+ "step": 1
20
+ },
21
+ {
22
+ "accuracy": 0.25,
23
+ "epoch": 0.03,
24
+ "step": 2
25
+ },
26
+ {
27
+ "accuracy": 0.75,
28
+ "epoch": 0.04,
29
+ "step": 3
30
+ },
31
+ {
32
+ "accuracy": 0.0,
33
+ "epoch": 0.06,
34
+ "step": 4
35
+ },
36
+ {
37
+ "accuracy": 0.0,
38
+ "epoch": 0.07,
39
+ "step": 5
40
+ },
41
+ {
42
+ "accuracy": 0.5,
43
+ "epoch": 0.08,
44
+ "step": 6
45
+ },
46
+ {
47
+ "accuracy": 0.75,
48
+ "epoch": 0.1,
49
+ "step": 7
50
+ },
51
+ {
52
+ "accuracy": 0.75,
53
+ "epoch": 0.11,
54
+ "step": 8
55
+ },
56
+ {
57
+ "accuracy": 1.0,
58
+ "epoch": 0.12,
59
+ "step": 9
60
+ },
61
+ {
62
+ "epoch": 0.14,
63
+ "grad_norm": 11.168214797973633,
64
+ "learning_rate": 4.8437500000000005e-05,
65
+ "loss": 1.4033,
66
+ "step": 10
67
+ },
68
+ {
69
+ "accuracy": 0.75,
70
+ "epoch": 0.14,
71
+ "step": 10
72
+ },
73
+ {
74
+ "accuracy": 1.0,
75
+ "epoch": 0.15,
76
+ "step": 11
77
+ },
78
+ {
79
+ "accuracy": 1.0,
80
+ "epoch": 0.17,
81
+ "step": 12
82
+ },
83
+ {
84
+ "accuracy": 0.5,
85
+ "epoch": 0.18,
86
+ "step": 13
87
+ },
88
+ {
89
+ "accuracy": 1.0,
90
+ "epoch": 0.18,
91
+ "step": 13
92
+ },
93
+ {
94
+ "accuracy": 1.0,
95
+ "epoch": 0.18,
96
+ "step": 13
97
+ },
98
+ {
99
+ "accuracy": 1.0,
100
+ "epoch": 0.18,
101
+ "step": 13
102
+ },
103
+ {
104
+ "accuracy": 0.75,
105
+ "epoch": 0.18,
106
+ "step": 13
107
+ },
108
+ {
109
+ "accuracy": 1.0,
110
+ "epoch": 0.18,
111
+ "step": 13
112
+ },
113
+ {
114
+ "accuracy": 1.0,
115
+ "epoch": 0.18,
116
+ "step": 13
117
+ },
118
+ {
119
+ "epoch": 0.18,
120
+ "eval_accuracy": 0.88,
121
+ "eval_loss": 0.5778742432594299,
122
+ "eval_runtime": 27.5022,
123
+ "eval_samples_per_second": 0.909,
124
+ "eval_steps_per_second": 0.255,
125
+ "step": 13
126
+ },
127
+ {
128
+ "accuracy": 1.0,
129
+ "epoch": 0.18,
130
+ "step": 13
131
+ },
132
+ {
133
+ "accuracy": 1.0,
134
+ "epoch": 1.01,
135
+ "step": 14
136
+ },
137
+ {
138
+ "accuracy": 1.0,
139
+ "epoch": 1.03,
140
+ "step": 15
141
+ },
142
+ {
143
+ "accuracy": 1.0,
144
+ "epoch": 1.04,
145
+ "step": 16
146
+ },
147
+ {
148
+ "accuracy": 1.0,
149
+ "epoch": 1.06,
150
+ "step": 17
151
+ },
152
+ {
153
+ "accuracy": 1.0,
154
+ "epoch": 1.07,
155
+ "step": 18
156
+ },
157
+ {
158
+ "accuracy": 1.0,
159
+ "epoch": 1.08,
160
+ "step": 19
161
+ },
162
+ {
163
+ "epoch": 1.1,
164
+ "grad_norm": 2.1656227111816406,
165
+ "learning_rate": 4.0625000000000005e-05,
166
+ "loss": 0.3402,
167
+ "step": 20
168
+ },
169
+ {
170
+ "accuracy": 1.0,
171
+ "epoch": 1.1,
172
+ "step": 20
173
+ },
174
+ {
175
+ "accuracy": 1.0,
176
+ "epoch": 1.11,
177
+ "step": 21
178
+ },
179
+ {
180
+ "accuracy": 1.0,
181
+ "epoch": 1.12,
182
+ "step": 22
183
+ },
184
+ {
185
+ "accuracy": 1.0,
186
+ "epoch": 1.14,
187
+ "step": 23
188
+ },
189
+ {
190
+ "accuracy": 1.0,
191
+ "epoch": 1.15,
192
+ "step": 24
193
+ },
194
+ {
195
+ "accuracy": 1.0,
196
+ "epoch": 1.17,
197
+ "step": 25
198
+ },
199
+ {
200
+ "accuracy": 0.75,
201
+ "epoch": 1.18,
202
+ "step": 26
203
+ },
204
+ {
205
+ "accuracy": 1.0,
206
+ "epoch": 1.18,
207
+ "step": 26
208
+ },
209
+ {
210
+ "accuracy": 0.75,
211
+ "epoch": 1.18,
212
+ "step": 26
213
+ },
214
+ {
215
+ "accuracy": 1.0,
216
+ "epoch": 1.18,
217
+ "step": 26
218
+ },
219
+ {
220
+ "accuracy": 0.75,
221
+ "epoch": 1.18,
222
+ "step": 26
223
+ },
224
+ {
225
+ "accuracy": 1.0,
226
+ "epoch": 1.18,
227
+ "step": 26
228
+ },
229
+ {
230
+ "accuracy": 0.0,
231
+ "epoch": 1.18,
232
+ "step": 26
233
+ },
234
+ {
235
+ "epoch": 1.18,
236
+ "eval_accuracy": 0.84,
237
+ "eval_loss": 0.33898457884788513,
238
+ "eval_runtime": 27.8625,
239
+ "eval_samples_per_second": 0.897,
240
+ "eval_steps_per_second": 0.251,
241
+ "step": 26
242
+ },
243
+ {
244
+ "accuracy": 1.0,
245
+ "epoch": 1.18,
246
+ "step": 26
247
+ },
248
+ {
249
+ "accuracy": 1.0,
250
+ "epoch": 2.01,
251
+ "step": 27
252
+ },
253
+ {
254
+ "accuracy": 1.0,
255
+ "epoch": 2.03,
256
+ "step": 28
257
+ },
258
+ {
259
+ "accuracy": 1.0,
260
+ "epoch": 2.04,
261
+ "step": 29
262
+ },
263
+ {
264
+ "epoch": 2.06,
265
+ "grad_norm": 0.17987509071826935,
266
+ "learning_rate": 3.2812500000000005e-05,
267
+ "loss": 0.0426,
268
+ "step": 30
269
+ },
270
+ {
271
+ "accuracy": 1.0,
272
+ "epoch": 2.06,
273
+ "step": 30
274
+ },
275
+ {
276
+ "accuracy": 1.0,
277
+ "epoch": 2.07,
278
+ "step": 31
279
+ },
280
+ {
281
+ "accuracy": 1.0,
282
+ "epoch": 2.08,
283
+ "step": 32
284
+ },
285
+ {
286
+ "accuracy": 1.0,
287
+ "epoch": 2.1,
288
+ "step": 33
289
+ },
290
+ {
291
+ "accuracy": 1.0,
292
+ "epoch": 2.11,
293
+ "step": 34
294
+ },
295
+ {
296
+ "accuracy": 1.0,
297
+ "epoch": 2.12,
298
+ "step": 35
299
+ },
300
+ {
301
+ "accuracy": 1.0,
302
+ "epoch": 2.14,
303
+ "step": 36
304
+ },
305
+ {
306
+ "accuracy": 1.0,
307
+ "epoch": 2.15,
308
+ "step": 37
309
+ },
310
+ {
311
+ "accuracy": 1.0,
312
+ "epoch": 2.17,
313
+ "step": 38
314
+ },
315
+ {
316
+ "accuracy": 1.0,
317
+ "epoch": 2.18,
318
+ "step": 39
319
+ },
320
+ {
321
+ "accuracy": 1.0,
322
+ "epoch": 2.18,
323
+ "step": 39
324
+ },
325
+ {
326
+ "accuracy": 1.0,
327
+ "epoch": 2.18,
328
+ "step": 39
329
+ },
330
+ {
331
+ "accuracy": 1.0,
332
+ "epoch": 2.18,
333
+ "step": 39
334
+ },
335
+ {
336
+ "accuracy": 0.75,
337
+ "epoch": 2.18,
338
+ "step": 39
339
+ },
340
+ {
341
+ "accuracy": 1.0,
342
+ "epoch": 2.18,
343
+ "step": 39
344
+ },
345
+ {
346
+ "accuracy": 1.0,
347
+ "epoch": 2.18,
348
+ "step": 39
349
+ },
350
+ {
351
+ "epoch": 2.18,
352
+ "eval_accuracy": 0.96,
353
+ "eval_loss": 0.21377582848072052,
354
+ "eval_runtime": 27.0552,
355
+ "eval_samples_per_second": 0.924,
356
+ "eval_steps_per_second": 0.259,
357
+ "step": 39
358
+ },
359
+ {
360
+ "accuracy": 1.0,
361
+ "epoch": 2.18,
362
+ "step": 39
363
+ },
364
+ {
365
+ "epoch": 3.01,
366
+ "grad_norm": 0.11805030703544617,
367
+ "learning_rate": 2.5e-05,
368
+ "loss": 0.0121,
369
+ "step": 40
370
+ },
371
+ {
372
+ "accuracy": 1.0,
373
+ "epoch": 3.01,
374
+ "step": 40
375
+ },
376
+ {
377
+ "accuracy": 1.0,
378
+ "epoch": 3.03,
379
+ "step": 41
380
+ },
381
+ {
382
+ "accuracy": 1.0,
383
+ "epoch": 3.04,
384
+ "step": 42
385
+ },
386
+ {
387
+ "accuracy": 1.0,
388
+ "epoch": 3.06,
389
+ "step": 43
390
+ },
391
+ {
392
+ "accuracy": 1.0,
393
+ "epoch": 3.07,
394
+ "step": 44
395
+ },
396
+ {
397
+ "accuracy": 1.0,
398
+ "epoch": 3.08,
399
+ "step": 45
400
+ },
401
+ {
402
+ "accuracy": 1.0,
403
+ "epoch": 3.1,
404
+ "step": 46
405
+ },
406
+ {
407
+ "accuracy": 1.0,
408
+ "epoch": 3.11,
409
+ "step": 47
410
+ },
411
+ {
412
+ "accuracy": 1.0,
413
+ "epoch": 3.12,
414
+ "step": 48
415
+ },
416
+ {
417
+ "accuracy": 1.0,
418
+ "epoch": 3.14,
419
+ "step": 49
420
+ },
421
+ {
422
+ "epoch": 3.15,
423
+ "grad_norm": 0.07389847934246063,
424
+ "learning_rate": 1.71875e-05,
425
+ "loss": 0.0049,
426
+ "step": 50
427
+ },
428
+ {
429
+ "accuracy": 1.0,
430
+ "epoch": 3.15,
431
+ "step": 50
432
+ },
433
+ {
434
+ "accuracy": 1.0,
435
+ "epoch": 3.17,
436
+ "step": 51
437
+ },
438
+ {
439
+ "accuracy": 1.0,
440
+ "epoch": 3.18,
441
+ "step": 52
442
+ },
443
+ {
444
+ "accuracy": 1.0,
445
+ "epoch": 3.18,
446
+ "step": 52
447
+ },
448
+ {
449
+ "accuracy": 1.0,
450
+ "epoch": 3.18,
451
+ "step": 52
452
+ },
453
+ {
454
+ "accuracy": 1.0,
455
+ "epoch": 3.18,
456
+ "step": 52
457
+ },
458
+ {
459
+ "accuracy": 0.75,
460
+ "epoch": 3.18,
461
+ "step": 52
462
+ },
463
+ {
464
+ "accuracy": 0.75,
465
+ "epoch": 3.18,
466
+ "step": 52
467
+ },
468
+ {
469
+ "accuracy": 1.0,
470
+ "epoch": 3.18,
471
+ "step": 52
472
+ },
473
+ {
474
+ "epoch": 3.18,
475
+ "eval_accuracy": 0.92,
476
+ "eval_loss": 0.18079356849193573,
477
+ "eval_runtime": 27.6737,
478
+ "eval_samples_per_second": 0.903,
479
+ "eval_steps_per_second": 0.253,
480
+ "step": 52
481
+ },
482
+ {
483
+ "accuracy": 1.0,
484
+ "epoch": 3.18,
485
+ "step": 52
486
+ },
487
+ {
488
+ "accuracy": 1.0,
489
+ "epoch": 4.01,
490
+ "step": 53
491
+ },
492
+ {
493
+ "accuracy": 1.0,
494
+ "epoch": 4.03,
495
+ "step": 54
496
+ },
497
+ {
498
+ "accuracy": 1.0,
499
+ "epoch": 4.04,
500
+ "step": 55
501
+ },
502
+ {
503
+ "accuracy": 1.0,
504
+ "epoch": 4.06,
505
+ "step": 56
506
+ },
507
+ {
508
+ "accuracy": 1.0,
509
+ "epoch": 4.07,
510
+ "step": 57
511
+ },
512
+ {
513
+ "accuracy": 1.0,
514
+ "epoch": 4.08,
515
+ "step": 58
516
+ },
517
+ {
518
+ "accuracy": 1.0,
519
+ "epoch": 4.1,
520
+ "step": 59
521
+ },
522
+ {
523
+ "epoch": 4.11,
524
+ "grad_norm": 0.16879861056804657,
525
+ "learning_rate": 9.375000000000001e-06,
526
+ "loss": 0.0029,
527
+ "step": 60
528
+ },
529
+ {
530
+ "accuracy": 1.0,
531
+ "epoch": 4.11,
532
+ "step": 60
533
+ },
534
+ {
535
+ "accuracy": 1.0,
536
+ "epoch": 4.12,
537
+ "step": 61
538
+ },
539
+ {
540
+ "accuracy": 1.0,
541
+ "epoch": 4.14,
542
+ "step": 62
543
+ },
544
+ {
545
+ "accuracy": 1.0,
546
+ "epoch": 4.15,
547
+ "step": 63
548
+ },
549
+ {
550
+ "accuracy": 1.0,
551
+ "epoch": 4.17,
552
+ "step": 64
553
+ },
554
+ {
555
+ "accuracy": 1.0,
556
+ "epoch": 4.18,
557
+ "step": 65
558
+ },
559
+ {
560
+ "accuracy": 0.75,
561
+ "epoch": 4.18,
562
+ "step": 65
563
+ },
564
+ {
565
+ "accuracy": 1.0,
566
+ "epoch": 4.18,
567
+ "step": 65
568
+ },
569
+ {
570
+ "accuracy": 1.0,
571
+ "epoch": 4.18,
572
+ "step": 65
573
+ },
574
+ {
575
+ "accuracy": 0.75,
576
+ "epoch": 4.18,
577
+ "step": 65
578
+ },
579
+ {
580
+ "accuracy": 1.0,
581
+ "epoch": 4.18,
582
+ "step": 65
583
+ },
584
+ {
585
+ "accuracy": 1.0,
586
+ "epoch": 4.18,
587
+ "step": 65
588
+ },
589
+ {
590
+ "epoch": 4.18,
591
+ "eval_accuracy": 0.92,
592
+ "eval_loss": 0.1889605075120926,
593
+ "eval_runtime": 25.2006,
594
+ "eval_samples_per_second": 0.992,
595
+ "eval_steps_per_second": 0.278,
596
+ "step": 65
597
+ },
598
+ {
599
+ "accuracy": 1.0,
600
+ "epoch": 4.18,
601
+ "step": 65
602
+ },
603
+ {
604
+ "accuracy": 1.0,
605
+ "epoch": 5.01,
606
+ "step": 66
607
+ },
608
+ {
609
+ "accuracy": 1.0,
610
+ "epoch": 5.03,
611
+ "step": 67
612
+ },
613
+ {
614
+ "accuracy": 1.0,
615
+ "epoch": 5.04,
616
+ "step": 68
617
+ },
618
+ {
619
+ "accuracy": 1.0,
620
+ "epoch": 5.06,
621
+ "step": 69
622
+ },
623
+ {
624
+ "epoch": 5.07,
625
+ "grad_norm": 0.03316669911146164,
626
+ "learning_rate": 1.5625e-06,
627
+ "loss": 0.0022,
628
+ "step": 70
629
+ },
630
+ {
631
+ "accuracy": 1.0,
632
+ "epoch": 5.07,
633
+ "step": 70
634
+ },
635
+ {
636
+ "accuracy": 1.0,
637
+ "epoch": 5.08,
638
+ "step": 71
639
+ },
640
+ {
641
+ "accuracy": 0.75,
642
+ "epoch": 5.1,
643
+ "step": 72
644
+ },
645
+ {
646
+ "accuracy": 0.75,
647
+ "epoch": 5.1,
648
+ "step": 72
649
+ },
650
+ {
651
+ "accuracy": 1.0,
652
+ "epoch": 5.1,
653
+ "step": 72
654
+ },
655
+ {
656
+ "accuracy": 1.0,
657
+ "epoch": 5.1,
658
+ "step": 72
659
+ },
660
+ {
661
+ "accuracy": 1.0,
662
+ "epoch": 5.1,
663
+ "step": 72
664
+ },
665
+ {
666
+ "accuracy": 1.0,
667
+ "epoch": 5.1,
668
+ "step": 72
669
+ },
670
+ {
671
+ "accuracy": 1.0,
672
+ "epoch": 5.1,
673
+ "step": 72
674
+ },
675
+ {
676
+ "epoch": 5.1,
677
+ "eval_accuracy": 0.92,
678
+ "eval_loss": 0.18929095566272736,
679
+ "eval_runtime": 25.0662,
680
+ "eval_samples_per_second": 0.997,
681
+ "eval_steps_per_second": 0.279,
682
+ "step": 72
683
+ },
684
+ {
685
+ "epoch": 5.1,
686
+ "step": 72,
687
+ "total_flos": 3.044708388358963e+17,
688
+ "train_loss": 0.25122544505090144,
689
+ "train_runtime": 480.2289,
690
+ "train_samples_per_second": 0.6,
691
+ "train_steps_per_second": 0.15
692
+ },
693
+ {
694
+ "accuracy": 1.0,
695
+ "epoch": 5.1,
696
+ "step": 72
697
+ },
698
+ {
699
+ "accuracy": 1.0,
700
+ "epoch": 5.1,
701
+ "step": 72
702
+ },
703
+ {
704
+ "accuracy": 1.0,
705
+ "epoch": 5.1,
706
+ "step": 72
707
+ },
708
+ {
709
+ "accuracy": 1.0,
710
+ "epoch": 5.1,
711
+ "step": 72
712
+ },
713
+ {
714
+ "accuracy": 1.0,
715
+ "epoch": 5.1,
716
+ "step": 72
717
+ },
718
+ {
719
+ "accuracy": 1.0,
720
+ "epoch": 5.1,
721
+ "step": 72
722
+ },
723
+ {
724
+ "accuracy": 0.0,
725
+ "epoch": 5.1,
726
+ "step": 72
727
+ },
728
+ {
729
+ "epoch": 5.1,
730
+ "eval_accuracy": 0.96,
731
+ "eval_loss": 0.1763344556093216,
732
+ "eval_runtime": 17.7295,
733
+ "eval_samples_per_second": 1.41,
734
+ "eval_steps_per_second": 0.395,
735
+ "step": 72
736
+ },
737
+ {
738
+ "accuracy": 1.0,
739
+ "epoch": 5.1,
740
+ "step": 72
741
+ },
742
+ {
743
+ "accuracy": 0.75,
744
+ "epoch": 5.1,
745
+ "step": 72
746
+ },
747
+ {
748
+ "accuracy": 1.0,
749
+ "epoch": 5.1,
750
+ "step": 72
751
+ },
752
+ {
753
+ "accuracy": 1.0,
754
+ "epoch": 5.1,
755
+ "step": 72
756
+ },
757
+ {
758
+ "accuracy": 1.0,
759
+ "epoch": 5.1,
760
+ "step": 72
761
+ },
762
+ {
763
+ "accuracy": 1.0,
764
+ "epoch": 5.1,
765
+ "step": 72
766
+ },
767
+ {
768
+ "accuracy": 1.0,
769
+ "epoch": 5.1,
770
+ "step": 72
771
+ },
772
+ {
773
+ "epoch": 5.1,
774
+ "eval_accuracy": 0.96,
775
+ "eval_loss": 0.1763344407081604,
776
+ "eval_runtime": 17.9669,
777
+ "eval_samples_per_second": 1.391,
778
+ "eval_steps_per_second": 0.39,
779
+ "step": 72
780
+ }
781
+ ],
782
+ "logging_steps": 10,
783
+ "max_steps": 72,
784
+ "num_input_tokens_seen": 0,
785
+ "num_train_epochs": 9223372036854775807,
786
+ "save_steps": 500,
787
+ "total_flos": 3.044708388358963e+17,
788
+ "train_batch_size": 4,
789
+ "trial_name": null,
790
+ "trial_params": null
791
+ }