phunc20 commited on
Commit
d98b3dd
1 Parent(s): 7251827

End of training

Browse files
all_results.json CHANGED
@@ -1,13 +1,13 @@
1
  {
2
- "epoch": 50.0,
3
- "eval_accuracy": 1.0,
4
- "eval_loss": 0.020261267200112343,
5
- "eval_runtime": 1.8244,
6
- "eval_samples_per_second": 19.733,
7
- "eval_steps_per_second": 0.548,
8
- "total_flos": 3.989386232229888e+17,
9
- "train_loss": 0.12627770403089622,
10
- "train_runtime": 1656.8438,
11
- "train_samples_per_second": 9.687,
12
- "train_steps_per_second": 0.091
13
  }
 
1
  {
2
+ "epoch": 20.0,
3
+ "eval_accuracy": 0.4,
4
+ "eval_loss": 0.7953054904937744,
5
+ "eval_runtime": 2.2455,
6
+ "eval_samples_per_second": 20.04,
7
+ "eval_steps_per_second": 0.445,
8
+ "total_flos": 1.7747176135901184e+17,
9
+ "train_loss": 0.1779410476485888,
10
+ "train_runtime": 979.9272,
11
+ "train_samples_per_second": 7.286,
12
+ "train_steps_per_second": 0.061
13
  }
eval_results.json CHANGED
@@ -1,8 +1,8 @@
1
  {
2
- "epoch": 50.0,
3
- "eval_accuracy": 1.0,
4
- "eval_loss": 0.020261267200112343,
5
- "eval_runtime": 1.8244,
6
- "eval_samples_per_second": 19.733,
7
- "eval_steps_per_second": 0.548
8
  }
 
1
  {
2
+ "epoch": 20.0,
3
+ "eval_accuracy": 0.4,
4
+ "eval_loss": 0.7953054904937744,
5
+ "eval_runtime": 2.2455,
6
+ "eval_samples_per_second": 20.04,
7
+ "eval_steps_per_second": 0.445
8
  }
runs/Jul28_14-07-40_8444a3ebd71c/events.out.tfevents.1690554363.8444a3ebd71c.1196.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:570d924efa2792091a5cc016a749af6141a0489eab1795854922becc34ad8dd5
3
+ size 405
train_results.json CHANGED
@@ -1,8 +1,8 @@
1
  {
2
- "epoch": 50.0,
3
- "total_flos": 3.989386232229888e+17,
4
- "train_loss": 0.12627770403089622,
5
- "train_runtime": 1656.8438,
6
- "train_samples_per_second": 9.687,
7
- "train_steps_per_second": 0.091
8
  }
 
1
  {
2
+ "epoch": 20.0,
3
+ "total_flos": 1.7747176135901184e+17,
4
+ "train_loss": 0.1779410476485888,
5
+ "train_runtime": 979.9272,
6
+ "train_samples_per_second": 7.286,
7
+ "train_steps_per_second": 0.061
8
  }
trainer_state.json CHANGED
@@ -1,565 +1,241 @@
1
  {
2
- "best_metric": 1.0,
3
- "best_model_checkpoint": "swin-tiny-patch4-window7-224-finetuned-wuhan/checkpoint-51",
4
- "epoch": 50.0,
5
- "global_step": 150,
6
  "is_hyper_param_search": false,
7
  "is_local_process_zero": true,
8
  "is_world_process_zero": true,
9
  "log_history": [
10
  {
11
  "epoch": 1.0,
12
- "eval_accuracy": 0.7777777777777778,
13
- "eval_loss": 0.6245499849319458,
14
- "eval_runtime": 24.4847,
15
- "eval_samples_per_second": 1.47,
16
- "eval_steps_per_second": 0.041,
17
  "step": 3
18
  },
19
  {
20
  "epoch": 2.0,
21
- "eval_accuracy": 0.7777777777777778,
22
- "eval_loss": 0.5320722460746765,
23
- "eval_runtime": 1.652,
24
- "eval_samples_per_second": 21.791,
25
- "eval_steps_per_second": 0.605,
26
  "step": 6
27
  },
28
  {
29
  "epoch": 3.0,
30
- "eval_accuracy": 0.7777777777777778,
31
- "eval_loss": 0.5123355388641357,
32
- "eval_runtime": 1.6429,
33
- "eval_samples_per_second": 21.912,
34
- "eval_steps_per_second": 0.609,
35
  "step": 9
36
  },
37
  {
38
  "epoch": 3.33,
39
- "learning_rate": 3.3333333333333335e-05,
40
- "loss": 0.6482,
41
  "step": 10
42
  },
43
  {
44
  "epoch": 4.0,
45
- "eval_accuracy": 0.7777777777777778,
46
- "eval_loss": 0.4955737888813019,
47
- "eval_runtime": 1.6364,
48
- "eval_samples_per_second": 22.0,
49
- "eval_steps_per_second": 0.611,
50
  "step": 12
51
  },
52
  {
53
  "epoch": 5.0,
54
- "eval_accuracy": 0.7777777777777778,
55
- "eval_loss": 0.4585157632827759,
56
- "eval_runtime": 1.6942,
57
- "eval_samples_per_second": 21.249,
58
- "eval_steps_per_second": 0.59,
59
  "step": 15
60
  },
61
  {
62
  "epoch": 6.0,
63
- "eval_accuracy": 0.8611111111111112,
64
- "eval_loss": 0.374308705329895,
65
- "eval_runtime": 1.632,
66
- "eval_samples_per_second": 22.058,
67
- "eval_steps_per_second": 0.613,
68
  "step": 18
69
  },
70
  {
71
  "epoch": 6.67,
72
- "learning_rate": 4.814814814814815e-05,
73
- "loss": 0.5574,
74
  "step": 20
75
  },
76
  {
77
  "epoch": 7.0,
78
- "eval_accuracy": 0.9166666666666666,
79
- "eval_loss": 0.28418225049972534,
80
- "eval_runtime": 1.6051,
81
- "eval_samples_per_second": 22.429,
82
- "eval_steps_per_second": 0.623,
83
  "step": 21
84
  },
85
  {
86
  "epoch": 8.0,
87
- "eval_accuracy": 0.9166666666666666,
88
- "eval_loss": 0.21250946819782257,
89
- "eval_runtime": 1.6507,
90
- "eval_samples_per_second": 21.809,
91
- "eval_steps_per_second": 0.606,
92
  "step": 24
93
  },
94
  {
95
  "epoch": 9.0,
96
- "eval_accuracy": 0.9166666666666666,
97
- "eval_loss": 0.268328458070755,
98
- "eval_runtime": 1.6501,
99
- "eval_samples_per_second": 21.816,
100
- "eval_steps_per_second": 0.606,
101
  "step": 27
102
  },
103
  {
104
  "epoch": 10.0,
105
- "learning_rate": 4.4444444444444447e-05,
106
- "loss": 0.4882,
107
  "step": 30
108
  },
109
  {
110
  "epoch": 10.0,
111
- "eval_accuracy": 0.9444444444444444,
112
- "eval_loss": 0.13163453340530396,
113
- "eval_runtime": 1.6879,
114
- "eval_samples_per_second": 21.329,
115
- "eval_steps_per_second": 0.592,
116
  "step": 30
117
  },
118
  {
119
  "epoch": 11.0,
120
- "eval_accuracy": 0.9444444444444444,
121
- "eval_loss": 0.13660234212875366,
122
- "eval_runtime": 1.7137,
123
- "eval_samples_per_second": 21.007,
124
- "eval_steps_per_second": 0.584,
125
  "step": 33
126
  },
127
  {
128
  "epoch": 12.0,
129
- "eval_accuracy": 0.9722222222222222,
130
- "eval_loss": 0.07448268681764603,
131
- "eval_runtime": 1.7626,
132
- "eval_samples_per_second": 20.424,
133
- "eval_steps_per_second": 0.567,
134
  "step": 36
135
  },
136
  {
137
  "epoch": 13.0,
138
- "eval_accuracy": 0.9444444444444444,
139
- "eval_loss": 0.10653182864189148,
140
- "eval_runtime": 1.7029,
141
- "eval_samples_per_second": 21.14,
142
- "eval_steps_per_second": 0.587,
143
  "step": 39
144
  },
145
  {
146
  "epoch": 13.33,
147
- "learning_rate": 4.074074074074074e-05,
148
- "loss": 0.0907,
149
  "step": 40
150
  },
151
  {
152
  "epoch": 14.0,
153
- "eval_accuracy": 0.9722222222222222,
154
- "eval_loss": 0.04769667983055115,
155
- "eval_runtime": 1.7434,
156
- "eval_samples_per_second": 20.65,
157
- "eval_steps_per_second": 0.574,
158
  "step": 42
159
  },
160
  {
161
  "epoch": 15.0,
162
- "eval_accuracy": 0.9444444444444444,
163
- "eval_loss": 0.045971717685461044,
164
- "eval_runtime": 1.6711,
165
- "eval_samples_per_second": 21.543,
166
- "eval_steps_per_second": 0.598,
167
  "step": 45
168
  },
169
  {
170
  "epoch": 16.0,
171
- "eval_accuracy": 0.9722222222222222,
172
- "eval_loss": 0.04381129518151283,
173
- "eval_runtime": 1.6352,
174
- "eval_samples_per_second": 22.016,
175
- "eval_steps_per_second": 0.612,
176
  "step": 48
177
  },
178
  {
179
  "epoch": 16.67,
180
- "learning_rate": 3.7037037037037037e-05,
181
- "loss": 0.0481,
182
  "step": 50
183
  },
184
  {
185
  "epoch": 17.0,
186
- "eval_accuracy": 1.0,
187
- "eval_loss": 0.020261267200112343,
188
- "eval_runtime": 1.6614,
189
- "eval_samples_per_second": 21.668,
190
- "eval_steps_per_second": 0.602,
191
  "step": 51
192
  },
193
  {
194
  "epoch": 18.0,
195
- "eval_accuracy": 1.0,
196
- "eval_loss": 0.009294789284467697,
197
- "eval_runtime": 1.6224,
198
- "eval_samples_per_second": 22.19,
199
- "eval_steps_per_second": 0.616,
200
  "step": 54
201
  },
202
  {
203
  "epoch": 19.0,
204
- "eval_accuracy": 1.0,
205
- "eval_loss": 0.008234969340264797,
206
- "eval_runtime": 1.6449,
207
- "eval_samples_per_second": 21.885,
208
- "eval_steps_per_second": 0.608,
209
  "step": 57
210
  },
211
  {
212
  "epoch": 20.0,
213
- "learning_rate": 3.3333333333333335e-05,
214
- "loss": 0.013,
215
  "step": 60
216
  },
217
  {
218
  "epoch": 20.0,
219
- "eval_accuracy": 1.0,
220
- "eval_loss": 0.0017433015163987875,
221
- "eval_runtime": 1.6486,
222
- "eval_samples_per_second": 21.837,
223
- "eval_steps_per_second": 0.607,
224
  "step": 60
225
  },
226
  {
227
- "epoch": 21.0,
228
- "eval_accuracy": 1.0,
229
- "eval_loss": 0.0007768174400553107,
230
- "eval_runtime": 1.7052,
231
- "eval_samples_per_second": 21.112,
232
- "eval_steps_per_second": 0.586,
233
- "step": 63
234
- },
235
- {
236
- "epoch": 22.0,
237
- "eval_accuracy": 1.0,
238
- "eval_loss": 0.00018507178174331784,
239
- "eval_runtime": 1.7002,
240
- "eval_samples_per_second": 21.174,
241
- "eval_steps_per_second": 0.588,
242
- "step": 66
243
- },
244
- {
245
- "epoch": 23.0,
246
- "eval_accuracy": 1.0,
247
- "eval_loss": 0.00012737045472022146,
248
- "eval_runtime": 1.6699,
249
- "eval_samples_per_second": 21.558,
250
- "eval_steps_per_second": 0.599,
251
- "step": 69
252
- },
253
- {
254
- "epoch": 23.33,
255
- "learning_rate": 2.962962962962963e-05,
256
- "loss": 0.0101,
257
- "step": 70
258
- },
259
- {
260
- "epoch": 24.0,
261
- "eval_accuracy": 0.9722222222222222,
262
- "eval_loss": 0.09382671862840652,
263
- "eval_runtime": 1.6527,
264
- "eval_samples_per_second": 21.783,
265
- "eval_steps_per_second": 0.605,
266
- "step": 72
267
- },
268
- {
269
- "epoch": 25.0,
270
- "eval_accuracy": 0.9722222222222222,
271
- "eval_loss": 0.10189218819141388,
272
- "eval_runtime": 1.6545,
273
- "eval_samples_per_second": 21.758,
274
- "eval_steps_per_second": 0.604,
275
- "step": 75
276
- },
277
- {
278
- "epoch": 26.0,
279
- "eval_accuracy": 1.0,
280
- "eval_loss": 0.0005055955843999982,
281
- "eval_runtime": 1.7212,
282
- "eval_samples_per_second": 20.916,
283
- "eval_steps_per_second": 0.581,
284
- "step": 78
285
- },
286
- {
287
- "epoch": 26.67,
288
- "learning_rate": 2.5925925925925925e-05,
289
- "loss": 0.0085,
290
- "step": 80
291
- },
292
- {
293
- "epoch": 27.0,
294
- "eval_accuracy": 1.0,
295
- "eval_loss": 1.9300923668197356e-05,
296
- "eval_runtime": 1.7849,
297
- "eval_samples_per_second": 20.17,
298
- "eval_steps_per_second": 0.56,
299
- "step": 81
300
- },
301
- {
302
- "epoch": 28.0,
303
- "eval_accuracy": 1.0,
304
- "eval_loss": 1.1416644156270195e-05,
305
- "eval_runtime": 1.7789,
306
- "eval_samples_per_second": 20.237,
307
- "eval_steps_per_second": 0.562,
308
- "step": 84
309
- },
310
- {
311
- "epoch": 29.0,
312
- "eval_accuracy": 1.0,
313
- "eval_loss": 5.5924607295310125e-05,
314
- "eval_runtime": 1.6926,
315
- "eval_samples_per_second": 21.269,
316
- "eval_steps_per_second": 0.591,
317
- "step": 87
318
- },
319
- {
320
- "epoch": 30.0,
321
- "learning_rate": 2.2222222222222223e-05,
322
- "loss": 0.0196,
323
- "step": 90
324
- },
325
- {
326
- "epoch": 30.0,
327
- "eval_accuracy": 1.0,
328
- "eval_loss": 0.00011896187061211094,
329
- "eval_runtime": 1.6527,
330
- "eval_samples_per_second": 21.782,
331
- "eval_steps_per_second": 0.605,
332
- "step": 90
333
- },
334
- {
335
- "epoch": 31.0,
336
- "eval_accuracy": 1.0,
337
- "eval_loss": 0.00012139210593886673,
338
- "eval_runtime": 1.6483,
339
- "eval_samples_per_second": 21.841,
340
- "eval_steps_per_second": 0.607,
341
- "step": 93
342
- },
343
- {
344
- "epoch": 32.0,
345
- "eval_accuracy": 1.0,
346
- "eval_loss": 4.184916542726569e-05,
347
- "eval_runtime": 1.6727,
348
- "eval_samples_per_second": 21.523,
349
- "eval_steps_per_second": 0.598,
350
- "step": 96
351
- },
352
- {
353
- "epoch": 33.0,
354
- "eval_accuracy": 1.0,
355
- "eval_loss": 1.933595194714144e-05,
356
- "eval_runtime": 1.6406,
357
- "eval_samples_per_second": 21.943,
358
- "eval_steps_per_second": 0.61,
359
- "step": 99
360
- },
361
- {
362
- "epoch": 33.33,
363
- "learning_rate": 1.8518518518518518e-05,
364
- "loss": 0.0027,
365
- "step": 100
366
- },
367
- {
368
- "epoch": 34.0,
369
- "eval_accuracy": 1.0,
370
- "eval_loss": 1.333714862994384e-05,
371
- "eval_runtime": 1.6592,
372
- "eval_samples_per_second": 21.697,
373
- "eval_steps_per_second": 0.603,
374
- "step": 102
375
- },
376
- {
377
- "epoch": 35.0,
378
- "eval_accuracy": 1.0,
379
- "eval_loss": 8.897241968952585e-06,
380
- "eval_runtime": 1.6396,
381
- "eval_samples_per_second": 21.957,
382
- "eval_steps_per_second": 0.61,
383
- "step": 105
384
- },
385
- {
386
- "epoch": 36.0,
387
- "eval_accuracy": 1.0,
388
- "eval_loss": 7.099337835825281e-06,
389
- "eval_runtime": 1.6407,
390
- "eval_samples_per_second": 21.942,
391
- "eval_steps_per_second": 0.61,
392
- "step": 108
393
- },
394
- {
395
- "epoch": 36.67,
396
- "learning_rate": 1.4814814814814815e-05,
397
- "loss": 0.0016,
398
- "step": 110
399
- },
400
- {
401
- "epoch": 37.0,
402
- "eval_accuracy": 1.0,
403
- "eval_loss": 5.609323125099763e-06,
404
- "eval_runtime": 1.6715,
405
- "eval_samples_per_second": 21.538,
406
- "eval_steps_per_second": 0.598,
407
- "step": 111
408
- },
409
- {
410
- "epoch": 38.0,
411
- "eval_accuracy": 1.0,
412
- "eval_loss": 4.562983122013975e-06,
413
- "eval_runtime": 1.9201,
414
- "eval_samples_per_second": 18.749,
415
- "eval_steps_per_second": 0.521,
416
- "step": 114
417
- },
418
- {
419
- "epoch": 39.0,
420
- "eval_accuracy": 1.0,
421
- "eval_loss": 3.596098849811824e-06,
422
- "eval_runtime": 2.0826,
423
- "eval_samples_per_second": 17.286,
424
- "eval_steps_per_second": 0.48,
425
- "step": 117
426
- },
427
- {
428
- "epoch": 40.0,
429
- "learning_rate": 1.1111111111111112e-05,
430
- "loss": 0.0021,
431
- "step": 120
432
- },
433
- {
434
- "epoch": 40.0,
435
- "eval_accuracy": 1.0,
436
- "eval_loss": 3.2384773476223927e-06,
437
- "eval_runtime": 1.6679,
438
- "eval_samples_per_second": 21.585,
439
- "eval_steps_per_second": 0.6,
440
- "step": 120
441
- },
442
- {
443
- "epoch": 41.0,
444
- "eval_accuracy": 1.0,
445
- "eval_loss": 3.013309651578311e-06,
446
- "eval_runtime": 1.6498,
447
- "eval_samples_per_second": 21.82,
448
- "eval_steps_per_second": 0.606,
449
- "step": 123
450
- },
451
- {
452
- "epoch": 42.0,
453
- "eval_accuracy": 1.0,
454
- "eval_loss": 2.781519697236945e-06,
455
- "eval_runtime": 1.6569,
456
- "eval_samples_per_second": 21.728,
457
- "eval_steps_per_second": 0.604,
458
- "step": 126
459
- },
460
- {
461
- "epoch": 43.0,
462
- "eval_accuracy": 1.0,
463
- "eval_loss": 2.4669488993822597e-06,
464
- "eval_runtime": 1.6535,
465
- "eval_samples_per_second": 21.772,
466
- "eval_steps_per_second": 0.605,
467
- "step": 129
468
- },
469
- {
470
- "epoch": 43.33,
471
- "learning_rate": 7.4074074074074075e-06,
472
- "loss": 0.0024,
473
- "step": 130
474
- },
475
- {
476
- "epoch": 44.0,
477
- "eval_accuracy": 1.0,
478
- "eval_loss": 2.09608538170869e-06,
479
- "eval_runtime": 1.6274,
480
- "eval_samples_per_second": 22.121,
481
- "eval_steps_per_second": 0.614,
482
- "step": 132
483
- },
484
- {
485
- "epoch": 45.0,
486
- "eval_accuracy": 1.0,
487
- "eval_loss": 1.89409422546305e-06,
488
- "eval_runtime": 1.6472,
489
- "eval_samples_per_second": 21.856,
490
- "eval_steps_per_second": 0.607,
491
- "step": 135
492
- },
493
- {
494
- "epoch": 46.0,
495
- "eval_accuracy": 1.0,
496
- "eval_loss": 1.821245518840442e-06,
497
- "eval_runtime": 1.646,
498
- "eval_samples_per_second": 21.872,
499
- "eval_steps_per_second": 0.608,
500
- "step": 138
501
- },
502
- {
503
- "epoch": 46.67,
504
- "learning_rate": 3.7037037037037037e-06,
505
- "loss": 0.0009,
506
- "step": 140
507
- },
508
- {
509
- "epoch": 47.0,
510
- "eval_accuracy": 1.0,
511
- "eval_loss": 1.8709155256146914e-06,
512
- "eval_runtime": 1.6474,
513
- "eval_samples_per_second": 21.852,
514
- "eval_steps_per_second": 0.607,
515
- "step": 141
516
- },
517
- {
518
- "epoch": 48.0,
519
- "eval_accuracy": 1.0,
520
- "eval_loss": 1.9536980744305765e-06,
521
- "eval_runtime": 1.6639,
522
- "eval_samples_per_second": 21.636,
523
- "eval_steps_per_second": 0.601,
524
- "step": 144
525
- },
526
- {
527
- "epoch": 49.0,
528
- "eval_accuracy": 1.0,
529
- "eval_loss": 2.006679324040306e-06,
530
- "eval_runtime": 1.6581,
531
- "eval_samples_per_second": 21.712,
532
- "eval_steps_per_second": 0.603,
533
- "step": 147
534
- },
535
- {
536
- "epoch": 50.0,
537
- "learning_rate": 0.0,
538
- "loss": 0.0006,
539
- "step": 150
540
- },
541
- {
542
- "epoch": 50.0,
543
- "eval_accuracy": 1.0,
544
- "eval_loss": 2.0265476905478863e-06,
545
- "eval_runtime": 1.7006,
546
- "eval_samples_per_second": 21.169,
547
- "eval_steps_per_second": 0.588,
548
- "step": 150
549
- },
550
- {
551
- "epoch": 50.0,
552
- "step": 150,
553
- "total_flos": 3.989386232229888e+17,
554
- "train_loss": 0.12627770403089622,
555
- "train_runtime": 1656.8438,
556
- "train_samples_per_second": 9.687,
557
- "train_steps_per_second": 0.091
558
  }
559
  ],
560
- "max_steps": 150,
561
- "num_train_epochs": 50,
562
- "total_flos": 3.989386232229888e+17,
563
  "trial_name": null,
564
  "trial_params": null
565
  }
 
1
  {
2
+ "best_metric": 0.7953054904937744,
3
+ "best_model_checkpoint": "swin-tiny-patch4-window7-224-finetuned-wuhan/checkpoint-3",
4
+ "epoch": 20.0,
5
+ "global_step": 60,
6
  "is_hyper_param_search": false,
7
  "is_local_process_zero": true,
8
  "is_world_process_zero": true,
9
  "log_history": [
10
  {
11
  "epoch": 1.0,
12
+ "eval_accuracy": 0.4,
13
+ "eval_loss": 0.7953054904937744,
14
+ "eval_runtime": 38.7172,
15
+ "eval_samples_per_second": 1.162,
16
+ "eval_steps_per_second": 0.026,
17
  "step": 3
18
  },
19
  {
20
  "epoch": 2.0,
21
+ "eval_accuracy": 0.4,
22
+ "eval_loss": 0.9477012753486633,
23
+ "eval_runtime": 2.1877,
24
+ "eval_samples_per_second": 20.569,
25
+ "eval_steps_per_second": 0.457,
26
  "step": 6
27
  },
28
  {
29
  "epoch": 3.0,
30
+ "eval_accuracy": 0.4,
31
+ "eval_loss": 1.010606050491333,
32
+ "eval_runtime": 2.1562,
33
+ "eval_samples_per_second": 20.87,
34
+ "eval_steps_per_second": 0.464,
35
  "step": 9
36
  },
37
  {
38
  "epoch": 3.33,
39
+ "learning_rate": 4.62962962962963e-05,
40
+ "loss": 0.5883,
41
  "step": 10
42
  },
43
  {
44
  "epoch": 4.0,
45
+ "eval_accuracy": 0.4,
46
+ "eval_loss": 1.417040228843689,
47
+ "eval_runtime": 2.225,
48
+ "eval_samples_per_second": 20.225,
49
+ "eval_steps_per_second": 0.449,
50
  "step": 12
51
  },
52
  {
53
  "epoch": 5.0,
54
+ "eval_accuracy": 0.4,
55
+ "eval_loss": 1.7435767650604248,
56
+ "eval_runtime": 2.2394,
57
+ "eval_samples_per_second": 20.095,
58
+ "eval_steps_per_second": 0.447,
59
  "step": 15
60
  },
61
  {
62
  "epoch": 6.0,
63
+ "eval_accuracy": 0.4,
64
+ "eval_loss": 2.5379722118377686,
65
+ "eval_runtime": 2.1794,
66
+ "eval_samples_per_second": 20.648,
67
+ "eval_steps_per_second": 0.459,
68
  "step": 18
69
  },
70
  {
71
  "epoch": 6.67,
72
+ "learning_rate": 3.7037037037037037e-05,
73
+ "loss": 0.241,
74
  "step": 20
75
  },
76
  {
77
  "epoch": 7.0,
78
+ "eval_accuracy": 0.4,
79
+ "eval_loss": 3.8802621364593506,
80
+ "eval_runtime": 2.1868,
81
+ "eval_samples_per_second": 20.578,
82
+ "eval_steps_per_second": 0.457,
83
  "step": 21
84
  },
85
  {
86
  "epoch": 8.0,
87
+ "eval_accuracy": 0.2222222222222222,
88
+ "eval_loss": 2.4039711952209473,
89
+ "eval_runtime": 2.2635,
90
+ "eval_samples_per_second": 19.881,
91
+ "eval_steps_per_second": 0.442,
92
  "step": 24
93
  },
94
  {
95
  "epoch": 9.0,
96
+ "eval_accuracy": 0.4,
97
+ "eval_loss": 3.9967715740203857,
98
+ "eval_runtime": 2.2078,
99
+ "eval_samples_per_second": 20.382,
100
+ "eval_steps_per_second": 0.453,
101
  "step": 27
102
  },
103
  {
104
  "epoch": 10.0,
105
+ "learning_rate": 2.777777777777778e-05,
106
+ "loss": 0.125,
107
  "step": 30
108
  },
109
  {
110
  "epoch": 10.0,
111
+ "eval_accuracy": 0.4,
112
+ "eval_loss": 3.27313494682312,
113
+ "eval_runtime": 2.2426,
114
+ "eval_samples_per_second": 20.066,
115
+ "eval_steps_per_second": 0.446,
116
  "step": 30
117
  },
118
  {
119
  "epoch": 11.0,
120
+ "eval_accuracy": 0.2222222222222222,
121
+ "eval_loss": 3.2202415466308594,
122
+ "eval_runtime": 2.281,
123
+ "eval_samples_per_second": 19.728,
124
+ "eval_steps_per_second": 0.438,
125
  "step": 33
126
  },
127
  {
128
  "epoch": 12.0,
129
+ "eval_accuracy": 0.4,
130
+ "eval_loss": 4.70084285736084,
131
+ "eval_runtime": 2.2753,
132
+ "eval_samples_per_second": 19.777,
133
+ "eval_steps_per_second": 0.439,
134
  "step": 36
135
  },
136
  {
137
  "epoch": 13.0,
138
+ "eval_accuracy": 0.35555555555555557,
139
+ "eval_loss": 4.558761119842529,
140
+ "eval_runtime": 2.2218,
141
+ "eval_samples_per_second": 20.254,
142
+ "eval_steps_per_second": 0.45,
143
  "step": 39
144
  },
145
  {
146
  "epoch": 13.33,
147
+ "learning_rate": 1.8518518518518518e-05,
148
+ "loss": 0.0766,
149
  "step": 40
150
  },
151
  {
152
  "epoch": 14.0,
153
+ "eval_accuracy": 0.24444444444444444,
154
+ "eval_loss": 4.54338264465332,
155
+ "eval_runtime": 2.2251,
156
+ "eval_samples_per_second": 20.223,
157
+ "eval_steps_per_second": 0.449,
158
  "step": 42
159
  },
160
  {
161
  "epoch": 15.0,
162
+ "eval_accuracy": 0.26666666666666666,
163
+ "eval_loss": 4.979237079620361,
164
+ "eval_runtime": 2.4295,
165
+ "eval_samples_per_second": 18.522,
166
+ "eval_steps_per_second": 0.412,
167
  "step": 45
168
  },
169
  {
170
  "epoch": 16.0,
171
+ "eval_accuracy": 0.26666666666666666,
172
+ "eval_loss": 5.409503936767578,
173
+ "eval_runtime": 2.1939,
174
+ "eval_samples_per_second": 20.512,
175
+ "eval_steps_per_second": 0.456,
176
  "step": 48
177
  },
178
  {
179
  "epoch": 16.67,
180
+ "learning_rate": 9.259259259259259e-06,
181
+ "loss": 0.0239,
182
  "step": 50
183
  },
184
  {
185
  "epoch": 17.0,
186
+ "eval_accuracy": 0.2222222222222222,
187
+ "eval_loss": 5.850742816925049,
188
+ "eval_runtime": 2.2566,
189
+ "eval_samples_per_second": 19.942,
190
+ "eval_steps_per_second": 0.443,
191
  "step": 51
192
  },
193
  {
194
  "epoch": 18.0,
195
+ "eval_accuracy": 0.2222222222222222,
196
+ "eval_loss": 6.102282524108887,
197
+ "eval_runtime": 2.2779,
198
+ "eval_samples_per_second": 19.755,
199
+ "eval_steps_per_second": 0.439,
200
  "step": 54
201
  },
202
  {
203
  "epoch": 19.0,
204
+ "eval_accuracy": 0.2222222222222222,
205
+ "eval_loss": 6.166590213775635,
206
+ "eval_runtime": 2.257,
207
+ "eval_samples_per_second": 19.938,
208
+ "eval_steps_per_second": 0.443,
209
  "step": 57
210
  },
211
  {
212
  "epoch": 20.0,
213
+ "learning_rate": 0.0,
214
+ "loss": 0.0129,
215
  "step": 60
216
  },
217
  {
218
  "epoch": 20.0,
219
+ "eval_accuracy": 0.2222222222222222,
220
+ "eval_loss": 6.194781303405762,
221
+ "eval_runtime": 2.3123,
222
+ "eval_samples_per_second": 19.461,
223
+ "eval_steps_per_second": 0.432,
224
  "step": 60
225
  },
226
  {
227
+ "epoch": 20.0,
228
+ "step": 60,
229
+ "total_flos": 1.7747176135901184e+17,
230
+ "train_loss": 0.1779410476485888,
231
+ "train_runtime": 979.9272,
232
+ "train_samples_per_second": 7.286,
233
+ "train_steps_per_second": 0.061
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
234
  }
235
  ],
236
+ "max_steps": 60,
237
+ "num_train_epochs": 20,
238
+ "total_flos": 1.7747176135901184e+17,
239
  "trial_name": null,
240
  "trial_params": null
241
  }