JackWong0911 commited on
Commit
2b8e301
·
verified ·
1 Parent(s): 1153622

End of training

Browse files
all_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 3.25,
3
+ "eval_accuracy": 0.9798270893371758,
4
+ "eval_loss": 0.07762069255113602,
5
+ "eval_runtime": 23.8915,
6
+ "eval_samples_per_second": 14.524,
7
+ "eval_steps_per_second": 14.524
8
+ }
runs/Feb18_06-04-57_93a789172441/events.out.tfevents.1708236569.93a789172441.1304.1 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e8ae3854c126ffaf70b901fe52e9af1bc86c8c0409eb163e62ca1c0952d7f768
3
- size 411
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:12a720f4e2c1ebb03a262983db019541e47f0376cb96de784146f54b012da4ff
3
+ size 734
test_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 3.25,
3
+ "eval_accuracy": 0.9798270893371758,
4
+ "eval_loss": 0.07762069255113602,
5
+ "eval_runtime": 23.8915,
6
+ "eval_samples_per_second": 14.524,
7
+ "eval_steps_per_second": 14.524
8
+ }
trainer_state.json ADDED
@@ -0,0 +1,802 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.9932885906040269,
3
+ "best_model_checkpoint": "timesformer-base-finetuned-k400-finetuned-ucf101-subset/checkpoint-300",
4
+ "epoch": 3.25,
5
+ "eval_steps": 500,
6
+ "global_step": 1200,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.01,
13
+ "learning_rate": 4.166666666666667e-06,
14
+ "loss": 2.4134,
15
+ "step": 10
16
+ },
17
+ {
18
+ "epoch": 0.02,
19
+ "learning_rate": 8.333333333333334e-06,
20
+ "loss": 2.3368,
21
+ "step": 20
22
+ },
23
+ {
24
+ "epoch": 0.03,
25
+ "learning_rate": 1.25e-05,
26
+ "loss": 1.9994,
27
+ "step": 30
28
+ },
29
+ {
30
+ "epoch": 0.03,
31
+ "learning_rate": 1.6666666666666667e-05,
32
+ "loss": 2.3569,
33
+ "step": 40
34
+ },
35
+ {
36
+ "epoch": 0.04,
37
+ "learning_rate": 2.0833333333333336e-05,
38
+ "loss": 2.1041,
39
+ "step": 50
40
+ },
41
+ {
42
+ "epoch": 0.05,
43
+ "learning_rate": 2.5e-05,
44
+ "loss": 1.0861,
45
+ "step": 60
46
+ },
47
+ {
48
+ "epoch": 0.06,
49
+ "learning_rate": 2.916666666666667e-05,
50
+ "loss": 0.9691,
51
+ "step": 70
52
+ },
53
+ {
54
+ "epoch": 0.07,
55
+ "learning_rate": 3.3333333333333335e-05,
56
+ "loss": 0.87,
57
+ "step": 80
58
+ },
59
+ {
60
+ "epoch": 0.07,
61
+ "learning_rate": 3.7500000000000003e-05,
62
+ "loss": 0.5282,
63
+ "step": 90
64
+ },
65
+ {
66
+ "epoch": 0.08,
67
+ "learning_rate": 4.166666666666667e-05,
68
+ "loss": 1.5578,
69
+ "step": 100
70
+ },
71
+ {
72
+ "epoch": 0.09,
73
+ "learning_rate": 4.5833333333333334e-05,
74
+ "loss": 0.9608,
75
+ "step": 110
76
+ },
77
+ {
78
+ "epoch": 0.1,
79
+ "learning_rate": 5e-05,
80
+ "loss": 0.5998,
81
+ "step": 120
82
+ },
83
+ {
84
+ "epoch": 0.11,
85
+ "learning_rate": 4.9537037037037035e-05,
86
+ "loss": 0.3374,
87
+ "step": 130
88
+ },
89
+ {
90
+ "epoch": 0.12,
91
+ "learning_rate": 4.9074074074074075e-05,
92
+ "loss": 0.4752,
93
+ "step": 140
94
+ },
95
+ {
96
+ "epoch": 0.12,
97
+ "learning_rate": 4.8611111111111115e-05,
98
+ "loss": 0.1997,
99
+ "step": 150
100
+ },
101
+ {
102
+ "epoch": 0.13,
103
+ "learning_rate": 4.814814814814815e-05,
104
+ "loss": 0.2247,
105
+ "step": 160
106
+ },
107
+ {
108
+ "epoch": 0.14,
109
+ "learning_rate": 4.768518518518519e-05,
110
+ "loss": 0.0149,
111
+ "step": 170
112
+ },
113
+ {
114
+ "epoch": 0.15,
115
+ "learning_rate": 4.722222222222222e-05,
116
+ "loss": 0.3434,
117
+ "step": 180
118
+ },
119
+ {
120
+ "epoch": 0.16,
121
+ "learning_rate": 4.675925925925926e-05,
122
+ "loss": 0.3084,
123
+ "step": 190
124
+ },
125
+ {
126
+ "epoch": 0.17,
127
+ "learning_rate": 4.62962962962963e-05,
128
+ "loss": 0.3887,
129
+ "step": 200
130
+ },
131
+ {
132
+ "epoch": 0.17,
133
+ "learning_rate": 4.5833333333333334e-05,
134
+ "loss": 0.0506,
135
+ "step": 210
136
+ },
137
+ {
138
+ "epoch": 0.18,
139
+ "learning_rate": 4.5370370370370374e-05,
140
+ "loss": 0.504,
141
+ "step": 220
142
+ },
143
+ {
144
+ "epoch": 0.19,
145
+ "learning_rate": 4.490740740740741e-05,
146
+ "loss": 0.0872,
147
+ "step": 230
148
+ },
149
+ {
150
+ "epoch": 0.2,
151
+ "learning_rate": 4.4444444444444447e-05,
152
+ "loss": 0.5141,
153
+ "step": 240
154
+ },
155
+ {
156
+ "epoch": 0.21,
157
+ "learning_rate": 4.3981481481481486e-05,
158
+ "loss": 0.0495,
159
+ "step": 250
160
+ },
161
+ {
162
+ "epoch": 0.22,
163
+ "learning_rate": 4.351851851851852e-05,
164
+ "loss": 0.0259,
165
+ "step": 260
166
+ },
167
+ {
168
+ "epoch": 0.23,
169
+ "learning_rate": 4.305555555555556e-05,
170
+ "loss": 0.4605,
171
+ "step": 270
172
+ },
173
+ {
174
+ "epoch": 0.23,
175
+ "learning_rate": 4.259259259259259e-05,
176
+ "loss": 0.0015,
177
+ "step": 280
178
+ },
179
+ {
180
+ "epoch": 0.24,
181
+ "learning_rate": 4.212962962962963e-05,
182
+ "loss": 0.1045,
183
+ "step": 290
184
+ },
185
+ {
186
+ "epoch": 0.25,
187
+ "learning_rate": 4.166666666666667e-05,
188
+ "loss": 0.0176,
189
+ "step": 300
190
+ },
191
+ {
192
+ "epoch": 0.25,
193
+ "eval_accuracy": 0.9932885906040269,
194
+ "eval_loss": 0.02020532451570034,
195
+ "eval_runtime": 10.0691,
196
+ "eval_samples_per_second": 14.798,
197
+ "eval_steps_per_second": 14.798,
198
+ "step": 300
199
+ },
200
+ {
201
+ "epoch": 1.01,
202
+ "learning_rate": 4.1203703703703705e-05,
203
+ "loss": 0.0022,
204
+ "step": 310
205
+ },
206
+ {
207
+ "epoch": 1.02,
208
+ "learning_rate": 4.074074074074074e-05,
209
+ "loss": 0.001,
210
+ "step": 320
211
+ },
212
+ {
213
+ "epoch": 1.02,
214
+ "learning_rate": 4.027777777777778e-05,
215
+ "loss": 0.3789,
216
+ "step": 330
217
+ },
218
+ {
219
+ "epoch": 1.03,
220
+ "learning_rate": 3.981481481481482e-05,
221
+ "loss": 0.0017,
222
+ "step": 340
223
+ },
224
+ {
225
+ "epoch": 1.04,
226
+ "learning_rate": 3.935185185185186e-05,
227
+ "loss": 0.001,
228
+ "step": 350
229
+ },
230
+ {
231
+ "epoch": 1.05,
232
+ "learning_rate": 3.888888888888889e-05,
233
+ "loss": 0.0008,
234
+ "step": 360
235
+ },
236
+ {
237
+ "epoch": 1.06,
238
+ "learning_rate": 3.8425925925925924e-05,
239
+ "loss": 0.0199,
240
+ "step": 370
241
+ },
242
+ {
243
+ "epoch": 1.07,
244
+ "learning_rate": 3.7962962962962964e-05,
245
+ "loss": 0.0095,
246
+ "step": 380
247
+ },
248
+ {
249
+ "epoch": 1.07,
250
+ "learning_rate": 3.7500000000000003e-05,
251
+ "loss": 0.002,
252
+ "step": 390
253
+ },
254
+ {
255
+ "epoch": 1.08,
256
+ "learning_rate": 3.7037037037037037e-05,
257
+ "loss": 0.0019,
258
+ "step": 400
259
+ },
260
+ {
261
+ "epoch": 1.09,
262
+ "learning_rate": 3.6574074074074076e-05,
263
+ "loss": 0.001,
264
+ "step": 410
265
+ },
266
+ {
267
+ "epoch": 1.1,
268
+ "learning_rate": 3.611111111111111e-05,
269
+ "loss": 0.0365,
270
+ "step": 420
271
+ },
272
+ {
273
+ "epoch": 1.11,
274
+ "learning_rate": 3.564814814814815e-05,
275
+ "loss": 0.0016,
276
+ "step": 430
277
+ },
278
+ {
279
+ "epoch": 1.12,
280
+ "learning_rate": 3.518518518518519e-05,
281
+ "loss": 0.0009,
282
+ "step": 440
283
+ },
284
+ {
285
+ "epoch": 1.12,
286
+ "learning_rate": 3.472222222222222e-05,
287
+ "loss": 0.5999,
288
+ "step": 450
289
+ },
290
+ {
291
+ "epoch": 1.13,
292
+ "learning_rate": 3.425925925925926e-05,
293
+ "loss": 0.025,
294
+ "step": 460
295
+ },
296
+ {
297
+ "epoch": 1.14,
298
+ "learning_rate": 3.3796296296296295e-05,
299
+ "loss": 0.0014,
300
+ "step": 470
301
+ },
302
+ {
303
+ "epoch": 1.15,
304
+ "learning_rate": 3.3333333333333335e-05,
305
+ "loss": 0.4351,
306
+ "step": 480
307
+ },
308
+ {
309
+ "epoch": 1.16,
310
+ "learning_rate": 3.2870370370370375e-05,
311
+ "loss": 0.0008,
312
+ "step": 490
313
+ },
314
+ {
315
+ "epoch": 1.17,
316
+ "learning_rate": 3.240740740740741e-05,
317
+ "loss": 0.0012,
318
+ "step": 500
319
+ },
320
+ {
321
+ "epoch": 1.18,
322
+ "learning_rate": 3.194444444444444e-05,
323
+ "loss": 0.0032,
324
+ "step": 510
325
+ },
326
+ {
327
+ "epoch": 1.18,
328
+ "learning_rate": 3.148148148148148e-05,
329
+ "loss": 0.0071,
330
+ "step": 520
331
+ },
332
+ {
333
+ "epoch": 1.19,
334
+ "learning_rate": 3.101851851851852e-05,
335
+ "loss": 0.0014,
336
+ "step": 530
337
+ },
338
+ {
339
+ "epoch": 1.2,
340
+ "learning_rate": 3.055555555555556e-05,
341
+ "loss": 0.0005,
342
+ "step": 540
343
+ },
344
+ {
345
+ "epoch": 1.21,
346
+ "learning_rate": 3.0092592592592593e-05,
347
+ "loss": 0.0261,
348
+ "step": 550
349
+ },
350
+ {
351
+ "epoch": 1.22,
352
+ "learning_rate": 2.962962962962963e-05,
353
+ "loss": 0.0004,
354
+ "step": 560
355
+ },
356
+ {
357
+ "epoch": 1.23,
358
+ "learning_rate": 2.916666666666667e-05,
359
+ "loss": 0.0154,
360
+ "step": 570
361
+ },
362
+ {
363
+ "epoch": 1.23,
364
+ "learning_rate": 2.8703703703703706e-05,
365
+ "loss": 0.0021,
366
+ "step": 580
367
+ },
368
+ {
369
+ "epoch": 1.24,
370
+ "learning_rate": 2.824074074074074e-05,
371
+ "loss": 0.0004,
372
+ "step": 590
373
+ },
374
+ {
375
+ "epoch": 1.25,
376
+ "learning_rate": 2.777777777777778e-05,
377
+ "loss": 0.002,
378
+ "step": 600
379
+ },
380
+ {
381
+ "epoch": 1.25,
382
+ "eval_accuracy": 0.9798657718120806,
383
+ "eval_loss": 0.13705500960350037,
384
+ "eval_runtime": 10.1041,
385
+ "eval_samples_per_second": 14.746,
386
+ "eval_steps_per_second": 14.746,
387
+ "step": 600
388
+ },
389
+ {
390
+ "epoch": 2.01,
391
+ "learning_rate": 2.7314814814814816e-05,
392
+ "loss": 0.0004,
393
+ "step": 610
394
+ },
395
+ {
396
+ "epoch": 2.02,
397
+ "learning_rate": 2.6851851851851855e-05,
398
+ "loss": 0.0003,
399
+ "step": 620
400
+ },
401
+ {
402
+ "epoch": 2.02,
403
+ "learning_rate": 2.6388888888888892e-05,
404
+ "loss": 0.0004,
405
+ "step": 630
406
+ },
407
+ {
408
+ "epoch": 2.03,
409
+ "learning_rate": 2.5925925925925925e-05,
410
+ "loss": 0.0007,
411
+ "step": 640
412
+ },
413
+ {
414
+ "epoch": 2.04,
415
+ "learning_rate": 2.5462962962962965e-05,
416
+ "loss": 0.0007,
417
+ "step": 650
418
+ },
419
+ {
420
+ "epoch": 2.05,
421
+ "learning_rate": 2.5e-05,
422
+ "loss": 0.0029,
423
+ "step": 660
424
+ },
425
+ {
426
+ "epoch": 2.06,
427
+ "learning_rate": 2.4537037037037038e-05,
428
+ "loss": 0.0003,
429
+ "step": 670
430
+ },
431
+ {
432
+ "epoch": 2.07,
433
+ "learning_rate": 2.4074074074074074e-05,
434
+ "loss": 0.0007,
435
+ "step": 680
436
+ },
437
+ {
438
+ "epoch": 2.08,
439
+ "learning_rate": 2.361111111111111e-05,
440
+ "loss": 0.0003,
441
+ "step": 690
442
+ },
443
+ {
444
+ "epoch": 2.08,
445
+ "learning_rate": 2.314814814814815e-05,
446
+ "loss": 0.0003,
447
+ "step": 700
448
+ },
449
+ {
450
+ "epoch": 2.09,
451
+ "learning_rate": 2.2685185185185187e-05,
452
+ "loss": 0.0004,
453
+ "step": 710
454
+ },
455
+ {
456
+ "epoch": 2.1,
457
+ "learning_rate": 2.2222222222222223e-05,
458
+ "loss": 0.0004,
459
+ "step": 720
460
+ },
461
+ {
462
+ "epoch": 2.11,
463
+ "learning_rate": 2.175925925925926e-05,
464
+ "loss": 0.0003,
465
+ "step": 730
466
+ },
467
+ {
468
+ "epoch": 2.12,
469
+ "learning_rate": 2.1296296296296296e-05,
470
+ "loss": 0.0009,
471
+ "step": 740
472
+ },
473
+ {
474
+ "epoch": 2.12,
475
+ "learning_rate": 2.0833333333333336e-05,
476
+ "loss": 0.0004,
477
+ "step": 750
478
+ },
479
+ {
480
+ "epoch": 2.13,
481
+ "learning_rate": 2.037037037037037e-05,
482
+ "loss": 0.0002,
483
+ "step": 760
484
+ },
485
+ {
486
+ "epoch": 2.14,
487
+ "learning_rate": 1.990740740740741e-05,
488
+ "loss": 0.0005,
489
+ "step": 770
490
+ },
491
+ {
492
+ "epoch": 2.15,
493
+ "learning_rate": 1.9444444444444445e-05,
494
+ "loss": 0.0002,
495
+ "step": 780
496
+ },
497
+ {
498
+ "epoch": 2.16,
499
+ "learning_rate": 1.8981481481481482e-05,
500
+ "loss": 0.0003,
501
+ "step": 790
502
+ },
503
+ {
504
+ "epoch": 2.17,
505
+ "learning_rate": 1.8518518518518518e-05,
506
+ "loss": 0.0002,
507
+ "step": 800
508
+ },
509
+ {
510
+ "epoch": 2.17,
511
+ "learning_rate": 1.8055555555555555e-05,
512
+ "loss": 0.0002,
513
+ "step": 810
514
+ },
515
+ {
516
+ "epoch": 2.18,
517
+ "learning_rate": 1.7592592592592595e-05,
518
+ "loss": 0.0002,
519
+ "step": 820
520
+ },
521
+ {
522
+ "epoch": 2.19,
523
+ "learning_rate": 1.712962962962963e-05,
524
+ "loss": 0.0003,
525
+ "step": 830
526
+ },
527
+ {
528
+ "epoch": 2.2,
529
+ "learning_rate": 1.6666666666666667e-05,
530
+ "loss": 0.0004,
531
+ "step": 840
532
+ },
533
+ {
534
+ "epoch": 2.21,
535
+ "learning_rate": 1.6203703703703704e-05,
536
+ "loss": 0.0002,
537
+ "step": 850
538
+ },
539
+ {
540
+ "epoch": 2.22,
541
+ "learning_rate": 1.574074074074074e-05,
542
+ "loss": 0.0003,
543
+ "step": 860
544
+ },
545
+ {
546
+ "epoch": 2.23,
547
+ "learning_rate": 1.527777777777778e-05,
548
+ "loss": 0.0002,
549
+ "step": 870
550
+ },
551
+ {
552
+ "epoch": 2.23,
553
+ "learning_rate": 1.4814814814814815e-05,
554
+ "loss": 0.0002,
555
+ "step": 880
556
+ },
557
+ {
558
+ "epoch": 2.24,
559
+ "learning_rate": 1.4351851851851853e-05,
560
+ "loss": 0.666,
561
+ "step": 890
562
+ },
563
+ {
564
+ "epoch": 2.25,
565
+ "learning_rate": 1.388888888888889e-05,
566
+ "loss": 0.0002,
567
+ "step": 900
568
+ },
569
+ {
570
+ "epoch": 2.25,
571
+ "eval_accuracy": 0.9798657718120806,
572
+ "eval_loss": 0.0970994308590889,
573
+ "eval_runtime": 10.0997,
574
+ "eval_samples_per_second": 14.753,
575
+ "eval_steps_per_second": 14.753,
576
+ "step": 900
577
+ },
578
+ {
579
+ "epoch": 3.01,
580
+ "learning_rate": 1.3425925925925928e-05,
581
+ "loss": 0.0004,
582
+ "step": 910
583
+ },
584
+ {
585
+ "epoch": 3.02,
586
+ "learning_rate": 1.2962962962962962e-05,
587
+ "loss": 0.0002,
588
+ "step": 920
589
+ },
590
+ {
591
+ "epoch": 3.02,
592
+ "learning_rate": 1.25e-05,
593
+ "loss": 0.0002,
594
+ "step": 930
595
+ },
596
+ {
597
+ "epoch": 3.03,
598
+ "learning_rate": 1.2037037037037037e-05,
599
+ "loss": 0.0002,
600
+ "step": 940
601
+ },
602
+ {
603
+ "epoch": 3.04,
604
+ "learning_rate": 1.1574074074074075e-05,
605
+ "loss": 0.0002,
606
+ "step": 950
607
+ },
608
+ {
609
+ "epoch": 3.05,
610
+ "learning_rate": 1.1111111111111112e-05,
611
+ "loss": 0.0003,
612
+ "step": 960
613
+ },
614
+ {
615
+ "epoch": 3.06,
616
+ "learning_rate": 1.0648148148148148e-05,
617
+ "loss": 0.0003,
618
+ "step": 970
619
+ },
620
+ {
621
+ "epoch": 3.07,
622
+ "learning_rate": 1.0185185185185185e-05,
623
+ "loss": 0.0002,
624
+ "step": 980
625
+ },
626
+ {
627
+ "epoch": 3.08,
628
+ "learning_rate": 9.722222222222223e-06,
629
+ "loss": 0.0002,
630
+ "step": 990
631
+ },
632
+ {
633
+ "epoch": 3.08,
634
+ "learning_rate": 9.259259259259259e-06,
635
+ "loss": 0.0002,
636
+ "step": 1000
637
+ },
638
+ {
639
+ "epoch": 3.09,
640
+ "learning_rate": 8.796296296296297e-06,
641
+ "loss": 0.0003,
642
+ "step": 1010
643
+ },
644
+ {
645
+ "epoch": 3.1,
646
+ "learning_rate": 8.333333333333334e-06,
647
+ "loss": 0.0002,
648
+ "step": 1020
649
+ },
650
+ {
651
+ "epoch": 3.11,
652
+ "learning_rate": 7.87037037037037e-06,
653
+ "loss": 0.0004,
654
+ "step": 1030
655
+ },
656
+ {
657
+ "epoch": 3.12,
658
+ "learning_rate": 7.4074074074074075e-06,
659
+ "loss": 0.0002,
660
+ "step": 1040
661
+ },
662
+ {
663
+ "epoch": 3.12,
664
+ "learning_rate": 6.944444444444445e-06,
665
+ "loss": 0.0002,
666
+ "step": 1050
667
+ },
668
+ {
669
+ "epoch": 3.13,
670
+ "learning_rate": 6.481481481481481e-06,
671
+ "loss": 0.0059,
672
+ "step": 1060
673
+ },
674
+ {
675
+ "epoch": 3.14,
676
+ "learning_rate": 6.0185185185185185e-06,
677
+ "loss": 0.0002,
678
+ "step": 1070
679
+ },
680
+ {
681
+ "epoch": 3.15,
682
+ "learning_rate": 5.555555555555556e-06,
683
+ "loss": 0.0002,
684
+ "step": 1080
685
+ },
686
+ {
687
+ "epoch": 3.16,
688
+ "learning_rate": 5.092592592592592e-06,
689
+ "loss": 0.0003,
690
+ "step": 1090
691
+ },
692
+ {
693
+ "epoch": 3.17,
694
+ "learning_rate": 4.6296296296296296e-06,
695
+ "loss": 0.0002,
696
+ "step": 1100
697
+ },
698
+ {
699
+ "epoch": 3.17,
700
+ "learning_rate": 4.166666666666667e-06,
701
+ "loss": 0.0002,
702
+ "step": 1110
703
+ },
704
+ {
705
+ "epoch": 3.18,
706
+ "learning_rate": 3.7037037037037037e-06,
707
+ "loss": 0.0003,
708
+ "step": 1120
709
+ },
710
+ {
711
+ "epoch": 3.19,
712
+ "learning_rate": 3.2407407407407406e-06,
713
+ "loss": 0.0003,
714
+ "step": 1130
715
+ },
716
+ {
717
+ "epoch": 3.2,
718
+ "learning_rate": 2.777777777777778e-06,
719
+ "loss": 0.0008,
720
+ "step": 1140
721
+ },
722
+ {
723
+ "epoch": 3.21,
724
+ "learning_rate": 2.3148148148148148e-06,
725
+ "loss": 0.0002,
726
+ "step": 1150
727
+ },
728
+ {
729
+ "epoch": 3.22,
730
+ "learning_rate": 1.8518518518518519e-06,
731
+ "loss": 0.0001,
732
+ "step": 1160
733
+ },
734
+ {
735
+ "epoch": 3.23,
736
+ "learning_rate": 1.388888888888889e-06,
737
+ "loss": 0.0002,
738
+ "step": 1170
739
+ },
740
+ {
741
+ "epoch": 3.23,
742
+ "learning_rate": 9.259259259259259e-07,
743
+ "loss": 0.0002,
744
+ "step": 1180
745
+ },
746
+ {
747
+ "epoch": 3.24,
748
+ "learning_rate": 4.6296296296296297e-07,
749
+ "loss": 0.0002,
750
+ "step": 1190
751
+ },
752
+ {
753
+ "epoch": 3.25,
754
+ "learning_rate": 0.0,
755
+ "loss": 0.0032,
756
+ "step": 1200
757
+ },
758
+ {
759
+ "epoch": 3.25,
760
+ "eval_accuracy": 0.9798657718120806,
761
+ "eval_loss": 0.09196619689464569,
762
+ "eval_runtime": 10.2231,
763
+ "eval_samples_per_second": 14.575,
764
+ "eval_steps_per_second": 14.575,
765
+ "step": 1200
766
+ },
767
+ {
768
+ "epoch": 3.25,
769
+ "step": 1200,
770
+ "total_flos": 1.0514301109272576e+18,
771
+ "train_loss": 0.20139034370173856,
772
+ "train_runtime": 230.2456,
773
+ "train_samples_per_second": 5.212,
774
+ "train_steps_per_second": 5.212
775
+ },
776
+ {
777
+ "epoch": 3.25,
778
+ "eval_accuracy": 0.9798270893371758,
779
+ "eval_loss": 0.07762070000171661,
780
+ "eval_runtime": 23.5957,
781
+ "eval_samples_per_second": 14.706,
782
+ "eval_steps_per_second": 14.706,
783
+ "step": 1200
784
+ },
785
+ {
786
+ "epoch": 3.25,
787
+ "eval_accuracy": 0.9798270893371758,
788
+ "eval_loss": 0.07762069255113602,
789
+ "eval_runtime": 23.8915,
790
+ "eval_samples_per_second": 14.524,
791
+ "eval_steps_per_second": 14.524,
792
+ "step": 1200
793
+ }
794
+ ],
795
+ "logging_steps": 10,
796
+ "max_steps": 1200,
797
+ "num_train_epochs": 9223372036854775807,
798
+ "save_steps": 500,
799
+ "total_flos": 1.0514301109272576e+18,
800
+ "trial_name": null,
801
+ "trial_params": null
802
+ }