meetmayaat commited on
Commit
abe4a41
·
1 Parent(s): 6ed819a

Training in progress, epoch 0

Browse files
all_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 4.2,
3
+ "eval_accuracy": 0.9930693069306931,
4
+ "eval_loss": 0.032540928572416306,
5
+ "eval_runtime": 127.8623,
6
+ "eval_samples_per_second": 7.899,
7
+ "eval_steps_per_second": 3.95
8
+ }
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3908d673d4bad6d16d6b2d0f84907cb80139e91514a31e87cf619685e5024a1c
3
  size 345003509
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1e7ffe9ccd9ca241e1634de295eb8f66c7151af6db6fbb003bba131ded76822d
3
  size 345003509
test_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 4.2,
3
+ "eval_accuracy": 0.9930693069306931,
4
+ "eval_loss": 0.032540928572416306,
5
+ "eval_runtime": 127.8623,
6
+ "eval_samples_per_second": 7.899,
7
+ "eval_steps_per_second": 3.95
8
+ }
trainer_state.json ADDED
@@ -0,0 +1,1012 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 1.0,
3
+ "best_model_checkpoint": "videomae-base-finetuned-ucf101-subset/checkpoint-1540",
4
+ "epoch": 4.197402597402597,
5
+ "global_step": 1540,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 0.01,
12
+ "learning_rate": 3.2467532467532465e-06,
13
+ "loss": 2.371,
14
+ "step": 10
15
+ },
16
+ {
17
+ "epoch": 0.01,
18
+ "learning_rate": 6.493506493506493e-06,
19
+ "loss": 2.3544,
20
+ "step": 20
21
+ },
22
+ {
23
+ "epoch": 0.02,
24
+ "learning_rate": 9.740259740259742e-06,
25
+ "loss": 2.3804,
26
+ "step": 30
27
+ },
28
+ {
29
+ "epoch": 0.03,
30
+ "learning_rate": 1.2987012987012986e-05,
31
+ "loss": 2.1976,
32
+ "step": 40
33
+ },
34
+ {
35
+ "epoch": 0.03,
36
+ "learning_rate": 1.6233766233766234e-05,
37
+ "loss": 2.2581,
38
+ "step": 50
39
+ },
40
+ {
41
+ "epoch": 0.04,
42
+ "learning_rate": 1.9480519480519483e-05,
43
+ "loss": 2.3111,
44
+ "step": 60
45
+ },
46
+ {
47
+ "epoch": 0.05,
48
+ "learning_rate": 2.272727272727273e-05,
49
+ "loss": 2.3106,
50
+ "step": 70
51
+ },
52
+ {
53
+ "epoch": 0.05,
54
+ "learning_rate": 2.5974025974025972e-05,
55
+ "loss": 2.141,
56
+ "step": 80
57
+ },
58
+ {
59
+ "epoch": 0.06,
60
+ "learning_rate": 2.922077922077922e-05,
61
+ "loss": 2.2013,
62
+ "step": 90
63
+ },
64
+ {
65
+ "epoch": 0.06,
66
+ "learning_rate": 3.246753246753247e-05,
67
+ "loss": 2.14,
68
+ "step": 100
69
+ },
70
+ {
71
+ "epoch": 0.07,
72
+ "learning_rate": 3.571428571428572e-05,
73
+ "loss": 2.0491,
74
+ "step": 110
75
+ },
76
+ {
77
+ "epoch": 0.08,
78
+ "learning_rate": 3.8961038961038966e-05,
79
+ "loss": 1.7111,
80
+ "step": 120
81
+ },
82
+ {
83
+ "epoch": 0.08,
84
+ "learning_rate": 4.220779220779221e-05,
85
+ "loss": 1.6285,
86
+ "step": 130
87
+ },
88
+ {
89
+ "epoch": 0.09,
90
+ "learning_rate": 4.545454545454546e-05,
91
+ "loss": 1.8353,
92
+ "step": 140
93
+ },
94
+ {
95
+ "epoch": 0.1,
96
+ "learning_rate": 4.87012987012987e-05,
97
+ "loss": 1.5636,
98
+ "step": 150
99
+ },
100
+ {
101
+ "epoch": 0.1,
102
+ "learning_rate": 4.978354978354979e-05,
103
+ "loss": 1.5912,
104
+ "step": 160
105
+ },
106
+ {
107
+ "epoch": 0.11,
108
+ "learning_rate": 4.9422799422799424e-05,
109
+ "loss": 1.3838,
110
+ "step": 170
111
+ },
112
+ {
113
+ "epoch": 0.12,
114
+ "learning_rate": 4.9062049062049066e-05,
115
+ "loss": 1.607,
116
+ "step": 180
117
+ },
118
+ {
119
+ "epoch": 0.12,
120
+ "learning_rate": 4.87012987012987e-05,
121
+ "loss": 1.2506,
122
+ "step": 190
123
+ },
124
+ {
125
+ "epoch": 0.13,
126
+ "learning_rate": 4.834054834054834e-05,
127
+ "loss": 1.4536,
128
+ "step": 200
129
+ },
130
+ {
131
+ "epoch": 0.14,
132
+ "learning_rate": 4.797979797979798e-05,
133
+ "loss": 1.1586,
134
+ "step": 210
135
+ },
136
+ {
137
+ "epoch": 0.14,
138
+ "learning_rate": 4.761904761904762e-05,
139
+ "loss": 1.0506,
140
+ "step": 220
141
+ },
142
+ {
143
+ "epoch": 0.15,
144
+ "learning_rate": 4.725829725829726e-05,
145
+ "loss": 1.2725,
146
+ "step": 230
147
+ },
148
+ {
149
+ "epoch": 0.16,
150
+ "learning_rate": 4.6897546897546904e-05,
151
+ "loss": 1.4716,
152
+ "step": 240
153
+ },
154
+ {
155
+ "epoch": 0.16,
156
+ "learning_rate": 4.653679653679654e-05,
157
+ "loss": 0.6488,
158
+ "step": 250
159
+ },
160
+ {
161
+ "epoch": 0.17,
162
+ "learning_rate": 4.617604617604618e-05,
163
+ "loss": 0.4272,
164
+ "step": 260
165
+ },
166
+ {
167
+ "epoch": 0.18,
168
+ "learning_rate": 4.5815295815295817e-05,
169
+ "loss": 1.3825,
170
+ "step": 270
171
+ },
172
+ {
173
+ "epoch": 0.18,
174
+ "learning_rate": 4.545454545454546e-05,
175
+ "loss": 0.8926,
176
+ "step": 280
177
+ },
178
+ {
179
+ "epoch": 0.19,
180
+ "learning_rate": 4.5093795093795094e-05,
181
+ "loss": 0.1798,
182
+ "step": 290
183
+ },
184
+ {
185
+ "epoch": 0.19,
186
+ "learning_rate": 4.4733044733044736e-05,
187
+ "loss": 0.6196,
188
+ "step": 300
189
+ },
190
+ {
191
+ "epoch": 0.2,
192
+ "eval_accuracy": 0.6438356164383562,
193
+ "eval_loss": 0.970087468624115,
194
+ "eval_runtime": 27.779,
195
+ "eval_samples_per_second": 7.884,
196
+ "eval_steps_per_second": 3.96,
197
+ "step": 309
198
+ },
199
+ {
200
+ "epoch": 1.0,
201
+ "learning_rate": 4.437229437229438e-05,
202
+ "loss": 1.2441,
203
+ "step": 310
204
+ },
205
+ {
206
+ "epoch": 1.01,
207
+ "learning_rate": 4.401154401154401e-05,
208
+ "loss": 0.632,
209
+ "step": 320
210
+ },
211
+ {
212
+ "epoch": 1.01,
213
+ "learning_rate": 4.3650793650793655e-05,
214
+ "loss": 0.9114,
215
+ "step": 330
216
+ },
217
+ {
218
+ "epoch": 1.02,
219
+ "learning_rate": 4.329004329004329e-05,
220
+ "loss": 0.6274,
221
+ "step": 340
222
+ },
223
+ {
224
+ "epoch": 1.03,
225
+ "learning_rate": 4.292929292929293e-05,
226
+ "loss": 0.6229,
227
+ "step": 350
228
+ },
229
+ {
230
+ "epoch": 1.03,
231
+ "learning_rate": 4.256854256854257e-05,
232
+ "loss": 0.5724,
233
+ "step": 360
234
+ },
235
+ {
236
+ "epoch": 1.04,
237
+ "learning_rate": 4.220779220779221e-05,
238
+ "loss": 0.5662,
239
+ "step": 370
240
+ },
241
+ {
242
+ "epoch": 1.05,
243
+ "learning_rate": 4.184704184704185e-05,
244
+ "loss": 0.9723,
245
+ "step": 380
246
+ },
247
+ {
248
+ "epoch": 1.05,
249
+ "learning_rate": 4.148629148629149e-05,
250
+ "loss": 0.3876,
251
+ "step": 390
252
+ },
253
+ {
254
+ "epoch": 1.06,
255
+ "learning_rate": 4.112554112554113e-05,
256
+ "loss": 0.5582,
257
+ "step": 400
258
+ },
259
+ {
260
+ "epoch": 1.07,
261
+ "learning_rate": 4.0764790764790763e-05,
262
+ "loss": 0.5509,
263
+ "step": 410
264
+ },
265
+ {
266
+ "epoch": 1.07,
267
+ "learning_rate": 4.0404040404040405e-05,
268
+ "loss": 0.3355,
269
+ "step": 420
270
+ },
271
+ {
272
+ "epoch": 1.08,
273
+ "learning_rate": 4.004329004329004e-05,
274
+ "loss": 0.297,
275
+ "step": 430
276
+ },
277
+ {
278
+ "epoch": 1.09,
279
+ "learning_rate": 3.968253968253968e-05,
280
+ "loss": 0.4709,
281
+ "step": 440
282
+ },
283
+ {
284
+ "epoch": 1.09,
285
+ "learning_rate": 3.9321789321789324e-05,
286
+ "loss": 0.3066,
287
+ "step": 450
288
+ },
289
+ {
290
+ "epoch": 1.1,
291
+ "learning_rate": 3.8961038961038966e-05,
292
+ "loss": 0.9948,
293
+ "step": 460
294
+ },
295
+ {
296
+ "epoch": 1.1,
297
+ "learning_rate": 3.86002886002886e-05,
298
+ "loss": 0.5551,
299
+ "step": 470
300
+ },
301
+ {
302
+ "epoch": 1.11,
303
+ "learning_rate": 3.8239538239538244e-05,
304
+ "loss": 0.4996,
305
+ "step": 480
306
+ },
307
+ {
308
+ "epoch": 1.12,
309
+ "learning_rate": 3.787878787878788e-05,
310
+ "loss": 0.1511,
311
+ "step": 490
312
+ },
313
+ {
314
+ "epoch": 1.12,
315
+ "learning_rate": 3.751803751803752e-05,
316
+ "loss": 0.9123,
317
+ "step": 500
318
+ },
319
+ {
320
+ "epoch": 1.13,
321
+ "learning_rate": 3.7157287157287156e-05,
322
+ "loss": 0.4422,
323
+ "step": 510
324
+ },
325
+ {
326
+ "epoch": 1.14,
327
+ "learning_rate": 3.67965367965368e-05,
328
+ "loss": 0.8064,
329
+ "step": 520
330
+ },
331
+ {
332
+ "epoch": 1.14,
333
+ "learning_rate": 3.643578643578644e-05,
334
+ "loss": 0.3332,
335
+ "step": 530
336
+ },
337
+ {
338
+ "epoch": 1.15,
339
+ "learning_rate": 3.6075036075036075e-05,
340
+ "loss": 0.141,
341
+ "step": 540
342
+ },
343
+ {
344
+ "epoch": 1.16,
345
+ "learning_rate": 3.571428571428572e-05,
346
+ "loss": 0.2082,
347
+ "step": 550
348
+ },
349
+ {
350
+ "epoch": 1.16,
351
+ "learning_rate": 3.535353535353535e-05,
352
+ "loss": 0.388,
353
+ "step": 560
354
+ },
355
+ {
356
+ "epoch": 1.17,
357
+ "learning_rate": 3.4992784992784994e-05,
358
+ "loss": 0.9416,
359
+ "step": 570
360
+ },
361
+ {
362
+ "epoch": 1.18,
363
+ "learning_rate": 3.463203463203463e-05,
364
+ "loss": 0.1318,
365
+ "step": 580
366
+ },
367
+ {
368
+ "epoch": 1.18,
369
+ "learning_rate": 3.427128427128427e-05,
370
+ "loss": 0.358,
371
+ "step": 590
372
+ },
373
+ {
374
+ "epoch": 1.19,
375
+ "learning_rate": 3.391053391053391e-05,
376
+ "loss": 0.9192,
377
+ "step": 600
378
+ },
379
+ {
380
+ "epoch": 1.2,
381
+ "learning_rate": 3.3549783549783555e-05,
382
+ "loss": 0.6286,
383
+ "step": 610
384
+ },
385
+ {
386
+ "epoch": 1.2,
387
+ "eval_accuracy": 0.8356164383561644,
388
+ "eval_loss": 0.39893510937690735,
389
+ "eval_runtime": 27.6316,
390
+ "eval_samples_per_second": 7.926,
391
+ "eval_steps_per_second": 3.981,
392
+ "step": 618
393
+ },
394
+ {
395
+ "epoch": 2.0,
396
+ "learning_rate": 3.318903318903319e-05,
397
+ "loss": 0.544,
398
+ "step": 620
399
+ },
400
+ {
401
+ "epoch": 2.01,
402
+ "learning_rate": 3.282828282828283e-05,
403
+ "loss": 0.2274,
404
+ "step": 630
405
+ },
406
+ {
407
+ "epoch": 2.01,
408
+ "learning_rate": 3.246753246753247e-05,
409
+ "loss": 0.1103,
410
+ "step": 640
411
+ },
412
+ {
413
+ "epoch": 2.02,
414
+ "learning_rate": 3.210678210678211e-05,
415
+ "loss": 0.5241,
416
+ "step": 650
417
+ },
418
+ {
419
+ "epoch": 2.03,
420
+ "learning_rate": 3.1746031746031745e-05,
421
+ "loss": 0.1825,
422
+ "step": 660
423
+ },
424
+ {
425
+ "epoch": 2.03,
426
+ "learning_rate": 3.1385281385281387e-05,
427
+ "loss": 0.0486,
428
+ "step": 670
429
+ },
430
+ {
431
+ "epoch": 2.04,
432
+ "learning_rate": 3.102453102453103e-05,
433
+ "loss": 0.2033,
434
+ "step": 680
435
+ },
436
+ {
437
+ "epoch": 2.05,
438
+ "learning_rate": 3.0663780663780664e-05,
439
+ "loss": 0.264,
440
+ "step": 690
441
+ },
442
+ {
443
+ "epoch": 2.05,
444
+ "learning_rate": 3.0303030303030306e-05,
445
+ "loss": 0.4847,
446
+ "step": 700
447
+ },
448
+ {
449
+ "epoch": 2.06,
450
+ "learning_rate": 2.9942279942279944e-05,
451
+ "loss": 0.3505,
452
+ "step": 710
453
+ },
454
+ {
455
+ "epoch": 2.07,
456
+ "learning_rate": 2.9581529581529583e-05,
457
+ "loss": 0.0655,
458
+ "step": 720
459
+ },
460
+ {
461
+ "epoch": 2.07,
462
+ "learning_rate": 2.922077922077922e-05,
463
+ "loss": 0.0815,
464
+ "step": 730
465
+ },
466
+ {
467
+ "epoch": 2.08,
468
+ "learning_rate": 2.886002886002886e-05,
469
+ "loss": 0.4071,
470
+ "step": 740
471
+ },
472
+ {
473
+ "epoch": 2.09,
474
+ "learning_rate": 2.8499278499278502e-05,
475
+ "loss": 0.5683,
476
+ "step": 750
477
+ },
478
+ {
479
+ "epoch": 2.09,
480
+ "learning_rate": 2.813852813852814e-05,
481
+ "loss": 0.4974,
482
+ "step": 760
483
+ },
484
+ {
485
+ "epoch": 2.1,
486
+ "learning_rate": 2.777777777777778e-05,
487
+ "loss": 0.0227,
488
+ "step": 770
489
+ },
490
+ {
491
+ "epoch": 2.11,
492
+ "learning_rate": 2.7417027417027418e-05,
493
+ "loss": 0.2471,
494
+ "step": 780
495
+ },
496
+ {
497
+ "epoch": 2.11,
498
+ "learning_rate": 2.7056277056277056e-05,
499
+ "loss": 0.0955,
500
+ "step": 790
501
+ },
502
+ {
503
+ "epoch": 2.12,
504
+ "learning_rate": 2.6695526695526695e-05,
505
+ "loss": 0.5168,
506
+ "step": 800
507
+ },
508
+ {
509
+ "epoch": 2.12,
510
+ "learning_rate": 2.6334776334776333e-05,
511
+ "loss": 0.3265,
512
+ "step": 810
513
+ },
514
+ {
515
+ "epoch": 2.13,
516
+ "learning_rate": 2.5974025974025972e-05,
517
+ "loss": 0.0915,
518
+ "step": 820
519
+ },
520
+ {
521
+ "epoch": 2.14,
522
+ "learning_rate": 2.5613275613275617e-05,
523
+ "loss": 0.2889,
524
+ "step": 830
525
+ },
526
+ {
527
+ "epoch": 2.14,
528
+ "learning_rate": 2.5252525252525256e-05,
529
+ "loss": 0.7475,
530
+ "step": 840
531
+ },
532
+ {
533
+ "epoch": 2.15,
534
+ "learning_rate": 2.4891774891774894e-05,
535
+ "loss": 0.1556,
536
+ "step": 850
537
+ },
538
+ {
539
+ "epoch": 2.16,
540
+ "learning_rate": 2.4531024531024533e-05,
541
+ "loss": 0.3085,
542
+ "step": 860
543
+ },
544
+ {
545
+ "epoch": 2.16,
546
+ "learning_rate": 2.417027417027417e-05,
547
+ "loss": 0.1803,
548
+ "step": 870
549
+ },
550
+ {
551
+ "epoch": 2.17,
552
+ "learning_rate": 2.380952380952381e-05,
553
+ "loss": 0.537,
554
+ "step": 880
555
+ },
556
+ {
557
+ "epoch": 2.18,
558
+ "learning_rate": 2.3448773448773452e-05,
559
+ "loss": 0.0856,
560
+ "step": 890
561
+ },
562
+ {
563
+ "epoch": 2.18,
564
+ "learning_rate": 2.308802308802309e-05,
565
+ "loss": 0.0916,
566
+ "step": 900
567
+ },
568
+ {
569
+ "epoch": 2.19,
570
+ "learning_rate": 2.272727272727273e-05,
571
+ "loss": 0.0067,
572
+ "step": 910
573
+ },
574
+ {
575
+ "epoch": 2.2,
576
+ "learning_rate": 2.2366522366522368e-05,
577
+ "loss": 0.1874,
578
+ "step": 920
579
+ },
580
+ {
581
+ "epoch": 2.2,
582
+ "eval_accuracy": 0.9863013698630136,
583
+ "eval_loss": 0.029501434415578842,
584
+ "eval_runtime": 29.1447,
585
+ "eval_samples_per_second": 7.514,
586
+ "eval_steps_per_second": 3.774,
587
+ "step": 927
588
+ },
589
+ {
590
+ "epoch": 3.0,
591
+ "learning_rate": 2.2005772005772006e-05,
592
+ "loss": 0.2108,
593
+ "step": 930
594
+ },
595
+ {
596
+ "epoch": 3.01,
597
+ "learning_rate": 2.1645021645021645e-05,
598
+ "loss": 0.0128,
599
+ "step": 940
600
+ },
601
+ {
602
+ "epoch": 3.01,
603
+ "learning_rate": 2.1284271284271284e-05,
604
+ "loss": 0.1758,
605
+ "step": 950
606
+ },
607
+ {
608
+ "epoch": 3.02,
609
+ "learning_rate": 2.0923520923520926e-05,
610
+ "loss": 0.2967,
611
+ "step": 960
612
+ },
613
+ {
614
+ "epoch": 3.03,
615
+ "learning_rate": 2.0562770562770564e-05,
616
+ "loss": 0.0074,
617
+ "step": 970
618
+ },
619
+ {
620
+ "epoch": 3.03,
621
+ "learning_rate": 2.0202020202020203e-05,
622
+ "loss": 0.0223,
623
+ "step": 980
624
+ },
625
+ {
626
+ "epoch": 3.04,
627
+ "learning_rate": 1.984126984126984e-05,
628
+ "loss": 0.329,
629
+ "step": 990
630
+ },
631
+ {
632
+ "epoch": 3.05,
633
+ "learning_rate": 1.9480519480519483e-05,
634
+ "loss": 0.6423,
635
+ "step": 1000
636
+ },
637
+ {
638
+ "epoch": 3.05,
639
+ "learning_rate": 1.9119769119769122e-05,
640
+ "loss": 0.0031,
641
+ "step": 1010
642
+ },
643
+ {
644
+ "epoch": 3.06,
645
+ "learning_rate": 1.875901875901876e-05,
646
+ "loss": 0.0095,
647
+ "step": 1020
648
+ },
649
+ {
650
+ "epoch": 3.07,
651
+ "learning_rate": 1.83982683982684e-05,
652
+ "loss": 0.2479,
653
+ "step": 1030
654
+ },
655
+ {
656
+ "epoch": 3.07,
657
+ "learning_rate": 1.8037518037518038e-05,
658
+ "loss": 0.0092,
659
+ "step": 1040
660
+ },
661
+ {
662
+ "epoch": 3.08,
663
+ "learning_rate": 1.7676767676767676e-05,
664
+ "loss": 0.0762,
665
+ "step": 1050
666
+ },
667
+ {
668
+ "epoch": 3.09,
669
+ "learning_rate": 1.7316017316017315e-05,
670
+ "loss": 0.004,
671
+ "step": 1060
672
+ },
673
+ {
674
+ "epoch": 3.09,
675
+ "learning_rate": 1.6955266955266957e-05,
676
+ "loss": 0.0034,
677
+ "step": 1070
678
+ },
679
+ {
680
+ "epoch": 3.1,
681
+ "learning_rate": 1.6594516594516595e-05,
682
+ "loss": 0.0028,
683
+ "step": 1080
684
+ },
685
+ {
686
+ "epoch": 3.11,
687
+ "learning_rate": 1.6233766233766234e-05,
688
+ "loss": 0.0146,
689
+ "step": 1090
690
+ },
691
+ {
692
+ "epoch": 3.11,
693
+ "learning_rate": 1.5873015873015872e-05,
694
+ "loss": 0.0143,
695
+ "step": 1100
696
+ },
697
+ {
698
+ "epoch": 3.12,
699
+ "learning_rate": 1.5512265512265514e-05,
700
+ "loss": 0.0034,
701
+ "step": 1110
702
+ },
703
+ {
704
+ "epoch": 3.13,
705
+ "learning_rate": 1.5151515151515153e-05,
706
+ "loss": 0.1589,
707
+ "step": 1120
708
+ },
709
+ {
710
+ "epoch": 3.13,
711
+ "learning_rate": 1.4790764790764791e-05,
712
+ "loss": 0.0032,
713
+ "step": 1130
714
+ },
715
+ {
716
+ "epoch": 3.14,
717
+ "learning_rate": 1.443001443001443e-05,
718
+ "loss": 0.3291,
719
+ "step": 1140
720
+ },
721
+ {
722
+ "epoch": 3.14,
723
+ "learning_rate": 1.406926406926407e-05,
724
+ "loss": 0.0644,
725
+ "step": 1150
726
+ },
727
+ {
728
+ "epoch": 3.15,
729
+ "learning_rate": 1.3708513708513709e-05,
730
+ "loss": 0.0078,
731
+ "step": 1160
732
+ },
733
+ {
734
+ "epoch": 3.16,
735
+ "learning_rate": 1.3347763347763347e-05,
736
+ "loss": 0.0576,
737
+ "step": 1170
738
+ },
739
+ {
740
+ "epoch": 3.16,
741
+ "learning_rate": 1.2987012987012986e-05,
742
+ "loss": 0.5392,
743
+ "step": 1180
744
+ },
745
+ {
746
+ "epoch": 3.17,
747
+ "learning_rate": 1.2626262626262628e-05,
748
+ "loss": 0.0208,
749
+ "step": 1190
750
+ },
751
+ {
752
+ "epoch": 3.18,
753
+ "learning_rate": 1.2265512265512267e-05,
754
+ "loss": 0.0025,
755
+ "step": 1200
756
+ },
757
+ {
758
+ "epoch": 3.18,
759
+ "learning_rate": 1.1904761904761905e-05,
760
+ "loss": 0.0617,
761
+ "step": 1210
762
+ },
763
+ {
764
+ "epoch": 3.19,
765
+ "learning_rate": 1.1544011544011545e-05,
766
+ "loss": 0.0035,
767
+ "step": 1220
768
+ },
769
+ {
770
+ "epoch": 3.2,
771
+ "learning_rate": 1.1183261183261184e-05,
772
+ "loss": 0.0107,
773
+ "step": 1230
774
+ },
775
+ {
776
+ "epoch": 3.2,
777
+ "eval_accuracy": 0.9863013698630136,
778
+ "eval_loss": 0.049655068665742874,
779
+ "eval_runtime": 28.1147,
780
+ "eval_samples_per_second": 7.79,
781
+ "eval_steps_per_second": 3.913,
782
+ "step": 1236
783
+ },
784
+ {
785
+ "epoch": 4.0,
786
+ "learning_rate": 1.0822510822510823e-05,
787
+ "loss": 0.0022,
788
+ "step": 1240
789
+ },
790
+ {
791
+ "epoch": 4.01,
792
+ "learning_rate": 1.0461760461760463e-05,
793
+ "loss": 0.1563,
794
+ "step": 1250
795
+ },
796
+ {
797
+ "epoch": 4.02,
798
+ "learning_rate": 1.0101010101010101e-05,
799
+ "loss": 0.0031,
800
+ "step": 1260
801
+ },
802
+ {
803
+ "epoch": 4.02,
804
+ "learning_rate": 9.740259740259742e-06,
805
+ "loss": 0.0027,
806
+ "step": 1270
807
+ },
808
+ {
809
+ "epoch": 4.03,
810
+ "learning_rate": 9.37950937950938e-06,
811
+ "loss": 0.0085,
812
+ "step": 1280
813
+ },
814
+ {
815
+ "epoch": 4.04,
816
+ "learning_rate": 9.018759018759019e-06,
817
+ "loss": 0.0024,
818
+ "step": 1290
819
+ },
820
+ {
821
+ "epoch": 4.04,
822
+ "learning_rate": 8.658008658008657e-06,
823
+ "loss": 0.003,
824
+ "step": 1300
825
+ },
826
+ {
827
+ "epoch": 4.05,
828
+ "learning_rate": 8.297258297258298e-06,
829
+ "loss": 0.0027,
830
+ "step": 1310
831
+ },
832
+ {
833
+ "epoch": 4.05,
834
+ "learning_rate": 7.936507936507936e-06,
835
+ "loss": 0.2252,
836
+ "step": 1320
837
+ },
838
+ {
839
+ "epoch": 4.06,
840
+ "learning_rate": 7.5757575757575764e-06,
841
+ "loss": 0.1245,
842
+ "step": 1330
843
+ },
844
+ {
845
+ "epoch": 4.07,
846
+ "learning_rate": 7.215007215007215e-06,
847
+ "loss": 0.0019,
848
+ "step": 1340
849
+ },
850
+ {
851
+ "epoch": 4.07,
852
+ "learning_rate": 6.854256854256854e-06,
853
+ "loss": 0.0021,
854
+ "step": 1350
855
+ },
856
+ {
857
+ "epoch": 4.08,
858
+ "learning_rate": 6.493506493506493e-06,
859
+ "loss": 0.0102,
860
+ "step": 1360
861
+ },
862
+ {
863
+ "epoch": 4.09,
864
+ "learning_rate": 6.132756132756133e-06,
865
+ "loss": 0.0033,
866
+ "step": 1370
867
+ },
868
+ {
869
+ "epoch": 4.09,
870
+ "learning_rate": 5.772005772005773e-06,
871
+ "loss": 0.0024,
872
+ "step": 1380
873
+ },
874
+ {
875
+ "epoch": 4.1,
876
+ "learning_rate": 5.411255411255411e-06,
877
+ "loss": 0.0024,
878
+ "step": 1390
879
+ },
880
+ {
881
+ "epoch": 4.11,
882
+ "learning_rate": 5.050505050505051e-06,
883
+ "loss": 0.0021,
884
+ "step": 1400
885
+ },
886
+ {
887
+ "epoch": 4.11,
888
+ "learning_rate": 4.68975468975469e-06,
889
+ "loss": 0.0029,
890
+ "step": 1410
891
+ },
892
+ {
893
+ "epoch": 4.12,
894
+ "learning_rate": 4.329004329004329e-06,
895
+ "loss": 0.0069,
896
+ "step": 1420
897
+ },
898
+ {
899
+ "epoch": 4.13,
900
+ "learning_rate": 3.968253968253968e-06,
901
+ "loss": 0.0159,
902
+ "step": 1430
903
+ },
904
+ {
905
+ "epoch": 4.13,
906
+ "learning_rate": 3.6075036075036075e-06,
907
+ "loss": 0.0021,
908
+ "step": 1440
909
+ },
910
+ {
911
+ "epoch": 4.14,
912
+ "learning_rate": 3.2467532467532465e-06,
913
+ "loss": 0.0022,
914
+ "step": 1450
915
+ },
916
+ {
917
+ "epoch": 4.15,
918
+ "learning_rate": 2.8860028860028863e-06,
919
+ "loss": 0.0026,
920
+ "step": 1460
921
+ },
922
+ {
923
+ "epoch": 4.15,
924
+ "learning_rate": 2.5252525252525253e-06,
925
+ "loss": 0.0019,
926
+ "step": 1470
927
+ },
928
+ {
929
+ "epoch": 4.16,
930
+ "learning_rate": 2.1645021645021643e-06,
931
+ "loss": 0.0027,
932
+ "step": 1480
933
+ },
934
+ {
935
+ "epoch": 4.16,
936
+ "learning_rate": 1.8037518037518038e-06,
937
+ "loss": 0.0025,
938
+ "step": 1490
939
+ },
940
+ {
941
+ "epoch": 4.17,
942
+ "learning_rate": 1.4430014430014432e-06,
943
+ "loss": 0.0025,
944
+ "step": 1500
945
+ },
946
+ {
947
+ "epoch": 4.18,
948
+ "learning_rate": 1.0822510822510822e-06,
949
+ "loss": 0.0023,
950
+ "step": 1510
951
+ },
952
+ {
953
+ "epoch": 4.18,
954
+ "learning_rate": 7.215007215007216e-07,
955
+ "loss": 0.0024,
956
+ "step": 1520
957
+ },
958
+ {
959
+ "epoch": 4.19,
960
+ "learning_rate": 3.607503607503608e-07,
961
+ "loss": 0.002,
962
+ "step": 1530
963
+ },
964
+ {
965
+ "epoch": 4.2,
966
+ "learning_rate": 0.0,
967
+ "loss": 0.0024,
968
+ "step": 1540
969
+ },
970
+ {
971
+ "epoch": 4.2,
972
+ "eval_accuracy": 1.0,
973
+ "eval_loss": 0.005777956917881966,
974
+ "eval_runtime": 27.7557,
975
+ "eval_samples_per_second": 7.89,
976
+ "eval_steps_per_second": 3.963,
977
+ "step": 1540
978
+ },
979
+ {
980
+ "epoch": 4.2,
981
+ "step": 1540,
982
+ "total_flos": 3.8331681355608883e+18,
983
+ "train_loss": 0.5046061665956657,
984
+ "train_runtime": 1118.8917,
985
+ "train_samples_per_second": 2.753,
986
+ "train_steps_per_second": 1.376
987
+ },
988
+ {
989
+ "epoch": 4.2,
990
+ "eval_accuracy": 0.9930693069306931,
991
+ "eval_loss": 0.032540928572416306,
992
+ "eval_runtime": 128.4671,
993
+ "eval_samples_per_second": 7.862,
994
+ "eval_steps_per_second": 3.931,
995
+ "step": 1540
996
+ },
997
+ {
998
+ "epoch": 4.2,
999
+ "eval_accuracy": 0.9930693069306931,
1000
+ "eval_loss": 0.032540928572416306,
1001
+ "eval_runtime": 127.8623,
1002
+ "eval_samples_per_second": 7.899,
1003
+ "eval_steps_per_second": 3.95,
1004
+ "step": 1540
1005
+ }
1006
+ ],
1007
+ "max_steps": 1540,
1008
+ "num_train_epochs": 9223372036854775807,
1009
+ "total_flos": 3.8331681355608883e+18,
1010
+ "trial_name": null,
1011
+ "trial_params": null
1012
+ }
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d1d935c7630d059ce9bf0f00e2bf80bed08500afcee0170a21a83887317f7073
3
  size 4027
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e1dca3997653b1cdb565474679b4645175c6ada2fe80a14f780fdef952112dac
3
  size 4027