dvs commited on
Commit
309ba1b
1 Parent(s): 2012993

End of training

Browse files
all_results.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "eval_accuracy": 0.796875,
3
+ "eval_loss": 1.0793333053588867
4
+ }
runs/Jul30_02-04-29_0a73ac2281b9/events.out.tfevents.1690682762.0a73ac2281b9.1276.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:77ab2b5bddfb7e1962af1444851419db35dd878d760b3f731fb08b99453940a2
3
- size 34304
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5f5e527186579f58e8daea26050a45ab54d29d29292973dcf48521569d9038c5
3
+ size 34627
test_results.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "eval_accuracy": 0.796875,
3
+ "eval_loss": 1.0793333053588867
4
+ }
trainer_state.json ADDED
@@ -0,0 +1,1135 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.8191489361702128,
3
+ "best_model_checkpoint": "videomae-base-finetuned-movienet-take2/checkpoint-1302",
4
+ "epoch": 9.010135135135135,
5
+ "global_step": 1704,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 0.0,
12
+ "learning_rate": 1.6891891891891894e-06,
13
+ "loss": 1.6719,
14
+ "step": 10
15
+ },
16
+ {
17
+ "epoch": 0.01,
18
+ "learning_rate": 3.3783783783783788e-06,
19
+ "loss": 1.6396,
20
+ "step": 20
21
+ },
22
+ {
23
+ "epoch": 0.01,
24
+ "learning_rate": 5.067567567567568e-06,
25
+ "loss": 1.5972,
26
+ "step": 30
27
+ },
28
+ {
29
+ "epoch": 0.01,
30
+ "learning_rate": 6.7567567567567575e-06,
31
+ "loss": 1.598,
32
+ "step": 40
33
+ },
34
+ {
35
+ "epoch": 0.02,
36
+ "learning_rate": 8.445945945945946e-06,
37
+ "loss": 1.596,
38
+ "step": 50
39
+ },
40
+ {
41
+ "epoch": 0.02,
42
+ "learning_rate": 1.0135135135135136e-05,
43
+ "loss": 1.568,
44
+ "step": 60
45
+ },
46
+ {
47
+ "epoch": 0.02,
48
+ "learning_rate": 1.1824324324324325e-05,
49
+ "loss": 1.5668,
50
+ "step": 70
51
+ },
52
+ {
53
+ "epoch": 0.03,
54
+ "learning_rate": 1.3513513513513515e-05,
55
+ "loss": 1.5481,
56
+ "step": 80
57
+ },
58
+ {
59
+ "epoch": 0.03,
60
+ "learning_rate": 1.5202702702702704e-05,
61
+ "loss": 1.5096,
62
+ "step": 90
63
+ },
64
+ {
65
+ "epoch": 0.03,
66
+ "learning_rate": 1.6891891891891892e-05,
67
+ "loss": 1.5268,
68
+ "step": 100
69
+ },
70
+ {
71
+ "epoch": 0.04,
72
+ "learning_rate": 1.8581081081081082e-05,
73
+ "loss": 1.5309,
74
+ "step": 110
75
+ },
76
+ {
77
+ "epoch": 0.04,
78
+ "learning_rate": 2.0270270270270273e-05,
79
+ "loss": 1.4613,
80
+ "step": 120
81
+ },
82
+ {
83
+ "epoch": 0.04,
84
+ "learning_rate": 2.195945945945946e-05,
85
+ "loss": 1.4655,
86
+ "step": 130
87
+ },
88
+ {
89
+ "epoch": 0.05,
90
+ "learning_rate": 2.364864864864865e-05,
91
+ "loss": 1.1861,
92
+ "step": 140
93
+ },
94
+ {
95
+ "epoch": 0.05,
96
+ "learning_rate": 2.533783783783784e-05,
97
+ "loss": 1.2159,
98
+ "step": 150
99
+ },
100
+ {
101
+ "epoch": 0.05,
102
+ "learning_rate": 2.702702702702703e-05,
103
+ "loss": 1.0353,
104
+ "step": 160
105
+ },
106
+ {
107
+ "epoch": 0.06,
108
+ "learning_rate": 2.8716216216216217e-05,
109
+ "loss": 1.0126,
110
+ "step": 170
111
+ },
112
+ {
113
+ "epoch": 0.06,
114
+ "learning_rate": 3.0405405405405407e-05,
115
+ "loss": 1.0917,
116
+ "step": 180
117
+ },
118
+ {
119
+ "epoch": 0.06,
120
+ "eval_accuracy": 0.5425531914893617,
121
+ "eval_loss": 1.008441686630249,
122
+ "eval_runtime": 325.3141,
123
+ "eval_samples_per_second": 0.578,
124
+ "eval_steps_per_second": 0.074,
125
+ "step": 186
126
+ },
127
+ {
128
+ "epoch": 1.0,
129
+ "learning_rate": 3.20945945945946e-05,
130
+ "loss": 0.9827,
131
+ "step": 190
132
+ },
133
+ {
134
+ "epoch": 1.0,
135
+ "learning_rate": 3.3783783783783784e-05,
136
+ "loss": 0.9337,
137
+ "step": 200
138
+ },
139
+ {
140
+ "epoch": 1.01,
141
+ "learning_rate": 3.547297297297297e-05,
142
+ "loss": 0.9799,
143
+ "step": 210
144
+ },
145
+ {
146
+ "epoch": 1.01,
147
+ "learning_rate": 3.7162162162162165e-05,
148
+ "loss": 0.8158,
149
+ "step": 220
150
+ },
151
+ {
152
+ "epoch": 1.01,
153
+ "learning_rate": 3.885135135135135e-05,
154
+ "loss": 0.791,
155
+ "step": 230
156
+ },
157
+ {
158
+ "epoch": 1.02,
159
+ "learning_rate": 4.0540540540540545e-05,
160
+ "loss": 1.0988,
161
+ "step": 240
162
+ },
163
+ {
164
+ "epoch": 1.02,
165
+ "learning_rate": 4.222972972972973e-05,
166
+ "loss": 0.934,
167
+ "step": 250
168
+ },
169
+ {
170
+ "epoch": 1.02,
171
+ "learning_rate": 4.391891891891892e-05,
172
+ "loss": 0.8967,
173
+ "step": 260
174
+ },
175
+ {
176
+ "epoch": 1.03,
177
+ "learning_rate": 4.560810810810811e-05,
178
+ "loss": 0.9449,
179
+ "step": 270
180
+ },
181
+ {
182
+ "epoch": 1.03,
183
+ "learning_rate": 4.72972972972973e-05,
184
+ "loss": 0.7262,
185
+ "step": 280
186
+ },
187
+ {
188
+ "epoch": 1.04,
189
+ "learning_rate": 4.8986486486486486e-05,
190
+ "loss": 0.8733,
191
+ "step": 290
192
+ },
193
+ {
194
+ "epoch": 1.04,
195
+ "learning_rate": 4.9924924924924924e-05,
196
+ "loss": 0.7646,
197
+ "step": 300
198
+ },
199
+ {
200
+ "epoch": 1.04,
201
+ "learning_rate": 4.973723723723724e-05,
202
+ "loss": 0.6704,
203
+ "step": 310
204
+ },
205
+ {
206
+ "epoch": 1.05,
207
+ "learning_rate": 4.954954954954955e-05,
208
+ "loss": 0.8049,
209
+ "step": 320
210
+ },
211
+ {
212
+ "epoch": 1.05,
213
+ "learning_rate": 4.9361861861861864e-05,
214
+ "loss": 0.6962,
215
+ "step": 330
216
+ },
217
+ {
218
+ "epoch": 1.05,
219
+ "learning_rate": 4.9174174174174175e-05,
220
+ "loss": 0.6775,
221
+ "step": 340
222
+ },
223
+ {
224
+ "epoch": 1.06,
225
+ "learning_rate": 4.8986486486486486e-05,
226
+ "loss": 0.6874,
227
+ "step": 350
228
+ },
229
+ {
230
+ "epoch": 1.06,
231
+ "learning_rate": 4.87987987987988e-05,
232
+ "loss": 0.7424,
233
+ "step": 360
234
+ },
235
+ {
236
+ "epoch": 1.06,
237
+ "learning_rate": 4.8611111111111115e-05,
238
+ "loss": 0.7221,
239
+ "step": 370
240
+ },
241
+ {
242
+ "epoch": 1.06,
243
+ "eval_accuracy": 0.7180851063829787,
244
+ "eval_loss": 0.6874406933784485,
245
+ "eval_runtime": 140.1323,
246
+ "eval_samples_per_second": 1.342,
247
+ "eval_steps_per_second": 0.171,
248
+ "step": 372
249
+ },
250
+ {
251
+ "epoch": 2.0,
252
+ "learning_rate": 4.8423423423423426e-05,
253
+ "loss": 0.4945,
254
+ "step": 380
255
+ },
256
+ {
257
+ "epoch": 2.01,
258
+ "learning_rate": 4.823573573573574e-05,
259
+ "loss": 0.493,
260
+ "step": 390
261
+ },
262
+ {
263
+ "epoch": 2.01,
264
+ "learning_rate": 4.804804804804805e-05,
265
+ "loss": 0.7461,
266
+ "step": 400
267
+ },
268
+ {
269
+ "epoch": 2.01,
270
+ "learning_rate": 4.786036036036036e-05,
271
+ "loss": 0.4885,
272
+ "step": 410
273
+ },
274
+ {
275
+ "epoch": 2.02,
276
+ "learning_rate": 4.767267267267268e-05,
277
+ "loss": 0.6439,
278
+ "step": 420
279
+ },
280
+ {
281
+ "epoch": 2.02,
282
+ "learning_rate": 4.748498498498499e-05,
283
+ "loss": 0.6739,
284
+ "step": 430
285
+ },
286
+ {
287
+ "epoch": 2.02,
288
+ "learning_rate": 4.72972972972973e-05,
289
+ "loss": 0.5467,
290
+ "step": 440
291
+ },
292
+ {
293
+ "epoch": 2.03,
294
+ "learning_rate": 4.710960960960961e-05,
295
+ "loss": 0.6623,
296
+ "step": 450
297
+ },
298
+ {
299
+ "epoch": 2.03,
300
+ "learning_rate": 4.692192192192192e-05,
301
+ "loss": 0.4457,
302
+ "step": 460
303
+ },
304
+ {
305
+ "epoch": 2.03,
306
+ "learning_rate": 4.673423423423424e-05,
307
+ "loss": 0.4094,
308
+ "step": 470
309
+ },
310
+ {
311
+ "epoch": 2.04,
312
+ "learning_rate": 4.654654654654655e-05,
313
+ "loss": 0.5707,
314
+ "step": 480
315
+ },
316
+ {
317
+ "epoch": 2.04,
318
+ "learning_rate": 4.635885885885886e-05,
319
+ "loss": 0.5932,
320
+ "step": 490
321
+ },
322
+ {
323
+ "epoch": 2.04,
324
+ "learning_rate": 4.617117117117117e-05,
325
+ "loss": 0.5556,
326
+ "step": 500
327
+ },
328
+ {
329
+ "epoch": 2.05,
330
+ "learning_rate": 4.5983483483483484e-05,
331
+ "loss": 0.6922,
332
+ "step": 510
333
+ },
334
+ {
335
+ "epoch": 2.05,
336
+ "learning_rate": 4.57957957957958e-05,
337
+ "loss": 0.5235,
338
+ "step": 520
339
+ },
340
+ {
341
+ "epoch": 2.05,
342
+ "learning_rate": 4.560810810810811e-05,
343
+ "loss": 0.5206,
344
+ "step": 530
345
+ },
346
+ {
347
+ "epoch": 2.06,
348
+ "learning_rate": 4.5420420420420424e-05,
349
+ "loss": 0.5925,
350
+ "step": 540
351
+ },
352
+ {
353
+ "epoch": 2.06,
354
+ "learning_rate": 4.5232732732732735e-05,
355
+ "loss": 0.5015,
356
+ "step": 550
357
+ },
358
+ {
359
+ "epoch": 2.06,
360
+ "eval_accuracy": 0.675531914893617,
361
+ "eval_loss": 0.8818714022636414,
362
+ "eval_runtime": 139.1461,
363
+ "eval_samples_per_second": 1.351,
364
+ "eval_steps_per_second": 0.172,
365
+ "step": 558
366
+ },
367
+ {
368
+ "epoch": 3.0,
369
+ "learning_rate": 4.5045045045045046e-05,
370
+ "loss": 0.9722,
371
+ "step": 560
372
+ },
373
+ {
374
+ "epoch": 3.0,
375
+ "learning_rate": 4.4857357357357364e-05,
376
+ "loss": 0.3877,
377
+ "step": 570
378
+ },
379
+ {
380
+ "epoch": 3.01,
381
+ "learning_rate": 4.4669669669669675e-05,
382
+ "loss": 0.4829,
383
+ "step": 580
384
+ },
385
+ {
386
+ "epoch": 3.01,
387
+ "learning_rate": 4.4481981981981986e-05,
388
+ "loss": 0.4713,
389
+ "step": 590
390
+ },
391
+ {
392
+ "epoch": 3.01,
393
+ "learning_rate": 4.42942942942943e-05,
394
+ "loss": 0.3729,
395
+ "step": 600
396
+ },
397
+ {
398
+ "epoch": 3.02,
399
+ "learning_rate": 4.410660660660661e-05,
400
+ "loss": 0.3128,
401
+ "step": 610
402
+ },
403
+ {
404
+ "epoch": 3.02,
405
+ "learning_rate": 4.391891891891892e-05,
406
+ "loss": 0.553,
407
+ "step": 620
408
+ },
409
+ {
410
+ "epoch": 3.02,
411
+ "learning_rate": 4.373123123123124e-05,
412
+ "loss": 0.4738,
413
+ "step": 630
414
+ },
415
+ {
416
+ "epoch": 3.03,
417
+ "learning_rate": 4.354354354354355e-05,
418
+ "loss": 0.3917,
419
+ "step": 640
420
+ },
421
+ {
422
+ "epoch": 3.03,
423
+ "learning_rate": 4.335585585585586e-05,
424
+ "loss": 0.3353,
425
+ "step": 650
426
+ },
427
+ {
428
+ "epoch": 3.03,
429
+ "learning_rate": 4.316816816816817e-05,
430
+ "loss": 0.4164,
431
+ "step": 660
432
+ },
433
+ {
434
+ "epoch": 3.04,
435
+ "learning_rate": 4.298048048048048e-05,
436
+ "loss": 0.4818,
437
+ "step": 670
438
+ },
439
+ {
440
+ "epoch": 3.04,
441
+ "learning_rate": 4.27927927927928e-05,
442
+ "loss": 0.4163,
443
+ "step": 680
444
+ },
445
+ {
446
+ "epoch": 3.04,
447
+ "learning_rate": 4.260510510510511e-05,
448
+ "loss": 0.338,
449
+ "step": 690
450
+ },
451
+ {
452
+ "epoch": 3.05,
453
+ "learning_rate": 4.241741741741742e-05,
454
+ "loss": 0.3834,
455
+ "step": 700
456
+ },
457
+ {
458
+ "epoch": 3.05,
459
+ "learning_rate": 4.222972972972973e-05,
460
+ "loss": 0.3242,
461
+ "step": 710
462
+ },
463
+ {
464
+ "epoch": 3.05,
465
+ "learning_rate": 4.204204204204204e-05,
466
+ "loss": 0.3029,
467
+ "step": 720
468
+ },
469
+ {
470
+ "epoch": 3.06,
471
+ "learning_rate": 4.185435435435436e-05,
472
+ "loss": 0.483,
473
+ "step": 730
474
+ },
475
+ {
476
+ "epoch": 3.06,
477
+ "learning_rate": 4.166666666666667e-05,
478
+ "loss": 0.3678,
479
+ "step": 740
480
+ },
481
+ {
482
+ "epoch": 3.06,
483
+ "eval_accuracy": 0.7553191489361702,
484
+ "eval_loss": 0.6245753765106201,
485
+ "eval_runtime": 110.5708,
486
+ "eval_samples_per_second": 1.7,
487
+ "eval_steps_per_second": 0.217,
488
+ "step": 744
489
+ },
490
+ {
491
+ "epoch": 4.0,
492
+ "learning_rate": 4.147897897897898e-05,
493
+ "loss": 0.4088,
494
+ "step": 750
495
+ },
496
+ {
497
+ "epoch": 4.01,
498
+ "learning_rate": 4.1291291291291294e-05,
499
+ "loss": 0.2268,
500
+ "step": 760
501
+ },
502
+ {
503
+ "epoch": 4.01,
504
+ "learning_rate": 4.1103603603603605e-05,
505
+ "loss": 0.2889,
506
+ "step": 770
507
+ },
508
+ {
509
+ "epoch": 4.01,
510
+ "learning_rate": 4.091591591591592e-05,
511
+ "loss": 0.3062,
512
+ "step": 780
513
+ },
514
+ {
515
+ "epoch": 4.02,
516
+ "learning_rate": 4.0728228228228234e-05,
517
+ "loss": 0.2331,
518
+ "step": 790
519
+ },
520
+ {
521
+ "epoch": 4.02,
522
+ "learning_rate": 4.0540540540540545e-05,
523
+ "loss": 0.2727,
524
+ "step": 800
525
+ },
526
+ {
527
+ "epoch": 4.02,
528
+ "learning_rate": 4.0352852852852856e-05,
529
+ "loss": 0.0624,
530
+ "step": 810
531
+ },
532
+ {
533
+ "epoch": 4.03,
534
+ "learning_rate": 4.016516516516517e-05,
535
+ "loss": 0.2055,
536
+ "step": 820
537
+ },
538
+ {
539
+ "epoch": 4.03,
540
+ "learning_rate": 3.9977477477477485e-05,
541
+ "loss": 0.389,
542
+ "step": 830
543
+ },
544
+ {
545
+ "epoch": 4.03,
546
+ "learning_rate": 3.9789789789789796e-05,
547
+ "loss": 0.3561,
548
+ "step": 840
549
+ },
550
+ {
551
+ "epoch": 4.04,
552
+ "learning_rate": 3.960210210210211e-05,
553
+ "loss": 0.1887,
554
+ "step": 850
555
+ },
556
+ {
557
+ "epoch": 4.04,
558
+ "learning_rate": 3.941441441441442e-05,
559
+ "loss": 0.3762,
560
+ "step": 860
561
+ },
562
+ {
563
+ "epoch": 4.04,
564
+ "learning_rate": 3.922672672672673e-05,
565
+ "loss": 0.3079,
566
+ "step": 870
567
+ },
568
+ {
569
+ "epoch": 4.05,
570
+ "learning_rate": 3.903903903903904e-05,
571
+ "loss": 0.3228,
572
+ "step": 880
573
+ },
574
+ {
575
+ "epoch": 4.05,
576
+ "learning_rate": 3.885135135135135e-05,
577
+ "loss": 0.3692,
578
+ "step": 890
579
+ },
580
+ {
581
+ "epoch": 4.05,
582
+ "learning_rate": 3.866366366366366e-05,
583
+ "loss": 0.2801,
584
+ "step": 900
585
+ },
586
+ {
587
+ "epoch": 4.06,
588
+ "learning_rate": 3.8475975975975974e-05,
589
+ "loss": 0.1766,
590
+ "step": 910
591
+ },
592
+ {
593
+ "epoch": 4.06,
594
+ "learning_rate": 3.8288288288288285e-05,
595
+ "loss": 0.1004,
596
+ "step": 920
597
+ },
598
+ {
599
+ "epoch": 4.06,
600
+ "learning_rate": 3.81006006006006e-05,
601
+ "loss": 0.2759,
602
+ "step": 930
603
+ },
604
+ {
605
+ "epoch": 4.06,
606
+ "eval_accuracy": 0.7606382978723404,
607
+ "eval_loss": 0.9069157242774963,
608
+ "eval_runtime": 111.6385,
609
+ "eval_samples_per_second": 1.684,
610
+ "eval_steps_per_second": 0.215,
611
+ "step": 930
612
+ },
613
+ {
614
+ "epoch": 5.0,
615
+ "learning_rate": 3.7912912912912914e-05,
616
+ "loss": 0.0877,
617
+ "step": 940
618
+ },
619
+ {
620
+ "epoch": 5.01,
621
+ "learning_rate": 3.7725225225225225e-05,
622
+ "loss": 0.2627,
623
+ "step": 950
624
+ },
625
+ {
626
+ "epoch": 5.01,
627
+ "learning_rate": 3.7537537537537536e-05,
628
+ "loss": 0.1291,
629
+ "step": 960
630
+ },
631
+ {
632
+ "epoch": 5.01,
633
+ "learning_rate": 3.734984984984985e-05,
634
+ "loss": 0.2871,
635
+ "step": 970
636
+ },
637
+ {
638
+ "epoch": 5.02,
639
+ "learning_rate": 3.7162162162162165e-05,
640
+ "loss": 0.4653,
641
+ "step": 980
642
+ },
643
+ {
644
+ "epoch": 5.02,
645
+ "learning_rate": 3.6974474474474476e-05,
646
+ "loss": 0.2982,
647
+ "step": 990
648
+ },
649
+ {
650
+ "epoch": 5.02,
651
+ "learning_rate": 3.678678678678679e-05,
652
+ "loss": 0.2621,
653
+ "step": 1000
654
+ },
655
+ {
656
+ "epoch": 5.03,
657
+ "learning_rate": 3.65990990990991e-05,
658
+ "loss": 0.1349,
659
+ "step": 1010
660
+ },
661
+ {
662
+ "epoch": 5.03,
663
+ "learning_rate": 3.641141141141141e-05,
664
+ "loss": 0.1245,
665
+ "step": 1020
666
+ },
667
+ {
668
+ "epoch": 5.03,
669
+ "learning_rate": 3.622372372372373e-05,
670
+ "loss": 0.1143,
671
+ "step": 1030
672
+ },
673
+ {
674
+ "epoch": 5.04,
675
+ "learning_rate": 3.603603603603604e-05,
676
+ "loss": 0.2005,
677
+ "step": 1040
678
+ },
679
+ {
680
+ "epoch": 5.04,
681
+ "learning_rate": 3.584834834834835e-05,
682
+ "loss": 0.1979,
683
+ "step": 1050
684
+ },
685
+ {
686
+ "epoch": 5.04,
687
+ "learning_rate": 3.566066066066066e-05,
688
+ "loss": 0.3614,
689
+ "step": 1060
690
+ },
691
+ {
692
+ "epoch": 5.05,
693
+ "learning_rate": 3.547297297297297e-05,
694
+ "loss": 0.217,
695
+ "step": 1070
696
+ },
697
+ {
698
+ "epoch": 5.05,
699
+ "learning_rate": 3.528528528528528e-05,
700
+ "loss": 0.3563,
701
+ "step": 1080
702
+ },
703
+ {
704
+ "epoch": 5.05,
705
+ "learning_rate": 3.50975975975976e-05,
706
+ "loss": 0.355,
707
+ "step": 1090
708
+ },
709
+ {
710
+ "epoch": 5.06,
711
+ "learning_rate": 3.490990990990991e-05,
712
+ "loss": 0.239,
713
+ "step": 1100
714
+ },
715
+ {
716
+ "epoch": 5.06,
717
+ "learning_rate": 3.472222222222222e-05,
718
+ "loss": 0.3954,
719
+ "step": 1110
720
+ },
721
+ {
722
+ "epoch": 5.06,
723
+ "eval_accuracy": 0.7659574468085106,
724
+ "eval_loss": 0.8444852828979492,
725
+ "eval_runtime": 128.1344,
726
+ "eval_samples_per_second": 1.467,
727
+ "eval_steps_per_second": 0.187,
728
+ "step": 1116
729
+ },
730
+ {
731
+ "epoch": 6.0,
732
+ "learning_rate": 3.453453453453453e-05,
733
+ "loss": 0.279,
734
+ "step": 1120
735
+ },
736
+ {
737
+ "epoch": 6.0,
738
+ "learning_rate": 3.4346846846846844e-05,
739
+ "loss": 0.0194,
740
+ "step": 1130
741
+ },
742
+ {
743
+ "epoch": 6.01,
744
+ "learning_rate": 3.415915915915916e-05,
745
+ "loss": 0.0181,
746
+ "step": 1140
747
+ },
748
+ {
749
+ "epoch": 6.01,
750
+ "learning_rate": 3.397147147147147e-05,
751
+ "loss": 0.0482,
752
+ "step": 1150
753
+ },
754
+ {
755
+ "epoch": 6.01,
756
+ "learning_rate": 3.3783783783783784e-05,
757
+ "loss": 0.1143,
758
+ "step": 1160
759
+ },
760
+ {
761
+ "epoch": 6.02,
762
+ "learning_rate": 3.3596096096096095e-05,
763
+ "loss": 0.0299,
764
+ "step": 1170
765
+ },
766
+ {
767
+ "epoch": 6.02,
768
+ "learning_rate": 3.3408408408408406e-05,
769
+ "loss": 0.0741,
770
+ "step": 1180
771
+ },
772
+ {
773
+ "epoch": 6.03,
774
+ "learning_rate": 3.3220720720720724e-05,
775
+ "loss": 0.2265,
776
+ "step": 1190
777
+ },
778
+ {
779
+ "epoch": 6.03,
780
+ "learning_rate": 3.3033033033033035e-05,
781
+ "loss": 0.1181,
782
+ "step": 1200
783
+ },
784
+ {
785
+ "epoch": 6.03,
786
+ "learning_rate": 3.2845345345345346e-05,
787
+ "loss": 0.2526,
788
+ "step": 1210
789
+ },
790
+ {
791
+ "epoch": 6.04,
792
+ "learning_rate": 3.265765765765766e-05,
793
+ "loss": 0.206,
794
+ "step": 1220
795
+ },
796
+ {
797
+ "epoch": 6.04,
798
+ "learning_rate": 3.246996996996997e-05,
799
+ "loss": 0.2485,
800
+ "step": 1230
801
+ },
802
+ {
803
+ "epoch": 6.04,
804
+ "learning_rate": 3.2282282282282286e-05,
805
+ "loss": 0.0098,
806
+ "step": 1240
807
+ },
808
+ {
809
+ "epoch": 6.05,
810
+ "learning_rate": 3.20945945945946e-05,
811
+ "loss": 0.0529,
812
+ "step": 1250
813
+ },
814
+ {
815
+ "epoch": 6.05,
816
+ "learning_rate": 3.190690690690691e-05,
817
+ "loss": 0.3244,
818
+ "step": 1260
819
+ },
820
+ {
821
+ "epoch": 6.05,
822
+ "learning_rate": 3.171921921921922e-05,
823
+ "loss": 0.3008,
824
+ "step": 1270
825
+ },
826
+ {
827
+ "epoch": 6.06,
828
+ "learning_rate": 3.153153153153153e-05,
829
+ "loss": 0.2757,
830
+ "step": 1280
831
+ },
832
+ {
833
+ "epoch": 6.06,
834
+ "learning_rate": 3.134384384384385e-05,
835
+ "loss": 0.2518,
836
+ "step": 1290
837
+ },
838
+ {
839
+ "epoch": 6.06,
840
+ "learning_rate": 3.115615615615616e-05,
841
+ "loss": 0.0327,
842
+ "step": 1300
843
+ },
844
+ {
845
+ "epoch": 6.06,
846
+ "eval_accuracy": 0.8191489361702128,
847
+ "eval_loss": 0.8311583995819092,
848
+ "eval_runtime": 149.5054,
849
+ "eval_samples_per_second": 1.257,
850
+ "eval_steps_per_second": 0.161,
851
+ "step": 1302
852
+ },
853
+ {
854
+ "epoch": 7.0,
855
+ "learning_rate": 3.096846846846847e-05,
856
+ "loss": 0.1377,
857
+ "step": 1310
858
+ },
859
+ {
860
+ "epoch": 7.01,
861
+ "learning_rate": 3.078078078078078e-05,
862
+ "loss": 0.191,
863
+ "step": 1320
864
+ },
865
+ {
866
+ "epoch": 7.01,
867
+ "learning_rate": 3.059309309309309e-05,
868
+ "loss": 0.085,
869
+ "step": 1330
870
+ },
871
+ {
872
+ "epoch": 7.01,
873
+ "learning_rate": 3.0405405405405407e-05,
874
+ "loss": 0.0236,
875
+ "step": 1340
876
+ },
877
+ {
878
+ "epoch": 7.02,
879
+ "learning_rate": 3.0217717717717718e-05,
880
+ "loss": 0.0419,
881
+ "step": 1350
882
+ },
883
+ {
884
+ "epoch": 7.02,
885
+ "learning_rate": 3.0030030030030033e-05,
886
+ "loss": 0.1571,
887
+ "step": 1360
888
+ },
889
+ {
890
+ "epoch": 7.02,
891
+ "learning_rate": 2.9842342342342344e-05,
892
+ "loss": 0.0076,
893
+ "step": 1370
894
+ },
895
+ {
896
+ "epoch": 7.03,
897
+ "learning_rate": 2.9654654654654658e-05,
898
+ "loss": 0.0132,
899
+ "step": 1380
900
+ },
901
+ {
902
+ "epoch": 7.03,
903
+ "learning_rate": 2.946696696696697e-05,
904
+ "loss": 0.1189,
905
+ "step": 1390
906
+ },
907
+ {
908
+ "epoch": 7.03,
909
+ "learning_rate": 2.927927927927928e-05,
910
+ "loss": 0.0322,
911
+ "step": 1400
912
+ },
913
+ {
914
+ "epoch": 7.04,
915
+ "learning_rate": 2.9091591591591595e-05,
916
+ "loss": 0.0019,
917
+ "step": 1410
918
+ },
919
+ {
920
+ "epoch": 7.04,
921
+ "learning_rate": 2.8903903903903906e-05,
922
+ "loss": 0.0816,
923
+ "step": 1420
924
+ },
925
+ {
926
+ "epoch": 7.04,
927
+ "learning_rate": 2.8716216216216217e-05,
928
+ "loss": 0.1199,
929
+ "step": 1430
930
+ },
931
+ {
932
+ "epoch": 7.05,
933
+ "learning_rate": 2.852852852852853e-05,
934
+ "loss": 0.1295,
935
+ "step": 1440
936
+ },
937
+ {
938
+ "epoch": 7.05,
939
+ "learning_rate": 2.8340840840840843e-05,
940
+ "loss": 0.0567,
941
+ "step": 1450
942
+ },
943
+ {
944
+ "epoch": 7.05,
945
+ "learning_rate": 2.8153153153153157e-05,
946
+ "loss": 0.0828,
947
+ "step": 1460
948
+ },
949
+ {
950
+ "epoch": 7.06,
951
+ "learning_rate": 2.7965465465465468e-05,
952
+ "loss": 0.0826,
953
+ "step": 1470
954
+ },
955
+ {
956
+ "epoch": 7.06,
957
+ "learning_rate": 2.777777777777778e-05,
958
+ "loss": 0.059,
959
+ "step": 1480
960
+ },
961
+ {
962
+ "epoch": 7.06,
963
+ "eval_accuracy": 0.7872340425531915,
964
+ "eval_loss": 1.1619175672531128,
965
+ "eval_runtime": 117.2087,
966
+ "eval_samples_per_second": 1.604,
967
+ "eval_steps_per_second": 0.205,
968
+ "step": 1488
969
+ },
970
+ {
971
+ "epoch": 8.0,
972
+ "learning_rate": 2.7590090090090094e-05,
973
+ "loss": 0.0026,
974
+ "step": 1490
975
+ },
976
+ {
977
+ "epoch": 8.0,
978
+ "learning_rate": 2.7402402402402405e-05,
979
+ "loss": 0.1052,
980
+ "step": 1500
981
+ },
982
+ {
983
+ "epoch": 8.01,
984
+ "learning_rate": 2.721471471471472e-05,
985
+ "loss": 0.0362,
986
+ "step": 1510
987
+ },
988
+ {
989
+ "epoch": 8.01,
990
+ "learning_rate": 2.702702702702703e-05,
991
+ "loss": 0.0663,
992
+ "step": 1520
993
+ },
994
+ {
995
+ "epoch": 8.01,
996
+ "learning_rate": 2.683933933933934e-05,
997
+ "loss": 0.0092,
998
+ "step": 1530
999
+ },
1000
+ {
1001
+ "epoch": 8.02,
1002
+ "learning_rate": 2.6651651651651656e-05,
1003
+ "loss": 0.0325,
1004
+ "step": 1540
1005
+ },
1006
+ {
1007
+ "epoch": 8.02,
1008
+ "learning_rate": 2.6463963963963967e-05,
1009
+ "loss": 0.0014,
1010
+ "step": 1550
1011
+ },
1012
+ {
1013
+ "epoch": 8.02,
1014
+ "learning_rate": 2.6276276276276278e-05,
1015
+ "loss": 0.2578,
1016
+ "step": 1560
1017
+ },
1018
+ {
1019
+ "epoch": 8.03,
1020
+ "learning_rate": 2.6088588588588592e-05,
1021
+ "loss": 0.0899,
1022
+ "step": 1570
1023
+ },
1024
+ {
1025
+ "epoch": 8.03,
1026
+ "learning_rate": 2.5900900900900903e-05,
1027
+ "loss": 0.154,
1028
+ "step": 1580
1029
+ },
1030
+ {
1031
+ "epoch": 8.03,
1032
+ "learning_rate": 2.5713213213213218e-05,
1033
+ "loss": 0.0036,
1034
+ "step": 1590
1035
+ },
1036
+ {
1037
+ "epoch": 8.04,
1038
+ "learning_rate": 2.552552552552553e-05,
1039
+ "loss": 0.0216,
1040
+ "step": 1600
1041
+ },
1042
+ {
1043
+ "epoch": 8.04,
1044
+ "learning_rate": 2.533783783783784e-05,
1045
+ "loss": 0.0871,
1046
+ "step": 1610
1047
+ },
1048
+ {
1049
+ "epoch": 8.04,
1050
+ "learning_rate": 2.5150150150150154e-05,
1051
+ "loss": 0.0168,
1052
+ "step": 1620
1053
+ },
1054
+ {
1055
+ "epoch": 8.05,
1056
+ "learning_rate": 2.4962462462462462e-05,
1057
+ "loss": 0.0016,
1058
+ "step": 1630
1059
+ },
1060
+ {
1061
+ "epoch": 8.05,
1062
+ "learning_rate": 2.4774774774774777e-05,
1063
+ "loss": 0.0011,
1064
+ "step": 1640
1065
+ },
1066
+ {
1067
+ "epoch": 8.05,
1068
+ "learning_rate": 2.4587087087087088e-05,
1069
+ "loss": 0.0011,
1070
+ "step": 1650
1071
+ },
1072
+ {
1073
+ "epoch": 8.06,
1074
+ "learning_rate": 2.43993993993994e-05,
1075
+ "loss": 0.0504,
1076
+ "step": 1660
1077
+ },
1078
+ {
1079
+ "epoch": 8.06,
1080
+ "learning_rate": 2.4211711711711713e-05,
1081
+ "loss": 0.0032,
1082
+ "step": 1670
1083
+ },
1084
+ {
1085
+ "epoch": 8.06,
1086
+ "eval_accuracy": 0.8031914893617021,
1087
+ "eval_loss": 1.1739730834960938,
1088
+ "eval_runtime": 123.2699,
1089
+ "eval_samples_per_second": 1.525,
1090
+ "eval_steps_per_second": 0.195,
1091
+ "step": 1674
1092
+ },
1093
+ {
1094
+ "epoch": 9.0,
1095
+ "learning_rate": 2.4024024024024024e-05,
1096
+ "loss": 0.001,
1097
+ "step": 1680
1098
+ },
1099
+ {
1100
+ "epoch": 9.01,
1101
+ "learning_rate": 2.383633633633634e-05,
1102
+ "loss": 0.0105,
1103
+ "step": 1690
1104
+ },
1105
+ {
1106
+ "epoch": 9.01,
1107
+ "learning_rate": 2.364864864864865e-05,
1108
+ "loss": 0.1208,
1109
+ "step": 1700
1110
+ },
1111
+ {
1112
+ "epoch": 9.01,
1113
+ "eval_accuracy": 0.796875,
1114
+ "eval_loss": 1.0793333053588867,
1115
+ "eval_runtime": 292.2482,
1116
+ "eval_samples_per_second": 0.657,
1117
+ "eval_steps_per_second": 0.082,
1118
+ "step": 1704
1119
+ },
1120
+ {
1121
+ "epoch": 9.01,
1122
+ "eval_accuracy": 0.796875,
1123
+ "eval_loss": 1.0793333053588867,
1124
+ "eval_runtime": 131.1948,
1125
+ "eval_samples_per_second": 1.463,
1126
+ "eval_steps_per_second": 0.183,
1127
+ "step": 1704
1128
+ }
1129
+ ],
1130
+ "max_steps": 2960,
1131
+ "num_train_epochs": 9223372036854775807,
1132
+ "total_flos": 1.6868427640627692e+19,
1133
+ "trial_name": null,
1134
+ "trial_params": null
1135
+ }