linkanjarad commited on
Commit
6d33e17
1 Parent(s): 214dc8b

End of training

Browse files
all_results.json ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 5.0,
3
+ "eval_accuracy": 0.7145092460881934,
4
+ "eval_loss": 1.3798919916152954,
5
+ "eval_runtime": 32.4641,
6
+ "eval_samples_per_second": 216.547,
7
+ "eval_steps_per_second": 0.862,
8
+ "total_flos": 8.4800692666368e+17,
9
+ "train_loss": 1.9910735707129201,
10
+ "train_runtime": 2091.2925,
11
+ "train_samples_per_second": 151.258,
12
+ "train_steps_per_second": 0.593
13
+ }
eval_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 5.0,
3
+ "eval_accuracy": 0.7145092460881934,
4
+ "eval_loss": 1.3798919916152954,
5
+ "eval_runtime": 32.4641,
6
+ "eval_samples_per_second": 216.547,
7
+ "eval_steps_per_second": 0.862
8
+ }
runs/Apr04_05-11-30_1aca0a99cc36/events.out.tfevents.1680587821.1aca0a99cc36.23.12 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6b73be08101635666ce446a934b6db39be6f9f6c7ecea31e9a33e466c2a22fec
3
+ size 363
train_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 5.0,
3
+ "total_flos": 8.4800692666368e+17,
4
+ "train_loss": 1.9910735707129201,
5
+ "train_runtime": 2091.2925,
6
+ "train_samples_per_second": 151.258,
7
+ "train_steps_per_second": 0.593
8
+ }
trainer_state.json ADDED
@@ -0,0 +1,814 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.7145092460881934,
3
+ "best_model_checkpoint": "mobilenet_v2_1.0_224-plant-disease-identification/checkpoint-1240",
4
+ "epoch": 5.0,
5
+ "global_step": 1240,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 0.04,
12
+ "learning_rate": 2.419354838709677e-05,
13
+ "loss": 3.9201,
14
+ "step": 10
15
+ },
16
+ {
17
+ "epoch": 0.08,
18
+ "learning_rate": 4.838709677419354e-05,
19
+ "loss": 3.9242,
20
+ "step": 20
21
+ },
22
+ {
23
+ "epoch": 0.12,
24
+ "learning_rate": 7.258064516129032e-05,
25
+ "loss": 3.8715,
26
+ "step": 30
27
+ },
28
+ {
29
+ "epoch": 0.16,
30
+ "learning_rate": 9.677419354838708e-05,
31
+ "loss": 3.826,
32
+ "step": 40
33
+ },
34
+ {
35
+ "epoch": 0.2,
36
+ "learning_rate": 0.00012096774193548386,
37
+ "loss": 3.8171,
38
+ "step": 50
39
+ },
40
+ {
41
+ "epoch": 0.24,
42
+ "learning_rate": 0.00014516129032258063,
43
+ "loss": 3.7068,
44
+ "step": 60
45
+ },
46
+ {
47
+ "epoch": 0.28,
48
+ "learning_rate": 0.00016935483870967742,
49
+ "loss": 3.6646,
50
+ "step": 70
51
+ },
52
+ {
53
+ "epoch": 0.32,
54
+ "learning_rate": 0.00019354838709677416,
55
+ "loss": 3.5948,
56
+ "step": 80
57
+ },
58
+ {
59
+ "epoch": 0.36,
60
+ "learning_rate": 0.00021774193548387095,
61
+ "loss": 3.5158,
62
+ "step": 90
63
+ },
64
+ {
65
+ "epoch": 0.4,
66
+ "learning_rate": 0.00024193548387096771,
67
+ "loss": 3.4091,
68
+ "step": 100
69
+ },
70
+ {
71
+ "epoch": 0.44,
72
+ "learning_rate": 0.0002661290322580645,
73
+ "loss": 3.3351,
74
+ "step": 110
75
+ },
76
+ {
77
+ "epoch": 0.48,
78
+ "learning_rate": 0.00029032258064516127,
79
+ "loss": 3.2331,
80
+ "step": 120
81
+ },
82
+ {
83
+ "epoch": 0.52,
84
+ "learning_rate": 0.00029838709677419353,
85
+ "loss": 3.1194,
86
+ "step": 130
87
+ },
88
+ {
89
+ "epoch": 0.56,
90
+ "learning_rate": 0.00029569892473118274,
91
+ "loss": 3.0321,
92
+ "step": 140
93
+ },
94
+ {
95
+ "epoch": 0.6,
96
+ "learning_rate": 0.000293010752688172,
97
+ "loss": 2.941,
98
+ "step": 150
99
+ },
100
+ {
101
+ "epoch": 0.65,
102
+ "learning_rate": 0.00029032258064516127,
103
+ "loss": 2.8464,
104
+ "step": 160
105
+ },
106
+ {
107
+ "epoch": 0.69,
108
+ "learning_rate": 0.00028763440860215053,
109
+ "loss": 2.7874,
110
+ "step": 170
111
+ },
112
+ {
113
+ "epoch": 0.73,
114
+ "learning_rate": 0.00028494623655913974,
115
+ "loss": 2.7077,
116
+ "step": 180
117
+ },
118
+ {
119
+ "epoch": 0.77,
120
+ "learning_rate": 0.000282258064516129,
121
+ "loss": 2.6118,
122
+ "step": 190
123
+ },
124
+ {
125
+ "epoch": 0.81,
126
+ "learning_rate": 0.00027956989247311827,
127
+ "loss": 2.5675,
128
+ "step": 200
129
+ },
130
+ {
131
+ "epoch": 0.85,
132
+ "learning_rate": 0.0002768817204301075,
133
+ "loss": 2.5306,
134
+ "step": 210
135
+ },
136
+ {
137
+ "epoch": 0.89,
138
+ "learning_rate": 0.00027419354838709674,
139
+ "loss": 2.462,
140
+ "step": 220
141
+ },
142
+ {
143
+ "epoch": 0.93,
144
+ "learning_rate": 0.000271505376344086,
145
+ "loss": 2.4002,
146
+ "step": 230
147
+ },
148
+ {
149
+ "epoch": 0.97,
150
+ "learning_rate": 0.00026881720430107527,
151
+ "loss": 2.3889,
152
+ "step": 240
153
+ },
154
+ {
155
+ "epoch": 1.0,
156
+ "eval_accuracy": 0.6310099573257468,
157
+ "eval_loss": 2.1952064037323,
158
+ "eval_runtime": 32.494,
159
+ "eval_samples_per_second": 216.348,
160
+ "eval_steps_per_second": 0.862,
161
+ "step": 248
162
+ },
163
+ {
164
+ "epoch": 1.01,
165
+ "learning_rate": 0.0002661290322580645,
166
+ "loss": 2.3746,
167
+ "step": 250
168
+ },
169
+ {
170
+ "epoch": 1.05,
171
+ "learning_rate": 0.00026344086021505374,
172
+ "loss": 2.3061,
173
+ "step": 260
174
+ },
175
+ {
176
+ "epoch": 1.09,
177
+ "learning_rate": 0.000260752688172043,
178
+ "loss": 2.2709,
179
+ "step": 270
180
+ },
181
+ {
182
+ "epoch": 1.13,
183
+ "learning_rate": 0.0002580645161290322,
184
+ "loss": 2.1836,
185
+ "step": 280
186
+ },
187
+ {
188
+ "epoch": 1.17,
189
+ "learning_rate": 0.0002553763440860215,
190
+ "loss": 2.1468,
191
+ "step": 290
192
+ },
193
+ {
194
+ "epoch": 1.21,
195
+ "learning_rate": 0.00025268817204301074,
196
+ "loss": 2.1378,
197
+ "step": 300
198
+ },
199
+ {
200
+ "epoch": 1.25,
201
+ "learning_rate": 0.00025,
202
+ "loss": 2.1195,
203
+ "step": 310
204
+ },
205
+ {
206
+ "epoch": 1.29,
207
+ "learning_rate": 0.0002473118279569892,
208
+ "loss": 2.0858,
209
+ "step": 320
210
+ },
211
+ {
212
+ "epoch": 1.33,
213
+ "learning_rate": 0.0002446236559139785,
214
+ "loss": 2.054,
215
+ "step": 330
216
+ },
217
+ {
218
+ "epoch": 1.37,
219
+ "learning_rate": 0.00024193548387096771,
220
+ "loss": 2.0506,
221
+ "step": 340
222
+ },
223
+ {
224
+ "epoch": 1.41,
225
+ "learning_rate": 0.00023924731182795698,
226
+ "loss": 2.0189,
227
+ "step": 350
228
+ },
229
+ {
230
+ "epoch": 1.45,
231
+ "learning_rate": 0.00023655913978494621,
232
+ "loss": 1.988,
233
+ "step": 360
234
+ },
235
+ {
236
+ "epoch": 1.49,
237
+ "learning_rate": 0.00023387096774193545,
238
+ "loss": 1.959,
239
+ "step": 370
240
+ },
241
+ {
242
+ "epoch": 1.53,
243
+ "learning_rate": 0.0002311827956989247,
244
+ "loss": 1.9234,
245
+ "step": 380
246
+ },
247
+ {
248
+ "epoch": 1.57,
249
+ "learning_rate": 0.00022849462365591398,
250
+ "loss": 1.9085,
251
+ "step": 390
252
+ },
253
+ {
254
+ "epoch": 1.61,
255
+ "learning_rate": 0.00022580645161290321,
256
+ "loss": 1.8899,
257
+ "step": 400
258
+ },
259
+ {
260
+ "epoch": 1.65,
261
+ "learning_rate": 0.00022311827956989245,
262
+ "loss": 1.8872,
263
+ "step": 410
264
+ },
265
+ {
266
+ "epoch": 1.69,
267
+ "learning_rate": 0.00022043010752688171,
268
+ "loss": 1.8375,
269
+ "step": 420
270
+ },
271
+ {
272
+ "epoch": 1.73,
273
+ "learning_rate": 0.00021774193548387095,
274
+ "loss": 1.8898,
275
+ "step": 430
276
+ },
277
+ {
278
+ "epoch": 1.77,
279
+ "learning_rate": 0.0002150537634408602,
280
+ "loss": 1.8581,
281
+ "step": 440
282
+ },
283
+ {
284
+ "epoch": 1.81,
285
+ "learning_rate": 0.00021236559139784942,
286
+ "loss": 1.8599,
287
+ "step": 450
288
+ },
289
+ {
290
+ "epoch": 1.85,
291
+ "learning_rate": 0.00020967741935483871,
292
+ "loss": 1.802,
293
+ "step": 460
294
+ },
295
+ {
296
+ "epoch": 1.9,
297
+ "learning_rate": 0.00020698924731182795,
298
+ "loss": 1.8318,
299
+ "step": 470
300
+ },
301
+ {
302
+ "epoch": 1.94,
303
+ "learning_rate": 0.0002043010752688172,
304
+ "loss": 1.7989,
305
+ "step": 480
306
+ },
307
+ {
308
+ "epoch": 1.98,
309
+ "learning_rate": 0.00020161290322580642,
310
+ "loss": 1.8202,
311
+ "step": 490
312
+ },
313
+ {
314
+ "epoch": 2.0,
315
+ "eval_accuracy": 0.701280227596017,
316
+ "eval_loss": 1.6362959146499634,
317
+ "eval_runtime": 33.4879,
318
+ "eval_samples_per_second": 209.927,
319
+ "eval_steps_per_second": 0.836,
320
+ "step": 496
321
+ },
322
+ {
323
+ "epoch": 2.02,
324
+ "learning_rate": 0.0001989247311827957,
325
+ "loss": 1.8297,
326
+ "step": 500
327
+ },
328
+ {
329
+ "epoch": 2.06,
330
+ "learning_rate": 0.00019623655913978492,
331
+ "loss": 1.7744,
332
+ "step": 510
333
+ },
334
+ {
335
+ "epoch": 2.1,
336
+ "learning_rate": 0.00019354838709677416,
337
+ "loss": 1.7534,
338
+ "step": 520
339
+ },
340
+ {
341
+ "epoch": 2.14,
342
+ "learning_rate": 0.0001908602150537634,
343
+ "loss": 1.7636,
344
+ "step": 530
345
+ },
346
+ {
347
+ "epoch": 2.18,
348
+ "learning_rate": 0.0001881720430107527,
349
+ "loss": 1.7439,
350
+ "step": 540
351
+ },
352
+ {
353
+ "epoch": 2.22,
354
+ "learning_rate": 0.00018548387096774192,
355
+ "loss": 1.7016,
356
+ "step": 550
357
+ },
358
+ {
359
+ "epoch": 2.26,
360
+ "learning_rate": 0.00018279569892473116,
361
+ "loss": 1.717,
362
+ "step": 560
363
+ },
364
+ {
365
+ "epoch": 2.3,
366
+ "learning_rate": 0.0001801075268817204,
367
+ "loss": 1.7345,
368
+ "step": 570
369
+ },
370
+ {
371
+ "epoch": 2.34,
372
+ "learning_rate": 0.00017741935483870966,
373
+ "loss": 1.7058,
374
+ "step": 580
375
+ },
376
+ {
377
+ "epoch": 2.38,
378
+ "learning_rate": 0.0001747311827956989,
379
+ "loss": 1.6664,
380
+ "step": 590
381
+ },
382
+ {
383
+ "epoch": 2.42,
384
+ "learning_rate": 0.00017204301075268816,
385
+ "loss": 1.6923,
386
+ "step": 600
387
+ },
388
+ {
389
+ "epoch": 2.46,
390
+ "learning_rate": 0.00016935483870967742,
391
+ "loss": 1.6606,
392
+ "step": 610
393
+ },
394
+ {
395
+ "epoch": 2.5,
396
+ "learning_rate": 0.00016666666666666666,
397
+ "loss": 1.6848,
398
+ "step": 620
399
+ },
400
+ {
401
+ "epoch": 2.54,
402
+ "learning_rate": 0.0001639784946236559,
403
+ "loss": 1.6863,
404
+ "step": 630
405
+ },
406
+ {
407
+ "epoch": 2.58,
408
+ "learning_rate": 0.00016129032258064513,
409
+ "loss": 1.6436,
410
+ "step": 640
411
+ },
412
+ {
413
+ "epoch": 2.62,
414
+ "learning_rate": 0.0001586021505376344,
415
+ "loss": 1.6944,
416
+ "step": 650
417
+ },
418
+ {
419
+ "epoch": 2.66,
420
+ "learning_rate": 0.00015591397849462366,
421
+ "loss": 1.644,
422
+ "step": 660
423
+ },
424
+ {
425
+ "epoch": 2.7,
426
+ "learning_rate": 0.0001532258064516129,
427
+ "loss": 1.6657,
428
+ "step": 670
429
+ },
430
+ {
431
+ "epoch": 2.74,
432
+ "learning_rate": 0.00015053763440860213,
433
+ "loss": 1.6636,
434
+ "step": 680
435
+ },
436
+ {
437
+ "epoch": 2.78,
438
+ "learning_rate": 0.00014784946236559137,
439
+ "loss": 1.664,
440
+ "step": 690
441
+ },
442
+ {
443
+ "epoch": 2.82,
444
+ "learning_rate": 0.00014516129032258063,
445
+ "loss": 1.6413,
446
+ "step": 700
447
+ },
448
+ {
449
+ "epoch": 2.86,
450
+ "learning_rate": 0.00014247311827956987,
451
+ "loss": 1.6534,
452
+ "step": 710
453
+ },
454
+ {
455
+ "epoch": 2.9,
456
+ "learning_rate": 0.00013978494623655913,
457
+ "loss": 1.6356,
458
+ "step": 720
459
+ },
460
+ {
461
+ "epoch": 2.94,
462
+ "learning_rate": 0.00013709677419354837,
463
+ "loss": 1.6479,
464
+ "step": 730
465
+ },
466
+ {
467
+ "epoch": 2.98,
468
+ "learning_rate": 0.00013440860215053763,
469
+ "loss": 1.6266,
470
+ "step": 740
471
+ },
472
+ {
473
+ "epoch": 3.0,
474
+ "eval_accuracy": 0.6342816500711238,
475
+ "eval_loss": 1.6291429996490479,
476
+ "eval_runtime": 32.1288,
477
+ "eval_samples_per_second": 218.807,
478
+ "eval_steps_per_second": 0.871,
479
+ "step": 744
480
+ },
481
+ {
482
+ "epoch": 3.02,
483
+ "learning_rate": 0.00013172043010752687,
484
+ "loss": 1.6561,
485
+ "step": 750
486
+ },
487
+ {
488
+ "epoch": 3.06,
489
+ "learning_rate": 0.0001290322580645161,
490
+ "loss": 1.6028,
491
+ "step": 760
492
+ },
493
+ {
494
+ "epoch": 3.1,
495
+ "learning_rate": 0.00012634408602150537,
496
+ "loss": 1.5976,
497
+ "step": 770
498
+ },
499
+ {
500
+ "epoch": 3.15,
501
+ "learning_rate": 0.0001236559139784946,
502
+ "loss": 1.5662,
503
+ "step": 780
504
+ },
505
+ {
506
+ "epoch": 3.19,
507
+ "learning_rate": 0.00012096774193548386,
508
+ "loss": 1.5979,
509
+ "step": 790
510
+ },
511
+ {
512
+ "epoch": 3.23,
513
+ "learning_rate": 0.00011827956989247311,
514
+ "loss": 1.5985,
515
+ "step": 800
516
+ },
517
+ {
518
+ "epoch": 3.27,
519
+ "learning_rate": 0.00011559139784946234,
520
+ "loss": 1.565,
521
+ "step": 810
522
+ },
523
+ {
524
+ "epoch": 3.31,
525
+ "learning_rate": 0.00011290322580645161,
526
+ "loss": 1.5848,
527
+ "step": 820
528
+ },
529
+ {
530
+ "epoch": 3.35,
531
+ "learning_rate": 0.00011021505376344086,
532
+ "loss": 1.5779,
533
+ "step": 830
534
+ },
535
+ {
536
+ "epoch": 3.39,
537
+ "learning_rate": 0.0001075268817204301,
538
+ "loss": 1.6202,
539
+ "step": 840
540
+ },
541
+ {
542
+ "epoch": 3.43,
543
+ "learning_rate": 0.00010483870967741936,
544
+ "loss": 1.582,
545
+ "step": 850
546
+ },
547
+ {
548
+ "epoch": 3.47,
549
+ "learning_rate": 0.0001021505376344086,
550
+ "loss": 1.5881,
551
+ "step": 860
552
+ },
553
+ {
554
+ "epoch": 3.51,
555
+ "learning_rate": 9.946236559139784e-05,
556
+ "loss": 1.6339,
557
+ "step": 870
558
+ },
559
+ {
560
+ "epoch": 3.55,
561
+ "learning_rate": 9.677419354838708e-05,
562
+ "loss": 1.5905,
563
+ "step": 880
564
+ },
565
+ {
566
+ "epoch": 3.59,
567
+ "learning_rate": 9.408602150537634e-05,
568
+ "loss": 1.5989,
569
+ "step": 890
570
+ },
571
+ {
572
+ "epoch": 3.63,
573
+ "learning_rate": 9.139784946236558e-05,
574
+ "loss": 1.512,
575
+ "step": 900
576
+ },
577
+ {
578
+ "epoch": 3.67,
579
+ "learning_rate": 8.870967741935483e-05,
580
+ "loss": 1.6037,
581
+ "step": 910
582
+ },
583
+ {
584
+ "epoch": 3.71,
585
+ "learning_rate": 8.602150537634408e-05,
586
+ "loss": 1.5541,
587
+ "step": 920
588
+ },
589
+ {
590
+ "epoch": 3.75,
591
+ "learning_rate": 8.333333333333333e-05,
592
+ "loss": 1.5853,
593
+ "step": 930
594
+ },
595
+ {
596
+ "epoch": 3.79,
597
+ "learning_rate": 8.064516129032257e-05,
598
+ "loss": 1.5876,
599
+ "step": 940
600
+ },
601
+ {
602
+ "epoch": 3.83,
603
+ "learning_rate": 7.795698924731183e-05,
604
+ "loss": 1.5725,
605
+ "step": 950
606
+ },
607
+ {
608
+ "epoch": 3.87,
609
+ "learning_rate": 7.526881720430107e-05,
610
+ "loss": 1.5877,
611
+ "step": 960
612
+ },
613
+ {
614
+ "epoch": 3.91,
615
+ "learning_rate": 7.258064516129032e-05,
616
+ "loss": 1.5616,
617
+ "step": 970
618
+ },
619
+ {
620
+ "epoch": 3.95,
621
+ "learning_rate": 6.989247311827957e-05,
622
+ "loss": 1.5312,
623
+ "step": 980
624
+ },
625
+ {
626
+ "epoch": 3.99,
627
+ "learning_rate": 6.720430107526882e-05,
628
+ "loss": 1.5566,
629
+ "step": 990
630
+ },
631
+ {
632
+ "epoch": 4.0,
633
+ "eval_accuracy": 0.7129445234708393,
634
+ "eval_loss": 1.3513665199279785,
635
+ "eval_runtime": 32.1577,
636
+ "eval_samples_per_second": 218.61,
637
+ "eval_steps_per_second": 0.871,
638
+ "step": 992
639
+ },
640
+ {
641
+ "epoch": 4.03,
642
+ "learning_rate": 6.451612903225805e-05,
643
+ "loss": 1.5856,
644
+ "step": 1000
645
+ },
646
+ {
647
+ "epoch": 4.07,
648
+ "learning_rate": 6.18279569892473e-05,
649
+ "loss": 1.5224,
650
+ "step": 1010
651
+ },
652
+ {
653
+ "epoch": 4.11,
654
+ "learning_rate": 5.9139784946236554e-05,
655
+ "loss": 1.6315,
656
+ "step": 1020
657
+ },
658
+ {
659
+ "epoch": 4.15,
660
+ "learning_rate": 5.6451612903225804e-05,
661
+ "loss": 1.5596,
662
+ "step": 1030
663
+ },
664
+ {
665
+ "epoch": 4.19,
666
+ "learning_rate": 5.376344086021505e-05,
667
+ "loss": 1.5664,
668
+ "step": 1040
669
+ },
670
+ {
671
+ "epoch": 4.23,
672
+ "learning_rate": 5.10752688172043e-05,
673
+ "loss": 1.5844,
674
+ "step": 1050
675
+ },
676
+ {
677
+ "epoch": 4.27,
678
+ "learning_rate": 4.838709677419354e-05,
679
+ "loss": 1.5564,
680
+ "step": 1060
681
+ },
682
+ {
683
+ "epoch": 4.31,
684
+ "learning_rate": 4.569892473118279e-05,
685
+ "loss": 1.5299,
686
+ "step": 1070
687
+ },
688
+ {
689
+ "epoch": 4.35,
690
+ "learning_rate": 4.301075268817204e-05,
691
+ "loss": 1.5303,
692
+ "step": 1080
693
+ },
694
+ {
695
+ "epoch": 4.4,
696
+ "learning_rate": 4.0322580645161284e-05,
697
+ "loss": 1.5471,
698
+ "step": 1090
699
+ },
700
+ {
701
+ "epoch": 4.44,
702
+ "learning_rate": 3.7634408602150534e-05,
703
+ "loss": 1.5416,
704
+ "step": 1100
705
+ },
706
+ {
707
+ "epoch": 4.48,
708
+ "learning_rate": 3.4946236559139784e-05,
709
+ "loss": 1.4994,
710
+ "step": 1110
711
+ },
712
+ {
713
+ "epoch": 4.52,
714
+ "learning_rate": 3.225806451612903e-05,
715
+ "loss": 1.5726,
716
+ "step": 1120
717
+ },
718
+ {
719
+ "epoch": 4.56,
720
+ "learning_rate": 2.9569892473118277e-05,
721
+ "loss": 1.5627,
722
+ "step": 1130
723
+ },
724
+ {
725
+ "epoch": 4.6,
726
+ "learning_rate": 2.6881720430107523e-05,
727
+ "loss": 1.5658,
728
+ "step": 1140
729
+ },
730
+ {
731
+ "epoch": 4.64,
732
+ "learning_rate": 2.419354838709677e-05,
733
+ "loss": 1.5639,
734
+ "step": 1150
735
+ },
736
+ {
737
+ "epoch": 4.68,
738
+ "learning_rate": 2.150537634408602e-05,
739
+ "loss": 1.5296,
740
+ "step": 1160
741
+ },
742
+ {
743
+ "epoch": 4.72,
744
+ "learning_rate": 1.8817204301075267e-05,
745
+ "loss": 1.5235,
746
+ "step": 1170
747
+ },
748
+ {
749
+ "epoch": 4.76,
750
+ "learning_rate": 1.6129032258064513e-05,
751
+ "loss": 1.5826,
752
+ "step": 1180
753
+ },
754
+ {
755
+ "epoch": 4.8,
756
+ "learning_rate": 1.3440860215053762e-05,
757
+ "loss": 1.5631,
758
+ "step": 1190
759
+ },
760
+ {
761
+ "epoch": 4.84,
762
+ "learning_rate": 1.075268817204301e-05,
763
+ "loss": 1.4985,
764
+ "step": 1200
765
+ },
766
+ {
767
+ "epoch": 4.88,
768
+ "learning_rate": 8.064516129032257e-06,
769
+ "loss": 1.5313,
770
+ "step": 1210
771
+ },
772
+ {
773
+ "epoch": 4.92,
774
+ "learning_rate": 5.376344086021505e-06,
775
+ "loss": 1.5255,
776
+ "step": 1220
777
+ },
778
+ {
779
+ "epoch": 4.96,
780
+ "learning_rate": 2.6881720430107525e-06,
781
+ "loss": 1.5456,
782
+ "step": 1230
783
+ },
784
+ {
785
+ "epoch": 5.0,
786
+ "learning_rate": 0.0,
787
+ "loss": 1.5507,
788
+ "step": 1240
789
+ },
790
+ {
791
+ "epoch": 5.0,
792
+ "eval_accuracy": 0.7145092460881934,
793
+ "eval_loss": 1.3798919916152954,
794
+ "eval_runtime": 32.2801,
795
+ "eval_samples_per_second": 217.781,
796
+ "eval_steps_per_second": 0.867,
797
+ "step": 1240
798
+ },
799
+ {
800
+ "epoch": 5.0,
801
+ "step": 1240,
802
+ "total_flos": 8.4800692666368e+17,
803
+ "train_loss": 1.9910735707129201,
804
+ "train_runtime": 2091.2925,
805
+ "train_samples_per_second": 151.258,
806
+ "train_steps_per_second": 0.593
807
+ }
808
+ ],
809
+ "max_steps": 1240,
810
+ "num_train_epochs": 5,
811
+ "total_flos": 8.4800692666368e+17,
812
+ "trial_name": null,
813
+ "trial_params": null
814
+ }