ppicazo commited on
Commit
7423f45
·
verified ·
1 Parent(s): 9112b9e

End of training

Browse files
Files changed (5) hide show
  1. README.md +2 -0
  2. all_results.json +13 -0
  3. eval_results.json +8 -0
  4. train_results.json +8 -0
  5. trainer_state.json +605 -0
README.md CHANGED
@@ -3,6 +3,8 @@ library_name: transformers
3
  license: apache-2.0
4
  base_model: google/vit-base-patch16-224-in21k
5
  tags:
 
 
6
  - generated_from_trainer
7
  datasets:
8
  - imagefolder
 
3
  license: apache-2.0
4
  base_model: google/vit-base-patch16-224-in21k
5
  tags:
6
+ - image-classification
7
+ - vision
8
  - generated_from_trainer
9
  datasets:
10
  - imagefolder
all_results.json ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 5.0,
3
+ "eval_accuracy": 0.9952153110047847,
4
+ "eval_loss": 0.02545962668955326,
5
+ "eval_runtime": 27.2843,
6
+ "eval_samples_per_second": 7.66,
7
+ "eval_steps_per_second": 0.99,
8
+ "total_flos": 4.583651185703117e+17,
9
+ "train_loss": 0.044068760142938514,
10
+ "train_runtime": 1744.9647,
11
+ "train_samples_per_second": 3.39,
12
+ "train_steps_per_second": 0.424
13
+ }
eval_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 5.0,
3
+ "eval_accuracy": 0.9952153110047847,
4
+ "eval_loss": 0.02545962668955326,
5
+ "eval_runtime": 27.2843,
6
+ "eval_samples_per_second": 7.66,
7
+ "eval_steps_per_second": 0.99
8
+ }
train_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 5.0,
3
+ "total_flos": 4.583651185703117e+17,
4
+ "train_loss": 0.044068760142938514,
5
+ "train_runtime": 1744.9647,
6
+ "train_samples_per_second": 3.39,
7
+ "train_steps_per_second": 0.424
8
+ }
trainer_state.json ADDED
@@ -0,0 +1,605 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.02545962668955326,
3
+ "best_model_checkpoint": "./outputsstar/checkpoint-740",
4
+ "epoch": 5.0,
5
+ "eval_steps": 500,
6
+ "global_step": 740,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.06756756756756757,
13
+ "grad_norm": 1.9284253120422363,
14
+ "learning_rate": 1.972972972972973e-05,
15
+ "loss": 0.5718,
16
+ "step": 10
17
+ },
18
+ {
19
+ "epoch": 0.13513513513513514,
20
+ "grad_norm": 1.4602636098861694,
21
+ "learning_rate": 1.9459459459459463e-05,
22
+ "loss": 0.3133,
23
+ "step": 20
24
+ },
25
+ {
26
+ "epoch": 0.20270270270270271,
27
+ "grad_norm": 1.0061994791030884,
28
+ "learning_rate": 1.918918918918919e-05,
29
+ "loss": 0.1601,
30
+ "step": 30
31
+ },
32
+ {
33
+ "epoch": 0.2702702702702703,
34
+ "grad_norm": 0.45298728346824646,
35
+ "learning_rate": 1.891891891891892e-05,
36
+ "loss": 0.1146,
37
+ "step": 40
38
+ },
39
+ {
40
+ "epoch": 0.33783783783783783,
41
+ "grad_norm": 0.5685911178588867,
42
+ "learning_rate": 1.864864864864865e-05,
43
+ "loss": 0.0863,
44
+ "step": 50
45
+ },
46
+ {
47
+ "epoch": 0.40540540540540543,
48
+ "grad_norm": 0.4350438714027405,
49
+ "learning_rate": 1.8378378378378383e-05,
50
+ "loss": 0.0465,
51
+ "step": 60
52
+ },
53
+ {
54
+ "epoch": 0.47297297297297297,
55
+ "grad_norm": 0.20809537172317505,
56
+ "learning_rate": 1.8108108108108108e-05,
57
+ "loss": 0.0345,
58
+ "step": 70
59
+ },
60
+ {
61
+ "epoch": 0.5405405405405406,
62
+ "grad_norm": 0.1794459968805313,
63
+ "learning_rate": 1.783783783783784e-05,
64
+ "loss": 0.0447,
65
+ "step": 80
66
+ },
67
+ {
68
+ "epoch": 0.6081081081081081,
69
+ "grad_norm": 0.17304065823554993,
70
+ "learning_rate": 1.756756756756757e-05,
71
+ "loss": 0.0638,
72
+ "step": 90
73
+ },
74
+ {
75
+ "epoch": 0.6756756756756757,
76
+ "grad_norm": 0.16675682365894318,
77
+ "learning_rate": 1.72972972972973e-05,
78
+ "loss": 0.058,
79
+ "step": 100
80
+ },
81
+ {
82
+ "epoch": 0.7432432432432432,
83
+ "grad_norm": 0.158709317445755,
84
+ "learning_rate": 1.7027027027027028e-05,
85
+ "loss": 0.0691,
86
+ "step": 110
87
+ },
88
+ {
89
+ "epoch": 0.8108108108108109,
90
+ "grad_norm": 0.17359796166419983,
91
+ "learning_rate": 1.6756756756756757e-05,
92
+ "loss": 0.075,
93
+ "step": 120
94
+ },
95
+ {
96
+ "epoch": 0.8783783783783784,
97
+ "grad_norm": 3.065023422241211,
98
+ "learning_rate": 1.648648648648649e-05,
99
+ "loss": 0.0731,
100
+ "step": 130
101
+ },
102
+ {
103
+ "epoch": 0.9459459459459459,
104
+ "grad_norm": 0.18713080883026123,
105
+ "learning_rate": 1.6216216216216218e-05,
106
+ "loss": 0.0436,
107
+ "step": 140
108
+ },
109
+ {
110
+ "epoch": 1.0,
111
+ "eval_accuracy": 0.9808612440191388,
112
+ "eval_loss": 0.05818231776356697,
113
+ "eval_runtime": 27.0314,
114
+ "eval_samples_per_second": 7.732,
115
+ "eval_steps_per_second": 0.999,
116
+ "step": 148
117
+ },
118
+ {
119
+ "epoch": 1.0135135135135136,
120
+ "grad_norm": 1.1932803392410278,
121
+ "learning_rate": 1.5945945945945947e-05,
122
+ "loss": 0.0697,
123
+ "step": 150
124
+ },
125
+ {
126
+ "epoch": 1.0810810810810811,
127
+ "grad_norm": 0.15206500887870789,
128
+ "learning_rate": 1.5675675675675676e-05,
129
+ "loss": 0.0186,
130
+ "step": 160
131
+ },
132
+ {
133
+ "epoch": 1.1486486486486487,
134
+ "grad_norm": 5.430366039276123,
135
+ "learning_rate": 1.540540540540541e-05,
136
+ "loss": 0.0391,
137
+ "step": 170
138
+ },
139
+ {
140
+ "epoch": 1.2162162162162162,
141
+ "grad_norm": 0.12790042161941528,
142
+ "learning_rate": 1.5135135135135138e-05,
143
+ "loss": 0.0149,
144
+ "step": 180
145
+ },
146
+ {
147
+ "epoch": 1.2837837837837838,
148
+ "grad_norm": 0.09696532785892487,
149
+ "learning_rate": 1.4864864864864865e-05,
150
+ "loss": 0.0134,
151
+ "step": 190
152
+ },
153
+ {
154
+ "epoch": 1.3513513513513513,
155
+ "grad_norm": 0.10962755233049393,
156
+ "learning_rate": 1.4594594594594596e-05,
157
+ "loss": 0.0775,
158
+ "step": 200
159
+ },
160
+ {
161
+ "epoch": 1.4189189189189189,
162
+ "grad_norm": 0.10070909559726715,
163
+ "learning_rate": 1.4324324324324326e-05,
164
+ "loss": 0.0524,
165
+ "step": 210
166
+ },
167
+ {
168
+ "epoch": 1.4864864864864864,
169
+ "grad_norm": 0.09208140522241592,
170
+ "learning_rate": 1.4054054054054055e-05,
171
+ "loss": 0.0243,
172
+ "step": 220
173
+ },
174
+ {
175
+ "epoch": 1.554054054054054,
176
+ "grad_norm": 5.711668968200684,
177
+ "learning_rate": 1.3783783783783784e-05,
178
+ "loss": 0.0358,
179
+ "step": 230
180
+ },
181
+ {
182
+ "epoch": 1.6216216216216215,
183
+ "grad_norm": 0.09372463822364807,
184
+ "learning_rate": 1.3513513513513515e-05,
185
+ "loss": 0.0125,
186
+ "step": 240
187
+ },
188
+ {
189
+ "epoch": 1.689189189189189,
190
+ "grad_norm": 0.08806200325489044,
191
+ "learning_rate": 1.3243243243243244e-05,
192
+ "loss": 0.0532,
193
+ "step": 250
194
+ },
195
+ {
196
+ "epoch": 1.7567567567567568,
197
+ "grad_norm": 25.615135192871094,
198
+ "learning_rate": 1.2972972972972975e-05,
199
+ "loss": 0.0761,
200
+ "step": 260
201
+ },
202
+ {
203
+ "epoch": 1.8243243243243243,
204
+ "grad_norm": 0.10457191616296768,
205
+ "learning_rate": 1.2702702702702702e-05,
206
+ "loss": 0.0417,
207
+ "step": 270
208
+ },
209
+ {
210
+ "epoch": 1.8918918918918919,
211
+ "grad_norm": 0.09721718728542328,
212
+ "learning_rate": 1.2432432432432433e-05,
213
+ "loss": 0.0144,
214
+ "step": 280
215
+ },
216
+ {
217
+ "epoch": 1.9594594594594594,
218
+ "grad_norm": 0.0960867628455162,
219
+ "learning_rate": 1.2162162162162164e-05,
220
+ "loss": 0.0121,
221
+ "step": 290
222
+ },
223
+ {
224
+ "epoch": 2.0,
225
+ "eval_accuracy": 0.9904306220095693,
226
+ "eval_loss": 0.04049909487366676,
227
+ "eval_runtime": 27.4721,
228
+ "eval_samples_per_second": 7.608,
229
+ "eval_steps_per_second": 0.983,
230
+ "step": 296
231
+ },
232
+ {
233
+ "epoch": 2.027027027027027,
234
+ "grad_norm": 0.08215823024511337,
235
+ "learning_rate": 1.1891891891891894e-05,
236
+ "loss": 0.0587,
237
+ "step": 300
238
+ },
239
+ {
240
+ "epoch": 2.0945945945945947,
241
+ "grad_norm": 0.08944419026374817,
242
+ "learning_rate": 1.1621621621621622e-05,
243
+ "loss": 0.0616,
244
+ "step": 310
245
+ },
246
+ {
247
+ "epoch": 2.1621621621621623,
248
+ "grad_norm": 0.07855982333421707,
249
+ "learning_rate": 1.1351351351351352e-05,
250
+ "loss": 0.0139,
251
+ "step": 320
252
+ },
253
+ {
254
+ "epoch": 2.22972972972973,
255
+ "grad_norm": 0.07730930298566818,
256
+ "learning_rate": 1.1081081081081081e-05,
257
+ "loss": 0.0461,
258
+ "step": 330
259
+ },
260
+ {
261
+ "epoch": 2.2972972972972974,
262
+ "grad_norm": 0.0793551355600357,
263
+ "learning_rate": 1.0810810810810812e-05,
264
+ "loss": 0.0101,
265
+ "step": 340
266
+ },
267
+ {
268
+ "epoch": 2.364864864864865,
269
+ "grad_norm": 0.07596410065889359,
270
+ "learning_rate": 1.0540540540540541e-05,
271
+ "loss": 0.01,
272
+ "step": 350
273
+ },
274
+ {
275
+ "epoch": 2.4324324324324325,
276
+ "grad_norm": 0.08209327608346939,
277
+ "learning_rate": 1.027027027027027e-05,
278
+ "loss": 0.0147,
279
+ "step": 360
280
+ },
281
+ {
282
+ "epoch": 2.5,
283
+ "grad_norm": 0.07307254523038864,
284
+ "learning_rate": 1e-05,
285
+ "loss": 0.01,
286
+ "step": 370
287
+ },
288
+ {
289
+ "epoch": 2.5675675675675675,
290
+ "grad_norm": 0.07255389541387558,
291
+ "learning_rate": 9.729729729729732e-06,
292
+ "loss": 0.0418,
293
+ "step": 380
294
+ },
295
+ {
296
+ "epoch": 2.635135135135135,
297
+ "grad_norm": 0.08818744868040085,
298
+ "learning_rate": 9.45945945945946e-06,
299
+ "loss": 0.0703,
300
+ "step": 390
301
+ },
302
+ {
303
+ "epoch": 2.7027027027027026,
304
+ "grad_norm": 0.0737389624118805,
305
+ "learning_rate": 9.189189189189191e-06,
306
+ "loss": 0.0279,
307
+ "step": 400
308
+ },
309
+ {
310
+ "epoch": 2.77027027027027,
311
+ "grad_norm": 0.06960991024971008,
312
+ "learning_rate": 8.91891891891892e-06,
313
+ "loss": 0.009,
314
+ "step": 410
315
+ },
316
+ {
317
+ "epoch": 2.8378378378378377,
318
+ "grad_norm": 0.06750474125146866,
319
+ "learning_rate": 8.64864864864865e-06,
320
+ "loss": 0.009,
321
+ "step": 420
322
+ },
323
+ {
324
+ "epoch": 2.9054054054054053,
325
+ "grad_norm": 0.07102343440055847,
326
+ "learning_rate": 8.378378378378378e-06,
327
+ "loss": 0.0081,
328
+ "step": 430
329
+ },
330
+ {
331
+ "epoch": 2.972972972972973,
332
+ "grad_norm": 0.06397751718759537,
333
+ "learning_rate": 8.108108108108109e-06,
334
+ "loss": 0.0112,
335
+ "step": 440
336
+ },
337
+ {
338
+ "epoch": 3.0,
339
+ "eval_accuracy": 0.9856459330143541,
340
+ "eval_loss": 0.038280732929706573,
341
+ "eval_runtime": 27.6482,
342
+ "eval_samples_per_second": 7.559,
343
+ "eval_steps_per_second": 0.977,
344
+ "step": 444
345
+ },
346
+ {
347
+ "epoch": 3.0405405405405403,
348
+ "grad_norm": 0.07215096056461334,
349
+ "learning_rate": 7.837837837837838e-06,
350
+ "loss": 0.0153,
351
+ "step": 450
352
+ },
353
+ {
354
+ "epoch": 3.108108108108108,
355
+ "grad_norm": 0.06951985508203506,
356
+ "learning_rate": 7.567567567567569e-06,
357
+ "loss": 0.0085,
358
+ "step": 460
359
+ },
360
+ {
361
+ "epoch": 3.175675675675676,
362
+ "grad_norm": 0.060418710112571716,
363
+ "learning_rate": 7.297297297297298e-06,
364
+ "loss": 0.0095,
365
+ "step": 470
366
+ },
367
+ {
368
+ "epoch": 3.2432432432432434,
369
+ "grad_norm": 2.964932441711426,
370
+ "learning_rate": 7.027027027027028e-06,
371
+ "loss": 0.0109,
372
+ "step": 480
373
+ },
374
+ {
375
+ "epoch": 3.310810810810811,
376
+ "grad_norm": 0.06342046707868576,
377
+ "learning_rate": 6.7567567567567575e-06,
378
+ "loss": 0.0088,
379
+ "step": 490
380
+ },
381
+ {
382
+ "epoch": 3.3783783783783785,
383
+ "grad_norm": 0.06240825727581978,
384
+ "learning_rate": 6.486486486486487e-06,
385
+ "loss": 0.008,
386
+ "step": 500
387
+ },
388
+ {
389
+ "epoch": 3.445945945945946,
390
+ "grad_norm": 0.06396786123514175,
391
+ "learning_rate": 6.2162162162162164e-06,
392
+ "loss": 0.0453,
393
+ "step": 510
394
+ },
395
+ {
396
+ "epoch": 3.5135135135135136,
397
+ "grad_norm": 0.06505484133958817,
398
+ "learning_rate": 5.945945945945947e-06,
399
+ "loss": 0.0075,
400
+ "step": 520
401
+ },
402
+ {
403
+ "epoch": 3.581081081081081,
404
+ "grad_norm": 0.057356029748916626,
405
+ "learning_rate": 5.675675675675676e-06,
406
+ "loss": 0.0239,
407
+ "step": 530
408
+ },
409
+ {
410
+ "epoch": 3.6486486486486487,
411
+ "grad_norm": 0.0630515068769455,
412
+ "learning_rate": 5.405405405405406e-06,
413
+ "loss": 0.0169,
414
+ "step": 540
415
+ },
416
+ {
417
+ "epoch": 3.7162162162162162,
418
+ "grad_norm": 0.06203653663396835,
419
+ "learning_rate": 5.135135135135135e-06,
420
+ "loss": 0.0162,
421
+ "step": 550
422
+ },
423
+ {
424
+ "epoch": 3.7837837837837838,
425
+ "grad_norm": 0.06313777714967728,
426
+ "learning_rate": 4.864864864864866e-06,
427
+ "loss": 0.0072,
428
+ "step": 560
429
+ },
430
+ {
431
+ "epoch": 3.8513513513513513,
432
+ "grad_norm": 0.06151194870471954,
433
+ "learning_rate": 4.594594594594596e-06,
434
+ "loss": 0.0108,
435
+ "step": 570
436
+ },
437
+ {
438
+ "epoch": 3.918918918918919,
439
+ "grad_norm": 0.06091887503862381,
440
+ "learning_rate": 4.324324324324325e-06,
441
+ "loss": 0.1161,
442
+ "step": 580
443
+ },
444
+ {
445
+ "epoch": 3.9864864864864864,
446
+ "grad_norm": 0.14475536346435547,
447
+ "learning_rate": 4.0540540540540545e-06,
448
+ "loss": 0.01,
449
+ "step": 590
450
+ },
451
+ {
452
+ "epoch": 4.0,
453
+ "eval_accuracy": 0.9952153110047847,
454
+ "eval_loss": 0.0269942469894886,
455
+ "eval_runtime": 27.6031,
456
+ "eval_samples_per_second": 7.572,
457
+ "eval_steps_per_second": 0.978,
458
+ "step": 592
459
+ },
460
+ {
461
+ "epoch": 4.054054054054054,
462
+ "grad_norm": 0.056809261441230774,
463
+ "learning_rate": 3.7837837837837844e-06,
464
+ "loss": 0.0187,
465
+ "step": 600
466
+ },
467
+ {
468
+ "epoch": 4.121621621621622,
469
+ "grad_norm": 0.056312572211027145,
470
+ "learning_rate": 3.513513513513514e-06,
471
+ "loss": 0.0073,
472
+ "step": 610
473
+ },
474
+ {
475
+ "epoch": 4.1891891891891895,
476
+ "grad_norm": 0.08059559762477875,
477
+ "learning_rate": 3.2432432432432437e-06,
478
+ "loss": 0.0557,
479
+ "step": 620
480
+ },
481
+ {
482
+ "epoch": 4.256756756756757,
483
+ "grad_norm": 0.065690778195858,
484
+ "learning_rate": 2.9729729729729736e-06,
485
+ "loss": 0.0076,
486
+ "step": 630
487
+ },
488
+ {
489
+ "epoch": 4.324324324324325,
490
+ "grad_norm": 0.05522730574011803,
491
+ "learning_rate": 2.702702702702703e-06,
492
+ "loss": 0.0069,
493
+ "step": 640
494
+ },
495
+ {
496
+ "epoch": 4.391891891891892,
497
+ "grad_norm": 0.054099809378385544,
498
+ "learning_rate": 2.432432432432433e-06,
499
+ "loss": 0.0082,
500
+ "step": 650
501
+ },
502
+ {
503
+ "epoch": 4.45945945945946,
504
+ "grad_norm": 0.06278300285339355,
505
+ "learning_rate": 2.1621621621621623e-06,
506
+ "loss": 0.0105,
507
+ "step": 660
508
+ },
509
+ {
510
+ "epoch": 4.527027027027027,
511
+ "grad_norm": 0.05770929157733917,
512
+ "learning_rate": 1.8918918918918922e-06,
513
+ "loss": 0.0071,
514
+ "step": 670
515
+ },
516
+ {
517
+ "epoch": 4.594594594594595,
518
+ "grad_norm": 0.054900798946619034,
519
+ "learning_rate": 1.6216216216216219e-06,
520
+ "loss": 0.0087,
521
+ "step": 680
522
+ },
523
+ {
524
+ "epoch": 4.662162162162162,
525
+ "grad_norm": 0.07473506033420563,
526
+ "learning_rate": 1.3513513513513515e-06,
527
+ "loss": 0.0577,
528
+ "step": 690
529
+ },
530
+ {
531
+ "epoch": 4.72972972972973,
532
+ "grad_norm": 0.053288765251636505,
533
+ "learning_rate": 1.0810810810810812e-06,
534
+ "loss": 0.0069,
535
+ "step": 700
536
+ },
537
+ {
538
+ "epoch": 4.797297297297297,
539
+ "grad_norm": 0.05479385703802109,
540
+ "learning_rate": 8.108108108108109e-07,
541
+ "loss": 0.0069,
542
+ "step": 710
543
+ },
544
+ {
545
+ "epoch": 4.864864864864865,
546
+ "grad_norm": 6.568968772888184,
547
+ "learning_rate": 5.405405405405406e-07,
548
+ "loss": 0.0143,
549
+ "step": 720
550
+ },
551
+ {
552
+ "epoch": 4.9324324324324325,
553
+ "grad_norm": 0.06765338033437729,
554
+ "learning_rate": 2.702702702702703e-07,
555
+ "loss": 0.0074,
556
+ "step": 730
557
+ },
558
+ {
559
+ "epoch": 5.0,
560
+ "grad_norm": 0.0712118148803711,
561
+ "learning_rate": 0.0,
562
+ "loss": 0.0098,
563
+ "step": 740
564
+ },
565
+ {
566
+ "epoch": 5.0,
567
+ "eval_accuracy": 0.9952153110047847,
568
+ "eval_loss": 0.02545962668955326,
569
+ "eval_runtime": 28.1075,
570
+ "eval_samples_per_second": 7.436,
571
+ "eval_steps_per_second": 0.961,
572
+ "step": 740
573
+ },
574
+ {
575
+ "epoch": 5.0,
576
+ "step": 740,
577
+ "total_flos": 4.583651185703117e+17,
578
+ "train_loss": 0.044068760142938514,
579
+ "train_runtime": 1744.9647,
580
+ "train_samples_per_second": 3.39,
581
+ "train_steps_per_second": 0.424
582
+ }
583
+ ],
584
+ "logging_steps": 10,
585
+ "max_steps": 740,
586
+ "num_input_tokens_seen": 0,
587
+ "num_train_epochs": 5,
588
+ "save_steps": 500,
589
+ "stateful_callbacks": {
590
+ "TrainerControl": {
591
+ "args": {
592
+ "should_epoch_stop": false,
593
+ "should_evaluate": false,
594
+ "should_log": false,
595
+ "should_save": true,
596
+ "should_training_stop": true
597
+ },
598
+ "attributes": {}
599
+ }
600
+ },
601
+ "total_flos": 4.583651185703117e+17,
602
+ "train_batch_size": 8,
603
+ "trial_name": null,
604
+ "trial_params": null
605
+ }