suredream commited on
Commit
c994b8a
1 Parent(s): 00df8de

End of training

Browse files
README.md CHANGED
@@ -2,6 +2,8 @@
2
  license: apache-2.0
3
  base_model: google/vit-base-patch16-224-in21k
4
  tags:
 
 
5
  - generated_from_trainer
6
  metrics:
7
  - accuracy
@@ -15,10 +17,10 @@ should probably proofread and complete it, then remove this comment. -->
15
 
16
  # vit-base-beans
17
 
18
- This model is a fine-tuned version of [google/vit-base-patch16-224-in21k](https://huggingface.co/google/vit-base-patch16-224-in21k) on an unknown dataset.
19
  It achieves the following results on the evaluation set:
20
- - Loss: 0.0824
21
- - Accuracy: 0.9774
22
 
23
  ## Model description
24
 
 
2
  license: apache-2.0
3
  base_model: google/vit-base-patch16-224-in21k
4
  tags:
5
+ - image-classification
6
+ - vision
7
  - generated_from_trainer
8
  metrics:
9
  - accuracy
 
17
 
18
  # vit-base-beans
19
 
20
+ This model is a fine-tuned version of [google/vit-base-patch16-224-in21k](https://huggingface.co/google/vit-base-patch16-224-in21k) on the beans dataset.
21
  It achieves the following results on the evaluation set:
22
+ - Loss: 0.0650
23
+ - Accuracy: 0.9925
24
 
25
  ## Model description
26
 
all_results.json ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 5.0,
3
+ "eval_accuracy": 0.9924812030075187,
4
+ "eval_loss": 0.06496671587228775,
5
+ "eval_runtime": 2.4595,
6
+ "eval_samples_per_second": 54.077,
7
+ "eval_steps_per_second": 6.912,
8
+ "total_flos": 4.006371770595533e+17,
9
+ "train_loss": 0.2193689556305225,
10
+ "train_runtime": 319.7554,
11
+ "train_samples_per_second": 16.169,
12
+ "train_steps_per_second": 2.033
13
+ }
eval_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 5.0,
3
+ "eval_accuracy": 0.9924812030075187,
4
+ "eval_loss": 0.06496671587228775,
5
+ "eval_runtime": 2.4595,
6
+ "eval_samples_per_second": 54.077,
7
+ "eval_steps_per_second": 6.912
8
+ }
runs/Jul06_17-44-23_d9568e0fc9ba/events.out.tfevents.1720288227.d9568e0fc9ba.2235.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:06f476945d678bc717cdfa6963b55b75163fd615b2216dd2b4a7ef85c1797587
3
+ size 411
train_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 5.0,
3
+ "total_flos": 4.006371770595533e+17,
4
+ "train_loss": 0.2193689556305225,
5
+ "train_runtime": 319.7554,
6
+ "train_samples_per_second": 16.169,
7
+ "train_steps_per_second": 2.033
8
+ }
trainer_state.json ADDED
@@ -0,0 +1,542 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.06496671587228775,
3
+ "best_model_checkpoint": "./beans_outputs/checkpoint-520",
4
+ "epoch": 5.0,
5
+ "eval_steps": 500,
6
+ "global_step": 650,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.07692307692307693,
13
+ "grad_norm": 2.1983582973480225,
14
+ "learning_rate": 1.9692307692307696e-05,
15
+ "loss": 1.0245,
16
+ "step": 10
17
+ },
18
+ {
19
+ "epoch": 0.15384615384615385,
20
+ "grad_norm": 1.8467624187469482,
21
+ "learning_rate": 1.9384615384615386e-05,
22
+ "loss": 0.9453,
23
+ "step": 20
24
+ },
25
+ {
26
+ "epoch": 0.23076923076923078,
27
+ "grad_norm": 2.103004217147827,
28
+ "learning_rate": 1.907692307692308e-05,
29
+ "loss": 0.8407,
30
+ "step": 30
31
+ },
32
+ {
33
+ "epoch": 0.3076923076923077,
34
+ "grad_norm": 2.6212635040283203,
35
+ "learning_rate": 1.876923076923077e-05,
36
+ "loss": 0.6962,
37
+ "step": 40
38
+ },
39
+ {
40
+ "epoch": 0.38461538461538464,
41
+ "grad_norm": 4.0500969886779785,
42
+ "learning_rate": 1.8461538461538465e-05,
43
+ "loss": 0.6627,
44
+ "step": 50
45
+ },
46
+ {
47
+ "epoch": 0.46153846153846156,
48
+ "grad_norm": 2.1369540691375732,
49
+ "learning_rate": 1.8153846153846155e-05,
50
+ "loss": 0.5824,
51
+ "step": 60
52
+ },
53
+ {
54
+ "epoch": 0.5384615384615384,
55
+ "grad_norm": 1.9217969179153442,
56
+ "learning_rate": 1.784615384615385e-05,
57
+ "loss": 0.5207,
58
+ "step": 70
59
+ },
60
+ {
61
+ "epoch": 0.6153846153846154,
62
+ "grad_norm": 1.2160992622375488,
63
+ "learning_rate": 1.753846153846154e-05,
64
+ "loss": 0.3929,
65
+ "step": 80
66
+ },
67
+ {
68
+ "epoch": 0.6923076923076923,
69
+ "grad_norm": 2.5192856788635254,
70
+ "learning_rate": 1.7230769230769234e-05,
71
+ "loss": 0.3531,
72
+ "step": 90
73
+ },
74
+ {
75
+ "epoch": 0.7692307692307693,
76
+ "grad_norm": 2.9285073280334473,
77
+ "learning_rate": 1.6923076923076924e-05,
78
+ "loss": 0.3694,
79
+ "step": 100
80
+ },
81
+ {
82
+ "epoch": 0.8461538461538461,
83
+ "grad_norm": 2.098353147506714,
84
+ "learning_rate": 1.6615384615384618e-05,
85
+ "loss": 0.3324,
86
+ "step": 110
87
+ },
88
+ {
89
+ "epoch": 0.9230769230769231,
90
+ "grad_norm": 2.5526487827301025,
91
+ "learning_rate": 1.630769230769231e-05,
92
+ "loss": 0.2447,
93
+ "step": 120
94
+ },
95
+ {
96
+ "epoch": 1.0,
97
+ "grad_norm": 7.012009143829346,
98
+ "learning_rate": 1.6000000000000003e-05,
99
+ "loss": 0.2838,
100
+ "step": 130
101
+ },
102
+ {
103
+ "epoch": 1.0,
104
+ "eval_accuracy": 0.9624060150375939,
105
+ "eval_loss": 0.21691447496414185,
106
+ "eval_runtime": 1.8915,
107
+ "eval_samples_per_second": 70.313,
108
+ "eval_steps_per_second": 8.987,
109
+ "step": 130
110
+ },
111
+ {
112
+ "epoch": 1.0769230769230769,
113
+ "grad_norm": 1.6030009984970093,
114
+ "learning_rate": 1.5692307692307693e-05,
115
+ "loss": 0.1997,
116
+ "step": 140
117
+ },
118
+ {
119
+ "epoch": 1.1538461538461537,
120
+ "grad_norm": 3.190946578979492,
121
+ "learning_rate": 1.5384615384615387e-05,
122
+ "loss": 0.2249,
123
+ "step": 150
124
+ },
125
+ {
126
+ "epoch": 1.2307692307692308,
127
+ "grad_norm": 1.4254164695739746,
128
+ "learning_rate": 1.5076923076923078e-05,
129
+ "loss": 0.2047,
130
+ "step": 160
131
+ },
132
+ {
133
+ "epoch": 1.3076923076923077,
134
+ "grad_norm": 0.5190562605857849,
135
+ "learning_rate": 1.4769230769230772e-05,
136
+ "loss": 0.2217,
137
+ "step": 170
138
+ },
139
+ {
140
+ "epoch": 1.3846153846153846,
141
+ "grad_norm": 0.6067346334457397,
142
+ "learning_rate": 1.4461538461538462e-05,
143
+ "loss": 0.2069,
144
+ "step": 180
145
+ },
146
+ {
147
+ "epoch": 1.4615384615384617,
148
+ "grad_norm": 3.877462387084961,
149
+ "learning_rate": 1.4153846153846156e-05,
150
+ "loss": 0.1627,
151
+ "step": 190
152
+ },
153
+ {
154
+ "epoch": 1.5384615384615383,
155
+ "grad_norm": 0.4851893484592438,
156
+ "learning_rate": 1.3846153846153847e-05,
157
+ "loss": 0.2515,
158
+ "step": 200
159
+ },
160
+ {
161
+ "epoch": 1.6153846153846154,
162
+ "grad_norm": 0.7414268851280212,
163
+ "learning_rate": 1.353846153846154e-05,
164
+ "loss": 0.1788,
165
+ "step": 210
166
+ },
167
+ {
168
+ "epoch": 1.6923076923076923,
169
+ "grad_norm": 2.4538869857788086,
170
+ "learning_rate": 1.3230769230769231e-05,
171
+ "loss": 0.2098,
172
+ "step": 220
173
+ },
174
+ {
175
+ "epoch": 1.7692307692307692,
176
+ "grad_norm": 1.7667008638381958,
177
+ "learning_rate": 1.2923076923076925e-05,
178
+ "loss": 0.1678,
179
+ "step": 230
180
+ },
181
+ {
182
+ "epoch": 1.8461538461538463,
183
+ "grad_norm": 4.910299777984619,
184
+ "learning_rate": 1.2615384615384616e-05,
185
+ "loss": 0.2644,
186
+ "step": 240
187
+ },
188
+ {
189
+ "epoch": 1.9230769230769231,
190
+ "grad_norm": 0.383217453956604,
191
+ "learning_rate": 1.230769230769231e-05,
192
+ "loss": 0.1394,
193
+ "step": 250
194
+ },
195
+ {
196
+ "epoch": 2.0,
197
+ "grad_norm": 0.3504723310470581,
198
+ "learning_rate": 1.2e-05,
199
+ "loss": 0.1324,
200
+ "step": 260
201
+ },
202
+ {
203
+ "epoch": 2.0,
204
+ "eval_accuracy": 0.9699248120300752,
205
+ "eval_loss": 0.13457302749156952,
206
+ "eval_runtime": 2.0055,
207
+ "eval_samples_per_second": 66.318,
208
+ "eval_steps_per_second": 8.477,
209
+ "step": 260
210
+ },
211
+ {
212
+ "epoch": 2.076923076923077,
213
+ "grad_norm": 0.5011544227600098,
214
+ "learning_rate": 1.1692307692307694e-05,
215
+ "loss": 0.0904,
216
+ "step": 270
217
+ },
218
+ {
219
+ "epoch": 2.1538461538461537,
220
+ "grad_norm": 0.3368860185146332,
221
+ "learning_rate": 1.1384615384615385e-05,
222
+ "loss": 0.1434,
223
+ "step": 280
224
+ },
225
+ {
226
+ "epoch": 2.230769230769231,
227
+ "grad_norm": 6.839877128601074,
228
+ "learning_rate": 1.1076923076923079e-05,
229
+ "loss": 0.124,
230
+ "step": 290
231
+ },
232
+ {
233
+ "epoch": 2.3076923076923075,
234
+ "grad_norm": 8.27059555053711,
235
+ "learning_rate": 1.076923076923077e-05,
236
+ "loss": 0.1441,
237
+ "step": 300
238
+ },
239
+ {
240
+ "epoch": 2.3846153846153846,
241
+ "grad_norm": 4.772457599639893,
242
+ "learning_rate": 1.0461538461538463e-05,
243
+ "loss": 0.1723,
244
+ "step": 310
245
+ },
246
+ {
247
+ "epoch": 2.4615384615384617,
248
+ "grad_norm": 0.3270654082298279,
249
+ "learning_rate": 1.0153846153846154e-05,
250
+ "loss": 0.1571,
251
+ "step": 320
252
+ },
253
+ {
254
+ "epoch": 2.5384615384615383,
255
+ "grad_norm": 6.340713024139404,
256
+ "learning_rate": 9.846153846153848e-06,
257
+ "loss": 0.1882,
258
+ "step": 330
259
+ },
260
+ {
261
+ "epoch": 2.6153846153846154,
262
+ "grad_norm": 1.2030677795410156,
263
+ "learning_rate": 9.53846153846154e-06,
264
+ "loss": 0.0736,
265
+ "step": 340
266
+ },
267
+ {
268
+ "epoch": 2.6923076923076925,
269
+ "grad_norm": 0.3556363880634308,
270
+ "learning_rate": 9.230769230769232e-06,
271
+ "loss": 0.1333,
272
+ "step": 350
273
+ },
274
+ {
275
+ "epoch": 2.769230769230769,
276
+ "grad_norm": 10.645792961120605,
277
+ "learning_rate": 8.923076923076925e-06,
278
+ "loss": 0.1295,
279
+ "step": 360
280
+ },
281
+ {
282
+ "epoch": 2.8461538461538463,
283
+ "grad_norm": 0.30723875761032104,
284
+ "learning_rate": 8.615384615384617e-06,
285
+ "loss": 0.1506,
286
+ "step": 370
287
+ },
288
+ {
289
+ "epoch": 2.9230769230769234,
290
+ "grad_norm": 1.1151694059371948,
291
+ "learning_rate": 8.307692307692309e-06,
292
+ "loss": 0.1301,
293
+ "step": 380
294
+ },
295
+ {
296
+ "epoch": 3.0,
297
+ "grad_norm": 0.29431405663490295,
298
+ "learning_rate": 8.000000000000001e-06,
299
+ "loss": 0.143,
300
+ "step": 390
301
+ },
302
+ {
303
+ "epoch": 3.0,
304
+ "eval_accuracy": 0.9699248120300752,
305
+ "eval_loss": 0.09983458369970322,
306
+ "eval_runtime": 2.4088,
307
+ "eval_samples_per_second": 55.214,
308
+ "eval_steps_per_second": 7.057,
309
+ "step": 390
310
+ },
311
+ {
312
+ "epoch": 3.076923076923077,
313
+ "grad_norm": 2.359541893005371,
314
+ "learning_rate": 7.692307692307694e-06,
315
+ "loss": 0.1319,
316
+ "step": 400
317
+ },
318
+ {
319
+ "epoch": 3.1538461538461537,
320
+ "grad_norm": 6.216188907623291,
321
+ "learning_rate": 7.384615384615386e-06,
322
+ "loss": 0.1523,
323
+ "step": 410
324
+ },
325
+ {
326
+ "epoch": 3.230769230769231,
327
+ "grad_norm": 9.072651863098145,
328
+ "learning_rate": 7.076923076923078e-06,
329
+ "loss": 0.1394,
330
+ "step": 420
331
+ },
332
+ {
333
+ "epoch": 3.3076923076923075,
334
+ "grad_norm": 0.23217681050300598,
335
+ "learning_rate": 6.76923076923077e-06,
336
+ "loss": 0.0776,
337
+ "step": 430
338
+ },
339
+ {
340
+ "epoch": 3.3846153846153846,
341
+ "grad_norm": 8.235204696655273,
342
+ "learning_rate": 6.461538461538463e-06,
343
+ "loss": 0.1129,
344
+ "step": 440
345
+ },
346
+ {
347
+ "epoch": 3.4615384615384617,
348
+ "grad_norm": 12.133755683898926,
349
+ "learning_rate": 6.153846153846155e-06,
350
+ "loss": 0.0812,
351
+ "step": 450
352
+ },
353
+ {
354
+ "epoch": 3.5384615384615383,
355
+ "grad_norm": 5.274909496307373,
356
+ "learning_rate": 5.846153846153847e-06,
357
+ "loss": 0.0968,
358
+ "step": 460
359
+ },
360
+ {
361
+ "epoch": 3.6153846153846154,
362
+ "grad_norm": 8.703495025634766,
363
+ "learning_rate": 5.538461538461539e-06,
364
+ "loss": 0.0805,
365
+ "step": 470
366
+ },
367
+ {
368
+ "epoch": 3.6923076923076925,
369
+ "grad_norm": 0.21897560358047485,
370
+ "learning_rate": 5.230769230769232e-06,
371
+ "loss": 0.0964,
372
+ "step": 480
373
+ },
374
+ {
375
+ "epoch": 3.769230769230769,
376
+ "grad_norm": 0.21305297315120697,
377
+ "learning_rate": 4.923076923076924e-06,
378
+ "loss": 0.075,
379
+ "step": 490
380
+ },
381
+ {
382
+ "epoch": 3.8461538461538463,
383
+ "grad_norm": 0.9238463044166565,
384
+ "learning_rate": 4.615384615384616e-06,
385
+ "loss": 0.1348,
386
+ "step": 500
387
+ },
388
+ {
389
+ "epoch": 3.9230769230769234,
390
+ "grad_norm": 0.21227774024009705,
391
+ "learning_rate": 4.307692307692308e-06,
392
+ "loss": 0.127,
393
+ "step": 510
394
+ },
395
+ {
396
+ "epoch": 4.0,
397
+ "grad_norm": 0.30383384227752686,
398
+ "learning_rate": 4.000000000000001e-06,
399
+ "loss": 0.0833,
400
+ "step": 520
401
+ },
402
+ {
403
+ "epoch": 4.0,
404
+ "eval_accuracy": 0.9924812030075187,
405
+ "eval_loss": 0.06496671587228775,
406
+ "eval_runtime": 2.4064,
407
+ "eval_samples_per_second": 55.27,
408
+ "eval_steps_per_second": 7.065,
409
+ "step": 520
410
+ },
411
+ {
412
+ "epoch": 4.076923076923077,
413
+ "grad_norm": 5.725286960601807,
414
+ "learning_rate": 3.692307692307693e-06,
415
+ "loss": 0.0969,
416
+ "step": 530
417
+ },
418
+ {
419
+ "epoch": 4.153846153846154,
420
+ "grad_norm": 1.5072094202041626,
421
+ "learning_rate": 3.384615384615385e-06,
422
+ "loss": 0.1634,
423
+ "step": 540
424
+ },
425
+ {
426
+ "epoch": 4.230769230769231,
427
+ "grad_norm": 0.3428334891796112,
428
+ "learning_rate": 3.0769230769230774e-06,
429
+ "loss": 0.1552,
430
+ "step": 550
431
+ },
432
+ {
433
+ "epoch": 4.3076923076923075,
434
+ "grad_norm": 1.1749656200408936,
435
+ "learning_rate": 2.7692307692307697e-06,
436
+ "loss": 0.0503,
437
+ "step": 560
438
+ },
439
+ {
440
+ "epoch": 4.384615384615385,
441
+ "grad_norm": 0.32822975516319275,
442
+ "learning_rate": 2.461538461538462e-06,
443
+ "loss": 0.1335,
444
+ "step": 570
445
+ },
446
+ {
447
+ "epoch": 4.461538461538462,
448
+ "grad_norm": 0.2676811218261719,
449
+ "learning_rate": 2.153846153846154e-06,
450
+ "loss": 0.0836,
451
+ "step": 580
452
+ },
453
+ {
454
+ "epoch": 4.538461538461538,
455
+ "grad_norm": 8.637232780456543,
456
+ "learning_rate": 1.8461538461538465e-06,
457
+ "loss": 0.0739,
458
+ "step": 590
459
+ },
460
+ {
461
+ "epoch": 4.615384615384615,
462
+ "grad_norm": 2.967637777328491,
463
+ "learning_rate": 1.5384615384615387e-06,
464
+ "loss": 0.0973,
465
+ "step": 600
466
+ },
467
+ {
468
+ "epoch": 4.6923076923076925,
469
+ "grad_norm": 4.9968953132629395,
470
+ "learning_rate": 1.230769230769231e-06,
471
+ "loss": 0.0857,
472
+ "step": 610
473
+ },
474
+ {
475
+ "epoch": 4.769230769230769,
476
+ "grad_norm": 0.2506353259086609,
477
+ "learning_rate": 9.230769230769232e-07,
478
+ "loss": 0.0831,
479
+ "step": 620
480
+ },
481
+ {
482
+ "epoch": 4.846153846153846,
483
+ "grad_norm": 0.21034254133701324,
484
+ "learning_rate": 6.153846153846155e-07,
485
+ "loss": 0.066,
486
+ "step": 630
487
+ },
488
+ {
489
+ "epoch": 4.923076923076923,
490
+ "grad_norm": 0.23136074841022491,
491
+ "learning_rate": 3.0769230769230774e-07,
492
+ "loss": 0.0781,
493
+ "step": 640
494
+ },
495
+ {
496
+ "epoch": 5.0,
497
+ "grad_norm": 0.6315775513648987,
498
+ "learning_rate": 0.0,
499
+ "loss": 0.1099,
500
+ "step": 650
501
+ },
502
+ {
503
+ "epoch": 5.0,
504
+ "eval_accuracy": 0.9774436090225563,
505
+ "eval_loss": 0.0823998898267746,
506
+ "eval_runtime": 2.4012,
507
+ "eval_samples_per_second": 55.389,
508
+ "eval_steps_per_second": 7.08,
509
+ "step": 650
510
+ },
511
+ {
512
+ "epoch": 5.0,
513
+ "step": 650,
514
+ "total_flos": 4.006371770595533e+17,
515
+ "train_loss": 0.2193689556305225,
516
+ "train_runtime": 319.7554,
517
+ "train_samples_per_second": 16.169,
518
+ "train_steps_per_second": 2.033
519
+ }
520
+ ],
521
+ "logging_steps": 10,
522
+ "max_steps": 650,
523
+ "num_input_tokens_seen": 0,
524
+ "num_train_epochs": 5,
525
+ "save_steps": 500,
526
+ "stateful_callbacks": {
527
+ "TrainerControl": {
528
+ "args": {
529
+ "should_epoch_stop": false,
530
+ "should_evaluate": false,
531
+ "should_log": false,
532
+ "should_save": true,
533
+ "should_training_stop": true
534
+ },
535
+ "attributes": {}
536
+ }
537
+ },
538
+ "total_flos": 4.006371770595533e+17,
539
+ "train_batch_size": 8,
540
+ "trial_name": null,
541
+ "trial_params": null
542
+ }