BilalMuftuoglu commited on
Commit
3275870
·
verified ·
1 Parent(s): 1874da2

End of training

Browse files
README.md CHANGED
@@ -22,7 +22,7 @@ model-index:
22
  metrics:
23
  - name: Accuracy
24
  type: accuracy
25
- value: 0.5277777777777778
26
  ---
27
 
28
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -32,8 +32,8 @@ should probably proofread and complete it, then remove this comment. -->
32
 
33
  This model is a fine-tuned version of [facebook/deit-base-distilled-patch16-224](https://huggingface.co/facebook/deit-base-distilled-patch16-224) on the imagefolder dataset.
34
  It achieves the following results on the evaluation set:
35
- - Loss: 0.8886
36
- - Accuracy: 0.5278
37
 
38
  ## Model description
39
 
 
22
  metrics:
23
  - name: Accuracy
24
  type: accuracy
25
+ value: 0.6388888888888888
26
  ---
27
 
28
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 
32
 
33
  This model is a fine-tuned version of [facebook/deit-base-distilled-patch16-224](https://huggingface.co/facebook/deit-base-distilled-patch16-224) on the imagefolder dataset.
34
  It achieves the following results on the evaluation set:
35
+ - Loss: 0.7785
36
+ - Accuracy: 0.6389
37
 
38
  ## Model description
39
 
all_results.json ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 57.142857142857146,
3
+ "eval_accuracy": 0.6388888888888888,
4
+ "eval_loss": 0.7784740328788757,
5
+ "eval_runtime": 0.5378,
6
+ "eval_samples_per_second": 66.935,
7
+ "eval_steps_per_second": 3.719,
8
+ "total_flos": 8.903293865079828e+17,
9
+ "train_loss": 0.5302144145965576,
10
+ "train_runtime": 562.7626,
11
+ "train_samples_per_second": 35.717,
12
+ "train_steps_per_second": 0.178
13
+ }
eval_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 57.142857142857146,
3
+ "eval_accuracy": 0.6388888888888888,
4
+ "eval_loss": 0.7784740328788757,
5
+ "eval_runtime": 0.5378,
6
+ "eval_samples_per_second": 66.935,
7
+ "eval_steps_per_second": 3.719
8
+ }
runs/May22_14-43-45_927069b479b5/events.out.tfevents.1716389656.927069b479b5.252.21 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:863a610beb9f51f6ab532e7200eba72ddd0b4dd7fd475685e1668f1c2831349c
3
+ size 405
train_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 57.142857142857146,
3
+ "total_flos": 8.903293865079828e+17,
4
+ "train_loss": 0.5302144145965576,
5
+ "train_runtime": 562.7626,
6
+ "train_samples_per_second": 35.717,
7
+ "train_steps_per_second": 0.178
8
+ }
trainer_state.json ADDED
@@ -0,0 +1,643 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.6388888888888888,
3
+ "best_model_checkpoint": "deit-base-distilled-patch16-224-hasta-65-fold3/checkpoint-38",
4
+ "epoch": 57.142857142857146,
5
+ "eval_steps": 500,
6
+ "global_step": 100,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.5714285714285714,
13
+ "eval_accuracy": 0.3888888888888889,
14
+ "eval_loss": 1.0781989097595215,
15
+ "eval_runtime": 0.4988,
16
+ "eval_samples_per_second": 72.179,
17
+ "eval_steps_per_second": 4.01,
18
+ "step": 1
19
+ },
20
+ {
21
+ "epoch": 1.7142857142857144,
22
+ "eval_accuracy": 0.4444444444444444,
23
+ "eval_loss": 1.0919742584228516,
24
+ "eval_runtime": 0.4962,
25
+ "eval_samples_per_second": 72.549,
26
+ "eval_steps_per_second": 4.03,
27
+ "step": 3
28
+ },
29
+ {
30
+ "epoch": 2.857142857142857,
31
+ "eval_accuracy": 0.3333333333333333,
32
+ "eval_loss": 1.1444017887115479,
33
+ "eval_runtime": 0.5029,
34
+ "eval_samples_per_second": 71.59,
35
+ "eval_steps_per_second": 3.977,
36
+ "step": 5
37
+ },
38
+ {
39
+ "epoch": 4.0,
40
+ "eval_accuracy": 0.4444444444444444,
41
+ "eval_loss": 1.0610096454620361,
42
+ "eval_runtime": 0.5067,
43
+ "eval_samples_per_second": 71.052,
44
+ "eval_steps_per_second": 3.947,
45
+ "step": 7
46
+ },
47
+ {
48
+ "epoch": 4.571428571428571,
49
+ "eval_accuracy": 0.5,
50
+ "eval_loss": 1.0670982599258423,
51
+ "eval_runtime": 0.5087,
52
+ "eval_samples_per_second": 70.762,
53
+ "eval_steps_per_second": 3.931,
54
+ "step": 8
55
+ },
56
+ {
57
+ "epoch": 5.714285714285714,
58
+ "grad_norm": 5.576918601989746,
59
+ "learning_rate": 5e-05,
60
+ "loss": 1.0571,
61
+ "step": 10
62
+ },
63
+ {
64
+ "epoch": 5.714285714285714,
65
+ "eval_accuracy": 0.4444444444444444,
66
+ "eval_loss": 1.179304599761963,
67
+ "eval_runtime": 0.4963,
68
+ "eval_samples_per_second": 72.537,
69
+ "eval_steps_per_second": 4.03,
70
+ "step": 10
71
+ },
72
+ {
73
+ "epoch": 6.857142857142857,
74
+ "eval_accuracy": 0.4722222222222222,
75
+ "eval_loss": 1.086612343788147,
76
+ "eval_runtime": 0.487,
77
+ "eval_samples_per_second": 73.923,
78
+ "eval_steps_per_second": 4.107,
79
+ "step": 12
80
+ },
81
+ {
82
+ "epoch": 8.0,
83
+ "eval_accuracy": 0.5,
84
+ "eval_loss": 1.1467864513397217,
85
+ "eval_runtime": 0.4832,
86
+ "eval_samples_per_second": 74.51,
87
+ "eval_steps_per_second": 4.139,
88
+ "step": 14
89
+ },
90
+ {
91
+ "epoch": 8.571428571428571,
92
+ "eval_accuracy": 0.4166666666666667,
93
+ "eval_loss": 1.2370481491088867,
94
+ "eval_runtime": 0.4877,
95
+ "eval_samples_per_second": 73.81,
96
+ "eval_steps_per_second": 4.101,
97
+ "step": 15
98
+ },
99
+ {
100
+ "epoch": 9.714285714285714,
101
+ "eval_accuracy": 0.5,
102
+ "eval_loss": 1.0559484958648682,
103
+ "eval_runtime": 0.5002,
104
+ "eval_samples_per_second": 71.967,
105
+ "eval_steps_per_second": 3.998,
106
+ "step": 17
107
+ },
108
+ {
109
+ "epoch": 10.857142857142858,
110
+ "eval_accuracy": 0.5277777777777778,
111
+ "eval_loss": 0.9752185344696045,
112
+ "eval_runtime": 0.5095,
113
+ "eval_samples_per_second": 70.655,
114
+ "eval_steps_per_second": 3.925,
115
+ "step": 19
116
+ },
117
+ {
118
+ "epoch": 11.428571428571429,
119
+ "grad_norm": 8.030916213989258,
120
+ "learning_rate": 4.4444444444444447e-05,
121
+ "loss": 0.8894,
122
+ "step": 20
123
+ },
124
+ {
125
+ "epoch": 12.0,
126
+ "eval_accuracy": 0.5,
127
+ "eval_loss": 1.0525615215301514,
128
+ "eval_runtime": 0.4928,
129
+ "eval_samples_per_second": 73.055,
130
+ "eval_steps_per_second": 4.059,
131
+ "step": 21
132
+ },
133
+ {
134
+ "epoch": 12.571428571428571,
135
+ "eval_accuracy": 0.5555555555555556,
136
+ "eval_loss": 1.0316534042358398,
137
+ "eval_runtime": 0.4988,
138
+ "eval_samples_per_second": 72.176,
139
+ "eval_steps_per_second": 4.01,
140
+ "step": 22
141
+ },
142
+ {
143
+ "epoch": 13.714285714285714,
144
+ "eval_accuracy": 0.5555555555555556,
145
+ "eval_loss": 1.0261681079864502,
146
+ "eval_runtime": 0.4974,
147
+ "eval_samples_per_second": 72.378,
148
+ "eval_steps_per_second": 4.021,
149
+ "step": 24
150
+ },
151
+ {
152
+ "epoch": 14.857142857142858,
153
+ "eval_accuracy": 0.4722222222222222,
154
+ "eval_loss": 0.9768860340118408,
155
+ "eval_runtime": 0.494,
156
+ "eval_samples_per_second": 72.872,
157
+ "eval_steps_per_second": 4.048,
158
+ "step": 26
159
+ },
160
+ {
161
+ "epoch": 16.0,
162
+ "eval_accuracy": 0.4722222222222222,
163
+ "eval_loss": 0.9296702146530151,
164
+ "eval_runtime": 0.4924,
165
+ "eval_samples_per_second": 73.118,
166
+ "eval_steps_per_second": 4.062,
167
+ "step": 28
168
+ },
169
+ {
170
+ "epoch": 16.571428571428573,
171
+ "eval_accuracy": 0.5555555555555556,
172
+ "eval_loss": 0.8848314881324768,
173
+ "eval_runtime": 0.4909,
174
+ "eval_samples_per_second": 73.333,
175
+ "eval_steps_per_second": 4.074,
176
+ "step": 29
177
+ },
178
+ {
179
+ "epoch": 17.142857142857142,
180
+ "grad_norm": 4.720308303833008,
181
+ "learning_rate": 3.888888888888889e-05,
182
+ "loss": 0.7239,
183
+ "step": 30
184
+ },
185
+ {
186
+ "epoch": 17.714285714285715,
187
+ "eval_accuracy": 0.5833333333333334,
188
+ "eval_loss": 0.8514459729194641,
189
+ "eval_runtime": 0.5,
190
+ "eval_samples_per_second": 71.997,
191
+ "eval_steps_per_second": 4.0,
192
+ "step": 31
193
+ },
194
+ {
195
+ "epoch": 18.857142857142858,
196
+ "eval_accuracy": 0.5,
197
+ "eval_loss": 0.8981277942657471,
198
+ "eval_runtime": 0.5083,
199
+ "eval_samples_per_second": 70.828,
200
+ "eval_steps_per_second": 3.935,
201
+ "step": 33
202
+ },
203
+ {
204
+ "epoch": 20.0,
205
+ "eval_accuracy": 0.5,
206
+ "eval_loss": 0.9670491814613342,
207
+ "eval_runtime": 0.499,
208
+ "eval_samples_per_second": 72.145,
209
+ "eval_steps_per_second": 4.008,
210
+ "step": 35
211
+ },
212
+ {
213
+ "epoch": 20.571428571428573,
214
+ "eval_accuracy": 0.5555555555555556,
215
+ "eval_loss": 0.85024094581604,
216
+ "eval_runtime": 0.4914,
217
+ "eval_samples_per_second": 73.257,
218
+ "eval_steps_per_second": 4.07,
219
+ "step": 36
220
+ },
221
+ {
222
+ "epoch": 21.714285714285715,
223
+ "eval_accuracy": 0.6388888888888888,
224
+ "eval_loss": 0.7784740328788757,
225
+ "eval_runtime": 0.5025,
226
+ "eval_samples_per_second": 71.636,
227
+ "eval_steps_per_second": 3.98,
228
+ "step": 38
229
+ },
230
+ {
231
+ "epoch": 22.857142857142858,
232
+ "grad_norm": 6.049220561981201,
233
+ "learning_rate": 3.3333333333333335e-05,
234
+ "loss": 0.6094,
235
+ "step": 40
236
+ },
237
+ {
238
+ "epoch": 22.857142857142858,
239
+ "eval_accuracy": 0.5555555555555556,
240
+ "eval_loss": 0.9256177544593811,
241
+ "eval_runtime": 0.4987,
242
+ "eval_samples_per_second": 72.183,
243
+ "eval_steps_per_second": 4.01,
244
+ "step": 40
245
+ },
246
+ {
247
+ "epoch": 24.0,
248
+ "eval_accuracy": 0.5277777777777778,
249
+ "eval_loss": 0.903743326663971,
250
+ "eval_runtime": 0.4838,
251
+ "eval_samples_per_second": 74.409,
252
+ "eval_steps_per_second": 4.134,
253
+ "step": 42
254
+ },
255
+ {
256
+ "epoch": 24.571428571428573,
257
+ "eval_accuracy": 0.5277777777777778,
258
+ "eval_loss": 0.8753263354301453,
259
+ "eval_runtime": 0.4952,
260
+ "eval_samples_per_second": 72.701,
261
+ "eval_steps_per_second": 4.039,
262
+ "step": 43
263
+ },
264
+ {
265
+ "epoch": 25.714285714285715,
266
+ "eval_accuracy": 0.5555555555555556,
267
+ "eval_loss": 0.8113481402397156,
268
+ "eval_runtime": 0.493,
269
+ "eval_samples_per_second": 73.029,
270
+ "eval_steps_per_second": 4.057,
271
+ "step": 45
272
+ },
273
+ {
274
+ "epoch": 26.857142857142858,
275
+ "eval_accuracy": 0.5,
276
+ "eval_loss": 0.9797316789627075,
277
+ "eval_runtime": 0.4954,
278
+ "eval_samples_per_second": 72.663,
279
+ "eval_steps_per_second": 4.037,
280
+ "step": 47
281
+ },
282
+ {
283
+ "epoch": 28.0,
284
+ "eval_accuracy": 0.5,
285
+ "eval_loss": 1.0318821668624878,
286
+ "eval_runtime": 0.4986,
287
+ "eval_samples_per_second": 72.196,
288
+ "eval_steps_per_second": 4.011,
289
+ "step": 49
290
+ },
291
+ {
292
+ "epoch": 28.571428571428573,
293
+ "grad_norm": 4.888261318206787,
294
+ "learning_rate": 2.777777777777778e-05,
295
+ "loss": 0.4826,
296
+ "step": 50
297
+ },
298
+ {
299
+ "epoch": 28.571428571428573,
300
+ "eval_accuracy": 0.5,
301
+ "eval_loss": 0.9113612771034241,
302
+ "eval_runtime": 0.4876,
303
+ "eval_samples_per_second": 73.834,
304
+ "eval_steps_per_second": 4.102,
305
+ "step": 50
306
+ },
307
+ {
308
+ "epoch": 29.714285714285715,
309
+ "eval_accuracy": 0.6388888888888888,
310
+ "eval_loss": 0.7637109160423279,
311
+ "eval_runtime": 0.4915,
312
+ "eval_samples_per_second": 73.252,
313
+ "eval_steps_per_second": 4.07,
314
+ "step": 52
315
+ },
316
+ {
317
+ "epoch": 30.857142857142858,
318
+ "eval_accuracy": 0.5555555555555556,
319
+ "eval_loss": 0.80479896068573,
320
+ "eval_runtime": 0.4951,
321
+ "eval_samples_per_second": 72.711,
322
+ "eval_steps_per_second": 4.04,
323
+ "step": 54
324
+ },
325
+ {
326
+ "epoch": 32.0,
327
+ "eval_accuracy": 0.5,
328
+ "eval_loss": 0.9822417497634888,
329
+ "eval_runtime": 0.4875,
330
+ "eval_samples_per_second": 73.85,
331
+ "eval_steps_per_second": 4.103,
332
+ "step": 56
333
+ },
334
+ {
335
+ "epoch": 32.57142857142857,
336
+ "eval_accuracy": 0.5277777777777778,
337
+ "eval_loss": 0.9030971527099609,
338
+ "eval_runtime": 0.4931,
339
+ "eval_samples_per_second": 73.011,
340
+ "eval_steps_per_second": 4.056,
341
+ "step": 57
342
+ },
343
+ {
344
+ "epoch": 33.714285714285715,
345
+ "eval_accuracy": 0.5833333333333334,
346
+ "eval_loss": 0.7210705280303955,
347
+ "eval_runtime": 0.4818,
348
+ "eval_samples_per_second": 74.719,
349
+ "eval_steps_per_second": 4.151,
350
+ "step": 59
351
+ },
352
+ {
353
+ "epoch": 34.285714285714285,
354
+ "grad_norm": 5.53534460067749,
355
+ "learning_rate": 2.2222222222222223e-05,
356
+ "loss": 0.3943,
357
+ "step": 60
358
+ },
359
+ {
360
+ "epoch": 34.857142857142854,
361
+ "eval_accuracy": 0.6111111111111112,
362
+ "eval_loss": 0.6978909969329834,
363
+ "eval_runtime": 0.4896,
364
+ "eval_samples_per_second": 73.536,
365
+ "eval_steps_per_second": 4.085,
366
+ "step": 61
367
+ },
368
+ {
369
+ "epoch": 36.0,
370
+ "eval_accuracy": 0.6111111111111112,
371
+ "eval_loss": 0.7323928475379944,
372
+ "eval_runtime": 0.4914,
373
+ "eval_samples_per_second": 73.26,
374
+ "eval_steps_per_second": 4.07,
375
+ "step": 63
376
+ },
377
+ {
378
+ "epoch": 36.57142857142857,
379
+ "eval_accuracy": 0.6388888888888888,
380
+ "eval_loss": 0.7461583018302917,
381
+ "eval_runtime": 0.5029,
382
+ "eval_samples_per_second": 71.586,
383
+ "eval_steps_per_second": 3.977,
384
+ "step": 64
385
+ },
386
+ {
387
+ "epoch": 37.714285714285715,
388
+ "eval_accuracy": 0.5833333333333334,
389
+ "eval_loss": 0.7727600932121277,
390
+ "eval_runtime": 0.4906,
391
+ "eval_samples_per_second": 73.38,
392
+ "eval_steps_per_second": 4.077,
393
+ "step": 66
394
+ },
395
+ {
396
+ "epoch": 38.857142857142854,
397
+ "eval_accuracy": 0.6388888888888888,
398
+ "eval_loss": 0.753002941608429,
399
+ "eval_runtime": 0.4949,
400
+ "eval_samples_per_second": 72.747,
401
+ "eval_steps_per_second": 4.041,
402
+ "step": 68
403
+ },
404
+ {
405
+ "epoch": 40.0,
406
+ "grad_norm": 5.077225208282471,
407
+ "learning_rate": 1.6666666666666667e-05,
408
+ "loss": 0.3325,
409
+ "step": 70
410
+ },
411
+ {
412
+ "epoch": 40.0,
413
+ "eval_accuracy": 0.6388888888888888,
414
+ "eval_loss": 0.7361128926277161,
415
+ "eval_runtime": 0.4916,
416
+ "eval_samples_per_second": 73.235,
417
+ "eval_steps_per_second": 4.069,
418
+ "step": 70
419
+ },
420
+ {
421
+ "epoch": 40.57142857142857,
422
+ "eval_accuracy": 0.6388888888888888,
423
+ "eval_loss": 0.7226569652557373,
424
+ "eval_runtime": 0.4863,
425
+ "eval_samples_per_second": 74.034,
426
+ "eval_steps_per_second": 4.113,
427
+ "step": 71
428
+ },
429
+ {
430
+ "epoch": 41.714285714285715,
431
+ "eval_accuracy": 0.5833333333333334,
432
+ "eval_loss": 0.7938054800033569,
433
+ "eval_runtime": 0.4921,
434
+ "eval_samples_per_second": 73.158,
435
+ "eval_steps_per_second": 4.064,
436
+ "step": 73
437
+ },
438
+ {
439
+ "epoch": 42.857142857142854,
440
+ "eval_accuracy": 0.5555555555555556,
441
+ "eval_loss": 0.8002898693084717,
442
+ "eval_runtime": 0.4883,
443
+ "eval_samples_per_second": 73.73,
444
+ "eval_steps_per_second": 4.096,
445
+ "step": 75
446
+ },
447
+ {
448
+ "epoch": 44.0,
449
+ "eval_accuracy": 0.6388888888888888,
450
+ "eval_loss": 0.754361093044281,
451
+ "eval_runtime": 0.4969,
452
+ "eval_samples_per_second": 72.444,
453
+ "eval_steps_per_second": 4.025,
454
+ "step": 77
455
+ },
456
+ {
457
+ "epoch": 44.57142857142857,
458
+ "eval_accuracy": 0.6388888888888888,
459
+ "eval_loss": 0.7556236982345581,
460
+ "eval_runtime": 0.4969,
461
+ "eval_samples_per_second": 72.45,
462
+ "eval_steps_per_second": 4.025,
463
+ "step": 78
464
+ },
465
+ {
466
+ "epoch": 45.714285714285715,
467
+ "grad_norm": 3.50972843170166,
468
+ "learning_rate": 1.1111111111111112e-05,
469
+ "loss": 0.2911,
470
+ "step": 80
471
+ },
472
+ {
473
+ "epoch": 45.714285714285715,
474
+ "eval_accuracy": 0.5833333333333334,
475
+ "eval_loss": 0.7857760190963745,
476
+ "eval_runtime": 0.5038,
477
+ "eval_samples_per_second": 71.451,
478
+ "eval_steps_per_second": 3.97,
479
+ "step": 80
480
+ },
481
+ {
482
+ "epoch": 46.857142857142854,
483
+ "eval_accuracy": 0.5555555555555556,
484
+ "eval_loss": 0.799206018447876,
485
+ "eval_runtime": 0.5005,
486
+ "eval_samples_per_second": 71.93,
487
+ "eval_steps_per_second": 3.996,
488
+ "step": 82
489
+ },
490
+ {
491
+ "epoch": 48.0,
492
+ "eval_accuracy": 0.6111111111111112,
493
+ "eval_loss": 0.8293063640594482,
494
+ "eval_runtime": 0.4894,
495
+ "eval_samples_per_second": 73.56,
496
+ "eval_steps_per_second": 4.087,
497
+ "step": 84
498
+ },
499
+ {
500
+ "epoch": 48.57142857142857,
501
+ "eval_accuracy": 0.5833333333333334,
502
+ "eval_loss": 0.8294222354888916,
503
+ "eval_runtime": 0.488,
504
+ "eval_samples_per_second": 73.778,
505
+ "eval_steps_per_second": 4.099,
506
+ "step": 85
507
+ },
508
+ {
509
+ "epoch": 49.714285714285715,
510
+ "eval_accuracy": 0.5833333333333334,
511
+ "eval_loss": 0.8113357424736023,
512
+ "eval_runtime": 0.4924,
513
+ "eval_samples_per_second": 73.105,
514
+ "eval_steps_per_second": 4.061,
515
+ "step": 87
516
+ },
517
+ {
518
+ "epoch": 50.857142857142854,
519
+ "eval_accuracy": 0.5277777777777778,
520
+ "eval_loss": 0.8061643242835999,
521
+ "eval_runtime": 0.5103,
522
+ "eval_samples_per_second": 70.542,
523
+ "eval_steps_per_second": 3.919,
524
+ "step": 89
525
+ },
526
+ {
527
+ "epoch": 51.42857142857143,
528
+ "grad_norm": 4.2429914474487305,
529
+ "learning_rate": 5.555555555555556e-06,
530
+ "loss": 0.2577,
531
+ "step": 90
532
+ },
533
+ {
534
+ "epoch": 52.0,
535
+ "eval_accuracy": 0.5555555555555556,
536
+ "eval_loss": 0.8508003950119019,
537
+ "eval_runtime": 0.4998,
538
+ "eval_samples_per_second": 72.032,
539
+ "eval_steps_per_second": 4.002,
540
+ "step": 91
541
+ },
542
+ {
543
+ "epoch": 52.57142857142857,
544
+ "eval_accuracy": 0.5555555555555556,
545
+ "eval_loss": 0.874424397945404,
546
+ "eval_runtime": 0.5048,
547
+ "eval_samples_per_second": 71.314,
548
+ "eval_steps_per_second": 3.962,
549
+ "step": 92
550
+ },
551
+ {
552
+ "epoch": 53.714285714285715,
553
+ "eval_accuracy": 0.5555555555555556,
554
+ "eval_loss": 0.894795298576355,
555
+ "eval_runtime": 0.4866,
556
+ "eval_samples_per_second": 73.986,
557
+ "eval_steps_per_second": 4.11,
558
+ "step": 94
559
+ },
560
+ {
561
+ "epoch": 54.857142857142854,
562
+ "eval_accuracy": 0.5277777777777778,
563
+ "eval_loss": 0.8976125717163086,
564
+ "eval_runtime": 0.4871,
565
+ "eval_samples_per_second": 73.913,
566
+ "eval_steps_per_second": 4.106,
567
+ "step": 96
568
+ },
569
+ {
570
+ "epoch": 56.0,
571
+ "eval_accuracy": 0.5277777777777778,
572
+ "eval_loss": 0.8932664394378662,
573
+ "eval_runtime": 0.5026,
574
+ "eval_samples_per_second": 71.622,
575
+ "eval_steps_per_second": 3.979,
576
+ "step": 98
577
+ },
578
+ {
579
+ "epoch": 56.57142857142857,
580
+ "eval_accuracy": 0.5277777777777778,
581
+ "eval_loss": 0.8899792432785034,
582
+ "eval_runtime": 0.4931,
583
+ "eval_samples_per_second": 73.013,
584
+ "eval_steps_per_second": 4.056,
585
+ "step": 99
586
+ },
587
+ {
588
+ "epoch": 57.142857142857146,
589
+ "grad_norm": 3.8109960556030273,
590
+ "learning_rate": 0.0,
591
+ "loss": 0.2642,
592
+ "step": 100
593
+ },
594
+ {
595
+ "epoch": 57.142857142857146,
596
+ "eval_accuracy": 0.5277777777777778,
597
+ "eval_loss": 0.8885748386383057,
598
+ "eval_runtime": 0.4937,
599
+ "eval_samples_per_second": 72.912,
600
+ "eval_steps_per_second": 4.051,
601
+ "step": 100
602
+ },
603
+ {
604
+ "epoch": 57.142857142857146,
605
+ "step": 100,
606
+ "total_flos": 8.903293865079828e+17,
607
+ "train_loss": 0.5302144145965576,
608
+ "train_runtime": 562.7626,
609
+ "train_samples_per_second": 35.717,
610
+ "train_steps_per_second": 0.178
611
+ },
612
+ {
613
+ "epoch": 57.142857142857146,
614
+ "eval_accuracy": 0.6388888888888888,
615
+ "eval_loss": 0.7784740328788757,
616
+ "eval_runtime": 0.5378,
617
+ "eval_samples_per_second": 66.935,
618
+ "eval_steps_per_second": 3.719,
619
+ "step": 100
620
+ }
621
+ ],
622
+ "logging_steps": 10,
623
+ "max_steps": 100,
624
+ "num_input_tokens_seen": 0,
625
+ "num_train_epochs": 100,
626
+ "save_steps": 500,
627
+ "stateful_callbacks": {
628
+ "TrainerControl": {
629
+ "args": {
630
+ "should_epoch_stop": false,
631
+ "should_evaluate": false,
632
+ "should_log": false,
633
+ "should_save": true,
634
+ "should_training_stop": true
635
+ },
636
+ "attributes": {}
637
+ }
638
+ },
639
+ "total_flos": 8.903293865079828e+17,
640
+ "train_batch_size": 32,
641
+ "trial_name": null,
642
+ "trial_params": null
643
+ }