lixiqi commited on
Commit
3999dcc
1 Parent(s): c01aab3

End of training

Browse files
all_results.json ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 3.0,
3
+ "eval_accuracy": 0.6862635831707997,
4
+ "eval_loss": 0.8496666550636292,
5
+ "eval_runtime": 62.2477,
6
+ "eval_samples_per_second": 115.313,
7
+ "eval_steps_per_second": 3.615,
8
+ "total_flos": 6.668732964123095e+18,
9
+ "train_loss": 1.1464171437990098,
10
+ "train_runtime": 2129.0691,
11
+ "train_samples_per_second": 40.453,
12
+ "train_steps_per_second": 0.316
13
+ }
eval_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 3.0,
3
+ "eval_accuracy": 0.6862635831707997,
4
+ "eval_loss": 0.8496666550636292,
5
+ "eval_runtime": 62.2477,
6
+ "eval_samples_per_second": 115.313,
7
+ "eval_steps_per_second": 3.615
8
+ }
runs/Jan09_09-14-35_b4ebfdaa0ca7/events.out.tfevents.1673257986.b4ebfdaa0ca7.23.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3f53cde8acdcc42541f6a8cd144c418b9a3188f44702ff12f46f3490d0faa6ba
3
+ size 363
train_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 3.0,
3
+ "total_flos": 6.668732964123095e+18,
4
+ "train_loss": 1.1464171437990098,
5
+ "train_runtime": 2129.0691,
6
+ "train_samples_per_second": 40.453,
7
+ "train_steps_per_second": 0.316
8
+ }
trainer_state.json ADDED
@@ -0,0 +1,454 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.6862635831707997,
3
+ "best_model_checkpoint": "beit-base-patch16-224-pt22k-ft22k-finetuned-FER2013-7e-05/checkpoint-672",
4
+ "epoch": 2.997772828507795,
5
+ "global_step": 672,
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": 1.0294117647058823e-05,
13
+ "loss": 1.9001,
14
+ "step": 10
15
+ },
16
+ {
17
+ "epoch": 0.09,
18
+ "learning_rate": 2.0588235294117645e-05,
19
+ "loss": 1.7513,
20
+ "step": 20
21
+ },
22
+ {
23
+ "epoch": 0.13,
24
+ "learning_rate": 3.088235294117647e-05,
25
+ "loss": 1.6223,
26
+ "step": 30
27
+ },
28
+ {
29
+ "epoch": 0.18,
30
+ "learning_rate": 4.117647058823529e-05,
31
+ "loss": 1.5127,
32
+ "step": 40
33
+ },
34
+ {
35
+ "epoch": 0.22,
36
+ "learning_rate": 5.147058823529412e-05,
37
+ "loss": 1.414,
38
+ "step": 50
39
+ },
40
+ {
41
+ "epoch": 0.27,
42
+ "learning_rate": 6.176470588235294e-05,
43
+ "loss": 1.3549,
44
+ "step": 60
45
+ },
46
+ {
47
+ "epoch": 0.31,
48
+ "learning_rate": 6.976821192052979e-05,
49
+ "loss": 1.3773,
50
+ "step": 70
51
+ },
52
+ {
53
+ "epoch": 0.36,
54
+ "learning_rate": 6.86092715231788e-05,
55
+ "loss": 1.2798,
56
+ "step": 80
57
+ },
58
+ {
59
+ "epoch": 0.4,
60
+ "learning_rate": 6.74503311258278e-05,
61
+ "loss": 1.2661,
62
+ "step": 90
63
+ },
64
+ {
65
+ "epoch": 0.45,
66
+ "learning_rate": 6.629139072847681e-05,
67
+ "loss": 1.3509,
68
+ "step": 100
69
+ },
70
+ {
71
+ "epoch": 0.49,
72
+ "learning_rate": 6.513245033112582e-05,
73
+ "loss": 1.3001,
74
+ "step": 110
75
+ },
76
+ {
77
+ "epoch": 0.53,
78
+ "learning_rate": 6.397350993377483e-05,
79
+ "loss": 1.2536,
80
+ "step": 120
81
+ },
82
+ {
83
+ "epoch": 0.58,
84
+ "learning_rate": 6.281456953642384e-05,
85
+ "loss": 1.1808,
86
+ "step": 130
87
+ },
88
+ {
89
+ "epoch": 0.62,
90
+ "learning_rate": 6.165562913907283e-05,
91
+ "loss": 1.2998,
92
+ "step": 140
93
+ },
94
+ {
95
+ "epoch": 0.67,
96
+ "learning_rate": 6.049668874172185e-05,
97
+ "loss": 1.232,
98
+ "step": 150
99
+ },
100
+ {
101
+ "epoch": 0.71,
102
+ "learning_rate": 5.933774834437086e-05,
103
+ "loss": 1.2809,
104
+ "step": 160
105
+ },
106
+ {
107
+ "epoch": 0.76,
108
+ "learning_rate": 5.8178807947019866e-05,
109
+ "loss": 1.2072,
110
+ "step": 170
111
+ },
112
+ {
113
+ "epoch": 0.8,
114
+ "learning_rate": 5.7019867549668874e-05,
115
+ "loss": 1.2004,
116
+ "step": 180
117
+ },
118
+ {
119
+ "epoch": 0.85,
120
+ "learning_rate": 5.5860927152317876e-05,
121
+ "loss": 1.2,
122
+ "step": 190
123
+ },
124
+ {
125
+ "epoch": 0.89,
126
+ "learning_rate": 5.4701986754966884e-05,
127
+ "loss": 1.2034,
128
+ "step": 200
129
+ },
130
+ {
131
+ "epoch": 0.94,
132
+ "learning_rate": 5.354304635761589e-05,
133
+ "loss": 1.1671,
134
+ "step": 210
135
+ },
136
+ {
137
+ "epoch": 0.98,
138
+ "learning_rate": 5.23841059602649e-05,
139
+ "loss": 1.1607,
140
+ "step": 220
141
+ },
142
+ {
143
+ "epoch": 1.0,
144
+ "eval_accuracy": 0.6238506547784898,
145
+ "eval_loss": 1.0028917789459229,
146
+ "eval_runtime": 64.6131,
147
+ "eval_samples_per_second": 111.092,
148
+ "eval_steps_per_second": 3.482,
149
+ "step": 224
150
+ },
151
+ {
152
+ "epoch": 1.03,
153
+ "learning_rate": 5.12251655629139e-05,
154
+ "loss": 1.2012,
155
+ "step": 230
156
+ },
157
+ {
158
+ "epoch": 1.07,
159
+ "learning_rate": 5.006622516556291e-05,
160
+ "loss": 1.099,
161
+ "step": 240
162
+ },
163
+ {
164
+ "epoch": 1.12,
165
+ "learning_rate": 4.890728476821192e-05,
166
+ "loss": 1.1241,
167
+ "step": 250
168
+ },
169
+ {
170
+ "epoch": 1.16,
171
+ "learning_rate": 4.7748344370860927e-05,
172
+ "loss": 1.1595,
173
+ "step": 260
174
+ },
175
+ {
176
+ "epoch": 1.2,
177
+ "learning_rate": 4.658940397350993e-05,
178
+ "loss": 1.1434,
179
+ "step": 270
180
+ },
181
+ {
182
+ "epoch": 1.25,
183
+ "learning_rate": 4.5430463576158936e-05,
184
+ "loss": 1.1487,
185
+ "step": 280
186
+ },
187
+ {
188
+ "epoch": 1.29,
189
+ "learning_rate": 4.4271523178807944e-05,
190
+ "loss": 1.1553,
191
+ "step": 290
192
+ },
193
+ {
194
+ "epoch": 1.34,
195
+ "learning_rate": 4.311258278145695e-05,
196
+ "loss": 1.075,
197
+ "step": 300
198
+ },
199
+ {
200
+ "epoch": 1.38,
201
+ "learning_rate": 4.1953642384105954e-05,
202
+ "loss": 1.1167,
203
+ "step": 310
204
+ },
205
+ {
206
+ "epoch": 1.43,
207
+ "learning_rate": 4.079470198675496e-05,
208
+ "loss": 1.1692,
209
+ "step": 320
210
+ },
211
+ {
212
+ "epoch": 1.47,
213
+ "learning_rate": 3.963576158940397e-05,
214
+ "loss": 1.0329,
215
+ "step": 330
216
+ },
217
+ {
218
+ "epoch": 1.52,
219
+ "learning_rate": 3.847682119205298e-05,
220
+ "loss": 1.0411,
221
+ "step": 340
222
+ },
223
+ {
224
+ "epoch": 1.56,
225
+ "learning_rate": 3.731788079470198e-05,
226
+ "loss": 1.0907,
227
+ "step": 350
228
+ },
229
+ {
230
+ "epoch": 1.61,
231
+ "learning_rate": 3.615894039735099e-05,
232
+ "loss": 1.0668,
233
+ "step": 360
234
+ },
235
+ {
236
+ "epoch": 1.65,
237
+ "learning_rate": 3.5e-05,
238
+ "loss": 1.0787,
239
+ "step": 370
240
+ },
241
+ {
242
+ "epoch": 1.69,
243
+ "learning_rate": 3.3841059602649005e-05,
244
+ "loss": 1.1329,
245
+ "step": 380
246
+ },
247
+ {
248
+ "epoch": 1.74,
249
+ "learning_rate": 3.2682119205298013e-05,
250
+ "loss": 1.1198,
251
+ "step": 390
252
+ },
253
+ {
254
+ "epoch": 1.78,
255
+ "learning_rate": 3.152317880794702e-05,
256
+ "loss": 1.0488,
257
+ "step": 400
258
+ },
259
+ {
260
+ "epoch": 1.83,
261
+ "learning_rate": 3.0364238410596023e-05,
262
+ "loss": 1.0372,
263
+ "step": 410
264
+ },
265
+ {
266
+ "epoch": 1.87,
267
+ "learning_rate": 2.920529801324503e-05,
268
+ "loss": 1.1048,
269
+ "step": 420
270
+ },
271
+ {
272
+ "epoch": 1.92,
273
+ "learning_rate": 2.8046357615894036e-05,
274
+ "loss": 1.0333,
275
+ "step": 430
276
+ },
277
+ {
278
+ "epoch": 1.96,
279
+ "learning_rate": 2.6887417218543045e-05,
280
+ "loss": 1.0262,
281
+ "step": 440
282
+ },
283
+ {
284
+ "epoch": 2.0,
285
+ "eval_accuracy": 0.6611869601560323,
286
+ "eval_loss": 0.908954381942749,
287
+ "eval_runtime": 68.0669,
288
+ "eval_samples_per_second": 105.455,
289
+ "eval_steps_per_second": 3.306,
290
+ "step": 448
291
+ },
292
+ {
293
+ "epoch": 2.01,
294
+ "learning_rate": 2.572847682119205e-05,
295
+ "loss": 1.0595,
296
+ "step": 450
297
+ },
298
+ {
299
+ "epoch": 2.05,
300
+ "learning_rate": 2.4569536423841058e-05,
301
+ "loss": 1.0029,
302
+ "step": 460
303
+ },
304
+ {
305
+ "epoch": 2.1,
306
+ "learning_rate": 2.3410596026490062e-05,
307
+ "loss": 1.0359,
308
+ "step": 470
309
+ },
310
+ {
311
+ "epoch": 2.14,
312
+ "learning_rate": 2.225165562913907e-05,
313
+ "loss": 1.0081,
314
+ "step": 480
315
+ },
316
+ {
317
+ "epoch": 2.19,
318
+ "learning_rate": 2.1092715231788076e-05,
319
+ "loss": 1.0402,
320
+ "step": 490
321
+ },
322
+ {
323
+ "epoch": 2.23,
324
+ "learning_rate": 1.9933774834437084e-05,
325
+ "loss": 0.9973,
326
+ "step": 500
327
+ },
328
+ {
329
+ "epoch": 2.28,
330
+ "learning_rate": 1.877483443708609e-05,
331
+ "loss": 0.994,
332
+ "step": 510
333
+ },
334
+ {
335
+ "epoch": 2.32,
336
+ "learning_rate": 1.7615894039735097e-05,
337
+ "loss": 1.0113,
338
+ "step": 520
339
+ },
340
+ {
341
+ "epoch": 2.37,
342
+ "learning_rate": 1.6456953642384105e-05,
343
+ "loss": 1.03,
344
+ "step": 530
345
+ },
346
+ {
347
+ "epoch": 2.41,
348
+ "learning_rate": 1.529801324503311e-05,
349
+ "loss": 0.9968,
350
+ "step": 540
351
+ },
352
+ {
353
+ "epoch": 2.45,
354
+ "learning_rate": 1.4139072847682118e-05,
355
+ "loss": 0.9676,
356
+ "step": 550
357
+ },
358
+ {
359
+ "epoch": 2.5,
360
+ "learning_rate": 1.2980132450331125e-05,
361
+ "loss": 1.0599,
362
+ "step": 560
363
+ },
364
+ {
365
+ "epoch": 2.54,
366
+ "learning_rate": 1.1821192052980131e-05,
367
+ "loss": 1.0016,
368
+ "step": 570
369
+ },
370
+ {
371
+ "epoch": 2.59,
372
+ "learning_rate": 1.0662251655629138e-05,
373
+ "loss": 1.0137,
374
+ "step": 580
375
+ },
376
+ {
377
+ "epoch": 2.63,
378
+ "learning_rate": 9.503311258278145e-06,
379
+ "loss": 1.0053,
380
+ "step": 590
381
+ },
382
+ {
383
+ "epoch": 2.68,
384
+ "learning_rate": 8.344370860927151e-06,
385
+ "loss": 1.0308,
386
+ "step": 600
387
+ },
388
+ {
389
+ "epoch": 2.72,
390
+ "learning_rate": 7.1854304635761585e-06,
391
+ "loss": 1.0103,
392
+ "step": 610
393
+ },
394
+ {
395
+ "epoch": 2.77,
396
+ "learning_rate": 6.026490066225165e-06,
397
+ "loss": 0.9795,
398
+ "step": 620
399
+ },
400
+ {
401
+ "epoch": 2.81,
402
+ "learning_rate": 4.867549668874172e-06,
403
+ "loss": 0.9804,
404
+ "step": 630
405
+ },
406
+ {
407
+ "epoch": 2.86,
408
+ "learning_rate": 3.7086092715231786e-06,
409
+ "loss": 0.9553,
410
+ "step": 640
411
+ },
412
+ {
413
+ "epoch": 2.9,
414
+ "learning_rate": 2.549668874172185e-06,
415
+ "loss": 0.9442,
416
+ "step": 650
417
+ },
418
+ {
419
+ "epoch": 2.94,
420
+ "learning_rate": 1.390728476821192e-06,
421
+ "loss": 1.0215,
422
+ "step": 660
423
+ },
424
+ {
425
+ "epoch": 2.99,
426
+ "learning_rate": 2.3178807947019866e-07,
427
+ "loss": 0.9666,
428
+ "step": 670
429
+ },
430
+ {
431
+ "epoch": 3.0,
432
+ "eval_accuracy": 0.6862635831707997,
433
+ "eval_loss": 0.8496666550636292,
434
+ "eval_runtime": 64.1194,
435
+ "eval_samples_per_second": 111.947,
436
+ "eval_steps_per_second": 3.509,
437
+ "step": 672
438
+ },
439
+ {
440
+ "epoch": 3.0,
441
+ "step": 672,
442
+ "total_flos": 6.668732964123095e+18,
443
+ "train_loss": 1.1464171437990098,
444
+ "train_runtime": 2129.0691,
445
+ "train_samples_per_second": 40.453,
446
+ "train_steps_per_second": 0.316
447
+ }
448
+ ],
449
+ "max_steps": 672,
450
+ "num_train_epochs": 3,
451
+ "total_flos": 6.668732964123095e+18,
452
+ "trial_name": null,
453
+ "trial_params": null
454
+ }