Axion004 commited on
Commit
d46dcb2
1 Parent(s): d2d8f44

End of training

Browse files
all_results.json ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 3.0,
3
+ "eval_accuracy": 0.9814814814814815,
4
+ "eval_loss": 0.06550158560276031,
5
+ "eval_runtime": 21.4267,
6
+ "eval_samples_per_second": 126.011,
7
+ "eval_steps_per_second": 3.967,
8
+ "total_flos": 1.8124066505760768e+18,
9
+ "train_loss": 0.3264210811832495,
10
+ "train_runtime": 1089.539,
11
+ "train_samples_per_second": 66.909,
12
+ "train_steps_per_second": 0.523
13
+ }
eval_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 3.0,
3
+ "eval_accuracy": 0.9814814814814815,
4
+ "eval_loss": 0.06550158560276031,
5
+ "eval_runtime": 21.4267,
6
+ "eval_samples_per_second": 126.011,
7
+ "eval_steps_per_second": 3.967
8
+ }
runs/Apr05_04-04-57_49636eb3d605/events.out.tfevents.1712291350.49636eb3d605.5313.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2b644e628a912318f01b0fbcd0235f7a2ae3c49775e04feb5f9e8967b55be286
3
+ size 411
train_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 3.0,
3
+ "total_flos": 1.8124066505760768e+18,
4
+ "train_loss": 0.3264210811832495,
5
+ "train_runtime": 1089.539,
6
+ "train_samples_per_second": 66.909,
7
+ "train_steps_per_second": 0.523
8
+ }
trainer_state.json ADDED
@@ -0,0 +1,456 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.9814814814814815,
3
+ "best_model_checkpoint": "swin-tiny-patch4-window7-224-finetuned-eurosat/checkpoint-570",
4
+ "epoch": 3.0,
5
+ "eval_steps": 500,
6
+ "global_step": 570,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.05,
13
+ "grad_norm": 5.7690863609313965,
14
+ "learning_rate": 8.771929824561403e-06,
15
+ "loss": 2.2623,
16
+ "step": 10
17
+ },
18
+ {
19
+ "epoch": 0.11,
20
+ "grad_norm": 7.180535316467285,
21
+ "learning_rate": 1.7543859649122806e-05,
22
+ "loss": 2.0467,
23
+ "step": 20
24
+ },
25
+ {
26
+ "epoch": 0.16,
27
+ "grad_norm": 12.502141952514648,
28
+ "learning_rate": 2.6315789473684212e-05,
29
+ "loss": 1.6134,
30
+ "step": 30
31
+ },
32
+ {
33
+ "epoch": 0.21,
34
+ "grad_norm": 12.182085037231445,
35
+ "learning_rate": 3.508771929824561e-05,
36
+ "loss": 1.0089,
37
+ "step": 40
38
+ },
39
+ {
40
+ "epoch": 0.26,
41
+ "grad_norm": 15.876863479614258,
42
+ "learning_rate": 4.3859649122807014e-05,
43
+ "loss": 0.6195,
44
+ "step": 50
45
+ },
46
+ {
47
+ "epoch": 0.32,
48
+ "grad_norm": 23.71845054626465,
49
+ "learning_rate": 4.970760233918128e-05,
50
+ "loss": 0.5156,
51
+ "step": 60
52
+ },
53
+ {
54
+ "epoch": 0.37,
55
+ "grad_norm": 15.944512367248535,
56
+ "learning_rate": 4.8732943469785574e-05,
57
+ "loss": 0.4736,
58
+ "step": 70
59
+ },
60
+ {
61
+ "epoch": 0.42,
62
+ "grad_norm": 22.624839782714844,
63
+ "learning_rate": 4.7758284600389865e-05,
64
+ "loss": 0.3892,
65
+ "step": 80
66
+ },
67
+ {
68
+ "epoch": 0.47,
69
+ "grad_norm": 13.724577903747559,
70
+ "learning_rate": 4.678362573099415e-05,
71
+ "loss": 0.3564,
72
+ "step": 90
73
+ },
74
+ {
75
+ "epoch": 0.53,
76
+ "grad_norm": 9.811408996582031,
77
+ "learning_rate": 4.580896686159844e-05,
78
+ "loss": 0.3488,
79
+ "step": 100
80
+ },
81
+ {
82
+ "epoch": 0.58,
83
+ "grad_norm": 7.73867654800415,
84
+ "learning_rate": 4.483430799220273e-05,
85
+ "loss": 0.3028,
86
+ "step": 110
87
+ },
88
+ {
89
+ "epoch": 0.63,
90
+ "grad_norm": 14.532332420349121,
91
+ "learning_rate": 4.3859649122807014e-05,
92
+ "loss": 0.2982,
93
+ "step": 120
94
+ },
95
+ {
96
+ "epoch": 0.68,
97
+ "grad_norm": 17.203603744506836,
98
+ "learning_rate": 4.2884990253411305e-05,
99
+ "loss": 0.2659,
100
+ "step": 130
101
+ },
102
+ {
103
+ "epoch": 0.74,
104
+ "grad_norm": 17.189725875854492,
105
+ "learning_rate": 4.1910331384015596e-05,
106
+ "loss": 0.2745,
107
+ "step": 140
108
+ },
109
+ {
110
+ "epoch": 0.79,
111
+ "grad_norm": 12.759488105773926,
112
+ "learning_rate": 4.093567251461988e-05,
113
+ "loss": 0.2586,
114
+ "step": 150
115
+ },
116
+ {
117
+ "epoch": 0.84,
118
+ "grad_norm": 15.634223937988281,
119
+ "learning_rate": 3.996101364522417e-05,
120
+ "loss": 0.2208,
121
+ "step": 160
122
+ },
123
+ {
124
+ "epoch": 0.89,
125
+ "grad_norm": 17.382017135620117,
126
+ "learning_rate": 3.898635477582846e-05,
127
+ "loss": 0.2191,
128
+ "step": 170
129
+ },
130
+ {
131
+ "epoch": 0.95,
132
+ "grad_norm": 23.635671615600586,
133
+ "learning_rate": 3.8011695906432746e-05,
134
+ "loss": 0.2517,
135
+ "step": 180
136
+ },
137
+ {
138
+ "epoch": 1.0,
139
+ "grad_norm": 17.320865631103516,
140
+ "learning_rate": 3.7037037037037037e-05,
141
+ "loss": 0.2747,
142
+ "step": 190
143
+ },
144
+ {
145
+ "epoch": 1.0,
146
+ "eval_accuracy": 0.9562962962962963,
147
+ "eval_loss": 0.13819058239459991,
148
+ "eval_runtime": 17.3473,
149
+ "eval_samples_per_second": 155.644,
150
+ "eval_steps_per_second": 4.9,
151
+ "step": 190
152
+ },
153
+ {
154
+ "epoch": 1.05,
155
+ "grad_norm": 6.783141613006592,
156
+ "learning_rate": 3.606237816764133e-05,
157
+ "loss": 0.1881,
158
+ "step": 200
159
+ },
160
+ {
161
+ "epoch": 1.11,
162
+ "grad_norm": 12.496849060058594,
163
+ "learning_rate": 3.508771929824561e-05,
164
+ "loss": 0.2501,
165
+ "step": 210
166
+ },
167
+ {
168
+ "epoch": 1.16,
169
+ "grad_norm": 11.41723346710205,
170
+ "learning_rate": 3.41130604288499e-05,
171
+ "loss": 0.2282,
172
+ "step": 220
173
+ },
174
+ {
175
+ "epoch": 1.21,
176
+ "grad_norm": 12.789288520812988,
177
+ "learning_rate": 3.313840155945419e-05,
178
+ "loss": 0.2056,
179
+ "step": 230
180
+ },
181
+ {
182
+ "epoch": 1.26,
183
+ "grad_norm": 15.091114044189453,
184
+ "learning_rate": 3.216374269005848e-05,
185
+ "loss": 0.1959,
186
+ "step": 240
187
+ },
188
+ {
189
+ "epoch": 1.32,
190
+ "grad_norm": 13.9872465133667,
191
+ "learning_rate": 3.118908382066277e-05,
192
+ "loss": 0.192,
193
+ "step": 250
194
+ },
195
+ {
196
+ "epoch": 1.37,
197
+ "grad_norm": 12.632612228393555,
198
+ "learning_rate": 3.0214424951267055e-05,
199
+ "loss": 0.2159,
200
+ "step": 260
201
+ },
202
+ {
203
+ "epoch": 1.42,
204
+ "grad_norm": 5.643543243408203,
205
+ "learning_rate": 2.9239766081871346e-05,
206
+ "loss": 0.2369,
207
+ "step": 270
208
+ },
209
+ {
210
+ "epoch": 1.47,
211
+ "grad_norm": 12.24279499053955,
212
+ "learning_rate": 2.8265107212475634e-05,
213
+ "loss": 0.2166,
214
+ "step": 280
215
+ },
216
+ {
217
+ "epoch": 1.53,
218
+ "grad_norm": 9.774775505065918,
219
+ "learning_rate": 2.729044834307992e-05,
220
+ "loss": 0.1558,
221
+ "step": 290
222
+ },
223
+ {
224
+ "epoch": 1.58,
225
+ "grad_norm": 11.163515090942383,
226
+ "learning_rate": 2.6315789473684212e-05,
227
+ "loss": 0.1835,
228
+ "step": 300
229
+ },
230
+ {
231
+ "epoch": 1.63,
232
+ "grad_norm": 15.248787879943848,
233
+ "learning_rate": 2.53411306042885e-05,
234
+ "loss": 0.2193,
235
+ "step": 310
236
+ },
237
+ {
238
+ "epoch": 1.68,
239
+ "grad_norm": 13.8126220703125,
240
+ "learning_rate": 2.4366471734892787e-05,
241
+ "loss": 0.1867,
242
+ "step": 320
243
+ },
244
+ {
245
+ "epoch": 1.74,
246
+ "grad_norm": 5.466386795043945,
247
+ "learning_rate": 2.3391812865497074e-05,
248
+ "loss": 0.1383,
249
+ "step": 330
250
+ },
251
+ {
252
+ "epoch": 1.79,
253
+ "grad_norm": 11.421280860900879,
254
+ "learning_rate": 2.2417153996101365e-05,
255
+ "loss": 0.1611,
256
+ "step": 340
257
+ },
258
+ {
259
+ "epoch": 1.84,
260
+ "grad_norm": 3.8385016918182373,
261
+ "learning_rate": 2.1442495126705653e-05,
262
+ "loss": 0.1518,
263
+ "step": 350
264
+ },
265
+ {
266
+ "epoch": 1.89,
267
+ "grad_norm": 15.16893196105957,
268
+ "learning_rate": 2.046783625730994e-05,
269
+ "loss": 0.198,
270
+ "step": 360
271
+ },
272
+ {
273
+ "epoch": 1.95,
274
+ "grad_norm": 8.695472717285156,
275
+ "learning_rate": 1.949317738791423e-05,
276
+ "loss": 0.1843,
277
+ "step": 370
278
+ },
279
+ {
280
+ "epoch": 2.0,
281
+ "grad_norm": 10.149725914001465,
282
+ "learning_rate": 1.8518518518518518e-05,
283
+ "loss": 0.1928,
284
+ "step": 380
285
+ },
286
+ {
287
+ "epoch": 2.0,
288
+ "eval_accuracy": 0.9714814814814815,
289
+ "eval_loss": 0.09133487939834595,
290
+ "eval_runtime": 17.3865,
291
+ "eval_samples_per_second": 155.293,
292
+ "eval_steps_per_second": 4.889,
293
+ "step": 380
294
+ },
295
+ {
296
+ "epoch": 2.05,
297
+ "grad_norm": 8.00893783569336,
298
+ "learning_rate": 1.7543859649122806e-05,
299
+ "loss": 0.1681,
300
+ "step": 390
301
+ },
302
+ {
303
+ "epoch": 2.11,
304
+ "grad_norm": 16.080177307128906,
305
+ "learning_rate": 1.6569200779727097e-05,
306
+ "loss": 0.1489,
307
+ "step": 400
308
+ },
309
+ {
310
+ "epoch": 2.16,
311
+ "grad_norm": 13.361900329589844,
312
+ "learning_rate": 1.5594541910331384e-05,
313
+ "loss": 0.1362,
314
+ "step": 410
315
+ },
316
+ {
317
+ "epoch": 2.21,
318
+ "grad_norm": 11.800583839416504,
319
+ "learning_rate": 1.4619883040935673e-05,
320
+ "loss": 0.1489,
321
+ "step": 420
322
+ },
323
+ {
324
+ "epoch": 2.26,
325
+ "grad_norm": 13.107502937316895,
326
+ "learning_rate": 1.364522417153996e-05,
327
+ "loss": 0.1813,
328
+ "step": 430
329
+ },
330
+ {
331
+ "epoch": 2.32,
332
+ "grad_norm": 8.709113121032715,
333
+ "learning_rate": 1.267056530214425e-05,
334
+ "loss": 0.1874,
335
+ "step": 440
336
+ },
337
+ {
338
+ "epoch": 2.37,
339
+ "grad_norm": 6.434211730957031,
340
+ "learning_rate": 1.1695906432748537e-05,
341
+ "loss": 0.1782,
342
+ "step": 450
343
+ },
344
+ {
345
+ "epoch": 2.42,
346
+ "grad_norm": 18.821304321289062,
347
+ "learning_rate": 1.0721247563352826e-05,
348
+ "loss": 0.1365,
349
+ "step": 460
350
+ },
351
+ {
352
+ "epoch": 2.47,
353
+ "grad_norm": 5.870109558105469,
354
+ "learning_rate": 9.746588693957115e-06,
355
+ "loss": 0.1518,
356
+ "step": 470
357
+ },
358
+ {
359
+ "epoch": 2.53,
360
+ "grad_norm": 3.519899845123291,
361
+ "learning_rate": 8.771929824561403e-06,
362
+ "loss": 0.139,
363
+ "step": 480
364
+ },
365
+ {
366
+ "epoch": 2.58,
367
+ "grad_norm": 23.94843292236328,
368
+ "learning_rate": 7.797270955165692e-06,
369
+ "loss": 0.1486,
370
+ "step": 490
371
+ },
372
+ {
373
+ "epoch": 2.63,
374
+ "grad_norm": 5.265621185302734,
375
+ "learning_rate": 6.82261208576998e-06,
376
+ "loss": 0.1329,
377
+ "step": 500
378
+ },
379
+ {
380
+ "epoch": 2.68,
381
+ "grad_norm": 4.568530559539795,
382
+ "learning_rate": 5.8479532163742686e-06,
383
+ "loss": 0.1513,
384
+ "step": 510
385
+ },
386
+ {
387
+ "epoch": 2.74,
388
+ "grad_norm": 8.631195068359375,
389
+ "learning_rate": 4.873294346978558e-06,
390
+ "loss": 0.1549,
391
+ "step": 520
392
+ },
393
+ {
394
+ "epoch": 2.79,
395
+ "grad_norm": 6.977248191833496,
396
+ "learning_rate": 3.898635477582846e-06,
397
+ "loss": 0.1465,
398
+ "step": 530
399
+ },
400
+ {
401
+ "epoch": 2.84,
402
+ "grad_norm": 12.340450286865234,
403
+ "learning_rate": 2.9239766081871343e-06,
404
+ "loss": 0.1662,
405
+ "step": 540
406
+ },
407
+ {
408
+ "epoch": 2.89,
409
+ "grad_norm": 6.968770980834961,
410
+ "learning_rate": 1.949317738791423e-06,
411
+ "loss": 0.1449,
412
+ "step": 550
413
+ },
414
+ {
415
+ "epoch": 2.95,
416
+ "grad_norm": 6.5286688804626465,
417
+ "learning_rate": 9.746588693957115e-07,
418
+ "loss": 0.1513,
419
+ "step": 560
420
+ },
421
+ {
422
+ "epoch": 3.0,
423
+ "grad_norm": 9.231646537780762,
424
+ "learning_rate": 0.0,
425
+ "loss": 0.1317,
426
+ "step": 570
427
+ },
428
+ {
429
+ "epoch": 3.0,
430
+ "eval_accuracy": 0.9814814814814815,
431
+ "eval_loss": 0.06550158560276031,
432
+ "eval_runtime": 17.1307,
433
+ "eval_samples_per_second": 157.612,
434
+ "eval_steps_per_second": 4.962,
435
+ "step": 570
436
+ },
437
+ {
438
+ "epoch": 3.0,
439
+ "step": 570,
440
+ "total_flos": 1.8124066505760768e+18,
441
+ "train_loss": 0.3264210811832495,
442
+ "train_runtime": 1089.539,
443
+ "train_samples_per_second": 66.909,
444
+ "train_steps_per_second": 0.523
445
+ }
446
+ ],
447
+ "logging_steps": 10,
448
+ "max_steps": 570,
449
+ "num_input_tokens_seen": 0,
450
+ "num_train_epochs": 3,
451
+ "save_steps": 500,
452
+ "total_flos": 1.8124066505760768e+18,
453
+ "train_batch_size": 32,
454
+ "trial_name": null,
455
+ "trial_params": null
456
+ }