djoels commited on
Commit
c1f4bfa
1 Parent(s): 0e4f763

End of training

Browse files
Files changed (3) hide show
  1. all_results.json +8 -0
  2. train_results.json +8 -0
  3. trainer_state.json +394 -0
all_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 3.0,
3
+ "total_flos": 1.8124066505760768e+18,
4
+ "train_loss": 0.3482265052042509,
5
+ "train_runtime": 1139.0864,
6
+ "train_samples_per_second": 63.999,
7
+ "train_steps_per_second": 0.5
8
+ }
train_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 3.0,
3
+ "total_flos": 1.8124066505760768e+18,
4
+ "train_loss": 0.3482265052042509,
5
+ "train_runtime": 1139.0864,
6
+ "train_samples_per_second": 63.999,
7
+ "train_steps_per_second": 0.5
8
+ }
trainer_state.json ADDED
@@ -0,0 +1,394 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.9829629629629629,
3
+ "best_model_checkpoint": "swin-tiny-patch4-window7-224-finetuned-eurosat/checkpoint-570",
4
+ "epoch": 3.0,
5
+ "global_step": 570,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 0.05,
12
+ "learning_rate": 8.771929824561403e-06,
13
+ "loss": 2.3901,
14
+ "step": 10
15
+ },
16
+ {
17
+ "epoch": 0.11,
18
+ "learning_rate": 1.7543859649122806e-05,
19
+ "loss": 2.1559,
20
+ "step": 20
21
+ },
22
+ {
23
+ "epoch": 0.16,
24
+ "learning_rate": 2.6315789473684212e-05,
25
+ "loss": 1.7444,
26
+ "step": 30
27
+ },
28
+ {
29
+ "epoch": 0.21,
30
+ "learning_rate": 3.508771929824561e-05,
31
+ "loss": 1.0997,
32
+ "step": 40
33
+ },
34
+ {
35
+ "epoch": 0.26,
36
+ "learning_rate": 4.3859649122807014e-05,
37
+ "loss": 0.7129,
38
+ "step": 50
39
+ },
40
+ {
41
+ "epoch": 0.32,
42
+ "learning_rate": 4.970760233918128e-05,
43
+ "loss": 0.5608,
44
+ "step": 60
45
+ },
46
+ {
47
+ "epoch": 0.37,
48
+ "learning_rate": 4.8732943469785574e-05,
49
+ "loss": 0.5319,
50
+ "step": 70
51
+ },
52
+ {
53
+ "epoch": 0.42,
54
+ "learning_rate": 4.7758284600389865e-05,
55
+ "loss": 0.4172,
56
+ "step": 80
57
+ },
58
+ {
59
+ "epoch": 0.47,
60
+ "learning_rate": 4.678362573099415e-05,
61
+ "loss": 0.4157,
62
+ "step": 90
63
+ },
64
+ {
65
+ "epoch": 0.53,
66
+ "learning_rate": 4.580896686159844e-05,
67
+ "loss": 0.3686,
68
+ "step": 100
69
+ },
70
+ {
71
+ "epoch": 0.58,
72
+ "learning_rate": 4.483430799220273e-05,
73
+ "loss": 0.3185,
74
+ "step": 110
75
+ },
76
+ {
77
+ "epoch": 0.63,
78
+ "learning_rate": 4.3859649122807014e-05,
79
+ "loss": 0.3281,
80
+ "step": 120
81
+ },
82
+ {
83
+ "epoch": 0.68,
84
+ "learning_rate": 4.2884990253411305e-05,
85
+ "loss": 0.3118,
86
+ "step": 130
87
+ },
88
+ {
89
+ "epoch": 0.74,
90
+ "learning_rate": 4.1910331384015596e-05,
91
+ "loss": 0.3707,
92
+ "step": 140
93
+ },
94
+ {
95
+ "epoch": 0.79,
96
+ "learning_rate": 4.093567251461988e-05,
97
+ "loss": 0.277,
98
+ "step": 150
99
+ },
100
+ {
101
+ "epoch": 0.84,
102
+ "learning_rate": 3.996101364522417e-05,
103
+ "loss": 0.2955,
104
+ "step": 160
105
+ },
106
+ {
107
+ "epoch": 0.89,
108
+ "learning_rate": 3.898635477582846e-05,
109
+ "loss": 0.2961,
110
+ "step": 170
111
+ },
112
+ {
113
+ "epoch": 0.95,
114
+ "learning_rate": 3.8011695906432746e-05,
115
+ "loss": 0.2457,
116
+ "step": 180
117
+ },
118
+ {
119
+ "epoch": 1.0,
120
+ "learning_rate": 3.7037037037037037e-05,
121
+ "loss": 0.2589,
122
+ "step": 190
123
+ },
124
+ {
125
+ "epoch": 1.0,
126
+ "eval_accuracy": 0.9648148148148148,
127
+ "eval_loss": 0.10355421155691147,
128
+ "eval_runtime": 17.5741,
129
+ "eval_samples_per_second": 153.635,
130
+ "eval_steps_per_second": 4.837,
131
+ "step": 190
132
+ },
133
+ {
134
+ "epoch": 1.05,
135
+ "learning_rate": 3.606237816764133e-05,
136
+ "loss": 0.2515,
137
+ "step": 200
138
+ },
139
+ {
140
+ "epoch": 1.11,
141
+ "learning_rate": 3.508771929824561e-05,
142
+ "loss": 0.2063,
143
+ "step": 210
144
+ },
145
+ {
146
+ "epoch": 1.16,
147
+ "learning_rate": 3.41130604288499e-05,
148
+ "loss": 0.206,
149
+ "step": 220
150
+ },
151
+ {
152
+ "epoch": 1.21,
153
+ "learning_rate": 3.313840155945419e-05,
154
+ "loss": 0.236,
155
+ "step": 230
156
+ },
157
+ {
158
+ "epoch": 1.26,
159
+ "learning_rate": 3.216374269005848e-05,
160
+ "loss": 0.2413,
161
+ "step": 240
162
+ },
163
+ {
164
+ "epoch": 1.32,
165
+ "learning_rate": 3.118908382066277e-05,
166
+ "loss": 0.2199,
167
+ "step": 250
168
+ },
169
+ {
170
+ "epoch": 1.37,
171
+ "learning_rate": 3.0214424951267055e-05,
172
+ "loss": 0.2157,
173
+ "step": 260
174
+ },
175
+ {
176
+ "epoch": 1.42,
177
+ "learning_rate": 2.9239766081871346e-05,
178
+ "loss": 0.1987,
179
+ "step": 270
180
+ },
181
+ {
182
+ "epoch": 1.47,
183
+ "learning_rate": 2.8265107212475634e-05,
184
+ "loss": 0.2209,
185
+ "step": 280
186
+ },
187
+ {
188
+ "epoch": 1.53,
189
+ "learning_rate": 2.729044834307992e-05,
190
+ "loss": 0.1911,
191
+ "step": 290
192
+ },
193
+ {
194
+ "epoch": 1.58,
195
+ "learning_rate": 2.6315789473684212e-05,
196
+ "loss": 0.1676,
197
+ "step": 300
198
+ },
199
+ {
200
+ "epoch": 1.63,
201
+ "learning_rate": 2.53411306042885e-05,
202
+ "loss": 0.2317,
203
+ "step": 310
204
+ },
205
+ {
206
+ "epoch": 1.68,
207
+ "learning_rate": 2.4366471734892787e-05,
208
+ "loss": 0.1638,
209
+ "step": 320
210
+ },
211
+ {
212
+ "epoch": 1.74,
213
+ "learning_rate": 2.3391812865497074e-05,
214
+ "loss": 0.1766,
215
+ "step": 330
216
+ },
217
+ {
218
+ "epoch": 1.79,
219
+ "learning_rate": 2.2417153996101365e-05,
220
+ "loss": 0.1882,
221
+ "step": 340
222
+ },
223
+ {
224
+ "epoch": 1.84,
225
+ "learning_rate": 2.1442495126705653e-05,
226
+ "loss": 0.2007,
227
+ "step": 350
228
+ },
229
+ {
230
+ "epoch": 1.89,
231
+ "learning_rate": 2.046783625730994e-05,
232
+ "loss": 0.1836,
233
+ "step": 360
234
+ },
235
+ {
236
+ "epoch": 1.95,
237
+ "learning_rate": 1.949317738791423e-05,
238
+ "loss": 0.1717,
239
+ "step": 370
240
+ },
241
+ {
242
+ "epoch": 2.0,
243
+ "learning_rate": 1.8518518518518518e-05,
244
+ "loss": 0.1845,
245
+ "step": 380
246
+ },
247
+ {
248
+ "epoch": 2.0,
249
+ "eval_accuracy": 0.9762962962962963,
250
+ "eval_loss": 0.07066227495670319,
251
+ "eval_runtime": 17.4727,
252
+ "eval_samples_per_second": 154.527,
253
+ "eval_steps_per_second": 4.865,
254
+ "step": 380
255
+ },
256
+ {
257
+ "epoch": 2.05,
258
+ "learning_rate": 1.7543859649122806e-05,
259
+ "loss": 0.1687,
260
+ "step": 390
261
+ },
262
+ {
263
+ "epoch": 2.11,
264
+ "learning_rate": 1.6569200779727097e-05,
265
+ "loss": 0.1573,
266
+ "step": 400
267
+ },
268
+ {
269
+ "epoch": 2.16,
270
+ "learning_rate": 1.5594541910331384e-05,
271
+ "loss": 0.1552,
272
+ "step": 410
273
+ },
274
+ {
275
+ "epoch": 2.21,
276
+ "learning_rate": 1.4619883040935673e-05,
277
+ "loss": 0.1699,
278
+ "step": 420
279
+ },
280
+ {
281
+ "epoch": 2.26,
282
+ "learning_rate": 1.364522417153996e-05,
283
+ "loss": 0.1745,
284
+ "step": 430
285
+ },
286
+ {
287
+ "epoch": 2.32,
288
+ "learning_rate": 1.267056530214425e-05,
289
+ "loss": 0.1546,
290
+ "step": 440
291
+ },
292
+ {
293
+ "epoch": 2.37,
294
+ "learning_rate": 1.1695906432748537e-05,
295
+ "loss": 0.1513,
296
+ "step": 450
297
+ },
298
+ {
299
+ "epoch": 2.42,
300
+ "learning_rate": 1.0721247563352826e-05,
301
+ "loss": 0.1512,
302
+ "step": 460
303
+ },
304
+ {
305
+ "epoch": 2.47,
306
+ "learning_rate": 9.746588693957115e-06,
307
+ "loss": 0.1379,
308
+ "step": 470
309
+ },
310
+ {
311
+ "epoch": 2.53,
312
+ "learning_rate": 8.771929824561403e-06,
313
+ "loss": 0.1518,
314
+ "step": 480
315
+ },
316
+ {
317
+ "epoch": 2.58,
318
+ "learning_rate": 7.797270955165692e-06,
319
+ "loss": 0.133,
320
+ "step": 490
321
+ },
322
+ {
323
+ "epoch": 2.63,
324
+ "learning_rate": 6.82261208576998e-06,
325
+ "loss": 0.1998,
326
+ "step": 500
327
+ },
328
+ {
329
+ "epoch": 2.68,
330
+ "learning_rate": 5.8479532163742686e-06,
331
+ "loss": 0.1375,
332
+ "step": 510
333
+ },
334
+ {
335
+ "epoch": 2.74,
336
+ "learning_rate": 4.873294346978558e-06,
337
+ "loss": 0.1833,
338
+ "step": 520
339
+ },
340
+ {
341
+ "epoch": 2.79,
342
+ "learning_rate": 3.898635477582846e-06,
343
+ "loss": 0.1197,
344
+ "step": 530
345
+ },
346
+ {
347
+ "epoch": 2.84,
348
+ "learning_rate": 2.9239766081871343e-06,
349
+ "loss": 0.1408,
350
+ "step": 540
351
+ },
352
+ {
353
+ "epoch": 2.89,
354
+ "learning_rate": 1.949317738791423e-06,
355
+ "loss": 0.1639,
356
+ "step": 550
357
+ },
358
+ {
359
+ "epoch": 2.95,
360
+ "learning_rate": 9.746588693957115e-07,
361
+ "loss": 0.1252,
362
+ "step": 560
363
+ },
364
+ {
365
+ "epoch": 3.0,
366
+ "learning_rate": 0.0,
367
+ "loss": 0.1179,
368
+ "step": 570
369
+ },
370
+ {
371
+ "epoch": 3.0,
372
+ "eval_accuracy": 0.9829629629629629,
373
+ "eval_loss": 0.058953214436769485,
374
+ "eval_runtime": 17.4205,
375
+ "eval_samples_per_second": 154.99,
376
+ "eval_steps_per_second": 4.879,
377
+ "step": 570
378
+ },
379
+ {
380
+ "epoch": 3.0,
381
+ "step": 570,
382
+ "total_flos": 1.8124066505760768e+18,
383
+ "train_loss": 0.3482265052042509,
384
+ "train_runtime": 1139.0864,
385
+ "train_samples_per_second": 63.999,
386
+ "train_steps_per_second": 0.5
387
+ }
388
+ ],
389
+ "max_steps": 570,
390
+ "num_train_epochs": 3,
391
+ "total_flos": 1.8124066505760768e+18,
392
+ "trial_name": null,
393
+ "trial_params": null
394
+ }