matinbaig43 commited on
Commit
f5371f7
·
verified ·
1 Parent(s): 3c1de00

End of training

Browse files
all_results.json ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 1.0,
3
+ "eval_accuracy": 0.9796511627906976,
4
+ "eval_loss": 0.05999711528420448,
5
+ "eval_runtime": 43.4372,
6
+ "eval_samples_per_second": 95.034,
7
+ "eval_steps_per_second": 11.879,
8
+ "total_flos": 5.373364651307827e+17,
9
+ "train_loss": 0.4849770265494206,
10
+ "train_runtime": 814.9685,
11
+ "train_samples_per_second": 20.258,
12
+ "train_steps_per_second": 0.633
13
+ }
eval_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 1.0,
3
+ "eval_accuracy": 0.9796511627906976,
4
+ "eval_loss": 0.05999711528420448,
5
+ "eval_runtime": 43.4372,
6
+ "eval_samples_per_second": 95.034,
7
+ "eval_steps_per_second": 11.879
8
+ }
runs/Nov08_12-12-46_e08e60dcaf10/events.out.tfevents.1731068920.e08e60dcaf10.1221.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0b6cfb985d10377ff0b982408110ff44b75fecc3237f98e76b7f804609897888
3
+ size 411
train_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 1.0,
3
+ "total_flos": 5.373364651307827e+17,
4
+ "train_loss": 0.4849770265494206,
5
+ "train_runtime": 814.9685,
6
+ "train_samples_per_second": 20.258,
7
+ "train_steps_per_second": 0.633
8
+ }
trainer_state.json ADDED
@@ -0,0 +1,408 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.9796511627906976,
3
+ "best_model_checkpoint": "swinv2-tiny-patch4-window16-256-finetuned-plantdisease/checkpoint-516",
4
+ "epoch": 1.0,
5
+ "eval_steps": 500,
6
+ "global_step": 516,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.01937984496124031,
13
+ "grad_norm": 6.976014614105225,
14
+ "learning_rate": 9.615384615384616e-06,
15
+ "loss": 2.6613,
16
+ "step": 10
17
+ },
18
+ {
19
+ "epoch": 0.03875968992248062,
20
+ "grad_norm": 7.513162612915039,
21
+ "learning_rate": 1.923076923076923e-05,
22
+ "loss": 2.5144,
23
+ "step": 20
24
+ },
25
+ {
26
+ "epoch": 0.05813953488372093,
27
+ "grad_norm": 8.978872299194336,
28
+ "learning_rate": 2.8846153846153845e-05,
29
+ "loss": 2.289,
30
+ "step": 30
31
+ },
32
+ {
33
+ "epoch": 0.07751937984496124,
34
+ "grad_norm": 9.438762664794922,
35
+ "learning_rate": 3.846153846153846e-05,
36
+ "loss": 2.0166,
37
+ "step": 40
38
+ },
39
+ {
40
+ "epoch": 0.09689922480620156,
41
+ "grad_norm": 13.305523872375488,
42
+ "learning_rate": 4.8076923076923084e-05,
43
+ "loss": 1.6406,
44
+ "step": 50
45
+ },
46
+ {
47
+ "epoch": 0.11627906976744186,
48
+ "grad_norm": 13.694558143615723,
49
+ "learning_rate": 4.913793103448276e-05,
50
+ "loss": 1.1596,
51
+ "step": 60
52
+ },
53
+ {
54
+ "epoch": 0.13565891472868216,
55
+ "grad_norm": 12.902932167053223,
56
+ "learning_rate": 4.806034482758621e-05,
57
+ "loss": 0.9728,
58
+ "step": 70
59
+ },
60
+ {
61
+ "epoch": 0.15503875968992248,
62
+ "grad_norm": 10.918025016784668,
63
+ "learning_rate": 4.698275862068966e-05,
64
+ "loss": 0.7231,
65
+ "step": 80
66
+ },
67
+ {
68
+ "epoch": 0.1744186046511628,
69
+ "grad_norm": 11.306808471679688,
70
+ "learning_rate": 4.590517241379311e-05,
71
+ "loss": 0.6395,
72
+ "step": 90
73
+ },
74
+ {
75
+ "epoch": 0.1937984496124031,
76
+ "grad_norm": 33.67359924316406,
77
+ "learning_rate": 4.482758620689655e-05,
78
+ "loss": 0.6615,
79
+ "step": 100
80
+ },
81
+ {
82
+ "epoch": 0.2131782945736434,
83
+ "grad_norm": 10.94041919708252,
84
+ "learning_rate": 4.375e-05,
85
+ "loss": 0.5263,
86
+ "step": 110
87
+ },
88
+ {
89
+ "epoch": 0.23255813953488372,
90
+ "grad_norm": 10.666516304016113,
91
+ "learning_rate": 4.267241379310345e-05,
92
+ "loss": 0.4751,
93
+ "step": 120
94
+ },
95
+ {
96
+ "epoch": 0.25193798449612403,
97
+ "grad_norm": 10.321724891662598,
98
+ "learning_rate": 4.1594827586206896e-05,
99
+ "loss": 0.4072,
100
+ "step": 130
101
+ },
102
+ {
103
+ "epoch": 0.2713178294573643,
104
+ "grad_norm": 11.352335929870605,
105
+ "learning_rate": 4.0517241379310344e-05,
106
+ "loss": 0.3549,
107
+ "step": 140
108
+ },
109
+ {
110
+ "epoch": 0.29069767441860467,
111
+ "grad_norm": 13.436570167541504,
112
+ "learning_rate": 3.94396551724138e-05,
113
+ "loss": 0.3766,
114
+ "step": 150
115
+ },
116
+ {
117
+ "epoch": 0.31007751937984496,
118
+ "grad_norm": 9.901206016540527,
119
+ "learning_rate": 3.8362068965517246e-05,
120
+ "loss": 0.3293,
121
+ "step": 160
122
+ },
123
+ {
124
+ "epoch": 0.32945736434108525,
125
+ "grad_norm": 7.431344985961914,
126
+ "learning_rate": 3.7284482758620694e-05,
127
+ "loss": 0.3218,
128
+ "step": 170
129
+ },
130
+ {
131
+ "epoch": 0.3488372093023256,
132
+ "grad_norm": 11.188233375549316,
133
+ "learning_rate": 3.620689655172414e-05,
134
+ "loss": 0.2562,
135
+ "step": 180
136
+ },
137
+ {
138
+ "epoch": 0.3682170542635659,
139
+ "grad_norm": 28.794321060180664,
140
+ "learning_rate": 3.512931034482759e-05,
141
+ "loss": 0.3317,
142
+ "step": 190
143
+ },
144
+ {
145
+ "epoch": 0.3875968992248062,
146
+ "grad_norm": 12.812822341918945,
147
+ "learning_rate": 3.405172413793103e-05,
148
+ "loss": 0.333,
149
+ "step": 200
150
+ },
151
+ {
152
+ "epoch": 0.4069767441860465,
153
+ "grad_norm": 15.580060958862305,
154
+ "learning_rate": 3.297413793103448e-05,
155
+ "loss": 0.3234,
156
+ "step": 210
157
+ },
158
+ {
159
+ "epoch": 0.4263565891472868,
160
+ "grad_norm": 13.454980850219727,
161
+ "learning_rate": 3.1896551724137935e-05,
162
+ "loss": 0.2975,
163
+ "step": 220
164
+ },
165
+ {
166
+ "epoch": 0.44573643410852715,
167
+ "grad_norm": 10.901363372802734,
168
+ "learning_rate": 3.081896551724138e-05,
169
+ "loss": 0.2117,
170
+ "step": 230
171
+ },
172
+ {
173
+ "epoch": 0.46511627906976744,
174
+ "grad_norm": 4.9573493003845215,
175
+ "learning_rate": 2.974137931034483e-05,
176
+ "loss": 0.1921,
177
+ "step": 240
178
+ },
179
+ {
180
+ "epoch": 0.4844961240310077,
181
+ "grad_norm": 10.217713356018066,
182
+ "learning_rate": 2.866379310344828e-05,
183
+ "loss": 0.1963,
184
+ "step": 250
185
+ },
186
+ {
187
+ "epoch": 0.5038759689922481,
188
+ "grad_norm": 11.932710647583008,
189
+ "learning_rate": 2.7586206896551727e-05,
190
+ "loss": 0.2642,
191
+ "step": 260
192
+ },
193
+ {
194
+ "epoch": 0.5232558139534884,
195
+ "grad_norm": 61.47119140625,
196
+ "learning_rate": 2.650862068965517e-05,
197
+ "loss": 0.2581,
198
+ "step": 270
199
+ },
200
+ {
201
+ "epoch": 0.5426356589147286,
202
+ "grad_norm": 14.920116424560547,
203
+ "learning_rate": 2.543103448275862e-05,
204
+ "loss": 0.2522,
205
+ "step": 280
206
+ },
207
+ {
208
+ "epoch": 0.562015503875969,
209
+ "grad_norm": 9.092141151428223,
210
+ "learning_rate": 2.435344827586207e-05,
211
+ "loss": 0.2536,
212
+ "step": 290
213
+ },
214
+ {
215
+ "epoch": 0.5813953488372093,
216
+ "grad_norm": 9.711197853088379,
217
+ "learning_rate": 2.327586206896552e-05,
218
+ "loss": 0.1451,
219
+ "step": 300
220
+ },
221
+ {
222
+ "epoch": 0.6007751937984496,
223
+ "grad_norm": 16.53685760498047,
224
+ "learning_rate": 2.2198275862068967e-05,
225
+ "loss": 0.19,
226
+ "step": 310
227
+ },
228
+ {
229
+ "epoch": 0.6201550387596899,
230
+ "grad_norm": 13.619780540466309,
231
+ "learning_rate": 2.1120689655172415e-05,
232
+ "loss": 0.1973,
233
+ "step": 320
234
+ },
235
+ {
236
+ "epoch": 0.6395348837209303,
237
+ "grad_norm": 14.635655403137207,
238
+ "learning_rate": 2.0043103448275863e-05,
239
+ "loss": 0.2135,
240
+ "step": 330
241
+ },
242
+ {
243
+ "epoch": 0.6589147286821705,
244
+ "grad_norm": 10.346831321716309,
245
+ "learning_rate": 1.896551724137931e-05,
246
+ "loss": 0.1712,
247
+ "step": 340
248
+ },
249
+ {
250
+ "epoch": 0.6782945736434108,
251
+ "grad_norm": 3.3771607875823975,
252
+ "learning_rate": 1.7887931034482762e-05,
253
+ "loss": 0.2015,
254
+ "step": 350
255
+ },
256
+ {
257
+ "epoch": 0.6976744186046512,
258
+ "grad_norm": 9.400130271911621,
259
+ "learning_rate": 1.6810344827586207e-05,
260
+ "loss": 0.2124,
261
+ "step": 360
262
+ },
263
+ {
264
+ "epoch": 0.7170542635658915,
265
+ "grad_norm": 6.391541957855225,
266
+ "learning_rate": 1.5732758620689655e-05,
267
+ "loss": 0.1983,
268
+ "step": 370
269
+ },
270
+ {
271
+ "epoch": 0.7364341085271318,
272
+ "grad_norm": 12.541404724121094,
273
+ "learning_rate": 1.4655172413793103e-05,
274
+ "loss": 0.1571,
275
+ "step": 380
276
+ },
277
+ {
278
+ "epoch": 0.7558139534883721,
279
+ "grad_norm": 12.3185396194458,
280
+ "learning_rate": 1.3577586206896553e-05,
281
+ "loss": 0.1778,
282
+ "step": 390
283
+ },
284
+ {
285
+ "epoch": 0.7751937984496124,
286
+ "grad_norm": 12.450446128845215,
287
+ "learning_rate": 1.25e-05,
288
+ "loss": 0.137,
289
+ "step": 400
290
+ },
291
+ {
292
+ "epoch": 0.7945736434108527,
293
+ "grad_norm": 3.400618314743042,
294
+ "learning_rate": 1.1422413793103449e-05,
295
+ "loss": 0.149,
296
+ "step": 410
297
+ },
298
+ {
299
+ "epoch": 0.813953488372093,
300
+ "grad_norm": 3.4296200275421143,
301
+ "learning_rate": 1.0344827586206897e-05,
302
+ "loss": 0.1692,
303
+ "step": 420
304
+ },
305
+ {
306
+ "epoch": 0.8333333333333334,
307
+ "grad_norm": 8.436596870422363,
308
+ "learning_rate": 9.267241379310346e-06,
309
+ "loss": 0.1282,
310
+ "step": 430
311
+ },
312
+ {
313
+ "epoch": 0.8527131782945736,
314
+ "grad_norm": 13.49636459350586,
315
+ "learning_rate": 8.189655172413793e-06,
316
+ "loss": 0.2076,
317
+ "step": 440
318
+ },
319
+ {
320
+ "epoch": 0.872093023255814,
321
+ "grad_norm": 12.991996765136719,
322
+ "learning_rate": 7.112068965517242e-06,
323
+ "loss": 0.1375,
324
+ "step": 450
325
+ },
326
+ {
327
+ "epoch": 0.8914728682170543,
328
+ "grad_norm": 8.396629333496094,
329
+ "learning_rate": 6.03448275862069e-06,
330
+ "loss": 0.1238,
331
+ "step": 460
332
+ },
333
+ {
334
+ "epoch": 0.9108527131782945,
335
+ "grad_norm": 10.368714332580566,
336
+ "learning_rate": 4.9568965517241384e-06,
337
+ "loss": 0.1866,
338
+ "step": 470
339
+ },
340
+ {
341
+ "epoch": 0.9302325581395349,
342
+ "grad_norm": 10.175681114196777,
343
+ "learning_rate": 3.8793103448275865e-06,
344
+ "loss": 0.1286,
345
+ "step": 480
346
+ },
347
+ {
348
+ "epoch": 0.9496124031007752,
349
+ "grad_norm": 10.659682273864746,
350
+ "learning_rate": 2.8017241379310345e-06,
351
+ "loss": 0.1754,
352
+ "step": 490
353
+ },
354
+ {
355
+ "epoch": 0.9689922480620154,
356
+ "grad_norm": 8.461567878723145,
357
+ "learning_rate": 1.724137931034483e-06,
358
+ "loss": 0.1282,
359
+ "step": 500
360
+ },
361
+ {
362
+ "epoch": 0.9883720930232558,
363
+ "grad_norm": 12.434035301208496,
364
+ "learning_rate": 6.46551724137931e-07,
365
+ "loss": 0.1394,
366
+ "step": 510
367
+ },
368
+ {
369
+ "epoch": 1.0,
370
+ "eval_accuracy": 0.9796511627906976,
371
+ "eval_loss": 0.05999711528420448,
372
+ "eval_runtime": 43.7399,
373
+ "eval_samples_per_second": 94.376,
374
+ "eval_steps_per_second": 11.797,
375
+ "step": 516
376
+ },
377
+ {
378
+ "epoch": 1.0,
379
+ "step": 516,
380
+ "total_flos": 5.373364651307827e+17,
381
+ "train_loss": 0.4849770265494206,
382
+ "train_runtime": 814.9685,
383
+ "train_samples_per_second": 20.258,
384
+ "train_steps_per_second": 0.633
385
+ }
386
+ ],
387
+ "logging_steps": 10,
388
+ "max_steps": 516,
389
+ "num_input_tokens_seen": 0,
390
+ "num_train_epochs": 1,
391
+ "save_steps": 500,
392
+ "stateful_callbacks": {
393
+ "TrainerControl": {
394
+ "args": {
395
+ "should_epoch_stop": false,
396
+ "should_evaluate": false,
397
+ "should_log": false,
398
+ "should_save": true,
399
+ "should_training_stop": true
400
+ },
401
+ "attributes": {}
402
+ }
403
+ },
404
+ "total_flos": 5.373364651307827e+17,
405
+ "train_batch_size": 8,
406
+ "trial_name": null,
407
+ "trial_params": null
408
+ }