Hugging Face's logo

Naterea
/
yt_noyt_V2_MoreData_3-0

Image Classification
Transformers
Safetensors
resnet
Trained with AutoTrain
Inference Endpoints
Model card Files Community
Naterea commited on
Commit
71ef540
•
1 Parent(s): 3f361fb

Upload folder using huggingface_hub

Browse files
Files changed (34) hide show
  1. README.md +32 -0
  2. checkpoint-114/config.json +50 -0
  3. checkpoint-114/model.safetensors +3 -0
  4. checkpoint-114/optimizer.pt +3 -0
  5. checkpoint-114/rng_state.pth +3 -0
  6. checkpoint-114/scheduler.pt +3 -0
  7. checkpoint-114/trainer_state.json +744 -0
  8. checkpoint-114/training_args.bin +3 -0
  9. checkpoint-152/config.json +50 -0
  10. checkpoint-152/model.safetensors +3 -0
  11. checkpoint-152/optimizer.pt +3 -0
  12. checkpoint-152/rng_state.pth +3 -0
  13. checkpoint-152/scheduler.pt +3 -0
  14. checkpoint-152/trainer_state.json +985 -0
  15. checkpoint-152/training_args.bin +3 -0
  16. checkpoint-38/config.json +50 -0
  17. checkpoint-38/model.safetensors +3 -0
  18. checkpoint-38/optimizer.pt +3 -0
  19. checkpoint-38/rng_state.pth +3 -0
  20. checkpoint-38/scheduler.pt +3 -0
  21. checkpoint-38/trainer_state.json +262 -0
  22. checkpoint-38/training_args.bin +3 -0
  23. checkpoint-76/config.json +50 -0
  24. checkpoint-76/model.safetensors +3 -0
  25. checkpoint-76/optimizer.pt +3 -0
  26. checkpoint-76/rng_state.pth +3 -0
  27. checkpoint-76/scheduler.pt +3 -0
  28. checkpoint-76/trainer_state.json +503 -0
  29. checkpoint-76/training_args.bin +3 -0
  30. config.json +50 -0
  31. model.safetensors +3 -0
  32. preprocessor_config.json +22 -0
  33. training_args.bin +3 -0
  34. training_params.json +28 -0
README.md ADDED
@@ -0,0 +1,32 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+
2
+ ---
3
+ tags:
4
+ - autotrain
5
+ - image-classification
6
+ widget:
7
+ - src: https://huggingface.co/datasets/mishig/sample_images/resolve/main/tiger.jpg
8
+ example_title: Tiger
9
+ - src: https://huggingface.co/datasets/mishig/sample_images/resolve/main/teapot.jpg
10
+ example_title: Teapot
11
+ - src: https://huggingface.co/datasets/mishig/sample_images/resolve/main/palace.jpg
12
+ example_title: Palace
13
+ datasets:
14
+ - Naterea/autotrain-data-yt_noyt_V2_MoreData_3
15
+ ---
16
+
17
+ # Model Trained Using AutoTrain
18
+
19
+ - Problem type: Image Classification
20
+
21
+ ## Validation Metricsg
22
+ loss: 0.509366512298584
23
+
24
+ f1: 0.0
25
+
26
+ precision: 0.0
27
+
28
+ recall: 0.0
29
+
30
+ auc: 1.0
31
+
32
+ accuracy: 0.6052631578947368
checkpoint-114/config.json ADDED
@@ -0,0 +1,50 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "microsoft/resnet-50",
3
+ "_num_labels": 2,
4
+ "architectures": [
5
+ "ResNetForImageClassification"
6
+ ],
7
+ "depths": [
8
+ 3,
9
+ 4,
10
+ 6,
11
+ 3
12
+ ],
13
+ "downsample_in_bottleneck": false,
14
+ "downsample_in_first_stage": false,
15
+ "embedding_size": 64,
16
+ "hidden_act": "relu",
17
+ "hidden_sizes": [
18
+ 256,
19
+ 512,
20
+ 1024,
21
+ 2048
22
+ ],
23
+ "id2label": {
24
+ "0": "noyt",
25
+ "1": "yt"
26
+ },
27
+ "label2id": {
28
+ "noyt": 0,
29
+ "yt": 1
30
+ },
31
+ "layer_type": "bottleneck",
32
+ "model_type": "resnet",
33
+ "num_channels": 3,
34
+ "out_features": [
35
+ "stage4"
36
+ ],
37
+ "out_indices": [
38
+ 4
39
+ ],
40
+ "problem_type": "single_label_classification",
41
+ "stage_names": [
42
+ "stem",
43
+ "stage1",
44
+ "stage2",
45
+ "stage3",
46
+ "stage4"
47
+ ],
48
+ "torch_dtype": "float32",
49
+ "transformers_version": "4.36.1"
50
+ }
checkpoint-114/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:37f73e7cc2393e66829774bc7539afab3633582ae5a14cc2739a82487fdcc004
3
+ size 94302952
checkpoint-114/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fdbe510a4b559eec2f7d98dc3bf1b06dd3a0e5898296535d46a87e618949dc67
3
+ size 188228026
checkpoint-114/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fb9edf2496ab7eb26880a14e8d66bb836aaa687060eb097f7d18ce2854dfca40
3
+ size 13990
checkpoint-114/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a865407f583e7d4d6f6c130624fdb3e307be2aeb22bd2175c3a6a90670f6a727
3
+ size 1064
checkpoint-114/trainer_state.json ADDED
@@ -0,0 +1,744 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.513079047203064,
3
+ "best_model_checkpoint": "/tmp/model/checkpoint-114",
4
+ "epoch": 3.0,
5
+ "eval_steps": 500,
6
+ "global_step": 114,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.03,
13
+ "learning_rate": 3.2e-06,
14
+ "loss": 0.6931,
15
+ "step": 1
16
+ },
17
+ {
18
+ "epoch": 0.05,
19
+ "learning_rate": 6.4e-06,
20
+ "loss": 0.6931,
21
+ "step": 2
22
+ },
23
+ {
24
+ "epoch": 0.08,
25
+ "learning_rate": 9.6e-06,
26
+ "loss": 0.6931,
27
+ "step": 3
28
+ },
29
+ {
30
+ "epoch": 0.11,
31
+ "learning_rate": 1.28e-05,
32
+ "loss": 0.693,
33
+ "step": 4
34
+ },
35
+ {
36
+ "epoch": 0.13,
37
+ "learning_rate": 1.6e-05,
38
+ "loss": 0.6929,
39
+ "step": 5
40
+ },
41
+ {
42
+ "epoch": 0.16,
43
+ "learning_rate": 1.92e-05,
44
+ "loss": 0.6927,
45
+ "step": 6
46
+ },
47
+ {
48
+ "epoch": 0.18,
49
+ "learning_rate": 2.24e-05,
50
+ "loss": 0.6921,
51
+ "step": 7
52
+ },
53
+ {
54
+ "epoch": 0.21,
55
+ "learning_rate": 2.56e-05,
56
+ "loss": 0.6916,
57
+ "step": 8
58
+ },
59
+ {
60
+ "epoch": 0.24,
61
+ "learning_rate": 2.88e-05,
62
+ "loss": 0.6903,
63
+ "step": 9
64
+ },
65
+ {
66
+ "epoch": 0.26,
67
+ "learning_rate": 3.2e-05,
68
+ "loss": 0.692,
69
+ "step": 10
70
+ },
71
+ {
72
+ "epoch": 0.29,
73
+ "learning_rate": 3.52e-05,
74
+ "loss": 0.6883,
75
+ "step": 11
76
+ },
77
+ {
78
+ "epoch": 0.32,
79
+ "learning_rate": 3.84e-05,
80
+ "loss": 0.6922,
81
+ "step": 12
82
+ },
83
+ {
84
+ "epoch": 0.34,
85
+ "learning_rate": 4.1599999999999995e-05,
86
+ "loss": 0.6872,
87
+ "step": 13
88
+ },
89
+ {
90
+ "epoch": 0.37,
91
+ "learning_rate": 4.48e-05,
92
+ "loss": 0.6915,
93
+ "step": 14
94
+ },
95
+ {
96
+ "epoch": 0.39,
97
+ "learning_rate": 4.8e-05,
98
+ "loss": 0.6924,
99
+ "step": 15
100
+ },
101
+ {
102
+ "epoch": 0.42,
103
+ "learning_rate": 5.12e-05,
104
+ "loss": 0.6924,
105
+ "step": 16
106
+ },
107
+ {
108
+ "epoch": 0.45,
109
+ "learning_rate": 5.08235294117647e-05,
110
+ "loss": 0.6804,
111
+ "step": 17
112
+ },
113
+ {
114
+ "epoch": 0.47,
115
+ "learning_rate": 5.0447058823529415e-05,
116
+ "loss": 0.6788,
117
+ "step": 18
118
+ },
119
+ {
120
+ "epoch": 0.5,
121
+ "learning_rate": 5.007058823529411e-05,
122
+ "loss": 0.6869,
123
+ "step": 19
124
+ },
125
+ {
126
+ "epoch": 0.53,
127
+ "learning_rate": 4.969411764705882e-05,
128
+ "loss": 0.681,
129
+ "step": 20
130
+ },
131
+ {
132
+ "epoch": 0.55,
133
+ "learning_rate": 4.931764705882353e-05,
134
+ "loss": 0.6895,
135
+ "step": 21
136
+ },
137
+ {
138
+ "epoch": 0.58,
139
+ "learning_rate": 4.8941176470588235e-05,
140
+ "loss": 0.6844,
141
+ "step": 22
142
+ },
143
+ {
144
+ "epoch": 0.61,
145
+ "learning_rate": 4.856470588235294e-05,
146
+ "loss": 0.6761,
147
+ "step": 23
148
+ },
149
+ {
150
+ "epoch": 0.63,
151
+ "learning_rate": 4.8188235294117645e-05,
152
+ "loss": 0.6691,
153
+ "step": 24
154
+ },
155
+ {
156
+ "epoch": 0.66,
157
+ "learning_rate": 4.781176470588235e-05,
158
+ "loss": 0.6717,
159
+ "step": 25
160
+ },
161
+ {
162
+ "epoch": 0.68,
163
+ "learning_rate": 4.7435294117647055e-05,
164
+ "loss": 0.6752,
165
+ "step": 26
166
+ },
167
+ {
168
+ "epoch": 0.71,
169
+ "learning_rate": 4.705882352941176e-05,
170
+ "loss": 0.6837,
171
+ "step": 27
172
+ },
173
+ {
174
+ "epoch": 0.74,
175
+ "learning_rate": 4.6682352941176466e-05,
176
+ "loss": 0.6834,
177
+ "step": 28
178
+ },
179
+ {
180
+ "epoch": 0.76,
181
+ "learning_rate": 4.630588235294118e-05,
182
+ "loss": 0.6646,
183
+ "step": 29
184
+ },
185
+ {
186
+ "epoch": 0.79,
187
+ "learning_rate": 4.592941176470588e-05,
188
+ "loss": 0.6719,
189
+ "step": 30
190
+ },
191
+ {
192
+ "epoch": 0.82,
193
+ "learning_rate": 4.555294117647058e-05,
194
+ "loss": 0.667,
195
+ "step": 31
196
+ },
197
+ {
198
+ "epoch": 0.84,
199
+ "learning_rate": 4.517647058823529e-05,
200
+ "loss": 0.6774,
201
+ "step": 32
202
+ },
203
+ {
204
+ "epoch": 0.87,
205
+ "learning_rate": 4.48e-05,
206
+ "loss": 0.678,
207
+ "step": 33
208
+ },
209
+ {
210
+ "epoch": 0.89,
211
+ "learning_rate": 4.44235294117647e-05,
212
+ "loss": 0.6657,
213
+ "step": 34
214
+ },
215
+ {
216
+ "epoch": 0.92,
217
+ "learning_rate": 4.4047058823529415e-05,
218
+ "loss": 0.6539,
219
+ "step": 35
220
+ },
221
+ {
222
+ "epoch": 0.95,
223
+ "learning_rate": 4.367058823529411e-05,
224
+ "loss": 0.662,
225
+ "step": 36
226
+ },
227
+ {
228
+ "epoch": 0.97,
229
+ "learning_rate": 4.329411764705882e-05,
230
+ "loss": 0.7082,
231
+ "step": 37
232
+ },
233
+ {
234
+ "epoch": 1.0,
235
+ "learning_rate": 4.291764705882353e-05,
236
+ "loss": 0.6554,
237
+ "step": 38
238
+ },
239
+ {
240
+ "epoch": 1.0,
241
+ "eval_accuracy": 0.6052631578947368,
242
+ "eval_auc": 0.9916264090177134,
243
+ "eval_f1": 0.0,
244
+ "eval_loss": 0.665397047996521,
245
+ "eval_precision": 0.0,
246
+ "eval_recall": 0.0,
247
+ "eval_runtime": 14.6602,
248
+ "eval_samples_per_second": 7.776,
249
+ "eval_steps_per_second": 0.341,
250
+ "step": 38
251
+ },
252
+ {
253
+ "epoch": 1.03,
254
+ "learning_rate": 4.2541176470588235e-05,
255
+ "loss": 0.638,
256
+ "step": 39
257
+ },
258
+ {
259
+ "epoch": 1.05,
260
+ "learning_rate": 4.216470588235294e-05,
261
+ "loss": 0.6432,
262
+ "step": 40
263
+ },
264
+ {
265
+ "epoch": 1.08,
266
+ "learning_rate": 4.1788235294117646e-05,
267
+ "loss": 0.6896,
268
+ "step": 41
269
+ },
270
+ {
271
+ "epoch": 1.11,
272
+ "learning_rate": 4.141176470588235e-05,
273
+ "loss": 0.677,
274
+ "step": 42
275
+ },
276
+ {
277
+ "epoch": 1.13,
278
+ "learning_rate": 4.1035294117647056e-05,
279
+ "loss": 0.6312,
280
+ "step": 43
281
+ },
282
+ {
283
+ "epoch": 1.16,
284
+ "learning_rate": 4.065882352941176e-05,
285
+ "loss": 0.637,
286
+ "step": 44
287
+ },
288
+ {
289
+ "epoch": 1.18,
290
+ "learning_rate": 4.0282352941176466e-05,
291
+ "loss": 0.6274,
292
+ "step": 45
293
+ },
294
+ {
295
+ "epoch": 1.21,
296
+ "learning_rate": 3.990588235294118e-05,
297
+ "loss": 0.6335,
298
+ "step": 46
299
+ },
300
+ {
301
+ "epoch": 1.24,
302
+ "learning_rate": 3.952941176470588e-05,
303
+ "loss": 0.6302,
304
+ "step": 47
305
+ },
306
+ {
307
+ "epoch": 1.26,
308
+ "learning_rate": 3.915294117647058e-05,
309
+ "loss": 0.6223,
310
+ "step": 48
311
+ },
312
+ {
313
+ "epoch": 1.29,
314
+ "learning_rate": 3.877647058823529e-05,
315
+ "loss": 0.668,
316
+ "step": 49
317
+ },
318
+ {
319
+ "epoch": 1.32,
320
+ "learning_rate": 3.84e-05,
321
+ "loss": 0.6216,
322
+ "step": 50
323
+ },
324
+ {
325
+ "epoch": 1.34,
326
+ "learning_rate": 3.80235294117647e-05,
327
+ "loss": 0.6518,
328
+ "step": 51
329
+ },
330
+ {
331
+ "epoch": 1.37,
332
+ "learning_rate": 3.7647058823529415e-05,
333
+ "loss": 0.6599,
334
+ "step": 52
335
+ },
336
+ {
337
+ "epoch": 1.39,
338
+ "learning_rate": 3.7270588235294114e-05,
339
+ "loss": 0.6562,
340
+ "step": 53
341
+ },
342
+ {
343
+ "epoch": 1.42,
344
+ "learning_rate": 3.689411764705882e-05,
345
+ "loss": 0.6329,
346
+ "step": 54
347
+ },
348
+ {
349
+ "epoch": 1.45,
350
+ "learning_rate": 3.651764705882353e-05,
351
+ "loss": 0.6358,
352
+ "step": 55
353
+ },
354
+ {
355
+ "epoch": 1.47,
356
+ "learning_rate": 3.6141176470588236e-05,
357
+ "loss": 0.6074,
358
+ "step": 56
359
+ },
360
+ {
361
+ "epoch": 1.5,
362
+ "learning_rate": 3.576470588235294e-05,
363
+ "loss": 0.6036,
364
+ "step": 57
365
+ },
366
+ {
367
+ "epoch": 1.53,
368
+ "learning_rate": 3.5388235294117646e-05,
369
+ "loss": 0.6039,
370
+ "step": 58
371
+ },
372
+ {
373
+ "epoch": 1.55,
374
+ "learning_rate": 3.501176470588235e-05,
375
+ "loss": 0.6243,
376
+ "step": 59
377
+ },
378
+ {
379
+ "epoch": 1.58,
380
+ "learning_rate": 3.4635294117647056e-05,
381
+ "loss": 0.6479,
382
+ "step": 60
383
+ },
384
+ {
385
+ "epoch": 1.61,
386
+ "learning_rate": 3.425882352941176e-05,
387
+ "loss": 0.6312,
388
+ "step": 61
389
+ },
390
+ {
391
+ "epoch": 1.63,
392
+ "learning_rate": 3.3882352941176466e-05,
393
+ "loss": 0.6259,
394
+ "step": 62
395
+ },
396
+ {
397
+ "epoch": 1.66,
398
+ "learning_rate": 3.350588235294118e-05,
399
+ "loss": 0.6058,
400
+ "step": 63
401
+ },
402
+ {
403
+ "epoch": 1.68,
404
+ "learning_rate": 3.312941176470588e-05,
405
+ "loss": 0.5793,
406
+ "step": 64
407
+ },
408
+ {
409
+ "epoch": 1.71,
410
+ "learning_rate": 3.275294117647058e-05,
411
+ "loss": 0.6781,
412
+ "step": 65
413
+ },
414
+ {
415
+ "epoch": 1.74,
416
+ "learning_rate": 3.2376470588235293e-05,
417
+ "loss": 0.599,
418
+ "step": 66
419
+ },
420
+ {
421
+ "epoch": 1.76,
422
+ "learning_rate": 3.2e-05,
423
+ "loss": 0.5805,
424
+ "step": 67
425
+ },
426
+ {
427
+ "epoch": 1.79,
428
+ "learning_rate": 3.1623529411764704e-05,
429
+ "loss": 0.5873,
430
+ "step": 68
431
+ },
432
+ {
433
+ "epoch": 1.82,
434
+ "learning_rate": 3.1247058823529416e-05,
435
+ "loss": 0.6044,
436
+ "step": 69
437
+ },
438
+ {
439
+ "epoch": 1.84,
440
+ "learning_rate": 3.0870588235294114e-05,
441
+ "loss": 0.5808,
442
+ "step": 70
443
+ },
444
+ {
445
+ "epoch": 1.87,
446
+ "learning_rate": 3.0494117647058822e-05,
447
+ "loss": 0.5655,
448
+ "step": 71
449
+ },
450
+ {
451
+ "epoch": 1.89,
452
+ "learning_rate": 3.0117647058823527e-05,
453
+ "loss": 0.5661,
454
+ "step": 72
455
+ },
456
+ {
457
+ "epoch": 1.92,
458
+ "learning_rate": 2.9741176470588236e-05,
459
+ "loss": 0.6197,
460
+ "step": 73
461
+ },
462
+ {
463
+ "epoch": 1.95,
464
+ "learning_rate": 2.9364705882352938e-05,
465
+ "loss": 0.6197,
466
+ "step": 74
467
+ },
468
+ {
469
+ "epoch": 1.97,
470
+ "learning_rate": 2.8988235294117646e-05,
471
+ "loss": 0.6297,
472
+ "step": 75
473
+ },
474
+ {
475
+ "epoch": 2.0,
476
+ "learning_rate": 2.861176470588235e-05,
477
+ "loss": 0.5994,
478
+ "step": 76
479
+ },
480
+ {
481
+ "epoch": 2.0,
482
+ "eval_accuracy": 0.6052631578947368,
483
+ "eval_auc": 1.0,
484
+ "eval_f1": 0.0,
485
+ "eval_loss": 0.6067062616348267,
486
+ "eval_precision": 0.0,
487
+ "eval_recall": 0.0,
488
+ "eval_runtime": 17.1278,
489
+ "eval_samples_per_second": 6.656,
490
+ "eval_steps_per_second": 0.292,
491
+ "step": 76
492
+ },
493
+ {
494
+ "epoch": 2.03,
495
+ "learning_rate": 2.823529411764706e-05,
496
+ "loss": 0.5467,
497
+ "step": 77
498
+ },
499
+ {
500
+ "epoch": 2.05,
501
+ "learning_rate": 2.785882352941176e-05,
502
+ "loss": 0.6236,
503
+ "step": 78
504
+ },
505
+ {
506
+ "epoch": 2.08,
507
+ "learning_rate": 2.748235294117647e-05,
508
+ "loss": 0.5555,
509
+ "step": 79
510
+ },
511
+ {
512
+ "epoch": 2.11,
513
+ "learning_rate": 2.7105882352941175e-05,
514
+ "loss": 0.5419,
515
+ "step": 80
516
+ },
517
+ {
518
+ "epoch": 2.13,
519
+ "learning_rate": 2.6729411764705884e-05,
520
+ "loss": 0.5382,
521
+ "step": 81
522
+ },
523
+ {
524
+ "epoch": 2.16,
525
+ "learning_rate": 2.6352941176470585e-05,
526
+ "loss": 0.5472,
527
+ "step": 82
528
+ },
529
+ {
530
+ "epoch": 2.18,
531
+ "learning_rate": 2.597647058823529e-05,
532
+ "loss": 0.5559,
533
+ "step": 83
534
+ },
535
+ {
536
+ "epoch": 2.21,
537
+ "learning_rate": 2.56e-05,
538
+ "loss": 0.548,
539
+ "step": 84
540
+ },
541
+ {
542
+ "epoch": 2.24,
543
+ "learning_rate": 2.5223529411764707e-05,
544
+ "loss": 0.5815,
545
+ "step": 85
546
+ },
547
+ {
548
+ "epoch": 2.26,
549
+ "learning_rate": 2.484705882352941e-05,
550
+ "loss": 0.5619,
551
+ "step": 86
552
+ },
553
+ {
554
+ "epoch": 2.29,
555
+ "learning_rate": 2.4470588235294118e-05,
556
+ "loss": 0.5197,
557
+ "step": 87
558
+ },
559
+ {
560
+ "epoch": 2.32,
561
+ "learning_rate": 2.4094117647058823e-05,
562
+ "loss": 0.5246,
563
+ "step": 88
564
+ },
565
+ {
566
+ "epoch": 2.34,
567
+ "learning_rate": 2.3717647058823528e-05,
568
+ "loss": 0.5393,
569
+ "step": 89
570
+ },
571
+ {
572
+ "epoch": 2.37,
573
+ "learning_rate": 2.3341176470588233e-05,
574
+ "loss": 0.5529,
575
+ "step": 90
576
+ },
577
+ {
578
+ "epoch": 2.39,
579
+ "learning_rate": 2.296470588235294e-05,
580
+ "loss": 0.5507,
581
+ "step": 91
582
+ },
583
+ {
584
+ "epoch": 2.42,
585
+ "learning_rate": 2.2588235294117646e-05,
586
+ "loss": 0.5175,
587
+ "step": 92
588
+ },
589
+ {
590
+ "epoch": 2.45,
591
+ "learning_rate": 2.221176470588235e-05,
592
+ "loss": 0.5444,
593
+ "step": 93
594
+ },
595
+ {
596
+ "epoch": 2.47,
597
+ "learning_rate": 2.1835294117647057e-05,
598
+ "loss": 0.5424,
599
+ "step": 94
600
+ },
601
+ {
602
+ "epoch": 2.5,
603
+ "learning_rate": 2.1458823529411765e-05,
604
+ "loss": 0.593,
605
+ "step": 95
606
+ },
607
+ {
608
+ "epoch": 2.53,
609
+ "learning_rate": 2.108235294117647e-05,
610
+ "loss": 0.651,
611
+ "step": 96
612
+ },
613
+ {
614
+ "epoch": 2.55,
615
+ "learning_rate": 2.0705882352941175e-05,
616
+ "loss": 0.5191,
617
+ "step": 97
618
+ },
619
+ {
620
+ "epoch": 2.58,
621
+ "learning_rate": 2.032941176470588e-05,
622
+ "loss": 0.492,
623
+ "step": 98
624
+ },
625
+ {
626
+ "epoch": 2.61,
627
+ "learning_rate": 1.995294117647059e-05,
628
+ "loss": 0.4923,
629
+ "step": 99
630
+ },
631
+ {
632
+ "epoch": 2.63,
633
+ "learning_rate": 1.957647058823529e-05,
634
+ "loss": 0.5894,
635
+ "step": 100
636
+ },
637
+ {
638
+ "epoch": 2.66,
639
+ "learning_rate": 1.92e-05,
640
+ "loss": 0.5365,
641
+ "step": 101
642
+ },
643
+ {
644
+ "epoch": 2.68,
645
+ "learning_rate": 1.8823529411764708e-05,
646
+ "loss": 0.5324,
647
+ "step": 102
648
+ },
649
+ {
650
+ "epoch": 2.71,
651
+ "learning_rate": 1.844705882352941e-05,
652
+ "loss": 0.5131,
653
+ "step": 103
654
+ },
655
+ {
656
+ "epoch": 2.74,
657
+ "learning_rate": 1.8070588235294118e-05,
658
+ "loss": 0.504,
659
+ "step": 104
660
+ },
661
+ {
662
+ "epoch": 2.76,
663
+ "learning_rate": 1.7694117647058823e-05,
664
+ "loss": 0.5161,
665
+ "step": 105
666
+ },
667
+ {
668
+ "epoch": 2.79,
669
+ "learning_rate": 1.7317647058823528e-05,
670
+ "loss": 0.5085,
671
+ "step": 106
672
+ },
673
+ {
674
+ "epoch": 2.82,
675
+ "learning_rate": 1.6941176470588233e-05,
676
+ "loss": 0.5989,
677
+ "step": 107
678
+ },
679
+ {
680
+ "epoch": 2.84,
681
+ "learning_rate": 1.656470588235294e-05,
682
+ "loss": 0.4853,
683
+ "step": 108
684
+ },
685
+ {
686
+ "epoch": 2.87,
687
+ "learning_rate": 1.6188235294117647e-05,
688
+ "loss": 0.5312,
689
+ "step": 109
690
+ },
691
+ {
692
+ "epoch": 2.89,
693
+ "learning_rate": 1.5811764705882352e-05,
694
+ "loss": 0.6316,
695
+ "step": 110
696
+ },
697
+ {
698
+ "epoch": 2.92,
699
+ "learning_rate": 1.5435294117647057e-05,
700
+ "loss": 0.4843,
701
+ "step": 111
702
+ },
703
+ {
704
+ "epoch": 2.95,
705
+ "learning_rate": 1.5058823529411764e-05,
706
+ "loss": 0.5249,
707
+ "step": 112
708
+ },
709
+ {
710
+ "epoch": 2.97,
711
+ "learning_rate": 1.4682352941176469e-05,
712
+ "loss": 0.4826,
713
+ "step": 113
714
+ },
715
+ {
716
+ "epoch": 3.0,
717
+ "learning_rate": 1.4305882352941176e-05,
718
+ "loss": 0.6083,
719
+ "step": 114
720
+ },
721
+ {
722
+ "epoch": 3.0,
723
+ "eval_accuracy": 0.6052631578947368,
724
+ "eval_auc": 1.0,
725
+ "eval_f1": 0.0,
726
+ "eval_loss": 0.513079047203064,
727
+ "eval_precision": 0.0,
728
+ "eval_recall": 0.0,
729
+ "eval_runtime": 16.7903,
730
+ "eval_samples_per_second": 6.79,
731
+ "eval_steps_per_second": 0.298,
732
+ "step": 114
733
+ }
734
+ ],
735
+ "logging_steps": 1,
736
+ "max_steps": 152,
737
+ "num_input_tokens_seen": 0,
738
+ "num_train_epochs": 4,
739
+ "save_steps": 500,
740
+ "total_flos": 2.89863256790016e+16,
741
+ "train_batch_size": 12,
742
+ "trial_name": null,
743
+ "trial_params": null
744
+ }
checkpoint-114/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b43bbb7646e77fbfe08fc58bdd0570e06512356b907dac87a07a6fef2ab304d5
3
+ size 4728
checkpoint-152/config.json ADDED
@@ -0,0 +1,50 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "microsoft/resnet-50",
3
+ "_num_labels": 2,
4
+ "architectures": [
5
+ "ResNetForImageClassification"
6
+ ],
7
+ "depths": [
8
+ 3,
9
+ 4,
10
+ 6,
11
+ 3
12
+ ],
13
+ "downsample_in_bottleneck": false,
14
+ "downsample_in_first_stage": false,
15
+ "embedding_size": 64,
16
+ "hidden_act": "relu",
17
+ "hidden_sizes": [
18
+ 256,
19
+ 512,
20
+ 1024,
21
+ 2048
22
+ ],
23
+ "id2label": {
24
+ "0": "noyt",
25
+ "1": "yt"
26
+ },
27
+ "label2id": {
28
+ "noyt": 0,
29
+ "yt": 1
30
+ },
31
+ "layer_type": "bottleneck",
32
+ "model_type": "resnet",
33
+ "num_channels": 3,
34
+ "out_features": [
35
+ "stage4"
36
+ ],
37
+ "out_indices": [
38
+ 4
39
+ ],
40
+ "problem_type": "single_label_classification",
41
+ "stage_names": [
42
+ "stem",
43
+ "stage1",
44
+ "stage2",
45
+ "stage3",
46
+ "stage4"
47
+ ],
48
+ "torch_dtype": "float32",
49
+ "transformers_version": "4.36.1"
50
+ }
checkpoint-152/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c45a39ba983c9f5f8c36000e20c57e4eaf4cc38d1d305c0665f2d463d78cfa1d
3
+ size 94302952
checkpoint-152/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a2a45638d99d9b262391d88e16362cac5a655d790a044202d86b5cf4695109ac
3
+ size 188228026
checkpoint-152/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:06b39488f1463155c139a4901d44b9ad71a1700c3d6b2c40378d386675db1c37
3
+ size 14054
checkpoint-152/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c7688a208fc605a81bddc71e6f73958ba601f64d150a66e9f875adfbb3f021f0
3
+ size 1064
checkpoint-152/trainer_state.json ADDED
@@ -0,0 +1,985 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.509366512298584,
3
+ "best_model_checkpoint": "/tmp/model/checkpoint-152",
4
+ "epoch": 4.0,
5
+ "eval_steps": 500,
6
+ "global_step": 152,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.03,
13
+ "learning_rate": 3.2e-06,
14
+ "loss": 0.6931,
15
+ "step": 1
16
+ },
17
+ {
18
+ "epoch": 0.05,
19
+ "learning_rate": 6.4e-06,
20
+ "loss": 0.6931,
21
+ "step": 2
22
+ },
23
+ {
24
+ "epoch": 0.08,
25
+ "learning_rate": 9.6e-06,
26
+ "loss": 0.6931,
27
+ "step": 3
28
+ },
29
+ {
30
+ "epoch": 0.11,
31
+ "learning_rate": 1.28e-05,
32
+ "loss": 0.693,
33
+ "step": 4
34
+ },
35
+ {
36
+ "epoch": 0.13,
37
+ "learning_rate": 1.6e-05,
38
+ "loss": 0.6929,
39
+ "step": 5
40
+ },
41
+ {
42
+ "epoch": 0.16,
43
+ "learning_rate": 1.92e-05,
44
+ "loss": 0.6927,
45
+ "step": 6
46
+ },
47
+ {
48
+ "epoch": 0.18,
49
+ "learning_rate": 2.24e-05,
50
+ "loss": 0.6921,
51
+ "step": 7
52
+ },
53
+ {
54
+ "epoch": 0.21,
55
+ "learning_rate": 2.56e-05,
56
+ "loss": 0.6916,
57
+ "step": 8
58
+ },
59
+ {
60
+ "epoch": 0.24,
61
+ "learning_rate": 2.88e-05,
62
+ "loss": 0.6903,
63
+ "step": 9
64
+ },
65
+ {
66
+ "epoch": 0.26,
67
+ "learning_rate": 3.2e-05,
68
+ "loss": 0.692,
69
+ "step": 10
70
+ },
71
+ {
72
+ "epoch": 0.29,
73
+ "learning_rate": 3.52e-05,
74
+ "loss": 0.6883,
75
+ "step": 11
76
+ },
77
+ {
78
+ "epoch": 0.32,
79
+ "learning_rate": 3.84e-05,
80
+ "loss": 0.6922,
81
+ "step": 12
82
+ },
83
+ {
84
+ "epoch": 0.34,
85
+ "learning_rate": 4.1599999999999995e-05,
86
+ "loss": 0.6872,
87
+ "step": 13
88
+ },
89
+ {
90
+ "epoch": 0.37,
91
+ "learning_rate": 4.48e-05,
92
+ "loss": 0.6915,
93
+ "step": 14
94
+ },
95
+ {
96
+ "epoch": 0.39,
97
+ "learning_rate": 4.8e-05,
98
+ "loss": 0.6924,
99
+ "step": 15
100
+ },
101
+ {
102
+ "epoch": 0.42,
103
+ "learning_rate": 5.12e-05,
104
+ "loss": 0.6924,
105
+ "step": 16
106
+ },
107
+ {
108
+ "epoch": 0.45,
109
+ "learning_rate": 5.08235294117647e-05,
110
+ "loss": 0.6804,
111
+ "step": 17
112
+ },
113
+ {
114
+ "epoch": 0.47,
115
+ "learning_rate": 5.0447058823529415e-05,
116
+ "loss": 0.6788,
117
+ "step": 18
118
+ },
119
+ {
120
+ "epoch": 0.5,
121
+ "learning_rate": 5.007058823529411e-05,
122
+ "loss": 0.6869,
123
+ "step": 19
124
+ },
125
+ {
126
+ "epoch": 0.53,
127
+ "learning_rate": 4.969411764705882e-05,
128
+ "loss": 0.681,
129
+ "step": 20
130
+ },
131
+ {
132
+ "epoch": 0.55,
133
+ "learning_rate": 4.931764705882353e-05,
134
+ "loss": 0.6895,
135
+ "step": 21
136
+ },
137
+ {
138
+ "epoch": 0.58,
139
+ "learning_rate": 4.8941176470588235e-05,
140
+ "loss": 0.6844,
141
+ "step": 22
142
+ },
143
+ {
144
+ "epoch": 0.61,
145
+ "learning_rate": 4.856470588235294e-05,
146
+ "loss": 0.6761,
147
+ "step": 23
148
+ },
149
+ {
150
+ "epoch": 0.63,
151
+ "learning_rate": 4.8188235294117645e-05,
152
+ "loss": 0.6691,
153
+ "step": 24
154
+ },
155
+ {
156
+ "epoch": 0.66,
157
+ "learning_rate": 4.781176470588235e-05,
158
+ "loss": 0.6717,
159
+ "step": 25
160
+ },
161
+ {
162
+ "epoch": 0.68,
163
+ "learning_rate": 4.7435294117647055e-05,
164
+ "loss": 0.6752,
165
+ "step": 26
166
+ },
167
+ {
168
+ "epoch": 0.71,
169
+ "learning_rate": 4.705882352941176e-05,
170
+ "loss": 0.6837,
171
+ "step": 27
172
+ },
173
+ {
174
+ "epoch": 0.74,
175
+ "learning_rate": 4.6682352941176466e-05,
176
+ "loss": 0.6834,
177
+ "step": 28
178
+ },
179
+ {
180
+ "epoch": 0.76,
181
+ "learning_rate": 4.630588235294118e-05,
182
+ "loss": 0.6646,
183
+ "step": 29
184
+ },
185
+ {
186
+ "epoch": 0.79,
187
+ "learning_rate": 4.592941176470588e-05,
188
+ "loss": 0.6719,
189
+ "step": 30
190
+ },
191
+ {
192
+ "epoch": 0.82,
193
+ "learning_rate": 4.555294117647058e-05,
194
+ "loss": 0.667,
195
+ "step": 31
196
+ },
197
+ {
198
+ "epoch": 0.84,
199
+ "learning_rate": 4.517647058823529e-05,
200
+ "loss": 0.6774,
201
+ "step": 32
202
+ },
203
+ {
204
+ "epoch": 0.87,
205
+ "learning_rate": 4.48e-05,
206
+ "loss": 0.678,
207
+ "step": 33
208
+ },
209
+ {
210
+ "epoch": 0.89,
211
+ "learning_rate": 4.44235294117647e-05,
212
+ "loss": 0.6657,
213
+ "step": 34
214
+ },
215
+ {
216
+ "epoch": 0.92,
217
+ "learning_rate": 4.4047058823529415e-05,
218
+ "loss": 0.6539,
219
+ "step": 35
220
+ },
221
+ {
222
+ "epoch": 0.95,
223
+ "learning_rate": 4.367058823529411e-05,
224
+ "loss": 0.662,
225
+ "step": 36
226
+ },
227
+ {
228
+ "epoch": 0.97,
229
+ "learning_rate": 4.329411764705882e-05,
230
+ "loss": 0.7082,
231
+ "step": 37
232
+ },
233
+ {
234
+ "epoch": 1.0,
235
+ "learning_rate": 4.291764705882353e-05,
236
+ "loss": 0.6554,
237
+ "step": 38
238
+ },
239
+ {
240
+ "epoch": 1.0,
241
+ "eval_accuracy": 0.6052631578947368,
242
+ "eval_auc": 0.9916264090177134,
243
+ "eval_f1": 0.0,
244
+ "eval_loss": 0.665397047996521,
245
+ "eval_precision": 0.0,
246
+ "eval_recall": 0.0,
247
+ "eval_runtime": 14.6602,
248
+ "eval_samples_per_second": 7.776,
249
+ "eval_steps_per_second": 0.341,
250
+ "step": 38
251
+ },
252
+ {
253
+ "epoch": 1.03,
254
+ "learning_rate": 4.2541176470588235e-05,
255
+ "loss": 0.638,
256
+ "step": 39
257
+ },
258
+ {
259
+ "epoch": 1.05,
260
+ "learning_rate": 4.216470588235294e-05,
261
+ "loss": 0.6432,
262
+ "step": 40
263
+ },
264
+ {
265
+ "epoch": 1.08,
266
+ "learning_rate": 4.1788235294117646e-05,
267
+ "loss": 0.6896,
268
+ "step": 41
269
+ },
270
+ {
271
+ "epoch": 1.11,
272
+ "learning_rate": 4.141176470588235e-05,
273
+ "loss": 0.677,
274
+ "step": 42
275
+ },
276
+ {
277
+ "epoch": 1.13,
278
+ "learning_rate": 4.1035294117647056e-05,
279
+ "loss": 0.6312,
280
+ "step": 43
281
+ },
282
+ {
283
+ "epoch": 1.16,
284
+ "learning_rate": 4.065882352941176e-05,
285
+ "loss": 0.637,
286
+ "step": 44
287
+ },
288
+ {
289
+ "epoch": 1.18,
290
+ "learning_rate": 4.0282352941176466e-05,
291
+ "loss": 0.6274,
292
+ "step": 45
293
+ },
294
+ {
295
+ "epoch": 1.21,
296
+ "learning_rate": 3.990588235294118e-05,
297
+ "loss": 0.6335,
298
+ "step": 46
299
+ },
300
+ {
301
+ "epoch": 1.24,
302
+ "learning_rate": 3.952941176470588e-05,
303
+ "loss": 0.6302,
304
+ "step": 47
305
+ },
306
+ {
307
+ "epoch": 1.26,
308
+ "learning_rate": 3.915294117647058e-05,
309
+ "loss": 0.6223,
310
+ "step": 48
311
+ },
312
+ {
313
+ "epoch": 1.29,
314
+ "learning_rate": 3.877647058823529e-05,
315
+ "loss": 0.668,
316
+ "step": 49
317
+ },
318
+ {
319
+ "epoch": 1.32,
320
+ "learning_rate": 3.84e-05,
321
+ "loss": 0.6216,
322
+ "step": 50
323
+ },
324
+ {
325
+ "epoch": 1.34,
326
+ "learning_rate": 3.80235294117647e-05,
327
+ "loss": 0.6518,
328
+ "step": 51
329
+ },
330
+ {
331
+ "epoch": 1.37,
332
+ "learning_rate": 3.7647058823529415e-05,
333
+ "loss": 0.6599,
334
+ "step": 52
335
+ },
336
+ {
337
+ "epoch": 1.39,
338
+ "learning_rate": 3.7270588235294114e-05,
339
+ "loss": 0.6562,
340
+ "step": 53
341
+ },
342
+ {
343
+ "epoch": 1.42,
344
+ "learning_rate": 3.689411764705882e-05,
345
+ "loss": 0.6329,
346
+ "step": 54
347
+ },
348
+ {
349
+ "epoch": 1.45,
350
+ "learning_rate": 3.651764705882353e-05,
351
+ "loss": 0.6358,
352
+ "step": 55
353
+ },
354
+ {
355
+ "epoch": 1.47,
356
+ "learning_rate": 3.6141176470588236e-05,
357
+ "loss": 0.6074,
358
+ "step": 56
359
+ },
360
+ {
361
+ "epoch": 1.5,
362
+ "learning_rate": 3.576470588235294e-05,
363
+ "loss": 0.6036,
364
+ "step": 57
365
+ },
366
+ {
367
+ "epoch": 1.53,
368
+ "learning_rate": 3.5388235294117646e-05,
369
+ "loss": 0.6039,
370
+ "step": 58
371
+ },
372
+ {
373
+ "epoch": 1.55,
374
+ "learning_rate": 3.501176470588235e-05,
375
+ "loss": 0.6243,
376
+ "step": 59
377
+ },
378
+ {
379
+ "epoch": 1.58,
380
+ "learning_rate": 3.4635294117647056e-05,
381
+ "loss": 0.6479,
382
+ "step": 60
383
+ },
384
+ {
385
+ "epoch": 1.61,
386
+ "learning_rate": 3.425882352941176e-05,
387
+ "loss": 0.6312,
388
+ "step": 61
389
+ },
390
+ {
391
+ "epoch": 1.63,
392
+ "learning_rate": 3.3882352941176466e-05,
393
+ "loss": 0.6259,
394
+ "step": 62
395
+ },
396
+ {
397
+ "epoch": 1.66,
398
+ "learning_rate": 3.350588235294118e-05,
399
+ "loss": 0.6058,
400
+ "step": 63
401
+ },
402
+ {
403
+ "epoch": 1.68,
404
+ "learning_rate": 3.312941176470588e-05,
405
+ "loss": 0.5793,
406
+ "step": 64
407
+ },
408
+ {
409
+ "epoch": 1.71,
410
+ "learning_rate": 3.275294117647058e-05,
411
+ "loss": 0.6781,
412
+ "step": 65
413
+ },
414
+ {
415
+ "epoch": 1.74,
416
+ "learning_rate": 3.2376470588235293e-05,
417
+ "loss": 0.599,
418
+ "step": 66
419
+ },
420
+ {
421
+ "epoch": 1.76,
422
+ "learning_rate": 3.2e-05,
423
+ "loss": 0.5805,
424
+ "step": 67
425
+ },
426
+ {
427
+ "epoch": 1.79,
428
+ "learning_rate": 3.1623529411764704e-05,
429
+ "loss": 0.5873,
430
+ "step": 68
431
+ },
432
+ {
433
+ "epoch": 1.82,
434
+ "learning_rate": 3.1247058823529416e-05,
435
+ "loss": 0.6044,
436
+ "step": 69
437
+ },
438
+ {
439
+ "epoch": 1.84,
440
+ "learning_rate": 3.0870588235294114e-05,
441
+ "loss": 0.5808,
442
+ "step": 70
443
+ },
444
+ {
445
+ "epoch": 1.87,
446
+ "learning_rate": 3.0494117647058822e-05,
447
+ "loss": 0.5655,
448
+ "step": 71
449
+ },
450
+ {
451
+ "epoch": 1.89,
452
+ "learning_rate": 3.0117647058823527e-05,
453
+ "loss": 0.5661,
454
+ "step": 72
455
+ },
456
+ {
457
+ "epoch": 1.92,
458
+ "learning_rate": 2.9741176470588236e-05,
459
+ "loss": 0.6197,
460
+ "step": 73
461
+ },
462
+ {
463
+ "epoch": 1.95,
464
+ "learning_rate": 2.9364705882352938e-05,
465
+ "loss": 0.6197,
466
+ "step": 74
467
+ },
468
+ {
469
+ "epoch": 1.97,
470
+ "learning_rate": 2.8988235294117646e-05,
471
+ "loss": 0.6297,
472
+ "step": 75
473
+ },
474
+ {
475
+ "epoch": 2.0,
476
+ "learning_rate": 2.861176470588235e-05,
477
+ "loss": 0.5994,
478
+ "step": 76
479
+ },
480
+ {
481
+ "epoch": 2.0,
482
+ "eval_accuracy": 0.6052631578947368,
483
+ "eval_auc": 1.0,
484
+ "eval_f1": 0.0,
485
+ "eval_loss": 0.6067062616348267,
486
+ "eval_precision": 0.0,
487
+ "eval_recall": 0.0,
488
+ "eval_runtime": 17.1278,
489
+ "eval_samples_per_second": 6.656,
490
+ "eval_steps_per_second": 0.292,
491
+ "step": 76
492
+ },
493
+ {
494
+ "epoch": 2.03,
495
+ "learning_rate": 2.823529411764706e-05,
496
+ "loss": 0.5467,
497
+ "step": 77
498
+ },
499
+ {
500
+ "epoch": 2.05,
501
+ "learning_rate": 2.785882352941176e-05,
502
+ "loss": 0.6236,
503
+ "step": 78
504
+ },
505
+ {
506
+ "epoch": 2.08,
507
+ "learning_rate": 2.748235294117647e-05,
508
+ "loss": 0.5555,
509
+ "step": 79
510
+ },
511
+ {
512
+ "epoch": 2.11,
513
+ "learning_rate": 2.7105882352941175e-05,
514
+ "loss": 0.5419,
515
+ "step": 80
516
+ },
517
+ {
518
+ "epoch": 2.13,
519
+ "learning_rate": 2.6729411764705884e-05,
520
+ "loss": 0.5382,
521
+ "step": 81
522
+ },
523
+ {
524
+ "epoch": 2.16,
525
+ "learning_rate": 2.6352941176470585e-05,
526
+ "loss": 0.5472,
527
+ "step": 82
528
+ },
529
+ {
530
+ "epoch": 2.18,
531
+ "learning_rate": 2.597647058823529e-05,
532
+ "loss": 0.5559,
533
+ "step": 83
534
+ },
535
+ {
536
+ "epoch": 2.21,
537
+ "learning_rate": 2.56e-05,
538
+ "loss": 0.548,
539
+ "step": 84
540
+ },
541
+ {
542
+ "epoch": 2.24,
543
+ "learning_rate": 2.5223529411764707e-05,
544
+ "loss": 0.5815,
545
+ "step": 85
546
+ },
547
+ {
548
+ "epoch": 2.26,
549
+ "learning_rate": 2.484705882352941e-05,
550
+ "loss": 0.5619,
551
+ "step": 86
552
+ },
553
+ {
554
+ "epoch": 2.29,
555
+ "learning_rate": 2.4470588235294118e-05,
556
+ "loss": 0.5197,
557
+ "step": 87
558
+ },
559
+ {
560
+ "epoch": 2.32,
561
+ "learning_rate": 2.4094117647058823e-05,
562
+ "loss": 0.5246,
563
+ "step": 88
564
+ },
565
+ {
566
+ "epoch": 2.34,
567
+ "learning_rate": 2.3717647058823528e-05,
568
+ "loss": 0.5393,
569
+ "step": 89
570
+ },
571
+ {
572
+ "epoch": 2.37,
573
+ "learning_rate": 2.3341176470588233e-05,
574
+ "loss": 0.5529,
575
+ "step": 90
576
+ },
577
+ {
578
+ "epoch": 2.39,
579
+ "learning_rate": 2.296470588235294e-05,
580
+ "loss": 0.5507,
581
+ "step": 91
582
+ },
583
+ {
584
+ "epoch": 2.42,
585
+ "learning_rate": 2.2588235294117646e-05,
586
+ "loss": 0.5175,
587
+ "step": 92
588
+ },
589
+ {
590
+ "epoch": 2.45,
591
+ "learning_rate": 2.221176470588235e-05,
592
+ "loss": 0.5444,
593
+ "step": 93
594
+ },
595
+ {
596
+ "epoch": 2.47,
597
+ "learning_rate": 2.1835294117647057e-05,
598
+ "loss": 0.5424,
599
+ "step": 94
600
+ },
601
+ {
602
+ "epoch": 2.5,
603
+ "learning_rate": 2.1458823529411765e-05,
604
+ "loss": 0.593,
605
+ "step": 95
606
+ },
607
+ {
608
+ "epoch": 2.53,
609
+ "learning_rate": 2.108235294117647e-05,
610
+ "loss": 0.651,
611
+ "step": 96
612
+ },
613
+ {
614
+ "epoch": 2.55,
615
+ "learning_rate": 2.0705882352941175e-05,
616
+ "loss": 0.5191,
617
+ "step": 97
618
+ },
619
+ {
620
+ "epoch": 2.58,
621
+ "learning_rate": 2.032941176470588e-05,
622
+ "loss": 0.492,
623
+ "step": 98
624
+ },
625
+ {
626
+ "epoch": 2.61,
627
+ "learning_rate": 1.995294117647059e-05,
628
+ "loss": 0.4923,
629
+ "step": 99
630
+ },
631
+ {
632
+ "epoch": 2.63,
633
+ "learning_rate": 1.957647058823529e-05,
634
+ "loss": 0.5894,
635
+ "step": 100
636
+ },
637
+ {
638
+ "epoch": 2.66,
639
+ "learning_rate": 1.92e-05,
640
+ "loss": 0.5365,
641
+ "step": 101
642
+ },
643
+ {
644
+ "epoch": 2.68,
645
+ "learning_rate": 1.8823529411764708e-05,
646
+ "loss": 0.5324,
647
+ "step": 102
648
+ },
649
+ {
650
+ "epoch": 2.71,
651
+ "learning_rate": 1.844705882352941e-05,
652
+ "loss": 0.5131,
653
+ "step": 103
654
+ },
655
+ {
656
+ "epoch": 2.74,
657
+ "learning_rate": 1.8070588235294118e-05,
658
+ "loss": 0.504,
659
+ "step": 104
660
+ },
661
+ {
662
+ "epoch": 2.76,
663
+ "learning_rate": 1.7694117647058823e-05,
664
+ "loss": 0.5161,
665
+ "step": 105
666
+ },
667
+ {
668
+ "epoch": 2.79,
669
+ "learning_rate": 1.7317647058823528e-05,
670
+ "loss": 0.5085,
671
+ "step": 106
672
+ },
673
+ {
674
+ "epoch": 2.82,
675
+ "learning_rate": 1.6941176470588233e-05,
676
+ "loss": 0.5989,
677
+ "step": 107
678
+ },
679
+ {
680
+ "epoch": 2.84,
681
+ "learning_rate": 1.656470588235294e-05,
682
+ "loss": 0.4853,
683
+ "step": 108
684
+ },
685
+ {
686
+ "epoch": 2.87,
687
+ "learning_rate": 1.6188235294117647e-05,
688
+ "loss": 0.5312,
689
+ "step": 109
690
+ },
691
+ {
692
+ "epoch": 2.89,
693
+ "learning_rate": 1.5811764705882352e-05,
694
+ "loss": 0.6316,
695
+ "step": 110
696
+ },
697
+ {
698
+ "epoch": 2.92,
699
+ "learning_rate": 1.5435294117647057e-05,
700
+ "loss": 0.4843,
701
+ "step": 111
702
+ },
703
+ {
704
+ "epoch": 2.95,
705
+ "learning_rate": 1.5058823529411764e-05,
706
+ "loss": 0.5249,
707
+ "step": 112
708
+ },
709
+ {
710
+ "epoch": 2.97,
711
+ "learning_rate": 1.4682352941176469e-05,
712
+ "loss": 0.4826,
713
+ "step": 113
714
+ },
715
+ {
716
+ "epoch": 3.0,
717
+ "learning_rate": 1.4305882352941176e-05,
718
+ "loss": 0.6083,
719
+ "step": 114
720
+ },
721
+ {
722
+ "epoch": 3.0,
723
+ "eval_accuracy": 0.6052631578947368,
724
+ "eval_auc": 1.0,
725
+ "eval_f1": 0.0,
726
+ "eval_loss": 0.513079047203064,
727
+ "eval_precision": 0.0,
728
+ "eval_recall": 0.0,
729
+ "eval_runtime": 16.7903,
730
+ "eval_samples_per_second": 6.79,
731
+ "eval_steps_per_second": 0.298,
732
+ "step": 114
733
+ },
734
+ {
735
+ "epoch": 3.03,
736
+ "learning_rate": 1.392941176470588e-05,
737
+ "loss": 0.4868,
738
+ "step": 115
739
+ },
740
+ {
741
+ "epoch": 3.05,
742
+ "learning_rate": 1.3552941176470588e-05,
743
+ "loss": 0.543,
744
+ "step": 116
745
+ },
746
+ {
747
+ "epoch": 3.08,
748
+ "learning_rate": 1.3176470588235293e-05,
749
+ "loss": 0.4724,
750
+ "step": 117
751
+ },
752
+ {
753
+ "epoch": 3.11,
754
+ "learning_rate": 1.28e-05,
755
+ "loss": 0.5019,
756
+ "step": 118
757
+ },
758
+ {
759
+ "epoch": 3.13,
760
+ "learning_rate": 1.2423529411764705e-05,
761
+ "loss": 0.5136,
762
+ "step": 119
763
+ },
764
+ {
765
+ "epoch": 3.16,
766
+ "learning_rate": 1.2047058823529411e-05,
767
+ "loss": 0.5565,
768
+ "step": 120
769
+ },
770
+ {
771
+ "epoch": 3.18,
772
+ "learning_rate": 1.1670588235294116e-05,
773
+ "loss": 0.639,
774
+ "step": 121
775
+ },
776
+ {
777
+ "epoch": 3.21,
778
+ "learning_rate": 1.1294117647058823e-05,
779
+ "loss": 0.5833,
780
+ "step": 122
781
+ },
782
+ {
783
+ "epoch": 3.24,
784
+ "learning_rate": 1.0917647058823528e-05,
785
+ "loss": 0.4672,
786
+ "step": 123
787
+ },
788
+ {
789
+ "epoch": 3.26,
790
+ "learning_rate": 1.0541176470588235e-05,
791
+ "loss": 0.4539,
792
+ "step": 124
793
+ },
794
+ {
795
+ "epoch": 3.29,
796
+ "learning_rate": 1.016470588235294e-05,
797
+ "loss": 0.5085,
798
+ "step": 125
799
+ },
800
+ {
801
+ "epoch": 3.32,
802
+ "learning_rate": 9.788235294117645e-06,
803
+ "loss": 0.491,
804
+ "step": 126
805
+ },
806
+ {
807
+ "epoch": 3.34,
808
+ "learning_rate": 9.411764705882354e-06,
809
+ "loss": 0.4659,
810
+ "step": 127
811
+ },
812
+ {
813
+ "epoch": 3.37,
814
+ "learning_rate": 9.035294117647059e-06,
815
+ "loss": 0.4791,
816
+ "step": 128
817
+ },
818
+ {
819
+ "epoch": 3.39,
820
+ "learning_rate": 8.658823529411764e-06,
821
+ "loss": 0.4923,
822
+ "step": 129
823
+ },
824
+ {
825
+ "epoch": 3.42,
826
+ "learning_rate": 8.28235294117647e-06,
827
+ "loss": 0.4692,
828
+ "step": 130
829
+ },
830
+ {
831
+ "epoch": 3.45,
832
+ "learning_rate": 7.905882352941176e-06,
833
+ "loss": 0.465,
834
+ "step": 131
835
+ },
836
+ {
837
+ "epoch": 3.47,
838
+ "learning_rate": 7.529411764705882e-06,
839
+ "loss": 0.4835,
840
+ "step": 132
841
+ },
842
+ {
843
+ "epoch": 3.5,
844
+ "learning_rate": 7.152941176470588e-06,
845
+ "loss": 0.4555,
846
+ "step": 133
847
+ },
848
+ {
849
+ "epoch": 3.53,
850
+ "learning_rate": 6.776470588235294e-06,
851
+ "loss": 0.4546,
852
+ "step": 134
853
+ },
854
+ {
855
+ "epoch": 3.55,
856
+ "learning_rate": 6.4e-06,
857
+ "loss": 0.4552,
858
+ "step": 135
859
+ },
860
+ {
861
+ "epoch": 3.58,
862
+ "learning_rate": 6.023529411764706e-06,
863
+ "loss": 0.4711,
864
+ "step": 136
865
+ },
866
+ {
867
+ "epoch": 3.61,
868
+ "learning_rate": 5.647058823529412e-06,
869
+ "loss": 0.4727,
870
+ "step": 137
871
+ },
872
+ {
873
+ "epoch": 3.63,
874
+ "learning_rate": 5.2705882352941176e-06,
875
+ "loss": 0.4586,
876
+ "step": 138
877
+ },
878
+ {
879
+ "epoch": 3.66,
880
+ "learning_rate": 4.894117647058823e-06,
881
+ "loss": 0.5134,
882
+ "step": 139
883
+ },
884
+ {
885
+ "epoch": 3.68,
886
+ "learning_rate": 4.5176470588235295e-06,
887
+ "loss": 0.4833,
888
+ "step": 140
889
+ },
890
+ {
891
+ "epoch": 3.71,
892
+ "learning_rate": 4.141176470588235e-06,
893
+ "loss": 0.4854,
894
+ "step": 141
895
+ },
896
+ {
897
+ "epoch": 3.74,
898
+ "learning_rate": 3.764705882352941e-06,
899
+ "loss": 0.4587,
900
+ "step": 142
901
+ },
902
+ {
903
+ "epoch": 3.76,
904
+ "learning_rate": 3.388235294117647e-06,
905
+ "loss": 0.5004,
906
+ "step": 143
907
+ },
908
+ {
909
+ "epoch": 3.79,
910
+ "learning_rate": 3.011764705882353e-06,
911
+ "loss": 0.4824,
912
+ "step": 144
913
+ },
914
+ {
915
+ "epoch": 3.82,
916
+ "learning_rate": 2.6352941176470588e-06,
917
+ "loss": 0.5131,
918
+ "step": 145
919
+ },
920
+ {
921
+ "epoch": 3.84,
922
+ "learning_rate": 2.2588235294117647e-06,
923
+ "loss": 0.461,
924
+ "step": 146
925
+ },
926
+ {
927
+ "epoch": 3.87,
928
+ "learning_rate": 1.8823529411764705e-06,
929
+ "loss": 0.4932,
930
+ "step": 147
931
+ },
932
+ {
933
+ "epoch": 3.89,
934
+ "learning_rate": 1.5058823529411764e-06,
935
+ "loss": 0.4902,
936
+ "step": 148
937
+ },
938
+ {
939
+ "epoch": 3.92,
940
+ "learning_rate": 1.1294117647058824e-06,
941
+ "loss": 0.4743,
942
+ "step": 149
943
+ },
944
+ {
945
+ "epoch": 3.95,
946
+ "learning_rate": 7.529411764705882e-07,
947
+ "loss": 0.5645,
948
+ "step": 150
949
+ },
950
+ {
951
+ "epoch": 3.97,
952
+ "learning_rate": 3.764705882352941e-07,
953
+ "loss": 0.4807,
954
+ "step": 151
955
+ },
956
+ {
957
+ "epoch": 4.0,
958
+ "learning_rate": 0.0,
959
+ "loss": 0.4483,
960
+ "step": 152
961
+ },
962
+ {
963
+ "epoch": 4.0,
964
+ "eval_accuracy": 0.6052631578947368,
965
+ "eval_auc": 1.0,
966
+ "eval_f1": 0.0,
967
+ "eval_loss": 0.509366512298584,
968
+ "eval_precision": 0.0,
969
+ "eval_recall": 0.0,
970
+ "eval_runtime": 16.2553,
971
+ "eval_samples_per_second": 7.013,
972
+ "eval_steps_per_second": 0.308,
973
+ "step": 152
974
+ }
975
+ ],
976
+ "logging_steps": 1,
977
+ "max_steps": 152,
978
+ "num_input_tokens_seen": 0,
979
+ "num_train_epochs": 4,
980
+ "save_steps": 500,
981
+ "total_flos": 3.86484342386688e+16,
982
+ "train_batch_size": 12,
983
+ "trial_name": null,
984
+ "trial_params": null
985
+ }
checkpoint-152/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b43bbb7646e77fbfe08fc58bdd0570e06512356b907dac87a07a6fef2ab304d5
3
+ size 4728
checkpoint-38/config.json ADDED
@@ -0,0 +1,50 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "microsoft/resnet-50",
3
+ "_num_labels": 2,
4
+ "architectures": [
5
+ "ResNetForImageClassification"
6
+ ],
7
+ "depths": [
8
+ 3,
9
+ 4,
10
+ 6,
11
+ 3
12
+ ],
13
+ "downsample_in_bottleneck": false,
14
+ "downsample_in_first_stage": false,
15
+ "embedding_size": 64,
16
+ "hidden_act": "relu",
17
+ "hidden_sizes": [
18
+ 256,
19
+ 512,
20
+ 1024,
21
+ 2048
22
+ ],
23
+ "id2label": {
24
+ "0": "noyt",
25
+ "1": "yt"
26
+ },
27
+ "label2id": {
28
+ "noyt": 0,
29
+ "yt": 1
30
+ },
31
+ "layer_type": "bottleneck",
32
+ "model_type": "resnet",
33
+ "num_channels": 3,
34
+ "out_features": [
35
+ "stage4"
36
+ ],
37
+ "out_indices": [
38
+ 4
39
+ ],
40
+ "problem_type": "single_label_classification",
41
+ "stage_names": [
42
+ "stem",
43
+ "stage1",
44
+ "stage2",
45
+ "stage3",
46
+ "stage4"
47
+ ],
48
+ "torch_dtype": "float32",
49
+ "transformers_version": "4.36.1"
50
+ }
checkpoint-38/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fef1e793e074fb69ddeeabd400d824f957c64bd4c15f4aff0634847949d8361e
3
+ size 94302952
checkpoint-38/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b95b798fb220bb5490e19ed5601bc11e62d3c94582bd24fb3ff2456f391ae50c
3
+ size 188228026
checkpoint-38/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c975e8638faf0c77c9cf63060d92144d1faca9abbd95190a3f04c191aa273f12
3
+ size 13990
checkpoint-38/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b55e88bdcf1f8f1f189cd82e57272e7ad4f453625b7bdba84909b60e463172c4
3
+ size 1064
checkpoint-38/trainer_state.json ADDED
@@ -0,0 +1,262 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.665397047996521,
3
+ "best_model_checkpoint": "/tmp/model/checkpoint-38",
4
+ "epoch": 1.0,
5
+ "eval_steps": 500,
6
+ "global_step": 38,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.03,
13
+ "learning_rate": 3.2e-06,
14
+ "loss": 0.6931,
15
+ "step": 1
16
+ },
17
+ {
18
+ "epoch": 0.05,
19
+ "learning_rate": 6.4e-06,
20
+ "loss": 0.6931,
21
+ "step": 2
22
+ },
23
+ {
24
+ "epoch": 0.08,
25
+ "learning_rate": 9.6e-06,
26
+ "loss": 0.6931,
27
+ "step": 3
28
+ },
29
+ {
30
+ "epoch": 0.11,
31
+ "learning_rate": 1.28e-05,
32
+ "loss": 0.693,
33
+ "step": 4
34
+ },
35
+ {
36
+ "epoch": 0.13,
37
+ "learning_rate": 1.6e-05,
38
+ "loss": 0.6929,
39
+ "step": 5
40
+ },
41
+ {
42
+ "epoch": 0.16,
43
+ "learning_rate": 1.92e-05,
44
+ "loss": 0.6927,
45
+ "step": 6
46
+ },
47
+ {
48
+ "epoch": 0.18,
49
+ "learning_rate": 2.24e-05,
50
+ "loss": 0.6921,
51
+ "step": 7
52
+ },
53
+ {
54
+ "epoch": 0.21,
55
+ "learning_rate": 2.56e-05,
56
+ "loss": 0.6916,
57
+ "step": 8
58
+ },
59
+ {
60
+ "epoch": 0.24,
61
+ "learning_rate": 2.88e-05,
62
+ "loss": 0.6903,
63
+ "step": 9
64
+ },
65
+ {
66
+ "epoch": 0.26,
67
+ "learning_rate": 3.2e-05,
68
+ "loss": 0.692,
69
+ "step": 10
70
+ },
71
+ {
72
+ "epoch": 0.29,
73
+ "learning_rate": 3.52e-05,
74
+ "loss": 0.6883,
75
+ "step": 11
76
+ },
77
+ {
78
+ "epoch": 0.32,
79
+ "learning_rate": 3.84e-05,
80
+ "loss": 0.6922,
81
+ "step": 12
82
+ },
83
+ {
84
+ "epoch": 0.34,
85
+ "learning_rate": 4.1599999999999995e-05,
86
+ "loss": 0.6872,
87
+ "step": 13
88
+ },
89
+ {
90
+ "epoch": 0.37,
91
+ "learning_rate": 4.48e-05,
92
+ "loss": 0.6915,
93
+ "step": 14
94
+ },
95
+ {
96
+ "epoch": 0.39,
97
+ "learning_rate": 4.8e-05,
98
+ "loss": 0.6924,
99
+ "step": 15
100
+ },
101
+ {
102
+ "epoch": 0.42,
103
+ "learning_rate": 5.12e-05,
104
+ "loss": 0.6924,
105
+ "step": 16
106
+ },
107
+ {
108
+ "epoch": 0.45,
109
+ "learning_rate": 5.08235294117647e-05,
110
+ "loss": 0.6804,
111
+ "step": 17
112
+ },
113
+ {
114
+ "epoch": 0.47,
115
+ "learning_rate": 5.0447058823529415e-05,
116
+ "loss": 0.6788,
117
+ "step": 18
118
+ },
119
+ {
120
+ "epoch": 0.5,
121
+ "learning_rate": 5.007058823529411e-05,
122
+ "loss": 0.6869,
123
+ "step": 19
124
+ },
125
+ {
126
+ "epoch": 0.53,
127
+ "learning_rate": 4.969411764705882e-05,
128
+ "loss": 0.681,
129
+ "step": 20
130
+ },
131
+ {
132
+ "epoch": 0.55,
133
+ "learning_rate": 4.931764705882353e-05,
134
+ "loss": 0.6895,
135
+ "step": 21
136
+ },
137
+ {
138
+ "epoch": 0.58,
139
+ "learning_rate": 4.8941176470588235e-05,
140
+ "loss": 0.6844,
141
+ "step": 22
142
+ },
143
+ {
144
+ "epoch": 0.61,
145
+ "learning_rate": 4.856470588235294e-05,
146
+ "loss": 0.6761,
147
+ "step": 23
148
+ },
149
+ {
150
+ "epoch": 0.63,
151
+ "learning_rate": 4.8188235294117645e-05,
152
+ "loss": 0.6691,
153
+ "step": 24
154
+ },
155
+ {
156
+ "epoch": 0.66,
157
+ "learning_rate": 4.781176470588235e-05,
158
+ "loss": 0.6717,
159
+ "step": 25
160
+ },
161
+ {
162
+ "epoch": 0.68,
163
+ "learning_rate": 4.7435294117647055e-05,
164
+ "loss": 0.6752,
165
+ "step": 26
166
+ },
167
+ {
168
+ "epoch": 0.71,
169
+ "learning_rate": 4.705882352941176e-05,
170
+ "loss": 0.6837,
171
+ "step": 27
172
+ },
173
+ {
174
+ "epoch": 0.74,
175
+ "learning_rate": 4.6682352941176466e-05,
176
+ "loss": 0.6834,
177
+ "step": 28
178
+ },
179
+ {
180
+ "epoch": 0.76,
181
+ "learning_rate": 4.630588235294118e-05,
182
+ "loss": 0.6646,
183
+ "step": 29
184
+ },
185
+ {
186
+ "epoch": 0.79,
187
+ "learning_rate": 4.592941176470588e-05,
188
+ "loss": 0.6719,
189
+ "step": 30
190
+ },
191
+ {
192
+ "epoch": 0.82,
193
+ "learning_rate": 4.555294117647058e-05,
194
+ "loss": 0.667,
195
+ "step": 31
196
+ },
197
+ {
198
+ "epoch": 0.84,
199
+ "learning_rate": 4.517647058823529e-05,
200
+ "loss": 0.6774,
201
+ "step": 32
202
+ },
203
+ {
204
+ "epoch": 0.87,
205
+ "learning_rate": 4.48e-05,
206
+ "loss": 0.678,
207
+ "step": 33
208
+ },
209
+ {
210
+ "epoch": 0.89,
211
+ "learning_rate": 4.44235294117647e-05,
212
+ "loss": 0.6657,
213
+ "step": 34
214
+ },
215
+ {
216
+ "epoch": 0.92,
217
+ "learning_rate": 4.4047058823529415e-05,
218
+ "loss": 0.6539,
219
+ "step": 35
220
+ },
221
+ {
222
+ "epoch": 0.95,
223
+ "learning_rate": 4.367058823529411e-05,
224
+ "loss": 0.662,
225
+ "step": 36
226
+ },
227
+ {
228
+ "epoch": 0.97,
229
+ "learning_rate": 4.329411764705882e-05,
230
+ "loss": 0.7082,
231
+ "step": 37
232
+ },
233
+ {
234
+ "epoch": 1.0,
235
+ "learning_rate": 4.291764705882353e-05,
236
+ "loss": 0.6554,
237
+ "step": 38
238
+ },
239
+ {
240
+ "epoch": 1.0,
241
+ "eval_accuracy": 0.6052631578947368,
242
+ "eval_auc": 0.9916264090177134,
243
+ "eval_f1": 0.0,
244
+ "eval_loss": 0.665397047996521,
245
+ "eval_precision": 0.0,
246
+ "eval_recall": 0.0,
247
+ "eval_runtime": 14.6602,
248
+ "eval_samples_per_second": 7.776,
249
+ "eval_steps_per_second": 0.341,
250
+ "step": 38
251
+ }
252
+ ],
253
+ "logging_steps": 1,
254
+ "max_steps": 152,
255
+ "num_input_tokens_seen": 0,
256
+ "num_train_epochs": 4,
257
+ "save_steps": 500,
258
+ "total_flos": 9662108559667200.0,
259
+ "train_batch_size": 12,
260
+ "trial_name": null,
261
+ "trial_params": null
262
+ }
checkpoint-38/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b43bbb7646e77fbfe08fc58bdd0570e06512356b907dac87a07a6fef2ab304d5
3
+ size 4728
checkpoint-76/config.json ADDED
@@ -0,0 +1,50 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "microsoft/resnet-50",
3
+ "_num_labels": 2,
4
+ "architectures": [
5
+ "ResNetForImageClassification"
6
+ ],
7
+ "depths": [
8
+ 3,
9
+ 4,
10
+ 6,
11
+ 3
12
+ ],
13
+ "downsample_in_bottleneck": false,
14
+ "downsample_in_first_stage": false,
15
+ "embedding_size": 64,
16
+ "hidden_act": "relu",
17
+ "hidden_sizes": [
18
+ 256,
19
+ 512,
20
+ 1024,
21
+ 2048
22
+ ],
23
+ "id2label": {
24
+ "0": "noyt",
25
+ "1": "yt"
26
+ },
27
+ "label2id": {
28
+ "noyt": 0,
29
+ "yt": 1
30
+ },
31
+ "layer_type": "bottleneck",
32
+ "model_type": "resnet",
33
+ "num_channels": 3,
34
+ "out_features": [
35
+ "stage4"
36
+ ],
37
+ "out_indices": [
38
+ 4
39
+ ],
40
+ "problem_type": "single_label_classification",
41
+ "stage_names": [
42
+ "stem",
43
+ "stage1",
44
+ "stage2",
45
+ "stage3",
46
+ "stage4"
47
+ ],
48
+ "torch_dtype": "float32",
49
+ "transformers_version": "4.36.1"
50
+ }
checkpoint-76/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ecc9e898998da5b3be9a775908736253e10f4967204973e0c6808f448e75c8bf
3
+ size 94302952
checkpoint-76/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9b76fffd211174dc447cbfdea2e45eb8acea41a89e37e58add8117a3634aff19
3
+ size 188228026
checkpoint-76/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5df0a81516b37bfcdee4126da382055bf5fd8d3e239c6aad24a3430691a62634
3
+ size 13990
checkpoint-76/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c603313ca6f729a48feceadc369a317c4addcbe278d2c47c8adfe2e34a106168
3
+ size 1064
checkpoint-76/trainer_state.json ADDED
@@ -0,0 +1,503 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.6067062616348267,
3
+ "best_model_checkpoint": "/tmp/model/checkpoint-76",
4
+ "epoch": 2.0,
5
+ "eval_steps": 500,
6
+ "global_step": 76,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.03,
13
+ "learning_rate": 3.2e-06,
14
+ "loss": 0.6931,
15
+ "step": 1
16
+ },
17
+ {
18
+ "epoch": 0.05,
19
+ "learning_rate": 6.4e-06,
20
+ "loss": 0.6931,
21
+ "step": 2
22
+ },
23
+ {
24
+ "epoch": 0.08,
25
+ "learning_rate": 9.6e-06,
26
+ "loss": 0.6931,
27
+ "step": 3
28
+ },
29
+ {
30
+ "epoch": 0.11,
31
+ "learning_rate": 1.28e-05,
32
+ "loss": 0.693,
33
+ "step": 4
34
+ },
35
+ {
36
+ "epoch": 0.13,
37
+ "learning_rate": 1.6e-05,
38
+ "loss": 0.6929,
39
+ "step": 5
40
+ },
41
+ {
42
+ "epoch": 0.16,
43
+ "learning_rate": 1.92e-05,
44
+ "loss": 0.6927,
45
+ "step": 6
46
+ },
47
+ {
48
+ "epoch": 0.18,
49
+ "learning_rate": 2.24e-05,
50
+ "loss": 0.6921,
51
+ "step": 7
52
+ },
53
+ {
54
+ "epoch": 0.21,
55
+ "learning_rate": 2.56e-05,
56
+ "loss": 0.6916,
57
+ "step": 8
58
+ },
59
+ {
60
+ "epoch": 0.24,
61
+ "learning_rate": 2.88e-05,
62
+ "loss": 0.6903,
63
+ "step": 9
64
+ },
65
+ {
66
+ "epoch": 0.26,
67
+ "learning_rate": 3.2e-05,
68
+ "loss": 0.692,
69
+ "step": 10
70
+ },
71
+ {
72
+ "epoch": 0.29,
73
+ "learning_rate": 3.52e-05,
74
+ "loss": 0.6883,
75
+ "step": 11
76
+ },
77
+ {
78
+ "epoch": 0.32,
79
+ "learning_rate": 3.84e-05,
80
+ "loss": 0.6922,
81
+ "step": 12
82
+ },
83
+ {
84
+ "epoch": 0.34,
85
+ "learning_rate": 4.1599999999999995e-05,
86
+ "loss": 0.6872,
87
+ "step": 13
88
+ },
89
+ {
90
+ "epoch": 0.37,
91
+ "learning_rate": 4.48e-05,
92
+ "loss": 0.6915,
93
+ "step": 14
94
+ },
95
+ {
96
+ "epoch": 0.39,
97
+ "learning_rate": 4.8e-05,
98
+ "loss": 0.6924,
99
+ "step": 15
100
+ },
101
+ {
102
+ "epoch": 0.42,
103
+ "learning_rate": 5.12e-05,
104
+ "loss": 0.6924,
105
+ "step": 16
106
+ },
107
+ {
108
+ "epoch": 0.45,
109
+ "learning_rate": 5.08235294117647e-05,
110
+ "loss": 0.6804,
111
+ "step": 17
112
+ },
113
+ {
114
+ "epoch": 0.47,
115
+ "learning_rate": 5.0447058823529415e-05,
116
+ "loss": 0.6788,
117
+ "step": 18
118
+ },
119
+ {
120
+ "epoch": 0.5,
121
+ "learning_rate": 5.007058823529411e-05,
122
+ "loss": 0.6869,
123
+ "step": 19
124
+ },
125
+ {
126
+ "epoch": 0.53,
127
+ "learning_rate": 4.969411764705882e-05,
128
+ "loss": 0.681,
129
+ "step": 20
130
+ },
131
+ {
132
+ "epoch": 0.55,
133
+ "learning_rate": 4.931764705882353e-05,
134
+ "loss": 0.6895,
135
+ "step": 21
136
+ },
137
+ {
138
+ "epoch": 0.58,
139
+ "learning_rate": 4.8941176470588235e-05,
140
+ "loss": 0.6844,
141
+ "step": 22
142
+ },
143
+ {
144
+ "epoch": 0.61,
145
+ "learning_rate": 4.856470588235294e-05,
146
+ "loss": 0.6761,
147
+ "step": 23
148
+ },
149
+ {
150
+ "epoch": 0.63,
151
+ "learning_rate": 4.8188235294117645e-05,
152
+ "loss": 0.6691,
153
+ "step": 24
154
+ },
155
+ {
156
+ "epoch": 0.66,
157
+ "learning_rate": 4.781176470588235e-05,
158
+ "loss": 0.6717,
159
+ "step": 25
160
+ },
161
+ {
162
+ "epoch": 0.68,
163
+ "learning_rate": 4.7435294117647055e-05,
164
+ "loss": 0.6752,
165
+ "step": 26
166
+ },
167
+ {
168
+ "epoch": 0.71,
169
+ "learning_rate": 4.705882352941176e-05,
170
+ "loss": 0.6837,
171
+ "step": 27
172
+ },
173
+ {
174
+ "epoch": 0.74,
175
+ "learning_rate": 4.6682352941176466e-05,
176
+ "loss": 0.6834,
177
+ "step": 28
178
+ },
179
+ {
180
+ "epoch": 0.76,
181
+ "learning_rate": 4.630588235294118e-05,
182
+ "loss": 0.6646,
183
+ "step": 29
184
+ },
185
+ {
186
+ "epoch": 0.79,
187
+ "learning_rate": 4.592941176470588e-05,
188
+ "loss": 0.6719,
189
+ "step": 30
190
+ },
191
+ {
192
+ "epoch": 0.82,
193
+ "learning_rate": 4.555294117647058e-05,
194
+ "loss": 0.667,
195
+ "step": 31
196
+ },
197
+ {
198
+ "epoch": 0.84,
199
+ "learning_rate": 4.517647058823529e-05,
200
+ "loss": 0.6774,
201
+ "step": 32
202
+ },
203
+ {
204
+ "epoch": 0.87,
205
+ "learning_rate": 4.48e-05,
206
+ "loss": 0.678,
207
+ "step": 33
208
+ },
209
+ {
210
+ "epoch": 0.89,
211
+ "learning_rate": 4.44235294117647e-05,
212
+ "loss": 0.6657,
213
+ "step": 34
214
+ },
215
+ {
216
+ "epoch": 0.92,
217
+ "learning_rate": 4.4047058823529415e-05,
218
+ "loss": 0.6539,
219
+ "step": 35
220
+ },
221
+ {
222
+ "epoch": 0.95,
223
+ "learning_rate": 4.367058823529411e-05,
224
+ "loss": 0.662,
225
+ "step": 36
226
+ },
227
+ {
228
+ "epoch": 0.97,
229
+ "learning_rate": 4.329411764705882e-05,
230
+ "loss": 0.7082,
231
+ "step": 37
232
+ },
233
+ {
234
+ "epoch": 1.0,
235
+ "learning_rate": 4.291764705882353e-05,
236
+ "loss": 0.6554,
237
+ "step": 38
238
+ },
239
+ {
240
+ "epoch": 1.0,
241
+ "eval_accuracy": 0.6052631578947368,
242
+ "eval_auc": 0.9916264090177134,
243
+ "eval_f1": 0.0,
244
+ "eval_loss": 0.665397047996521,
245
+ "eval_precision": 0.0,
246
+ "eval_recall": 0.0,
247
+ "eval_runtime": 14.6602,
248
+ "eval_samples_per_second": 7.776,
249
+ "eval_steps_per_second": 0.341,
250
+ "step": 38
251
+ },
252
+ {
253
+ "epoch": 1.03,
254
+ "learning_rate": 4.2541176470588235e-05,
255
+ "loss": 0.638,
256
+ "step": 39
257
+ },
258
+ {
259
+ "epoch": 1.05,
260
+ "learning_rate": 4.216470588235294e-05,
261
+ "loss": 0.6432,
262
+ "step": 40
263
+ },
264
+ {
265
+ "epoch": 1.08,
266
+ "learning_rate": 4.1788235294117646e-05,
267
+ "loss": 0.6896,
268
+ "step": 41
269
+ },
270
+ {
271
+ "epoch": 1.11,
272
+ "learning_rate": 4.141176470588235e-05,
273
+ "loss": 0.677,
274
+ "step": 42
275
+ },
276
+ {
277
+ "epoch": 1.13,
278
+ "learning_rate": 4.1035294117647056e-05,
279
+ "loss": 0.6312,
280
+ "step": 43
281
+ },
282
+ {
283
+ "epoch": 1.16,
284
+ "learning_rate": 4.065882352941176e-05,
285
+ "loss": 0.637,
286
+ "step": 44
287
+ },
288
+ {
289
+ "epoch": 1.18,
290
+ "learning_rate": 4.0282352941176466e-05,
291
+ "loss": 0.6274,
292
+ "step": 45
293
+ },
294
+ {
295
+ "epoch": 1.21,
296
+ "learning_rate": 3.990588235294118e-05,
297
+ "loss": 0.6335,
298
+ "step": 46
299
+ },
300
+ {
301
+ "epoch": 1.24,
302
+ "learning_rate": 3.952941176470588e-05,
303
+ "loss": 0.6302,
304
+ "step": 47
305
+ },
306
+ {
307
+ "epoch": 1.26,
308
+ "learning_rate": 3.915294117647058e-05,
309
+ "loss": 0.6223,
310
+ "step": 48
311
+ },
312
+ {
313
+ "epoch": 1.29,
314
+ "learning_rate": 3.877647058823529e-05,
315
+ "loss": 0.668,
316
+ "step": 49
317
+ },
318
+ {
319
+ "epoch": 1.32,
320
+ "learning_rate": 3.84e-05,
321
+ "loss": 0.6216,
322
+ "step": 50
323
+ },
324
+ {
325
+ "epoch": 1.34,
326
+ "learning_rate": 3.80235294117647e-05,
327
+ "loss": 0.6518,
328
+ "step": 51
329
+ },
330
+ {
331
+ "epoch": 1.37,
332
+ "learning_rate": 3.7647058823529415e-05,
333
+ "loss": 0.6599,
334
+ "step": 52
335
+ },
336
+ {
337
+ "epoch": 1.39,
338
+ "learning_rate": 3.7270588235294114e-05,
339
+ "loss": 0.6562,
340
+ "step": 53
341
+ },
342
+ {
343
+ "epoch": 1.42,
344
+ "learning_rate": 3.689411764705882e-05,
345
+ "loss": 0.6329,
346
+ "step": 54
347
+ },
348
+ {
349
+ "epoch": 1.45,
350
+ "learning_rate": 3.651764705882353e-05,
351
+ "loss": 0.6358,
352
+ "step": 55
353
+ },
354
+ {
355
+ "epoch": 1.47,
356
+ "learning_rate": 3.6141176470588236e-05,
357
+ "loss": 0.6074,
358
+ "step": 56
359
+ },
360
+ {
361
+ "epoch": 1.5,
362
+ "learning_rate": 3.576470588235294e-05,
363
+ "loss": 0.6036,
364
+ "step": 57
365
+ },
366
+ {
367
+ "epoch": 1.53,
368
+ "learning_rate": 3.5388235294117646e-05,
369
+ "loss": 0.6039,
370
+ "step": 58
371
+ },
372
+ {
373
+ "epoch": 1.55,
374
+ "learning_rate": 3.501176470588235e-05,
375
+ "loss": 0.6243,
376
+ "step": 59
377
+ },
378
+ {
379
+ "epoch": 1.58,
380
+ "learning_rate": 3.4635294117647056e-05,
381
+ "loss": 0.6479,
382
+ "step": 60
383
+ },
384
+ {
385
+ "epoch": 1.61,
386
+ "learning_rate": 3.425882352941176e-05,
387
+ "loss": 0.6312,
388
+ "step": 61
389
+ },
390
+ {
391
+ "epoch": 1.63,
392
+ "learning_rate": 3.3882352941176466e-05,
393
+ "loss": 0.6259,
394
+ "step": 62
395
+ },
396
+ {
397
+ "epoch": 1.66,
398
+ "learning_rate": 3.350588235294118e-05,
399
+ "loss": 0.6058,
400
+ "step": 63
401
+ },
402
+ {
403
+ "epoch": 1.68,
404
+ "learning_rate": 3.312941176470588e-05,
405
+ "loss": 0.5793,
406
+ "step": 64
407
+ },
408
+ {
409
+ "epoch": 1.71,
410
+ "learning_rate": 3.275294117647058e-05,
411
+ "loss": 0.6781,
412
+ "step": 65
413
+ },
414
+ {
415
+ "epoch": 1.74,
416
+ "learning_rate": 3.2376470588235293e-05,
417
+ "loss": 0.599,
418
+ "step": 66
419
+ },
420
+ {
421
+ "epoch": 1.76,
422
+ "learning_rate": 3.2e-05,
423
+ "loss": 0.5805,
424
+ "step": 67
425
+ },
426
+ {
427
+ "epoch": 1.79,
428
+ "learning_rate": 3.1623529411764704e-05,
429
+ "loss": 0.5873,
430
+ "step": 68
431
+ },
432
+ {
433
+ "epoch": 1.82,
434
+ "learning_rate": 3.1247058823529416e-05,
435
+ "loss": 0.6044,
436
+ "step": 69
437
+ },
438
+ {
439
+ "epoch": 1.84,
440
+ "learning_rate": 3.0870588235294114e-05,
441
+ "loss": 0.5808,
442
+ "step": 70
443
+ },
444
+ {
445
+ "epoch": 1.87,
446
+ "learning_rate": 3.0494117647058822e-05,
447
+ "loss": 0.5655,
448
+ "step": 71
449
+ },
450
+ {
451
+ "epoch": 1.89,
452
+ "learning_rate": 3.0117647058823527e-05,
453
+ "loss": 0.5661,
454
+ "step": 72
455
+ },
456
+ {
457
+ "epoch": 1.92,
458
+ "learning_rate": 2.9741176470588236e-05,
459
+ "loss": 0.6197,
460
+ "step": 73
461
+ },
462
+ {
463
+ "epoch": 1.95,
464
+ "learning_rate": 2.9364705882352938e-05,
465
+ "loss": 0.6197,
466
+ "step": 74
467
+ },
468
+ {
469
+ "epoch": 1.97,
470
+ "learning_rate": 2.8988235294117646e-05,
471
+ "loss": 0.6297,
472
+ "step": 75
473
+ },
474
+ {
475
+ "epoch": 2.0,
476
+ "learning_rate": 2.861176470588235e-05,
477
+ "loss": 0.5994,
478
+ "step": 76
479
+ },
480
+ {
481
+ "epoch": 2.0,
482
+ "eval_accuracy": 0.6052631578947368,
483
+ "eval_auc": 1.0,
484
+ "eval_f1": 0.0,
485
+ "eval_loss": 0.6067062616348267,
486
+ "eval_precision": 0.0,
487
+ "eval_recall": 0.0,
488
+ "eval_runtime": 17.1278,
489
+ "eval_samples_per_second": 6.656,
490
+ "eval_steps_per_second": 0.292,
491
+ "step": 76
492
+ }
493
+ ],
494
+ "logging_steps": 1,
495
+ "max_steps": 152,
496
+ "num_input_tokens_seen": 0,
497
+ "num_train_epochs": 4,
498
+ "save_steps": 500,
499
+ "total_flos": 1.93242171193344e+16,
500
+ "train_batch_size": 12,
501
+ "trial_name": null,
502
+ "trial_params": null
503
+ }
checkpoint-76/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b43bbb7646e77fbfe08fc58bdd0570e06512356b907dac87a07a6fef2ab304d5
3
+ size 4728
config.json ADDED
@@ -0,0 +1,50 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "microsoft/resnet-50",
3
+ "_num_labels": 2,
4
+ "architectures": [
5
+ "ResNetForImageClassification"
6
+ ],
7
+ "depths": [
8
+ 3,
9
+ 4,
10
+ 6,
11
+ 3
12
+ ],
13
+ "downsample_in_bottleneck": false,
14
+ "downsample_in_first_stage": false,
15
+ "embedding_size": 64,
16
+ "hidden_act": "relu",
17
+ "hidden_sizes": [
18
+ 256,
19
+ 512,
20
+ 1024,
21
+ 2048
22
+ ],
23
+ "id2label": {
24
+ "0": "noyt",
25
+ "1": "yt"
26
+ },
27
+ "label2id": {
28
+ "noyt": 0,
29
+ "yt": 1
30
+ },
31
+ "layer_type": "bottleneck",
32
+ "model_type": "resnet",
33
+ "num_channels": 3,
34
+ "out_features": [
35
+ "stage4"
36
+ ],
37
+ "out_indices": [
38
+ 4
39
+ ],
40
+ "problem_type": "single_label_classification",
41
+ "stage_names": [
42
+ "stem",
43
+ "stage1",
44
+ "stage2",
45
+ "stage3",
46
+ "stage4"
47
+ ],
48
+ "torch_dtype": "float32",
49
+ "transformers_version": "4.36.1"
50
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c45a39ba983c9f5f8c36000e20c57e4eaf4cc38d1d305c0665f2d463d78cfa1d
3
+ size 94302952
preprocessor_config.json ADDED
@@ -0,0 +1,22 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "crop_pct": 0.875,
3
+ "do_normalize": true,
4
+ "do_rescale": true,
5
+ "do_resize": true,
6
+ "image_mean": [
7
+ 0.485,
8
+ 0.456,
9
+ 0.406
10
+ ],
11
+ "image_processor_type": "ConvNextImageProcessor",
12
+ "image_std": [
13
+ 0.229,
14
+ 0.224,
15
+ 0.225
16
+ ],
17
+ "resample": 3,
18
+ "rescale_factor": 0.00392156862745098,
19
+ "size": {
20
+ "shortest_edge": 224
21
+ }
22
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b43bbb7646e77fbfe08fc58bdd0570e06512356b907dac87a07a6fef2ab304d5
3
+ size 4728
training_params.json ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "data_path": "Naterea/autotrain-data-yt_noyt_V2_MoreData_3",
3
+ "model": "microsoft/resnet-50",
4
+ "lr": 5.12e-05,
5
+ "epochs": 4,
6
+ "batch_size": 12,
7
+ "warmup_ratio": 0.1,
8
+ "gradient_accumulation": 1,
9
+ "optimizer": "adamw_torch",
10
+ "scheduler": "linear",
11
+ "weight_decay": 0.0,
12
+ "max_grad_norm": 1.0,
13
+ "seed": 42,
14
+ "train_split": "train",
15
+ "valid_split": "validation",
16
+ "logging_steps": -1,
17
+ "project_name": "/tmp/model",
18
+ "auto_find_batch_size": false,
19
+ "mixed_precision": "fp32",
20
+ "save_total_limit": 12,
21
+ "save_strategy": "epoch",
22
+ "push_to_hub": true,
23
+ "repo_id": "Naterea/yt_noyt_V2_MoreData_3-0",
24
+ "evaluation_strategy": "epoch",
25
+ "image_column": "autotrain_image",
26
+ "target_column": "autotrain_label",
27
+ "log": "none"
28
+ }