Emilio407 commited on
Commit
27e4307
·
verified ·
1 Parent(s): 06bdee1

Upload folder using huggingface_hub

Browse files
README.md ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+
2
+ ---
3
+ tags:
4
+ - autotrain
5
+ - image-classification
6
+ base_model: microsoft/resnet-50
7
+ widget:
8
+ - src: https://huggingface.co/datasets/mishig/sample_images/resolve/main/tiger.jpg
9
+ example_title: Tiger
10
+ - src: https://huggingface.co/datasets/mishig/sample_images/resolve/main/teapot.jpg
11
+ example_title: Teapot
12
+ - src: https://huggingface.co/datasets/mishig/sample_images/resolve/main/palace.jpg
13
+ example_title: Palace
14
+ ---
15
+
16
+ # Model Trained Using AutoTrain
17
+
18
+ - Problem type: Image Classification
19
+
20
+ ## Validation Metrics
21
+ loss: 0.6819557547569275
22
+
23
+ f1: 0.6808510638297872
24
+
25
+ precision: 0.5333333333333333
26
+
27
+ recall: 0.9411764705882353
28
+
29
+ auc: 0.6039915966386554
30
+
31
+ accuracy: 0.5161290322580645
checkpoint-96/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": "no",
25
+ "1": "yes"
26
+ },
27
+ "label2id": {
28
+ "no": 0,
29
+ "yes": 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": "4.44.0"
50
+ }
checkpoint-96/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:60542323dbdd56c2e70952bb1e2ea38bf1083618d28f7671137ca73f11ab8314
3
+ size 94302952
checkpoint-96/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bde7cc55a28541aef4d3a753fe7e2bb2ce80156ed8ec5b67177d13eb9806ccc1
3
+ size 188232506
checkpoint-96/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0db96fb843f3a39b5eedf5a6276eca689c9aa44974ef2a5fce48bfab4ff75119
3
+ size 14244
checkpoint-96/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1d791700bc8335285f71be6cf043f7dd0fd23aa49a4bae0862f8043341b8b866
3
+ size 1064
checkpoint-96/trainer_state.json ADDED
@@ -0,0 +1,792 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.6819557547569275,
3
+ "best_model_checkpoint": "prostate-mri-T2w-v01/checkpoint-96",
4
+ "epoch": 6.0,
5
+ "eval_steps": 500,
6
+ "global_step": 96,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.0625,
13
+ "grad_norm": 6.9218926429748535,
14
+ "learning_rate": 6.25e-07,
15
+ "loss": 0.7026,
16
+ "step": 1
17
+ },
18
+ {
19
+ "epoch": 0.125,
20
+ "grad_norm": 8.463187217712402,
21
+ "learning_rate": 1.25e-06,
22
+ "loss": 0.6897,
23
+ "step": 2
24
+ },
25
+ {
26
+ "epoch": 0.1875,
27
+ "grad_norm": 7.885867118835449,
28
+ "learning_rate": 1.875e-06,
29
+ "loss": 0.6738,
30
+ "step": 3
31
+ },
32
+ {
33
+ "epoch": 0.25,
34
+ "grad_norm": 12.486954689025879,
35
+ "learning_rate": 2.5e-06,
36
+ "loss": 0.6963,
37
+ "step": 4
38
+ },
39
+ {
40
+ "epoch": 0.3125,
41
+ "grad_norm": 9.765836715698242,
42
+ "learning_rate": 3.125e-06,
43
+ "loss": 0.6987,
44
+ "step": 5
45
+ },
46
+ {
47
+ "epoch": 0.375,
48
+ "grad_norm": 8.386995315551758,
49
+ "learning_rate": 3.75e-06,
50
+ "loss": 0.7004,
51
+ "step": 6
52
+ },
53
+ {
54
+ "epoch": 0.4375,
55
+ "grad_norm": 9.164388656616211,
56
+ "learning_rate": 4.375e-06,
57
+ "loss": 0.668,
58
+ "step": 7
59
+ },
60
+ {
61
+ "epoch": 0.5,
62
+ "grad_norm": 4.771695137023926,
63
+ "learning_rate": 5e-06,
64
+ "loss": 0.6904,
65
+ "step": 8
66
+ },
67
+ {
68
+ "epoch": 0.5625,
69
+ "grad_norm": 7.426454544067383,
70
+ "learning_rate": 5.625e-06,
71
+ "loss": 0.7024,
72
+ "step": 9
73
+ },
74
+ {
75
+ "epoch": 0.625,
76
+ "grad_norm": 5.934999465942383,
77
+ "learning_rate": 6.25e-06,
78
+ "loss": 0.6982,
79
+ "step": 10
80
+ },
81
+ {
82
+ "epoch": 0.6875,
83
+ "grad_norm": 5.554957389831543,
84
+ "learning_rate": 6.875000000000001e-06,
85
+ "loss": 0.698,
86
+ "step": 11
87
+ },
88
+ {
89
+ "epoch": 0.75,
90
+ "grad_norm": 5.586301326751709,
91
+ "learning_rate": 7.5e-06,
92
+ "loss": 0.686,
93
+ "step": 12
94
+ },
95
+ {
96
+ "epoch": 0.8125,
97
+ "grad_norm": 6.572750091552734,
98
+ "learning_rate": 8.125000000000001e-06,
99
+ "loss": 0.6807,
100
+ "step": 13
101
+ },
102
+ {
103
+ "epoch": 0.875,
104
+ "grad_norm": 5.920419692993164,
105
+ "learning_rate": 8.75e-06,
106
+ "loss": 0.6921,
107
+ "step": 14
108
+ },
109
+ {
110
+ "epoch": 0.9375,
111
+ "grad_norm": 10.7252779006958,
112
+ "learning_rate": 9.375000000000001e-06,
113
+ "loss": 0.6975,
114
+ "step": 15
115
+ },
116
+ {
117
+ "epoch": 1.0,
118
+ "grad_norm": 21.941551208496094,
119
+ "learning_rate": 1e-05,
120
+ "loss": 0.6868,
121
+ "step": 16
122
+ },
123
+ {
124
+ "epoch": 1.0,
125
+ "eval_accuracy": 0.5,
126
+ "eval_auc": 0.4831932773109244,
127
+ "eval_f1": 0.4918032786885246,
128
+ "eval_loss": 0.6948714852333069,
129
+ "eval_precision": 0.5555555555555556,
130
+ "eval_recall": 0.4411764705882353,
131
+ "eval_runtime": 1.0055,
132
+ "eval_samples_per_second": 61.659,
133
+ "eval_steps_per_second": 1.989,
134
+ "step": 16
135
+ },
136
+ {
137
+ "epoch": 1.0625,
138
+ "grad_norm": 7.140624046325684,
139
+ "learning_rate": 1.0625e-05,
140
+ "loss": 0.6921,
141
+ "step": 17
142
+ },
143
+ {
144
+ "epoch": 1.125,
145
+ "grad_norm": 7.36794900894165,
146
+ "learning_rate": 1.125e-05,
147
+ "loss": 0.6877,
148
+ "step": 18
149
+ },
150
+ {
151
+ "epoch": 1.1875,
152
+ "grad_norm": 10.255731582641602,
153
+ "learning_rate": 1.1875e-05,
154
+ "loss": 0.6946,
155
+ "step": 19
156
+ },
157
+ {
158
+ "epoch": 1.25,
159
+ "grad_norm": 7.5590667724609375,
160
+ "learning_rate": 1.25e-05,
161
+ "loss": 0.6873,
162
+ "step": 20
163
+ },
164
+ {
165
+ "epoch": 1.3125,
166
+ "grad_norm": 10.777117729187012,
167
+ "learning_rate": 1.3125e-05,
168
+ "loss": 0.6907,
169
+ "step": 21
170
+ },
171
+ {
172
+ "epoch": 1.375,
173
+ "grad_norm": 6.053137302398682,
174
+ "learning_rate": 1.3750000000000002e-05,
175
+ "loss": 0.677,
176
+ "step": 22
177
+ },
178
+ {
179
+ "epoch": 1.4375,
180
+ "grad_norm": 5.271788120269775,
181
+ "learning_rate": 1.4374999999999999e-05,
182
+ "loss": 0.6919,
183
+ "step": 23
184
+ },
185
+ {
186
+ "epoch": 1.5,
187
+ "grad_norm": 6.248932838439941,
188
+ "learning_rate": 1.5e-05,
189
+ "loss": 0.6938,
190
+ "step": 24
191
+ },
192
+ {
193
+ "epoch": 1.5625,
194
+ "grad_norm": 7.127931118011475,
195
+ "learning_rate": 1.5625e-05,
196
+ "loss": 0.6804,
197
+ "step": 25
198
+ },
199
+ {
200
+ "epoch": 1.625,
201
+ "grad_norm": 5.395265579223633,
202
+ "learning_rate": 1.6250000000000002e-05,
203
+ "loss": 0.6938,
204
+ "step": 26
205
+ },
206
+ {
207
+ "epoch": 1.6875,
208
+ "grad_norm": 8.488815307617188,
209
+ "learning_rate": 1.6875000000000004e-05,
210
+ "loss": 0.6909,
211
+ "step": 27
212
+ },
213
+ {
214
+ "epoch": 1.75,
215
+ "grad_norm": 6.858600616455078,
216
+ "learning_rate": 1.75e-05,
217
+ "loss": 0.6907,
218
+ "step": 28
219
+ },
220
+ {
221
+ "epoch": 1.8125,
222
+ "grad_norm": 7.674286842346191,
223
+ "learning_rate": 1.8125e-05,
224
+ "loss": 0.6912,
225
+ "step": 29
226
+ },
227
+ {
228
+ "epoch": 1.875,
229
+ "grad_norm": 6.898157596588135,
230
+ "learning_rate": 1.8750000000000002e-05,
231
+ "loss": 0.6782,
232
+ "step": 30
233
+ },
234
+ {
235
+ "epoch": 1.9375,
236
+ "grad_norm": 5.758520603179932,
237
+ "learning_rate": 1.9375e-05,
238
+ "loss": 0.7087,
239
+ "step": 31
240
+ },
241
+ {
242
+ "epoch": 2.0,
243
+ "grad_norm": 9.98084831237793,
244
+ "learning_rate": 2e-05,
245
+ "loss": 0.7129,
246
+ "step": 32
247
+ },
248
+ {
249
+ "epoch": 2.0,
250
+ "eval_accuracy": 0.6290322580645161,
251
+ "eval_auc": 0.5273109243697479,
252
+ "eval_f1": 0.6666666666666666,
253
+ "eval_loss": 0.6898942589759827,
254
+ "eval_precision": 0.6571428571428571,
255
+ "eval_recall": 0.6764705882352942,
256
+ "eval_runtime": 0.9907,
257
+ "eval_samples_per_second": 62.581,
258
+ "eval_steps_per_second": 2.019,
259
+ "step": 32
260
+ },
261
+ {
262
+ "epoch": 2.0625,
263
+ "grad_norm": 5.439036846160889,
264
+ "learning_rate": 2.0625e-05,
265
+ "loss": 0.6921,
266
+ "step": 33
267
+ },
268
+ {
269
+ "epoch": 2.125,
270
+ "grad_norm": 5.089821815490723,
271
+ "learning_rate": 2.125e-05,
272
+ "loss": 0.7075,
273
+ "step": 34
274
+ },
275
+ {
276
+ "epoch": 2.1875,
277
+ "grad_norm": 5.559844017028809,
278
+ "learning_rate": 2.1875e-05,
279
+ "loss": 0.6758,
280
+ "step": 35
281
+ },
282
+ {
283
+ "epoch": 2.25,
284
+ "grad_norm": 7.2915496826171875,
285
+ "learning_rate": 2.25e-05,
286
+ "loss": 0.6877,
287
+ "step": 36
288
+ },
289
+ {
290
+ "epoch": 2.3125,
291
+ "grad_norm": 6.99595308303833,
292
+ "learning_rate": 2.3125000000000003e-05,
293
+ "loss": 0.6921,
294
+ "step": 37
295
+ },
296
+ {
297
+ "epoch": 2.375,
298
+ "grad_norm": 5.015499114990234,
299
+ "learning_rate": 2.375e-05,
300
+ "loss": 0.6711,
301
+ "step": 38
302
+ },
303
+ {
304
+ "epoch": 2.4375,
305
+ "grad_norm": 6.5360517501831055,
306
+ "learning_rate": 2.4375e-05,
307
+ "loss": 0.6804,
308
+ "step": 39
309
+ },
310
+ {
311
+ "epoch": 2.5,
312
+ "grad_norm": 6.66691780090332,
313
+ "learning_rate": 2.5e-05,
314
+ "loss": 0.6912,
315
+ "step": 40
316
+ },
317
+ {
318
+ "epoch": 2.5625,
319
+ "grad_norm": 10.940932273864746,
320
+ "learning_rate": 2.5625e-05,
321
+ "loss": 0.699,
322
+ "step": 41
323
+ },
324
+ {
325
+ "epoch": 2.625,
326
+ "grad_norm": 4.8793816566467285,
327
+ "learning_rate": 2.625e-05,
328
+ "loss": 0.6914,
329
+ "step": 42
330
+ },
331
+ {
332
+ "epoch": 2.6875,
333
+ "grad_norm": 5.5832343101501465,
334
+ "learning_rate": 2.6875e-05,
335
+ "loss": 0.6953,
336
+ "step": 43
337
+ },
338
+ {
339
+ "epoch": 2.75,
340
+ "grad_norm": 13.049569129943848,
341
+ "learning_rate": 2.7500000000000004e-05,
342
+ "loss": 0.6973,
343
+ "step": 44
344
+ },
345
+ {
346
+ "epoch": 2.8125,
347
+ "grad_norm": 8.290694236755371,
348
+ "learning_rate": 2.8125000000000003e-05,
349
+ "loss": 0.6978,
350
+ "step": 45
351
+ },
352
+ {
353
+ "epoch": 2.875,
354
+ "grad_norm": 8.824386596679688,
355
+ "learning_rate": 2.8749999999999997e-05,
356
+ "loss": 0.689,
357
+ "step": 46
358
+ },
359
+ {
360
+ "epoch": 2.9375,
361
+ "grad_norm": 8.694557189941406,
362
+ "learning_rate": 2.9375000000000003e-05,
363
+ "loss": 0.7039,
364
+ "step": 47
365
+ },
366
+ {
367
+ "epoch": 3.0,
368
+ "grad_norm": 13.123662948608398,
369
+ "learning_rate": 3e-05,
370
+ "loss": 0.7129,
371
+ "step": 48
372
+ },
373
+ {
374
+ "epoch": 3.0,
375
+ "eval_accuracy": 0.5806451612903226,
376
+ "eval_auc": 0.5189075630252101,
377
+ "eval_f1": 0.6976744186046512,
378
+ "eval_loss": 0.6869328618049622,
379
+ "eval_precision": 0.5769230769230769,
380
+ "eval_recall": 0.8823529411764706,
381
+ "eval_runtime": 0.9817,
382
+ "eval_samples_per_second": 63.153,
383
+ "eval_steps_per_second": 2.037,
384
+ "step": 48
385
+ },
386
+ {
387
+ "epoch": 3.0625,
388
+ "grad_norm": 8.405984878540039,
389
+ "learning_rate": 3.0625000000000006e-05,
390
+ "loss": 0.6912,
391
+ "step": 49
392
+ },
393
+ {
394
+ "epoch": 3.125,
395
+ "grad_norm": 11.393486976623535,
396
+ "learning_rate": 3.125e-05,
397
+ "loss": 0.679,
398
+ "step": 50
399
+ },
400
+ {
401
+ "epoch": 3.1875,
402
+ "grad_norm": 7.367499828338623,
403
+ "learning_rate": 3.1875e-05,
404
+ "loss": 0.7205,
405
+ "step": 51
406
+ },
407
+ {
408
+ "epoch": 3.25,
409
+ "grad_norm": 7.851259231567383,
410
+ "learning_rate": 3.2500000000000004e-05,
411
+ "loss": 0.6877,
412
+ "step": 52
413
+ },
414
+ {
415
+ "epoch": 3.3125,
416
+ "grad_norm": 15.551215171813965,
417
+ "learning_rate": 3.3125e-05,
418
+ "loss": 0.6865,
419
+ "step": 53
420
+ },
421
+ {
422
+ "epoch": 3.375,
423
+ "grad_norm": 6.169222354888916,
424
+ "learning_rate": 3.375000000000001e-05,
425
+ "loss": 0.6853,
426
+ "step": 54
427
+ },
428
+ {
429
+ "epoch": 3.4375,
430
+ "grad_norm": 5.225166320800781,
431
+ "learning_rate": 3.4375e-05,
432
+ "loss": 0.6951,
433
+ "step": 55
434
+ },
435
+ {
436
+ "epoch": 3.5,
437
+ "grad_norm": 6.697177886962891,
438
+ "learning_rate": 3.5e-05,
439
+ "loss": 0.6738,
440
+ "step": 56
441
+ },
442
+ {
443
+ "epoch": 3.5625,
444
+ "grad_norm": 8.565425872802734,
445
+ "learning_rate": 3.5625000000000005e-05,
446
+ "loss": 0.6936,
447
+ "step": 57
448
+ },
449
+ {
450
+ "epoch": 3.625,
451
+ "grad_norm": 4.674345970153809,
452
+ "learning_rate": 3.625e-05,
453
+ "loss": 0.7007,
454
+ "step": 58
455
+ },
456
+ {
457
+ "epoch": 3.6875,
458
+ "grad_norm": 6.7598371505737305,
459
+ "learning_rate": 3.6875e-05,
460
+ "loss": 0.7031,
461
+ "step": 59
462
+ },
463
+ {
464
+ "epoch": 3.75,
465
+ "grad_norm": 5.33363151550293,
466
+ "learning_rate": 3.7500000000000003e-05,
467
+ "loss": 0.6978,
468
+ "step": 60
469
+ },
470
+ {
471
+ "epoch": 3.8125,
472
+ "grad_norm": 4.975074291229248,
473
+ "learning_rate": 3.8125e-05,
474
+ "loss": 0.6992,
475
+ "step": 61
476
+ },
477
+ {
478
+ "epoch": 3.875,
479
+ "grad_norm": 5.9460673332214355,
480
+ "learning_rate": 3.875e-05,
481
+ "loss": 0.698,
482
+ "step": 62
483
+ },
484
+ {
485
+ "epoch": 3.9375,
486
+ "grad_norm": 6.137637615203857,
487
+ "learning_rate": 3.9375e-05,
488
+ "loss": 0.6721,
489
+ "step": 63
490
+ },
491
+ {
492
+ "epoch": 4.0,
493
+ "grad_norm": 7.683951377868652,
494
+ "learning_rate": 4e-05,
495
+ "loss": 0.6458,
496
+ "step": 64
497
+ },
498
+ {
499
+ "epoch": 4.0,
500
+ "eval_accuracy": 0.5806451612903226,
501
+ "eval_auc": 0.4690126050420168,
502
+ "eval_f1": 0.675,
503
+ "eval_loss": 0.6907132267951965,
504
+ "eval_precision": 0.5869565217391305,
505
+ "eval_recall": 0.7941176470588235,
506
+ "eval_runtime": 1.0012,
507
+ "eval_samples_per_second": 61.926,
508
+ "eval_steps_per_second": 1.998,
509
+ "step": 64
510
+ },
511
+ {
512
+ "epoch": 4.0625,
513
+ "grad_norm": 6.240651607513428,
514
+ "learning_rate": 4.0625000000000005e-05,
515
+ "loss": 0.6936,
516
+ "step": 65
517
+ },
518
+ {
519
+ "epoch": 4.125,
520
+ "grad_norm": 6.195248603820801,
521
+ "learning_rate": 4.125e-05,
522
+ "loss": 0.7053,
523
+ "step": 66
524
+ },
525
+ {
526
+ "epoch": 4.1875,
527
+ "grad_norm": 5.479919910430908,
528
+ "learning_rate": 4.1875e-05,
529
+ "loss": 0.6921,
530
+ "step": 67
531
+ },
532
+ {
533
+ "epoch": 4.25,
534
+ "grad_norm": 6.832111835479736,
535
+ "learning_rate": 4.25e-05,
536
+ "loss": 0.6721,
537
+ "step": 68
538
+ },
539
+ {
540
+ "epoch": 4.3125,
541
+ "grad_norm": 7.457818984985352,
542
+ "learning_rate": 4.3125000000000005e-05,
543
+ "loss": 0.6838,
544
+ "step": 69
545
+ },
546
+ {
547
+ "epoch": 4.375,
548
+ "grad_norm": 9.509450912475586,
549
+ "learning_rate": 4.375e-05,
550
+ "loss": 0.6978,
551
+ "step": 70
552
+ },
553
+ {
554
+ "epoch": 4.4375,
555
+ "grad_norm": 4.208181381225586,
556
+ "learning_rate": 4.4375e-05,
557
+ "loss": 0.6863,
558
+ "step": 71
559
+ },
560
+ {
561
+ "epoch": 4.5,
562
+ "grad_norm": 5.488190174102783,
563
+ "learning_rate": 4.5e-05,
564
+ "loss": 0.6948,
565
+ "step": 72
566
+ },
567
+ {
568
+ "epoch": 4.5625,
569
+ "grad_norm": 6.613465309143066,
570
+ "learning_rate": 4.5625e-05,
571
+ "loss": 0.7004,
572
+ "step": 73
573
+ },
574
+ {
575
+ "epoch": 4.625,
576
+ "grad_norm": 7.014777660369873,
577
+ "learning_rate": 4.6250000000000006e-05,
578
+ "loss": 0.6562,
579
+ "step": 74
580
+ },
581
+ {
582
+ "epoch": 4.6875,
583
+ "grad_norm": 9.429577827453613,
584
+ "learning_rate": 4.6875e-05,
585
+ "loss": 0.7031,
586
+ "step": 75
587
+ },
588
+ {
589
+ "epoch": 4.75,
590
+ "grad_norm": 4.446032524108887,
591
+ "learning_rate": 4.75e-05,
592
+ "loss": 0.6848,
593
+ "step": 76
594
+ },
595
+ {
596
+ "epoch": 4.8125,
597
+ "grad_norm": 8.153448104858398,
598
+ "learning_rate": 4.8125000000000004e-05,
599
+ "loss": 0.699,
600
+ "step": 77
601
+ },
602
+ {
603
+ "epoch": 4.875,
604
+ "grad_norm": 7.079260349273682,
605
+ "learning_rate": 4.875e-05,
606
+ "loss": 0.6843,
607
+ "step": 78
608
+ },
609
+ {
610
+ "epoch": 4.9375,
611
+ "grad_norm": 4.8226213455200195,
612
+ "learning_rate": 4.937500000000001e-05,
613
+ "loss": 0.6763,
614
+ "step": 79
615
+ },
616
+ {
617
+ "epoch": 5.0,
618
+ "grad_norm": 16.139135360717773,
619
+ "learning_rate": 5e-05,
620
+ "loss": 0.651,
621
+ "step": 80
622
+ },
623
+ {
624
+ "epoch": 5.0,
625
+ "eval_accuracy": 0.5,
626
+ "eval_auc": 0.5246848739495799,
627
+ "eval_f1": 0.6666666666666666,
628
+ "eval_loss": 0.6864917278289795,
629
+ "eval_precision": 0.5254237288135594,
630
+ "eval_recall": 0.9117647058823529,
631
+ "eval_runtime": 1.0013,
632
+ "eval_samples_per_second": 61.918,
633
+ "eval_steps_per_second": 1.997,
634
+ "step": 80
635
+ },
636
+ {
637
+ "epoch": 5.0625,
638
+ "grad_norm": 6.197685718536377,
639
+ "learning_rate": 4.993055555555556e-05,
640
+ "loss": 0.678,
641
+ "step": 81
642
+ },
643
+ {
644
+ "epoch": 5.125,
645
+ "grad_norm": 5.559277057647705,
646
+ "learning_rate": 4.986111111111111e-05,
647
+ "loss": 0.6677,
648
+ "step": 82
649
+ },
650
+ {
651
+ "epoch": 5.1875,
652
+ "grad_norm": 11.058768272399902,
653
+ "learning_rate": 4.979166666666667e-05,
654
+ "loss": 0.6851,
655
+ "step": 83
656
+ },
657
+ {
658
+ "epoch": 5.25,
659
+ "grad_norm": 7.209768772125244,
660
+ "learning_rate": 4.972222222222223e-05,
661
+ "loss": 0.6838,
662
+ "step": 84
663
+ },
664
+ {
665
+ "epoch": 5.3125,
666
+ "grad_norm": 5.192998886108398,
667
+ "learning_rate": 4.965277777777778e-05,
668
+ "loss": 0.6899,
669
+ "step": 85
670
+ },
671
+ {
672
+ "epoch": 5.375,
673
+ "grad_norm": 6.706368923187256,
674
+ "learning_rate": 4.958333333333334e-05,
675
+ "loss": 0.6956,
676
+ "step": 86
677
+ },
678
+ {
679
+ "epoch": 5.4375,
680
+ "grad_norm": 8.244791030883789,
681
+ "learning_rate": 4.951388888888889e-05,
682
+ "loss": 0.6785,
683
+ "step": 87
684
+ },
685
+ {
686
+ "epoch": 5.5,
687
+ "grad_norm": 10.724773406982422,
688
+ "learning_rate": 4.9444444444444446e-05,
689
+ "loss": 0.6863,
690
+ "step": 88
691
+ },
692
+ {
693
+ "epoch": 5.5625,
694
+ "grad_norm": 5.7804484367370605,
695
+ "learning_rate": 4.937500000000001e-05,
696
+ "loss": 0.6404,
697
+ "step": 89
698
+ },
699
+ {
700
+ "epoch": 5.625,
701
+ "grad_norm": 8.586164474487305,
702
+ "learning_rate": 4.930555555555556e-05,
703
+ "loss": 0.6904,
704
+ "step": 90
705
+ },
706
+ {
707
+ "epoch": 5.6875,
708
+ "grad_norm": 7.401065826416016,
709
+ "learning_rate": 4.923611111111112e-05,
710
+ "loss": 0.6985,
711
+ "step": 91
712
+ },
713
+ {
714
+ "epoch": 5.75,
715
+ "grad_norm": 6.9926042556762695,
716
+ "learning_rate": 4.9166666666666665e-05,
717
+ "loss": 0.667,
718
+ "step": 92
719
+ },
720
+ {
721
+ "epoch": 5.8125,
722
+ "grad_norm": 6.541015625,
723
+ "learning_rate": 4.909722222222222e-05,
724
+ "loss": 0.6868,
725
+ "step": 93
726
+ },
727
+ {
728
+ "epoch": 5.875,
729
+ "grad_norm": 8.960890769958496,
730
+ "learning_rate": 4.902777777777778e-05,
731
+ "loss": 0.7009,
732
+ "step": 94
733
+ },
734
+ {
735
+ "epoch": 5.9375,
736
+ "grad_norm": 6.148426532745361,
737
+ "learning_rate": 4.8958333333333335e-05,
738
+ "loss": 0.6677,
739
+ "step": 95
740
+ },
741
+ {
742
+ "epoch": 6.0,
743
+ "grad_norm": 18.49876594543457,
744
+ "learning_rate": 4.888888888888889e-05,
745
+ "loss": 0.6842,
746
+ "step": 96
747
+ },
748
+ {
749
+ "epoch": 6.0,
750
+ "eval_accuracy": 0.5161290322580645,
751
+ "eval_auc": 0.6039915966386554,
752
+ "eval_f1": 0.6808510638297872,
753
+ "eval_loss": 0.6819557547569275,
754
+ "eval_precision": 0.5333333333333333,
755
+ "eval_recall": 0.9411764705882353,
756
+ "eval_runtime": 0.9944,
757
+ "eval_samples_per_second": 62.35,
758
+ "eval_steps_per_second": 2.011,
759
+ "step": 96
760
+ }
761
+ ],
762
+ "logging_steps": 1,
763
+ "max_steps": 800,
764
+ "num_input_tokens_seen": 0,
765
+ "num_train_epochs": 50,
766
+ "save_steps": 500,
767
+ "stateful_callbacks": {
768
+ "EarlyStoppingCallback": {
769
+ "args": {
770
+ "early_stopping_patience": 5,
771
+ "early_stopping_threshold": 0.01
772
+ },
773
+ "attributes": {
774
+ "early_stopping_patience_counter": 0
775
+ }
776
+ },
777
+ "TrainerControl": {
778
+ "args": {
779
+ "should_epoch_stop": false,
780
+ "should_evaluate": false,
781
+ "should_log": false,
782
+ "should_save": true,
783
+ "should_training_stop": true
784
+ },
785
+ "attributes": {}
786
+ }
787
+ },
788
+ "total_flos": 3.134345545949184e+16,
789
+ "train_batch_size": 16,
790
+ "trial_name": null,
791
+ "trial_params": null
792
+ }
checkpoint-96/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cd916140fa6771f12caa38c1e9cb46fe7ac4fc15bf2d7d633979a14270ea5919
3
+ size 5176
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": "no",
25
+ "1": "yes"
26
+ },
27
+ "label2id": {
28
+ "no": 0,
29
+ "yes": 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": "4.44.0"
50
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:60542323dbdd56c2e70952bb1e2ea38bf1083618d28f7671137ca73f11ab8314
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
+ }
runs/Aug17_21-59-02_tufta/events.out.tfevents.1723946343.tufta.50472.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0f81a9bd9659d4c518150ea077f48b4b3fb2829769f61ba6c0a3b8c9a39f592e
3
- size 5016
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:022621ab898a1aea45904022425cbcf0d9e181b041bb817dcc498ac98bfc1e96
3
+ size 28290
runs/Aug17_21-59-02_tufta/events.out.tfevents.1723946407.tufta.50472.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7101f9d9ea9bb2234d15eb8cdd301d726d0f67d102fdb5d9b86424154e3079cb
3
+ size 597
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cd916140fa6771f12caa38c1e9cb46fe7ac4fc15bf2d7d633979a14270ea5919
3
+ size 5176
training_params.json ADDED
@@ -0,0 +1,29 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "data_path": "prostate-mri-T2w-v01/autotrain-data",
3
+ "model": "microsoft/resnet-50",
4
+ "username": "Emilio407",
5
+ "lr": 5e-05,
6
+ "epochs": 50,
7
+ "batch_size": 16,
8
+ "warmup_ratio": 0.1,
9
+ "gradient_accumulation": 1,
10
+ "optimizer": "adamw_torch",
11
+ "scheduler": "linear",
12
+ "weight_decay": 0.0,
13
+ "max_grad_norm": 1.0,
14
+ "seed": 42,
15
+ "train_split": "train",
16
+ "valid_split": "validation",
17
+ "logging_steps": -1,
18
+ "project_name": "prostate-mri-T2w-v01",
19
+ "auto_find_batch_size": false,
20
+ "mixed_precision": "bf16",
21
+ "save_total_limit": 1,
22
+ "push_to_hub": true,
23
+ "eval_strategy": "epoch",
24
+ "image_column": "autotrain_image",
25
+ "target_column": "autotrain_label",
26
+ "log": "tensorboard",
27
+ "early_stopping_patience": 5,
28
+ "early_stopping_threshold": 0.01
29
+ }