Hugging Face's logo

Augusto777
/
swinv2-tiny-patch4-window8-256-dmae-va-U5-42B

Image Classification
Transformers
TensorBoard
Safetensors
swinv2
Generated from Trainer
Model card Files
xet
 Metrics Community
Augusto777 commited on
Commit
01e28b0
·
verified ·
1 Parent(s): 88c0376

Training in progress, epoch 0

Browse files
Files changed (12) hide show
  1. model.safetensors +1 -1
  2. runs/Apr18_22-23-10_DESKTOP-SKBE9FB/events.out.tfevents.1713500593.DESKTOP-SKBE9FB.6812.0 +2 -2
  3. runs/Apr18_22-30-59_DESKTOP-SKBE9FB/events.out.tfevents.1713501061.DESKTOP-SKBE9FB.5296.0 +3 -0
  4. tmp-checkpoint-209/config.json +58 -0
  5. tmp-checkpoint-209/model.safetensors +3 -0
  6. tmp-checkpoint-209/optimizer.pt +3 -0
  7. tmp-checkpoint-209/preprocessor_config.json +22 -0
  8. tmp-checkpoint-209/rng_state.pth +3 -0
  9. tmp-checkpoint-209/scheduler.pt +3 -0
  10. tmp-checkpoint-209/trainer_state.json +366 -0
  11. tmp-checkpoint-209/training_args.bin +3 -0
  12. training_args.bin +1 -1
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b553c29284076f1a9f636a710eec4456f5de4bef598dca3536591b625439266f
3
  size 110356296
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f154b2bf60acc2741d603539a3908e779c4b19b4e372a92a2833d5ff046ba480
3
  size 110356296
runs/Apr18_22-23-10_DESKTOP-SKBE9FB/events.out.tfevents.1713500593.DESKTOP-SKBE9FB.6812.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2507ae6c1c59f195359e8c9cebe19b18d247484327ee46db45c1cadbc057d338
3
- size 15282
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a157c08c7e1e358881aa080f03b1eaefca8d38e87a8e83366f625fc7f577a7b7
3
+ size 16085
runs/Apr18_22-30-59_DESKTOP-SKBE9FB/events.out.tfevents.1713501061.DESKTOP-SKBE9FB.5296.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:89c64686bb833a86f5c601eb1940a6b0b93c76b1b9197a353c675dcd68685eb2
3
+ size 5138
tmp-checkpoint-209/config.json ADDED
@@ -0,0 +1,58 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "microsoft/swinv2-tiny-patch4-window8-256",
3
+ "architectures": [
4
+ "Swinv2ForImageClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.0,
7
+ "depths": [
8
+ 2,
9
+ 2,
10
+ 6,
11
+ 2
12
+ ],
13
+ "drop_path_rate": 0.1,
14
+ "embed_dim": 96,
15
+ "encoder_stride": 32,
16
+ "hidden_act": "gelu",
17
+ "hidden_dropout_prob": 0.0,
18
+ "hidden_size": 768,
19
+ "id2label": {
20
+ "0": "avanzada",
21
+ "1": "leve",
22
+ "2": "moderada",
23
+ "3": "no dmae"
24
+ },
25
+ "image_size": 256,
26
+ "initializer_range": 0.02,
27
+ "label2id": {
28
+ "avanzada": 0,
29
+ "leve": 1,
30
+ "moderada": 2,
31
+ "no dmae": 3
32
+ },
33
+ "layer_norm_eps": 1e-05,
34
+ "mlp_ratio": 4.0,
35
+ "model_type": "swinv2",
36
+ "num_channels": 3,
37
+ "num_heads": [
38
+ 3,
39
+ 6,
40
+ 12,
41
+ 24
42
+ ],
43
+ "num_layers": 4,
44
+ "patch_size": 4,
45
+ "path_norm": true,
46
+ "pretrained_window_sizes": [
47
+ 0,
48
+ 0,
49
+ 0,
50
+ 0
51
+ ],
52
+ "problem_type": "single_label_classification",
53
+ "qkv_bias": true,
54
+ "torch_dtype": "float32",
55
+ "transformers_version": "4.36.2",
56
+ "use_absolute_embeddings": false,
57
+ "window_size": 8
58
+ }
tmp-checkpoint-209/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fde20255a6da74070d7432434b4308d059ccec0197773b1e78cf6de80a5d88dd
3
+ size 110356296
tmp-checkpoint-209/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9d9704ff06135e6d0d653ccf8a94ada70e3b8172ddfa24726bb7384a36f70ac2
3
+ size 220853562
tmp-checkpoint-209/preprocessor_config.json ADDED
@@ -0,0 +1,22 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "do_normalize": true,
3
+ "do_rescale": true,
4
+ "do_resize": true,
5
+ "image_mean": [
6
+ 0.485,
7
+ 0.456,
8
+ 0.406
9
+ ],
10
+ "image_processor_type": "ViTImageProcessor",
11
+ "image_std": [
12
+ 0.229,
13
+ 0.224,
14
+ 0.225
15
+ ],
16
+ "resample": 3,
17
+ "rescale_factor": 0.00392156862745098,
18
+ "size": {
19
+ "height": 256,
20
+ "width": 256
21
+ }
22
+ }
tmp-checkpoint-209/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c1ec6abdbb322070af056f450a7f277305a191e5915fd5a627e1cb1b80eec3e3
3
+ size 14244
tmp-checkpoint-209/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c4a475d82a4dac2508f8d8a7a87478ff2901d1f98c2d5e24c6072600492c64de
3
+ size 1064
tmp-checkpoint-209/trainer_state.json ADDED
@@ -0,0 +1,366 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.7833333333333333,
3
+ "best_model_checkpoint": "swinv2-tiny-patch4-window8-256-dmae-va-U5-42B\\checkpoint-155",
4
+ "epoch": 26.967741935483872,
5
+ "eval_steps": 500,
6
+ "global_step": 209,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.9,
13
+ "eval_accuracy": 0.45,
14
+ "eval_loss": 1.3843282461166382,
15
+ "eval_runtime": 0.8985,
16
+ "eval_samples_per_second": 66.778,
17
+ "eval_steps_per_second": 2.226,
18
+ "step": 7
19
+ },
20
+ {
21
+ "epoch": 1.55,
22
+ "learning_rate": 1.6000000000000003e-05,
23
+ "loss": 1.3855,
24
+ "step": 12
25
+ },
26
+ {
27
+ "epoch": 1.94,
28
+ "eval_accuracy": 0.45,
29
+ "eval_loss": 1.3692599534988403,
30
+ "eval_runtime": 0.8682,
31
+ "eval_samples_per_second": 69.109,
32
+ "eval_steps_per_second": 2.304,
33
+ "step": 15
34
+ },
35
+ {
36
+ "epoch": 2.97,
37
+ "eval_accuracy": 0.45,
38
+ "eval_loss": 1.3112239837646484,
39
+ "eval_runtime": 0.8507,
40
+ "eval_samples_per_second": 70.53,
41
+ "eval_steps_per_second": 2.351,
42
+ "step": 23
43
+ },
44
+ {
45
+ "epoch": 3.1,
46
+ "learning_rate": 3.2000000000000005e-05,
47
+ "loss": 1.3665,
48
+ "step": 24
49
+ },
50
+ {
51
+ "epoch": 4.0,
52
+ "eval_accuracy": 0.5,
53
+ "eval_loss": 1.182310938835144,
54
+ "eval_runtime": 0.8795,
55
+ "eval_samples_per_second": 68.219,
56
+ "eval_steps_per_second": 2.274,
57
+ "step": 31
58
+ },
59
+ {
60
+ "epoch": 4.65,
61
+ "learning_rate": 3.909090909090909e-05,
62
+ "loss": 1.2656,
63
+ "step": 36
64
+ },
65
+ {
66
+ "epoch": 4.9,
67
+ "eval_accuracy": 0.5166666666666667,
68
+ "eval_loss": 1.0430983304977417,
69
+ "eval_runtime": 0.8504,
70
+ "eval_samples_per_second": 70.556,
71
+ "eval_steps_per_second": 2.352,
72
+ "step": 38
73
+ },
74
+ {
75
+ "epoch": 5.94,
76
+ "eval_accuracy": 0.5,
77
+ "eval_loss": 0.9782969951629639,
78
+ "eval_runtime": 0.8875,
79
+ "eval_samples_per_second": 67.607,
80
+ "eval_steps_per_second": 2.254,
81
+ "step": 46
82
+ },
83
+ {
84
+ "epoch": 6.19,
85
+ "learning_rate": 3.7272727272727276e-05,
86
+ "loss": 1.1097,
87
+ "step": 48
88
+ },
89
+ {
90
+ "epoch": 6.97,
91
+ "eval_accuracy": 0.55,
92
+ "eval_loss": 0.9232853651046753,
93
+ "eval_runtime": 0.9233,
94
+ "eval_samples_per_second": 64.981,
95
+ "eval_steps_per_second": 2.166,
96
+ "step": 54
97
+ },
98
+ {
99
+ "epoch": 7.74,
100
+ "learning_rate": 3.545454545454546e-05,
101
+ "loss": 0.9542,
102
+ "step": 60
103
+ },
104
+ {
105
+ "epoch": 8.0,
106
+ "eval_accuracy": 0.6166666666666667,
107
+ "eval_loss": 0.8490957617759705,
108
+ "eval_runtime": 0.9001,
109
+ "eval_samples_per_second": 66.661,
110
+ "eval_steps_per_second": 2.222,
111
+ "step": 62
112
+ },
113
+ {
114
+ "epoch": 8.9,
115
+ "eval_accuracy": 0.6,
116
+ "eval_loss": 0.8462814092636108,
117
+ "eval_runtime": 0.8868,
118
+ "eval_samples_per_second": 67.657,
119
+ "eval_steps_per_second": 2.255,
120
+ "step": 69
121
+ },
122
+ {
123
+ "epoch": 9.29,
124
+ "learning_rate": 3.363636363636364e-05,
125
+ "loss": 0.8565,
126
+ "step": 72
127
+ },
128
+ {
129
+ "epoch": 9.94,
130
+ "eval_accuracy": 0.6,
131
+ "eval_loss": 0.8351749777793884,
132
+ "eval_runtime": 1.1225,
133
+ "eval_samples_per_second": 53.451,
134
+ "eval_steps_per_second": 1.782,
135
+ "step": 77
136
+ },
137
+ {
138
+ "epoch": 10.84,
139
+ "learning_rate": 3.181818181818182e-05,
140
+ "loss": 0.7473,
141
+ "step": 84
142
+ },
143
+ {
144
+ "epoch": 10.97,
145
+ "eval_accuracy": 0.5833333333333334,
146
+ "eval_loss": 0.8304904699325562,
147
+ "eval_runtime": 1.0952,
148
+ "eval_samples_per_second": 54.782,
149
+ "eval_steps_per_second": 1.826,
150
+ "step": 85
151
+ },
152
+ {
153
+ "epoch": 12.0,
154
+ "eval_accuracy": 0.65,
155
+ "eval_loss": 0.7703030109405518,
156
+ "eval_runtime": 0.9077,
157
+ "eval_samples_per_second": 66.103,
158
+ "eval_steps_per_second": 2.203,
159
+ "step": 93
160
+ },
161
+ {
162
+ "epoch": 12.39,
163
+ "learning_rate": 3.0000000000000004e-05,
164
+ "loss": 0.6981,
165
+ "step": 96
166
+ },
167
+ {
168
+ "epoch": 12.9,
169
+ "eval_accuracy": 0.6333333333333333,
170
+ "eval_loss": 0.8429493308067322,
171
+ "eval_runtime": 0.9329,
172
+ "eval_samples_per_second": 64.316,
173
+ "eval_steps_per_second": 2.144,
174
+ "step": 100
175
+ },
176
+ {
177
+ "epoch": 13.94,
178
+ "learning_rate": 2.8181818181818185e-05,
179
+ "loss": 0.5937,
180
+ "step": 108
181
+ },
182
+ {
183
+ "epoch": 13.94,
184
+ "eval_accuracy": 0.7,
185
+ "eval_loss": 0.7051786780357361,
186
+ "eval_runtime": 0.9214,
187
+ "eval_samples_per_second": 65.121,
188
+ "eval_steps_per_second": 2.171,
189
+ "step": 108
190
+ },
191
+ {
192
+ "epoch": 14.97,
193
+ "eval_accuracy": 0.6833333333333333,
194
+ "eval_loss": 0.6948642134666443,
195
+ "eval_runtime": 0.9648,
196
+ "eval_samples_per_second": 62.189,
197
+ "eval_steps_per_second": 2.073,
198
+ "step": 116
199
+ },
200
+ {
201
+ "epoch": 15.48,
202
+ "learning_rate": 2.6363636363636365e-05,
203
+ "loss": 0.549,
204
+ "step": 120
205
+ },
206
+ {
207
+ "epoch": 16.0,
208
+ "eval_accuracy": 0.7,
209
+ "eval_loss": 0.740279495716095,
210
+ "eval_runtime": 0.9273,
211
+ "eval_samples_per_second": 64.707,
212
+ "eval_steps_per_second": 2.157,
213
+ "step": 124
214
+ },
215
+ {
216
+ "epoch": 16.9,
217
+ "eval_accuracy": 0.75,
218
+ "eval_loss": 0.6784736514091492,
219
+ "eval_runtime": 0.9242,
220
+ "eval_samples_per_second": 64.921,
221
+ "eval_steps_per_second": 2.164,
222
+ "step": 131
223
+ },
224
+ {
225
+ "epoch": 17.03,
226
+ "learning_rate": 2.454545454545455e-05,
227
+ "loss": 0.4983,
228
+ "step": 132
229
+ },
230
+ {
231
+ "epoch": 17.94,
232
+ "eval_accuracy": 0.7166666666666667,
233
+ "eval_loss": 0.6915722489356995,
234
+ "eval_runtime": 0.941,
235
+ "eval_samples_per_second": 63.762,
236
+ "eval_steps_per_second": 2.125,
237
+ "step": 139
238
+ },
239
+ {
240
+ "epoch": 18.58,
241
+ "learning_rate": 2.2727272727272733e-05,
242
+ "loss": 0.4534,
243
+ "step": 144
244
+ },
245
+ {
246
+ "epoch": 18.97,
247
+ "eval_accuracy": 0.75,
248
+ "eval_loss": 0.6501169800758362,
249
+ "eval_runtime": 0.8838,
250
+ "eval_samples_per_second": 67.889,
251
+ "eval_steps_per_second": 2.263,
252
+ "step": 147
253
+ },
254
+ {
255
+ "epoch": 20.0,
256
+ "eval_accuracy": 0.7833333333333333,
257
+ "eval_loss": 0.6499305963516235,
258
+ "eval_runtime": 1.2045,
259
+ "eval_samples_per_second": 49.812,
260
+ "eval_steps_per_second": 1.66,
261
+ "step": 155
262
+ },
263
+ {
264
+ "epoch": 20.13,
265
+ "learning_rate": 2.090909090909091e-05,
266
+ "loss": 0.4209,
267
+ "step": 156
268
+ },
269
+ {
270
+ "epoch": 20.9,
271
+ "eval_accuracy": 0.7,
272
+ "eval_loss": 0.8589470386505127,
273
+ "eval_runtime": 0.995,
274
+ "eval_samples_per_second": 60.3,
275
+ "eval_steps_per_second": 2.01,
276
+ "step": 162
277
+ },
278
+ {
279
+ "epoch": 21.68,
280
+ "learning_rate": 1.9090909090909094e-05,
281
+ "loss": 0.4248,
282
+ "step": 168
283
+ },
284
+ {
285
+ "epoch": 21.94,
286
+ "eval_accuracy": 0.7166666666666667,
287
+ "eval_loss": 0.6511362791061401,
288
+ "eval_runtime": 0.9148,
289
+ "eval_samples_per_second": 65.586,
290
+ "eval_steps_per_second": 2.186,
291
+ "step": 170
292
+ },
293
+ {
294
+ "epoch": 22.97,
295
+ "eval_accuracy": 0.7333333333333333,
296
+ "eval_loss": 0.7100386023521423,
297
+ "eval_runtime": 1.135,
298
+ "eval_samples_per_second": 52.865,
299
+ "eval_steps_per_second": 1.762,
300
+ "step": 178
301
+ },
302
+ {
303
+ "epoch": 23.23,
304
+ "learning_rate": 1.7272727272727274e-05,
305
+ "loss": 0.3901,
306
+ "step": 180
307
+ },
308
+ {
309
+ "epoch": 24.0,
310
+ "eval_accuracy": 0.75,
311
+ "eval_loss": 0.6456588506698608,
312
+ "eval_runtime": 0.9592,
313
+ "eval_samples_per_second": 62.554,
314
+ "eval_steps_per_second": 2.085,
315
+ "step": 186
316
+ },
317
+ {
318
+ "epoch": 24.77,
319
+ "learning_rate": 1.5454545454545454e-05,
320
+ "loss": 0.3477,
321
+ "step": 192
322
+ },
323
+ {
324
+ "epoch": 24.9,
325
+ "eval_accuracy": 0.75,
326
+ "eval_loss": 0.6582431197166443,
327
+ "eval_runtime": 0.8667,
328
+ "eval_samples_per_second": 69.227,
329
+ "eval_steps_per_second": 2.308,
330
+ "step": 193
331
+ },
332
+ {
333
+ "epoch": 25.94,
334
+ "eval_accuracy": 0.75,
335
+ "eval_loss": 0.6813774704933167,
336
+ "eval_runtime": 1.0831,
337
+ "eval_samples_per_second": 55.399,
338
+ "eval_steps_per_second": 1.847,
339
+ "step": 201
340
+ },
341
+ {
342
+ "epoch": 26.32,
343
+ "learning_rate": 1.3636363636363637e-05,
344
+ "loss": 0.3236,
345
+ "step": 204
346
+ },
347
+ {
348
+ "epoch": 26.97,
349
+ "eval_accuracy": 0.7166666666666667,
350
+ "eval_loss": 0.712448239326477,
351
+ "eval_runtime": 0.9632,
352
+ "eval_samples_per_second": 62.295,
353
+ "eval_steps_per_second": 2.077,
354
+ "step": 209
355
+ }
356
+ ],
357
+ "logging_steps": 12,
358
+ "max_steps": 294,
359
+ "num_input_tokens_seen": 0,
360
+ "num_train_epochs": 42,
361
+ "save_steps": 500,
362
+ "total_flos": 8.556354835395379e+17,
363
+ "train_batch_size": 32,
364
+ "trial_name": null,
365
+ "trial_params": null
366
+ }
tmp-checkpoint-209/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:673b70606ff5c7802955e41eccdbe1fc2a3277196e5ba5a8fbc18800da82c2fc
3
+ size 4792
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:673b70606ff5c7802955e41eccdbe1fc2a3277196e5ba5a8fbc18800da82c2fc
3
  size 4792
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b8228c7083080fdd60bba26c820f7c2f7a48a1e40453c2b0af5292a456d9f611
3
  size 4792