fashxp commited on
Commit
e9f12b3
1 Parent(s): 5ae162a

Upload folder using huggingface_hub

Browse files
README.md ADDED
@@ -0,0 +1,42 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ - cars-countries/autotrain-data
15
+ ---
16
+
17
+ # Model Trained Using AutoTrain
18
+
19
+ - Problem type: Image Classification
20
+
21
+ ## Validation Metricsg
22
+ loss: 1.2113300561904907
23
+
24
+ f1_macro: 0.35240829346092506
25
+
26
+ f1_micro: 0.5098039215686274
27
+
28
+ f1_weighted: 0.43996622572473965
29
+
30
+ precision_macro: 0.443963963963964
31
+
32
+ precision_micro: 0.5098039215686274
33
+
34
+ precision_weighted: 0.5037272566684332
35
+
36
+ recall_macro: 0.36746031746031743
37
+
38
+ recall_micro: 0.5098039215686274
39
+
40
+ recall_weighted: 0.5098039215686274
41
+
42
+ accuracy: 0.5098039215686274
checkpoint-78/config.json ADDED
@@ -0,0 +1,39 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "google/vit-base-patch16-224",
3
+ "_num_labels": 5,
4
+ "architectures": [
5
+ "ViTForImageClassification"
6
+ ],
7
+ "attention_probs_dropout_prob": 0.0,
8
+ "encoder_stride": 16,
9
+ "hidden_act": "gelu",
10
+ "hidden_dropout_prob": 0.0,
11
+ "hidden_size": 768,
12
+ "id2label": {
13
+ "0": "France",
14
+ "1": "Germany",
15
+ "2": "Italy",
16
+ "3": "United Kingdom",
17
+ "4": "United States"
18
+ },
19
+ "image_size": 224,
20
+ "initializer_range": 0.02,
21
+ "intermediate_size": 3072,
22
+ "label2id": {
23
+ "France": 0,
24
+ "Germany": 1,
25
+ "Italy": 2,
26
+ "United Kingdom": 3,
27
+ "United States": 4
28
+ },
29
+ "layer_norm_eps": 1e-12,
30
+ "model_type": "vit",
31
+ "num_attention_heads": 12,
32
+ "num_channels": 3,
33
+ "num_hidden_layers": 12,
34
+ "patch_size": 16,
35
+ "problem_type": "single_label_classification",
36
+ "qkv_bias": true,
37
+ "torch_dtype": "float32",
38
+ "transformers_version": "4.38.0"
39
+ }
checkpoint-78/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8eaaf30550054ba91a78d4aecf5360935d8a68754bfc52033bb7e4f83071d9bb
3
+ size 343233204
checkpoint-78/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:27f136d6b2cbc35e5696483bcea3f135fae17ddffb81c0dfbbfd8d7e3de5228d
3
+ size 686587322
checkpoint-78/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9b4580a7a025f50eefafa2b2c2db868e41ae7a639d5105867574eab0726df32d
3
+ size 14244
checkpoint-78/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b9728e1dd5aa3bd3d927bc38fcfc121d63538e00387df786439d6d962be8b8d5
3
+ size 1064
checkpoint-78/trainer_state.json ADDED
@@ -0,0 +1,621 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 1.2113300561904907,
3
+ "best_model_checkpoint": "cars-countries/checkpoint-78",
4
+ "epoch": 3.0,
5
+ "eval_steps": 500,
6
+ "global_step": 78,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.04,
13
+ "grad_norm": Infinity,
14
+ "learning_rate": 0.0,
15
+ "loss": 1.781,
16
+ "step": 1
17
+ },
18
+ {
19
+ "epoch": 0.08,
20
+ "grad_norm": 9.921228408813477,
21
+ "learning_rate": 6.25e-06,
22
+ "loss": 1.5569,
23
+ "step": 2
24
+ },
25
+ {
26
+ "epoch": 0.12,
27
+ "grad_norm": 7.8902506828308105,
28
+ "learning_rate": 1.25e-05,
29
+ "loss": 1.5381,
30
+ "step": 3
31
+ },
32
+ {
33
+ "epoch": 0.15,
34
+ "grad_norm": 9.90084457397461,
35
+ "learning_rate": 1.8750000000000002e-05,
36
+ "loss": 1.5947,
37
+ "step": 4
38
+ },
39
+ {
40
+ "epoch": 0.19,
41
+ "grad_norm": 10.790699005126953,
42
+ "learning_rate": 2.5e-05,
43
+ "loss": 1.3412,
44
+ "step": 5
45
+ },
46
+ {
47
+ "epoch": 0.23,
48
+ "grad_norm": 9.438414573669434,
49
+ "learning_rate": 3.125e-05,
50
+ "loss": 1.5891,
51
+ "step": 6
52
+ },
53
+ {
54
+ "epoch": 0.27,
55
+ "grad_norm": 14.554863929748535,
56
+ "learning_rate": 3.7500000000000003e-05,
57
+ "loss": 1.5911,
58
+ "step": 7
59
+ },
60
+ {
61
+ "epoch": 0.31,
62
+ "grad_norm": 11.261236190795898,
63
+ "learning_rate": 4.375e-05,
64
+ "loss": 1.6023,
65
+ "step": 8
66
+ },
67
+ {
68
+ "epoch": 0.35,
69
+ "grad_norm": 10.684854507446289,
70
+ "learning_rate": 5e-05,
71
+ "loss": 1.5315,
72
+ "step": 9
73
+ },
74
+ {
75
+ "epoch": 0.38,
76
+ "grad_norm": 8.2311429977417,
77
+ "learning_rate": 4.928571428571429e-05,
78
+ "loss": 1.4993,
79
+ "step": 10
80
+ },
81
+ {
82
+ "epoch": 0.42,
83
+ "grad_norm": 8.519936561584473,
84
+ "learning_rate": 4.8571428571428576e-05,
85
+ "loss": 1.5576,
86
+ "step": 11
87
+ },
88
+ {
89
+ "epoch": 0.46,
90
+ "grad_norm": 7.320441246032715,
91
+ "learning_rate": 4.785714285714286e-05,
92
+ "loss": 1.5395,
93
+ "step": 12
94
+ },
95
+ {
96
+ "epoch": 0.5,
97
+ "grad_norm": 19.024276733398438,
98
+ "learning_rate": 4.714285714285714e-05,
99
+ "loss": 1.5867,
100
+ "step": 13
101
+ },
102
+ {
103
+ "epoch": 0.54,
104
+ "grad_norm": 8.801590919494629,
105
+ "learning_rate": 4.642857142857143e-05,
106
+ "loss": 1.2448,
107
+ "step": 14
108
+ },
109
+ {
110
+ "epoch": 0.58,
111
+ "grad_norm": 8.235298156738281,
112
+ "learning_rate": 4.5714285714285716e-05,
113
+ "loss": 1.4907,
114
+ "step": 15
115
+ },
116
+ {
117
+ "epoch": 0.62,
118
+ "grad_norm": 9.275227546691895,
119
+ "learning_rate": 4.5e-05,
120
+ "loss": 1.4567,
121
+ "step": 16
122
+ },
123
+ {
124
+ "epoch": 0.65,
125
+ "grad_norm": 9.200013160705566,
126
+ "learning_rate": 4.428571428571428e-05,
127
+ "loss": 1.6051,
128
+ "step": 17
129
+ },
130
+ {
131
+ "epoch": 0.69,
132
+ "grad_norm": 7.5380120277404785,
133
+ "learning_rate": 4.3571428571428576e-05,
134
+ "loss": 1.3018,
135
+ "step": 18
136
+ },
137
+ {
138
+ "epoch": 0.73,
139
+ "grad_norm": 9.66368579864502,
140
+ "learning_rate": 4.2857142857142856e-05,
141
+ "loss": 1.2577,
142
+ "step": 19
143
+ },
144
+ {
145
+ "epoch": 0.77,
146
+ "grad_norm": 6.4247260093688965,
147
+ "learning_rate": 4.214285714285714e-05,
148
+ "loss": 1.3549,
149
+ "step": 20
150
+ },
151
+ {
152
+ "epoch": 0.81,
153
+ "grad_norm": 7.779500484466553,
154
+ "learning_rate": 4.1428571428571437e-05,
155
+ "loss": 1.3177,
156
+ "step": 21
157
+ },
158
+ {
159
+ "epoch": 0.85,
160
+ "grad_norm": 9.328712463378906,
161
+ "learning_rate": 4.0714285714285717e-05,
162
+ "loss": 1.9277,
163
+ "step": 22
164
+ },
165
+ {
166
+ "epoch": 0.88,
167
+ "grad_norm": 9.957062721252441,
168
+ "learning_rate": 4e-05,
169
+ "loss": 1.543,
170
+ "step": 23
171
+ },
172
+ {
173
+ "epoch": 0.92,
174
+ "grad_norm": 11.664092063903809,
175
+ "learning_rate": 3.928571428571429e-05,
176
+ "loss": 1.4666,
177
+ "step": 24
178
+ },
179
+ {
180
+ "epoch": 0.96,
181
+ "grad_norm": 7.613643646240234,
182
+ "learning_rate": 3.857142857142858e-05,
183
+ "loss": 1.6037,
184
+ "step": 25
185
+ },
186
+ {
187
+ "epoch": 1.0,
188
+ "grad_norm": 16.03534698486328,
189
+ "learning_rate": 3.785714285714286e-05,
190
+ "loss": 1.2129,
191
+ "step": 26
192
+ },
193
+ {
194
+ "epoch": 1.0,
195
+ "eval_accuracy": 0.39215686274509803,
196
+ "eval_f1_macro": 0.17172161172161174,
197
+ "eval_f1_micro": 0.39215686274509803,
198
+ "eval_f1_weighted": 0.26543130072541843,
199
+ "eval_loss": 1.3392212390899658,
200
+ "eval_precision_macro": 0.32999999999999996,
201
+ "eval_precision_micro": 0.39215686274509803,
202
+ "eval_precision_weighted": 0.4598039215686274,
203
+ "eval_recall_macro": 0.2365079365079365,
204
+ "eval_recall_micro": 0.39215686274509803,
205
+ "eval_recall_weighted": 0.39215686274509803,
206
+ "eval_runtime": 0.9569,
207
+ "eval_samples_per_second": 53.295,
208
+ "eval_steps_per_second": 4.18,
209
+ "step": 26
210
+ },
211
+ {
212
+ "epoch": 1.04,
213
+ "grad_norm": 7.75885009765625,
214
+ "learning_rate": 3.7142857142857143e-05,
215
+ "loss": 1.3228,
216
+ "step": 27
217
+ },
218
+ {
219
+ "epoch": 1.08,
220
+ "grad_norm": 8.9802827835083,
221
+ "learning_rate": 3.642857142857143e-05,
222
+ "loss": 1.2236,
223
+ "step": 28
224
+ },
225
+ {
226
+ "epoch": 1.12,
227
+ "grad_norm": 11.71562671661377,
228
+ "learning_rate": 3.571428571428572e-05,
229
+ "loss": 1.6211,
230
+ "step": 29
231
+ },
232
+ {
233
+ "epoch": 1.15,
234
+ "grad_norm": 8.007612228393555,
235
+ "learning_rate": 3.5e-05,
236
+ "loss": 1.0492,
237
+ "step": 30
238
+ },
239
+ {
240
+ "epoch": 1.19,
241
+ "grad_norm": 8.764470100402832,
242
+ "learning_rate": 3.428571428571429e-05,
243
+ "loss": 1.2495,
244
+ "step": 31
245
+ },
246
+ {
247
+ "epoch": 1.23,
248
+ "grad_norm": 9.003642082214355,
249
+ "learning_rate": 3.357142857142857e-05,
250
+ "loss": 1.4517,
251
+ "step": 32
252
+ },
253
+ {
254
+ "epoch": 1.27,
255
+ "grad_norm": 8.626983642578125,
256
+ "learning_rate": 3.285714285714286e-05,
257
+ "loss": 1.188,
258
+ "step": 33
259
+ },
260
+ {
261
+ "epoch": 1.31,
262
+ "grad_norm": 6.939526557922363,
263
+ "learning_rate": 3.2142857142857144e-05,
264
+ "loss": 1.1346,
265
+ "step": 34
266
+ },
267
+ {
268
+ "epoch": 1.35,
269
+ "grad_norm": 8.789880752563477,
270
+ "learning_rate": 3.142857142857143e-05,
271
+ "loss": 1.4955,
272
+ "step": 35
273
+ },
274
+ {
275
+ "epoch": 1.38,
276
+ "grad_norm": 8.395410537719727,
277
+ "learning_rate": 3.071428571428572e-05,
278
+ "loss": 1.1301,
279
+ "step": 36
280
+ },
281
+ {
282
+ "epoch": 1.42,
283
+ "grad_norm": 9.601696968078613,
284
+ "learning_rate": 3e-05,
285
+ "loss": 1.3088,
286
+ "step": 37
287
+ },
288
+ {
289
+ "epoch": 1.46,
290
+ "grad_norm": 9.192988395690918,
291
+ "learning_rate": 2.9285714285714288e-05,
292
+ "loss": 1.3069,
293
+ "step": 38
294
+ },
295
+ {
296
+ "epoch": 1.5,
297
+ "grad_norm": 10.932126998901367,
298
+ "learning_rate": 2.857142857142857e-05,
299
+ "loss": 1.5361,
300
+ "step": 39
301
+ },
302
+ {
303
+ "epoch": 1.54,
304
+ "grad_norm": 8.457172393798828,
305
+ "learning_rate": 2.785714285714286e-05,
306
+ "loss": 1.0766,
307
+ "step": 40
308
+ },
309
+ {
310
+ "epoch": 1.58,
311
+ "grad_norm": 8.215372085571289,
312
+ "learning_rate": 2.714285714285714e-05,
313
+ "loss": 1.1533,
314
+ "step": 41
315
+ },
316
+ {
317
+ "epoch": 1.62,
318
+ "grad_norm": 9.27467155456543,
319
+ "learning_rate": 2.642857142857143e-05,
320
+ "loss": 1.2253,
321
+ "step": 42
322
+ },
323
+ {
324
+ "epoch": 1.65,
325
+ "grad_norm": 8.538656234741211,
326
+ "learning_rate": 2.5714285714285714e-05,
327
+ "loss": 1.5666,
328
+ "step": 43
329
+ },
330
+ {
331
+ "epoch": 1.69,
332
+ "grad_norm": 9.004700660705566,
333
+ "learning_rate": 2.5e-05,
334
+ "loss": 1.2428,
335
+ "step": 44
336
+ },
337
+ {
338
+ "epoch": 1.73,
339
+ "grad_norm": 9.92335319519043,
340
+ "learning_rate": 2.4285714285714288e-05,
341
+ "loss": 1.3294,
342
+ "step": 45
343
+ },
344
+ {
345
+ "epoch": 1.77,
346
+ "grad_norm": 6.969778537750244,
347
+ "learning_rate": 2.357142857142857e-05,
348
+ "loss": 0.892,
349
+ "step": 46
350
+ },
351
+ {
352
+ "epoch": 1.81,
353
+ "grad_norm": 9.29692554473877,
354
+ "learning_rate": 2.2857142857142858e-05,
355
+ "loss": 0.8958,
356
+ "step": 47
357
+ },
358
+ {
359
+ "epoch": 1.85,
360
+ "grad_norm": 8.588207244873047,
361
+ "learning_rate": 2.214285714285714e-05,
362
+ "loss": 0.965,
363
+ "step": 48
364
+ },
365
+ {
366
+ "epoch": 1.88,
367
+ "grad_norm": 7.432168483734131,
368
+ "learning_rate": 2.1428571428571428e-05,
369
+ "loss": 1.1908,
370
+ "step": 49
371
+ },
372
+ {
373
+ "epoch": 1.92,
374
+ "grad_norm": 8.40340518951416,
375
+ "learning_rate": 2.0714285714285718e-05,
376
+ "loss": 1.3141,
377
+ "step": 50
378
+ },
379
+ {
380
+ "epoch": 1.96,
381
+ "grad_norm": 11.749902725219727,
382
+ "learning_rate": 2e-05,
383
+ "loss": 1.664,
384
+ "step": 51
385
+ },
386
+ {
387
+ "epoch": 2.0,
388
+ "grad_norm": Infinity,
389
+ "learning_rate": 2e-05,
390
+ "loss": 2.0425,
391
+ "step": 52
392
+ },
393
+ {
394
+ "epoch": 2.0,
395
+ "eval_accuracy": 0.47058823529411764,
396
+ "eval_f1_macro": 0.30023902651021295,
397
+ "eval_f1_micro": 0.47058823529411764,
398
+ "eval_f1_weighted": 0.3905676133991189,
399
+ "eval_loss": 1.2403396368026733,
400
+ "eval_precision_macro": 0.4878048780487805,
401
+ "eval_precision_micro": 0.47058823529411764,
402
+ "eval_precision_weighted": 0.5961262553802008,
403
+ "eval_recall_macro": 0.32301587301587303,
404
+ "eval_recall_micro": 0.47058823529411764,
405
+ "eval_recall_weighted": 0.47058823529411764,
406
+ "eval_runtime": 0.9273,
407
+ "eval_samples_per_second": 54.997,
408
+ "eval_steps_per_second": 4.314,
409
+ "step": 52
410
+ },
411
+ {
412
+ "epoch": 2.04,
413
+ "grad_norm": 11.03630256652832,
414
+ "learning_rate": 1.928571428571429e-05,
415
+ "loss": 1.1866,
416
+ "step": 53
417
+ },
418
+ {
419
+ "epoch": 2.08,
420
+ "grad_norm": 7.543542861938477,
421
+ "learning_rate": 1.8571428571428572e-05,
422
+ "loss": 1.1695,
423
+ "step": 54
424
+ },
425
+ {
426
+ "epoch": 2.12,
427
+ "grad_norm": 8.078568458557129,
428
+ "learning_rate": 1.785714285714286e-05,
429
+ "loss": 0.9876,
430
+ "step": 55
431
+ },
432
+ {
433
+ "epoch": 2.15,
434
+ "grad_norm": 9.406330108642578,
435
+ "learning_rate": 1.7142857142857145e-05,
436
+ "loss": 1.4199,
437
+ "step": 56
438
+ },
439
+ {
440
+ "epoch": 2.19,
441
+ "grad_norm": 8.94027328491211,
442
+ "learning_rate": 1.642857142857143e-05,
443
+ "loss": 1.0628,
444
+ "step": 57
445
+ },
446
+ {
447
+ "epoch": 2.23,
448
+ "grad_norm": 7.433661937713623,
449
+ "learning_rate": 1.5714285714285715e-05,
450
+ "loss": 1.0264,
451
+ "step": 58
452
+ },
453
+ {
454
+ "epoch": 2.27,
455
+ "grad_norm": 7.517592430114746,
456
+ "learning_rate": 1.5e-05,
457
+ "loss": 0.8727,
458
+ "step": 59
459
+ },
460
+ {
461
+ "epoch": 2.31,
462
+ "grad_norm": 11.105234146118164,
463
+ "learning_rate": 1.4285714285714285e-05,
464
+ "loss": 1.0733,
465
+ "step": 60
466
+ },
467
+ {
468
+ "epoch": 2.35,
469
+ "grad_norm": 8.228996276855469,
470
+ "learning_rate": 1.357142857142857e-05,
471
+ "loss": 0.7755,
472
+ "step": 61
473
+ },
474
+ {
475
+ "epoch": 2.38,
476
+ "grad_norm": 10.02564525604248,
477
+ "learning_rate": 1.2857142857142857e-05,
478
+ "loss": 1.3597,
479
+ "step": 62
480
+ },
481
+ {
482
+ "epoch": 2.42,
483
+ "grad_norm": 7.33097505569458,
484
+ "learning_rate": 1.2142857142857144e-05,
485
+ "loss": 0.8739,
486
+ "step": 63
487
+ },
488
+ {
489
+ "epoch": 2.46,
490
+ "grad_norm": 11.741021156311035,
491
+ "learning_rate": 1.1428571428571429e-05,
492
+ "loss": 1.3264,
493
+ "step": 64
494
+ },
495
+ {
496
+ "epoch": 2.5,
497
+ "grad_norm": 10.197936058044434,
498
+ "learning_rate": 1.0714285714285714e-05,
499
+ "loss": 1.1468,
500
+ "step": 65
501
+ },
502
+ {
503
+ "epoch": 2.54,
504
+ "grad_norm": 9.967548370361328,
505
+ "learning_rate": 1e-05,
506
+ "loss": 1.2385,
507
+ "step": 66
508
+ },
509
+ {
510
+ "epoch": 2.58,
511
+ "grad_norm": 6.901878356933594,
512
+ "learning_rate": 9.285714285714286e-06,
513
+ "loss": 0.7635,
514
+ "step": 67
515
+ },
516
+ {
517
+ "epoch": 2.62,
518
+ "grad_norm": 7.190940856933594,
519
+ "learning_rate": 8.571428571428573e-06,
520
+ "loss": 0.8255,
521
+ "step": 68
522
+ },
523
+ {
524
+ "epoch": 2.65,
525
+ "grad_norm": 9.144484519958496,
526
+ "learning_rate": 7.857142857142858e-06,
527
+ "loss": 1.0753,
528
+ "step": 69
529
+ },
530
+ {
531
+ "epoch": 2.69,
532
+ "grad_norm": 6.83949089050293,
533
+ "learning_rate": 7.142857142857143e-06,
534
+ "loss": 1.0511,
535
+ "step": 70
536
+ },
537
+ {
538
+ "epoch": 2.73,
539
+ "grad_norm": 11.242728233337402,
540
+ "learning_rate": 6.428571428571429e-06,
541
+ "loss": 1.6024,
542
+ "step": 71
543
+ },
544
+ {
545
+ "epoch": 2.77,
546
+ "grad_norm": 9.73320484161377,
547
+ "learning_rate": 5.7142857142857145e-06,
548
+ "loss": 1.0241,
549
+ "step": 72
550
+ },
551
+ {
552
+ "epoch": 2.81,
553
+ "grad_norm": 13.551000595092773,
554
+ "learning_rate": 5e-06,
555
+ "loss": 1.0143,
556
+ "step": 73
557
+ },
558
+ {
559
+ "epoch": 2.85,
560
+ "grad_norm": 9.739935874938965,
561
+ "learning_rate": 4.285714285714286e-06,
562
+ "loss": 1.528,
563
+ "step": 74
564
+ },
565
+ {
566
+ "epoch": 2.88,
567
+ "grad_norm": 7.910869598388672,
568
+ "learning_rate": 3.5714285714285714e-06,
569
+ "loss": 0.9389,
570
+ "step": 75
571
+ },
572
+ {
573
+ "epoch": 2.92,
574
+ "grad_norm": 9.845719337463379,
575
+ "learning_rate": 2.8571428571428573e-06,
576
+ "loss": 1.2907,
577
+ "step": 76
578
+ },
579
+ {
580
+ "epoch": 2.96,
581
+ "grad_norm": 6.709384441375732,
582
+ "learning_rate": 2.142857142857143e-06,
583
+ "loss": 1.0141,
584
+ "step": 77
585
+ },
586
+ {
587
+ "epoch": 3.0,
588
+ "grad_norm": 16.175195693969727,
589
+ "learning_rate": 1.4285714285714286e-06,
590
+ "loss": 1.4561,
591
+ "step": 78
592
+ },
593
+ {
594
+ "epoch": 3.0,
595
+ "eval_accuracy": 0.5098039215686274,
596
+ "eval_f1_macro": 0.35240829346092506,
597
+ "eval_f1_micro": 0.5098039215686274,
598
+ "eval_f1_weighted": 0.43996622572473965,
599
+ "eval_loss": 1.2113300561904907,
600
+ "eval_precision_macro": 0.443963963963964,
601
+ "eval_precision_micro": 0.5098039215686274,
602
+ "eval_precision_weighted": 0.5037272566684332,
603
+ "eval_recall_macro": 0.36746031746031743,
604
+ "eval_recall_micro": 0.5098039215686274,
605
+ "eval_recall_weighted": 0.5098039215686274,
606
+ "eval_runtime": 0.9222,
607
+ "eval_samples_per_second": 55.303,
608
+ "eval_steps_per_second": 4.337,
609
+ "step": 78
610
+ }
611
+ ],
612
+ "logging_steps": 1,
613
+ "max_steps": 78,
614
+ "num_input_tokens_seen": 0,
615
+ "num_train_epochs": 3,
616
+ "save_steps": 500,
617
+ "total_flos": 4.696140837323981e+16,
618
+ "train_batch_size": 8,
619
+ "trial_name": null,
620
+ "trial_params": null
621
+ }
checkpoint-78/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4bffd28c8a57b2820a76fcabae7f026624e1e4b1406c92a435e74b16aa7f3966
3
+ size 4920
config.json ADDED
@@ -0,0 +1,39 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "google/vit-base-patch16-224",
3
+ "_num_labels": 5,
4
+ "architectures": [
5
+ "ViTForImageClassification"
6
+ ],
7
+ "attention_probs_dropout_prob": 0.0,
8
+ "encoder_stride": 16,
9
+ "hidden_act": "gelu",
10
+ "hidden_dropout_prob": 0.0,
11
+ "hidden_size": 768,
12
+ "id2label": {
13
+ "0": "France",
14
+ "1": "Germany",
15
+ "2": "Italy",
16
+ "3": "United Kingdom",
17
+ "4": "United States"
18
+ },
19
+ "image_size": 224,
20
+ "initializer_range": 0.02,
21
+ "intermediate_size": 3072,
22
+ "label2id": {
23
+ "France": 0,
24
+ "Germany": 1,
25
+ "Italy": 2,
26
+ "United Kingdom": 3,
27
+ "United States": 4
28
+ },
29
+ "layer_norm_eps": 1e-12,
30
+ "model_type": "vit",
31
+ "num_attention_heads": 12,
32
+ "num_channels": 3,
33
+ "num_hidden_layers": 12,
34
+ "patch_size": 16,
35
+ "problem_type": "single_label_classification",
36
+ "qkv_bias": true,
37
+ "torch_dtype": "float32",
38
+ "transformers_version": "4.38.0"
39
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8eaaf30550054ba91a78d4aecf5360935d8a68754bfc52033bb7e4f83071d9bb
3
+ size 343233204
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
+ 0.5,
7
+ 0.5,
8
+ 0.5
9
+ ],
10
+ "image_processor_type": "ViTImageProcessor",
11
+ "image_std": [
12
+ 0.5,
13
+ 0.5,
14
+ 0.5
15
+ ],
16
+ "resample": 2,
17
+ "rescale_factor": 0.00392156862745098,
18
+ "size": {
19
+ "height": 224,
20
+ "width": 224
21
+ }
22
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4bffd28c8a57b2820a76fcabae7f026624e1e4b1406c92a435e74b16aa7f3966
3
+ size 4920
training_params.json ADDED
@@ -0,0 +1,29 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "data_path": "cars-countries/autotrain-data",
3
+ "model": "google/vit-base-patch16-224",
4
+ "username": "fashxp",
5
+ "lr": 5e-05,
6
+ "epochs": 3,
7
+ "batch_size": 8,
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": "cars-countries",
19
+ "auto_find_batch_size": false,
20
+ "mixed_precision": "fp16",
21
+ "save_total_limit": 1,
22
+ "save_strategy": "epoch",
23
+ "push_to_hub": true,
24
+ "repo_id": "fashxp/cars-countries",
25
+ "evaluation_strategy": "epoch",
26
+ "image_column": "autotrain_image",
27
+ "target_column": "autotrain_label",
28
+ "log": "none"
29
+ }