Hugging Face's logo

SeyedAli
/
Image-Valence

Image Classification
Transformers
TensorBoard
Safetensors
vit
Generated from Trainer
Model card Files
xet
Metrics Community
SeyedAli commited on
Commit
0473add
·
verified ·
1 Parent(s): 22d4f13

SeyedAli/Valence

Browse files
Files changed (9) hide show
  1. README.md +65 -0
  2. all_results.json +8 -0
  3. config.json +38 -0
  4. model.safetensors +3 -0
  5. preprocessor_config.json +22 -0
  6. runs/Feb12_09-22-05_3945894e4f8b/events.out.tfevents.1707729743.3945894e4f8b.938.2 +3 -0
  7. train_results.json +8 -0
  8. trainer_state.json +379 -0
  9. training_args.bin +3 -0
README.md ADDED
@@ -0,0 +1,65 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ base_model: google/vit-base-patch16-224-in21k
4
+ tags:
5
+ - image-classification
6
+ - generated_from_trainer
7
+ metrics:
8
+ - accuracy
9
+ model-index:
10
+ - name: vit-Valence
11
+ results: []
12
+ ---
13
+
14
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
15
+ should probably proofread and complete it, then remove this comment. -->
16
+
17
+ # vit-Valence
18
+
19
+ This model is a fine-tuned version of [google/vit-base-patch16-224-in21k](https://huggingface.co/google/vit-base-patch16-224-in21k) on the custom dataset.
20
+ It achieves the following results on the evaluation set:
21
+ - Loss: 1.4464
22
+ - Accuracy: 0.5863
23
+
24
+ ## Model description
25
+
26
+ More information needed
27
+
28
+ ## Intended uses & limitations
29
+
30
+ More information needed
31
+
32
+ ## Training and evaluation data
33
+
34
+ More information needed
35
+
36
+ ## Training procedure
37
+
38
+ ### Training hyperparameters
39
+
40
+ The following hyperparameters were used during training:
41
+ - learning_rate: 0.0002
42
+ - train_batch_size: 16
43
+ - eval_batch_size: 8
44
+ - seed: 42
45
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
46
+ - lr_scheduler_type: linear
47
+ - num_epochs: 4
48
+
49
+ ### Training results
50
+
51
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy |
52
+ |:-------------:|:-----:|:----:|:---------------:|:--------:|
53
+ | 1.2256 | 0.78 | 100 | 1.0936 | 0.5451 |
54
+ | 0.7315 | 1.56 | 200 | 0.9981 | 0.5882 |
55
+ | 0.2118 | 2.34 | 300 | 1.1650 | 0.5902 |
56
+ | 0.1119 | 3.12 | 400 | 1.2864 | 0.5863 |
57
+ | 0.1116 | 3.91 | 500 | 1.4464 | 0.5863 |
58
+
59
+
60
+ ### Framework versions
61
+
62
+ - Transformers 4.35.2
63
+ - Pytorch 2.1.0+cu121
64
+ - Datasets 2.17.0
65
+ - Tokenizers 0.15.1
all_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 4.0,
3
+ "total_flos": 6.311117323294802e+17,
4
+ "train_loss": 0.5731766858662013,
5
+ "train_runtime": 408.7689,
6
+ "train_samples_per_second": 19.923,
7
+ "train_steps_per_second": 1.253
8
+ }
config.json ADDED
@@ -0,0 +1,38 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "google/vit-base-patch16-224-in21k",
3
+ "architectures": [
4
+ "ViTForImageClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.0,
7
+ "encoder_stride": 16,
8
+ "hidden_act": "gelu",
9
+ "hidden_dropout_prob": 0.0,
10
+ "hidden_size": 768,
11
+ "id2label": {
12
+ "0": "0",
13
+ "1": "1",
14
+ "2": "2",
15
+ "3": "3",
16
+ "4": "4"
17
+ },
18
+ "image_size": 224,
19
+ "initializer_range": 0.02,
20
+ "intermediate_size": 3072,
21
+ "label2id": {
22
+ "0": "0",
23
+ "1": "1",
24
+ "2": "2",
25
+ "3": "3",
26
+ "4": "4"
27
+ },
28
+ "layer_norm_eps": 1e-12,
29
+ "model_type": "vit",
30
+ "num_attention_heads": 12,
31
+ "num_channels": 3,
32
+ "num_hidden_layers": 12,
33
+ "patch_size": 16,
34
+ "problem_type": "single_label_classification",
35
+ "qkv_bias": true,
36
+ "torch_dtype": "float32",
37
+ "transformers_version": "4.35.2"
38
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ae869bfa4ff2b4ef976982d4a55945a201f090442efdf815193e6ca7f11623e0
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
+ }
runs/Feb12_09-22-05_3945894e4f8b/events.out.tfevents.1707729743.3945894e4f8b.938.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:085c961888dc9ca7cf28b7faab2baf459daa04d2feac188f1f08dd3d56a6983c
3
+ size 14191
train_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 4.0,
3
+ "total_flos": 6.311117323294802e+17,
4
+ "train_loss": 0.5731766858662013,
5
+ "train_runtime": 408.7689,
6
+ "train_samples_per_second": 19.923,
7
+ "train_steps_per_second": 1.253
8
+ }
trainer_state.json ADDED
@@ -0,0 +1,379 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.998068630695343,
3
+ "best_model_checkpoint": "./vit-Valence/checkpoint-200",
4
+ "epoch": 4.0,
5
+ "eval_steps": 100,
6
+ "global_step": 512,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.08,
13
+ "learning_rate": 0.00019609375,
14
+ "loss": 1.527,
15
+ "step": 10
16
+ },
17
+ {
18
+ "epoch": 0.16,
19
+ "learning_rate": 0.0001921875,
20
+ "loss": 1.3365,
21
+ "step": 20
22
+ },
23
+ {
24
+ "epoch": 0.23,
25
+ "learning_rate": 0.00018828125,
26
+ "loss": 1.3176,
27
+ "step": 30
28
+ },
29
+ {
30
+ "epoch": 0.31,
31
+ "learning_rate": 0.000184375,
32
+ "loss": 1.2405,
33
+ "step": 40
34
+ },
35
+ {
36
+ "epoch": 0.39,
37
+ "learning_rate": 0.00018046875000000002,
38
+ "loss": 1.1474,
39
+ "step": 50
40
+ },
41
+ {
42
+ "epoch": 0.47,
43
+ "learning_rate": 0.00017656250000000002,
44
+ "loss": 1.1061,
45
+ "step": 60
46
+ },
47
+ {
48
+ "epoch": 0.55,
49
+ "learning_rate": 0.00017265625,
50
+ "loss": 1.1234,
51
+ "step": 70
52
+ },
53
+ {
54
+ "epoch": 0.62,
55
+ "learning_rate": 0.00016875,
56
+ "loss": 1.1591,
57
+ "step": 80
58
+ },
59
+ {
60
+ "epoch": 0.7,
61
+ "learning_rate": 0.00016484375,
62
+ "loss": 1.083,
63
+ "step": 90
64
+ },
65
+ {
66
+ "epoch": 0.78,
67
+ "learning_rate": 0.0001609375,
68
+ "loss": 1.2256,
69
+ "step": 100
70
+ },
71
+ {
72
+ "epoch": 0.78,
73
+ "eval_accuracy": 0.5450980392156862,
74
+ "eval_loss": 1.0935585498809814,
75
+ "eval_runtime": 8.8454,
76
+ "eval_samples_per_second": 57.657,
77
+ "eval_steps_per_second": 7.235,
78
+ "step": 100
79
+ },
80
+ {
81
+ "epoch": 0.86,
82
+ "learning_rate": 0.00015703125,
83
+ "loss": 1.1669,
84
+ "step": 110
85
+ },
86
+ {
87
+ "epoch": 0.94,
88
+ "learning_rate": 0.000153125,
89
+ "loss": 1.0515,
90
+ "step": 120
91
+ },
92
+ {
93
+ "epoch": 1.02,
94
+ "learning_rate": 0.00014921875000000002,
95
+ "loss": 0.9945,
96
+ "step": 130
97
+ },
98
+ {
99
+ "epoch": 1.09,
100
+ "learning_rate": 0.00014531250000000002,
101
+ "loss": 0.7937,
102
+ "step": 140
103
+ },
104
+ {
105
+ "epoch": 1.17,
106
+ "learning_rate": 0.00014140625,
107
+ "loss": 0.7721,
108
+ "step": 150
109
+ },
110
+ {
111
+ "epoch": 1.25,
112
+ "learning_rate": 0.0001375,
113
+ "loss": 0.7106,
114
+ "step": 160
115
+ },
116
+ {
117
+ "epoch": 1.33,
118
+ "learning_rate": 0.00013359375,
119
+ "loss": 0.6943,
120
+ "step": 170
121
+ },
122
+ {
123
+ "epoch": 1.41,
124
+ "learning_rate": 0.0001296875,
125
+ "loss": 0.7345,
126
+ "step": 180
127
+ },
128
+ {
129
+ "epoch": 1.48,
130
+ "learning_rate": 0.00012578125,
131
+ "loss": 0.7497,
132
+ "step": 190
133
+ },
134
+ {
135
+ "epoch": 1.56,
136
+ "learning_rate": 0.00012187500000000001,
137
+ "loss": 0.7315,
138
+ "step": 200
139
+ },
140
+ {
141
+ "epoch": 1.56,
142
+ "eval_accuracy": 0.5882352941176471,
143
+ "eval_loss": 0.998068630695343,
144
+ "eval_runtime": 9.2665,
145
+ "eval_samples_per_second": 55.037,
146
+ "eval_steps_per_second": 6.907,
147
+ "step": 200
148
+ },
149
+ {
150
+ "epoch": 1.64,
151
+ "learning_rate": 0.00011796875,
152
+ "loss": 0.6931,
153
+ "step": 210
154
+ },
155
+ {
156
+ "epoch": 1.72,
157
+ "learning_rate": 0.0001140625,
158
+ "loss": 0.6189,
159
+ "step": 220
160
+ },
161
+ {
162
+ "epoch": 1.8,
163
+ "learning_rate": 0.00011015625000000001,
164
+ "loss": 0.6924,
165
+ "step": 230
166
+ },
167
+ {
168
+ "epoch": 1.88,
169
+ "learning_rate": 0.00010625000000000001,
170
+ "loss": 0.7201,
171
+ "step": 240
172
+ },
173
+ {
174
+ "epoch": 1.95,
175
+ "learning_rate": 0.00010234375,
176
+ "loss": 0.7225,
177
+ "step": 250
178
+ },
179
+ {
180
+ "epoch": 2.03,
181
+ "learning_rate": 9.84375e-05,
182
+ "loss": 0.4755,
183
+ "step": 260
184
+ },
185
+ {
186
+ "epoch": 2.11,
187
+ "learning_rate": 9.453125000000001e-05,
188
+ "loss": 0.2789,
189
+ "step": 270
190
+ },
191
+ {
192
+ "epoch": 2.19,
193
+ "learning_rate": 9.062500000000001e-05,
194
+ "loss": 0.3311,
195
+ "step": 280
196
+ },
197
+ {
198
+ "epoch": 2.27,
199
+ "learning_rate": 8.671875e-05,
200
+ "loss": 0.3663,
201
+ "step": 290
202
+ },
203
+ {
204
+ "epoch": 2.34,
205
+ "learning_rate": 8.28125e-05,
206
+ "loss": 0.2118,
207
+ "step": 300
208
+ },
209
+ {
210
+ "epoch": 2.34,
211
+ "eval_accuracy": 0.5901960784313726,
212
+ "eval_loss": 1.1650166511535645,
213
+ "eval_runtime": 8.9508,
214
+ "eval_samples_per_second": 56.978,
215
+ "eval_steps_per_second": 7.15,
216
+ "step": 300
217
+ },
218
+ {
219
+ "epoch": 2.42,
220
+ "learning_rate": 7.890625000000001e-05,
221
+ "loss": 0.2309,
222
+ "step": 310
223
+ },
224
+ {
225
+ "epoch": 2.5,
226
+ "learning_rate": 7.500000000000001e-05,
227
+ "loss": 0.2993,
228
+ "step": 320
229
+ },
230
+ {
231
+ "epoch": 2.58,
232
+ "learning_rate": 7.109375e-05,
233
+ "loss": 0.2645,
234
+ "step": 330
235
+ },
236
+ {
237
+ "epoch": 2.66,
238
+ "learning_rate": 6.71875e-05,
239
+ "loss": 0.339,
240
+ "step": 340
241
+ },
242
+ {
243
+ "epoch": 2.73,
244
+ "learning_rate": 6.328125e-05,
245
+ "loss": 0.2321,
246
+ "step": 350
247
+ },
248
+ {
249
+ "epoch": 2.81,
250
+ "learning_rate": 5.9375e-05,
251
+ "loss": 0.2505,
252
+ "step": 360
253
+ },
254
+ {
255
+ "epoch": 2.89,
256
+ "learning_rate": 5.546875e-05,
257
+ "loss": 0.3216,
258
+ "step": 370
259
+ },
260
+ {
261
+ "epoch": 2.97,
262
+ "learning_rate": 5.15625e-05,
263
+ "loss": 0.2255,
264
+ "step": 380
265
+ },
266
+ {
267
+ "epoch": 3.05,
268
+ "learning_rate": 4.765625e-05,
269
+ "loss": 0.2241,
270
+ "step": 390
271
+ },
272
+ {
273
+ "epoch": 3.12,
274
+ "learning_rate": 4.375e-05,
275
+ "loss": 0.1119,
276
+ "step": 400
277
+ },
278
+ {
279
+ "epoch": 3.12,
280
+ "eval_accuracy": 0.5862745098039216,
281
+ "eval_loss": 1.2863526344299316,
282
+ "eval_runtime": 8.5079,
283
+ "eval_samples_per_second": 59.944,
284
+ "eval_steps_per_second": 7.522,
285
+ "step": 400
286
+ },
287
+ {
288
+ "epoch": 3.2,
289
+ "learning_rate": 3.984375e-05,
290
+ "loss": 0.127,
291
+ "step": 410
292
+ },
293
+ {
294
+ "epoch": 3.28,
295
+ "learning_rate": 3.59375e-05,
296
+ "loss": 0.117,
297
+ "step": 420
298
+ },
299
+ {
300
+ "epoch": 3.36,
301
+ "learning_rate": 3.203125e-05,
302
+ "loss": 0.0675,
303
+ "step": 430
304
+ },
305
+ {
306
+ "epoch": 3.44,
307
+ "learning_rate": 2.8125000000000003e-05,
308
+ "loss": 0.0978,
309
+ "step": 440
310
+ },
311
+ {
312
+ "epoch": 3.52,
313
+ "learning_rate": 2.4218750000000003e-05,
314
+ "loss": 0.0846,
315
+ "step": 450
316
+ },
317
+ {
318
+ "epoch": 3.59,
319
+ "learning_rate": 2.0312500000000002e-05,
320
+ "loss": 0.0999,
321
+ "step": 460
322
+ },
323
+ {
324
+ "epoch": 3.67,
325
+ "learning_rate": 1.6406250000000002e-05,
326
+ "loss": 0.0756,
327
+ "step": 470
328
+ },
329
+ {
330
+ "epoch": 3.75,
331
+ "learning_rate": 1.25e-05,
332
+ "loss": 0.1008,
333
+ "step": 480
334
+ },
335
+ {
336
+ "epoch": 3.83,
337
+ "learning_rate": 8.59375e-06,
338
+ "loss": 0.0679,
339
+ "step": 490
340
+ },
341
+ {
342
+ "epoch": 3.91,
343
+ "learning_rate": 4.6875000000000004e-06,
344
+ "loss": 0.1116,
345
+ "step": 500
346
+ },
347
+ {
348
+ "epoch": 3.91,
349
+ "eval_accuracy": 0.5862745098039216,
350
+ "eval_loss": 1.4464128017425537,
351
+ "eval_runtime": 9.2975,
352
+ "eval_samples_per_second": 54.853,
353
+ "eval_steps_per_second": 6.884,
354
+ "step": 500
355
+ },
356
+ {
357
+ "epoch": 3.98,
358
+ "learning_rate": 7.8125e-07,
359
+ "loss": 0.1127,
360
+ "step": 510
361
+ },
362
+ {
363
+ "epoch": 4.0,
364
+ "step": 512,
365
+ "total_flos": 6.311117323294802e+17,
366
+ "train_loss": 0.5731766858662013,
367
+ "train_runtime": 408.7689,
368
+ "train_samples_per_second": 19.923,
369
+ "train_steps_per_second": 1.253
370
+ }
371
+ ],
372
+ "logging_steps": 10,
373
+ "max_steps": 512,
374
+ "num_train_epochs": 4,
375
+ "save_steps": 100,
376
+ "total_flos": 6.311117323294802e+17,
377
+ "trial_name": null,
378
+ "trial_params": null
379
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ebb00c8ab16299855da6c1b2548a3332a03d2ba336965e6ca63995cad83f74d1
3
+ size 4536