HimAJ commited on
Commit
395efd4
·
verified ·
1 Parent(s): 112d5a7

Upload folder using huggingface_hub

Browse files
checkpoint-3400/config.json ADDED
@@ -0,0 +1,45 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "ViTForImageClassification"
4
+ ],
5
+ "attention_probs_dropout_prob": 0.0,
6
+ "dtype": "float32",
7
+ "encoder_stride": 16,
8
+ "hidden_act": "gelu",
9
+ "hidden_dropout_prob": 0.0,
10
+ "hidden_size": 768,
11
+ "id2label": {
12
+ "0": "anger",
13
+ "1": "contempt",
14
+ "2": "disgust",
15
+ "3": "fear",
16
+ "4": "happy",
17
+ "5": "neutral",
18
+ "6": "sad",
19
+ "7": "surprise"
20
+ },
21
+ "image_size": 224,
22
+ "initializer_range": 0.02,
23
+ "intermediate_size": 3072,
24
+ "label2id": {
25
+ "anger": "0",
26
+ "contempt": "1",
27
+ "disgust": "2",
28
+ "fear": "3",
29
+ "happy": "4",
30
+ "neutral": "5",
31
+ "sad": "6",
32
+ "surprise": "7"
33
+ },
34
+ "layer_norm_eps": 1e-12,
35
+ "model_type": "vit",
36
+ "num_attention_heads": 12,
37
+ "num_channels": 3,
38
+ "num_hidden_layers": 12,
39
+ "patch_size": 16,
40
+ "pooler_act": "tanh",
41
+ "pooler_output_size": 768,
42
+ "problem_type": "single_label_classification",
43
+ "qkv_bias": true,
44
+ "transformers_version": "4.57.3"
45
+ }
checkpoint-3400/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:41f0456248e27f1f0606463d3f5816840ca22ae7f3864137bd1529d62a54df1a
3
+ size 343242432
checkpoint-3400/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2df1d0d882d9d2bcddd02570db69852accefd36809d5f4529d772df9696f5e69
3
+ size 686600587
checkpoint-3400/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:22dbf3c2822bd0e012a008f2f8f6fc37e79fd72d0b78e165acf9c07025f5405f
3
+ size 14455
checkpoint-3400/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c12d23a7bc6ab06788f8ab2a95b69ea92d91493a5ff0dec3f64c332eb5606cce
3
+ size 1465
checkpoint-3400/trainer_state.json ADDED
@@ -0,0 +1,290 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": 2488,
3
+ "best_metric": 0.7773311897106109,
4
+ "best_model_checkpoint": null,
5
+ "epoch": 2.733118971061093,
6
+ "eval_steps": 500,
7
+ "global_step": 3400,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.08038585209003216,
14
+ "grad_norm": 10.019948959350586,
15
+ "learning_rate": 1.946945337620579e-05,
16
+ "loss": 1.2824,
17
+ "step": 100
18
+ },
19
+ {
20
+ "epoch": 0.1607717041800643,
21
+ "grad_norm": 8.063481330871582,
22
+ "learning_rate": 1.8933547695605573e-05,
23
+ "loss": 1.159,
24
+ "step": 200
25
+ },
26
+ {
27
+ "epoch": 0.24115755627009647,
28
+ "grad_norm": 13.041501998901367,
29
+ "learning_rate": 1.839764201500536e-05,
30
+ "loss": 1.0909,
31
+ "step": 300
32
+ },
33
+ {
34
+ "epoch": 0.3215434083601286,
35
+ "grad_norm": 8.986650466918945,
36
+ "learning_rate": 1.7861736334405145e-05,
37
+ "loss": 1.0968,
38
+ "step": 400
39
+ },
40
+ {
41
+ "epoch": 0.40192926045016075,
42
+ "grad_norm": 7.692521572113037,
43
+ "learning_rate": 1.732583065380493e-05,
44
+ "loss": 1.0873,
45
+ "step": 500
46
+ },
47
+ {
48
+ "epoch": 0.48231511254019294,
49
+ "grad_norm": 9.055645942687988,
50
+ "learning_rate": 1.6789924973204718e-05,
51
+ "loss": 1.0169,
52
+ "step": 600
53
+ },
54
+ {
55
+ "epoch": 0.5627009646302251,
56
+ "grad_norm": 7.9042463302612305,
57
+ "learning_rate": 1.6254019292604505e-05,
58
+ "loss": 1.0865,
59
+ "step": 700
60
+ },
61
+ {
62
+ "epoch": 0.6430868167202572,
63
+ "grad_norm": 7.55495548248291,
64
+ "learning_rate": 1.571811361200429e-05,
65
+ "loss": 1.0137,
66
+ "step": 800
67
+ },
68
+ {
69
+ "epoch": 0.7234726688102894,
70
+ "grad_norm": 6.291072368621826,
71
+ "learning_rate": 1.5182207931404074e-05,
72
+ "loss": 1.0695,
73
+ "step": 900
74
+ },
75
+ {
76
+ "epoch": 0.8038585209003215,
77
+ "grad_norm": 9.746781349182129,
78
+ "learning_rate": 1.4646302250803858e-05,
79
+ "loss": 1.0335,
80
+ "step": 1000
81
+ },
82
+ {
83
+ "epoch": 0.8842443729903537,
84
+ "grad_norm": 6.898703098297119,
85
+ "learning_rate": 1.4110396570203646e-05,
86
+ "loss": 0.987,
87
+ "step": 1100
88
+ },
89
+ {
90
+ "epoch": 0.9646302250803859,
91
+ "grad_norm": 8.23352336883545,
92
+ "learning_rate": 1.3574490889603432e-05,
93
+ "loss": 0.9442,
94
+ "step": 1200
95
+ },
96
+ {
97
+ "epoch": 1.0,
98
+ "eval_accuracy": 0.6370578778135049,
99
+ "eval_loss": 0.9694849848747253,
100
+ "eval_runtime": 840.7369,
101
+ "eval_samples_per_second": 2.959,
102
+ "eval_steps_per_second": 0.37,
103
+ "step": 1244
104
+ },
105
+ {
106
+ "epoch": 1.045016077170418,
107
+ "grad_norm": 9.776803016662598,
108
+ "learning_rate": 1.3038585209003216e-05,
109
+ "loss": 0.868,
110
+ "step": 1300
111
+ },
112
+ {
113
+ "epoch": 1.1254019292604502,
114
+ "grad_norm": 10.52991771697998,
115
+ "learning_rate": 1.2502679528403e-05,
116
+ "loss": 0.7531,
117
+ "step": 1400
118
+ },
119
+ {
120
+ "epoch": 1.2057877813504823,
121
+ "grad_norm": 11.897740364074707,
122
+ "learning_rate": 1.1966773847802788e-05,
123
+ "loss": 0.7265,
124
+ "step": 1500
125
+ },
126
+ {
127
+ "epoch": 1.2861736334405145,
128
+ "grad_norm": 7.514660835266113,
129
+ "learning_rate": 1.1430868167202574e-05,
130
+ "loss": 0.7793,
131
+ "step": 1600
132
+ },
133
+ {
134
+ "epoch": 1.3665594855305465,
135
+ "grad_norm": 10.338397979736328,
136
+ "learning_rate": 1.0894962486602359e-05,
137
+ "loss": 0.7701,
138
+ "step": 1700
139
+ },
140
+ {
141
+ "epoch": 1.4469453376205788,
142
+ "grad_norm": 13.336085319519043,
143
+ "learning_rate": 1.0359056806002143e-05,
144
+ "loss": 0.7251,
145
+ "step": 1800
146
+ },
147
+ {
148
+ "epoch": 1.527331189710611,
149
+ "grad_norm": 9.34284496307373,
150
+ "learning_rate": 9.823151125401929e-06,
151
+ "loss": 0.7506,
152
+ "step": 1900
153
+ },
154
+ {
155
+ "epoch": 1.607717041800643,
156
+ "grad_norm": 10.490428924560547,
157
+ "learning_rate": 9.287245444801717e-06,
158
+ "loss": 0.7982,
159
+ "step": 2000
160
+ },
161
+ {
162
+ "epoch": 1.6881028938906752,
163
+ "grad_norm": 7.529485702514648,
164
+ "learning_rate": 8.751339764201501e-06,
165
+ "loss": 0.6313,
166
+ "step": 2100
167
+ },
168
+ {
169
+ "epoch": 1.7684887459807075,
170
+ "grad_norm": 12.055130958557129,
171
+ "learning_rate": 8.215434083601287e-06,
172
+ "loss": 0.6671,
173
+ "step": 2200
174
+ },
175
+ {
176
+ "epoch": 1.8488745980707395,
177
+ "grad_norm": 8.625040054321289,
178
+ "learning_rate": 7.679528403001071e-06,
179
+ "loss": 0.6896,
180
+ "step": 2300
181
+ },
182
+ {
183
+ "epoch": 1.9292604501607717,
184
+ "grad_norm": 8.715214729309082,
185
+ "learning_rate": 7.143622722400858e-06,
186
+ "loss": 0.672,
187
+ "step": 2400
188
+ },
189
+ {
190
+ "epoch": 2.0,
191
+ "eval_accuracy": 0.7773311897106109,
192
+ "eval_loss": 0.6390692591667175,
193
+ "eval_runtime": 680.6477,
194
+ "eval_samples_per_second": 3.655,
195
+ "eval_steps_per_second": 0.457,
196
+ "step": 2488
197
+ },
198
+ {
199
+ "epoch": 2.009646302250804,
200
+ "grad_norm": 15.922383308410645,
201
+ "learning_rate": 6.607717041800643e-06,
202
+ "loss": 0.6789,
203
+ "step": 2500
204
+ },
205
+ {
206
+ "epoch": 2.090032154340836,
207
+ "grad_norm": 5.49733829498291,
208
+ "learning_rate": 6.071811361200429e-06,
209
+ "loss": 0.5946,
210
+ "step": 2600
211
+ },
212
+ {
213
+ "epoch": 2.170418006430868,
214
+ "grad_norm": 7.4076714515686035,
215
+ "learning_rate": 5.535905680600214e-06,
216
+ "loss": 0.5985,
217
+ "step": 2700
218
+ },
219
+ {
220
+ "epoch": 2.2508038585209005,
221
+ "grad_norm": 10.85772705078125,
222
+ "learning_rate": 5e-06,
223
+ "loss": 0.6036,
224
+ "step": 2800
225
+ },
226
+ {
227
+ "epoch": 2.3311897106109325,
228
+ "grad_norm": 7.137866497039795,
229
+ "learning_rate": 4.4640943193997856e-06,
230
+ "loss": 0.5502,
231
+ "step": 2900
232
+ },
233
+ {
234
+ "epoch": 2.4115755627009645,
235
+ "grad_norm": 6.020912170410156,
236
+ "learning_rate": 3.928188638799572e-06,
237
+ "loss": 0.6147,
238
+ "step": 3000
239
+ },
240
+ {
241
+ "epoch": 2.491961414790997,
242
+ "grad_norm": 13.015932083129883,
243
+ "learning_rate": 3.392282958199357e-06,
244
+ "loss": 0.5449,
245
+ "step": 3100
246
+ },
247
+ {
248
+ "epoch": 2.572347266881029,
249
+ "grad_norm": 9.120644569396973,
250
+ "learning_rate": 2.8563772775991428e-06,
251
+ "loss": 0.5881,
252
+ "step": 3200
253
+ },
254
+ {
255
+ "epoch": 2.652733118971061,
256
+ "grad_norm": 8.311524391174316,
257
+ "learning_rate": 2.3204715969989283e-06,
258
+ "loss": 0.5486,
259
+ "step": 3300
260
+ },
261
+ {
262
+ "epoch": 2.733118971061093,
263
+ "grad_norm": 13.35053825378418,
264
+ "learning_rate": 1.784565916398714e-06,
265
+ "loss": 0.5958,
266
+ "step": 3400
267
+ }
268
+ ],
269
+ "logging_steps": 100,
270
+ "max_steps": 3732,
271
+ "num_input_tokens_seen": 0,
272
+ "num_train_epochs": 3,
273
+ "save_steps": 200,
274
+ "stateful_callbacks": {
275
+ "TrainerControl": {
276
+ "args": {
277
+ "should_epoch_stop": false,
278
+ "should_evaluate": false,
279
+ "should_log": false,
280
+ "should_save": true,
281
+ "should_training_stop": false
282
+ },
283
+ "attributes": {}
284
+ }
285
+ },
286
+ "total_flos": 2.1072754965687828e+18,
287
+ "train_batch_size": 8,
288
+ "trial_name": null,
289
+ "trial_params": null
290
+ }
checkpoint-3400/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d0ba41b78fb9f233a65b0c2a6b875ec90644efb6b193c931d1e5c5f69391c7d7
3
+ size 5905
checkpoint-3600/config.json ADDED
@@ -0,0 +1,45 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "ViTForImageClassification"
4
+ ],
5
+ "attention_probs_dropout_prob": 0.0,
6
+ "dtype": "float32",
7
+ "encoder_stride": 16,
8
+ "hidden_act": "gelu",
9
+ "hidden_dropout_prob": 0.0,
10
+ "hidden_size": 768,
11
+ "id2label": {
12
+ "0": "anger",
13
+ "1": "contempt",
14
+ "2": "disgust",
15
+ "3": "fear",
16
+ "4": "happy",
17
+ "5": "neutral",
18
+ "6": "sad",
19
+ "7": "surprise"
20
+ },
21
+ "image_size": 224,
22
+ "initializer_range": 0.02,
23
+ "intermediate_size": 3072,
24
+ "label2id": {
25
+ "anger": "0",
26
+ "contempt": "1",
27
+ "disgust": "2",
28
+ "fear": "3",
29
+ "happy": "4",
30
+ "neutral": "5",
31
+ "sad": "6",
32
+ "surprise": "7"
33
+ },
34
+ "layer_norm_eps": 1e-12,
35
+ "model_type": "vit",
36
+ "num_attention_heads": 12,
37
+ "num_channels": 3,
38
+ "num_hidden_layers": 12,
39
+ "patch_size": 16,
40
+ "pooler_act": "tanh",
41
+ "pooler_output_size": 768,
42
+ "problem_type": "single_label_classification",
43
+ "qkv_bias": true,
44
+ "transformers_version": "4.57.3"
45
+ }
checkpoint-3600/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2d3141b1d64241c51bb55415ba3e4f7ff173b8479aec154e69e3497ac04489bf
3
+ size 343242432
checkpoint-3600/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a525dc18888b1155712c0e7873959c112cf51e6afd289c03c9f326dffcb13b3f
3
+ size 686600587
checkpoint-3600/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:22dbf3c2822bd0e012a008f2f8f6fc37e79fd72d0b78e165acf9c07025f5405f
3
+ size 14455
checkpoint-3600/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d5fb3a26ee12109820d069cdf6b9f01db3c645d99db15921417a38e8b948cd69
3
+ size 1465
checkpoint-3600/trainer_state.json ADDED
@@ -0,0 +1,304 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": 2488,
3
+ "best_metric": 0.7773311897106109,
4
+ "best_model_checkpoint": null,
5
+ "epoch": 2.8938906752411575,
6
+ "eval_steps": 500,
7
+ "global_step": 3600,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.08038585209003216,
14
+ "grad_norm": 10.019948959350586,
15
+ "learning_rate": 1.946945337620579e-05,
16
+ "loss": 1.2824,
17
+ "step": 100
18
+ },
19
+ {
20
+ "epoch": 0.1607717041800643,
21
+ "grad_norm": 8.063481330871582,
22
+ "learning_rate": 1.8933547695605573e-05,
23
+ "loss": 1.159,
24
+ "step": 200
25
+ },
26
+ {
27
+ "epoch": 0.24115755627009647,
28
+ "grad_norm": 13.041501998901367,
29
+ "learning_rate": 1.839764201500536e-05,
30
+ "loss": 1.0909,
31
+ "step": 300
32
+ },
33
+ {
34
+ "epoch": 0.3215434083601286,
35
+ "grad_norm": 8.986650466918945,
36
+ "learning_rate": 1.7861736334405145e-05,
37
+ "loss": 1.0968,
38
+ "step": 400
39
+ },
40
+ {
41
+ "epoch": 0.40192926045016075,
42
+ "grad_norm": 7.692521572113037,
43
+ "learning_rate": 1.732583065380493e-05,
44
+ "loss": 1.0873,
45
+ "step": 500
46
+ },
47
+ {
48
+ "epoch": 0.48231511254019294,
49
+ "grad_norm": 9.055645942687988,
50
+ "learning_rate": 1.6789924973204718e-05,
51
+ "loss": 1.0169,
52
+ "step": 600
53
+ },
54
+ {
55
+ "epoch": 0.5627009646302251,
56
+ "grad_norm": 7.9042463302612305,
57
+ "learning_rate": 1.6254019292604505e-05,
58
+ "loss": 1.0865,
59
+ "step": 700
60
+ },
61
+ {
62
+ "epoch": 0.6430868167202572,
63
+ "grad_norm": 7.55495548248291,
64
+ "learning_rate": 1.571811361200429e-05,
65
+ "loss": 1.0137,
66
+ "step": 800
67
+ },
68
+ {
69
+ "epoch": 0.7234726688102894,
70
+ "grad_norm": 6.291072368621826,
71
+ "learning_rate": 1.5182207931404074e-05,
72
+ "loss": 1.0695,
73
+ "step": 900
74
+ },
75
+ {
76
+ "epoch": 0.8038585209003215,
77
+ "grad_norm": 9.746781349182129,
78
+ "learning_rate": 1.4646302250803858e-05,
79
+ "loss": 1.0335,
80
+ "step": 1000
81
+ },
82
+ {
83
+ "epoch": 0.8842443729903537,
84
+ "grad_norm": 6.898703098297119,
85
+ "learning_rate": 1.4110396570203646e-05,
86
+ "loss": 0.987,
87
+ "step": 1100
88
+ },
89
+ {
90
+ "epoch": 0.9646302250803859,
91
+ "grad_norm": 8.23352336883545,
92
+ "learning_rate": 1.3574490889603432e-05,
93
+ "loss": 0.9442,
94
+ "step": 1200
95
+ },
96
+ {
97
+ "epoch": 1.0,
98
+ "eval_accuracy": 0.6370578778135049,
99
+ "eval_loss": 0.9694849848747253,
100
+ "eval_runtime": 840.7369,
101
+ "eval_samples_per_second": 2.959,
102
+ "eval_steps_per_second": 0.37,
103
+ "step": 1244
104
+ },
105
+ {
106
+ "epoch": 1.045016077170418,
107
+ "grad_norm": 9.776803016662598,
108
+ "learning_rate": 1.3038585209003216e-05,
109
+ "loss": 0.868,
110
+ "step": 1300
111
+ },
112
+ {
113
+ "epoch": 1.1254019292604502,
114
+ "grad_norm": 10.52991771697998,
115
+ "learning_rate": 1.2502679528403e-05,
116
+ "loss": 0.7531,
117
+ "step": 1400
118
+ },
119
+ {
120
+ "epoch": 1.2057877813504823,
121
+ "grad_norm": 11.897740364074707,
122
+ "learning_rate": 1.1966773847802788e-05,
123
+ "loss": 0.7265,
124
+ "step": 1500
125
+ },
126
+ {
127
+ "epoch": 1.2861736334405145,
128
+ "grad_norm": 7.514660835266113,
129
+ "learning_rate": 1.1430868167202574e-05,
130
+ "loss": 0.7793,
131
+ "step": 1600
132
+ },
133
+ {
134
+ "epoch": 1.3665594855305465,
135
+ "grad_norm": 10.338397979736328,
136
+ "learning_rate": 1.0894962486602359e-05,
137
+ "loss": 0.7701,
138
+ "step": 1700
139
+ },
140
+ {
141
+ "epoch": 1.4469453376205788,
142
+ "grad_norm": 13.336085319519043,
143
+ "learning_rate": 1.0359056806002143e-05,
144
+ "loss": 0.7251,
145
+ "step": 1800
146
+ },
147
+ {
148
+ "epoch": 1.527331189710611,
149
+ "grad_norm": 9.34284496307373,
150
+ "learning_rate": 9.823151125401929e-06,
151
+ "loss": 0.7506,
152
+ "step": 1900
153
+ },
154
+ {
155
+ "epoch": 1.607717041800643,
156
+ "grad_norm": 10.490428924560547,
157
+ "learning_rate": 9.287245444801717e-06,
158
+ "loss": 0.7982,
159
+ "step": 2000
160
+ },
161
+ {
162
+ "epoch": 1.6881028938906752,
163
+ "grad_norm": 7.529485702514648,
164
+ "learning_rate": 8.751339764201501e-06,
165
+ "loss": 0.6313,
166
+ "step": 2100
167
+ },
168
+ {
169
+ "epoch": 1.7684887459807075,
170
+ "grad_norm": 12.055130958557129,
171
+ "learning_rate": 8.215434083601287e-06,
172
+ "loss": 0.6671,
173
+ "step": 2200
174
+ },
175
+ {
176
+ "epoch": 1.8488745980707395,
177
+ "grad_norm": 8.625040054321289,
178
+ "learning_rate": 7.679528403001071e-06,
179
+ "loss": 0.6896,
180
+ "step": 2300
181
+ },
182
+ {
183
+ "epoch": 1.9292604501607717,
184
+ "grad_norm": 8.715214729309082,
185
+ "learning_rate": 7.143622722400858e-06,
186
+ "loss": 0.672,
187
+ "step": 2400
188
+ },
189
+ {
190
+ "epoch": 2.0,
191
+ "eval_accuracy": 0.7773311897106109,
192
+ "eval_loss": 0.6390692591667175,
193
+ "eval_runtime": 680.6477,
194
+ "eval_samples_per_second": 3.655,
195
+ "eval_steps_per_second": 0.457,
196
+ "step": 2488
197
+ },
198
+ {
199
+ "epoch": 2.009646302250804,
200
+ "grad_norm": 15.922383308410645,
201
+ "learning_rate": 6.607717041800643e-06,
202
+ "loss": 0.6789,
203
+ "step": 2500
204
+ },
205
+ {
206
+ "epoch": 2.090032154340836,
207
+ "grad_norm": 5.49733829498291,
208
+ "learning_rate": 6.071811361200429e-06,
209
+ "loss": 0.5946,
210
+ "step": 2600
211
+ },
212
+ {
213
+ "epoch": 2.170418006430868,
214
+ "grad_norm": 7.4076714515686035,
215
+ "learning_rate": 5.535905680600214e-06,
216
+ "loss": 0.5985,
217
+ "step": 2700
218
+ },
219
+ {
220
+ "epoch": 2.2508038585209005,
221
+ "grad_norm": 10.85772705078125,
222
+ "learning_rate": 5e-06,
223
+ "loss": 0.6036,
224
+ "step": 2800
225
+ },
226
+ {
227
+ "epoch": 2.3311897106109325,
228
+ "grad_norm": 7.137866497039795,
229
+ "learning_rate": 4.4640943193997856e-06,
230
+ "loss": 0.5502,
231
+ "step": 2900
232
+ },
233
+ {
234
+ "epoch": 2.4115755627009645,
235
+ "grad_norm": 6.020912170410156,
236
+ "learning_rate": 3.928188638799572e-06,
237
+ "loss": 0.6147,
238
+ "step": 3000
239
+ },
240
+ {
241
+ "epoch": 2.491961414790997,
242
+ "grad_norm": 13.015932083129883,
243
+ "learning_rate": 3.392282958199357e-06,
244
+ "loss": 0.5449,
245
+ "step": 3100
246
+ },
247
+ {
248
+ "epoch": 2.572347266881029,
249
+ "grad_norm": 9.120644569396973,
250
+ "learning_rate": 2.8563772775991428e-06,
251
+ "loss": 0.5881,
252
+ "step": 3200
253
+ },
254
+ {
255
+ "epoch": 2.652733118971061,
256
+ "grad_norm": 8.311524391174316,
257
+ "learning_rate": 2.3204715969989283e-06,
258
+ "loss": 0.5486,
259
+ "step": 3300
260
+ },
261
+ {
262
+ "epoch": 2.733118971061093,
263
+ "grad_norm": 13.35053825378418,
264
+ "learning_rate": 1.784565916398714e-06,
265
+ "loss": 0.5958,
266
+ "step": 3400
267
+ },
268
+ {
269
+ "epoch": 2.8135048231511255,
270
+ "grad_norm": 16.09385871887207,
271
+ "learning_rate": 1.2486602357984997e-06,
272
+ "loss": 0.6082,
273
+ "step": 3500
274
+ },
275
+ {
276
+ "epoch": 2.8938906752411575,
277
+ "grad_norm": 9.562971115112305,
278
+ "learning_rate": 7.127545551982852e-07,
279
+ "loss": 0.5594,
280
+ "step": 3600
281
+ }
282
+ ],
283
+ "logging_steps": 100,
284
+ "max_steps": 3732,
285
+ "num_input_tokens_seen": 0,
286
+ "num_train_epochs": 3,
287
+ "save_steps": 200,
288
+ "stateful_callbacks": {
289
+ "TrainerControl": {
290
+ "args": {
291
+ "should_epoch_stop": false,
292
+ "should_evaluate": false,
293
+ "should_log": false,
294
+ "should_save": true,
295
+ "should_training_stop": false
296
+ },
297
+ "attributes": {}
298
+ }
299
+ },
300
+ "total_flos": 2.2312693474995732e+18,
301
+ "train_batch_size": 8,
302
+ "trial_name": null,
303
+ "trial_params": null
304
+ }
checkpoint-3600/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d0ba41b78fb9f233a65b0c2a6b875ec90644efb6b193c931d1e5c5f69391c7d7
3
+ size 5905
checkpoint-3732/config.json ADDED
@@ -0,0 +1,45 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "ViTForImageClassification"
4
+ ],
5
+ "attention_probs_dropout_prob": 0.0,
6
+ "dtype": "float32",
7
+ "encoder_stride": 16,
8
+ "hidden_act": "gelu",
9
+ "hidden_dropout_prob": 0.0,
10
+ "hidden_size": 768,
11
+ "id2label": {
12
+ "0": "anger",
13
+ "1": "contempt",
14
+ "2": "disgust",
15
+ "3": "fear",
16
+ "4": "happy",
17
+ "5": "neutral",
18
+ "6": "sad",
19
+ "7": "surprise"
20
+ },
21
+ "image_size": 224,
22
+ "initializer_range": 0.02,
23
+ "intermediate_size": 3072,
24
+ "label2id": {
25
+ "anger": "0",
26
+ "contempt": "1",
27
+ "disgust": "2",
28
+ "fear": "3",
29
+ "happy": "4",
30
+ "neutral": "5",
31
+ "sad": "6",
32
+ "surprise": "7"
33
+ },
34
+ "layer_norm_eps": 1e-12,
35
+ "model_type": "vit",
36
+ "num_attention_heads": 12,
37
+ "num_channels": 3,
38
+ "num_hidden_layers": 12,
39
+ "patch_size": 16,
40
+ "pooler_act": "tanh",
41
+ "pooler_output_size": 768,
42
+ "problem_type": "single_label_classification",
43
+ "qkv_bias": true,
44
+ "transformers_version": "4.57.3"
45
+ }
checkpoint-3732/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8042f5d8525c3fcd046818ef47c0a408fb3cf19641062a0ddbe7dcb988074e71
3
+ size 343242432
checkpoint-3732/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0ea7e9e20efbb8863a34f99f2df1f2c11af75a85807ffa44417a3285aaa7c344
3
+ size 686600587
checkpoint-3732/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:22dbf3c2822bd0e012a008f2f8f6fc37e79fd72d0b78e165acf9c07025f5405f
3
+ size 14455
checkpoint-3732/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e842b18da9a03233c55cb3838b93e2fb950a36a84937fcc6640c9a8d649167a4
3
+ size 1465
checkpoint-3732/trainer_state.json ADDED
@@ -0,0 +1,311 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": 2488,
3
+ "best_metric": 0.7773311897106109,
4
+ "best_model_checkpoint": null,
5
+ "epoch": 3.0,
6
+ "eval_steps": 500,
7
+ "global_step": 3732,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.08038585209003216,
14
+ "grad_norm": 10.019948959350586,
15
+ "learning_rate": 1.946945337620579e-05,
16
+ "loss": 1.2824,
17
+ "step": 100
18
+ },
19
+ {
20
+ "epoch": 0.1607717041800643,
21
+ "grad_norm": 8.063481330871582,
22
+ "learning_rate": 1.8933547695605573e-05,
23
+ "loss": 1.159,
24
+ "step": 200
25
+ },
26
+ {
27
+ "epoch": 0.24115755627009647,
28
+ "grad_norm": 13.041501998901367,
29
+ "learning_rate": 1.839764201500536e-05,
30
+ "loss": 1.0909,
31
+ "step": 300
32
+ },
33
+ {
34
+ "epoch": 0.3215434083601286,
35
+ "grad_norm": 8.986650466918945,
36
+ "learning_rate": 1.7861736334405145e-05,
37
+ "loss": 1.0968,
38
+ "step": 400
39
+ },
40
+ {
41
+ "epoch": 0.40192926045016075,
42
+ "grad_norm": 7.692521572113037,
43
+ "learning_rate": 1.732583065380493e-05,
44
+ "loss": 1.0873,
45
+ "step": 500
46
+ },
47
+ {
48
+ "epoch": 0.48231511254019294,
49
+ "grad_norm": 9.055645942687988,
50
+ "learning_rate": 1.6789924973204718e-05,
51
+ "loss": 1.0169,
52
+ "step": 600
53
+ },
54
+ {
55
+ "epoch": 0.5627009646302251,
56
+ "grad_norm": 7.9042463302612305,
57
+ "learning_rate": 1.6254019292604505e-05,
58
+ "loss": 1.0865,
59
+ "step": 700
60
+ },
61
+ {
62
+ "epoch": 0.6430868167202572,
63
+ "grad_norm": 7.55495548248291,
64
+ "learning_rate": 1.571811361200429e-05,
65
+ "loss": 1.0137,
66
+ "step": 800
67
+ },
68
+ {
69
+ "epoch": 0.7234726688102894,
70
+ "grad_norm": 6.291072368621826,
71
+ "learning_rate": 1.5182207931404074e-05,
72
+ "loss": 1.0695,
73
+ "step": 900
74
+ },
75
+ {
76
+ "epoch": 0.8038585209003215,
77
+ "grad_norm": 9.746781349182129,
78
+ "learning_rate": 1.4646302250803858e-05,
79
+ "loss": 1.0335,
80
+ "step": 1000
81
+ },
82
+ {
83
+ "epoch": 0.8842443729903537,
84
+ "grad_norm": 6.898703098297119,
85
+ "learning_rate": 1.4110396570203646e-05,
86
+ "loss": 0.987,
87
+ "step": 1100
88
+ },
89
+ {
90
+ "epoch": 0.9646302250803859,
91
+ "grad_norm": 8.23352336883545,
92
+ "learning_rate": 1.3574490889603432e-05,
93
+ "loss": 0.9442,
94
+ "step": 1200
95
+ },
96
+ {
97
+ "epoch": 1.0,
98
+ "eval_accuracy": 0.6370578778135049,
99
+ "eval_loss": 0.9694849848747253,
100
+ "eval_runtime": 840.7369,
101
+ "eval_samples_per_second": 2.959,
102
+ "eval_steps_per_second": 0.37,
103
+ "step": 1244
104
+ },
105
+ {
106
+ "epoch": 1.045016077170418,
107
+ "grad_norm": 9.776803016662598,
108
+ "learning_rate": 1.3038585209003216e-05,
109
+ "loss": 0.868,
110
+ "step": 1300
111
+ },
112
+ {
113
+ "epoch": 1.1254019292604502,
114
+ "grad_norm": 10.52991771697998,
115
+ "learning_rate": 1.2502679528403e-05,
116
+ "loss": 0.7531,
117
+ "step": 1400
118
+ },
119
+ {
120
+ "epoch": 1.2057877813504823,
121
+ "grad_norm": 11.897740364074707,
122
+ "learning_rate": 1.1966773847802788e-05,
123
+ "loss": 0.7265,
124
+ "step": 1500
125
+ },
126
+ {
127
+ "epoch": 1.2861736334405145,
128
+ "grad_norm": 7.514660835266113,
129
+ "learning_rate": 1.1430868167202574e-05,
130
+ "loss": 0.7793,
131
+ "step": 1600
132
+ },
133
+ {
134
+ "epoch": 1.3665594855305465,
135
+ "grad_norm": 10.338397979736328,
136
+ "learning_rate": 1.0894962486602359e-05,
137
+ "loss": 0.7701,
138
+ "step": 1700
139
+ },
140
+ {
141
+ "epoch": 1.4469453376205788,
142
+ "grad_norm": 13.336085319519043,
143
+ "learning_rate": 1.0359056806002143e-05,
144
+ "loss": 0.7251,
145
+ "step": 1800
146
+ },
147
+ {
148
+ "epoch": 1.527331189710611,
149
+ "grad_norm": 9.34284496307373,
150
+ "learning_rate": 9.823151125401929e-06,
151
+ "loss": 0.7506,
152
+ "step": 1900
153
+ },
154
+ {
155
+ "epoch": 1.607717041800643,
156
+ "grad_norm": 10.490428924560547,
157
+ "learning_rate": 9.287245444801717e-06,
158
+ "loss": 0.7982,
159
+ "step": 2000
160
+ },
161
+ {
162
+ "epoch": 1.6881028938906752,
163
+ "grad_norm": 7.529485702514648,
164
+ "learning_rate": 8.751339764201501e-06,
165
+ "loss": 0.6313,
166
+ "step": 2100
167
+ },
168
+ {
169
+ "epoch": 1.7684887459807075,
170
+ "grad_norm": 12.055130958557129,
171
+ "learning_rate": 8.215434083601287e-06,
172
+ "loss": 0.6671,
173
+ "step": 2200
174
+ },
175
+ {
176
+ "epoch": 1.8488745980707395,
177
+ "grad_norm": 8.625040054321289,
178
+ "learning_rate": 7.679528403001071e-06,
179
+ "loss": 0.6896,
180
+ "step": 2300
181
+ },
182
+ {
183
+ "epoch": 1.9292604501607717,
184
+ "grad_norm": 8.715214729309082,
185
+ "learning_rate": 7.143622722400858e-06,
186
+ "loss": 0.672,
187
+ "step": 2400
188
+ },
189
+ {
190
+ "epoch": 2.0,
191
+ "eval_accuracy": 0.7773311897106109,
192
+ "eval_loss": 0.6390692591667175,
193
+ "eval_runtime": 680.6477,
194
+ "eval_samples_per_second": 3.655,
195
+ "eval_steps_per_second": 0.457,
196
+ "step": 2488
197
+ },
198
+ {
199
+ "epoch": 2.009646302250804,
200
+ "grad_norm": 15.922383308410645,
201
+ "learning_rate": 6.607717041800643e-06,
202
+ "loss": 0.6789,
203
+ "step": 2500
204
+ },
205
+ {
206
+ "epoch": 2.090032154340836,
207
+ "grad_norm": 5.49733829498291,
208
+ "learning_rate": 6.071811361200429e-06,
209
+ "loss": 0.5946,
210
+ "step": 2600
211
+ },
212
+ {
213
+ "epoch": 2.170418006430868,
214
+ "grad_norm": 7.4076714515686035,
215
+ "learning_rate": 5.535905680600214e-06,
216
+ "loss": 0.5985,
217
+ "step": 2700
218
+ },
219
+ {
220
+ "epoch": 2.2508038585209005,
221
+ "grad_norm": 10.85772705078125,
222
+ "learning_rate": 5e-06,
223
+ "loss": 0.6036,
224
+ "step": 2800
225
+ },
226
+ {
227
+ "epoch": 2.3311897106109325,
228
+ "grad_norm": 7.137866497039795,
229
+ "learning_rate": 4.4640943193997856e-06,
230
+ "loss": 0.5502,
231
+ "step": 2900
232
+ },
233
+ {
234
+ "epoch": 2.4115755627009645,
235
+ "grad_norm": 6.020912170410156,
236
+ "learning_rate": 3.928188638799572e-06,
237
+ "loss": 0.6147,
238
+ "step": 3000
239
+ },
240
+ {
241
+ "epoch": 2.491961414790997,
242
+ "grad_norm": 13.015932083129883,
243
+ "learning_rate": 3.392282958199357e-06,
244
+ "loss": 0.5449,
245
+ "step": 3100
246
+ },
247
+ {
248
+ "epoch": 2.572347266881029,
249
+ "grad_norm": 9.120644569396973,
250
+ "learning_rate": 2.8563772775991428e-06,
251
+ "loss": 0.5881,
252
+ "step": 3200
253
+ },
254
+ {
255
+ "epoch": 2.652733118971061,
256
+ "grad_norm": 8.311524391174316,
257
+ "learning_rate": 2.3204715969989283e-06,
258
+ "loss": 0.5486,
259
+ "step": 3300
260
+ },
261
+ {
262
+ "epoch": 2.733118971061093,
263
+ "grad_norm": 13.35053825378418,
264
+ "learning_rate": 1.784565916398714e-06,
265
+ "loss": 0.5958,
266
+ "step": 3400
267
+ },
268
+ {
269
+ "epoch": 2.8135048231511255,
270
+ "grad_norm": 16.09385871887207,
271
+ "learning_rate": 1.2486602357984997e-06,
272
+ "loss": 0.6082,
273
+ "step": 3500
274
+ },
275
+ {
276
+ "epoch": 2.8938906752411575,
277
+ "grad_norm": 9.562971115112305,
278
+ "learning_rate": 7.127545551982852e-07,
279
+ "loss": 0.5594,
280
+ "step": 3600
281
+ },
282
+ {
283
+ "epoch": 2.97427652733119,
284
+ "grad_norm": 2.4870011806488037,
285
+ "learning_rate": 1.7684887459807076e-07,
286
+ "loss": 0.5797,
287
+ "step": 3700
288
+ }
289
+ ],
290
+ "logging_steps": 100,
291
+ "max_steps": 3732,
292
+ "num_input_tokens_seen": 0,
293
+ "num_train_epochs": 3,
294
+ "save_steps": 200,
295
+ "stateful_callbacks": {
296
+ "TrainerControl": {
297
+ "args": {
298
+ "should_epoch_stop": false,
299
+ "should_evaluate": false,
300
+ "should_log": false,
301
+ "should_save": true,
302
+ "should_training_stop": true
303
+ },
304
+ "attributes": {}
305
+ }
306
+ },
307
+ "total_flos": 2.312795304486568e+18,
308
+ "train_batch_size": 8,
309
+ "trial_name": null,
310
+ "trial_params": null
311
+ }
checkpoint-3732/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d0ba41b78fb9f233a65b0c2a6b875ec90644efb6b193c931d1e5c5f69391c7d7
3
+ size 5905
config.json ADDED
@@ -0,0 +1,45 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "ViTForImageClassification"
4
+ ],
5
+ "attention_probs_dropout_prob": 0.0,
6
+ "dtype": "float32",
7
+ "encoder_stride": 16,
8
+ "hidden_act": "gelu",
9
+ "hidden_dropout_prob": 0.0,
10
+ "hidden_size": 768,
11
+ "id2label": {
12
+ "0": "anger",
13
+ "1": "contempt",
14
+ "2": "disgust",
15
+ "3": "fear",
16
+ "4": "happy",
17
+ "5": "neutral",
18
+ "6": "sad",
19
+ "7": "surprise"
20
+ },
21
+ "image_size": 224,
22
+ "initializer_range": 0.02,
23
+ "intermediate_size": 3072,
24
+ "label2id": {
25
+ "anger": "0",
26
+ "contempt": "1",
27
+ "disgust": "2",
28
+ "fear": "3",
29
+ "happy": "4",
30
+ "neutral": "5",
31
+ "sad": "6",
32
+ "surprise": "7"
33
+ },
34
+ "layer_norm_eps": 1e-12,
35
+ "model_type": "vit",
36
+ "num_attention_heads": 12,
37
+ "num_channels": 3,
38
+ "num_hidden_layers": 12,
39
+ "patch_size": 16,
40
+ "pooler_act": "tanh",
41
+ "pooler_output_size": 768,
42
+ "problem_type": "single_label_classification",
43
+ "qkv_bias": true,
44
+ "transformers_version": "4.57.3"
45
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8042f5d8525c3fcd046818ef47c0a408fb3cf19641062a0ddbe7dcb988074e71
3
+ size 343242432
preprocessor_config.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "do_convert_rgb": null,
3
+ "do_normalize": true,
4
+ "do_rescale": true,
5
+ "do_resize": "google/vit-base-patch16-224",
6
+ "image_mean": [
7
+ 0.5,
8
+ 0.5,
9
+ 0.5
10
+ ],
11
+ "image_processor_type": "ViTFeatureExtractor",
12
+ "image_std": [
13
+ 0.5,
14
+ 0.5,
15
+ 0.5
16
+ ],
17
+ "resample": 2,
18
+ "rescale_factor": 0.00392156862745098,
19
+ "size": {
20
+ "height": 224,
21
+ "width": 224
22
+ },
23
+ "trust_remote_code": true
24
+ }