End of training
Browse files- README.md +3 -3
- all_results.json +13 -0
- eval_results.json +8 -0
- train_results.json +8 -0
- trainer_state.json +334 -0
README.md
CHANGED
@@ -22,7 +22,7 @@ model-index:
|
|
22 |
metrics:
|
23 |
- name: Accuracy
|
24 |
type: accuracy
|
25 |
-
value: 0.
|
26 |
---
|
27 |
|
28 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
@@ -32,8 +32,8 @@ should probably proofread and complete it, then remove this comment. -->
|
|
32 |
|
33 |
This model is a fine-tuned version of [google/vit-base-patch16-224](https://huggingface.co/google/vit-base-patch16-224) on the image_folder dataset.
|
34 |
It achieves the following results on the evaluation set:
|
35 |
-
- Loss: 0.
|
36 |
-
- Accuracy: 0.
|
37 |
|
38 |
## Model description
|
39 |
|
|
|
22 |
metrics:
|
23 |
- name: Accuracy
|
24 |
type: accuracy
|
25 |
+
value: 0.8655030800821355
|
26 |
---
|
27 |
|
28 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
|
32 |
|
33 |
This model is a fine-tuned version of [google/vit-base-patch16-224](https://huggingface.co/google/vit-base-patch16-224) on the image_folder dataset.
|
34 |
It achieves the following results on the evaluation set:
|
35 |
+
- Loss: 0.6720
|
36 |
+
- Accuracy: 0.8655
|
37 |
|
38 |
## Model description
|
39 |
|
all_results.json
ADDED
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 16.0,
|
3 |
+
"eval_accuracy": 0.8655030800821355,
|
4 |
+
"eval_loss": 0.67196124792099,
|
5 |
+
"eval_runtime": 8.7346,
|
6 |
+
"eval_samples_per_second": 111.511,
|
7 |
+
"eval_steps_per_second": 0.916,
|
8 |
+
"total_flos": 1.087746145977493e+19,
|
9 |
+
"train_loss": 1.7795628476617993,
|
10 |
+
"train_runtime": 3092.1212,
|
11 |
+
"train_samples_per_second": 119.027,
|
12 |
+
"train_steps_per_second": 0.231
|
13 |
+
}
|
eval_results.json
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 16.0,
|
3 |
+
"eval_accuracy": 0.8655030800821355,
|
4 |
+
"eval_loss": 0.67196124792099,
|
5 |
+
"eval_runtime": 8.7346,
|
6 |
+
"eval_samples_per_second": 111.511,
|
7 |
+
"eval_steps_per_second": 0.916
|
8 |
+
}
|
train_results.json
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 16.0,
|
3 |
+
"total_flos": 1.087746145977493e+19,
|
4 |
+
"train_loss": 1.7795628476617993,
|
5 |
+
"train_runtime": 3092.1212,
|
6 |
+
"train_samples_per_second": 119.027,
|
7 |
+
"train_steps_per_second": 0.231
|
8 |
+
}
|
trainer_state.json
ADDED
@@ -0,0 +1,334 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 0.8655030800821355,
|
3 |
+
"best_model_checkpoint": "AnimeCharacterClassifierMark1/checkpoint-258",
|
4 |
+
"epoch": 16.0,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 276,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.58,
|
13 |
+
"learning_rate": 6.944444444444445e-06,
|
14 |
+
"loss": 5.0145,
|
15 |
+
"step": 10
|
16 |
+
},
|
17 |
+
{
|
18 |
+
"epoch": 0.99,
|
19 |
+
"eval_accuracy": 0.009240246406570842,
|
20 |
+
"eval_loss": 4.930349826812744,
|
21 |
+
"eval_runtime": 9.5929,
|
22 |
+
"eval_samples_per_second": 101.533,
|
23 |
+
"eval_steps_per_second": 0.834,
|
24 |
+
"step": 17
|
25 |
+
},
|
26 |
+
{
|
27 |
+
"epoch": 1.16,
|
28 |
+
"learning_rate": 1.388888888888889e-05,
|
29 |
+
"loss": 4.932,
|
30 |
+
"step": 20
|
31 |
+
},
|
32 |
+
{
|
33 |
+
"epoch": 1.74,
|
34 |
+
"learning_rate": 2.0833333333333336e-05,
|
35 |
+
"loss": 4.8416,
|
36 |
+
"step": 30
|
37 |
+
},
|
38 |
+
{
|
39 |
+
"epoch": 1.97,
|
40 |
+
"eval_accuracy": 0.028747433264887063,
|
41 |
+
"eval_loss": 4.748697757720947,
|
42 |
+
"eval_runtime": 8.8137,
|
43 |
+
"eval_samples_per_second": 110.51,
|
44 |
+
"eval_steps_per_second": 0.908,
|
45 |
+
"step": 34
|
46 |
+
},
|
47 |
+
{
|
48 |
+
"epoch": 2.32,
|
49 |
+
"learning_rate": 2.777777777777778e-05,
|
50 |
+
"loss": 4.6652,
|
51 |
+
"step": 40
|
52 |
+
},
|
53 |
+
{
|
54 |
+
"epoch": 2.9,
|
55 |
+
"learning_rate": 3.472222222222222e-05,
|
56 |
+
"loss": 4.4383,
|
57 |
+
"step": 50
|
58 |
+
},
|
59 |
+
{
|
60 |
+
"epoch": 2.96,
|
61 |
+
"eval_accuracy": 0.11704312114989733,
|
62 |
+
"eval_loss": 4.359685897827148,
|
63 |
+
"eval_runtime": 10.311,
|
64 |
+
"eval_samples_per_second": 94.462,
|
65 |
+
"eval_steps_per_second": 0.776,
|
66 |
+
"step": 51
|
67 |
+
},
|
68 |
+
{
|
69 |
+
"epoch": 3.48,
|
70 |
+
"learning_rate": 4.166666666666667e-05,
|
71 |
+
"loss": 4.0762,
|
72 |
+
"step": 60
|
73 |
+
},
|
74 |
+
{
|
75 |
+
"epoch": 4.0,
|
76 |
+
"eval_accuracy": 0.32238193018480493,
|
77 |
+
"eval_loss": 3.641871213912964,
|
78 |
+
"eval_runtime": 9.02,
|
79 |
+
"eval_samples_per_second": 107.982,
|
80 |
+
"eval_steps_per_second": 0.887,
|
81 |
+
"step": 69
|
82 |
+
},
|
83 |
+
{
|
84 |
+
"epoch": 4.06,
|
85 |
+
"learning_rate": 4.8611111111111115e-05,
|
86 |
+
"loss": 3.6518,
|
87 |
+
"step": 70
|
88 |
+
},
|
89 |
+
{
|
90 |
+
"epoch": 4.64,
|
91 |
+
"learning_rate": 4.937694704049845e-05,
|
92 |
+
"loss": 3.108,
|
93 |
+
"step": 80
|
94 |
+
},
|
95 |
+
{
|
96 |
+
"epoch": 4.99,
|
97 |
+
"eval_accuracy": 0.5246406570841889,
|
98 |
+
"eval_loss": 2.857390880584717,
|
99 |
+
"eval_runtime": 8.9304,
|
100 |
+
"eval_samples_per_second": 109.065,
|
101 |
+
"eval_steps_per_second": 0.896,
|
102 |
+
"step": 86
|
103 |
+
},
|
104 |
+
{
|
105 |
+
"epoch": 5.22,
|
106 |
+
"learning_rate": 4.85981308411215e-05,
|
107 |
+
"loss": 2.606,
|
108 |
+
"step": 90
|
109 |
+
},
|
110 |
+
{
|
111 |
+
"epoch": 5.8,
|
112 |
+
"learning_rate": 4.781931464174455e-05,
|
113 |
+
"loss": 2.1571,
|
114 |
+
"step": 100
|
115 |
+
},
|
116 |
+
{
|
117 |
+
"epoch": 5.97,
|
118 |
+
"eval_accuracy": 0.6652977412731006,
|
119 |
+
"eval_loss": 2.2128942012786865,
|
120 |
+
"eval_runtime": 8.8437,
|
121 |
+
"eval_samples_per_second": 110.136,
|
122 |
+
"eval_steps_per_second": 0.905,
|
123 |
+
"step": 103
|
124 |
+
},
|
125 |
+
{
|
126 |
+
"epoch": 6.38,
|
127 |
+
"learning_rate": 4.7040498442367604e-05,
|
128 |
+
"loss": 1.7668,
|
129 |
+
"step": 110
|
130 |
+
},
|
131 |
+
{
|
132 |
+
"epoch": 6.96,
|
133 |
+
"learning_rate": 4.6261682242990654e-05,
|
134 |
+
"loss": 1.4685,
|
135 |
+
"step": 120
|
136 |
+
},
|
137 |
+
{
|
138 |
+
"epoch": 6.96,
|
139 |
+
"eval_accuracy": 0.7494866529774127,
|
140 |
+
"eval_loss": 1.7289572954177856,
|
141 |
+
"eval_runtime": 9.9463,
|
142 |
+
"eval_samples_per_second": 97.926,
|
143 |
+
"eval_steps_per_second": 0.804,
|
144 |
+
"step": 120
|
145 |
+
},
|
146 |
+
{
|
147 |
+
"epoch": 7.54,
|
148 |
+
"learning_rate": 4.548286604361371e-05,
|
149 |
+
"loss": 1.1649,
|
150 |
+
"step": 130
|
151 |
+
},
|
152 |
+
{
|
153 |
+
"epoch": 8.0,
|
154 |
+
"eval_accuracy": 0.797741273100616,
|
155 |
+
"eval_loss": 1.3861801624298096,
|
156 |
+
"eval_runtime": 8.8226,
|
157 |
+
"eval_samples_per_second": 110.398,
|
158 |
+
"eval_steps_per_second": 0.907,
|
159 |
+
"step": 138
|
160 |
+
},
|
161 |
+
{
|
162 |
+
"epoch": 8.12,
|
163 |
+
"learning_rate": 4.470404984423676e-05,
|
164 |
+
"loss": 0.9897,
|
165 |
+
"step": 140
|
166 |
+
},
|
167 |
+
{
|
168 |
+
"epoch": 8.7,
|
169 |
+
"learning_rate": 4.392523364485982e-05,
|
170 |
+
"loss": 0.7905,
|
171 |
+
"step": 150
|
172 |
+
},
|
173 |
+
{
|
174 |
+
"epoch": 8.99,
|
175 |
+
"eval_accuracy": 0.8213552361396304,
|
176 |
+
"eval_loss": 1.1588941812515259,
|
177 |
+
"eval_runtime": 8.795,
|
178 |
+
"eval_samples_per_second": 110.745,
|
179 |
+
"eval_steps_per_second": 0.91,
|
180 |
+
"step": 155
|
181 |
+
},
|
182 |
+
{
|
183 |
+
"epoch": 9.28,
|
184 |
+
"learning_rate": 4.314641744548287e-05,
|
185 |
+
"loss": 0.6727,
|
186 |
+
"step": 160
|
187 |
+
},
|
188 |
+
{
|
189 |
+
"epoch": 9.86,
|
190 |
+
"learning_rate": 4.236760124610592e-05,
|
191 |
+
"loss": 0.5549,
|
192 |
+
"step": 170
|
193 |
+
},
|
194 |
+
{
|
195 |
+
"epoch": 9.97,
|
196 |
+
"eval_accuracy": 0.8295687885010267,
|
197 |
+
"eval_loss": 1.0262539386749268,
|
198 |
+
"eval_runtime": 8.8584,
|
199 |
+
"eval_samples_per_second": 109.953,
|
200 |
+
"eval_steps_per_second": 0.903,
|
201 |
+
"step": 172
|
202 |
+
},
|
203 |
+
{
|
204 |
+
"epoch": 10.43,
|
205 |
+
"learning_rate": 4.1588785046728974e-05,
|
206 |
+
"loss": 0.4577,
|
207 |
+
"step": 180
|
208 |
+
},
|
209 |
+
{
|
210 |
+
"epoch": 10.96,
|
211 |
+
"eval_accuracy": 0.8367556468172485,
|
212 |
+
"eval_loss": 0.8994325995445251,
|
213 |
+
"eval_runtime": 8.7654,
|
214 |
+
"eval_samples_per_second": 111.119,
|
215 |
+
"eval_steps_per_second": 0.913,
|
216 |
+
"step": 189
|
217 |
+
},
|
218 |
+
{
|
219 |
+
"epoch": 11.01,
|
220 |
+
"learning_rate": 4.0809968847352024e-05,
|
221 |
+
"loss": 0.3757,
|
222 |
+
"step": 190
|
223 |
+
},
|
224 |
+
{
|
225 |
+
"epoch": 11.59,
|
226 |
+
"learning_rate": 4.003115264797508e-05,
|
227 |
+
"loss": 0.2964,
|
228 |
+
"step": 200
|
229 |
+
},
|
230 |
+
{
|
231 |
+
"epoch": 12.0,
|
232 |
+
"eval_accuracy": 0.8552361396303901,
|
233 |
+
"eval_loss": 0.808638870716095,
|
234 |
+
"eval_runtime": 11.2618,
|
235 |
+
"eval_samples_per_second": 86.487,
|
236 |
+
"eval_steps_per_second": 0.71,
|
237 |
+
"step": 207
|
238 |
+
},
|
239 |
+
{
|
240 |
+
"epoch": 12.17,
|
241 |
+
"learning_rate": 3.925233644859813e-05,
|
242 |
+
"loss": 0.2592,
|
243 |
+
"step": 210
|
244 |
+
},
|
245 |
+
{
|
246 |
+
"epoch": 12.75,
|
247 |
+
"learning_rate": 3.847352024922119e-05,
|
248 |
+
"loss": 0.194,
|
249 |
+
"step": 220
|
250 |
+
},
|
251 |
+
{
|
252 |
+
"epoch": 12.99,
|
253 |
+
"eval_accuracy": 0.8583162217659137,
|
254 |
+
"eval_loss": 0.744567334651947,
|
255 |
+
"eval_runtime": 8.8124,
|
256 |
+
"eval_samples_per_second": 110.526,
|
257 |
+
"eval_steps_per_second": 0.908,
|
258 |
+
"step": 224
|
259 |
+
},
|
260 |
+
{
|
261 |
+
"epoch": 13.33,
|
262 |
+
"learning_rate": 3.769470404984424e-05,
|
263 |
+
"loss": 0.1626,
|
264 |
+
"step": 230
|
265 |
+
},
|
266 |
+
{
|
267 |
+
"epoch": 13.91,
|
268 |
+
"learning_rate": 3.691588785046729e-05,
|
269 |
+
"loss": 0.1358,
|
270 |
+
"step": 240
|
271 |
+
},
|
272 |
+
{
|
273 |
+
"epoch": 13.97,
|
274 |
+
"eval_accuracy": 0.8572895277207392,
|
275 |
+
"eval_loss": 0.7063936591148376,
|
276 |
+
"eval_runtime": 8.8917,
|
277 |
+
"eval_samples_per_second": 109.54,
|
278 |
+
"eval_steps_per_second": 0.9,
|
279 |
+
"step": 241
|
280 |
+
},
|
281 |
+
{
|
282 |
+
"epoch": 14.49,
|
283 |
+
"learning_rate": 3.6137071651090344e-05,
|
284 |
+
"loss": 0.1116,
|
285 |
+
"step": 250
|
286 |
+
},
|
287 |
+
{
|
288 |
+
"epoch": 14.96,
|
289 |
+
"eval_accuracy": 0.8655030800821355,
|
290 |
+
"eval_loss": 0.67196124792099,
|
291 |
+
"eval_runtime": 9.0077,
|
292 |
+
"eval_samples_per_second": 108.129,
|
293 |
+
"eval_steps_per_second": 0.888,
|
294 |
+
"step": 258
|
295 |
+
},
|
296 |
+
{
|
297 |
+
"epoch": 15.07,
|
298 |
+
"learning_rate": 3.5358255451713394e-05,
|
299 |
+
"loss": 0.0974,
|
300 |
+
"step": 260
|
301 |
+
},
|
302 |
+
{
|
303 |
+
"epoch": 15.65,
|
304 |
+
"learning_rate": 3.457943925233645e-05,
|
305 |
+
"loss": 0.0811,
|
306 |
+
"step": 270
|
307 |
+
},
|
308 |
+
{
|
309 |
+
"epoch": 16.0,
|
310 |
+
"eval_accuracy": 0.864476386036961,
|
311 |
+
"eval_loss": 0.6515084505081177,
|
312 |
+
"eval_runtime": 9.3868,
|
313 |
+
"eval_samples_per_second": 103.762,
|
314 |
+
"eval_steps_per_second": 0.852,
|
315 |
+
"step": 276
|
316 |
+
},
|
317 |
+
{
|
318 |
+
"epoch": 16.0,
|
319 |
+
"step": 276,
|
320 |
+
"total_flos": 1.087746145977493e+19,
|
321 |
+
"train_loss": 1.7795628476617993,
|
322 |
+
"train_runtime": 3092.1212,
|
323 |
+
"train_samples_per_second": 119.027,
|
324 |
+
"train_steps_per_second": 0.231
|
325 |
+
}
|
326 |
+
],
|
327 |
+
"logging_steps": 10,
|
328 |
+
"max_steps": 714,
|
329 |
+
"num_train_epochs": 42,
|
330 |
+
"save_steps": 500,
|
331 |
+
"total_flos": 1.087746145977493e+19,
|
332 |
+
"trial_name": null,
|
333 |
+
"trial_params": null
|
334 |
+
}
|