Upload folder using huggingface_hub
Browse files- checkpoint-21765/config.json +1 -1
- checkpoint-21765/model.safetensors +1 -1
- checkpoint-21765/optimizer.pt +1 -1
- checkpoint-21765/scheduler.pt +1 -1
- checkpoint-21765/trainer_state.json +155 -155
- checkpoint-21765/training_args.bin +1 -1
- config.json +1 -1
- model.safetensors +1 -1
- training_args.bin +1 -1
checkpoint-21765/config.json
CHANGED
@@ -1,5 +1,5 @@
|
|
1 |
{
|
2 |
-
"_name_or_path": "
|
3 |
"architectures": [
|
4 |
"ViTForImageClassification"
|
5 |
],
|
|
|
1 |
{
|
2 |
+
"_name_or_path": "dima806/car_brands_image_detection",
|
3 |
"architectures": [
|
4 |
"ViTForImageClassification"
|
5 |
],
|
checkpoint-21765/model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 344211388
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5cda4fcd3994c0f781b29c079ea9a736c6cef52f288246182579e7170492d6b3
|
3 |
size 344211388
|
checkpoint-21765/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 688543237
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4bd3c52086c11d2fd5002e0460518be110d2c4397c8c498ce688c71c949ae45d
|
3 |
size 688543237
|
checkpoint-21765/scheduler.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 627
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:564a7026b795995ce34d000ba43eb760ae94321f3fac37b894d99cba02b2a9c9
|
3 |
size 627
|
checkpoint-21765/trainer_state.json
CHANGED
@@ -1,5 +1,5 @@
|
|
1 |
{
|
2 |
-
"best_metric":
|
3 |
"best_model_checkpoint": "car_brands_image_detection/checkpoint-21765",
|
4 |
"epoch": 5.0,
|
5 |
"eval_steps": 500,
|
@@ -10,348 +10,348 @@
|
|
10 |
"log_history": [
|
11 |
{
|
12 |
"epoch": 0.11,
|
13 |
-
"grad_norm":
|
14 |
-
"learning_rate":
|
15 |
-
"loss":
|
16 |
"step": 500
|
17 |
},
|
18 |
{
|
19 |
"epoch": 0.23,
|
20 |
-
"grad_norm":
|
21 |
-
"learning_rate":
|
22 |
-
"loss":
|
23 |
"step": 1000
|
24 |
},
|
25 |
{
|
26 |
"epoch": 0.34,
|
27 |
-
"grad_norm":
|
28 |
-
"learning_rate":
|
29 |
-
"loss":
|
30 |
"step": 1500
|
31 |
},
|
32 |
{
|
33 |
"epoch": 0.46,
|
34 |
-
"grad_norm":
|
35 |
-
"learning_rate":
|
36 |
-
"loss":
|
37 |
"step": 2000
|
38 |
},
|
39 |
{
|
40 |
"epoch": 0.57,
|
41 |
-
"grad_norm":
|
42 |
-
"learning_rate":
|
43 |
-
"loss":
|
44 |
"step": 2500
|
45 |
},
|
46 |
{
|
47 |
"epoch": 0.69,
|
48 |
-
"grad_norm": 2.
|
49 |
-
"learning_rate":
|
50 |
-
"loss":
|
51 |
"step": 3000
|
52 |
},
|
53 |
{
|
54 |
"epoch": 0.8,
|
55 |
-
"grad_norm":
|
56 |
-
"learning_rate":
|
57 |
-
"loss":
|
58 |
"step": 3500
|
59 |
},
|
60 |
{
|
61 |
"epoch": 0.92,
|
62 |
-
"grad_norm":
|
63 |
-
"learning_rate":
|
64 |
-
"loss":
|
65 |
"step": 4000
|
66 |
},
|
67 |
{
|
68 |
"epoch": 1.0,
|
69 |
-
"eval_accuracy": 0.
|
70 |
-
"eval_loss":
|
71 |
-
"eval_runtime":
|
72 |
-
"eval_samples_per_second":
|
73 |
-
"eval_steps_per_second":
|
74 |
"step": 4353
|
75 |
},
|
76 |
{
|
77 |
"epoch": 1.03,
|
78 |
-
"grad_norm":
|
79 |
-
"learning_rate":
|
80 |
-
"loss":
|
81 |
"step": 4500
|
82 |
},
|
83 |
{
|
84 |
"epoch": 1.15,
|
85 |
-
"grad_norm":
|
86 |
-
"learning_rate":
|
87 |
-
"loss":
|
88 |
"step": 5000
|
89 |
},
|
90 |
{
|
91 |
"epoch": 1.26,
|
92 |
-
"grad_norm":
|
93 |
-
"learning_rate":
|
94 |
-
"loss":
|
95 |
"step": 5500
|
96 |
},
|
97 |
{
|
98 |
"epoch": 1.38,
|
99 |
-
"grad_norm":
|
100 |
-
"learning_rate":
|
101 |
-
"loss":
|
102 |
"step": 6000
|
103 |
},
|
104 |
{
|
105 |
"epoch": 1.49,
|
106 |
-
"grad_norm":
|
107 |
-
"learning_rate":
|
108 |
-
"loss":
|
109 |
"step": 6500
|
110 |
},
|
111 |
{
|
112 |
"epoch": 1.61,
|
113 |
-
"grad_norm":
|
114 |
-
"learning_rate":
|
115 |
-
"loss":
|
116 |
"step": 7000
|
117 |
},
|
118 |
{
|
119 |
"epoch": 1.72,
|
120 |
-
"grad_norm":
|
121 |
-
"learning_rate":
|
122 |
-
"loss":
|
123 |
"step": 7500
|
124 |
},
|
125 |
{
|
126 |
"epoch": 1.84,
|
127 |
-
"grad_norm":
|
128 |
-
"learning_rate":
|
129 |
-
"loss":
|
130 |
"step": 8000
|
131 |
},
|
132 |
{
|
133 |
"epoch": 1.95,
|
134 |
-
"grad_norm":
|
135 |
-
"learning_rate":
|
136 |
-
"loss":
|
137 |
"step": 8500
|
138 |
},
|
139 |
{
|
140 |
"epoch": 2.0,
|
141 |
-
"eval_accuracy": 0.
|
142 |
-
"eval_loss":
|
143 |
-
"eval_runtime":
|
144 |
-
"eval_samples_per_second":
|
145 |
-
"eval_steps_per_second": 11.
|
146 |
"step": 8706
|
147 |
},
|
148 |
{
|
149 |
"epoch": 2.07,
|
150 |
-
"grad_norm":
|
151 |
-
"learning_rate":
|
152 |
-
"loss":
|
153 |
"step": 9000
|
154 |
},
|
155 |
{
|
156 |
"epoch": 2.18,
|
157 |
-
"grad_norm":
|
158 |
-
"learning_rate":
|
159 |
-
"loss":
|
160 |
"step": 9500
|
161 |
},
|
162 |
{
|
163 |
"epoch": 2.3,
|
164 |
-
"grad_norm":
|
165 |
-
"learning_rate":
|
166 |
-
"loss": 4.
|
167 |
"step": 10000
|
168 |
},
|
169 |
{
|
170 |
"epoch": 2.41,
|
171 |
-
"grad_norm":
|
172 |
-
"learning_rate":
|
173 |
-
"loss": 4.
|
174 |
"step": 10500
|
175 |
},
|
176 |
{
|
177 |
"epoch": 2.53,
|
178 |
-
"grad_norm":
|
179 |
-
"learning_rate":
|
180 |
-
"loss": 4.
|
181 |
"step": 11000
|
182 |
},
|
183 |
{
|
184 |
"epoch": 2.64,
|
185 |
-
"grad_norm":
|
186 |
-
"learning_rate":
|
187 |
-
"loss": 4.
|
188 |
"step": 11500
|
189 |
},
|
190 |
{
|
191 |
"epoch": 2.76,
|
192 |
-
"grad_norm":
|
193 |
-
"learning_rate":
|
194 |
-
"loss": 4.
|
195 |
"step": 12000
|
196 |
},
|
197 |
{
|
198 |
"epoch": 2.87,
|
199 |
-
"grad_norm":
|
200 |
-
"learning_rate":
|
201 |
-
"loss":
|
202 |
"step": 12500
|
203 |
},
|
204 |
{
|
205 |
"epoch": 2.99,
|
206 |
-
"grad_norm":
|
207 |
-
"learning_rate":
|
208 |
-
"loss":
|
209 |
"step": 13000
|
210 |
},
|
211 |
{
|
212 |
"epoch": 3.0,
|
213 |
-
"eval_accuracy": 0.
|
214 |
-
"eval_loss": 4.
|
215 |
-
"eval_runtime":
|
216 |
-
"eval_samples_per_second": 90.
|
217 |
-
"eval_steps_per_second": 11.
|
218 |
"step": 13059
|
219 |
},
|
220 |
{
|
221 |
"epoch": 3.1,
|
222 |
-
"grad_norm":
|
223 |
-
"learning_rate": 1.
|
224 |
-
"loss":
|
225 |
"step": 13500
|
226 |
},
|
227 |
{
|
228 |
"epoch": 3.22,
|
229 |
-
"grad_norm":
|
230 |
-
"learning_rate": 1.
|
231 |
-
"loss":
|
232 |
"step": 14000
|
233 |
},
|
234 |
{
|
235 |
"epoch": 3.33,
|
236 |
-
"grad_norm":
|
237 |
-
"learning_rate": 1.
|
238 |
-
"loss":
|
239 |
"step": 14500
|
240 |
},
|
241 |
{
|
242 |
"epoch": 3.45,
|
243 |
-
"grad_norm":
|
244 |
-
"learning_rate":
|
245 |
-
"loss":
|
246 |
"step": 15000
|
247 |
},
|
248 |
{
|
249 |
"epoch": 3.56,
|
250 |
-
"grad_norm":
|
251 |
-
"learning_rate":
|
252 |
-
"loss":
|
253 |
"step": 15500
|
254 |
},
|
255 |
{
|
256 |
"epoch": 3.68,
|
257 |
-
"grad_norm":
|
258 |
-
"learning_rate":
|
259 |
-
"loss":
|
260 |
"step": 16000
|
261 |
},
|
262 |
{
|
263 |
"epoch": 3.79,
|
264 |
-
"grad_norm":
|
265 |
-
"learning_rate":
|
266 |
-
"loss":
|
267 |
"step": 16500
|
268 |
},
|
269 |
{
|
270 |
"epoch": 3.91,
|
271 |
-
"grad_norm":
|
272 |
-
"learning_rate":
|
273 |
-
"loss":
|
274 |
"step": 17000
|
275 |
},
|
276 |
{
|
277 |
"epoch": 4.0,
|
278 |
-
"eval_accuracy": 0.
|
279 |
-
"eval_loss":
|
280 |
-
"eval_runtime":
|
281 |
-
"eval_samples_per_second":
|
282 |
-
"eval_steps_per_second": 11.
|
283 |
"step": 17412
|
284 |
},
|
285 |
{
|
286 |
"epoch": 4.02,
|
287 |
-
"grad_norm":
|
288 |
-
"learning_rate":
|
289 |
-
"loss":
|
290 |
"step": 17500
|
291 |
},
|
292 |
{
|
293 |
"epoch": 4.14,
|
294 |
-
"grad_norm":
|
295 |
-
"learning_rate":
|
296 |
-
"loss":
|
297 |
"step": 18000
|
298 |
},
|
299 |
{
|
300 |
"epoch": 4.25,
|
301 |
-
"grad_norm":
|
302 |
-
"learning_rate":
|
303 |
-
"loss":
|
304 |
"step": 18500
|
305 |
},
|
306 |
{
|
307 |
"epoch": 4.36,
|
308 |
-
"grad_norm":
|
309 |
-
"learning_rate":
|
310 |
-
"loss":
|
311 |
"step": 19000
|
312 |
},
|
313 |
{
|
314 |
"epoch": 4.48,
|
315 |
-
"grad_norm": 3.
|
316 |
-
"learning_rate":
|
317 |
-
"loss":
|
318 |
"step": 19500
|
319 |
},
|
320 |
{
|
321 |
"epoch": 4.59,
|
322 |
-
"grad_norm":
|
323 |
-
"learning_rate":
|
324 |
-
"loss":
|
325 |
"step": 20000
|
326 |
},
|
327 |
{
|
328 |
"epoch": 4.71,
|
329 |
-
"grad_norm":
|
330 |
-
"learning_rate":
|
331 |
-
"loss":
|
332 |
"step": 20500
|
333 |
},
|
334 |
{
|
335 |
"epoch": 4.82,
|
336 |
-
"grad_norm": 3.
|
337 |
-
"learning_rate": 1.
|
338 |
-
"loss":
|
339 |
"step": 21000
|
340 |
},
|
341 |
{
|
342 |
"epoch": 4.94,
|
343 |
-
"grad_norm":
|
344 |
-
"learning_rate":
|
345 |
-
"loss":
|
346 |
"step": 21500
|
347 |
},
|
348 |
{
|
349 |
"epoch": 5.0,
|
350 |
-
"eval_accuracy": 0.
|
351 |
-
"eval_loss":
|
352 |
-
"eval_runtime":
|
353 |
-
"eval_samples_per_second":
|
354 |
-
"eval_steps_per_second":
|
355 |
"step": 21765
|
356 |
}
|
357 |
],
|
|
|
1 |
{
|
2 |
+
"best_metric": 3.9286768436431885,
|
3 |
"best_model_checkpoint": "car_brands_image_detection/checkpoint-21765",
|
4 |
"epoch": 5.0,
|
5 |
"eval_steps": 500,
|
|
|
10 |
"log_history": [
|
11 |
{
|
12 |
"epoch": 0.11,
|
13 |
+
"grad_norm": 3.6166505813598633,
|
14 |
+
"learning_rate": 2.937830992401566e-06,
|
15 |
+
"loss": 4.5799,
|
16 |
"step": 500
|
17 |
},
|
18 |
{
|
19 |
"epoch": 0.23,
|
20 |
+
"grad_norm": 2.645850419998169,
|
21 |
+
"learning_rate": 2.8687543172921943e-06,
|
22 |
+
"loss": 4.5716,
|
23 |
"step": 1000
|
24 |
},
|
25 |
{
|
26 |
"epoch": 0.34,
|
27 |
+
"grad_norm": 2.978064775466919,
|
28 |
+
"learning_rate": 2.799677642182823e-06,
|
29 |
+
"loss": 4.5286,
|
30 |
"step": 1500
|
31 |
},
|
32 |
{
|
33 |
"epoch": 0.46,
|
34 |
+
"grad_norm": 2.759573459625244,
|
35 |
+
"learning_rate": 2.7306009670734517e-06,
|
36 |
+
"loss": 4.4846,
|
37 |
"step": 2000
|
38 |
},
|
39 |
{
|
40 |
"epoch": 0.57,
|
41 |
+
"grad_norm": 2.4581897258758545,
|
42 |
+
"learning_rate": 2.66152429196408e-06,
|
43 |
+
"loss": 4.4705,
|
44 |
"step": 2500
|
45 |
},
|
46 |
{
|
47 |
"epoch": 0.69,
|
48 |
+
"grad_norm": 2.911447286605835,
|
49 |
+
"learning_rate": 2.592447616854709e-06,
|
50 |
+
"loss": 4.4394,
|
51 |
"step": 3000
|
52 |
},
|
53 |
{
|
54 |
"epoch": 0.8,
|
55 |
+
"grad_norm": 3.8367297649383545,
|
56 |
+
"learning_rate": 2.5233709417453375e-06,
|
57 |
+
"loss": 4.41,
|
58 |
"step": 3500
|
59 |
},
|
60 |
{
|
61 |
"epoch": 0.92,
|
62 |
+
"grad_norm": 2.930182456970215,
|
63 |
+
"learning_rate": 2.454294266635966e-06,
|
64 |
+
"loss": 4.385,
|
65 |
"step": 4000
|
66 |
},
|
67 |
{
|
68 |
"epoch": 1.0,
|
69 |
+
"eval_accuracy": 0.40094773118897187,
|
70 |
+
"eval_loss": 4.410472869873047,
|
71 |
+
"eval_runtime": 357.321,
|
72 |
+
"eval_samples_per_second": 97.447,
|
73 |
+
"eval_steps_per_second": 12.182,
|
74 |
"step": 4353
|
75 |
},
|
76 |
{
|
77 |
"epoch": 1.03,
|
78 |
+
"grad_norm": 3.3039791584014893,
|
79 |
+
"learning_rate": 2.3852175915265945e-06,
|
80 |
+
"loss": 4.3545,
|
81 |
"step": 4500
|
82 |
},
|
83 |
{
|
84 |
"epoch": 1.15,
|
85 |
+
"grad_norm": 3.3890039920806885,
|
86 |
+
"learning_rate": 2.316140916417223e-06,
|
87 |
+
"loss": 4.3126,
|
88 |
"step": 5000
|
89 |
},
|
90 |
{
|
91 |
"epoch": 1.26,
|
92 |
+
"grad_norm": 4.098603248596191,
|
93 |
+
"learning_rate": 2.247064241307852e-06,
|
94 |
+
"loss": 4.2967,
|
95 |
"step": 5500
|
96 |
},
|
97 |
{
|
98 |
"epoch": 1.38,
|
99 |
+
"grad_norm": 3.3784146308898926,
|
100 |
+
"learning_rate": 2.1779875661984803e-06,
|
101 |
+
"loss": 4.2693,
|
102 |
"step": 6000
|
103 |
},
|
104 |
{
|
105 |
"epoch": 1.49,
|
106 |
+
"grad_norm": 3.1738123893737793,
|
107 |
+
"learning_rate": 2.1089108910891088e-06,
|
108 |
+
"loss": 4.2466,
|
109 |
"step": 6500
|
110 |
},
|
111 |
{
|
112 |
"epoch": 1.61,
|
113 |
+
"grad_norm": 3.7148706912994385,
|
114 |
+
"learning_rate": 2.0398342159797372e-06,
|
115 |
+
"loss": 4.2021,
|
116 |
"step": 7000
|
117 |
},
|
118 |
{
|
119 |
"epoch": 1.72,
|
120 |
+
"grad_norm": 3.290153741836548,
|
121 |
+
"learning_rate": 1.970757540870366e-06,
|
122 |
+
"loss": 4.1814,
|
123 |
"step": 7500
|
124 |
},
|
125 |
{
|
126 |
"epoch": 1.84,
|
127 |
+
"grad_norm": 3.142911672592163,
|
128 |
+
"learning_rate": 1.9016808657609948e-06,
|
129 |
+
"loss": 4.1626,
|
130 |
"step": 8000
|
131 |
},
|
132 |
{
|
133 |
"epoch": 1.95,
|
134 |
+
"grad_norm": 4.143848896026611,
|
135 |
+
"learning_rate": 1.8326041906516235e-06,
|
136 |
+
"loss": 4.1376,
|
137 |
"step": 8500
|
138 |
},
|
139 |
{
|
140 |
"epoch": 2.0,
|
141 |
+
"eval_accuracy": 0.43512349224583574,
|
142 |
+
"eval_loss": 4.2049126625061035,
|
143 |
+
"eval_runtime": 371.7808,
|
144 |
+
"eval_samples_per_second": 93.657,
|
145 |
+
"eval_steps_per_second": 11.709,
|
146 |
"step": 8706
|
147 |
},
|
148 |
{
|
149 |
"epoch": 2.07,
|
150 |
+
"grad_norm": 3.016541004180908,
|
151 |
+
"learning_rate": 1.763527515542252e-06,
|
152 |
+
"loss": 4.1126,
|
153 |
"step": 9000
|
154 |
},
|
155 |
{
|
156 |
"epoch": 2.18,
|
157 |
+
"grad_norm": 3.141395092010498,
|
158 |
+
"learning_rate": 1.6944508404328806e-06,
|
159 |
+
"loss": 4.0881,
|
160 |
"step": 9500
|
161 |
},
|
162 |
{
|
163 |
"epoch": 2.3,
|
164 |
+
"grad_norm": 4.218649864196777,
|
165 |
+
"learning_rate": 1.6253741653235091e-06,
|
166 |
+
"loss": 4.0854,
|
167 |
"step": 10000
|
168 |
},
|
169 |
{
|
170 |
"epoch": 2.41,
|
171 |
+
"grad_norm": 3.368730306625366,
|
172 |
+
"learning_rate": 1.5562974902141378e-06,
|
173 |
+
"loss": 4.0432,
|
174 |
"step": 10500
|
175 |
},
|
176 |
{
|
177 |
"epoch": 2.53,
|
178 |
+
"grad_norm": 3.461085557937622,
|
179 |
+
"learning_rate": 1.4872208151047663e-06,
|
180 |
+
"loss": 4.0324,
|
181 |
"step": 11000
|
182 |
},
|
183 |
{
|
184 |
"epoch": 2.64,
|
185 |
+
"grad_norm": 3.5780344009399414,
|
186 |
+
"learning_rate": 1.418144139995395e-06,
|
187 |
+
"loss": 4.0083,
|
188 |
"step": 11500
|
189 |
},
|
190 |
{
|
191 |
"epoch": 2.76,
|
192 |
+
"grad_norm": 3.727916955947876,
|
193 |
+
"learning_rate": 1.3490674648860236e-06,
|
194 |
+
"loss": 4.0215,
|
195 |
"step": 12000
|
196 |
},
|
197 |
{
|
198 |
"epoch": 2.87,
|
199 |
+
"grad_norm": 3.84293532371521,
|
200 |
+
"learning_rate": 1.279990789776652e-06,
|
201 |
+
"loss": 3.9905,
|
202 |
"step": 12500
|
203 |
},
|
204 |
{
|
205 |
"epoch": 2.99,
|
206 |
+
"grad_norm": 4.721088409423828,
|
207 |
+
"learning_rate": 1.2109141146672808e-06,
|
208 |
+
"loss": 3.9723,
|
209 |
"step": 13000
|
210 |
},
|
211 |
{
|
212 |
"epoch": 3.0,
|
213 |
+
"eval_accuracy": 0.4607696726019529,
|
214 |
+
"eval_loss": 4.052371025085449,
|
215 |
+
"eval_runtime": 385.9466,
|
216 |
+
"eval_samples_per_second": 90.22,
|
217 |
+
"eval_steps_per_second": 11.279,
|
218 |
"step": 13059
|
219 |
},
|
220 |
{
|
221 |
"epoch": 3.1,
|
222 |
+
"grad_norm": 4.341360092163086,
|
223 |
+
"learning_rate": 1.1418374395579092e-06,
|
224 |
+
"loss": 3.9604,
|
225 |
"step": 13500
|
226 |
},
|
227 |
{
|
228 |
"epoch": 3.22,
|
229 |
+
"grad_norm": 4.207143306732178,
|
230 |
+
"learning_rate": 1.0727607644485377e-06,
|
231 |
+
"loss": 3.9293,
|
232 |
"step": 14000
|
233 |
},
|
234 |
{
|
235 |
"epoch": 3.33,
|
236 |
+
"grad_norm": 4.3804850578308105,
|
237 |
+
"learning_rate": 1.0036840893391666e-06,
|
238 |
+
"loss": 3.9193,
|
239 |
"step": 14500
|
240 |
},
|
241 |
{
|
242 |
"epoch": 3.45,
|
243 |
+
"grad_norm": 3.7782533168792725,
|
244 |
+
"learning_rate": 9.346074142297951e-07,
|
245 |
+
"loss": 3.9125,
|
246 |
"step": 15000
|
247 |
},
|
248 |
{
|
249 |
"epoch": 3.56,
|
250 |
+
"grad_norm": 3.5943124294281006,
|
251 |
+
"learning_rate": 8.655307391204237e-07,
|
252 |
+
"loss": 3.8896,
|
253 |
"step": 15500
|
254 |
},
|
255 |
{
|
256 |
"epoch": 3.68,
|
257 |
+
"grad_norm": 3.702357053756714,
|
258 |
+
"learning_rate": 7.964540640110522e-07,
|
259 |
+
"loss": 3.9014,
|
260 |
"step": 16000
|
261 |
},
|
262 |
{
|
263 |
"epoch": 3.79,
|
264 |
+
"grad_norm": 3.796862840652466,
|
265 |
+
"learning_rate": 7.273773889016809e-07,
|
266 |
+
"loss": 3.891,
|
267 |
"step": 16500
|
268 |
},
|
269 |
{
|
270 |
"epoch": 3.91,
|
271 |
+
"grad_norm": 4.275099277496338,
|
272 |
+
"learning_rate": 6.583007137923095e-07,
|
273 |
+
"loss": 3.8704,
|
274 |
"step": 17000
|
275 |
},
|
276 |
{
|
277 |
"epoch": 4.0,
|
278 |
+
"eval_accuracy": 0.4705054566341183,
|
279 |
+
"eval_loss": 3.9602584838867188,
|
280 |
+
"eval_runtime": 391.9958,
|
281 |
+
"eval_samples_per_second": 88.827,
|
282 |
+
"eval_steps_per_second": 11.105,
|
283 |
"step": 17412
|
284 |
},
|
285 |
{
|
286 |
"epoch": 4.02,
|
287 |
+
"grad_norm": 3.892676591873169,
|
288 |
+
"learning_rate": 5.892240386829381e-07,
|
289 |
+
"loss": 3.8528,
|
290 |
"step": 17500
|
291 |
},
|
292 |
{
|
293 |
"epoch": 4.14,
|
294 |
+
"grad_norm": 3.8556807041168213,
|
295 |
+
"learning_rate": 5.201473635735666e-07,
|
296 |
+
"loss": 3.8603,
|
297 |
"step": 18000
|
298 |
},
|
299 |
{
|
300 |
"epoch": 4.25,
|
301 |
+
"grad_norm": 4.647615909576416,
|
302 |
+
"learning_rate": 4.5107068846419527e-07,
|
303 |
+
"loss": 3.8373,
|
304 |
"step": 18500
|
305 |
},
|
306 |
{
|
307 |
"epoch": 4.36,
|
308 |
+
"grad_norm": 5.085917949676514,
|
309 |
+
"learning_rate": 3.819940133548239e-07,
|
310 |
+
"loss": 3.8558,
|
311 |
"step": 19000
|
312 |
},
|
313 |
{
|
314 |
"epoch": 4.48,
|
315 |
+
"grad_norm": 3.4918742179870605,
|
316 |
+
"learning_rate": 3.1291733824545247e-07,
|
317 |
+
"loss": 3.8305,
|
318 |
"step": 19500
|
319 |
},
|
320 |
{
|
321 |
"epoch": 4.59,
|
322 |
+
"grad_norm": 5.628491401672363,
|
323 |
+
"learning_rate": 2.4384066313608105e-07,
|
324 |
+
"loss": 3.8442,
|
325 |
"step": 20000
|
326 |
},
|
327 |
{
|
328 |
"epoch": 4.71,
|
329 |
+
"grad_norm": 6.177685737609863,
|
330 |
+
"learning_rate": 1.7476398802670965e-07,
|
331 |
+
"loss": 3.821,
|
332 |
"step": 20500
|
333 |
},
|
334 |
{
|
335 |
"epoch": 4.82,
|
336 |
+
"grad_norm": 3.602433681488037,
|
337 |
+
"learning_rate": 1.0568731291733824e-07,
|
338 |
+
"loss": 3.8144,
|
339 |
"step": 21000
|
340 |
},
|
341 |
{
|
342 |
"epoch": 4.94,
|
343 |
+
"grad_norm": 3.561356782913208,
|
344 |
+
"learning_rate": 3.6610637807966844e-08,
|
345 |
+
"loss": 3.8221,
|
346 |
"step": 21500
|
347 |
},
|
348 |
{
|
349 |
"epoch": 5.0,
|
350 |
+
"eval_accuracy": 0.4763928776565192,
|
351 |
+
"eval_loss": 3.9286768436431885,
|
352 |
+
"eval_runtime": 356.658,
|
353 |
+
"eval_samples_per_second": 97.629,
|
354 |
+
"eval_steps_per_second": 12.205,
|
355 |
"step": 21765
|
356 |
}
|
357 |
],
|
checkpoint-21765/training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4411
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5f7d6ebaabd45a62aff4f53a34471baa85aa1bc1190c00a62cccf0cf6bcbae76
|
3 |
size 4411
|
config.json
CHANGED
@@ -1,5 +1,5 @@
|
|
1 |
{
|
2 |
-
"_name_or_path": "
|
3 |
"architectures": [
|
4 |
"ViTForImageClassification"
|
5 |
],
|
|
|
1 |
{
|
2 |
+
"_name_or_path": "dima806/car_brands_image_detection",
|
3 |
"architectures": [
|
4 |
"ViTForImageClassification"
|
5 |
],
|
model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 344211388
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5cda4fcd3994c0f781b29c079ea9a736c6cef52f288246182579e7170492d6b3
|
3 |
size 344211388
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4411
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5f7d6ebaabd45a62aff4f53a34471baa85aa1bc1190c00a62cccf0cf6bcbae76
|
3 |
size 4411
|