End of training
Browse files- all_results.json +11 -11
- eval_results.json +6 -6
- runs/Mar29_05-51-50_01165a1d2f58/events.out.tfevents.1711692701.01165a1d2f58.7243.1 +3 -0
- train_results.json +6 -6
- trainer_state.json +123 -294
all_results.json
CHANGED
@@ -1,13 +1,13 @@
|
|
1 |
{
|
2 |
-
"epoch":
|
3 |
-
"eval_accuracy": 0.
|
4 |
-
"eval_loss": 0.
|
5 |
-
"eval_runtime":
|
6 |
-
"eval_samples_per_second":
|
7 |
-
"eval_steps_per_second": 4.
|
8 |
-
"total_flos":
|
9 |
-
"train_loss": 0.
|
10 |
-
"train_runtime":
|
11 |
-
"train_samples_per_second":
|
12 |
-
"train_steps_per_second": 0.
|
13 |
}
|
|
|
1 |
{
|
2 |
+
"epoch": 2.98,
|
3 |
+
"eval_accuracy": 0.9358974358974359,
|
4 |
+
"eval_loss": 0.17716573178768158,
|
5 |
+
"eval_runtime": 9.4517,
|
6 |
+
"eval_samples_per_second": 148.545,
|
7 |
+
"eval_steps_per_second": 4.655,
|
8 |
+
"total_flos": 9.625811808320225e+17,
|
9 |
+
"train_loss": 0.22732183539948494,
|
10 |
+
"train_runtime": 623.8374,
|
11 |
+
"train_samples_per_second": 60.737,
|
12 |
+
"train_steps_per_second": 0.471
|
13 |
}
|
eval_results.json
CHANGED
@@ -1,8 +1,8 @@
|
|
1 |
{
|
2 |
-
"epoch":
|
3 |
-
"eval_accuracy": 0.
|
4 |
-
"eval_loss": 0.
|
5 |
-
"eval_runtime":
|
6 |
-
"eval_samples_per_second":
|
7 |
-
"eval_steps_per_second": 4.
|
8 |
}
|
|
|
1 |
{
|
2 |
+
"epoch": 2.98,
|
3 |
+
"eval_accuracy": 0.9358974358974359,
|
4 |
+
"eval_loss": 0.17716573178768158,
|
5 |
+
"eval_runtime": 9.4517,
|
6 |
+
"eval_samples_per_second": 148.545,
|
7 |
+
"eval_steps_per_second": 4.655
|
8 |
}
|
runs/Mar29_05-51-50_01165a1d2f58/events.out.tfevents.1711692701.01165a1d2f58.7243.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:580dead3d1a166c4a86a2a3ccc6e213927b25746a4f91d48a52423ea572b09ec
|
3 |
+
size 411
|
train_results.json
CHANGED
@@ -1,8 +1,8 @@
|
|
1 |
{
|
2 |
-
"epoch":
|
3 |
-
"total_flos":
|
4 |
-
"train_loss": 0.
|
5 |
-
"train_runtime":
|
6 |
-
"train_samples_per_second":
|
7 |
-
"train_steps_per_second": 0.
|
8 |
}
|
|
|
1 |
{
|
2 |
+
"epoch": 2.98,
|
3 |
+
"total_flos": 9.625811808320225e+17,
|
4 |
+
"train_loss": 0.22732183539948494,
|
5 |
+
"train_runtime": 623.8374,
|
6 |
+
"train_samples_per_second": 60.737,
|
7 |
+
"train_steps_per_second": 0.471
|
8 |
}
|
trainer_state.json
CHANGED
@@ -1,397 +1,226 @@
|
|
1 |
{
|
2 |
-
"best_metric": 0.
|
3 |
-
"best_model_checkpoint": "swin-tiny-patch4-window7-224-finetuned-eurosat/checkpoint-
|
4 |
-
"epoch":
|
5 |
-
"
|
6 |
-
"global_step": 570,
|
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.
|
13 |
-
"learning_rate":
|
14 |
-
"loss":
|
15 |
"step": 10
|
16 |
},
|
17 |
{
|
18 |
-
"epoch": 0.
|
19 |
-
"learning_rate":
|
20 |
-
"loss":
|
21 |
"step": 20
|
22 |
},
|
23 |
{
|
24 |
-
"epoch": 0.
|
25 |
-
"learning_rate":
|
26 |
-
"loss":
|
27 |
"step": 30
|
28 |
},
|
29 |
{
|
30 |
-
"epoch": 0.
|
31 |
-
"learning_rate":
|
32 |
-
"loss": 0.
|
33 |
"step": 40
|
34 |
},
|
35 |
{
|
36 |
-
"epoch": 0.
|
37 |
-
"learning_rate":
|
38 |
-
"loss": 0.
|
39 |
"step": 50
|
40 |
},
|
41 |
{
|
42 |
-
"epoch": 0.
|
43 |
-
"learning_rate":
|
44 |
-
"loss": 0.
|
45 |
"step": 60
|
46 |
},
|
47 |
{
|
48 |
-
"epoch": 0.
|
49 |
-
"learning_rate":
|
50 |
-
"loss": 0.
|
51 |
"step": 70
|
52 |
},
|
53 |
{
|
54 |
-
"epoch": 0.
|
55 |
-
"learning_rate":
|
56 |
-
"loss": 0.
|
57 |
"step": 80
|
58 |
},
|
59 |
{
|
60 |
-
"epoch": 0.
|
61 |
-
"learning_rate":
|
62 |
-
"loss": 0.
|
63 |
"step": 90
|
64 |
},
|
65 |
{
|
66 |
-
"epoch": 0.
|
67 |
-
"
|
68 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
69 |
"step": 100
|
70 |
},
|
71 |
{
|
72 |
-
"epoch":
|
73 |
-
"learning_rate":
|
74 |
-
"loss": 0.
|
75 |
"step": 110
|
76 |
},
|
77 |
{
|
78 |
-
"epoch":
|
79 |
-
"learning_rate":
|
80 |
-
"loss": 0.
|
81 |
"step": 120
|
82 |
},
|
83 |
{
|
84 |
-
"epoch":
|
85 |
-
"learning_rate":
|
86 |
-
"loss": 0.
|
87 |
"step": 130
|
88 |
},
|
89 |
{
|
90 |
-
"epoch":
|
91 |
-
"learning_rate":
|
92 |
-
"loss": 0.
|
93 |
"step": 140
|
94 |
},
|
95 |
{
|
96 |
-
"epoch":
|
97 |
-
"learning_rate":
|
98 |
-
"loss": 0.
|
99 |
"step": 150
|
100 |
},
|
101 |
{
|
102 |
-
"epoch":
|
103 |
-
"learning_rate":
|
104 |
-
"loss": 0.
|
105 |
"step": 160
|
106 |
},
|
107 |
{
|
108 |
-
"epoch":
|
109 |
-
"learning_rate":
|
110 |
-
"loss": 0.
|
111 |
"step": 170
|
112 |
},
|
113 |
{
|
114 |
-
"epoch":
|
115 |
-
"learning_rate": 3.
|
116 |
-
"loss": 0.
|
117 |
"step": 180
|
118 |
},
|
119 |
{
|
120 |
-
"epoch": 1.
|
121 |
-
"learning_rate":
|
122 |
-
"loss": 0.
|
123 |
"step": 190
|
124 |
},
|
125 |
{
|
126 |
-
"epoch": 1.
|
127 |
-
"eval_accuracy": 0.
|
128 |
-
"eval_loss": 0.
|
129 |
-
"eval_runtime":
|
130 |
-
"eval_samples_per_second":
|
131 |
-
"eval_steps_per_second": 4.
|
132 |
-
"step":
|
133 |
},
|
134 |
{
|
135 |
-
"epoch":
|
136 |
-
"learning_rate":
|
137 |
-
"loss": 0.
|
138 |
"step": 200
|
139 |
},
|
140 |
{
|
141 |
-
"epoch":
|
142 |
-
"learning_rate":
|
143 |
-
"loss": 0.
|
144 |
"step": 210
|
145 |
},
|
146 |
{
|
147 |
-
"epoch":
|
148 |
-
"learning_rate":
|
149 |
-
"loss": 0.
|
150 |
"step": 220
|
151 |
},
|
152 |
{
|
153 |
-
"epoch":
|
154 |
-
"learning_rate":
|
155 |
-
"loss": 0.
|
156 |
"step": 230
|
157 |
},
|
158 |
{
|
159 |
-
"epoch":
|
160 |
-
"learning_rate":
|
161 |
-
"loss": 0.
|
162 |
"step": 240
|
163 |
},
|
164 |
{
|
165 |
-
"epoch":
|
166 |
-
"learning_rate":
|
167 |
-
"loss": 0.
|
168 |
"step": 250
|
169 |
},
|
170 |
{
|
171 |
-
"epoch":
|
172 |
-
"learning_rate":
|
173 |
-
"loss": 0.
|
174 |
"step": 260
|
175 |
},
|
176 |
{
|
177 |
-
"epoch":
|
178 |
-
"learning_rate":
|
179 |
-
"loss": 0.
|
180 |
"step": 270
|
181 |
},
|
182 |
{
|
183 |
-
"epoch":
|
184 |
-
"learning_rate":
|
185 |
-
"loss": 0.
|
186 |
"step": 280
|
187 |
},
|
188 |
{
|
189 |
-
"epoch":
|
190 |
-
"learning_rate":
|
191 |
-
"loss": 0.
|
192 |
"step": 290
|
193 |
},
|
194 |
{
|
195 |
-
"epoch":
|
196 |
-
"
|
197 |
-
"
|
198 |
-
"
|
199 |
-
|
200 |
-
|
201 |
-
"
|
202 |
-
"learning_rate": 2.53411306042885e-05,
|
203 |
-
"loss": 0.1762,
|
204 |
-
"step": 310
|
205 |
-
},
|
206 |
-
{
|
207 |
-
"epoch": 1.68,
|
208 |
-
"learning_rate": 2.4366471734892787e-05,
|
209 |
-
"loss": 0.1482,
|
210 |
-
"step": 320
|
211 |
-
},
|
212 |
-
{
|
213 |
-
"epoch": 1.74,
|
214 |
-
"learning_rate": 2.3391812865497074e-05,
|
215 |
-
"loss": 0.1565,
|
216 |
-
"step": 330
|
217 |
-
},
|
218 |
-
{
|
219 |
-
"epoch": 1.79,
|
220 |
-
"learning_rate": 2.2417153996101365e-05,
|
221 |
-
"loss": 0.1722,
|
222 |
-
"step": 340
|
223 |
-
},
|
224 |
-
{
|
225 |
-
"epoch": 1.84,
|
226 |
-
"learning_rate": 2.1442495126705653e-05,
|
227 |
-
"loss": 0.1737,
|
228 |
-
"step": 350
|
229 |
-
},
|
230 |
-
{
|
231 |
-
"epoch": 1.89,
|
232 |
-
"learning_rate": 2.046783625730994e-05,
|
233 |
-
"loss": 0.1442,
|
234 |
-
"step": 360
|
235 |
-
},
|
236 |
-
{
|
237 |
-
"epoch": 1.95,
|
238 |
-
"learning_rate": 1.949317738791423e-05,
|
239 |
-
"loss": 0.1678,
|
240 |
-
"step": 370
|
241 |
-
},
|
242 |
-
{
|
243 |
-
"epoch": 2.0,
|
244 |
-
"learning_rate": 1.8518518518518518e-05,
|
245 |
-
"loss": 0.1616,
|
246 |
-
"step": 380
|
247 |
-
},
|
248 |
-
{
|
249 |
-
"epoch": 2.0,
|
250 |
-
"eval_accuracy": 0.9740740740740741,
|
251 |
-
"eval_loss": 0.0751405879855156,
|
252 |
-
"eval_runtime": 16.9062,
|
253 |
-
"eval_samples_per_second": 159.704,
|
254 |
-
"eval_steps_per_second": 5.028,
|
255 |
-
"step": 380
|
256 |
},
|
257 |
{
|
258 |
-
"epoch": 2.
|
259 |
-
"
|
260 |
-
"
|
261 |
-
"
|
262 |
-
|
263 |
-
|
264 |
-
"
|
265 |
-
"learning_rate": 1.6569200779727097e-05,
|
266 |
-
"loss": 0.1432,
|
267 |
-
"step": 400
|
268 |
-
},
|
269 |
-
{
|
270 |
-
"epoch": 2.16,
|
271 |
-
"learning_rate": 1.5594541910331384e-05,
|
272 |
-
"loss": 0.1707,
|
273 |
-
"step": 410
|
274 |
-
},
|
275 |
-
{
|
276 |
-
"epoch": 2.21,
|
277 |
-
"learning_rate": 1.4619883040935673e-05,
|
278 |
-
"loss": 0.1698,
|
279 |
-
"step": 420
|
280 |
-
},
|
281 |
-
{
|
282 |
-
"epoch": 2.26,
|
283 |
-
"learning_rate": 1.364522417153996e-05,
|
284 |
-
"loss": 0.1359,
|
285 |
-
"step": 430
|
286 |
-
},
|
287 |
-
{
|
288 |
-
"epoch": 2.32,
|
289 |
-
"learning_rate": 1.267056530214425e-05,
|
290 |
-
"loss": 0.177,
|
291 |
-
"step": 440
|
292 |
-
},
|
293 |
-
{
|
294 |
-
"epoch": 2.37,
|
295 |
-
"learning_rate": 1.1695906432748537e-05,
|
296 |
-
"loss": 0.1201,
|
297 |
-
"step": 450
|
298 |
-
},
|
299 |
-
{
|
300 |
-
"epoch": 2.42,
|
301 |
-
"learning_rate": 1.0721247563352826e-05,
|
302 |
-
"loss": 0.1487,
|
303 |
-
"step": 460
|
304 |
-
},
|
305 |
-
{
|
306 |
-
"epoch": 2.47,
|
307 |
-
"learning_rate": 9.746588693957115e-06,
|
308 |
-
"loss": 0.1459,
|
309 |
-
"step": 470
|
310 |
-
},
|
311 |
-
{
|
312 |
-
"epoch": 2.53,
|
313 |
-
"learning_rate": 8.771929824561403e-06,
|
314 |
-
"loss": 0.1591,
|
315 |
-
"step": 480
|
316 |
-
},
|
317 |
-
{
|
318 |
-
"epoch": 2.58,
|
319 |
-
"learning_rate": 7.797270955165692e-06,
|
320 |
-
"loss": 0.1647,
|
321 |
-
"step": 490
|
322 |
-
},
|
323 |
-
{
|
324 |
-
"epoch": 2.63,
|
325 |
-
"learning_rate": 6.82261208576998e-06,
|
326 |
-
"loss": 0.1611,
|
327 |
-
"step": 500
|
328 |
-
},
|
329 |
-
{
|
330 |
-
"epoch": 2.68,
|
331 |
-
"learning_rate": 5.8479532163742686e-06,
|
332 |
-
"loss": 0.1318,
|
333 |
-
"step": 510
|
334 |
-
},
|
335 |
-
{
|
336 |
-
"epoch": 2.74,
|
337 |
-
"learning_rate": 4.873294346978558e-06,
|
338 |
-
"loss": 0.1241,
|
339 |
-
"step": 520
|
340 |
-
},
|
341 |
-
{
|
342 |
-
"epoch": 2.79,
|
343 |
-
"learning_rate": 3.898635477582846e-06,
|
344 |
-
"loss": 0.152,
|
345 |
-
"step": 530
|
346 |
-
},
|
347 |
-
{
|
348 |
-
"epoch": 2.84,
|
349 |
-
"learning_rate": 2.9239766081871343e-06,
|
350 |
-
"loss": 0.1573,
|
351 |
-
"step": 540
|
352 |
-
},
|
353 |
-
{
|
354 |
-
"epoch": 2.89,
|
355 |
-
"learning_rate": 1.949317738791423e-06,
|
356 |
-
"loss": 0.1152,
|
357 |
-
"step": 550
|
358 |
-
},
|
359 |
-
{
|
360 |
-
"epoch": 2.95,
|
361 |
-
"learning_rate": 9.746588693957115e-07,
|
362 |
-
"loss": 0.1235,
|
363 |
-
"step": 560
|
364 |
-
},
|
365 |
-
{
|
366 |
-
"epoch": 3.0,
|
367 |
-
"learning_rate": 0.0,
|
368 |
-
"loss": 0.1469,
|
369 |
-
"step": 570
|
370 |
-
},
|
371 |
-
{
|
372 |
-
"epoch": 3.0,
|
373 |
-
"eval_accuracy": 0.9840740740740741,
|
374 |
-
"eval_loss": 0.0557386614382267,
|
375 |
-
"eval_runtime": 16.9406,
|
376 |
-
"eval_samples_per_second": 159.38,
|
377 |
-
"eval_steps_per_second": 5.018,
|
378 |
-
"step": 570
|
379 |
-
},
|
380 |
-
{
|
381 |
-
"epoch": 3.0,
|
382 |
-
"step": 570,
|
383 |
-
"total_flos": 1.8124066505760768e+18,
|
384 |
-
"train_loss": 0.31778242818096225,
|
385 |
-
"train_runtime": 1131.972,
|
386 |
-
"train_samples_per_second": 64.401,
|
387 |
-
"train_steps_per_second": 0.504
|
388 |
}
|
389 |
],
|
390 |
-
"
|
391 |
-
"max_steps": 570,
|
392 |
"num_train_epochs": 3,
|
393 |
-
"
|
394 |
-
"total_flos": 1.8124066505760768e+18,
|
395 |
"trial_name": null,
|
396 |
"trial_params": null
|
397 |
}
|
|
|
1 |
{
|
2 |
+
"best_metric": 0.9358974358974359,
|
3 |
+
"best_model_checkpoint": "swin-tiny-patch4-window7-224-finetuned-eurosat/checkpoint-197",
|
4 |
+
"epoch": 2.9772151898734176,
|
5 |
+
"global_step": 294,
|
|
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
9 |
"log_history": [
|
10 |
{
|
11 |
+
"epoch": 0.1,
|
12 |
+
"learning_rate": 3.522727272727273e-05,
|
13 |
+
"loss": 0.2741,
|
14 |
"step": 10
|
15 |
},
|
16 |
{
|
17 |
+
"epoch": 0.2,
|
18 |
+
"learning_rate": 3.3333333333333335e-05,
|
19 |
+
"loss": 0.2632,
|
20 |
"step": 20
|
21 |
},
|
22 |
{
|
23 |
+
"epoch": 0.3,
|
24 |
+
"learning_rate": 3.143939393939394e-05,
|
25 |
+
"loss": 0.2745,
|
26 |
"step": 30
|
27 |
},
|
28 |
{
|
29 |
+
"epoch": 0.41,
|
30 |
+
"learning_rate": 2.954545454545455e-05,
|
31 |
+
"loss": 0.2581,
|
32 |
"step": 40
|
33 |
},
|
34 |
{
|
35 |
+
"epoch": 0.51,
|
36 |
+
"learning_rate": 2.7651515151515152e-05,
|
37 |
+
"loss": 0.2809,
|
38 |
"step": 50
|
39 |
},
|
40 |
{
|
41 |
+
"epoch": 0.61,
|
42 |
+
"learning_rate": 2.575757575757576e-05,
|
43 |
+
"loss": 0.223,
|
44 |
"step": 60
|
45 |
},
|
46 |
{
|
47 |
+
"epoch": 0.71,
|
48 |
+
"learning_rate": 2.3863636363636365e-05,
|
49 |
+
"loss": 0.2812,
|
50 |
"step": 70
|
51 |
},
|
52 |
{
|
53 |
+
"epoch": 0.81,
|
54 |
+
"learning_rate": 2.1969696969696972e-05,
|
55 |
+
"loss": 0.2188,
|
56 |
"step": 80
|
57 |
},
|
58 |
{
|
59 |
+
"epoch": 0.91,
|
60 |
+
"learning_rate": 2.0075757575757575e-05,
|
61 |
+
"loss": 0.2447,
|
62 |
"step": 90
|
63 |
},
|
64 |
{
|
65 |
+
"epoch": 0.99,
|
66 |
+
"eval_accuracy": 0.9323361823361823,
|
67 |
+
"eval_loss": 0.18062111735343933,
|
68 |
+
"eval_runtime": 9.6659,
|
69 |
+
"eval_samples_per_second": 145.253,
|
70 |
+
"eval_steps_per_second": 4.552,
|
71 |
+
"step": 98
|
72 |
+
},
|
73 |
+
{
|
74 |
+
"epoch": 1.01,
|
75 |
+
"learning_rate": 1.8181818181818182e-05,
|
76 |
+
"loss": 0.2251,
|
77 |
"step": 100
|
78 |
},
|
79 |
{
|
80 |
+
"epoch": 1.11,
|
81 |
+
"learning_rate": 1.628787878787879e-05,
|
82 |
+
"loss": 0.2101,
|
83 |
"step": 110
|
84 |
},
|
85 |
{
|
86 |
+
"epoch": 1.22,
|
87 |
+
"learning_rate": 1.4393939393939396e-05,
|
88 |
+
"loss": 0.225,
|
89 |
"step": 120
|
90 |
},
|
91 |
{
|
92 |
+
"epoch": 1.32,
|
93 |
+
"learning_rate": 1.25e-05,
|
94 |
+
"loss": 0.248,
|
95 |
"step": 130
|
96 |
},
|
97 |
{
|
98 |
+
"epoch": 1.42,
|
99 |
+
"learning_rate": 1.0606060606060607e-05,
|
100 |
+
"loss": 0.2189,
|
101 |
"step": 140
|
102 |
},
|
103 |
{
|
104 |
+
"epoch": 1.52,
|
105 |
+
"learning_rate": 8.712121212121212e-06,
|
106 |
+
"loss": 0.2285,
|
107 |
"step": 150
|
108 |
},
|
109 |
{
|
110 |
+
"epoch": 1.62,
|
111 |
+
"learning_rate": 6.818181818181818e-06,
|
112 |
+
"loss": 0.2232,
|
113 |
"step": 160
|
114 |
},
|
115 |
{
|
116 |
+
"epoch": 1.72,
|
117 |
+
"learning_rate": 4.924242424242424e-06,
|
118 |
+
"loss": 0.2191,
|
119 |
"step": 170
|
120 |
},
|
121 |
{
|
122 |
+
"epoch": 1.82,
|
123 |
+
"learning_rate": 3.0303030303030305e-06,
|
124 |
+
"loss": 0.2231,
|
125 |
"step": 180
|
126 |
},
|
127 |
{
|
128 |
+
"epoch": 1.92,
|
129 |
+
"learning_rate": 1.1363636363636364e-06,
|
130 |
+
"loss": 0.1986,
|
131 |
"step": 190
|
132 |
},
|
133 |
{
|
134 |
+
"epoch": 1.99,
|
135 |
+
"eval_accuracy": 0.9358974358974359,
|
136 |
+
"eval_loss": 0.17716573178768158,
|
137 |
+
"eval_runtime": 9.3711,
|
138 |
+
"eval_samples_per_second": 149.823,
|
139 |
+
"eval_steps_per_second": 4.695,
|
140 |
+
"step": 197
|
141 |
},
|
142 |
{
|
143 |
+
"epoch": 2.03,
|
144 |
+
"learning_rate": 0.0,
|
145 |
+
"loss": 0.2088,
|
146 |
"step": 200
|
147 |
},
|
148 |
{
|
149 |
+
"epoch": 2.13,
|
150 |
+
"learning_rate": 0.0,
|
151 |
+
"loss": 0.2201,
|
152 |
"step": 210
|
153 |
},
|
154 |
{
|
155 |
+
"epoch": 2.23,
|
156 |
+
"learning_rate": 0.0,
|
157 |
+
"loss": 0.1851,
|
158 |
"step": 220
|
159 |
},
|
160 |
{
|
161 |
+
"epoch": 2.33,
|
162 |
+
"learning_rate": 0.0,
|
163 |
+
"loss": 0.2126,
|
164 |
"step": 230
|
165 |
},
|
166 |
{
|
167 |
+
"epoch": 2.43,
|
168 |
+
"learning_rate": 0.0,
|
169 |
+
"loss": 0.2031,
|
170 |
"step": 240
|
171 |
},
|
172 |
{
|
173 |
+
"epoch": 2.53,
|
174 |
+
"learning_rate": 0.0,
|
175 |
+
"loss": 0.2218,
|
176 |
"step": 250
|
177 |
},
|
178 |
{
|
179 |
+
"epoch": 2.63,
|
180 |
+
"learning_rate": 0.0,
|
181 |
+
"loss": 0.2018,
|
182 |
"step": 260
|
183 |
},
|
184 |
{
|
185 |
+
"epoch": 2.73,
|
186 |
+
"learning_rate": 0.0,
|
187 |
+
"loss": 0.2096,
|
188 |
"step": 270
|
189 |
},
|
190 |
{
|
191 |
+
"epoch": 2.84,
|
192 |
+
"learning_rate": 0.0,
|
193 |
+
"loss": 0.2128,
|
194 |
"step": 280
|
195 |
},
|
196 |
{
|
197 |
+
"epoch": 2.94,
|
198 |
+
"learning_rate": 0.0,
|
199 |
+
"loss": 0.1933,
|
200 |
"step": 290
|
201 |
},
|
202 |
{
|
203 |
+
"epoch": 2.98,
|
204 |
+
"eval_accuracy": 0.9358974358974359,
|
205 |
+
"eval_loss": 0.17716573178768158,
|
206 |
+
"eval_runtime": 9.0385,
|
207 |
+
"eval_samples_per_second": 155.336,
|
208 |
+
"eval_steps_per_second": 4.868,
|
209 |
+
"step": 294
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
210 |
},
|
211 |
{
|
212 |
+
"epoch": 2.98,
|
213 |
+
"step": 294,
|
214 |
+
"total_flos": 9.625811808320225e+17,
|
215 |
+
"train_loss": 0.22732183539948494,
|
216 |
+
"train_runtime": 623.8374,
|
217 |
+
"train_samples_per_second": 60.737,
|
218 |
+
"train_steps_per_second": 0.471
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
219 |
}
|
220 |
],
|
221 |
+
"max_steps": 294,
|
|
|
222 |
"num_train_epochs": 3,
|
223 |
+
"total_flos": 9.625811808320225e+17,
|
|
|
224 |
"trial_name": null,
|
225 |
"trial_params": null
|
226 |
}
|