End of training
Browse files- all_results.json +11 -11
- eval_results.json +6 -6
- runs/Jul21_17-20-08_9d2c660dfb38/events.out.tfevents.1689969005.9d2c660dfb38.3566.1 +3 -0
- train_results.json +6 -6
- trainer_state.json +1062 -621
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":
|
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": 14.93,
|
3 |
+
"eval_accuracy": 0.986863711001642,
|
4 |
+
"eval_loss": 0.07206606864929199,
|
5 |
+
"eval_runtime": 37.3968,
|
6 |
+
"eval_samples_per_second": 32.57,
|
7 |
+
"eval_steps_per_second": 2.059,
|
8 |
+
"total_flos": 9.675577376037974e+18,
|
9 |
+
"train_loss": 0.8123349746416884,
|
10 |
+
"train_runtime": 8647.4379,
|
11 |
+
"train_samples_per_second": 6.333,
|
12 |
+
"train_steps_per_second": 0.198
|
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":
|
8 |
}
|
|
|
1 |
{
|
2 |
+
"epoch": 14.93,
|
3 |
+
"eval_accuracy": 0.986863711001642,
|
4 |
+
"eval_loss": 0.07206606864929199,
|
5 |
+
"eval_runtime": 37.3968,
|
6 |
+
"eval_samples_per_second": 32.57,
|
7 |
+
"eval_steps_per_second": 2.059
|
8 |
}
|
runs/Jul21_17-20-08_9d2c660dfb38/events.out.tfevents.1689969005.9d2c660dfb38.3566.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cf78fe1c185c6c8e1b88ea8dc45c162161ae89130bb350163653a1adc3d6f9a4
|
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": 14.93,
|
3 |
+
"total_flos": 9.675577376037974e+18,
|
4 |
+
"train_loss": 0.8123349746416884,
|
5 |
+
"train_runtime": 8647.4379,
|
6 |
+
"train_samples_per_second": 6.333,
|
7 |
+
"train_steps_per_second": 0.198
|
8 |
}
|
trainer_state.json
CHANGED
@@ -1,1771 +1,2212 @@
|
|
1 |
{
|
2 |
-
"best_metric": 0.
|
3 |
-
"best_model_checkpoint": "convnextv2-large-1k-224-finetuned-Lesion-Classification-HAM10000-AH-60-20-20-Shuffled/checkpoint-
|
4 |
-
"epoch":
|
5 |
-
"global_step":
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
9 |
"log_history": [
|
10 |
{
|
11 |
"epoch": 0.04,
|
12 |
-
"learning_rate":
|
13 |
-
"loss": 1.
|
14 |
"step": 5
|
15 |
},
|
16 |
{
|
17 |
"epoch": 0.09,
|
18 |
-
"learning_rate":
|
19 |
-
"loss": 1.
|
20 |
"step": 10
|
21 |
},
|
22 |
{
|
23 |
"epoch": 0.13,
|
24 |
-
"learning_rate":
|
25 |
-
"loss": 1.
|
26 |
"step": 15
|
27 |
},
|
28 |
{
|
29 |
"epoch": 0.17,
|
30 |
-
"learning_rate":
|
31 |
-
"loss": 1.
|
32 |
"step": 20
|
33 |
},
|
34 |
{
|
35 |
"epoch": 0.22,
|
36 |
-
"learning_rate":
|
37 |
-
"loss": 1.
|
38 |
"step": 25
|
39 |
},
|
40 |
{
|
41 |
"epoch": 0.26,
|
42 |
-
"learning_rate":
|
43 |
-
"loss": 1.
|
44 |
"step": 30
|
45 |
},
|
46 |
{
|
47 |
"epoch": 0.31,
|
48 |
-
"learning_rate": 1.
|
49 |
-
"loss": 1.
|
50 |
"step": 35
|
51 |
},
|
52 |
{
|
53 |
"epoch": 0.35,
|
54 |
-
"learning_rate": 1.
|
55 |
-
"loss": 1.
|
56 |
"step": 40
|
57 |
},
|
58 |
{
|
59 |
"epoch": 0.39,
|
60 |
-
"learning_rate": 1.
|
61 |
-
"loss": 1.
|
62 |
"step": 45
|
63 |
},
|
64 |
{
|
65 |
"epoch": 0.44,
|
66 |
-
"learning_rate":
|
67 |
-
"loss": 1.
|
68 |
"step": 50
|
69 |
},
|
70 |
{
|
71 |
"epoch": 0.48,
|
72 |
-
"learning_rate":
|
73 |
-
"loss": 1.
|
74 |
"step": 55
|
75 |
},
|
76 |
{
|
77 |
"epoch": 0.52,
|
78 |
-
"learning_rate":
|
79 |
-
"loss": 1.
|
80 |
"step": 60
|
81 |
},
|
82 |
{
|
83 |
"epoch": 0.57,
|
84 |
-
"learning_rate": 2.
|
85 |
-
"loss": 1.
|
86 |
"step": 65
|
87 |
},
|
88 |
{
|
89 |
"epoch": 0.61,
|
90 |
-
"learning_rate": 2.
|
91 |
"loss": 1.9269,
|
92 |
"step": 70
|
93 |
},
|
94 |
{
|
95 |
"epoch": 0.66,
|
96 |
-
"learning_rate":
|
97 |
-
"loss": 1.
|
98 |
"step": 75
|
99 |
},
|
100 |
{
|
101 |
"epoch": 0.7,
|
102 |
-
"learning_rate":
|
103 |
-
"loss": 1.
|
104 |
"step": 80
|
105 |
},
|
106 |
{
|
107 |
"epoch": 0.74,
|
108 |
-
"learning_rate":
|
109 |
-
"loss": 1.
|
110 |
"step": 85
|
111 |
},
|
112 |
{
|
113 |
"epoch": 0.79,
|
114 |
-
"learning_rate":
|
115 |
-
"loss": 1.
|
116 |
"step": 90
|
117 |
},
|
118 |
{
|
119 |
"epoch": 0.83,
|
120 |
-
"learning_rate": 3.
|
121 |
-
"loss": 1.
|
122 |
"step": 95
|
123 |
},
|
124 |
{
|
125 |
"epoch": 0.87,
|
126 |
-
"learning_rate":
|
127 |
-
"loss": 1.
|
128 |
"step": 100
|
129 |
},
|
130 |
{
|
131 |
"epoch": 0.92,
|
132 |
-
"learning_rate":
|
133 |
-
"loss": 1.
|
134 |
"step": 105
|
135 |
},
|
136 |
{
|
137 |
"epoch": 0.96,
|
138 |
-
"learning_rate":
|
139 |
-
"loss": 1.
|
140 |
"step": 110
|
141 |
},
|
142 |
{
|
143 |
"epoch": 1.0,
|
144 |
-
"eval_accuracy": 0.
|
145 |
-
"eval_loss": 1.
|
146 |
-
"eval_runtime":
|
147 |
-
"eval_samples_per_second":
|
148 |
-
"eval_steps_per_second": 0.
|
149 |
"step": 114
|
150 |
},
|
151 |
{
|
152 |
"epoch": 1.0,
|
153 |
-
"learning_rate":
|
154 |
-
"loss": 1.
|
155 |
"step": 115
|
156 |
},
|
157 |
{
|
158 |
"epoch": 1.05,
|
159 |
-
"learning_rate":
|
160 |
-
"loss": 1.
|
161 |
"step": 120
|
162 |
},
|
163 |
{
|
164 |
"epoch": 1.09,
|
165 |
-
"learning_rate":
|
166 |
-
"loss": 1.
|
167 |
"step": 125
|
168 |
},
|
169 |
{
|
170 |
"epoch": 1.14,
|
171 |
-
"learning_rate":
|
172 |
-
"loss": 1.
|
173 |
"step": 130
|
174 |
},
|
175 |
{
|
176 |
"epoch": 1.18,
|
177 |
-
"learning_rate":
|
178 |
-
"loss": 1.
|
179 |
"step": 135
|
180 |
},
|
181 |
{
|
182 |
"epoch": 1.22,
|
183 |
-
"learning_rate":
|
184 |
-
"loss": 1.
|
185 |
"step": 140
|
186 |
},
|
187 |
{
|
188 |
"epoch": 1.27,
|
189 |
-
"learning_rate":
|
190 |
-
"loss": 1.
|
191 |
"step": 145
|
192 |
},
|
193 |
{
|
194 |
"epoch": 1.31,
|
195 |
-
"learning_rate":
|
196 |
-
"loss": 1.
|
197 |
"step": 150
|
198 |
},
|
199 |
{
|
200 |
"epoch": 1.35,
|
201 |
-
"learning_rate":
|
202 |
-
"loss": 1.
|
203 |
"step": 155
|
204 |
},
|
205 |
{
|
206 |
"epoch": 1.4,
|
207 |
-
"learning_rate":
|
208 |
-
"loss": 1.
|
209 |
"step": 160
|
210 |
},
|
211 |
{
|
212 |
"epoch": 1.44,
|
213 |
-
"learning_rate":
|
214 |
-
"loss": 1.
|
215 |
"step": 165
|
216 |
},
|
217 |
{
|
218 |
"epoch": 1.48,
|
219 |
-
"learning_rate":
|
220 |
-
"loss": 1.
|
221 |
"step": 170
|
222 |
},
|
223 |
{
|
224 |
"epoch": 1.53,
|
225 |
-
"learning_rate":
|
226 |
-
"loss": 1.
|
227 |
"step": 175
|
228 |
},
|
229 |
{
|
230 |
"epoch": 1.57,
|
231 |
-
"learning_rate":
|
232 |
-
"loss": 1.
|
233 |
"step": 180
|
234 |
},
|
235 |
{
|
236 |
"epoch": 1.62,
|
237 |
-
"learning_rate":
|
238 |
-
"loss": 1.
|
239 |
"step": 185
|
240 |
},
|
241 |
{
|
242 |
"epoch": 1.66,
|
243 |
-
"learning_rate":
|
244 |
-
"loss": 1.
|
245 |
"step": 190
|
246 |
},
|
247 |
{
|
248 |
"epoch": 1.7,
|
249 |
-
"learning_rate":
|
250 |
-
"loss": 1.
|
251 |
"step": 195
|
252 |
},
|
253 |
{
|
254 |
"epoch": 1.75,
|
255 |
-
"learning_rate":
|
256 |
-
"loss": 1.
|
257 |
"step": 200
|
258 |
},
|
259 |
{
|
260 |
"epoch": 1.79,
|
261 |
-
"learning_rate":
|
262 |
-
"loss": 1.
|
263 |
"step": 205
|
264 |
},
|
265 |
{
|
266 |
"epoch": 1.83,
|
267 |
-
"learning_rate":
|
268 |
-
"loss": 1.
|
269 |
"step": 210
|
270 |
},
|
271 |
{
|
272 |
"epoch": 1.88,
|
273 |
-
"learning_rate":
|
274 |
-
"loss": 1.
|
275 |
"step": 215
|
276 |
},
|
277 |
{
|
278 |
"epoch": 1.92,
|
279 |
-
"learning_rate":
|
280 |
-
"loss": 1.
|
281 |
"step": 220
|
282 |
},
|
283 |
{
|
284 |
"epoch": 1.97,
|
285 |
-
"learning_rate":
|
286 |
-
"loss": 1.
|
287 |
"step": 225
|
288 |
},
|
289 |
{
|
290 |
"epoch": 2.0,
|
291 |
-
"eval_accuracy": 0.
|
292 |
-
"eval_loss": 1.
|
293 |
-
"eval_runtime":
|
294 |
-
"eval_samples_per_second":
|
295 |
-
"eval_steps_per_second": 1.
|
296 |
"step": 229
|
297 |
},
|
298 |
{
|
299 |
"epoch": 2.01,
|
300 |
-
"learning_rate":
|
301 |
-
"loss": 1.
|
302 |
"step": 230
|
303 |
},
|
304 |
{
|
305 |
"epoch": 2.05,
|
306 |
-
"learning_rate":
|
307 |
-
"loss": 1.
|
308 |
"step": 235
|
309 |
},
|
310 |
{
|
311 |
"epoch": 2.1,
|
312 |
-
"learning_rate":
|
313 |
-
"loss": 1.
|
314 |
"step": 240
|
315 |
},
|
316 |
{
|
317 |
"epoch": 2.14,
|
318 |
-
"learning_rate":
|
319 |
-
"loss": 1.
|
320 |
"step": 245
|
321 |
},
|
322 |
{
|
323 |
"epoch": 2.18,
|
324 |
-
"learning_rate":
|
325 |
-
"loss": 1.
|
326 |
"step": 250
|
327 |
},
|
328 |
{
|
329 |
"epoch": 2.23,
|
330 |
-
"learning_rate":
|
331 |
-
"loss": 1.
|
332 |
"step": 255
|
333 |
},
|
334 |
{
|
335 |
"epoch": 2.27,
|
336 |
-
"learning_rate":
|
337 |
-
"loss": 1.
|
338 |
"step": 260
|
339 |
},
|
340 |
{
|
341 |
"epoch": 2.31,
|
342 |
-
"learning_rate":
|
343 |
-
"loss": 1.
|
344 |
"step": 265
|
345 |
},
|
346 |
{
|
347 |
"epoch": 2.36,
|
348 |
-
"learning_rate":
|
349 |
-
"loss": 1.
|
350 |
"step": 270
|
351 |
},
|
352 |
{
|
353 |
"epoch": 2.4,
|
354 |
-
"learning_rate":
|
355 |
-
"loss": 1.
|
356 |
"step": 275
|
357 |
},
|
358 |
{
|
359 |
"epoch": 2.45,
|
360 |
-
"learning_rate":
|
361 |
-
"loss": 1.
|
362 |
"step": 280
|
363 |
},
|
364 |
{
|
365 |
"epoch": 2.49,
|
366 |
-
"learning_rate":
|
367 |
-
"loss": 1.
|
368 |
"step": 285
|
369 |
},
|
370 |
{
|
371 |
"epoch": 2.53,
|
372 |
-
"learning_rate":
|
373 |
-
"loss": 1.
|
374 |
"step": 290
|
375 |
},
|
376 |
{
|
377 |
"epoch": 2.58,
|
378 |
-
"learning_rate":
|
379 |
-
"loss": 1.
|
380 |
"step": 295
|
381 |
},
|
382 |
{
|
383 |
"epoch": 2.62,
|
384 |
-
"learning_rate":
|
385 |
-
"loss": 1.
|
386 |
"step": 300
|
387 |
},
|
388 |
{
|
389 |
"epoch": 2.66,
|
390 |
-
"learning_rate":
|
391 |
-
"loss": 1.
|
392 |
"step": 305
|
393 |
},
|
394 |
{
|
395 |
"epoch": 2.71,
|
396 |
-
"learning_rate": 1.
|
397 |
-
"loss": 1.
|
398 |
"step": 310
|
399 |
},
|
400 |
{
|
401 |
"epoch": 2.75,
|
402 |
-
"learning_rate": 1.
|
403 |
-
"loss": 1.
|
404 |
"step": 315
|
405 |
},
|
406 |
{
|
407 |
"epoch": 2.79,
|
408 |
-
"learning_rate": 1.
|
409 |
-
"loss": 1.
|
410 |
"step": 320
|
411 |
},
|
412 |
{
|
413 |
"epoch": 2.84,
|
414 |
-
"learning_rate": 1.
|
415 |
-
"loss": 1.
|
416 |
"step": 325
|
417 |
},
|
418 |
{
|
419 |
"epoch": 2.88,
|
420 |
-
"learning_rate": 1.
|
421 |
-
"loss": 1.
|
422 |
"step": 330
|
423 |
},
|
424 |
{
|
425 |
"epoch": 2.93,
|
426 |
-
"learning_rate": 1.
|
427 |
-
"loss": 1.
|
428 |
"step": 335
|
429 |
},
|
430 |
{
|
431 |
"epoch": 2.97,
|
432 |
-
"learning_rate": 1.
|
433 |
-
"loss": 1.
|
434 |
"step": 340
|
435 |
},
|
436 |
{
|
437 |
"epoch": 3.0,
|
438 |
-
"eval_accuracy": 0.
|
439 |
-
"eval_loss": 1.
|
440 |
-
"eval_runtime":
|
441 |
-
"eval_samples_per_second": 29.
|
442 |
-
"eval_steps_per_second": 1.
|
443 |
"step": 343
|
444 |
},
|
445 |
{
|
446 |
"epoch": 3.01,
|
447 |
-
"learning_rate": 1.
|
448 |
-
"loss": 1.
|
449 |
"step": 345
|
450 |
},
|
451 |
{
|
452 |
"epoch": 3.06,
|
453 |
-
"learning_rate": 1.
|
454 |
-
"loss": 1.
|
455 |
"step": 350
|
456 |
},
|
457 |
{
|
458 |
"epoch": 3.1,
|
459 |
-
"learning_rate": 1.
|
460 |
-
"loss": 1.
|
461 |
"step": 355
|
462 |
},
|
463 |
{
|
464 |
"epoch": 3.14,
|
465 |
-
"learning_rate": 1.
|
466 |
-
"loss": 1.
|
467 |
"step": 360
|
468 |
},
|
469 |
{
|
470 |
"epoch": 3.19,
|
471 |
-
"learning_rate": 1.
|
472 |
-
"loss": 1.
|
473 |
"step": 365
|
474 |
},
|
475 |
{
|
476 |
"epoch": 3.23,
|
477 |
-
"learning_rate": 1.
|
478 |
-
"loss": 1.
|
479 |
"step": 370
|
480 |
},
|
481 |
{
|
482 |
"epoch": 3.28,
|
483 |
-
"learning_rate": 1.
|
484 |
-
"loss": 1.
|
485 |
"step": 375
|
486 |
},
|
487 |
{
|
488 |
"epoch": 3.32,
|
489 |
-
"learning_rate": 1.
|
490 |
-
"loss": 1.
|
491 |
"step": 380
|
492 |
},
|
493 |
{
|
494 |
"epoch": 3.36,
|
495 |
-
"learning_rate": 1.
|
496 |
-
"loss": 1.
|
497 |
"step": 385
|
498 |
},
|
499 |
{
|
500 |
"epoch": 3.41,
|
501 |
-
"learning_rate": 1.
|
502 |
-
"loss": 1.
|
503 |
"step": 390
|
504 |
},
|
505 |
{
|
506 |
"epoch": 3.45,
|
507 |
-
"learning_rate": 1.
|
508 |
-
"loss": 1.
|
509 |
"step": 395
|
510 |
},
|
511 |
{
|
512 |
"epoch": 3.49,
|
513 |
-
"learning_rate": 1.
|
514 |
-
"loss": 1.
|
515 |
"step": 400
|
516 |
},
|
517 |
{
|
518 |
"epoch": 3.54,
|
519 |
-
"learning_rate": 1.
|
520 |
-
"loss": 1.
|
521 |
"step": 405
|
522 |
},
|
523 |
{
|
524 |
"epoch": 3.58,
|
525 |
-
"learning_rate": 1.
|
526 |
-
"loss": 1.
|
527 |
"step": 410
|
528 |
},
|
529 |
{
|
530 |
"epoch": 3.62,
|
531 |
-
"learning_rate": 1.
|
532 |
-
"loss": 1.
|
533 |
"step": 415
|
534 |
},
|
535 |
{
|
536 |
"epoch": 3.67,
|
537 |
-
"learning_rate": 1.
|
538 |
-
"loss": 1.
|
539 |
"step": 420
|
540 |
},
|
541 |
{
|
542 |
"epoch": 3.71,
|
543 |
-
"learning_rate": 1.
|
544 |
-
"loss": 1.
|
545 |
"step": 425
|
546 |
},
|
547 |
{
|
548 |
"epoch": 3.76,
|
549 |
-
"learning_rate": 1.
|
550 |
-
"loss": 1.
|
551 |
"step": 430
|
552 |
},
|
553 |
{
|
554 |
"epoch": 3.8,
|
555 |
-
"learning_rate": 1.
|
556 |
-
"loss":
|
557 |
"step": 435
|
558 |
},
|
559 |
{
|
560 |
"epoch": 3.84,
|
561 |
-
"learning_rate": 1.
|
562 |
-
"loss": 1.
|
563 |
"step": 440
|
564 |
},
|
565 |
{
|
566 |
"epoch": 3.89,
|
567 |
-
"learning_rate": 1.
|
568 |
-
"loss": 1.
|
569 |
"step": 445
|
570 |
},
|
571 |
{
|
572 |
"epoch": 3.93,
|
573 |
-
"learning_rate": 1.
|
574 |
-
"loss": 1.
|
575 |
"step": 450
|
576 |
},
|
577 |
{
|
578 |
"epoch": 3.97,
|
579 |
-
"learning_rate": 1.
|
580 |
-
"loss": 1.
|
581 |
"step": 455
|
582 |
},
|
583 |
{
|
584 |
"epoch": 4.0,
|
585 |
-
"eval_accuracy": 0.
|
586 |
-
"eval_loss":
|
587 |
-
"eval_runtime":
|
588 |
-
"eval_samples_per_second":
|
589 |
-
"eval_steps_per_second": 1.
|
590 |
"step": 458
|
591 |
},
|
592 |
{
|
593 |
"epoch": 4.02,
|
594 |
-
"learning_rate": 1.
|
595 |
-
"loss":
|
596 |
"step": 460
|
597 |
},
|
598 |
{
|
599 |
"epoch": 4.06,
|
600 |
-
"learning_rate": 1.
|
601 |
-
"loss": 1.
|
602 |
"step": 465
|
603 |
},
|
604 |
{
|
605 |
"epoch": 4.1,
|
606 |
-
"learning_rate": 1.
|
607 |
-
"loss":
|
608 |
"step": 470
|
609 |
},
|
610 |
{
|
611 |
"epoch": 4.15,
|
612 |
-
"learning_rate": 1.
|
613 |
-
"loss": 1.
|
614 |
"step": 475
|
615 |
},
|
616 |
{
|
617 |
"epoch": 4.19,
|
618 |
-
"learning_rate": 1.
|
619 |
-
"loss":
|
620 |
"step": 480
|
621 |
},
|
622 |
{
|
623 |
"epoch": 4.24,
|
624 |
-
"learning_rate": 1.
|
625 |
-
"loss":
|
626 |
"step": 485
|
627 |
},
|
628 |
{
|
629 |
"epoch": 4.28,
|
630 |
-
"learning_rate": 1.
|
631 |
-
"loss":
|
632 |
"step": 490
|
633 |
},
|
634 |
{
|
635 |
"epoch": 4.32,
|
636 |
-
"learning_rate":
|
637 |
-
"loss":
|
638 |
"step": 495
|
639 |
},
|
640 |
{
|
641 |
"epoch": 4.37,
|
642 |
-
"learning_rate":
|
643 |
-
"loss":
|
644 |
"step": 500
|
645 |
},
|
646 |
{
|
647 |
"epoch": 4.41,
|
648 |
-
"learning_rate":
|
649 |
-
"loss": 0.
|
650 |
"step": 505
|
651 |
},
|
652 |
{
|
653 |
"epoch": 4.45,
|
654 |
-
"learning_rate":
|
655 |
-
"loss":
|
656 |
"step": 510
|
657 |
},
|
658 |
{
|
659 |
"epoch": 4.5,
|
660 |
-
"learning_rate":
|
661 |
-
"loss":
|
662 |
"step": 515
|
663 |
},
|
664 |
{
|
665 |
"epoch": 4.54,
|
666 |
-
"learning_rate":
|
667 |
-
"loss":
|
668 |
"step": 520
|
669 |
},
|
670 |
{
|
671 |
"epoch": 4.59,
|
672 |
-
"learning_rate":
|
673 |
-
"loss":
|
674 |
"step": 525
|
675 |
},
|
676 |
{
|
677 |
"epoch": 4.63,
|
678 |
-
"learning_rate":
|
679 |
-
"loss": 0.
|
680 |
"step": 530
|
681 |
},
|
682 |
{
|
683 |
"epoch": 4.67,
|
684 |
-
"learning_rate":
|
685 |
-
"loss":
|
686 |
"step": 535
|
687 |
},
|
688 |
{
|
689 |
"epoch": 4.72,
|
690 |
-
"learning_rate":
|
691 |
-
"loss":
|
692 |
"step": 540
|
693 |
},
|
694 |
{
|
695 |
"epoch": 4.76,
|
696 |
-
"learning_rate":
|
697 |
-
"loss": 0.
|
698 |
"step": 545
|
699 |
},
|
700 |
{
|
701 |
"epoch": 4.8,
|
702 |
-
"learning_rate":
|
703 |
-
"loss": 0.
|
704 |
"step": 550
|
705 |
},
|
706 |
{
|
707 |
"epoch": 4.85,
|
708 |
-
"learning_rate":
|
709 |
-
"loss": 0.
|
710 |
"step": 555
|
711 |
},
|
712 |
{
|
713 |
"epoch": 4.89,
|
714 |
-
"learning_rate":
|
715 |
-
"loss": 0.
|
716 |
"step": 560
|
717 |
},
|
718 |
{
|
719 |
"epoch": 4.93,
|
720 |
-
"learning_rate":
|
721 |
-
"loss": 0.
|
722 |
"step": 565
|
723 |
},
|
724 |
{
|
725 |
"epoch": 4.98,
|
726 |
-
"learning_rate":
|
727 |
-
"loss": 0.
|
728 |
"step": 570
|
729 |
},
|
730 |
{
|
731 |
"epoch": 5.0,
|
732 |
-
"eval_accuracy": 0.
|
733 |
-
"eval_loss": 0.
|
734 |
-
"eval_runtime":
|
735 |
-
"eval_samples_per_second": 29.
|
736 |
-
"eval_steps_per_second": 1.
|
737 |
"step": 572
|
738 |
},
|
739 |
{
|
740 |
"epoch": 5.02,
|
741 |
-
"learning_rate":
|
742 |
-
"loss": 0.
|
743 |
"step": 575
|
744 |
},
|
745 |
{
|
746 |
"epoch": 5.07,
|
747 |
-
"learning_rate":
|
748 |
-
"loss": 0.
|
749 |
"step": 580
|
750 |
},
|
751 |
{
|
752 |
"epoch": 5.11,
|
753 |
-
"learning_rate":
|
754 |
-
"loss": 0.
|
755 |
"step": 585
|
756 |
},
|
757 |
{
|
758 |
"epoch": 5.15,
|
759 |
-
"learning_rate":
|
760 |
-
"loss": 0.
|
761 |
"step": 590
|
762 |
},
|
763 |
{
|
764 |
"epoch": 5.2,
|
765 |
-
"learning_rate":
|
766 |
-
"loss": 0.
|
767 |
"step": 595
|
768 |
},
|
769 |
{
|
770 |
"epoch": 5.24,
|
771 |
-
"learning_rate":
|
772 |
-
"loss": 0.
|
773 |
"step": 600
|
774 |
},
|
775 |
{
|
776 |
"epoch": 5.28,
|
777 |
-
"learning_rate":
|
778 |
-
"loss": 0.
|
779 |
"step": 605
|
780 |
},
|
781 |
{
|
782 |
"epoch": 5.33,
|
783 |
-
"learning_rate":
|
784 |
-
"loss": 0.
|
785 |
"step": 610
|
786 |
},
|
787 |
{
|
788 |
"epoch": 5.37,
|
789 |
-
"learning_rate":
|
790 |
-
"loss": 0.
|
791 |
"step": 615
|
792 |
},
|
793 |
{
|
794 |
"epoch": 5.41,
|
795 |
-
"learning_rate": 2.
|
796 |
-
"loss": 0.
|
797 |
"step": 620
|
798 |
},
|
799 |
{
|
800 |
"epoch": 5.46,
|
801 |
-
"learning_rate": 2.
|
802 |
-
"loss": 0.
|
803 |
"step": 625
|
804 |
},
|
805 |
{
|
806 |
"epoch": 5.5,
|
807 |
-
"learning_rate": 2.
|
808 |
-
"loss": 0.
|
809 |
"step": 630
|
810 |
},
|
811 |
{
|
812 |
"epoch": 5.55,
|
813 |
-
"learning_rate": 2.
|
814 |
-
"loss": 0.
|
815 |
"step": 635
|
816 |
},
|
817 |
{
|
818 |
"epoch": 5.59,
|
819 |
-
"learning_rate": 2.
|
820 |
-
"loss": 0.
|
821 |
"step": 640
|
822 |
},
|
823 |
{
|
824 |
"epoch": 5.63,
|
825 |
-
"learning_rate": 2.
|
826 |
-
"loss": 0.
|
827 |
"step": 645
|
828 |
},
|
829 |
{
|
830 |
"epoch": 5.68,
|
831 |
-
"learning_rate": 2.
|
832 |
-
"loss": 0.
|
833 |
"step": 650
|
834 |
},
|
835 |
{
|
836 |
"epoch": 5.72,
|
837 |
-
"learning_rate": 2.
|
838 |
-
"loss": 0.
|
839 |
"step": 655
|
840 |
},
|
841 |
{
|
842 |
"epoch": 5.76,
|
843 |
-
"learning_rate": 2.
|
844 |
-
"loss": 0.
|
845 |
"step": 660
|
846 |
},
|
847 |
{
|
848 |
"epoch": 5.81,
|
849 |
-
"learning_rate": 2.
|
850 |
-
"loss": 0.
|
851 |
"step": 665
|
852 |
},
|
853 |
{
|
854 |
"epoch": 5.85,
|
855 |
-
"learning_rate": 2.
|
856 |
-
"loss": 0.
|
857 |
"step": 670
|
858 |
},
|
859 |
{
|
860 |
"epoch": 5.9,
|
861 |
-
"learning_rate": 2.
|
862 |
-
"loss": 0.
|
863 |
"step": 675
|
864 |
},
|
865 |
{
|
866 |
"epoch": 5.94,
|
867 |
-
"learning_rate": 2.
|
868 |
-
"loss": 0.
|
869 |
"step": 680
|
870 |
},
|
871 |
{
|
872 |
"epoch": 5.98,
|
873 |
-
"learning_rate": 2.
|
874 |
-
"loss": 0.
|
875 |
"step": 685
|
876 |
},
|
877 |
{
|
878 |
"epoch": 6.0,
|
879 |
-
"eval_accuracy": 0.
|
880 |
-
"eval_loss": 0.
|
881 |
-
"eval_runtime":
|
882 |
-
"eval_samples_per_second": 29.
|
883 |
-
"eval_steps_per_second": 1.
|
884 |
"step": 687
|
885 |
},
|
886 |
{
|
887 |
"epoch": 6.03,
|
888 |
-
"learning_rate": 2.
|
889 |
-
"loss": 0.
|
890 |
"step": 690
|
891 |
},
|
892 |
{
|
893 |
"epoch": 6.07,
|
894 |
-
"learning_rate": 2.
|
895 |
-
"loss": 0.
|
896 |
"step": 695
|
897 |
},
|
898 |
{
|
899 |
"epoch": 6.11,
|
900 |
-
"learning_rate": 2.
|
901 |
-
"loss": 0.
|
902 |
"step": 700
|
903 |
},
|
904 |
{
|
905 |
"epoch": 6.16,
|
906 |
-
"learning_rate": 2.
|
907 |
-
"loss": 0.
|
908 |
"step": 705
|
909 |
},
|
910 |
{
|
911 |
"epoch": 6.2,
|
912 |
-
"learning_rate": 2.
|
913 |
-
"loss": 0.
|
914 |
"step": 710
|
915 |
},
|
916 |
{
|
917 |
"epoch": 6.24,
|
918 |
-
"learning_rate": 2.
|
919 |
-
"loss": 0.
|
920 |
"step": 715
|
921 |
},
|
922 |
{
|
923 |
"epoch": 6.29,
|
924 |
-
"learning_rate": 2.
|
925 |
-
"loss": 0.
|
926 |
"step": 720
|
927 |
},
|
928 |
{
|
929 |
"epoch": 6.33,
|
930 |
-
"learning_rate": 2.
|
931 |
-
"loss":
|
932 |
"step": 725
|
933 |
},
|
934 |
{
|
935 |
"epoch": 6.38,
|
936 |
-
"learning_rate": 2.
|
937 |
-
"loss": 0.
|
938 |
"step": 730
|
939 |
},
|
940 |
{
|
941 |
"epoch": 6.42,
|
942 |
-
"learning_rate": 2.
|
943 |
-
"loss": 0.
|
944 |
"step": 735
|
945 |
},
|
946 |
{
|
947 |
"epoch": 6.46,
|
948 |
-
"learning_rate":
|
949 |
-
"loss": 0.
|
950 |
"step": 740
|
951 |
},
|
952 |
{
|
953 |
"epoch": 6.51,
|
954 |
-
"learning_rate":
|
955 |
-
"loss": 0.
|
956 |
"step": 745
|
957 |
},
|
958 |
{
|
959 |
"epoch": 6.55,
|
960 |
-
"learning_rate":
|
961 |
-
"loss": 0.
|
962 |
"step": 750
|
963 |
},
|
964 |
{
|
965 |
"epoch": 6.59,
|
966 |
-
"learning_rate":
|
967 |
-
"loss": 0.
|
968 |
"step": 755
|
969 |
},
|
970 |
{
|
971 |
"epoch": 6.64,
|
972 |
-
"learning_rate":
|
973 |
-
"loss": 0.
|
974 |
"step": 760
|
975 |
},
|
976 |
{
|
977 |
"epoch": 6.68,
|
978 |
-
"learning_rate":
|
979 |
-
"loss": 0.
|
980 |
"step": 765
|
981 |
},
|
982 |
{
|
983 |
"epoch": 6.72,
|
984 |
-
"learning_rate":
|
985 |
-
"loss": 0.
|
986 |
"step": 770
|
987 |
},
|
988 |
{
|
989 |
"epoch": 6.77,
|
990 |
-
"learning_rate":
|
991 |
-
"loss": 0.
|
992 |
"step": 775
|
993 |
},
|
994 |
{
|
995 |
"epoch": 6.81,
|
996 |
-
"learning_rate":
|
997 |
-
"loss": 0.
|
998 |
"step": 780
|
999 |
},
|
1000 |
{
|
1001 |
"epoch": 6.86,
|
1002 |
-
"learning_rate":
|
1003 |
-
"loss": 0.
|
1004 |
"step": 785
|
1005 |
},
|
1006 |
{
|
1007 |
"epoch": 6.9,
|
1008 |
-
"learning_rate":
|
1009 |
-
"loss": 0.
|
1010 |
"step": 790
|
1011 |
},
|
1012 |
{
|
1013 |
"epoch": 6.94,
|
1014 |
-
"learning_rate":
|
1015 |
-
"loss": 0.
|
1016 |
"step": 795
|
1017 |
},
|
1018 |
{
|
1019 |
"epoch": 6.99,
|
1020 |
-
"learning_rate":
|
1021 |
-
"loss": 0.
|
1022 |
"step": 800
|
1023 |
},
|
1024 |
{
|
1025 |
"epoch": 7.0,
|
1026 |
-
"eval_accuracy": 0.
|
1027 |
-
"eval_loss": 0.
|
1028 |
-
"eval_runtime":
|
1029 |
-
"eval_samples_per_second":
|
1030 |
-
"eval_steps_per_second": 1.
|
1031 |
"step": 801
|
1032 |
},
|
1033 |
{
|
1034 |
"epoch": 7.03,
|
1035 |
-
"learning_rate":
|
1036 |
-
"loss": 0.
|
1037 |
"step": 805
|
1038 |
},
|
1039 |
{
|
1040 |
"epoch": 7.07,
|
1041 |
-
"learning_rate":
|
1042 |
-
"loss": 0.
|
1043 |
"step": 810
|
1044 |
},
|
1045 |
{
|
1046 |
"epoch": 7.12,
|
1047 |
-
"learning_rate":
|
1048 |
-
"loss": 0.
|
1049 |
"step": 815
|
1050 |
},
|
1051 |
{
|
1052 |
"epoch": 7.16,
|
1053 |
-
"learning_rate":
|
1054 |
-
"loss": 0.
|
1055 |
"step": 820
|
1056 |
},
|
1057 |
{
|
1058 |
"epoch": 7.21,
|
1059 |
-
"learning_rate":
|
1060 |
-
"loss": 0.
|
1061 |
"step": 825
|
1062 |
},
|
1063 |
{
|
1064 |
"epoch": 7.25,
|
1065 |
-
"learning_rate":
|
1066 |
-
"loss": 0.
|
1067 |
"step": 830
|
1068 |
},
|
1069 |
{
|
1070 |
"epoch": 7.29,
|
1071 |
-
"learning_rate":
|
1072 |
-
"loss": 0.
|
1073 |
"step": 835
|
1074 |
},
|
1075 |
{
|
1076 |
"epoch": 7.34,
|
1077 |
-
"learning_rate":
|
1078 |
-
"loss": 0.
|
1079 |
"step": 840
|
1080 |
},
|
1081 |
{
|
1082 |
"epoch": 7.38,
|
1083 |
-
"learning_rate":
|
1084 |
-
"loss": 0.
|
1085 |
"step": 845
|
1086 |
},
|
1087 |
{
|
1088 |
"epoch": 7.42,
|
1089 |
-
"learning_rate":
|
1090 |
-
"loss": 0.
|
1091 |
"step": 850
|
1092 |
},
|
1093 |
{
|
1094 |
"epoch": 7.47,
|
1095 |
-
"learning_rate":
|
1096 |
-
"loss": 0.
|
1097 |
"step": 855
|
1098 |
},
|
1099 |
{
|
1100 |
"epoch": 7.51,
|
1101 |
-
"learning_rate":
|
1102 |
-
"loss": 0.
|
1103 |
"step": 860
|
1104 |
},
|
1105 |
{
|
1106 |
"epoch": 7.55,
|
1107 |
-
"learning_rate":
|
1108 |
-
"loss": 0.
|
1109 |
"step": 865
|
1110 |
},
|
1111 |
{
|
1112 |
"epoch": 7.6,
|
1113 |
-
"learning_rate":
|
1114 |
-
"loss": 0.
|
1115 |
"step": 870
|
1116 |
},
|
1117 |
{
|
1118 |
"epoch": 7.64,
|
1119 |
-
"learning_rate":
|
1120 |
-
"loss": 0.
|
1121 |
"step": 875
|
1122 |
},
|
1123 |
{
|
1124 |
"epoch": 7.69,
|
1125 |
-
"learning_rate":
|
1126 |
-
"loss": 0.
|
1127 |
"step": 880
|
1128 |
},
|
1129 |
{
|
1130 |
"epoch": 7.73,
|
1131 |
-
"learning_rate":
|
1132 |
-
"loss": 0.
|
1133 |
"step": 885
|
1134 |
},
|
1135 |
{
|
1136 |
"epoch": 7.77,
|
1137 |
-
"learning_rate":
|
1138 |
-
"loss": 0.
|
1139 |
"step": 890
|
1140 |
},
|
1141 |
{
|
1142 |
"epoch": 7.82,
|
1143 |
-
"learning_rate":
|
1144 |
-
"loss": 0.
|
1145 |
"step": 895
|
1146 |
},
|
1147 |
{
|
1148 |
"epoch": 7.86,
|
1149 |
-
"learning_rate":
|
1150 |
-
"loss": 0.
|
1151 |
"step": 900
|
1152 |
},
|
1153 |
{
|
1154 |
"epoch": 7.9,
|
1155 |
-
"learning_rate":
|
1156 |
-
"loss": 0.
|
1157 |
"step": 905
|
1158 |
},
|
1159 |
{
|
1160 |
"epoch": 7.95,
|
1161 |
-
"learning_rate":
|
1162 |
-
"loss": 0.
|
1163 |
"step": 910
|
1164 |
},
|
1165 |
{
|
1166 |
"epoch": 7.99,
|
1167 |
-
"learning_rate":
|
1168 |
-
"loss": 0.
|
1169 |
"step": 915
|
1170 |
},
|
1171 |
{
|
1172 |
"epoch": 8.0,
|
1173 |
-
"eval_accuracy": 0.
|
1174 |
-
"eval_loss": 0.
|
1175 |
-
"eval_runtime":
|
1176 |
-
"eval_samples_per_second": 29.
|
1177 |
-
"eval_steps_per_second": 1.
|
1178 |
"step": 916
|
1179 |
},
|
1180 |
{
|
1181 |
"epoch": 8.03,
|
1182 |
-
"learning_rate":
|
1183 |
-
"loss": 0.
|
1184 |
"step": 920
|
1185 |
},
|
1186 |
{
|
1187 |
"epoch": 8.08,
|
1188 |
-
"learning_rate": 3.
|
1189 |
-
"loss": 0.
|
1190 |
"step": 925
|
1191 |
},
|
1192 |
{
|
1193 |
"epoch": 8.12,
|
1194 |
-
"learning_rate": 3.
|
1195 |
-
"loss": 0.
|
1196 |
"step": 930
|
1197 |
},
|
1198 |
{
|
1199 |
"epoch": 8.17,
|
1200 |
-
"learning_rate": 3.
|
1201 |
-
"loss": 0.
|
1202 |
"step": 935
|
1203 |
},
|
1204 |
{
|
1205 |
"epoch": 8.21,
|
1206 |
-
"learning_rate": 3.
|
1207 |
-
"loss": 0.
|
1208 |
"step": 940
|
1209 |
},
|
1210 |
{
|
1211 |
"epoch": 8.25,
|
1212 |
-
"learning_rate": 3.
|
1213 |
-
"loss": 0.
|
1214 |
"step": 945
|
1215 |
},
|
1216 |
{
|
1217 |
"epoch": 8.3,
|
1218 |
-
"learning_rate": 3.
|
1219 |
-
"loss": 0.
|
1220 |
"step": 950
|
1221 |
},
|
1222 |
{
|
1223 |
"epoch": 8.34,
|
1224 |
-
"learning_rate": 3.
|
1225 |
-
"loss": 0.
|
1226 |
"step": 955
|
1227 |
},
|
1228 |
{
|
1229 |
"epoch": 8.38,
|
1230 |
-
"learning_rate": 3.
|
1231 |
-
"loss": 0.
|
1232 |
"step": 960
|
1233 |
},
|
1234 |
{
|
1235 |
"epoch": 8.43,
|
1236 |
-
"learning_rate": 3.
|
1237 |
-
"loss": 0.
|
1238 |
"step": 965
|
1239 |
},
|
1240 |
{
|
1241 |
"epoch": 8.47,
|
1242 |
-
"learning_rate": 3.
|
1243 |
-
"loss": 0.
|
1244 |
"step": 970
|
1245 |
},
|
1246 |
{
|
1247 |
"epoch": 8.52,
|
1248 |
-
"learning_rate": 3.
|
1249 |
-
"loss": 0.
|
1250 |
"step": 975
|
1251 |
},
|
1252 |
{
|
1253 |
"epoch": 8.56,
|
1254 |
-
"learning_rate": 3.
|
1255 |
-
"loss": 0.
|
1256 |
"step": 980
|
1257 |
},
|
1258 |
{
|
1259 |
"epoch": 8.6,
|
1260 |
-
"learning_rate": 3.
|
1261 |
-
"loss": 0.
|
1262 |
"step": 985
|
1263 |
},
|
1264 |
{
|
1265 |
"epoch": 8.65,
|
1266 |
-
"learning_rate":
|
1267 |
-
"loss": 0.
|
1268 |
"step": 990
|
1269 |
},
|
1270 |
{
|
1271 |
"epoch": 8.69,
|
1272 |
-
"learning_rate":
|
1273 |
-
"loss": 0.
|
1274 |
"step": 995
|
1275 |
},
|
1276 |
{
|
1277 |
"epoch": 8.73,
|
1278 |
-
"learning_rate":
|
1279 |
-
"loss": 0.
|
1280 |
"step": 1000
|
1281 |
},
|
1282 |
{
|
1283 |
"epoch": 8.78,
|
1284 |
-
"learning_rate":
|
1285 |
-
"loss": 0.
|
1286 |
"step": 1005
|
1287 |
},
|
1288 |
{
|
1289 |
"epoch": 8.82,
|
1290 |
-
"learning_rate":
|
1291 |
-
"loss": 0.
|
1292 |
"step": 1010
|
1293 |
},
|
1294 |
{
|
1295 |
"epoch": 8.86,
|
1296 |
-
"learning_rate":
|
1297 |
-
"loss": 0.
|
1298 |
"step": 1015
|
1299 |
},
|
1300 |
{
|
1301 |
"epoch": 8.91,
|
1302 |
-
"learning_rate":
|
1303 |
-
"loss": 0.
|
1304 |
"step": 1020
|
1305 |
},
|
1306 |
{
|
1307 |
"epoch": 8.95,
|
1308 |
-
"learning_rate":
|
1309 |
-
"loss": 0.
|
1310 |
"step": 1025
|
1311 |
},
|
1312 |
{
|
1313 |
"epoch": 9.0,
|
1314 |
-
"learning_rate":
|
1315 |
-
"loss": 0.
|
1316 |
"step": 1030
|
1317 |
},
|
1318 |
{
|
1319 |
"epoch": 9.0,
|
1320 |
-
"eval_accuracy": 0.
|
1321 |
-
"eval_loss": 0.
|
1322 |
-
"eval_runtime":
|
1323 |
-
"eval_samples_per_second": 29.
|
1324 |
-
"eval_steps_per_second": 1.
|
1325 |
"step": 1030
|
1326 |
},
|
1327 |
{
|
1328 |
"epoch": 9.04,
|
1329 |
-
"learning_rate":
|
1330 |
-
"loss": 0.
|
1331 |
"step": 1035
|
1332 |
},
|
1333 |
{
|
1334 |
"epoch": 9.08,
|
1335 |
-
"learning_rate":
|
1336 |
-
"loss": 0.
|
1337 |
"step": 1040
|
1338 |
},
|
1339 |
{
|
1340 |
"epoch": 9.13,
|
1341 |
-
"learning_rate":
|
1342 |
-
"loss": 0.
|
1343 |
"step": 1045
|
1344 |
},
|
1345 |
{
|
1346 |
"epoch": 9.17,
|
1347 |
-
"learning_rate":
|
1348 |
-
"loss": 0.
|
1349 |
"step": 1050
|
1350 |
},
|
1351 |
{
|
1352 |
"epoch": 9.21,
|
1353 |
-
"learning_rate":
|
1354 |
-
"loss": 0.
|
1355 |
"step": 1055
|
1356 |
},
|
1357 |
{
|
1358 |
"epoch": 9.26,
|
1359 |
-
"learning_rate":
|
1360 |
-
"loss": 0.
|
1361 |
"step": 1060
|
1362 |
},
|
1363 |
{
|
1364 |
"epoch": 9.3,
|
1365 |
-
"learning_rate":
|
1366 |
-
"loss": 0.
|
1367 |
"step": 1065
|
1368 |
},
|
1369 |
{
|
1370 |
"epoch": 9.34,
|
1371 |
-
"learning_rate":
|
1372 |
-
"loss": 0.
|
1373 |
"step": 1070
|
1374 |
},
|
1375 |
{
|
1376 |
"epoch": 9.39,
|
1377 |
-
"learning_rate":
|
1378 |
-
"loss": 0.
|
1379 |
"step": 1075
|
1380 |
},
|
1381 |
{
|
1382 |
"epoch": 9.43,
|
1383 |
-
"learning_rate":
|
1384 |
-
"loss": 0.
|
1385 |
"step": 1080
|
1386 |
},
|
1387 |
{
|
1388 |
"epoch": 9.48,
|
1389 |
-
"learning_rate":
|
1390 |
-
"loss": 0.
|
1391 |
"step": 1085
|
1392 |
},
|
1393 |
{
|
1394 |
"epoch": 9.52,
|
1395 |
-
"learning_rate":
|
1396 |
-
"loss": 0.
|
1397 |
"step": 1090
|
1398 |
},
|
1399 |
{
|
1400 |
"epoch": 9.56,
|
1401 |
-
"learning_rate":
|
1402 |
-
"loss": 0.
|
1403 |
"step": 1095
|
1404 |
},
|
1405 |
{
|
1406 |
"epoch": 9.61,
|
1407 |
-
"learning_rate":
|
1408 |
-
"loss": 0.
|
1409 |
"step": 1100
|
1410 |
},
|
1411 |
{
|
1412 |
"epoch": 9.65,
|
1413 |
-
"learning_rate":
|
1414 |
-
"loss": 0.
|
1415 |
"step": 1105
|
1416 |
},
|
1417 |
{
|
1418 |
"epoch": 9.69,
|
1419 |
-
"learning_rate":
|
1420 |
-
"loss": 0.
|
1421 |
"step": 1110
|
1422 |
},
|
1423 |
{
|
1424 |
"epoch": 9.74,
|
1425 |
-
"learning_rate":
|
1426 |
-
"loss": 0.
|
1427 |
"step": 1115
|
1428 |
},
|
1429 |
{
|
1430 |
"epoch": 9.78,
|
1431 |
-
"learning_rate":
|
1432 |
-
"loss": 0.
|
1433 |
"step": 1120
|
1434 |
},
|
1435 |
{
|
1436 |
"epoch": 9.83,
|
1437 |
-
"learning_rate":
|
1438 |
-
"loss": 0.
|
1439 |
"step": 1125
|
1440 |
},
|
1441 |
{
|
1442 |
"epoch": 9.87,
|
1443 |
-
"learning_rate":
|
1444 |
-
"loss": 0.
|
1445 |
"step": 1130
|
1446 |
},
|
1447 |
{
|
1448 |
"epoch": 9.91,
|
1449 |
-
"learning_rate":
|
1450 |
-
"loss": 0.
|
1451 |
"step": 1135
|
1452 |
},
|
1453 |
{
|
1454 |
"epoch": 9.96,
|
1455 |
-
"learning_rate":
|
1456 |
-
"loss": 0.
|
1457 |
"step": 1140
|
1458 |
},
|
1459 |
{
|
1460 |
"epoch": 10.0,
|
1461 |
-
"learning_rate":
|
1462 |
-
"loss": 0.
|
1463 |
"step": 1145
|
1464 |
},
|
1465 |
{
|
1466 |
"epoch": 10.0,
|
1467 |
-
"eval_accuracy": 0.
|
1468 |
-
"eval_loss": 0.
|
1469 |
-
"eval_runtime":
|
1470 |
-
"eval_samples_per_second": 29.
|
1471 |
-
"eval_steps_per_second": 1.
|
1472 |
"step": 1145
|
1473 |
},
|
1474 |
{
|
1475 |
"epoch": 10.04,
|
1476 |
-
"learning_rate":
|
1477 |
-
"loss": 0.
|
1478 |
"step": 1150
|
1479 |
},
|
1480 |
{
|
1481 |
"epoch": 10.09,
|
1482 |
-
"learning_rate":
|
1483 |
-
"loss": 0.
|
1484 |
"step": 1155
|
1485 |
},
|
1486 |
{
|
1487 |
"epoch": 10.13,
|
1488 |
-
"learning_rate":
|
1489 |
-
"loss": 0.
|
1490 |
"step": 1160
|
1491 |
},
|
1492 |
{
|
1493 |
"epoch": 10.17,
|
1494 |
-
"learning_rate":
|
1495 |
-
"loss": 0.
|
1496 |
"step": 1165
|
1497 |
},
|
1498 |
{
|
1499 |
"epoch": 10.22,
|
1500 |
-
"learning_rate":
|
1501 |
-
"loss": 0.
|
1502 |
"step": 1170
|
1503 |
},
|
1504 |
{
|
1505 |
"epoch": 10.26,
|
1506 |
-
"learning_rate":
|
1507 |
-
"loss": 0.
|
1508 |
"step": 1175
|
1509 |
},
|
1510 |
{
|
1511 |
"epoch": 10.31,
|
1512 |
-
"learning_rate":
|
1513 |
-
"loss": 0.
|
1514 |
"step": 1180
|
1515 |
},
|
1516 |
{
|
1517 |
"epoch": 10.35,
|
1518 |
-
"learning_rate":
|
1519 |
-
"loss": 0.
|
1520 |
"step": 1185
|
1521 |
},
|
1522 |
{
|
1523 |
"epoch": 10.39,
|
1524 |
-
"learning_rate":
|
1525 |
-
"loss": 0.
|
1526 |
"step": 1190
|
1527 |
},
|
1528 |
{
|
1529 |
"epoch": 10.44,
|
1530 |
-
"learning_rate":
|
1531 |
-
"loss": 0.
|
1532 |
"step": 1195
|
1533 |
},
|
1534 |
{
|
1535 |
"epoch": 10.48,
|
1536 |
-
"learning_rate":
|
1537 |
-
"loss": 0.
|
1538 |
"step": 1200
|
1539 |
},
|
1540 |
{
|
1541 |
"epoch": 10.52,
|
1542 |
-
"learning_rate":
|
1543 |
-
"loss": 0.
|
1544 |
"step": 1205
|
1545 |
},
|
1546 |
{
|
1547 |
"epoch": 10.57,
|
1548 |
-
"learning_rate":
|
1549 |
-
"loss": 0.
|
1550 |
"step": 1210
|
1551 |
},
|
1552 |
{
|
1553 |
"epoch": 10.61,
|
1554 |
-
"learning_rate":
|
1555 |
-
"loss": 0.
|
1556 |
"step": 1215
|
1557 |
},
|
1558 |
{
|
1559 |
"epoch": 10.66,
|
1560 |
-
"learning_rate":
|
1561 |
-
"loss": 0.
|
1562 |
"step": 1220
|
1563 |
},
|
1564 |
{
|
1565 |
"epoch": 10.7,
|
1566 |
-
"learning_rate":
|
1567 |
-
"loss": 0.
|
1568 |
"step": 1225
|
1569 |
},
|
1570 |
{
|
1571 |
"epoch": 10.74,
|
1572 |
-
"learning_rate":
|
1573 |
-
"loss": 0.
|
1574 |
"step": 1230
|
1575 |
},
|
1576 |
{
|
1577 |
"epoch": 10.79,
|
1578 |
-
"learning_rate": 4.
|
1579 |
-
"loss": 0.
|
1580 |
"step": 1235
|
1581 |
},
|
1582 |
{
|
1583 |
"epoch": 10.83,
|
1584 |
-
"learning_rate": 4.
|
1585 |
-
"loss": 0.
|
1586 |
"step": 1240
|
1587 |
},
|
1588 |
{
|
1589 |
"epoch": 10.87,
|
1590 |
-
"learning_rate": 4.
|
1591 |
-
"loss": 0.
|
1592 |
"step": 1245
|
1593 |
},
|
1594 |
{
|
1595 |
"epoch": 10.92,
|
1596 |
-
"learning_rate": 4.
|
1597 |
-
"loss": 0.
|
1598 |
"step": 1250
|
1599 |
},
|
1600 |
{
|
1601 |
"epoch": 10.96,
|
1602 |
-
"learning_rate": 4.
|
1603 |
-
"loss": 0.
|
1604 |
"step": 1255
|
1605 |
},
|
1606 |
{
|
1607 |
"epoch": 11.0,
|
1608 |
-
"eval_accuracy": 0.
|
1609 |
-
"eval_loss": 0.
|
1610 |
-
"eval_runtime":
|
1611 |
-
"eval_samples_per_second": 29.
|
1612 |
-
"eval_steps_per_second": 1.
|
1613 |
"step": 1259
|
1614 |
},
|
1615 |
{
|
1616 |
"epoch": 11.0,
|
1617 |
-
"learning_rate":
|
1618 |
-
"loss": 0.
|
1619 |
"step": 1260
|
1620 |
},
|
1621 |
{
|
1622 |
"epoch": 11.05,
|
1623 |
-
"learning_rate":
|
1624 |
-
"loss": 0.
|
1625 |
"step": 1265
|
1626 |
},
|
1627 |
{
|
1628 |
"epoch": 11.09,
|
1629 |
-
"learning_rate":
|
1630 |
-
"loss": 0.
|
1631 |
"step": 1270
|
1632 |
},
|
1633 |
{
|
1634 |
"epoch": 11.14,
|
1635 |
-
"learning_rate":
|
1636 |
-
"loss": 0.
|
1637 |
"step": 1275
|
1638 |
},
|
1639 |
{
|
1640 |
"epoch": 11.18,
|
1641 |
-
"learning_rate":
|
1642 |
-
"loss": 0.
|
1643 |
"step": 1280
|
1644 |
},
|
1645 |
{
|
1646 |
"epoch": 11.22,
|
1647 |
-
"learning_rate":
|
1648 |
-
"loss": 0.
|
1649 |
"step": 1285
|
1650 |
},
|
1651 |
{
|
1652 |
"epoch": 11.27,
|
1653 |
-
"learning_rate":
|
1654 |
-
"loss": 0.
|
1655 |
"step": 1290
|
1656 |
},
|
1657 |
{
|
1658 |
"epoch": 11.31,
|
1659 |
-
"learning_rate":
|
1660 |
-
"loss": 0.
|
1661 |
"step": 1295
|
1662 |
},
|
1663 |
{
|
1664 |
"epoch": 11.35,
|
1665 |
-
"learning_rate":
|
1666 |
-
"loss": 0.
|
1667 |
"step": 1300
|
1668 |
},
|
1669 |
{
|
1670 |
"epoch": 11.4,
|
1671 |
-
"learning_rate":
|
1672 |
-
"loss": 0.
|
1673 |
"step": 1305
|
1674 |
},
|
1675 |
{
|
1676 |
"epoch": 11.44,
|
1677 |
-
"learning_rate":
|
1678 |
-
"loss": 0.
|
1679 |
"step": 1310
|
1680 |
},
|
1681 |
{
|
1682 |
"epoch": 11.48,
|
1683 |
-
"learning_rate":
|
1684 |
-
"loss": 0.
|
1685 |
"step": 1315
|
1686 |
},
|
1687 |
{
|
1688 |
"epoch": 11.53,
|
1689 |
-
"learning_rate":
|
1690 |
-
"loss": 0.
|
1691 |
"step": 1320
|
1692 |
},
|
1693 |
{
|
1694 |
"epoch": 11.57,
|
1695 |
-
"learning_rate":
|
1696 |
-
"loss": 0.
|
1697 |
"step": 1325
|
1698 |
},
|
1699 |
{
|
1700 |
"epoch": 11.62,
|
1701 |
-
"learning_rate":
|
1702 |
-
"loss": 0.
|
1703 |
"step": 1330
|
1704 |
},
|
1705 |
{
|
1706 |
"epoch": 11.66,
|
1707 |
-
"learning_rate":
|
1708 |
-
"loss": 0.
|
1709 |
"step": 1335
|
1710 |
},
|
1711 |
{
|
1712 |
"epoch": 11.7,
|
1713 |
-
"learning_rate":
|
1714 |
-
"loss": 0.
|
1715 |
"step": 1340
|
1716 |
},
|
1717 |
{
|
1718 |
"epoch": 11.75,
|
1719 |
-
"learning_rate":
|
1720 |
-
"loss": 0.
|
1721 |
"step": 1345
|
1722 |
},
|
1723 |
{
|
1724 |
"epoch": 11.79,
|
1725 |
-
"learning_rate":
|
1726 |
-
"loss": 0.
|
1727 |
"step": 1350
|
1728 |
},
|
1729 |
{
|
1730 |
"epoch": 11.83,
|
1731 |
-
"learning_rate": 4.
|
1732 |
-
"loss": 0.
|
1733 |
"step": 1355
|
1734 |
},
|
1735 |
{
|
1736 |
"epoch": 11.88,
|
1737 |
-
"learning_rate":
|
1738 |
-
"loss": 0.
|
1739 |
"step": 1360
|
1740 |
},
|
1741 |
{
|
1742 |
"epoch": 11.92,
|
1743 |
-
"learning_rate":
|
1744 |
-
"loss": 0.
|
1745 |
"step": 1365
|
1746 |
},
|
1747 |
{
|
1748 |
-
"epoch": 11.
|
1749 |
-
"
|
1750 |
-
"
|
1751 |
-
"
|
1752 |
-
|
1753 |
-
|
1754 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1755 |
},
|
1756 |
{
|
1757 |
-
"epoch":
|
1758 |
-
"step":
|
1759 |
-
"total_flos":
|
1760 |
-
"train_loss": 0.
|
1761 |
-
"train_runtime":
|
1762 |
-
"train_samples_per_second":
|
1763 |
-
"train_steps_per_second": 0.
|
1764 |
}
|
1765 |
],
|
1766 |
-
"max_steps":
|
1767 |
-
"num_train_epochs":
|
1768 |
-
"total_flos":
|
1769 |
"trial_name": null,
|
1770 |
"trial_params": null
|
1771 |
}
|
|
|
1 |
{
|
2 |
+
"best_metric": 0.986863711001642,
|
3 |
+
"best_model_checkpoint": "convnextv2-large-1k-224-finetuned-Lesion-Classification-HAM10000-AH-60-20-20-Shuffled/checkpoint-1710",
|
4 |
+
"epoch": 14.934497816593886,
|
5 |
+
"global_step": 1710,
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
9 |
"log_history": [
|
10 |
{
|
11 |
"epoch": 0.04,
|
12 |
+
"learning_rate": 1.6244314489928526e-07,
|
13 |
+
"loss": 1.9453,
|
14 |
"step": 5
|
15 |
},
|
16 |
{
|
17 |
"epoch": 0.09,
|
18 |
+
"learning_rate": 3.248862897985705e-07,
|
19 |
+
"loss": 1.9411,
|
20 |
"step": 10
|
21 |
},
|
22 |
{
|
23 |
"epoch": 0.13,
|
24 |
+
"learning_rate": 4.873294346978557e-07,
|
25 |
+
"loss": 1.9441,
|
26 |
"step": 15
|
27 |
},
|
28 |
{
|
29 |
"epoch": 0.17,
|
30 |
+
"learning_rate": 6.49772579597141e-07,
|
31 |
+
"loss": 1.9426,
|
32 |
"step": 20
|
33 |
},
|
34 |
{
|
35 |
"epoch": 0.22,
|
36 |
+
"learning_rate": 8.122157244964262e-07,
|
37 |
+
"loss": 1.941,
|
38 |
"step": 25
|
39 |
},
|
40 |
{
|
41 |
"epoch": 0.26,
|
42 |
+
"learning_rate": 9.746588693957115e-07,
|
43 |
+
"loss": 1.9436,
|
44 |
"step": 30
|
45 |
},
|
46 |
{
|
47 |
"epoch": 0.31,
|
48 |
+
"learning_rate": 1.1371020142949968e-06,
|
49 |
+
"loss": 1.9444,
|
50 |
"step": 35
|
51 |
},
|
52 |
{
|
53 |
"epoch": 0.35,
|
54 |
+
"learning_rate": 1.299545159194282e-06,
|
55 |
+
"loss": 1.942,
|
56 |
"step": 40
|
57 |
},
|
58 |
{
|
59 |
"epoch": 0.39,
|
60 |
+
"learning_rate": 1.4619883040935671e-06,
|
61 |
+
"loss": 1.9417,
|
62 |
"step": 45
|
63 |
},
|
64 |
{
|
65 |
"epoch": 0.44,
|
66 |
+
"learning_rate": 1.6244314489928524e-06,
|
67 |
+
"loss": 1.9413,
|
68 |
"step": 50
|
69 |
},
|
70 |
{
|
71 |
"epoch": 0.48,
|
72 |
+
"learning_rate": 1.7868745938921377e-06,
|
73 |
+
"loss": 1.9417,
|
74 |
"step": 55
|
75 |
},
|
76 |
{
|
77 |
"epoch": 0.52,
|
78 |
+
"learning_rate": 1.949317738791423e-06,
|
79 |
+
"loss": 1.9326,
|
80 |
"step": 60
|
81 |
},
|
82 |
{
|
83 |
"epoch": 0.57,
|
84 |
+
"learning_rate": 2.1117608836907083e-06,
|
85 |
+
"loss": 1.9317,
|
86 |
"step": 65
|
87 |
},
|
88 |
{
|
89 |
"epoch": 0.61,
|
90 |
+
"learning_rate": 2.2742040285899936e-06,
|
91 |
"loss": 1.9269,
|
92 |
"step": 70
|
93 |
},
|
94 |
{
|
95 |
"epoch": 0.66,
|
96 |
+
"learning_rate": 2.436647173489279e-06,
|
97 |
+
"loss": 1.9216,
|
98 |
"step": 75
|
99 |
},
|
100 |
{
|
101 |
"epoch": 0.7,
|
102 |
+
"learning_rate": 2.599090318388564e-06,
|
103 |
+
"loss": 1.9201,
|
104 |
"step": 80
|
105 |
},
|
106 |
{
|
107 |
"epoch": 0.74,
|
108 |
+
"learning_rate": 2.7615334632878494e-06,
|
109 |
+
"loss": 1.926,
|
110 |
"step": 85
|
111 |
},
|
112 |
{
|
113 |
"epoch": 0.79,
|
114 |
+
"learning_rate": 2.9239766081871343e-06,
|
115 |
+
"loss": 1.9273,
|
116 |
"step": 90
|
117 |
},
|
118 |
{
|
119 |
"epoch": 0.83,
|
120 |
+
"learning_rate": 3.0864197530864196e-06,
|
121 |
+
"loss": 1.9209,
|
122 |
"step": 95
|
123 |
},
|
124 |
{
|
125 |
"epoch": 0.87,
|
126 |
+
"learning_rate": 3.248862897985705e-06,
|
127 |
+
"loss": 1.9173,
|
128 |
"step": 100
|
129 |
},
|
130 |
{
|
131 |
"epoch": 0.92,
|
132 |
+
"learning_rate": 3.41130604288499e-06,
|
133 |
+
"loss": 1.911,
|
134 |
"step": 105
|
135 |
},
|
136 |
{
|
137 |
"epoch": 0.96,
|
138 |
+
"learning_rate": 3.5737491877842754e-06,
|
139 |
+
"loss": 1.8937,
|
140 |
"step": 110
|
141 |
},
|
142 |
{
|
143 |
"epoch": 1.0,
|
144 |
+
"eval_accuracy": 0.31444991789819376,
|
145 |
+
"eval_loss": 1.904041051864624,
|
146 |
+
"eval_runtime": 616.7304,
|
147 |
+
"eval_samples_per_second": 1.975,
|
148 |
+
"eval_steps_per_second": 0.125,
|
149 |
"step": 114
|
150 |
},
|
151 |
{
|
152 |
"epoch": 1.0,
|
153 |
+
"learning_rate": 3.7361923326835607e-06,
|
154 |
+
"loss": 1.9124,
|
155 |
"step": 115
|
156 |
},
|
157 |
{
|
158 |
"epoch": 1.05,
|
159 |
+
"learning_rate": 3.898635477582846e-06,
|
160 |
+
"loss": 1.8871,
|
161 |
"step": 120
|
162 |
},
|
163 |
{
|
164 |
"epoch": 1.09,
|
165 |
+
"learning_rate": 4.061078622482131e-06,
|
166 |
+
"loss": 1.8914,
|
167 |
"step": 125
|
168 |
},
|
169 |
{
|
170 |
"epoch": 1.14,
|
171 |
+
"learning_rate": 4.2235217673814166e-06,
|
172 |
+
"loss": 1.8914,
|
173 |
"step": 130
|
174 |
},
|
175 |
{
|
176 |
"epoch": 1.18,
|
177 |
+
"learning_rate": 4.3859649122807014e-06,
|
178 |
+
"loss": 1.8827,
|
179 |
"step": 135
|
180 |
},
|
181 |
{
|
182 |
"epoch": 1.22,
|
183 |
+
"learning_rate": 4.548408057179987e-06,
|
184 |
+
"loss": 1.8704,
|
185 |
"step": 140
|
186 |
},
|
187 |
{
|
188 |
"epoch": 1.27,
|
189 |
+
"learning_rate": 4.710851202079272e-06,
|
190 |
+
"loss": 1.8753,
|
191 |
"step": 145
|
192 |
},
|
193 |
{
|
194 |
"epoch": 1.31,
|
195 |
+
"learning_rate": 4.873294346978558e-06,
|
196 |
+
"loss": 1.8738,
|
197 |
"step": 150
|
198 |
},
|
199 |
{
|
200 |
"epoch": 1.35,
|
201 |
+
"learning_rate": 5.0357374918778426e-06,
|
202 |
+
"loss": 1.8556,
|
203 |
"step": 155
|
204 |
},
|
205 |
{
|
206 |
"epoch": 1.4,
|
207 |
+
"learning_rate": 5.198180636777128e-06,
|
208 |
+
"loss": 1.8545,
|
209 |
"step": 160
|
210 |
},
|
211 |
{
|
212 |
"epoch": 1.44,
|
213 |
+
"learning_rate": 5.360623781676413e-06,
|
214 |
+
"loss": 1.8496,
|
215 |
"step": 165
|
216 |
},
|
217 |
{
|
218 |
"epoch": 1.48,
|
219 |
+
"learning_rate": 5.523066926575699e-06,
|
220 |
+
"loss": 1.8479,
|
221 |
"step": 170
|
222 |
},
|
223 |
{
|
224 |
"epoch": 1.53,
|
225 |
+
"learning_rate": 5.685510071474984e-06,
|
226 |
+
"loss": 1.8349,
|
227 |
"step": 175
|
228 |
},
|
229 |
{
|
230 |
"epoch": 1.57,
|
231 |
+
"learning_rate": 5.8479532163742686e-06,
|
232 |
+
"loss": 1.8179,
|
233 |
"step": 180
|
234 |
},
|
235 |
{
|
236 |
"epoch": 1.62,
|
237 |
+
"learning_rate": 6.010396361273554e-06,
|
238 |
+
"loss": 1.8176,
|
239 |
"step": 185
|
240 |
},
|
241 |
{
|
242 |
"epoch": 1.66,
|
243 |
+
"learning_rate": 6.172839506172839e-06,
|
244 |
+
"loss": 1.792,
|
245 |
"step": 190
|
246 |
},
|
247 |
{
|
248 |
"epoch": 1.7,
|
249 |
+
"learning_rate": 6.335282651072125e-06,
|
250 |
+
"loss": 1.7878,
|
251 |
"step": 195
|
252 |
},
|
253 |
{
|
254 |
"epoch": 1.75,
|
255 |
+
"learning_rate": 6.49772579597141e-06,
|
256 |
+
"loss": 1.7465,
|
257 |
"step": 200
|
258 |
},
|
259 |
{
|
260 |
"epoch": 1.79,
|
261 |
+
"learning_rate": 6.660168940870695e-06,
|
262 |
+
"loss": 1.7532,
|
263 |
"step": 205
|
264 |
},
|
265 |
{
|
266 |
"epoch": 1.83,
|
267 |
+
"learning_rate": 6.82261208576998e-06,
|
268 |
+
"loss": 1.745,
|
269 |
"step": 210
|
270 |
},
|
271 |
{
|
272 |
"epoch": 1.88,
|
273 |
+
"learning_rate": 6.985055230669266e-06,
|
274 |
+
"loss": 1.7252,
|
275 |
"step": 215
|
276 |
},
|
277 |
{
|
278 |
"epoch": 1.92,
|
279 |
+
"learning_rate": 7.147498375568551e-06,
|
280 |
+
"loss": 1.7058,
|
281 |
"step": 220
|
282 |
},
|
283 |
{
|
284 |
"epoch": 1.97,
|
285 |
+
"learning_rate": 7.3099415204678366e-06,
|
286 |
+
"loss": 1.7208,
|
287 |
"step": 225
|
288 |
},
|
289 |
{
|
290 |
"epoch": 2.0,
|
291 |
+
"eval_accuracy": 0.5632183908045977,
|
292 |
+
"eval_loss": 1.6890546083450317,
|
293 |
+
"eval_runtime": 40.5734,
|
294 |
+
"eval_samples_per_second": 30.02,
|
295 |
+
"eval_steps_per_second": 1.898,
|
296 |
"step": 229
|
297 |
},
|
298 |
{
|
299 |
"epoch": 2.01,
|
300 |
+
"learning_rate": 7.4723846653671214e-06,
|
301 |
+
"loss": 1.6461,
|
302 |
"step": 230
|
303 |
},
|
304 |
{
|
305 |
"epoch": 2.05,
|
306 |
+
"learning_rate": 7.634827810266407e-06,
|
307 |
+
"loss": 1.6444,
|
308 |
"step": 235
|
309 |
},
|
310 |
{
|
311 |
"epoch": 2.1,
|
312 |
+
"learning_rate": 7.797270955165692e-06,
|
313 |
+
"loss": 1.6875,
|
314 |
"step": 240
|
315 |
},
|
316 |
{
|
317 |
"epoch": 2.14,
|
318 |
+
"learning_rate": 7.959714100064977e-06,
|
319 |
+
"loss": 1.6254,
|
320 |
"step": 245
|
321 |
},
|
322 |
{
|
323 |
"epoch": 2.18,
|
324 |
+
"learning_rate": 8.122157244964262e-06,
|
325 |
+
"loss": 1.6179,
|
326 |
"step": 250
|
327 |
},
|
328 |
{
|
329 |
"epoch": 2.23,
|
330 |
+
"learning_rate": 8.284600389863548e-06,
|
331 |
+
"loss": 1.5889,
|
332 |
"step": 255
|
333 |
},
|
334 |
{
|
335 |
"epoch": 2.27,
|
336 |
+
"learning_rate": 8.447043534762833e-06,
|
337 |
+
"loss": 1.6202,
|
338 |
"step": 260
|
339 |
},
|
340 |
{
|
341 |
"epoch": 2.31,
|
342 |
+
"learning_rate": 8.609486679662118e-06,
|
343 |
+
"loss": 1.5886,
|
344 |
"step": 265
|
345 |
},
|
346 |
{
|
347 |
"epoch": 2.36,
|
348 |
+
"learning_rate": 8.771929824561403e-06,
|
349 |
+
"loss": 1.5682,
|
350 |
"step": 270
|
351 |
},
|
352 |
{
|
353 |
"epoch": 2.4,
|
354 |
+
"learning_rate": 8.93437296946069e-06,
|
355 |
+
"loss": 1.5373,
|
356 |
"step": 275
|
357 |
},
|
358 |
{
|
359 |
"epoch": 2.45,
|
360 |
+
"learning_rate": 9.096816114359974e-06,
|
361 |
+
"loss": 1.5263,
|
362 |
"step": 280
|
363 |
},
|
364 |
{
|
365 |
"epoch": 2.49,
|
366 |
+
"learning_rate": 9.259259259259259e-06,
|
367 |
+
"loss": 1.5475,
|
368 |
"step": 285
|
369 |
},
|
370 |
{
|
371 |
"epoch": 2.53,
|
372 |
+
"learning_rate": 9.421702404158544e-06,
|
373 |
+
"loss": 1.505,
|
374 |
"step": 290
|
375 |
},
|
376 |
{
|
377 |
"epoch": 2.58,
|
378 |
+
"learning_rate": 9.584145549057829e-06,
|
379 |
+
"loss": 1.5201,
|
380 |
"step": 295
|
381 |
},
|
382 |
{
|
383 |
"epoch": 2.62,
|
384 |
+
"learning_rate": 9.746588693957115e-06,
|
385 |
+
"loss": 1.5083,
|
386 |
"step": 300
|
387 |
},
|
388 |
{
|
389 |
"epoch": 2.66,
|
390 |
+
"learning_rate": 9.9090318388564e-06,
|
391 |
+
"loss": 1.4397,
|
392 |
"step": 305
|
393 |
},
|
394 |
{
|
395 |
"epoch": 2.71,
|
396 |
+
"learning_rate": 1.0071474983755685e-05,
|
397 |
+
"loss": 1.4664,
|
398 |
"step": 310
|
399 |
},
|
400 |
{
|
401 |
"epoch": 2.75,
|
402 |
+
"learning_rate": 1.023391812865497e-05,
|
403 |
+
"loss": 1.5037,
|
404 |
"step": 315
|
405 |
},
|
406 |
{
|
407 |
"epoch": 2.79,
|
408 |
+
"learning_rate": 1.0396361273554257e-05,
|
409 |
+
"loss": 1.4622,
|
410 |
"step": 320
|
411 |
},
|
412 |
{
|
413 |
"epoch": 2.84,
|
414 |
+
"learning_rate": 1.0558804418453541e-05,
|
415 |
+
"loss": 1.4399,
|
416 |
"step": 325
|
417 |
},
|
418 |
{
|
419 |
"epoch": 2.88,
|
420 |
+
"learning_rate": 1.0721247563352826e-05,
|
421 |
+
"loss": 1.4542,
|
422 |
"step": 330
|
423 |
},
|
424 |
{
|
425 |
"epoch": 2.93,
|
426 |
+
"learning_rate": 1.0883690708252111e-05,
|
427 |
+
"loss": 1.3944,
|
428 |
"step": 335
|
429 |
},
|
430 |
{
|
431 |
"epoch": 2.97,
|
432 |
+
"learning_rate": 1.1046133853151398e-05,
|
433 |
+
"loss": 1.3822,
|
434 |
"step": 340
|
435 |
},
|
436 |
{
|
437 |
"epoch": 3.0,
|
438 |
+
"eval_accuracy": 0.6896551724137931,
|
439 |
+
"eval_loss": 1.3553680181503296,
|
440 |
+
"eval_runtime": 40.9111,
|
441 |
+
"eval_samples_per_second": 29.772,
|
442 |
+
"eval_steps_per_second": 1.882,
|
443 |
"step": 343
|
444 |
},
|
445 |
{
|
446 |
"epoch": 3.01,
|
447 |
+
"learning_rate": 1.1208576998050683e-05,
|
448 |
+
"loss": 1.4175,
|
449 |
"step": 345
|
450 |
},
|
451 |
{
|
452 |
"epoch": 3.06,
|
453 |
+
"learning_rate": 1.1371020142949967e-05,
|
454 |
+
"loss": 1.3444,
|
455 |
"step": 350
|
456 |
},
|
457 |
{
|
458 |
"epoch": 3.1,
|
459 |
+
"learning_rate": 1.1533463287849252e-05,
|
460 |
+
"loss": 1.3079,
|
461 |
"step": 355
|
462 |
},
|
463 |
{
|
464 |
"epoch": 3.14,
|
465 |
+
"learning_rate": 1.1695906432748537e-05,
|
466 |
+
"loss": 1.3218,
|
467 |
"step": 360
|
468 |
},
|
469 |
{
|
470 |
"epoch": 3.19,
|
471 |
+
"learning_rate": 1.1858349577647824e-05,
|
472 |
+
"loss": 1.4138,
|
473 |
"step": 365
|
474 |
},
|
475 |
{
|
476 |
"epoch": 3.23,
|
477 |
+
"learning_rate": 1.2020792722547109e-05,
|
478 |
+
"loss": 1.2797,
|
479 |
"step": 370
|
480 |
},
|
481 |
{
|
482 |
"epoch": 3.28,
|
483 |
+
"learning_rate": 1.2183235867446393e-05,
|
484 |
+
"loss": 1.2803,
|
485 |
"step": 375
|
486 |
},
|
487 |
{
|
488 |
"epoch": 3.32,
|
489 |
+
"learning_rate": 1.2345679012345678e-05,
|
490 |
+
"loss": 1.2611,
|
491 |
"step": 380
|
492 |
},
|
493 |
{
|
494 |
"epoch": 3.36,
|
495 |
+
"learning_rate": 1.2508122157244965e-05,
|
496 |
+
"loss": 1.2967,
|
497 |
"step": 385
|
498 |
},
|
499 |
{
|
500 |
"epoch": 3.41,
|
501 |
+
"learning_rate": 1.267056530214425e-05,
|
502 |
+
"loss": 1.2756,
|
503 |
"step": 390
|
504 |
},
|
505 |
{
|
506 |
"epoch": 3.45,
|
507 |
+
"learning_rate": 1.2833008447043535e-05,
|
508 |
+
"loss": 1.2863,
|
509 |
"step": 395
|
510 |
},
|
511 |
{
|
512 |
"epoch": 3.49,
|
513 |
+
"learning_rate": 1.299545159194282e-05,
|
514 |
+
"loss": 1.2217,
|
515 |
"step": 400
|
516 |
},
|
517 |
{
|
518 |
"epoch": 3.54,
|
519 |
+
"learning_rate": 1.3157894736842106e-05,
|
520 |
+
"loss": 1.2313,
|
521 |
"step": 405
|
522 |
},
|
523 |
{
|
524 |
"epoch": 3.58,
|
525 |
+
"learning_rate": 1.332033788174139e-05,
|
526 |
+
"loss": 1.159,
|
527 |
"step": 410
|
528 |
},
|
529 |
{
|
530 |
"epoch": 3.62,
|
531 |
+
"learning_rate": 1.3482781026640676e-05,
|
532 |
+
"loss": 1.1975,
|
533 |
"step": 415
|
534 |
},
|
535 |
{
|
536 |
"epoch": 3.67,
|
537 |
+
"learning_rate": 1.364522417153996e-05,
|
538 |
+
"loss": 1.1318,
|
539 |
"step": 420
|
540 |
},
|
541 |
{
|
542 |
"epoch": 3.71,
|
543 |
+
"learning_rate": 1.3807667316439245e-05,
|
544 |
+
"loss": 1.2315,
|
545 |
"step": 425
|
546 |
},
|
547 |
{
|
548 |
"epoch": 3.76,
|
549 |
+
"learning_rate": 1.3970110461338532e-05,
|
550 |
+
"loss": 1.1827,
|
551 |
"step": 430
|
552 |
},
|
553 |
{
|
554 |
"epoch": 3.8,
|
555 |
+
"learning_rate": 1.4132553606237817e-05,
|
556 |
+
"loss": 1.1353,
|
557 |
"step": 435
|
558 |
},
|
559 |
{
|
560 |
"epoch": 3.84,
|
561 |
+
"learning_rate": 1.4294996751137102e-05,
|
562 |
+
"loss": 1.1391,
|
563 |
"step": 440
|
564 |
},
|
565 |
{
|
566 |
"epoch": 3.89,
|
567 |
+
"learning_rate": 1.4457439896036387e-05,
|
568 |
+
"loss": 1.1578,
|
569 |
"step": 445
|
570 |
},
|
571 |
{
|
572 |
"epoch": 3.93,
|
573 |
+
"learning_rate": 1.4619883040935673e-05,
|
574 |
+
"loss": 1.0354,
|
575 |
"step": 450
|
576 |
},
|
577 |
{
|
578 |
"epoch": 3.97,
|
579 |
+
"learning_rate": 1.4782326185834958e-05,
|
580 |
+
"loss": 1.1497,
|
581 |
"step": 455
|
582 |
},
|
583 |
{
|
584 |
"epoch": 4.0,
|
585 |
+
"eval_accuracy": 0.5755336617405583,
|
586 |
+
"eval_loss": 1.2437011003494263,
|
587 |
+
"eval_runtime": 40.5859,
|
588 |
+
"eval_samples_per_second": 30.01,
|
589 |
+
"eval_steps_per_second": 1.897,
|
590 |
"step": 458
|
591 |
},
|
592 |
{
|
593 |
"epoch": 4.02,
|
594 |
+
"learning_rate": 1.4944769330734243e-05,
|
595 |
+
"loss": 1.1786,
|
596 |
"step": 460
|
597 |
},
|
598 |
{
|
599 |
"epoch": 4.06,
|
600 |
+
"learning_rate": 1.5107212475633528e-05,
|
601 |
+
"loss": 1.1497,
|
602 |
"step": 465
|
603 |
},
|
604 |
{
|
605 |
"epoch": 4.1,
|
606 |
+
"learning_rate": 1.5269655620532814e-05,
|
607 |
+
"loss": 0.97,
|
608 |
"step": 470
|
609 |
},
|
610 |
{
|
611 |
"epoch": 4.15,
|
612 |
+
"learning_rate": 1.54320987654321e-05,
|
613 |
+
"loss": 1.0531,
|
614 |
"step": 475
|
615 |
},
|
616 |
{
|
617 |
"epoch": 4.19,
|
618 |
+
"learning_rate": 1.5594541910331384e-05,
|
619 |
+
"loss": 1.0656,
|
620 |
"step": 480
|
621 |
},
|
622 |
{
|
623 |
"epoch": 4.24,
|
624 |
+
"learning_rate": 1.575698505523067e-05,
|
625 |
+
"loss": 1.0906,
|
626 |
"step": 485
|
627 |
},
|
628 |
{
|
629 |
"epoch": 4.28,
|
630 |
+
"learning_rate": 1.5919428200129954e-05,
|
631 |
+
"loss": 1.055,
|
632 |
"step": 490
|
633 |
},
|
634 |
{
|
635 |
"epoch": 4.32,
|
636 |
+
"learning_rate": 1.608187134502924e-05,
|
637 |
+
"loss": 0.9732,
|
638 |
"step": 495
|
639 |
},
|
640 |
{
|
641 |
"epoch": 4.37,
|
642 |
+
"learning_rate": 1.6244314489928523e-05,
|
643 |
+
"loss": 0.9716,
|
644 |
"step": 500
|
645 |
},
|
646 |
{
|
647 |
"epoch": 4.41,
|
648 |
+
"learning_rate": 1.640675763482781e-05,
|
649 |
+
"loss": 0.9626,
|
650 |
"step": 505
|
651 |
},
|
652 |
{
|
653 |
"epoch": 4.45,
|
654 |
+
"learning_rate": 1.6569200779727097e-05,
|
655 |
+
"loss": 1.0368,
|
656 |
"step": 510
|
657 |
},
|
658 |
{
|
659 |
"epoch": 4.5,
|
660 |
+
"learning_rate": 1.673164392462638e-05,
|
661 |
+
"loss": 1.0035,
|
662 |
"step": 515
|
663 |
},
|
664 |
{
|
665 |
"epoch": 4.54,
|
666 |
+
"learning_rate": 1.6894087069525666e-05,
|
667 |
+
"loss": 1.0017,
|
668 |
"step": 520
|
669 |
},
|
670 |
{
|
671 |
"epoch": 4.59,
|
672 |
+
"learning_rate": 1.705653021442495e-05,
|
673 |
+
"loss": 1.0096,
|
674 |
"step": 525
|
675 |
},
|
676 |
{
|
677 |
"epoch": 4.63,
|
678 |
+
"learning_rate": 1.7218973359324236e-05,
|
679 |
+
"loss": 0.9619,
|
680 |
"step": 530
|
681 |
},
|
682 |
{
|
683 |
"epoch": 4.67,
|
684 |
+
"learning_rate": 1.738141650422352e-05,
|
685 |
+
"loss": 1.0007,
|
686 |
"step": 535
|
687 |
},
|
688 |
{
|
689 |
"epoch": 4.72,
|
690 |
+
"learning_rate": 1.7543859649122806e-05,
|
691 |
+
"loss": 1.011,
|
692 |
"step": 540
|
693 |
},
|
694 |
{
|
695 |
"epoch": 4.76,
|
696 |
+
"learning_rate": 1.770630279402209e-05,
|
697 |
+
"loss": 0.9446,
|
698 |
"step": 545
|
699 |
},
|
700 |
{
|
701 |
"epoch": 4.8,
|
702 |
+
"learning_rate": 1.786874593892138e-05,
|
703 |
+
"loss": 0.9822,
|
704 |
"step": 550
|
705 |
},
|
706 |
{
|
707 |
"epoch": 4.85,
|
708 |
+
"learning_rate": 1.8031189083820664e-05,
|
709 |
+
"loss": 0.893,
|
710 |
"step": 555
|
711 |
},
|
712 |
{
|
713 |
"epoch": 4.89,
|
714 |
+
"learning_rate": 1.819363222871995e-05,
|
715 |
+
"loss": 0.9674,
|
716 |
"step": 560
|
717 |
},
|
718 |
{
|
719 |
"epoch": 4.93,
|
720 |
+
"learning_rate": 1.8356075373619233e-05,
|
721 |
+
"loss": 0.9752,
|
722 |
"step": 565
|
723 |
},
|
724 |
{
|
725 |
"epoch": 4.98,
|
726 |
+
"learning_rate": 1.8518518518518518e-05,
|
727 |
+
"loss": 0.8979,
|
728 |
"step": 570
|
729 |
},
|
730 |
{
|
731 |
"epoch": 5.0,
|
732 |
+
"eval_accuracy": 0.7701149425287356,
|
733 |
+
"eval_loss": 0.8547766208648682,
|
734 |
+
"eval_runtime": 40.6835,
|
735 |
+
"eval_samples_per_second": 29.938,
|
736 |
+
"eval_steps_per_second": 1.893,
|
737 |
"step": 572
|
738 |
},
|
739 |
{
|
740 |
"epoch": 5.02,
|
741 |
+
"learning_rate": 1.8680961663417803e-05,
|
742 |
+
"loss": 0.8804,
|
743 |
"step": 575
|
744 |
},
|
745 |
{
|
746 |
"epoch": 5.07,
|
747 |
+
"learning_rate": 1.8843404808317088e-05,
|
748 |
+
"loss": 0.8632,
|
749 |
"step": 580
|
750 |
},
|
751 |
{
|
752 |
"epoch": 5.11,
|
753 |
+
"learning_rate": 1.9005847953216373e-05,
|
754 |
+
"loss": 0.8972,
|
755 |
"step": 585
|
756 |
},
|
757 |
{
|
758 |
"epoch": 5.15,
|
759 |
+
"learning_rate": 1.9168291098115658e-05,
|
760 |
+
"loss": 0.9237,
|
761 |
"step": 590
|
762 |
},
|
763 |
{
|
764 |
"epoch": 5.2,
|
765 |
+
"learning_rate": 1.9330734243014946e-05,
|
766 |
+
"loss": 0.8721,
|
767 |
"step": 595
|
768 |
},
|
769 |
{
|
770 |
"epoch": 5.24,
|
771 |
+
"learning_rate": 1.949317738791423e-05,
|
772 |
+
"loss": 0.877,
|
773 |
"step": 600
|
774 |
},
|
775 |
{
|
776 |
"epoch": 5.28,
|
777 |
+
"learning_rate": 1.9655620532813516e-05,
|
778 |
+
"loss": 0.7675,
|
779 |
"step": 605
|
780 |
},
|
781 |
{
|
782 |
"epoch": 5.33,
|
783 |
+
"learning_rate": 1.98180636777128e-05,
|
784 |
+
"loss": 0.8211,
|
785 |
"step": 610
|
786 |
},
|
787 |
{
|
788 |
"epoch": 5.37,
|
789 |
+
"learning_rate": 1.9980506822612085e-05,
|
790 |
+
"loss": 0.8718,
|
791 |
"step": 615
|
792 |
},
|
793 |
{
|
794 |
"epoch": 5.41,
|
795 |
+
"learning_rate": 2.014294996751137e-05,
|
796 |
+
"loss": 0.8683,
|
797 |
"step": 620
|
798 |
},
|
799 |
{
|
800 |
"epoch": 5.46,
|
801 |
+
"learning_rate": 2.0305393112410655e-05,
|
802 |
+
"loss": 0.8462,
|
803 |
"step": 625
|
804 |
},
|
805 |
{
|
806 |
"epoch": 5.5,
|
807 |
+
"learning_rate": 2.046783625730994e-05,
|
808 |
+
"loss": 0.7876,
|
809 |
"step": 630
|
810 |
},
|
811 |
{
|
812 |
"epoch": 5.55,
|
813 |
+
"learning_rate": 2.0630279402209228e-05,
|
814 |
+
"loss": 0.7767,
|
815 |
"step": 635
|
816 |
},
|
817 |
{
|
818 |
"epoch": 5.59,
|
819 |
+
"learning_rate": 2.0792722547108513e-05,
|
820 |
+
"loss": 0.807,
|
821 |
"step": 640
|
822 |
},
|
823 |
{
|
824 |
"epoch": 5.63,
|
825 |
+
"learning_rate": 2.0955165692007798e-05,
|
826 |
+
"loss": 0.8431,
|
827 |
"step": 645
|
828 |
},
|
829 |
{
|
830 |
"epoch": 5.68,
|
831 |
+
"learning_rate": 2.1117608836907083e-05,
|
832 |
+
"loss": 0.8107,
|
833 |
"step": 650
|
834 |
},
|
835 |
{
|
836 |
"epoch": 5.72,
|
837 |
+
"learning_rate": 2.1280051981806368e-05,
|
838 |
+
"loss": 0.7945,
|
839 |
"step": 655
|
840 |
},
|
841 |
{
|
842 |
"epoch": 5.76,
|
843 |
+
"learning_rate": 2.1442495126705653e-05,
|
844 |
+
"loss": 0.8266,
|
845 |
"step": 660
|
846 |
},
|
847 |
{
|
848 |
"epoch": 5.81,
|
849 |
+
"learning_rate": 2.1604938271604937e-05,
|
850 |
+
"loss": 0.6723,
|
851 |
"step": 665
|
852 |
},
|
853 |
{
|
854 |
"epoch": 5.85,
|
855 |
+
"learning_rate": 2.1767381416504222e-05,
|
856 |
+
"loss": 0.7881,
|
857 |
"step": 670
|
858 |
},
|
859 |
{
|
860 |
"epoch": 5.9,
|
861 |
+
"learning_rate": 2.1929824561403507e-05,
|
862 |
+
"loss": 0.7899,
|
863 |
"step": 675
|
864 |
},
|
865 |
{
|
866 |
"epoch": 5.94,
|
867 |
+
"learning_rate": 2.2092267706302795e-05,
|
868 |
+
"loss": 0.7952,
|
869 |
"step": 680
|
870 |
},
|
871 |
{
|
872 |
"epoch": 5.98,
|
873 |
+
"learning_rate": 2.225471085120208e-05,
|
874 |
+
"loss": 0.6382,
|
875 |
"step": 685
|
876 |
},
|
877 |
{
|
878 |
"epoch": 6.0,
|
879 |
+
"eval_accuracy": 0.8423645320197044,
|
880 |
+
"eval_loss": 0.635892391204834,
|
881 |
+
"eval_runtime": 40.9628,
|
882 |
+
"eval_samples_per_second": 29.734,
|
883 |
+
"eval_steps_per_second": 1.88,
|
884 |
"step": 687
|
885 |
},
|
886 |
{
|
887 |
"epoch": 6.03,
|
888 |
+
"learning_rate": 2.2417153996101365e-05,
|
889 |
+
"loss": 0.6826,
|
890 |
"step": 690
|
891 |
},
|
892 |
{
|
893 |
"epoch": 6.07,
|
894 |
+
"learning_rate": 2.257959714100065e-05,
|
895 |
+
"loss": 0.7219,
|
896 |
"step": 695
|
897 |
},
|
898 |
{
|
899 |
"epoch": 6.11,
|
900 |
+
"learning_rate": 2.2742040285899935e-05,
|
901 |
+
"loss": 0.6355,
|
902 |
"step": 700
|
903 |
},
|
904 |
{
|
905 |
"epoch": 6.16,
|
906 |
+
"learning_rate": 2.290448343079922e-05,
|
907 |
+
"loss": 0.7145,
|
908 |
"step": 705
|
909 |
},
|
910 |
{
|
911 |
"epoch": 6.2,
|
912 |
+
"learning_rate": 2.3066926575698505e-05,
|
913 |
+
"loss": 0.776,
|
914 |
"step": 710
|
915 |
},
|
916 |
{
|
917 |
"epoch": 6.24,
|
918 |
+
"learning_rate": 2.322936972059779e-05,
|
919 |
+
"loss": 0.7932,
|
920 |
"step": 715
|
921 |
},
|
922 |
{
|
923 |
"epoch": 6.29,
|
924 |
+
"learning_rate": 2.3391812865497074e-05,
|
925 |
+
"loss": 0.7708,
|
926 |
"step": 720
|
927 |
},
|
928 |
{
|
929 |
"epoch": 6.33,
|
930 |
+
"learning_rate": 2.3554256010396363e-05,
|
931 |
+
"loss": 1.0012,
|
932 |
"step": 725
|
933 |
},
|
934 |
{
|
935 |
"epoch": 6.38,
|
936 |
+
"learning_rate": 2.3716699155295647e-05,
|
937 |
+
"loss": 0.877,
|
938 |
"step": 730
|
939 |
},
|
940 |
{
|
941 |
"epoch": 6.42,
|
942 |
+
"learning_rate": 2.3879142300194932e-05,
|
943 |
+
"loss": 0.853,
|
944 |
"step": 735
|
945 |
},
|
946 |
{
|
947 |
"epoch": 6.46,
|
948 |
+
"learning_rate": 2.4041585445094217e-05,
|
949 |
+
"loss": 0.7479,
|
950 |
"step": 740
|
951 |
},
|
952 |
{
|
953 |
"epoch": 6.51,
|
954 |
+
"learning_rate": 2.4204028589993502e-05,
|
955 |
+
"loss": 0.7461,
|
956 |
"step": 745
|
957 |
},
|
958 |
{
|
959 |
"epoch": 6.55,
|
960 |
+
"learning_rate": 2.4366471734892787e-05,
|
961 |
+
"loss": 0.69,
|
962 |
"step": 750
|
963 |
},
|
964 |
{
|
965 |
"epoch": 6.59,
|
966 |
+
"learning_rate": 2.4528914879792072e-05,
|
967 |
+
"loss": 0.7074,
|
968 |
"step": 755
|
969 |
},
|
970 |
{
|
971 |
"epoch": 6.64,
|
972 |
+
"learning_rate": 2.4691358024691357e-05,
|
973 |
+
"loss": 0.8053,
|
974 |
"step": 760
|
975 |
},
|
976 |
{
|
977 |
"epoch": 6.68,
|
978 |
+
"learning_rate": 2.485380116959064e-05,
|
979 |
+
"loss": 0.7961,
|
980 |
"step": 765
|
981 |
},
|
982 |
{
|
983 |
"epoch": 6.72,
|
984 |
+
"learning_rate": 2.501624431448993e-05,
|
985 |
+
"loss": 0.5924,
|
986 |
"step": 770
|
987 |
},
|
988 |
{
|
989 |
"epoch": 6.77,
|
990 |
+
"learning_rate": 2.5178687459389218e-05,
|
991 |
+
"loss": 0.7107,
|
992 |
"step": 775
|
993 |
},
|
994 |
{
|
995 |
"epoch": 6.81,
|
996 |
+
"learning_rate": 2.53411306042885e-05,
|
997 |
+
"loss": 0.6898,
|
998 |
"step": 780
|
999 |
},
|
1000 |
{
|
1001 |
"epoch": 6.86,
|
1002 |
+
"learning_rate": 2.5503573749187788e-05,
|
1003 |
+
"loss": 0.4885,
|
1004 |
"step": 785
|
1005 |
},
|
1006 |
{
|
1007 |
"epoch": 6.9,
|
1008 |
+
"learning_rate": 2.566601689408707e-05,
|
1009 |
+
"loss": 0.506,
|
1010 |
"step": 790
|
1011 |
},
|
1012 |
{
|
1013 |
"epoch": 6.94,
|
1014 |
+
"learning_rate": 2.5828460038986357e-05,
|
1015 |
+
"loss": 0.62,
|
1016 |
"step": 795
|
1017 |
},
|
1018 |
{
|
1019 |
"epoch": 6.99,
|
1020 |
+
"learning_rate": 2.599090318388564e-05,
|
1021 |
+
"loss": 0.583,
|
1022 |
"step": 800
|
1023 |
},
|
1024 |
{
|
1025 |
"epoch": 7.0,
|
1026 |
+
"eval_accuracy": 0.896551724137931,
|
1027 |
+
"eval_loss": 0.4686902165412903,
|
1028 |
+
"eval_runtime": 40.488,
|
1029 |
+
"eval_samples_per_second": 30.083,
|
1030 |
+
"eval_steps_per_second": 1.902,
|
1031 |
"step": 801
|
1032 |
},
|
1033 |
{
|
1034 |
"epoch": 7.03,
|
1035 |
+
"learning_rate": 2.6153346328784927e-05,
|
1036 |
+
"loss": 0.4595,
|
1037 |
"step": 805
|
1038 |
},
|
1039 |
{
|
1040 |
"epoch": 7.07,
|
1041 |
+
"learning_rate": 2.6315789473684212e-05,
|
1042 |
+
"loss": 0.7041,
|
1043 |
"step": 810
|
1044 |
},
|
1045 |
{
|
1046 |
"epoch": 7.12,
|
1047 |
+
"learning_rate": 2.6478232618583497e-05,
|
1048 |
+
"loss": 0.6583,
|
1049 |
"step": 815
|
1050 |
},
|
1051 |
{
|
1052 |
"epoch": 7.16,
|
1053 |
+
"learning_rate": 2.664067576348278e-05,
|
1054 |
+
"loss": 0.5882,
|
1055 |
"step": 820
|
1056 |
},
|
1057 |
{
|
1058 |
"epoch": 7.21,
|
1059 |
+
"learning_rate": 2.680311890838207e-05,
|
1060 |
+
"loss": 0.6583,
|
1061 |
"step": 825
|
1062 |
},
|
1063 |
{
|
1064 |
"epoch": 7.25,
|
1065 |
+
"learning_rate": 2.696556205328135e-05,
|
1066 |
+
"loss": 0.5782,
|
1067 |
"step": 830
|
1068 |
},
|
1069 |
{
|
1070 |
"epoch": 7.29,
|
1071 |
+
"learning_rate": 2.712800519818064e-05,
|
1072 |
+
"loss": 0.6136,
|
1073 |
"step": 835
|
1074 |
},
|
1075 |
{
|
1076 |
"epoch": 7.34,
|
1077 |
+
"learning_rate": 2.729044834307992e-05,
|
1078 |
+
"loss": 0.5521,
|
1079 |
"step": 840
|
1080 |
},
|
1081 |
{
|
1082 |
"epoch": 7.38,
|
1083 |
+
"learning_rate": 2.745289148797921e-05,
|
1084 |
+
"loss": 0.5885,
|
1085 |
"step": 845
|
1086 |
},
|
1087 |
{
|
1088 |
"epoch": 7.42,
|
1089 |
+
"learning_rate": 2.761533463287849e-05,
|
1090 |
+
"loss": 0.6475,
|
1091 |
"step": 850
|
1092 |
},
|
1093 |
{
|
1094 |
"epoch": 7.47,
|
1095 |
+
"learning_rate": 2.777777777777778e-05,
|
1096 |
+
"loss": 0.5424,
|
1097 |
"step": 855
|
1098 |
},
|
1099 |
{
|
1100 |
"epoch": 7.51,
|
1101 |
+
"learning_rate": 2.7940220922677064e-05,
|
1102 |
+
"loss": 0.5995,
|
1103 |
"step": 860
|
1104 |
},
|
1105 |
{
|
1106 |
"epoch": 7.55,
|
1107 |
+
"learning_rate": 2.8102664067576352e-05,
|
1108 |
+
"loss": 0.4372,
|
1109 |
"step": 865
|
1110 |
},
|
1111 |
{
|
1112 |
"epoch": 7.6,
|
1113 |
+
"learning_rate": 2.8265107212475634e-05,
|
1114 |
+
"loss": 0.6169,
|
1115 |
"step": 870
|
1116 |
},
|
1117 |
{
|
1118 |
"epoch": 7.64,
|
1119 |
+
"learning_rate": 2.8427550357374922e-05,
|
1120 |
+
"loss": 0.7263,
|
1121 |
"step": 875
|
1122 |
},
|
1123 |
{
|
1124 |
"epoch": 7.69,
|
1125 |
+
"learning_rate": 2.8589993502274203e-05,
|
1126 |
+
"loss": 0.5229,
|
1127 |
"step": 880
|
1128 |
},
|
1129 |
{
|
1130 |
"epoch": 7.73,
|
1131 |
+
"learning_rate": 2.875243664717349e-05,
|
1132 |
+
"loss": 0.5604,
|
1133 |
"step": 885
|
1134 |
},
|
1135 |
{
|
1136 |
"epoch": 7.77,
|
1137 |
+
"learning_rate": 2.8914879792072773e-05,
|
1138 |
+
"loss": 0.649,
|
1139 |
"step": 890
|
1140 |
},
|
1141 |
{
|
1142 |
"epoch": 7.82,
|
1143 |
+
"learning_rate": 2.907732293697206e-05,
|
1144 |
+
"loss": 0.5875,
|
1145 |
"step": 895
|
1146 |
},
|
1147 |
{
|
1148 |
"epoch": 7.86,
|
1149 |
+
"learning_rate": 2.9239766081871346e-05,
|
1150 |
+
"loss": 0.6519,
|
1151 |
"step": 900
|
1152 |
},
|
1153 |
{
|
1154 |
"epoch": 7.9,
|
1155 |
+
"learning_rate": 2.9402209226770635e-05,
|
1156 |
+
"loss": 0.4926,
|
1157 |
"step": 905
|
1158 |
},
|
1159 |
{
|
1160 |
"epoch": 7.95,
|
1161 |
+
"learning_rate": 2.9564652371669916e-05,
|
1162 |
+
"loss": 0.5014,
|
1163 |
"step": 910
|
1164 |
},
|
1165 |
{
|
1166 |
"epoch": 7.99,
|
1167 |
+
"learning_rate": 2.9727095516569204e-05,
|
1168 |
+
"loss": 0.6295,
|
1169 |
"step": 915
|
1170 |
},
|
1171 |
{
|
1172 |
"epoch": 8.0,
|
1173 |
+
"eval_accuracy": 0.8456486042692939,
|
1174 |
+
"eval_loss": 0.502933144569397,
|
1175 |
+
"eval_runtime": 40.6293,
|
1176 |
+
"eval_samples_per_second": 29.978,
|
1177 |
+
"eval_steps_per_second": 1.895,
|
1178 |
"step": 916
|
1179 |
},
|
1180 |
{
|
1181 |
"epoch": 8.03,
|
1182 |
+
"learning_rate": 2.9889538661468486e-05,
|
1183 |
+
"loss": 0.5978,
|
1184 |
"step": 920
|
1185 |
},
|
1186 |
{
|
1187 |
"epoch": 8.08,
|
1188 |
+
"learning_rate": 3.0051981806367774e-05,
|
1189 |
+
"loss": 0.5042,
|
1190 |
"step": 925
|
1191 |
},
|
1192 |
{
|
1193 |
"epoch": 8.12,
|
1194 |
+
"learning_rate": 3.0214424951267055e-05,
|
1195 |
+
"loss": 0.4356,
|
1196 |
"step": 930
|
1197 |
},
|
1198 |
{
|
1199 |
"epoch": 8.17,
|
1200 |
+
"learning_rate": 3.0376868096166344e-05,
|
1201 |
+
"loss": 0.4456,
|
1202 |
"step": 935
|
1203 |
},
|
1204 |
{
|
1205 |
"epoch": 8.21,
|
1206 |
+
"learning_rate": 3.053931124106563e-05,
|
1207 |
+
"loss": 0.458,
|
1208 |
"step": 940
|
1209 |
},
|
1210 |
{
|
1211 |
"epoch": 8.25,
|
1212 |
+
"learning_rate": 3.0701754385964913e-05,
|
1213 |
+
"loss": 0.5482,
|
1214 |
"step": 945
|
1215 |
},
|
1216 |
{
|
1217 |
"epoch": 8.3,
|
1218 |
+
"learning_rate": 3.08641975308642e-05,
|
1219 |
+
"loss": 0.4893,
|
1220 |
"step": 950
|
1221 |
},
|
1222 |
{
|
1223 |
"epoch": 8.34,
|
1224 |
+
"learning_rate": 3.102664067576348e-05,
|
1225 |
+
"loss": 0.5415,
|
1226 |
"step": 955
|
1227 |
},
|
1228 |
{
|
1229 |
"epoch": 8.38,
|
1230 |
+
"learning_rate": 3.118908382066277e-05,
|
1231 |
+
"loss": 0.4136,
|
1232 |
"step": 960
|
1233 |
},
|
1234 |
{
|
1235 |
"epoch": 8.43,
|
1236 |
+
"learning_rate": 3.135152696556205e-05,
|
1237 |
+
"loss": 0.4674,
|
1238 |
"step": 965
|
1239 |
},
|
1240 |
{
|
1241 |
"epoch": 8.47,
|
1242 |
+
"learning_rate": 3.151397011046134e-05,
|
1243 |
+
"loss": 0.4243,
|
1244 |
"step": 970
|
1245 |
},
|
1246 |
{
|
1247 |
"epoch": 8.52,
|
1248 |
+
"learning_rate": 3.167641325536063e-05,
|
1249 |
+
"loss": 0.6295,
|
1250 |
"step": 975
|
1251 |
},
|
1252 |
{
|
1253 |
"epoch": 8.56,
|
1254 |
+
"learning_rate": 3.183885640025991e-05,
|
1255 |
+
"loss": 0.5712,
|
1256 |
"step": 980
|
1257 |
},
|
1258 |
{
|
1259 |
"epoch": 8.6,
|
1260 |
+
"learning_rate": 3.20012995451592e-05,
|
1261 |
+
"loss": 0.5626,
|
1262 |
"step": 985
|
1263 |
},
|
1264 |
{
|
1265 |
"epoch": 8.65,
|
1266 |
+
"learning_rate": 3.216374269005848e-05,
|
1267 |
+
"loss": 0.6171,
|
1268 |
"step": 990
|
1269 |
},
|
1270 |
{
|
1271 |
"epoch": 8.69,
|
1272 |
+
"learning_rate": 3.232618583495777e-05,
|
1273 |
+
"loss": 0.5435,
|
1274 |
"step": 995
|
1275 |
},
|
1276 |
{
|
1277 |
"epoch": 8.73,
|
1278 |
+
"learning_rate": 3.248862897985705e-05,
|
1279 |
+
"loss": 0.4296,
|
1280 |
"step": 1000
|
1281 |
},
|
1282 |
{
|
1283 |
"epoch": 8.78,
|
1284 |
+
"learning_rate": 3.265107212475634e-05,
|
1285 |
+
"loss": 0.4617,
|
1286 |
"step": 1005
|
1287 |
},
|
1288 |
{
|
1289 |
"epoch": 8.82,
|
1290 |
+
"learning_rate": 3.281351526965562e-05,
|
1291 |
+
"loss": 0.4562,
|
1292 |
"step": 1010
|
1293 |
},
|
1294 |
{
|
1295 |
"epoch": 8.86,
|
1296 |
+
"learning_rate": 3.297595841455491e-05,
|
1297 |
+
"loss": 0.5265,
|
1298 |
"step": 1015
|
1299 |
},
|
1300 |
{
|
1301 |
"epoch": 8.91,
|
1302 |
+
"learning_rate": 3.313840155945419e-05,
|
1303 |
+
"loss": 0.3641,
|
1304 |
"step": 1020
|
1305 |
},
|
1306 |
{
|
1307 |
"epoch": 8.95,
|
1308 |
+
"learning_rate": 3.330084470435348e-05,
|
1309 |
+
"loss": 0.5487,
|
1310 |
"step": 1025
|
1311 |
},
|
1312 |
{
|
1313 |
"epoch": 9.0,
|
1314 |
+
"learning_rate": 3.346328784925276e-05,
|
1315 |
+
"loss": 0.5367,
|
1316 |
"step": 1030
|
1317 |
},
|
1318 |
{
|
1319 |
"epoch": 9.0,
|
1320 |
+
"eval_accuracy": 0.8669950738916257,
|
1321 |
+
"eval_loss": 0.47418925166130066,
|
1322 |
+
"eval_runtime": 40.7104,
|
1323 |
+
"eval_samples_per_second": 29.919,
|
1324 |
+
"eval_steps_per_second": 1.891,
|
1325 |
"step": 1030
|
1326 |
},
|
1327 |
{
|
1328 |
"epoch": 9.04,
|
1329 |
+
"learning_rate": 3.362573099415205e-05,
|
1330 |
+
"loss": 0.6724,
|
1331 |
"step": 1035
|
1332 |
},
|
1333 |
{
|
1334 |
"epoch": 9.08,
|
1335 |
+
"learning_rate": 3.378817413905133e-05,
|
1336 |
+
"loss": 0.6034,
|
1337 |
"step": 1040
|
1338 |
},
|
1339 |
{
|
1340 |
"epoch": 9.13,
|
1341 |
+
"learning_rate": 3.395061728395062e-05,
|
1342 |
+
"loss": 0.644,
|
1343 |
"step": 1045
|
1344 |
},
|
1345 |
{
|
1346 |
"epoch": 9.17,
|
1347 |
+
"learning_rate": 3.41130604288499e-05,
|
1348 |
+
"loss": 0.4588,
|
1349 |
"step": 1050
|
1350 |
},
|
1351 |
{
|
1352 |
"epoch": 9.21,
|
1353 |
+
"learning_rate": 3.427550357374919e-05,
|
1354 |
+
"loss": 0.477,
|
1355 |
"step": 1055
|
1356 |
},
|
1357 |
{
|
1358 |
"epoch": 9.26,
|
1359 |
+
"learning_rate": 3.443794671864847e-05,
|
1360 |
+
"loss": 0.4355,
|
1361 |
"step": 1060
|
1362 |
},
|
1363 |
{
|
1364 |
"epoch": 9.3,
|
1365 |
+
"learning_rate": 3.4600389863547764e-05,
|
1366 |
+
"loss": 0.4206,
|
1367 |
"step": 1065
|
1368 |
},
|
1369 |
{
|
1370 |
"epoch": 9.34,
|
1371 |
+
"learning_rate": 3.476283300844704e-05,
|
1372 |
+
"loss": 0.4886,
|
1373 |
"step": 1070
|
1374 |
},
|
1375 |
{
|
1376 |
"epoch": 9.39,
|
1377 |
+
"learning_rate": 3.492527615334633e-05,
|
1378 |
+
"loss": 0.361,
|
1379 |
"step": 1075
|
1380 |
},
|
1381 |
{
|
1382 |
"epoch": 9.43,
|
1383 |
+
"learning_rate": 3.508771929824561e-05,
|
1384 |
+
"loss": 0.3122,
|
1385 |
"step": 1080
|
1386 |
},
|
1387 |
{
|
1388 |
"epoch": 9.48,
|
1389 |
+
"learning_rate": 3.52501624431449e-05,
|
1390 |
+
"loss": 0.3294,
|
1391 |
"step": 1085
|
1392 |
},
|
1393 |
{
|
1394 |
"epoch": 9.52,
|
1395 |
+
"learning_rate": 3.541260558804418e-05,
|
1396 |
+
"loss": 0.4127,
|
1397 |
"step": 1090
|
1398 |
},
|
1399 |
{
|
1400 |
"epoch": 9.56,
|
1401 |
+
"learning_rate": 3.557504873294347e-05,
|
1402 |
+
"loss": 0.4817,
|
1403 |
"step": 1095
|
1404 |
},
|
1405 |
{
|
1406 |
"epoch": 9.61,
|
1407 |
+
"learning_rate": 3.573749187784276e-05,
|
1408 |
+
"loss": 0.3645,
|
1409 |
"step": 1100
|
1410 |
},
|
1411 |
{
|
1412 |
"epoch": 9.65,
|
1413 |
+
"learning_rate": 3.589993502274204e-05,
|
1414 |
+
"loss": 0.3088,
|
1415 |
"step": 1105
|
1416 |
},
|
1417 |
{
|
1418 |
"epoch": 9.69,
|
1419 |
+
"learning_rate": 3.606237816764133e-05,
|
1420 |
+
"loss": 0.364,
|
1421 |
"step": 1110
|
1422 |
},
|
1423 |
{
|
1424 |
"epoch": 9.74,
|
1425 |
+
"learning_rate": 3.622482131254061e-05,
|
1426 |
+
"loss": 0.3626,
|
1427 |
"step": 1115
|
1428 |
},
|
1429 |
{
|
1430 |
"epoch": 9.78,
|
1431 |
+
"learning_rate": 3.63872644574399e-05,
|
1432 |
+
"loss": 0.3565,
|
1433 |
"step": 1120
|
1434 |
},
|
1435 |
{
|
1436 |
"epoch": 9.83,
|
1437 |
+
"learning_rate": 3.654970760233918e-05,
|
1438 |
+
"loss": 0.3839,
|
1439 |
"step": 1125
|
1440 |
},
|
1441 |
{
|
1442 |
"epoch": 9.87,
|
1443 |
+
"learning_rate": 3.671215074723847e-05,
|
1444 |
+
"loss": 0.397,
|
1445 |
"step": 1130
|
1446 |
},
|
1447 |
{
|
1448 |
"epoch": 9.91,
|
1449 |
+
"learning_rate": 3.687459389213775e-05,
|
1450 |
+
"loss": 0.5443,
|
1451 |
"step": 1135
|
1452 |
},
|
1453 |
{
|
1454 |
"epoch": 9.96,
|
1455 |
+
"learning_rate": 3.7037037037037037e-05,
|
1456 |
+
"loss": 0.4872,
|
1457 |
"step": 1140
|
1458 |
},
|
1459 |
{
|
1460 |
"epoch": 10.0,
|
1461 |
+
"learning_rate": 3.719948018193632e-05,
|
1462 |
+
"loss": 0.5091,
|
1463 |
"step": 1145
|
1464 |
},
|
1465 |
{
|
1466 |
"epoch": 10.0,
|
1467 |
+
"eval_accuracy": 0.9211822660098522,
|
1468 |
+
"eval_loss": 0.3038104474544525,
|
1469 |
+
"eval_runtime": 40.7057,
|
1470 |
+
"eval_samples_per_second": 29.922,
|
1471 |
+
"eval_steps_per_second": 1.892,
|
1472 |
"step": 1145
|
1473 |
},
|
1474 |
{
|
1475 |
"epoch": 10.04,
|
1476 |
+
"learning_rate": 3.7361923326835606e-05,
|
1477 |
+
"loss": 0.2693,
|
1478 |
"step": 1150
|
1479 |
},
|
1480 |
{
|
1481 |
"epoch": 10.09,
|
1482 |
+
"learning_rate": 3.75243664717349e-05,
|
1483 |
+
"loss": 0.258,
|
1484 |
"step": 1155
|
1485 |
},
|
1486 |
{
|
1487 |
"epoch": 10.13,
|
1488 |
+
"learning_rate": 3.7686809616634176e-05,
|
1489 |
+
"loss": 0.4722,
|
1490 |
"step": 1160
|
1491 |
},
|
1492 |
{
|
1493 |
"epoch": 10.17,
|
1494 |
+
"learning_rate": 3.784925276153347e-05,
|
1495 |
+
"loss": 0.3623,
|
1496 |
"step": 1165
|
1497 |
},
|
1498 |
{
|
1499 |
"epoch": 10.22,
|
1500 |
+
"learning_rate": 3.8011695906432746e-05,
|
1501 |
+
"loss": 0.4347,
|
1502 |
"step": 1170
|
1503 |
},
|
1504 |
{
|
1505 |
"epoch": 10.26,
|
1506 |
+
"learning_rate": 3.817413905133204e-05,
|
1507 |
+
"loss": 0.5497,
|
1508 |
"step": 1175
|
1509 |
},
|
1510 |
{
|
1511 |
"epoch": 10.31,
|
1512 |
+
"learning_rate": 3.8336582196231315e-05,
|
1513 |
+
"loss": 0.4095,
|
1514 |
"step": 1180
|
1515 |
},
|
1516 |
{
|
1517 |
"epoch": 10.35,
|
1518 |
+
"learning_rate": 3.849902534113061e-05,
|
1519 |
+
"loss": 0.3934,
|
1520 |
"step": 1185
|
1521 |
},
|
1522 |
{
|
1523 |
"epoch": 10.39,
|
1524 |
+
"learning_rate": 3.866146848602989e-05,
|
1525 |
+
"loss": 0.4325,
|
1526 |
"step": 1190
|
1527 |
},
|
1528 |
{
|
1529 |
"epoch": 10.44,
|
1530 |
+
"learning_rate": 3.882391163092918e-05,
|
1531 |
+
"loss": 0.5688,
|
1532 |
"step": 1195
|
1533 |
},
|
1534 |
{
|
1535 |
"epoch": 10.48,
|
1536 |
+
"learning_rate": 3.898635477582846e-05,
|
1537 |
+
"loss": 0.5056,
|
1538 |
"step": 1200
|
1539 |
},
|
1540 |
{
|
1541 |
"epoch": 10.52,
|
1542 |
+
"learning_rate": 3.9148797920727747e-05,
|
1543 |
+
"loss": 0.5651,
|
1544 |
"step": 1205
|
1545 |
},
|
1546 |
{
|
1547 |
"epoch": 10.57,
|
1548 |
+
"learning_rate": 3.931124106562703e-05,
|
1549 |
+
"loss": 0.3713,
|
1550 |
"step": 1210
|
1551 |
},
|
1552 |
{
|
1553 |
"epoch": 10.61,
|
1554 |
+
"learning_rate": 3.9473684210526316e-05,
|
1555 |
+
"loss": 0.4504,
|
1556 |
"step": 1215
|
1557 |
},
|
1558 |
{
|
1559 |
"epoch": 10.66,
|
1560 |
+
"learning_rate": 3.96361273554256e-05,
|
1561 |
+
"loss": 0.4941,
|
1562 |
"step": 1220
|
1563 |
},
|
1564 |
{
|
1565 |
"epoch": 10.7,
|
1566 |
+
"learning_rate": 3.9798570500324886e-05,
|
1567 |
+
"loss": 0.4764,
|
1568 |
"step": 1225
|
1569 |
},
|
1570 |
{
|
1571 |
"epoch": 10.74,
|
1572 |
+
"learning_rate": 3.996101364522417e-05,
|
1573 |
+
"loss": 0.392,
|
1574 |
"step": 1230
|
1575 |
},
|
1576 |
{
|
1577 |
"epoch": 10.79,
|
1578 |
+
"learning_rate": 4.012345679012346e-05,
|
1579 |
+
"loss": 0.5135,
|
1580 |
"step": 1235
|
1581 |
},
|
1582 |
{
|
1583 |
"epoch": 10.83,
|
1584 |
+
"learning_rate": 4.028589993502274e-05,
|
1585 |
+
"loss": 0.3799,
|
1586 |
"step": 1240
|
1587 |
},
|
1588 |
{
|
1589 |
"epoch": 10.87,
|
1590 |
+
"learning_rate": 4.044834307992203e-05,
|
1591 |
+
"loss": 0.3701,
|
1592 |
"step": 1245
|
1593 |
},
|
1594 |
{
|
1595 |
"epoch": 10.92,
|
1596 |
+
"learning_rate": 4.061078622482131e-05,
|
1597 |
+
"loss": 0.3229,
|
1598 |
"step": 1250
|
1599 |
},
|
1600 |
{
|
1601 |
"epoch": 10.96,
|
1602 |
+
"learning_rate": 4.07732293697206e-05,
|
1603 |
+
"loss": 0.3521,
|
1604 |
"step": 1255
|
1605 |
},
|
1606 |
{
|
1607 |
"epoch": 11.0,
|
1608 |
+
"eval_accuracy": 0.9605911330049262,
|
1609 |
+
"eval_loss": 0.18549488484859467,
|
1610 |
+
"eval_runtime": 40.628,
|
1611 |
+
"eval_samples_per_second": 29.979,
|
1612 |
+
"eval_steps_per_second": 1.895,
|
1613 |
"step": 1259
|
1614 |
},
|
1615 |
{
|
1616 |
"epoch": 11.0,
|
1617 |
+
"learning_rate": 4.093567251461988e-05,
|
1618 |
+
"loss": 0.3195,
|
1619 |
"step": 1260
|
1620 |
},
|
1621 |
{
|
1622 |
"epoch": 11.05,
|
1623 |
+
"learning_rate": 4.109811565951917e-05,
|
1624 |
+
"loss": 0.3136,
|
1625 |
"step": 1265
|
1626 |
},
|
1627 |
{
|
1628 |
"epoch": 11.09,
|
1629 |
+
"learning_rate": 4.1260558804418457e-05,
|
1630 |
+
"loss": 0.2692,
|
1631 |
"step": 1270
|
1632 |
},
|
1633 |
{
|
1634 |
"epoch": 11.14,
|
1635 |
+
"learning_rate": 4.142300194931774e-05,
|
1636 |
+
"loss": 0.3812,
|
1637 |
"step": 1275
|
1638 |
},
|
1639 |
{
|
1640 |
"epoch": 11.18,
|
1641 |
+
"learning_rate": 4.1585445094217026e-05,
|
1642 |
+
"loss": 0.375,
|
1643 |
"step": 1280
|
1644 |
},
|
1645 |
{
|
1646 |
"epoch": 11.22,
|
1647 |
+
"learning_rate": 4.174788823911631e-05,
|
1648 |
+
"loss": 0.3822,
|
1649 |
"step": 1285
|
1650 |
},
|
1651 |
{
|
1652 |
"epoch": 11.27,
|
1653 |
+
"learning_rate": 4.1910331384015596e-05,
|
1654 |
+
"loss": 0.3694,
|
1655 |
"step": 1290
|
1656 |
},
|
1657 |
{
|
1658 |
"epoch": 11.31,
|
1659 |
+
"learning_rate": 4.207277452891488e-05,
|
1660 |
+
"loss": 0.341,
|
1661 |
"step": 1295
|
1662 |
},
|
1663 |
{
|
1664 |
"epoch": 11.35,
|
1665 |
+
"learning_rate": 4.2235217673814166e-05,
|
1666 |
+
"loss": 0.2623,
|
1667 |
"step": 1300
|
1668 |
},
|
1669 |
{
|
1670 |
"epoch": 11.4,
|
1671 |
+
"learning_rate": 4.239766081871345e-05,
|
1672 |
+
"loss": 0.4251,
|
1673 |
"step": 1305
|
1674 |
},
|
1675 |
{
|
1676 |
"epoch": 11.44,
|
1677 |
+
"learning_rate": 4.2560103963612735e-05,
|
1678 |
+
"loss": 0.489,
|
1679 |
"step": 1310
|
1680 |
},
|
1681 |
{
|
1682 |
"epoch": 11.48,
|
1683 |
+
"learning_rate": 4.272254710851202e-05,
|
1684 |
+
"loss": 0.2665,
|
1685 |
"step": 1315
|
1686 |
},
|
1687 |
{
|
1688 |
"epoch": 11.53,
|
1689 |
+
"learning_rate": 4.2884990253411305e-05,
|
1690 |
+
"loss": 0.2983,
|
1691 |
"step": 1320
|
1692 |
},
|
1693 |
{
|
1694 |
"epoch": 11.57,
|
1695 |
+
"learning_rate": 4.30474333983106e-05,
|
1696 |
+
"loss": 0.3795,
|
1697 |
"step": 1325
|
1698 |
},
|
1699 |
{
|
1700 |
"epoch": 11.62,
|
1701 |
+
"learning_rate": 4.3209876543209875e-05,
|
1702 |
+
"loss": 0.2786,
|
1703 |
"step": 1330
|
1704 |
},
|
1705 |
{
|
1706 |
"epoch": 11.66,
|
1707 |
+
"learning_rate": 4.3372319688109166e-05,
|
1708 |
+
"loss": 0.2519,
|
1709 |
"step": 1335
|
1710 |
},
|
1711 |
{
|
1712 |
"epoch": 11.7,
|
1713 |
+
"learning_rate": 4.3534762833008445e-05,
|
1714 |
+
"loss": 0.3996,
|
1715 |
"step": 1340
|
1716 |
},
|
1717 |
{
|
1718 |
"epoch": 11.75,
|
1719 |
+
"learning_rate": 4.3697205977907736e-05,
|
1720 |
+
"loss": 0.4282,
|
1721 |
"step": 1345
|
1722 |
},
|
1723 |
{
|
1724 |
"epoch": 11.79,
|
1725 |
+
"learning_rate": 4.3859649122807014e-05,
|
1726 |
+
"loss": 0.5874,
|
1727 |
"step": 1350
|
1728 |
},
|
1729 |
{
|
1730 |
"epoch": 11.83,
|
1731 |
+
"learning_rate": 4.4022092267706306e-05,
|
1732 |
+
"loss": 0.4892,
|
1733 |
"step": 1355
|
1734 |
},
|
1735 |
{
|
1736 |
"epoch": 11.88,
|
1737 |
+
"learning_rate": 4.418453541260559e-05,
|
1738 |
+
"loss": 0.3275,
|
1739 |
"step": 1360
|
1740 |
},
|
1741 |
{
|
1742 |
"epoch": 11.92,
|
1743 |
+
"learning_rate": 4.4346978557504876e-05,
|
1744 |
+
"loss": 0.2496,
|
1745 |
"step": 1365
|
1746 |
},
|
1747 |
{
|
1748 |
+
"epoch": 11.97,
|
1749 |
+
"learning_rate": 4.450942170240416e-05,
|
1750 |
+
"loss": 0.318,
|
1751 |
+
"step": 1370
|
1752 |
+
},
|
1753 |
+
{
|
1754 |
+
"epoch": 12.0,
|
1755 |
+
"eval_accuracy": 0.9573070607553367,
|
1756 |
+
"eval_loss": 0.1892772614955902,
|
1757 |
+
"eval_runtime": 40.7256,
|
1758 |
+
"eval_samples_per_second": 29.908,
|
1759 |
+
"eval_steps_per_second": 1.891,
|
1760 |
+
"step": 1374
|
1761 |
+
},
|
1762 |
+
{
|
1763 |
+
"epoch": 12.01,
|
1764 |
+
"learning_rate": 4.4671864847303445e-05,
|
1765 |
+
"loss": 0.2485,
|
1766 |
+
"step": 1375
|
1767 |
+
},
|
1768 |
+
{
|
1769 |
+
"epoch": 12.05,
|
1770 |
+
"learning_rate": 4.483430799220273e-05,
|
1771 |
+
"loss": 0.2923,
|
1772 |
+
"step": 1380
|
1773 |
+
},
|
1774 |
+
{
|
1775 |
+
"epoch": 12.1,
|
1776 |
+
"learning_rate": 4.4996751137102015e-05,
|
1777 |
+
"loss": 0.2871,
|
1778 |
+
"step": 1385
|
1779 |
+
},
|
1780 |
+
{
|
1781 |
+
"epoch": 12.14,
|
1782 |
+
"learning_rate": 4.51591942820013e-05,
|
1783 |
+
"loss": 0.4304,
|
1784 |
+
"step": 1390
|
1785 |
+
},
|
1786 |
+
{
|
1787 |
+
"epoch": 12.18,
|
1788 |
+
"learning_rate": 4.5321637426900585e-05,
|
1789 |
+
"loss": 0.374,
|
1790 |
+
"step": 1395
|
1791 |
+
},
|
1792 |
+
{
|
1793 |
+
"epoch": 12.23,
|
1794 |
+
"learning_rate": 4.548408057179987e-05,
|
1795 |
+
"loss": 0.3159,
|
1796 |
+
"step": 1400
|
1797 |
+
},
|
1798 |
+
{
|
1799 |
+
"epoch": 12.27,
|
1800 |
+
"learning_rate": 4.5646523716699155e-05,
|
1801 |
+
"loss": 0.3889,
|
1802 |
+
"step": 1405
|
1803 |
+
},
|
1804 |
+
{
|
1805 |
+
"epoch": 12.31,
|
1806 |
+
"learning_rate": 4.580896686159844e-05,
|
1807 |
+
"loss": 0.3718,
|
1808 |
+
"step": 1410
|
1809 |
+
},
|
1810 |
+
{
|
1811 |
+
"epoch": 12.36,
|
1812 |
+
"learning_rate": 4.597141000649773e-05,
|
1813 |
+
"loss": 0.235,
|
1814 |
+
"step": 1415
|
1815 |
+
},
|
1816 |
+
{
|
1817 |
+
"epoch": 12.4,
|
1818 |
+
"learning_rate": 4.613385315139701e-05,
|
1819 |
+
"loss": 0.3755,
|
1820 |
+
"step": 1420
|
1821 |
+
},
|
1822 |
+
{
|
1823 |
+
"epoch": 12.45,
|
1824 |
+
"learning_rate": 4.62962962962963e-05,
|
1825 |
+
"loss": 0.3717,
|
1826 |
+
"step": 1425
|
1827 |
+
},
|
1828 |
+
{
|
1829 |
+
"epoch": 12.49,
|
1830 |
+
"learning_rate": 4.645873944119558e-05,
|
1831 |
+
"loss": 0.2505,
|
1832 |
+
"step": 1430
|
1833 |
+
},
|
1834 |
+
{
|
1835 |
+
"epoch": 12.53,
|
1836 |
+
"learning_rate": 4.662118258609487e-05,
|
1837 |
+
"loss": 0.2414,
|
1838 |
+
"step": 1435
|
1839 |
+
},
|
1840 |
+
{
|
1841 |
+
"epoch": 12.58,
|
1842 |
+
"learning_rate": 4.678362573099415e-05,
|
1843 |
+
"loss": 0.2584,
|
1844 |
+
"step": 1440
|
1845 |
+
},
|
1846 |
+
{
|
1847 |
+
"epoch": 12.62,
|
1848 |
+
"learning_rate": 4.694606887589344e-05,
|
1849 |
+
"loss": 0.2999,
|
1850 |
+
"step": 1445
|
1851 |
+
},
|
1852 |
+
{
|
1853 |
+
"epoch": 12.66,
|
1854 |
+
"learning_rate": 4.7108512020792725e-05,
|
1855 |
+
"loss": 0.2287,
|
1856 |
+
"step": 1450
|
1857 |
+
},
|
1858 |
+
{
|
1859 |
+
"epoch": 12.71,
|
1860 |
+
"learning_rate": 4.727095516569201e-05,
|
1861 |
+
"loss": 0.2235,
|
1862 |
+
"step": 1455
|
1863 |
+
},
|
1864 |
+
{
|
1865 |
+
"epoch": 12.75,
|
1866 |
+
"learning_rate": 4.7433398310591295e-05,
|
1867 |
+
"loss": 0.2618,
|
1868 |
+
"step": 1460
|
1869 |
+
},
|
1870 |
+
{
|
1871 |
+
"epoch": 12.79,
|
1872 |
+
"learning_rate": 4.759584145549058e-05,
|
1873 |
+
"loss": 0.3309,
|
1874 |
+
"step": 1465
|
1875 |
+
},
|
1876 |
+
{
|
1877 |
+
"epoch": 12.84,
|
1878 |
+
"learning_rate": 4.7758284600389865e-05,
|
1879 |
+
"loss": 0.3737,
|
1880 |
+
"step": 1470
|
1881 |
+
},
|
1882 |
+
{
|
1883 |
+
"epoch": 12.88,
|
1884 |
+
"learning_rate": 4.792072774528915e-05,
|
1885 |
+
"loss": 0.3204,
|
1886 |
+
"step": 1475
|
1887 |
+
},
|
1888 |
+
{
|
1889 |
+
"epoch": 12.93,
|
1890 |
+
"learning_rate": 4.8083170890188434e-05,
|
1891 |
+
"loss": 0.3666,
|
1892 |
+
"step": 1480
|
1893 |
+
},
|
1894 |
+
{
|
1895 |
+
"epoch": 12.97,
|
1896 |
+
"learning_rate": 4.824561403508772e-05,
|
1897 |
+
"loss": 0.2725,
|
1898 |
+
"step": 1485
|
1899 |
+
},
|
1900 |
+
{
|
1901 |
+
"epoch": 13.0,
|
1902 |
+
"eval_accuracy": 0.9408866995073891,
|
1903 |
+
"eval_loss": 0.22919727861881256,
|
1904 |
+
"eval_runtime": 40.7292,
|
1905 |
+
"eval_samples_per_second": 29.905,
|
1906 |
+
"eval_steps_per_second": 1.891,
|
1907 |
+
"step": 1488
|
1908 |
+
},
|
1909 |
+
{
|
1910 |
+
"epoch": 13.01,
|
1911 |
+
"learning_rate": 4.8408057179987004e-05,
|
1912 |
+
"loss": 0.2363,
|
1913 |
+
"step": 1490
|
1914 |
+
},
|
1915 |
+
{
|
1916 |
+
"epoch": 13.06,
|
1917 |
+
"learning_rate": 4.857050032488629e-05,
|
1918 |
+
"loss": 0.3268,
|
1919 |
+
"step": 1495
|
1920 |
+
},
|
1921 |
+
{
|
1922 |
+
"epoch": 13.1,
|
1923 |
+
"learning_rate": 4.8732943469785574e-05,
|
1924 |
+
"loss": 0.3668,
|
1925 |
+
"step": 1500
|
1926 |
+
},
|
1927 |
+
{
|
1928 |
+
"epoch": 13.14,
|
1929 |
+
"learning_rate": 4.8895386614684865e-05,
|
1930 |
+
"loss": 0.3087,
|
1931 |
+
"step": 1505
|
1932 |
+
},
|
1933 |
+
{
|
1934 |
+
"epoch": 13.19,
|
1935 |
+
"learning_rate": 4.9057829759584143e-05,
|
1936 |
+
"loss": 0.26,
|
1937 |
+
"step": 1510
|
1938 |
+
},
|
1939 |
+
{
|
1940 |
+
"epoch": 13.23,
|
1941 |
+
"learning_rate": 4.9220272904483435e-05,
|
1942 |
+
"loss": 0.3764,
|
1943 |
+
"step": 1515
|
1944 |
+
},
|
1945 |
+
{
|
1946 |
+
"epoch": 13.28,
|
1947 |
+
"learning_rate": 4.938271604938271e-05,
|
1948 |
+
"loss": 0.4524,
|
1949 |
+
"step": 1520
|
1950 |
+
},
|
1951 |
+
{
|
1952 |
+
"epoch": 13.32,
|
1953 |
+
"learning_rate": 4.9545159194282005e-05,
|
1954 |
+
"loss": 0.3772,
|
1955 |
+
"step": 1525
|
1956 |
+
},
|
1957 |
+
{
|
1958 |
+
"epoch": 13.36,
|
1959 |
+
"learning_rate": 4.970760233918128e-05,
|
1960 |
+
"loss": 0.3396,
|
1961 |
+
"step": 1530
|
1962 |
+
},
|
1963 |
+
{
|
1964 |
+
"epoch": 13.41,
|
1965 |
+
"learning_rate": 4.9870045484080575e-05,
|
1966 |
+
"loss": 0.3826,
|
1967 |
+
"step": 1535
|
1968 |
+
},
|
1969 |
+
{
|
1970 |
+
"epoch": 13.45,
|
1971 |
+
"learning_rate": 4.970760233918128e-05,
|
1972 |
+
"loss": 0.2902,
|
1973 |
+
"step": 1540
|
1974 |
+
},
|
1975 |
+
{
|
1976 |
+
"epoch": 13.49,
|
1977 |
+
"learning_rate": 4.824561403508772e-05,
|
1978 |
+
"loss": 0.2995,
|
1979 |
+
"step": 1545
|
1980 |
+
},
|
1981 |
+
{
|
1982 |
+
"epoch": 13.54,
|
1983 |
+
"learning_rate": 4.678362573099415e-05,
|
1984 |
+
"loss": 0.2406,
|
1985 |
+
"step": 1550
|
1986 |
+
},
|
1987 |
+
{
|
1988 |
+
"epoch": 13.58,
|
1989 |
+
"learning_rate": 4.5321637426900585e-05,
|
1990 |
+
"loss": 0.2968,
|
1991 |
+
"step": 1555
|
1992 |
+
},
|
1993 |
+
{
|
1994 |
+
"epoch": 13.62,
|
1995 |
+
"learning_rate": 4.3859649122807014e-05,
|
1996 |
+
"loss": 0.2552,
|
1997 |
+
"step": 1560
|
1998 |
+
},
|
1999 |
+
{
|
2000 |
+
"epoch": 13.67,
|
2001 |
+
"learning_rate": 4.239766081871345e-05,
|
2002 |
+
"loss": 0.2546,
|
2003 |
+
"step": 1565
|
2004 |
+
},
|
2005 |
+
{
|
2006 |
+
"epoch": 13.71,
|
2007 |
+
"learning_rate": 4.093567251461988e-05,
|
2008 |
+
"loss": 0.3931,
|
2009 |
+
"step": 1570
|
2010 |
+
},
|
2011 |
+
{
|
2012 |
+
"epoch": 13.76,
|
2013 |
+
"learning_rate": 3.9473684210526316e-05,
|
2014 |
+
"loss": 0.177,
|
2015 |
+
"step": 1575
|
2016 |
+
},
|
2017 |
+
{
|
2018 |
+
"epoch": 13.8,
|
2019 |
+
"learning_rate": 3.8011695906432746e-05,
|
2020 |
+
"loss": 0.2625,
|
2021 |
+
"step": 1580
|
2022 |
+
},
|
2023 |
+
{
|
2024 |
+
"epoch": 13.84,
|
2025 |
+
"learning_rate": 3.654970760233918e-05,
|
2026 |
+
"loss": 0.3622,
|
2027 |
+
"step": 1585
|
2028 |
+
},
|
2029 |
+
{
|
2030 |
+
"epoch": 13.89,
|
2031 |
+
"learning_rate": 3.508771929824561e-05,
|
2032 |
+
"loss": 0.1971,
|
2033 |
+
"step": 1590
|
2034 |
+
},
|
2035 |
+
{
|
2036 |
+
"epoch": 13.93,
|
2037 |
+
"learning_rate": 3.362573099415205e-05,
|
2038 |
+
"loss": 0.2986,
|
2039 |
+
"step": 1595
|
2040 |
+
},
|
2041 |
+
{
|
2042 |
+
"epoch": 13.97,
|
2043 |
+
"learning_rate": 3.216374269005848e-05,
|
2044 |
+
"loss": 0.2937,
|
2045 |
+
"step": 1600
|
2046 |
+
},
|
2047 |
+
{
|
2048 |
+
"epoch": 14.0,
|
2049 |
+
"eval_accuracy": 0.9835796387520526,
|
2050 |
+
"eval_loss": 0.08656656742095947,
|
2051 |
+
"eval_runtime": 40.617,
|
2052 |
+
"eval_samples_per_second": 29.987,
|
2053 |
+
"eval_steps_per_second": 1.896,
|
2054 |
+
"step": 1603
|
2055 |
+
},
|
2056 |
+
{
|
2057 |
+
"epoch": 14.02,
|
2058 |
+
"learning_rate": 3.0701754385964913e-05,
|
2059 |
+
"loss": 0.2555,
|
2060 |
+
"step": 1605
|
2061 |
+
},
|
2062 |
+
{
|
2063 |
+
"epoch": 14.06,
|
2064 |
+
"learning_rate": 2.9239766081871346e-05,
|
2065 |
+
"loss": 0.1262,
|
2066 |
+
"step": 1610
|
2067 |
+
},
|
2068 |
+
{
|
2069 |
+
"epoch": 14.1,
|
2070 |
+
"learning_rate": 2.777777777777778e-05,
|
2071 |
+
"loss": 0.2058,
|
2072 |
+
"step": 1615
|
2073 |
+
},
|
2074 |
+
{
|
2075 |
+
"epoch": 14.15,
|
2076 |
+
"learning_rate": 2.6315789473684212e-05,
|
2077 |
+
"loss": 0.3217,
|
2078 |
+
"step": 1620
|
2079 |
+
},
|
2080 |
+
{
|
2081 |
+
"epoch": 14.19,
|
2082 |
+
"learning_rate": 2.485380116959064e-05,
|
2083 |
+
"loss": 0.1943,
|
2084 |
+
"step": 1625
|
2085 |
+
},
|
2086 |
+
{
|
2087 |
+
"epoch": 14.24,
|
2088 |
+
"learning_rate": 2.3391812865497074e-05,
|
2089 |
+
"loss": 0.1544,
|
2090 |
+
"step": 1630
|
2091 |
+
},
|
2092 |
+
{
|
2093 |
+
"epoch": 14.28,
|
2094 |
+
"learning_rate": 2.1929824561403507e-05,
|
2095 |
+
"loss": 0.142,
|
2096 |
+
"step": 1635
|
2097 |
+
},
|
2098 |
+
{
|
2099 |
+
"epoch": 14.32,
|
2100 |
+
"learning_rate": 2.046783625730994e-05,
|
2101 |
+
"loss": 0.1831,
|
2102 |
+
"step": 1640
|
2103 |
+
},
|
2104 |
+
{
|
2105 |
+
"epoch": 14.37,
|
2106 |
+
"learning_rate": 1.9005847953216373e-05,
|
2107 |
+
"loss": 0.1592,
|
2108 |
+
"step": 1645
|
2109 |
+
},
|
2110 |
+
{
|
2111 |
+
"epoch": 14.41,
|
2112 |
+
"learning_rate": 1.7543859649122806e-05,
|
2113 |
+
"loss": 0.1605,
|
2114 |
+
"step": 1650
|
2115 |
+
},
|
2116 |
+
{
|
2117 |
+
"epoch": 14.45,
|
2118 |
+
"learning_rate": 1.608187134502924e-05,
|
2119 |
+
"loss": 0.2399,
|
2120 |
+
"step": 1655
|
2121 |
+
},
|
2122 |
+
{
|
2123 |
+
"epoch": 14.5,
|
2124 |
+
"learning_rate": 1.4619883040935673e-05,
|
2125 |
+
"loss": 0.169,
|
2126 |
+
"step": 1660
|
2127 |
+
},
|
2128 |
+
{
|
2129 |
+
"epoch": 14.54,
|
2130 |
+
"learning_rate": 1.3157894736842106e-05,
|
2131 |
+
"loss": 0.3231,
|
2132 |
+
"step": 1665
|
2133 |
+
},
|
2134 |
+
{
|
2135 |
+
"epoch": 14.59,
|
2136 |
+
"learning_rate": 1.1695906432748537e-05,
|
2137 |
+
"loss": 0.2028,
|
2138 |
+
"step": 1670
|
2139 |
+
},
|
2140 |
+
{
|
2141 |
+
"epoch": 14.63,
|
2142 |
+
"learning_rate": 1.023391812865497e-05,
|
2143 |
+
"loss": 0.1459,
|
2144 |
+
"step": 1675
|
2145 |
+
},
|
2146 |
+
{
|
2147 |
+
"epoch": 14.67,
|
2148 |
+
"learning_rate": 8.771929824561403e-06,
|
2149 |
+
"loss": 0.139,
|
2150 |
+
"step": 1680
|
2151 |
+
},
|
2152 |
+
{
|
2153 |
+
"epoch": 14.72,
|
2154 |
+
"learning_rate": 7.3099415204678366e-06,
|
2155 |
+
"loss": 0.2303,
|
2156 |
+
"step": 1685
|
2157 |
+
},
|
2158 |
+
{
|
2159 |
+
"epoch": 14.76,
|
2160 |
+
"learning_rate": 5.8479532163742686e-06,
|
2161 |
+
"loss": 0.1616,
|
2162 |
+
"step": 1690
|
2163 |
+
},
|
2164 |
+
{
|
2165 |
+
"epoch": 14.8,
|
2166 |
+
"learning_rate": 4.3859649122807014e-06,
|
2167 |
+
"loss": 0.1633,
|
2168 |
+
"step": 1695
|
2169 |
+
},
|
2170 |
+
{
|
2171 |
+
"epoch": 14.85,
|
2172 |
+
"learning_rate": 2.9239766081871343e-06,
|
2173 |
+
"loss": 0.2043,
|
2174 |
+
"step": 1700
|
2175 |
+
},
|
2176 |
+
{
|
2177 |
+
"epoch": 14.89,
|
2178 |
+
"learning_rate": 1.4619883040935671e-06,
|
2179 |
+
"loss": 0.1392,
|
2180 |
+
"step": 1705
|
2181 |
+
},
|
2182 |
+
{
|
2183 |
+
"epoch": 14.93,
|
2184 |
+
"learning_rate": 0.0,
|
2185 |
+
"loss": 0.1185,
|
2186 |
+
"step": 1710
|
2187 |
+
},
|
2188 |
+
{
|
2189 |
+
"epoch": 14.93,
|
2190 |
+
"eval_accuracy": 0.986863711001642,
|
2191 |
+
"eval_loss": 0.07206606864929199,
|
2192 |
+
"eval_runtime": 40.6097,
|
2193 |
+
"eval_samples_per_second": 29.993,
|
2194 |
+
"eval_steps_per_second": 1.896,
|
2195 |
+
"step": 1710
|
2196 |
},
|
2197 |
{
|
2198 |
+
"epoch": 14.93,
|
2199 |
+
"step": 1710,
|
2200 |
+
"total_flos": 9.675577376037974e+18,
|
2201 |
+
"train_loss": 0.8123349746416884,
|
2202 |
+
"train_runtime": 8647.4379,
|
2203 |
+
"train_samples_per_second": 6.333,
|
2204 |
+
"train_steps_per_second": 0.198
|
2205 |
}
|
2206 |
],
|
2207 |
+
"max_steps": 1710,
|
2208 |
+
"num_train_epochs": 15,
|
2209 |
+
"total_flos": 9.675577376037974e+18,
|
2210 |
"trial_name": null,
|
2211 |
"trial_params": null
|
2212 |
}
|