tiagoblima
commited on
Commit
•
378a488
1
Parent(s):
ab5985e
End of training
Browse files- README.md +3 -1
- all_results.json +11 -11
- eval_results.json +6 -6
- train_results.json +6 -6
- trainer_state.json +650 -364
README.md
CHANGED
@@ -3,6 +3,8 @@ license: mit
|
|
3 |
base_model: unicamp-dl/ptt5-base-portuguese-vocab
|
4 |
tags:
|
5 |
- generated_from_trainer
|
|
|
|
|
6 |
model-index:
|
7 |
- name: t5_base-qg-ap-test
|
8 |
results: []
|
@@ -13,7 +15,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
13 |
|
14 |
# t5_base-qg-ap-test
|
15 |
|
16 |
-
This model is a fine-tuned version of [unicamp-dl/ptt5-base-portuguese-vocab](https://huggingface.co/unicamp-dl/ptt5-base-portuguese-vocab) on
|
17 |
It achieves the following results on the evaluation set:
|
18 |
- Loss: 0.0163
|
19 |
|
|
|
3 |
base_model: unicamp-dl/ptt5-base-portuguese-vocab
|
4 |
tags:
|
5 |
- generated_from_trainer
|
6 |
+
datasets:
|
7 |
+
- tiagoblima/du-qg-squadv1_pt
|
8 |
model-index:
|
9 |
- name: t5_base-qg-ap-test
|
10 |
results: []
|
|
|
15 |
|
16 |
# t5_base-qg-ap-test
|
17 |
|
18 |
+
This model is a fine-tuned version of [unicamp-dl/ptt5-base-portuguese-vocab](https://huggingface.co/unicamp-dl/ptt5-base-portuguese-vocab) on the tiagoblima/du-qg-squadv1_pt dataset.
|
19 |
It achieves the following results on the evaluation set:
|
20 |
- Loss: 0.0163
|
21 |
|
all_results.json
CHANGED
@@ -1,13 +1,13 @@
|
|
1 |
{
|
2 |
-
"epoch":
|
3 |
-
"eval_loss":
|
4 |
-
"eval_runtime":
|
5 |
-
"eval_samples":
|
6 |
-
"eval_samples_per_second":
|
7 |
-
"eval_steps_per_second":
|
8 |
-
"train_loss":
|
9 |
-
"train_runtime":
|
10 |
-
"train_samples":
|
11 |
-
"train_samples_per_second":
|
12 |
-
"train_steps_per_second": 0.
|
13 |
}
|
|
|
1 |
{
|
2 |
+
"epoch": 100.0,
|
3 |
+
"eval_loss": 0.016336046159267426,
|
4 |
+
"eval_runtime": 0.2314,
|
5 |
+
"eval_samples": 8,
|
6 |
+
"eval_samples_per_second": 34.579,
|
7 |
+
"eval_steps_per_second": 4.322,
|
8 |
+
"train_loss": 1.40092041015625,
|
9 |
+
"train_runtime": 1064.353,
|
10 |
+
"train_samples": 8,
|
11 |
+
"train_samples_per_second": 0.752,
|
12 |
+
"train_steps_per_second": 0.094
|
13 |
}
|
eval_results.json
CHANGED
@@ -1,8 +1,8 @@
|
|
1 |
{
|
2 |
-
"epoch":
|
3 |
-
"eval_loss":
|
4 |
-
"eval_runtime":
|
5 |
-
"eval_samples":
|
6 |
-
"eval_samples_per_second":
|
7 |
-
"eval_steps_per_second":
|
8 |
}
|
|
|
1 |
{
|
2 |
+
"epoch": 100.0,
|
3 |
+
"eval_loss": 0.016336046159267426,
|
4 |
+
"eval_runtime": 0.2314,
|
5 |
+
"eval_samples": 8,
|
6 |
+
"eval_samples_per_second": 34.579,
|
7 |
+
"eval_steps_per_second": 4.322
|
8 |
}
|
train_results.json
CHANGED
@@ -1,8 +1,8 @@
|
|
1 |
{
|
2 |
-
"epoch":
|
3 |
-
"train_loss":
|
4 |
-
"train_runtime":
|
5 |
-
"train_samples":
|
6 |
-
"train_samples_per_second":
|
7 |
-
"train_steps_per_second": 0.
|
8 |
}
|
|
|
1 |
{
|
2 |
+
"epoch": 100.0,
|
3 |
+
"train_loss": 1.40092041015625,
|
4 |
+
"train_runtime": 1064.353,
|
5 |
+
"train_samples": 8,
|
6 |
+
"train_samples_per_second": 0.752,
|
7 |
+
"train_steps_per_second": 0.094
|
8 |
}
|
trainer_state.json
CHANGED
@@ -1,548 +1,834 @@
|
|
1 |
{
|
2 |
-
"best_metric":
|
3 |
-
"best_model_checkpoint": "/temp/t5_base-qg-ap-test/checkpoint-
|
4 |
-
"epoch":
|
5 |
"eval_steps": 500,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
10 |
"log_history": [
|
11 |
{
|
12 |
-
"epoch": 0
|
13 |
-
"
|
14 |
-
"
|
15 |
-
"
|
|
|
|
|
16 |
},
|
17 |
{
|
18 |
-
"epoch": 0
|
19 |
-
"
|
20 |
-
"
|
21 |
-
"
|
|
|
|
|
22 |
},
|
23 |
{
|
24 |
-
"epoch": 0
|
25 |
-
"
|
26 |
-
"
|
27 |
-
"
|
|
|
|
|
28 |
},
|
29 |
{
|
30 |
-
"epoch": 0
|
31 |
-
"
|
32 |
-
"
|
33 |
-
"
|
|
|
|
|
34 |
},
|
35 |
{
|
36 |
-
"epoch": 0
|
37 |
-
"
|
38 |
-
"
|
39 |
-
"
|
|
|
|
|
40 |
},
|
41 |
{
|
42 |
-
"epoch": 0
|
43 |
-
"
|
44 |
-
"
|
45 |
-
"
|
|
|
|
|
46 |
},
|
47 |
{
|
48 |
-
"epoch": 0
|
49 |
-
"
|
50 |
-
"
|
51 |
-
"
|
|
|
|
|
52 |
},
|
53 |
{
|
54 |
-
"epoch": 0
|
55 |
-
"
|
56 |
-
"
|
57 |
-
"
|
|
|
|
|
58 |
},
|
59 |
{
|
60 |
-
"epoch": 0
|
61 |
-
"
|
62 |
-
"
|
63 |
-
"
|
|
|
|
|
64 |
},
|
65 |
{
|
66 |
-
"epoch": 0
|
67 |
-
"
|
68 |
-
"
|
69 |
-
"
|
|
|
|
|
70 |
},
|
71 |
{
|
72 |
-
"epoch": 0
|
73 |
-
"
|
74 |
-
"
|
75 |
-
"
|
|
|
|
|
76 |
},
|
77 |
{
|
78 |
-
"epoch": 0
|
79 |
-
"
|
80 |
-
"
|
81 |
-
"
|
|
|
|
|
82 |
},
|
83 |
{
|
84 |
-
"epoch": 0
|
85 |
-
"
|
86 |
-
"
|
87 |
-
"
|
|
|
|
|
88 |
},
|
89 |
{
|
90 |
-
"epoch": 0
|
91 |
-
"
|
92 |
-
"
|
93 |
-
"
|
|
|
|
|
94 |
},
|
95 |
{
|
96 |
-
"epoch": 0
|
97 |
-
"
|
98 |
-
"
|
99 |
-
"
|
|
|
|
|
100 |
},
|
101 |
{
|
102 |
-
"epoch": 0
|
103 |
-
"
|
104 |
-
"
|
105 |
-
"
|
|
|
|
|
106 |
},
|
107 |
{
|
108 |
-
"epoch":
|
109 |
-
"eval_loss":
|
110 |
-
"eval_runtime":
|
111 |
-
"eval_samples_per_second":
|
112 |
-
"eval_steps_per_second":
|
113 |
-
"step":
|
114 |
},
|
115 |
{
|
116 |
-
"epoch":
|
117 |
-
"
|
118 |
-
"
|
119 |
-
"
|
|
|
|
|
120 |
},
|
121 |
{
|
122 |
-
"epoch":
|
123 |
-
"
|
124 |
-
"
|
125 |
-
"
|
|
|
|
|
126 |
},
|
127 |
{
|
128 |
-
"epoch":
|
129 |
-
"
|
130 |
-
"
|
131 |
-
"
|
|
|
|
|
132 |
},
|
133 |
{
|
134 |
-
"epoch":
|
135 |
-
"
|
136 |
-
"
|
137 |
-
"
|
|
|
|
|
138 |
},
|
139 |
{
|
140 |
-
"epoch":
|
141 |
-
"
|
142 |
-
"
|
143 |
-
"
|
|
|
|
|
144 |
},
|
145 |
{
|
146 |
-
"epoch":
|
147 |
-
"
|
148 |
-
"
|
149 |
-
"
|
|
|
|
|
150 |
},
|
151 |
{
|
152 |
-
"epoch":
|
153 |
-
"
|
154 |
-
"
|
155 |
-
"
|
|
|
|
|
156 |
},
|
157 |
{
|
158 |
-
"epoch":
|
159 |
-
"
|
160 |
-
"
|
161 |
-
"
|
|
|
|
|
162 |
},
|
163 |
{
|
164 |
-
"epoch":
|
165 |
-
"
|
166 |
-
"
|
167 |
-
"
|
|
|
|
|
168 |
},
|
169 |
{
|
170 |
-
"epoch":
|
171 |
-
"
|
172 |
-
"
|
173 |
-
"
|
|
|
|
|
174 |
},
|
175 |
{
|
176 |
-
"epoch":
|
177 |
-
"
|
178 |
-
"
|
179 |
-
"
|
|
|
|
|
180 |
},
|
181 |
{
|
182 |
-
"epoch":
|
183 |
-
"
|
184 |
-
"
|
185 |
-
"
|
|
|
|
|
186 |
},
|
187 |
{
|
188 |
-
"epoch":
|
189 |
-
"
|
190 |
-
"
|
191 |
-
"
|
|
|
|
|
192 |
},
|
193 |
{
|
194 |
-
"epoch":
|
195 |
-
"
|
196 |
-
"
|
197 |
-
"
|
|
|
|
|
198 |
},
|
199 |
{
|
200 |
-
"epoch":
|
201 |
-
"
|
202 |
-
"
|
203 |
-
"
|
|
|
|
|
204 |
},
|
205 |
{
|
206 |
-
"epoch":
|
207 |
-
"
|
208 |
-
"
|
209 |
-
"
|
|
|
|
|
210 |
},
|
211 |
{
|
212 |
-
"epoch":
|
213 |
-
"eval_loss":
|
214 |
-
"eval_runtime":
|
215 |
-
"eval_samples_per_second":
|
216 |
-
"eval_steps_per_second":
|
217 |
-
"step":
|
218 |
},
|
219 |
{
|
220 |
-
"epoch":
|
221 |
-
"
|
222 |
-
"
|
223 |
-
"
|
|
|
|
|
224 |
},
|
225 |
{
|
226 |
-
"epoch":
|
227 |
-
"
|
228 |
-
"
|
229 |
-
"
|
|
|
|
|
230 |
},
|
231 |
{
|
232 |
-
"epoch":
|
233 |
-
"
|
234 |
-
"
|
235 |
-
"
|
|
|
|
|
236 |
},
|
237 |
{
|
238 |
-
"epoch":
|
239 |
-
"
|
240 |
-
"
|
241 |
-
"
|
|
|
|
|
242 |
},
|
243 |
{
|
244 |
-
"epoch":
|
245 |
-
"
|
246 |
-
"
|
247 |
-
"
|
|
|
|
|
248 |
},
|
249 |
{
|
250 |
-
"epoch":
|
251 |
-
"
|
252 |
-
"
|
253 |
-
"
|
|
|
|
|
254 |
},
|
255 |
{
|
256 |
-
"epoch":
|
257 |
-
"
|
258 |
-
"
|
259 |
-
"
|
|
|
|
|
260 |
},
|
261 |
{
|
262 |
-
"epoch":
|
263 |
-
"
|
264 |
-
"
|
265 |
-
"
|
|
|
|
|
266 |
},
|
267 |
{
|
268 |
-
"epoch":
|
269 |
-
"
|
270 |
-
"
|
271 |
-
"
|
|
|
|
|
272 |
},
|
273 |
{
|
274 |
-
"epoch":
|
275 |
-
"
|
276 |
-
"
|
277 |
-
"
|
|
|
|
|
278 |
},
|
279 |
{
|
280 |
-
"epoch":
|
281 |
-
"
|
282 |
-
"
|
283 |
-
"
|
|
|
|
|
284 |
},
|
285 |
{
|
286 |
-
"epoch":
|
287 |
-
"
|
288 |
-
"
|
289 |
-
"
|
|
|
|
|
290 |
},
|
291 |
{
|
292 |
-
"epoch":
|
293 |
-
"
|
294 |
-
"
|
295 |
-
"
|
|
|
|
|
296 |
},
|
297 |
{
|
298 |
-
"epoch":
|
299 |
-
"
|
300 |
-
"
|
301 |
-
"
|
|
|
|
|
302 |
},
|
303 |
{
|
304 |
-
"epoch":
|
305 |
-
"
|
306 |
-
"
|
307 |
-
"
|
|
|
|
|
308 |
},
|
309 |
{
|
310 |
-
"epoch":
|
311 |
-
"
|
312 |
-
"
|
313 |
-
"
|
|
|
|
|
314 |
},
|
315 |
{
|
316 |
-
"epoch":
|
317 |
-
"eval_loss":
|
318 |
-
"eval_runtime":
|
319 |
-
"eval_samples_per_second":
|
320 |
-
"eval_steps_per_second":
|
321 |
-
"step":
|
322 |
},
|
323 |
{
|
324 |
-
"epoch":
|
325 |
-
"
|
326 |
-
"
|
327 |
-
"
|
|
|
|
|
328 |
},
|
329 |
{
|
330 |
-
"epoch":
|
331 |
-
"
|
332 |
-
"
|
333 |
-
"
|
|
|
|
|
334 |
},
|
335 |
{
|
336 |
-
"epoch":
|
337 |
-
"
|
338 |
-
"
|
339 |
-
"
|
|
|
|
|
340 |
},
|
341 |
{
|
342 |
-
"epoch":
|
343 |
-
"
|
344 |
-
"
|
345 |
-
"
|
|
|
|
|
346 |
},
|
347 |
{
|
348 |
-
"epoch":
|
349 |
-
"
|
350 |
-
"
|
351 |
-
"
|
|
|
|
|
352 |
},
|
353 |
{
|
354 |
-
"epoch":
|
355 |
-
"
|
356 |
-
"
|
357 |
-
"
|
|
|
|
|
358 |
},
|
359 |
{
|
360 |
-
"epoch":
|
361 |
-
"
|
362 |
-
"
|
363 |
-
"
|
|
|
|
|
364 |
},
|
365 |
{
|
366 |
-
"epoch":
|
367 |
-
"
|
368 |
-
"
|
369 |
-
"
|
|
|
|
|
370 |
},
|
371 |
{
|
372 |
-
"epoch":
|
373 |
-
"
|
374 |
-
"
|
375 |
-
"
|
|
|
|
|
376 |
},
|
377 |
{
|
378 |
-
"epoch":
|
379 |
-
"
|
380 |
-
"
|
381 |
-
"
|
|
|
|
|
382 |
},
|
383 |
{
|
384 |
-
"epoch":
|
385 |
-
"
|
386 |
-
"
|
387 |
-
"
|
|
|
|
|
388 |
},
|
389 |
{
|
390 |
-
"epoch":
|
391 |
-
"
|
392 |
-
"
|
393 |
-
"
|
|
|
|
|
394 |
},
|
395 |
{
|
396 |
-
"epoch":
|
397 |
-
"
|
398 |
-
"
|
399 |
-
"
|
|
|
|
|
400 |
},
|
401 |
{
|
402 |
-
"epoch":
|
403 |
-
"
|
404 |
-
"
|
405 |
-
"
|
|
|
|
|
406 |
},
|
407 |
{
|
408 |
-
"epoch":
|
409 |
-
"
|
410 |
-
"
|
411 |
-
"
|
|
|
|
|
412 |
},
|
413 |
{
|
414 |
-
"epoch":
|
415 |
-
"
|
416 |
-
"
|
417 |
-
"
|
|
|
|
|
418 |
},
|
419 |
{
|
420 |
-
"epoch":
|
421 |
-
"eval_loss":
|
422 |
-
"eval_runtime":
|
423 |
-
"eval_samples_per_second":
|
424 |
-
"eval_steps_per_second":
|
425 |
-
"step":
|
426 |
},
|
427 |
{
|
428 |
-
"epoch":
|
429 |
-
"
|
430 |
-
"
|
431 |
-
"
|
|
|
|
|
432 |
},
|
433 |
{
|
434 |
-
"epoch":
|
435 |
-
"
|
436 |
-
"
|
437 |
-
"
|
|
|
|
|
438 |
},
|
439 |
{
|
440 |
-
"epoch":
|
441 |
-
"
|
442 |
-
"
|
443 |
-
"
|
|
|
|
|
444 |
},
|
445 |
{
|
446 |
-
"epoch":
|
447 |
-
"
|
448 |
-
"
|
449 |
-
"
|
|
|
|
|
450 |
},
|
451 |
{
|
452 |
-
"epoch":
|
453 |
-
"
|
454 |
-
"
|
455 |
-
"
|
|
|
|
|
456 |
},
|
457 |
{
|
458 |
-
"epoch":
|
459 |
-
"
|
460 |
-
"
|
461 |
-
"
|
|
|
|
|
462 |
},
|
463 |
{
|
464 |
-
"epoch":
|
465 |
-
"
|
466 |
-
"
|
467 |
-
"
|
|
|
|
|
468 |
},
|
469 |
{
|
470 |
-
"epoch":
|
471 |
-
"
|
472 |
-
"
|
473 |
-
"
|
|
|
|
|
474 |
},
|
475 |
{
|
476 |
-
"epoch":
|
477 |
-
"
|
478 |
-
"
|
479 |
-
"
|
|
|
|
|
480 |
},
|
481 |
{
|
482 |
-
"epoch":
|
483 |
-
"
|
484 |
-
"
|
485 |
-
"
|
|
|
|
|
486 |
},
|
487 |
{
|
488 |
-
"epoch":
|
489 |
-
"
|
490 |
-
"
|
491 |
-
"
|
|
|
|
|
492 |
},
|
493 |
{
|
494 |
-
"epoch":
|
495 |
-
"
|
496 |
-
"
|
497 |
-
"
|
|
|
|
|
498 |
},
|
499 |
{
|
500 |
-
"epoch":
|
501 |
-
"
|
502 |
-
"
|
503 |
-
"
|
|
|
|
|
504 |
},
|
505 |
{
|
506 |
-
"epoch":
|
507 |
-
"
|
508 |
-
"
|
509 |
-
"
|
|
|
|
|
510 |
},
|
511 |
{
|
512 |
-
"epoch":
|
513 |
-
"
|
514 |
-
"
|
515 |
-
"
|
|
|
|
|
516 |
},
|
517 |
{
|
518 |
-
"epoch":
|
519 |
-
"
|
520 |
-
"
|
521 |
-
"
|
|
|
|
|
522 |
},
|
523 |
{
|
524 |
-
"epoch":
|
525 |
-
"eval_loss":
|
526 |
-
"eval_runtime":
|
527 |
-
"eval_samples_per_second":
|
528 |
-
"eval_steps_per_second":
|
529 |
-
"step":
|
530 |
},
|
531 |
{
|
532 |
-
"epoch":
|
533 |
-
"
|
534 |
-
"
|
535 |
-
"
|
536 |
-
"
|
537 |
-
"
|
538 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
539 |
}
|
540 |
],
|
541 |
"logging_steps": 100,
|
542 |
-
"max_steps":
|
543 |
-
"num_train_epochs":
|
544 |
"save_steps": 500,
|
545 |
-
"total_flos":
|
546 |
"trial_name": null,
|
547 |
"trial_params": null
|
548 |
}
|
|
|
1 |
{
|
2 |
+
"best_metric": 0.016336046159267426,
|
3 |
+
"best_model_checkpoint": "/temp/t5_base-qg-ap-test/checkpoint-100",
|
4 |
+
"epoch": 100.0,
|
5 |
"eval_steps": 500,
|
6 |
+
"global_step": 100,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
10 |
"log_history": [
|
11 |
{
|
12 |
+
"epoch": 1.0,
|
13 |
+
"eval_loss": 12.805366516113281,
|
14 |
+
"eval_runtime": 0.2208,
|
15 |
+
"eval_samples_per_second": 36.238,
|
16 |
+
"eval_steps_per_second": 4.53,
|
17 |
+
"step": 1
|
18 |
},
|
19 |
{
|
20 |
+
"epoch": 2.0,
|
21 |
+
"eval_loss": 10.788012504577637,
|
22 |
+
"eval_runtime": 0.2356,
|
23 |
+
"eval_samples_per_second": 33.954,
|
24 |
+
"eval_steps_per_second": 4.244,
|
25 |
+
"step": 2
|
26 |
},
|
27 |
{
|
28 |
+
"epoch": 3.0,
|
29 |
+
"eval_loss": 8.873129844665527,
|
30 |
+
"eval_runtime": 0.2362,
|
31 |
+
"eval_samples_per_second": 33.872,
|
32 |
+
"eval_steps_per_second": 4.234,
|
33 |
+
"step": 3
|
34 |
},
|
35 |
{
|
36 |
+
"epoch": 4.0,
|
37 |
+
"eval_loss": 7.4068284034729,
|
38 |
+
"eval_runtime": 0.2351,
|
39 |
+
"eval_samples_per_second": 34.03,
|
40 |
+
"eval_steps_per_second": 4.254,
|
41 |
+
"step": 4
|
42 |
},
|
43 |
{
|
44 |
+
"epoch": 5.0,
|
45 |
+
"eval_loss": 6.458061218261719,
|
46 |
+
"eval_runtime": 0.2334,
|
47 |
+
"eval_samples_per_second": 34.275,
|
48 |
+
"eval_steps_per_second": 4.284,
|
49 |
+
"step": 5
|
50 |
},
|
51 |
{
|
52 |
+
"epoch": 6.0,
|
53 |
+
"eval_loss": 5.647502422332764,
|
54 |
+
"eval_runtime": 0.2335,
|
55 |
+
"eval_samples_per_second": 34.259,
|
56 |
+
"eval_steps_per_second": 4.282,
|
57 |
+
"step": 6
|
58 |
},
|
59 |
{
|
60 |
+
"epoch": 7.0,
|
61 |
+
"eval_loss": 4.959558486938477,
|
62 |
+
"eval_runtime": 0.2256,
|
63 |
+
"eval_samples_per_second": 35.464,
|
64 |
+
"eval_steps_per_second": 4.433,
|
65 |
+
"step": 7
|
66 |
},
|
67 |
{
|
68 |
+
"epoch": 8.0,
|
69 |
+
"eval_loss": 4.50578498840332,
|
70 |
+
"eval_runtime": 0.2359,
|
71 |
+
"eval_samples_per_second": 33.916,
|
72 |
+
"eval_steps_per_second": 4.239,
|
73 |
+
"step": 8
|
74 |
},
|
75 |
{
|
76 |
+
"epoch": 9.0,
|
77 |
+
"eval_loss": 4.076832294464111,
|
78 |
+
"eval_runtime": 0.2354,
|
79 |
+
"eval_samples_per_second": 33.984,
|
80 |
+
"eval_steps_per_second": 4.248,
|
81 |
+
"step": 9
|
82 |
},
|
83 |
{
|
84 |
+
"epoch": 10.0,
|
85 |
+
"eval_loss": 3.704714059829712,
|
86 |
+
"eval_runtime": 0.2353,
|
87 |
+
"eval_samples_per_second": 33.999,
|
88 |
+
"eval_steps_per_second": 4.25,
|
89 |
+
"step": 10
|
90 |
},
|
91 |
{
|
92 |
+
"epoch": 11.0,
|
93 |
+
"eval_loss": 3.4143009185791016,
|
94 |
+
"eval_runtime": 0.2359,
|
95 |
+
"eval_samples_per_second": 33.914,
|
96 |
+
"eval_steps_per_second": 4.239,
|
97 |
+
"step": 11
|
98 |
},
|
99 |
{
|
100 |
+
"epoch": 12.0,
|
101 |
+
"eval_loss": 3.1360208988189697,
|
102 |
+
"eval_runtime": 0.2359,
|
103 |
+
"eval_samples_per_second": 33.913,
|
104 |
+
"eval_steps_per_second": 4.239,
|
105 |
+
"step": 12
|
106 |
},
|
107 |
{
|
108 |
+
"epoch": 13.0,
|
109 |
+
"eval_loss": 2.8865740299224854,
|
110 |
+
"eval_runtime": 0.2356,
|
111 |
+
"eval_samples_per_second": 33.955,
|
112 |
+
"eval_steps_per_second": 4.244,
|
113 |
+
"step": 13
|
114 |
},
|
115 |
{
|
116 |
+
"epoch": 14.0,
|
117 |
+
"eval_loss": 2.6324548721313477,
|
118 |
+
"eval_runtime": 0.234,
|
119 |
+
"eval_samples_per_second": 34.185,
|
120 |
+
"eval_steps_per_second": 4.273,
|
121 |
+
"step": 14
|
122 |
},
|
123 |
{
|
124 |
+
"epoch": 15.0,
|
125 |
+
"eval_loss": 2.388902187347412,
|
126 |
+
"eval_runtime": 0.2365,
|
127 |
+
"eval_samples_per_second": 33.826,
|
128 |
+
"eval_steps_per_second": 4.228,
|
129 |
+
"step": 15
|
130 |
},
|
131 |
{
|
132 |
+
"epoch": 16.0,
|
133 |
+
"eval_loss": 2.1914408206939697,
|
134 |
+
"eval_runtime": 0.2324,
|
135 |
+
"eval_samples_per_second": 34.427,
|
136 |
+
"eval_steps_per_second": 4.303,
|
137 |
+
"step": 16
|
138 |
},
|
139 |
{
|
140 |
+
"epoch": 17.0,
|
141 |
+
"eval_loss": 2.0423526763916016,
|
142 |
+
"eval_runtime": 0.2363,
|
143 |
+
"eval_samples_per_second": 33.85,
|
144 |
+
"eval_steps_per_second": 4.231,
|
145 |
+
"step": 17
|
146 |
},
|
147 |
{
|
148 |
+
"epoch": 18.0,
|
149 |
+
"eval_loss": 1.9110742807388306,
|
150 |
+
"eval_runtime": 0.2247,
|
151 |
+
"eval_samples_per_second": 35.611,
|
152 |
+
"eval_steps_per_second": 4.451,
|
153 |
+
"step": 18
|
154 |
},
|
155 |
{
|
156 |
+
"epoch": 19.0,
|
157 |
+
"eval_loss": 1.7762634754180908,
|
158 |
+
"eval_runtime": 0.2365,
|
159 |
+
"eval_samples_per_second": 33.825,
|
160 |
+
"eval_steps_per_second": 4.228,
|
161 |
+
"step": 19
|
162 |
},
|
163 |
{
|
164 |
+
"epoch": 20.0,
|
165 |
+
"eval_loss": 1.6505231857299805,
|
166 |
+
"eval_runtime": 0.2253,
|
167 |
+
"eval_samples_per_second": 35.504,
|
168 |
+
"eval_steps_per_second": 4.438,
|
169 |
+
"step": 20
|
170 |
},
|
171 |
{
|
172 |
+
"epoch": 21.0,
|
173 |
+
"eval_loss": 1.525721788406372,
|
174 |
+
"eval_runtime": 0.2362,
|
175 |
+
"eval_samples_per_second": 33.872,
|
176 |
+
"eval_steps_per_second": 4.234,
|
177 |
+
"step": 21
|
178 |
},
|
179 |
{
|
180 |
+
"epoch": 22.0,
|
181 |
+
"eval_loss": 1.4125868082046509,
|
182 |
+
"eval_runtime": 0.235,
|
183 |
+
"eval_samples_per_second": 34.046,
|
184 |
+
"eval_steps_per_second": 4.256,
|
185 |
+
"step": 22
|
186 |
},
|
187 |
{
|
188 |
+
"epoch": 23.0,
|
189 |
+
"eval_loss": 1.3109110593795776,
|
190 |
+
"eval_runtime": 0.2369,
|
191 |
+
"eval_samples_per_second": 33.769,
|
192 |
+
"eval_steps_per_second": 4.221,
|
193 |
+
"step": 23
|
194 |
},
|
195 |
{
|
196 |
+
"epoch": 24.0,
|
197 |
+
"eval_loss": 1.2188917398452759,
|
198 |
+
"eval_runtime": 0.2319,
|
199 |
+
"eval_samples_per_second": 34.5,
|
200 |
+
"eval_steps_per_second": 4.312,
|
201 |
+
"step": 24
|
202 |
},
|
203 |
{
|
204 |
+
"epoch": 25.0,
|
205 |
+
"eval_loss": 1.1338324546813965,
|
206 |
+
"eval_runtime": 0.2362,
|
207 |
+
"eval_samples_per_second": 33.873,
|
208 |
+
"eval_steps_per_second": 4.234,
|
209 |
+
"step": 25
|
210 |
},
|
211 |
{
|
212 |
+
"epoch": 26.0,
|
213 |
+
"eval_loss": 1.0485577583312988,
|
214 |
+
"eval_runtime": 0.2311,
|
215 |
+
"eval_samples_per_second": 34.62,
|
216 |
+
"eval_steps_per_second": 4.328,
|
217 |
+
"step": 26
|
218 |
},
|
219 |
{
|
220 |
+
"epoch": 27.0,
|
221 |
+
"eval_loss": 0.9640414118766785,
|
222 |
+
"eval_runtime": 0.2359,
|
223 |
+
"eval_samples_per_second": 33.914,
|
224 |
+
"eval_steps_per_second": 4.239,
|
225 |
+
"step": 27
|
226 |
},
|
227 |
{
|
228 |
+
"epoch": 28.0,
|
229 |
+
"eval_loss": 0.8827559947967529,
|
230 |
+
"eval_runtime": 0.2268,
|
231 |
+
"eval_samples_per_second": 35.271,
|
232 |
+
"eval_steps_per_second": 4.409,
|
233 |
+
"step": 28
|
234 |
},
|
235 |
{
|
236 |
+
"epoch": 29.0,
|
237 |
+
"eval_loss": 0.8060356378555298,
|
238 |
+
"eval_runtime": 0.2364,
|
239 |
+
"eval_samples_per_second": 33.848,
|
240 |
+
"eval_steps_per_second": 4.231,
|
241 |
+
"step": 29
|
242 |
},
|
243 |
{
|
244 |
+
"epoch": 30.0,
|
245 |
+
"eval_loss": 0.7329221367835999,
|
246 |
+
"eval_runtime": 0.2336,
|
247 |
+
"eval_samples_per_second": 34.244,
|
248 |
+
"eval_steps_per_second": 4.281,
|
249 |
+
"step": 30
|
250 |
},
|
251 |
{
|
252 |
+
"epoch": 31.0,
|
253 |
+
"eval_loss": 0.6638815402984619,
|
254 |
+
"eval_runtime": 0.2359,
|
255 |
+
"eval_samples_per_second": 33.912,
|
256 |
+
"eval_steps_per_second": 4.239,
|
257 |
+
"step": 31
|
258 |
},
|
259 |
{
|
260 |
+
"epoch": 32.0,
|
261 |
+
"eval_loss": 0.6010197997093201,
|
262 |
+
"eval_runtime": 0.235,
|
263 |
+
"eval_samples_per_second": 34.042,
|
264 |
+
"eval_steps_per_second": 4.255,
|
265 |
+
"step": 32
|
266 |
},
|
267 |
{
|
268 |
+
"epoch": 33.0,
|
269 |
+
"eval_loss": 0.5438850522041321,
|
270 |
+
"eval_runtime": 0.2331,
|
271 |
+
"eval_samples_per_second": 34.324,
|
272 |
+
"eval_steps_per_second": 4.29,
|
273 |
+
"step": 33
|
274 |
},
|
275 |
{
|
276 |
+
"epoch": 34.0,
|
277 |
+
"eval_loss": 0.4924549162387848,
|
278 |
+
"eval_runtime": 0.2353,
|
279 |
+
"eval_samples_per_second": 34.004,
|
280 |
+
"eval_steps_per_second": 4.25,
|
281 |
+
"step": 34
|
282 |
},
|
283 |
{
|
284 |
+
"epoch": 35.0,
|
285 |
+
"eval_loss": 0.4471151828765869,
|
286 |
+
"eval_runtime": 0.2413,
|
287 |
+
"eval_samples_per_second": 33.158,
|
288 |
+
"eval_steps_per_second": 4.145,
|
289 |
+
"step": 35
|
290 |
},
|
291 |
{
|
292 |
+
"epoch": 36.0,
|
293 |
+
"eval_loss": 0.4065961539745331,
|
294 |
+
"eval_runtime": 0.2355,
|
295 |
+
"eval_samples_per_second": 33.966,
|
296 |
+
"eval_steps_per_second": 4.246,
|
297 |
+
"step": 36
|
298 |
},
|
299 |
{
|
300 |
+
"epoch": 37.0,
|
301 |
+
"eval_loss": 0.3690074682235718,
|
302 |
+
"eval_runtime": 0.2363,
|
303 |
+
"eval_samples_per_second": 33.853,
|
304 |
+
"eval_steps_per_second": 4.232,
|
305 |
+
"step": 37
|
306 |
},
|
307 |
{
|
308 |
+
"epoch": 38.0,
|
309 |
+
"eval_loss": 0.3340989649295807,
|
310 |
+
"eval_runtime": 0.2363,
|
311 |
+
"eval_samples_per_second": 33.86,
|
312 |
+
"eval_steps_per_second": 4.232,
|
313 |
+
"step": 38
|
314 |
},
|
315 |
{
|
316 |
+
"epoch": 39.0,
|
317 |
+
"eval_loss": 0.3023061454296112,
|
318 |
+
"eval_runtime": 0.2338,
|
319 |
+
"eval_samples_per_second": 34.218,
|
320 |
+
"eval_steps_per_second": 4.277,
|
321 |
+
"step": 39
|
322 |
},
|
323 |
{
|
324 |
+
"epoch": 40.0,
|
325 |
+
"eval_loss": 0.27456292510032654,
|
326 |
+
"eval_runtime": 0.2359,
|
327 |
+
"eval_samples_per_second": 33.907,
|
328 |
+
"eval_steps_per_second": 4.238,
|
329 |
+
"step": 40
|
330 |
},
|
331 |
{
|
332 |
+
"epoch": 41.0,
|
333 |
+
"eval_loss": 0.24695347249507904,
|
334 |
+
"eval_runtime": 0.2296,
|
335 |
+
"eval_samples_per_second": 34.843,
|
336 |
+
"eval_steps_per_second": 4.355,
|
337 |
+
"step": 41
|
338 |
},
|
339 |
{
|
340 |
+
"epoch": 42.0,
|
341 |
+
"eval_loss": 0.220541313290596,
|
342 |
+
"eval_runtime": 0.2354,
|
343 |
+
"eval_samples_per_second": 33.99,
|
344 |
+
"eval_steps_per_second": 4.249,
|
345 |
+
"step": 42
|
346 |
},
|
347 |
{
|
348 |
+
"epoch": 43.0,
|
349 |
+
"eval_loss": 0.19677509367465973,
|
350 |
+
"eval_runtime": 0.2327,
|
351 |
+
"eval_samples_per_second": 34.379,
|
352 |
+
"eval_steps_per_second": 4.297,
|
353 |
+
"step": 43
|
354 |
},
|
355 |
{
|
356 |
+
"epoch": 44.0,
|
357 |
+
"eval_loss": 0.17713746428489685,
|
358 |
+
"eval_runtime": 0.2348,
|
359 |
+
"eval_samples_per_second": 34.066,
|
360 |
+
"eval_steps_per_second": 4.258,
|
361 |
+
"step": 44
|
362 |
},
|
363 |
{
|
364 |
+
"epoch": 45.0,
|
365 |
+
"eval_loss": 0.15933585166931152,
|
366 |
+
"eval_runtime": 0.2234,
|
367 |
+
"eval_samples_per_second": 35.814,
|
368 |
+
"eval_steps_per_second": 4.477,
|
369 |
+
"step": 45
|
370 |
},
|
371 |
{
|
372 |
+
"epoch": 46.0,
|
373 |
+
"eval_loss": 0.14242056012153625,
|
374 |
+
"eval_runtime": 0.2366,
|
375 |
+
"eval_samples_per_second": 33.807,
|
376 |
+
"eval_steps_per_second": 4.226,
|
377 |
+
"step": 46
|
378 |
},
|
379 |
{
|
380 |
+
"epoch": 47.0,
|
381 |
+
"eval_loss": 0.1287701427936554,
|
382 |
+
"eval_runtime": 0.2313,
|
383 |
+
"eval_samples_per_second": 34.594,
|
384 |
+
"eval_steps_per_second": 4.324,
|
385 |
+
"step": 47
|
386 |
},
|
387 |
{
|
388 |
+
"epoch": 48.0,
|
389 |
+
"eval_loss": 0.11695855855941772,
|
390 |
+
"eval_runtime": 0.2269,
|
391 |
+
"eval_samples_per_second": 35.251,
|
392 |
+
"eval_steps_per_second": 4.406,
|
393 |
+
"step": 48
|
394 |
},
|
395 |
{
|
396 |
+
"epoch": 49.0,
|
397 |
+
"eval_loss": 0.1070137694478035,
|
398 |
+
"eval_runtime": 0.2278,
|
399 |
+
"eval_samples_per_second": 35.111,
|
400 |
+
"eval_steps_per_second": 4.389,
|
401 |
+
"step": 49
|
402 |
},
|
403 |
{
|
404 |
+
"epoch": 50.0,
|
405 |
+
"eval_loss": 0.09962165355682373,
|
406 |
+
"eval_runtime": 0.2347,
|
407 |
+
"eval_samples_per_second": 34.085,
|
408 |
+
"eval_steps_per_second": 4.261,
|
409 |
+
"step": 50
|
410 |
},
|
411 |
{
|
412 |
+
"epoch": 51.0,
|
413 |
+
"eval_loss": 0.09394610673189163,
|
414 |
+
"eval_runtime": 0.2348,
|
415 |
+
"eval_samples_per_second": 34.077,
|
416 |
+
"eval_steps_per_second": 4.26,
|
417 |
+
"step": 51
|
418 |
},
|
419 |
{
|
420 |
+
"epoch": 52.0,
|
421 |
+
"eval_loss": 0.08877500891685486,
|
422 |
+
"eval_runtime": 0.2326,
|
423 |
+
"eval_samples_per_second": 34.394,
|
424 |
+
"eval_steps_per_second": 4.299,
|
425 |
+
"step": 52
|
426 |
},
|
427 |
{
|
428 |
+
"epoch": 53.0,
|
429 |
+
"eval_loss": 0.08450286090373993,
|
430 |
+
"eval_runtime": 0.2348,
|
431 |
+
"eval_samples_per_second": 34.07,
|
432 |
+
"eval_steps_per_second": 4.259,
|
433 |
+
"step": 53
|
434 |
},
|
435 |
{
|
436 |
+
"epoch": 54.0,
|
437 |
+
"eval_loss": 0.0817728266119957,
|
438 |
+
"eval_runtime": 0.2313,
|
439 |
+
"eval_samples_per_second": 34.588,
|
440 |
+
"eval_steps_per_second": 4.324,
|
441 |
+
"step": 54
|
442 |
},
|
443 |
{
|
444 |
+
"epoch": 55.0,
|
445 |
+
"eval_loss": 0.07895343005657196,
|
446 |
+
"eval_runtime": 0.2359,
|
447 |
+
"eval_samples_per_second": 33.915,
|
448 |
+
"eval_steps_per_second": 4.239,
|
449 |
+
"step": 55
|
450 |
},
|
451 |
{
|
452 |
+
"epoch": 56.0,
|
453 |
+
"eval_loss": 0.07630708068609238,
|
454 |
+
"eval_runtime": 0.2283,
|
455 |
+
"eval_samples_per_second": 35.038,
|
456 |
+
"eval_steps_per_second": 4.38,
|
457 |
+
"step": 56
|
458 |
},
|
459 |
{
|
460 |
+
"epoch": 57.0,
|
461 |
+
"eval_loss": 0.0731731578707695,
|
462 |
+
"eval_runtime": 0.2364,
|
463 |
+
"eval_samples_per_second": 33.835,
|
464 |
+
"eval_steps_per_second": 4.229,
|
465 |
+
"step": 57
|
466 |
},
|
467 |
{
|
468 |
+
"epoch": 58.0,
|
469 |
+
"eval_loss": 0.06972303986549377,
|
470 |
+
"eval_runtime": 0.2275,
|
471 |
+
"eval_samples_per_second": 35.171,
|
472 |
+
"eval_steps_per_second": 4.396,
|
473 |
+
"step": 58
|
474 |
},
|
475 |
{
|
476 |
+
"epoch": 59.0,
|
477 |
+
"eval_loss": 0.06655264645814896,
|
478 |
+
"eval_runtime": 0.2357,
|
479 |
+
"eval_samples_per_second": 33.941,
|
480 |
+
"eval_steps_per_second": 4.243,
|
481 |
+
"step": 59
|
482 |
},
|
483 |
{
|
484 |
+
"epoch": 60.0,
|
485 |
+
"eval_loss": 0.06421676278114319,
|
486 |
+
"eval_runtime": 0.2353,
|
487 |
+
"eval_samples_per_second": 34.001,
|
488 |
+
"eval_steps_per_second": 4.25,
|
489 |
+
"step": 60
|
490 |
},
|
491 |
{
|
492 |
+
"epoch": 61.0,
|
493 |
+
"eval_loss": 0.06110429763793945,
|
494 |
+
"eval_runtime": 0.2361,
|
495 |
+
"eval_samples_per_second": 33.886,
|
496 |
+
"eval_steps_per_second": 4.236,
|
497 |
+
"step": 61
|
498 |
},
|
499 |
{
|
500 |
+
"epoch": 62.0,
|
501 |
+
"eval_loss": 0.05834279954433441,
|
502 |
+
"eval_runtime": 0.2379,
|
503 |
+
"eval_samples_per_second": 33.624,
|
504 |
+
"eval_steps_per_second": 4.203,
|
505 |
+
"step": 62
|
506 |
},
|
507 |
{
|
508 |
+
"epoch": 63.0,
|
509 |
+
"eval_loss": 0.055961962789297104,
|
510 |
+
"eval_runtime": 0.2264,
|
511 |
+
"eval_samples_per_second": 35.335,
|
512 |
+
"eval_steps_per_second": 4.417,
|
513 |
+
"step": 63
|
514 |
},
|
515 |
{
|
516 |
+
"epoch": 64.0,
|
517 |
+
"eval_loss": 0.05323232710361481,
|
518 |
+
"eval_runtime": 0.2359,
|
519 |
+
"eval_samples_per_second": 33.916,
|
520 |
+
"eval_steps_per_second": 4.24,
|
521 |
+
"step": 64
|
522 |
},
|
523 |
{
|
524 |
+
"epoch": 65.0,
|
525 |
+
"eval_loss": 0.051185671240091324,
|
526 |
+
"eval_runtime": 0.2338,
|
527 |
+
"eval_samples_per_second": 34.213,
|
528 |
+
"eval_steps_per_second": 4.277,
|
529 |
+
"step": 65
|
530 |
},
|
531 |
{
|
532 |
+
"epoch": 66.0,
|
533 |
+
"eval_loss": 0.04865783825516701,
|
534 |
+
"eval_runtime": 0.2358,
|
535 |
+
"eval_samples_per_second": 33.928,
|
536 |
+
"eval_steps_per_second": 4.241,
|
537 |
+
"step": 66
|
538 |
},
|
539 |
{
|
540 |
+
"epoch": 67.0,
|
541 |
+
"eval_loss": 0.04639100283384323,
|
542 |
+
"eval_runtime": 0.2281,
|
543 |
+
"eval_samples_per_second": 35.066,
|
544 |
+
"eval_steps_per_second": 4.383,
|
545 |
+
"step": 67
|
546 |
},
|
547 |
{
|
548 |
+
"epoch": 68.0,
|
549 |
+
"eval_loss": 0.04309353977441788,
|
550 |
+
"eval_runtime": 0.2365,
|
551 |
+
"eval_samples_per_second": 33.827,
|
552 |
+
"eval_steps_per_second": 4.228,
|
553 |
+
"step": 68
|
554 |
},
|
555 |
{
|
556 |
+
"epoch": 69.0,
|
557 |
+
"eval_loss": 0.03992551565170288,
|
558 |
+
"eval_runtime": 0.2324,
|
559 |
+
"eval_samples_per_second": 34.422,
|
560 |
+
"eval_steps_per_second": 4.303,
|
561 |
+
"step": 69
|
562 |
},
|
563 |
{
|
564 |
+
"epoch": 70.0,
|
565 |
+
"eval_loss": 0.03812782093882561,
|
566 |
+
"eval_runtime": 0.2236,
|
567 |
+
"eval_samples_per_second": 35.783,
|
568 |
+
"eval_steps_per_second": 4.473,
|
569 |
+
"step": 70
|
570 |
},
|
571 |
{
|
572 |
+
"epoch": 71.0,
|
573 |
+
"eval_loss": 0.03636465594172478,
|
574 |
+
"eval_runtime": 0.2325,
|
575 |
+
"eval_samples_per_second": 34.401,
|
576 |
+
"eval_steps_per_second": 4.3,
|
577 |
+
"step": 71
|
578 |
},
|
579 |
{
|
580 |
+
"epoch": 72.0,
|
581 |
+
"eval_loss": 0.034834641963243484,
|
582 |
+
"eval_runtime": 0.2358,
|
583 |
+
"eval_samples_per_second": 33.926,
|
584 |
+
"eval_steps_per_second": 4.241,
|
585 |
+
"step": 72
|
586 |
},
|
587 |
{
|
588 |
+
"epoch": 73.0,
|
589 |
+
"eval_loss": 0.03329307958483696,
|
590 |
+
"eval_runtime": 0.2345,
|
591 |
+
"eval_samples_per_second": 34.111,
|
592 |
+
"eval_steps_per_second": 4.264,
|
593 |
+
"step": 73
|
594 |
},
|
595 |
{
|
596 |
+
"epoch": 74.0,
|
597 |
+
"eval_loss": 0.031552691012620926,
|
598 |
+
"eval_runtime": 0.2364,
|
599 |
+
"eval_samples_per_second": 33.845,
|
600 |
+
"eval_steps_per_second": 4.231,
|
601 |
+
"step": 74
|
602 |
},
|
603 |
{
|
604 |
+
"epoch": 75.0,
|
605 |
+
"eval_loss": 0.029882650822401047,
|
606 |
+
"eval_runtime": 0.2329,
|
607 |
+
"eval_samples_per_second": 34.351,
|
608 |
+
"eval_steps_per_second": 4.294,
|
609 |
+
"step": 75
|
610 |
},
|
611 |
{
|
612 |
+
"epoch": 76.0,
|
613 |
+
"eval_loss": 0.028516214340925217,
|
614 |
+
"eval_runtime": 0.2359,
|
615 |
+
"eval_samples_per_second": 33.907,
|
616 |
+
"eval_steps_per_second": 4.238,
|
617 |
+
"step": 76
|
618 |
},
|
619 |
{
|
620 |
+
"epoch": 77.0,
|
621 |
+
"eval_loss": 0.027370158582925797,
|
622 |
+
"eval_runtime": 0.2246,
|
623 |
+
"eval_samples_per_second": 35.624,
|
624 |
+
"eval_steps_per_second": 4.453,
|
625 |
+
"step": 77
|
626 |
},
|
627 |
{
|
628 |
+
"epoch": 78.0,
|
629 |
+
"eval_loss": 0.026426443830132484,
|
630 |
+
"eval_runtime": 0.2254,
|
631 |
+
"eval_samples_per_second": 35.492,
|
632 |
+
"eval_steps_per_second": 4.436,
|
633 |
+
"step": 78
|
634 |
},
|
635 |
{
|
636 |
+
"epoch": 79.0,
|
637 |
+
"eval_loss": 0.02534804865717888,
|
638 |
+
"eval_runtime": 0.2295,
|
639 |
+
"eval_samples_per_second": 34.856,
|
640 |
+
"eval_steps_per_second": 4.357,
|
641 |
+
"step": 79
|
642 |
},
|
643 |
{
|
644 |
+
"epoch": 80.0,
|
645 |
+
"eval_loss": 0.024182336404919624,
|
646 |
+
"eval_runtime": 0.2363,
|
647 |
+
"eval_samples_per_second": 33.856,
|
648 |
+
"eval_steps_per_second": 4.232,
|
649 |
+
"step": 80
|
650 |
},
|
651 |
{
|
652 |
+
"epoch": 81.0,
|
653 |
+
"eval_loss": 0.023593546822667122,
|
654 |
+
"eval_runtime": 0.2361,
|
655 |
+
"eval_samples_per_second": 33.881,
|
656 |
+
"eval_steps_per_second": 4.235,
|
657 |
+
"step": 81
|
658 |
},
|
659 |
{
|
660 |
+
"epoch": 82.0,
|
661 |
+
"eval_loss": 0.023052040487527847,
|
662 |
+
"eval_runtime": 0.2361,
|
663 |
+
"eval_samples_per_second": 33.879,
|
664 |
+
"eval_steps_per_second": 4.235,
|
665 |
+
"step": 82
|
666 |
},
|
667 |
{
|
668 |
+
"epoch": 83.0,
|
669 |
+
"eval_loss": 0.02290300466120243,
|
670 |
+
"eval_runtime": 0.2361,
|
671 |
+
"eval_samples_per_second": 33.884,
|
672 |
+
"eval_steps_per_second": 4.236,
|
673 |
+
"step": 83
|
674 |
},
|
675 |
{
|
676 |
+
"epoch": 84.0,
|
677 |
+
"eval_loss": 0.02261677198112011,
|
678 |
+
"eval_runtime": 0.2286,
|
679 |
+
"eval_samples_per_second": 35.002,
|
680 |
+
"eval_steps_per_second": 4.375,
|
681 |
+
"step": 84
|
682 |
},
|
683 |
{
|
684 |
+
"epoch": 85.0,
|
685 |
+
"eval_loss": 0.022289568558335304,
|
686 |
+
"eval_runtime": 0.2353,
|
687 |
+
"eval_samples_per_second": 34.003,
|
688 |
+
"eval_steps_per_second": 4.25,
|
689 |
+
"step": 85
|
690 |
},
|
691 |
{
|
692 |
+
"epoch": 86.0,
|
693 |
+
"eval_loss": 0.02184910513460636,
|
694 |
+
"eval_runtime": 0.2287,
|
695 |
+
"eval_samples_per_second": 34.986,
|
696 |
+
"eval_steps_per_second": 4.373,
|
697 |
+
"step": 86
|
698 |
+
},
|
699 |
+
{
|
700 |
+
"epoch": 87.0,
|
701 |
+
"eval_loss": 0.021228935569524765,
|
702 |
+
"eval_runtime": 0.2349,
|
703 |
+
"eval_samples_per_second": 34.051,
|
704 |
+
"eval_steps_per_second": 4.256,
|
705 |
+
"step": 87
|
706 |
+
},
|
707 |
+
{
|
708 |
+
"epoch": 88.0,
|
709 |
+
"eval_loss": 0.020517783239483833,
|
710 |
+
"eval_runtime": 0.2353,
|
711 |
+
"eval_samples_per_second": 34.002,
|
712 |
+
"eval_steps_per_second": 4.25,
|
713 |
+
"step": 88
|
714 |
+
},
|
715 |
+
{
|
716 |
+
"epoch": 89.0,
|
717 |
+
"eval_loss": 0.019832810387015343,
|
718 |
+
"eval_runtime": 0.2232,
|
719 |
+
"eval_samples_per_second": 35.839,
|
720 |
+
"eval_steps_per_second": 4.48,
|
721 |
+
"step": 89
|
722 |
+
},
|
723 |
+
{
|
724 |
+
"epoch": 90.0,
|
725 |
+
"eval_loss": 0.0191506277769804,
|
726 |
+
"eval_runtime": 0.2312,
|
727 |
+
"eval_samples_per_second": 34.605,
|
728 |
+
"eval_steps_per_second": 4.326,
|
729 |
+
"step": 90
|
730 |
+
},
|
731 |
+
{
|
732 |
+
"epoch": 91.0,
|
733 |
+
"eval_loss": 0.018617864698171616,
|
734 |
+
"eval_runtime": 0.2243,
|
735 |
+
"eval_samples_per_second": 35.667,
|
736 |
+
"eval_steps_per_second": 4.458,
|
737 |
+
"step": 91
|
738 |
+
},
|
739 |
+
{
|
740 |
+
"epoch": 92.0,
|
741 |
+
"eval_loss": 0.01811818592250347,
|
742 |
+
"eval_runtime": 0.2348,
|
743 |
+
"eval_samples_per_second": 34.07,
|
744 |
+
"eval_steps_per_second": 4.259,
|
745 |
+
"step": 92
|
746 |
+
},
|
747 |
+
{
|
748 |
+
"epoch": 93.0,
|
749 |
+
"eval_loss": 0.01765601523220539,
|
750 |
+
"eval_runtime": 0.2363,
|
751 |
+
"eval_samples_per_second": 33.853,
|
752 |
+
"eval_steps_per_second": 4.232,
|
753 |
+
"step": 93
|
754 |
+
},
|
755 |
+
{
|
756 |
+
"epoch": 94.0,
|
757 |
+
"eval_loss": 0.017278417944908142,
|
758 |
+
"eval_runtime": 0.2264,
|
759 |
+
"eval_samples_per_second": 35.331,
|
760 |
+
"eval_steps_per_second": 4.416,
|
761 |
+
"step": 94
|
762 |
+
},
|
763 |
+
{
|
764 |
+
"epoch": 95.0,
|
765 |
+
"eval_loss": 0.016984442248940468,
|
766 |
+
"eval_runtime": 0.2349,
|
767 |
+
"eval_samples_per_second": 34.053,
|
768 |
+
"eval_steps_per_second": 4.257,
|
769 |
+
"step": 95
|
770 |
+
},
|
771 |
+
{
|
772 |
+
"epoch": 96.0,
|
773 |
+
"eval_loss": 0.01675889454782009,
|
774 |
+
"eval_runtime": 0.2343,
|
775 |
+
"eval_samples_per_second": 34.141,
|
776 |
+
"eval_steps_per_second": 4.268,
|
777 |
+
"step": 96
|
778 |
+
},
|
779 |
+
{
|
780 |
+
"epoch": 97.0,
|
781 |
+
"eval_loss": 0.016593070700764656,
|
782 |
+
"eval_runtime": 0.2359,
|
783 |
+
"eval_samples_per_second": 33.915,
|
784 |
+
"eval_steps_per_second": 4.239,
|
785 |
+
"step": 97
|
786 |
+
},
|
787 |
+
{
|
788 |
+
"epoch": 98.0,
|
789 |
+
"eval_loss": 0.016466278582811356,
|
790 |
+
"eval_runtime": 0.2296,
|
791 |
+
"eval_samples_per_second": 34.851,
|
792 |
+
"eval_steps_per_second": 4.356,
|
793 |
+
"step": 98
|
794 |
+
},
|
795 |
+
{
|
796 |
+
"epoch": 99.0,
|
797 |
+
"eval_loss": 0.016385838389396667,
|
798 |
+
"eval_runtime": 0.2364,
|
799 |
+
"eval_samples_per_second": 33.84,
|
800 |
+
"eval_steps_per_second": 4.23,
|
801 |
+
"step": 99
|
802 |
+
},
|
803 |
+
{
|
804 |
+
"epoch": 100.0,
|
805 |
+
"learning_rate": 0.0,
|
806 |
+
"loss": 1.4009,
|
807 |
+
"step": 100
|
808 |
+
},
|
809 |
+
{
|
810 |
+
"epoch": 100.0,
|
811 |
+
"eval_loss": 0.016336046159267426,
|
812 |
+
"eval_runtime": 0.2203,
|
813 |
+
"eval_samples_per_second": 36.315,
|
814 |
+
"eval_steps_per_second": 4.539,
|
815 |
+
"step": 100
|
816 |
+
},
|
817 |
+
{
|
818 |
+
"epoch": 100.0,
|
819 |
+
"step": 100,
|
820 |
+
"total_flos": 487166312448000.0,
|
821 |
+
"train_loss": 1.40092041015625,
|
822 |
+
"train_runtime": 1064.353,
|
823 |
+
"train_samples_per_second": 0.752,
|
824 |
+
"train_steps_per_second": 0.094
|
825 |
}
|
826 |
],
|
827 |
"logging_steps": 100,
|
828 |
+
"max_steps": 100,
|
829 |
+
"num_train_epochs": 100,
|
830 |
"save_steps": 500,
|
831 |
+
"total_flos": 487166312448000.0,
|
832 |
"trial_name": null,
|
833 |
"trial_params": null
|
834 |
}
|