End of training
Browse files- README.md +2 -0
- all_results.json +15 -15
- eval_results.json +8 -8
- predict_results.json +3 -3
- predict_results.txt +38 -38
- runs/Jun03_15-23-46_a358b85c7679/events.out.tfevents.1717428885.a358b85c7679.170314.1 +3 -0
- train_results.json +4 -4
- trainer_state.json +202 -202
README.md
CHANGED
@@ -1,4 +1,6 @@
|
|
1 |
---
|
|
|
|
|
2 |
license: mit
|
3 |
base_model: indolem/indobert-base-uncased
|
4 |
tags:
|
|
|
1 |
---
|
2 |
+
language:
|
3 |
+
- id
|
4 |
license: mit
|
5 |
base_model: indolem/indobert-base-uncased
|
6 |
tags:
|
all_results.json
CHANGED
@@ -1,21 +1,21 @@
|
|
1 |
{
|
2 |
"accuracy": 0.9203187250996016,
|
3 |
"epoch": 20.0,
|
4 |
-
"eval_accuracy": 0.
|
5 |
-
"eval_f1": 0.
|
6 |
-
"eval_loss": 0.
|
7 |
-
"eval_precision": 0.
|
8 |
-
"eval_recall": 0.
|
9 |
-
"eval_runtime":
|
10 |
"eval_samples": 399,
|
11 |
-
"eval_samples_per_second":
|
12 |
-
"eval_steps_per_second":
|
13 |
-
"f1": 0.
|
14 |
-
"precision": 0.
|
15 |
-
"recall": 0.
|
16 |
-
"train_loss": 0.
|
17 |
-
"train_runtime":
|
18 |
"train_samples": 3645,
|
19 |
-
"train_samples_per_second":
|
20 |
-
"train_steps_per_second":
|
21 |
}
|
|
|
1 |
{
|
2 |
"accuracy": 0.9203187250996016,
|
3 |
"epoch": 20.0,
|
4 |
+
"eval_accuracy": 0.8796992481203008,
|
5 |
+
"eval_f1": 0.8563025210084034,
|
6 |
+
"eval_loss": 0.31680676341056824,
|
7 |
+
"eval_precision": 0.8529936381473334,
|
8 |
+
"eval_recall": 0.8598836152027641,
|
9 |
+
"eval_runtime": 1.8096,
|
10 |
"eval_samples": 399,
|
11 |
+
"eval_samples_per_second": 220.495,
|
12 |
+
"eval_steps_per_second": 27.631,
|
13 |
+
"f1": 0.9045572941422515,
|
14 |
+
"precision": 0.901511292239769,
|
15 |
+
"recall": 0.9077895947111239,
|
16 |
+
"train_loss": 0.2318932650519199,
|
17 |
+
"train_runtime": 643.2373,
|
18 |
"train_samples": 3645,
|
19 |
+
"train_samples_per_second": 113.333,
|
20 |
+
"train_steps_per_second": 3.793
|
21 |
}
|
eval_results.json
CHANGED
@@ -1,12 +1,12 @@
|
|
1 |
{
|
2 |
"epoch": 20.0,
|
3 |
-
"eval_accuracy": 0.
|
4 |
-
"eval_f1": 0.
|
5 |
-
"eval_loss": 0.
|
6 |
-
"eval_precision": 0.
|
7 |
-
"eval_recall": 0.
|
8 |
-
"eval_runtime":
|
9 |
"eval_samples": 399,
|
10 |
-
"eval_samples_per_second":
|
11 |
-
"eval_steps_per_second":
|
12 |
}
|
|
|
1 |
{
|
2 |
"epoch": 20.0,
|
3 |
+
"eval_accuracy": 0.8796992481203008,
|
4 |
+
"eval_f1": 0.8563025210084034,
|
5 |
+
"eval_loss": 0.31680676341056824,
|
6 |
+
"eval_precision": 0.8529936381473334,
|
7 |
+
"eval_recall": 0.8598836152027641,
|
8 |
+
"eval_runtime": 1.8096,
|
9 |
"eval_samples": 399,
|
10 |
+
"eval_samples_per_second": 220.495,
|
11 |
+
"eval_steps_per_second": 27.631
|
12 |
}
|
predict_results.json
CHANGED
@@ -1,6 +1,6 @@
|
|
1 |
{
|
2 |
"accuracy": 0.9203187250996016,
|
3 |
-
"f1": 0.
|
4 |
-
"precision": 0.
|
5 |
-
"recall": 0.
|
6 |
}
|
|
|
1 |
{
|
2 |
"accuracy": 0.9203187250996016,
|
3 |
+
"f1": 0.9045572941422515,
|
4 |
+
"precision": 0.901511292239769,
|
5 |
+
"recall": 0.9077895947111239
|
6 |
}
|
predict_results.txt
CHANGED
@@ -18,7 +18,7 @@ index prediction
|
|
18 |
16 1
|
19 |
17 1
|
20 |
18 1
|
21 |
-
19
|
22 |
20 1
|
23 |
21 0
|
24 |
22 1
|
@@ -39,9 +39,9 @@ index prediction
|
|
39 |
37 1
|
40 |
38 0
|
41 |
39 1
|
42 |
-
40
|
43 |
41 1
|
44 |
-
42
|
45 |
43 1
|
46 |
44 1
|
47 |
45 1
|
@@ -55,7 +55,7 @@ index prediction
|
|
55 |
53 1
|
56 |
54 1
|
57 |
55 1
|
58 |
-
56
|
59 |
57 1
|
60 |
58 1
|
61 |
59 1
|
@@ -70,17 +70,17 @@ index prediction
|
|
70 |
68 0
|
71 |
69 1
|
72 |
70 1
|
73 |
-
71
|
74 |
72 1
|
75 |
73 1
|
76 |
74 1
|
77 |
-
75
|
78 |
76 1
|
79 |
77 1
|
80 |
78 0
|
81 |
79 1
|
82 |
80 1
|
83 |
-
81
|
84 |
82 1
|
85 |
83 1
|
86 |
84 1
|
@@ -99,7 +99,7 @@ index prediction
|
|
99 |
97 1
|
100 |
98 1
|
101 |
99 0
|
102 |
-
100
|
103 |
101 1
|
104 |
102 1
|
105 |
103 1
|
@@ -113,7 +113,7 @@ index prediction
|
|
113 |
111 1
|
114 |
112 1
|
115 |
113 1
|
116 |
-
114
|
117 |
115 1
|
118 |
116 1
|
119 |
117 1
|
@@ -169,7 +169,7 @@ index prediction
|
|
169 |
167 1
|
170 |
168 1
|
171 |
169 1
|
172 |
-
170
|
173 |
171 1
|
174 |
172 1
|
175 |
173 1
|
@@ -215,7 +215,7 @@ index prediction
|
|
215 |
213 1
|
216 |
214 1
|
217 |
215 1
|
218 |
-
216
|
219 |
217 1
|
220 |
218 1
|
221 |
219 1
|
@@ -258,8 +258,8 @@ index prediction
|
|
258 |
256 1
|
259 |
257 1
|
260 |
258 1
|
261 |
-
259
|
262 |
-
260
|
263 |
261 1
|
264 |
262 1
|
265 |
263 1
|
@@ -286,11 +286,11 @@ index prediction
|
|
286 |
284 1
|
287 |
285 1
|
288 |
286 1
|
289 |
-
287
|
290 |
288 1
|
291 |
289 0
|
292 |
290 1
|
293 |
-
291
|
294 |
292 1
|
295 |
293 1
|
296 |
294 0
|
@@ -359,7 +359,7 @@ index prediction
|
|
359 |
357 0
|
360 |
358 0
|
361 |
359 0
|
362 |
-
360
|
363 |
361 0
|
364 |
362 0
|
365 |
363 0
|
@@ -372,8 +372,8 @@ index prediction
|
|
372 |
370 0
|
373 |
371 0
|
374 |
372 0
|
375 |
-
373
|
376 |
-
374
|
377 |
375 0
|
378 |
376 0
|
379 |
377 0
|
@@ -383,7 +383,7 @@ index prediction
|
|
383 |
381 0
|
384 |
382 0
|
385 |
383 0
|
386 |
-
384
|
387 |
385 1
|
388 |
386 0
|
389 |
387 0
|
@@ -418,7 +418,7 @@ index prediction
|
|
418 |
416 0
|
419 |
417 0
|
420 |
418 0
|
421 |
-
419
|
422 |
420 0
|
423 |
421 0
|
424 |
422 0
|
@@ -436,7 +436,7 @@ index prediction
|
|
436 |
434 0
|
437 |
435 0
|
438 |
436 0
|
439 |
-
437
|
440 |
438 0
|
441 |
439 0
|
442 |
440 0
|
@@ -485,7 +485,7 @@ index prediction
|
|
485 |
483 0
|
486 |
484 0
|
487 |
485 0
|
488 |
-
486
|
489 |
487 0
|
490 |
488 0
|
491 |
489 0
|
@@ -536,7 +536,7 @@ index prediction
|
|
536 |
534 0
|
537 |
535 0
|
538 |
536 0
|
539 |
-
537
|
540 |
538 0
|
541 |
539 0
|
542 |
540 0
|
@@ -569,7 +569,7 @@ index prediction
|
|
569 |
567 0
|
570 |
568 0
|
571 |
569 0
|
572 |
-
570
|
573 |
571 0
|
574 |
572 0
|
575 |
573 0
|
@@ -585,13 +585,13 @@ index prediction
|
|
585 |
583 0
|
586 |
584 0
|
587 |
585 0
|
588 |
-
586
|
589 |
587 0
|
590 |
588 0
|
591 |
589 0
|
592 |
590 0
|
593 |
591 0
|
594 |
-
592
|
595 |
593 0
|
596 |
594 0
|
597 |
595 0
|
@@ -626,7 +626,7 @@ index prediction
|
|
626 |
624 0
|
627 |
625 0
|
628 |
626 0
|
629 |
-
627
|
630 |
628 0
|
631 |
629 0
|
632 |
630 0
|
@@ -656,7 +656,7 @@ index prediction
|
|
656 |
654 0
|
657 |
655 0
|
658 |
656 0
|
659 |
-
657
|
660 |
658 1
|
661 |
659 0
|
662 |
660 0
|
@@ -672,7 +672,7 @@ index prediction
|
|
672 |
670 0
|
673 |
671 0
|
674 |
672 0
|
675 |
-
673
|
676 |
674 0
|
677 |
675 0
|
678 |
676 0
|
@@ -681,7 +681,7 @@ index prediction
|
|
681 |
679 0
|
682 |
680 0
|
683 |
681 0
|
684 |
-
682
|
685 |
683 0
|
686 |
684 0
|
687 |
685 0
|
@@ -716,9 +716,9 @@ index prediction
|
|
716 |
714 0
|
717 |
715 0
|
718 |
716 0
|
719 |
-
717
|
720 |
718 0
|
721 |
-
719
|
722 |
720 0
|
723 |
721 0
|
724 |
722 0
|
@@ -739,7 +739,7 @@ index prediction
|
|
739 |
737 0
|
740 |
738 0
|
741 |
739 0
|
742 |
-
740
|
743 |
741 0
|
744 |
742 0
|
745 |
743 0
|
@@ -753,7 +753,7 @@ index prediction
|
|
753 |
751 0
|
754 |
752 0
|
755 |
753 0
|
756 |
-
754
|
757 |
755 0
|
758 |
756 0
|
759 |
757 0
|
@@ -773,7 +773,7 @@ index prediction
|
|
773 |
771 0
|
774 |
772 0
|
775 |
773 0
|
776 |
-
774
|
777 |
775 0
|
778 |
776 0
|
779 |
777 0
|
@@ -811,7 +811,7 @@ index prediction
|
|
811 |
809 0
|
812 |
810 0
|
813 |
811 0
|
814 |
-
812
|
815 |
813 0
|
816 |
814 0
|
817 |
815 0
|
@@ -824,7 +824,7 @@ index prediction
|
|
824 |
822 0
|
825 |
823 0
|
826 |
824 0
|
827 |
-
825
|
828 |
826 0
|
829 |
827 0
|
830 |
828 0
|
@@ -851,7 +851,7 @@ index prediction
|
|
851 |
849 0
|
852 |
850 0
|
853 |
851 0
|
854 |
-
852
|
855 |
853 0
|
856 |
854 0
|
857 |
855 0
|
|
|
18 |
16 1
|
19 |
17 1
|
20 |
18 1
|
21 |
+
19 1
|
22 |
20 1
|
23 |
21 0
|
24 |
22 1
|
|
|
39 |
37 1
|
40 |
38 0
|
41 |
39 1
|
42 |
+
40 1
|
43 |
41 1
|
44 |
+
42 0
|
45 |
43 1
|
46 |
44 1
|
47 |
45 1
|
|
|
55 |
53 1
|
56 |
54 1
|
57 |
55 1
|
58 |
+
56 0
|
59 |
57 1
|
60 |
58 1
|
61 |
59 1
|
|
|
70 |
68 0
|
71 |
69 1
|
72 |
70 1
|
73 |
+
71 0
|
74 |
72 1
|
75 |
73 1
|
76 |
74 1
|
77 |
+
75 0
|
78 |
76 1
|
79 |
77 1
|
80 |
78 0
|
81 |
79 1
|
82 |
80 1
|
83 |
+
81 0
|
84 |
82 1
|
85 |
83 1
|
86 |
84 1
|
|
|
99 |
97 1
|
100 |
98 1
|
101 |
99 0
|
102 |
+
100 1
|
103 |
101 1
|
104 |
102 1
|
105 |
103 1
|
|
|
113 |
111 1
|
114 |
112 1
|
115 |
113 1
|
116 |
+
114 1
|
117 |
115 1
|
118 |
116 1
|
119 |
117 1
|
|
|
169 |
167 1
|
170 |
168 1
|
171 |
169 1
|
172 |
+
170 1
|
173 |
171 1
|
174 |
172 1
|
175 |
173 1
|
|
|
215 |
213 1
|
216 |
214 1
|
217 |
215 1
|
218 |
+
216 1
|
219 |
217 1
|
220 |
218 1
|
221 |
219 1
|
|
|
258 |
256 1
|
259 |
257 1
|
260 |
258 1
|
261 |
+
259 1
|
262 |
+
260 0
|
263 |
261 1
|
264 |
262 1
|
265 |
263 1
|
|
|
286 |
284 1
|
287 |
285 1
|
288 |
286 1
|
289 |
+
287 1
|
290 |
288 1
|
291 |
289 0
|
292 |
290 1
|
293 |
+
291 1
|
294 |
292 1
|
295 |
293 1
|
296 |
294 0
|
|
|
359 |
357 0
|
360 |
358 0
|
361 |
359 0
|
362 |
+
360 1
|
363 |
361 0
|
364 |
362 0
|
365 |
363 0
|
|
|
372 |
370 0
|
373 |
371 0
|
374 |
372 0
|
375 |
+
373 1
|
376 |
+
374 1
|
377 |
375 0
|
378 |
376 0
|
379 |
377 0
|
|
|
383 |
381 0
|
384 |
382 0
|
385 |
383 0
|
386 |
+
384 0
|
387 |
385 1
|
388 |
386 0
|
389 |
387 0
|
|
|
418 |
416 0
|
419 |
417 0
|
420 |
418 0
|
421 |
+
419 0
|
422 |
420 0
|
423 |
421 0
|
424 |
422 0
|
|
|
436 |
434 0
|
437 |
435 0
|
438 |
436 0
|
439 |
+
437 1
|
440 |
438 0
|
441 |
439 0
|
442 |
440 0
|
|
|
485 |
483 0
|
486 |
484 0
|
487 |
485 0
|
488 |
+
486 0
|
489 |
487 0
|
490 |
488 0
|
491 |
489 0
|
|
|
536 |
534 0
|
537 |
535 0
|
538 |
536 0
|
539 |
+
537 0
|
540 |
538 0
|
541 |
539 0
|
542 |
540 0
|
|
|
569 |
567 0
|
570 |
568 0
|
571 |
569 0
|
572 |
+
570 0
|
573 |
571 0
|
574 |
572 0
|
575 |
573 0
|
|
|
585 |
583 0
|
586 |
584 0
|
587 |
585 0
|
588 |
+
586 1
|
589 |
587 0
|
590 |
588 0
|
591 |
589 0
|
592 |
590 0
|
593 |
591 0
|
594 |
+
592 1
|
595 |
593 0
|
596 |
594 0
|
597 |
595 0
|
|
|
626 |
624 0
|
627 |
625 0
|
628 |
626 0
|
629 |
+
627 1
|
630 |
628 0
|
631 |
629 0
|
632 |
630 0
|
|
|
656 |
654 0
|
657 |
655 0
|
658 |
656 0
|
659 |
+
657 0
|
660 |
658 1
|
661 |
659 0
|
662 |
660 0
|
|
|
672 |
670 0
|
673 |
671 0
|
674 |
672 0
|
675 |
+
673 1
|
676 |
674 0
|
677 |
675 0
|
678 |
676 0
|
|
|
681 |
679 0
|
682 |
680 0
|
683 |
681 0
|
684 |
+
682 0
|
685 |
683 0
|
686 |
684 0
|
687 |
685 0
|
|
|
716 |
714 0
|
717 |
715 0
|
718 |
716 0
|
719 |
+
717 1
|
720 |
718 0
|
721 |
+
719 1
|
722 |
720 0
|
723 |
721 0
|
724 |
722 0
|
|
|
739 |
737 0
|
740 |
738 0
|
741 |
739 0
|
742 |
+
740 1
|
743 |
741 0
|
744 |
742 0
|
745 |
743 0
|
|
|
753 |
751 0
|
754 |
752 0
|
755 |
753 0
|
756 |
+
754 1
|
757 |
755 0
|
758 |
756 0
|
759 |
757 0
|
|
|
773 |
771 0
|
774 |
772 0
|
775 |
773 0
|
776 |
+
774 0
|
777 |
775 0
|
778 |
776 0
|
779 |
777 0
|
|
|
811 |
809 0
|
812 |
810 0
|
813 |
811 0
|
814 |
+
812 0
|
815 |
813 0
|
816 |
814 0
|
817 |
815 0
|
|
|
824 |
822 0
|
825 |
823 0
|
826 |
824 0
|
827 |
+
825 1
|
828 |
826 0
|
829 |
827 0
|
830 |
828 0
|
|
|
851 |
849 0
|
852 |
850 0
|
853 |
851 0
|
854 |
+
852 0
|
855 |
853 0
|
856 |
854 0
|
857 |
855 0
|
runs/Jun03_15-23-46_a358b85c7679/events.out.tfevents.1717428885.a358b85c7679.170314.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:230b1beb8a7077d9c3359fe928ab04829edae8c1bf07d6d7eb58b5ad4d3c671e
|
3 |
+
size 560
|
train_results.json
CHANGED
@@ -1,8 +1,8 @@
|
|
1 |
{
|
2 |
"epoch": 20.0,
|
3 |
-
"train_loss": 0.
|
4 |
-
"train_runtime":
|
5 |
"train_samples": 3645,
|
6 |
-
"train_samples_per_second":
|
7 |
-
"train_steps_per_second":
|
8 |
}
|
|
|
1 |
{
|
2 |
"epoch": 20.0,
|
3 |
+
"train_loss": 0.2318932650519199,
|
4 |
+
"train_runtime": 643.2373,
|
5 |
"train_samples": 3645,
|
6 |
+
"train_samples_per_second": 113.333,
|
7 |
+
"train_steps_per_second": 3.793
|
8 |
}
|
trainer_state.json
CHANGED
@@ -10,392 +10,392 @@
|
|
10 |
"log_history": [
|
11 |
{
|
12 |
"epoch": 1.0,
|
13 |
-
"grad_norm": 3.
|
14 |
"learning_rate": 4.75e-05,
|
15 |
-
"loss": 0.
|
16 |
"step": 122
|
17 |
},
|
18 |
{
|
19 |
"epoch": 1.0,
|
20 |
-
"eval_accuracy": 0.
|
21 |
-
"eval_f1": 0.
|
22 |
-
"eval_loss": 0.
|
23 |
-
"eval_precision": 0.
|
24 |
-
"eval_recall": 0.
|
25 |
-
"eval_runtime":
|
26 |
-
"eval_samples_per_second":
|
27 |
-
"eval_steps_per_second":
|
28 |
"step": 122
|
29 |
},
|
30 |
{
|
31 |
"epoch": 2.0,
|
32 |
-
"grad_norm": 3.
|
33 |
"learning_rate": 4.5e-05,
|
34 |
-
"loss": 0.
|
35 |
"step": 244
|
36 |
},
|
37 |
{
|
38 |
"epoch": 2.0,
|
39 |
-
"eval_accuracy": 0.
|
40 |
-
"eval_f1": 0.
|
41 |
-
"eval_loss": 0.
|
42 |
-
"eval_precision": 0.
|
43 |
-
"eval_recall": 0.
|
44 |
-
"eval_runtime":
|
45 |
-
"eval_samples_per_second":
|
46 |
-
"eval_steps_per_second":
|
47 |
"step": 244
|
48 |
},
|
49 |
{
|
50 |
"epoch": 3.0,
|
51 |
-
"grad_norm":
|
52 |
"learning_rate": 4.25e-05,
|
53 |
-
"loss": 0.
|
54 |
"step": 366
|
55 |
},
|
56 |
{
|
57 |
"epoch": 3.0,
|
58 |
-
"eval_accuracy": 0.
|
59 |
-
"eval_f1": 0.
|
60 |
-
"eval_loss": 0.
|
61 |
-
"eval_precision": 0.
|
62 |
-
"eval_recall": 0.
|
63 |
-
"eval_runtime":
|
64 |
-
"eval_samples_per_second":
|
65 |
-
"eval_steps_per_second":
|
66 |
"step": 366
|
67 |
},
|
68 |
{
|
69 |
"epoch": 4.0,
|
70 |
-
"grad_norm":
|
71 |
"learning_rate": 4e-05,
|
72 |
-
"loss": 0.
|
73 |
"step": 488
|
74 |
},
|
75 |
{
|
76 |
"epoch": 4.0,
|
77 |
-
"eval_accuracy": 0.
|
78 |
-
"eval_f1": 0.
|
79 |
-
"eval_loss": 0.
|
80 |
-
"eval_precision": 0.
|
81 |
-
"eval_recall": 0.
|
82 |
-
"eval_runtime":
|
83 |
-
"eval_samples_per_second":
|
84 |
-
"eval_steps_per_second":
|
85 |
"step": 488
|
86 |
},
|
87 |
{
|
88 |
"epoch": 5.0,
|
89 |
-
"grad_norm":
|
90 |
"learning_rate": 3.7500000000000003e-05,
|
91 |
-
"loss": 0.
|
92 |
"step": 610
|
93 |
},
|
94 |
{
|
95 |
"epoch": 5.0,
|
96 |
-
"eval_accuracy": 0.
|
97 |
-
"eval_f1": 0.
|
98 |
-
"eval_loss": 0.
|
99 |
-
"eval_precision": 0.
|
100 |
-
"eval_recall": 0.
|
101 |
-
"eval_runtime":
|
102 |
-
"eval_samples_per_second":
|
103 |
-
"eval_steps_per_second":
|
104 |
"step": 610
|
105 |
},
|
106 |
{
|
107 |
"epoch": 6.0,
|
108 |
-
"grad_norm": 2.
|
109 |
"learning_rate": 3.5e-05,
|
110 |
-
"loss": 0.
|
111 |
"step": 732
|
112 |
},
|
113 |
{
|
114 |
"epoch": 6.0,
|
115 |
-
"eval_accuracy": 0.
|
116 |
-
"eval_f1": 0.
|
117 |
-
"eval_loss": 0.
|
118 |
-
"eval_precision": 0.
|
119 |
-
"eval_recall": 0.
|
120 |
-
"eval_runtime":
|
121 |
-
"eval_samples_per_second":
|
122 |
-
"eval_steps_per_second":
|
123 |
"step": 732
|
124 |
},
|
125 |
{
|
126 |
"epoch": 7.0,
|
127 |
-
"grad_norm": 1.
|
128 |
"learning_rate": 3.2500000000000004e-05,
|
129 |
-
"loss": 0.
|
130 |
"step": 854
|
131 |
},
|
132 |
{
|
133 |
"epoch": 7.0,
|
134 |
-
"eval_accuracy": 0.
|
135 |
-
"eval_f1": 0.
|
136 |
-
"eval_loss": 0.
|
137 |
-
"eval_precision": 0.
|
138 |
-
"eval_recall": 0.
|
139 |
-
"eval_runtime":
|
140 |
-
"eval_samples_per_second":
|
141 |
-
"eval_steps_per_second":
|
142 |
"step": 854
|
143 |
},
|
144 |
{
|
145 |
"epoch": 8.0,
|
146 |
-
"grad_norm": 3.
|
147 |
"learning_rate": 3e-05,
|
148 |
-
"loss": 0.
|
149 |
"step": 976
|
150 |
},
|
151 |
{
|
152 |
"epoch": 8.0,
|
153 |
-
"eval_accuracy": 0.
|
154 |
-
"eval_f1": 0.
|
155 |
-
"eval_loss": 0.
|
156 |
-
"eval_precision": 0.
|
157 |
-
"eval_recall": 0.
|
158 |
-
"eval_runtime":
|
159 |
-
"eval_samples_per_second":
|
160 |
-
"eval_steps_per_second":
|
161 |
"step": 976
|
162 |
},
|
163 |
{
|
164 |
"epoch": 9.0,
|
165 |
-
"grad_norm":
|
166 |
"learning_rate": 2.7500000000000004e-05,
|
167 |
-
"loss": 0.
|
168 |
"step": 1098
|
169 |
},
|
170 |
{
|
171 |
"epoch": 9.0,
|
172 |
"eval_accuracy": 0.8847117794486216,
|
173 |
-
"eval_f1": 0.
|
174 |
-
"eval_loss": 0.
|
175 |
-
"eval_precision": 0.
|
176 |
-
"eval_recall": 0.
|
177 |
-
"eval_runtime":
|
178 |
-
"eval_samples_per_second":
|
179 |
-
"eval_steps_per_second":
|
180 |
"step": 1098
|
181 |
},
|
182 |
{
|
183 |
"epoch": 10.0,
|
184 |
-
"grad_norm": 3.
|
185 |
"learning_rate": 2.5e-05,
|
186 |
-
"loss": 0.
|
187 |
"step": 1220
|
188 |
},
|
189 |
{
|
190 |
"epoch": 10.0,
|
191 |
-
"eval_accuracy": 0.
|
192 |
-
"eval_f1": 0.
|
193 |
-
"eval_loss": 0.
|
194 |
-
"eval_precision": 0.
|
195 |
-
"eval_recall": 0.
|
196 |
-
"eval_runtime":
|
197 |
-
"eval_samples_per_second":
|
198 |
-
"eval_steps_per_second":
|
199 |
"step": 1220
|
200 |
},
|
201 |
{
|
202 |
"epoch": 11.0,
|
203 |
-
"grad_norm":
|
204 |
"learning_rate": 2.25e-05,
|
205 |
-
"loss": 0.
|
206 |
"step": 1342
|
207 |
},
|
208 |
{
|
209 |
"epoch": 11.0,
|
210 |
-
"eval_accuracy": 0.
|
211 |
-
"eval_f1": 0.
|
212 |
-
"eval_loss": 0.
|
213 |
-
"eval_precision": 0.
|
214 |
-
"eval_recall": 0.
|
215 |
-
"eval_runtime":
|
216 |
-
"eval_samples_per_second":
|
217 |
-
"eval_steps_per_second":
|
218 |
"step": 1342
|
219 |
},
|
220 |
{
|
221 |
"epoch": 12.0,
|
222 |
-
"grad_norm":
|
223 |
"learning_rate": 2e-05,
|
224 |
-
"loss": 0.
|
225 |
"step": 1464
|
226 |
},
|
227 |
{
|
228 |
"epoch": 12.0,
|
229 |
-
"eval_accuracy": 0.
|
230 |
-
"eval_f1": 0.
|
231 |
-
"eval_loss": 0.
|
232 |
-
"eval_precision": 0.
|
233 |
-
"eval_recall": 0.
|
234 |
-
"eval_runtime":
|
235 |
-
"eval_samples_per_second":
|
236 |
-
"eval_steps_per_second":
|
237 |
"step": 1464
|
238 |
},
|
239 |
{
|
240 |
"epoch": 13.0,
|
241 |
-
"grad_norm":
|
242 |
"learning_rate": 1.75e-05,
|
243 |
-
"loss": 0.
|
244 |
"step": 1586
|
245 |
},
|
246 |
{
|
247 |
"epoch": 13.0,
|
248 |
"eval_accuracy": 0.8796992481203008,
|
249 |
-
"eval_f1": 0.
|
250 |
-
"eval_loss": 0.
|
251 |
-
"eval_precision": 0.
|
252 |
-
"eval_recall": 0.
|
253 |
-
"eval_runtime":
|
254 |
-
"eval_samples_per_second":
|
255 |
-
"eval_steps_per_second":
|
256 |
"step": 1586
|
257 |
},
|
258 |
{
|
259 |
"epoch": 14.0,
|
260 |
-
"grad_norm":
|
261 |
"learning_rate": 1.5e-05,
|
262 |
-
"loss": 0.
|
263 |
"step": 1708
|
264 |
},
|
265 |
{
|
266 |
"epoch": 14.0,
|
267 |
-
"eval_accuracy": 0.
|
268 |
-
"eval_f1": 0.
|
269 |
-
"eval_loss": 0.
|
270 |
-
"eval_precision": 0.
|
271 |
-
"eval_recall": 0.
|
272 |
-
"eval_runtime":
|
273 |
-
"eval_samples_per_second":
|
274 |
-
"eval_steps_per_second":
|
275 |
"step": 1708
|
276 |
},
|
277 |
{
|
278 |
"epoch": 15.0,
|
279 |
-
"grad_norm": 0.
|
280 |
"learning_rate": 1.25e-05,
|
281 |
-
"loss": 0.
|
282 |
"step": 1830
|
283 |
},
|
284 |
{
|
285 |
"epoch": 15.0,
|
286 |
-
"eval_accuracy": 0.
|
287 |
-
"eval_f1": 0.
|
288 |
-
"eval_loss": 0.
|
289 |
-
"eval_precision": 0.
|
290 |
-
"eval_recall": 0.
|
291 |
-
"eval_runtime":
|
292 |
-
"eval_samples_per_second":
|
293 |
-
"eval_steps_per_second":
|
294 |
"step": 1830
|
295 |
},
|
296 |
{
|
297 |
"epoch": 16.0,
|
298 |
-
"grad_norm":
|
299 |
"learning_rate": 1e-05,
|
300 |
-
"loss": 0.
|
301 |
"step": 1952
|
302 |
},
|
303 |
{
|
304 |
"epoch": 16.0,
|
305 |
-
"eval_accuracy": 0.
|
306 |
-
"eval_f1": 0.
|
307 |
-
"eval_loss": 0.
|
308 |
-
"eval_precision": 0.
|
309 |
-
"eval_recall": 0.
|
310 |
-
"eval_runtime":
|
311 |
-
"eval_samples_per_second":
|
312 |
-
"eval_steps_per_second":
|
313 |
"step": 1952
|
314 |
},
|
315 |
{
|
316 |
"epoch": 17.0,
|
317 |
-
"grad_norm":
|
318 |
"learning_rate": 7.5e-06,
|
319 |
-
"loss": 0.
|
320 |
"step": 2074
|
321 |
},
|
322 |
{
|
323 |
"epoch": 17.0,
|
324 |
-
"eval_accuracy": 0.
|
325 |
-
"eval_f1": 0.
|
326 |
-
"eval_loss": 0.
|
327 |
-
"eval_precision": 0.
|
328 |
-
"eval_recall": 0.
|
329 |
-
"eval_runtime":
|
330 |
-
"eval_samples_per_second":
|
331 |
-
"eval_steps_per_second":
|
332 |
"step": 2074
|
333 |
},
|
334 |
{
|
335 |
"epoch": 18.0,
|
336 |
-
"grad_norm":
|
337 |
"learning_rate": 5e-06,
|
338 |
-
"loss": 0.
|
339 |
"step": 2196
|
340 |
},
|
341 |
{
|
342 |
"epoch": 18.0,
|
343 |
-
"eval_accuracy": 0.
|
344 |
-
"eval_f1": 0.
|
345 |
-
"eval_loss": 0.
|
346 |
-
"eval_precision": 0.
|
347 |
-
"eval_recall": 0.
|
348 |
-
"eval_runtime":
|
349 |
-
"eval_samples_per_second":
|
350 |
-
"eval_steps_per_second":
|
351 |
"step": 2196
|
352 |
},
|
353 |
{
|
354 |
"epoch": 19.0,
|
355 |
-
"grad_norm":
|
356 |
"learning_rate": 2.5e-06,
|
357 |
-
"loss": 0.
|
358 |
"step": 2318
|
359 |
},
|
360 |
{
|
361 |
"epoch": 19.0,
|
362 |
-
"eval_accuracy": 0.
|
363 |
-
"eval_f1": 0.
|
364 |
-
"eval_loss": 0.
|
365 |
-
"eval_precision": 0.
|
366 |
-
"eval_recall": 0.
|
367 |
-
"eval_runtime":
|
368 |
-
"eval_samples_per_second":
|
369 |
-
"eval_steps_per_second":
|
370 |
"step": 2318
|
371 |
},
|
372 |
{
|
373 |
"epoch": 20.0,
|
374 |
-
"grad_norm": 3.
|
375 |
"learning_rate": 0.0,
|
376 |
-
"loss": 0.
|
377 |
"step": 2440
|
378 |
},
|
379 |
{
|
380 |
"epoch": 20.0,
|
381 |
-
"eval_accuracy": 0.
|
382 |
-
"eval_f1": 0.
|
383 |
-
"eval_loss": 0.
|
384 |
-
"eval_precision": 0.
|
385 |
-
"eval_recall": 0.
|
386 |
-
"eval_runtime":
|
387 |
-
"eval_samples_per_second":
|
388 |
-
"eval_steps_per_second":
|
389 |
"step": 2440
|
390 |
},
|
391 |
{
|
392 |
"epoch": 20.0,
|
393 |
"step": 2440,
|
394 |
"total_flos": 8460375995160000.0,
|
395 |
-
"train_loss": 0.
|
396 |
-
"train_runtime":
|
397 |
-
"train_samples_per_second":
|
398 |
-
"train_steps_per_second":
|
399 |
}
|
400 |
],
|
401 |
"logging_steps": 500,
|
|
|
10 |
"log_history": [
|
11 |
{
|
12 |
"epoch": 1.0,
|
13 |
+
"grad_norm": 3.639183521270752,
|
14 |
"learning_rate": 4.75e-05,
|
15 |
+
"loss": 0.5413,
|
16 |
"step": 122
|
17 |
},
|
18 |
{
|
19 |
"epoch": 1.0,
|
20 |
+
"eval_accuracy": 0.7243107769423559,
|
21 |
+
"eval_f1": 0.6445578231292517,
|
22 |
+
"eval_loss": 0.5006802678108215,
|
23 |
+
"eval_precision": 0.6593400801180687,
|
24 |
+
"eval_recall": 0.6374340789234406,
|
25 |
+
"eval_runtime": 1.8003,
|
26 |
+
"eval_samples_per_second": 221.628,
|
27 |
+
"eval_steps_per_second": 27.773,
|
28 |
"step": 122
|
29 |
},
|
30 |
{
|
31 |
"epoch": 2.0,
|
32 |
+
"grad_norm": 3.4983344078063965,
|
33 |
"learning_rate": 4.5e-05,
|
34 |
+
"loss": 0.4584,
|
35 |
"step": 244
|
36 |
},
|
37 |
{
|
38 |
"epoch": 2.0,
|
39 |
+
"eval_accuracy": 0.8295739348370927,
|
40 |
+
"eval_f1": 0.7760942760942761,
|
41 |
+
"eval_loss": 0.3855762183666229,
|
42 |
+
"eval_precision": 0.8122789566755084,
|
43 |
+
"eval_recall": 0.7569103473358793,
|
44 |
+
"eval_runtime": 1.8373,
|
45 |
+
"eval_samples_per_second": 217.166,
|
46 |
+
"eval_steps_per_second": 27.214,
|
47 |
"step": 244
|
48 |
},
|
49 |
{
|
50 |
"epoch": 3.0,
|
51 |
+
"grad_norm": 5.97755765914917,
|
52 |
"learning_rate": 4.25e-05,
|
53 |
+
"loss": 0.3559,
|
54 |
"step": 366
|
55 |
},
|
56 |
{
|
57 |
"epoch": 3.0,
|
58 |
+
"eval_accuracy": 0.8571428571428571,
|
59 |
+
"eval_f1": 0.8079089841803424,
|
60 |
+
"eval_loss": 0.3407064378261566,
|
61 |
+
"eval_precision": 0.8638322884012539,
|
62 |
+
"eval_recall": 0.7814148026913984,
|
63 |
+
"eval_runtime": 1.8397,
|
64 |
+
"eval_samples_per_second": 216.877,
|
65 |
+
"eval_steps_per_second": 27.178,
|
66 |
"step": 366
|
67 |
},
|
68 |
{
|
69 |
"epoch": 4.0,
|
70 |
+
"grad_norm": 2.0363476276397705,
|
71 |
"learning_rate": 4e-05,
|
72 |
+
"loss": 0.2961,
|
73 |
"step": 488
|
74 |
},
|
75 |
{
|
76 |
"epoch": 4.0,
|
77 |
+
"eval_accuracy": 0.8696741854636592,
|
78 |
+
"eval_f1": 0.8419946387230413,
|
79 |
+
"eval_loss": 0.3088829517364502,
|
80 |
+
"eval_precision": 0.8437691365584814,
|
81 |
+
"eval_recall": 0.8402891434806329,
|
82 |
+
"eval_runtime": 1.8466,
|
83 |
+
"eval_samples_per_second": 216.069,
|
84 |
+
"eval_steps_per_second": 27.076,
|
85 |
"step": 488
|
86 |
},
|
87 |
{
|
88 |
"epoch": 5.0,
|
89 |
+
"grad_norm": 2.3318538665771484,
|
90 |
"learning_rate": 3.7500000000000003e-05,
|
91 |
+
"loss": 0.276,
|
92 |
"step": 610
|
93 |
},
|
94 |
{
|
95 |
"epoch": 5.0,
|
96 |
+
"eval_accuracy": 0.8621553884711779,
|
97 |
+
"eval_f1": 0.8365204824303285,
|
98 |
+
"eval_loss": 0.29173794388771057,
|
99 |
+
"eval_precision": 0.8313636363636363,
|
100 |
+
"eval_recall": 0.8424713584288053,
|
101 |
+
"eval_runtime": 1.8414,
|
102 |
+
"eval_samples_per_second": 216.677,
|
103 |
+
"eval_steps_per_second": 27.153,
|
104 |
"step": 610
|
105 |
},
|
106 |
{
|
107 |
"epoch": 6.0,
|
108 |
+
"grad_norm": 2.3067033290863037,
|
109 |
"learning_rate": 3.5e-05,
|
110 |
+
"loss": 0.2555,
|
111 |
"step": 732
|
112 |
},
|
113 |
{
|
114 |
"epoch": 6.0,
|
115 |
+
"eval_accuracy": 0.8696741854636592,
|
116 |
+
"eval_f1": 0.842789598108747,
|
117 |
+
"eval_loss": 0.29054704308509827,
|
118 |
+
"eval_precision": 0.842789598108747,
|
119 |
+
"eval_recall": 0.842789598108747,
|
120 |
+
"eval_runtime": 1.847,
|
121 |
+
"eval_samples_per_second": 216.025,
|
122 |
+
"eval_steps_per_second": 27.071,
|
123 |
"step": 732
|
124 |
},
|
125 |
{
|
126 |
"epoch": 7.0,
|
127 |
+
"grad_norm": 1.5437530279159546,
|
128 |
"learning_rate": 3.2500000000000004e-05,
|
129 |
+
"loss": 0.2427,
|
130 |
"step": 854
|
131 |
},
|
132 |
{
|
133 |
"epoch": 7.0,
|
134 |
+
"eval_accuracy": 0.8771929824561403,
|
135 |
+
"eval_f1": 0.84402249790578,
|
136 |
+
"eval_loss": 0.30313801765441895,
|
137 |
+
"eval_precision": 0.8669909824394875,
|
138 |
+
"eval_recall": 0.8281051100200036,
|
139 |
+
"eval_runtime": 1.8479,
|
140 |
+
"eval_samples_per_second": 215.922,
|
141 |
+
"eval_steps_per_second": 27.058,
|
142 |
"step": 854
|
143 |
},
|
144 |
{
|
145 |
"epoch": 8.0,
|
146 |
+
"grad_norm": 3.033709764480591,
|
147 |
"learning_rate": 3e-05,
|
148 |
+
"loss": 0.2219,
|
149 |
"step": 976
|
150 |
},
|
151 |
{
|
152 |
"epoch": 8.0,
|
153 |
+
"eval_accuracy": 0.8771929824561403,
|
154 |
+
"eval_f1": 0.8522278069611882,
|
155 |
+
"eval_loss": 0.2907596528530121,
|
156 |
+
"eval_precision": 0.8513631702756499,
|
157 |
+
"eval_recall": 0.8531096563011457,
|
158 |
+
"eval_runtime": 1.8468,
|
159 |
+
"eval_samples_per_second": 216.053,
|
160 |
+
"eval_steps_per_second": 27.074,
|
161 |
"step": 976
|
162 |
},
|
163 |
{
|
164 |
"epoch": 9.0,
|
165 |
+
"grad_norm": 2.670888900756836,
|
166 |
"learning_rate": 2.7500000000000004e-05,
|
167 |
+
"loss": 0.2158,
|
168 |
"step": 1098
|
169 |
},
|
170 |
{
|
171 |
"epoch": 9.0,
|
172 |
"eval_accuracy": 0.8847117794486216,
|
173 |
+
"eval_f1": 0.8539996181748759,
|
174 |
+
"eval_loss": 0.3083769381046295,
|
175 |
+
"eval_precision": 0.8759595959595959,
|
176 |
+
"eval_recall": 0.8384251682124022,
|
177 |
+
"eval_runtime": 1.856,
|
178 |
+
"eval_samples_per_second": 214.979,
|
179 |
+
"eval_steps_per_second": 26.94,
|
180 |
"step": 1098
|
181 |
},
|
182 |
{
|
183 |
"epoch": 10.0,
|
184 |
+
"grad_norm": 3.6058239936828613,
|
185 |
"learning_rate": 2.5e-05,
|
186 |
+
"loss": 0.2,
|
187 |
"step": 1220
|
188 |
},
|
189 |
{
|
190 |
"epoch": 10.0,
|
191 |
+
"eval_accuracy": 0.87468671679198,
|
192 |
+
"eval_f1": 0.8517301860990547,
|
193 |
+
"eval_loss": 0.29381993412971497,
|
194 |
+
"eval_precision": 0.8456788321167883,
|
195 |
+
"eval_recall": 0.8588379705400981,
|
196 |
+
"eval_runtime": 1.8468,
|
197 |
+
"eval_samples_per_second": 216.045,
|
198 |
+
"eval_steps_per_second": 27.073,
|
199 |
"step": 1220
|
200 |
},
|
201 |
{
|
202 |
"epoch": 11.0,
|
203 |
+
"grad_norm": 3.181007146835327,
|
204 |
"learning_rate": 2.25e-05,
|
205 |
+
"loss": 0.1885,
|
206 |
"step": 1342
|
207 |
},
|
208 |
{
|
209 |
"epoch": 11.0,
|
210 |
+
"eval_accuracy": 0.8771929824561403,
|
211 |
+
"eval_f1": 0.8514869535493182,
|
212 |
+
"eval_loss": 0.2976568639278412,
|
213 |
+
"eval_precision": 0.8523821128305106,
|
214 |
+
"eval_recall": 0.8506092016730314,
|
215 |
+
"eval_runtime": 1.8451,
|
216 |
+
"eval_samples_per_second": 216.253,
|
217 |
+
"eval_steps_per_second": 27.099,
|
218 |
"step": 1342
|
219 |
},
|
220 |
{
|
221 |
"epoch": 12.0,
|
222 |
+
"grad_norm": 3.1322133541107178,
|
223 |
"learning_rate": 2e-05,
|
224 |
+
"loss": 0.183,
|
225 |
"step": 1464
|
226 |
},
|
227 |
{
|
228 |
"epoch": 12.0,
|
229 |
+
"eval_accuracy": 0.8847117794486216,
|
230 |
+
"eval_f1": 0.8556621579112929,
|
231 |
+
"eval_loss": 0.30698344111442566,
|
232 |
+
"eval_precision": 0.871654421411703,
|
233 |
+
"eval_recall": 0.8434260774686306,
|
234 |
+
"eval_runtime": 1.8533,
|
235 |
+
"eval_samples_per_second": 215.295,
|
236 |
+
"eval_steps_per_second": 26.979,
|
237 |
"step": 1464
|
238 |
},
|
239 |
{
|
240 |
"epoch": 13.0,
|
241 |
+
"grad_norm": 1.6321003437042236,
|
242 |
"learning_rate": 1.75e-05,
|
243 |
+
"loss": 0.1752,
|
244 |
"step": 1586
|
245 |
},
|
246 |
{
|
247 |
"epoch": 13.0,
|
248 |
"eval_accuracy": 0.8796992481203008,
|
249 |
+
"eval_f1": 0.8569892473118279,
|
250 |
+
"eval_loss": 0.29585033655166626,
|
251 |
+
"eval_precision": 0.8522004241781549,
|
252 |
+
"eval_recall": 0.8623840698308783,
|
253 |
+
"eval_runtime": 1.846,
|
254 |
+
"eval_samples_per_second": 216.146,
|
255 |
+
"eval_steps_per_second": 27.086,
|
256 |
"step": 1586
|
257 |
},
|
258 |
{
|
259 |
"epoch": 14.0,
|
260 |
+
"grad_norm": 3.546229600906372,
|
261 |
"learning_rate": 1.5e-05,
|
262 |
+
"loss": 0.1558,
|
263 |
"step": 1708
|
264 |
},
|
265 |
{
|
266 |
"epoch": 14.0,
|
267 |
+
"eval_accuracy": 0.87468671679198,
|
268 |
+
"eval_f1": 0.8530841286673736,
|
269 |
+
"eval_loss": 0.3040328025817871,
|
270 |
+
"eval_precision": 0.8446597760551249,
|
271 |
+
"eval_recall": 0.8638388797963266,
|
272 |
+
"eval_runtime": 1.8508,
|
273 |
+
"eval_samples_per_second": 215.586,
|
274 |
+
"eval_steps_per_second": 27.016,
|
275 |
"step": 1708
|
276 |
},
|
277 |
{
|
278 |
"epoch": 15.0,
|
279 |
+
"grad_norm": 0.5455009937286377,
|
280 |
"learning_rate": 1.25e-05,
|
281 |
+
"loss": 0.1538,
|
282 |
"step": 1830
|
283 |
},
|
284 |
{
|
285 |
"epoch": 15.0,
|
286 |
+
"eval_accuracy": 0.8721804511278195,
|
287 |
+
"eval_f1": 0.8484099018899409,
|
288 |
+
"eval_loss": 0.30823931097984314,
|
289 |
+
"eval_precision": 0.8430645161290322,
|
290 |
+
"eval_recall": 0.8545644662665939,
|
291 |
+
"eval_runtime": 1.848,
|
292 |
+
"eval_samples_per_second": 215.904,
|
293 |
+
"eval_steps_per_second": 27.056,
|
294 |
"step": 1830
|
295 |
},
|
296 |
{
|
297 |
"epoch": 16.0,
|
298 |
+
"grad_norm": 2.4319658279418945,
|
299 |
"learning_rate": 1e-05,
|
300 |
+
"loss": 0.152,
|
301 |
"step": 1952
|
302 |
},
|
303 |
{
|
304 |
"epoch": 16.0,
|
305 |
+
"eval_accuracy": 0.8771929824561403,
|
306 |
+
"eval_f1": 0.8483536940081443,
|
307 |
+
"eval_loss": 0.30997762084007263,
|
308 |
+
"eval_precision": 0.8575792287132493,
|
309 |
+
"eval_recall": 0.8406073831605747,
|
310 |
+
"eval_runtime": 1.8455,
|
311 |
+
"eval_samples_per_second": 216.202,
|
312 |
+
"eval_steps_per_second": 27.093,
|
313 |
"step": 1952
|
314 |
},
|
315 |
{
|
316 |
"epoch": 17.0,
|
317 |
+
"grad_norm": 3.420119285583496,
|
318 |
"learning_rate": 7.5e-06,
|
319 |
+
"loss": 0.1436,
|
320 |
"step": 2074
|
321 |
},
|
322 |
{
|
323 |
"epoch": 17.0,
|
324 |
+
"eval_accuracy": 0.87468671679198,
|
325 |
+
"eval_f1": 0.8510304659498208,
|
326 |
+
"eval_loss": 0.31050172448158264,
|
327 |
+
"eval_precision": 0.8463237893248498,
|
328 |
+
"eval_recall": 0.8563375159119839,
|
329 |
+
"eval_runtime": 1.8478,
|
330 |
+
"eval_samples_per_second": 215.931,
|
331 |
+
"eval_steps_per_second": 27.059,
|
332 |
"step": 2074
|
333 |
},
|
334 |
{
|
335 |
"epoch": 18.0,
|
336 |
+
"grad_norm": 0.7008257508277893,
|
337 |
"learning_rate": 5e-06,
|
338 |
+
"loss": 0.1426,
|
339 |
"step": 2196
|
340 |
},
|
341 |
{
|
342 |
"epoch": 18.0,
|
343 |
+
"eval_accuracy": 0.87468671679198,
|
344 |
+
"eval_f1": 0.8503151260504201,
|
345 |
+
"eval_loss": 0.3118613362312317,
|
346 |
+
"eval_precision": 0.8470628455912955,
|
347 |
+
"eval_recall": 0.8538370612838698,
|
348 |
+
"eval_runtime": 1.8481,
|
349 |
+
"eval_samples_per_second": 215.903,
|
350 |
+
"eval_steps_per_second": 27.056,
|
351 |
"step": 2196
|
352 |
},
|
353 |
{
|
354 |
"epoch": 19.0,
|
355 |
+
"grad_norm": 2.8680572509765625,
|
356 |
"learning_rate": 2.5e-06,
|
357 |
+
"loss": 0.1398,
|
358 |
"step": 2318
|
359 |
},
|
360 |
{
|
361 |
"epoch": 19.0,
|
362 |
+
"eval_accuracy": 0.8796992481203008,
|
363 |
+
"eval_f1": 0.8569892473118279,
|
364 |
+
"eval_loss": 0.316354900598526,
|
365 |
+
"eval_precision": 0.8522004241781549,
|
366 |
+
"eval_recall": 0.8623840698308783,
|
367 |
+
"eval_runtime": 1.8465,
|
368 |
+
"eval_samples_per_second": 216.08,
|
369 |
+
"eval_steps_per_second": 27.078,
|
370 |
"step": 2318
|
371 |
},
|
372 |
{
|
373 |
"epoch": 20.0,
|
374 |
+
"grad_norm": 3.442784547805786,
|
375 |
"learning_rate": 0.0,
|
376 |
+
"loss": 0.14,
|
377 |
"step": 2440
|
378 |
},
|
379 |
{
|
380 |
"epoch": 20.0,
|
381 |
+
"eval_accuracy": 0.8796992481203008,
|
382 |
+
"eval_f1": 0.8563025210084034,
|
383 |
+
"eval_loss": 0.31680676341056824,
|
384 |
+
"eval_precision": 0.8529936381473334,
|
385 |
+
"eval_recall": 0.8598836152027641,
|
386 |
+
"eval_runtime": 1.8511,
|
387 |
+
"eval_samples_per_second": 215.549,
|
388 |
+
"eval_steps_per_second": 27.011,
|
389 |
"step": 2440
|
390 |
},
|
391 |
{
|
392 |
"epoch": 20.0,
|
393 |
"step": 2440,
|
394 |
"total_flos": 8460375995160000.0,
|
395 |
+
"train_loss": 0.2318932650519199,
|
396 |
+
"train_runtime": 643.2373,
|
397 |
+
"train_samples_per_second": 113.333,
|
398 |
+
"train_steps_per_second": 3.793
|
399 |
}
|
400 |
],
|
401 |
"logging_steps": 500,
|