End of training
Browse files- README.md +2 -0
- all_results.json +16 -16
- eval_results.json +8 -8
- predict_results.json +4 -4
- predict_results.txt +38 -38
- runs/Jun03_13-00-03_a358b85c7679/events.out.tfevents.1717420243.a358b85c7679.93606.1 +3 -0
- train_results.json +4 -4
- trainer_state.json +200 -200
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.
|
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": 3638,
|
19 |
-
"train_samples_per_second":
|
20 |
-
"train_steps_per_second":
|
21 |
}
|
|
|
1 |
{
|
2 |
+
"accuracy": 0.897131552917903,
|
3 |
"epoch": 20.0,
|
4 |
+
"eval_accuracy": 0.9072681704260651,
|
5 |
+
"eval_f1": 0.8884169154604891,
|
6 |
+
"eval_loss": 0.2881532311439514,
|
7 |
+
"eval_precision": 0.8874630556728391,
|
8 |
+
"eval_recall": 0.8893889798145117,
|
9 |
+
"eval_runtime": 1.7985,
|
10 |
"eval_samples": 399,
|
11 |
+
"eval_samples_per_second": 221.847,
|
12 |
+
"eval_steps_per_second": 27.8,
|
13 |
+
"f1": 0.8762860397036814,
|
14 |
+
"precision": 0.8762860397036814,
|
15 |
+
"recall": 0.8762860397036814,
|
16 |
+
"train_loss": 0.2206378909408069,
|
17 |
+
"train_runtime": 624.8021,
|
18 |
"train_samples": 3638,
|
19 |
+
"train_samples_per_second": 116.453,
|
20 |
+
"train_steps_per_second": 3.905
|
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": 0.9072681704260651,
|
4 |
+
"eval_f1": 0.8884169154604891,
|
5 |
+
"eval_loss": 0.2881532311439514,
|
6 |
+
"eval_precision": 0.8874630556728391,
|
7 |
+
"eval_recall": 0.8893889798145117,
|
8 |
+
"eval_runtime": 1.7985,
|
9 |
"eval_samples": 399,
|
10 |
+
"eval_samples_per_second": 221.847,
|
11 |
+
"eval_steps_per_second": 27.8
|
12 |
}
|
predict_results.json
CHANGED
@@ -1,6 +1,6 @@
|
|
1 |
{
|
2 |
-
"accuracy": 0.
|
3 |
-
"f1": 0.
|
4 |
-
"precision": 0.
|
5 |
-
"recall": 0.
|
6 |
}
|
|
|
1 |
{
|
2 |
+
"accuracy": 0.897131552917903,
|
3 |
+
"f1": 0.8762860397036814,
|
4 |
+
"precision": 0.8762860397036814,
|
5 |
+
"recall": 0.8762860397036814
|
6 |
}
|
predict_results.txt
CHANGED
@@ -12,7 +12,7 @@ index prediction
|
|
12 |
10 1
|
13 |
11 1
|
14 |
12 1
|
15 |
-
13
|
16 |
14 1
|
17 |
15 0
|
18 |
16 1
|
@@ -28,7 +28,7 @@ index prediction
|
|
28 |
26 1
|
29 |
27 1
|
30 |
28 1
|
31 |
-
29
|
32 |
30 1
|
33 |
31 1
|
34 |
32 1
|
@@ -49,7 +49,7 @@ index prediction
|
|
49 |
47 1
|
50 |
48 1
|
51 |
49 0
|
52 |
-
50
|
53 |
51 1
|
54 |
52 0
|
55 |
53 1
|
@@ -58,7 +58,7 @@ index prediction
|
|
58 |
56 1
|
59 |
57 0
|
60 |
58 1
|
61 |
-
59
|
62 |
60 1
|
63 |
61 1
|
64 |
62 1
|
@@ -78,7 +78,7 @@ index prediction
|
|
78 |
76 1
|
79 |
77 1
|
80 |
78 1
|
81 |
-
79
|
82 |
80 0
|
83 |
81 1
|
84 |
82 1
|
@@ -90,16 +90,16 @@ index prediction
|
|
90 |
88 1
|
91 |
89 1
|
92 |
90 1
|
93 |
-
91
|
94 |
-
92
|
95 |
93 1
|
96 |
94 1
|
97 |
95 1
|
98 |
96 1
|
99 |
-
97
|
100 |
98 1
|
101 |
99 0
|
102 |
-
100
|
103 |
101 0
|
104 |
102 1
|
105 |
103 1
|
@@ -180,7 +180,7 @@ index prediction
|
|
180 |
178 1
|
181 |
179 1
|
182 |
180 1
|
183 |
-
181
|
184 |
182 1
|
185 |
183 1
|
186 |
184 1
|
@@ -224,12 +224,12 @@ index prediction
|
|
224 |
222 1
|
225 |
223 1
|
226 |
224 0
|
227 |
-
225
|
228 |
226 0
|
229 |
227 0
|
230 |
-
228
|
231 |
229 0
|
232 |
-
230
|
233 |
231 1
|
234 |
232 1
|
235 |
233 1
|
@@ -271,8 +271,8 @@ index prediction
|
|
271 |
269 1
|
272 |
270 1
|
273 |
271 1
|
274 |
-
272
|
275 |
-
273
|
276 |
274 1
|
277 |
275 1
|
278 |
276 1
|
@@ -329,7 +329,7 @@ index prediction
|
|
329 |
327 0
|
330 |
328 1
|
331 |
329 0
|
332 |
-
330
|
333 |
331 0
|
334 |
332 0
|
335 |
333 0
|
@@ -365,7 +365,7 @@ index prediction
|
|
365 |
363 0
|
366 |
364 1
|
367 |
365 0
|
368 |
-
366
|
369 |
367 0
|
370 |
368 0
|
371 |
369 0
|
@@ -375,7 +375,7 @@ index prediction
|
|
375 |
373 0
|
376 |
374 0
|
377 |
375 0
|
378 |
-
376
|
379 |
377 0
|
380 |
378 0
|
381 |
379 0
|
@@ -419,8 +419,8 @@ index prediction
|
|
419 |
417 0
|
420 |
418 0
|
421 |
419 0
|
422 |
-
420
|
423 |
-
421
|
424 |
422 0
|
425 |
423 0
|
426 |
424 0
|
@@ -454,7 +454,7 @@ index prediction
|
|
454 |
452 0
|
455 |
453 0
|
456 |
454 0
|
457 |
-
455
|
458 |
456 0
|
459 |
457 0
|
460 |
458 0
|
@@ -470,7 +470,7 @@ index prediction
|
|
470 |
468 0
|
471 |
469 0
|
472 |
470 0
|
473 |
-
471
|
474 |
472 0
|
475 |
473 0
|
476 |
474 0
|
@@ -610,7 +610,7 @@ index prediction
|
|
610 |
608 1
|
611 |
609 0
|
612 |
610 1
|
613 |
-
611
|
614 |
612 0
|
615 |
613 0
|
616 |
614 0
|
@@ -625,9 +625,9 @@ index prediction
|
|
625 |
623 0
|
626 |
624 0
|
627 |
625 0
|
628 |
-
626
|
629 |
627 0
|
630 |
-
628
|
631 |
629 0
|
632 |
630 0
|
633 |
631 0
|
@@ -662,7 +662,7 @@ index prediction
|
|
662 |
660 0
|
663 |
661 0
|
664 |
662 0
|
665 |
-
663
|
666 |
664 0
|
667 |
665 0
|
668 |
666 0
|
@@ -727,7 +727,7 @@ index prediction
|
|
727 |
725 0
|
728 |
726 0
|
729 |
727 0
|
730 |
-
728
|
731 |
729 0
|
732 |
730 0
|
733 |
731 0
|
@@ -764,19 +764,19 @@ index prediction
|
|
764 |
762 0
|
765 |
763 0
|
766 |
764 0
|
767 |
-
765
|
768 |
766 0
|
769 |
767 0
|
770 |
768 0
|
771 |
769 0
|
772 |
770 1
|
773 |
771 0
|
774 |
-
772
|
775 |
773 0
|
776 |
774 0
|
777 |
775 0
|
778 |
776 0
|
779 |
-
777
|
780 |
778 0
|
781 |
779 0
|
782 |
780 0
|
@@ -799,7 +799,7 @@ index prediction
|
|
799 |
797 0
|
800 |
798 0
|
801 |
799 0
|
802 |
-
800
|
803 |
801 0
|
804 |
802 0
|
805 |
803 0
|
@@ -818,7 +818,7 @@ index prediction
|
|
818 |
816 0
|
819 |
817 0
|
820 |
818 0
|
821 |
-
819
|
822 |
820 0
|
823 |
821 0
|
824 |
822 0
|
@@ -893,7 +893,7 @@ index prediction
|
|
893 |
891 0
|
894 |
892 0
|
895 |
893 0
|
896 |
-
894
|
897 |
895 0
|
898 |
896 0
|
899 |
897 1
|
@@ -905,13 +905,13 @@ index prediction
|
|
905 |
903 0
|
906 |
904 0
|
907 |
905 0
|
908 |
-
906
|
909 |
907 1
|
910 |
908 0
|
911 |
909 0
|
912 |
910 0
|
913 |
911 0
|
914 |
-
912
|
915 |
913 0
|
916 |
914 0
|
917 |
915 0
|
@@ -949,7 +949,7 @@ index prediction
|
|
949 |
947 0
|
950 |
948 0
|
951 |
949 0
|
952 |
-
950
|
953 |
951 0
|
954 |
952 0
|
955 |
953 0
|
@@ -968,7 +968,7 @@ index prediction
|
|
968 |
966 0
|
969 |
967 0
|
970 |
968 0
|
971 |
-
969
|
972 |
970 0
|
973 |
971 0
|
974 |
972 0
|
@@ -991,7 +991,7 @@ index prediction
|
|
991 |
989 0
|
992 |
990 0
|
993 |
991 0
|
994 |
-
992
|
995 |
993 0
|
996 |
994 0
|
997 |
995 0
|
|
|
12 |
10 1
|
13 |
11 1
|
14 |
12 1
|
15 |
+
13 0
|
16 |
14 1
|
17 |
15 0
|
18 |
16 1
|
|
|
28 |
26 1
|
29 |
27 1
|
30 |
28 1
|
31 |
+
29 1
|
32 |
30 1
|
33 |
31 1
|
34 |
32 1
|
|
|
49 |
47 1
|
50 |
48 1
|
51 |
49 0
|
52 |
+
50 0
|
53 |
51 1
|
54 |
52 0
|
55 |
53 1
|
|
|
58 |
56 1
|
59 |
57 0
|
60 |
58 1
|
61 |
+
59 0
|
62 |
60 1
|
63 |
61 1
|
64 |
62 1
|
|
|
78 |
76 1
|
79 |
77 1
|
80 |
78 1
|
81 |
+
79 0
|
82 |
80 0
|
83 |
81 1
|
84 |
82 1
|
|
|
90 |
88 1
|
91 |
89 1
|
92 |
90 1
|
93 |
+
91 0
|
94 |
+
92 0
|
95 |
93 1
|
96 |
94 1
|
97 |
95 1
|
98 |
96 1
|
99 |
+
97 0
|
100 |
98 1
|
101 |
99 0
|
102 |
+
100 0
|
103 |
101 0
|
104 |
102 1
|
105 |
103 1
|
|
|
180 |
178 1
|
181 |
179 1
|
182 |
180 1
|
183 |
+
181 0
|
184 |
182 1
|
185 |
183 1
|
186 |
184 1
|
|
|
224 |
222 1
|
225 |
223 1
|
226 |
224 0
|
227 |
+
225 0
|
228 |
226 0
|
229 |
227 0
|
230 |
+
228 0
|
231 |
229 0
|
232 |
+
230 0
|
233 |
231 1
|
234 |
232 1
|
235 |
233 1
|
|
|
271 |
269 1
|
272 |
270 1
|
273 |
271 1
|
274 |
+
272 0
|
275 |
+
273 1
|
276 |
274 1
|
277 |
275 1
|
278 |
276 1
|
|
|
329 |
327 0
|
330 |
328 1
|
331 |
329 0
|
332 |
+
330 0
|
333 |
331 0
|
334 |
332 0
|
335 |
333 0
|
|
|
365 |
363 0
|
366 |
364 1
|
367 |
365 0
|
368 |
+
366 0
|
369 |
367 0
|
370 |
368 0
|
371 |
369 0
|
|
|
375 |
373 0
|
376 |
374 0
|
377 |
375 0
|
378 |
+
376 0
|
379 |
377 0
|
380 |
378 0
|
381 |
379 0
|
|
|
419 |
417 0
|
420 |
418 0
|
421 |
419 0
|
422 |
+
420 0
|
423 |
+
421 0
|
424 |
422 0
|
425 |
423 0
|
426 |
424 0
|
|
|
454 |
452 0
|
455 |
453 0
|
456 |
454 0
|
457 |
+
455 0
|
458 |
456 0
|
459 |
457 0
|
460 |
458 0
|
|
|
470 |
468 0
|
471 |
469 0
|
472 |
470 0
|
473 |
+
471 1
|
474 |
472 0
|
475 |
473 0
|
476 |
474 0
|
|
|
610 |
608 1
|
611 |
609 0
|
612 |
610 1
|
613 |
+
611 0
|
614 |
612 0
|
615 |
613 0
|
616 |
614 0
|
|
|
625 |
623 0
|
626 |
624 0
|
627 |
625 0
|
628 |
+
626 0
|
629 |
627 0
|
630 |
+
628 0
|
631 |
629 0
|
632 |
630 0
|
633 |
631 0
|
|
|
662 |
660 0
|
663 |
661 0
|
664 |
662 0
|
665 |
+
663 0
|
666 |
664 0
|
667 |
665 0
|
668 |
666 0
|
|
|
727 |
725 0
|
728 |
726 0
|
729 |
727 0
|
730 |
+
728 0
|
731 |
729 0
|
732 |
730 0
|
733 |
731 0
|
|
|
764 |
762 0
|
765 |
763 0
|
766 |
764 0
|
767 |
+
765 0
|
768 |
766 0
|
769 |
767 0
|
770 |
768 0
|
771 |
769 0
|
772 |
770 1
|
773 |
771 0
|
774 |
+
772 1
|
775 |
773 0
|
776 |
774 0
|
777 |
775 0
|
778 |
776 0
|
779 |
+
777 1
|
780 |
778 0
|
781 |
779 0
|
782 |
780 0
|
|
|
799 |
797 0
|
800 |
798 0
|
801 |
799 0
|
802 |
+
800 1
|
803 |
801 0
|
804 |
802 0
|
805 |
803 0
|
|
|
818 |
816 0
|
819 |
817 0
|
820 |
818 0
|
821 |
+
819 0
|
822 |
820 0
|
823 |
821 0
|
824 |
822 0
|
|
|
893 |
891 0
|
894 |
892 0
|
895 |
893 0
|
896 |
+
894 1
|
897 |
895 0
|
898 |
896 0
|
899 |
897 1
|
|
|
905 |
903 0
|
906 |
904 0
|
907 |
905 0
|
908 |
+
906 0
|
909 |
907 1
|
910 |
908 0
|
911 |
909 0
|
912 |
910 0
|
913 |
911 0
|
914 |
+
912 0
|
915 |
913 0
|
916 |
914 0
|
917 |
915 0
|
|
|
949 |
947 0
|
950 |
948 0
|
951 |
949 0
|
952 |
+
950 0
|
953 |
951 0
|
954 |
952 0
|
955 |
953 0
|
|
|
968 |
966 0
|
969 |
967 0
|
970 |
968 0
|
971 |
+
969 0
|
972 |
970 0
|
973 |
971 0
|
974 |
972 0
|
|
|
991 |
989 0
|
992 |
990 0
|
993 |
991 0
|
994 |
+
992 0
|
995 |
993 0
|
996 |
994 0
|
997 |
995 0
|
runs/Jun03_13-00-03_a358b85c7679/events.out.tfevents.1717420243.a358b85c7679.93606.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d57fb59c0f550f9bc1db0d79869ca08aff8fe34cb4137c1133773b37f468ce16
|
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": 3638,
|
6 |
-
"train_samples_per_second":
|
7 |
-
"train_steps_per_second":
|
8 |
}
|
|
|
1 |
{
|
2 |
"epoch": 20.0,
|
3 |
+
"train_loss": 0.2206378909408069,
|
4 |
+
"train_runtime": 624.8021,
|
5 |
"train_samples": 3638,
|
6 |
+
"train_samples_per_second": 116.453,
|
7 |
+
"train_steps_per_second": 3.905
|
8 |
}
|
trainer_state.json
CHANGED
@@ -10,392 +10,392 @@
|
|
10 |
"log_history": [
|
11 |
{
|
12 |
"epoch": 1.0,
|
13 |
-
"grad_norm": 4.
|
14 |
"learning_rate": 4.75e-05,
|
15 |
"loss": 0.5417,
|
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":
|
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": 0.
|
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":
|
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.
|
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":
|
185 |
"learning_rate": 2.5e-05,
|
186 |
-
"loss": 0.
|
187 |
"step": 1220
|
188 |
},
|
189 |
{
|
190 |
"epoch": 10.0,
|
191 |
"eval_accuracy": 0.9072681704260651,
|
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": 0.899749373433584,
|
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.
|
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": 0.9047619047619048,
|
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":
|
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": 8444128359504000.0,
|
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": 4.196406364440918,
|
14 |
"learning_rate": 4.75e-05,
|
15 |
"loss": 0.5417,
|
16 |
"step": 122
|
17 |
},
|
18 |
{
|
19 |
"epoch": 1.0,
|
20 |
+
"eval_accuracy": 0.7543859649122807,
|
21 |
+
"eval_f1": 0.6730602006688964,
|
22 |
+
"eval_loss": 0.47316503524780273,
|
23 |
+
"eval_precision": 0.7027985359158151,
|
24 |
+
"eval_recall": 0.6612111292962357,
|
25 |
+
"eval_runtime": 1.7797,
|
26 |
+
"eval_samples_per_second": 224.194,
|
27 |
+
"eval_steps_per_second": 28.094,
|
28 |
"step": 122
|
29 |
},
|
30 |
{
|
31 |
"epoch": 2.0,
|
32 |
+
"grad_norm": 3.380220651626587,
|
33 |
"learning_rate": 4.5e-05,
|
34 |
+
"loss": 0.4395,
|
35 |
"step": 244
|
36 |
},
|
37 |
{
|
38 |
"epoch": 2.0,
|
39 |
+
"eval_accuracy": 0.7919799498746867,
|
40 |
+
"eval_f1": 0.7705259948585406,
|
41 |
+
"eval_loss": 0.4128379225730896,
|
42 |
+
"eval_precision": 0.7612839958158996,
|
43 |
+
"eval_recall": 0.8028277868703401,
|
44 |
+
"eval_runtime": 1.7767,
|
45 |
+
"eval_samples_per_second": 224.574,
|
46 |
+
"eval_steps_per_second": 28.142,
|
47 |
"step": 244
|
48 |
},
|
49 |
{
|
50 |
"epoch": 3.0,
|
51 |
+
"grad_norm": 2.2583518028259277,
|
52 |
"learning_rate": 4.25e-05,
|
53 |
+
"loss": 0.3319,
|
54 |
"step": 366
|
55 |
},
|
56 |
{
|
57 |
"epoch": 3.0,
|
58 |
+
"eval_accuracy": 0.8646616541353384,
|
59 |
+
"eval_f1": 0.8315033783783784,
|
60 |
+
"eval_loss": 0.32298392057418823,
|
61 |
+
"eval_precision": 0.8438775510204082,
|
62 |
+
"eval_recall": 0.8217403164211674,
|
63 |
+
"eval_runtime": 1.7811,
|
64 |
+
"eval_samples_per_second": 224.023,
|
65 |
+
"eval_steps_per_second": 28.073,
|
66 |
"step": 366
|
67 |
},
|
68 |
{
|
69 |
"epoch": 4.0,
|
70 |
+
"grad_norm": 0.8704787492752075,
|
71 |
"learning_rate": 4e-05,
|
72 |
+
"loss": 0.2873,
|
73 |
"step": 488
|
74 |
},
|
75 |
{
|
76 |
"epoch": 4.0,
|
77 |
+
"eval_accuracy": 0.8521303258145363,
|
78 |
+
"eval_f1": 0.8237962290701417,
|
79 |
+
"eval_loss": 0.322201669216156,
|
80 |
+
"eval_precision": 0.8201159969225307,
|
81 |
+
"eval_recall": 0.8278777959629023,
|
82 |
+
"eval_runtime": 1.7743,
|
83 |
+
"eval_samples_per_second": 224.873,
|
84 |
+
"eval_steps_per_second": 28.18,
|
85 |
"step": 488
|
86 |
},
|
87 |
{
|
88 |
"epoch": 5.0,
|
89 |
+
"grad_norm": 0.8079779148101807,
|
90 |
"learning_rate": 3.7500000000000003e-05,
|
91 |
+
"loss": 0.2571,
|
92 |
"step": 610
|
93 |
},
|
94 |
{
|
95 |
"epoch": 5.0,
|
96 |
+
"eval_accuracy": 0.8721804511278195,
|
97 |
+
"eval_f1": 0.8484099018899409,
|
98 |
+
"eval_loss": 0.29681602120399475,
|
99 |
+
"eval_precision": 0.8430645161290322,
|
100 |
+
"eval_recall": 0.8545644662665939,
|
101 |
+
"eval_runtime": 1.7796,
|
102 |
+
"eval_samples_per_second": 224.208,
|
103 |
+
"eval_steps_per_second": 28.096,
|
104 |
"step": 610
|
105 |
},
|
106 |
{
|
107 |
"epoch": 6.0,
|
108 |
+
"grad_norm": 2.8642373085021973,
|
109 |
"learning_rate": 3.5e-05,
|
110 |
+
"loss": 0.2443,
|
111 |
"step": 732
|
112 |
},
|
113 |
{
|
114 |
"epoch": 6.0,
|
115 |
+
"eval_accuracy": 0.8671679197994987,
|
116 |
+
"eval_f1": 0.8466330637850383,
|
117 |
+
"eval_loss": 0.29177311062812805,
|
118 |
+
"eval_precision": 0.8353276671885485,
|
119 |
+
"eval_recall": 0.8635206401163849,
|
120 |
+
"eval_runtime": 1.7765,
|
121 |
+
"eval_samples_per_second": 224.594,
|
122 |
+
"eval_steps_per_second": 28.145,
|
123 |
"step": 732
|
124 |
},
|
125 |
{
|
126 |
"epoch": 7.0,
|
127 |
+
"grad_norm": 0.3272399306297302,
|
128 |
"learning_rate": 3.2500000000000004e-05,
|
129 |
+
"loss": 0.2256,
|
130 |
"step": 854
|
131 |
},
|
132 |
{
|
133 |
"epoch": 7.0,
|
134 |
+
"eval_accuracy": 0.8646616541353384,
|
135 |
+
"eval_f1": 0.8447157518450185,
|
136 |
+
"eval_loss": 0.2981509566307068,
|
137 |
+
"eval_precision": 0.8325401217487549,
|
138 |
+
"eval_recall": 0.864248045099109,
|
139 |
+
"eval_runtime": 1.7799,
|
140 |
+
"eval_samples_per_second": 224.168,
|
141 |
+
"eval_steps_per_second": 28.091,
|
142 |
"step": 854
|
143 |
},
|
144 |
{
|
145 |
"epoch": 8.0,
|
146 |
+
"grad_norm": 2.9290239810943604,
|
147 |
"learning_rate": 3e-05,
|
148 |
+
"loss": 0.2172,
|
149 |
"step": 976
|
150 |
},
|
151 |
{
|
152 |
"epoch": 8.0,
|
153 |
+
"eval_accuracy": 0.8922305764411027,
|
154 |
+
"eval_f1": 0.8646934961080748,
|
155 |
+
"eval_loss": 0.2722471356391907,
|
156 |
+
"eval_precision": 0.882551000198059,
|
157 |
+
"eval_recall": 0.8512456810329151,
|
158 |
+
"eval_runtime": 1.7818,
|
159 |
+
"eval_samples_per_second": 223.935,
|
160 |
+
"eval_steps_per_second": 28.062,
|
161 |
"step": 976
|
162 |
},
|
163 |
{
|
164 |
"epoch": 9.0,
|
165 |
+
"grad_norm": 6.677186012268066,
|
166 |
"learning_rate": 2.7500000000000004e-05,
|
167 |
+
"loss": 0.2049,
|
168 |
"step": 1098
|
169 |
},
|
170 |
{
|
171 |
"epoch": 9.0,
|
172 |
+
"eval_accuracy": 0.8947368421052632,
|
173 |
+
"eval_f1": 0.8748655913978494,
|
174 |
+
"eval_loss": 0.264840692281723,
|
175 |
+
"eval_precision": 0.86983032873807,
|
176 |
+
"eval_recall": 0.8805237315875614,
|
177 |
+
"eval_runtime": 1.7819,
|
178 |
+
"eval_samples_per_second": 223.922,
|
179 |
+
"eval_steps_per_second": 28.06,
|
180 |
"step": 1098
|
181 |
},
|
182 |
{
|
183 |
"epoch": 10.0,
|
184 |
+
"grad_norm": 2.770735502243042,
|
185 |
"learning_rate": 2.5e-05,
|
186 |
+
"loss": 0.1914,
|
187 |
"step": 1220
|
188 |
},
|
189 |
{
|
190 |
"epoch": 10.0,
|
191 |
"eval_accuracy": 0.9072681704260651,
|
192 |
+
"eval_f1": 0.8848664457009163,
|
193 |
+
"eval_loss": 0.2680298984050751,
|
194 |
+
"eval_precision": 0.8977236138837015,
|
195 |
+
"eval_recall": 0.8743862520458265,
|
196 |
+
"eval_runtime": 1.7909,
|
197 |
+
"eval_samples_per_second": 222.787,
|
198 |
+
"eval_steps_per_second": 27.918,
|
199 |
"step": 1220
|
200 |
},
|
201 |
{
|
202 |
"epoch": 11.0,
|
203 |
+
"grad_norm": 0.3618270754814148,
|
204 |
"learning_rate": 2.25e-05,
|
205 |
+
"loss": 0.1724,
|
206 |
"step": 1342
|
207 |
},
|
208 |
{
|
209 |
"epoch": 11.0,
|
210 |
+
"eval_accuracy": 0.899749373433584,
|
211 |
+
"eval_f1": 0.8808243727598566,
|
212 |
+
"eval_loss": 0.264539897441864,
|
213 |
+
"eval_precision": 0.875706963591375,
|
214 |
+
"eval_recall": 0.8865702855064557,
|
215 |
+
"eval_runtime": 1.7802,
|
216 |
+
"eval_samples_per_second": 224.138,
|
217 |
+
"eval_steps_per_second": 28.087,
|
218 |
"step": 1342
|
219 |
},
|
220 |
{
|
221 |
"epoch": 12.0,
|
222 |
+
"grad_norm": 2.054783582687378,
|
223 |
"learning_rate": 2e-05,
|
224 |
+
"loss": 0.1689,
|
225 |
"step": 1464
|
226 |
},
|
227 |
{
|
228 |
"epoch": 12.0,
|
229 |
"eval_accuracy": 0.899749373433584,
|
230 |
+
"eval_f1": 0.881931703852755,
|
231 |
+
"eval_loss": 0.27462852001190186,
|
232 |
+
"eval_precision": 0.8740012737378415,
|
233 |
+
"eval_recall": 0.8915711947626841,
|
234 |
+
"eval_runtime": 1.778,
|
235 |
+
"eval_samples_per_second": 224.405,
|
236 |
+
"eval_steps_per_second": 28.121,
|
237 |
"step": 1464
|
238 |
},
|
239 |
{
|
240 |
"epoch": 13.0,
|
241 |
+
"grad_norm": 0.6106524467468262,
|
242 |
"learning_rate": 1.75e-05,
|
243 |
+
"loss": 0.1473,
|
244 |
"step": 1586
|
245 |
},
|
246 |
{
|
247 |
"epoch": 13.0,
|
248 |
+
"eval_accuracy": 0.9047619047619048,
|
249 |
+
"eval_f1": 0.8800854160075926,
|
250 |
+
"eval_loss": 0.28370755910873413,
|
251 |
+
"eval_precision": 0.9002425410326267,
|
252 |
+
"eval_recall": 0.8651118385160939,
|
253 |
+
"eval_runtime": 1.785,
|
254 |
+
"eval_samples_per_second": 223.535,
|
255 |
+
"eval_steps_per_second": 28.012,
|
256 |
"step": 1586
|
257 |
},
|
258 |
{
|
259 |
"epoch": 14.0,
|
260 |
+
"grad_norm": 4.3967108726501465,
|
261 |
"learning_rate": 1.5e-05,
|
262 |
+
"loss": 0.1577,
|
263 |
"step": 1708
|
264 |
},
|
265 |
{
|
266 |
"epoch": 14.0,
|
267 |
+
"eval_accuracy": 0.9022556390977443,
|
268 |
+
"eval_f1": 0.884617951284618,
|
269 |
+
"eval_loss": 0.2892190217971802,
|
270 |
+
"eval_precision": 0.8772893772893773,
|
271 |
+
"eval_recall": 0.8933442444080741,
|
272 |
+
"eval_runtime": 1.7818,
|
273 |
+
"eval_samples_per_second": 223.936,
|
274 |
+
"eval_steps_per_second": 28.062,
|
275 |
"step": 1708
|
276 |
},
|
277 |
{
|
278 |
"epoch": 15.0,
|
279 |
+
"grad_norm": 0.48143357038497925,
|
280 |
"learning_rate": 1.25e-05,
|
281 |
+
"loss": 0.1468,
|
282 |
"step": 1830
|
283 |
},
|
284 |
{
|
285 |
"epoch": 15.0,
|
286 |
+
"eval_accuracy": 0.9022556390977443,
|
287 |
+
"eval_f1": 0.8829621606985718,
|
288 |
+
"eval_loss": 0.27894169092178345,
|
289 |
+
"eval_precision": 0.8802419354838709,
|
290 |
+
"eval_recall": 0.8858428805237315,
|
291 |
+
"eval_runtime": 1.7862,
|
292 |
+
"eval_samples_per_second": 223.376,
|
293 |
+
"eval_steps_per_second": 27.992,
|
294 |
"step": 1830
|
295 |
},
|
296 |
{
|
297 |
"epoch": 16.0,
|
298 |
+
"grad_norm": 0.6658376455307007,
|
299 |
"learning_rate": 1e-05,
|
300 |
+
"loss": 0.1473,
|
301 |
"step": 1952
|
302 |
},
|
303 |
{
|
304 |
"epoch": 16.0,
|
305 |
+
"eval_accuracy": 0.8972431077694235,
|
306 |
+
"eval_f1": 0.8775533117267087,
|
307 |
+
"eval_loss": 0.28521186113357544,
|
308 |
+
"eval_precision": 0.873246730188791,
|
309 |
+
"eval_recall": 0.8822967812329514,
|
310 |
+
"eval_runtime": 1.778,
|
311 |
+
"eval_samples_per_second": 224.41,
|
312 |
+
"eval_steps_per_second": 28.121,
|
313 |
"step": 1952
|
314 |
},
|
315 |
{
|
316 |
"epoch": 17.0,
|
317 |
+
"grad_norm": 1.4181182384490967,
|
318 |
"learning_rate": 7.5e-06,
|
319 |
+
"loss": 0.1274,
|
320 |
"step": 2074
|
321 |
},
|
322 |
{
|
323 |
"epoch": 17.0,
|
324 |
"eval_accuracy": 0.9047619047619048,
|
325 |
+
"eval_f1": 0.8856836962422341,
|
326 |
+
"eval_loss": 0.28584179282188416,
|
327 |
+
"eval_precision": 0.8838235294117647,
|
328 |
+
"eval_recall": 0.8876159301691217,
|
329 |
+
"eval_runtime": 1.7792,
|
330 |
+
"eval_samples_per_second": 224.253,
|
331 |
+
"eval_steps_per_second": 28.102,
|
332 |
"step": 2074
|
333 |
},
|
334 |
{
|
335 |
"epoch": 18.0,
|
336 |
+
"grad_norm": 5.91610050201416,
|
337 |
"learning_rate": 5e-06,
|
338 |
+
"loss": 0.1318,
|
339 |
"step": 2196
|
340 |
},
|
341 |
{
|
342 |
"epoch": 18.0,
|
343 |
+
"eval_accuracy": 0.899749373433584,
|
344 |
+
"eval_f1": 0.8802521008403361,
|
345 |
+
"eval_loss": 0.29269006848335266,
|
346 |
+
"eval_precision": 0.8767168083714847,
|
347 |
+
"eval_recall": 0.8840698308783415,
|
348 |
+
"eval_runtime": 1.7862,
|
349 |
+
"eval_samples_per_second": 223.383,
|
350 |
+
"eval_steps_per_second": 27.993,
|
351 |
"step": 2196
|
352 |
},
|
353 |
{
|
354 |
"epoch": 19.0,
|
355 |
+
"grad_norm": 6.210901737213135,
|
356 |
"learning_rate": 2.5e-06,
|
357 |
+
"loss": 0.1355,
|
358 |
"step": 2318
|
359 |
},
|
360 |
{
|
361 |
"epoch": 19.0,
|
362 |
+
"eval_accuracy": 0.9072681704260651,
|
363 |
+
"eval_f1": 0.8884169154604891,
|
364 |
+
"eval_loss": 0.2884277403354645,
|
365 |
+
"eval_precision": 0.8874630556728391,
|
366 |
+
"eval_recall": 0.8893889798145117,
|
367 |
+
"eval_runtime": 1.7806,
|
368 |
+
"eval_samples_per_second": 224.08,
|
369 |
+
"eval_steps_per_second": 28.08,
|
370 |
"step": 2318
|
371 |
},
|
372 |
{
|
373 |
"epoch": 20.0,
|
374 |
+
"grad_norm": 1.5748217105865479,
|
375 |
"learning_rate": 0.0,
|
376 |
+
"loss": 0.1367,
|
377 |
"step": 2440
|
378 |
},
|
379 |
{
|
380 |
"epoch": 20.0,
|
381 |
+
"eval_accuracy": 0.9072681704260651,
|
382 |
+
"eval_f1": 0.8884169154604891,
|
383 |
+
"eval_loss": 0.2881532311439514,
|
384 |
+
"eval_precision": 0.8874630556728391,
|
385 |
+
"eval_recall": 0.8893889798145117,
|
386 |
+
"eval_runtime": 1.7811,
|
387 |
+
"eval_samples_per_second": 224.016,
|
388 |
+
"eval_steps_per_second": 28.072,
|
389 |
"step": 2440
|
390 |
},
|
391 |
{
|
392 |
"epoch": 20.0,
|
393 |
"step": 2440,
|
394 |
"total_flos": 8444128359504000.0,
|
395 |
+
"train_loss": 0.2206378909408069,
|
396 |
+
"train_runtime": 624.8021,
|
397 |
+
"train_samples_per_second": 116.453,
|
398 |
+
"train_steps_per_second": 3.905
|
399 |
}
|
400 |
],
|
401 |
"logging_steps": 500,
|