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 +39 -39
- runs/Jun03_15-01-46_a358b85c7679/events.out.tfevents.1717427545.a358b85c7679.158543.1 +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.
|
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": 0.9183266932270916,
|
3 |
"epoch": 20.0,
|
4 |
+
"eval_accuracy": 0.8822055137844611,
|
5 |
+
"eval_f1": 0.855319904024935,
|
6 |
+
"eval_loss": 0.3026413023471832,
|
7 |
+
"eval_precision": 0.862378106322743,
|
8 |
+
"eval_recall": 0.8491543917075832,
|
9 |
+
"eval_runtime": 1.8078,
|
10 |
"eval_samples": 399,
|
11 |
+
"eval_samples_per_second": 220.713,
|
12 |
+
"eval_steps_per_second": 27.658,
|
13 |
+
"f1": 0.9005988602337487,
|
14 |
+
"precision": 0.9039776379609248,
|
15 |
+
"recall": 0.897413049726933,
|
16 |
+
"train_loss": 0.24652244458433056,
|
17 |
+
"train_runtime": 623.7969,
|
18 |
"train_samples": 3645,
|
19 |
+
"train_samples_per_second": 116.865,
|
20 |
+
"train_steps_per_second": 3.912
|
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": 0.8822055137844611,
|
4 |
+
"eval_f1": 0.855319904024935,
|
5 |
+
"eval_loss": 0.3026413023471832,
|
6 |
+
"eval_precision": 0.862378106322743,
|
7 |
+
"eval_recall": 0.8491543917075832,
|
8 |
+
"eval_runtime": 1.8078,
|
9 |
"eval_samples": 399,
|
10 |
+
"eval_samples_per_second": 220.713,
|
11 |
+
"eval_steps_per_second": 27.658
|
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": 0.9183266932270916,
|
3 |
+
"f1": 0.9005988602337487,
|
4 |
+
"precision": 0.9039776379609248,
|
5 |
+
"recall": 0.897413049726933
|
6 |
}
|
predict_results.txt
CHANGED
@@ -13,8 +13,8 @@ index prediction
|
|
13 |
11 1
|
14 |
12 0
|
15 |
13 1
|
16 |
-
14
|
17 |
-
15
|
18 |
16 0
|
19 |
17 1
|
20 |
18 1
|
@@ -37,16 +37,16 @@ index prediction
|
|
37 |
35 1
|
38 |
36 1
|
39 |
37 1
|
40 |
-
38
|
41 |
39 0
|
42 |
40 0
|
43 |
41 1
|
44 |
-
42
|
45 |
43 1
|
46 |
44 1
|
47 |
45 1
|
48 |
46 1
|
49 |
-
47
|
50 |
48 0
|
51 |
49 1
|
52 |
50 1
|
@@ -57,7 +57,7 @@ index prediction
|
|
57 |
55 1
|
58 |
56 1
|
59 |
57 1
|
60 |
-
58
|
61 |
59 1
|
62 |
60 1
|
63 |
61 1
|
@@ -85,7 +85,7 @@ index prediction
|
|
85 |
83 1
|
86 |
84 1
|
87 |
85 1
|
88 |
-
86
|
89 |
87 1
|
90 |
88 1
|
91 |
89 1
|
@@ -113,14 +113,14 @@ index prediction
|
|
113 |
111 1
|
114 |
112 1
|
115 |
113 1
|
116 |
-
114
|
117 |
115 1
|
118 |
116 1
|
119 |
117 1
|
120 |
118 1
|
121 |
119 1
|
122 |
120 1
|
123 |
-
121
|
124 |
122 1
|
125 |
123 1
|
126 |
124 1
|
@@ -152,11 +152,11 @@ index prediction
|
|
152 |
150 1
|
153 |
151 1
|
154 |
152 1
|
155 |
-
153
|
156 |
154 1
|
157 |
155 1
|
158 |
156 1
|
159 |
-
157
|
160 |
158 1
|
161 |
159 1
|
162 |
160 1
|
@@ -192,7 +192,7 @@ index prediction
|
|
192 |
190 0
|
193 |
191 1
|
194 |
192 1
|
195 |
-
193
|
196 |
194 1
|
197 |
195 1
|
198 |
196 1
|
@@ -207,7 +207,7 @@ index prediction
|
|
207 |
205 1
|
208 |
206 1
|
209 |
207 0
|
210 |
-
208
|
211 |
209 1
|
212 |
210 1
|
213 |
211 1
|
@@ -220,11 +220,11 @@ index prediction
|
|
220 |
218 1
|
221 |
219 1
|
222 |
220 1
|
223 |
-
221
|
224 |
222 1
|
225 |
223 1
|
226 |
224 1
|
227 |
-
225
|
228 |
226 1
|
229 |
227 1
|
230 |
228 1
|
@@ -245,7 +245,7 @@ index prediction
|
|
245 |
243 1
|
246 |
244 1
|
247 |
245 1
|
248 |
-
246
|
249 |
247 1
|
250 |
248 1
|
251 |
249 1
|
@@ -258,7 +258,7 @@ index prediction
|
|
258 |
256 1
|
259 |
257 1
|
260 |
258 1
|
261 |
-
259
|
262 |
260 0
|
263 |
261 1
|
264 |
262 1
|
@@ -271,7 +271,7 @@ index prediction
|
|
271 |
269 0
|
272 |
270 1
|
273 |
271 1
|
274 |
-
272
|
275 |
273 1
|
276 |
274 1
|
277 |
275 1
|
@@ -288,7 +288,7 @@ index prediction
|
|
288 |
286 1
|
289 |
287 0
|
290 |
288 1
|
291 |
-
289
|
292 |
290 1
|
293 |
291 0
|
294 |
292 1
|
@@ -300,7 +300,7 @@ index prediction
|
|
300 |
298 0
|
301 |
299 0
|
302 |
300 0
|
303 |
-
301
|
304 |
302 0
|
305 |
303 0
|
306 |
304 0
|
@@ -356,10 +356,10 @@ index prediction
|
|
356 |
354 0
|
357 |
355 0
|
358 |
356 0
|
359 |
-
357
|
360 |
358 0
|
361 |
359 0
|
362 |
-
360
|
363 |
361 0
|
364 |
362 0
|
365 |
363 0
|
@@ -396,7 +396,7 @@ index prediction
|
|
396 |
394 0
|
397 |
395 0
|
398 |
396 1
|
399 |
-
397
|
400 |
398 0
|
401 |
399 0
|
402 |
400 0
|
@@ -423,7 +423,7 @@ index prediction
|
|
423 |
421 0
|
424 |
422 0
|
425 |
423 0
|
426 |
-
424
|
427 |
425 0
|
428 |
426 0
|
429 |
427 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
|
@@ -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
|
@@ -558,7 +558,7 @@ index prediction
|
|
558 |
556 0
|
559 |
557 0
|
560 |
558 0
|
561 |
-
559
|
562 |
560 0
|
563 |
561 0
|
564 |
562 0
|
@@ -610,7 +610,7 @@ index prediction
|
|
610 |
608 0
|
611 |
609 0
|
612 |
610 0
|
613 |
-
611
|
614 |
612 0
|
615 |
613 0
|
616 |
614 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
|
@@ -716,7 +716,7 @@ index prediction
|
|
716 |
714 0
|
717 |
715 0
|
718 |
716 0
|
719 |
-
717
|
720 |
718 0
|
721 |
719 0
|
722 |
720 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
|
@@ -762,7 +762,7 @@ index prediction
|
|
762 |
760 0
|
763 |
761 0
|
764 |
762 0
|
765 |
-
763
|
766 |
764 0
|
767 |
765 0
|
768 |
766 0
|
@@ -772,13 +772,13 @@ index prediction
|
|
772 |
770 0
|
773 |
771 0
|
774 |
772 0
|
775 |
-
773
|
776 |
-
774
|
777 |
775 0
|
778 |
776 0
|
779 |
777 0
|
780 |
778 0
|
781 |
-
779
|
782 |
780 0
|
783 |
781 0
|
784 |
782 0
|
@@ -792,11 +792,11 @@ index prediction
|
|
792 |
790 0
|
793 |
791 0
|
794 |
792 0
|
795 |
-
793
|
796 |
794 0
|
797 |
795 0
|
798 |
796 0
|
799 |
-
797
|
800 |
798 1
|
801 |
799 0
|
802 |
800 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
|
|
|
13 |
11 1
|
14 |
12 0
|
15 |
13 1
|
16 |
+
14 0
|
17 |
+
15 0
|
18 |
16 0
|
19 |
17 1
|
20 |
18 1
|
|
|
37 |
35 1
|
38 |
36 1
|
39 |
37 1
|
40 |
+
38 0
|
41 |
39 0
|
42 |
40 0
|
43 |
41 1
|
44 |
+
42 0
|
45 |
43 1
|
46 |
44 1
|
47 |
45 1
|
48 |
46 1
|
49 |
+
47 0
|
50 |
48 0
|
51 |
49 1
|
52 |
50 1
|
|
|
57 |
55 1
|
58 |
56 1
|
59 |
57 1
|
60 |
+
58 1
|
61 |
59 1
|
62 |
60 1
|
63 |
61 1
|
|
|
85 |
83 1
|
86 |
84 1
|
87 |
85 1
|
88 |
+
86 1
|
89 |
87 1
|
90 |
88 1
|
91 |
89 1
|
|
|
113 |
111 1
|
114 |
112 1
|
115 |
113 1
|
116 |
+
114 0
|
117 |
115 1
|
118 |
116 1
|
119 |
117 1
|
120 |
118 1
|
121 |
119 1
|
122 |
120 1
|
123 |
+
121 1
|
124 |
122 1
|
125 |
123 1
|
126 |
124 1
|
|
|
152 |
150 1
|
153 |
151 1
|
154 |
152 1
|
155 |
+
153 0
|
156 |
154 1
|
157 |
155 1
|
158 |
156 1
|
159 |
+
157 0
|
160 |
158 1
|
161 |
159 1
|
162 |
160 1
|
|
|
192 |
190 0
|
193 |
191 1
|
194 |
192 1
|
195 |
+
193 1
|
196 |
194 1
|
197 |
195 1
|
198 |
196 1
|
|
|
207 |
205 1
|
208 |
206 1
|
209 |
207 0
|
210 |
+
208 0
|
211 |
209 1
|
212 |
210 1
|
213 |
211 1
|
|
|
220 |
218 1
|
221 |
219 1
|
222 |
220 1
|
223 |
+
221 0
|
224 |
222 1
|
225 |
223 1
|
226 |
224 1
|
227 |
+
225 1
|
228 |
226 1
|
229 |
227 1
|
230 |
228 1
|
|
|
245 |
243 1
|
246 |
244 1
|
247 |
245 1
|
248 |
+
246 1
|
249 |
247 1
|
250 |
248 1
|
251 |
249 1
|
|
|
258 |
256 1
|
259 |
257 1
|
260 |
258 1
|
261 |
+
259 1
|
262 |
260 0
|
263 |
261 1
|
264 |
262 1
|
|
|
271 |
269 0
|
272 |
270 1
|
273 |
271 1
|
274 |
+
272 1
|
275 |
273 1
|
276 |
274 1
|
277 |
275 1
|
|
|
288 |
286 1
|
289 |
287 0
|
290 |
288 1
|
291 |
+
289 1
|
292 |
290 1
|
293 |
291 0
|
294 |
292 1
|
|
|
300 |
298 0
|
301 |
299 0
|
302 |
300 0
|
303 |
+
301 0
|
304 |
302 0
|
305 |
303 0
|
306 |
304 0
|
|
|
356 |
354 0
|
357 |
355 0
|
358 |
356 0
|
359 |
+
357 1
|
360 |
358 0
|
361 |
359 0
|
362 |
+
360 0
|
363 |
361 0
|
364 |
362 0
|
365 |
363 0
|
|
|
396 |
394 0
|
397 |
395 0
|
398 |
396 1
|
399 |
+
397 0
|
400 |
398 0
|
401 |
399 0
|
402 |
400 0
|
|
|
423 |
421 0
|
424 |
422 0
|
425 |
423 0
|
426 |
+
424 1
|
427 |
425 0
|
428 |
426 0
|
429 |
427 0
|
|
|
436 |
434 0
|
437 |
435 0
|
438 |
436 0
|
439 |
+
437 0
|
440 |
438 0
|
441 |
439 0
|
442 |
440 0
|
|
|
536 |
534 0
|
537 |
535 0
|
538 |
536 0
|
539 |
+
537 1
|
540 |
538 0
|
541 |
539 0
|
542 |
540 0
|
|
|
558 |
556 0
|
559 |
557 0
|
560 |
558 0
|
561 |
+
559 0
|
562 |
560 0
|
563 |
561 0
|
564 |
562 0
|
|
|
610 |
608 0
|
611 |
609 0
|
612 |
610 0
|
613 |
+
611 1
|
614 |
612 0
|
615 |
613 0
|
616 |
614 0
|
|
|
626 |
624 0
|
627 |
625 0
|
628 |
626 0
|
629 |
+
627 0
|
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
|
|
|
716 |
714 0
|
717 |
715 0
|
718 |
716 0
|
719 |
+
717 0
|
720 |
718 0
|
721 |
719 0
|
722 |
720 0
|
|
|
753 |
751 0
|
754 |
752 0
|
755 |
753 0
|
756 |
+
754 0
|
757 |
755 0
|
758 |
756 0
|
759 |
757 0
|
|
|
762 |
760 0
|
763 |
761 0
|
764 |
762 0
|
765 |
+
763 1
|
766 |
764 0
|
767 |
765 0
|
768 |
766 0
|
|
|
772 |
770 0
|
773 |
771 0
|
774 |
772 0
|
775 |
+
773 0
|
776 |
+
774 1
|
777 |
775 0
|
778 |
776 0
|
779 |
777 0
|
780 |
778 0
|
781 |
+
779 0
|
782 |
780 0
|
783 |
781 0
|
784 |
782 0
|
|
|
792 |
790 0
|
793 |
791 0
|
794 |
792 0
|
795 |
+
793 1
|
796 |
794 0
|
797 |
795 0
|
798 |
796 0
|
799 |
+
797 1
|
800 |
798 1
|
801 |
799 0
|
802 |
800 0
|
|
|
851 |
849 0
|
852 |
850 0
|
853 |
851 0
|
854 |
+
852 1
|
855 |
853 0
|
856 |
854 0
|
857 |
855 0
|
runs/Jun03_15-01-46_a358b85c7679/events.out.tfevents.1717427545.a358b85c7679.158543.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9106848a02fa4c3a2a8c888b728e37234caabffdf8b01b4ebb53776969a294fa
|
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": 0.24652244458433056,
|
4 |
+
"train_runtime": 623.7969,
|
5 |
"train_samples": 3645,
|
6 |
+
"train_samples_per_second": 116.865,
|
7 |
+
"train_steps_per_second": 3.912
|
8 |
}
|
trainer_state.json
CHANGED
@@ -10,392 +10,392 @@
|
|
10 |
"log_history": [
|
11 |
{
|
12 |
"epoch": 1.0,
|
13 |
-
"grad_norm":
|
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":
|
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": 1.
|
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": 0.8696741854636592,
|
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": 4.
|
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": 2.
|
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.
|
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":
|
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": 0.8822055137844611,
|
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": 3.
|
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": 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": 3.928847551345825,
|
14 |
"learning_rate": 4.75e-05,
|
15 |
+
"loss": 0.5514,
|
16 |
"step": 122
|
17 |
},
|
18 |
{
|
19 |
"epoch": 1.0,
|
20 |
+
"eval_accuracy": 0.7218045112781954,
|
21 |
+
"eval_f1": 0.6545993371027491,
|
22 |
+
"eval_loss": 0.5084339380264282,
|
23 |
+
"eval_precision": 0.6600553802562947,
|
24 |
+
"eval_recall": 0.6506637570467357,
|
25 |
+
"eval_runtime": 1.7877,
|
26 |
+
"eval_samples_per_second": 223.186,
|
27 |
+
"eval_steps_per_second": 27.968,
|
28 |
"step": 122
|
29 |
},
|
30 |
{
|
31 |
"epoch": 2.0,
|
32 |
+
"grad_norm": 3.589020013809204,
|
33 |
"learning_rate": 4.5e-05,
|
34 |
+
"loss": 0.4753,
|
35 |
"step": 244
|
36 |
},
|
37 |
{
|
38 |
"epoch": 2.0,
|
39 |
+
"eval_accuracy": 0.8170426065162907,
|
40 |
+
"eval_f1": 0.7662453352594198,
|
41 |
+
"eval_loss": 0.40073099732398987,
|
42 |
+
"eval_precision": 0.7870255775577557,
|
43 |
+
"eval_recall": 0.7530460083651573,
|
44 |
+
"eval_runtime": 1.8277,
|
45 |
+
"eval_samples_per_second": 218.302,
|
46 |
+
"eval_steps_per_second": 27.356,
|
47 |
"step": 244
|
48 |
},
|
49 |
{
|
50 |
"epoch": 3.0,
|
51 |
+
"grad_norm": 7.217240810394287,
|
52 |
"learning_rate": 4.25e-05,
|
53 |
+
"loss": 0.3834,
|
54 |
"step": 366
|
55 |
},
|
56 |
{
|
57 |
"epoch": 3.0,
|
58 |
+
"eval_accuracy": 0.8395989974937343,
|
59 |
+
"eval_f1": 0.7805280528052805,
|
60 |
+
"eval_loss": 0.35415172576904297,
|
61 |
+
"eval_precision": 0.8448765432098766,
|
62 |
+
"eval_recall": 0.7540007274049827,
|
63 |
+
"eval_runtime": 1.8275,
|
64 |
+
"eval_samples_per_second": 218.333,
|
65 |
+
"eval_steps_per_second": 27.36,
|
66 |
"step": 366
|
67 |
},
|
68 |
{
|
69 |
"epoch": 4.0,
|
70 |
+
"grad_norm": 1.0342143774032593,
|
71 |
"learning_rate": 4e-05,
|
72 |
+
"loss": 0.3188,
|
73 |
"step": 488
|
74 |
},
|
75 |
{
|
76 |
"epoch": 4.0,
|
77 |
+
"eval_accuracy": 0.8621553884711779,
|
78 |
+
"eval_f1": 0.8333016825553572,
|
79 |
+
"eval_loss": 0.32140952348709106,
|
80 |
+
"eval_precision": 0.8341507249908615,
|
81 |
+
"eval_recall": 0.8324695399163484,
|
82 |
+
"eval_runtime": 1.8265,
|
83 |
+
"eval_samples_per_second": 218.445,
|
84 |
+
"eval_steps_per_second": 27.374,
|
85 |
"step": 488
|
86 |
},
|
87 |
{
|
88 |
"epoch": 5.0,
|
89 |
+
"grad_norm": 1.17711341381073,
|
90 |
"learning_rate": 3.7500000000000003e-05,
|
91 |
+
"loss": 0.2981,
|
92 |
"step": 610
|
93 |
},
|
94 |
{
|
95 |
"epoch": 5.0,
|
96 |
+
"eval_accuracy": 0.8822055137844611,
|
97 |
+
"eval_f1": 0.855319904024935,
|
98 |
+
"eval_loss": 0.2984267771244049,
|
99 |
+
"eval_precision": 0.862378106322743,
|
100 |
+
"eval_recall": 0.8491543917075832,
|
101 |
+
"eval_runtime": 1.8288,
|
102 |
+
"eval_samples_per_second": 218.18,
|
103 |
+
"eval_steps_per_second": 27.341,
|
104 |
"step": 610
|
105 |
},
|
106 |
{
|
107 |
"epoch": 6.0,
|
108 |
+
"grad_norm": 4.153679370880127,
|
109 |
"learning_rate": 3.5e-05,
|
110 |
+
"loss": 0.2835,
|
111 |
"step": 732
|
112 |
},
|
113 |
{
|
114 |
"epoch": 6.0,
|
115 |
"eval_accuracy": 0.8696741854636592,
|
116 |
+
"eval_f1": 0.8368354828562441,
|
117 |
+
"eval_loss": 0.28104665875434875,
|
118 |
+
"eval_precision": 0.8520237470480189,
|
119 |
+
"eval_recall": 0.8252864157119476,
|
120 |
+
"eval_runtime": 1.8275,
|
121 |
+
"eval_samples_per_second": 218.335,
|
122 |
+
"eval_steps_per_second": 27.36,
|
123 |
"step": 732
|
124 |
},
|
125 |
{
|
126 |
"epoch": 7.0,
|
127 |
+
"grad_norm": 1.0657362937927246,
|
128 |
"learning_rate": 3.2500000000000004e-05,
|
129 |
+
"loss": 0.2517,
|
130 |
"step": 854
|
131 |
},
|
132 |
{
|
133 |
"epoch": 7.0,
|
134 |
+
"eval_accuracy": 0.8872180451127819,
|
135 |
+
"eval_f1": 0.8622036668943447,
|
136 |
+
"eval_loss": 0.28660351037979126,
|
137 |
+
"eval_precision": 0.8671602787456446,
|
138 |
+
"eval_recall": 0.8577014002545917,
|
139 |
+
"eval_runtime": 1.7903,
|
140 |
+
"eval_samples_per_second": 222.862,
|
141 |
+
"eval_steps_per_second": 27.928,
|
142 |
"step": 854
|
143 |
},
|
144 |
{
|
145 |
"epoch": 8.0,
|
146 |
+
"grad_norm": 3.21960711479187,
|
147 |
"learning_rate": 3e-05,
|
148 |
+
"loss": 0.2374,
|
149 |
"step": 976
|
150 |
},
|
151 |
{
|
152 |
"epoch": 8.0,
|
153 |
+
"eval_accuracy": 0.8796992481203008,
|
154 |
+
"eval_f1": 0.8485289465359063,
|
155 |
+
"eval_loss": 0.2996794879436493,
|
156 |
+
"eval_precision": 0.8671008040401356,
|
157 |
+
"eval_recall": 0.8348790689216221,
|
158 |
+
"eval_runtime": 1.7958,
|
159 |
+
"eval_samples_per_second": 222.185,
|
160 |
+
"eval_steps_per_second": 27.843,
|
161 |
"step": 976
|
162 |
},
|
163 |
{
|
164 |
"epoch": 9.0,
|
165 |
+
"grad_norm": 4.313467025756836,
|
166 |
"learning_rate": 2.7500000000000004e-05,
|
167 |
+
"loss": 0.2293,
|
168 |
"step": 1098
|
169 |
},
|
170 |
{
|
171 |
"epoch": 9.0,
|
172 |
+
"eval_accuracy": 0.8796992481203008,
|
173 |
+
"eval_f1": 0.8518472677764712,
|
174 |
+
"eval_loss": 0.29089975357055664,
|
175 |
+
"eval_precision": 0.8599810186649794,
|
176 |
+
"eval_recall": 0.844880887434079,
|
177 |
+
"eval_runtime": 1.7949,
|
178 |
+
"eval_samples_per_second": 222.299,
|
179 |
+
"eval_steps_per_second": 27.857,
|
180 |
"step": 1098
|
181 |
},
|
182 |
{
|
183 |
"epoch": 10.0,
|
184 |
+
"grad_norm": 2.5997090339660645,
|
185 |
"learning_rate": 2.5e-05,
|
186 |
+
"loss": 0.2091,
|
187 |
"step": 1220
|
188 |
},
|
189 |
{
|
190 |
"epoch": 10.0,
|
191 |
+
"eval_accuracy": 0.8822055137844611,
|
192 |
+
"eval_f1": 0.8589543987905864,
|
193 |
+
"eval_loss": 0.29276683926582336,
|
194 |
+
"eval_precision": 0.8564068100358423,
|
195 |
+
"eval_recall": 0.8616566648481543,
|
196 |
+
"eval_runtime": 1.7944,
|
197 |
+
"eval_samples_per_second": 222.357,
|
198 |
+
"eval_steps_per_second": 27.864,
|
199 |
"step": 1220
|
200 |
},
|
201 |
{
|
202 |
"epoch": 11.0,
|
203 |
+
"grad_norm": 3.3290369510650635,
|
204 |
"learning_rate": 2.25e-05,
|
205 |
+
"loss": 0.198,
|
206 |
"step": 1342
|
207 |
},
|
208 |
{
|
209 |
"epoch": 11.0,
|
210 |
+
"eval_accuracy": 0.8796992481203008,
|
211 |
+
"eval_f1": 0.8569892473118279,
|
212 |
+
"eval_loss": 0.28468698263168335,
|
213 |
+
"eval_precision": 0.8522004241781549,
|
214 |
+
"eval_recall": 0.8623840698308783,
|
215 |
+
"eval_runtime": 1.8002,
|
216 |
+
"eval_samples_per_second": 221.645,
|
217 |
+
"eval_steps_per_second": 27.775,
|
218 |
"step": 1342
|
219 |
},
|
220 |
{
|
221 |
"epoch": 12.0,
|
222 |
+
"grad_norm": 5.568458557128906,
|
223 |
"learning_rate": 2e-05,
|
224 |
+
"loss": 0.1906,
|
225 |
"step": 1464
|
226 |
},
|
227 |
{
|
228 |
"epoch": 12.0,
|
229 |
+
"eval_accuracy": 0.87468671679198,
|
230 |
+
"eval_f1": 0.843111041207927,
|
231 |
+
"eval_loss": 0.31200090050697327,
|
232 |
+
"eval_precision": 0.8585673051692468,
|
233 |
+
"eval_recall": 0.831332969630842,
|
234 |
+
"eval_runtime": 1.7936,
|
235 |
+
"eval_samples_per_second": 222.458,
|
236 |
+
"eval_steps_per_second": 27.877,
|
237 |
"step": 1464
|
238 |
},
|
239 |
{
|
240 |
"epoch": 13.0,
|
241 |
+
"grad_norm": 1.5475130081176758,
|
242 |
"learning_rate": 1.75e-05,
|
243 |
+
"loss": 0.1818,
|
244 |
"step": 1586
|
245 |
},
|
246 |
{
|
247 |
"epoch": 13.0,
|
248 |
+
"eval_accuracy": 0.8771929824561403,
|
249 |
+
"eval_f1": 0.850729517396184,
|
250 |
+
"eval_loss": 0.2906310558319092,
|
251 |
+
"eval_precision": 0.8535087719298247,
|
252 |
+
"eval_recall": 0.8481087470449173,
|
253 |
+
"eval_runtime": 1.795,
|
254 |
+
"eval_samples_per_second": 222.279,
|
255 |
+
"eval_steps_per_second": 27.854,
|
256 |
"step": 1586
|
257 |
},
|
258 |
{
|
259 |
"epoch": 14.0,
|
260 |
+
"grad_norm": 5.56436014175415,
|
261 |
"learning_rate": 1.5e-05,
|
262 |
+
"loss": 0.1756,
|
263 |
"step": 1708
|
264 |
},
|
265 |
{
|
266 |
"epoch": 14.0,
|
267 |
+
"eval_accuracy": 0.8771929824561403,
|
268 |
+
"eval_f1": 0.8514869535493182,
|
269 |
+
"eval_loss": 0.28101998567581177,
|
270 |
+
"eval_precision": 0.8523821128305106,
|
271 |
+
"eval_recall": 0.8506092016730314,
|
272 |
+
"eval_runtime": 1.7948,
|
273 |
+
"eval_samples_per_second": 222.311,
|
274 |
+
"eval_steps_per_second": 27.859,
|
275 |
"step": 1708
|
276 |
},
|
277 |
{
|
278 |
"epoch": 15.0,
|
279 |
+
"grad_norm": 1.7677656412124634,
|
280 |
"learning_rate": 1.25e-05,
|
281 |
+
"loss": 0.174,
|
282 |
"step": 1830
|
283 |
},
|
284 |
{
|
285 |
"epoch": 15.0,
|
286 |
+
"eval_accuracy": 0.8847117794486216,
|
287 |
+
"eval_f1": 0.8595070422535211,
|
288 |
+
"eval_loss": 0.2828814685344696,
|
289 |
+
"eval_precision": 0.8633733523114054,
|
290 |
+
"eval_recall": 0.8559283506092017,
|
291 |
+
"eval_runtime": 1.7987,
|
292 |
+
"eval_samples_per_second": 221.825,
|
293 |
+
"eval_steps_per_second": 27.798,
|
294 |
"step": 1830
|
295 |
},
|
296 |
{
|
297 |
"epoch": 16.0,
|
298 |
+
"grad_norm": 2.1199889183044434,
|
299 |
"learning_rate": 1e-05,
|
300 |
+
"loss": 0.1705,
|
301 |
"step": 1952
|
302 |
},
|
303 |
{
|
304 |
"epoch": 16.0,
|
305 |
"eval_accuracy": 0.8822055137844611,
|
306 |
+
"eval_f1": 0.855319904024935,
|
307 |
+
"eval_loss": 0.292202889919281,
|
308 |
+
"eval_precision": 0.862378106322743,
|
309 |
+
"eval_recall": 0.8491543917075832,
|
310 |
+
"eval_runtime": 1.7972,
|
311 |
+
"eval_samples_per_second": 222.011,
|
312 |
+
"eval_steps_per_second": 27.821,
|
313 |
"step": 1952
|
314 |
},
|
315 |
{
|
316 |
"epoch": 17.0,
|
317 |
+
"grad_norm": 2.521127223968506,
|
318 |
"learning_rate": 7.5e-06,
|
319 |
+
"loss": 0.1509,
|
320 |
"step": 2074
|
321 |
},
|
322 |
{
|
323 |
"epoch": 17.0,
|
324 |
+
"eval_accuracy": 0.8822055137844611,
|
325 |
+
"eval_f1": 0.8568221901555235,
|
326 |
+
"eval_loss": 0.2991296947002411,
|
327 |
+
"eval_precision": 0.8596491228070176,
|
328 |
+
"eval_recall": 0.8541553009638116,
|
329 |
+
"eval_runtime": 1.7965,
|
330 |
+
"eval_samples_per_second": 222.104,
|
331 |
+
"eval_steps_per_second": 27.833,
|
332 |
"step": 2074
|
333 |
},
|
334 |
{
|
335 |
"epoch": 18.0,
|
336 |
+
"grad_norm": 3.4539577960968018,
|
337 |
"learning_rate": 5e-06,
|
338 |
+
"loss": 0.1549,
|
339 |
"step": 2196
|
340 |
},
|
341 |
{
|
342 |
"epoch": 18.0,
|
343 |
+
"eval_accuracy": 0.8822055137844611,
|
344 |
+
"eval_f1": 0.855319904024935,
|
345 |
+
"eval_loss": 0.3000391125679016,
|
346 |
+
"eval_precision": 0.862378106322743,
|
347 |
+
"eval_recall": 0.8491543917075832,
|
348 |
+
"eval_runtime": 1.7991,
|
349 |
+
"eval_samples_per_second": 221.772,
|
350 |
+
"eval_steps_per_second": 27.791,
|
351 |
"step": 2196
|
352 |
},
|
353 |
{
|
354 |
"epoch": 19.0,
|
355 |
+
"grad_norm": 1.3508776426315308,
|
356 |
"learning_rate": 2.5e-06,
|
357 |
+
"loss": 0.1469,
|
358 |
"step": 2318
|
359 |
},
|
360 |
{
|
361 |
"epoch": 19.0,
|
362 |
+
"eval_accuracy": 0.8847117794486216,
|
363 |
+
"eval_f1": 0.8609292598654301,
|
364 |
+
"eval_loss": 0.2942558228969574,
|
365 |
+
"eval_precision": 0.8609292598654301,
|
366 |
+
"eval_recall": 0.8609292598654301,
|
367 |
+
"eval_runtime": 1.8067,
|
368 |
+
"eval_samples_per_second": 220.841,
|
369 |
+
"eval_steps_per_second": 27.674,
|
370 |
"step": 2318
|
371 |
},
|
372 |
{
|
373 |
"epoch": 20.0,
|
374 |
+
"grad_norm": 3.1654489040374756,
|
375 |
"learning_rate": 0.0,
|
376 |
+
"loss": 0.1493,
|
377 |
"step": 2440
|
378 |
},
|
379 |
{
|
380 |
"epoch": 20.0,
|
381 |
+
"eval_accuracy": 0.8822055137844611,
|
382 |
+
"eval_f1": 0.855319904024935,
|
383 |
+
"eval_loss": 0.3026413023471832,
|
384 |
+
"eval_precision": 0.862378106322743,
|
385 |
+
"eval_recall": 0.8491543917075832,
|
386 |
+
"eval_runtime": 1.7968,
|
387 |
+
"eval_samples_per_second": 222.067,
|
388 |
+
"eval_steps_per_second": 27.828,
|
389 |
"step": 2440
|
390 |
},
|
391 |
{
|
392 |
"epoch": 20.0,
|
393 |
"step": 2440,
|
394 |
"total_flos": 8460375995160000.0,
|
395 |
+
"train_loss": 0.24652244458433056,
|
396 |
+
"train_runtime": 623.7969,
|
397 |
+
"train_samples_per_second": 116.865,
|
398 |
+
"train_steps_per_second": 3.912
|
399 |
}
|
400 |
],
|
401 |
"logging_steps": 500,
|