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 +36 -36
- runs/Jun03_13-11-00_a358b85c7679/events.out.tfevents.1717420912.a358b85c7679.99454.1 +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": 3638,
|
| 19 |
-
"train_samples_per_second":
|
| 20 |
-
"train_steps_per_second":
|
| 21 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"accuracy": 0.8991097922848664,
|
| 3 |
"epoch": 20.0,
|
| 4 |
+
"eval_accuracy": 0.8922305764411027,
|
| 5 |
+
"eval_f1": 0.8721887408091659,
|
| 6 |
+
"eval_loss": 0.27931535243988037,
|
| 7 |
+
"eval_precision": 0.866466275659824,
|
| 8 |
+
"eval_recall": 0.8787506819421713,
|
| 9 |
+
"eval_runtime": 1.8379,
|
| 10 |
"eval_samples": 399,
|
| 11 |
+
"eval_samples_per_second": 217.098,
|
| 12 |
+
"eval_steps_per_second": 27.205,
|
| 13 |
+
"f1": 0.8800505285490955,
|
| 14 |
+
"precision": 0.8759675118494317,
|
| 15 |
+
"recall": 0.8845246947861856,
|
| 16 |
+
"train_loss": 0.2269888150887411,
|
| 17 |
+
"train_runtime": 635.9179,
|
| 18 |
"train_samples": 3638,
|
| 19 |
+
"train_samples_per_second": 114.417,
|
| 20 |
+
"train_steps_per_second": 3.837
|
| 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": 0.8922305764411027,
|
| 4 |
+
"eval_f1": 0.8721887408091659,
|
| 5 |
+
"eval_loss": 0.27931535243988037,
|
| 6 |
+
"eval_precision": 0.866466275659824,
|
| 7 |
+
"eval_recall": 0.8787506819421713,
|
| 8 |
+
"eval_runtime": 1.8379,
|
| 9 |
"eval_samples": 399,
|
| 10 |
+
"eval_samples_per_second": 217.098,
|
| 11 |
+
"eval_steps_per_second": 27.205
|
| 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": 0.8991097922848664,
|
| 3 |
+
"f1": 0.8800505285490955,
|
| 4 |
+
"precision": 0.8759675118494317,
|
| 5 |
+
"recall": 0.8845246947861856
|
| 6 |
}
|
predict_results.txt
CHANGED
|
@@ -1,7 +1,7 @@
|
|
| 1 |
index prediction
|
| 2 |
0 1
|
| 3 |
-
1
|
| 4 |
-
2
|
| 5 |
3 1
|
| 6 |
4 0
|
| 7 |
5 1
|
|
@@ -39,12 +39,12 @@ index prediction
|
|
| 39 |
37 1
|
| 40 |
38 1
|
| 41 |
39 0
|
| 42 |
-
40
|
| 43 |
41 1
|
| 44 |
42 1
|
| 45 |
43 0
|
| 46 |
44 0
|
| 47 |
-
45
|
| 48 |
46 1
|
| 49 |
47 1
|
| 50 |
48 1
|
|
@@ -70,15 +70,15 @@ index prediction
|
|
| 70 |
68 1
|
| 71 |
69 1
|
| 72 |
70 1
|
| 73 |
-
71
|
| 74 |
72 1
|
| 75 |
73 1
|
| 76 |
74 1
|
| 77 |
75 1
|
| 78 |
76 1
|
| 79 |
-
77
|
| 80 |
78 1
|
| 81 |
-
79
|
| 82 |
80 0
|
| 83 |
81 0
|
| 84 |
82 1
|
|
@@ -99,7 +99,7 @@ index prediction
|
|
| 99 |
97 0
|
| 100 |
98 1
|
| 101 |
99 0
|
| 102 |
-
100
|
| 103 |
101 0
|
| 104 |
102 1
|
| 105 |
103 1
|
|
@@ -117,14 +117,14 @@ index prediction
|
|
| 117 |
115 1
|
| 118 |
116 1
|
| 119 |
117 1
|
| 120 |
-
118
|
| 121 |
119 1
|
| 122 |
120 1
|
| 123 |
121 1
|
| 124 |
122 1
|
| 125 |
123 1
|
| 126 |
124 1
|
| 127 |
-
125
|
| 128 |
126 1
|
| 129 |
127 1
|
| 130 |
128 1
|
|
@@ -134,7 +134,7 @@ index prediction
|
|
| 134 |
132 1
|
| 135 |
133 1
|
| 136 |
134 1
|
| 137 |
-
135
|
| 138 |
136 0
|
| 139 |
137 1
|
| 140 |
138 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
|
|
@@ -206,7 +206,7 @@ index prediction
|
|
| 206 |
204 1
|
| 207 |
205 0
|
| 208 |
206 1
|
| 209 |
-
207
|
| 210 |
208 1
|
| 211 |
209 1
|
| 212 |
210 1
|
|
@@ -248,7 +248,7 @@ index prediction
|
|
| 248 |
246 0
|
| 249 |
247 1
|
| 250 |
248 1
|
| 251 |
-
249
|
| 252 |
250 1
|
| 253 |
251 1
|
| 254 |
252 1
|
|
@@ -264,7 +264,7 @@ index prediction
|
|
| 264 |
262 1
|
| 265 |
263 1
|
| 266 |
264 1
|
| 267 |
-
265
|
| 268 |
266 1
|
| 269 |
267 1
|
| 270 |
268 1
|
|
@@ -279,7 +279,7 @@ index prediction
|
|
| 279 |
277 1
|
| 280 |
278 1
|
| 281 |
279 1
|
| 282 |
-
280
|
| 283 |
281 1
|
| 284 |
282 1
|
| 285 |
283 1
|
|
@@ -313,9 +313,9 @@ index prediction
|
|
| 313 |
311 0
|
| 314 |
312 0
|
| 315 |
313 0
|
| 316 |
-
314
|
| 317 |
315 0
|
| 318 |
-
316
|
| 319 |
317 0
|
| 320 |
318 1
|
| 321 |
319 0
|
|
@@ -363,7 +363,7 @@ index prediction
|
|
| 363 |
361 0
|
| 364 |
362 0
|
| 365 |
363 0
|
| 366 |
-
364
|
| 367 |
365 0
|
| 368 |
366 1
|
| 369 |
367 0
|
|
@@ -400,7 +400,7 @@ index prediction
|
|
| 400 |
398 1
|
| 401 |
399 0
|
| 402 |
400 0
|
| 403 |
-
401
|
| 404 |
402 1
|
| 405 |
403 0
|
| 406 |
404 0
|
|
@@ -413,7 +413,7 @@ index prediction
|
|
| 413 |
411 0
|
| 414 |
412 0
|
| 415 |
413 0
|
| 416 |
-
414
|
| 417 |
415 0
|
| 418 |
416 0
|
| 419 |
417 0
|
|
@@ -451,7 +451,7 @@ index prediction
|
|
| 451 |
449 0
|
| 452 |
450 0
|
| 453 |
451 0
|
| 454 |
-
452
|
| 455 |
453 0
|
| 456 |
454 0
|
| 457 |
455 1
|
|
@@ -510,20 +510,20 @@ index prediction
|
|
| 510 |
508 0
|
| 511 |
509 0
|
| 512 |
510 0
|
| 513 |
-
511
|
| 514 |
512 0
|
| 515 |
513 0
|
| 516 |
514 0
|
| 517 |
515 0
|
| 518 |
516 0
|
| 519 |
517 0
|
| 520 |
-
518
|
| 521 |
519 0
|
| 522 |
520 0
|
| 523 |
521 0
|
| 524 |
522 0
|
| 525 |
523 0
|
| 526 |
-
524
|
| 527 |
525 0
|
| 528 |
526 0
|
| 529 |
527 0
|
|
@@ -773,10 +773,10 @@ index prediction
|
|
| 773 |
771 0
|
| 774 |
772 0
|
| 775 |
773 0
|
| 776 |
-
774
|
| 777 |
775 0
|
| 778 |
776 0
|
| 779 |
-
777
|
| 780 |
778 0
|
| 781 |
779 0
|
| 782 |
780 0
|
|
@@ -794,7 +794,7 @@ index prediction
|
|
| 794 |
792 0
|
| 795 |
793 0
|
| 796 |
794 0
|
| 797 |
-
795
|
| 798 |
796 0
|
| 799 |
797 0
|
| 800 |
798 0
|
|
@@ -831,7 +831,7 @@ index prediction
|
|
| 831 |
829 0
|
| 832 |
830 0
|
| 833 |
831 0
|
| 834 |
-
832
|
| 835 |
833 1
|
| 836 |
834 0
|
| 837 |
835 0
|
|
@@ -847,7 +847,7 @@ index prediction
|
|
| 847 |
845 0
|
| 848 |
846 0
|
| 849 |
847 0
|
| 850 |
-
848
|
| 851 |
849 0
|
| 852 |
850 0
|
| 853 |
851 0
|
|
@@ -882,7 +882,7 @@ index prediction
|
|
| 882 |
880 0
|
| 883 |
881 0
|
| 884 |
882 0
|
| 885 |
-
883
|
| 886 |
884 0
|
| 887 |
885 0
|
| 888 |
886 0
|
|
@@ -967,8 +967,8 @@ index prediction
|
|
| 967 |
965 0
|
| 968 |
966 0
|
| 969 |
967 0
|
| 970 |
-
968
|
| 971 |
-
969
|
| 972 |
970 0
|
| 973 |
971 0
|
| 974 |
972 0
|
|
@@ -979,18 +979,18 @@ index prediction
|
|
| 979 |
977 0
|
| 980 |
978 0
|
| 981 |
979 0
|
| 982 |
-
980
|
| 983 |
981 0
|
| 984 |
982 0
|
| 985 |
983 0
|
| 986 |
984 0
|
| 987 |
985 0
|
| 988 |
-
986
|
| 989 |
987 0
|
| 990 |
988 0
|
| 991 |
989 0
|
| 992 |
990 0
|
| 993 |
-
991
|
| 994 |
992 0
|
| 995 |
993 0
|
| 996 |
994 0
|
|
|
|
| 1 |
index prediction
|
| 2 |
0 1
|
| 3 |
+
1 0
|
| 4 |
+
2 1
|
| 5 |
3 1
|
| 6 |
4 0
|
| 7 |
5 1
|
|
|
|
| 39 |
37 1
|
| 40 |
38 1
|
| 41 |
39 0
|
| 42 |
+
40 1
|
| 43 |
41 1
|
| 44 |
42 1
|
| 45 |
43 0
|
| 46 |
44 0
|
| 47 |
+
45 1
|
| 48 |
46 1
|
| 49 |
47 1
|
| 50 |
48 1
|
|
|
|
| 70 |
68 1
|
| 71 |
69 1
|
| 72 |
70 1
|
| 73 |
+
71 0
|
| 74 |
72 1
|
| 75 |
73 1
|
| 76 |
74 1
|
| 77 |
75 1
|
| 78 |
76 1
|
| 79 |
+
77 1
|
| 80 |
78 1
|
| 81 |
+
79 0
|
| 82 |
80 0
|
| 83 |
81 0
|
| 84 |
82 1
|
|
|
|
| 99 |
97 0
|
| 100 |
98 1
|
| 101 |
99 0
|
| 102 |
+
100 1
|
| 103 |
101 0
|
| 104 |
102 1
|
| 105 |
103 1
|
|
|
|
| 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
|
| 127 |
+
125 0
|
| 128 |
126 1
|
| 129 |
127 1
|
| 130 |
128 1
|
|
|
|
| 134 |
132 1
|
| 135 |
133 1
|
| 136 |
134 1
|
| 137 |
+
135 0
|
| 138 |
136 0
|
| 139 |
137 1
|
| 140 |
138 1
|
|
|
|
| 180 |
178 1
|
| 181 |
179 1
|
| 182 |
180 1
|
| 183 |
+
181 0
|
| 184 |
182 1
|
| 185 |
183 1
|
| 186 |
184 1
|
|
|
|
| 206 |
204 1
|
| 207 |
205 0
|
| 208 |
206 1
|
| 209 |
+
207 1
|
| 210 |
208 1
|
| 211 |
209 1
|
| 212 |
210 1
|
|
|
|
| 248 |
246 0
|
| 249 |
247 1
|
| 250 |
248 1
|
| 251 |
+
249 0
|
| 252 |
250 1
|
| 253 |
251 1
|
| 254 |
252 1
|
|
|
|
| 264 |
262 1
|
| 265 |
263 1
|
| 266 |
264 1
|
| 267 |
+
265 1
|
| 268 |
266 1
|
| 269 |
267 1
|
| 270 |
268 1
|
|
|
|
| 279 |
277 1
|
| 280 |
278 1
|
| 281 |
279 1
|
| 282 |
+
280 0
|
| 283 |
281 1
|
| 284 |
282 1
|
| 285 |
283 1
|
|
|
|
| 313 |
311 0
|
| 314 |
312 0
|
| 315 |
313 0
|
| 316 |
+
314 0
|
| 317 |
315 0
|
| 318 |
+
316 1
|
| 319 |
317 0
|
| 320 |
318 1
|
| 321 |
319 0
|
|
|
|
| 363 |
361 0
|
| 364 |
362 0
|
| 365 |
363 0
|
| 366 |
+
364 0
|
| 367 |
365 0
|
| 368 |
366 1
|
| 369 |
367 0
|
|
|
|
| 400 |
398 1
|
| 401 |
399 0
|
| 402 |
400 0
|
| 403 |
+
401 0
|
| 404 |
402 1
|
| 405 |
403 0
|
| 406 |
404 0
|
|
|
|
| 413 |
411 0
|
| 414 |
412 0
|
| 415 |
413 0
|
| 416 |
+
414 1
|
| 417 |
415 0
|
| 418 |
416 0
|
| 419 |
417 0
|
|
|
|
| 451 |
449 0
|
| 452 |
450 0
|
| 453 |
451 0
|
| 454 |
+
452 0
|
| 455 |
453 0
|
| 456 |
454 0
|
| 457 |
455 1
|
|
|
|
| 510 |
508 0
|
| 511 |
509 0
|
| 512 |
510 0
|
| 513 |
+
511 0
|
| 514 |
512 0
|
| 515 |
513 0
|
| 516 |
514 0
|
| 517 |
515 0
|
| 518 |
516 0
|
| 519 |
517 0
|
| 520 |
+
518 1
|
| 521 |
519 0
|
| 522 |
520 0
|
| 523 |
521 0
|
| 524 |
522 0
|
| 525 |
523 0
|
| 526 |
+
524 0
|
| 527 |
525 0
|
| 528 |
526 0
|
| 529 |
527 0
|
|
|
|
| 773 |
771 0
|
| 774 |
772 0
|
| 775 |
773 0
|
| 776 |
+
774 0
|
| 777 |
775 0
|
| 778 |
776 0
|
| 779 |
+
777 1
|
| 780 |
778 0
|
| 781 |
779 0
|
| 782 |
780 0
|
|
|
|
| 794 |
792 0
|
| 795 |
793 0
|
| 796 |
794 0
|
| 797 |
+
795 0
|
| 798 |
796 0
|
| 799 |
797 0
|
| 800 |
798 0
|
|
|
|
| 831 |
829 0
|
| 832 |
830 0
|
| 833 |
831 0
|
| 834 |
+
832 0
|
| 835 |
833 1
|
| 836 |
834 0
|
| 837 |
835 0
|
|
|
|
| 847 |
845 0
|
| 848 |
846 0
|
| 849 |
847 0
|
| 850 |
+
848 0
|
| 851 |
849 0
|
| 852 |
850 0
|
| 853 |
851 0
|
|
|
|
| 882 |
880 0
|
| 883 |
881 0
|
| 884 |
882 0
|
| 885 |
+
883 0
|
| 886 |
884 0
|
| 887 |
885 0
|
| 888 |
886 0
|
|
|
|
| 967 |
965 0
|
| 968 |
966 0
|
| 969 |
967 0
|
| 970 |
+
968 1
|
| 971 |
+
969 0
|
| 972 |
970 0
|
| 973 |
971 0
|
| 974 |
972 0
|
|
|
|
| 979 |
977 0
|
| 980 |
978 0
|
| 981 |
979 0
|
| 982 |
+
980 1
|
| 983 |
981 0
|
| 984 |
982 0
|
| 985 |
983 0
|
| 986 |
984 0
|
| 987 |
985 0
|
| 988 |
+
986 1
|
| 989 |
987 0
|
| 990 |
988 0
|
| 991 |
989 0
|
| 992 |
990 0
|
| 993 |
+
991 1
|
| 994 |
992 0
|
| 995 |
993 0
|
| 996 |
994 0
|
runs/Jun03_13-11-00_a358b85c7679/events.out.tfevents.1717420912.a358b85c7679.99454.1
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:77ca22525a8fdacb0393d85c4cc246d5039ea8401844b7c071b64d239660d172
|
| 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": 0.2269888150887411,
|
| 4 |
+
"train_runtime": 635.9179,
|
| 5 |
"train_samples": 3638,
|
| 6 |
+
"train_samples_per_second": 114.417,
|
| 7 |
+
"train_steps_per_second": 3.837
|
| 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": 3.
|
| 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": 2.
|
| 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": 0.
|
| 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":
|
| 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": 0.8922305764411027,
|
| 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.
|
| 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": 0.
|
| 280 |
"learning_rate": 1.25e-05,
|
| 281 |
-
"loss": 0.
|
| 282 |
"step": 1830
|
| 283 |
},
|
| 284 |
{
|
| 285 |
"epoch": 15.0,
|
| 286 |
"eval_accuracy": 0.9022556390977443,
|
| 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": 1.
|
| 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": 3.
|
| 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": 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": 6.223746299743652,
|
| 14 |
"learning_rate": 4.75e-05,
|
| 15 |
+
"loss": 0.5424,
|
| 16 |
"step": 122
|
| 17 |
},
|
| 18 |
{
|
| 19 |
"epoch": 1.0,
|
| 20 |
+
"eval_accuracy": 0.7418546365914787,
|
| 21 |
+
"eval_f1": 0.6575164379109477,
|
| 22 |
+
"eval_loss": 0.4762427806854248,
|
| 23 |
+
"eval_precision": 0.6837301587301587,
|
| 24 |
+
"eval_recall": 0.647344971813057,
|
| 25 |
+
"eval_runtime": 1.7978,
|
| 26 |
+
"eval_samples_per_second": 221.935,
|
| 27 |
+
"eval_steps_per_second": 27.811,
|
| 28 |
"step": 122
|
| 29 |
},
|
| 30 |
{
|
| 31 |
"epoch": 2.0,
|
| 32 |
+
"grad_norm": 4.059021949768066,
|
| 33 |
"learning_rate": 4.5e-05,
|
| 34 |
+
"loss": 0.4345,
|
| 35 |
"step": 244
|
| 36 |
},
|
| 37 |
{
|
| 38 |
"epoch": 2.0,
|
| 39 |
+
"eval_accuracy": 0.7894736842105263,
|
| 40 |
+
"eval_f1": 0.7673663168415792,
|
| 41 |
+
"eval_loss": 0.41568055748939514,
|
| 42 |
+
"eval_precision": 0.7581367924528302,
|
| 43 |
+
"eval_recall": 0.7985542825968357,
|
| 44 |
+
"eval_runtime": 1.7989,
|
| 45 |
+
"eval_samples_per_second": 221.802,
|
| 46 |
+
"eval_steps_per_second": 27.795,
|
| 47 |
"step": 244
|
| 48 |
},
|
| 49 |
{
|
| 50 |
"epoch": 3.0,
|
| 51 |
+
"grad_norm": 3.354827404022217,
|
| 52 |
"learning_rate": 4.25e-05,
|
| 53 |
+
"loss": 0.3391,
|
| 54 |
"step": 366
|
| 55 |
},
|
| 56 |
{
|
| 57 |
"epoch": 3.0,
|
| 58 |
+
"eval_accuracy": 0.8546365914786967,
|
| 59 |
+
"eval_f1": 0.8180088078011953,
|
| 60 |
+
"eval_loss": 0.33879804611206055,
|
| 61 |
+
"eval_precision": 0.8323930726843348,
|
| 62 |
+
"eval_recall": 0.8071467539552646,
|
| 63 |
+
"eval_runtime": 1.8074,
|
| 64 |
+
"eval_samples_per_second": 220.763,
|
| 65 |
+
"eval_steps_per_second": 27.665,
|
| 66 |
"step": 366
|
| 67 |
},
|
| 68 |
{
|
| 69 |
"epoch": 4.0,
|
| 70 |
+
"grad_norm": 2.747511863708496,
|
| 71 |
"learning_rate": 4e-05,
|
| 72 |
+
"loss": 0.2837,
|
| 73 |
"step": 488
|
| 74 |
},
|
| 75 |
{
|
| 76 |
"epoch": 4.0,
|
| 77 |
+
"eval_accuracy": 0.8621553884711779,
|
| 78 |
+
"eval_f1": 0.8333016825553572,
|
| 79 |
+
"eval_loss": 0.32792460918426514,
|
| 80 |
+
"eval_precision": 0.8341507249908615,
|
| 81 |
+
"eval_recall": 0.8324695399163484,
|
| 82 |
+
"eval_runtime": 1.804,
|
| 83 |
+
"eval_samples_per_second": 221.178,
|
| 84 |
+
"eval_steps_per_second": 27.717,
|
| 85 |
"step": 488
|
| 86 |
},
|
| 87 |
{
|
| 88 |
"epoch": 5.0,
|
| 89 |
+
"grad_norm": 0.42053157091140747,
|
| 90 |
"learning_rate": 3.7500000000000003e-05,
|
| 91 |
+
"loss": 0.2761,
|
| 92 |
"step": 610
|
| 93 |
},
|
| 94 |
{
|
| 95 |
"epoch": 5.0,
|
| 96 |
+
"eval_accuracy": 0.8646616541353384,
|
| 97 |
+
"eval_f1": 0.8391129032258065,
|
| 98 |
+
"eval_loss": 0.31322285532951355,
|
| 99 |
+
"eval_precision": 0.8345705196182396,
|
| 100 |
+
"eval_recall": 0.8442444080741953,
|
| 101 |
+
"eval_runtime": 1.8022,
|
| 102 |
+
"eval_samples_per_second": 221.397,
|
| 103 |
+
"eval_steps_per_second": 27.744,
|
| 104 |
"step": 610
|
| 105 |
},
|
| 106 |
{
|
| 107 |
"epoch": 6.0,
|
| 108 |
+
"grad_norm": 2.2977254390716553,
|
| 109 |
"learning_rate": 3.5e-05,
|
| 110 |
+
"loss": 0.2459,
|
| 111 |
"step": 732
|
| 112 |
},
|
| 113 |
{
|
| 114 |
"epoch": 6.0,
|
| 115 |
+
"eval_accuracy": 0.87468671679198,
|
| 116 |
+
"eval_f1": 0.8543795620437956,
|
| 117 |
+
"eval_loss": 0.3032587468624115,
|
| 118 |
+
"eval_precision": 0.843984962406015,
|
| 119 |
+
"eval_recall": 0.868839789052555,
|
| 120 |
+
"eval_runtime": 1.8072,
|
| 121 |
+
"eval_samples_per_second": 220.78,
|
| 122 |
+
"eval_steps_per_second": 27.667,
|
| 123 |
"step": 732
|
| 124 |
},
|
| 125 |
{
|
| 126 |
"epoch": 7.0,
|
| 127 |
+
"grad_norm": 2.8183882236480713,
|
| 128 |
"learning_rate": 3.2500000000000004e-05,
|
| 129 |
+
"loss": 0.2321,
|
| 130 |
"step": 854
|
| 131 |
},
|
| 132 |
{
|
| 133 |
"epoch": 7.0,
|
| 134 |
+
"eval_accuracy": 0.8822055137844611,
|
| 135 |
+
"eval_f1": 0.8622085718274466,
|
| 136 |
+
"eval_loss": 0.2870577275753021,
|
| 137 |
+
"eval_precision": 0.8530168716042322,
|
| 138 |
+
"eval_recall": 0.8741589379887251,
|
| 139 |
+
"eval_runtime": 1.8055,
|
| 140 |
+
"eval_samples_per_second": 220.996,
|
| 141 |
+
"eval_steps_per_second": 27.694,
|
| 142 |
"step": 854
|
| 143 |
},
|
| 144 |
{
|
| 145 |
"epoch": 8.0,
|
| 146 |
+
"grad_norm": 3.4162003993988037,
|
| 147 |
"learning_rate": 3e-05,
|
| 148 |
+
"loss": 0.2206,
|
| 149 |
"step": 976
|
| 150 |
},
|
| 151 |
{
|
| 152 |
"epoch": 8.0,
|
| 153 |
+
"eval_accuracy": 0.8822055137844611,
|
| 154 |
+
"eval_f1": 0.8560793854229822,
|
| 155 |
+
"eval_loss": 0.2634139955043793,
|
| 156 |
+
"eval_precision": 0.8609538327526132,
|
| 157 |
+
"eval_recall": 0.8516548463356974,
|
| 158 |
+
"eval_runtime": 1.8055,
|
| 159 |
+
"eval_samples_per_second": 220.985,
|
| 160 |
+
"eval_steps_per_second": 27.692,
|
| 161 |
"step": 976
|
| 162 |
},
|
| 163 |
{
|
| 164 |
"epoch": 9.0,
|
| 165 |
+
"grad_norm": 5.009228229522705,
|
| 166 |
"learning_rate": 2.7500000000000004e-05,
|
| 167 |
+
"loss": 0.2067,
|
| 168 |
"step": 1098
|
| 169 |
},
|
| 170 |
{
|
| 171 |
"epoch": 9.0,
|
| 172 |
"eval_accuracy": 0.8922305764411027,
|
| 173 |
+
"eval_f1": 0.8703223612108386,
|
| 174 |
+
"eval_loss": 0.2633897066116333,
|
| 175 |
+
"eval_precision": 0.8694131129742446,
|
| 176 |
+
"eval_recall": 0.8712493180578287,
|
| 177 |
+
"eval_runtime": 1.8057,
|
| 178 |
+
"eval_samples_per_second": 220.963,
|
| 179 |
+
"eval_steps_per_second": 27.69,
|
| 180 |
"step": 1098
|
| 181 |
},
|
| 182 |
{
|
| 183 |
"epoch": 10.0,
|
| 184 |
+
"grad_norm": 0.9459621906280518,
|
| 185 |
"learning_rate": 2.5e-05,
|
| 186 |
+
"loss": 0.192,
|
| 187 |
"step": 1220
|
| 188 |
},
|
| 189 |
{
|
| 190 |
"epoch": 10.0,
|
| 191 |
+
"eval_accuracy": 0.8922305764411027,
|
| 192 |
+
"eval_f1": 0.8631217838765008,
|
| 193 |
+
"eval_loss": 0.2696186900138855,
|
| 194 |
+
"eval_precision": 0.8872804935927859,
|
| 195 |
+
"eval_recall": 0.8462447717766868,
|
| 196 |
+
"eval_runtime": 1.8049,
|
| 197 |
+
"eval_samples_per_second": 221.061,
|
| 198 |
+
"eval_steps_per_second": 27.702,
|
| 199 |
"step": 1220
|
| 200 |
},
|
| 201 |
{
|
| 202 |
"epoch": 11.0,
|
| 203 |
+
"grad_norm": 0.9607306122779846,
|
| 204 |
"learning_rate": 2.25e-05,
|
| 205 |
+
"loss": 0.1866,
|
| 206 |
"step": 1342
|
| 207 |
},
|
| 208 |
{
|
| 209 |
"epoch": 11.0,
|
| 210 |
+
"eval_accuracy": 0.8972431077694235,
|
| 211 |
+
"eval_f1": 0.8808495451466529,
|
| 212 |
+
"eval_loss": 0.2752375304698944,
|
| 213 |
+
"eval_precision": 0.8691495353421572,
|
| 214 |
+
"eval_recall": 0.8972995090016367,
|
| 215 |
+
"eval_runtime": 1.8092,
|
| 216 |
+
"eval_samples_per_second": 220.542,
|
| 217 |
+
"eval_steps_per_second": 27.637,
|
| 218 |
"step": 1342
|
| 219 |
},
|
| 220 |
{
|
| 221 |
"epoch": 12.0,
|
| 222 |
+
"grad_norm": 4.809903621673584,
|
| 223 |
"learning_rate": 2e-05,
|
| 224 |
+
"loss": 0.1786,
|
| 225 |
"step": 1464
|
| 226 |
},
|
| 227 |
{
|
| 228 |
"epoch": 12.0,
|
| 229 |
+
"eval_accuracy": 0.8972431077694235,
|
| 230 |
+
"eval_f1": 0.8792560061999484,
|
| 231 |
+
"eval_loss": 0.2651856243610382,
|
| 232 |
+
"eval_precision": 0.8707622232472325,
|
| 233 |
+
"eval_recall": 0.889798145117294,
|
| 234 |
+
"eval_runtime": 1.8065,
|
| 235 |
+
"eval_samples_per_second": 220.87,
|
| 236 |
+
"eval_steps_per_second": 27.678,
|
| 237 |
"step": 1464
|
| 238 |
},
|
| 239 |
{
|
| 240 |
"epoch": 13.0,
|
| 241 |
+
"grad_norm": 0.7058310508728027,
|
| 242 |
"learning_rate": 1.75e-05,
|
| 243 |
+
"loss": 0.1695,
|
| 244 |
"step": 1586
|
| 245 |
},
|
| 246 |
{
|
| 247 |
"epoch": 13.0,
|
| 248 |
+
"eval_accuracy": 0.9072681704260651,
|
| 249 |
+
"eval_f1": 0.8867007927797945,
|
| 250 |
+
"eval_loss": 0.25362077355384827,
|
| 251 |
+
"eval_precision": 0.89198606271777,
|
| 252 |
+
"eval_recall": 0.8818876159301692,
|
| 253 |
+
"eval_runtime": 1.82,
|
| 254 |
+
"eval_samples_per_second": 219.234,
|
| 255 |
+
"eval_steps_per_second": 27.473,
|
| 256 |
"step": 1586
|
| 257 |
},
|
| 258 |
{
|
| 259 |
"epoch": 14.0,
|
| 260 |
+
"grad_norm": 7.428104877471924,
|
| 261 |
"learning_rate": 1.5e-05,
|
| 262 |
+
"loss": 0.1664,
|
| 263 |
"step": 1708
|
| 264 |
},
|
| 265 |
{
|
| 266 |
"epoch": 14.0,
|
| 267 |
+
"eval_accuracy": 0.8872180451127819,
|
| 268 |
+
"eval_f1": 0.8680720368560659,
|
| 269 |
+
"eval_loss": 0.2736993730068207,
|
| 270 |
+
"eval_precision": 0.8587217615098657,
|
| 271 |
+
"eval_recall": 0.8802054919076197,
|
| 272 |
+
"eval_runtime": 1.8089,
|
| 273 |
+
"eval_samples_per_second": 220.576,
|
| 274 |
+
"eval_steps_per_second": 27.641,
|
| 275 |
"step": 1708
|
| 276 |
},
|
| 277 |
{
|
| 278 |
"epoch": 15.0,
|
| 279 |
+
"grad_norm": 0.6353508234024048,
|
| 280 |
"learning_rate": 1.25e-05,
|
| 281 |
+
"loss": 0.1521,
|
| 282 |
"step": 1830
|
| 283 |
},
|
| 284 |
{
|
| 285 |
"epoch": 15.0,
|
| 286 |
"eval_accuracy": 0.9022556390977443,
|
| 287 |
+
"eval_f1": 0.8829621606985718,
|
| 288 |
+
"eval_loss": 0.26195329427719116,
|
| 289 |
+
"eval_precision": 0.8802419354838709,
|
| 290 |
+
"eval_recall": 0.8858428805237315,
|
| 291 |
+
"eval_runtime": 1.8126,
|
| 292 |
+
"eval_samples_per_second": 220.122,
|
| 293 |
+
"eval_steps_per_second": 27.584,
|
| 294 |
"step": 1830
|
| 295 |
},
|
| 296 |
{
|
| 297 |
"epoch": 16.0,
|
| 298 |
+
"grad_norm": 1.580483317375183,
|
| 299 |
"learning_rate": 1e-05,
|
| 300 |
+
"loss": 0.1494,
|
| 301 |
"step": 1952
|
| 302 |
},
|
| 303 |
{
|
| 304 |
"epoch": 16.0,
|
| 305 |
+
"eval_accuracy": 0.8922305764411027,
|
| 306 |
+
"eval_f1": 0.8760914310475572,
|
| 307 |
+
"eval_loss": 0.30298247933387756,
|
| 308 |
+
"eval_precision": 0.8629851740796268,
|
| 309 |
+
"eval_recall": 0.8962538643389707,
|
| 310 |
+
"eval_runtime": 1.8105,
|
| 311 |
+
"eval_samples_per_second": 220.383,
|
| 312 |
+
"eval_steps_per_second": 27.617,
|
| 313 |
"step": 1952
|
| 314 |
},
|
| 315 |
{
|
| 316 |
"epoch": 17.0,
|
| 317 |
+
"grad_norm": 3.5637781620025635,
|
| 318 |
"learning_rate": 7.5e-06,
|
| 319 |
+
"loss": 0.1487,
|
| 320 |
"step": 2074
|
| 321 |
},
|
| 322 |
{
|
| 323 |
"epoch": 17.0,
|
| 324 |
+
"eval_accuracy": 0.8922305764411027,
|
| 325 |
+
"eval_f1": 0.8733660552828726,
|
| 326 |
+
"eval_loss": 0.2702126204967499,
|
| 327 |
+
"eval_precision": 0.8650109547970479,
|
| 328 |
+
"eval_recall": 0.8837515911983997,
|
| 329 |
+
"eval_runtime": 1.8055,
|
| 330 |
+
"eval_samples_per_second": 220.99,
|
| 331 |
+
"eval_steps_per_second": 27.693,
|
| 332 |
"step": 2074
|
| 333 |
},
|
| 334 |
{
|
| 335 |
"epoch": 18.0,
|
| 336 |
+
"grad_norm": 3.6467041969299316,
|
| 337 |
"learning_rate": 5e-06,
|
| 338 |
+
"loss": 0.1494,
|
| 339 |
"step": 2196
|
| 340 |
},
|
| 341 |
{
|
| 342 |
"epoch": 18.0,
|
| 343 |
+
"eval_accuracy": 0.8947368421052632,
|
| 344 |
+
"eval_f1": 0.8765906680805938,
|
| 345 |
+
"eval_loss": 0.2763027548789978,
|
| 346 |
+
"eval_precision": 0.8675710594315245,
|
| 347 |
+
"eval_recall": 0.888025095471904,
|
| 348 |
+
"eval_runtime": 1.8075,
|
| 349 |
+
"eval_samples_per_second": 220.753,
|
| 350 |
+
"eval_steps_per_second": 27.663,
|
| 351 |
"step": 2196
|
| 352 |
},
|
| 353 |
{
|
| 354 |
"epoch": 19.0,
|
| 355 |
+
"grad_norm": 4.27400541305542,
|
| 356 |
"learning_rate": 2.5e-06,
|
| 357 |
+
"loss": 0.1334,
|
| 358 |
"step": 2318
|
| 359 |
},
|
| 360 |
{
|
| 361 |
"epoch": 19.0,
|
| 362 |
+
"eval_accuracy": 0.8922305764411027,
|
| 363 |
+
"eval_f1": 0.8733660552828726,
|
| 364 |
+
"eval_loss": 0.28261518478393555,
|
| 365 |
+
"eval_precision": 0.8650109547970479,
|
| 366 |
+
"eval_recall": 0.8837515911983997,
|
| 367 |
+
"eval_runtime": 1.8039,
|
| 368 |
+
"eval_samples_per_second": 221.182,
|
| 369 |
+
"eval_steps_per_second": 27.717,
|
| 370 |
"step": 2318
|
| 371 |
},
|
| 372 |
{
|
| 373 |
"epoch": 20.0,
|
| 374 |
+
"grad_norm": 0.5643185377120972,
|
| 375 |
"learning_rate": 0.0,
|
| 376 |
+
"loss": 0.1325,
|
| 377 |
"step": 2440
|
| 378 |
},
|
| 379 |
{
|
| 380 |
"epoch": 20.0,
|
| 381 |
+
"eval_accuracy": 0.8922305764411027,
|
| 382 |
+
"eval_f1": 0.8721887408091659,
|
| 383 |
+
"eval_loss": 0.27931535243988037,
|
| 384 |
+
"eval_precision": 0.866466275659824,
|
| 385 |
+
"eval_recall": 0.8787506819421713,
|
| 386 |
+
"eval_runtime": 1.804,
|
| 387 |
+
"eval_samples_per_second": 221.175,
|
| 388 |
+
"eval_steps_per_second": 27.716,
|
| 389 |
"step": 2440
|
| 390 |
},
|
| 391 |
{
|
| 392 |
"epoch": 20.0,
|
| 393 |
"step": 2440,
|
| 394 |
"total_flos": 8444128359504000.0,
|
| 395 |
+
"train_loss": 0.2269888150887411,
|
| 396 |
+
"train_runtime": 635.9179,
|
| 397 |
+
"train_samples_per_second": 114.417,
|
| 398 |
+
"train_steps_per_second": 3.837
|
| 399 |
}
|
| 400 |
],
|
| 401 |
"logging_steps": 500,
|