add runs
Browse files
runs/events.out.tfevents.1749646322.e94a13c67921.313.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6aab7d47b7d3ac9228957c5fd6c915387bea4f690dfc7324c8002e176ba0de9d
|
| 3 |
+
size 71848
|
runs/events.out.tfevents.1749682764.5f90df3066a1.160.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6c61e2dcd8095d210c6541ea6bb516f43f31b20ef19a84aecc5ad78b453cf453
|
| 3 |
+
size 17382
|
runs/events.out.tfevents.1749707184.ac794c70d841.149.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:af3ae59a469d6ffffd2f475c9ec671873a749a3b2673892e0c4cbede7f73c31a
|
| 3 |
+
size 6654
|
runs/logs.txt
ADDED
|
@@ -0,0 +1,1101 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
The best model checkpoint is: None
|
| 2 |
+
epoch: 0.5494505494505495
|
| 3 |
+
eval_accuracy: 0.9279279279279279
|
| 4 |
+
eval_f1_macro: 0.44779362776725307
|
| 5 |
+
eval_f1_micro: 0.8259838786154575
|
| 6 |
+
eval_loss: 0.23371347784996033
|
| 7 |
+
eval_precision: 0.524253414795906
|
| 8 |
+
eval_recall: 0.43887022747783067
|
| 9 |
+
eval_runtime: 43.3503
|
| 10 |
+
eval_samples_per_second: 14.925
|
| 11 |
+
eval_steps_per_second: 7.474
|
| 12 |
+
step: 100
|
| 13 |
+
epoch: 1.098901098901099
|
| 14 |
+
eval_accuracy: 0.9453402982814747
|
| 15 |
+
eval_f1_macro: 0.5701184625811972
|
| 16 |
+
eval_f1_micro: 0.8833059403615873
|
| 17 |
+
eval_loss: 0.17616893351078033
|
| 18 |
+
eval_precision: 0.6059862763992172
|
| 19 |
+
eval_recall: 0.5754789448410762
|
| 20 |
+
eval_runtime: 43.8839
|
| 21 |
+
eval_samples_per_second: 14.743
|
| 22 |
+
eval_steps_per_second: 7.383
|
| 23 |
+
step: 200
|
| 24 |
+
epoch: 1.6483516483516483
|
| 25 |
+
eval_accuracy: 0.9537436596260126
|
| 26 |
+
eval_f1_macro: 0.6125710321521306
|
| 27 |
+
eval_f1_micro: 0.9048067860508954
|
| 28 |
+
eval_loss: 0.16005800664424896
|
| 29 |
+
eval_precision: 0.6505768603414704
|
| 30 |
+
eval_recall: 0.6139028567910085
|
| 31 |
+
eval_runtime: 44.4902
|
| 32 |
+
eval_samples_per_second: 14.543
|
| 33 |
+
eval_steps_per_second: 7.283
|
| 34 |
+
step: 300
|
| 35 |
+
epoch: 2.197802197802198
|
| 36 |
+
eval_accuracy: 0.95116965705201
|
| 37 |
+
eval_f1_macro: 0.618135634877473
|
| 38 |
+
eval_f1_micro: 0.9088312306593669
|
| 39 |
+
eval_loss: 0.14168420433998108
|
| 40 |
+
eval_precision: 0.6498782608610779
|
| 41 |
+
eval_recall: 0.6074507651627667
|
| 42 |
+
eval_runtime: 44.3202
|
| 43 |
+
eval_samples_per_second: 14.598
|
| 44 |
+
eval_steps_per_second: 7.31
|
| 45 |
+
step: 400
|
| 46 |
+
epoch: 2.7472527472527473
|
| 47 |
+
eval_accuracy: 0.9501854795972443
|
| 48 |
+
eval_f1_macro: 0.677664108799177
|
| 49 |
+
eval_f1_micro: 0.9026672905942912
|
| 50 |
+
eval_loss: 0.1492519974708557
|
| 51 |
+
eval_precision: 0.6810877682669256
|
| 52 |
+
eval_recall: 0.6803215779427296
|
| 53 |
+
eval_runtime: 44.7133
|
| 54 |
+
eval_samples_per_second: 14.47
|
| 55 |
+
eval_steps_per_second: 7.246
|
| 56 |
+
step: 500
|
| 57 |
+
epoch: 3.2967032967032965
|
| 58 |
+
eval_accuracy: 0.9521538345067757
|
| 59 |
+
eval_f1_macro: 0.7159450885353134
|
| 60 |
+
eval_f1_micro: 0.9118881118881119
|
| 61 |
+
eval_loss: 0.18011879920959473
|
| 62 |
+
eval_precision: 0.7071775864977841
|
| 63 |
+
eval_recall: 0.7263909914767879
|
| 64 |
+
eval_runtime: 44.3241
|
| 65 |
+
eval_samples_per_second: 14.597
|
| 66 |
+
eval_steps_per_second: 7.31
|
| 67 |
+
step: 600
|
| 68 |
+
epoch: 3.8461538461538463
|
| 69 |
+
eval_accuracy: 0.9477628889393596
|
| 70 |
+
eval_f1_macro: 0.739795339427405
|
| 71 |
+
eval_f1_micro: 0.9264949184589932
|
| 72 |
+
eval_loss: 0.14054477214813232
|
| 73 |
+
eval_precision: 0.7607844372701156
|
| 74 |
+
eval_recall: 0.7318431721847922
|
| 75 |
+
eval_runtime: 44.4715
|
| 76 |
+
eval_samples_per_second: 14.549
|
| 77 |
+
eval_steps_per_second: 7.286
|
| 78 |
+
step: 700
|
| 79 |
+
epoch: 4.395604395604396
|
| 80 |
+
eval_accuracy: 0.9626012567189037
|
| 81 |
+
eval_f1_macro: 0.7642509447334085
|
| 82 |
+
eval_f1_micro: 0.9261523988711193
|
| 83 |
+
eval_loss: 0.1472887098789215
|
| 84 |
+
eval_precision: 0.7844108844957702
|
| 85 |
+
eval_recall: 0.7585659665576563
|
| 86 |
+
eval_runtime: 44.1535
|
| 87 |
+
eval_samples_per_second: 14.653
|
| 88 |
+
eval_steps_per_second: 7.338
|
| 89 |
+
step: 800
|
| 90 |
+
epoch: 4.945054945054945
|
| 91 |
+
eval_accuracy: 0.9589673707320766
|
| 92 |
+
eval_f1_macro: 0.7539784197175663
|
| 93 |
+
eval_f1_micro: 0.9202797202797203
|
| 94 |
+
eval_loss: 0.13378015160560608
|
| 95 |
+
eval_precision: 0.7499806532935454
|
| 96 |
+
eval_recall: 0.7627374125453109
|
| 97 |
+
eval_runtime: 44.2366
|
| 98 |
+
eval_samples_per_second: 14.626
|
| 99 |
+
eval_steps_per_second: 7.324
|
| 100 |
+
step: 900
|
| 101 |
+
epoch: 5.4945054945054945
|
| 102 |
+
eval_accuracy: 0.9621470209705504
|
| 103 |
+
eval_f1_macro: 0.7827556488480677
|
| 104 |
+
eval_f1_micro: 0.9345531315974667
|
| 105 |
+
eval_loss: 0.1560617834329605
|
| 106 |
+
eval_precision: 0.7854423746754686
|
| 107 |
+
eval_recall: 0.7860690774346966
|
| 108 |
+
eval_runtime: 44.5619
|
| 109 |
+
eval_samples_per_second: 14.519
|
| 110 |
+
eval_steps_per_second: 7.271
|
| 111 |
+
step: 1000
|
| 112 |
+
epoch: 6.043956043956044
|
| 113 |
+
eval_accuracy: 0.963963963963964
|
| 114 |
+
eval_f1_macro: 0.7585567269579849
|
| 115 |
+
eval_f1_micro: 0.9282385834109972
|
| 116 |
+
eval_loss: 0.14864178001880646
|
| 117 |
+
eval_precision: 0.7599596397846446
|
| 118 |
+
eval_recall: 0.7780677312824537
|
| 119 |
+
eval_runtime: 44.3759
|
| 120 |
+
eval_samples_per_second: 14.58
|
| 121 |
+
eval_steps_per_second: 7.301
|
| 122 |
+
step: 1100
|
| 123 |
+
epoch: 6.593406593406593
|
| 124 |
+
eval_accuracy: 0.9577560754031342
|
| 125 |
+
eval_f1_macro: 0.7600496285297305
|
| 126 |
+
eval_f1_micro: 0.9237983587338805
|
| 127 |
+
eval_loss: 0.15428850054740906
|
| 128 |
+
eval_precision: 0.7725484033588037
|
| 129 |
+
eval_recall: 0.7614890515670951
|
| 130 |
+
eval_runtime: 44.0387
|
| 131 |
+
eval_samples_per_second: 14.692
|
| 132 |
+
eval_steps_per_second: 7.357
|
| 133 |
+
step: 1200
|
| 134 |
+
epoch: 7.142857142857143
|
| 135 |
+
eval_accuracy: 0.9625255507608449
|
| 136 |
+
eval_f1_macro: 0.7877845997520632
|
| 137 |
+
eval_f1_micro: 0.9343720491029274
|
| 138 |
+
eval_loss: 0.16259320080280304
|
| 139 |
+
eval_precision: 0.8283909338489288
|
| 140 |
+
eval_recall: 0.7640533779494474
|
| 141 |
+
eval_runtime: 44.5412
|
| 142 |
+
eval_samples_per_second: 14.526
|
| 143 |
+
eval_steps_per_second: 7.274
|
| 144 |
+
step: 1300
|
| 145 |
+
epoch: 7.6923076923076925
|
| 146 |
+
eval_accuracy: 0.95942160648043
|
| 147 |
+
eval_f1_macro: 0.7702199144752583
|
| 148 |
+
eval_f1_micro: 0.9283869452923221
|
| 149 |
+
eval_loss: 0.17969951033592224
|
| 150 |
+
eval_precision: 0.8027447318311205
|
| 151 |
+
eval_recall: 0.7531377667006539
|
| 152 |
+
eval_runtime: 44.9836
|
| 153 |
+
eval_samples_per_second: 14.383
|
| 154 |
+
eval_steps_per_second: 7.203
|
| 155 |
+
step: 1400
|
| 156 |
+
epoch: 8.241758241758241
|
| 157 |
+
eval_accuracy: 0.9651752592929064
|
| 158 |
+
eval_f1_macro: 0.7892760425303124
|
| 159 |
+
eval_f1_micro: 0.9332708967454927
|
| 160 |
+
eval_loss: 0.1661366969347
|
| 161 |
+
eval_precision: 0.7860171577041786
|
| 162 |
+
eval_recall: 0.7969562083031705
|
| 163 |
+
eval_runtime: 47.7205
|
| 164 |
+
eval_samples_per_second: 13.558
|
| 165 |
+
eval_steps_per_second: 6.79
|
| 166 |
+
step: 1500
|
| 167 |
+
epoch: 8.791208791208792
|
| 168 |
+
eval_accuracy: 0.9608600196835491
|
| 169 |
+
eval_f1_macro: 0.8077080189784076
|
| 170 |
+
eval_f1_micro: 0.9359605911330049
|
| 171 |
+
eval_loss: 0.1693376749753952
|
| 172 |
+
eval_precision: 0.8144288844035119
|
| 173 |
+
eval_recall: 0.8039449777566106
|
| 174 |
+
eval_runtime: 48.312
|
| 175 |
+
eval_samples_per_second: 13.392
|
| 176 |
+
eval_steps_per_second: 6.706
|
| 177 |
+
step: 1600
|
| 178 |
+
epoch: 9.340659340659341
|
| 179 |
+
eval_accuracy: 0.9592701945643122
|
| 180 |
+
eval_f1_macro: 0.7795970196055722
|
| 181 |
+
eval_f1_micro: 0.9289566236811255
|
| 182 |
+
eval_loss: 0.18387655913829803
|
| 183 |
+
eval_precision: 0.7773975385956675
|
| 184 |
+
eval_recall: 0.7863282306441239
|
| 185 |
+
eval_runtime: 44.3441
|
| 186 |
+
eval_samples_per_second: 14.59
|
| 187 |
+
eval_steps_per_second: 7.306
|
| 188 |
+
step: 1700
|
| 189 |
+
epoch: 9.89010989010989
|
| 190 |
+
eval_accuracy: 0.9573775456128397
|
| 191 |
+
eval_f1_macro: 0.7811036840473671
|
| 192 |
+
eval_f1_micro: 0.9305164319248826
|
| 193 |
+
eval_loss: 0.202822744846344
|
| 194 |
+
eval_precision: 0.7731644500752529
|
| 195 |
+
eval_recall: 0.791453040582895
|
| 196 |
+
eval_runtime: 45.1616
|
| 197 |
+
eval_samples_per_second: 14.326
|
| 198 |
+
eval_steps_per_second: 7.174
|
| 199 |
+
step: 1800
|
| 200 |
+
epoch: 10.43956043956044
|
| 201 |
+
eval_accuracy: 0.9598001362707245
|
| 202 |
+
eval_f1_macro: 0.7750039155813875
|
| 203 |
+
eval_f1_micro: 0.9292929292929294
|
| 204 |
+
eval_loss: 0.1823168247938156
|
| 205 |
+
eval_precision: 0.75464522856061
|
| 206 |
+
eval_recall: 0.7993151995573852
|
| 207 |
+
eval_runtime: 44.6993
|
| 208 |
+
eval_samples_per_second: 14.474
|
| 209 |
+
eval_steps_per_second: 7.248
|
| 210 |
+
step: 1900
|
| 211 |
+
epoch: 10.989010989010989
|
| 212 |
+
eval_accuracy: 0.9681277916572034
|
| 213 |
+
eval_f1_macro: 0.7977636018344789
|
| 214 |
+
eval_f1_micro: 0.9412317818523741
|
| 215 |
+
eval_loss: 0.17782962322235107
|
| 216 |
+
eval_precision: 0.7854749693925036
|
| 217 |
+
eval_recall: 0.8119371640365305
|
| 218 |
+
eval_runtime: 45.0
|
| 219 |
+
eval_samples_per_second: 14.378
|
| 220 |
+
eval_steps_per_second: 7.2
|
| 221 |
+
step: 2000
|
| 222 |
+
epoch: 11.538461538461538
|
| 223 |
+
eval_accuracy: 0.9635097282156105
|
| 224 |
+
eval_f1_macro: 0.7994067172260165
|
| 225 |
+
eval_f1_micro: 0.9365601503759399
|
| 226 |
+
eval_loss: 0.20882855355739594
|
| 227 |
+
eval_precision: 0.7971939876415218
|
| 228 |
+
eval_recall: 0.8072369210553384
|
| 229 |
+
eval_runtime: 44.6973
|
| 230 |
+
eval_samples_per_second: 14.475
|
| 231 |
+
eval_steps_per_second: 7.249
|
| 232 |
+
step: 2100
|
| 233 |
+
epoch: 12.087912087912088
|
| 234 |
+
eval_accuracy: 0.9629040805511394
|
| 235 |
+
eval_f1_macro: 0.7908311844046272
|
| 236 |
+
eval_f1_micro: 0.9330524344569288
|
| 237 |
+
eval_loss: 0.21229593455791473
|
| 238 |
+
eval_precision: 0.772262603683336
|
| 239 |
+
eval_recall: 0.8137563281635996
|
| 240 |
+
eval_runtime: 44.7043
|
| 241 |
+
eval_samples_per_second: 14.473
|
| 242 |
+
eval_steps_per_second: 7.248
|
| 243 |
+
step: 2200
|
| 244 |
+
epoch: 12.637362637362637
|
| 245 |
+
eval_accuracy: 0.9613899613899614
|
| 246 |
+
eval_f1_macro: 0.7927954863853546
|
| 247 |
+
eval_f1_micro: 0.9317493594223154
|
| 248 |
+
eval_loss: 0.18339429795742035
|
| 249 |
+
eval_precision: 0.7777311672067361
|
| 250 |
+
eval_recall: 0.8206438001195944
|
| 251 |
+
eval_runtime: 45.3634
|
| 252 |
+
eval_samples_per_second: 14.263
|
| 253 |
+
eval_steps_per_second: 7.142
|
| 254 |
+
step: 2300
|
| 255 |
+
epoch: 13.186813186813186
|
| 256 |
+
eval_accuracy: 0.9626012567189037
|
| 257 |
+
eval_f1_macro: 0.8017358306147485
|
| 258 |
+
eval_f1_micro: 0.9376323840903742
|
| 259 |
+
eval_loss: 0.20664654672145844
|
| 260 |
+
eval_precision: 0.7969263008203343
|
| 261 |
+
eval_recall: 0.8083837152235677
|
| 262 |
+
eval_runtime: 44.7893
|
| 263 |
+
eval_samples_per_second: 14.445
|
| 264 |
+
eval_steps_per_second: 7.234
|
| 265 |
+
step: 2400
|
| 266 |
+
epoch: 13.736263736263737
|
| 267 |
+
eval_accuracy: 0.9629040805511394
|
| 268 |
+
eval_f1_macro: 0.7956467999630891
|
| 269 |
+
eval_f1_micro: 0.9427625354777672
|
| 270 |
+
eval_loss: 0.22279223799705505
|
| 271 |
+
eval_precision: 0.8380750231080947
|
| 272 |
+
eval_recall: 0.7644342502020218
|
| 273 |
+
eval_runtime: 45.1654
|
| 274 |
+
eval_samples_per_second: 14.325
|
| 275 |
+
eval_steps_per_second: 7.174
|
| 276 |
+
step: 2500
|
| 277 |
+
epoch: 14.285714285714286
|
| 278 |
+
eval_accuracy: 0.9613142554319025
|
| 279 |
+
eval_f1_macro: 0.7872515152700843
|
| 280 |
+
eval_f1_micro: 0.9370004701457452
|
| 281 |
+
eval_loss: 0.23372818529605865
|
| 282 |
+
eval_precision: 0.7869409352414076
|
| 283 |
+
eval_recall: 0.7940077477870195
|
| 284 |
+
eval_runtime: 44.8213
|
| 285 |
+
eval_samples_per_second: 14.435
|
| 286 |
+
eval_steps_per_second: 7.229
|
| 287 |
+
step: 2600
|
| 288 |
+
epoch: 14.835164835164836
|
| 289 |
+
eval_accuracy: 0.9615413733060791
|
| 290 |
+
eval_f1_macro: 0.7828275380236529
|
| 291 |
+
eval_f1_micro: 0.9376323840903742
|
| 292 |
+
eval_loss: 0.21177199482917786
|
| 293 |
+
eval_precision: 0.7806243661989258
|
| 294 |
+
eval_recall: 0.7920396081498648
|
| 295 |
+
eval_runtime: 45.1302
|
| 296 |
+
eval_samples_per_second: 14.336
|
| 297 |
+
eval_steps_per_second: 7.179
|
| 298 |
+
step: 2700
|
| 299 |
+
epoch: 15.384615384615385
|
| 300 |
+
eval_accuracy: 0.9647967295026119
|
| 301 |
+
eval_f1_macro: 0.7793292518024486
|
| 302 |
+
eval_f1_micro: 0.9364595545134818
|
| 303 |
+
eval_loss: 0.2239152491092682
|
| 304 |
+
eval_precision: 0.7727003032309672
|
| 305 |
+
eval_recall: 0.7929491509061503
|
| 306 |
+
eval_runtime: 44.0725
|
| 307 |
+
eval_samples_per_second: 14.68
|
| 308 |
+
eval_steps_per_second: 7.352
|
| 309 |
+
step: 2800
|
| 310 |
+
epoch: 15.934065934065934
|
| 311 |
+
eval_accuracy: 0.962449844802786
|
| 312 |
+
eval_f1_macro: 0.797642857288319
|
| 313 |
+
eval_f1_micro: 0.9396855198310256
|
| 314 |
+
eval_loss: 0.22395440936088562
|
| 315 |
+
eval_precision: 0.8023814361717921
|
| 316 |
+
eval_recall: 0.7989511945936412
|
| 317 |
+
eval_runtime: 45.061
|
| 318 |
+
eval_samples_per_second: 14.358
|
| 319 |
+
eval_steps_per_second: 7.19
|
| 320 |
+
step: 2900
|
| 321 |
+
epoch: 16.483516483516482
|
| 322 |
+
eval_accuracy: 0.9635097282156105
|
| 323 |
+
eval_f1_macro: 0.8007590114957123
|
| 324 |
+
eval_f1_micro: 0.9381783860311467
|
| 325 |
+
eval_loss: 0.21377483010292053
|
| 326 |
+
eval_precision: 0.7998484024146872
|
| 327 |
+
eval_recall: 0.8044673620531326
|
| 328 |
+
eval_runtime: 44.8078
|
| 329 |
+
eval_samples_per_second: 14.439
|
| 330 |
+
eval_steps_per_second: 7.231
|
| 331 |
+
step: 3000
|
| 332 |
+
epoch: 17.032967032967033
|
| 333 |
+
eval_accuracy: 0.9615413733060791
|
| 334 |
+
eval_f1_macro: 0.7972339760531477
|
| 335 |
+
eval_f1_micro: 0.9448669201520913
|
| 336 |
+
eval_loss: 0.25914421677589417
|
| 337 |
+
eval_precision: 0.8406870841557026
|
| 338 |
+
eval_recall: 0.7692548535455201
|
| 339 |
+
eval_runtime: 45.187
|
| 340 |
+
eval_samples_per_second: 14.318
|
| 341 |
+
eval_steps_per_second: 7.17
|
| 342 |
+
step: 3100
|
| 343 |
+
epoch: 17.582417582417584
|
| 344 |
+
eval_accuracy: 0.9603300779771368
|
| 345 |
+
eval_f1_macro: 0.7766581399687886
|
| 346 |
+
eval_f1_micro: 0.9382948657560056
|
| 347 |
+
eval_loss: 0.23785334825515747
|
| 348 |
+
eval_precision: 0.788816751077448
|
| 349 |
+
eval_recall: 0.7751752130854819
|
| 350 |
+
eval_runtime: 44.3184
|
| 351 |
+
eval_samples_per_second: 14.599
|
| 352 |
+
eval_steps_per_second: 7.311
|
| 353 |
+
step: 3200
|
| 354 |
+
epoch: 18.13186813186813
|
| 355 |
+
eval_accuracy: 0.9629040805511394
|
| 356 |
+
eval_f1_macro: 0.8092147621930836
|
| 357 |
+
eval_f1_micro: 0.9476427386875148
|
| 358 |
+
eval_loss: 0.21717622876167297
|
| 359 |
+
eval_precision: 0.8299199793359493
|
| 360 |
+
eval_recall: 0.7944793541881009
|
| 361 |
+
eval_runtime: 44.5086
|
| 362 |
+
eval_samples_per_second: 14.537
|
| 363 |
+
eval_steps_per_second: 7.279
|
| 364 |
+
step: 3300
|
| 365 |
+
epoch: 18.681318681318682
|
| 366 |
+
eval_accuracy: 0.963206904383375
|
| 367 |
+
eval_f1_macro: 0.7921136917184642
|
| 368 |
+
eval_f1_micro: 0.9447069943289225
|
| 369 |
+
eval_loss: 0.25109174847602844
|
| 370 |
+
eval_precision: 0.8232275440646566
|
| 371 |
+
eval_recall: 0.7741817218631578
|
| 372 |
+
eval_runtime: 44.2432
|
| 373 |
+
eval_samples_per_second: 14.624
|
| 374 |
+
eval_steps_per_second: 7.323
|
| 375 |
+
step: 3400
|
| 376 |
+
epoch: 19.23076923076923
|
| 377 |
+
eval_accuracy: 0.9620713150124914
|
| 378 |
+
eval_f1_macro: 0.7990723555001413
|
| 379 |
+
eval_f1_micro: 0.9417566932832315
|
| 380 |
+
eval_loss: 0.2310410887002945
|
| 381 |
+
eval_precision: 0.8077156727254979
|
| 382 |
+
eval_recall: 0.7980887847063167
|
| 383 |
+
eval_runtime: 44.2994
|
| 384 |
+
eval_samples_per_second: 14.605
|
| 385 |
+
eval_steps_per_second: 7.314
|
| 386 |
+
step: 3500
|
| 387 |
+
epoch: 19.78021978021978
|
| 388 |
+
eval_accuracy: 0.9625255507608449
|
| 389 |
+
eval_f1_macro: 0.7860250761134995
|
| 390 |
+
eval_f1_micro: 0.94012258368694
|
| 391 |
+
eval_loss: 0.2525017261505127
|
| 392 |
+
eval_precision: 0.8042490033606836
|
| 393 |
+
eval_recall: 0.7760791914983172
|
| 394 |
+
eval_runtime: 44.7304
|
| 395 |
+
eval_samples_per_second: 14.464
|
| 396 |
+
eval_steps_per_second: 7.243
|
| 397 |
+
step: 3600
|
| 398 |
+
epoch: 20.32967032967033
|
| 399 |
+
eval_accuracy: 0.9602543720190779
|
| 400 |
+
eval_f1_macro: 0.8030856531080768
|
| 401 |
+
eval_f1_micro: 0.9432540616906052
|
| 402 |
+
eval_loss: 0.25282591581344604
|
| 403 |
+
eval_precision: 0.8063629084337276
|
| 404 |
+
eval_recall: 0.8017767352591536
|
| 405 |
+
eval_runtime: 44.6478
|
| 406 |
+
eval_samples_per_second: 14.491
|
| 407 |
+
eval_steps_per_second: 7.257
|
| 408 |
+
step: 3700
|
| 409 |
+
epoch: 20.87912087912088
|
| 410 |
+
eval_accuracy: 0.9593459005223711
|
| 411 |
+
eval_f1_macro: 0.7651362087651102
|
| 412 |
+
eval_f1_micro: 0.9344875994384652
|
| 413 |
+
eval_loss: 0.2721259593963623
|
| 414 |
+
eval_precision: 0.7763071761006594
|
| 415 |
+
eval_recall: 0.7631981340692928
|
| 416 |
+
eval_runtime: 45.045
|
| 417 |
+
eval_samples_per_second: 14.363
|
| 418 |
+
eval_steps_per_second: 7.193
|
| 419 |
+
step: 3800
|
| 420 |
+
epoch: 21.428571428571427
|
| 421 |
+
eval_accuracy: 0.9544250132485427
|
| 422 |
+
eval_f1_macro: 0.7915306498332647
|
| 423 |
+
eval_f1_micro: 0.9381030830783713
|
| 424 |
+
eval_loss: 0.2800194025039673
|
| 425 |
+
eval_precision: 0.8027168361122311
|
| 426 |
+
eval_recall: 0.7870901142011854
|
| 427 |
+
eval_runtime: 45.2109
|
| 428 |
+
eval_samples_per_second: 14.311
|
| 429 |
+
eval_steps_per_second: 7.166
|
| 430 |
+
step: 3900
|
| 431 |
+
epoch: 21.978021978021978
|
| 432 |
+
eval_accuracy: 0.9583617230676055
|
| 433 |
+
eval_f1_macro: 0.7848025720627654
|
| 434 |
+
eval_f1_micro: 0.9370170920159213
|
| 435 |
+
eval_loss: 0.24700461328029633
|
| 436 |
+
eval_precision: 0.7720466707094134
|
| 437 |
+
eval_recall: 0.8043284873614172
|
| 438 |
+
eval_runtime: 44.7875
|
| 439 |
+
eval_samples_per_second: 14.446
|
| 440 |
+
eval_steps_per_second: 7.234
|
| 441 |
+
step: 4000
|
| 442 |
+
epoch: 22.52747252747253
|
| 443 |
+
eval_accuracy: 0.9594973124384889
|
| 444 |
+
eval_f1_macro: 0.7710982637116797
|
| 445 |
+
eval_f1_micro: 0.9351503759398496
|
| 446 |
+
eval_loss: 0.26288092136383057
|
| 447 |
+
eval_precision: 0.7713017303448763
|
| 448 |
+
eval_recall: 0.7759084558853485
|
| 449 |
+
eval_runtime: 45.6494
|
| 450 |
+
eval_samples_per_second: 14.173
|
| 451 |
+
eval_steps_per_second: 7.098
|
| 452 |
+
step: 4100
|
| 453 |
+
epoch: 23.076923076923077
|
| 454 |
+
eval_accuracy: 0.9644939056703763
|
| 455 |
+
eval_f1_macro: 0.7997401570867027
|
| 456 |
+
eval_f1_micro: 0.9380739345420297
|
| 457 |
+
eval_loss: 0.2346334606409073
|
| 458 |
+
eval_precision: 0.8040306424173699
|
| 459 |
+
eval_recall: 0.7994416529253119
|
| 460 |
+
eval_runtime: 45.8503
|
| 461 |
+
eval_samples_per_second: 14.111
|
| 462 |
+
eval_steps_per_second: 7.066
|
| 463 |
+
step: 4200
|
| 464 |
+
epoch: 23.626373626373628
|
| 465 |
+
eval_accuracy: 0.963963963963964
|
| 466 |
+
eval_f1_macro: 0.7846635868423602
|
| 467 |
+
eval_f1_micro: 0.9387370405278039
|
| 468 |
+
eval_loss: 0.2391205132007599
|
| 469 |
+
eval_precision: 0.8027085402552897
|
| 470 |
+
eval_recall: 0.773531449887275
|
| 471 |
+
eval_runtime: 45.2946
|
| 472 |
+
eval_samples_per_second: 14.284
|
| 473 |
+
eval_steps_per_second: 7.153
|
| 474 |
+
step: 4300
|
| 475 |
+
epoch: 24.175824175824175
|
| 476 |
+
eval_accuracy: 0.9625255507608449
|
| 477 |
+
eval_f1_macro: 0.7744878795148958
|
| 478 |
+
eval_f1_micro: 0.9383529411764705
|
| 479 |
+
eval_loss: 0.25943806767463684
|
| 480 |
+
eval_precision: 0.7731878131326322
|
| 481 |
+
eval_recall: 0.7773631249536539
|
| 482 |
+
eval_runtime: 49.3015
|
| 483 |
+
eval_samples_per_second: 13.123
|
| 484 |
+
eval_steps_per_second: 6.572
|
| 485 |
+
step: 4400
|
| 486 |
+
epoch: 24.725274725274726
|
| 487 |
+
eval_accuracy: 0.963206904383375
|
| 488 |
+
eval_f1_macro: 0.7923914817190334
|
| 489 |
+
eval_f1_micro: 0.9407632872863498
|
| 490 |
+
eval_loss: 0.2456328272819519
|
| 491 |
+
eval_precision: 0.7881699378094942
|
| 492 |
+
eval_recall: 0.8061969378084447
|
| 493 |
+
eval_runtime: 45.7069
|
| 494 |
+
eval_samples_per_second: 14.155
|
| 495 |
+
eval_steps_per_second: 7.089
|
| 496 |
+
step: 4500
|
| 497 |
+
epoch: 25.274725274725274
|
| 498 |
+
eval_accuracy: 0.9653266712090242
|
| 499 |
+
eval_f1_macro: 0.8118528873507348
|
| 500 |
+
eval_f1_micro: 0.9459523247580834
|
| 501 |
+
eval_loss: 0.24003900587558746
|
| 502 |
+
eval_precision: 0.8281224158139593
|
| 503 |
+
eval_recall: 0.8020981204200461
|
| 504 |
+
eval_runtime: 45.3138
|
| 505 |
+
eval_samples_per_second: 14.278
|
| 506 |
+
eval_steps_per_second: 7.15
|
| 507 |
+
step: 4600
|
| 508 |
+
epoch: 25.824175824175825
|
| 509 |
+
eval_accuracy: 0.9613142554319025
|
| 510 |
+
eval_f1_macro: 0.793049242520214
|
| 511 |
+
eval_f1_micro: 0.9393226716839135
|
| 512 |
+
eval_loss: 0.24749039113521576
|
| 513 |
+
eval_precision: 0.8034501037947791
|
| 514 |
+
eval_recall: 0.7928553083181551
|
| 515 |
+
eval_runtime: 44.4971
|
| 516 |
+
eval_samples_per_second: 14.54
|
| 517 |
+
eval_steps_per_second: 7.281
|
| 518 |
+
step: 4700
|
| 519 |
+
epoch: 26.373626373626372
|
| 520 |
+
eval_accuracy: 0.9659323188734954
|
| 521 |
+
eval_f1_macro: 0.7988768987759145
|
| 522 |
+
eval_f1_micro: 0.945034206180703
|
| 523 |
+
eval_loss: 0.23364059627056122
|
| 524 |
+
eval_precision: 0.812631346847688
|
| 525 |
+
eval_recall: 0.7878423202902908
|
| 526 |
+
eval_runtime: 45.1806
|
| 527 |
+
eval_samples_per_second: 14.32
|
| 528 |
+
eval_steps_per_second: 7.171
|
| 529 |
+
step: 4800
|
| 530 |
+
epoch: 26.923076923076923
|
| 531 |
+
eval_accuracy: 0.9663108486637898
|
| 532 |
+
eval_f1_macro: 0.8046744625156108
|
| 533 |
+
eval_f1_micro: 0.9461556548318835
|
| 534 |
+
eval_loss: 0.234193354845047
|
| 535 |
+
eval_precision: 0.8165180558143772
|
| 536 |
+
eval_recall: 0.8006581400999713
|
| 537 |
+
eval_runtime: 45.1217
|
| 538 |
+
eval_samples_per_second: 14.339
|
| 539 |
+
eval_steps_per_second: 7.181
|
| 540 |
+
step: 4900
|
| 541 |
+
epoch: 27.47252747252747
|
| 542 |
+
eval_accuracy: 0.9657809069573775
|
| 543 |
+
eval_f1_macro: 0.8041254412943075
|
| 544 |
+
eval_f1_micro: 0.9447708578143361
|
| 545 |
+
eval_loss: 0.24632887542247772
|
| 546 |
+
eval_precision: 0.8045255948853929
|
| 547 |
+
eval_recall: 0.8095586089082767
|
| 548 |
+
eval_runtime: 44.9405
|
| 549 |
+
eval_samples_per_second: 14.397
|
| 550 |
+
eval_steps_per_second: 7.21
|
| 551 |
+
step: 5000
|
| 552 |
+
epoch: 28.021978021978022
|
| 553 |
+
eval_accuracy: 0.9637368460897873
|
| 554 |
+
eval_f1_macro: 0.7956903398417361
|
| 555 |
+
eval_f1_micro: 0.9436453666588069
|
| 556 |
+
eval_loss: 0.23329263925552368
|
| 557 |
+
eval_precision: 0.8011830083443847
|
| 558 |
+
eval_recall: 0.7972306205204887
|
| 559 |
+
eval_runtime: 44.6312
|
| 560 |
+
eval_samples_per_second: 14.497
|
| 561 |
+
eval_steps_per_second: 7.26
|
| 562 |
+
step: 5100
|
| 563 |
+
epoch: 28.571428571428573
|
| 564 |
+
eval_accuracy: 0.9627526686350216
|
| 565 |
+
eval_f1_macro: 0.7860235226715995
|
| 566 |
+
eval_f1_micro: 0.9388901896511356
|
| 567 |
+
eval_loss: 0.2486635446548462
|
| 568 |
+
eval_precision: 0.7801462064455899
|
| 569 |
+
eval_recall: 0.7932597037373754
|
| 570 |
+
eval_runtime: 45.4878
|
| 571 |
+
eval_samples_per_second: 14.224
|
| 572 |
+
eval_steps_per_second: 7.123
|
| 573 |
+
step: 5200
|
| 574 |
+
epoch: 29.12087912087912
|
| 575 |
+
eval_accuracy: 0.9645696116284351
|
| 576 |
+
eval_f1_macro: 0.8089643150816952
|
| 577 |
+
eval_f1_micro: 0.9448893075836082
|
| 578 |
+
eval_loss: 0.2528458535671234
|
| 579 |
+
eval_precision: 0.8324829961548832
|
| 580 |
+
eval_recall: 0.7945003481776624
|
| 581 |
+
eval_runtime: 44.4737
|
| 582 |
+
eval_samples_per_second: 14.548
|
| 583 |
+
eval_steps_per_second: 7.285
|
| 584 |
+
step: 5300
|
| 585 |
+
epoch: 29.67032967032967
|
| 586 |
+
eval_accuracy: 0.9657052009993187
|
| 587 |
+
eval_f1_macro: 0.8107023500958457
|
| 588 |
+
eval_f1_micro: 0.9472444653791805
|
| 589 |
+
eval_loss: 0.24543903768062592
|
| 590 |
+
eval_precision: 0.8084753521463686
|
| 591 |
+
eval_recall: 0.8131336396323268
|
| 592 |
+
eval_runtime: 44.3608
|
| 593 |
+
eval_samples_per_second: 14.585
|
| 594 |
+
eval_steps_per_second: 7.304
|
| 595 |
+
step: 5400
|
| 596 |
+
epoch: 30.21978021978022
|
| 597 |
+
eval_accuracy: 0.9638125520478462
|
| 598 |
+
eval_f1_macro: 0.7992932868882667
|
| 599 |
+
eval_f1_micro: 0.9442746296731719
|
| 600 |
+
eval_loss: 0.2687099575996399
|
| 601 |
+
eval_precision: 0.8024600763017596
|
| 602 |
+
eval_recall: 0.8015727168933665
|
| 603 |
+
eval_runtime: 43.8916
|
| 604 |
+
eval_samples_per_second: 14.741
|
| 605 |
+
eval_steps_per_second: 7.382
|
| 606 |
+
step: 5500
|
| 607 |
+
epoch: 30.76923076923077
|
| 608 |
+
eval_accuracy: 0.9619199030963737
|
| 609 |
+
eval_f1_macro: 0.8025632783404111
|
| 610 |
+
eval_f1_micro: 0.9419537517697028
|
| 611 |
+
eval_loss: 0.26613762974739075
|
| 612 |
+
eval_precision: 0.8223225866653339
|
| 613 |
+
eval_recall: 0.7909847668071477
|
| 614 |
+
eval_runtime: 45.2766
|
| 615 |
+
eval_samples_per_second: 14.29
|
| 616 |
+
eval_steps_per_second: 7.156
|
| 617 |
+
step: 5600
|
| 618 |
+
epoch: 31.318681318681318
|
| 619 |
+
eval_accuracy: 0.9649481414187296
|
| 620 |
+
eval_f1_macro: 0.7977640218685498
|
| 621 |
+
eval_f1_micro: 0.9467483506126295
|
| 622 |
+
eval_loss: 0.2611960768699646
|
| 623 |
+
eval_precision: 0.8033484068946717
|
| 624 |
+
eval_recall: 0.7970286511697031
|
| 625 |
+
eval_runtime: 44.9018
|
| 626 |
+
eval_samples_per_second: 14.409
|
| 627 |
+
eval_steps_per_second: 7.216
|
| 628 |
+
step: 5700
|
| 629 |
+
epoch: 31.86813186813187
|
| 630 |
+
eval_accuracy: 0.9610114315996668
|
| 631 |
+
eval_f1_macro: 0.7863768532160194
|
| 632 |
+
eval_f1_micro: 0.9440758293838862
|
| 633 |
+
eval_loss: 0.2801985740661621
|
| 634 |
+
eval_precision: 0.8057891748499286
|
| 635 |
+
eval_recall: 0.7756588237485877
|
| 636 |
+
eval_runtime: 43.746
|
| 637 |
+
eval_samples_per_second: 14.79
|
| 638 |
+
eval_steps_per_second: 7.406
|
| 639 |
+
step: 5800
|
| 640 |
+
epoch: 32.417582417582416
|
| 641 |
+
eval_accuracy: 0.9643424937542585
|
| 642 |
+
eval_f1_macro: 0.8187564056058605
|
| 643 |
+
eval_f1_micro: 0.9480887210948561
|
| 644 |
+
eval_loss: 0.28143009543418884
|
| 645 |
+
eval_precision: 0.8233423494449537
|
| 646 |
+
eval_recall: 0.8195567074125506
|
| 647 |
+
eval_runtime: 44.2774
|
| 648 |
+
eval_samples_per_second: 14.612
|
| 649 |
+
eval_steps_per_second: 7.318
|
| 650 |
+
step: 5900
|
| 651 |
+
epoch: 32.967032967032964
|
| 652 |
+
eval_accuracy: 0.9645696116284351
|
| 653 |
+
eval_f1_macro: 0.8076570834068726
|
| 654 |
+
eval_f1_micro: 0.9433962264150944
|
| 655 |
+
eval_loss: 0.26347750425338745
|
| 656 |
+
eval_precision: 0.824172229282013
|
| 657 |
+
eval_recall: 0.7977482351070675
|
| 658 |
+
eval_runtime: 43.4961
|
| 659 |
+
eval_samples_per_second: 14.875
|
| 660 |
+
eval_steps_per_second: 7.449
|
| 661 |
+
step: 6000
|
| 662 |
+
epoch: 33.51648351648352
|
| 663 |
+
eval_accuracy: 0.9654023771670831
|
| 664 |
+
eval_f1_macro: 0.7964755486032369
|
| 665 |
+
eval_f1_micro: 0.9415645617342131
|
| 666 |
+
eval_loss: 0.2616080939769745
|
| 667 |
+
eval_precision: 0.8085753045920492
|
| 668 |
+
eval_recall: 0.7891916139415374
|
| 669 |
+
eval_runtime: 43.827
|
| 670 |
+
eval_samples_per_second: 14.763
|
| 671 |
+
eval_steps_per_second: 7.393
|
| 672 |
+
step: 6100
|
| 673 |
+
epoch: 34.065934065934066
|
| 674 |
+
eval_accuracy: 0.9646453175864941
|
| 675 |
+
eval_f1_macro: 0.7964348864809602
|
| 676 |
+
eval_f1_micro: 0.9433160132262636
|
| 677 |
+
eval_loss: 0.2700709104537964
|
| 678 |
+
eval_precision: 0.818093736065898
|
| 679 |
+
eval_recall: 0.7795606046391407
|
| 680 |
+
eval_runtime: 43.6759
|
| 681 |
+
eval_samples_per_second: 14.814
|
| 682 |
+
eval_steps_per_second: 7.418
|
| 683 |
+
step: 6200
|
| 684 |
+
epoch: 34.61538461538461
|
| 685 |
+
eval_accuracy: 0.9643424937542585
|
| 686 |
+
eval_f1_macro: 0.8133289499620897
|
| 687 |
+
eval_f1_micro: 0.9461049658743234
|
| 688 |
+
eval_loss: 0.26818060874938965
|
| 689 |
+
eval_precision: 0.8231080515202032
|
| 690 |
+
eval_recall: 0.8100326762608566
|
| 691 |
+
eval_runtime: 43.6363
|
| 692 |
+
eval_samples_per_second: 14.827
|
| 693 |
+
eval_steps_per_second: 7.425
|
| 694 |
+
step: 6300
|
| 695 |
+
epoch: 35.16483516483517
|
| 696 |
+
eval_accuracy: 0.9635854341736695
|
| 697 |
+
eval_f1_macro: 0.8006390679122667
|
| 698 |
+
eval_f1_micro: 0.9428638608041383
|
| 699 |
+
eval_loss: 0.26141873002052307
|
| 700 |
+
eval_precision: 0.8010798085935986
|
| 701 |
+
eval_recall: 0.8061793115441633
|
| 702 |
+
eval_runtime: 45.6308
|
| 703 |
+
eval_samples_per_second: 14.179
|
| 704 |
+
eval_steps_per_second: 7.1
|
| 705 |
+
step: 6400
|
| 706 |
+
epoch: 35.714285714285715
|
| 707 |
+
eval_accuracy: 0.9616170792641381
|
| 708 |
+
eval_f1_macro: 0.799236532508514
|
| 709 |
+
eval_f1_micro: 0.9417293233082707
|
| 710 |
+
eval_loss: 0.27979525923728943
|
| 711 |
+
eval_precision: 0.8002904477617854
|
| 712 |
+
eval_recall: 0.8034743200478014
|
| 713 |
+
eval_runtime: 45.4452
|
| 714 |
+
eval_samples_per_second: 14.237
|
| 715 |
+
eval_steps_per_second: 7.129
|
| 716 |
+
step: 6500
|
| 717 |
+
epoch: 36.26373626373626
|
| 718 |
+
eval_accuracy: 0.9614656673480203
|
| 719 |
+
eval_f1_macro: 0.7799609083219631
|
| 720 |
+
eval_f1_micro: 0.9383819379115711
|
| 721 |
+
eval_loss: 0.283438503742218
|
| 722 |
+
eval_precision: 0.7820427933942771
|
| 723 |
+
eval_recall: 0.7827238691963142
|
| 724 |
+
eval_runtime: 45.5841
|
| 725 |
+
eval_samples_per_second: 14.194
|
| 726 |
+
eval_steps_per_second: 7.108
|
| 727 |
+
step: 6600
|
| 728 |
+
epoch: 36.81318681318681
|
| 729 |
+
eval_accuracy: 0.9641153758800818
|
| 730 |
+
eval_f1_macro: 0.803165988111203
|
| 731 |
+
eval_f1_micro: 0.9453180004693733
|
| 732 |
+
eval_loss: 0.2649484872817993
|
| 733 |
+
eval_precision: 0.7994147247721745
|
| 734 |
+
eval_recall: 0.812946401787402
|
| 735 |
+
eval_runtime: 44.3079
|
| 736 |
+
eval_samples_per_second: 14.602
|
| 737 |
+
eval_steps_per_second: 7.312
|
| 738 |
+
step: 6700
|
| 739 |
+
epoch: 37.362637362637365
|
| 740 |
+
eval_accuracy: 0.963963963963964
|
| 741 |
+
eval_f1_macro: 0.8068861518366868
|
| 742 |
+
eval_f1_micro: 0.9459332393041843
|
| 743 |
+
eval_loss: 0.2608170211315155
|
| 744 |
+
eval_precision: 0.8148880504932015
|
| 745 |
+
eval_recall: 0.805646524343903
|
| 746 |
+
eval_runtime: 45.1224
|
| 747 |
+
eval_samples_per_second: 14.339
|
| 748 |
+
eval_steps_per_second: 7.18
|
| 749 |
+
step: 6800
|
| 750 |
+
epoch: 37.91208791208791
|
| 751 |
+
eval_accuracy: 0.9632826103414339
|
| 752 |
+
eval_f1_macro: 0.7921492011173231
|
| 753 |
+
eval_f1_micro: 0.941425546930134
|
| 754 |
+
eval_loss: 0.26367324590682983
|
| 755 |
+
eval_precision: 0.7903065239860718
|
| 756 |
+
eval_recall: 0.8007200982942264
|
| 757 |
+
eval_runtime: 44.652
|
| 758 |
+
eval_samples_per_second: 14.49
|
| 759 |
+
eval_steps_per_second: 7.256
|
| 760 |
+
step: 6900
|
| 761 |
+
epoch: 38.46153846153846
|
| 762 |
+
eval_accuracy: 0.9644939056703763
|
| 763 |
+
eval_f1_macro: 0.7937313082723505
|
| 764 |
+
eval_f1_micro: 0.9442746296731719
|
| 765 |
+
eval_loss: 0.2764584720134735
|
| 766 |
+
eval_precision: 0.7846545168204612
|
| 767 |
+
eval_recall: 0.8042339023416424
|
| 768 |
+
eval_runtime: 44.7458
|
| 769 |
+
eval_samples_per_second: 14.459
|
| 770 |
+
eval_steps_per_second: 7.241
|
| 771 |
+
step: 7000
|
| 772 |
+
epoch: 39.010989010989015
|
| 773 |
+
eval_accuracy: 0.9635097282156105
|
| 774 |
+
eval_f1_macro: 0.8110315719104696
|
| 775 |
+
eval_f1_micro: 0.9445623967916961
|
| 776 |
+
eval_loss: 0.2770596444606781
|
| 777 |
+
eval_precision: 0.8284858376718844
|
| 778 |
+
eval_recall: 0.8003057574658939
|
| 779 |
+
eval_runtime: 45.1138
|
| 780 |
+
eval_samples_per_second: 14.342
|
| 781 |
+
eval_steps_per_second: 7.182
|
| 782 |
+
step: 7100
|
| 783 |
+
epoch: 39.56043956043956
|
| 784 |
+
eval_accuracy: 0.9633583162994928
|
| 785 |
+
eval_f1_macro: 0.7940810046385522
|
| 786 |
+
eval_f1_micro: 0.9411210551106926
|
| 787 |
+
eval_loss: 0.2770184576511383
|
| 788 |
+
eval_precision: 0.806356709560804
|
| 789 |
+
eval_recall: 0.7910310057863054
|
| 790 |
+
eval_runtime: 44.9172
|
| 791 |
+
eval_samples_per_second: 14.404
|
| 792 |
+
eval_steps_per_second: 7.213
|
| 793 |
+
step: 7200
|
| 794 |
+
epoch: 40.10989010989011
|
| 795 |
+
eval_accuracy: 0.9641153758800818
|
| 796 |
+
eval_f1_macro: 0.8014863389143968
|
| 797 |
+
eval_f1_micro: 0.9444182760244937
|
| 798 |
+
eval_loss: 0.2869568467140198
|
| 799 |
+
eval_precision: 0.8169500700948074
|
| 800 |
+
eval_recall: 0.7982874345948012
|
| 801 |
+
eval_runtime: 45.322
|
| 802 |
+
eval_samples_per_second: 14.276
|
| 803 |
+
eval_steps_per_second: 7.149
|
| 804 |
+
step: 7300
|
| 805 |
+
epoch: 40.65934065934066
|
| 806 |
+
eval_accuracy: 0.9617684911802559
|
| 807 |
+
eval_f1_macro: 0.7875102151630142
|
| 808 |
+
eval_f1_micro: 0.9403723780344097
|
| 809 |
+
eval_loss: 0.29141849279403687
|
| 810 |
+
eval_precision: 0.7827880403102108
|
| 811 |
+
eval_recall: 0.7941908671972514
|
| 812 |
+
eval_runtime: 45.0842
|
| 813 |
+
eval_samples_per_second: 14.351
|
| 814 |
+
eval_steps_per_second: 7.187
|
| 815 |
+
step: 7400
|
| 816 |
+
epoch: 41.20879120879121
|
| 817 |
+
eval_accuracy: 0.9641153758800818
|
| 818 |
+
eval_f1_macro: 0.8079919036793346
|
| 819 |
+
eval_f1_micro: 0.9426422190879172
|
| 820 |
+
eval_loss: 0.2814047634601593
|
| 821 |
+
eval_precision: 0.8102026208158473
|
| 822 |
+
eval_recall: 0.8131733915745034
|
| 823 |
+
eval_runtime: 45.2532
|
| 824 |
+
eval_samples_per_second: 14.297
|
| 825 |
+
eval_steps_per_second: 7.16
|
| 826 |
+
step: 7500
|
| 827 |
+
epoch: 41.75824175824176
|
| 828 |
+
eval_accuracy: 0.9640396699220228
|
| 829 |
+
eval_f1_macro: 0.8051347504982652
|
| 830 |
+
eval_f1_micro: 0.9419233482247825
|
| 831 |
+
eval_loss: 0.27665001153945923
|
| 832 |
+
eval_precision: 0.8032159883999278
|
| 833 |
+
eval_recall: 0.8103156542927008
|
| 834 |
+
eval_runtime: 44.8371
|
| 835 |
+
eval_samples_per_second: 14.43
|
| 836 |
+
eval_steps_per_second: 7.226
|
| 837 |
+
step: 7600
|
| 838 |
+
epoch: 42.30769230769231
|
| 839 |
+
eval_accuracy: 0.9647210235445529
|
| 840 |
+
eval_f1_macro: 0.8118497311443793
|
| 841 |
+
eval_f1_micro: 0.9440905874026893
|
| 842 |
+
eval_loss: 0.28366151452064514
|
| 843 |
+
eval_precision: 0.8204164033389687
|
| 844 |
+
eval_recall: 0.8062455964873161
|
| 845 |
+
eval_runtime: 45.4519
|
| 846 |
+
eval_samples_per_second: 14.235
|
| 847 |
+
eval_steps_per_second: 7.128
|
| 848 |
+
step: 7700
|
| 849 |
+
epoch: 42.857142857142854
|
| 850 |
+
eval_accuracy: 0.9636611401317283
|
| 851 |
+
eval_f1_macro: 0.8122120993969504
|
| 852 |
+
eval_f1_micro: 0.9452830188679244
|
| 853 |
+
eval_loss: 0.2867574989795685
|
| 854 |
+
eval_precision: 0.8290684365674612
|
| 855 |
+
eval_recall: 0.8025544152658044
|
| 856 |
+
eval_runtime: 45.1263
|
| 857 |
+
eval_samples_per_second: 14.338
|
| 858 |
+
eval_steps_per_second: 7.18
|
| 859 |
+
step: 7800
|
| 860 |
+
epoch: 43.40659340659341
|
| 861 |
+
eval_accuracy: 0.9635854341736695
|
| 862 |
+
eval_f1_macro: 0.8066897544477346
|
| 863 |
+
eval_f1_micro: 0.9449822904368359
|
| 864 |
+
eval_loss: 0.2875712811946869
|
| 865 |
+
eval_precision: 0.822187852486261
|
| 866 |
+
eval_recall: 0.7960530174707015
|
| 867 |
+
eval_runtime: 44.9884
|
| 868 |
+
eval_samples_per_second: 14.382
|
| 869 |
+
eval_steps_per_second: 7.202
|
| 870 |
+
step: 7900
|
| 871 |
+
epoch: 43.956043956043956
|
| 872 |
+
eval_accuracy: 0.9640396699220228
|
| 873 |
+
eval_f1_macro: 0.8154534980960727
|
| 874 |
+
eval_f1_micro: 0.948214707968787
|
| 875 |
+
eval_loss: 0.2859266996383667
|
| 876 |
+
eval_precision: 0.8333106043653709
|
| 877 |
+
eval_recall: 0.801658117985518
|
| 878 |
+
eval_runtime: 45.0495
|
| 879 |
+
eval_samples_per_second: 14.362
|
| 880 |
+
eval_steps_per_second: 7.192
|
| 881 |
+
step: 8000
|
| 882 |
+
epoch: 44.505494505494504
|
| 883 |
+
eval_accuracy: 0.963963963963964
|
| 884 |
+
eval_f1_macro: 0.8163601419073814
|
| 885 |
+
eval_f1_micro: 0.9478158205430933
|
| 886 |
+
eval_loss: 0.28253597021102905
|
| 887 |
+
eval_precision: 0.8328103029797022
|
| 888 |
+
eval_recall: 0.8052075988077261
|
| 889 |
+
eval_runtime: 45.5102
|
| 890 |
+
eval_samples_per_second: 14.217
|
| 891 |
+
eval_steps_per_second: 7.119
|
| 892 |
+
step: 8100
|
| 893 |
+
epoch: 45.05494505494506
|
| 894 |
+
eval_accuracy: 0.9629797865091982
|
| 895 |
+
eval_f1_macro: 0.7931291286087614
|
| 896 |
+
eval_f1_micro: 0.9402914903620122
|
| 897 |
+
eval_loss: 0.2868800461292267
|
| 898 |
+
eval_precision: 0.7946587510699699
|
| 899 |
+
eval_recall: 0.7971834697200124
|
| 900 |
+
eval_runtime: 45.6754
|
| 901 |
+
eval_samples_per_second: 14.165
|
| 902 |
+
eval_steps_per_second: 7.094
|
| 903 |
+
step: 8200
|
| 904 |
+
epoch: 45.604395604395606
|
| 905 |
+
eval_accuracy: 0.9629797865091982
|
| 906 |
+
eval_f1_macro: 0.7972692753369095
|
| 907 |
+
eval_f1_micro: 0.9417293233082707
|
| 908 |
+
eval_loss: 0.28883811831474304
|
| 909 |
+
eval_precision: 0.8009078916874377
|
| 910 |
+
eval_recall: 0.7984434165059959
|
| 911 |
+
eval_runtime: 46.1802
|
| 912 |
+
eval_samples_per_second: 14.01
|
| 913 |
+
eval_steps_per_second: 7.016
|
| 914 |
+
step: 8300
|
| 915 |
+
epoch: 46.15384615384615
|
| 916 |
+
eval_accuracy: 0.9633583162994928
|
| 917 |
+
eval_f1_macro: 0.7972486561729999
|
| 918 |
+
eval_f1_micro: 0.9438149197355996
|
| 919 |
+
eval_loss: 0.2899405360221863
|
| 920 |
+
eval_precision: 0.8085490129325279
|
| 921 |
+
eval_recall: 0.7912819744965353
|
| 922 |
+
eval_runtime: 45.9139
|
| 923 |
+
eval_samples_per_second: 14.092
|
| 924 |
+
eval_steps_per_second: 7.057
|
| 925 |
+
step: 8400
|
| 926 |
+
epoch: 46.7032967032967
|
| 927 |
+
eval_accuracy: 0.9644181997123173
|
| 928 |
+
eval_f1_macro: 0.8125838731519763
|
| 929 |
+
eval_f1_micro: 0.9462264150943396
|
| 930 |
+
eval_loss: 0.2826482057571411
|
| 931 |
+
eval_precision: 0.8290854608746453
|
| 932 |
+
eval_recall: 0.8014535642456371
|
| 933 |
+
eval_runtime: 45.6708
|
| 934 |
+
eval_samples_per_second: 14.167
|
| 935 |
+
eval_steps_per_second: 7.094
|
| 936 |
+
step: 8500
|
| 937 |
+
eval_loss: 0.03311534598469734
|
| 938 |
+
eval_precision: 0.9759338033605358
|
| 939 |
+
eval_recall: 0.9723612057778244
|
| 940 |
+
eval_f1_micro: 0.9896079357581484
|
| 941 |
+
eval_f1_macro: 0.9739296477625715
|
| 942 |
+
eval_accuracy: 0.9946272666218939
|
| 943 |
+
eval_runtime: 44.1392
|
| 944 |
+
eval_samples_per_second: 14.658
|
| 945 |
+
eval_steps_per_second: 7.34
|
| 946 |
+
epoch: 47.252747252747255
|
| 947 |
+
step: 8600
|
| 948 |
+
eval_loss: 0.03324605152010918
|
| 949 |
+
eval_precision: 0.9789527841238704
|
| 950 |
+
eval_recall: 0.958025715484146
|
| 951 |
+
eval_f1_micro: 0.9891150023663038
|
| 952 |
+
eval_f1_macro: 0.9677676145226746
|
| 953 |
+
eval_accuracy: 0.993657189761958
|
| 954 |
+
eval_runtime: 44.5425
|
| 955 |
+
eval_samples_per_second: 14.525
|
| 956 |
+
eval_steps_per_second: 7.274
|
| 957 |
+
epoch: 47.8021978021978
|
| 958 |
+
step: 8700
|
| 959 |
+
eval_loss: 0.030670231208205223
|
| 960 |
+
eval_precision: 0.9856038233754327
|
| 961 |
+
eval_recall: 0.9720278724444911
|
| 962 |
+
eval_f1_micro: 0.9905392620624408
|
| 963 |
+
eval_f1_macro: 0.978556993403294
|
| 964 |
+
eval_accuracy: 0.9949257518095664
|
| 965 |
+
eval_runtime: 44.1046
|
| 966 |
+
eval_samples_per_second: 14.67
|
| 967 |
+
eval_steps_per_second: 7.346
|
| 968 |
+
epoch: 48.35164835164835
|
| 969 |
+
step: 8800
|
| 970 |
+
eval_loss: 0.033358242362737656
|
| 971 |
+
eval_precision: 0.9949656842941409
|
| 972 |
+
eval_recall: 0.9637565469462805
|
| 973 |
+
eval_f1_micro: 0.9912384560738811
|
| 974 |
+
eval_f1_macro: 0.9781750704253561
|
| 975 |
+
eval_accuracy: 0.9947765092157301
|
| 976 |
+
eval_runtime: 44.272
|
| 977 |
+
eval_samples_per_second: 14.614
|
| 978 |
+
eval_steps_per_second: 7.318
|
| 979 |
+
epoch: 48.9010989010989
|
| 980 |
+
step: 8900
|
| 981 |
+
eval_loss: 0.03132859990000725
|
| 982 |
+
eval_precision: 0.992040280974681
|
| 983 |
+
eval_recall: 0.9694768520363277
|
| 984 |
+
eval_f1_micro: 0.9907692307692307
|
| 985 |
+
eval_f1_macro: 0.9801348621957375
|
| 986 |
+
eval_accuracy: 0.9947765092157301
|
| 987 |
+
eval_runtime: 44.5511
|
| 988 |
+
eval_samples_per_second: 14.523
|
| 989 |
+
eval_steps_per_second: 7.273
|
| 990 |
+
epoch: 49.45054945054945
|
| 991 |
+
step: 9000
|
| 992 |
+
eval_loss: 0.03677159175276756
|
| 993 |
+
eval_precision: 0.9892855575800686
|
| 994 |
+
eval_recall: 0.9670782706525548
|
| 995 |
+
eval_f1_micro: 0.9907692307692307
|
| 996 |
+
eval_f1_macro: 0.9775698170217979
|
| 997 |
+
eval_accuracy: 0.9944034027311395
|
| 998 |
+
eval_runtime: 45.2859
|
| 999 |
+
eval_samples_per_second: 14.287
|
| 1000 |
+
eval_steps_per_second: 7.155
|
| 1001 |
+
epoch: 50.0
|
| 1002 |
+
step: 9100
|
| 1003 |
+
eval_loss: 0.036768753081560135
|
| 1004 |
+
eval_precision: 0.9921925343242547
|
| 1005 |
+
eval_recall: 0.969629291060718
|
| 1006 |
+
eval_f1_micro: 0.9912426035502958
|
| 1007 |
+
eval_f1_macro: 0.9802872083261458
|
| 1008 |
+
eval_accuracy: 0.9948511305126483
|
| 1009 |
+
eval_runtime: 44.9084
|
| 1010 |
+
eval_samples_per_second: 14.407
|
| 1011 |
+
eval_steps_per_second: 7.215
|
| 1012 |
+
epoch: 50.54945054945055
|
| 1013 |
+
step: 9200
|
| 1014 |
+
eval_loss: 0.03708318993449211
|
| 1015 |
+
eval_precision: 0.9923647040177782
|
| 1016 |
+
eval_recall: 0.969629291060718
|
| 1017 |
+
eval_f1_micro: 0.9914772727272728
|
| 1018 |
+
eval_f1_macro: 0.9803735922030832
|
| 1019 |
+
eval_accuracy: 0.9949257518095664
|
| 1020 |
+
eval_runtime: 44.2951
|
| 1021 |
+
eval_samples_per_second: 14.607
|
| 1022 |
+
eval_steps_per_second: 7.315
|
| 1023 |
+
epoch: 51.0989010989011
|
| 1024 |
+
step: 9300
|
| 1025 |
+
eval_loss: 0.038258761167526245
|
| 1026 |
+
eval_precision: 0.9896303752162644
|
| 1027 |
+
eval_recall: 0.9670782706525548
|
| 1028 |
+
eval_f1_micro: 0.9912384560738811
|
| 1029 |
+
eval_f1_macro: 0.9777427048366552
|
| 1030 |
+
eval_accuracy: 0.994701887918812
|
| 1031 |
+
eval_runtime: 45.0721
|
| 1032 |
+
eval_samples_per_second: 14.355
|
| 1033 |
+
eval_steps_per_second: 7.188
|
| 1034 |
+
epoch: 51.64835164835165
|
| 1035 |
+
step: 9400
|
| 1036 |
+
eval_loss: 0.03704264387488365
|
| 1037 |
+
eval_precision: 0.9925373519604505
|
| 1038 |
+
eval_recall: 0.969629291060718
|
| 1039 |
+
eval_f1_micro: 0.9917120530428605
|
| 1040 |
+
eval_f1_macro: 0.980460096141003
|
| 1041 |
+
eval_accuracy: 0.9950003731064846
|
| 1042 |
+
eval_runtime: 44.8213
|
| 1043 |
+
eval_samples_per_second: 14.435
|
| 1044 |
+
eval_steps_per_second: 7.229
|
| 1045 |
+
epoch: 52.1978021978022
|
| 1046 |
+
step: 9500
|
| 1047 |
+
eval_loss: 0.03854644298553467
|
| 1048 |
+
eval_precision: 0.9894577272735922
|
| 1049 |
+
eval_recall: 0.9670782706525548
|
| 1050 |
+
eval_f1_micro: 0.9910037878787878
|
| 1051 |
+
eval_f1_macro: 0.9776562008987353
|
| 1052 |
+
eval_accuracy: 0.9944780240280576
|
| 1053 |
+
eval_runtime: 45.314
|
| 1054 |
+
eval_samples_per_second: 14.278
|
| 1055 |
+
eval_steps_per_second: 7.15
|
| 1056 |
+
epoch: 52.747252747252745
|
| 1057 |
+
step: 9600
|
| 1058 |
+
eval_loss: 0.038166310638189316
|
| 1059 |
+
eval_precision: 0.9904893293615804
|
| 1060 |
+
eval_recall: 0.969629291060718
|
| 1061 |
+
eval_f1_micro: 0.9914772727272728
|
| 1062 |
+
eval_f1_macro: 0.9794098281415824
|
| 1063 |
+
eval_accuracy: 0.9949257518095664
|
| 1064 |
+
eval_runtime: 44.8406
|
| 1065 |
+
eval_samples_per_second: 14.429
|
| 1066 |
+
eval_steps_per_second: 7.226
|
| 1067 |
+
epoch: 53.2967032967033
|
| 1068 |
+
step: 9700
|
| 1069 |
+
eval_loss: 0.038449596613645554
|
| 1070 |
+
eval_precision: 0.9925373519604505
|
| 1071 |
+
eval_recall: 0.969629291060718
|
| 1072 |
+
eval_f1_micro: 0.9917120530428605
|
| 1073 |
+
eval_f1_macro: 0.980460096141003
|
| 1074 |
+
eval_accuracy: 0.9950003731064846
|
| 1075 |
+
eval_runtime: 45.2016
|
| 1076 |
+
eval_samples_per_second: 14.314
|
| 1077 |
+
eval_steps_per_second: 7.168
|
| 1078 |
+
epoch: 53.84615384615385
|
| 1079 |
+
step: 9800
|
| 1080 |
+
eval_loss: 0.0385122187435627
|
| 1081 |
+
eval_precision: 0.9923647040177782
|
| 1082 |
+
eval_recall: 0.969629291060718
|
| 1083 |
+
eval_f1_micro: 0.9914772727272728
|
| 1084 |
+
eval_f1_macro: 0.9803735922030832
|
| 1085 |
+
eval_accuracy: 0.9949257518095664
|
| 1086 |
+
eval_runtime: 44.8943
|
| 1087 |
+
eval_samples_per_second: 14.412
|
| 1088 |
+
eval_steps_per_second: 7.217
|
| 1089 |
+
epoch: 54.395604395604394
|
| 1090 |
+
step: 9900
|
| 1091 |
+
eval_loss: 0.03857136517763138
|
| 1092 |
+
eval_precision: 0.9923647040177782
|
| 1093 |
+
eval_recall: 0.969629291060718
|
| 1094 |
+
eval_f1_micro: 0.9914772727272728
|
| 1095 |
+
eval_f1_macro: 0.9803735922030832
|
| 1096 |
+
eval_accuracy: 0.9949257518095664
|
| 1097 |
+
eval_runtime: 44.7347
|
| 1098 |
+
eval_samples_per_second: 14.463
|
| 1099 |
+
eval_steps_per_second: 7.243
|
| 1100 |
+
epoch: 54.94505494505494
|
| 1101 |
+
step: 10000
|