End of training
Browse files- README.md +5 -5
- all_results.json +16 -0
- eval_results.json +11 -0
- runs/Sep04_12-18-52_5bdf525bf655/events.out.tfevents.1725455481.5bdf525bf655.4076.1 +3 -0
- train_results.json +8 -0
- trainer_state.json +1040 -0
README.md
CHANGED
|
@@ -20,11 +20,11 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 20 |
|
| 21 |
This model is a fine-tuned version of [facebook/convnextv2-base-22k-224](https://huggingface.co/facebook/convnextv2-base-22k-224) on an unknown dataset.
|
| 22 |
It achieves the following results on the evaluation set:
|
| 23 |
-
- Loss:
|
| 24 |
-
- Accuracy: 0.
|
| 25 |
-
- F1: 0.
|
| 26 |
-
- Precision: 0.
|
| 27 |
-
- Recall: 0.
|
| 28 |
|
| 29 |
## Model description
|
| 30 |
|
|
|
|
| 20 |
|
| 21 |
This model is a fine-tuned version of [facebook/convnextv2-base-22k-224](https://huggingface.co/facebook/convnextv2-base-22k-224) on an unknown dataset.
|
| 22 |
It achieves the following results on the evaluation set:
|
| 23 |
+
- Loss: 0.9781
|
| 24 |
+
- Accuracy: 0.5748
|
| 25 |
+
- F1: 0.5697
|
| 26 |
+
- Precision: 0.5822
|
| 27 |
+
- Recall: 0.5748
|
| 28 |
|
| 29 |
## Model description
|
| 30 |
|
all_results.json
ADDED
|
@@ -0,0 +1,16 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 11.941463414634146,
|
| 3 |
+
"eval_accuracy": 0.5748393021120294,
|
| 4 |
+
"eval_f1": 0.5696724052779626,
|
| 5 |
+
"eval_loss": 0.9780603051185608,
|
| 6 |
+
"eval_precision": 0.5821729436076757,
|
| 7 |
+
"eval_recall": 0.5748393021120294,
|
| 8 |
+
"eval_runtime": 10.5431,
|
| 9 |
+
"eval_samples_per_second": 103.29,
|
| 10 |
+
"eval_steps_per_second": 6.545,
|
| 11 |
+
"total_flos": 6.197635483154842e+18,
|
| 12 |
+
"train_loss": 1.0363535090209612,
|
| 13 |
+
"train_runtime": 3088.0708,
|
| 14 |
+
"train_samples_per_second": 25.461,
|
| 15 |
+
"train_steps_per_second": 0.396
|
| 16 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,11 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 11.941463414634146,
|
| 3 |
+
"eval_accuracy": 0.5748393021120294,
|
| 4 |
+
"eval_f1": 0.5696724052779626,
|
| 5 |
+
"eval_loss": 0.9780603051185608,
|
| 6 |
+
"eval_precision": 0.5821729436076757,
|
| 7 |
+
"eval_recall": 0.5748393021120294,
|
| 8 |
+
"eval_runtime": 10.5431,
|
| 9 |
+
"eval_samples_per_second": 103.29,
|
| 10 |
+
"eval_steps_per_second": 6.545
|
| 11 |
+
}
|
runs/Sep04_12-18-52_5bdf525bf655/events.out.tfevents.1725455481.5bdf525bf655.4076.1
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:474c9b46e4bcd11623679b20598eef248414c0dc43ed0ab6b037f4d2aef1441a
|
| 3 |
+
size 560
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 11.941463414634146,
|
| 3 |
+
"total_flos": 6.197635483154842e+18,
|
| 4 |
+
"train_loss": 1.0363535090209612,
|
| 5 |
+
"train_runtime": 3088.0708,
|
| 6 |
+
"train_samples_per_second": 25.461,
|
| 7 |
+
"train_steps_per_second": 0.396
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,1040 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.5748393021120294,
|
| 3 |
+
"best_model_checkpoint": "convnextv2-base-22k-224-finetuned-tekno24/checkpoint-615",
|
| 4 |
+
"epoch": 11.941463414634146,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 1224,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.0975609756097561,
|
| 13 |
+
"grad_norm": 12.655921936035156,
|
| 14 |
+
"learning_rate": 4.0650406504065046e-06,
|
| 15 |
+
"loss": 1.4164,
|
| 16 |
+
"step": 10
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.1951219512195122,
|
| 20 |
+
"grad_norm": 17.018129348754883,
|
| 21 |
+
"learning_rate": 8.130081300813009e-06,
|
| 22 |
+
"loss": 1.4339,
|
| 23 |
+
"step": 20
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.2926829268292683,
|
| 27 |
+
"grad_norm": 16.979167938232422,
|
| 28 |
+
"learning_rate": 1.1788617886178862e-05,
|
| 29 |
+
"loss": 1.4233,
|
| 30 |
+
"step": 30
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.3902439024390244,
|
| 34 |
+
"grad_norm": 18.95262908935547,
|
| 35 |
+
"learning_rate": 1.5447154471544717e-05,
|
| 36 |
+
"loss": 1.3995,
|
| 37 |
+
"step": 40
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.4878048780487805,
|
| 41 |
+
"grad_norm": 10.330867767333984,
|
| 42 |
+
"learning_rate": 1.9512195121951222e-05,
|
| 43 |
+
"loss": 1.3879,
|
| 44 |
+
"step": 50
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.5853658536585366,
|
| 48 |
+
"grad_norm": 7.81517219543457,
|
| 49 |
+
"learning_rate": 2.3577235772357724e-05,
|
| 50 |
+
"loss": 1.3701,
|
| 51 |
+
"step": 60
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.6829268292682927,
|
| 55 |
+
"grad_norm": 13.965815544128418,
|
| 56 |
+
"learning_rate": 2.764227642276423e-05,
|
| 57 |
+
"loss": 1.3374,
|
| 58 |
+
"step": 70
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.7804878048780488,
|
| 62 |
+
"grad_norm": 13.348392486572266,
|
| 63 |
+
"learning_rate": 3.170731707317073e-05,
|
| 64 |
+
"loss": 1.3221,
|
| 65 |
+
"step": 80
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.8780487804878049,
|
| 69 |
+
"grad_norm": 13.079450607299805,
|
| 70 |
+
"learning_rate": 3.577235772357724e-05,
|
| 71 |
+
"loss": 1.3228,
|
| 72 |
+
"step": 90
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.975609756097561,
|
| 76 |
+
"grad_norm": 9.20757007598877,
|
| 77 |
+
"learning_rate": 3.983739837398374e-05,
|
| 78 |
+
"loss": 1.2643,
|
| 79 |
+
"step": 100
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.9951219512195122,
|
| 83 |
+
"eval_accuracy": 0.5206611570247934,
|
| 84 |
+
"eval_f1": 0.47635822656042665,
|
| 85 |
+
"eval_loss": 1.1486896276474,
|
| 86 |
+
"eval_precision": 0.4782877718762662,
|
| 87 |
+
"eval_recall": 0.5206611570247934,
|
| 88 |
+
"eval_runtime": 10.5321,
|
| 89 |
+
"eval_samples_per_second": 103.399,
|
| 90 |
+
"eval_steps_per_second": 6.551,
|
| 91 |
+
"step": 102
|
| 92 |
+
},
|
| 93 |
+
{
|
| 94 |
+
"epoch": 1.0731707317073171,
|
| 95 |
+
"grad_norm": 11.261804580688477,
|
| 96 |
+
"learning_rate": 4.390243902439025e-05,
|
| 97 |
+
"loss": 1.2688,
|
| 98 |
+
"step": 110
|
| 99 |
+
},
|
| 100 |
+
{
|
| 101 |
+
"epoch": 1.170731707317073,
|
| 102 |
+
"grad_norm": 20.570632934570312,
|
| 103 |
+
"learning_rate": 4.796747967479675e-05,
|
| 104 |
+
"loss": 1.2293,
|
| 105 |
+
"step": 120
|
| 106 |
+
},
|
| 107 |
+
{
|
| 108 |
+
"epoch": 1.2682926829268293,
|
| 109 |
+
"grad_norm": 8.604395866394043,
|
| 110 |
+
"learning_rate": 4.9772933696639425e-05,
|
| 111 |
+
"loss": 1.2657,
|
| 112 |
+
"step": 130
|
| 113 |
+
},
|
| 114 |
+
{
|
| 115 |
+
"epoch": 1.3658536585365852,
|
| 116 |
+
"grad_norm": 23.755281448364258,
|
| 117 |
+
"learning_rate": 4.931880108991826e-05,
|
| 118 |
+
"loss": 1.2812,
|
| 119 |
+
"step": 140
|
| 120 |
+
},
|
| 121 |
+
{
|
| 122 |
+
"epoch": 1.4634146341463414,
|
| 123 |
+
"grad_norm": 17.45159912109375,
|
| 124 |
+
"learning_rate": 4.886466848319709e-05,
|
| 125 |
+
"loss": 1.2578,
|
| 126 |
+
"step": 150
|
| 127 |
+
},
|
| 128 |
+
{
|
| 129 |
+
"epoch": 1.5609756097560976,
|
| 130 |
+
"grad_norm": 6.092088222503662,
|
| 131 |
+
"learning_rate": 4.841053587647593e-05,
|
| 132 |
+
"loss": 1.2356,
|
| 133 |
+
"step": 160
|
| 134 |
+
},
|
| 135 |
+
{
|
| 136 |
+
"epoch": 1.6585365853658538,
|
| 137 |
+
"grad_norm": 7.634965419769287,
|
| 138 |
+
"learning_rate": 4.795640326975477e-05,
|
| 139 |
+
"loss": 1.2367,
|
| 140 |
+
"step": 170
|
| 141 |
+
},
|
| 142 |
+
{
|
| 143 |
+
"epoch": 1.7560975609756098,
|
| 144 |
+
"grad_norm": 12.493597984313965,
|
| 145 |
+
"learning_rate": 4.750227066303361e-05,
|
| 146 |
+
"loss": 1.2391,
|
| 147 |
+
"step": 180
|
| 148 |
+
},
|
| 149 |
+
{
|
| 150 |
+
"epoch": 1.8536585365853657,
|
| 151 |
+
"grad_norm": 7.179015159606934,
|
| 152 |
+
"learning_rate": 4.704813805631245e-05,
|
| 153 |
+
"loss": 1.2718,
|
| 154 |
+
"step": 190
|
| 155 |
+
},
|
| 156 |
+
{
|
| 157 |
+
"epoch": 1.951219512195122,
|
| 158 |
+
"grad_norm": 11.228482246398926,
|
| 159 |
+
"learning_rate": 4.659400544959128e-05,
|
| 160 |
+
"loss": 1.1889,
|
| 161 |
+
"step": 200
|
| 162 |
+
},
|
| 163 |
+
{
|
| 164 |
+
"epoch": 2.0,
|
| 165 |
+
"eval_accuracy": 0.5087235996326905,
|
| 166 |
+
"eval_f1": 0.5190802114624434,
|
| 167 |
+
"eval_loss": 1.1037839651107788,
|
| 168 |
+
"eval_precision": 0.5564617175099487,
|
| 169 |
+
"eval_recall": 0.5087235996326905,
|
| 170 |
+
"eval_runtime": 10.5165,
|
| 171 |
+
"eval_samples_per_second": 103.551,
|
| 172 |
+
"eval_steps_per_second": 6.561,
|
| 173 |
+
"step": 205
|
| 174 |
+
},
|
| 175 |
+
{
|
| 176 |
+
"epoch": 2.048780487804878,
|
| 177 |
+
"grad_norm": 8.938887596130371,
|
| 178 |
+
"learning_rate": 4.613987284287012e-05,
|
| 179 |
+
"loss": 1.1869,
|
| 180 |
+
"step": 210
|
| 181 |
+
},
|
| 182 |
+
{
|
| 183 |
+
"epoch": 2.1463414634146343,
|
| 184 |
+
"grad_norm": 8.932198524475098,
|
| 185 |
+
"learning_rate": 4.5685740236148955e-05,
|
| 186 |
+
"loss": 1.208,
|
| 187 |
+
"step": 220
|
| 188 |
+
},
|
| 189 |
+
{
|
| 190 |
+
"epoch": 2.2439024390243905,
|
| 191 |
+
"grad_norm": 5.741872787475586,
|
| 192 |
+
"learning_rate": 4.52316076294278e-05,
|
| 193 |
+
"loss": 1.2029,
|
| 194 |
+
"step": 230
|
| 195 |
+
},
|
| 196 |
+
{
|
| 197 |
+
"epoch": 2.341463414634146,
|
| 198 |
+
"grad_norm": 8.091480255126953,
|
| 199 |
+
"learning_rate": 4.477747502270663e-05,
|
| 200 |
+
"loss": 1.19,
|
| 201 |
+
"step": 240
|
| 202 |
+
},
|
| 203 |
+
{
|
| 204 |
+
"epoch": 2.4390243902439024,
|
| 205 |
+
"grad_norm": 7.227927207946777,
|
| 206 |
+
"learning_rate": 4.432334241598547e-05,
|
| 207 |
+
"loss": 1.2083,
|
| 208 |
+
"step": 250
|
| 209 |
+
},
|
| 210 |
+
{
|
| 211 |
+
"epoch": 2.5365853658536586,
|
| 212 |
+
"grad_norm": 5.250303745269775,
|
| 213 |
+
"learning_rate": 4.3869209809264305e-05,
|
| 214 |
+
"loss": 1.1941,
|
| 215 |
+
"step": 260
|
| 216 |
+
},
|
| 217 |
+
{
|
| 218 |
+
"epoch": 2.6341463414634148,
|
| 219 |
+
"grad_norm": 8.268411636352539,
|
| 220 |
+
"learning_rate": 4.341507720254315e-05,
|
| 221 |
+
"loss": 1.1783,
|
| 222 |
+
"step": 270
|
| 223 |
+
},
|
| 224 |
+
{
|
| 225 |
+
"epoch": 2.7317073170731705,
|
| 226 |
+
"grad_norm": 6.347944259643555,
|
| 227 |
+
"learning_rate": 4.296094459582199e-05,
|
| 228 |
+
"loss": 1.1653,
|
| 229 |
+
"step": 280
|
| 230 |
+
},
|
| 231 |
+
{
|
| 232 |
+
"epoch": 2.8292682926829267,
|
| 233 |
+
"grad_norm": 8.626900672912598,
|
| 234 |
+
"learning_rate": 4.250681198910082e-05,
|
| 235 |
+
"loss": 1.1733,
|
| 236 |
+
"step": 290
|
| 237 |
+
},
|
| 238 |
+
{
|
| 239 |
+
"epoch": 2.926829268292683,
|
| 240 |
+
"grad_norm": 7.539112567901611,
|
| 241 |
+
"learning_rate": 4.2052679382379655e-05,
|
| 242 |
+
"loss": 1.215,
|
| 243 |
+
"step": 300
|
| 244 |
+
},
|
| 245 |
+
{
|
| 246 |
+
"epoch": 2.995121951219512,
|
| 247 |
+
"eval_accuracy": 0.4830119375573921,
|
| 248 |
+
"eval_f1": 0.4794682324453807,
|
| 249 |
+
"eval_loss": 1.0810357332229614,
|
| 250 |
+
"eval_precision": 0.5588554246566038,
|
| 251 |
+
"eval_recall": 0.4830119375573921,
|
| 252 |
+
"eval_runtime": 10.5448,
|
| 253 |
+
"eval_samples_per_second": 103.274,
|
| 254 |
+
"eval_steps_per_second": 6.544,
|
| 255 |
+
"step": 307
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 3.024390243902439,
|
| 259 |
+
"grad_norm": 7.887587547302246,
|
| 260 |
+
"learning_rate": 4.159854677565849e-05,
|
| 261 |
+
"loss": 1.1419,
|
| 262 |
+
"step": 310
|
| 263 |
+
},
|
| 264 |
+
{
|
| 265 |
+
"epoch": 3.1219512195121952,
|
| 266 |
+
"grad_norm": 8.143919944763184,
|
| 267 |
+
"learning_rate": 4.114441416893734e-05,
|
| 268 |
+
"loss": 1.1339,
|
| 269 |
+
"step": 320
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 3.2195121951219514,
|
| 273 |
+
"grad_norm": 8.059014320373535,
|
| 274 |
+
"learning_rate": 4.069028156221617e-05,
|
| 275 |
+
"loss": 1.0966,
|
| 276 |
+
"step": 330
|
| 277 |
+
},
|
| 278 |
+
{
|
| 279 |
+
"epoch": 3.317073170731707,
|
| 280 |
+
"grad_norm": 7.19610595703125,
|
| 281 |
+
"learning_rate": 4.0236148955495005e-05,
|
| 282 |
+
"loss": 1.1837,
|
| 283 |
+
"step": 340
|
| 284 |
+
},
|
| 285 |
+
{
|
| 286 |
+
"epoch": 3.4146341463414633,
|
| 287 |
+
"grad_norm": 6.76222038269043,
|
| 288 |
+
"learning_rate": 3.978201634877384e-05,
|
| 289 |
+
"loss": 1.1768,
|
| 290 |
+
"step": 350
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 3.5121951219512195,
|
| 294 |
+
"grad_norm": 6.472099781036377,
|
| 295 |
+
"learning_rate": 3.932788374205268e-05,
|
| 296 |
+
"loss": 1.1588,
|
| 297 |
+
"step": 360
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 3.6097560975609757,
|
| 301 |
+
"grad_norm": 7.446631908416748,
|
| 302 |
+
"learning_rate": 3.887375113533152e-05,
|
| 303 |
+
"loss": 1.1531,
|
| 304 |
+
"step": 370
|
| 305 |
+
},
|
| 306 |
+
{
|
| 307 |
+
"epoch": 3.7073170731707314,
|
| 308 |
+
"grad_norm": 7.529073238372803,
|
| 309 |
+
"learning_rate": 3.8419618528610355e-05,
|
| 310 |
+
"loss": 1.1203,
|
| 311 |
+
"step": 380
|
| 312 |
+
},
|
| 313 |
+
{
|
| 314 |
+
"epoch": 3.8048780487804876,
|
| 315 |
+
"grad_norm": 8.24229907989502,
|
| 316 |
+
"learning_rate": 3.796548592188919e-05,
|
| 317 |
+
"loss": 1.1788,
|
| 318 |
+
"step": 390
|
| 319 |
+
},
|
| 320 |
+
{
|
| 321 |
+
"epoch": 3.902439024390244,
|
| 322 |
+
"grad_norm": 5.0005412101745605,
|
| 323 |
+
"learning_rate": 3.751135331516803e-05,
|
| 324 |
+
"loss": 1.1577,
|
| 325 |
+
"step": 400
|
| 326 |
+
},
|
| 327 |
+
{
|
| 328 |
+
"epoch": 4.0,
|
| 329 |
+
"grad_norm": 11.378023147583008,
|
| 330 |
+
"learning_rate": 3.705722070844687e-05,
|
| 331 |
+
"loss": 1.1062,
|
| 332 |
+
"step": 410
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 4.0,
|
| 336 |
+
"eval_accuracy": 0.5619834710743802,
|
| 337 |
+
"eval_f1": 0.5281037322147313,
|
| 338 |
+
"eval_loss": 1.0103230476379395,
|
| 339 |
+
"eval_precision": 0.5357616363900534,
|
| 340 |
+
"eval_recall": 0.5619834710743802,
|
| 341 |
+
"eval_runtime": 10.5649,
|
| 342 |
+
"eval_samples_per_second": 103.077,
|
| 343 |
+
"eval_steps_per_second": 6.531,
|
| 344 |
+
"step": 410
|
| 345 |
+
},
|
| 346 |
+
{
|
| 347 |
+
"epoch": 4.097560975609756,
|
| 348 |
+
"grad_norm": 7.739734172821045,
|
| 349 |
+
"learning_rate": 3.6603088101725705e-05,
|
| 350 |
+
"loss": 1.076,
|
| 351 |
+
"step": 420
|
| 352 |
+
},
|
| 353 |
+
{
|
| 354 |
+
"epoch": 4.195121951219512,
|
| 355 |
+
"grad_norm": 6.631500244140625,
|
| 356 |
+
"learning_rate": 3.614895549500454e-05,
|
| 357 |
+
"loss": 1.1469,
|
| 358 |
+
"step": 430
|
| 359 |
+
},
|
| 360 |
+
{
|
| 361 |
+
"epoch": 4.2926829268292686,
|
| 362 |
+
"grad_norm": 9.386627197265625,
|
| 363 |
+
"learning_rate": 3.569482288828338e-05,
|
| 364 |
+
"loss": 1.0905,
|
| 365 |
+
"step": 440
|
| 366 |
+
},
|
| 367 |
+
{
|
| 368 |
+
"epoch": 4.390243902439025,
|
| 369 |
+
"grad_norm": 11.621010780334473,
|
| 370 |
+
"learning_rate": 3.524069028156222e-05,
|
| 371 |
+
"loss": 1.1032,
|
| 372 |
+
"step": 450
|
| 373 |
+
},
|
| 374 |
+
{
|
| 375 |
+
"epoch": 4.487804878048781,
|
| 376 |
+
"grad_norm": 8.444263458251953,
|
| 377 |
+
"learning_rate": 3.4786557674841055e-05,
|
| 378 |
+
"loss": 1.1181,
|
| 379 |
+
"step": 460
|
| 380 |
+
},
|
| 381 |
+
{
|
| 382 |
+
"epoch": 4.585365853658536,
|
| 383 |
+
"grad_norm": 8.17673110961914,
|
| 384 |
+
"learning_rate": 3.433242506811989e-05,
|
| 385 |
+
"loss": 1.116,
|
| 386 |
+
"step": 470
|
| 387 |
+
},
|
| 388 |
+
{
|
| 389 |
+
"epoch": 4.682926829268292,
|
| 390 |
+
"grad_norm": 6.36055326461792,
|
| 391 |
+
"learning_rate": 3.387829246139873e-05,
|
| 392 |
+
"loss": 1.0976,
|
| 393 |
+
"step": 480
|
| 394 |
+
},
|
| 395 |
+
{
|
| 396 |
+
"epoch": 4.780487804878049,
|
| 397 |
+
"grad_norm": 6.861799240112305,
|
| 398 |
+
"learning_rate": 3.342415985467757e-05,
|
| 399 |
+
"loss": 1.0847,
|
| 400 |
+
"step": 490
|
| 401 |
+
},
|
| 402 |
+
{
|
| 403 |
+
"epoch": 4.878048780487805,
|
| 404 |
+
"grad_norm": 8.115589141845703,
|
| 405 |
+
"learning_rate": 3.2970027247956405e-05,
|
| 406 |
+
"loss": 1.1018,
|
| 407 |
+
"step": 500
|
| 408 |
+
},
|
| 409 |
+
{
|
| 410 |
+
"epoch": 4.975609756097561,
|
| 411 |
+
"grad_norm": 10.135653495788574,
|
| 412 |
+
"learning_rate": 3.251589464123524e-05,
|
| 413 |
+
"loss": 1.089,
|
| 414 |
+
"step": 510
|
| 415 |
+
},
|
| 416 |
+
{
|
| 417 |
+
"epoch": 4.995121951219512,
|
| 418 |
+
"eval_accuracy": 0.5344352617079889,
|
| 419 |
+
"eval_f1": 0.5440491210548923,
|
| 420 |
+
"eval_loss": 1.0458588600158691,
|
| 421 |
+
"eval_precision": 0.5719778943634586,
|
| 422 |
+
"eval_recall": 0.5344352617079889,
|
| 423 |
+
"eval_runtime": 10.4912,
|
| 424 |
+
"eval_samples_per_second": 103.801,
|
| 425 |
+
"eval_steps_per_second": 6.577,
|
| 426 |
+
"step": 512
|
| 427 |
+
},
|
| 428 |
+
{
|
| 429 |
+
"epoch": 5.073170731707317,
|
| 430 |
+
"grad_norm": 6.753456115722656,
|
| 431 |
+
"learning_rate": 3.206176203451408e-05,
|
| 432 |
+
"loss": 1.0425,
|
| 433 |
+
"step": 520
|
| 434 |
+
},
|
| 435 |
+
{
|
| 436 |
+
"epoch": 5.170731707317073,
|
| 437 |
+
"grad_norm": 8.520686149597168,
|
| 438 |
+
"learning_rate": 3.160762942779292e-05,
|
| 439 |
+
"loss": 1.0978,
|
| 440 |
+
"step": 530
|
| 441 |
+
},
|
| 442 |
+
{
|
| 443 |
+
"epoch": 5.2682926829268295,
|
| 444 |
+
"grad_norm": 9.387904167175293,
|
| 445 |
+
"learning_rate": 3.1153496821071755e-05,
|
| 446 |
+
"loss": 1.0495,
|
| 447 |
+
"step": 540
|
| 448 |
+
},
|
| 449 |
+
{
|
| 450 |
+
"epoch": 5.365853658536586,
|
| 451 |
+
"grad_norm": 9.20468807220459,
|
| 452 |
+
"learning_rate": 3.069936421435059e-05,
|
| 453 |
+
"loss": 1.117,
|
| 454 |
+
"step": 550
|
| 455 |
+
},
|
| 456 |
+
{
|
| 457 |
+
"epoch": 5.463414634146342,
|
| 458 |
+
"grad_norm": 11.512433052062988,
|
| 459 |
+
"learning_rate": 3.0245231607629433e-05,
|
| 460 |
+
"loss": 1.0678,
|
| 461 |
+
"step": 560
|
| 462 |
+
},
|
| 463 |
+
{
|
| 464 |
+
"epoch": 5.560975609756097,
|
| 465 |
+
"grad_norm": 8.392121315002441,
|
| 466 |
+
"learning_rate": 2.9791099000908267e-05,
|
| 467 |
+
"loss": 1.0267,
|
| 468 |
+
"step": 570
|
| 469 |
+
},
|
| 470 |
+
{
|
| 471 |
+
"epoch": 5.658536585365853,
|
| 472 |
+
"grad_norm": 10.961865425109863,
|
| 473 |
+
"learning_rate": 2.9336966394187105e-05,
|
| 474 |
+
"loss": 1.0381,
|
| 475 |
+
"step": 580
|
| 476 |
+
},
|
| 477 |
+
{
|
| 478 |
+
"epoch": 5.7560975609756095,
|
| 479 |
+
"grad_norm": 6.7657599449157715,
|
| 480 |
+
"learning_rate": 2.888283378746594e-05,
|
| 481 |
+
"loss": 1.0351,
|
| 482 |
+
"step": 590
|
| 483 |
+
},
|
| 484 |
+
{
|
| 485 |
+
"epoch": 5.853658536585366,
|
| 486 |
+
"grad_norm": 10.026562690734863,
|
| 487 |
+
"learning_rate": 2.8428701180744776e-05,
|
| 488 |
+
"loss": 1.0566,
|
| 489 |
+
"step": 600
|
| 490 |
+
},
|
| 491 |
+
{
|
| 492 |
+
"epoch": 5.951219512195122,
|
| 493 |
+
"grad_norm": 10.82862663269043,
|
| 494 |
+
"learning_rate": 2.7974568574023617e-05,
|
| 495 |
+
"loss": 1.0335,
|
| 496 |
+
"step": 610
|
| 497 |
+
},
|
| 498 |
+
{
|
| 499 |
+
"epoch": 6.0,
|
| 500 |
+
"eval_accuracy": 0.5748393021120294,
|
| 501 |
+
"eval_f1": 0.5696724052779626,
|
| 502 |
+
"eval_loss": 0.9780603051185608,
|
| 503 |
+
"eval_precision": 0.5821729436076757,
|
| 504 |
+
"eval_recall": 0.5748393021120294,
|
| 505 |
+
"eval_runtime": 10.5116,
|
| 506 |
+
"eval_samples_per_second": 103.6,
|
| 507 |
+
"eval_steps_per_second": 6.564,
|
| 508 |
+
"step": 615
|
| 509 |
+
},
|
| 510 |
+
{
|
| 511 |
+
"epoch": 6.048780487804878,
|
| 512 |
+
"grad_norm": 10.993868827819824,
|
| 513 |
+
"learning_rate": 2.7520435967302455e-05,
|
| 514 |
+
"loss": 0.9885,
|
| 515 |
+
"step": 620
|
| 516 |
+
},
|
| 517 |
+
{
|
| 518 |
+
"epoch": 6.146341463414634,
|
| 519 |
+
"grad_norm": 7.851088523864746,
|
| 520 |
+
"learning_rate": 2.7066303360581292e-05,
|
| 521 |
+
"loss": 1.0104,
|
| 522 |
+
"step": 630
|
| 523 |
+
},
|
| 524 |
+
{
|
| 525 |
+
"epoch": 6.2439024390243905,
|
| 526 |
+
"grad_norm": 8.290712356567383,
|
| 527 |
+
"learning_rate": 2.6612170753860126e-05,
|
| 528 |
+
"loss": 0.992,
|
| 529 |
+
"step": 640
|
| 530 |
+
},
|
| 531 |
+
{
|
| 532 |
+
"epoch": 6.341463414634147,
|
| 533 |
+
"grad_norm": 8.147354125976562,
|
| 534 |
+
"learning_rate": 2.6158038147138964e-05,
|
| 535 |
+
"loss": 1.0323,
|
| 536 |
+
"step": 650
|
| 537 |
+
},
|
| 538 |
+
{
|
| 539 |
+
"epoch": 6.439024390243903,
|
| 540 |
+
"grad_norm": 8.147374153137207,
|
| 541 |
+
"learning_rate": 2.5703905540417805e-05,
|
| 542 |
+
"loss": 1.0089,
|
| 543 |
+
"step": 660
|
| 544 |
+
},
|
| 545 |
+
{
|
| 546 |
+
"epoch": 6.536585365853659,
|
| 547 |
+
"grad_norm": 13.995866775512695,
|
| 548 |
+
"learning_rate": 2.5249772933696642e-05,
|
| 549 |
+
"loss": 1.0377,
|
| 550 |
+
"step": 670
|
| 551 |
+
},
|
| 552 |
+
{
|
| 553 |
+
"epoch": 6.634146341463414,
|
| 554 |
+
"grad_norm": 10.2506685256958,
|
| 555 |
+
"learning_rate": 2.4795640326975476e-05,
|
| 556 |
+
"loss": 0.979,
|
| 557 |
+
"step": 680
|
| 558 |
+
},
|
| 559 |
+
{
|
| 560 |
+
"epoch": 6.7317073170731705,
|
| 561 |
+
"grad_norm": 11.913418769836426,
|
| 562 |
+
"learning_rate": 2.4341507720254317e-05,
|
| 563 |
+
"loss": 0.9912,
|
| 564 |
+
"step": 690
|
| 565 |
+
},
|
| 566 |
+
{
|
| 567 |
+
"epoch": 6.829268292682927,
|
| 568 |
+
"grad_norm": 8.07094669342041,
|
| 569 |
+
"learning_rate": 2.388737511353315e-05,
|
| 570 |
+
"loss": 1.0496,
|
| 571 |
+
"step": 700
|
| 572 |
+
},
|
| 573 |
+
{
|
| 574 |
+
"epoch": 6.926829268292683,
|
| 575 |
+
"grad_norm": 11.005784034729004,
|
| 576 |
+
"learning_rate": 2.343324250681199e-05,
|
| 577 |
+
"loss": 1.0139,
|
| 578 |
+
"step": 710
|
| 579 |
+
},
|
| 580 |
+
{
|
| 581 |
+
"epoch": 6.995121951219512,
|
| 582 |
+
"eval_accuracy": 0.559228650137741,
|
| 583 |
+
"eval_f1": 0.5604831098024555,
|
| 584 |
+
"eval_loss": 0.990472674369812,
|
| 585 |
+
"eval_precision": 0.5624792636698613,
|
| 586 |
+
"eval_recall": 0.559228650137741,
|
| 587 |
+
"eval_runtime": 10.478,
|
| 588 |
+
"eval_samples_per_second": 103.932,
|
| 589 |
+
"eval_steps_per_second": 6.585,
|
| 590 |
+
"step": 717
|
| 591 |
+
},
|
| 592 |
+
{
|
| 593 |
+
"epoch": 7.024390243902439,
|
| 594 |
+
"grad_norm": 7.640585899353027,
|
| 595 |
+
"learning_rate": 2.297910990009083e-05,
|
| 596 |
+
"loss": 1.0333,
|
| 597 |
+
"step": 720
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"epoch": 7.121951219512195,
|
| 601 |
+
"grad_norm": 10.462299346923828,
|
| 602 |
+
"learning_rate": 2.2524977293369664e-05,
|
| 603 |
+
"loss": 0.9744,
|
| 604 |
+
"step": 730
|
| 605 |
+
},
|
| 606 |
+
{
|
| 607 |
+
"epoch": 7.219512195121951,
|
| 608 |
+
"grad_norm": 9.705671310424805,
|
| 609 |
+
"learning_rate": 2.2070844686648505e-05,
|
| 610 |
+
"loss": 0.9582,
|
| 611 |
+
"step": 740
|
| 612 |
+
},
|
| 613 |
+
{
|
| 614 |
+
"epoch": 7.317073170731708,
|
| 615 |
+
"grad_norm": 7.699019908905029,
|
| 616 |
+
"learning_rate": 2.161671207992734e-05,
|
| 617 |
+
"loss": 0.979,
|
| 618 |
+
"step": 750
|
| 619 |
+
},
|
| 620 |
+
{
|
| 621 |
+
"epoch": 7.414634146341464,
|
| 622 |
+
"grad_norm": 12.271793365478516,
|
| 623 |
+
"learning_rate": 2.1162579473206176e-05,
|
| 624 |
+
"loss": 0.9407,
|
| 625 |
+
"step": 760
|
| 626 |
+
},
|
| 627 |
+
{
|
| 628 |
+
"epoch": 7.512195121951219,
|
| 629 |
+
"grad_norm": 8.415149688720703,
|
| 630 |
+
"learning_rate": 2.0708446866485014e-05,
|
| 631 |
+
"loss": 0.9282,
|
| 632 |
+
"step": 770
|
| 633 |
+
},
|
| 634 |
+
{
|
| 635 |
+
"epoch": 7.609756097560975,
|
| 636 |
+
"grad_norm": 10.61991024017334,
|
| 637 |
+
"learning_rate": 2.025431425976385e-05,
|
| 638 |
+
"loss": 0.9563,
|
| 639 |
+
"step": 780
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 7.7073170731707314,
|
| 643 |
+
"grad_norm": 7.090912818908691,
|
| 644 |
+
"learning_rate": 1.980018165304269e-05,
|
| 645 |
+
"loss": 0.9637,
|
| 646 |
+
"step": 790
|
| 647 |
+
},
|
| 648 |
+
{
|
| 649 |
+
"epoch": 7.804878048780488,
|
| 650 |
+
"grad_norm": 11.96972370147705,
|
| 651 |
+
"learning_rate": 1.9346049046321526e-05,
|
| 652 |
+
"loss": 0.998,
|
| 653 |
+
"step": 800
|
| 654 |
+
},
|
| 655 |
+
{
|
| 656 |
+
"epoch": 7.902439024390244,
|
| 657 |
+
"grad_norm": 8.186046600341797,
|
| 658 |
+
"learning_rate": 1.8891916439600364e-05,
|
| 659 |
+
"loss": 0.9622,
|
| 660 |
+
"step": 810
|
| 661 |
+
},
|
| 662 |
+
{
|
| 663 |
+
"epoch": 8.0,
|
| 664 |
+
"grad_norm": 15.831442832946777,
|
| 665 |
+
"learning_rate": 1.84377838328792e-05,
|
| 666 |
+
"loss": 0.9047,
|
| 667 |
+
"step": 820
|
| 668 |
+
},
|
| 669 |
+
{
|
| 670 |
+
"epoch": 8.0,
|
| 671 |
+
"eval_accuracy": 0.5629017447199265,
|
| 672 |
+
"eval_f1": 0.5524851150741983,
|
| 673 |
+
"eval_loss": 0.9877268075942993,
|
| 674 |
+
"eval_precision": 0.5482104981099638,
|
| 675 |
+
"eval_recall": 0.5629017447199265,
|
| 676 |
+
"eval_runtime": 10.4831,
|
| 677 |
+
"eval_samples_per_second": 103.882,
|
| 678 |
+
"eval_steps_per_second": 6.582,
|
| 679 |
+
"step": 820
|
| 680 |
+
},
|
| 681 |
+
{
|
| 682 |
+
"epoch": 8.097560975609756,
|
| 683 |
+
"grad_norm": 8.30269718170166,
|
| 684 |
+
"learning_rate": 1.798365122615804e-05,
|
| 685 |
+
"loss": 0.9005,
|
| 686 |
+
"step": 830
|
| 687 |
+
},
|
| 688 |
+
{
|
| 689 |
+
"epoch": 8.195121951219512,
|
| 690 |
+
"grad_norm": 10.962409973144531,
|
| 691 |
+
"learning_rate": 1.7529518619436876e-05,
|
| 692 |
+
"loss": 0.9167,
|
| 693 |
+
"step": 840
|
| 694 |
+
},
|
| 695 |
+
{
|
| 696 |
+
"epoch": 8.292682926829269,
|
| 697 |
+
"grad_norm": 8.846582412719727,
|
| 698 |
+
"learning_rate": 1.7075386012715714e-05,
|
| 699 |
+
"loss": 0.9393,
|
| 700 |
+
"step": 850
|
| 701 |
+
},
|
| 702 |
+
{
|
| 703 |
+
"epoch": 8.390243902439025,
|
| 704 |
+
"grad_norm": 10.282524108886719,
|
| 705 |
+
"learning_rate": 1.662125340599455e-05,
|
| 706 |
+
"loss": 0.9473,
|
| 707 |
+
"step": 860
|
| 708 |
+
},
|
| 709 |
+
{
|
| 710 |
+
"epoch": 8.487804878048781,
|
| 711 |
+
"grad_norm": 11.323814392089844,
|
| 712 |
+
"learning_rate": 1.616712079927339e-05,
|
| 713 |
+
"loss": 0.8695,
|
| 714 |
+
"step": 870
|
| 715 |
+
},
|
| 716 |
+
{
|
| 717 |
+
"epoch": 8.585365853658537,
|
| 718 |
+
"grad_norm": 10.95213794708252,
|
| 719 |
+
"learning_rate": 1.5712988192552226e-05,
|
| 720 |
+
"loss": 0.9257,
|
| 721 |
+
"step": 880
|
| 722 |
+
},
|
| 723 |
+
{
|
| 724 |
+
"epoch": 8.682926829268293,
|
| 725 |
+
"grad_norm": 11.248684883117676,
|
| 726 |
+
"learning_rate": 1.5258855585831064e-05,
|
| 727 |
+
"loss": 0.8916,
|
| 728 |
+
"step": 890
|
| 729 |
+
},
|
| 730 |
+
{
|
| 731 |
+
"epoch": 8.78048780487805,
|
| 732 |
+
"grad_norm": 10.221022605895996,
|
| 733 |
+
"learning_rate": 1.48047229791099e-05,
|
| 734 |
+
"loss": 0.8961,
|
| 735 |
+
"step": 900
|
| 736 |
+
},
|
| 737 |
+
{
|
| 738 |
+
"epoch": 8.878048780487806,
|
| 739 |
+
"grad_norm": 8.226391792297363,
|
| 740 |
+
"learning_rate": 1.4350590372388739e-05,
|
| 741 |
+
"loss": 0.8783,
|
| 742 |
+
"step": 910
|
| 743 |
+
},
|
| 744 |
+
{
|
| 745 |
+
"epoch": 8.975609756097562,
|
| 746 |
+
"grad_norm": 9.135197639465332,
|
| 747 |
+
"learning_rate": 1.3896457765667576e-05,
|
| 748 |
+
"loss": 0.8856,
|
| 749 |
+
"step": 920
|
| 750 |
+
},
|
| 751 |
+
{
|
| 752 |
+
"epoch": 8.995121951219513,
|
| 753 |
+
"eval_accuracy": 0.5564738292011019,
|
| 754 |
+
"eval_f1": 0.556882933826955,
|
| 755 |
+
"eval_loss": 1.0059682130813599,
|
| 756 |
+
"eval_precision": 0.5592586252036796,
|
| 757 |
+
"eval_recall": 0.5564738292011019,
|
| 758 |
+
"eval_runtime": 10.5466,
|
| 759 |
+
"eval_samples_per_second": 103.256,
|
| 760 |
+
"eval_steps_per_second": 6.542,
|
| 761 |
+
"step": 922
|
| 762 |
+
},
|
| 763 |
+
{
|
| 764 |
+
"epoch": 9.073170731707316,
|
| 765 |
+
"grad_norm": 11.500414848327637,
|
| 766 |
+
"learning_rate": 1.3442325158946412e-05,
|
| 767 |
+
"loss": 0.8476,
|
| 768 |
+
"step": 930
|
| 769 |
+
},
|
| 770 |
+
{
|
| 771 |
+
"epoch": 9.170731707317072,
|
| 772 |
+
"grad_norm": 11.68885612487793,
|
| 773 |
+
"learning_rate": 1.2988192552225251e-05,
|
| 774 |
+
"loss": 0.869,
|
| 775 |
+
"step": 940
|
| 776 |
+
},
|
| 777 |
+
{
|
| 778 |
+
"epoch": 9.268292682926829,
|
| 779 |
+
"grad_norm": 9.877538681030273,
|
| 780 |
+
"learning_rate": 1.2534059945504087e-05,
|
| 781 |
+
"loss": 0.8572,
|
| 782 |
+
"step": 950
|
| 783 |
+
},
|
| 784 |
+
{
|
| 785 |
+
"epoch": 9.365853658536585,
|
| 786 |
+
"grad_norm": 11.605177879333496,
|
| 787 |
+
"learning_rate": 1.2079927338782924e-05,
|
| 788 |
+
"loss": 0.8434,
|
| 789 |
+
"step": 960
|
| 790 |
+
},
|
| 791 |
+
{
|
| 792 |
+
"epoch": 9.463414634146341,
|
| 793 |
+
"grad_norm": 10.330570220947266,
|
| 794 |
+
"learning_rate": 1.1625794732061762e-05,
|
| 795 |
+
"loss": 0.894,
|
| 796 |
+
"step": 970
|
| 797 |
+
},
|
| 798 |
+
{
|
| 799 |
+
"epoch": 9.560975609756097,
|
| 800 |
+
"grad_norm": 9.849478721618652,
|
| 801 |
+
"learning_rate": 1.11716621253406e-05,
|
| 802 |
+
"loss": 0.894,
|
| 803 |
+
"step": 980
|
| 804 |
+
},
|
| 805 |
+
{
|
| 806 |
+
"epoch": 9.658536585365853,
|
| 807 |
+
"grad_norm": 9.98214340209961,
|
| 808 |
+
"learning_rate": 1.0717529518619437e-05,
|
| 809 |
+
"loss": 0.8652,
|
| 810 |
+
"step": 990
|
| 811 |
+
},
|
| 812 |
+
{
|
| 813 |
+
"epoch": 9.75609756097561,
|
| 814 |
+
"grad_norm": 9.999092102050781,
|
| 815 |
+
"learning_rate": 1.0263396911898274e-05,
|
| 816 |
+
"loss": 0.8855,
|
| 817 |
+
"step": 1000
|
| 818 |
+
},
|
| 819 |
+
{
|
| 820 |
+
"epoch": 9.853658536585366,
|
| 821 |
+
"grad_norm": 10.021332740783691,
|
| 822 |
+
"learning_rate": 9.809264305177112e-06,
|
| 823 |
+
"loss": 0.8754,
|
| 824 |
+
"step": 1010
|
| 825 |
+
},
|
| 826 |
+
{
|
| 827 |
+
"epoch": 9.951219512195122,
|
| 828 |
+
"grad_norm": 10.624610900878906,
|
| 829 |
+
"learning_rate": 9.35513169845595e-06,
|
| 830 |
+
"loss": 0.8306,
|
| 831 |
+
"step": 1020
|
| 832 |
+
},
|
| 833 |
+
{
|
| 834 |
+
"epoch": 10.0,
|
| 835 |
+
"eval_accuracy": 0.566574839302112,
|
| 836 |
+
"eval_f1": 0.5574087205222212,
|
| 837 |
+
"eval_loss": 0.9907031655311584,
|
| 838 |
+
"eval_precision": 0.5531200477134914,
|
| 839 |
+
"eval_recall": 0.566574839302112,
|
| 840 |
+
"eval_runtime": 10.5011,
|
| 841 |
+
"eval_samples_per_second": 103.703,
|
| 842 |
+
"eval_steps_per_second": 6.571,
|
| 843 |
+
"step": 1025
|
| 844 |
+
},
|
| 845 |
+
{
|
| 846 |
+
"epoch": 10.048780487804878,
|
| 847 |
+
"grad_norm": 9.162467956542969,
|
| 848 |
+
"learning_rate": 8.900999091734787e-06,
|
| 849 |
+
"loss": 0.8177,
|
| 850 |
+
"step": 1030
|
| 851 |
+
},
|
| 852 |
+
{
|
| 853 |
+
"epoch": 10.146341463414634,
|
| 854 |
+
"grad_norm": 9.493200302124023,
|
| 855 |
+
"learning_rate": 8.446866485013624e-06,
|
| 856 |
+
"loss": 0.7632,
|
| 857 |
+
"step": 1040
|
| 858 |
+
},
|
| 859 |
+
{
|
| 860 |
+
"epoch": 10.24390243902439,
|
| 861 |
+
"grad_norm": 9.642596244812012,
|
| 862 |
+
"learning_rate": 7.992733878292462e-06,
|
| 863 |
+
"loss": 0.7732,
|
| 864 |
+
"step": 1050
|
| 865 |
+
},
|
| 866 |
+
{
|
| 867 |
+
"epoch": 10.341463414634147,
|
| 868 |
+
"grad_norm": 11.928635597229004,
|
| 869 |
+
"learning_rate": 7.538601271571299e-06,
|
| 870 |
+
"loss": 0.7979,
|
| 871 |
+
"step": 1060
|
| 872 |
+
},
|
| 873 |
+
{
|
| 874 |
+
"epoch": 10.439024390243903,
|
| 875 |
+
"grad_norm": 9.884861946105957,
|
| 876 |
+
"learning_rate": 7.084468664850137e-06,
|
| 877 |
+
"loss": 0.834,
|
| 878 |
+
"step": 1070
|
| 879 |
+
},
|
| 880 |
+
{
|
| 881 |
+
"epoch": 10.536585365853659,
|
| 882 |
+
"grad_norm": 10.674219131469727,
|
| 883 |
+
"learning_rate": 6.6303360581289735e-06,
|
| 884 |
+
"loss": 0.83,
|
| 885 |
+
"step": 1080
|
| 886 |
+
},
|
| 887 |
+
{
|
| 888 |
+
"epoch": 10.634146341463415,
|
| 889 |
+
"grad_norm": 11.04780387878418,
|
| 890 |
+
"learning_rate": 6.176203451407812e-06,
|
| 891 |
+
"loss": 0.8157,
|
| 892 |
+
"step": 1090
|
| 893 |
+
},
|
| 894 |
+
{
|
| 895 |
+
"epoch": 10.731707317073171,
|
| 896 |
+
"grad_norm": 11.664216995239258,
|
| 897 |
+
"learning_rate": 5.7220708446866485e-06,
|
| 898 |
+
"loss": 0.8041,
|
| 899 |
+
"step": 1100
|
| 900 |
+
},
|
| 901 |
+
{
|
| 902 |
+
"epoch": 10.829268292682928,
|
| 903 |
+
"grad_norm": 11.164298057556152,
|
| 904 |
+
"learning_rate": 5.267938237965486e-06,
|
| 905 |
+
"loss": 0.7685,
|
| 906 |
+
"step": 1110
|
| 907 |
+
},
|
| 908 |
+
{
|
| 909 |
+
"epoch": 10.926829268292684,
|
| 910 |
+
"grad_norm": 11.851963996887207,
|
| 911 |
+
"learning_rate": 4.813805631244324e-06,
|
| 912 |
+
"loss": 0.8458,
|
| 913 |
+
"step": 1120
|
| 914 |
+
},
|
| 915 |
+
{
|
| 916 |
+
"epoch": 10.995121951219513,
|
| 917 |
+
"eval_accuracy": 0.5500459136822773,
|
| 918 |
+
"eval_f1": 0.5489227474870219,
|
| 919 |
+
"eval_loss": 1.0134857892990112,
|
| 920 |
+
"eval_precision": 0.5505838083040273,
|
| 921 |
+
"eval_recall": 0.5500459136822773,
|
| 922 |
+
"eval_runtime": 10.4709,
|
| 923 |
+
"eval_samples_per_second": 104.003,
|
| 924 |
+
"eval_steps_per_second": 6.59,
|
| 925 |
+
"step": 1127
|
| 926 |
+
},
|
| 927 |
+
{
|
| 928 |
+
"epoch": 11.024390243902438,
|
| 929 |
+
"grad_norm": 9.90632438659668,
|
| 930 |
+
"learning_rate": 4.359673024523161e-06,
|
| 931 |
+
"loss": 0.7881,
|
| 932 |
+
"step": 1130
|
| 933 |
+
},
|
| 934 |
+
{
|
| 935 |
+
"epoch": 11.121951219512194,
|
| 936 |
+
"grad_norm": 11.564204216003418,
|
| 937 |
+
"learning_rate": 3.9055404178019984e-06,
|
| 938 |
+
"loss": 0.7449,
|
| 939 |
+
"step": 1140
|
| 940 |
+
},
|
| 941 |
+
{
|
| 942 |
+
"epoch": 11.21951219512195,
|
| 943 |
+
"grad_norm": 10.323161125183105,
|
| 944 |
+
"learning_rate": 3.451407811080836e-06,
|
| 945 |
+
"loss": 0.7865,
|
| 946 |
+
"step": 1150
|
| 947 |
+
},
|
| 948 |
+
{
|
| 949 |
+
"epoch": 11.317073170731707,
|
| 950 |
+
"grad_norm": 11.201330184936523,
|
| 951 |
+
"learning_rate": 2.997275204359673e-06,
|
| 952 |
+
"loss": 0.781,
|
| 953 |
+
"step": 1160
|
| 954 |
+
},
|
| 955 |
+
{
|
| 956 |
+
"epoch": 11.414634146341463,
|
| 957 |
+
"grad_norm": 9.596723556518555,
|
| 958 |
+
"learning_rate": 2.5431425976385105e-06,
|
| 959 |
+
"loss": 0.7847,
|
| 960 |
+
"step": 1170
|
| 961 |
+
},
|
| 962 |
+
{
|
| 963 |
+
"epoch": 11.512195121951219,
|
| 964 |
+
"grad_norm": 10.385799407958984,
|
| 965 |
+
"learning_rate": 2.089009990917348e-06,
|
| 966 |
+
"loss": 0.8139,
|
| 967 |
+
"step": 1180
|
| 968 |
+
},
|
| 969 |
+
{
|
| 970 |
+
"epoch": 11.609756097560975,
|
| 971 |
+
"grad_norm": 12.413230895996094,
|
| 972 |
+
"learning_rate": 1.6348773841961852e-06,
|
| 973 |
+
"loss": 0.7824,
|
| 974 |
+
"step": 1190
|
| 975 |
+
},
|
| 976 |
+
{
|
| 977 |
+
"epoch": 11.707317073170731,
|
| 978 |
+
"grad_norm": 10.438215255737305,
|
| 979 |
+
"learning_rate": 1.1807447774750227e-06,
|
| 980 |
+
"loss": 0.7464,
|
| 981 |
+
"step": 1200
|
| 982 |
+
},
|
| 983 |
+
{
|
| 984 |
+
"epoch": 11.804878048780488,
|
| 985 |
+
"grad_norm": 10.087923049926758,
|
| 986 |
+
"learning_rate": 7.266121707538601e-07,
|
| 987 |
+
"loss": 0.8032,
|
| 988 |
+
"step": 1210
|
| 989 |
+
},
|
| 990 |
+
{
|
| 991 |
+
"epoch": 11.902439024390244,
|
| 992 |
+
"grad_norm": 10.667466163635254,
|
| 993 |
+
"learning_rate": 2.7247956403269756e-07,
|
| 994 |
+
"loss": 0.815,
|
| 995 |
+
"step": 1220
|
| 996 |
+
},
|
| 997 |
+
{
|
| 998 |
+
"epoch": 11.941463414634146,
|
| 999 |
+
"eval_accuracy": 0.549127640036731,
|
| 1000 |
+
"eval_f1": 0.5520258447427934,
|
| 1001 |
+
"eval_loss": 1.0185083150863647,
|
| 1002 |
+
"eval_precision": 0.5558049078671707,
|
| 1003 |
+
"eval_recall": 0.549127640036731,
|
| 1004 |
+
"eval_runtime": 10.5534,
|
| 1005 |
+
"eval_samples_per_second": 103.19,
|
| 1006 |
+
"eval_steps_per_second": 6.538,
|
| 1007 |
+
"step": 1224
|
| 1008 |
+
},
|
| 1009 |
+
{
|
| 1010 |
+
"epoch": 11.941463414634146,
|
| 1011 |
+
"step": 1224,
|
| 1012 |
+
"total_flos": 6.197635483154842e+18,
|
| 1013 |
+
"train_loss": 1.0363535090209612,
|
| 1014 |
+
"train_runtime": 3088.0708,
|
| 1015 |
+
"train_samples_per_second": 25.461,
|
| 1016 |
+
"train_steps_per_second": 0.396
|
| 1017 |
+
}
|
| 1018 |
+
],
|
| 1019 |
+
"logging_steps": 10,
|
| 1020 |
+
"max_steps": 1224,
|
| 1021 |
+
"num_input_tokens_seen": 0,
|
| 1022 |
+
"num_train_epochs": 12,
|
| 1023 |
+
"save_steps": 500,
|
| 1024 |
+
"stateful_callbacks": {
|
| 1025 |
+
"TrainerControl": {
|
| 1026 |
+
"args": {
|
| 1027 |
+
"should_epoch_stop": false,
|
| 1028 |
+
"should_evaluate": false,
|
| 1029 |
+
"should_log": false,
|
| 1030 |
+
"should_save": true,
|
| 1031 |
+
"should_training_stop": true
|
| 1032 |
+
},
|
| 1033 |
+
"attributes": {}
|
| 1034 |
+
}
|
| 1035 |
+
},
|
| 1036 |
+
"total_flos": 6.197635483154842e+18,
|
| 1037 |
+
"train_batch_size": 16,
|
| 1038 |
+
"trial_name": null,
|
| 1039 |
+
"trial_params": null
|
| 1040 |
+
}
|