End of training
Browse files- README.md +5 -5
- all_results.json +16 -0
- eval_results.json +11 -0
- runs/Sep05_17-02-41_d597b29d658a/events.out.tfevents.1725558615.d597b29d658a.956.5 +3 -0
- train_results.json +8 -0
- trainer_state.json +1242 -0
README.md
CHANGED
|
@@ -21,11 +21,11 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 21 |
|
| 22 |
This model is a fine-tuned version of [microsoft/swin-tiny-patch4-window7-224](https://huggingface.co/microsoft/swin-tiny-patch4-window7-224) on an unknown dataset.
|
| 23 |
It achieves the following results on the evaluation set:
|
| 24 |
-
- Loss: 0.
|
| 25 |
-
- Accuracy: 0.
|
| 26 |
-
- F1: 0.
|
| 27 |
-
- Precision: 0.
|
| 28 |
-
- Recall: 0.
|
| 29 |
|
| 30 |
## Model description
|
| 31 |
|
|
|
|
| 21 |
|
| 22 |
This model is a fine-tuned version of [microsoft/swin-tiny-patch4-window7-224](https://huggingface.co/microsoft/swin-tiny-patch4-window7-224) on an unknown dataset.
|
| 23 |
It achieves the following results on the evaluation set:
|
| 24 |
+
- Loss: 0.9108
|
| 25 |
+
- Accuracy: 0.6221
|
| 26 |
+
- F1: 0.6116
|
| 27 |
+
- Precision: 0.6170
|
| 28 |
+
- Recall: 0.6221
|
| 29 |
|
| 30 |
## Model description
|
| 31 |
|
all_results.json
ADDED
|
@@ -0,0 +1,16 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 29.357798165137616,
|
| 3 |
+
"eval_accuracy": 0.6221198156682027,
|
| 4 |
+
"eval_f1": 0.6115919254751536,
|
| 5 |
+
"eval_loss": 0.9107956886291504,
|
| 6 |
+
"eval_precision": 0.616963195553811,
|
| 7 |
+
"eval_recall": 0.6221198156682027,
|
| 8 |
+
"eval_runtime": 0.9657,
|
| 9 |
+
"eval_samples_per_second": 224.713,
|
| 10 |
+
"eval_steps_per_second": 14.498,
|
| 11 |
+
"total_flos": 3.8130472219998413e+18,
|
| 12 |
+
"train_loss": 1.1265972677866618,
|
| 13 |
+
"train_runtime": 2449.5651,
|
| 14 |
+
"train_samples_per_second": 63.991,
|
| 15 |
+
"train_steps_per_second": 0.49
|
| 16 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,11 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 29.357798165137616,
|
| 3 |
+
"eval_accuracy": 0.6221198156682027,
|
| 4 |
+
"eval_f1": 0.6115919254751536,
|
| 5 |
+
"eval_loss": 0.9107956886291504,
|
| 6 |
+
"eval_precision": 0.616963195553811,
|
| 7 |
+
"eval_recall": 0.6221198156682027,
|
| 8 |
+
"eval_runtime": 0.9657,
|
| 9 |
+
"eval_samples_per_second": 224.713,
|
| 10 |
+
"eval_steps_per_second": 14.498
|
| 11 |
+
}
|
runs/Sep05_17-02-41_d597b29d658a/events.out.tfevents.1725558615.d597b29d658a.956.5
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a40eae4e8b846749180eebce45420798eb6b10b79d873feea8956b6cde171e7c
|
| 3 |
+
size 560
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 29.357798165137616,
|
| 3 |
+
"total_flos": 3.8130472219998413e+18,
|
| 4 |
+
"train_loss": 1.1265972677866618,
|
| 5 |
+
"train_runtime": 2449.5651,
|
| 6 |
+
"train_samples_per_second": 63.991,
|
| 7 |
+
"train_steps_per_second": 0.49
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,1242 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.6115919254751536,
|
| 3 |
+
"best_model_checkpoint": "swin-tiny-patch4-window7-224-finetuned-tekno24-highdata-90-3rd/checkpoint-858",
|
| 4 |
+
"epoch": 29.357798165137616,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 1200,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.24464831804281345,
|
| 13 |
+
"grad_norm": 6.330469131469727,
|
| 14 |
+
"learning_rate": 2.4999999999999998e-06,
|
| 15 |
+
"loss": 1.4219,
|
| 16 |
+
"step": 10
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.4892966360856269,
|
| 20 |
+
"grad_norm": 4.396063327789307,
|
| 21 |
+
"learning_rate": 4.9999999999999996e-06,
|
| 22 |
+
"loss": 1.3862,
|
| 23 |
+
"step": 20
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.7339449541284404,
|
| 27 |
+
"grad_norm": 8.383111000061035,
|
| 28 |
+
"learning_rate": 7.5e-06,
|
| 29 |
+
"loss": 1.3539,
|
| 30 |
+
"step": 30
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.9785932721712538,
|
| 34 |
+
"grad_norm": 4.335956573486328,
|
| 35 |
+
"learning_rate": 9.999999999999999e-06,
|
| 36 |
+
"loss": 1.3622,
|
| 37 |
+
"step": 40
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.9785932721712538,
|
| 41 |
+
"eval_accuracy": 0.3686635944700461,
|
| 42 |
+
"eval_f1": 0.24531431172017315,
|
| 43 |
+
"eval_loss": 1.345871925354004,
|
| 44 |
+
"eval_precision": 0.2573782313691113,
|
| 45 |
+
"eval_recall": 0.3686635944700461,
|
| 46 |
+
"eval_runtime": 0.8809,
|
| 47 |
+
"eval_samples_per_second": 246.332,
|
| 48 |
+
"eval_steps_per_second": 15.892,
|
| 49 |
+
"step": 40
|
| 50 |
+
},
|
| 51 |
+
{
|
| 52 |
+
"epoch": 1.2232415902140672,
|
| 53 |
+
"grad_norm": 4.0306572914123535,
|
| 54 |
+
"learning_rate": 1.25e-05,
|
| 55 |
+
"loss": 1.3462,
|
| 56 |
+
"step": 50
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 1.4678899082568808,
|
| 60 |
+
"grad_norm": 5.952158451080322,
|
| 61 |
+
"learning_rate": 1.5e-05,
|
| 62 |
+
"loss": 1.3484,
|
| 63 |
+
"step": 60
|
| 64 |
+
},
|
| 65 |
+
{
|
| 66 |
+
"epoch": 1.7125382262996942,
|
| 67 |
+
"grad_norm": 4.490999698638916,
|
| 68 |
+
"learning_rate": 1.7500000000000002e-05,
|
| 69 |
+
"loss": 1.3272,
|
| 70 |
+
"step": 70
|
| 71 |
+
},
|
| 72 |
+
{
|
| 73 |
+
"epoch": 1.9571865443425076,
|
| 74 |
+
"grad_norm": 4.4648823738098145,
|
| 75 |
+
"learning_rate": 1.9999999999999998e-05,
|
| 76 |
+
"loss": 1.335,
|
| 77 |
+
"step": 80
|
| 78 |
+
},
|
| 79 |
+
{
|
| 80 |
+
"epoch": 1.981651376146789,
|
| 81 |
+
"eval_accuracy": 0.3778801843317972,
|
| 82 |
+
"eval_f1": 0.36347086798868594,
|
| 83 |
+
"eval_loss": 1.329477310180664,
|
| 84 |
+
"eval_precision": 0.35923465537774313,
|
| 85 |
+
"eval_recall": 0.3778801843317972,
|
| 86 |
+
"eval_runtime": 0.858,
|
| 87 |
+
"eval_samples_per_second": 252.915,
|
| 88 |
+
"eval_steps_per_second": 16.317,
|
| 89 |
+
"step": 81
|
| 90 |
+
},
|
| 91 |
+
{
|
| 92 |
+
"epoch": 2.2018348623853212,
|
| 93 |
+
"grad_norm": 3.4146816730499268,
|
| 94 |
+
"learning_rate": 2.25e-05,
|
| 95 |
+
"loss": 1.3282,
|
| 96 |
+
"step": 90
|
| 97 |
+
},
|
| 98 |
+
{
|
| 99 |
+
"epoch": 2.4464831804281344,
|
| 100 |
+
"grad_norm": 2.6035099029541016,
|
| 101 |
+
"learning_rate": 2.5e-05,
|
| 102 |
+
"loss": 1.3004,
|
| 103 |
+
"step": 100
|
| 104 |
+
},
|
| 105 |
+
{
|
| 106 |
+
"epoch": 2.691131498470948,
|
| 107 |
+
"grad_norm": 4.214941024780273,
|
| 108 |
+
"learning_rate": 2.75e-05,
|
| 109 |
+
"loss": 1.2825,
|
| 110 |
+
"step": 110
|
| 111 |
+
},
|
| 112 |
+
{
|
| 113 |
+
"epoch": 2.9357798165137616,
|
| 114 |
+
"grad_norm": 4.834983825683594,
|
| 115 |
+
"learning_rate": 3e-05,
|
| 116 |
+
"loss": 1.2404,
|
| 117 |
+
"step": 120
|
| 118 |
+
},
|
| 119 |
+
{
|
| 120 |
+
"epoch": 2.984709480122324,
|
| 121 |
+
"eval_accuracy": 0.5023041474654378,
|
| 122 |
+
"eval_f1": 0.4893126350217038,
|
| 123 |
+
"eval_loss": 1.1256120204925537,
|
| 124 |
+
"eval_precision": 0.5048490267556228,
|
| 125 |
+
"eval_recall": 0.5023041474654378,
|
| 126 |
+
"eval_runtime": 0.8434,
|
| 127 |
+
"eval_samples_per_second": 257.293,
|
| 128 |
+
"eval_steps_per_second": 16.6,
|
| 129 |
+
"step": 122
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 3.180428134556575,
|
| 133 |
+
"grad_norm": 3.794398784637451,
|
| 134 |
+
"learning_rate": 2.9993654251233013e-05,
|
| 135 |
+
"loss": 1.2474,
|
| 136 |
+
"step": 130
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 3.4250764525993884,
|
| 140 |
+
"grad_norm": 5.768642425537109,
|
| 141 |
+
"learning_rate": 2.9974622374069024e-05,
|
| 142 |
+
"loss": 1.195,
|
| 143 |
+
"step": 140
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 3.669724770642202,
|
| 147 |
+
"grad_norm": 3.9253504276275635,
|
| 148 |
+
"learning_rate": 2.9942920471376185e-05,
|
| 149 |
+
"loss": 1.2086,
|
| 150 |
+
"step": 150
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"epoch": 3.914373088685015,
|
| 154 |
+
"grad_norm": 4.371098518371582,
|
| 155 |
+
"learning_rate": 2.9898575366129145e-05,
|
| 156 |
+
"loss": 1.2113,
|
| 157 |
+
"step": 160
|
| 158 |
+
},
|
| 159 |
+
{
|
| 160 |
+
"epoch": 3.9877675840978593,
|
| 161 |
+
"eval_accuracy": 0.5345622119815668,
|
| 162 |
+
"eval_f1": 0.49180767021976945,
|
| 163 |
+
"eval_loss": 1.10813570022583,
|
| 164 |
+
"eval_precision": 0.5409206372379718,
|
| 165 |
+
"eval_recall": 0.5345622119815668,
|
| 166 |
+
"eval_runtime": 0.8699,
|
| 167 |
+
"eval_samples_per_second": 249.465,
|
| 168 |
+
"eval_steps_per_second": 16.095,
|
| 169 |
+
"step": 163
|
| 170 |
+
},
|
| 171 |
+
{
|
| 172 |
+
"epoch": 4.159021406727828,
|
| 173 |
+
"grad_norm": 2.8948540687561035,
|
| 174 |
+
"learning_rate": 2.9841624578714165e-05,
|
| 175 |
+
"loss": 1.1962,
|
| 176 |
+
"step": 170
|
| 177 |
+
},
|
| 178 |
+
{
|
| 179 |
+
"epoch": 4.4036697247706424,
|
| 180 |
+
"grad_norm": 4.7834649085998535,
|
| 181 |
+
"learning_rate": 2.977211629518312e-05,
|
| 182 |
+
"loss": 1.2218,
|
| 183 |
+
"step": 180
|
| 184 |
+
},
|
| 185 |
+
{
|
| 186 |
+
"epoch": 4.648318042813456,
|
| 187 |
+
"grad_norm": 7.953682899475098,
|
| 188 |
+
"learning_rate": 2.9690109326483276e-05,
|
| 189 |
+
"loss": 1.1939,
|
| 190 |
+
"step": 190
|
| 191 |
+
},
|
| 192 |
+
{
|
| 193 |
+
"epoch": 4.892966360856269,
|
| 194 |
+
"grad_norm": 4.670468807220459,
|
| 195 |
+
"learning_rate": 2.959567305869736e-05,
|
| 196 |
+
"loss": 1.1617,
|
| 197 |
+
"step": 200
|
| 198 |
+
},
|
| 199 |
+
{
|
| 200 |
+
"epoch": 4.990825688073395,
|
| 201 |
+
"eval_accuracy": 0.5299539170506913,
|
| 202 |
+
"eval_f1": 0.4937854301455633,
|
| 203 |
+
"eval_loss": 1.0666954517364502,
|
| 204 |
+
"eval_precision": 0.5204300879512693,
|
| 205 |
+
"eval_recall": 0.5299539170506913,
|
| 206 |
+
"eval_runtime": 0.8676,
|
| 207 |
+
"eval_samples_per_second": 250.129,
|
| 208 |
+
"eval_steps_per_second": 16.137,
|
| 209 |
+
"step": 204
|
| 210 |
+
},
|
| 211 |
+
{
|
| 212 |
+
"epoch": 5.137614678899083,
|
| 213 |
+
"grad_norm": 3.710249662399292,
|
| 214 |
+
"learning_rate": 2.9488887394336025e-05,
|
| 215 |
+
"loss": 1.1513,
|
| 216 |
+
"step": 210
|
| 217 |
+
},
|
| 218 |
+
{
|
| 219 |
+
"epoch": 5.382262996941896,
|
| 220 |
+
"grad_norm": 5.402332305908203,
|
| 221 |
+
"learning_rate": 2.9369842684732334e-05,
|
| 222 |
+
"loss": 1.1615,
|
| 223 |
+
"step": 220
|
| 224 |
+
},
|
| 225 |
+
{
|
| 226 |
+
"epoch": 5.626911314984709,
|
| 227 |
+
"grad_norm": 5.203404426574707,
|
| 228 |
+
"learning_rate": 2.923863965359551e-05,
|
| 229 |
+
"loss": 1.1667,
|
| 230 |
+
"step": 230
|
| 231 |
+
},
|
| 232 |
+
{
|
| 233 |
+
"epoch": 5.871559633027523,
|
| 234 |
+
"grad_norm": 3.1625759601593018,
|
| 235 |
+
"learning_rate": 2.9095389311788626e-05,
|
| 236 |
+
"loss": 1.1758,
|
| 237 |
+
"step": 240
|
| 238 |
+
},
|
| 239 |
+
{
|
| 240 |
+
"epoch": 5.99388379204893,
|
| 241 |
+
"eval_accuracy": 0.47465437788018433,
|
| 242 |
+
"eval_f1": 0.471263567537793,
|
| 243 |
+
"eval_loss": 1.1505143642425537,
|
| 244 |
+
"eval_precision": 0.5074166187040903,
|
| 245 |
+
"eval_recall": 0.47465437788018433,
|
| 246 |
+
"eval_runtime": 0.8615,
|
| 247 |
+
"eval_samples_per_second": 251.9,
|
| 248 |
+
"eval_steps_per_second": 16.252,
|
| 249 |
+
"step": 245
|
| 250 |
+
},
|
| 251 |
+
{
|
| 252 |
+
"epoch": 6.116207951070336,
|
| 253 |
+
"grad_norm": 3.6149017810821533,
|
| 254 |
+
"learning_rate": 2.8940212863402334e-05,
|
| 255 |
+
"loss": 1.1593,
|
| 256 |
+
"step": 250
|
| 257 |
+
},
|
| 258 |
+
{
|
| 259 |
+
"epoch": 6.36085626911315,
|
| 260 |
+
"grad_norm": 5.2453718185424805,
|
| 261 |
+
"learning_rate": 2.877324160320411e-05,
|
| 262 |
+
"loss": 1.1709,
|
| 263 |
+
"step": 260
|
| 264 |
+
},
|
| 265 |
+
{
|
| 266 |
+
"epoch": 6.605504587155964,
|
| 267 |
+
"grad_norm": 2.8466713428497314,
|
| 268 |
+
"learning_rate": 2.8594616805549752e-05,
|
| 269 |
+
"loss": 1.1796,
|
| 270 |
+
"step": 270
|
| 271 |
+
},
|
| 272 |
+
{
|
| 273 |
+
"epoch": 6.850152905198777,
|
| 274 |
+
"grad_norm": 5.2934489250183105,
|
| 275 |
+
"learning_rate": 2.8404489604851186e-05,
|
| 276 |
+
"loss": 1.1618,
|
| 277 |
+
"step": 280
|
| 278 |
+
},
|
| 279 |
+
{
|
| 280 |
+
"epoch": 6.996941896024465,
|
| 281 |
+
"eval_accuracy": 0.4930875576036866,
|
| 282 |
+
"eval_f1": 0.4779433197425019,
|
| 283 |
+
"eval_loss": 1.1315704584121704,
|
| 284 |
+
"eval_precision": 0.49500033007529604,
|
| 285 |
+
"eval_recall": 0.4930875576036866,
|
| 286 |
+
"eval_runtime": 0.8521,
|
| 287 |
+
"eval_samples_per_second": 254.672,
|
| 288 |
+
"eval_steps_per_second": 16.43,
|
| 289 |
+
"step": 286
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 7.09480122324159,
|
| 293 |
+
"grad_norm": 2.6427509784698486,
|
| 294 |
+
"learning_rate": 2.8203020867701665e-05,
|
| 295 |
+
"loss": 1.1743,
|
| 296 |
+
"step": 290
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 7.339449541284404,
|
| 300 |
+
"grad_norm": 4.475164890289307,
|
| 301 |
+
"learning_rate": 2.7990381056766583e-05,
|
| 302 |
+
"loss": 1.145,
|
| 303 |
+
"step": 300
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 7.584097859327217,
|
| 307 |
+
"grad_norm": 6.199124813079834,
|
| 308 |
+
"learning_rate": 2.7766750086554997e-05,
|
| 309 |
+
"loss": 1.1746,
|
| 310 |
+
"step": 310
|
| 311 |
+
},
|
| 312 |
+
{
|
| 313 |
+
"epoch": 7.82874617737003,
|
| 314 |
+
"grad_norm": 2.8797366619110107,
|
| 315 |
+
"learning_rate": 2.753231717119405e-05,
|
| 316 |
+
"loss": 1.1748,
|
| 317 |
+
"step": 320
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 8.0,
|
| 321 |
+
"eval_accuracy": 0.5161290322580645,
|
| 322 |
+
"eval_f1": 0.48266751828493326,
|
| 323 |
+
"eval_loss": 1.068114995956421,
|
| 324 |
+
"eval_precision": 0.5256066050304817,
|
| 325 |
+
"eval_recall": 0.5161290322580645,
|
| 326 |
+
"eval_runtime": 0.9022,
|
| 327 |
+
"eval_samples_per_second": 240.519,
|
| 328 |
+
"eval_steps_per_second": 15.517,
|
| 329 |
+
"step": 327
|
| 330 |
+
},
|
| 331 |
+
{
|
| 332 |
+
"epoch": 8.073394495412844,
|
| 333 |
+
"grad_norm": 3.447052001953125,
|
| 334 |
+
"learning_rate": 2.728728066433488e-05,
|
| 335 |
+
"loss": 1.1551,
|
| 336 |
+
"step": 330
|
| 337 |
+
},
|
| 338 |
+
{
|
| 339 |
+
"epoch": 8.318042813455657,
|
| 340 |
+
"grad_norm": 8.132365226745605,
|
| 341 |
+
"learning_rate": 2.7031847891325658e-05,
|
| 342 |
+
"loss": 1.1553,
|
| 343 |
+
"step": 340
|
| 344 |
+
},
|
| 345 |
+
{
|
| 346 |
+
"epoch": 8.562691131498472,
|
| 347 |
+
"grad_norm": 4.7136969566345215,
|
| 348 |
+
"learning_rate": 2.6766234973793638e-05,
|
| 349 |
+
"loss": 1.1417,
|
| 350 |
+
"step": 350
|
| 351 |
+
},
|
| 352 |
+
{
|
| 353 |
+
"epoch": 8.807339449541285,
|
| 354 |
+
"grad_norm": 5.761626243591309,
|
| 355 |
+
"learning_rate": 2.649066664678467e-05,
|
| 356 |
+
"loss": 1.1421,
|
| 357 |
+
"step": 360
|
| 358 |
+
},
|
| 359 |
+
{
|
| 360 |
+
"epoch": 8.978593272171254,
|
| 361 |
+
"eval_accuracy": 0.5714285714285714,
|
| 362 |
+
"eval_f1": 0.5445015753271358,
|
| 363 |
+
"eval_loss": 0.9743120670318604,
|
| 364 |
+
"eval_precision": 0.5487771652399015,
|
| 365 |
+
"eval_recall": 0.5714285714285714,
|
| 366 |
+
"eval_runtime": 0.8766,
|
| 367 |
+
"eval_samples_per_second": 247.558,
|
| 368 |
+
"eval_steps_per_second": 15.971,
|
| 369 |
+
"step": 367
|
| 370 |
+
},
|
| 371 |
+
{
|
| 372 |
+
"epoch": 9.051987767584098,
|
| 373 |
+
"grad_norm": 4.3898138999938965,
|
| 374 |
+
"learning_rate": 2.620537606861494e-05,
|
| 375 |
+
"loss": 1.1345,
|
| 376 |
+
"step": 370
|
| 377 |
+
},
|
| 378 |
+
{
|
| 379 |
+
"epoch": 9.296636085626911,
|
| 380 |
+
"grad_norm": 4.993420600891113,
|
| 381 |
+
"learning_rate": 2.5910604623595732e-05,
|
| 382 |
+
"loss": 1.1397,
|
| 383 |
+
"step": 380
|
| 384 |
+
},
|
| 385 |
+
{
|
| 386 |
+
"epoch": 9.541284403669724,
|
| 387 |
+
"grad_norm": 4.071462631225586,
|
| 388 |
+
"learning_rate": 2.5606601717798212e-05,
|
| 389 |
+
"loss": 1.1463,
|
| 390 |
+
"step": 390
|
| 391 |
+
},
|
| 392 |
+
{
|
| 393 |
+
"epoch": 9.785932721712538,
|
| 394 |
+
"grad_norm": 9.125846862792969,
|
| 395 |
+
"learning_rate": 2.5293624568031008e-05,
|
| 396 |
+
"loss": 1.1565,
|
| 397 |
+
"step": 400
|
| 398 |
+
},
|
| 399 |
+
{
|
| 400 |
+
"epoch": 9.98165137614679,
|
| 401 |
+
"eval_accuracy": 0.5622119815668203,
|
| 402 |
+
"eval_f1": 0.5142422921536122,
|
| 403 |
+
"eval_loss": 0.9705408215522766,
|
| 404 |
+
"eval_precision": 0.5428585184675699,
|
| 405 |
+
"eval_recall": 0.5622119815668203,
|
| 406 |
+
"eval_runtime": 0.8818,
|
| 407 |
+
"eval_samples_per_second": 246.084,
|
| 408 |
+
"eval_steps_per_second": 15.876,
|
| 409 |
+
"step": 408
|
| 410 |
+
},
|
| 411 |
+
{
|
| 412 |
+
"epoch": 10.030581039755353,
|
| 413 |
+
"grad_norm": 3.2460174560546875,
|
| 414 |
+
"learning_rate": 2.4971937984209064e-05,
|
| 415 |
+
"loss": 1.1213,
|
| 416 |
+
"step": 410
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"epoch": 10.275229357798166,
|
| 420 |
+
"grad_norm": 3.74979829788208,
|
| 421 |
+
"learning_rate": 2.464181414529809e-05,
|
| 422 |
+
"loss": 1.1653,
|
| 423 |
+
"step": 420
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 10.519877675840979,
|
| 427 |
+
"grad_norm": 4.549282073974609,
|
| 428 |
+
"learning_rate": 2.43035323690239e-05,
|
| 429 |
+
"loss": 1.1195,
|
| 430 |
+
"step": 430
|
| 431 |
+
},
|
| 432 |
+
{
|
| 433 |
+
"epoch": 10.764525993883792,
|
| 434 |
+
"grad_norm": 5.184534549713135,
|
| 435 |
+
"learning_rate": 2.3957378875541795e-05,
|
| 436 |
+
"loss": 1.1297,
|
| 437 |
+
"step": 440
|
| 438 |
+
},
|
| 439 |
+
{
|
| 440 |
+
"epoch": 10.984709480122325,
|
| 441 |
+
"eval_accuracy": 0.5529953917050692,
|
| 442 |
+
"eval_f1": 0.5365471718335717,
|
| 443 |
+
"eval_loss": 0.9878734350204468,
|
| 444 |
+
"eval_precision": 0.5343152202928371,
|
| 445 |
+
"eval_recall": 0.5529953917050692,
|
| 446 |
+
"eval_runtime": 0.8858,
|
| 447 |
+
"eval_samples_per_second": 244.969,
|
| 448 |
+
"eval_steps_per_second": 15.804,
|
| 449 |
+
"step": 449
|
| 450 |
+
},
|
| 451 |
+
{
|
| 452 |
+
"epoch": 11.009174311926605,
|
| 453 |
+
"grad_norm": 5.1757049560546875,
|
| 454 |
+
"learning_rate": 2.360364654526569e-05,
|
| 455 |
+
"loss": 1.1315,
|
| 456 |
+
"step": 450
|
| 457 |
+
},
|
| 458 |
+
{
|
| 459 |
+
"epoch": 11.253822629969418,
|
| 460 |
+
"grad_norm": 4.584784507751465,
|
| 461 |
+
"learning_rate": 2.324263467106209e-05,
|
| 462 |
+
"loss": 1.0953,
|
| 463 |
+
"step": 460
|
| 464 |
+
},
|
| 465 |
+
{
|
| 466 |
+
"epoch": 11.498470948012232,
|
| 467 |
+
"grad_norm": 5.368664264678955,
|
| 468 |
+
"learning_rate": 2.28746487050184e-05,
|
| 469 |
+
"loss": 1.1434,
|
| 470 |
+
"step": 470
|
| 471 |
+
},
|
| 472 |
+
{
|
| 473 |
+
"epoch": 11.743119266055047,
|
| 474 |
+
"grad_norm": 3.2927210330963135,
|
| 475 |
+
"learning_rate": 2.25e-05,
|
| 476 |
+
"loss": 1.1204,
|
| 477 |
+
"step": 480
|
| 478 |
+
},
|
| 479 |
+
{
|
| 480 |
+
"epoch": 11.98776758409786,
|
| 481 |
+
"grad_norm": 2.96950626373291,
|
| 482 |
+
"learning_rate": 2.2119005546214607e-05,
|
| 483 |
+
"loss": 1.1249,
|
| 484 |
+
"step": 490
|
| 485 |
+
},
|
| 486 |
+
{
|
| 487 |
+
"epoch": 11.98776758409786,
|
| 488 |
+
"eval_accuracy": 0.576036866359447,
|
| 489 |
+
"eval_f1": 0.5401449505661916,
|
| 490 |
+
"eval_loss": 0.9852494597434998,
|
| 491 |
+
"eval_precision": 0.6055202291285648,
|
| 492 |
+
"eval_recall": 0.576036866359447,
|
| 493 |
+
"eval_runtime": 0.8582,
|
| 494 |
+
"eval_samples_per_second": 252.863,
|
| 495 |
+
"eval_steps_per_second": 16.314,
|
| 496 |
+
"step": 490
|
| 497 |
+
},
|
| 498 |
+
{
|
| 499 |
+
"epoch": 12.232415902140673,
|
| 500 |
+
"grad_norm": 4.752162456512451,
|
| 501 |
+
"learning_rate": 2.1731987703006933e-05,
|
| 502 |
+
"loss": 1.0875,
|
| 503 |
+
"step": 500
|
| 504 |
+
},
|
| 505 |
+
{
|
| 506 |
+
"epoch": 12.477064220183486,
|
| 507 |
+
"grad_norm": 4.843075275421143,
|
| 508 |
+
"learning_rate": 2.1339273926110493e-05,
|
| 509 |
+
"loss": 1.1289,
|
| 510 |
+
"step": 510
|
| 511 |
+
},
|
| 512 |
+
{
|
| 513 |
+
"epoch": 12.7217125382263,
|
| 514 |
+
"grad_norm": 3.870483636856079,
|
| 515 |
+
"learning_rate": 2.0941196490587352e-05,
|
| 516 |
+
"loss": 1.0987,
|
| 517 |
+
"step": 520
|
| 518 |
+
},
|
| 519 |
+
{
|
| 520 |
+
"epoch": 12.966360856269112,
|
| 521 |
+
"grad_norm": 5.1215081214904785,
|
| 522 |
+
"learning_rate": 2.0538092209690267e-05,
|
| 523 |
+
"loss": 1.1289,
|
| 524 |
+
"step": 530
|
| 525 |
+
},
|
| 526 |
+
{
|
| 527 |
+
"epoch": 12.990825688073395,
|
| 528 |
+
"eval_accuracy": 0.5714285714285714,
|
| 529 |
+
"eval_f1": 0.53625493827214,
|
| 530 |
+
"eval_loss": 0.9554733037948608,
|
| 531 |
+
"eval_precision": 0.5409489632358654,
|
| 532 |
+
"eval_recall": 0.5714285714285714,
|
| 533 |
+
"eval_runtime": 0.8589,
|
| 534 |
+
"eval_samples_per_second": 252.652,
|
| 535 |
+
"eval_steps_per_second": 16.3,
|
| 536 |
+
"step": 531
|
| 537 |
+
},
|
| 538 |
+
{
|
| 539 |
+
"epoch": 13.211009174311927,
|
| 540 |
+
"grad_norm": 3.453106164932251,
|
| 541 |
+
"learning_rate": 2.0130302149885033e-05,
|
| 542 |
+
"loss": 1.1112,
|
| 543 |
+
"step": 540
|
| 544 |
+
},
|
| 545 |
+
{
|
| 546 |
+
"epoch": 13.45565749235474,
|
| 547 |
+
"grad_norm": 3.6579651832580566,
|
| 548 |
+
"learning_rate": 1.9718171342274207e-05,
|
| 549 |
+
"loss": 1.093,
|
| 550 |
+
"step": 550
|
| 551 |
+
},
|
| 552 |
+
{
|
| 553 |
+
"epoch": 13.700305810397554,
|
| 554 |
+
"grad_norm": 4.116721153259277,
|
| 555 |
+
"learning_rate": 1.9302048490666356e-05,
|
| 556 |
+
"loss": 1.071,
|
| 557 |
+
"step": 560
|
| 558 |
+
},
|
| 559 |
+
{
|
| 560 |
+
"epoch": 13.944954128440367,
|
| 561 |
+
"grad_norm": 4.801394939422607,
|
| 562 |
+
"learning_rate": 1.888228567653781e-05,
|
| 563 |
+
"loss": 1.1102,
|
| 564 |
+
"step": 570
|
| 565 |
+
},
|
| 566 |
+
{
|
| 567 |
+
"epoch": 13.99388379204893,
|
| 568 |
+
"eval_accuracy": 0.5990783410138248,
|
| 569 |
+
"eval_f1": 0.5795304519070373,
|
| 570 |
+
"eval_loss": 0.9438399076461792,
|
| 571 |
+
"eval_precision": 0.6032853066292203,
|
| 572 |
+
"eval_recall": 0.5990783410138248,
|
| 573 |
+
"eval_runtime": 0.8683,
|
| 574 |
+
"eval_samples_per_second": 249.915,
|
| 575 |
+
"eval_steps_per_second": 16.124,
|
| 576 |
+
"step": 572
|
| 577 |
+
},
|
| 578 |
+
{
|
| 579 |
+
"epoch": 14.18960244648318,
|
| 580 |
+
"grad_norm": 3.2803945541381836,
|
| 581 |
+
"learning_rate": 1.8459238061136604e-05,
|
| 582 |
+
"loss": 1.0885,
|
| 583 |
+
"step": 580
|
| 584 |
+
},
|
| 585 |
+
{
|
| 586 |
+
"epoch": 14.434250764525993,
|
| 587 |
+
"grad_norm": 4.159581661224365,
|
| 588 |
+
"learning_rate": 1.8033263584980572e-05,
|
| 589 |
+
"loss": 1.0843,
|
| 590 |
+
"step": 590
|
| 591 |
+
},
|
| 592 |
+
{
|
| 593 |
+
"epoch": 14.678899082568808,
|
| 594 |
+
"grad_norm": 4.556077480316162,
|
| 595 |
+
"learning_rate": 1.760472266500396e-05,
|
| 596 |
+
"loss": 1.1073,
|
| 597 |
+
"step": 600
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"epoch": 14.923547400611621,
|
| 601 |
+
"grad_norm": 5.622644901275635,
|
| 602 |
+
"learning_rate": 1.7173977889608698e-05,
|
| 603 |
+
"loss": 1.1011,
|
| 604 |
+
"step": 610
|
| 605 |
+
},
|
| 606 |
+
{
|
| 607 |
+
"epoch": 14.996941896024465,
|
| 608 |
+
"eval_accuracy": 0.5990783410138248,
|
| 609 |
+
"eval_f1": 0.5839986401752663,
|
| 610 |
+
"eval_loss": 0.9491886496543884,
|
| 611 |
+
"eval_precision": 0.6015877856086249,
|
| 612 |
+
"eval_recall": 0.5990783410138248,
|
| 613 |
+
"eval_runtime": 0.8608,
|
| 614 |
+
"eval_samples_per_second": 252.096,
|
| 615 |
+
"eval_steps_per_second": 16.264,
|
| 616 |
+
"step": 613
|
| 617 |
+
},
|
| 618 |
+
{
|
| 619 |
+
"epoch": 15.168195718654435,
|
| 620 |
+
"grad_norm": 4.210937976837158,
|
| 621 |
+
"learning_rate": 1.6741393711878455e-05,
|
| 622 |
+
"loss": 1.105,
|
| 623 |
+
"step": 620
|
| 624 |
+
},
|
| 625 |
+
{
|
| 626 |
+
"epoch": 15.412844036697248,
|
| 627 |
+
"grad_norm": 4.558620452880859,
|
| 628 |
+
"learning_rate": 1.6307336141214877e-05,
|
| 629 |
+
"loss": 1.1142,
|
| 630 |
+
"step": 630
|
| 631 |
+
},
|
| 632 |
+
{
|
| 633 |
+
"epoch": 15.65749235474006,
|
| 634 |
+
"grad_norm": 4.51144552230835,
|
| 635 |
+
"learning_rate": 1.587217243365714e-05,
|
| 636 |
+
"loss": 1.0468,
|
| 637 |
+
"step": 640
|
| 638 |
+
},
|
| 639 |
+
{
|
| 640 |
+
"epoch": 15.902140672782874,
|
| 641 |
+
"grad_norm": 4.054220199584961,
|
| 642 |
+
"learning_rate": 1.543627078114667e-05,
|
| 643 |
+
"loss": 1.1293,
|
| 644 |
+
"step": 650
|
| 645 |
+
},
|
| 646 |
+
{
|
| 647 |
+
"epoch": 16.0,
|
| 648 |
+
"eval_accuracy": 0.5714285714285714,
|
| 649 |
+
"eval_f1": 0.5547707796966923,
|
| 650 |
+
"eval_loss": 0.9825624823570251,
|
| 651 |
+
"eval_precision": 0.5999554049946036,
|
| 652 |
+
"eval_recall": 0.5714285714285714,
|
| 653 |
+
"eval_runtime": 0.886,
|
| 654 |
+
"eval_samples_per_second": 244.909,
|
| 655 |
+
"eval_steps_per_second": 15.801,
|
| 656 |
+
"step": 654
|
| 657 |
+
},
|
| 658 |
+
{
|
| 659 |
+
"epoch": 16.146788990825687,
|
| 660 |
+
"grad_norm": 4.0673298835754395,
|
| 661 |
+
"learning_rate": 1.5e-05,
|
| 662 |
+
"loss": 1.1229,
|
| 663 |
+
"step": 660
|
| 664 |
+
},
|
| 665 |
+
{
|
| 666 |
+
"epoch": 16.3914373088685,
|
| 667 |
+
"grad_norm": 4.635714530944824,
|
| 668 |
+
"learning_rate": 1.4563729218853329e-05,
|
| 669 |
+
"loss": 1.1104,
|
| 670 |
+
"step": 670
|
| 671 |
+
},
|
| 672 |
+
{
|
| 673 |
+
"epoch": 16.636085626911314,
|
| 674 |
+
"grad_norm": 5.1717610359191895,
|
| 675 |
+
"learning_rate": 1.4127827566342864e-05,
|
| 676 |
+
"loss": 1.0871,
|
| 677 |
+
"step": 680
|
| 678 |
+
},
|
| 679 |
+
{
|
| 680 |
+
"epoch": 16.88073394495413,
|
| 681 |
+
"grad_norm": 3.7032668590545654,
|
| 682 |
+
"learning_rate": 1.3692663858785127e-05,
|
| 683 |
+
"loss": 1.0706,
|
| 684 |
+
"step": 690
|
| 685 |
+
},
|
| 686 |
+
{
|
| 687 |
+
"epoch": 16.978593272171253,
|
| 688 |
+
"eval_accuracy": 0.5944700460829493,
|
| 689 |
+
"eval_f1": 0.5739258278528425,
|
| 690 |
+
"eval_loss": 0.9465323686599731,
|
| 691 |
+
"eval_precision": 0.6001352759137449,
|
| 692 |
+
"eval_recall": 0.5944700460829493,
|
| 693 |
+
"eval_runtime": 0.8837,
|
| 694 |
+
"eval_samples_per_second": 245.555,
|
| 695 |
+
"eval_steps_per_second": 15.842,
|
| 696 |
+
"step": 694
|
| 697 |
+
},
|
| 698 |
+
{
|
| 699 |
+
"epoch": 17.125382262996943,
|
| 700 |
+
"grad_norm": 3.981715440750122,
|
| 701 |
+
"learning_rate": 1.3258606288121545e-05,
|
| 702 |
+
"loss": 1.0666,
|
| 703 |
+
"step": 700
|
| 704 |
+
},
|
| 705 |
+
{
|
| 706 |
+
"epoch": 17.370030581039757,
|
| 707 |
+
"grad_norm": 4.0711846351623535,
|
| 708 |
+
"learning_rate": 1.2826022110391301e-05,
|
| 709 |
+
"loss": 1.0819,
|
| 710 |
+
"step": 710
|
| 711 |
+
},
|
| 712 |
+
{
|
| 713 |
+
"epoch": 17.61467889908257,
|
| 714 |
+
"grad_norm": 4.841401100158691,
|
| 715 |
+
"learning_rate": 1.2395277334996045e-05,
|
| 716 |
+
"loss": 1.0992,
|
| 717 |
+
"step": 720
|
| 718 |
+
},
|
| 719 |
+
{
|
| 720 |
+
"epoch": 17.859327217125383,
|
| 721 |
+
"grad_norm": 4.324009418487549,
|
| 722 |
+
"learning_rate": 1.1966736415019434e-05,
|
| 723 |
+
"loss": 1.0825,
|
| 724 |
+
"step": 730
|
| 725 |
+
},
|
| 726 |
+
{
|
| 727 |
+
"epoch": 17.98165137614679,
|
| 728 |
+
"eval_accuracy": 0.6082949308755761,
|
| 729 |
+
"eval_f1": 0.5860764206601137,
|
| 730 |
+
"eval_loss": 0.9267781972885132,
|
| 731 |
+
"eval_precision": 0.608336555917201,
|
| 732 |
+
"eval_recall": 0.6082949308755761,
|
| 733 |
+
"eval_runtime": 0.8665,
|
| 734 |
+
"eval_samples_per_second": 250.427,
|
| 735 |
+
"eval_steps_per_second": 16.157,
|
| 736 |
+
"step": 735
|
| 737 |
+
},
|
| 738 |
+
{
|
| 739 |
+
"epoch": 18.103975535168196,
|
| 740 |
+
"grad_norm": 5.315589427947998,
|
| 741 |
+
"learning_rate": 1.1540761938863397e-05,
|
| 742 |
+
"loss": 1.0897,
|
| 743 |
+
"step": 740
|
| 744 |
+
},
|
| 745 |
+
{
|
| 746 |
+
"epoch": 18.34862385321101,
|
| 747 |
+
"grad_norm": 5.192884922027588,
|
| 748 |
+
"learning_rate": 1.1117714323462188e-05,
|
| 749 |
+
"loss": 1.0724,
|
| 750 |
+
"step": 750
|
| 751 |
+
},
|
| 752 |
+
{
|
| 753 |
+
"epoch": 18.593272171253822,
|
| 754 |
+
"grad_norm": 4.687433242797852,
|
| 755 |
+
"learning_rate": 1.069795150933365e-05,
|
| 756 |
+
"loss": 1.079,
|
| 757 |
+
"step": 760
|
| 758 |
+
},
|
| 759 |
+
{
|
| 760 |
+
"epoch": 18.837920489296636,
|
| 761 |
+
"grad_norm": 5.24461555480957,
|
| 762 |
+
"learning_rate": 1.0281828657725798e-05,
|
| 763 |
+
"loss": 1.0989,
|
| 764 |
+
"step": 770
|
| 765 |
+
},
|
| 766 |
+
{
|
| 767 |
+
"epoch": 18.984709480122323,
|
| 768 |
+
"eval_accuracy": 0.6082949308755761,
|
| 769 |
+
"eval_f1": 0.5900226152184301,
|
| 770 |
+
"eval_loss": 0.9349210262298584,
|
| 771 |
+
"eval_precision": 0.616806148489978,
|
| 772 |
+
"eval_recall": 0.6082949308755761,
|
| 773 |
+
"eval_runtime": 0.8555,
|
| 774 |
+
"eval_samples_per_second": 253.66,
|
| 775 |
+
"eval_steps_per_second": 16.365,
|
| 776 |
+
"step": 776
|
| 777 |
+
},
|
| 778 |
+
{
|
| 779 |
+
"epoch": 19.08256880733945,
|
| 780 |
+
"grad_norm": 4.098168849945068,
|
| 781 |
+
"learning_rate": 9.86969785011497e-06,
|
| 782 |
+
"loss": 1.0785,
|
| 783 |
+
"step": 780
|
| 784 |
+
},
|
| 785 |
+
{
|
| 786 |
+
"epoch": 19.327217125382262,
|
| 787 |
+
"grad_norm": 4.730178356170654,
|
| 788 |
+
"learning_rate": 9.461907790309735e-06,
|
| 789 |
+
"loss": 1.069,
|
| 790 |
+
"step": 790
|
| 791 |
+
},
|
| 792 |
+
{
|
| 793 |
+
"epoch": 19.571865443425075,
|
| 794 |
+
"grad_norm": 5.353407859802246,
|
| 795 |
+
"learning_rate": 9.058803509412647e-06,
|
| 796 |
+
"loss": 1.0864,
|
| 797 |
+
"step": 800
|
| 798 |
+
},
|
| 799 |
+
{
|
| 800 |
+
"epoch": 19.81651376146789,
|
| 801 |
+
"grad_norm": 5.941184043884277,
|
| 802 |
+
"learning_rate": 8.66072607388951e-06,
|
| 803 |
+
"loss": 1.0541,
|
| 804 |
+
"step": 810
|
| 805 |
+
},
|
| 806 |
+
{
|
| 807 |
+
"epoch": 19.98776758409786,
|
| 808 |
+
"eval_accuracy": 0.6175115207373272,
|
| 809 |
+
"eval_f1": 0.6103037127467525,
|
| 810 |
+
"eval_loss": 0.9407837986946106,
|
| 811 |
+
"eval_precision": 0.6331867057673509,
|
| 812 |
+
"eval_recall": 0.6175115207373272,
|
| 813 |
+
"eval_runtime": 0.8803,
|
| 814 |
+
"eval_samples_per_second": 246.5,
|
| 815 |
+
"eval_steps_per_second": 15.903,
|
| 816 |
+
"step": 817
|
| 817 |
+
},
|
| 818 |
+
{
|
| 819 |
+
"epoch": 20.061162079510705,
|
| 820 |
+
"grad_norm": 5.963148593902588,
|
| 821 |
+
"learning_rate": 8.268012296993067e-06,
|
| 822 |
+
"loss": 1.0919,
|
| 823 |
+
"step": 820
|
| 824 |
+
},
|
| 825 |
+
{
|
| 826 |
+
"epoch": 20.30581039755352,
|
| 827 |
+
"grad_norm": 5.1851606369018555,
|
| 828 |
+
"learning_rate": 7.880994453785394e-06,
|
| 829 |
+
"loss": 1.0722,
|
| 830 |
+
"step": 830
|
| 831 |
+
},
|
| 832 |
+
{
|
| 833 |
+
"epoch": 20.55045871559633,
|
| 834 |
+
"grad_norm": 4.50276517868042,
|
| 835 |
+
"learning_rate": 7.500000000000004e-06,
|
| 836 |
+
"loss": 1.0523,
|
| 837 |
+
"step": 840
|
| 838 |
+
},
|
| 839 |
+
{
|
| 840 |
+
"epoch": 20.795107033639145,
|
| 841 |
+
"grad_norm": 4.3782453536987305,
|
| 842 |
+
"learning_rate": 7.1253512949815995e-06,
|
| 843 |
+
"loss": 1.0883,
|
| 844 |
+
"step": 850
|
| 845 |
+
},
|
| 846 |
+
{
|
| 847 |
+
"epoch": 20.990825688073393,
|
| 848 |
+
"eval_accuracy": 0.6221198156682027,
|
| 849 |
+
"eval_f1": 0.6115919254751536,
|
| 850 |
+
"eval_loss": 0.9107956886291504,
|
| 851 |
+
"eval_precision": 0.616963195553811,
|
| 852 |
+
"eval_recall": 0.6221198156682027,
|
| 853 |
+
"eval_runtime": 0.8511,
|
| 854 |
+
"eval_samples_per_second": 254.955,
|
| 855 |
+
"eval_steps_per_second": 16.449,
|
| 856 |
+
"step": 858
|
| 857 |
+
},
|
| 858 |
+
{
|
| 859 |
+
"epoch": 21.039755351681958,
|
| 860 |
+
"grad_norm": 5.798299312591553,
|
| 861 |
+
"learning_rate": 6.75736532893791e-06,
|
| 862 |
+
"loss": 1.0634,
|
| 863 |
+
"step": 860
|
| 864 |
+
},
|
| 865 |
+
{
|
| 866 |
+
"epoch": 21.28440366972477,
|
| 867 |
+
"grad_norm": 4.693358421325684,
|
| 868 |
+
"learning_rate": 6.3963534547343126e-06,
|
| 869 |
+
"loss": 1.0804,
|
| 870 |
+
"step": 870
|
| 871 |
+
},
|
| 872 |
+
{
|
| 873 |
+
"epoch": 21.529051987767584,
|
| 874 |
+
"grad_norm": 5.018470764160156,
|
| 875 |
+
"learning_rate": 6.0426211244582105e-06,
|
| 876 |
+
"loss": 1.0485,
|
| 877 |
+
"step": 880
|
| 878 |
+
},
|
| 879 |
+
{
|
| 880 |
+
"epoch": 21.773700305810397,
|
| 881 |
+
"grad_norm": 4.43956995010376,
|
| 882 |
+
"learning_rate": 5.696467630976101e-06,
|
| 883 |
+
"loss": 1.0828,
|
| 884 |
+
"step": 890
|
| 885 |
+
},
|
| 886 |
+
{
|
| 887 |
+
"epoch": 21.99388379204893,
|
| 888 |
+
"eval_accuracy": 0.5990783410138248,
|
| 889 |
+
"eval_f1": 0.5912505275453264,
|
| 890 |
+
"eval_loss": 0.9411961436271667,
|
| 891 |
+
"eval_precision": 0.6205200942687754,
|
| 892 |
+
"eval_recall": 0.5990783410138248,
|
| 893 |
+
"eval_runtime": 0.8609,
|
| 894 |
+
"eval_samples_per_second": 252.076,
|
| 895 |
+
"eval_steps_per_second": 16.263,
|
| 896 |
+
"step": 899
|
| 897 |
+
},
|
| 898 |
+
{
|
| 899 |
+
"epoch": 22.01834862385321,
|
| 900 |
+
"grad_norm": 4.936504364013672,
|
| 901 |
+
"learning_rate": 5.3581858547019095e-06,
|
| 902 |
+
"loss": 1.0715,
|
| 903 |
+
"step": 900
|
| 904 |
+
},
|
| 905 |
+
{
|
| 906 |
+
"epoch": 22.262996941896024,
|
| 907 |
+
"grad_norm": 5.165542125701904,
|
| 908 |
+
"learning_rate": 5.0280620157909316e-06,
|
| 909 |
+
"loss": 1.06,
|
| 910 |
+
"step": 910
|
| 911 |
+
},
|
| 912 |
+
{
|
| 913 |
+
"epoch": 22.507645259938837,
|
| 914 |
+
"grad_norm": 4.64872407913208,
|
| 915 |
+
"learning_rate": 4.706375431968998e-06,
|
| 916 |
+
"loss": 1.0631,
|
| 917 |
+
"step": 920
|
| 918 |
+
},
|
| 919 |
+
{
|
| 920 |
+
"epoch": 22.75229357798165,
|
| 921 |
+
"grad_norm": 4.921236991882324,
|
| 922 |
+
"learning_rate": 4.393398282201788e-06,
|
| 923 |
+
"loss": 1.0601,
|
| 924 |
+
"step": 930
|
| 925 |
+
},
|
| 926 |
+
{
|
| 927 |
+
"epoch": 22.996941896024463,
|
| 928 |
+
"grad_norm": 4.369044780731201,
|
| 929 |
+
"learning_rate": 4.089395376404269e-06,
|
| 930 |
+
"loss": 1.0492,
|
| 931 |
+
"step": 940
|
| 932 |
+
},
|
| 933 |
+
{
|
| 934 |
+
"epoch": 22.996941896024463,
|
| 935 |
+
"eval_accuracy": 0.6129032258064516,
|
| 936 |
+
"eval_f1": 0.6002888307021196,
|
| 937 |
+
"eval_loss": 0.9262792468070984,
|
| 938 |
+
"eval_precision": 0.6441948258190624,
|
| 939 |
+
"eval_recall": 0.6129032258064516,
|
| 940 |
+
"eval_runtime": 0.8685,
|
| 941 |
+
"eval_samples_per_second": 249.843,
|
| 942 |
+
"eval_steps_per_second": 16.119,
|
| 943 |
+
"step": 940
|
| 944 |
+
},
|
| 945 |
+
{
|
| 946 |
+
"epoch": 23.24159021406728,
|
| 947 |
+
"grad_norm": 5.06370735168457,
|
| 948 |
+
"learning_rate": 3.7946239313850626e-06,
|
| 949 |
+
"loss": 1.0591,
|
| 950 |
+
"step": 950
|
| 951 |
+
},
|
| 952 |
+
{
|
| 953 |
+
"epoch": 23.486238532110093,
|
| 954 |
+
"grad_norm": 5.190964698791504,
|
| 955 |
+
"learning_rate": 3.5093333532153316e-06,
|
| 956 |
+
"loss": 1.0401,
|
| 957 |
+
"step": 960
|
| 958 |
+
},
|
| 959 |
+
{
|
| 960 |
+
"epoch": 23.730886850152906,
|
| 961 |
+
"grad_norm": 6.742732524871826,
|
| 962 |
+
"learning_rate": 3.2337650262063646e-06,
|
| 963 |
+
"loss": 1.0891,
|
| 964 |
+
"step": 970
|
| 965 |
+
},
|
| 966 |
+
{
|
| 967 |
+
"epoch": 23.97553516819572,
|
| 968 |
+
"grad_norm": 4.73397159576416,
|
| 969 |
+
"learning_rate": 2.9681521086743426e-06,
|
| 970 |
+
"loss": 1.0486,
|
| 971 |
+
"step": 980
|
| 972 |
+
},
|
| 973 |
+
{
|
| 974 |
+
"epoch": 24.0,
|
| 975 |
+
"eval_accuracy": 0.6129032258064516,
|
| 976 |
+
"eval_f1": 0.6069089976834864,
|
| 977 |
+
"eval_loss": 0.9253664016723633,
|
| 978 |
+
"eval_precision": 0.6137060060993463,
|
| 979 |
+
"eval_recall": 0.6129032258064516,
|
| 980 |
+
"eval_runtime": 0.883,
|
| 981 |
+
"eval_samples_per_second": 245.748,
|
| 982 |
+
"eval_steps_per_second": 15.855,
|
| 983 |
+
"step": 981
|
| 984 |
+
},
|
| 985 |
+
{
|
| 986 |
+
"epoch": 24.220183486238533,
|
| 987 |
+
"grad_norm": 4.736702919006348,
|
| 988 |
+
"learning_rate": 2.7127193356651214e-06,
|
| 989 |
+
"loss": 1.0439,
|
| 990 |
+
"step": 990
|
| 991 |
+
},
|
| 992 |
+
{
|
| 993 |
+
"epoch": 24.464831804281346,
|
| 994 |
+
"grad_norm": 4.618147373199463,
|
| 995 |
+
"learning_rate": 2.467682828805956e-06,
|
| 996 |
+
"loss": 1.0428,
|
| 997 |
+
"step": 1000
|
| 998 |
+
},
|
| 999 |
+
{
|
| 1000 |
+
"epoch": 24.70948012232416,
|
| 1001 |
+
"grad_norm": 5.107517719268799,
|
| 1002 |
+
"learning_rate": 2.233249913445004e-06,
|
| 1003 |
+
"loss": 1.0535,
|
| 1004 |
+
"step": 1010
|
| 1005 |
+
},
|
| 1006 |
+
{
|
| 1007 |
+
"epoch": 24.954128440366972,
|
| 1008 |
+
"grad_norm": 5.802303314208984,
|
| 1009 |
+
"learning_rate": 2.0096189432334194e-06,
|
| 1010 |
+
"loss": 1.0648,
|
| 1011 |
+
"step": 1020
|
| 1012 |
+
},
|
| 1013 |
+
{
|
| 1014 |
+
"epoch": 24.978593272171253,
|
| 1015 |
+
"eval_accuracy": 0.5990783410138248,
|
| 1016 |
+
"eval_f1": 0.5880284966872402,
|
| 1017 |
+
"eval_loss": 0.9164543747901917,
|
| 1018 |
+
"eval_precision": 0.6001504954993327,
|
| 1019 |
+
"eval_recall": 0.5990783410138248,
|
| 1020 |
+
"eval_runtime": 0.8507,
|
| 1021 |
+
"eval_samples_per_second": 255.079,
|
| 1022 |
+
"eval_steps_per_second": 16.457,
|
| 1023 |
+
"step": 1021
|
| 1024 |
+
},
|
| 1025 |
+
{
|
| 1026 |
+
"epoch": 25.198776758409785,
|
| 1027 |
+
"grad_norm": 4.453035831451416,
|
| 1028 |
+
"learning_rate": 1.7969791322983354e-06,
|
| 1029 |
+
"loss": 1.0255,
|
| 1030 |
+
"step": 1030
|
| 1031 |
+
},
|
| 1032 |
+
{
|
| 1033 |
+
"epoch": 25.4434250764526,
|
| 1034 |
+
"grad_norm": 5.172535419464111,
|
| 1035 |
+
"learning_rate": 1.5955103951488177e-06,
|
| 1036 |
+
"loss": 1.0636,
|
| 1037 |
+
"step": 1040
|
| 1038 |
+
},
|
| 1039 |
+
{
|
| 1040 |
+
"epoch": 25.68807339449541,
|
| 1041 |
+
"grad_norm": 4.380440711975098,
|
| 1042 |
+
"learning_rate": 1.4053831944502509e-06,
|
| 1043 |
+
"loss": 1.0454,
|
| 1044 |
+
"step": 1050
|
| 1045 |
+
},
|
| 1046 |
+
{
|
| 1047 |
+
"epoch": 25.932721712538225,
|
| 1048 |
+
"grad_norm": 4.616762638092041,
|
| 1049 |
+
"learning_rate": 1.2267583967958918e-06,
|
| 1050 |
+
"loss": 1.079,
|
| 1051 |
+
"step": 1060
|
| 1052 |
+
},
|
| 1053 |
+
{
|
| 1054 |
+
"epoch": 25.98165137614679,
|
| 1055 |
+
"eval_accuracy": 0.5898617511520737,
|
| 1056 |
+
"eval_f1": 0.5794668921596123,
|
| 1057 |
+
"eval_loss": 0.9294114112854004,
|
| 1058 |
+
"eval_precision": 0.6006132884013068,
|
| 1059 |
+
"eval_recall": 0.5898617511520737,
|
| 1060 |
+
"eval_runtime": 0.8875,
|
| 1061 |
+
"eval_samples_per_second": 244.511,
|
| 1062 |
+
"eval_steps_per_second": 15.775,
|
| 1063 |
+
"step": 1062
|
| 1064 |
+
},
|
| 1065 |
+
{
|
| 1066 |
+
"epoch": 26.17737003058104,
|
| 1067 |
+
"grad_norm": 4.948554992675781,
|
| 1068 |
+
"learning_rate": 1.059787136597662e-06,
|
| 1069 |
+
"loss": 1.0615,
|
| 1070 |
+
"step": 1070
|
| 1071 |
+
},
|
| 1072 |
+
{
|
| 1073 |
+
"epoch": 26.422018348623855,
|
| 1074 |
+
"grad_norm": 5.786351680755615,
|
| 1075 |
+
"learning_rate": 9.046106882113753e-07,
|
| 1076 |
+
"loss": 1.0472,
|
| 1077 |
+
"step": 1080
|
| 1078 |
+
},
|
| 1079 |
+
{
|
| 1080 |
+
"epoch": 26.666666666666668,
|
| 1081 |
+
"grad_norm": 4.639774322509766,
|
| 1082 |
+
"learning_rate": 7.613603464044916e-07,
|
| 1083 |
+
"loss": 1.0473,
|
| 1084 |
+
"step": 1090
|
| 1085 |
+
},
|
| 1086 |
+
{
|
| 1087 |
+
"epoch": 26.91131498470948,
|
| 1088 |
+
"grad_norm": 5.199443340301514,
|
| 1089 |
+
"learning_rate": 6.301573152676665e-07,
|
| 1090 |
+
"loss": 1.0459,
|
| 1091 |
+
"step": 1100
|
| 1092 |
+
},
|
| 1093 |
+
{
|
| 1094 |
+
"epoch": 26.984709480122323,
|
| 1095 |
+
"eval_accuracy": 0.6082949308755761,
|
| 1096 |
+
"eval_f1": 0.5953286856512663,
|
| 1097 |
+
"eval_loss": 0.923698902130127,
|
| 1098 |
+
"eval_precision": 0.6167649855641182,
|
| 1099 |
+
"eval_recall": 0.6082949308755761,
|
| 1100 |
+
"eval_runtime": 0.8646,
|
| 1101 |
+
"eval_samples_per_second": 250.99,
|
| 1102 |
+
"eval_steps_per_second": 16.193,
|
| 1103 |
+
"step": 1103
|
| 1104 |
+
},
|
| 1105 |
+
{
|
| 1106 |
+
"epoch": 27.155963302752294,
|
| 1107 |
+
"grad_norm": 5.868374824523926,
|
| 1108 |
+
"learning_rate": 5.11112605663977e-07,
|
| 1109 |
+
"loss": 1.0628,
|
| 1110 |
+
"step": 1110
|
| 1111 |
+
},
|
| 1112 |
+
{
|
| 1113 |
+
"epoch": 27.400611620795107,
|
| 1114 |
+
"grad_norm": 4.410027980804443,
|
| 1115 |
+
"learning_rate": 4.043269413026429e-07,
|
| 1116 |
+
"loss": 1.0471,
|
| 1117 |
+
"step": 1120
|
| 1118 |
+
},
|
| 1119 |
+
{
|
| 1120 |
+
"epoch": 27.64525993883792,
|
| 1121 |
+
"grad_norm": 4.9952192306518555,
|
| 1122 |
+
"learning_rate": 3.0989067351672783e-07,
|
| 1123 |
+
"loss": 1.0557,
|
| 1124 |
+
"step": 1130
|
| 1125 |
+
},
|
| 1126 |
+
{
|
| 1127 |
+
"epoch": 27.889908256880734,
|
| 1128 |
+
"grad_norm": 4.651206970214844,
|
| 1129 |
+
"learning_rate": 2.278837048168797e-07,
|
| 1130 |
+
"loss": 1.057,
|
| 1131 |
+
"step": 1140
|
| 1132 |
+
},
|
| 1133 |
+
{
|
| 1134 |
+
"epoch": 27.98776758409786,
|
| 1135 |
+
"eval_accuracy": 0.6082949308755761,
|
| 1136 |
+
"eval_f1": 0.5953286856512663,
|
| 1137 |
+
"eval_loss": 0.9232858419418335,
|
| 1138 |
+
"eval_precision": 0.6167649855641182,
|
| 1139 |
+
"eval_recall": 0.6082949308755761,
|
| 1140 |
+
"eval_runtime": 0.8831,
|
| 1141 |
+
"eval_samples_per_second": 245.732,
|
| 1142 |
+
"eval_steps_per_second": 15.854,
|
| 1143 |
+
"step": 1144
|
| 1144 |
+
},
|
| 1145 |
+
{
|
| 1146 |
+
"epoch": 28.134556574923547,
|
| 1147 |
+
"grad_norm": 4.553572177886963,
|
| 1148 |
+
"learning_rate": 1.5837542128583294e-07,
|
| 1149 |
+
"loss": 1.0341,
|
| 1150 |
+
"step": 1150
|
| 1151 |
+
},
|
| 1152 |
+
{
|
| 1153 |
+
"epoch": 28.37920489296636,
|
| 1154 |
+
"grad_norm": 5.814303398132324,
|
| 1155 |
+
"learning_rate": 1.0142463387085465e-07,
|
| 1156 |
+
"loss": 1.0547,
|
| 1157 |
+
"step": 1160
|
| 1158 |
+
},
|
| 1159 |
+
{
|
| 1160 |
+
"epoch": 28.623853211009173,
|
| 1161 |
+
"grad_norm": 4.839509963989258,
|
| 1162 |
+
"learning_rate": 5.7079528623816824e-08,
|
| 1163 |
+
"loss": 1.0585,
|
| 1164 |
+
"step": 1170
|
| 1165 |
+
},
|
| 1166 |
+
{
|
| 1167 |
+
"epoch": 28.868501529051986,
|
| 1168 |
+
"grad_norm": 4.723291873931885,
|
| 1169 |
+
"learning_rate": 2.5377625930977367e-08,
|
| 1170 |
+
"loss": 1.0496,
|
| 1171 |
+
"step": 1180
|
| 1172 |
+
},
|
| 1173 |
+
{
|
| 1174 |
+
"epoch": 28.990825688073393,
|
| 1175 |
+
"eval_accuracy": 0.5990783410138248,
|
| 1176 |
+
"eval_f1": 0.5874155589819042,
|
| 1177 |
+
"eval_loss": 0.923707902431488,
|
| 1178 |
+
"eval_precision": 0.6076854618844824,
|
| 1179 |
+
"eval_recall": 0.5990783410138248,
|
| 1180 |
+
"eval_runtime": 0.8527,
|
| 1181 |
+
"eval_samples_per_second": 254.495,
|
| 1182 |
+
"eval_steps_per_second": 16.419,
|
| 1183 |
+
"step": 1185
|
| 1184 |
+
},
|
| 1185 |
+
{
|
| 1186 |
+
"epoch": 29.1131498470948,
|
| 1187 |
+
"grad_norm": 4.5172576904296875,
|
| 1188 |
+
"learning_rate": 6.345748766991011e-09,
|
| 1189 |
+
"loss": 1.0385,
|
| 1190 |
+
"step": 1190
|
| 1191 |
+
},
|
| 1192 |
+
{
|
| 1193 |
+
"epoch": 29.357798165137616,
|
| 1194 |
+
"grad_norm": 4.991288661956787,
|
| 1195 |
+
"learning_rate": 0.0,
|
| 1196 |
+
"loss": 1.0509,
|
| 1197 |
+
"step": 1200
|
| 1198 |
+
},
|
| 1199 |
+
{
|
| 1200 |
+
"epoch": 29.357798165137616,
|
| 1201 |
+
"eval_accuracy": 0.5990783410138248,
|
| 1202 |
+
"eval_f1": 0.5874155589819042,
|
| 1203 |
+
"eval_loss": 0.9237886071205139,
|
| 1204 |
+
"eval_precision": 0.6076854618844824,
|
| 1205 |
+
"eval_recall": 0.5990783410138248,
|
| 1206 |
+
"eval_runtime": 0.8997,
|
| 1207 |
+
"eval_samples_per_second": 241.202,
|
| 1208 |
+
"eval_steps_per_second": 15.561,
|
| 1209 |
+
"step": 1200
|
| 1210 |
+
},
|
| 1211 |
+
{
|
| 1212 |
+
"epoch": 29.357798165137616,
|
| 1213 |
+
"step": 1200,
|
| 1214 |
+
"total_flos": 3.8130472219998413e+18,
|
| 1215 |
+
"train_loss": 1.1265972677866618,
|
| 1216 |
+
"train_runtime": 2449.5651,
|
| 1217 |
+
"train_samples_per_second": 63.991,
|
| 1218 |
+
"train_steps_per_second": 0.49
|
| 1219 |
+
}
|
| 1220 |
+
],
|
| 1221 |
+
"logging_steps": 10,
|
| 1222 |
+
"max_steps": 1200,
|
| 1223 |
+
"num_input_tokens_seen": 0,
|
| 1224 |
+
"num_train_epochs": 30,
|
| 1225 |
+
"save_steps": 500,
|
| 1226 |
+
"stateful_callbacks": {
|
| 1227 |
+
"TrainerControl": {
|
| 1228 |
+
"args": {
|
| 1229 |
+
"should_epoch_stop": false,
|
| 1230 |
+
"should_evaluate": false,
|
| 1231 |
+
"should_log": false,
|
| 1232 |
+
"should_save": true,
|
| 1233 |
+
"should_training_stop": true
|
| 1234 |
+
},
|
| 1235 |
+
"attributes": {}
|
| 1236 |
+
}
|
| 1237 |
+
},
|
| 1238 |
+
"total_flos": 3.8130472219998413e+18,
|
| 1239 |
+
"train_batch_size": 16,
|
| 1240 |
+
"trial_name": null,
|
| 1241 |
+
"trial_params": null
|
| 1242 |
+
}
|