Commit
•
b720887
1
Parent(s):
a7cf66a
End of training
Browse files- README.md +4 -4
- all_results.json +16 -0
- eval_results.json +11 -0
- train_results.json +8 -0
- trainer_state.json +1459 -0
README.md
CHANGED
|
@@ -23,11 +23,11 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 23 |
|
| 24 |
This model is a fine-tuned version of [google/vit-base-patch16-224-in21k](https://huggingface.co/google/vit-base-patch16-224-in21k) on the medmnist-v2 dataset.
|
| 25 |
It achieves the following results on the evaluation set:
|
| 26 |
-
- Loss: 0.
|
| 27 |
- Accuracy: 0.9790
|
| 28 |
-
- Precision: 0.
|
| 29 |
-
- Recall: 0.
|
| 30 |
-
- F1: 0.
|
| 31 |
|
| 32 |
## Model description
|
| 33 |
|
|
|
|
| 23 |
|
| 24 |
This model is a fine-tuned version of [google/vit-base-patch16-224-in21k](https://huggingface.co/google/vit-base-patch16-224-in21k) on the medmnist-v2 dataset.
|
| 25 |
It achieves the following results on the evaluation set:
|
| 26 |
+
- Loss: 0.0692
|
| 27 |
- Accuracy: 0.9790
|
| 28 |
+
- Precision: 0.9772
|
| 29 |
+
- Recall: 0.9785
|
| 30 |
+
- F1: 0.9778
|
| 31 |
|
| 32 |
## Model description
|
| 33 |
|
all_results.json
ADDED
|
@@ -0,0 +1,16 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 10.0,
|
| 3 |
+
"eval_accuracy": 0.9789535223618825,
|
| 4 |
+
"eval_f1": 0.9778395609614629,
|
| 5 |
+
"eval_loss": 0.06918257474899292,
|
| 6 |
+
"eval_precision": 0.9772213544264792,
|
| 7 |
+
"eval_recall": 0.9785446056392397,
|
| 8 |
+
"eval_runtime": 18.1272,
|
| 9 |
+
"eval_samples_per_second": 188.722,
|
| 10 |
+
"eval_steps_per_second": 11.805,
|
| 11 |
+
"total_flos": 9.332136680499118e+18,
|
| 12 |
+
"train_loss": 0.29726991015959553,
|
| 13 |
+
"train_runtime": 1395.7704,
|
| 14 |
+
"train_samples_per_second": 85.68,
|
| 15 |
+
"train_steps_per_second": 1.34
|
| 16 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,11 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 10.0,
|
| 3 |
+
"eval_accuracy": 0.9789535223618825,
|
| 4 |
+
"eval_f1": 0.9778395609614629,
|
| 5 |
+
"eval_loss": 0.06918257474899292,
|
| 6 |
+
"eval_precision": 0.9772213544264792,
|
| 7 |
+
"eval_recall": 0.9785446056392397,
|
| 8 |
+
"eval_runtime": 18.1272,
|
| 9 |
+
"eval_samples_per_second": 188.722,
|
| 10 |
+
"eval_steps_per_second": 11.805
|
| 11 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 10.0,
|
| 3 |
+
"total_flos": 9.332136680499118e+18,
|
| 4 |
+
"train_loss": 0.29726991015959553,
|
| 5 |
+
"train_runtime": 1395.7704,
|
| 6 |
+
"train_samples_per_second": 85.68,
|
| 7 |
+
"train_steps_per_second": 1.34
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,1459 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.9789719626168224,
|
| 3 |
+
"best_model_checkpoint": "vit-base-patch16-224-in21k-finetuned-lora-medmnistv2/checkpoint-1870",
|
| 4 |
+
"epoch": 10.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 1870,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.05,
|
| 13 |
+
"grad_norm": 0.9260491132736206,
|
| 14 |
+
"learning_rate": 0.004973262032085562,
|
| 15 |
+
"loss": 1.5983,
|
| 16 |
+
"step": 10
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.11,
|
| 20 |
+
"grad_norm": 1.1307735443115234,
|
| 21 |
+
"learning_rate": 0.004946524064171123,
|
| 22 |
+
"loss": 0.9417,
|
| 23 |
+
"step": 20
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.16,
|
| 27 |
+
"grad_norm": 0.9537946581840515,
|
| 28 |
+
"learning_rate": 0.004919786096256685,
|
| 29 |
+
"loss": 0.7642,
|
| 30 |
+
"step": 30
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.21,
|
| 34 |
+
"grad_norm": 0.8597701191902161,
|
| 35 |
+
"learning_rate": 0.004893048128342246,
|
| 36 |
+
"loss": 0.6992,
|
| 37 |
+
"step": 40
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.27,
|
| 41 |
+
"grad_norm": 1.104675531387329,
|
| 42 |
+
"learning_rate": 0.004866310160427808,
|
| 43 |
+
"loss": 0.627,
|
| 44 |
+
"step": 50
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.32,
|
| 48 |
+
"grad_norm": 0.846555233001709,
|
| 49 |
+
"learning_rate": 0.004839572192513369,
|
| 50 |
+
"loss": 0.5047,
|
| 51 |
+
"step": 60
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.37,
|
| 55 |
+
"grad_norm": 1.423182487487793,
|
| 56 |
+
"learning_rate": 0.004812834224598931,
|
| 57 |
+
"loss": 0.5431,
|
| 58 |
+
"step": 70
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.43,
|
| 62 |
+
"grad_norm": 0.8424627780914307,
|
| 63 |
+
"learning_rate": 0.004786096256684492,
|
| 64 |
+
"loss": 0.5962,
|
| 65 |
+
"step": 80
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.48,
|
| 69 |
+
"grad_norm": 0.6608781814575195,
|
| 70 |
+
"learning_rate": 0.004759358288770054,
|
| 71 |
+
"loss": 0.4084,
|
| 72 |
+
"step": 90
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.53,
|
| 76 |
+
"grad_norm": 1.130247712135315,
|
| 77 |
+
"learning_rate": 0.004732620320855615,
|
| 78 |
+
"loss": 0.4932,
|
| 79 |
+
"step": 100
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.59,
|
| 83 |
+
"grad_norm": 0.6054658889770508,
|
| 84 |
+
"learning_rate": 0.004705882352941177,
|
| 85 |
+
"loss": 0.4684,
|
| 86 |
+
"step": 110
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.64,
|
| 90 |
+
"grad_norm": 0.8725093603134155,
|
| 91 |
+
"learning_rate": 0.004679144385026738,
|
| 92 |
+
"loss": 0.4429,
|
| 93 |
+
"step": 120
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.7,
|
| 97 |
+
"grad_norm": 0.6343618035316467,
|
| 98 |
+
"learning_rate": 0.0046524064171123,
|
| 99 |
+
"loss": 0.3952,
|
| 100 |
+
"step": 130
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 0.75,
|
| 104 |
+
"grad_norm": 0.9175045490264893,
|
| 105 |
+
"learning_rate": 0.0046256684491978615,
|
| 106 |
+
"loss": 0.4592,
|
| 107 |
+
"step": 140
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.8,
|
| 111 |
+
"grad_norm": 1.0295114517211914,
|
| 112 |
+
"learning_rate": 0.004598930481283423,
|
| 113 |
+
"loss": 0.4212,
|
| 114 |
+
"step": 150
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.86,
|
| 118 |
+
"grad_norm": 0.4232007563114166,
|
| 119 |
+
"learning_rate": 0.004572192513368984,
|
| 120 |
+
"loss": 0.4165,
|
| 121 |
+
"step": 160
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.91,
|
| 125 |
+
"grad_norm": 1.18360435962677,
|
| 126 |
+
"learning_rate": 0.00454812834224599,
|
| 127 |
+
"loss": 0.4245,
|
| 128 |
+
"step": 170
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.96,
|
| 132 |
+
"grad_norm": 0.7265322804450989,
|
| 133 |
+
"learning_rate": 0.004521390374331551,
|
| 134 |
+
"loss": 0.4059,
|
| 135 |
+
"step": 180
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 1.0,
|
| 139 |
+
"eval_accuracy": 0.9310747663551402,
|
| 140 |
+
"eval_f1": 0.9201346862223367,
|
| 141 |
+
"eval_loss": 0.18775394558906555,
|
| 142 |
+
"eval_precision": 0.913178148427007,
|
| 143 |
+
"eval_recall": 0.9327948208695145,
|
| 144 |
+
"eval_runtime": 9.5068,
|
| 145 |
+
"eval_samples_per_second": 180.082,
|
| 146 |
+
"eval_steps_per_second": 11.255,
|
| 147 |
+
"step": 187
|
| 148 |
+
},
|
| 149 |
+
{
|
| 150 |
+
"epoch": 1.02,
|
| 151 |
+
"grad_norm": 1.179917335510254,
|
| 152 |
+
"learning_rate": 0.004494652406417113,
|
| 153 |
+
"loss": 0.3646,
|
| 154 |
+
"step": 190
|
| 155 |
+
},
|
| 156 |
+
{
|
| 157 |
+
"epoch": 1.07,
|
| 158 |
+
"grad_norm": 1.1189391613006592,
|
| 159 |
+
"learning_rate": 0.004467914438502674,
|
| 160 |
+
"loss": 0.4339,
|
| 161 |
+
"step": 200
|
| 162 |
+
},
|
| 163 |
+
{
|
| 164 |
+
"epoch": 1.12,
|
| 165 |
+
"grad_norm": 0.8059839010238647,
|
| 166 |
+
"learning_rate": 0.004441176470588235,
|
| 167 |
+
"loss": 0.373,
|
| 168 |
+
"step": 210
|
| 169 |
+
},
|
| 170 |
+
{
|
| 171 |
+
"epoch": 1.18,
|
| 172 |
+
"grad_norm": 1.5934990644454956,
|
| 173 |
+
"learning_rate": 0.004414438502673797,
|
| 174 |
+
"loss": 0.4089,
|
| 175 |
+
"step": 220
|
| 176 |
+
},
|
| 177 |
+
{
|
| 178 |
+
"epoch": 1.23,
|
| 179 |
+
"grad_norm": 0.5738559365272522,
|
| 180 |
+
"learning_rate": 0.004387700534759359,
|
| 181 |
+
"loss": 0.4181,
|
| 182 |
+
"step": 230
|
| 183 |
+
},
|
| 184 |
+
{
|
| 185 |
+
"epoch": 1.28,
|
| 186 |
+
"grad_norm": 1.0053284168243408,
|
| 187 |
+
"learning_rate": 0.00436096256684492,
|
| 188 |
+
"loss": 0.354,
|
| 189 |
+
"step": 240
|
| 190 |
+
},
|
| 191 |
+
{
|
| 192 |
+
"epoch": 1.34,
|
| 193 |
+
"grad_norm": 0.6736829280853271,
|
| 194 |
+
"learning_rate": 0.004334224598930481,
|
| 195 |
+
"loss": 0.2862,
|
| 196 |
+
"step": 250
|
| 197 |
+
},
|
| 198 |
+
{
|
| 199 |
+
"epoch": 1.39,
|
| 200 |
+
"grad_norm": 0.7684084177017212,
|
| 201 |
+
"learning_rate": 0.0043074866310160425,
|
| 202 |
+
"loss": 0.3533,
|
| 203 |
+
"step": 260
|
| 204 |
+
},
|
| 205 |
+
{
|
| 206 |
+
"epoch": 1.44,
|
| 207 |
+
"grad_norm": 1.04612135887146,
|
| 208 |
+
"learning_rate": 0.004280748663101605,
|
| 209 |
+
"loss": 0.3654,
|
| 210 |
+
"step": 270
|
| 211 |
+
},
|
| 212 |
+
{
|
| 213 |
+
"epoch": 1.5,
|
| 214 |
+
"grad_norm": 0.7823394536972046,
|
| 215 |
+
"learning_rate": 0.004254010695187166,
|
| 216 |
+
"loss": 0.4385,
|
| 217 |
+
"step": 280
|
| 218 |
+
},
|
| 219 |
+
{
|
| 220 |
+
"epoch": 1.55,
|
| 221 |
+
"grad_norm": 0.9472429752349854,
|
| 222 |
+
"learning_rate": 0.004227272727272727,
|
| 223 |
+
"loss": 0.4417,
|
| 224 |
+
"step": 290
|
| 225 |
+
},
|
| 226 |
+
{
|
| 227 |
+
"epoch": 1.6,
|
| 228 |
+
"grad_norm": 0.889252245426178,
|
| 229 |
+
"learning_rate": 0.004200534759358289,
|
| 230 |
+
"loss": 0.3873,
|
| 231 |
+
"step": 300
|
| 232 |
+
},
|
| 233 |
+
{
|
| 234 |
+
"epoch": 1.66,
|
| 235 |
+
"grad_norm": 0.7252718806266785,
|
| 236 |
+
"learning_rate": 0.00417379679144385,
|
| 237 |
+
"loss": 0.3717,
|
| 238 |
+
"step": 310
|
| 239 |
+
},
|
| 240 |
+
{
|
| 241 |
+
"epoch": 1.71,
|
| 242 |
+
"grad_norm": 0.8687788844108582,
|
| 243 |
+
"learning_rate": 0.004147058823529412,
|
| 244 |
+
"loss": 0.3854,
|
| 245 |
+
"step": 320
|
| 246 |
+
},
|
| 247 |
+
{
|
| 248 |
+
"epoch": 1.76,
|
| 249 |
+
"grad_norm": 0.6197172999382019,
|
| 250 |
+
"learning_rate": 0.004122994652406417,
|
| 251 |
+
"loss": 0.3748,
|
| 252 |
+
"step": 330
|
| 253 |
+
},
|
| 254 |
+
{
|
| 255 |
+
"epoch": 1.82,
|
| 256 |
+
"grad_norm": 0.6506063342094421,
|
| 257 |
+
"learning_rate": 0.004096256684491978,
|
| 258 |
+
"loss": 0.2923,
|
| 259 |
+
"step": 340
|
| 260 |
+
},
|
| 261 |
+
{
|
| 262 |
+
"epoch": 1.87,
|
| 263 |
+
"grad_norm": 0.5267966389656067,
|
| 264 |
+
"learning_rate": 0.00406951871657754,
|
| 265 |
+
"loss": 0.4045,
|
| 266 |
+
"step": 350
|
| 267 |
+
},
|
| 268 |
+
{
|
| 269 |
+
"epoch": 1.93,
|
| 270 |
+
"grad_norm": 1.1251919269561768,
|
| 271 |
+
"learning_rate": 0.004042780748663102,
|
| 272 |
+
"loss": 0.3988,
|
| 273 |
+
"step": 360
|
| 274 |
+
},
|
| 275 |
+
{
|
| 276 |
+
"epoch": 1.98,
|
| 277 |
+
"grad_norm": 1.114890456199646,
|
| 278 |
+
"learning_rate": 0.004016042780748663,
|
| 279 |
+
"loss": 0.3796,
|
| 280 |
+
"step": 370
|
| 281 |
+
},
|
| 282 |
+
{
|
| 283 |
+
"epoch": 2.0,
|
| 284 |
+
"eval_accuracy": 0.9082943925233645,
|
| 285 |
+
"eval_f1": 0.886066241884805,
|
| 286 |
+
"eval_loss": 0.27294662594795227,
|
| 287 |
+
"eval_precision": 0.9131012141299326,
|
| 288 |
+
"eval_recall": 0.887497540228883,
|
| 289 |
+
"eval_runtime": 9.2331,
|
| 290 |
+
"eval_samples_per_second": 185.419,
|
| 291 |
+
"eval_steps_per_second": 11.589,
|
| 292 |
+
"step": 374
|
| 293 |
+
},
|
| 294 |
+
{
|
| 295 |
+
"epoch": 2.03,
|
| 296 |
+
"grad_norm": 0.7117612361907959,
|
| 297 |
+
"learning_rate": 0.003989304812834224,
|
| 298 |
+
"loss": 0.3724,
|
| 299 |
+
"step": 380
|
| 300 |
+
},
|
| 301 |
+
{
|
| 302 |
+
"epoch": 2.09,
|
| 303 |
+
"grad_norm": 0.9159232974052429,
|
| 304 |
+
"learning_rate": 0.00396524064171123,
|
| 305 |
+
"loss": 0.3155,
|
| 306 |
+
"step": 390
|
| 307 |
+
},
|
| 308 |
+
{
|
| 309 |
+
"epoch": 2.14,
|
| 310 |
+
"grad_norm": 0.6797966957092285,
|
| 311 |
+
"learning_rate": 0.003938502673796792,
|
| 312 |
+
"loss": 0.3531,
|
| 313 |
+
"step": 400
|
| 314 |
+
},
|
| 315 |
+
{
|
| 316 |
+
"epoch": 2.19,
|
| 317 |
+
"grad_norm": 0.912696361541748,
|
| 318 |
+
"learning_rate": 0.003911764705882353,
|
| 319 |
+
"loss": 0.2788,
|
| 320 |
+
"step": 410
|
| 321 |
+
},
|
| 322 |
+
{
|
| 323 |
+
"epoch": 2.25,
|
| 324 |
+
"grad_norm": 1.0336519479751587,
|
| 325 |
+
"learning_rate": 0.0038850267379679144,
|
| 326 |
+
"loss": 0.3692,
|
| 327 |
+
"step": 420
|
| 328 |
+
},
|
| 329 |
+
{
|
| 330 |
+
"epoch": 2.3,
|
| 331 |
+
"grad_norm": 0.8013398051261902,
|
| 332 |
+
"learning_rate": 0.003858288770053476,
|
| 333 |
+
"loss": 0.3561,
|
| 334 |
+
"step": 430
|
| 335 |
+
},
|
| 336 |
+
{
|
| 337 |
+
"epoch": 2.35,
|
| 338 |
+
"grad_norm": 0.6950948238372803,
|
| 339 |
+
"learning_rate": 0.003831550802139038,
|
| 340 |
+
"loss": 0.3295,
|
| 341 |
+
"step": 440
|
| 342 |
+
},
|
| 343 |
+
{
|
| 344 |
+
"epoch": 2.41,
|
| 345 |
+
"grad_norm": 0.7441625595092773,
|
| 346 |
+
"learning_rate": 0.003804812834224599,
|
| 347 |
+
"loss": 0.3285,
|
| 348 |
+
"step": 450
|
| 349 |
+
},
|
| 350 |
+
{
|
| 351 |
+
"epoch": 2.46,
|
| 352 |
+
"grad_norm": 4.745124816894531,
|
| 353 |
+
"learning_rate": 0.0037780748663101605,
|
| 354 |
+
"loss": 0.4162,
|
| 355 |
+
"step": 460
|
| 356 |
+
},
|
| 357 |
+
{
|
| 358 |
+
"epoch": 2.51,
|
| 359 |
+
"grad_norm": 1.3873414993286133,
|
| 360 |
+
"learning_rate": 0.003751336898395722,
|
| 361 |
+
"loss": 0.3424,
|
| 362 |
+
"step": 470
|
| 363 |
+
},
|
| 364 |
+
{
|
| 365 |
+
"epoch": 2.57,
|
| 366 |
+
"grad_norm": 0.7891167402267456,
|
| 367 |
+
"learning_rate": 0.0037272727272727275,
|
| 368 |
+
"loss": 0.3043,
|
| 369 |
+
"step": 480
|
| 370 |
+
},
|
| 371 |
+
{
|
| 372 |
+
"epoch": 2.62,
|
| 373 |
+
"grad_norm": 1.013873815536499,
|
| 374 |
+
"learning_rate": 0.003700534759358289,
|
| 375 |
+
"loss": 0.3754,
|
| 376 |
+
"step": 490
|
| 377 |
+
},
|
| 378 |
+
{
|
| 379 |
+
"epoch": 2.67,
|
| 380 |
+
"grad_norm": 0.9377150535583496,
|
| 381 |
+
"learning_rate": 0.00367379679144385,
|
| 382 |
+
"loss": 0.3675,
|
| 383 |
+
"step": 500
|
| 384 |
+
},
|
| 385 |
+
{
|
| 386 |
+
"epoch": 2.73,
|
| 387 |
+
"grad_norm": 2.7368648052215576,
|
| 388 |
+
"learning_rate": 0.0036470588235294117,
|
| 389 |
+
"loss": 0.2901,
|
| 390 |
+
"step": 510
|
| 391 |
+
},
|
| 392 |
+
{
|
| 393 |
+
"epoch": 2.78,
|
| 394 |
+
"grad_norm": 1.5487793684005737,
|
| 395 |
+
"learning_rate": 0.0036203208556149736,
|
| 396 |
+
"loss": 0.482,
|
| 397 |
+
"step": 520
|
| 398 |
+
},
|
| 399 |
+
{
|
| 400 |
+
"epoch": 2.83,
|
| 401 |
+
"grad_norm": 8.680522918701172,
|
| 402 |
+
"learning_rate": 0.003593582887700535,
|
| 403 |
+
"loss": 0.378,
|
| 404 |
+
"step": 530
|
| 405 |
+
},
|
| 406 |
+
{
|
| 407 |
+
"epoch": 2.89,
|
| 408 |
+
"grad_norm": 1.3777785301208496,
|
| 409 |
+
"learning_rate": 0.0035668449197860962,
|
| 410 |
+
"loss": 0.4919,
|
| 411 |
+
"step": 540
|
| 412 |
+
},
|
| 413 |
+
{
|
| 414 |
+
"epoch": 2.94,
|
| 415 |
+
"grad_norm": 2.1192550659179688,
|
| 416 |
+
"learning_rate": 0.0035401069518716578,
|
| 417 |
+
"loss": 0.3751,
|
| 418 |
+
"step": 550
|
| 419 |
+
},
|
| 420 |
+
{
|
| 421 |
+
"epoch": 2.99,
|
| 422 |
+
"grad_norm": 9.656478881835938,
|
| 423 |
+
"learning_rate": 0.0035133689839572193,
|
| 424 |
+
"loss": 0.424,
|
| 425 |
+
"step": 560
|
| 426 |
+
},
|
| 427 |
+
{
|
| 428 |
+
"epoch": 3.0,
|
| 429 |
+
"eval_accuracy": 0.866822429906542,
|
| 430 |
+
"eval_f1": 0.8491520459723211,
|
| 431 |
+
"eval_loss": 0.3701097071170807,
|
| 432 |
+
"eval_precision": 0.8797339861417046,
|
| 433 |
+
"eval_recall": 0.8520089249800192,
|
| 434 |
+
"eval_runtime": 9.219,
|
| 435 |
+
"eval_samples_per_second": 185.702,
|
| 436 |
+
"eval_steps_per_second": 11.606,
|
| 437 |
+
"step": 561
|
| 438 |
+
},
|
| 439 |
+
{
|
| 440 |
+
"epoch": 3.05,
|
| 441 |
+
"grad_norm": 1.5421924591064453,
|
| 442 |
+
"learning_rate": 0.0034866310160427804,
|
| 443 |
+
"loss": 0.4643,
|
| 444 |
+
"step": 570
|
| 445 |
+
},
|
| 446 |
+
{
|
| 447 |
+
"epoch": 3.1,
|
| 448 |
+
"grad_norm": 0.9370782375335693,
|
| 449 |
+
"learning_rate": 0.0034598930481283424,
|
| 450 |
+
"loss": 0.4274,
|
| 451 |
+
"step": 580
|
| 452 |
+
},
|
| 453 |
+
{
|
| 454 |
+
"epoch": 3.16,
|
| 455 |
+
"grad_norm": 1.6456141471862793,
|
| 456 |
+
"learning_rate": 0.003433155080213904,
|
| 457 |
+
"loss": 0.3616,
|
| 458 |
+
"step": 590
|
| 459 |
+
},
|
| 460 |
+
{
|
| 461 |
+
"epoch": 3.21,
|
| 462 |
+
"grad_norm": 1.2138258218765259,
|
| 463 |
+
"learning_rate": 0.0034064171122994654,
|
| 464 |
+
"loss": 0.4241,
|
| 465 |
+
"step": 600
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 3.26,
|
| 469 |
+
"grad_norm": 0.8959400057792664,
|
| 470 |
+
"learning_rate": 0.0033796791443850265,
|
| 471 |
+
"loss": 0.3392,
|
| 472 |
+
"step": 610
|
| 473 |
+
},
|
| 474 |
+
{
|
| 475 |
+
"epoch": 3.32,
|
| 476 |
+
"grad_norm": 0.8747026324272156,
|
| 477 |
+
"learning_rate": 0.003352941176470588,
|
| 478 |
+
"loss": 0.3533,
|
| 479 |
+
"step": 620
|
| 480 |
+
},
|
| 481 |
+
{
|
| 482 |
+
"epoch": 3.37,
|
| 483 |
+
"grad_norm": 1.7161656618118286,
|
| 484 |
+
"learning_rate": 0.00332620320855615,
|
| 485 |
+
"loss": 0.3407,
|
| 486 |
+
"step": 630
|
| 487 |
+
},
|
| 488 |
+
{
|
| 489 |
+
"epoch": 3.42,
|
| 490 |
+
"grad_norm": 0.9229569435119629,
|
| 491 |
+
"learning_rate": 0.0032994652406417115,
|
| 492 |
+
"loss": 0.3098,
|
| 493 |
+
"step": 640
|
| 494 |
+
},
|
| 495 |
+
{
|
| 496 |
+
"epoch": 3.48,
|
| 497 |
+
"grad_norm": 0.9468969702720642,
|
| 498 |
+
"learning_rate": 0.0032727272727272726,
|
| 499 |
+
"loss": 0.3896,
|
| 500 |
+
"step": 650
|
| 501 |
+
},
|
| 502 |
+
{
|
| 503 |
+
"epoch": 3.53,
|
| 504 |
+
"grad_norm": 1.4430208206176758,
|
| 505 |
+
"learning_rate": 0.003245989304812834,
|
| 506 |
+
"loss": 0.3395,
|
| 507 |
+
"step": 660
|
| 508 |
+
},
|
| 509 |
+
{
|
| 510 |
+
"epoch": 3.58,
|
| 511 |
+
"grad_norm": 1.20052969455719,
|
| 512 |
+
"learning_rate": 0.0032192513368983957,
|
| 513 |
+
"loss": 0.3448,
|
| 514 |
+
"step": 670
|
| 515 |
+
},
|
| 516 |
+
{
|
| 517 |
+
"epoch": 3.64,
|
| 518 |
+
"grad_norm": 1.1726669073104858,
|
| 519 |
+
"learning_rate": 0.0031925133689839577,
|
| 520 |
+
"loss": 0.342,
|
| 521 |
+
"step": 680
|
| 522 |
+
},
|
| 523 |
+
{
|
| 524 |
+
"epoch": 3.69,
|
| 525 |
+
"grad_norm": 0.7881722450256348,
|
| 526 |
+
"learning_rate": 0.0031657754010695188,
|
| 527 |
+
"loss": 0.301,
|
| 528 |
+
"step": 690
|
| 529 |
+
},
|
| 530 |
+
{
|
| 531 |
+
"epoch": 3.74,
|
| 532 |
+
"grad_norm": 0.7960072159767151,
|
| 533 |
+
"learning_rate": 0.0031390374331550803,
|
| 534 |
+
"loss": 0.2633,
|
| 535 |
+
"step": 700
|
| 536 |
+
},
|
| 537 |
+
{
|
| 538 |
+
"epoch": 3.8,
|
| 539 |
+
"grad_norm": 0.964872419834137,
|
| 540 |
+
"learning_rate": 0.003112299465240642,
|
| 541 |
+
"loss": 0.2691,
|
| 542 |
+
"step": 710
|
| 543 |
+
},
|
| 544 |
+
{
|
| 545 |
+
"epoch": 3.85,
|
| 546 |
+
"grad_norm": 0.9894037246704102,
|
| 547 |
+
"learning_rate": 0.003085561497326203,
|
| 548 |
+
"loss": 0.2859,
|
| 549 |
+
"step": 720
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"epoch": 3.9,
|
| 553 |
+
"grad_norm": 1.0027267932891846,
|
| 554 |
+
"learning_rate": 0.003058823529411765,
|
| 555 |
+
"loss": 0.3027,
|
| 556 |
+
"step": 730
|
| 557 |
+
},
|
| 558 |
+
{
|
| 559 |
+
"epoch": 3.96,
|
| 560 |
+
"grad_norm": 1.0325654745101929,
|
| 561 |
+
"learning_rate": 0.0030320855614973264,
|
| 562 |
+
"loss": 0.3141,
|
| 563 |
+
"step": 740
|
| 564 |
+
},
|
| 565 |
+
{
|
| 566 |
+
"epoch": 4.0,
|
| 567 |
+
"eval_accuracy": 0.9380841121495327,
|
| 568 |
+
"eval_f1": 0.9283105641226367,
|
| 569 |
+
"eval_loss": 0.18485769629478455,
|
| 570 |
+
"eval_precision": 0.9266830676466586,
|
| 571 |
+
"eval_recall": 0.9336478146798447,
|
| 572 |
+
"eval_runtime": 9.3787,
|
| 573 |
+
"eval_samples_per_second": 182.542,
|
| 574 |
+
"eval_steps_per_second": 11.409,
|
| 575 |
+
"step": 748
|
| 576 |
+
},
|
| 577 |
+
{
|
| 578 |
+
"epoch": 4.01,
|
| 579 |
+
"grad_norm": 1.263634443283081,
|
| 580 |
+
"learning_rate": 0.003005347593582888,
|
| 581 |
+
"loss": 0.3592,
|
| 582 |
+
"step": 750
|
| 583 |
+
},
|
| 584 |
+
{
|
| 585 |
+
"epoch": 4.06,
|
| 586 |
+
"grad_norm": 1.8158007860183716,
|
| 587 |
+
"learning_rate": 0.002978609625668449,
|
| 588 |
+
"loss": 0.364,
|
| 589 |
+
"step": 760
|
| 590 |
+
},
|
| 591 |
+
{
|
| 592 |
+
"epoch": 4.12,
|
| 593 |
+
"grad_norm": 0.9459696412086487,
|
| 594 |
+
"learning_rate": 0.0029518716577540106,
|
| 595 |
+
"loss": 0.3587,
|
| 596 |
+
"step": 770
|
| 597 |
+
},
|
| 598 |
+
{
|
| 599 |
+
"epoch": 4.17,
|
| 600 |
+
"grad_norm": 0.7624779343605042,
|
| 601 |
+
"learning_rate": 0.0029251336898395725,
|
| 602 |
+
"loss": 0.304,
|
| 603 |
+
"step": 780
|
| 604 |
+
},
|
| 605 |
+
{
|
| 606 |
+
"epoch": 4.22,
|
| 607 |
+
"grad_norm": 0.8625235557556152,
|
| 608 |
+
"learning_rate": 0.002898395721925134,
|
| 609 |
+
"loss": 0.2726,
|
| 610 |
+
"step": 790
|
| 611 |
+
},
|
| 612 |
+
{
|
| 613 |
+
"epoch": 4.28,
|
| 614 |
+
"grad_norm": 0.962257444858551,
|
| 615 |
+
"learning_rate": 0.002871657754010695,
|
| 616 |
+
"loss": 0.2601,
|
| 617 |
+
"step": 800
|
| 618 |
+
},
|
| 619 |
+
{
|
| 620 |
+
"epoch": 4.33,
|
| 621 |
+
"grad_norm": 0.6333624720573425,
|
| 622 |
+
"learning_rate": 0.0028449197860962567,
|
| 623 |
+
"loss": 0.3448,
|
| 624 |
+
"step": 810
|
| 625 |
+
},
|
| 626 |
+
{
|
| 627 |
+
"epoch": 4.39,
|
| 628 |
+
"grad_norm": 1.3983910083770752,
|
| 629 |
+
"learning_rate": 0.002818181818181818,
|
| 630 |
+
"loss": 0.3202,
|
| 631 |
+
"step": 820
|
| 632 |
+
},
|
| 633 |
+
{
|
| 634 |
+
"epoch": 4.44,
|
| 635 |
+
"grad_norm": 0.6626348495483398,
|
| 636 |
+
"learning_rate": 0.00279144385026738,
|
| 637 |
+
"loss": 0.2529,
|
| 638 |
+
"step": 830
|
| 639 |
+
},
|
| 640 |
+
{
|
| 641 |
+
"epoch": 4.49,
|
| 642 |
+
"grad_norm": 0.8221544027328491,
|
| 643 |
+
"learning_rate": 0.0027647058823529413,
|
| 644 |
+
"loss": 0.2523,
|
| 645 |
+
"step": 840
|
| 646 |
+
},
|
| 647 |
+
{
|
| 648 |
+
"epoch": 4.55,
|
| 649 |
+
"grad_norm": 0.7872591018676758,
|
| 650 |
+
"learning_rate": 0.002737967914438503,
|
| 651 |
+
"loss": 0.2832,
|
| 652 |
+
"step": 850
|
| 653 |
+
},
|
| 654 |
+
{
|
| 655 |
+
"epoch": 4.6,
|
| 656 |
+
"grad_norm": 1.50129234790802,
|
| 657 |
+
"learning_rate": 0.0027112299465240643,
|
| 658 |
+
"loss": 0.2912,
|
| 659 |
+
"step": 860
|
| 660 |
+
},
|
| 661 |
+
{
|
| 662 |
+
"epoch": 4.65,
|
| 663 |
+
"grad_norm": 0.7471727728843689,
|
| 664 |
+
"learning_rate": 0.0026844919786096254,
|
| 665 |
+
"loss": 0.3097,
|
| 666 |
+
"step": 870
|
| 667 |
+
},
|
| 668 |
+
{
|
| 669 |
+
"epoch": 4.71,
|
| 670 |
+
"grad_norm": 0.6078329086303711,
|
| 671 |
+
"learning_rate": 0.002657754010695187,
|
| 672 |
+
"loss": 0.2657,
|
| 673 |
+
"step": 880
|
| 674 |
+
},
|
| 675 |
+
{
|
| 676 |
+
"epoch": 4.76,
|
| 677 |
+
"grad_norm": 0.8674110174179077,
|
| 678 |
+
"learning_rate": 0.002631016042780749,
|
| 679 |
+
"loss": 0.2633,
|
| 680 |
+
"step": 890
|
| 681 |
+
},
|
| 682 |
+
{
|
| 683 |
+
"epoch": 4.81,
|
| 684 |
+
"grad_norm": 0.5421575307846069,
|
| 685 |
+
"learning_rate": 0.0026042780748663104,
|
| 686 |
+
"loss": 0.257,
|
| 687 |
+
"step": 900
|
| 688 |
+
},
|
| 689 |
+
{
|
| 690 |
+
"epoch": 4.87,
|
| 691 |
+
"grad_norm": 1.314867377281189,
|
| 692 |
+
"learning_rate": 0.0025775401069518715,
|
| 693 |
+
"loss": 0.2688,
|
| 694 |
+
"step": 910
|
| 695 |
+
},
|
| 696 |
+
{
|
| 697 |
+
"epoch": 4.92,
|
| 698 |
+
"grad_norm": 0.698221743106842,
|
| 699 |
+
"learning_rate": 0.002550802139037433,
|
| 700 |
+
"loss": 0.2506,
|
| 701 |
+
"step": 920
|
| 702 |
+
},
|
| 703 |
+
{
|
| 704 |
+
"epoch": 4.97,
|
| 705 |
+
"grad_norm": 0.5437451004981995,
|
| 706 |
+
"learning_rate": 0.0025240641711229946,
|
| 707 |
+
"loss": 0.2553,
|
| 708 |
+
"step": 930
|
| 709 |
+
},
|
| 710 |
+
{
|
| 711 |
+
"epoch": 5.0,
|
| 712 |
+
"eval_accuracy": 0.9643691588785047,
|
| 713 |
+
"eval_f1": 0.9617344813251135,
|
| 714 |
+
"eval_loss": 0.1074606254696846,
|
| 715 |
+
"eval_precision": 0.9630090863077152,
|
| 716 |
+
"eval_recall": 0.9611619604560873,
|
| 717 |
+
"eval_runtime": 9.213,
|
| 718 |
+
"eval_samples_per_second": 185.824,
|
| 719 |
+
"eval_steps_per_second": 11.614,
|
| 720 |
+
"step": 935
|
| 721 |
+
},
|
| 722 |
+
{
|
| 723 |
+
"epoch": 5.03,
|
| 724 |
+
"grad_norm": 0.9639925956726074,
|
| 725 |
+
"learning_rate": 0.002497326203208556,
|
| 726 |
+
"loss": 0.2186,
|
| 727 |
+
"step": 940
|
| 728 |
+
},
|
| 729 |
+
{
|
| 730 |
+
"epoch": 5.08,
|
| 731 |
+
"grad_norm": 1.0346194505691528,
|
| 732 |
+
"learning_rate": 0.0024705882352941176,
|
| 733 |
+
"loss": 0.3163,
|
| 734 |
+
"step": 950
|
| 735 |
+
},
|
| 736 |
+
{
|
| 737 |
+
"epoch": 5.13,
|
| 738 |
+
"grad_norm": 0.9101438522338867,
|
| 739 |
+
"learning_rate": 0.002443850267379679,
|
| 740 |
+
"loss": 0.257,
|
| 741 |
+
"step": 960
|
| 742 |
+
},
|
| 743 |
+
{
|
| 744 |
+
"epoch": 5.19,
|
| 745 |
+
"grad_norm": 0.9387779831886292,
|
| 746 |
+
"learning_rate": 0.0024171122994652407,
|
| 747 |
+
"loss": 0.2745,
|
| 748 |
+
"step": 970
|
| 749 |
+
},
|
| 750 |
+
{
|
| 751 |
+
"epoch": 5.24,
|
| 752 |
+
"grad_norm": 1.3407084941864014,
|
| 753 |
+
"learning_rate": 0.0023903743315508022,
|
| 754 |
+
"loss": 0.2775,
|
| 755 |
+
"step": 980
|
| 756 |
+
},
|
| 757 |
+
{
|
| 758 |
+
"epoch": 5.29,
|
| 759 |
+
"grad_norm": 0.7988283038139343,
|
| 760 |
+
"learning_rate": 0.0023636363636363638,
|
| 761 |
+
"loss": 0.2568,
|
| 762 |
+
"step": 990
|
| 763 |
+
},
|
| 764 |
+
{
|
| 765 |
+
"epoch": 5.35,
|
| 766 |
+
"grad_norm": 0.8980028033256531,
|
| 767 |
+
"learning_rate": 0.0023368983957219253,
|
| 768 |
+
"loss": 0.296,
|
| 769 |
+
"step": 1000
|
| 770 |
+
},
|
| 771 |
+
{
|
| 772 |
+
"epoch": 5.4,
|
| 773 |
+
"grad_norm": 0.8847124576568604,
|
| 774 |
+
"learning_rate": 0.002310160427807487,
|
| 775 |
+
"loss": 0.2525,
|
| 776 |
+
"step": 1010
|
| 777 |
+
},
|
| 778 |
+
{
|
| 779 |
+
"epoch": 5.45,
|
| 780 |
+
"grad_norm": 1.3140696287155151,
|
| 781 |
+
"learning_rate": 0.002283422459893048,
|
| 782 |
+
"loss": 0.2967,
|
| 783 |
+
"step": 1020
|
| 784 |
+
},
|
| 785 |
+
{
|
| 786 |
+
"epoch": 5.51,
|
| 787 |
+
"grad_norm": 0.6774911284446716,
|
| 788 |
+
"learning_rate": 0.00225668449197861,
|
| 789 |
+
"loss": 0.2735,
|
| 790 |
+
"step": 1030
|
| 791 |
+
},
|
| 792 |
+
{
|
| 793 |
+
"epoch": 5.56,
|
| 794 |
+
"grad_norm": 0.9686025977134705,
|
| 795 |
+
"learning_rate": 0.002229946524064171,
|
| 796 |
+
"loss": 0.2415,
|
| 797 |
+
"step": 1040
|
| 798 |
+
},
|
| 799 |
+
{
|
| 800 |
+
"epoch": 5.61,
|
| 801 |
+
"grad_norm": 1.3379433155059814,
|
| 802 |
+
"learning_rate": 0.0022032085561497325,
|
| 803 |
+
"loss": 0.2656,
|
| 804 |
+
"step": 1050
|
| 805 |
+
},
|
| 806 |
+
{
|
| 807 |
+
"epoch": 5.67,
|
| 808 |
+
"grad_norm": 0.6908765435218811,
|
| 809 |
+
"learning_rate": 0.002176470588235294,
|
| 810 |
+
"loss": 0.2532,
|
| 811 |
+
"step": 1060
|
| 812 |
+
},
|
| 813 |
+
{
|
| 814 |
+
"epoch": 5.72,
|
| 815 |
+
"grad_norm": 0.8308853507041931,
|
| 816 |
+
"learning_rate": 0.0021497326203208556,
|
| 817 |
+
"loss": 0.2428,
|
| 818 |
+
"step": 1070
|
| 819 |
+
},
|
| 820 |
+
{
|
| 821 |
+
"epoch": 5.78,
|
| 822 |
+
"grad_norm": 1.2064207792282104,
|
| 823 |
+
"learning_rate": 0.002122994652406417,
|
| 824 |
+
"loss": 0.2989,
|
| 825 |
+
"step": 1080
|
| 826 |
+
},
|
| 827 |
+
{
|
| 828 |
+
"epoch": 5.83,
|
| 829 |
+
"grad_norm": 0.8376064896583557,
|
| 830 |
+
"learning_rate": 0.0020962566844919786,
|
| 831 |
+
"loss": 0.2061,
|
| 832 |
+
"step": 1090
|
| 833 |
+
},
|
| 834 |
+
{
|
| 835 |
+
"epoch": 5.88,
|
| 836 |
+
"grad_norm": 0.9363247156143188,
|
| 837 |
+
"learning_rate": 0.00206951871657754,
|
| 838 |
+
"loss": 0.2447,
|
| 839 |
+
"step": 1100
|
| 840 |
+
},
|
| 841 |
+
{
|
| 842 |
+
"epoch": 5.94,
|
| 843 |
+
"grad_norm": 7.874444007873535,
|
| 844 |
+
"learning_rate": 0.0020427807486631017,
|
| 845 |
+
"loss": 0.2254,
|
| 846 |
+
"step": 1110
|
| 847 |
+
},
|
| 848 |
+
{
|
| 849 |
+
"epoch": 5.99,
|
| 850 |
+
"grad_norm": 0.9535788297653198,
|
| 851 |
+
"learning_rate": 0.002016042780748663,
|
| 852 |
+
"loss": 0.2686,
|
| 853 |
+
"step": 1120
|
| 854 |
+
},
|
| 855 |
+
{
|
| 856 |
+
"epoch": 6.0,
|
| 857 |
+
"eval_accuracy": 0.9485981308411215,
|
| 858 |
+
"eval_f1": 0.9488981890553403,
|
| 859 |
+
"eval_loss": 0.16793404519557953,
|
| 860 |
+
"eval_precision": 0.9560571498851578,
|
| 861 |
+
"eval_recall": 0.9437216744429628,
|
| 862 |
+
"eval_runtime": 9.2543,
|
| 863 |
+
"eval_samples_per_second": 184.995,
|
| 864 |
+
"eval_steps_per_second": 11.562,
|
| 865 |
+
"step": 1122
|
| 866 |
+
},
|
| 867 |
+
{
|
| 868 |
+
"epoch": 6.04,
|
| 869 |
+
"grad_norm": 0.9278040528297424,
|
| 870 |
+
"learning_rate": 0.0019893048128342247,
|
| 871 |
+
"loss": 0.256,
|
| 872 |
+
"step": 1130
|
| 873 |
+
},
|
| 874 |
+
{
|
| 875 |
+
"epoch": 6.1,
|
| 876 |
+
"grad_norm": 1.0177885293960571,
|
| 877 |
+
"learning_rate": 0.0019625668449197863,
|
| 878 |
+
"loss": 0.2173,
|
| 879 |
+
"step": 1140
|
| 880 |
+
},
|
| 881 |
+
{
|
| 882 |
+
"epoch": 6.15,
|
| 883 |
+
"grad_norm": 0.5898217558860779,
|
| 884 |
+
"learning_rate": 0.0019358288770053476,
|
| 885 |
+
"loss": 0.2257,
|
| 886 |
+
"step": 1150
|
| 887 |
+
},
|
| 888 |
+
{
|
| 889 |
+
"epoch": 6.2,
|
| 890 |
+
"grad_norm": 5.235673904418945,
|
| 891 |
+
"learning_rate": 0.0019090909090909091,
|
| 892 |
+
"loss": 0.2388,
|
| 893 |
+
"step": 1160
|
| 894 |
+
},
|
| 895 |
+
{
|
| 896 |
+
"epoch": 6.26,
|
| 897 |
+
"grad_norm": 1.1271004676818848,
|
| 898 |
+
"learning_rate": 0.0018823529411764706,
|
| 899 |
+
"loss": 0.2544,
|
| 900 |
+
"step": 1170
|
| 901 |
+
},
|
| 902 |
+
{
|
| 903 |
+
"epoch": 6.31,
|
| 904 |
+
"grad_norm": 0.6136900186538696,
|
| 905 |
+
"learning_rate": 0.001855614973262032,
|
| 906 |
+
"loss": 0.2785,
|
| 907 |
+
"step": 1180
|
| 908 |
+
},
|
| 909 |
+
{
|
| 910 |
+
"epoch": 6.36,
|
| 911 |
+
"grad_norm": 0.9343350529670715,
|
| 912 |
+
"learning_rate": 0.0018288770053475937,
|
| 913 |
+
"loss": 0.2304,
|
| 914 |
+
"step": 1190
|
| 915 |
+
},
|
| 916 |
+
{
|
| 917 |
+
"epoch": 6.42,
|
| 918 |
+
"grad_norm": 0.7129714488983154,
|
| 919 |
+
"learning_rate": 0.001802139037433155,
|
| 920 |
+
"loss": 0.1709,
|
| 921 |
+
"step": 1200
|
| 922 |
+
},
|
| 923 |
+
{
|
| 924 |
+
"epoch": 6.47,
|
| 925 |
+
"grad_norm": 0.8645954132080078,
|
| 926 |
+
"learning_rate": 0.0017754010695187168,
|
| 927 |
+
"loss": 0.2099,
|
| 928 |
+
"step": 1210
|
| 929 |
+
},
|
| 930 |
+
{
|
| 931 |
+
"epoch": 6.52,
|
| 932 |
+
"grad_norm": 0.4692780375480652,
|
| 933 |
+
"learning_rate": 0.001748663101604278,
|
| 934 |
+
"loss": 0.1801,
|
| 935 |
+
"step": 1220
|
| 936 |
+
},
|
| 937 |
+
{
|
| 938 |
+
"epoch": 6.58,
|
| 939 |
+
"grad_norm": 1.1131465435028076,
|
| 940 |
+
"learning_rate": 0.0017219251336898396,
|
| 941 |
+
"loss": 0.2187,
|
| 942 |
+
"step": 1230
|
| 943 |
+
},
|
| 944 |
+
{
|
| 945 |
+
"epoch": 6.63,
|
| 946 |
+
"grad_norm": 1.0496641397476196,
|
| 947 |
+
"learning_rate": 0.0016951871657754011,
|
| 948 |
+
"loss": 0.2381,
|
| 949 |
+
"step": 1240
|
| 950 |
+
},
|
| 951 |
+
{
|
| 952 |
+
"epoch": 6.68,
|
| 953 |
+
"grad_norm": 0.7512268424034119,
|
| 954 |
+
"learning_rate": 0.0016684491978609627,
|
| 955 |
+
"loss": 0.2171,
|
| 956 |
+
"step": 1250
|
| 957 |
+
},
|
| 958 |
+
{
|
| 959 |
+
"epoch": 6.74,
|
| 960 |
+
"grad_norm": 0.9206662774085999,
|
| 961 |
+
"learning_rate": 0.0016417112299465242,
|
| 962 |
+
"loss": 0.1716,
|
| 963 |
+
"step": 1260
|
| 964 |
+
},
|
| 965 |
+
{
|
| 966 |
+
"epoch": 6.79,
|
| 967 |
+
"grad_norm": 1.044285535812378,
|
| 968 |
+
"learning_rate": 0.0016149732620320857,
|
| 969 |
+
"loss": 0.1996,
|
| 970 |
+
"step": 1270
|
| 971 |
+
},
|
| 972 |
+
{
|
| 973 |
+
"epoch": 6.84,
|
| 974 |
+
"grad_norm": 1.5523549318313599,
|
| 975 |
+
"learning_rate": 0.001588235294117647,
|
| 976 |
+
"loss": 0.198,
|
| 977 |
+
"step": 1280
|
| 978 |
+
},
|
| 979 |
+
{
|
| 980 |
+
"epoch": 6.9,
|
| 981 |
+
"grad_norm": 0.7654513120651245,
|
| 982 |
+
"learning_rate": 0.0015614973262032088,
|
| 983 |
+
"loss": 0.2341,
|
| 984 |
+
"step": 1290
|
| 985 |
+
},
|
| 986 |
+
{
|
| 987 |
+
"epoch": 6.95,
|
| 988 |
+
"grad_norm": 1.145663857460022,
|
| 989 |
+
"learning_rate": 0.00153475935828877,
|
| 990 |
+
"loss": 0.2556,
|
| 991 |
+
"step": 1300
|
| 992 |
+
},
|
| 993 |
+
{
|
| 994 |
+
"epoch": 7.0,
|
| 995 |
+
"eval_accuracy": 0.9661214953271028,
|
| 996 |
+
"eval_f1": 0.9619479557860847,
|
| 997 |
+
"eval_loss": 0.09340371936559677,
|
| 998 |
+
"eval_precision": 0.9651383824240083,
|
| 999 |
+
"eval_recall": 0.9598949442531882,
|
| 1000 |
+
"eval_runtime": 9.0216,
|
| 1001 |
+
"eval_samples_per_second": 189.767,
|
| 1002 |
+
"eval_steps_per_second": 11.86,
|
| 1003 |
+
"step": 1309
|
| 1004 |
+
},
|
| 1005 |
+
{
|
| 1006 |
+
"epoch": 7.01,
|
| 1007 |
+
"grad_norm": 0.8554219603538513,
|
| 1008 |
+
"learning_rate": 0.0015080213903743314,
|
| 1009 |
+
"loss": 0.237,
|
| 1010 |
+
"step": 1310
|
| 1011 |
+
},
|
| 1012 |
+
{
|
| 1013 |
+
"epoch": 7.06,
|
| 1014 |
+
"grad_norm": 0.7055748701095581,
|
| 1015 |
+
"learning_rate": 0.0014812834224598931,
|
| 1016 |
+
"loss": 0.2317,
|
| 1017 |
+
"step": 1320
|
| 1018 |
+
},
|
| 1019 |
+
{
|
| 1020 |
+
"epoch": 7.11,
|
| 1021 |
+
"grad_norm": 1.0891897678375244,
|
| 1022 |
+
"learning_rate": 0.0014545454545454545,
|
| 1023 |
+
"loss": 0.1723,
|
| 1024 |
+
"step": 1330
|
| 1025 |
+
},
|
| 1026 |
+
{
|
| 1027 |
+
"epoch": 7.17,
|
| 1028 |
+
"grad_norm": 0.5554465651512146,
|
| 1029 |
+
"learning_rate": 0.0014278074866310162,
|
| 1030 |
+
"loss": 0.1986,
|
| 1031 |
+
"step": 1340
|
| 1032 |
+
},
|
| 1033 |
+
{
|
| 1034 |
+
"epoch": 7.22,
|
| 1035 |
+
"grad_norm": 1.0232211351394653,
|
| 1036 |
+
"learning_rate": 0.0014010695187165775,
|
| 1037 |
+
"loss": 0.2222,
|
| 1038 |
+
"step": 1350
|
| 1039 |
+
},
|
| 1040 |
+
{
|
| 1041 |
+
"epoch": 7.27,
|
| 1042 |
+
"grad_norm": 0.6204003095626831,
|
| 1043 |
+
"learning_rate": 0.001374331550802139,
|
| 1044 |
+
"loss": 0.1827,
|
| 1045 |
+
"step": 1360
|
| 1046 |
+
},
|
| 1047 |
+
{
|
| 1048 |
+
"epoch": 7.33,
|
| 1049 |
+
"grad_norm": 0.7353977560997009,
|
| 1050 |
+
"learning_rate": 0.0013475935828877006,
|
| 1051 |
+
"loss": 0.1649,
|
| 1052 |
+
"step": 1370
|
| 1053 |
+
},
|
| 1054 |
+
{
|
| 1055 |
+
"epoch": 7.38,
|
| 1056 |
+
"grad_norm": 0.734186053276062,
|
| 1057 |
+
"learning_rate": 0.001320855614973262,
|
| 1058 |
+
"loss": 0.194,
|
| 1059 |
+
"step": 1380
|
| 1060 |
+
},
|
| 1061 |
+
{
|
| 1062 |
+
"epoch": 7.43,
|
| 1063 |
+
"grad_norm": 0.47959616780281067,
|
| 1064 |
+
"learning_rate": 0.0012941176470588236,
|
| 1065 |
+
"loss": 0.1763,
|
| 1066 |
+
"step": 1390
|
| 1067 |
+
},
|
| 1068 |
+
{
|
| 1069 |
+
"epoch": 7.49,
|
| 1070 |
+
"grad_norm": 0.6939826607704163,
|
| 1071 |
+
"learning_rate": 0.0012673796791443852,
|
| 1072 |
+
"loss": 0.2286,
|
| 1073 |
+
"step": 1400
|
| 1074 |
+
},
|
| 1075 |
+
{
|
| 1076 |
+
"epoch": 7.54,
|
| 1077 |
+
"grad_norm": 0.948558509349823,
|
| 1078 |
+
"learning_rate": 0.0012406417112299467,
|
| 1079 |
+
"loss": 0.2506,
|
| 1080 |
+
"step": 1410
|
| 1081 |
+
},
|
| 1082 |
+
{
|
| 1083 |
+
"epoch": 7.59,
|
| 1084 |
+
"grad_norm": 0.8466843962669373,
|
| 1085 |
+
"learning_rate": 0.001213903743315508,
|
| 1086 |
+
"loss": 0.2175,
|
| 1087 |
+
"step": 1420
|
| 1088 |
+
},
|
| 1089 |
+
{
|
| 1090 |
+
"epoch": 7.65,
|
| 1091 |
+
"grad_norm": 0.6146303415298462,
|
| 1092 |
+
"learning_rate": 0.0011871657754010695,
|
| 1093 |
+
"loss": 0.1641,
|
| 1094 |
+
"step": 1430
|
| 1095 |
+
},
|
| 1096 |
+
{
|
| 1097 |
+
"epoch": 7.7,
|
| 1098 |
+
"grad_norm": 0.8321207761764526,
|
| 1099 |
+
"learning_rate": 0.001160427807486631,
|
| 1100 |
+
"loss": 0.1903,
|
| 1101 |
+
"step": 1440
|
| 1102 |
+
},
|
| 1103 |
+
{
|
| 1104 |
+
"epoch": 7.75,
|
| 1105 |
+
"grad_norm": 0.7309682965278625,
|
| 1106 |
+
"learning_rate": 0.0011336898395721926,
|
| 1107 |
+
"loss": 0.1981,
|
| 1108 |
+
"step": 1450
|
| 1109 |
+
},
|
| 1110 |
+
{
|
| 1111 |
+
"epoch": 7.81,
|
| 1112 |
+
"grad_norm": 0.5901007652282715,
|
| 1113 |
+
"learning_rate": 0.0011069518716577541,
|
| 1114 |
+
"loss": 0.2011,
|
| 1115 |
+
"step": 1460
|
| 1116 |
+
},
|
| 1117 |
+
{
|
| 1118 |
+
"epoch": 7.86,
|
| 1119 |
+
"grad_norm": 0.9141890406608582,
|
| 1120 |
+
"learning_rate": 0.0010802139037433154,
|
| 1121 |
+
"loss": 0.2735,
|
| 1122 |
+
"step": 1470
|
| 1123 |
+
},
|
| 1124 |
+
{
|
| 1125 |
+
"epoch": 7.91,
|
| 1126 |
+
"grad_norm": 0.813578724861145,
|
| 1127 |
+
"learning_rate": 0.001053475935828877,
|
| 1128 |
+
"loss": 0.2093,
|
| 1129 |
+
"step": 1480
|
| 1130 |
+
},
|
| 1131 |
+
{
|
| 1132 |
+
"epoch": 7.97,
|
| 1133 |
+
"grad_norm": 0.4584049582481384,
|
| 1134 |
+
"learning_rate": 0.0010267379679144385,
|
| 1135 |
+
"loss": 0.1777,
|
| 1136 |
+
"step": 1490
|
| 1137 |
+
},
|
| 1138 |
+
{
|
| 1139 |
+
"epoch": 8.0,
|
| 1140 |
+
"eval_accuracy": 0.969626168224299,
|
| 1141 |
+
"eval_f1": 0.9686486797969157,
|
| 1142 |
+
"eval_loss": 0.08350867033004761,
|
| 1143 |
+
"eval_precision": 0.9696703038283683,
|
| 1144 |
+
"eval_recall": 0.9682591946397131,
|
| 1145 |
+
"eval_runtime": 9.2254,
|
| 1146 |
+
"eval_samples_per_second": 185.574,
|
| 1147 |
+
"eval_steps_per_second": 11.598,
|
| 1148 |
+
"step": 1496
|
| 1149 |
+
},
|
| 1150 |
+
{
|
| 1151 |
+
"epoch": 8.02,
|
| 1152 |
+
"grad_norm": 0.7080217599868774,
|
| 1153 |
+
"learning_rate": 0.001,
|
| 1154 |
+
"loss": 0.1999,
|
| 1155 |
+
"step": 1500
|
| 1156 |
+
},
|
| 1157 |
+
{
|
| 1158 |
+
"epoch": 8.07,
|
| 1159 |
+
"grad_norm": 0.9281997084617615,
|
| 1160 |
+
"learning_rate": 0.0009732620320855614,
|
| 1161 |
+
"loss": 0.1688,
|
| 1162 |
+
"step": 1510
|
| 1163 |
+
},
|
| 1164 |
+
{
|
| 1165 |
+
"epoch": 8.13,
|
| 1166 |
+
"grad_norm": 0.8174493312835693,
|
| 1167 |
+
"learning_rate": 0.000946524064171123,
|
| 1168 |
+
"loss": 0.1731,
|
| 1169 |
+
"step": 1520
|
| 1170 |
+
},
|
| 1171 |
+
{
|
| 1172 |
+
"epoch": 8.18,
|
| 1173 |
+
"grad_norm": 0.6349031925201416,
|
| 1174 |
+
"learning_rate": 0.0009197860962566845,
|
| 1175 |
+
"loss": 0.1672,
|
| 1176 |
+
"step": 1530
|
| 1177 |
+
},
|
| 1178 |
+
{
|
| 1179 |
+
"epoch": 8.24,
|
| 1180 |
+
"grad_norm": 0.8174115419387817,
|
| 1181 |
+
"learning_rate": 0.000893048128342246,
|
| 1182 |
+
"loss": 0.1839,
|
| 1183 |
+
"step": 1540
|
| 1184 |
+
},
|
| 1185 |
+
{
|
| 1186 |
+
"epoch": 8.29,
|
| 1187 |
+
"grad_norm": 0.6900407671928406,
|
| 1188 |
+
"learning_rate": 0.0008663101604278075,
|
| 1189 |
+
"loss": 0.2044,
|
| 1190 |
+
"step": 1550
|
| 1191 |
+
},
|
| 1192 |
+
{
|
| 1193 |
+
"epoch": 8.34,
|
| 1194 |
+
"grad_norm": 0.2948859930038452,
|
| 1195 |
+
"learning_rate": 0.000839572192513369,
|
| 1196 |
+
"loss": 0.1328,
|
| 1197 |
+
"step": 1560
|
| 1198 |
+
},
|
| 1199 |
+
{
|
| 1200 |
+
"epoch": 8.4,
|
| 1201 |
+
"grad_norm": 0.7020041942596436,
|
| 1202 |
+
"learning_rate": 0.0008128342245989305,
|
| 1203 |
+
"loss": 0.1759,
|
| 1204 |
+
"step": 1570
|
| 1205 |
+
},
|
| 1206 |
+
{
|
| 1207 |
+
"epoch": 8.45,
|
| 1208 |
+
"grad_norm": 1.0418401956558228,
|
| 1209 |
+
"learning_rate": 0.000786096256684492,
|
| 1210 |
+
"loss": 0.1777,
|
| 1211 |
+
"step": 1580
|
| 1212 |
+
},
|
| 1213 |
+
{
|
| 1214 |
+
"epoch": 8.5,
|
| 1215 |
+
"grad_norm": 0.7473070025444031,
|
| 1216 |
+
"learning_rate": 0.0007593582887700536,
|
| 1217 |
+
"loss": 0.1631,
|
| 1218 |
+
"step": 1590
|
| 1219 |
+
},
|
| 1220 |
+
{
|
| 1221 |
+
"epoch": 8.56,
|
| 1222 |
+
"grad_norm": 0.8006024360656738,
|
| 1223 |
+
"learning_rate": 0.000732620320855615,
|
| 1224 |
+
"loss": 0.1566,
|
| 1225 |
+
"step": 1600
|
| 1226 |
+
},
|
| 1227 |
+
{
|
| 1228 |
+
"epoch": 8.61,
|
| 1229 |
+
"grad_norm": 1.0594407320022583,
|
| 1230 |
+
"learning_rate": 0.0007058823529411765,
|
| 1231 |
+
"loss": 0.184,
|
| 1232 |
+
"step": 1610
|
| 1233 |
+
},
|
| 1234 |
+
{
|
| 1235 |
+
"epoch": 8.66,
|
| 1236 |
+
"grad_norm": 0.6014285087585449,
|
| 1237 |
+
"learning_rate": 0.000679144385026738,
|
| 1238 |
+
"loss": 0.1583,
|
| 1239 |
+
"step": 1620
|
| 1240 |
+
},
|
| 1241 |
+
{
|
| 1242 |
+
"epoch": 8.72,
|
| 1243 |
+
"grad_norm": 0.6736869812011719,
|
| 1244 |
+
"learning_rate": 0.0006524064171122996,
|
| 1245 |
+
"loss": 0.1468,
|
| 1246 |
+
"step": 1630
|
| 1247 |
+
},
|
| 1248 |
+
{
|
| 1249 |
+
"epoch": 8.77,
|
| 1250 |
+
"grad_norm": 0.6957813501358032,
|
| 1251 |
+
"learning_rate": 0.0006256684491978609,
|
| 1252 |
+
"loss": 0.1731,
|
| 1253 |
+
"step": 1640
|
| 1254 |
+
},
|
| 1255 |
+
{
|
| 1256 |
+
"epoch": 8.82,
|
| 1257 |
+
"grad_norm": 0.5073075294494629,
|
| 1258 |
+
"learning_rate": 0.0005989304812834224,
|
| 1259 |
+
"loss": 0.176,
|
| 1260 |
+
"step": 1650
|
| 1261 |
+
},
|
| 1262 |
+
{
|
| 1263 |
+
"epoch": 8.88,
|
| 1264 |
+
"grad_norm": 0.5485414862632751,
|
| 1265 |
+
"learning_rate": 0.000572192513368984,
|
| 1266 |
+
"loss": 0.1936,
|
| 1267 |
+
"step": 1660
|
| 1268 |
+
},
|
| 1269 |
+
{
|
| 1270 |
+
"epoch": 8.93,
|
| 1271 |
+
"grad_norm": 0.8590062856674194,
|
| 1272 |
+
"learning_rate": 0.0005454545454545455,
|
| 1273 |
+
"loss": 0.1795,
|
| 1274 |
+
"step": 1670
|
| 1275 |
+
},
|
| 1276 |
+
{
|
| 1277 |
+
"epoch": 8.98,
|
| 1278 |
+
"grad_norm": 0.49274083971977234,
|
| 1279 |
+
"learning_rate": 0.000518716577540107,
|
| 1280 |
+
"loss": 0.1607,
|
| 1281 |
+
"step": 1680
|
| 1282 |
+
},
|
| 1283 |
+
{
|
| 1284 |
+
"epoch": 9.0,
|
| 1285 |
+
"eval_accuracy": 0.9772196261682243,
|
| 1286 |
+
"eval_f1": 0.9758896890562156,
|
| 1287 |
+
"eval_loss": 0.07392112910747528,
|
| 1288 |
+
"eval_precision": 0.9732910812266744,
|
| 1289 |
+
"eval_recall": 0.97920005624388,
|
| 1290 |
+
"eval_runtime": 9.2433,
|
| 1291 |
+
"eval_samples_per_second": 185.214,
|
| 1292 |
+
"eval_steps_per_second": 11.576,
|
| 1293 |
+
"step": 1683
|
| 1294 |
+
},
|
| 1295 |
+
{
|
| 1296 |
+
"epoch": 9.04,
|
| 1297 |
+
"grad_norm": 0.4997323751449585,
|
| 1298 |
+
"learning_rate": 0.0004919786096256684,
|
| 1299 |
+
"loss": 0.1352,
|
| 1300 |
+
"step": 1690
|
| 1301 |
+
},
|
| 1302 |
+
{
|
| 1303 |
+
"epoch": 9.09,
|
| 1304 |
+
"grad_norm": 0.5221167206764221,
|
| 1305 |
+
"learning_rate": 0.00046524064171122996,
|
| 1306 |
+
"loss": 0.1597,
|
| 1307 |
+
"step": 1700
|
| 1308 |
+
},
|
| 1309 |
+
{
|
| 1310 |
+
"epoch": 9.14,
|
| 1311 |
+
"grad_norm": 0.6731162071228027,
|
| 1312 |
+
"learning_rate": 0.0004385026737967915,
|
| 1313 |
+
"loss": 0.1639,
|
| 1314 |
+
"step": 1710
|
| 1315 |
+
},
|
| 1316 |
+
{
|
| 1317 |
+
"epoch": 9.2,
|
| 1318 |
+
"grad_norm": 0.5156794786453247,
|
| 1319 |
+
"learning_rate": 0.00041176470588235296,
|
| 1320 |
+
"loss": 0.1667,
|
| 1321 |
+
"step": 1720
|
| 1322 |
+
},
|
| 1323 |
+
{
|
| 1324 |
+
"epoch": 9.25,
|
| 1325 |
+
"grad_norm": 0.767203152179718,
|
| 1326 |
+
"learning_rate": 0.0003850267379679145,
|
| 1327 |
+
"loss": 0.1672,
|
| 1328 |
+
"step": 1730
|
| 1329 |
+
},
|
| 1330 |
+
{
|
| 1331 |
+
"epoch": 9.3,
|
| 1332 |
+
"grad_norm": 0.5664710402488708,
|
| 1333 |
+
"learning_rate": 0.0003582887700534759,
|
| 1334 |
+
"loss": 0.1428,
|
| 1335 |
+
"step": 1740
|
| 1336 |
+
},
|
| 1337 |
+
{
|
| 1338 |
+
"epoch": 9.36,
|
| 1339 |
+
"grad_norm": 0.37641459703445435,
|
| 1340 |
+
"learning_rate": 0.00033155080213903744,
|
| 1341 |
+
"loss": 0.1667,
|
| 1342 |
+
"step": 1750
|
| 1343 |
+
},
|
| 1344 |
+
{
|
| 1345 |
+
"epoch": 9.41,
|
| 1346 |
+
"grad_norm": 0.5527117252349854,
|
| 1347 |
+
"learning_rate": 0.0003048128342245989,
|
| 1348 |
+
"loss": 0.1723,
|
| 1349 |
+
"step": 1760
|
| 1350 |
+
},
|
| 1351 |
+
{
|
| 1352 |
+
"epoch": 9.47,
|
| 1353 |
+
"grad_norm": 0.8746387958526611,
|
| 1354 |
+
"learning_rate": 0.00027807486631016044,
|
| 1355 |
+
"loss": 0.1596,
|
| 1356 |
+
"step": 1770
|
| 1357 |
+
},
|
| 1358 |
+
{
|
| 1359 |
+
"epoch": 9.52,
|
| 1360 |
+
"grad_norm": 0.5461722612380981,
|
| 1361 |
+
"learning_rate": 0.0002513368983957219,
|
| 1362 |
+
"loss": 0.17,
|
| 1363 |
+
"step": 1780
|
| 1364 |
+
},
|
| 1365 |
+
{
|
| 1366 |
+
"epoch": 9.57,
|
| 1367 |
+
"grad_norm": 0.5201784372329712,
|
| 1368 |
+
"learning_rate": 0.00022459893048128345,
|
| 1369 |
+
"loss": 0.1268,
|
| 1370 |
+
"step": 1790
|
| 1371 |
+
},
|
| 1372 |
+
{
|
| 1373 |
+
"epoch": 9.63,
|
| 1374 |
+
"grad_norm": 0.44921737909317017,
|
| 1375 |
+
"learning_rate": 0.00019786096256684492,
|
| 1376 |
+
"loss": 0.1537,
|
| 1377 |
+
"step": 1800
|
| 1378 |
+
},
|
| 1379 |
+
{
|
| 1380 |
+
"epoch": 9.68,
|
| 1381 |
+
"grad_norm": 0.6538177728652954,
|
| 1382 |
+
"learning_rate": 0.00017112299465240642,
|
| 1383 |
+
"loss": 0.1564,
|
| 1384 |
+
"step": 1810
|
| 1385 |
+
},
|
| 1386 |
+
{
|
| 1387 |
+
"epoch": 9.73,
|
| 1388 |
+
"grad_norm": 0.39654332399368286,
|
| 1389 |
+
"learning_rate": 0.00014438502673796793,
|
| 1390 |
+
"loss": 0.1196,
|
| 1391 |
+
"step": 1820
|
| 1392 |
+
},
|
| 1393 |
+
{
|
| 1394 |
+
"epoch": 9.79,
|
| 1395 |
+
"grad_norm": 0.5751528143882751,
|
| 1396 |
+
"learning_rate": 0.00011764705882352942,
|
| 1397 |
+
"loss": 0.1953,
|
| 1398 |
+
"step": 1830
|
| 1399 |
+
},
|
| 1400 |
+
{
|
| 1401 |
+
"epoch": 9.84,
|
| 1402 |
+
"grad_norm": 0.7018762826919556,
|
| 1403 |
+
"learning_rate": 9.09090909090909e-05,
|
| 1404 |
+
"loss": 0.1414,
|
| 1405 |
+
"step": 1840
|
| 1406 |
+
},
|
| 1407 |
+
{
|
| 1408 |
+
"epoch": 9.89,
|
| 1409 |
+
"grad_norm": 0.8955555558204651,
|
| 1410 |
+
"learning_rate": 6.41711229946524e-05,
|
| 1411 |
+
"loss": 0.1415,
|
| 1412 |
+
"step": 1850
|
| 1413 |
+
},
|
| 1414 |
+
{
|
| 1415 |
+
"epoch": 9.95,
|
| 1416 |
+
"grad_norm": 0.29650095105171204,
|
| 1417 |
+
"learning_rate": 3.74331550802139e-05,
|
| 1418 |
+
"loss": 0.1361,
|
| 1419 |
+
"step": 1860
|
| 1420 |
+
},
|
| 1421 |
+
{
|
| 1422 |
+
"epoch": 10.0,
|
| 1423 |
+
"grad_norm": 0.6939311623573303,
|
| 1424 |
+
"learning_rate": 1.0695187165775402e-05,
|
| 1425 |
+
"loss": 0.1898,
|
| 1426 |
+
"step": 1870
|
| 1427 |
+
},
|
| 1428 |
+
{
|
| 1429 |
+
"epoch": 10.0,
|
| 1430 |
+
"eval_accuracy": 0.9789719626168224,
|
| 1431 |
+
"eval_f1": 0.9786328578443323,
|
| 1432 |
+
"eval_loss": 0.06271301954984665,
|
| 1433 |
+
"eval_precision": 0.9764445771965571,
|
| 1434 |
+
"eval_recall": 0.9811556249771411,
|
| 1435 |
+
"eval_runtime": 8.9863,
|
| 1436 |
+
"eval_samples_per_second": 190.512,
|
| 1437 |
+
"eval_steps_per_second": 11.907,
|
| 1438 |
+
"step": 1870
|
| 1439 |
+
},
|
| 1440 |
+
{
|
| 1441 |
+
"epoch": 10.0,
|
| 1442 |
+
"step": 1870,
|
| 1443 |
+
"total_flos": 9.332136680499118e+18,
|
| 1444 |
+
"train_loss": 0.29726991015959553,
|
| 1445 |
+
"train_runtime": 1395.7704,
|
| 1446 |
+
"train_samples_per_second": 85.68,
|
| 1447 |
+
"train_steps_per_second": 1.34
|
| 1448 |
+
}
|
| 1449 |
+
],
|
| 1450 |
+
"logging_steps": 10,
|
| 1451 |
+
"max_steps": 1870,
|
| 1452 |
+
"num_input_tokens_seen": 0,
|
| 1453 |
+
"num_train_epochs": 10,
|
| 1454 |
+
"save_steps": 500,
|
| 1455 |
+
"total_flos": 9.332136680499118e+18,
|
| 1456 |
+
"train_batch_size": 16,
|
| 1457 |
+
"trial_name": null,
|
| 1458 |
+
"trial_params": null
|
| 1459 |
+
}
|