Commit
•
59d1004
1
Parent(s):
37285c2
End of training
Browse files- README.md +5 -5
- 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 [microsoft/swin-large-patch4-window7-224-in22k](https://huggingface.co/microsoft/swin-large-patch4-window7-224-in22k) on the medmnist-v2 dataset.
|
| 25 |
It achieves the following results on the evaluation set:
|
| 26 |
-
- Loss: 0.
|
| 27 |
-
- Accuracy: 0.
|
| 28 |
-
- Precision: 0.
|
| 29 |
-
- Recall: 0.
|
| 30 |
-
- F1: 0.
|
| 31 |
|
| 32 |
## Model description
|
| 33 |
|
|
|
|
| 23 |
|
| 24 |
This model is a fine-tuned version of [microsoft/swin-large-patch4-window7-224-in22k](https://huggingface.co/microsoft/swin-large-patch4-window7-224-in22k) on the medmnist-v2 dataset.
|
| 25 |
It achieves the following results on the evaluation set:
|
| 26 |
+
- Loss: 0.1036
|
| 27 |
+
- Accuracy: 0.9649
|
| 28 |
+
- Precision: 0.9627
|
| 29 |
+
- Recall: 0.9616
|
| 30 |
+
- F1: 0.9619
|
| 31 |
|
| 32 |
## Model description
|
| 33 |
|
all_results.json
ADDED
|
@@ -0,0 +1,16 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 10.0,
|
| 3 |
+
"eval_accuracy": 0.9649225372698041,
|
| 4 |
+
"eval_f1": 0.9618809511152965,
|
| 5 |
+
"eval_loss": 0.10363399982452393,
|
| 6 |
+
"eval_precision": 0.9626584889347929,
|
| 7 |
+
"eval_recall": 0.9615716482526544,
|
| 8 |
+
"eval_runtime": 39.7158,
|
| 9 |
+
"eval_samples_per_second": 86.137,
|
| 10 |
+
"eval_steps_per_second": 5.388,
|
| 11 |
+
"total_flos": 2.1188849626596557e+19,
|
| 12 |
+
"train_loss": 0.34750947773775315,
|
| 13 |
+
"train_runtime": 3122.2212,
|
| 14 |
+
"train_samples_per_second": 38.303,
|
| 15 |
+
"train_steps_per_second": 0.599
|
| 16 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,11 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 10.0,
|
| 3 |
+
"eval_accuracy": 0.9649225372698041,
|
| 4 |
+
"eval_f1": 0.9618809511152965,
|
| 5 |
+
"eval_loss": 0.10363399982452393,
|
| 6 |
+
"eval_precision": 0.9626584889347929,
|
| 7 |
+
"eval_recall": 0.9615716482526544,
|
| 8 |
+
"eval_runtime": 39.7158,
|
| 9 |
+
"eval_samples_per_second": 86.137,
|
| 10 |
+
"eval_steps_per_second": 5.388
|
| 11 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 10.0,
|
| 3 |
+
"total_flos": 2.1188849626596557e+19,
|
| 4 |
+
"train_loss": 0.34750947773775315,
|
| 5 |
+
"train_runtime": 3122.2212,
|
| 6 |
+
"train_samples_per_second": 38.303,
|
| 7 |
+
"train_steps_per_second": 0.599
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,1459 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.9713785046728972,
|
| 3 |
+
"best_model_checkpoint": "swin-large-patch4-window7-224-in22k-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": 2.163198709487915,
|
| 14 |
+
"learning_rate": 0.004973262032085562,
|
| 15 |
+
"loss": 1.5101,
|
| 16 |
+
"step": 10
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.11,
|
| 20 |
+
"grad_norm": 1.4286870956420898,
|
| 21 |
+
"learning_rate": 0.004946524064171123,
|
| 22 |
+
"loss": 0.8667,
|
| 23 |
+
"step": 20
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.16,
|
| 27 |
+
"grad_norm": 1.847931981086731,
|
| 28 |
+
"learning_rate": 0.004919786096256685,
|
| 29 |
+
"loss": 0.7414,
|
| 30 |
+
"step": 30
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.21,
|
| 34 |
+
"grad_norm": 1.5748757123947144,
|
| 35 |
+
"learning_rate": 0.004893048128342246,
|
| 36 |
+
"loss": 0.755,
|
| 37 |
+
"step": 40
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.27,
|
| 41 |
+
"grad_norm": 2.017432928085327,
|
| 42 |
+
"learning_rate": 0.004866310160427808,
|
| 43 |
+
"loss": 0.6683,
|
| 44 |
+
"step": 50
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.32,
|
| 48 |
+
"grad_norm": 1.5988194942474365,
|
| 49 |
+
"learning_rate": 0.004839572192513369,
|
| 50 |
+
"loss": 0.7084,
|
| 51 |
+
"step": 60
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.37,
|
| 55 |
+
"grad_norm": 1.7127466201782227,
|
| 56 |
+
"learning_rate": 0.004812834224598931,
|
| 57 |
+
"loss": 0.6459,
|
| 58 |
+
"step": 70
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.43,
|
| 62 |
+
"grad_norm": 2.1388797760009766,
|
| 63 |
+
"learning_rate": 0.004786096256684492,
|
| 64 |
+
"loss": 0.7116,
|
| 65 |
+
"step": 80
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.48,
|
| 69 |
+
"grad_norm": 2.5939793586730957,
|
| 70 |
+
"learning_rate": 0.004759358288770054,
|
| 71 |
+
"loss": 0.5753,
|
| 72 |
+
"step": 90
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.53,
|
| 76 |
+
"grad_norm": 1.463460087776184,
|
| 77 |
+
"learning_rate": 0.004732620320855615,
|
| 78 |
+
"loss": 0.5938,
|
| 79 |
+
"step": 100
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.59,
|
| 83 |
+
"grad_norm": 1.9902774095535278,
|
| 84 |
+
"learning_rate": 0.004705882352941177,
|
| 85 |
+
"loss": 0.5525,
|
| 86 |
+
"step": 110
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.64,
|
| 90 |
+
"grad_norm": 1.881441593170166,
|
| 91 |
+
"learning_rate": 0.004679144385026738,
|
| 92 |
+
"loss": 0.5788,
|
| 93 |
+
"step": 120
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.7,
|
| 97 |
+
"grad_norm": 2.161348581314087,
|
| 98 |
+
"learning_rate": 0.0046524064171123,
|
| 99 |
+
"loss": 0.5378,
|
| 100 |
+
"step": 130
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 0.75,
|
| 104 |
+
"grad_norm": 1.5160846710205078,
|
| 105 |
+
"learning_rate": 0.0046256684491978615,
|
| 106 |
+
"loss": 0.479,
|
| 107 |
+
"step": 140
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.8,
|
| 111 |
+
"grad_norm": 1.4215080738067627,
|
| 112 |
+
"learning_rate": 0.004598930481283423,
|
| 113 |
+
"loss": 0.5123,
|
| 114 |
+
"step": 150
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.86,
|
| 118 |
+
"grad_norm": 1.2568920850753784,
|
| 119 |
+
"learning_rate": 0.004572192513368984,
|
| 120 |
+
"loss": 0.5499,
|
| 121 |
+
"step": 160
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.91,
|
| 125 |
+
"grad_norm": 0.9570059180259705,
|
| 126 |
+
"learning_rate": 0.004545454545454545,
|
| 127 |
+
"loss": 0.4845,
|
| 128 |
+
"step": 170
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.96,
|
| 132 |
+
"grad_norm": 2.3021810054779053,
|
| 133 |
+
"learning_rate": 0.004518716577540107,
|
| 134 |
+
"loss": 0.5141,
|
| 135 |
+
"step": 180
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 1.0,
|
| 139 |
+
"eval_accuracy": 0.9065420560747663,
|
| 140 |
+
"eval_f1": 0.8872552707825272,
|
| 141 |
+
"eval_loss": 0.2832600176334381,
|
| 142 |
+
"eval_precision": 0.8954019032094056,
|
| 143 |
+
"eval_recall": 0.8949326095168356,
|
| 144 |
+
"eval_runtime": 19.6658,
|
| 145 |
+
"eval_samples_per_second": 87.054,
|
| 146 |
+
"eval_steps_per_second": 5.441,
|
| 147 |
+
"step": 187
|
| 148 |
+
},
|
| 149 |
+
{
|
| 150 |
+
"epoch": 1.02,
|
| 151 |
+
"grad_norm": 1.8552567958831787,
|
| 152 |
+
"learning_rate": 0.004491978609625669,
|
| 153 |
+
"loss": 0.4441,
|
| 154 |
+
"step": 190
|
| 155 |
+
},
|
| 156 |
+
{
|
| 157 |
+
"epoch": 1.07,
|
| 158 |
+
"grad_norm": 2.53872013092041,
|
| 159 |
+
"learning_rate": 0.00446524064171123,
|
| 160 |
+
"loss": 0.4436,
|
| 161 |
+
"step": 200
|
| 162 |
+
},
|
| 163 |
+
{
|
| 164 |
+
"epoch": 1.12,
|
| 165 |
+
"grad_norm": 1.3826777935028076,
|
| 166 |
+
"learning_rate": 0.004438502673796791,
|
| 167 |
+
"loss": 0.4632,
|
| 168 |
+
"step": 210
|
| 169 |
+
},
|
| 170 |
+
{
|
| 171 |
+
"epoch": 1.18,
|
| 172 |
+
"grad_norm": 2.2216227054595947,
|
| 173 |
+
"learning_rate": 0.004411764705882353,
|
| 174 |
+
"loss": 0.4429,
|
| 175 |
+
"step": 220
|
| 176 |
+
},
|
| 177 |
+
{
|
| 178 |
+
"epoch": 1.23,
|
| 179 |
+
"grad_norm": 1.8521422147750854,
|
| 180 |
+
"learning_rate": 0.004385026737967914,
|
| 181 |
+
"loss": 0.4472,
|
| 182 |
+
"step": 230
|
| 183 |
+
},
|
| 184 |
+
{
|
| 185 |
+
"epoch": 1.28,
|
| 186 |
+
"grad_norm": 2.058058977127075,
|
| 187 |
+
"learning_rate": 0.00436096256684492,
|
| 188 |
+
"loss": 0.4757,
|
| 189 |
+
"step": 240
|
| 190 |
+
},
|
| 191 |
+
{
|
| 192 |
+
"epoch": 1.34,
|
| 193 |
+
"grad_norm": 1.1437183618545532,
|
| 194 |
+
"learning_rate": 0.004334224598930481,
|
| 195 |
+
"loss": 0.3436,
|
| 196 |
+
"step": 250
|
| 197 |
+
},
|
| 198 |
+
{
|
| 199 |
+
"epoch": 1.39,
|
| 200 |
+
"grad_norm": 1.761400580406189,
|
| 201 |
+
"learning_rate": 0.0043074866310160425,
|
| 202 |
+
"loss": 0.4958,
|
| 203 |
+
"step": 260
|
| 204 |
+
},
|
| 205 |
+
{
|
| 206 |
+
"epoch": 1.44,
|
| 207 |
+
"grad_norm": 1.4134129285812378,
|
| 208 |
+
"learning_rate": 0.004280748663101605,
|
| 209 |
+
"loss": 0.4519,
|
| 210 |
+
"step": 270
|
| 211 |
+
},
|
| 212 |
+
{
|
| 213 |
+
"epoch": 1.5,
|
| 214 |
+
"grad_norm": 1.7341545820236206,
|
| 215 |
+
"learning_rate": 0.004254010695187166,
|
| 216 |
+
"loss": 0.528,
|
| 217 |
+
"step": 280
|
| 218 |
+
},
|
| 219 |
+
{
|
| 220 |
+
"epoch": 1.55,
|
| 221 |
+
"grad_norm": 2.980020761489868,
|
| 222 |
+
"learning_rate": 0.004227272727272727,
|
| 223 |
+
"loss": 0.5021,
|
| 224 |
+
"step": 290
|
| 225 |
+
},
|
| 226 |
+
{
|
| 227 |
+
"epoch": 1.6,
|
| 228 |
+
"grad_norm": 0.6755030751228333,
|
| 229 |
+
"learning_rate": 0.004200534759358289,
|
| 230 |
+
"loss": 0.4601,
|
| 231 |
+
"step": 300
|
| 232 |
+
},
|
| 233 |
+
{
|
| 234 |
+
"epoch": 1.66,
|
| 235 |
+
"grad_norm": 1.8686202764511108,
|
| 236 |
+
"learning_rate": 0.00417379679144385,
|
| 237 |
+
"loss": 0.4433,
|
| 238 |
+
"step": 310
|
| 239 |
+
},
|
| 240 |
+
{
|
| 241 |
+
"epoch": 1.71,
|
| 242 |
+
"grad_norm": 1.371077299118042,
|
| 243 |
+
"learning_rate": 0.004147058823529412,
|
| 244 |
+
"loss": 0.4323,
|
| 245 |
+
"step": 320
|
| 246 |
+
},
|
| 247 |
+
{
|
| 248 |
+
"epoch": 1.76,
|
| 249 |
+
"grad_norm": 1.0771093368530273,
|
| 250 |
+
"learning_rate": 0.004120320855614973,
|
| 251 |
+
"loss": 0.4251,
|
| 252 |
+
"step": 330
|
| 253 |
+
},
|
| 254 |
+
{
|
| 255 |
+
"epoch": 1.82,
|
| 256 |
+
"grad_norm": 1.185023546218872,
|
| 257 |
+
"learning_rate": 0.004093582887700535,
|
| 258 |
+
"loss": 0.4881,
|
| 259 |
+
"step": 340
|
| 260 |
+
},
|
| 261 |
+
{
|
| 262 |
+
"epoch": 1.87,
|
| 263 |
+
"grad_norm": 0.9843281507492065,
|
| 264 |
+
"learning_rate": 0.004066844919786096,
|
| 265 |
+
"loss": 0.4483,
|
| 266 |
+
"step": 350
|
| 267 |
+
},
|
| 268 |
+
{
|
| 269 |
+
"epoch": 1.93,
|
| 270 |
+
"grad_norm": 1.6477869749069214,
|
| 271 |
+
"learning_rate": 0.004040106951871658,
|
| 272 |
+
"loss": 0.4956,
|
| 273 |
+
"step": 360
|
| 274 |
+
},
|
| 275 |
+
{
|
| 276 |
+
"epoch": 1.98,
|
| 277 |
+
"grad_norm": 1.7044633626937866,
|
| 278 |
+
"learning_rate": 0.004013368983957219,
|
| 279 |
+
"loss": 0.4176,
|
| 280 |
+
"step": 370
|
| 281 |
+
},
|
| 282 |
+
{
|
| 283 |
+
"epoch": 2.0,
|
| 284 |
+
"eval_accuracy": 0.9310747663551402,
|
| 285 |
+
"eval_f1": 0.9182291375322846,
|
| 286 |
+
"eval_loss": 0.198581263422966,
|
| 287 |
+
"eval_precision": 0.924344363515161,
|
| 288 |
+
"eval_recall": 0.9209393532374213,
|
| 289 |
+
"eval_runtime": 19.6732,
|
| 290 |
+
"eval_samples_per_second": 87.022,
|
| 291 |
+
"eval_steps_per_second": 5.439,
|
| 292 |
+
"step": 374
|
| 293 |
+
},
|
| 294 |
+
{
|
| 295 |
+
"epoch": 2.03,
|
| 296 |
+
"grad_norm": 1.662027359008789,
|
| 297 |
+
"learning_rate": 0.003986631016042781,
|
| 298 |
+
"loss": 0.4022,
|
| 299 |
+
"step": 380
|
| 300 |
+
},
|
| 301 |
+
{
|
| 302 |
+
"epoch": 2.09,
|
| 303 |
+
"grad_norm": 1.188351035118103,
|
| 304 |
+
"learning_rate": 0.003959893048128342,
|
| 305 |
+
"loss": 0.3758,
|
| 306 |
+
"step": 390
|
| 307 |
+
},
|
| 308 |
+
{
|
| 309 |
+
"epoch": 2.14,
|
| 310 |
+
"grad_norm": 2.2225048542022705,
|
| 311 |
+
"learning_rate": 0.003933155080213904,
|
| 312 |
+
"loss": 0.4491,
|
| 313 |
+
"step": 400
|
| 314 |
+
},
|
| 315 |
+
{
|
| 316 |
+
"epoch": 2.19,
|
| 317 |
+
"grad_norm": 1.683356761932373,
|
| 318 |
+
"learning_rate": 0.0039064171122994654,
|
| 319 |
+
"loss": 0.3647,
|
| 320 |
+
"step": 410
|
| 321 |
+
},
|
| 322 |
+
{
|
| 323 |
+
"epoch": 2.25,
|
| 324 |
+
"grad_norm": 1.7646687030792236,
|
| 325 |
+
"learning_rate": 0.0038796791443850265,
|
| 326 |
+
"loss": 0.4666,
|
| 327 |
+
"step": 420
|
| 328 |
+
},
|
| 329 |
+
{
|
| 330 |
+
"epoch": 2.3,
|
| 331 |
+
"grad_norm": 2.173644781112671,
|
| 332 |
+
"learning_rate": 0.0038529411764705885,
|
| 333 |
+
"loss": 0.4314,
|
| 334 |
+
"step": 430
|
| 335 |
+
},
|
| 336 |
+
{
|
| 337 |
+
"epoch": 2.35,
|
| 338 |
+
"grad_norm": 0.8064551949501038,
|
| 339 |
+
"learning_rate": 0.00382620320855615,
|
| 340 |
+
"loss": 0.3944,
|
| 341 |
+
"step": 440
|
| 342 |
+
},
|
| 343 |
+
{
|
| 344 |
+
"epoch": 2.41,
|
| 345 |
+
"grad_norm": 0.9698677062988281,
|
| 346 |
+
"learning_rate": 0.003799465240641711,
|
| 347 |
+
"loss": 0.4314,
|
| 348 |
+
"step": 450
|
| 349 |
+
},
|
| 350 |
+
{
|
| 351 |
+
"epoch": 2.46,
|
| 352 |
+
"grad_norm": 0.9321346879005432,
|
| 353 |
+
"learning_rate": 0.0037727272727272726,
|
| 354 |
+
"loss": 0.467,
|
| 355 |
+
"step": 460
|
| 356 |
+
},
|
| 357 |
+
{
|
| 358 |
+
"epoch": 2.51,
|
| 359 |
+
"grad_norm": 2.6592769622802734,
|
| 360 |
+
"learning_rate": 0.003745989304812834,
|
| 361 |
+
"loss": 0.4024,
|
| 362 |
+
"step": 470
|
| 363 |
+
},
|
| 364 |
+
{
|
| 365 |
+
"epoch": 2.57,
|
| 366 |
+
"grad_norm": 1.7124016284942627,
|
| 367 |
+
"learning_rate": 0.003719251336898396,
|
| 368 |
+
"loss": 0.3283,
|
| 369 |
+
"step": 480
|
| 370 |
+
},
|
| 371 |
+
{
|
| 372 |
+
"epoch": 2.62,
|
| 373 |
+
"grad_norm": 3.178034543991089,
|
| 374 |
+
"learning_rate": 0.0036925133689839572,
|
| 375 |
+
"loss": 0.4377,
|
| 376 |
+
"step": 490
|
| 377 |
+
},
|
| 378 |
+
{
|
| 379 |
+
"epoch": 2.67,
|
| 380 |
+
"grad_norm": 1.2681751251220703,
|
| 381 |
+
"learning_rate": 0.0036657754010695188,
|
| 382 |
+
"loss": 0.3866,
|
| 383 |
+
"step": 500
|
| 384 |
+
},
|
| 385 |
+
{
|
| 386 |
+
"epoch": 2.73,
|
| 387 |
+
"grad_norm": 1.1923668384552002,
|
| 388 |
+
"learning_rate": 0.0036390374331550803,
|
| 389 |
+
"loss": 0.3366,
|
| 390 |
+
"step": 510
|
| 391 |
+
},
|
| 392 |
+
{
|
| 393 |
+
"epoch": 2.78,
|
| 394 |
+
"grad_norm": 1.499803066253662,
|
| 395 |
+
"learning_rate": 0.0036122994652406414,
|
| 396 |
+
"loss": 0.4578,
|
| 397 |
+
"step": 520
|
| 398 |
+
},
|
| 399 |
+
{
|
| 400 |
+
"epoch": 2.83,
|
| 401 |
+
"grad_norm": 1.887222409248352,
|
| 402 |
+
"learning_rate": 0.0035855614973262034,
|
| 403 |
+
"loss": 0.4189,
|
| 404 |
+
"step": 530
|
| 405 |
+
},
|
| 406 |
+
{
|
| 407 |
+
"epoch": 2.89,
|
| 408 |
+
"grad_norm": 1.3592134714126587,
|
| 409 |
+
"learning_rate": 0.003558823529411765,
|
| 410 |
+
"loss": 0.4008,
|
| 411 |
+
"step": 540
|
| 412 |
+
},
|
| 413 |
+
{
|
| 414 |
+
"epoch": 2.94,
|
| 415 |
+
"grad_norm": 3.0257527828216553,
|
| 416 |
+
"learning_rate": 0.0035320855614973264,
|
| 417 |
+
"loss": 0.3774,
|
| 418 |
+
"step": 550
|
| 419 |
+
},
|
| 420 |
+
{
|
| 421 |
+
"epoch": 2.99,
|
| 422 |
+
"grad_norm": 1.093493103981018,
|
| 423 |
+
"learning_rate": 0.0035053475935828875,
|
| 424 |
+
"loss": 0.3454,
|
| 425 |
+
"step": 560
|
| 426 |
+
},
|
| 427 |
+
{
|
| 428 |
+
"epoch": 3.0,
|
| 429 |
+
"eval_accuracy": 0.9503504672897196,
|
| 430 |
+
"eval_f1": 0.9402807880914787,
|
| 431 |
+
"eval_loss": 0.15674300491809845,
|
| 432 |
+
"eval_precision": 0.9426615409260363,
|
| 433 |
+
"eval_recall": 0.9397047025483766,
|
| 434 |
+
"eval_runtime": 19.5644,
|
| 435 |
+
"eval_samples_per_second": 87.506,
|
| 436 |
+
"eval_steps_per_second": 5.469,
|
| 437 |
+
"step": 561
|
| 438 |
+
},
|
| 439 |
+
{
|
| 440 |
+
"epoch": 3.05,
|
| 441 |
+
"grad_norm": 1.7053543329238892,
|
| 442 |
+
"learning_rate": 0.003478609625668449,
|
| 443 |
+
"loss": 0.3776,
|
| 444 |
+
"step": 570
|
| 445 |
+
},
|
| 446 |
+
{
|
| 447 |
+
"epoch": 3.1,
|
| 448 |
+
"grad_norm": 1.5041882991790771,
|
| 449 |
+
"learning_rate": 0.003451871657754011,
|
| 450 |
+
"loss": 0.4058,
|
| 451 |
+
"step": 580
|
| 452 |
+
},
|
| 453 |
+
{
|
| 454 |
+
"epoch": 3.16,
|
| 455 |
+
"grad_norm": 1.3619967699050903,
|
| 456 |
+
"learning_rate": 0.0034251336898395725,
|
| 457 |
+
"loss": 0.3646,
|
| 458 |
+
"step": 590
|
| 459 |
+
},
|
| 460 |
+
{
|
| 461 |
+
"epoch": 3.21,
|
| 462 |
+
"grad_norm": 1.1415998935699463,
|
| 463 |
+
"learning_rate": 0.0033983957219251336,
|
| 464 |
+
"loss": 0.4906,
|
| 465 |
+
"step": 600
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 3.26,
|
| 469 |
+
"grad_norm": 1.6870795488357544,
|
| 470 |
+
"learning_rate": 0.003371657754010695,
|
| 471 |
+
"loss": 0.3828,
|
| 472 |
+
"step": 610
|
| 473 |
+
},
|
| 474 |
+
{
|
| 475 |
+
"epoch": 3.32,
|
| 476 |
+
"grad_norm": 1.0538561344146729,
|
| 477 |
+
"learning_rate": 0.0033449197860962567,
|
| 478 |
+
"loss": 0.3728,
|
| 479 |
+
"step": 620
|
| 480 |
+
},
|
| 481 |
+
{
|
| 482 |
+
"epoch": 3.37,
|
| 483 |
+
"grad_norm": 2.340454339981079,
|
| 484 |
+
"learning_rate": 0.0033181818181818186,
|
| 485 |
+
"loss": 0.3809,
|
| 486 |
+
"step": 630
|
| 487 |
+
},
|
| 488 |
+
{
|
| 489 |
+
"epoch": 3.42,
|
| 490 |
+
"grad_norm": 2.317230224609375,
|
| 491 |
+
"learning_rate": 0.0032914438502673797,
|
| 492 |
+
"loss": 0.3391,
|
| 493 |
+
"step": 640
|
| 494 |
+
},
|
| 495 |
+
{
|
| 496 |
+
"epoch": 3.48,
|
| 497 |
+
"grad_norm": 1.242281436920166,
|
| 498 |
+
"learning_rate": 0.0032647058823529413,
|
| 499 |
+
"loss": 0.4091,
|
| 500 |
+
"step": 650
|
| 501 |
+
},
|
| 502 |
+
{
|
| 503 |
+
"epoch": 3.53,
|
| 504 |
+
"grad_norm": 1.23116934299469,
|
| 505 |
+
"learning_rate": 0.003237967914438503,
|
| 506 |
+
"loss": 0.3592,
|
| 507 |
+
"step": 660
|
| 508 |
+
},
|
| 509 |
+
{
|
| 510 |
+
"epoch": 3.58,
|
| 511 |
+
"grad_norm": 1.117090106010437,
|
| 512 |
+
"learning_rate": 0.003211229946524064,
|
| 513 |
+
"loss": 0.3867,
|
| 514 |
+
"step": 670
|
| 515 |
+
},
|
| 516 |
+
{
|
| 517 |
+
"epoch": 3.64,
|
| 518 |
+
"grad_norm": 1.0917716026306152,
|
| 519 |
+
"learning_rate": 0.0031844919786096254,
|
| 520 |
+
"loss": 0.4386,
|
| 521 |
+
"step": 680
|
| 522 |
+
},
|
| 523 |
+
{
|
| 524 |
+
"epoch": 3.69,
|
| 525 |
+
"grad_norm": 1.2080508470535278,
|
| 526 |
+
"learning_rate": 0.0031577540106951874,
|
| 527 |
+
"loss": 0.3466,
|
| 528 |
+
"step": 690
|
| 529 |
+
},
|
| 530 |
+
{
|
| 531 |
+
"epoch": 3.74,
|
| 532 |
+
"grad_norm": 1.695580244064331,
|
| 533 |
+
"learning_rate": 0.003131016042780749,
|
| 534 |
+
"loss": 0.3147,
|
| 535 |
+
"step": 700
|
| 536 |
+
},
|
| 537 |
+
{
|
| 538 |
+
"epoch": 3.8,
|
| 539 |
+
"grad_norm": 1.1604491472244263,
|
| 540 |
+
"learning_rate": 0.00310427807486631,
|
| 541 |
+
"loss": 0.3585,
|
| 542 |
+
"step": 710
|
| 543 |
+
},
|
| 544 |
+
{
|
| 545 |
+
"epoch": 3.85,
|
| 546 |
+
"grad_norm": 1.8931636810302734,
|
| 547 |
+
"learning_rate": 0.0030775401069518715,
|
| 548 |
+
"loss": 0.3578,
|
| 549 |
+
"step": 720
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"epoch": 3.9,
|
| 553 |
+
"grad_norm": 1.4620869159698486,
|
| 554 |
+
"learning_rate": 0.003050802139037433,
|
| 555 |
+
"loss": 0.3522,
|
| 556 |
+
"step": 730
|
| 557 |
+
},
|
| 558 |
+
{
|
| 559 |
+
"epoch": 3.96,
|
| 560 |
+
"grad_norm": 1.3944414854049683,
|
| 561 |
+
"learning_rate": 0.003024064171122995,
|
| 562 |
+
"loss": 0.3228,
|
| 563 |
+
"step": 740
|
| 564 |
+
},
|
| 565 |
+
{
|
| 566 |
+
"epoch": 4.0,
|
| 567 |
+
"eval_accuracy": 0.9357476635514018,
|
| 568 |
+
"eval_f1": 0.9283408808159395,
|
| 569 |
+
"eval_loss": 0.1848856657743454,
|
| 570 |
+
"eval_precision": 0.9231661406901872,
|
| 571 |
+
"eval_recall": 0.9426484043891363,
|
| 572 |
+
"eval_runtime": 19.683,
|
| 573 |
+
"eval_samples_per_second": 86.979,
|
| 574 |
+
"eval_steps_per_second": 5.436,
|
| 575 |
+
"step": 748
|
| 576 |
+
},
|
| 577 |
+
{
|
| 578 |
+
"epoch": 4.01,
|
| 579 |
+
"grad_norm": 1.7614619731903076,
|
| 580 |
+
"learning_rate": 0.002997326203208556,
|
| 581 |
+
"loss": 0.3463,
|
| 582 |
+
"step": 750
|
| 583 |
+
},
|
| 584 |
+
{
|
| 585 |
+
"epoch": 4.06,
|
| 586 |
+
"grad_norm": 2.866691827774048,
|
| 587 |
+
"learning_rate": 0.0029705882352941177,
|
| 588 |
+
"loss": 0.3431,
|
| 589 |
+
"step": 760
|
| 590 |
+
},
|
| 591 |
+
{
|
| 592 |
+
"epoch": 4.12,
|
| 593 |
+
"grad_norm": 3.0871615409851074,
|
| 594 |
+
"learning_rate": 0.002943850267379679,
|
| 595 |
+
"loss": 0.4329,
|
| 596 |
+
"step": 770
|
| 597 |
+
},
|
| 598 |
+
{
|
| 599 |
+
"epoch": 4.17,
|
| 600 |
+
"grad_norm": 1.3399722576141357,
|
| 601 |
+
"learning_rate": 0.0029171122994652403,
|
| 602 |
+
"loss": 0.3992,
|
| 603 |
+
"step": 780
|
| 604 |
+
},
|
| 605 |
+
{
|
| 606 |
+
"epoch": 4.22,
|
| 607 |
+
"grad_norm": 1.440559983253479,
|
| 608 |
+
"learning_rate": 0.0028903743315508022,
|
| 609 |
+
"loss": 0.3333,
|
| 610 |
+
"step": 790
|
| 611 |
+
},
|
| 612 |
+
{
|
| 613 |
+
"epoch": 4.28,
|
| 614 |
+
"grad_norm": 1.4606270790100098,
|
| 615 |
+
"learning_rate": 0.0028636363636363638,
|
| 616 |
+
"loss": 0.3108,
|
| 617 |
+
"step": 800
|
| 618 |
+
},
|
| 619 |
+
{
|
| 620 |
+
"epoch": 4.33,
|
| 621 |
+
"grad_norm": 2.4641544818878174,
|
| 622 |
+
"learning_rate": 0.0028368983957219253,
|
| 623 |
+
"loss": 0.3436,
|
| 624 |
+
"step": 810
|
| 625 |
+
},
|
| 626 |
+
{
|
| 627 |
+
"epoch": 4.39,
|
| 628 |
+
"grad_norm": 1.9653208255767822,
|
| 629 |
+
"learning_rate": 0.0028101604278074864,
|
| 630 |
+
"loss": 0.2766,
|
| 631 |
+
"step": 820
|
| 632 |
+
},
|
| 633 |
+
{
|
| 634 |
+
"epoch": 4.44,
|
| 635 |
+
"grad_norm": 1.0840091705322266,
|
| 636 |
+
"learning_rate": 0.002783422459893048,
|
| 637 |
+
"loss": 0.2568,
|
| 638 |
+
"step": 830
|
| 639 |
+
},
|
| 640 |
+
{
|
| 641 |
+
"epoch": 4.49,
|
| 642 |
+
"grad_norm": 1.0625332593917847,
|
| 643 |
+
"learning_rate": 0.00275668449197861,
|
| 644 |
+
"loss": 0.3366,
|
| 645 |
+
"step": 840
|
| 646 |
+
},
|
| 647 |
+
{
|
| 648 |
+
"epoch": 4.55,
|
| 649 |
+
"grad_norm": 0.9171143174171448,
|
| 650 |
+
"learning_rate": 0.0027299465240641714,
|
| 651 |
+
"loss": 0.339,
|
| 652 |
+
"step": 850
|
| 653 |
+
},
|
| 654 |
+
{
|
| 655 |
+
"epoch": 4.6,
|
| 656 |
+
"grad_norm": 1.6296868324279785,
|
| 657 |
+
"learning_rate": 0.0027032085561497325,
|
| 658 |
+
"loss": 0.359,
|
| 659 |
+
"step": 860
|
| 660 |
+
},
|
| 661 |
+
{
|
| 662 |
+
"epoch": 4.65,
|
| 663 |
+
"grad_norm": 1.949312448501587,
|
| 664 |
+
"learning_rate": 0.002676470588235294,
|
| 665 |
+
"loss": 0.3529,
|
| 666 |
+
"step": 870
|
| 667 |
+
},
|
| 668 |
+
{
|
| 669 |
+
"epoch": 4.71,
|
| 670 |
+
"grad_norm": 1.6241270303726196,
|
| 671 |
+
"learning_rate": 0.0026497326203208556,
|
| 672 |
+
"loss": 0.3364,
|
| 673 |
+
"step": 880
|
| 674 |
+
},
|
| 675 |
+
{
|
| 676 |
+
"epoch": 4.76,
|
| 677 |
+
"grad_norm": 2.172145366668701,
|
| 678 |
+
"learning_rate": 0.0026229946524064175,
|
| 679 |
+
"loss": 0.3374,
|
| 680 |
+
"step": 890
|
| 681 |
+
},
|
| 682 |
+
{
|
| 683 |
+
"epoch": 4.81,
|
| 684 |
+
"grad_norm": 3.377912998199463,
|
| 685 |
+
"learning_rate": 0.0025962566844919786,
|
| 686 |
+
"loss": 0.3555,
|
| 687 |
+
"step": 900
|
| 688 |
+
},
|
| 689 |
+
{
|
| 690 |
+
"epoch": 4.87,
|
| 691 |
+
"grad_norm": 1.194082260131836,
|
| 692 |
+
"learning_rate": 0.00256951871657754,
|
| 693 |
+
"loss": 0.3354,
|
| 694 |
+
"step": 910
|
| 695 |
+
},
|
| 696 |
+
{
|
| 697 |
+
"epoch": 4.92,
|
| 698 |
+
"grad_norm": 1.774932861328125,
|
| 699 |
+
"learning_rate": 0.0025427807486631017,
|
| 700 |
+
"loss": 0.3728,
|
| 701 |
+
"step": 920
|
| 702 |
+
},
|
| 703 |
+
{
|
| 704 |
+
"epoch": 4.97,
|
| 705 |
+
"grad_norm": 0.9065486192703247,
|
| 706 |
+
"learning_rate": 0.002516042780748663,
|
| 707 |
+
"loss": 0.3382,
|
| 708 |
+
"step": 930
|
| 709 |
+
},
|
| 710 |
+
{
|
| 711 |
+
"epoch": 5.0,
|
| 712 |
+
"eval_accuracy": 0.9398364485981309,
|
| 713 |
+
"eval_f1": 0.9320964504504674,
|
| 714 |
+
"eval_loss": 0.16266803443431854,
|
| 715 |
+
"eval_precision": 0.9301560138584124,
|
| 716 |
+
"eval_recall": 0.9396981551324834,
|
| 717 |
+
"eval_runtime": 19.6531,
|
| 718 |
+
"eval_samples_per_second": 87.111,
|
| 719 |
+
"eval_steps_per_second": 5.444,
|
| 720 |
+
"step": 935
|
| 721 |
+
},
|
| 722 |
+
{
|
| 723 |
+
"epoch": 5.03,
|
| 724 |
+
"grad_norm": 0.8373203873634338,
|
| 725 |
+
"learning_rate": 0.0024893048128342248,
|
| 726 |
+
"loss": 0.3115,
|
| 727 |
+
"step": 940
|
| 728 |
+
},
|
| 729 |
+
{
|
| 730 |
+
"epoch": 5.08,
|
| 731 |
+
"grad_norm": 1.6470876932144165,
|
| 732 |
+
"learning_rate": 0.002462566844919786,
|
| 733 |
+
"loss": 0.3746,
|
| 734 |
+
"step": 950
|
| 735 |
+
},
|
| 736 |
+
{
|
| 737 |
+
"epoch": 5.13,
|
| 738 |
+
"grad_norm": 2.556999444961548,
|
| 739 |
+
"learning_rate": 0.002435828877005348,
|
| 740 |
+
"loss": 0.3411,
|
| 741 |
+
"step": 960
|
| 742 |
+
},
|
| 743 |
+
{
|
| 744 |
+
"epoch": 5.19,
|
| 745 |
+
"grad_norm": 1.753217101097107,
|
| 746 |
+
"learning_rate": 0.002409090909090909,
|
| 747 |
+
"loss": 0.3095,
|
| 748 |
+
"step": 970
|
| 749 |
+
},
|
| 750 |
+
{
|
| 751 |
+
"epoch": 5.24,
|
| 752 |
+
"grad_norm": 2.667759895324707,
|
| 753 |
+
"learning_rate": 0.0023823529411764704,
|
| 754 |
+
"loss": 0.3358,
|
| 755 |
+
"step": 980
|
| 756 |
+
},
|
| 757 |
+
{
|
| 758 |
+
"epoch": 5.29,
|
| 759 |
+
"grad_norm": 1.6711212396621704,
|
| 760 |
+
"learning_rate": 0.002355614973262032,
|
| 761 |
+
"loss": 0.3263,
|
| 762 |
+
"step": 990
|
| 763 |
+
},
|
| 764 |
+
{
|
| 765 |
+
"epoch": 5.35,
|
| 766 |
+
"grad_norm": 1.8793816566467285,
|
| 767 |
+
"learning_rate": 0.0023288770053475935,
|
| 768 |
+
"loss": 0.3245,
|
| 769 |
+
"step": 1000
|
| 770 |
+
},
|
| 771 |
+
{
|
| 772 |
+
"epoch": 5.4,
|
| 773 |
+
"grad_norm": 1.3059521913528442,
|
| 774 |
+
"learning_rate": 0.002302139037433155,
|
| 775 |
+
"loss": 0.2904,
|
| 776 |
+
"step": 1010
|
| 777 |
+
},
|
| 778 |
+
{
|
| 779 |
+
"epoch": 5.45,
|
| 780 |
+
"grad_norm": 1.765958309173584,
|
| 781 |
+
"learning_rate": 0.0022754010695187166,
|
| 782 |
+
"loss": 0.3424,
|
| 783 |
+
"step": 1020
|
| 784 |
+
},
|
| 785 |
+
{
|
| 786 |
+
"epoch": 5.51,
|
| 787 |
+
"grad_norm": 0.9322473406791687,
|
| 788 |
+
"learning_rate": 0.002248663101604278,
|
| 789 |
+
"loss": 0.3716,
|
| 790 |
+
"step": 1030
|
| 791 |
+
},
|
| 792 |
+
{
|
| 793 |
+
"epoch": 5.56,
|
| 794 |
+
"grad_norm": 2.082515239715576,
|
| 795 |
+
"learning_rate": 0.0022219251336898396,
|
| 796 |
+
"loss": 0.2967,
|
| 797 |
+
"step": 1040
|
| 798 |
+
},
|
| 799 |
+
{
|
| 800 |
+
"epoch": 5.61,
|
| 801 |
+
"grad_norm": 1.6903836727142334,
|
| 802 |
+
"learning_rate": 0.002195187165775401,
|
| 803 |
+
"loss": 0.3244,
|
| 804 |
+
"step": 1050
|
| 805 |
+
},
|
| 806 |
+
{
|
| 807 |
+
"epoch": 5.67,
|
| 808 |
+
"grad_norm": 1.1631466150283813,
|
| 809 |
+
"learning_rate": 0.0021684491978609627,
|
| 810 |
+
"loss": 0.3141,
|
| 811 |
+
"step": 1060
|
| 812 |
+
},
|
| 813 |
+
{
|
| 814 |
+
"epoch": 5.72,
|
| 815 |
+
"grad_norm": 2.086376428604126,
|
| 816 |
+
"learning_rate": 0.002141711229946524,
|
| 817 |
+
"loss": 0.3211,
|
| 818 |
+
"step": 1070
|
| 819 |
+
},
|
| 820 |
+
{
|
| 821 |
+
"epoch": 5.78,
|
| 822 |
+
"grad_norm": 1.709187626838684,
|
| 823 |
+
"learning_rate": 0.0021149732620320857,
|
| 824 |
+
"loss": 0.3039,
|
| 825 |
+
"step": 1080
|
| 826 |
+
},
|
| 827 |
+
{
|
| 828 |
+
"epoch": 5.83,
|
| 829 |
+
"grad_norm": 1.7365305423736572,
|
| 830 |
+
"learning_rate": 0.0020882352941176473,
|
| 831 |
+
"loss": 0.2937,
|
| 832 |
+
"step": 1090
|
| 833 |
+
},
|
| 834 |
+
{
|
| 835 |
+
"epoch": 5.88,
|
| 836 |
+
"grad_norm": 1.2648741006851196,
|
| 837 |
+
"learning_rate": 0.0020614973262032084,
|
| 838 |
+
"loss": 0.2951,
|
| 839 |
+
"step": 1100
|
| 840 |
+
},
|
| 841 |
+
{
|
| 842 |
+
"epoch": 5.94,
|
| 843 |
+
"grad_norm": 1.2121895551681519,
|
| 844 |
+
"learning_rate": 0.00203475935828877,
|
| 845 |
+
"loss": 0.242,
|
| 846 |
+
"step": 1110
|
| 847 |
+
},
|
| 848 |
+
{
|
| 849 |
+
"epoch": 5.99,
|
| 850 |
+
"grad_norm": 1.6397563219070435,
|
| 851 |
+
"learning_rate": 0.0020080213903743314,
|
| 852 |
+
"loss": 0.3363,
|
| 853 |
+
"step": 1120
|
| 854 |
+
},
|
| 855 |
+
{
|
| 856 |
+
"epoch": 6.0,
|
| 857 |
+
"eval_accuracy": 0.9509345794392523,
|
| 858 |
+
"eval_f1": 0.9456282248184136,
|
| 859 |
+
"eval_loss": 0.14138737320899963,
|
| 860 |
+
"eval_precision": 0.9497944760971885,
|
| 861 |
+
"eval_recall": 0.9441674024122191,
|
| 862 |
+
"eval_runtime": 19.937,
|
| 863 |
+
"eval_samples_per_second": 85.87,
|
| 864 |
+
"eval_steps_per_second": 5.367,
|
| 865 |
+
"step": 1122
|
| 866 |
+
},
|
| 867 |
+
{
|
| 868 |
+
"epoch": 6.04,
|
| 869 |
+
"grad_norm": 1.3460767269134521,
|
| 870 |
+
"learning_rate": 0.001981283422459893,
|
| 871 |
+
"loss": 0.3134,
|
| 872 |
+
"step": 1130
|
| 873 |
+
},
|
| 874 |
+
{
|
| 875 |
+
"epoch": 6.1,
|
| 876 |
+
"grad_norm": 1.2124683856964111,
|
| 877 |
+
"learning_rate": 0.0019545454545454545,
|
| 878 |
+
"loss": 0.3028,
|
| 879 |
+
"step": 1140
|
| 880 |
+
},
|
| 881 |
+
{
|
| 882 |
+
"epoch": 6.15,
|
| 883 |
+
"grad_norm": 0.8806934952735901,
|
| 884 |
+
"learning_rate": 0.001927807486631016,
|
| 885 |
+
"loss": 0.2589,
|
| 886 |
+
"step": 1150
|
| 887 |
+
},
|
| 888 |
+
{
|
| 889 |
+
"epoch": 6.2,
|
| 890 |
+
"grad_norm": 1.059187889099121,
|
| 891 |
+
"learning_rate": 0.0019010695187165775,
|
| 892 |
+
"loss": 0.2888,
|
| 893 |
+
"step": 1160
|
| 894 |
+
},
|
| 895 |
+
{
|
| 896 |
+
"epoch": 6.26,
|
| 897 |
+
"grad_norm": 2.5121827125549316,
|
| 898 |
+
"learning_rate": 0.001874331550802139,
|
| 899 |
+
"loss": 0.2741,
|
| 900 |
+
"step": 1170
|
| 901 |
+
},
|
| 902 |
+
{
|
| 903 |
+
"epoch": 6.31,
|
| 904 |
+
"grad_norm": 1.0052329301834106,
|
| 905 |
+
"learning_rate": 0.0018475935828877006,
|
| 906 |
+
"loss": 0.3519,
|
| 907 |
+
"step": 1180
|
| 908 |
+
},
|
| 909 |
+
{
|
| 910 |
+
"epoch": 6.36,
|
| 911 |
+
"grad_norm": 1.4301072359085083,
|
| 912 |
+
"learning_rate": 0.0018208556149732621,
|
| 913 |
+
"loss": 0.2937,
|
| 914 |
+
"step": 1190
|
| 915 |
+
},
|
| 916 |
+
{
|
| 917 |
+
"epoch": 6.42,
|
| 918 |
+
"grad_norm": 1.09031343460083,
|
| 919 |
+
"learning_rate": 0.0017941176470588236,
|
| 920 |
+
"loss": 0.2252,
|
| 921 |
+
"step": 1200
|
| 922 |
+
},
|
| 923 |
+
{
|
| 924 |
+
"epoch": 6.47,
|
| 925 |
+
"grad_norm": 1.9657083749771118,
|
| 926 |
+
"learning_rate": 0.001767379679144385,
|
| 927 |
+
"loss": 0.267,
|
| 928 |
+
"step": 1210
|
| 929 |
+
},
|
| 930 |
+
{
|
| 931 |
+
"epoch": 6.52,
|
| 932 |
+
"grad_norm": 3.7427196502685547,
|
| 933 |
+
"learning_rate": 0.0017406417112299467,
|
| 934 |
+
"loss": 0.2493,
|
| 935 |
+
"step": 1220
|
| 936 |
+
},
|
| 937 |
+
{
|
| 938 |
+
"epoch": 6.58,
|
| 939 |
+
"grad_norm": 1.7291096448898315,
|
| 940 |
+
"learning_rate": 0.001713903743315508,
|
| 941 |
+
"loss": 0.2558,
|
| 942 |
+
"step": 1230
|
| 943 |
+
},
|
| 944 |
+
{
|
| 945 |
+
"epoch": 6.63,
|
| 946 |
+
"grad_norm": 2.8834567070007324,
|
| 947 |
+
"learning_rate": 0.0016871657754010698,
|
| 948 |
+
"loss": 0.3167,
|
| 949 |
+
"step": 1240
|
| 950 |
+
},
|
| 951 |
+
{
|
| 952 |
+
"epoch": 6.68,
|
| 953 |
+
"grad_norm": 1.6702009439468384,
|
| 954 |
+
"learning_rate": 0.001660427807486631,
|
| 955 |
+
"loss": 0.274,
|
| 956 |
+
"step": 1250
|
| 957 |
+
},
|
| 958 |
+
{
|
| 959 |
+
"epoch": 6.74,
|
| 960 |
+
"grad_norm": 1.7623697519302368,
|
| 961 |
+
"learning_rate": 0.0016336898395721924,
|
| 962 |
+
"loss": 0.2481,
|
| 963 |
+
"step": 1260
|
| 964 |
+
},
|
| 965 |
+
{
|
| 966 |
+
"epoch": 6.79,
|
| 967 |
+
"grad_norm": 1.8855972290039062,
|
| 968 |
+
"learning_rate": 0.0016069518716577541,
|
| 969 |
+
"loss": 0.2424,
|
| 970 |
+
"step": 1270
|
| 971 |
+
},
|
| 972 |
+
{
|
| 973 |
+
"epoch": 6.84,
|
| 974 |
+
"grad_norm": 1.7909148931503296,
|
| 975 |
+
"learning_rate": 0.0015802139037433154,
|
| 976 |
+
"loss": 0.2361,
|
| 977 |
+
"step": 1280
|
| 978 |
+
},
|
| 979 |
+
{
|
| 980 |
+
"epoch": 6.9,
|
| 981 |
+
"grad_norm": 1.424047589302063,
|
| 982 |
+
"learning_rate": 0.001553475935828877,
|
| 983 |
+
"loss": 0.2834,
|
| 984 |
+
"step": 1290
|
| 985 |
+
},
|
| 986 |
+
{
|
| 987 |
+
"epoch": 6.95,
|
| 988 |
+
"grad_norm": 1.3470966815948486,
|
| 989 |
+
"learning_rate": 0.0015267379679144385,
|
| 990 |
+
"loss": 0.2981,
|
| 991 |
+
"step": 1300
|
| 992 |
+
},
|
| 993 |
+
{
|
| 994 |
+
"epoch": 7.0,
|
| 995 |
+
"eval_accuracy": 0.9544392523364486,
|
| 996 |
+
"eval_f1": 0.9480272544883982,
|
| 997 |
+
"eval_loss": 0.11172817647457123,
|
| 998 |
+
"eval_precision": 0.9458066711610336,
|
| 999 |
+
"eval_recall": 0.9541586489707353,
|
| 1000 |
+
"eval_runtime": 19.6986,
|
| 1001 |
+
"eval_samples_per_second": 86.91,
|
| 1002 |
+
"eval_steps_per_second": 5.432,
|
| 1003 |
+
"step": 1309
|
| 1004 |
+
},
|
| 1005 |
+
{
|
| 1006 |
+
"epoch": 7.01,
|
| 1007 |
+
"grad_norm": 1.9716545343399048,
|
| 1008 |
+
"learning_rate": 0.0015,
|
| 1009 |
+
"loss": 0.2591,
|
| 1010 |
+
"step": 1310
|
| 1011 |
+
},
|
| 1012 |
+
{
|
| 1013 |
+
"epoch": 7.06,
|
| 1014 |
+
"grad_norm": 2.347787618637085,
|
| 1015 |
+
"learning_rate": 0.0014732620320855616,
|
| 1016 |
+
"loss": 0.2324,
|
| 1017 |
+
"step": 1320
|
| 1018 |
+
},
|
| 1019 |
+
{
|
| 1020 |
+
"epoch": 7.11,
|
| 1021 |
+
"grad_norm": 1.5514649152755737,
|
| 1022 |
+
"learning_rate": 0.001446524064171123,
|
| 1023 |
+
"loss": 0.2163,
|
| 1024 |
+
"step": 1330
|
| 1025 |
+
},
|
| 1026 |
+
{
|
| 1027 |
+
"epoch": 7.17,
|
| 1028 |
+
"grad_norm": 3.073544979095459,
|
| 1029 |
+
"learning_rate": 0.0014197860962566844,
|
| 1030 |
+
"loss": 0.2889,
|
| 1031 |
+
"step": 1340
|
| 1032 |
+
},
|
| 1033 |
+
{
|
| 1034 |
+
"epoch": 7.22,
|
| 1035 |
+
"grad_norm": 1.5972115993499756,
|
| 1036 |
+
"learning_rate": 0.0013930481283422461,
|
| 1037 |
+
"loss": 0.2589,
|
| 1038 |
+
"step": 1350
|
| 1039 |
+
},
|
| 1040 |
+
{
|
| 1041 |
+
"epoch": 7.27,
|
| 1042 |
+
"grad_norm": 1.8408401012420654,
|
| 1043 |
+
"learning_rate": 0.0013663101604278075,
|
| 1044 |
+
"loss": 0.2333,
|
| 1045 |
+
"step": 1360
|
| 1046 |
+
},
|
| 1047 |
+
{
|
| 1048 |
+
"epoch": 7.33,
|
| 1049 |
+
"grad_norm": 1.3704335689544678,
|
| 1050 |
+
"learning_rate": 0.0013395721925133692,
|
| 1051 |
+
"loss": 0.2103,
|
| 1052 |
+
"step": 1370
|
| 1053 |
+
},
|
| 1054 |
+
{
|
| 1055 |
+
"epoch": 7.38,
|
| 1056 |
+
"grad_norm": 3.6621859073638916,
|
| 1057 |
+
"learning_rate": 0.0013128342245989305,
|
| 1058 |
+
"loss": 0.2413,
|
| 1059 |
+
"step": 1380
|
| 1060 |
+
},
|
| 1061 |
+
{
|
| 1062 |
+
"epoch": 7.43,
|
| 1063 |
+
"grad_norm": 1.345258355140686,
|
| 1064 |
+
"learning_rate": 0.0012860962566844918,
|
| 1065 |
+
"loss": 0.2444,
|
| 1066 |
+
"step": 1390
|
| 1067 |
+
},
|
| 1068 |
+
{
|
| 1069 |
+
"epoch": 7.49,
|
| 1070 |
+
"grad_norm": 1.354202389717102,
|
| 1071 |
+
"learning_rate": 0.0012593582887700536,
|
| 1072 |
+
"loss": 0.2288,
|
| 1073 |
+
"step": 1400
|
| 1074 |
+
},
|
| 1075 |
+
{
|
| 1076 |
+
"epoch": 7.54,
|
| 1077 |
+
"grad_norm": 0.983450174331665,
|
| 1078 |
+
"learning_rate": 0.0012326203208556149,
|
| 1079 |
+
"loss": 0.2995,
|
| 1080 |
+
"step": 1410
|
| 1081 |
+
},
|
| 1082 |
+
{
|
| 1083 |
+
"epoch": 7.59,
|
| 1084 |
+
"grad_norm": 1.7251689434051514,
|
| 1085 |
+
"learning_rate": 0.0012058823529411764,
|
| 1086 |
+
"loss": 0.2898,
|
| 1087 |
+
"step": 1420
|
| 1088 |
+
},
|
| 1089 |
+
{
|
| 1090 |
+
"epoch": 7.65,
|
| 1091 |
+
"grad_norm": 1.4366217851638794,
|
| 1092 |
+
"learning_rate": 0.001179144385026738,
|
| 1093 |
+
"loss": 0.2509,
|
| 1094 |
+
"step": 1430
|
| 1095 |
+
},
|
| 1096 |
+
{
|
| 1097 |
+
"epoch": 7.7,
|
| 1098 |
+
"grad_norm": 1.6491020917892456,
|
| 1099 |
+
"learning_rate": 0.0011524064171122995,
|
| 1100 |
+
"loss": 0.2191,
|
| 1101 |
+
"step": 1440
|
| 1102 |
+
},
|
| 1103 |
+
{
|
| 1104 |
+
"epoch": 7.75,
|
| 1105 |
+
"grad_norm": 1.4462454319000244,
|
| 1106 |
+
"learning_rate": 0.001125668449197861,
|
| 1107 |
+
"loss": 0.2307,
|
| 1108 |
+
"step": 1450
|
| 1109 |
+
},
|
| 1110 |
+
{
|
| 1111 |
+
"epoch": 7.81,
|
| 1112 |
+
"grad_norm": 1.5503740310668945,
|
| 1113 |
+
"learning_rate": 0.0010989304812834225,
|
| 1114 |
+
"loss": 0.2167,
|
| 1115 |
+
"step": 1460
|
| 1116 |
+
},
|
| 1117 |
+
{
|
| 1118 |
+
"epoch": 7.86,
|
| 1119 |
+
"grad_norm": 1.5065810680389404,
|
| 1120 |
+
"learning_rate": 0.001072192513368984,
|
| 1121 |
+
"loss": 0.3377,
|
| 1122 |
+
"step": 1470
|
| 1123 |
+
},
|
| 1124 |
+
{
|
| 1125 |
+
"epoch": 7.91,
|
| 1126 |
+
"grad_norm": 1.3696374893188477,
|
| 1127 |
+
"learning_rate": 0.0010454545454545454,
|
| 1128 |
+
"loss": 0.24,
|
| 1129 |
+
"step": 1480
|
| 1130 |
+
},
|
| 1131 |
+
{
|
| 1132 |
+
"epoch": 7.97,
|
| 1133 |
+
"grad_norm": 0.9576804041862488,
|
| 1134 |
+
"learning_rate": 0.001018716577540107,
|
| 1135 |
+
"loss": 0.2214,
|
| 1136 |
+
"step": 1490
|
| 1137 |
+
},
|
| 1138 |
+
{
|
| 1139 |
+
"epoch": 8.0,
|
| 1140 |
+
"eval_accuracy": 0.9649532710280374,
|
| 1141 |
+
"eval_f1": 0.9609815836403053,
|
| 1142 |
+
"eval_loss": 0.11309263855218887,
|
| 1143 |
+
"eval_precision": 0.9642473014777337,
|
| 1144 |
+
"eval_recall": 0.9584474051621633,
|
| 1145 |
+
"eval_runtime": 19.6442,
|
| 1146 |
+
"eval_samples_per_second": 87.15,
|
| 1147 |
+
"eval_steps_per_second": 5.447,
|
| 1148 |
+
"step": 1496
|
| 1149 |
+
},
|
| 1150 |
+
{
|
| 1151 |
+
"epoch": 8.02,
|
| 1152 |
+
"grad_norm": 1.6305640935897827,
|
| 1153 |
+
"learning_rate": 0.0009919786096256684,
|
| 1154 |
+
"loss": 0.2645,
|
| 1155 |
+
"step": 1500
|
| 1156 |
+
},
|
| 1157 |
+
{
|
| 1158 |
+
"epoch": 8.07,
|
| 1159 |
+
"grad_norm": 1.0711798667907715,
|
| 1160 |
+
"learning_rate": 0.00096524064171123,
|
| 1161 |
+
"loss": 0.2063,
|
| 1162 |
+
"step": 1510
|
| 1163 |
+
},
|
| 1164 |
+
{
|
| 1165 |
+
"epoch": 8.13,
|
| 1166 |
+
"grad_norm": 1.2606171369552612,
|
| 1167 |
+
"learning_rate": 0.0009385026737967915,
|
| 1168 |
+
"loss": 0.1904,
|
| 1169 |
+
"step": 1520
|
| 1170 |
+
},
|
| 1171 |
+
{
|
| 1172 |
+
"epoch": 8.18,
|
| 1173 |
+
"grad_norm": 0.8554580807685852,
|
| 1174 |
+
"learning_rate": 0.0009117647058823529,
|
| 1175 |
+
"loss": 0.2078,
|
| 1176 |
+
"step": 1530
|
| 1177 |
+
},
|
| 1178 |
+
{
|
| 1179 |
+
"epoch": 8.24,
|
| 1180 |
+
"grad_norm": 1.0638494491577148,
|
| 1181 |
+
"learning_rate": 0.0008850267379679144,
|
| 1182 |
+
"loss": 0.2129,
|
| 1183 |
+
"step": 1540
|
| 1184 |
+
},
|
| 1185 |
+
{
|
| 1186 |
+
"epoch": 8.29,
|
| 1187 |
+
"grad_norm": 1.4322021007537842,
|
| 1188 |
+
"learning_rate": 0.000858288770053476,
|
| 1189 |
+
"loss": 0.2761,
|
| 1190 |
+
"step": 1550
|
| 1191 |
+
},
|
| 1192 |
+
{
|
| 1193 |
+
"epoch": 8.34,
|
| 1194 |
+
"grad_norm": 1.2639697790145874,
|
| 1195 |
+
"learning_rate": 0.0008315508021390375,
|
| 1196 |
+
"loss": 0.1979,
|
| 1197 |
+
"step": 1560
|
| 1198 |
+
},
|
| 1199 |
+
{
|
| 1200 |
+
"epoch": 8.4,
|
| 1201 |
+
"grad_norm": 1.108430027961731,
|
| 1202 |
+
"learning_rate": 0.0008048128342245989,
|
| 1203 |
+
"loss": 0.2051,
|
| 1204 |
+
"step": 1570
|
| 1205 |
+
},
|
| 1206 |
+
{
|
| 1207 |
+
"epoch": 8.45,
|
| 1208 |
+
"grad_norm": 2.08953857421875,
|
| 1209 |
+
"learning_rate": 0.0007780748663101605,
|
| 1210 |
+
"loss": 0.2306,
|
| 1211 |
+
"step": 1580
|
| 1212 |
+
},
|
| 1213 |
+
{
|
| 1214 |
+
"epoch": 8.5,
|
| 1215 |
+
"grad_norm": 1.464694857597351,
|
| 1216 |
+
"learning_rate": 0.000751336898395722,
|
| 1217 |
+
"loss": 0.1992,
|
| 1218 |
+
"step": 1590
|
| 1219 |
+
},
|
| 1220 |
+
{
|
| 1221 |
+
"epoch": 8.56,
|
| 1222 |
+
"grad_norm": 1.4773173332214355,
|
| 1223 |
+
"learning_rate": 0.0007245989304812835,
|
| 1224 |
+
"loss": 0.1764,
|
| 1225 |
+
"step": 1600
|
| 1226 |
+
},
|
| 1227 |
+
{
|
| 1228 |
+
"epoch": 8.61,
|
| 1229 |
+
"grad_norm": 2.048029661178589,
|
| 1230 |
+
"learning_rate": 0.000697860962566845,
|
| 1231 |
+
"loss": 0.237,
|
| 1232 |
+
"step": 1610
|
| 1233 |
+
},
|
| 1234 |
+
{
|
| 1235 |
+
"epoch": 8.66,
|
| 1236 |
+
"grad_norm": 1.0951212644577026,
|
| 1237 |
+
"learning_rate": 0.0006711229946524064,
|
| 1238 |
+
"loss": 0.1821,
|
| 1239 |
+
"step": 1620
|
| 1240 |
+
},
|
| 1241 |
+
{
|
| 1242 |
+
"epoch": 8.72,
|
| 1243 |
+
"grad_norm": 1.084712028503418,
|
| 1244 |
+
"learning_rate": 0.0006443850267379679,
|
| 1245 |
+
"loss": 0.1947,
|
| 1246 |
+
"step": 1630
|
| 1247 |
+
},
|
| 1248 |
+
{
|
| 1249 |
+
"epoch": 8.77,
|
| 1250 |
+
"grad_norm": 1.007285714149475,
|
| 1251 |
+
"learning_rate": 0.0006176470588235294,
|
| 1252 |
+
"loss": 0.2014,
|
| 1253 |
+
"step": 1640
|
| 1254 |
+
},
|
| 1255 |
+
{
|
| 1256 |
+
"epoch": 8.82,
|
| 1257 |
+
"grad_norm": 1.0643844604492188,
|
| 1258 |
+
"learning_rate": 0.0005909090909090909,
|
| 1259 |
+
"loss": 0.2411,
|
| 1260 |
+
"step": 1650
|
| 1261 |
+
},
|
| 1262 |
+
{
|
| 1263 |
+
"epoch": 8.88,
|
| 1264 |
+
"grad_norm": 2.0171964168548584,
|
| 1265 |
+
"learning_rate": 0.0005641711229946525,
|
| 1266 |
+
"loss": 0.2297,
|
| 1267 |
+
"step": 1660
|
| 1268 |
+
},
|
| 1269 |
+
{
|
| 1270 |
+
"epoch": 8.93,
|
| 1271 |
+
"grad_norm": 0.8814995884895325,
|
| 1272 |
+
"learning_rate": 0.0005374331550802139,
|
| 1273 |
+
"loss": 0.2052,
|
| 1274 |
+
"step": 1670
|
| 1275 |
+
},
|
| 1276 |
+
{
|
| 1277 |
+
"epoch": 8.98,
|
| 1278 |
+
"grad_norm": 1.338088035583496,
|
| 1279 |
+
"learning_rate": 0.0005106951871657754,
|
| 1280 |
+
"loss": 0.1928,
|
| 1281 |
+
"step": 1680
|
| 1282 |
+
},
|
| 1283 |
+
{
|
| 1284 |
+
"epoch": 9.0,
|
| 1285 |
+
"eval_accuracy": 0.9649532710280374,
|
| 1286 |
+
"eval_f1": 0.9624133353031232,
|
| 1287 |
+
"eval_loss": 0.09664417803287506,
|
| 1288 |
+
"eval_precision": 0.9632215980141733,
|
| 1289 |
+
"eval_recall": 0.9628324486352646,
|
| 1290 |
+
"eval_runtime": 19.7505,
|
| 1291 |
+
"eval_samples_per_second": 86.681,
|
| 1292 |
+
"eval_steps_per_second": 5.418,
|
| 1293 |
+
"step": 1683
|
| 1294 |
+
},
|
| 1295 |
+
{
|
| 1296 |
+
"epoch": 9.04,
|
| 1297 |
+
"grad_norm": 1.1753814220428467,
|
| 1298 |
+
"learning_rate": 0.0004839572192513369,
|
| 1299 |
+
"loss": 0.1862,
|
| 1300 |
+
"step": 1690
|
| 1301 |
+
},
|
| 1302 |
+
{
|
| 1303 |
+
"epoch": 9.09,
|
| 1304 |
+
"grad_norm": 0.9707505702972412,
|
| 1305 |
+
"learning_rate": 0.0004572192513368984,
|
| 1306 |
+
"loss": 0.2182,
|
| 1307 |
+
"step": 1700
|
| 1308 |
+
},
|
| 1309 |
+
{
|
| 1310 |
+
"epoch": 9.14,
|
| 1311 |
+
"grad_norm": 0.9967671632766724,
|
| 1312 |
+
"learning_rate": 0.0004304812834224599,
|
| 1313 |
+
"loss": 0.1923,
|
| 1314 |
+
"step": 1710
|
| 1315 |
+
},
|
| 1316 |
+
{
|
| 1317 |
+
"epoch": 9.2,
|
| 1318 |
+
"grad_norm": 1.496031641960144,
|
| 1319 |
+
"learning_rate": 0.00040374331550802143,
|
| 1320 |
+
"loss": 0.2105,
|
| 1321 |
+
"step": 1720
|
| 1322 |
+
},
|
| 1323 |
+
{
|
| 1324 |
+
"epoch": 9.25,
|
| 1325 |
+
"grad_norm": 0.8774816393852234,
|
| 1326 |
+
"learning_rate": 0.00037700534759358285,
|
| 1327 |
+
"loss": 0.1969,
|
| 1328 |
+
"step": 1730
|
| 1329 |
+
},
|
| 1330 |
+
{
|
| 1331 |
+
"epoch": 9.3,
|
| 1332 |
+
"grad_norm": 0.6063610315322876,
|
| 1333 |
+
"learning_rate": 0.0003502673796791444,
|
| 1334 |
+
"loss": 0.1577,
|
| 1335 |
+
"step": 1740
|
| 1336 |
+
},
|
| 1337 |
+
{
|
| 1338 |
+
"epoch": 9.36,
|
| 1339 |
+
"grad_norm": 0.8216743469238281,
|
| 1340 |
+
"learning_rate": 0.0003235294117647059,
|
| 1341 |
+
"loss": 0.2064,
|
| 1342 |
+
"step": 1750
|
| 1343 |
+
},
|
| 1344 |
+
{
|
| 1345 |
+
"epoch": 9.41,
|
| 1346 |
+
"grad_norm": 0.7338688373565674,
|
| 1347 |
+
"learning_rate": 0.0002967914438502674,
|
| 1348 |
+
"loss": 0.1793,
|
| 1349 |
+
"step": 1760
|
| 1350 |
+
},
|
| 1351 |
+
{
|
| 1352 |
+
"epoch": 9.47,
|
| 1353 |
+
"grad_norm": 0.910650372505188,
|
| 1354 |
+
"learning_rate": 0.00027005347593582886,
|
| 1355 |
+
"loss": 0.194,
|
| 1356 |
+
"step": 1770
|
| 1357 |
+
},
|
| 1358 |
+
{
|
| 1359 |
+
"epoch": 9.52,
|
| 1360 |
+
"grad_norm": 0.7778304219245911,
|
| 1361 |
+
"learning_rate": 0.00024331550802139036,
|
| 1362 |
+
"loss": 0.2203,
|
| 1363 |
+
"step": 1780
|
| 1364 |
+
},
|
| 1365 |
+
{
|
| 1366 |
+
"epoch": 9.57,
|
| 1367 |
+
"grad_norm": 1.0693227052688599,
|
| 1368 |
+
"learning_rate": 0.00021657754010695186,
|
| 1369 |
+
"loss": 0.1718,
|
| 1370 |
+
"step": 1790
|
| 1371 |
+
},
|
| 1372 |
+
{
|
| 1373 |
+
"epoch": 9.63,
|
| 1374 |
+
"grad_norm": 1.4808011054992676,
|
| 1375 |
+
"learning_rate": 0.0001898395721925134,
|
| 1376 |
+
"loss": 0.1696,
|
| 1377 |
+
"step": 1800
|
| 1378 |
+
},
|
| 1379 |
+
{
|
| 1380 |
+
"epoch": 9.68,
|
| 1381 |
+
"grad_norm": 0.8625634908676147,
|
| 1382 |
+
"learning_rate": 0.0001631016042780749,
|
| 1383 |
+
"loss": 0.1875,
|
| 1384 |
+
"step": 1810
|
| 1385 |
+
},
|
| 1386 |
+
{
|
| 1387 |
+
"epoch": 9.73,
|
| 1388 |
+
"grad_norm": 1.1236218214035034,
|
| 1389 |
+
"learning_rate": 0.00013636363636363637,
|
| 1390 |
+
"loss": 0.1772,
|
| 1391 |
+
"step": 1820
|
| 1392 |
+
},
|
| 1393 |
+
{
|
| 1394 |
+
"epoch": 9.79,
|
| 1395 |
+
"grad_norm": 1.027061939239502,
|
| 1396 |
+
"learning_rate": 0.00010962566844919787,
|
| 1397 |
+
"loss": 0.2274,
|
| 1398 |
+
"step": 1830
|
| 1399 |
+
},
|
| 1400 |
+
{
|
| 1401 |
+
"epoch": 9.84,
|
| 1402 |
+
"grad_norm": 0.977976381778717,
|
| 1403 |
+
"learning_rate": 8.288770053475936e-05,
|
| 1404 |
+
"loss": 0.1672,
|
| 1405 |
+
"step": 1840
|
| 1406 |
+
},
|
| 1407 |
+
{
|
| 1408 |
+
"epoch": 9.89,
|
| 1409 |
+
"grad_norm": 0.957969069480896,
|
| 1410 |
+
"learning_rate": 5.614973262032086e-05,
|
| 1411 |
+
"loss": 0.1966,
|
| 1412 |
+
"step": 1850
|
| 1413 |
+
},
|
| 1414 |
+
{
|
| 1415 |
+
"epoch": 9.95,
|
| 1416 |
+
"grad_norm": 0.6182002425193787,
|
| 1417 |
+
"learning_rate": 2.9411764705882354e-05,
|
| 1418 |
+
"loss": 0.1546,
|
| 1419 |
+
"step": 1860
|
| 1420 |
+
},
|
| 1421 |
+
{
|
| 1422 |
+
"epoch": 10.0,
|
| 1423 |
+
"grad_norm": 1.8023217916488647,
|
| 1424 |
+
"learning_rate": 2.6737967914438504e-06,
|
| 1425 |
+
"loss": 0.1901,
|
| 1426 |
+
"step": 1870
|
| 1427 |
+
},
|
| 1428 |
+
{
|
| 1429 |
+
"epoch": 10.0,
|
| 1430 |
+
"eval_accuracy": 0.9713785046728972,
|
| 1431 |
+
"eval_f1": 0.9692014832223894,
|
| 1432 |
+
"eval_loss": 0.07747028768062592,
|
| 1433 |
+
"eval_precision": 0.968992240300534,
|
| 1434 |
+
"eval_recall": 0.9698888041231651,
|
| 1435 |
+
"eval_runtime": 19.6225,
|
| 1436 |
+
"eval_samples_per_second": 87.247,
|
| 1437 |
+
"eval_steps_per_second": 5.453,
|
| 1438 |
+
"step": 1870
|
| 1439 |
+
},
|
| 1440 |
+
{
|
| 1441 |
+
"epoch": 10.0,
|
| 1442 |
+
"step": 1870,
|
| 1443 |
+
"total_flos": 2.1188849626596557e+19,
|
| 1444 |
+
"train_loss": 0.34750947773775315,
|
| 1445 |
+
"train_runtime": 3122.2212,
|
| 1446 |
+
"train_samples_per_second": 38.303,
|
| 1447 |
+
"train_steps_per_second": 0.599
|
| 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": 2.1188849626596557e+19,
|
| 1456 |
+
"train_batch_size": 16,
|
| 1457 |
+
"trial_name": null,
|
| 1458 |
+
"trial_params": null
|
| 1459 |
+
}
|