End of training
Browse files- README.md +3 -3
- all_results.json +13 -0
- eval_results.json +8 -0
- train_results.json +8 -0
- trainer_state.json +1114 -0
README.md
CHANGED
|
@@ -22,7 +22,7 @@ model-index:
|
|
| 22 |
metrics:
|
| 23 |
- name: Accuracy
|
| 24 |
type: accuracy
|
| 25 |
-
value: 0.
|
| 26 |
---
|
| 27 |
|
| 28 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
@@ -32,8 +32,8 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 32 |
|
| 33 |
This model is a fine-tuned version of [microsoft/swin-tiny-patch4-window7-224](https://huggingface.co/microsoft/swin-tiny-patch4-window7-224) on the imagefolder dataset.
|
| 34 |
It achieves the following results on the evaluation set:
|
| 35 |
-
- Loss: 0.
|
| 36 |
-
- Accuracy: 0.
|
| 37 |
|
| 38 |
## Model description
|
| 39 |
|
|
|
|
| 22 |
metrics:
|
| 23 |
- name: Accuracy
|
| 24 |
type: accuracy
|
| 25 |
+
value: 0.966893039049236
|
| 26 |
---
|
| 27 |
|
| 28 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
|
|
| 32 |
|
| 33 |
This model is a fine-tuned version of [microsoft/swin-tiny-patch4-window7-224](https://huggingface.co/microsoft/swin-tiny-patch4-window7-224) on the imagefolder dataset.
|
| 34 |
It achieves the following results on the evaluation set:
|
| 35 |
+
- Loss: 0.1131
|
| 36 |
+
- Accuracy: 0.9669
|
| 37 |
|
| 38 |
## Model description
|
| 39 |
|
all_results.json
ADDED
|
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 10.0,
|
| 3 |
+
"eval_accuracy": 0.966893039049236,
|
| 4 |
+
"eval_loss": 0.1130693331360817,
|
| 5 |
+
"eval_runtime": 8.6089,
|
| 6 |
+
"eval_samples_per_second": 136.835,
|
| 7 |
+
"eval_steps_per_second": 4.298,
|
| 8 |
+
"total_flos": 2.6335377898183066e+18,
|
| 9 |
+
"train_loss": 0.2811273262443313,
|
| 10 |
+
"train_runtime": 1705.57,
|
| 11 |
+
"train_samples_per_second": 62.114,
|
| 12 |
+
"train_steps_per_second": 0.487
|
| 13 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 10.0,
|
| 3 |
+
"eval_accuracy": 0.966893039049236,
|
| 4 |
+
"eval_loss": 0.1130693331360817,
|
| 5 |
+
"eval_runtime": 8.6089,
|
| 6 |
+
"eval_samples_per_second": 136.835,
|
| 7 |
+
"eval_steps_per_second": 4.298
|
| 8 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 10.0,
|
| 3 |
+
"total_flos": 2.6335377898183066e+18,
|
| 4 |
+
"train_loss": 0.2811273262443313,
|
| 5 |
+
"train_runtime": 1705.57,
|
| 6 |
+
"train_samples_per_second": 62.114,
|
| 7 |
+
"train_steps_per_second": 0.487
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,1114 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.966893039049236,
|
| 3 |
+
"best_model_checkpoint": "swin-tiny-patch4-window7-224-spa_saloon_classification/checkpoint-498",
|
| 4 |
+
"epoch": 10.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 830,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.06,
|
| 13 |
+
"learning_rate": 3.0120481927710846e-06,
|
| 14 |
+
"loss": 1.9163,
|
| 15 |
+
"step": 5
|
| 16 |
+
},
|
| 17 |
+
{
|
| 18 |
+
"epoch": 0.12,
|
| 19 |
+
"learning_rate": 6.024096385542169e-06,
|
| 20 |
+
"loss": 1.8781,
|
| 21 |
+
"step": 10
|
| 22 |
+
},
|
| 23 |
+
{
|
| 24 |
+
"epoch": 0.18,
|
| 25 |
+
"learning_rate": 9.036144578313253e-06,
|
| 26 |
+
"loss": 1.7858,
|
| 27 |
+
"step": 15
|
| 28 |
+
},
|
| 29 |
+
{
|
| 30 |
+
"epoch": 0.24,
|
| 31 |
+
"learning_rate": 1.2048192771084338e-05,
|
| 32 |
+
"loss": 1.7063,
|
| 33 |
+
"step": 20
|
| 34 |
+
},
|
| 35 |
+
{
|
| 36 |
+
"epoch": 0.3,
|
| 37 |
+
"learning_rate": 1.5060240963855424e-05,
|
| 38 |
+
"loss": 1.5479,
|
| 39 |
+
"step": 25
|
| 40 |
+
},
|
| 41 |
+
{
|
| 42 |
+
"epoch": 0.36,
|
| 43 |
+
"learning_rate": 1.8072289156626505e-05,
|
| 44 |
+
"loss": 1.3958,
|
| 45 |
+
"step": 30
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.42,
|
| 49 |
+
"learning_rate": 2.1084337349397593e-05,
|
| 50 |
+
"loss": 1.1757,
|
| 51 |
+
"step": 35
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.48,
|
| 55 |
+
"learning_rate": 2.4096385542168677e-05,
|
| 56 |
+
"loss": 0.9676,
|
| 57 |
+
"step": 40
|
| 58 |
+
},
|
| 59 |
+
{
|
| 60 |
+
"epoch": 0.54,
|
| 61 |
+
"learning_rate": 2.7108433734939758e-05,
|
| 62 |
+
"loss": 0.7777,
|
| 63 |
+
"step": 45
|
| 64 |
+
},
|
| 65 |
+
{
|
| 66 |
+
"epoch": 0.6,
|
| 67 |
+
"learning_rate": 3.012048192771085e-05,
|
| 68 |
+
"loss": 0.6423,
|
| 69 |
+
"step": 50
|
| 70 |
+
},
|
| 71 |
+
{
|
| 72 |
+
"epoch": 0.66,
|
| 73 |
+
"learning_rate": 3.313253012048193e-05,
|
| 74 |
+
"loss": 0.6183,
|
| 75 |
+
"step": 55
|
| 76 |
+
},
|
| 77 |
+
{
|
| 78 |
+
"epoch": 0.72,
|
| 79 |
+
"learning_rate": 3.614457831325301e-05,
|
| 80 |
+
"loss": 0.5876,
|
| 81 |
+
"step": 60
|
| 82 |
+
},
|
| 83 |
+
{
|
| 84 |
+
"epoch": 0.78,
|
| 85 |
+
"learning_rate": 3.91566265060241e-05,
|
| 86 |
+
"loss": 0.5514,
|
| 87 |
+
"step": 65
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.84,
|
| 91 |
+
"learning_rate": 4.2168674698795186e-05,
|
| 92 |
+
"loss": 0.49,
|
| 93 |
+
"step": 70
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.9,
|
| 97 |
+
"learning_rate": 4.5180722891566266e-05,
|
| 98 |
+
"loss": 0.4859,
|
| 99 |
+
"step": 75
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"epoch": 0.96,
|
| 103 |
+
"learning_rate": 4.8192771084337354e-05,
|
| 104 |
+
"loss": 0.4613,
|
| 105 |
+
"step": 80
|
| 106 |
+
},
|
| 107 |
+
{
|
| 108 |
+
"epoch": 1.0,
|
| 109 |
+
"eval_accuracy": 0.8718166383701188,
|
| 110 |
+
"eval_loss": 0.33570152521133423,
|
| 111 |
+
"eval_runtime": 7.7999,
|
| 112 |
+
"eval_samples_per_second": 151.027,
|
| 113 |
+
"eval_steps_per_second": 4.744,
|
| 114 |
+
"step": 83
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 1.02,
|
| 118 |
+
"learning_rate": 4.98661311914324e-05,
|
| 119 |
+
"loss": 0.4352,
|
| 120 |
+
"step": 85
|
| 121 |
+
},
|
| 122 |
+
{
|
| 123 |
+
"epoch": 1.08,
|
| 124 |
+
"learning_rate": 4.953145917001339e-05,
|
| 125 |
+
"loss": 0.4174,
|
| 126 |
+
"step": 90
|
| 127 |
+
},
|
| 128 |
+
{
|
| 129 |
+
"epoch": 1.14,
|
| 130 |
+
"learning_rate": 4.919678714859438e-05,
|
| 131 |
+
"loss": 0.4291,
|
| 132 |
+
"step": 95
|
| 133 |
+
},
|
| 134 |
+
{
|
| 135 |
+
"epoch": 1.2,
|
| 136 |
+
"learning_rate": 4.886211512717537e-05,
|
| 137 |
+
"loss": 0.3423,
|
| 138 |
+
"step": 100
|
| 139 |
+
},
|
| 140 |
+
{
|
| 141 |
+
"epoch": 1.27,
|
| 142 |
+
"learning_rate": 4.8527443105756356e-05,
|
| 143 |
+
"loss": 0.3444,
|
| 144 |
+
"step": 105
|
| 145 |
+
},
|
| 146 |
+
{
|
| 147 |
+
"epoch": 1.33,
|
| 148 |
+
"learning_rate": 4.8192771084337354e-05,
|
| 149 |
+
"loss": 0.3321,
|
| 150 |
+
"step": 110
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"epoch": 1.39,
|
| 154 |
+
"learning_rate": 4.7858099062918345e-05,
|
| 155 |
+
"loss": 0.3671,
|
| 156 |
+
"step": 115
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 1.45,
|
| 160 |
+
"learning_rate": 4.7523427041499336e-05,
|
| 161 |
+
"loss": 0.3157,
|
| 162 |
+
"step": 120
|
| 163 |
+
},
|
| 164 |
+
{
|
| 165 |
+
"epoch": 1.51,
|
| 166 |
+
"learning_rate": 4.718875502008032e-05,
|
| 167 |
+
"loss": 0.3427,
|
| 168 |
+
"step": 125
|
| 169 |
+
},
|
| 170 |
+
{
|
| 171 |
+
"epoch": 1.57,
|
| 172 |
+
"learning_rate": 4.685408299866131e-05,
|
| 173 |
+
"loss": 0.3368,
|
| 174 |
+
"step": 130
|
| 175 |
+
},
|
| 176 |
+
{
|
| 177 |
+
"epoch": 1.63,
|
| 178 |
+
"learning_rate": 4.651941097724231e-05,
|
| 179 |
+
"loss": 0.3249,
|
| 180 |
+
"step": 135
|
| 181 |
+
},
|
| 182 |
+
{
|
| 183 |
+
"epoch": 1.69,
|
| 184 |
+
"learning_rate": 4.61847389558233e-05,
|
| 185 |
+
"loss": 0.3338,
|
| 186 |
+
"step": 140
|
| 187 |
+
},
|
| 188 |
+
{
|
| 189 |
+
"epoch": 1.75,
|
| 190 |
+
"learning_rate": 4.5850066934404284e-05,
|
| 191 |
+
"loss": 0.3542,
|
| 192 |
+
"step": 145
|
| 193 |
+
},
|
| 194 |
+
{
|
| 195 |
+
"epoch": 1.81,
|
| 196 |
+
"learning_rate": 4.5515394912985275e-05,
|
| 197 |
+
"loss": 0.2853,
|
| 198 |
+
"step": 150
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 1.87,
|
| 202 |
+
"learning_rate": 4.5180722891566266e-05,
|
| 203 |
+
"loss": 0.2825,
|
| 204 |
+
"step": 155
|
| 205 |
+
},
|
| 206 |
+
{
|
| 207 |
+
"epoch": 1.93,
|
| 208 |
+
"learning_rate": 4.484605087014726e-05,
|
| 209 |
+
"loss": 0.3617,
|
| 210 |
+
"step": 160
|
| 211 |
+
},
|
| 212 |
+
{
|
| 213 |
+
"epoch": 1.99,
|
| 214 |
+
"learning_rate": 4.451137884872825e-05,
|
| 215 |
+
"loss": 0.2908,
|
| 216 |
+
"step": 165
|
| 217 |
+
},
|
| 218 |
+
{
|
| 219 |
+
"epoch": 2.0,
|
| 220 |
+
"eval_accuracy": 0.931239388794567,
|
| 221 |
+
"eval_loss": 0.18052884936332703,
|
| 222 |
+
"eval_runtime": 7.8584,
|
| 223 |
+
"eval_samples_per_second": 149.903,
|
| 224 |
+
"eval_steps_per_second": 4.708,
|
| 225 |
+
"step": 166
|
| 226 |
+
},
|
| 227 |
+
{
|
| 228 |
+
"epoch": 2.05,
|
| 229 |
+
"learning_rate": 4.417670682730924e-05,
|
| 230 |
+
"loss": 0.2903,
|
| 231 |
+
"step": 170
|
| 232 |
+
},
|
| 233 |
+
{
|
| 234 |
+
"epoch": 2.11,
|
| 235 |
+
"learning_rate": 4.384203480589023e-05,
|
| 236 |
+
"loss": 0.2862,
|
| 237 |
+
"step": 175
|
| 238 |
+
},
|
| 239 |
+
{
|
| 240 |
+
"epoch": 2.17,
|
| 241 |
+
"learning_rate": 4.350736278447122e-05,
|
| 242 |
+
"loss": 0.2783,
|
| 243 |
+
"step": 180
|
| 244 |
+
},
|
| 245 |
+
{
|
| 246 |
+
"epoch": 2.23,
|
| 247 |
+
"learning_rate": 4.317269076305221e-05,
|
| 248 |
+
"loss": 0.2825,
|
| 249 |
+
"step": 185
|
| 250 |
+
},
|
| 251 |
+
{
|
| 252 |
+
"epoch": 2.29,
|
| 253 |
+
"learning_rate": 4.2838018741633203e-05,
|
| 254 |
+
"loss": 0.2586,
|
| 255 |
+
"step": 190
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 2.35,
|
| 259 |
+
"learning_rate": 4.2503346720214194e-05,
|
| 260 |
+
"loss": 0.2355,
|
| 261 |
+
"step": 195
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 2.41,
|
| 265 |
+
"learning_rate": 4.2168674698795186e-05,
|
| 266 |
+
"loss": 0.236,
|
| 267 |
+
"step": 200
|
| 268 |
+
},
|
| 269 |
+
{
|
| 270 |
+
"epoch": 2.47,
|
| 271 |
+
"learning_rate": 4.183400267737617e-05,
|
| 272 |
+
"loss": 0.2348,
|
| 273 |
+
"step": 205
|
| 274 |
+
},
|
| 275 |
+
{
|
| 276 |
+
"epoch": 2.53,
|
| 277 |
+
"learning_rate": 4.149933065595716e-05,
|
| 278 |
+
"loss": 0.226,
|
| 279 |
+
"step": 210
|
| 280 |
+
},
|
| 281 |
+
{
|
| 282 |
+
"epoch": 2.59,
|
| 283 |
+
"learning_rate": 4.116465863453816e-05,
|
| 284 |
+
"loss": 0.2765,
|
| 285 |
+
"step": 215
|
| 286 |
+
},
|
| 287 |
+
{
|
| 288 |
+
"epoch": 2.65,
|
| 289 |
+
"learning_rate": 4.082998661311915e-05,
|
| 290 |
+
"loss": 0.2744,
|
| 291 |
+
"step": 220
|
| 292 |
+
},
|
| 293 |
+
{
|
| 294 |
+
"epoch": 2.71,
|
| 295 |
+
"learning_rate": 4.0495314591700134e-05,
|
| 296 |
+
"loss": 0.293,
|
| 297 |
+
"step": 225
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 2.77,
|
| 301 |
+
"learning_rate": 4.0160642570281125e-05,
|
| 302 |
+
"loss": 0.2416,
|
| 303 |
+
"step": 230
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 2.83,
|
| 307 |
+
"learning_rate": 3.9825970548862116e-05,
|
| 308 |
+
"loss": 0.2864,
|
| 309 |
+
"step": 235
|
| 310 |
+
},
|
| 311 |
+
{
|
| 312 |
+
"epoch": 2.89,
|
| 313 |
+
"learning_rate": 3.949129852744311e-05,
|
| 314 |
+
"loss": 0.2335,
|
| 315 |
+
"step": 240
|
| 316 |
+
},
|
| 317 |
+
{
|
| 318 |
+
"epoch": 2.95,
|
| 319 |
+
"learning_rate": 3.91566265060241e-05,
|
| 320 |
+
"loss": 0.2341,
|
| 321 |
+
"step": 245
|
| 322 |
+
},
|
| 323 |
+
{
|
| 324 |
+
"epoch": 3.0,
|
| 325 |
+
"eval_accuracy": 0.9516129032258065,
|
| 326 |
+
"eval_loss": 0.14258885383605957,
|
| 327 |
+
"eval_runtime": 8.0066,
|
| 328 |
+
"eval_samples_per_second": 147.128,
|
| 329 |
+
"eval_steps_per_second": 4.621,
|
| 330 |
+
"step": 249
|
| 331 |
+
},
|
| 332 |
+
{
|
| 333 |
+
"epoch": 3.01,
|
| 334 |
+
"learning_rate": 3.882195448460509e-05,
|
| 335 |
+
"loss": 0.2439,
|
| 336 |
+
"step": 250
|
| 337 |
+
},
|
| 338 |
+
{
|
| 339 |
+
"epoch": 3.07,
|
| 340 |
+
"learning_rate": 3.848728246318608e-05,
|
| 341 |
+
"loss": 0.2018,
|
| 342 |
+
"step": 255
|
| 343 |
+
},
|
| 344 |
+
{
|
| 345 |
+
"epoch": 3.13,
|
| 346 |
+
"learning_rate": 3.815261044176707e-05,
|
| 347 |
+
"loss": 0.2394,
|
| 348 |
+
"step": 260
|
| 349 |
+
},
|
| 350 |
+
{
|
| 351 |
+
"epoch": 3.19,
|
| 352 |
+
"learning_rate": 3.781793842034806e-05,
|
| 353 |
+
"loss": 0.2311,
|
| 354 |
+
"step": 265
|
| 355 |
+
},
|
| 356 |
+
{
|
| 357 |
+
"epoch": 3.25,
|
| 358 |
+
"learning_rate": 3.748326639892905e-05,
|
| 359 |
+
"loss": 0.2649,
|
| 360 |
+
"step": 270
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 3.31,
|
| 364 |
+
"learning_rate": 3.7148594377510044e-05,
|
| 365 |
+
"loss": 0.193,
|
| 366 |
+
"step": 275
|
| 367 |
+
},
|
| 368 |
+
{
|
| 369 |
+
"epoch": 3.37,
|
| 370 |
+
"learning_rate": 3.6813922356091035e-05,
|
| 371 |
+
"loss": 0.2252,
|
| 372 |
+
"step": 280
|
| 373 |
+
},
|
| 374 |
+
{
|
| 375 |
+
"epoch": 3.43,
|
| 376 |
+
"learning_rate": 3.647925033467202e-05,
|
| 377 |
+
"loss": 0.2396,
|
| 378 |
+
"step": 285
|
| 379 |
+
},
|
| 380 |
+
{
|
| 381 |
+
"epoch": 3.49,
|
| 382 |
+
"learning_rate": 3.614457831325301e-05,
|
| 383 |
+
"loss": 0.1846,
|
| 384 |
+
"step": 290
|
| 385 |
+
},
|
| 386 |
+
{
|
| 387 |
+
"epoch": 3.55,
|
| 388 |
+
"learning_rate": 3.580990629183401e-05,
|
| 389 |
+
"loss": 0.229,
|
| 390 |
+
"step": 295
|
| 391 |
+
},
|
| 392 |
+
{
|
| 393 |
+
"epoch": 3.61,
|
| 394 |
+
"learning_rate": 3.5475234270415e-05,
|
| 395 |
+
"loss": 0.2665,
|
| 396 |
+
"step": 300
|
| 397 |
+
},
|
| 398 |
+
{
|
| 399 |
+
"epoch": 3.67,
|
| 400 |
+
"learning_rate": 3.5140562248995983e-05,
|
| 401 |
+
"loss": 0.2018,
|
| 402 |
+
"step": 305
|
| 403 |
+
},
|
| 404 |
+
{
|
| 405 |
+
"epoch": 3.73,
|
| 406 |
+
"learning_rate": 3.4805890227576974e-05,
|
| 407 |
+
"loss": 0.195,
|
| 408 |
+
"step": 310
|
| 409 |
+
},
|
| 410 |
+
{
|
| 411 |
+
"epoch": 3.8,
|
| 412 |
+
"learning_rate": 3.4471218206157965e-05,
|
| 413 |
+
"loss": 0.2759,
|
| 414 |
+
"step": 315
|
| 415 |
+
},
|
| 416 |
+
{
|
| 417 |
+
"epoch": 3.86,
|
| 418 |
+
"learning_rate": 3.413654618473896e-05,
|
| 419 |
+
"loss": 0.2093,
|
| 420 |
+
"step": 320
|
| 421 |
+
},
|
| 422 |
+
{
|
| 423 |
+
"epoch": 3.92,
|
| 424 |
+
"learning_rate": 3.380187416331995e-05,
|
| 425 |
+
"loss": 0.1952,
|
| 426 |
+
"step": 325
|
| 427 |
+
},
|
| 428 |
+
{
|
| 429 |
+
"epoch": 3.98,
|
| 430 |
+
"learning_rate": 3.346720214190094e-05,
|
| 431 |
+
"loss": 0.1907,
|
| 432 |
+
"step": 330
|
| 433 |
+
},
|
| 434 |
+
{
|
| 435 |
+
"epoch": 4.0,
|
| 436 |
+
"eval_accuracy": 0.9422750424448217,
|
| 437 |
+
"eval_loss": 0.1471460461616516,
|
| 438 |
+
"eval_runtime": 8.6212,
|
| 439 |
+
"eval_samples_per_second": 136.639,
|
| 440 |
+
"eval_steps_per_second": 4.292,
|
| 441 |
+
"step": 332
|
| 442 |
+
},
|
| 443 |
+
{
|
| 444 |
+
"epoch": 4.04,
|
| 445 |
+
"learning_rate": 3.313253012048193e-05,
|
| 446 |
+
"loss": 0.1938,
|
| 447 |
+
"step": 335
|
| 448 |
+
},
|
| 449 |
+
{
|
| 450 |
+
"epoch": 4.1,
|
| 451 |
+
"learning_rate": 3.279785809906292e-05,
|
| 452 |
+
"loss": 0.2388,
|
| 453 |
+
"step": 340
|
| 454 |
+
},
|
| 455 |
+
{
|
| 456 |
+
"epoch": 4.16,
|
| 457 |
+
"learning_rate": 3.246318607764391e-05,
|
| 458 |
+
"loss": 0.1775,
|
| 459 |
+
"step": 345
|
| 460 |
+
},
|
| 461 |
+
{
|
| 462 |
+
"epoch": 4.22,
|
| 463 |
+
"learning_rate": 3.21285140562249e-05,
|
| 464 |
+
"loss": 0.1725,
|
| 465 |
+
"step": 350
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 4.28,
|
| 469 |
+
"learning_rate": 3.1793842034805894e-05,
|
| 470 |
+
"loss": 0.1386,
|
| 471 |
+
"step": 355
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 4.34,
|
| 475 |
+
"learning_rate": 3.1459170013386885e-05,
|
| 476 |
+
"loss": 0.1675,
|
| 477 |
+
"step": 360
|
| 478 |
+
},
|
| 479 |
+
{
|
| 480 |
+
"epoch": 4.4,
|
| 481 |
+
"learning_rate": 3.112449799196787e-05,
|
| 482 |
+
"loss": 0.2132,
|
| 483 |
+
"step": 365
|
| 484 |
+
},
|
| 485 |
+
{
|
| 486 |
+
"epoch": 4.46,
|
| 487 |
+
"learning_rate": 3.078982597054887e-05,
|
| 488 |
+
"loss": 0.1938,
|
| 489 |
+
"step": 370
|
| 490 |
+
},
|
| 491 |
+
{
|
| 492 |
+
"epoch": 4.52,
|
| 493 |
+
"learning_rate": 3.0455153949129854e-05,
|
| 494 |
+
"loss": 0.1983,
|
| 495 |
+
"step": 375
|
| 496 |
+
},
|
| 497 |
+
{
|
| 498 |
+
"epoch": 4.58,
|
| 499 |
+
"learning_rate": 3.012048192771085e-05,
|
| 500 |
+
"loss": 0.1875,
|
| 501 |
+
"step": 380
|
| 502 |
+
},
|
| 503 |
+
{
|
| 504 |
+
"epoch": 4.64,
|
| 505 |
+
"learning_rate": 2.9785809906291833e-05,
|
| 506 |
+
"loss": 0.1942,
|
| 507 |
+
"step": 385
|
| 508 |
+
},
|
| 509 |
+
{
|
| 510 |
+
"epoch": 4.7,
|
| 511 |
+
"learning_rate": 2.9451137884872827e-05,
|
| 512 |
+
"loss": 0.2072,
|
| 513 |
+
"step": 390
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 4.76,
|
| 517 |
+
"learning_rate": 2.911646586345382e-05,
|
| 518 |
+
"loss": 0.1521,
|
| 519 |
+
"step": 395
|
| 520 |
+
},
|
| 521 |
+
{
|
| 522 |
+
"epoch": 4.82,
|
| 523 |
+
"learning_rate": 2.878179384203481e-05,
|
| 524 |
+
"loss": 0.2497,
|
| 525 |
+
"step": 400
|
| 526 |
+
},
|
| 527 |
+
{
|
| 528 |
+
"epoch": 4.88,
|
| 529 |
+
"learning_rate": 2.8447121820615797e-05,
|
| 530 |
+
"loss": 0.2459,
|
| 531 |
+
"step": 405
|
| 532 |
+
},
|
| 533 |
+
{
|
| 534 |
+
"epoch": 4.94,
|
| 535 |
+
"learning_rate": 2.8112449799196788e-05,
|
| 536 |
+
"loss": 0.2132,
|
| 537 |
+
"step": 410
|
| 538 |
+
},
|
| 539 |
+
{
|
| 540 |
+
"epoch": 5.0,
|
| 541 |
+
"learning_rate": 2.777777777777778e-05,
|
| 542 |
+
"loss": 0.1836,
|
| 543 |
+
"step": 415
|
| 544 |
+
},
|
| 545 |
+
{
|
| 546 |
+
"epoch": 5.0,
|
| 547 |
+
"eval_accuracy": 0.9575551782682513,
|
| 548 |
+
"eval_loss": 0.11771776527166367,
|
| 549 |
+
"eval_runtime": 8.1927,
|
| 550 |
+
"eval_samples_per_second": 143.787,
|
| 551 |
+
"eval_steps_per_second": 4.516,
|
| 552 |
+
"step": 415
|
| 553 |
+
},
|
| 554 |
+
{
|
| 555 |
+
"epoch": 5.06,
|
| 556 |
+
"learning_rate": 2.7443105756358774e-05,
|
| 557 |
+
"loss": 0.144,
|
| 558 |
+
"step": 420
|
| 559 |
+
},
|
| 560 |
+
{
|
| 561 |
+
"epoch": 5.12,
|
| 562 |
+
"learning_rate": 2.7108433734939758e-05,
|
| 563 |
+
"loss": 0.167,
|
| 564 |
+
"step": 425
|
| 565 |
+
},
|
| 566 |
+
{
|
| 567 |
+
"epoch": 5.18,
|
| 568 |
+
"learning_rate": 2.6773761713520752e-05,
|
| 569 |
+
"loss": 0.2127,
|
| 570 |
+
"step": 430
|
| 571 |
+
},
|
| 572 |
+
{
|
| 573 |
+
"epoch": 5.24,
|
| 574 |
+
"learning_rate": 2.6439089692101743e-05,
|
| 575 |
+
"loss": 0.1836,
|
| 576 |
+
"step": 435
|
| 577 |
+
},
|
| 578 |
+
{
|
| 579 |
+
"epoch": 5.3,
|
| 580 |
+
"learning_rate": 2.6104417670682734e-05,
|
| 581 |
+
"loss": 0.1848,
|
| 582 |
+
"step": 440
|
| 583 |
+
},
|
| 584 |
+
{
|
| 585 |
+
"epoch": 5.36,
|
| 586 |
+
"learning_rate": 2.5769745649263722e-05,
|
| 587 |
+
"loss": 0.1538,
|
| 588 |
+
"step": 445
|
| 589 |
+
},
|
| 590 |
+
{
|
| 591 |
+
"epoch": 5.42,
|
| 592 |
+
"learning_rate": 2.5435073627844713e-05,
|
| 593 |
+
"loss": 0.1658,
|
| 594 |
+
"step": 450
|
| 595 |
+
},
|
| 596 |
+
{
|
| 597 |
+
"epoch": 5.48,
|
| 598 |
+
"learning_rate": 2.5100401606425704e-05,
|
| 599 |
+
"loss": 0.181,
|
| 600 |
+
"step": 455
|
| 601 |
+
},
|
| 602 |
+
{
|
| 603 |
+
"epoch": 5.54,
|
| 604 |
+
"learning_rate": 2.4765729585006695e-05,
|
| 605 |
+
"loss": 0.1735,
|
| 606 |
+
"step": 460
|
| 607 |
+
},
|
| 608 |
+
{
|
| 609 |
+
"epoch": 5.6,
|
| 610 |
+
"learning_rate": 2.4431057563587686e-05,
|
| 611 |
+
"loss": 0.1816,
|
| 612 |
+
"step": 465
|
| 613 |
+
},
|
| 614 |
+
{
|
| 615 |
+
"epoch": 5.66,
|
| 616 |
+
"learning_rate": 2.4096385542168677e-05,
|
| 617 |
+
"loss": 0.1797,
|
| 618 |
+
"step": 470
|
| 619 |
+
},
|
| 620 |
+
{
|
| 621 |
+
"epoch": 5.72,
|
| 622 |
+
"learning_rate": 2.3761713520749668e-05,
|
| 623 |
+
"loss": 0.1854,
|
| 624 |
+
"step": 475
|
| 625 |
+
},
|
| 626 |
+
{
|
| 627 |
+
"epoch": 5.78,
|
| 628 |
+
"learning_rate": 2.3427041499330656e-05,
|
| 629 |
+
"loss": 0.1567,
|
| 630 |
+
"step": 480
|
| 631 |
+
},
|
| 632 |
+
{
|
| 633 |
+
"epoch": 5.84,
|
| 634 |
+
"learning_rate": 2.309236947791165e-05,
|
| 635 |
+
"loss": 0.1433,
|
| 636 |
+
"step": 485
|
| 637 |
+
},
|
| 638 |
+
{
|
| 639 |
+
"epoch": 5.9,
|
| 640 |
+
"learning_rate": 2.2757697456492638e-05,
|
| 641 |
+
"loss": 0.1793,
|
| 642 |
+
"step": 490
|
| 643 |
+
},
|
| 644 |
+
{
|
| 645 |
+
"epoch": 5.96,
|
| 646 |
+
"learning_rate": 2.242302543507363e-05,
|
| 647 |
+
"loss": 0.1669,
|
| 648 |
+
"step": 495
|
| 649 |
+
},
|
| 650 |
+
{
|
| 651 |
+
"epoch": 6.0,
|
| 652 |
+
"eval_accuracy": 0.966893039049236,
|
| 653 |
+
"eval_loss": 0.1130693331360817,
|
| 654 |
+
"eval_runtime": 7.7073,
|
| 655 |
+
"eval_samples_per_second": 152.841,
|
| 656 |
+
"eval_steps_per_second": 4.801,
|
| 657 |
+
"step": 498
|
| 658 |
+
},
|
| 659 |
+
{
|
| 660 |
+
"epoch": 6.02,
|
| 661 |
+
"learning_rate": 2.208835341365462e-05,
|
| 662 |
+
"loss": 0.1968,
|
| 663 |
+
"step": 500
|
| 664 |
+
},
|
| 665 |
+
{
|
| 666 |
+
"epoch": 6.08,
|
| 667 |
+
"learning_rate": 2.175368139223561e-05,
|
| 668 |
+
"loss": 0.1459,
|
| 669 |
+
"step": 505
|
| 670 |
+
},
|
| 671 |
+
{
|
| 672 |
+
"epoch": 6.14,
|
| 673 |
+
"learning_rate": 2.1419009370816602e-05,
|
| 674 |
+
"loss": 0.1908,
|
| 675 |
+
"step": 510
|
| 676 |
+
},
|
| 677 |
+
{
|
| 678 |
+
"epoch": 6.2,
|
| 679 |
+
"learning_rate": 2.1084337349397593e-05,
|
| 680 |
+
"loss": 0.1881,
|
| 681 |
+
"step": 515
|
| 682 |
+
},
|
| 683 |
+
{
|
| 684 |
+
"epoch": 6.27,
|
| 685 |
+
"learning_rate": 2.074966532797858e-05,
|
| 686 |
+
"loss": 0.1672,
|
| 687 |
+
"step": 520
|
| 688 |
+
},
|
| 689 |
+
{
|
| 690 |
+
"epoch": 6.33,
|
| 691 |
+
"learning_rate": 2.0414993306559575e-05,
|
| 692 |
+
"loss": 0.1853,
|
| 693 |
+
"step": 525
|
| 694 |
+
},
|
| 695 |
+
{
|
| 696 |
+
"epoch": 6.39,
|
| 697 |
+
"learning_rate": 2.0080321285140562e-05,
|
| 698 |
+
"loss": 0.1939,
|
| 699 |
+
"step": 530
|
| 700 |
+
},
|
| 701 |
+
{
|
| 702 |
+
"epoch": 6.45,
|
| 703 |
+
"learning_rate": 1.9745649263721553e-05,
|
| 704 |
+
"loss": 0.1527,
|
| 705 |
+
"step": 535
|
| 706 |
+
},
|
| 707 |
+
{
|
| 708 |
+
"epoch": 6.51,
|
| 709 |
+
"learning_rate": 1.9410977242302544e-05,
|
| 710 |
+
"loss": 0.1743,
|
| 711 |
+
"step": 540
|
| 712 |
+
},
|
| 713 |
+
{
|
| 714 |
+
"epoch": 6.57,
|
| 715 |
+
"learning_rate": 1.9076305220883535e-05,
|
| 716 |
+
"loss": 0.1486,
|
| 717 |
+
"step": 545
|
| 718 |
+
},
|
| 719 |
+
{
|
| 720 |
+
"epoch": 6.63,
|
| 721 |
+
"learning_rate": 1.8741633199464527e-05,
|
| 722 |
+
"loss": 0.1789,
|
| 723 |
+
"step": 550
|
| 724 |
+
},
|
| 725 |
+
{
|
| 726 |
+
"epoch": 6.69,
|
| 727 |
+
"learning_rate": 1.8406961178045518e-05,
|
| 728 |
+
"loss": 0.1558,
|
| 729 |
+
"step": 555
|
| 730 |
+
},
|
| 731 |
+
{
|
| 732 |
+
"epoch": 6.75,
|
| 733 |
+
"learning_rate": 1.8072289156626505e-05,
|
| 734 |
+
"loss": 0.141,
|
| 735 |
+
"step": 560
|
| 736 |
+
},
|
| 737 |
+
{
|
| 738 |
+
"epoch": 6.81,
|
| 739 |
+
"learning_rate": 1.77376171352075e-05,
|
| 740 |
+
"loss": 0.1651,
|
| 741 |
+
"step": 565
|
| 742 |
+
},
|
| 743 |
+
{
|
| 744 |
+
"epoch": 6.87,
|
| 745 |
+
"learning_rate": 1.7402945113788487e-05,
|
| 746 |
+
"loss": 0.1338,
|
| 747 |
+
"step": 570
|
| 748 |
+
},
|
| 749 |
+
{
|
| 750 |
+
"epoch": 6.93,
|
| 751 |
+
"learning_rate": 1.706827309236948e-05,
|
| 752 |
+
"loss": 0.1594,
|
| 753 |
+
"step": 575
|
| 754 |
+
},
|
| 755 |
+
{
|
| 756 |
+
"epoch": 6.99,
|
| 757 |
+
"learning_rate": 1.673360107095047e-05,
|
| 758 |
+
"loss": 0.152,
|
| 759 |
+
"step": 580
|
| 760 |
+
},
|
| 761 |
+
{
|
| 762 |
+
"epoch": 7.0,
|
| 763 |
+
"eval_accuracy": 0.966044142614601,
|
| 764 |
+
"eval_loss": 0.10996944457292557,
|
| 765 |
+
"eval_runtime": 7.967,
|
| 766 |
+
"eval_samples_per_second": 147.861,
|
| 767 |
+
"eval_steps_per_second": 4.644,
|
| 768 |
+
"step": 581
|
| 769 |
+
},
|
| 770 |
+
{
|
| 771 |
+
"epoch": 7.05,
|
| 772 |
+
"learning_rate": 1.639892904953146e-05,
|
| 773 |
+
"loss": 0.1278,
|
| 774 |
+
"step": 585
|
| 775 |
+
},
|
| 776 |
+
{
|
| 777 |
+
"epoch": 7.11,
|
| 778 |
+
"learning_rate": 1.606425702811245e-05,
|
| 779 |
+
"loss": 0.1326,
|
| 780 |
+
"step": 590
|
| 781 |
+
},
|
| 782 |
+
{
|
| 783 |
+
"epoch": 7.17,
|
| 784 |
+
"learning_rate": 1.5729585006693442e-05,
|
| 785 |
+
"loss": 0.1364,
|
| 786 |
+
"step": 595
|
| 787 |
+
},
|
| 788 |
+
{
|
| 789 |
+
"epoch": 7.23,
|
| 790 |
+
"learning_rate": 1.5394912985274433e-05,
|
| 791 |
+
"loss": 0.1292,
|
| 792 |
+
"step": 600
|
| 793 |
+
},
|
| 794 |
+
{
|
| 795 |
+
"epoch": 7.29,
|
| 796 |
+
"learning_rate": 1.5060240963855424e-05,
|
| 797 |
+
"loss": 0.1808,
|
| 798 |
+
"step": 605
|
| 799 |
+
},
|
| 800 |
+
{
|
| 801 |
+
"epoch": 7.35,
|
| 802 |
+
"learning_rate": 1.4725568942436414e-05,
|
| 803 |
+
"loss": 0.1673,
|
| 804 |
+
"step": 610
|
| 805 |
+
},
|
| 806 |
+
{
|
| 807 |
+
"epoch": 7.41,
|
| 808 |
+
"learning_rate": 1.4390896921017405e-05,
|
| 809 |
+
"loss": 0.1472,
|
| 810 |
+
"step": 615
|
| 811 |
+
},
|
| 812 |
+
{
|
| 813 |
+
"epoch": 7.47,
|
| 814 |
+
"learning_rate": 1.4056224899598394e-05,
|
| 815 |
+
"loss": 0.1286,
|
| 816 |
+
"step": 620
|
| 817 |
+
},
|
| 818 |
+
{
|
| 819 |
+
"epoch": 7.53,
|
| 820 |
+
"learning_rate": 1.3721552878179387e-05,
|
| 821 |
+
"loss": 0.1349,
|
| 822 |
+
"step": 625
|
| 823 |
+
},
|
| 824 |
+
{
|
| 825 |
+
"epoch": 7.59,
|
| 826 |
+
"learning_rate": 1.3386880856760376e-05,
|
| 827 |
+
"loss": 0.1959,
|
| 828 |
+
"step": 630
|
| 829 |
+
},
|
| 830 |
+
{
|
| 831 |
+
"epoch": 7.65,
|
| 832 |
+
"learning_rate": 1.3052208835341367e-05,
|
| 833 |
+
"loss": 0.1359,
|
| 834 |
+
"step": 635
|
| 835 |
+
},
|
| 836 |
+
{
|
| 837 |
+
"epoch": 7.71,
|
| 838 |
+
"learning_rate": 1.2717536813922356e-05,
|
| 839 |
+
"loss": 0.1466,
|
| 840 |
+
"step": 640
|
| 841 |
+
},
|
| 842 |
+
{
|
| 843 |
+
"epoch": 7.77,
|
| 844 |
+
"learning_rate": 1.2382864792503347e-05,
|
| 845 |
+
"loss": 0.1386,
|
| 846 |
+
"step": 645
|
| 847 |
+
},
|
| 848 |
+
{
|
| 849 |
+
"epoch": 7.83,
|
| 850 |
+
"learning_rate": 1.2048192771084338e-05,
|
| 851 |
+
"loss": 0.1352,
|
| 852 |
+
"step": 650
|
| 853 |
+
},
|
| 854 |
+
{
|
| 855 |
+
"epoch": 7.89,
|
| 856 |
+
"learning_rate": 1.1713520749665328e-05,
|
| 857 |
+
"loss": 0.1608,
|
| 858 |
+
"step": 655
|
| 859 |
+
},
|
| 860 |
+
{
|
| 861 |
+
"epoch": 7.95,
|
| 862 |
+
"learning_rate": 1.1378848728246319e-05,
|
| 863 |
+
"loss": 0.1666,
|
| 864 |
+
"step": 660
|
| 865 |
+
},
|
| 866 |
+
{
|
| 867 |
+
"epoch": 8.0,
|
| 868 |
+
"eval_accuracy": 0.9626485568760611,
|
| 869 |
+
"eval_loss": 0.11297179758548737,
|
| 870 |
+
"eval_runtime": 8.3936,
|
| 871 |
+
"eval_samples_per_second": 140.345,
|
| 872 |
+
"eval_steps_per_second": 4.408,
|
| 873 |
+
"step": 664
|
| 874 |
+
},
|
| 875 |
+
{
|
| 876 |
+
"epoch": 8.01,
|
| 877 |
+
"learning_rate": 1.104417670682731e-05,
|
| 878 |
+
"loss": 0.1379,
|
| 879 |
+
"step": 665
|
| 880 |
+
},
|
| 881 |
+
{
|
| 882 |
+
"epoch": 8.07,
|
| 883 |
+
"learning_rate": 1.0709504685408301e-05,
|
| 884 |
+
"loss": 0.1651,
|
| 885 |
+
"step": 670
|
| 886 |
+
},
|
| 887 |
+
{
|
| 888 |
+
"epoch": 8.13,
|
| 889 |
+
"learning_rate": 1.037483266398929e-05,
|
| 890 |
+
"loss": 0.1656,
|
| 891 |
+
"step": 675
|
| 892 |
+
},
|
| 893 |
+
{
|
| 894 |
+
"epoch": 8.19,
|
| 895 |
+
"learning_rate": 1.0040160642570281e-05,
|
| 896 |
+
"loss": 0.1335,
|
| 897 |
+
"step": 680
|
| 898 |
+
},
|
| 899 |
+
{
|
| 900 |
+
"epoch": 8.25,
|
| 901 |
+
"learning_rate": 9.705488621151272e-06,
|
| 902 |
+
"loss": 0.1281,
|
| 903 |
+
"step": 685
|
| 904 |
+
},
|
| 905 |
+
{
|
| 906 |
+
"epoch": 8.31,
|
| 907 |
+
"learning_rate": 9.370816599732263e-06,
|
| 908 |
+
"loss": 0.1313,
|
| 909 |
+
"step": 690
|
| 910 |
+
},
|
| 911 |
+
{
|
| 912 |
+
"epoch": 8.37,
|
| 913 |
+
"learning_rate": 9.036144578313253e-06,
|
| 914 |
+
"loss": 0.1376,
|
| 915 |
+
"step": 695
|
| 916 |
+
},
|
| 917 |
+
{
|
| 918 |
+
"epoch": 8.43,
|
| 919 |
+
"learning_rate": 8.701472556894244e-06,
|
| 920 |
+
"loss": 0.1323,
|
| 921 |
+
"step": 700
|
| 922 |
+
},
|
| 923 |
+
{
|
| 924 |
+
"epoch": 8.49,
|
| 925 |
+
"learning_rate": 8.366800535475235e-06,
|
| 926 |
+
"loss": 0.1513,
|
| 927 |
+
"step": 705
|
| 928 |
+
},
|
| 929 |
+
{
|
| 930 |
+
"epoch": 8.55,
|
| 931 |
+
"learning_rate": 8.032128514056226e-06,
|
| 932 |
+
"loss": 0.1292,
|
| 933 |
+
"step": 710
|
| 934 |
+
},
|
| 935 |
+
{
|
| 936 |
+
"epoch": 8.61,
|
| 937 |
+
"learning_rate": 7.697456492637217e-06,
|
| 938 |
+
"loss": 0.1118,
|
| 939 |
+
"step": 715
|
| 940 |
+
},
|
| 941 |
+
{
|
| 942 |
+
"epoch": 8.67,
|
| 943 |
+
"learning_rate": 7.362784471218207e-06,
|
| 944 |
+
"loss": 0.1193,
|
| 945 |
+
"step": 720
|
| 946 |
+
},
|
| 947 |
+
{
|
| 948 |
+
"epoch": 8.73,
|
| 949 |
+
"learning_rate": 7.028112449799197e-06,
|
| 950 |
+
"loss": 0.1559,
|
| 951 |
+
"step": 725
|
| 952 |
+
},
|
| 953 |
+
{
|
| 954 |
+
"epoch": 8.8,
|
| 955 |
+
"learning_rate": 6.693440428380188e-06,
|
| 956 |
+
"loss": 0.148,
|
| 957 |
+
"step": 730
|
| 958 |
+
},
|
| 959 |
+
{
|
| 960 |
+
"epoch": 8.86,
|
| 961 |
+
"learning_rate": 6.358768406961178e-06,
|
| 962 |
+
"loss": 0.116,
|
| 963 |
+
"step": 735
|
| 964 |
+
},
|
| 965 |
+
{
|
| 966 |
+
"epoch": 8.92,
|
| 967 |
+
"learning_rate": 6.024096385542169e-06,
|
| 968 |
+
"loss": 0.1292,
|
| 969 |
+
"step": 740
|
| 970 |
+
},
|
| 971 |
+
{
|
| 972 |
+
"epoch": 8.98,
|
| 973 |
+
"learning_rate": 5.689424364123159e-06,
|
| 974 |
+
"loss": 0.1374,
|
| 975 |
+
"step": 745
|
| 976 |
+
},
|
| 977 |
+
{
|
| 978 |
+
"epoch": 9.0,
|
| 979 |
+
"eval_accuracy": 0.966893039049236,
|
| 980 |
+
"eval_loss": 0.1132010966539383,
|
| 981 |
+
"eval_runtime": 8.4232,
|
| 982 |
+
"eval_samples_per_second": 139.851,
|
| 983 |
+
"eval_steps_per_second": 4.393,
|
| 984 |
+
"step": 747
|
| 985 |
+
},
|
| 986 |
+
{
|
| 987 |
+
"epoch": 9.04,
|
| 988 |
+
"learning_rate": 5.3547523427041504e-06,
|
| 989 |
+
"loss": 0.1293,
|
| 990 |
+
"step": 750
|
| 991 |
+
},
|
| 992 |
+
{
|
| 993 |
+
"epoch": 9.1,
|
| 994 |
+
"learning_rate": 5.020080321285141e-06,
|
| 995 |
+
"loss": 0.1217,
|
| 996 |
+
"step": 755
|
| 997 |
+
},
|
| 998 |
+
{
|
| 999 |
+
"epoch": 9.16,
|
| 1000 |
+
"learning_rate": 4.685408299866132e-06,
|
| 1001 |
+
"loss": 0.1223,
|
| 1002 |
+
"step": 760
|
| 1003 |
+
},
|
| 1004 |
+
{
|
| 1005 |
+
"epoch": 9.22,
|
| 1006 |
+
"learning_rate": 4.350736278447122e-06,
|
| 1007 |
+
"loss": 0.1539,
|
| 1008 |
+
"step": 765
|
| 1009 |
+
},
|
| 1010 |
+
{
|
| 1011 |
+
"epoch": 9.28,
|
| 1012 |
+
"learning_rate": 4.016064257028113e-06,
|
| 1013 |
+
"loss": 0.1352,
|
| 1014 |
+
"step": 770
|
| 1015 |
+
},
|
| 1016 |
+
{
|
| 1017 |
+
"epoch": 9.34,
|
| 1018 |
+
"learning_rate": 3.6813922356091034e-06,
|
| 1019 |
+
"loss": 0.1311,
|
| 1020 |
+
"step": 775
|
| 1021 |
+
},
|
| 1022 |
+
{
|
| 1023 |
+
"epoch": 9.4,
|
| 1024 |
+
"learning_rate": 3.346720214190094e-06,
|
| 1025 |
+
"loss": 0.1168,
|
| 1026 |
+
"step": 780
|
| 1027 |
+
},
|
| 1028 |
+
{
|
| 1029 |
+
"epoch": 9.46,
|
| 1030 |
+
"learning_rate": 3.0120481927710846e-06,
|
| 1031 |
+
"loss": 0.1216,
|
| 1032 |
+
"step": 785
|
| 1033 |
+
},
|
| 1034 |
+
{
|
| 1035 |
+
"epoch": 9.52,
|
| 1036 |
+
"learning_rate": 2.6773761713520752e-06,
|
| 1037 |
+
"loss": 0.1102,
|
| 1038 |
+
"step": 790
|
| 1039 |
+
},
|
| 1040 |
+
{
|
| 1041 |
+
"epoch": 9.58,
|
| 1042 |
+
"learning_rate": 2.342704149933066e-06,
|
| 1043 |
+
"loss": 0.1335,
|
| 1044 |
+
"step": 795
|
| 1045 |
+
},
|
| 1046 |
+
{
|
| 1047 |
+
"epoch": 9.64,
|
| 1048 |
+
"learning_rate": 2.0080321285140564e-06,
|
| 1049 |
+
"loss": 0.1385,
|
| 1050 |
+
"step": 800
|
| 1051 |
+
},
|
| 1052 |
+
{
|
| 1053 |
+
"epoch": 9.7,
|
| 1054 |
+
"learning_rate": 1.673360107095047e-06,
|
| 1055 |
+
"loss": 0.1303,
|
| 1056 |
+
"step": 805
|
| 1057 |
+
},
|
| 1058 |
+
{
|
| 1059 |
+
"epoch": 9.76,
|
| 1060 |
+
"learning_rate": 1.3386880856760376e-06,
|
| 1061 |
+
"loss": 0.1314,
|
| 1062 |
+
"step": 810
|
| 1063 |
+
},
|
| 1064 |
+
{
|
| 1065 |
+
"epoch": 9.82,
|
| 1066 |
+
"learning_rate": 1.0040160642570282e-06,
|
| 1067 |
+
"loss": 0.1317,
|
| 1068 |
+
"step": 815
|
| 1069 |
+
},
|
| 1070 |
+
{
|
| 1071 |
+
"epoch": 9.88,
|
| 1072 |
+
"learning_rate": 6.693440428380188e-07,
|
| 1073 |
+
"loss": 0.1496,
|
| 1074 |
+
"step": 820
|
| 1075 |
+
},
|
| 1076 |
+
{
|
| 1077 |
+
"epoch": 9.94,
|
| 1078 |
+
"learning_rate": 3.346720214190094e-07,
|
| 1079 |
+
"loss": 0.1334,
|
| 1080 |
+
"step": 825
|
| 1081 |
+
},
|
| 1082 |
+
{
|
| 1083 |
+
"epoch": 10.0,
|
| 1084 |
+
"learning_rate": 0.0,
|
| 1085 |
+
"loss": 0.1278,
|
| 1086 |
+
"step": 830
|
| 1087 |
+
},
|
| 1088 |
+
{
|
| 1089 |
+
"epoch": 10.0,
|
| 1090 |
+
"eval_accuracy": 0.965195246179966,
|
| 1091 |
+
"eval_loss": 0.10753227770328522,
|
| 1092 |
+
"eval_runtime": 8.2617,
|
| 1093 |
+
"eval_samples_per_second": 142.586,
|
| 1094 |
+
"eval_steps_per_second": 4.479,
|
| 1095 |
+
"step": 830
|
| 1096 |
+
},
|
| 1097 |
+
{
|
| 1098 |
+
"epoch": 10.0,
|
| 1099 |
+
"step": 830,
|
| 1100 |
+
"total_flos": 2.6335377898183066e+18,
|
| 1101 |
+
"train_loss": 0.2811273262443313,
|
| 1102 |
+
"train_runtime": 1705.57,
|
| 1103 |
+
"train_samples_per_second": 62.114,
|
| 1104 |
+
"train_steps_per_second": 0.487
|
| 1105 |
+
}
|
| 1106 |
+
],
|
| 1107 |
+
"logging_steps": 5,
|
| 1108 |
+
"max_steps": 830,
|
| 1109 |
+
"num_train_epochs": 10,
|
| 1110 |
+
"save_steps": 500,
|
| 1111 |
+
"total_flos": 2.6335377898183066e+18,
|
| 1112 |
+
"trial_name": null,
|
| 1113 |
+
"trial_params": null
|
| 1114 |
+
}
|