🍻 cheers
Browse files- README.md +4 -3
- all_results.json +13 -0
- eval_results.json +8 -0
- train_results.json +8 -0
- trainer_state.json +1111 -0
README.md
CHANGED
|
@@ -3,6 +3,7 @@ library_name: transformers
|
|
| 3 |
license: apache-2.0
|
| 4 |
base_model: google/vit-base-patch16-224-in21k
|
| 5 |
tags:
|
|
|
|
| 6 |
- generated_from_trainer
|
| 7 |
metrics:
|
| 8 |
- accuracy
|
|
@@ -16,10 +17,10 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 16 |
|
| 17 |
# finetuned-for-YogaPosesv6
|
| 18 |
|
| 19 |
-
This model is a fine-tuned version of [google/vit-base-patch16-224-in21k](https://huggingface.co/google/vit-base-patch16-224-in21k) on
|
| 20 |
It achieves the following results on the evaluation set:
|
| 21 |
-
- Loss: 0.
|
| 22 |
-
- Accuracy: 0.
|
| 23 |
|
| 24 |
## Model description
|
| 25 |
|
|
|
|
| 3 |
license: apache-2.0
|
| 4 |
base_model: google/vit-base-patch16-224-in21k
|
| 5 |
tags:
|
| 6 |
+
- image-classification
|
| 7 |
- generated_from_trainer
|
| 8 |
metrics:
|
| 9 |
- accuracy
|
|
|
|
| 17 |
|
| 18 |
# finetuned-for-YogaPosesv6
|
| 19 |
|
| 20 |
+
This model is a fine-tuned version of [google/vit-base-patch16-224-in21k](https://huggingface.co/google/vit-base-patch16-224-in21k) on the yoga_pose_images dataset.
|
| 21 |
It achieves the following results on the evaluation set:
|
| 22 |
+
- Loss: 0.0562
|
| 23 |
+
- Accuracy: 0.9938
|
| 24 |
|
| 25 |
## Model description
|
| 26 |
|
all_results.json
ADDED
|
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 12.0,
|
| 3 |
+
"eval_accuracy": 0.9937694704049844,
|
| 4 |
+
"eval_loss": 0.056239403784275055,
|
| 5 |
+
"eval_runtime": 41.4407,
|
| 6 |
+
"eval_samples_per_second": 7.746,
|
| 7 |
+
"eval_steps_per_second": 0.989,
|
| 8 |
+
"total_flos": 1.685961057043243e+18,
|
| 9 |
+
"train_loss": 0.2119520413090219,
|
| 10 |
+
"train_runtime": 3626.0393,
|
| 11 |
+
"train_samples_per_second": 6.0,
|
| 12 |
+
"train_steps_per_second": 0.377
|
| 13 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 12.0,
|
| 3 |
+
"eval_accuracy": 0.9937694704049844,
|
| 4 |
+
"eval_loss": 0.056239403784275055,
|
| 5 |
+
"eval_runtime": 41.4407,
|
| 6 |
+
"eval_samples_per_second": 7.746,
|
| 7 |
+
"eval_steps_per_second": 0.989
|
| 8 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 12.0,
|
| 3 |
+
"total_flos": 1.685961057043243e+18,
|
| 4 |
+
"train_loss": 0.2119520413090219,
|
| 5 |
+
"train_runtime": 3626.0393,
|
| 6 |
+
"train_samples_per_second": 6.0,
|
| 7 |
+
"train_steps_per_second": 0.377
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,1111 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.9937694704049844,
|
| 3 |
+
"best_model_checkpoint": "finetuned-for-YogaPosesv6/checkpoint-500",
|
| 4 |
+
"epoch": 12.0,
|
| 5 |
+
"eval_steps": 100,
|
| 6 |
+
"global_step": 1368,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.08771929824561403,
|
| 13 |
+
"grad_norm": 2.090021848678589,
|
| 14 |
+
"learning_rate": 4.000000000000001e-06,
|
| 15 |
+
"loss": 1.6154,
|
| 16 |
+
"step": 10
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.17543859649122806,
|
| 20 |
+
"grad_norm": 2.025031566619873,
|
| 21 |
+
"learning_rate": 8.000000000000001e-06,
|
| 22 |
+
"loss": 1.6031,
|
| 23 |
+
"step": 20
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.2631578947368421,
|
| 27 |
+
"grad_norm": 2.1090877056121826,
|
| 28 |
+
"learning_rate": 1.2e-05,
|
| 29 |
+
"loss": 1.586,
|
| 30 |
+
"step": 30
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.3508771929824561,
|
| 34 |
+
"grad_norm": 1.609834909439087,
|
| 35 |
+
"learning_rate": 1.6000000000000003e-05,
|
| 36 |
+
"loss": 1.5428,
|
| 37 |
+
"step": 40
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.43859649122807015,
|
| 41 |
+
"grad_norm": 1.9895145893096924,
|
| 42 |
+
"learning_rate": 2e-05,
|
| 43 |
+
"loss": 1.5282,
|
| 44 |
+
"step": 50
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.5263157894736842,
|
| 48 |
+
"grad_norm": 1.7699527740478516,
|
| 49 |
+
"learning_rate": 2.4e-05,
|
| 50 |
+
"loss": 1.4324,
|
| 51 |
+
"step": 60
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.6140350877192983,
|
| 55 |
+
"grad_norm": 2.6045162677764893,
|
| 56 |
+
"learning_rate": 2.8000000000000003e-05,
|
| 57 |
+
"loss": 1.396,
|
| 58 |
+
"step": 70
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.7017543859649122,
|
| 62 |
+
"grad_norm": 1.8732093572616577,
|
| 63 |
+
"learning_rate": 3.2000000000000005e-05,
|
| 64 |
+
"loss": 1.2536,
|
| 65 |
+
"step": 80
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.7894736842105263,
|
| 69 |
+
"grad_norm": 2.3578813076019287,
|
| 70 |
+
"learning_rate": 3.6e-05,
|
| 71 |
+
"loss": 1.1474,
|
| 72 |
+
"step": 90
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.8771929824561403,
|
| 76 |
+
"grad_norm": 2.081122398376465,
|
| 77 |
+
"learning_rate": 4e-05,
|
| 78 |
+
"loss": 0.9954,
|
| 79 |
+
"step": 100
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.8771929824561403,
|
| 83 |
+
"eval_accuracy": 0.8504672897196262,
|
| 84 |
+
"eval_loss": 0.8301465511322021,
|
| 85 |
+
"eval_runtime": 38.1968,
|
| 86 |
+
"eval_samples_per_second": 8.404,
|
| 87 |
+
"eval_steps_per_second": 1.073,
|
| 88 |
+
"step": 100
|
| 89 |
+
},
|
| 90 |
+
{
|
| 91 |
+
"epoch": 0.9649122807017544,
|
| 92 |
+
"grad_norm": 1.9166618585586548,
|
| 93 |
+
"learning_rate": 4.4000000000000006e-05,
|
| 94 |
+
"loss": 0.8917,
|
| 95 |
+
"step": 110
|
| 96 |
+
},
|
| 97 |
+
{
|
| 98 |
+
"epoch": 1.0526315789473684,
|
| 99 |
+
"grad_norm": 1.809336543083191,
|
| 100 |
+
"learning_rate": 4.8e-05,
|
| 101 |
+
"loss": 0.7516,
|
| 102 |
+
"step": 120
|
| 103 |
+
},
|
| 104 |
+
{
|
| 105 |
+
"epoch": 1.1403508771929824,
|
| 106 |
+
"grad_norm": 1.7712376117706299,
|
| 107 |
+
"learning_rate": 5.2000000000000004e-05,
|
| 108 |
+
"loss": 0.642,
|
| 109 |
+
"step": 130
|
| 110 |
+
},
|
| 111 |
+
{
|
| 112 |
+
"epoch": 1.2280701754385965,
|
| 113 |
+
"grad_norm": 4.339776515960693,
|
| 114 |
+
"learning_rate": 5.6000000000000006e-05,
|
| 115 |
+
"loss": 0.5462,
|
| 116 |
+
"step": 140
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"epoch": 1.3157894736842106,
|
| 120 |
+
"grad_norm": 2.4626612663269043,
|
| 121 |
+
"learning_rate": 6e-05,
|
| 122 |
+
"loss": 0.5157,
|
| 123 |
+
"step": 150
|
| 124 |
+
},
|
| 125 |
+
{
|
| 126 |
+
"epoch": 1.4035087719298245,
|
| 127 |
+
"grad_norm": 2.7743422985076904,
|
| 128 |
+
"learning_rate": 6.400000000000001e-05,
|
| 129 |
+
"loss": 0.3905,
|
| 130 |
+
"step": 160
|
| 131 |
+
},
|
| 132 |
+
{
|
| 133 |
+
"epoch": 1.4912280701754386,
|
| 134 |
+
"grad_norm": 2.0569958686828613,
|
| 135 |
+
"learning_rate": 6.800000000000001e-05,
|
| 136 |
+
"loss": 0.3771,
|
| 137 |
+
"step": 170
|
| 138 |
+
},
|
| 139 |
+
{
|
| 140 |
+
"epoch": 1.5789473684210527,
|
| 141 |
+
"grad_norm": 2.521798849105835,
|
| 142 |
+
"learning_rate": 7.2e-05,
|
| 143 |
+
"loss": 0.3431,
|
| 144 |
+
"step": 180
|
| 145 |
+
},
|
| 146 |
+
{
|
| 147 |
+
"epoch": 1.6666666666666665,
|
| 148 |
+
"grad_norm": 3.117582082748413,
|
| 149 |
+
"learning_rate": 7.6e-05,
|
| 150 |
+
"loss": 0.3504,
|
| 151 |
+
"step": 190
|
| 152 |
+
},
|
| 153 |
+
{
|
| 154 |
+
"epoch": 1.7543859649122808,
|
| 155 |
+
"grad_norm": 4.949905872344971,
|
| 156 |
+
"learning_rate": 8e-05,
|
| 157 |
+
"loss": 0.3505,
|
| 158 |
+
"step": 200
|
| 159 |
+
},
|
| 160 |
+
{
|
| 161 |
+
"epoch": 1.7543859649122808,
|
| 162 |
+
"eval_accuracy": 0.9906542056074766,
|
| 163 |
+
"eval_loss": 0.18809494376182556,
|
| 164 |
+
"eval_runtime": 38.0933,
|
| 165 |
+
"eval_samples_per_second": 8.427,
|
| 166 |
+
"eval_steps_per_second": 1.076,
|
| 167 |
+
"step": 200
|
| 168 |
+
},
|
| 169 |
+
{
|
| 170 |
+
"epoch": 1.8421052631578947,
|
| 171 |
+
"grad_norm": 1.649777889251709,
|
| 172 |
+
"learning_rate": 8.4e-05,
|
| 173 |
+
"loss": 0.3895,
|
| 174 |
+
"step": 210
|
| 175 |
+
},
|
| 176 |
+
{
|
| 177 |
+
"epoch": 1.9298245614035088,
|
| 178 |
+
"grad_norm": 0.8415156006813049,
|
| 179 |
+
"learning_rate": 8.800000000000001e-05,
|
| 180 |
+
"loss": 0.3629,
|
| 181 |
+
"step": 220
|
| 182 |
+
},
|
| 183 |
+
{
|
| 184 |
+
"epoch": 2.017543859649123,
|
| 185 |
+
"grad_norm": 1.7786431312561035,
|
| 186 |
+
"learning_rate": 9.200000000000001e-05,
|
| 187 |
+
"loss": 0.3253,
|
| 188 |
+
"step": 230
|
| 189 |
+
},
|
| 190 |
+
{
|
| 191 |
+
"epoch": 2.1052631578947367,
|
| 192 |
+
"grad_norm": 0.7860630750656128,
|
| 193 |
+
"learning_rate": 9.6e-05,
|
| 194 |
+
"loss": 0.1751,
|
| 195 |
+
"step": 240
|
| 196 |
+
},
|
| 197 |
+
{
|
| 198 |
+
"epoch": 2.192982456140351,
|
| 199 |
+
"grad_norm": 2.1054885387420654,
|
| 200 |
+
"learning_rate": 0.0001,
|
| 201 |
+
"loss": 0.1661,
|
| 202 |
+
"step": 250
|
| 203 |
+
},
|
| 204 |
+
{
|
| 205 |
+
"epoch": 2.280701754385965,
|
| 206 |
+
"grad_norm": 2.020228147506714,
|
| 207 |
+
"learning_rate": 0.00010400000000000001,
|
| 208 |
+
"loss": 0.1355,
|
| 209 |
+
"step": 260
|
| 210 |
+
},
|
| 211 |
+
{
|
| 212 |
+
"epoch": 2.3684210526315788,
|
| 213 |
+
"grad_norm": 3.9270179271698,
|
| 214 |
+
"learning_rate": 0.00010800000000000001,
|
| 215 |
+
"loss": 0.1704,
|
| 216 |
+
"step": 270
|
| 217 |
+
},
|
| 218 |
+
{
|
| 219 |
+
"epoch": 2.456140350877193,
|
| 220 |
+
"grad_norm": 1.8998662233352661,
|
| 221 |
+
"learning_rate": 0.00011200000000000001,
|
| 222 |
+
"loss": 0.1457,
|
| 223 |
+
"step": 280
|
| 224 |
+
},
|
| 225 |
+
{
|
| 226 |
+
"epoch": 2.543859649122807,
|
| 227 |
+
"grad_norm": 2.661921739578247,
|
| 228 |
+
"learning_rate": 0.000116,
|
| 229 |
+
"loss": 0.2794,
|
| 230 |
+
"step": 290
|
| 231 |
+
},
|
| 232 |
+
{
|
| 233 |
+
"epoch": 2.6315789473684212,
|
| 234 |
+
"grad_norm": 1.873253583908081,
|
| 235 |
+
"learning_rate": 0.00012,
|
| 236 |
+
"loss": 0.1524,
|
| 237 |
+
"step": 300
|
| 238 |
+
},
|
| 239 |
+
{
|
| 240 |
+
"epoch": 2.6315789473684212,
|
| 241 |
+
"eval_accuracy": 0.9844236760124611,
|
| 242 |
+
"eval_loss": 0.09005746990442276,
|
| 243 |
+
"eval_runtime": 39.2232,
|
| 244 |
+
"eval_samples_per_second": 8.184,
|
| 245 |
+
"eval_steps_per_second": 1.045,
|
| 246 |
+
"step": 300
|
| 247 |
+
},
|
| 248 |
+
{
|
| 249 |
+
"epoch": 2.719298245614035,
|
| 250 |
+
"grad_norm": 10.5459623336792,
|
| 251 |
+
"learning_rate": 0.000124,
|
| 252 |
+
"loss": 0.1412,
|
| 253 |
+
"step": 310
|
| 254 |
+
},
|
| 255 |
+
{
|
| 256 |
+
"epoch": 2.807017543859649,
|
| 257 |
+
"grad_norm": 0.6081735491752625,
|
| 258 |
+
"learning_rate": 0.00012800000000000002,
|
| 259 |
+
"loss": 0.1265,
|
| 260 |
+
"step": 320
|
| 261 |
+
},
|
| 262 |
+
{
|
| 263 |
+
"epoch": 2.8947368421052633,
|
| 264 |
+
"grad_norm": 1.7558995485305786,
|
| 265 |
+
"learning_rate": 0.000132,
|
| 266 |
+
"loss": 0.1596,
|
| 267 |
+
"step": 330
|
| 268 |
+
},
|
| 269 |
+
{
|
| 270 |
+
"epoch": 2.982456140350877,
|
| 271 |
+
"grad_norm": 5.482118606567383,
|
| 272 |
+
"learning_rate": 0.00013600000000000003,
|
| 273 |
+
"loss": 0.2267,
|
| 274 |
+
"step": 340
|
| 275 |
+
},
|
| 276 |
+
{
|
| 277 |
+
"epoch": 3.0701754385964914,
|
| 278 |
+
"grad_norm": 1.7561366558074951,
|
| 279 |
+
"learning_rate": 0.00014,
|
| 280 |
+
"loss": 0.1492,
|
| 281 |
+
"step": 350
|
| 282 |
+
},
|
| 283 |
+
{
|
| 284 |
+
"epoch": 3.1578947368421053,
|
| 285 |
+
"grad_norm": 0.3525730073451996,
|
| 286 |
+
"learning_rate": 0.000144,
|
| 287 |
+
"loss": 0.1223,
|
| 288 |
+
"step": 360
|
| 289 |
+
},
|
| 290 |
+
{
|
| 291 |
+
"epoch": 3.245614035087719,
|
| 292 |
+
"grad_norm": 7.222944736480713,
|
| 293 |
+
"learning_rate": 0.000148,
|
| 294 |
+
"loss": 0.0743,
|
| 295 |
+
"step": 370
|
| 296 |
+
},
|
| 297 |
+
{
|
| 298 |
+
"epoch": 3.3333333333333335,
|
| 299 |
+
"grad_norm": 1.606289029121399,
|
| 300 |
+
"learning_rate": 0.000152,
|
| 301 |
+
"loss": 0.1583,
|
| 302 |
+
"step": 380
|
| 303 |
+
},
|
| 304 |
+
{
|
| 305 |
+
"epoch": 3.4210526315789473,
|
| 306 |
+
"grad_norm": 11.55585765838623,
|
| 307 |
+
"learning_rate": 0.00015600000000000002,
|
| 308 |
+
"loss": 0.097,
|
| 309 |
+
"step": 390
|
| 310 |
+
},
|
| 311 |
+
{
|
| 312 |
+
"epoch": 3.5087719298245617,
|
| 313 |
+
"grad_norm": 3.5140738487243652,
|
| 314 |
+
"learning_rate": 0.00016,
|
| 315 |
+
"loss": 0.152,
|
| 316 |
+
"step": 400
|
| 317 |
+
},
|
| 318 |
+
{
|
| 319 |
+
"epoch": 3.5087719298245617,
|
| 320 |
+
"eval_accuracy": 0.9688473520249221,
|
| 321 |
+
"eval_loss": 0.12413410097360611,
|
| 322 |
+
"eval_runtime": 38.7507,
|
| 323 |
+
"eval_samples_per_second": 8.284,
|
| 324 |
+
"eval_steps_per_second": 1.058,
|
| 325 |
+
"step": 400
|
| 326 |
+
},
|
| 327 |
+
{
|
| 328 |
+
"epoch": 3.5964912280701755,
|
| 329 |
+
"grad_norm": 0.612152099609375,
|
| 330 |
+
"learning_rate": 0.000164,
|
| 331 |
+
"loss": 0.1208,
|
| 332 |
+
"step": 410
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 3.6842105263157894,
|
| 336 |
+
"grad_norm": 0.37832212448120117,
|
| 337 |
+
"learning_rate": 0.000168,
|
| 338 |
+
"loss": 0.1313,
|
| 339 |
+
"step": 420
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 3.7719298245614032,
|
| 343 |
+
"grad_norm": 0.11094561964273453,
|
| 344 |
+
"learning_rate": 0.000172,
|
| 345 |
+
"loss": 0.0856,
|
| 346 |
+
"step": 430
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 3.8596491228070176,
|
| 350 |
+
"grad_norm": 9.22513198852539,
|
| 351 |
+
"learning_rate": 0.00017600000000000002,
|
| 352 |
+
"loss": 0.1476,
|
| 353 |
+
"step": 440
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 3.9473684210526314,
|
| 357 |
+
"grad_norm": 0.1537676453590393,
|
| 358 |
+
"learning_rate": 0.00018,
|
| 359 |
+
"loss": 0.1476,
|
| 360 |
+
"step": 450
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 4.035087719298246,
|
| 364 |
+
"grad_norm": 4.031546115875244,
|
| 365 |
+
"learning_rate": 0.00018400000000000003,
|
| 366 |
+
"loss": 0.1862,
|
| 367 |
+
"step": 460
|
| 368 |
+
},
|
| 369 |
+
{
|
| 370 |
+
"epoch": 4.12280701754386,
|
| 371 |
+
"grad_norm": 14.8175048828125,
|
| 372 |
+
"learning_rate": 0.000188,
|
| 373 |
+
"loss": 0.1613,
|
| 374 |
+
"step": 470
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 4.2105263157894735,
|
| 378 |
+
"grad_norm": 0.43281251192092896,
|
| 379 |
+
"learning_rate": 0.000192,
|
| 380 |
+
"loss": 0.0559,
|
| 381 |
+
"step": 480
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 4.298245614035087,
|
| 385 |
+
"grad_norm": 0.35636988282203674,
|
| 386 |
+
"learning_rate": 0.000196,
|
| 387 |
+
"loss": 0.1195,
|
| 388 |
+
"step": 490
|
| 389 |
+
},
|
| 390 |
+
{
|
| 391 |
+
"epoch": 4.385964912280702,
|
| 392 |
+
"grad_norm": 3.4196271896362305,
|
| 393 |
+
"learning_rate": 0.0002,
|
| 394 |
+
"loss": 0.1314,
|
| 395 |
+
"step": 500
|
| 396 |
+
},
|
| 397 |
+
{
|
| 398 |
+
"epoch": 4.385964912280702,
|
| 399 |
+
"eval_accuracy": 0.9937694704049844,
|
| 400 |
+
"eval_loss": 0.056239403784275055,
|
| 401 |
+
"eval_runtime": 39.3712,
|
| 402 |
+
"eval_samples_per_second": 8.153,
|
| 403 |
+
"eval_steps_per_second": 1.041,
|
| 404 |
+
"step": 500
|
| 405 |
+
},
|
| 406 |
+
{
|
| 407 |
+
"epoch": 4.473684210526316,
|
| 408 |
+
"grad_norm": 0.06787338107824326,
|
| 409 |
+
"learning_rate": 0.00019769585253456222,
|
| 410 |
+
"loss": 0.1154,
|
| 411 |
+
"step": 510
|
| 412 |
+
},
|
| 413 |
+
{
|
| 414 |
+
"epoch": 4.56140350877193,
|
| 415 |
+
"grad_norm": 0.06572376191616058,
|
| 416 |
+
"learning_rate": 0.00019539170506912442,
|
| 417 |
+
"loss": 0.2378,
|
| 418 |
+
"step": 520
|
| 419 |
+
},
|
| 420 |
+
{
|
| 421 |
+
"epoch": 4.649122807017544,
|
| 422 |
+
"grad_norm": 3.424962043762207,
|
| 423 |
+
"learning_rate": 0.00019308755760368663,
|
| 424 |
+
"loss": 0.1343,
|
| 425 |
+
"step": 530
|
| 426 |
+
},
|
| 427 |
+
{
|
| 428 |
+
"epoch": 4.7368421052631575,
|
| 429 |
+
"grad_norm": 11.719569206237793,
|
| 430 |
+
"learning_rate": 0.00019078341013824886,
|
| 431 |
+
"loss": 0.2701,
|
| 432 |
+
"step": 540
|
| 433 |
+
},
|
| 434 |
+
{
|
| 435 |
+
"epoch": 4.824561403508772,
|
| 436 |
+
"grad_norm": 1.354104995727539,
|
| 437 |
+
"learning_rate": 0.00018847926267281107,
|
| 438 |
+
"loss": 0.1904,
|
| 439 |
+
"step": 550
|
| 440 |
+
},
|
| 441 |
+
{
|
| 442 |
+
"epoch": 4.912280701754386,
|
| 443 |
+
"grad_norm": 2.770707368850708,
|
| 444 |
+
"learning_rate": 0.00018617511520737328,
|
| 445 |
+
"loss": 0.0849,
|
| 446 |
+
"step": 560
|
| 447 |
+
},
|
| 448 |
+
{
|
| 449 |
+
"epoch": 5.0,
|
| 450 |
+
"grad_norm": 0.06964010000228882,
|
| 451 |
+
"learning_rate": 0.00018387096774193548,
|
| 452 |
+
"loss": 0.1304,
|
| 453 |
+
"step": 570
|
| 454 |
+
},
|
| 455 |
+
{
|
| 456 |
+
"epoch": 5.087719298245614,
|
| 457 |
+
"grad_norm": 9.902205467224121,
|
| 458 |
+
"learning_rate": 0.0001815668202764977,
|
| 459 |
+
"loss": 0.1392,
|
| 460 |
+
"step": 580
|
| 461 |
+
},
|
| 462 |
+
{
|
| 463 |
+
"epoch": 5.175438596491228,
|
| 464 |
+
"grad_norm": 1.8981528282165527,
|
| 465 |
+
"learning_rate": 0.0001792626728110599,
|
| 466 |
+
"loss": 0.1597,
|
| 467 |
+
"step": 590
|
| 468 |
+
},
|
| 469 |
+
{
|
| 470 |
+
"epoch": 5.2631578947368425,
|
| 471 |
+
"grad_norm": 4.697043418884277,
|
| 472 |
+
"learning_rate": 0.00017695852534562213,
|
| 473 |
+
"loss": 0.1187,
|
| 474 |
+
"step": 600
|
| 475 |
+
},
|
| 476 |
+
{
|
| 477 |
+
"epoch": 5.2631578947368425,
|
| 478 |
+
"eval_accuracy": 0.9719626168224299,
|
| 479 |
+
"eval_loss": 0.12315332889556885,
|
| 480 |
+
"eval_runtime": 38.2715,
|
| 481 |
+
"eval_samples_per_second": 8.387,
|
| 482 |
+
"eval_steps_per_second": 1.071,
|
| 483 |
+
"step": 600
|
| 484 |
+
},
|
| 485 |
+
{
|
| 486 |
+
"epoch": 5.350877192982456,
|
| 487 |
+
"grad_norm": 6.32802152633667,
|
| 488 |
+
"learning_rate": 0.00017465437788018436,
|
| 489 |
+
"loss": 0.139,
|
| 490 |
+
"step": 610
|
| 491 |
+
},
|
| 492 |
+
{
|
| 493 |
+
"epoch": 5.43859649122807,
|
| 494 |
+
"grad_norm": 3.682849168777466,
|
| 495 |
+
"learning_rate": 0.00017235023041474657,
|
| 496 |
+
"loss": 0.1221,
|
| 497 |
+
"step": 620
|
| 498 |
+
},
|
| 499 |
+
{
|
| 500 |
+
"epoch": 5.526315789473684,
|
| 501 |
+
"grad_norm": 11.54771900177002,
|
| 502 |
+
"learning_rate": 0.00017004608294930878,
|
| 503 |
+
"loss": 0.1072,
|
| 504 |
+
"step": 630
|
| 505 |
+
},
|
| 506 |
+
{
|
| 507 |
+
"epoch": 5.614035087719298,
|
| 508 |
+
"grad_norm": 1.0544228553771973,
|
| 509 |
+
"learning_rate": 0.00016774193548387098,
|
| 510 |
+
"loss": 0.1002,
|
| 511 |
+
"step": 640
|
| 512 |
+
},
|
| 513 |
+
{
|
| 514 |
+
"epoch": 5.701754385964913,
|
| 515 |
+
"grad_norm": 2.5705864429473877,
|
| 516 |
+
"learning_rate": 0.0001654377880184332,
|
| 517 |
+
"loss": 0.1671,
|
| 518 |
+
"step": 650
|
| 519 |
+
},
|
| 520 |
+
{
|
| 521 |
+
"epoch": 5.7894736842105265,
|
| 522 |
+
"grad_norm": 0.06625229120254517,
|
| 523 |
+
"learning_rate": 0.0001631336405529954,
|
| 524 |
+
"loss": 0.0669,
|
| 525 |
+
"step": 660
|
| 526 |
+
},
|
| 527 |
+
{
|
| 528 |
+
"epoch": 5.87719298245614,
|
| 529 |
+
"grad_norm": 3.46781063079834,
|
| 530 |
+
"learning_rate": 0.0001608294930875576,
|
| 531 |
+
"loss": 0.0824,
|
| 532 |
+
"step": 670
|
| 533 |
+
},
|
| 534 |
+
{
|
| 535 |
+
"epoch": 5.964912280701754,
|
| 536 |
+
"grad_norm": 12.013016700744629,
|
| 537 |
+
"learning_rate": 0.00015852534562211984,
|
| 538 |
+
"loss": 0.2384,
|
| 539 |
+
"step": 680
|
| 540 |
+
},
|
| 541 |
+
{
|
| 542 |
+
"epoch": 6.052631578947368,
|
| 543 |
+
"grad_norm": 0.614715039730072,
|
| 544 |
+
"learning_rate": 0.00015622119815668204,
|
| 545 |
+
"loss": 0.1842,
|
| 546 |
+
"step": 690
|
| 547 |
+
},
|
| 548 |
+
{
|
| 549 |
+
"epoch": 6.140350877192983,
|
| 550 |
+
"grad_norm": 0.10228435695171356,
|
| 551 |
+
"learning_rate": 0.00015391705069124425,
|
| 552 |
+
"loss": 0.0936,
|
| 553 |
+
"step": 700
|
| 554 |
+
},
|
| 555 |
+
{
|
| 556 |
+
"epoch": 6.140350877192983,
|
| 557 |
+
"eval_accuracy": 0.9688473520249221,
|
| 558 |
+
"eval_loss": 0.08928032964468002,
|
| 559 |
+
"eval_runtime": 39.4265,
|
| 560 |
+
"eval_samples_per_second": 8.142,
|
| 561 |
+
"eval_steps_per_second": 1.04,
|
| 562 |
+
"step": 700
|
| 563 |
+
},
|
| 564 |
+
{
|
| 565 |
+
"epoch": 6.228070175438597,
|
| 566 |
+
"grad_norm": 0.7606862783432007,
|
| 567 |
+
"learning_rate": 0.00015161290322580646,
|
| 568 |
+
"loss": 0.0945,
|
| 569 |
+
"step": 710
|
| 570 |
+
},
|
| 571 |
+
{
|
| 572 |
+
"epoch": 6.315789473684211,
|
| 573 |
+
"grad_norm": 9.120923042297363,
|
| 574 |
+
"learning_rate": 0.00014930875576036866,
|
| 575 |
+
"loss": 0.0374,
|
| 576 |
+
"step": 720
|
| 577 |
+
},
|
| 578 |
+
{
|
| 579 |
+
"epoch": 6.4035087719298245,
|
| 580 |
+
"grad_norm": 0.06050215661525726,
|
| 581 |
+
"learning_rate": 0.00014700460829493087,
|
| 582 |
+
"loss": 0.0661,
|
| 583 |
+
"step": 730
|
| 584 |
+
},
|
| 585 |
+
{
|
| 586 |
+
"epoch": 6.491228070175438,
|
| 587 |
+
"grad_norm": 0.038630977272987366,
|
| 588 |
+
"learning_rate": 0.0001447004608294931,
|
| 589 |
+
"loss": 0.0551,
|
| 590 |
+
"step": 740
|
| 591 |
+
},
|
| 592 |
+
{
|
| 593 |
+
"epoch": 6.578947368421053,
|
| 594 |
+
"grad_norm": 0.04750620573759079,
|
| 595 |
+
"learning_rate": 0.0001423963133640553,
|
| 596 |
+
"loss": 0.1109,
|
| 597 |
+
"step": 750
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"epoch": 6.666666666666667,
|
| 601 |
+
"grad_norm": 0.04734950140118599,
|
| 602 |
+
"learning_rate": 0.00014009216589861752,
|
| 603 |
+
"loss": 0.0636,
|
| 604 |
+
"step": 760
|
| 605 |
+
},
|
| 606 |
+
{
|
| 607 |
+
"epoch": 6.754385964912281,
|
| 608 |
+
"grad_norm": 0.06434810161590576,
|
| 609 |
+
"learning_rate": 0.00013778801843317972,
|
| 610 |
+
"loss": 0.041,
|
| 611 |
+
"step": 770
|
| 612 |
+
},
|
| 613 |
+
{
|
| 614 |
+
"epoch": 6.842105263157895,
|
| 615 |
+
"grad_norm": 0.03571373596787453,
|
| 616 |
+
"learning_rate": 0.00013548387096774193,
|
| 617 |
+
"loss": 0.0907,
|
| 618 |
+
"step": 780
|
| 619 |
+
},
|
| 620 |
+
{
|
| 621 |
+
"epoch": 6.9298245614035086,
|
| 622 |
+
"grad_norm": 0.17006845772266388,
|
| 623 |
+
"learning_rate": 0.00013317972350230414,
|
| 624 |
+
"loss": 0.0656,
|
| 625 |
+
"step": 790
|
| 626 |
+
},
|
| 627 |
+
{
|
| 628 |
+
"epoch": 7.017543859649122,
|
| 629 |
+
"grad_norm": 0.12371964007616043,
|
| 630 |
+
"learning_rate": 0.00013087557603686637,
|
| 631 |
+
"loss": 0.0753,
|
| 632 |
+
"step": 800
|
| 633 |
+
},
|
| 634 |
+
{
|
| 635 |
+
"epoch": 7.017543859649122,
|
| 636 |
+
"eval_accuracy": 0.9626168224299065,
|
| 637 |
+
"eval_loss": 0.15095877647399902,
|
| 638 |
+
"eval_runtime": 38.9699,
|
| 639 |
+
"eval_samples_per_second": 8.237,
|
| 640 |
+
"eval_steps_per_second": 1.052,
|
| 641 |
+
"step": 800
|
| 642 |
+
},
|
| 643 |
+
{
|
| 644 |
+
"epoch": 7.105263157894737,
|
| 645 |
+
"grad_norm": 0.0659150779247284,
|
| 646 |
+
"learning_rate": 0.00012857142857142858,
|
| 647 |
+
"loss": 0.1629,
|
| 648 |
+
"step": 810
|
| 649 |
+
},
|
| 650 |
+
{
|
| 651 |
+
"epoch": 7.192982456140351,
|
| 652 |
+
"grad_norm": 0.04445948824286461,
|
| 653 |
+
"learning_rate": 0.0001262672811059908,
|
| 654 |
+
"loss": 0.0752,
|
| 655 |
+
"step": 820
|
| 656 |
+
},
|
| 657 |
+
{
|
| 658 |
+
"epoch": 7.280701754385965,
|
| 659 |
+
"grad_norm": 0.03627951070666313,
|
| 660 |
+
"learning_rate": 0.00012396313364055302,
|
| 661 |
+
"loss": 0.0597,
|
| 662 |
+
"step": 830
|
| 663 |
+
},
|
| 664 |
+
{
|
| 665 |
+
"epoch": 7.368421052631579,
|
| 666 |
+
"grad_norm": 0.02649592235684395,
|
| 667 |
+
"learning_rate": 0.00012165898617511522,
|
| 668 |
+
"loss": 0.0116,
|
| 669 |
+
"step": 840
|
| 670 |
+
},
|
| 671 |
+
{
|
| 672 |
+
"epoch": 7.456140350877193,
|
| 673 |
+
"grad_norm": 0.024187836796045303,
|
| 674 |
+
"learning_rate": 0.00011935483870967743,
|
| 675 |
+
"loss": 0.0523,
|
| 676 |
+
"step": 850
|
| 677 |
+
},
|
| 678 |
+
{
|
| 679 |
+
"epoch": 7.543859649122807,
|
| 680 |
+
"grad_norm": 0.21681664884090424,
|
| 681 |
+
"learning_rate": 0.00011705069124423964,
|
| 682 |
+
"loss": 0.0242,
|
| 683 |
+
"step": 860
|
| 684 |
+
},
|
| 685 |
+
{
|
| 686 |
+
"epoch": 7.631578947368421,
|
| 687 |
+
"grad_norm": 0.22589242458343506,
|
| 688 |
+
"learning_rate": 0.00011474654377880186,
|
| 689 |
+
"loss": 0.0306,
|
| 690 |
+
"step": 870
|
| 691 |
+
},
|
| 692 |
+
{
|
| 693 |
+
"epoch": 7.719298245614035,
|
| 694 |
+
"grad_norm": 0.04859558865427971,
|
| 695 |
+
"learning_rate": 0.00011244239631336406,
|
| 696 |
+
"loss": 0.0543,
|
| 697 |
+
"step": 880
|
| 698 |
+
},
|
| 699 |
+
{
|
| 700 |
+
"epoch": 7.807017543859649,
|
| 701 |
+
"grad_norm": 0.09744669497013092,
|
| 702 |
+
"learning_rate": 0.00011013824884792627,
|
| 703 |
+
"loss": 0.0189,
|
| 704 |
+
"step": 890
|
| 705 |
+
},
|
| 706 |
+
{
|
| 707 |
+
"epoch": 7.894736842105263,
|
| 708 |
+
"grad_norm": 0.021868959069252014,
|
| 709 |
+
"learning_rate": 0.00010783410138248849,
|
| 710 |
+
"loss": 0.0155,
|
| 711 |
+
"step": 900
|
| 712 |
+
},
|
| 713 |
+
{
|
| 714 |
+
"epoch": 7.894736842105263,
|
| 715 |
+
"eval_accuracy": 0.9906542056074766,
|
| 716 |
+
"eval_loss": 0.0535568930208683,
|
| 717 |
+
"eval_runtime": 38.9736,
|
| 718 |
+
"eval_samples_per_second": 8.236,
|
| 719 |
+
"eval_steps_per_second": 1.052,
|
| 720 |
+
"step": 900
|
| 721 |
+
},
|
| 722 |
+
{
|
| 723 |
+
"epoch": 7.982456140350877,
|
| 724 |
+
"grad_norm": 1.0035172700881958,
|
| 725 |
+
"learning_rate": 0.0001055299539170507,
|
| 726 |
+
"loss": 0.0246,
|
| 727 |
+
"step": 910
|
| 728 |
+
},
|
| 729 |
+
{
|
| 730 |
+
"epoch": 8.070175438596491,
|
| 731 |
+
"grad_norm": 0.02440941147506237,
|
| 732 |
+
"learning_rate": 0.0001032258064516129,
|
| 733 |
+
"loss": 0.0056,
|
| 734 |
+
"step": 920
|
| 735 |
+
},
|
| 736 |
+
{
|
| 737 |
+
"epoch": 8.157894736842104,
|
| 738 |
+
"grad_norm": 4.793999671936035,
|
| 739 |
+
"learning_rate": 0.00010092165898617512,
|
| 740 |
+
"loss": 0.0445,
|
| 741 |
+
"step": 930
|
| 742 |
+
},
|
| 743 |
+
{
|
| 744 |
+
"epoch": 8.24561403508772,
|
| 745 |
+
"grad_norm": 0.1290515512228012,
|
| 746 |
+
"learning_rate": 9.861751152073733e-05,
|
| 747 |
+
"loss": 0.0375,
|
| 748 |
+
"step": 940
|
| 749 |
+
},
|
| 750 |
+
{
|
| 751 |
+
"epoch": 8.333333333333334,
|
| 752 |
+
"grad_norm": 0.02080746926367283,
|
| 753 |
+
"learning_rate": 9.631336405529955e-05,
|
| 754 |
+
"loss": 0.0468,
|
| 755 |
+
"step": 950
|
| 756 |
+
},
|
| 757 |
+
{
|
| 758 |
+
"epoch": 8.421052631578947,
|
| 759 |
+
"grad_norm": 0.02122361958026886,
|
| 760 |
+
"learning_rate": 9.400921658986176e-05,
|
| 761 |
+
"loss": 0.0163,
|
| 762 |
+
"step": 960
|
| 763 |
+
},
|
| 764 |
+
{
|
| 765 |
+
"epoch": 8.508771929824562,
|
| 766 |
+
"grad_norm": 0.017971761524677277,
|
| 767 |
+
"learning_rate": 9.170506912442398e-05,
|
| 768 |
+
"loss": 0.0273,
|
| 769 |
+
"step": 970
|
| 770 |
+
},
|
| 771 |
+
{
|
| 772 |
+
"epoch": 8.596491228070175,
|
| 773 |
+
"grad_norm": 0.017901716753840446,
|
| 774 |
+
"learning_rate": 8.940092165898618e-05,
|
| 775 |
+
"loss": 0.0146,
|
| 776 |
+
"step": 980
|
| 777 |
+
},
|
| 778 |
+
{
|
| 779 |
+
"epoch": 8.68421052631579,
|
| 780 |
+
"grad_norm": 0.017680177465081215,
|
| 781 |
+
"learning_rate": 8.709677419354839e-05,
|
| 782 |
+
"loss": 0.0141,
|
| 783 |
+
"step": 990
|
| 784 |
+
},
|
| 785 |
+
{
|
| 786 |
+
"epoch": 8.771929824561404,
|
| 787 |
+
"grad_norm": 0.01786506175994873,
|
| 788 |
+
"learning_rate": 8.479262672811061e-05,
|
| 789 |
+
"loss": 0.0181,
|
| 790 |
+
"step": 1000
|
| 791 |
+
},
|
| 792 |
+
{
|
| 793 |
+
"epoch": 8.771929824561404,
|
| 794 |
+
"eval_accuracy": 0.9906542056074766,
|
| 795 |
+
"eval_loss": 0.05145588517189026,
|
| 796 |
+
"eval_runtime": 39.4613,
|
| 797 |
+
"eval_samples_per_second": 8.135,
|
| 798 |
+
"eval_steps_per_second": 1.039,
|
| 799 |
+
"step": 1000
|
| 800 |
+
},
|
| 801 |
+
{
|
| 802 |
+
"epoch": 8.859649122807017,
|
| 803 |
+
"grad_norm": 0.22676168382167816,
|
| 804 |
+
"learning_rate": 8.248847926267282e-05,
|
| 805 |
+
"loss": 0.0208,
|
| 806 |
+
"step": 1010
|
| 807 |
+
},
|
| 808 |
+
{
|
| 809 |
+
"epoch": 8.947368421052632,
|
| 810 |
+
"grad_norm": 0.018166787922382355,
|
| 811 |
+
"learning_rate": 8.018433179723502e-05,
|
| 812 |
+
"loss": 0.0043,
|
| 813 |
+
"step": 1020
|
| 814 |
+
},
|
| 815 |
+
{
|
| 816 |
+
"epoch": 9.035087719298245,
|
| 817 |
+
"grad_norm": 0.019866198301315308,
|
| 818 |
+
"learning_rate": 7.788018433179723e-05,
|
| 819 |
+
"loss": 0.0041,
|
| 820 |
+
"step": 1030
|
| 821 |
+
},
|
| 822 |
+
{
|
| 823 |
+
"epoch": 9.12280701754386,
|
| 824 |
+
"grad_norm": 0.016503507271409035,
|
| 825 |
+
"learning_rate": 7.557603686635945e-05,
|
| 826 |
+
"loss": 0.0128,
|
| 827 |
+
"step": 1040
|
| 828 |
+
},
|
| 829 |
+
{
|
| 830 |
+
"epoch": 9.210526315789474,
|
| 831 |
+
"grad_norm": 0.015296258963644505,
|
| 832 |
+
"learning_rate": 7.327188940092167e-05,
|
| 833 |
+
"loss": 0.004,
|
| 834 |
+
"step": 1050
|
| 835 |
+
},
|
| 836 |
+
{
|
| 837 |
+
"epoch": 9.298245614035087,
|
| 838 |
+
"grad_norm": 0.01723010092973709,
|
| 839 |
+
"learning_rate": 7.096774193548388e-05,
|
| 840 |
+
"loss": 0.0062,
|
| 841 |
+
"step": 1060
|
| 842 |
+
},
|
| 843 |
+
{
|
| 844 |
+
"epoch": 9.385964912280702,
|
| 845 |
+
"grad_norm": 0.035506654530763626,
|
| 846 |
+
"learning_rate": 6.86635944700461e-05,
|
| 847 |
+
"loss": 0.0057,
|
| 848 |
+
"step": 1070
|
| 849 |
+
},
|
| 850 |
+
{
|
| 851 |
+
"epoch": 9.473684210526315,
|
| 852 |
+
"grad_norm": 0.01574404165148735,
|
| 853 |
+
"learning_rate": 6.63594470046083e-05,
|
| 854 |
+
"loss": 0.0193,
|
| 855 |
+
"step": 1080
|
| 856 |
+
},
|
| 857 |
+
{
|
| 858 |
+
"epoch": 9.56140350877193,
|
| 859 |
+
"grad_norm": 0.014666405506432056,
|
| 860 |
+
"learning_rate": 6.405529953917051e-05,
|
| 861 |
+
"loss": 0.031,
|
| 862 |
+
"step": 1090
|
| 863 |
+
},
|
| 864 |
+
{
|
| 865 |
+
"epoch": 9.649122807017545,
|
| 866 |
+
"grad_norm": 0.01612703874707222,
|
| 867 |
+
"learning_rate": 6.175115207373272e-05,
|
| 868 |
+
"loss": 0.0037,
|
| 869 |
+
"step": 1100
|
| 870 |
+
},
|
| 871 |
+
{
|
| 872 |
+
"epoch": 9.649122807017545,
|
| 873 |
+
"eval_accuracy": 0.9906542056074766,
|
| 874 |
+
"eval_loss": 0.057048946619033813,
|
| 875 |
+
"eval_runtime": 39.5053,
|
| 876 |
+
"eval_samples_per_second": 8.125,
|
| 877 |
+
"eval_steps_per_second": 1.038,
|
| 878 |
+
"step": 1100
|
| 879 |
+
},
|
| 880 |
+
{
|
| 881 |
+
"epoch": 9.736842105263158,
|
| 882 |
+
"grad_norm": 0.019121702760457993,
|
| 883 |
+
"learning_rate": 5.944700460829493e-05,
|
| 884 |
+
"loss": 0.0304,
|
| 885 |
+
"step": 1110
|
| 886 |
+
},
|
| 887 |
+
{
|
| 888 |
+
"epoch": 9.824561403508772,
|
| 889 |
+
"grad_norm": 0.01632341369986534,
|
| 890 |
+
"learning_rate": 5.714285714285714e-05,
|
| 891 |
+
"loss": 0.0161,
|
| 892 |
+
"step": 1120
|
| 893 |
+
},
|
| 894 |
+
{
|
| 895 |
+
"epoch": 9.912280701754385,
|
| 896 |
+
"grad_norm": 0.01443589385598898,
|
| 897 |
+
"learning_rate": 5.4838709677419355e-05,
|
| 898 |
+
"loss": 0.0036,
|
| 899 |
+
"step": 1130
|
| 900 |
+
},
|
| 901 |
+
{
|
| 902 |
+
"epoch": 10.0,
|
| 903 |
+
"grad_norm": 0.015345915220677853,
|
| 904 |
+
"learning_rate": 5.253456221198156e-05,
|
| 905 |
+
"loss": 0.0035,
|
| 906 |
+
"step": 1140
|
| 907 |
+
},
|
| 908 |
+
{
|
| 909 |
+
"epoch": 10.087719298245615,
|
| 910 |
+
"grad_norm": 0.015197597444057465,
|
| 911 |
+
"learning_rate": 5.023041474654379e-05,
|
| 912 |
+
"loss": 0.0035,
|
| 913 |
+
"step": 1150
|
| 914 |
+
},
|
| 915 |
+
{
|
| 916 |
+
"epoch": 10.175438596491228,
|
| 917 |
+
"grad_norm": 0.014183932915329933,
|
| 918 |
+
"learning_rate": 4.792626728110599e-05,
|
| 919 |
+
"loss": 0.0143,
|
| 920 |
+
"step": 1160
|
| 921 |
+
},
|
| 922 |
+
{
|
| 923 |
+
"epoch": 10.263157894736842,
|
| 924 |
+
"grad_norm": 0.014778058975934982,
|
| 925 |
+
"learning_rate": 4.562211981566821e-05,
|
| 926 |
+
"loss": 0.0209,
|
| 927 |
+
"step": 1170
|
| 928 |
+
},
|
| 929 |
+
{
|
| 930 |
+
"epoch": 10.350877192982455,
|
| 931 |
+
"grad_norm": 0.012953384779393673,
|
| 932 |
+
"learning_rate": 4.3317972350230415e-05,
|
| 933 |
+
"loss": 0.0037,
|
| 934 |
+
"step": 1180
|
| 935 |
+
},
|
| 936 |
+
{
|
| 937 |
+
"epoch": 10.43859649122807,
|
| 938 |
+
"grad_norm": 0.013696621172130108,
|
| 939 |
+
"learning_rate": 4.101382488479263e-05,
|
| 940 |
+
"loss": 0.0033,
|
| 941 |
+
"step": 1190
|
| 942 |
+
},
|
| 943 |
+
{
|
| 944 |
+
"epoch": 10.526315789473685,
|
| 945 |
+
"grad_norm": 0.014558497816324234,
|
| 946 |
+
"learning_rate": 3.870967741935484e-05,
|
| 947 |
+
"loss": 0.0121,
|
| 948 |
+
"step": 1200
|
| 949 |
+
},
|
| 950 |
+
{
|
| 951 |
+
"epoch": 10.526315789473685,
|
| 952 |
+
"eval_accuracy": 0.9906542056074766,
|
| 953 |
+
"eval_loss": 0.05703161284327507,
|
| 954 |
+
"eval_runtime": 39.2742,
|
| 955 |
+
"eval_samples_per_second": 8.173,
|
| 956 |
+
"eval_steps_per_second": 1.044,
|
| 957 |
+
"step": 1200
|
| 958 |
+
},
|
| 959 |
+
{
|
| 960 |
+
"epoch": 10.614035087719298,
|
| 961 |
+
"grad_norm": 0.012670050375163555,
|
| 962 |
+
"learning_rate": 3.640552995391705e-05,
|
| 963 |
+
"loss": 0.0154,
|
| 964 |
+
"step": 1210
|
| 965 |
+
},
|
| 966 |
+
{
|
| 967 |
+
"epoch": 10.701754385964913,
|
| 968 |
+
"grad_norm": 0.01565767079591751,
|
| 969 |
+
"learning_rate": 3.410138248847927e-05,
|
| 970 |
+
"loss": 0.0157,
|
| 971 |
+
"step": 1220
|
| 972 |
+
},
|
| 973 |
+
{
|
| 974 |
+
"epoch": 10.789473684210526,
|
| 975 |
+
"grad_norm": 0.013182566501200199,
|
| 976 |
+
"learning_rate": 3.1797235023041475e-05,
|
| 977 |
+
"loss": 0.0033,
|
| 978 |
+
"step": 1230
|
| 979 |
+
},
|
| 980 |
+
{
|
| 981 |
+
"epoch": 10.87719298245614,
|
| 982 |
+
"grad_norm": 0.013745326548814774,
|
| 983 |
+
"learning_rate": 2.9493087557603688e-05,
|
| 984 |
+
"loss": 0.0285,
|
| 985 |
+
"step": 1240
|
| 986 |
+
},
|
| 987 |
+
{
|
| 988 |
+
"epoch": 10.964912280701755,
|
| 989 |
+
"grad_norm": 0.014731339178979397,
|
| 990 |
+
"learning_rate": 2.7188940092165898e-05,
|
| 991 |
+
"loss": 0.0032,
|
| 992 |
+
"step": 1250
|
| 993 |
+
},
|
| 994 |
+
{
|
| 995 |
+
"epoch": 11.052631578947368,
|
| 996 |
+
"grad_norm": 0.01686001382768154,
|
| 997 |
+
"learning_rate": 2.488479262672811e-05,
|
| 998 |
+
"loss": 0.0033,
|
| 999 |
+
"step": 1260
|
| 1000 |
+
},
|
| 1001 |
+
{
|
| 1002 |
+
"epoch": 11.140350877192983,
|
| 1003 |
+
"grad_norm": 0.014196813106536865,
|
| 1004 |
+
"learning_rate": 2.258064516129032e-05,
|
| 1005 |
+
"loss": 0.0233,
|
| 1006 |
+
"step": 1270
|
| 1007 |
+
},
|
| 1008 |
+
{
|
| 1009 |
+
"epoch": 11.228070175438596,
|
| 1010 |
+
"grad_norm": 0.012524433434009552,
|
| 1011 |
+
"learning_rate": 2.0276497695852538e-05,
|
| 1012 |
+
"loss": 0.0131,
|
| 1013 |
+
"step": 1280
|
| 1014 |
+
},
|
| 1015 |
+
{
|
| 1016 |
+
"epoch": 11.31578947368421,
|
| 1017 |
+
"grad_norm": 0.260022908449173,
|
| 1018 |
+
"learning_rate": 1.7972350230414748e-05,
|
| 1019 |
+
"loss": 0.0262,
|
| 1020 |
+
"step": 1290
|
| 1021 |
+
},
|
| 1022 |
+
{
|
| 1023 |
+
"epoch": 11.403508771929825,
|
| 1024 |
+
"grad_norm": 0.0144431721419096,
|
| 1025 |
+
"learning_rate": 1.5668202764976958e-05,
|
| 1026 |
+
"loss": 0.0065,
|
| 1027 |
+
"step": 1300
|
| 1028 |
+
},
|
| 1029 |
+
{
|
| 1030 |
+
"epoch": 11.403508771929825,
|
| 1031 |
+
"eval_accuracy": 0.9906542056074766,
|
| 1032 |
+
"eval_loss": 0.0564887560904026,
|
| 1033 |
+
"eval_runtime": 40.1326,
|
| 1034 |
+
"eval_samples_per_second": 7.998,
|
| 1035 |
+
"eval_steps_per_second": 1.022,
|
| 1036 |
+
"step": 1300
|
| 1037 |
+
},
|
| 1038 |
+
{
|
| 1039 |
+
"epoch": 11.491228070175438,
|
| 1040 |
+
"grad_norm": 0.012515190057456493,
|
| 1041 |
+
"learning_rate": 1.3364055299539171e-05,
|
| 1042 |
+
"loss": 0.0031,
|
| 1043 |
+
"step": 1310
|
| 1044 |
+
},
|
| 1045 |
+
{
|
| 1046 |
+
"epoch": 11.578947368421053,
|
| 1047 |
+
"grad_norm": 0.01271726656705141,
|
| 1048 |
+
"learning_rate": 1.1059907834101383e-05,
|
| 1049 |
+
"loss": 0.0031,
|
| 1050 |
+
"step": 1320
|
| 1051 |
+
},
|
| 1052 |
+
{
|
| 1053 |
+
"epoch": 11.666666666666666,
|
| 1054 |
+
"grad_norm": 0.014306453987956047,
|
| 1055 |
+
"learning_rate": 8.755760368663595e-06,
|
| 1056 |
+
"loss": 0.003,
|
| 1057 |
+
"step": 1330
|
| 1058 |
+
},
|
| 1059 |
+
{
|
| 1060 |
+
"epoch": 11.75438596491228,
|
| 1061 |
+
"grad_norm": 0.013644354417920113,
|
| 1062 |
+
"learning_rate": 6.451612903225806e-06,
|
| 1063 |
+
"loss": 0.0126,
|
| 1064 |
+
"step": 1340
|
| 1065 |
+
},
|
| 1066 |
+
{
|
| 1067 |
+
"epoch": 11.842105263157894,
|
| 1068 |
+
"grad_norm": 0.012905462644994259,
|
| 1069 |
+
"learning_rate": 4.147465437788019e-06,
|
| 1070 |
+
"loss": 0.0032,
|
| 1071 |
+
"step": 1350
|
| 1072 |
+
},
|
| 1073 |
+
{
|
| 1074 |
+
"epoch": 11.929824561403509,
|
| 1075 |
+
"grad_norm": 0.013774859718978405,
|
| 1076 |
+
"learning_rate": 1.8433179723502305e-06,
|
| 1077 |
+
"loss": 0.0033,
|
| 1078 |
+
"step": 1360
|
| 1079 |
+
},
|
| 1080 |
+
{
|
| 1081 |
+
"epoch": 12.0,
|
| 1082 |
+
"step": 1368,
|
| 1083 |
+
"total_flos": 1.685961057043243e+18,
|
| 1084 |
+
"train_loss": 0.2119520413090219,
|
| 1085 |
+
"train_runtime": 3626.0393,
|
| 1086 |
+
"train_samples_per_second": 6.0,
|
| 1087 |
+
"train_steps_per_second": 0.377
|
| 1088 |
+
}
|
| 1089 |
+
],
|
| 1090 |
+
"logging_steps": 10,
|
| 1091 |
+
"max_steps": 1368,
|
| 1092 |
+
"num_input_tokens_seen": 0,
|
| 1093 |
+
"num_train_epochs": 12,
|
| 1094 |
+
"save_steps": 100,
|
| 1095 |
+
"stateful_callbacks": {
|
| 1096 |
+
"TrainerControl": {
|
| 1097 |
+
"args": {
|
| 1098 |
+
"should_epoch_stop": false,
|
| 1099 |
+
"should_evaluate": false,
|
| 1100 |
+
"should_log": false,
|
| 1101 |
+
"should_save": true,
|
| 1102 |
+
"should_training_stop": true
|
| 1103 |
+
},
|
| 1104 |
+
"attributes": {}
|
| 1105 |
+
}
|
| 1106 |
+
},
|
| 1107 |
+
"total_flos": 1.685961057043243e+18,
|
| 1108 |
+
"train_batch_size": 16,
|
| 1109 |
+
"trial_name": null,
|
| 1110 |
+
"trial_params": null
|
| 1111 |
+
}
|