End of training
Browse files- README.md +3 -1
- all_results.json +15 -0
- eval_results.json +11 -0
- train_results.json +7 -0
- trainer_state.json +1506 -0
README.md
CHANGED
|
@@ -2,6 +2,8 @@
|
|
| 2 |
license: apache-2.0
|
| 3 |
base_model: facebook/dinov2-large
|
| 4 |
tags:
|
|
|
|
|
|
|
| 5 |
- generated_from_trainer
|
| 6 |
metrics:
|
| 7 |
- accuracy
|
|
@@ -18,7 +20,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 18 |
|
| 19 |
# dinov2-large-finetuned-galaxy10-decals
|
| 20 |
|
| 21 |
-
This model is a fine-tuned version of [facebook/dinov2-large](https://huggingface.co/facebook/dinov2-large) on
|
| 22 |
It achieves the following results on the evaluation set:
|
| 23 |
- Loss: 0.5869
|
| 24 |
- Accuracy: 0.8737
|
|
|
|
| 2 |
license: apache-2.0
|
| 3 |
base_model: facebook/dinov2-large
|
| 4 |
tags:
|
| 5 |
+
- image-classification
|
| 6 |
+
- vision
|
| 7 |
- generated_from_trainer
|
| 8 |
metrics:
|
| 9 |
- accuracy
|
|
|
|
| 20 |
|
| 21 |
# dinov2-large-finetuned-galaxy10-decals
|
| 22 |
|
| 23 |
+
This model is a fine-tuned version of [facebook/dinov2-large](https://huggingface.co/facebook/dinov2-large) on the matthieulel/galaxy10_decals dataset.
|
| 24 |
It achieves the following results on the evaluation set:
|
| 25 |
- Loss: 0.5869
|
| 26 |
- Accuracy: 0.8737
|
all_results.json
ADDED
|
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 29.76,
|
| 3 |
+
"eval_accuracy": 0.8737316798196166,
|
| 4 |
+
"eval_f1": 0.872156389323959,
|
| 5 |
+
"eval_loss": 0.586895227432251,
|
| 6 |
+
"eval_precision": 0.8722327180586174,
|
| 7 |
+
"eval_recall": 0.8737316798196166,
|
| 8 |
+
"eval_runtime": 22.0903,
|
| 9 |
+
"eval_samples_per_second": 80.307,
|
| 10 |
+
"eval_steps_per_second": 1.268,
|
| 11 |
+
"train_loss": 0.40524982412656146,
|
| 12 |
+
"train_runtime": 15843.7635,
|
| 13 |
+
"train_samples_per_second": 30.224,
|
| 14 |
+
"train_steps_per_second": 0.117
|
| 15 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,11 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 29.76,
|
| 3 |
+
"eval_accuracy": 0.8737316798196166,
|
| 4 |
+
"eval_f1": 0.872156389323959,
|
| 5 |
+
"eval_loss": 0.586895227432251,
|
| 6 |
+
"eval_precision": 0.8722327180586174,
|
| 7 |
+
"eval_recall": 0.8737316798196166,
|
| 8 |
+
"eval_runtime": 22.0903,
|
| 9 |
+
"eval_samples_per_second": 80.307,
|
| 10 |
+
"eval_steps_per_second": 1.268
|
| 11 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 29.76,
|
| 3 |
+
"train_loss": 0.40524982412656146,
|
| 4 |
+
"train_runtime": 15843.7635,
|
| 5 |
+
"train_samples_per_second": 30.224,
|
| 6 |
+
"train_steps_per_second": 0.117
|
| 7 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,1506 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.8737316798196166,
|
| 3 |
+
"best_model_checkpoint": "dinov2-large-finetuned-galaxy10-decals/checkpoint-1860",
|
| 4 |
+
"epoch": 29.76,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 1860,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.16,
|
| 13 |
+
"learning_rate": 2.688172043010753e-06,
|
| 14 |
+
"loss": 2.7977,
|
| 15 |
+
"step": 10
|
| 16 |
+
},
|
| 17 |
+
{
|
| 18 |
+
"epoch": 0.32,
|
| 19 |
+
"learning_rate": 5.376344086021506e-06,
|
| 20 |
+
"loss": 1.8679,
|
| 21 |
+
"step": 20
|
| 22 |
+
},
|
| 23 |
+
{
|
| 24 |
+
"epoch": 0.48,
|
| 25 |
+
"learning_rate": 8.064516129032258e-06,
|
| 26 |
+
"loss": 1.3021,
|
| 27 |
+
"step": 30
|
| 28 |
+
},
|
| 29 |
+
{
|
| 30 |
+
"epoch": 0.64,
|
| 31 |
+
"learning_rate": 1.0752688172043012e-05,
|
| 32 |
+
"loss": 1.004,
|
| 33 |
+
"step": 40
|
| 34 |
+
},
|
| 35 |
+
{
|
| 36 |
+
"epoch": 0.8,
|
| 37 |
+
"learning_rate": 1.3440860215053763e-05,
|
| 38 |
+
"loss": 0.9077,
|
| 39 |
+
"step": 50
|
| 40 |
+
},
|
| 41 |
+
{
|
| 42 |
+
"epoch": 0.96,
|
| 43 |
+
"learning_rate": 1.6129032258064517e-05,
|
| 44 |
+
"loss": 0.7564,
|
| 45 |
+
"step": 60
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.99,
|
| 49 |
+
"eval_accuracy": 0.7976324689966178,
|
| 50 |
+
"eval_f1": 0.79902483317454,
|
| 51 |
+
"eval_loss": 0.6187198758125305,
|
| 52 |
+
"eval_precision": 0.8170887985737173,
|
| 53 |
+
"eval_recall": 0.7976324689966178,
|
| 54 |
+
"eval_runtime": 24.6164,
|
| 55 |
+
"eval_samples_per_second": 72.066,
|
| 56 |
+
"eval_steps_per_second": 1.137,
|
| 57 |
+
"step": 62
|
| 58 |
+
},
|
| 59 |
+
{
|
| 60 |
+
"epoch": 1.12,
|
| 61 |
+
"learning_rate": 1.881720430107527e-05,
|
| 62 |
+
"loss": 0.8046,
|
| 63 |
+
"step": 70
|
| 64 |
+
},
|
| 65 |
+
{
|
| 66 |
+
"epoch": 1.28,
|
| 67 |
+
"learning_rate": 2.1505376344086024e-05,
|
| 68 |
+
"loss": 0.7356,
|
| 69 |
+
"step": 80
|
| 70 |
+
},
|
| 71 |
+
{
|
| 72 |
+
"epoch": 1.44,
|
| 73 |
+
"learning_rate": 2.4193548387096777e-05,
|
| 74 |
+
"loss": 0.7607,
|
| 75 |
+
"step": 90
|
| 76 |
+
},
|
| 77 |
+
{
|
| 78 |
+
"epoch": 1.6,
|
| 79 |
+
"learning_rate": 2.6881720430107527e-05,
|
| 80 |
+
"loss": 0.755,
|
| 81 |
+
"step": 100
|
| 82 |
+
},
|
| 83 |
+
{
|
| 84 |
+
"epoch": 1.76,
|
| 85 |
+
"learning_rate": 2.9569892473118284e-05,
|
| 86 |
+
"loss": 0.6772,
|
| 87 |
+
"step": 110
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 1.92,
|
| 91 |
+
"learning_rate": 3.2258064516129034e-05,
|
| 92 |
+
"loss": 0.7766,
|
| 93 |
+
"step": 120
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 2.0,
|
| 97 |
+
"eval_accuracy": 0.7852311161217588,
|
| 98 |
+
"eval_f1": 0.7781753717594276,
|
| 99 |
+
"eval_loss": 0.61021488904953,
|
| 100 |
+
"eval_precision": 0.8052476467823985,
|
| 101 |
+
"eval_recall": 0.7852311161217588,
|
| 102 |
+
"eval_runtime": 22.5165,
|
| 103 |
+
"eval_samples_per_second": 78.787,
|
| 104 |
+
"eval_steps_per_second": 1.244,
|
| 105 |
+
"step": 125
|
| 106 |
+
},
|
| 107 |
+
{
|
| 108 |
+
"epoch": 2.08,
|
| 109 |
+
"learning_rate": 3.494623655913979e-05,
|
| 110 |
+
"loss": 0.7641,
|
| 111 |
+
"step": 130
|
| 112 |
+
},
|
| 113 |
+
{
|
| 114 |
+
"epoch": 2.24,
|
| 115 |
+
"learning_rate": 3.763440860215054e-05,
|
| 116 |
+
"loss": 0.721,
|
| 117 |
+
"step": 140
|
| 118 |
+
},
|
| 119 |
+
{
|
| 120 |
+
"epoch": 2.4,
|
| 121 |
+
"learning_rate": 4.032258064516129e-05,
|
| 122 |
+
"loss": 0.7,
|
| 123 |
+
"step": 150
|
| 124 |
+
},
|
| 125 |
+
{
|
| 126 |
+
"epoch": 2.56,
|
| 127 |
+
"learning_rate": 4.301075268817205e-05,
|
| 128 |
+
"loss": 0.7117,
|
| 129 |
+
"step": 160
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 2.72,
|
| 133 |
+
"learning_rate": 4.56989247311828e-05,
|
| 134 |
+
"loss": 0.8347,
|
| 135 |
+
"step": 170
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 2.88,
|
| 139 |
+
"learning_rate": 4.8387096774193554e-05,
|
| 140 |
+
"loss": 0.7103,
|
| 141 |
+
"step": 180
|
| 142 |
+
},
|
| 143 |
+
{
|
| 144 |
+
"epoch": 2.99,
|
| 145 |
+
"eval_accuracy": 0.8089064261555806,
|
| 146 |
+
"eval_f1": 0.803152455190108,
|
| 147 |
+
"eval_loss": 0.5743524432182312,
|
| 148 |
+
"eval_precision": 0.8140192681408788,
|
| 149 |
+
"eval_recall": 0.8089064261555806,
|
| 150 |
+
"eval_runtime": 22.4141,
|
| 151 |
+
"eval_samples_per_second": 79.147,
|
| 152 |
+
"eval_steps_per_second": 1.249,
|
| 153 |
+
"step": 187
|
| 154 |
+
},
|
| 155 |
+
{
|
| 156 |
+
"epoch": 3.04,
|
| 157 |
+
"learning_rate": 4.98805256869773e-05,
|
| 158 |
+
"loss": 0.739,
|
| 159 |
+
"step": 190
|
| 160 |
+
},
|
| 161 |
+
{
|
| 162 |
+
"epoch": 3.2,
|
| 163 |
+
"learning_rate": 4.9581839904420555e-05,
|
| 164 |
+
"loss": 0.7019,
|
| 165 |
+
"step": 200
|
| 166 |
+
},
|
| 167 |
+
{
|
| 168 |
+
"epoch": 3.36,
|
| 169 |
+
"learning_rate": 4.92831541218638e-05,
|
| 170 |
+
"loss": 0.6871,
|
| 171 |
+
"step": 210
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 3.52,
|
| 175 |
+
"learning_rate": 4.898446833930705e-05,
|
| 176 |
+
"loss": 0.6587,
|
| 177 |
+
"step": 220
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 3.68,
|
| 181 |
+
"learning_rate": 4.86857825567503e-05,
|
| 182 |
+
"loss": 0.6707,
|
| 183 |
+
"step": 230
|
| 184 |
+
},
|
| 185 |
+
{
|
| 186 |
+
"epoch": 3.84,
|
| 187 |
+
"learning_rate": 4.8387096774193554e-05,
|
| 188 |
+
"loss": 0.6668,
|
| 189 |
+
"step": 240
|
| 190 |
+
},
|
| 191 |
+
{
|
| 192 |
+
"epoch": 4.0,
|
| 193 |
+
"learning_rate": 4.80884109916368e-05,
|
| 194 |
+
"loss": 0.6704,
|
| 195 |
+
"step": 250
|
| 196 |
+
},
|
| 197 |
+
{
|
| 198 |
+
"epoch": 4.0,
|
| 199 |
+
"eval_accuracy": 0.7745208568207441,
|
| 200 |
+
"eval_f1": 0.7663257051391182,
|
| 201 |
+
"eval_loss": 0.685870885848999,
|
| 202 |
+
"eval_precision": 0.7899083294864989,
|
| 203 |
+
"eval_recall": 0.7745208568207441,
|
| 204 |
+
"eval_runtime": 22.6111,
|
| 205 |
+
"eval_samples_per_second": 78.457,
|
| 206 |
+
"eval_steps_per_second": 1.238,
|
| 207 |
+
"step": 250
|
| 208 |
+
},
|
| 209 |
+
{
|
| 210 |
+
"epoch": 4.16,
|
| 211 |
+
"learning_rate": 4.778972520908005e-05,
|
| 212 |
+
"loss": 0.7294,
|
| 213 |
+
"step": 260
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 4.32,
|
| 217 |
+
"learning_rate": 4.74910394265233e-05,
|
| 218 |
+
"loss": 0.6412,
|
| 219 |
+
"step": 270
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 4.48,
|
| 223 |
+
"learning_rate": 4.7192353643966546e-05,
|
| 224 |
+
"loss": 0.5795,
|
| 225 |
+
"step": 280
|
| 226 |
+
},
|
| 227 |
+
{
|
| 228 |
+
"epoch": 4.64,
|
| 229 |
+
"learning_rate": 4.6893667861409805e-05,
|
| 230 |
+
"loss": 0.5931,
|
| 231 |
+
"step": 290
|
| 232 |
+
},
|
| 233 |
+
{
|
| 234 |
+
"epoch": 4.8,
|
| 235 |
+
"learning_rate": 4.659498207885305e-05,
|
| 236 |
+
"loss": 0.6334,
|
| 237 |
+
"step": 300
|
| 238 |
+
},
|
| 239 |
+
{
|
| 240 |
+
"epoch": 4.96,
|
| 241 |
+
"learning_rate": 4.62962962962963e-05,
|
| 242 |
+
"loss": 0.599,
|
| 243 |
+
"step": 310
|
| 244 |
+
},
|
| 245 |
+
{
|
| 246 |
+
"epoch": 4.99,
|
| 247 |
+
"eval_accuracy": 0.8376550169109357,
|
| 248 |
+
"eval_f1": 0.8359122308498544,
|
| 249 |
+
"eval_loss": 0.47291457653045654,
|
| 250 |
+
"eval_precision": 0.8411656033270575,
|
| 251 |
+
"eval_recall": 0.8376550169109357,
|
| 252 |
+
"eval_runtime": 22.5019,
|
| 253 |
+
"eval_samples_per_second": 78.838,
|
| 254 |
+
"eval_steps_per_second": 1.244,
|
| 255 |
+
"step": 312
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 5.12,
|
| 259 |
+
"learning_rate": 4.5997610513739546e-05,
|
| 260 |
+
"loss": 0.6053,
|
| 261 |
+
"step": 320
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 5.28,
|
| 265 |
+
"learning_rate": 4.56989247311828e-05,
|
| 266 |
+
"loss": 0.6048,
|
| 267 |
+
"step": 330
|
| 268 |
+
},
|
| 269 |
+
{
|
| 270 |
+
"epoch": 5.44,
|
| 271 |
+
"learning_rate": 4.540023894862604e-05,
|
| 272 |
+
"loss": 0.5873,
|
| 273 |
+
"step": 340
|
| 274 |
+
},
|
| 275 |
+
{
|
| 276 |
+
"epoch": 5.6,
|
| 277 |
+
"learning_rate": 4.51015531660693e-05,
|
| 278 |
+
"loss": 0.5687,
|
| 279 |
+
"step": 350
|
| 280 |
+
},
|
| 281 |
+
{
|
| 282 |
+
"epoch": 5.76,
|
| 283 |
+
"learning_rate": 4.4802867383512545e-05,
|
| 284 |
+
"loss": 0.5872,
|
| 285 |
+
"step": 360
|
| 286 |
+
},
|
| 287 |
+
{
|
| 288 |
+
"epoch": 5.92,
|
| 289 |
+
"learning_rate": 4.4504181600955796e-05,
|
| 290 |
+
"loss": 0.565,
|
| 291 |
+
"step": 370
|
| 292 |
+
},
|
| 293 |
+
{
|
| 294 |
+
"epoch": 6.0,
|
| 295 |
+
"eval_accuracy": 0.8517474633596392,
|
| 296 |
+
"eval_f1": 0.8507041486022975,
|
| 297 |
+
"eval_loss": 0.4464806914329529,
|
| 298 |
+
"eval_precision": 0.854164515473097,
|
| 299 |
+
"eval_recall": 0.8517474633596392,
|
| 300 |
+
"eval_runtime": 22.5499,
|
| 301 |
+
"eval_samples_per_second": 78.67,
|
| 302 |
+
"eval_steps_per_second": 1.242,
|
| 303 |
+
"step": 375
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 6.08,
|
| 307 |
+
"learning_rate": 4.420549581839905e-05,
|
| 308 |
+
"loss": 0.5211,
|
| 309 |
+
"step": 380
|
| 310 |
+
},
|
| 311 |
+
{
|
| 312 |
+
"epoch": 6.24,
|
| 313 |
+
"learning_rate": 4.390681003584229e-05,
|
| 314 |
+
"loss": 0.5786,
|
| 315 |
+
"step": 390
|
| 316 |
+
},
|
| 317 |
+
{
|
| 318 |
+
"epoch": 6.4,
|
| 319 |
+
"learning_rate": 4.360812425328555e-05,
|
| 320 |
+
"loss": 0.5157,
|
| 321 |
+
"step": 400
|
| 322 |
+
},
|
| 323 |
+
{
|
| 324 |
+
"epoch": 6.56,
|
| 325 |
+
"learning_rate": 4.3309438470728796e-05,
|
| 326 |
+
"loss": 0.548,
|
| 327 |
+
"step": 410
|
| 328 |
+
},
|
| 329 |
+
{
|
| 330 |
+
"epoch": 6.72,
|
| 331 |
+
"learning_rate": 4.301075268817205e-05,
|
| 332 |
+
"loss": 0.552,
|
| 333 |
+
"step": 420
|
| 334 |
+
},
|
| 335 |
+
{
|
| 336 |
+
"epoch": 6.88,
|
| 337 |
+
"learning_rate": 4.271206690561529e-05,
|
| 338 |
+
"loss": 0.5576,
|
| 339 |
+
"step": 430
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 6.99,
|
| 343 |
+
"eval_accuracy": 0.8483652762119503,
|
| 344 |
+
"eval_f1": 0.8451673044812301,
|
| 345 |
+
"eval_loss": 0.44785261154174805,
|
| 346 |
+
"eval_precision": 0.8565147367639446,
|
| 347 |
+
"eval_recall": 0.8483652762119503,
|
| 348 |
+
"eval_runtime": 22.4755,
|
| 349 |
+
"eval_samples_per_second": 78.93,
|
| 350 |
+
"eval_steps_per_second": 1.246,
|
| 351 |
+
"step": 437
|
| 352 |
+
},
|
| 353 |
+
{
|
| 354 |
+
"epoch": 7.04,
|
| 355 |
+
"learning_rate": 4.241338112305854e-05,
|
| 356 |
+
"loss": 0.572,
|
| 357 |
+
"step": 440
|
| 358 |
+
},
|
| 359 |
+
{
|
| 360 |
+
"epoch": 7.2,
|
| 361 |
+
"learning_rate": 4.2114695340501795e-05,
|
| 362 |
+
"loss": 0.524,
|
| 363 |
+
"step": 450
|
| 364 |
+
},
|
| 365 |
+
{
|
| 366 |
+
"epoch": 7.36,
|
| 367 |
+
"learning_rate": 4.1816009557945046e-05,
|
| 368 |
+
"loss": 0.5119,
|
| 369 |
+
"step": 460
|
| 370 |
+
},
|
| 371 |
+
{
|
| 372 |
+
"epoch": 7.52,
|
| 373 |
+
"learning_rate": 4.15173237753883e-05,
|
| 374 |
+
"loss": 0.4995,
|
| 375 |
+
"step": 470
|
| 376 |
+
},
|
| 377 |
+
{
|
| 378 |
+
"epoch": 7.68,
|
| 379 |
+
"learning_rate": 4.121863799283154e-05,
|
| 380 |
+
"loss": 0.4813,
|
| 381 |
+
"step": 480
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 7.84,
|
| 385 |
+
"learning_rate": 4.0919952210274794e-05,
|
| 386 |
+
"loss": 0.4991,
|
| 387 |
+
"step": 490
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 8.0,
|
| 391 |
+
"learning_rate": 4.062126642771804e-05,
|
| 392 |
+
"loss": 0.4966,
|
| 393 |
+
"step": 500
|
| 394 |
+
},
|
| 395 |
+
{
|
| 396 |
+
"epoch": 8.0,
|
| 397 |
+
"eval_accuracy": 0.8387824126268321,
|
| 398 |
+
"eval_f1": 0.8363143589644442,
|
| 399 |
+
"eval_loss": 0.48700129985809326,
|
| 400 |
+
"eval_precision": 0.8399418787633016,
|
| 401 |
+
"eval_recall": 0.8387824126268321,
|
| 402 |
+
"eval_runtime": 22.5233,
|
| 403 |
+
"eval_samples_per_second": 78.763,
|
| 404 |
+
"eval_steps_per_second": 1.243,
|
| 405 |
+
"step": 500
|
| 406 |
+
},
|
| 407 |
+
{
|
| 408 |
+
"epoch": 8.16,
|
| 409 |
+
"learning_rate": 4.032258064516129e-05,
|
| 410 |
+
"loss": 0.4157,
|
| 411 |
+
"step": 510
|
| 412 |
+
},
|
| 413 |
+
{
|
| 414 |
+
"epoch": 8.32,
|
| 415 |
+
"learning_rate": 4.002389486260454e-05,
|
| 416 |
+
"loss": 0.4344,
|
| 417 |
+
"step": 520
|
| 418 |
+
},
|
| 419 |
+
{
|
| 420 |
+
"epoch": 8.48,
|
| 421 |
+
"learning_rate": 3.972520908004779e-05,
|
| 422 |
+
"loss": 0.4766,
|
| 423 |
+
"step": 530
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 8.64,
|
| 427 |
+
"learning_rate": 3.9426523297491045e-05,
|
| 428 |
+
"loss": 0.5018,
|
| 429 |
+
"step": 540
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 8.8,
|
| 433 |
+
"learning_rate": 3.912783751493429e-05,
|
| 434 |
+
"loss": 0.5045,
|
| 435 |
+
"step": 550
|
| 436 |
+
},
|
| 437 |
+
{
|
| 438 |
+
"epoch": 8.96,
|
| 439 |
+
"learning_rate": 3.882915173237754e-05,
|
| 440 |
+
"loss": 0.4667,
|
| 441 |
+
"step": 560
|
| 442 |
+
},
|
| 443 |
+
{
|
| 444 |
+
"epoch": 8.99,
|
| 445 |
+
"eval_accuracy": 0.8444193912063134,
|
| 446 |
+
"eval_f1": 0.8442637097518081,
|
| 447 |
+
"eval_loss": 0.4763273298740387,
|
| 448 |
+
"eval_precision": 0.8495616108537656,
|
| 449 |
+
"eval_recall": 0.8444193912063134,
|
| 450 |
+
"eval_runtime": 22.5654,
|
| 451 |
+
"eval_samples_per_second": 78.616,
|
| 452 |
+
"eval_steps_per_second": 1.241,
|
| 453 |
+
"step": 562
|
| 454 |
+
},
|
| 455 |
+
{
|
| 456 |
+
"epoch": 9.12,
|
| 457 |
+
"learning_rate": 3.8530465949820786e-05,
|
| 458 |
+
"loss": 0.4291,
|
| 459 |
+
"step": 570
|
| 460 |
+
},
|
| 461 |
+
{
|
| 462 |
+
"epoch": 9.28,
|
| 463 |
+
"learning_rate": 3.8231780167264044e-05,
|
| 464 |
+
"loss": 0.4551,
|
| 465 |
+
"step": 580
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 9.44,
|
| 469 |
+
"learning_rate": 3.793309438470729e-05,
|
| 470 |
+
"loss": 0.4519,
|
| 471 |
+
"step": 590
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 9.6,
|
| 475 |
+
"learning_rate": 3.763440860215054e-05,
|
| 476 |
+
"loss": 0.4531,
|
| 477 |
+
"step": 600
|
| 478 |
+
},
|
| 479 |
+
{
|
| 480 |
+
"epoch": 9.76,
|
| 481 |
+
"learning_rate": 3.7335722819593785e-05,
|
| 482 |
+
"loss": 0.4401,
|
| 483 |
+
"step": 610
|
| 484 |
+
},
|
| 485 |
+
{
|
| 486 |
+
"epoch": 9.92,
|
| 487 |
+
"learning_rate": 3.7037037037037037e-05,
|
| 488 |
+
"loss": 0.4264,
|
| 489 |
+
"step": 620
|
| 490 |
+
},
|
| 491 |
+
{
|
| 492 |
+
"epoch": 10.0,
|
| 493 |
+
"eval_accuracy": 0.8376550169109357,
|
| 494 |
+
"eval_f1": 0.832389205615137,
|
| 495 |
+
"eval_loss": 0.4801747500896454,
|
| 496 |
+
"eval_precision": 0.8377843163688572,
|
| 497 |
+
"eval_recall": 0.8376550169109357,
|
| 498 |
+
"eval_runtime": 22.469,
|
| 499 |
+
"eval_samples_per_second": 78.953,
|
| 500 |
+
"eval_steps_per_second": 1.246,
|
| 501 |
+
"step": 625
|
| 502 |
+
},
|
| 503 |
+
{
|
| 504 |
+
"epoch": 10.08,
|
| 505 |
+
"learning_rate": 3.673835125448029e-05,
|
| 506 |
+
"loss": 0.4258,
|
| 507 |
+
"step": 630
|
| 508 |
+
},
|
| 509 |
+
{
|
| 510 |
+
"epoch": 10.24,
|
| 511 |
+
"learning_rate": 3.643966547192354e-05,
|
| 512 |
+
"loss": 0.4114,
|
| 513 |
+
"step": 640
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 10.4,
|
| 517 |
+
"learning_rate": 3.614097968936679e-05,
|
| 518 |
+
"loss": 0.4501,
|
| 519 |
+
"step": 650
|
| 520 |
+
},
|
| 521 |
+
{
|
| 522 |
+
"epoch": 10.56,
|
| 523 |
+
"learning_rate": 3.5842293906810036e-05,
|
| 524 |
+
"loss": 0.4344,
|
| 525 |
+
"step": 660
|
| 526 |
+
},
|
| 527 |
+
{
|
| 528 |
+
"epoch": 10.72,
|
| 529 |
+
"learning_rate": 3.554360812425329e-05,
|
| 530 |
+
"loss": 0.4555,
|
| 531 |
+
"step": 670
|
| 532 |
+
},
|
| 533 |
+
{
|
| 534 |
+
"epoch": 10.88,
|
| 535 |
+
"learning_rate": 3.524492234169653e-05,
|
| 536 |
+
"loss": 0.445,
|
| 537 |
+
"step": 680
|
| 538 |
+
},
|
| 539 |
+
{
|
| 540 |
+
"epoch": 10.99,
|
| 541 |
+
"eval_accuracy": 0.8376550169109357,
|
| 542 |
+
"eval_f1": 0.8343152148299824,
|
| 543 |
+
"eval_loss": 0.5245540738105774,
|
| 544 |
+
"eval_precision": 0.8383432199805607,
|
| 545 |
+
"eval_recall": 0.8376550169109357,
|
| 546 |
+
"eval_runtime": 22.4048,
|
| 547 |
+
"eval_samples_per_second": 79.179,
|
| 548 |
+
"eval_steps_per_second": 1.25,
|
| 549 |
+
"step": 687
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"epoch": 11.04,
|
| 553 |
+
"learning_rate": 3.494623655913979e-05,
|
| 554 |
+
"loss": 0.4096,
|
| 555 |
+
"step": 690
|
| 556 |
+
},
|
| 557 |
+
{
|
| 558 |
+
"epoch": 11.2,
|
| 559 |
+
"learning_rate": 3.4647550776583035e-05,
|
| 560 |
+
"loss": 0.3893,
|
| 561 |
+
"step": 700
|
| 562 |
+
},
|
| 563 |
+
{
|
| 564 |
+
"epoch": 11.36,
|
| 565 |
+
"learning_rate": 3.4348864994026287e-05,
|
| 566 |
+
"loss": 0.3837,
|
| 567 |
+
"step": 710
|
| 568 |
+
},
|
| 569 |
+
{
|
| 570 |
+
"epoch": 11.52,
|
| 571 |
+
"learning_rate": 3.405017921146954e-05,
|
| 572 |
+
"loss": 0.4279,
|
| 573 |
+
"step": 720
|
| 574 |
+
},
|
| 575 |
+
{
|
| 576 |
+
"epoch": 11.68,
|
| 577 |
+
"learning_rate": 3.375149342891278e-05,
|
| 578 |
+
"loss": 0.4347,
|
| 579 |
+
"step": 730
|
| 580 |
+
},
|
| 581 |
+
{
|
| 582 |
+
"epoch": 11.84,
|
| 583 |
+
"learning_rate": 3.3452807646356034e-05,
|
| 584 |
+
"loss": 0.3979,
|
| 585 |
+
"step": 740
|
| 586 |
+
},
|
| 587 |
+
{
|
| 588 |
+
"epoch": 12.0,
|
| 589 |
+
"learning_rate": 3.3154121863799286e-05,
|
| 590 |
+
"loss": 0.3935,
|
| 591 |
+
"step": 750
|
| 592 |
+
},
|
| 593 |
+
{
|
| 594 |
+
"epoch": 12.0,
|
| 595 |
+
"eval_accuracy": 0.8438556933483653,
|
| 596 |
+
"eval_f1": 0.8434227278877919,
|
| 597 |
+
"eval_loss": 0.48825180530548096,
|
| 598 |
+
"eval_precision": 0.8519248121654718,
|
| 599 |
+
"eval_recall": 0.8438556933483653,
|
| 600 |
+
"eval_runtime": 22.4171,
|
| 601 |
+
"eval_samples_per_second": 79.136,
|
| 602 |
+
"eval_steps_per_second": 1.249,
|
| 603 |
+
"step": 750
|
| 604 |
+
},
|
| 605 |
+
{
|
| 606 |
+
"epoch": 12.16,
|
| 607 |
+
"learning_rate": 3.285543608124254e-05,
|
| 608 |
+
"loss": 0.3493,
|
| 609 |
+
"step": 760
|
| 610 |
+
},
|
| 611 |
+
{
|
| 612 |
+
"epoch": 12.32,
|
| 613 |
+
"learning_rate": 3.255675029868578e-05,
|
| 614 |
+
"loss": 0.3344,
|
| 615 |
+
"step": 770
|
| 616 |
+
},
|
| 617 |
+
{
|
| 618 |
+
"epoch": 12.48,
|
| 619 |
+
"learning_rate": 3.2258064516129034e-05,
|
| 620 |
+
"loss": 0.3653,
|
| 621 |
+
"step": 780
|
| 622 |
+
},
|
| 623 |
+
{
|
| 624 |
+
"epoch": 12.64,
|
| 625 |
+
"learning_rate": 3.195937873357228e-05,
|
| 626 |
+
"loss": 0.4012,
|
| 627 |
+
"step": 790
|
| 628 |
+
},
|
| 629 |
+
{
|
| 630 |
+
"epoch": 12.8,
|
| 631 |
+
"learning_rate": 3.1660692951015537e-05,
|
| 632 |
+
"loss": 0.3749,
|
| 633 |
+
"step": 800
|
| 634 |
+
},
|
| 635 |
+
{
|
| 636 |
+
"epoch": 12.96,
|
| 637 |
+
"learning_rate": 3.136200716845878e-05,
|
| 638 |
+
"loss": 0.374,
|
| 639 |
+
"step": 810
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 12.99,
|
| 643 |
+
"eval_accuracy": 0.8568207440811725,
|
| 644 |
+
"eval_f1": 0.8568588686911519,
|
| 645 |
+
"eval_loss": 0.4510846436023712,
|
| 646 |
+
"eval_precision": 0.8602543269576464,
|
| 647 |
+
"eval_recall": 0.8568207440811725,
|
| 648 |
+
"eval_runtime": 22.4634,
|
| 649 |
+
"eval_samples_per_second": 78.973,
|
| 650 |
+
"eval_steps_per_second": 1.246,
|
| 651 |
+
"step": 812
|
| 652 |
+
},
|
| 653 |
+
{
|
| 654 |
+
"epoch": 13.12,
|
| 655 |
+
"learning_rate": 3.106332138590203e-05,
|
| 656 |
+
"loss": 0.346,
|
| 657 |
+
"step": 820
|
| 658 |
+
},
|
| 659 |
+
{
|
| 660 |
+
"epoch": 13.28,
|
| 661 |
+
"learning_rate": 3.0764635603345284e-05,
|
| 662 |
+
"loss": 0.3608,
|
| 663 |
+
"step": 830
|
| 664 |
+
},
|
| 665 |
+
{
|
| 666 |
+
"epoch": 13.44,
|
| 667 |
+
"learning_rate": 3.046594982078853e-05,
|
| 668 |
+
"loss": 0.3706,
|
| 669 |
+
"step": 840
|
| 670 |
+
},
|
| 671 |
+
{
|
| 672 |
+
"epoch": 13.6,
|
| 673 |
+
"learning_rate": 3.016726403823178e-05,
|
| 674 |
+
"loss": 0.3548,
|
| 675 |
+
"step": 850
|
| 676 |
+
},
|
| 677 |
+
{
|
| 678 |
+
"epoch": 13.76,
|
| 679 |
+
"learning_rate": 2.9868578255675032e-05,
|
| 680 |
+
"loss": 0.3618,
|
| 681 |
+
"step": 860
|
| 682 |
+
},
|
| 683 |
+
{
|
| 684 |
+
"epoch": 13.92,
|
| 685 |
+
"learning_rate": 2.9569892473118284e-05,
|
| 686 |
+
"loss": 0.3551,
|
| 687 |
+
"step": 870
|
| 688 |
+
},
|
| 689 |
+
{
|
| 690 |
+
"epoch": 14.0,
|
| 691 |
+
"eval_accuracy": 0.85456595264938,
|
| 692 |
+
"eval_f1": 0.8495500045026548,
|
| 693 |
+
"eval_loss": 0.5152960419654846,
|
| 694 |
+
"eval_precision": 0.8517389435426439,
|
| 695 |
+
"eval_recall": 0.85456595264938,
|
| 696 |
+
"eval_runtime": 22.3914,
|
| 697 |
+
"eval_samples_per_second": 79.227,
|
| 698 |
+
"eval_steps_per_second": 1.25,
|
| 699 |
+
"step": 875
|
| 700 |
+
},
|
| 701 |
+
{
|
| 702 |
+
"epoch": 14.08,
|
| 703 |
+
"learning_rate": 2.9271206690561532e-05,
|
| 704 |
+
"loss": 0.3527,
|
| 705 |
+
"step": 880
|
| 706 |
+
},
|
| 707 |
+
{
|
| 708 |
+
"epoch": 14.24,
|
| 709 |
+
"learning_rate": 2.897252090800478e-05,
|
| 710 |
+
"loss": 0.3111,
|
| 711 |
+
"step": 890
|
| 712 |
+
},
|
| 713 |
+
{
|
| 714 |
+
"epoch": 14.4,
|
| 715 |
+
"learning_rate": 2.8673835125448028e-05,
|
| 716 |
+
"loss": 0.316,
|
| 717 |
+
"step": 900
|
| 718 |
+
},
|
| 719 |
+
{
|
| 720 |
+
"epoch": 14.56,
|
| 721 |
+
"learning_rate": 2.8375149342891276e-05,
|
| 722 |
+
"loss": 0.3448,
|
| 723 |
+
"step": 910
|
| 724 |
+
},
|
| 725 |
+
{
|
| 726 |
+
"epoch": 14.72,
|
| 727 |
+
"learning_rate": 2.807646356033453e-05,
|
| 728 |
+
"loss": 0.341,
|
| 729 |
+
"step": 920
|
| 730 |
+
},
|
| 731 |
+
{
|
| 732 |
+
"epoch": 14.88,
|
| 733 |
+
"learning_rate": 2.777777777777778e-05,
|
| 734 |
+
"loss": 0.3573,
|
| 735 |
+
"step": 930
|
| 736 |
+
},
|
| 737 |
+
{
|
| 738 |
+
"epoch": 14.99,
|
| 739 |
+
"eval_accuracy": 0.8579481397970687,
|
| 740 |
+
"eval_f1": 0.8559499586233215,
|
| 741 |
+
"eval_loss": 0.47047653794288635,
|
| 742 |
+
"eval_precision": 0.8554345481699459,
|
| 743 |
+
"eval_recall": 0.8579481397970687,
|
| 744 |
+
"eval_runtime": 22.4353,
|
| 745 |
+
"eval_samples_per_second": 79.072,
|
| 746 |
+
"eval_steps_per_second": 1.248,
|
| 747 |
+
"step": 937
|
| 748 |
+
},
|
| 749 |
+
{
|
| 750 |
+
"epoch": 15.04,
|
| 751 |
+
"learning_rate": 2.747909199522103e-05,
|
| 752 |
+
"loss": 0.3155,
|
| 753 |
+
"step": 940
|
| 754 |
+
},
|
| 755 |
+
{
|
| 756 |
+
"epoch": 15.2,
|
| 757 |
+
"learning_rate": 2.718040621266428e-05,
|
| 758 |
+
"loss": 0.296,
|
| 759 |
+
"step": 950
|
| 760 |
+
},
|
| 761 |
+
{
|
| 762 |
+
"epoch": 15.36,
|
| 763 |
+
"learning_rate": 2.6881720430107527e-05,
|
| 764 |
+
"loss": 0.2889,
|
| 765 |
+
"step": 960
|
| 766 |
+
},
|
| 767 |
+
{
|
| 768 |
+
"epoch": 15.52,
|
| 769 |
+
"learning_rate": 2.6583034647550775e-05,
|
| 770 |
+
"loss": 0.3255,
|
| 771 |
+
"step": 970
|
| 772 |
+
},
|
| 773 |
+
{
|
| 774 |
+
"epoch": 15.68,
|
| 775 |
+
"learning_rate": 2.628434886499403e-05,
|
| 776 |
+
"loss": 0.3096,
|
| 777 |
+
"step": 980
|
| 778 |
+
},
|
| 779 |
+
{
|
| 780 |
+
"epoch": 15.84,
|
| 781 |
+
"learning_rate": 2.5985663082437278e-05,
|
| 782 |
+
"loss": 0.32,
|
| 783 |
+
"step": 990
|
| 784 |
+
},
|
| 785 |
+
{
|
| 786 |
+
"epoch": 16.0,
|
| 787 |
+
"learning_rate": 2.5686977299880526e-05,
|
| 788 |
+
"loss": 0.3385,
|
| 789 |
+
"step": 1000
|
| 790 |
+
},
|
| 791 |
+
{
|
| 792 |
+
"epoch": 16.0,
|
| 793 |
+
"eval_accuracy": 0.8517474633596392,
|
| 794 |
+
"eval_f1": 0.8517446619627265,
|
| 795 |
+
"eval_loss": 0.45465072989463806,
|
| 796 |
+
"eval_precision": 0.8534550844421815,
|
| 797 |
+
"eval_recall": 0.8517474633596392,
|
| 798 |
+
"eval_runtime": 22.4407,
|
| 799 |
+
"eval_samples_per_second": 79.053,
|
| 800 |
+
"eval_steps_per_second": 1.248,
|
| 801 |
+
"step": 1000
|
| 802 |
+
},
|
| 803 |
+
{
|
| 804 |
+
"epoch": 16.16,
|
| 805 |
+
"learning_rate": 2.5388291517323774e-05,
|
| 806 |
+
"loss": 0.3419,
|
| 807 |
+
"step": 1010
|
| 808 |
+
},
|
| 809 |
+
{
|
| 810 |
+
"epoch": 16.32,
|
| 811 |
+
"learning_rate": 2.5089605734767026e-05,
|
| 812 |
+
"loss": 0.2798,
|
| 813 |
+
"step": 1020
|
| 814 |
+
},
|
| 815 |
+
{
|
| 816 |
+
"epoch": 16.48,
|
| 817 |
+
"learning_rate": 2.4790919952210277e-05,
|
| 818 |
+
"loss": 0.2843,
|
| 819 |
+
"step": 1030
|
| 820 |
+
},
|
| 821 |
+
{
|
| 822 |
+
"epoch": 16.64,
|
| 823 |
+
"learning_rate": 2.4492234169653525e-05,
|
| 824 |
+
"loss": 0.3334,
|
| 825 |
+
"step": 1040
|
| 826 |
+
},
|
| 827 |
+
{
|
| 828 |
+
"epoch": 16.8,
|
| 829 |
+
"learning_rate": 2.4193548387096777e-05,
|
| 830 |
+
"loss": 0.2984,
|
| 831 |
+
"step": 1050
|
| 832 |
+
},
|
| 833 |
+
{
|
| 834 |
+
"epoch": 16.96,
|
| 835 |
+
"learning_rate": 2.3894862604540025e-05,
|
| 836 |
+
"loss": 0.2764,
|
| 837 |
+
"step": 1060
|
| 838 |
+
},
|
| 839 |
+
{
|
| 840 |
+
"epoch": 16.99,
|
| 841 |
+
"eval_accuracy": 0.8528748590755355,
|
| 842 |
+
"eval_f1": 0.851324755468265,
|
| 843 |
+
"eval_loss": 0.5189043879508972,
|
| 844 |
+
"eval_precision": 0.8543914754699317,
|
| 845 |
+
"eval_recall": 0.8528748590755355,
|
| 846 |
+
"eval_runtime": 22.43,
|
| 847 |
+
"eval_samples_per_second": 79.091,
|
| 848 |
+
"eval_steps_per_second": 1.248,
|
| 849 |
+
"step": 1062
|
| 850 |
+
},
|
| 851 |
+
{
|
| 852 |
+
"epoch": 17.12,
|
| 853 |
+
"learning_rate": 2.3596176821983273e-05,
|
| 854 |
+
"loss": 0.3212,
|
| 855 |
+
"step": 1070
|
| 856 |
+
},
|
| 857 |
+
{
|
| 858 |
+
"epoch": 17.28,
|
| 859 |
+
"learning_rate": 2.3297491039426525e-05,
|
| 860 |
+
"loss": 0.2831,
|
| 861 |
+
"step": 1080
|
| 862 |
+
},
|
| 863 |
+
{
|
| 864 |
+
"epoch": 17.44,
|
| 865 |
+
"learning_rate": 2.2998805256869773e-05,
|
| 866 |
+
"loss": 0.3095,
|
| 867 |
+
"step": 1090
|
| 868 |
+
},
|
| 869 |
+
{
|
| 870 |
+
"epoch": 17.6,
|
| 871 |
+
"learning_rate": 2.270011947431302e-05,
|
| 872 |
+
"loss": 0.2903,
|
| 873 |
+
"step": 1100
|
| 874 |
+
},
|
| 875 |
+
{
|
| 876 |
+
"epoch": 17.76,
|
| 877 |
+
"learning_rate": 2.2401433691756272e-05,
|
| 878 |
+
"loss": 0.2934,
|
| 879 |
+
"step": 1110
|
| 880 |
+
},
|
| 881 |
+
{
|
| 882 |
+
"epoch": 17.92,
|
| 883 |
+
"learning_rate": 2.2102747909199524e-05,
|
| 884 |
+
"loss": 0.2895,
|
| 885 |
+
"step": 1120
|
| 886 |
+
},
|
| 887 |
+
{
|
| 888 |
+
"epoch": 18.0,
|
| 889 |
+
"eval_accuracy": 0.8602029312288614,
|
| 890 |
+
"eval_f1": 0.8585833513511913,
|
| 891 |
+
"eval_loss": 0.5393418669700623,
|
| 892 |
+
"eval_precision": 0.8586924111201653,
|
| 893 |
+
"eval_recall": 0.8602029312288614,
|
| 894 |
+
"eval_runtime": 22.347,
|
| 895 |
+
"eval_samples_per_second": 79.384,
|
| 896 |
+
"eval_steps_per_second": 1.253,
|
| 897 |
+
"step": 1125
|
| 898 |
+
},
|
| 899 |
+
{
|
| 900 |
+
"epoch": 18.08,
|
| 901 |
+
"learning_rate": 2.1804062126642775e-05,
|
| 902 |
+
"loss": 0.2808,
|
| 903 |
+
"step": 1130
|
| 904 |
+
},
|
| 905 |
+
{
|
| 906 |
+
"epoch": 18.24,
|
| 907 |
+
"learning_rate": 2.1505376344086024e-05,
|
| 908 |
+
"loss": 0.262,
|
| 909 |
+
"step": 1140
|
| 910 |
+
},
|
| 911 |
+
{
|
| 912 |
+
"epoch": 18.4,
|
| 913 |
+
"learning_rate": 2.120669056152927e-05,
|
| 914 |
+
"loss": 0.2419,
|
| 915 |
+
"step": 1150
|
| 916 |
+
},
|
| 917 |
+
{
|
| 918 |
+
"epoch": 18.56,
|
| 919 |
+
"learning_rate": 2.0908004778972523e-05,
|
| 920 |
+
"loss": 0.2588,
|
| 921 |
+
"step": 1160
|
| 922 |
+
},
|
| 923 |
+
{
|
| 924 |
+
"epoch": 18.72,
|
| 925 |
+
"learning_rate": 2.060931899641577e-05,
|
| 926 |
+
"loss": 0.2648,
|
| 927 |
+
"step": 1170
|
| 928 |
+
},
|
| 929 |
+
{
|
| 930 |
+
"epoch": 18.88,
|
| 931 |
+
"learning_rate": 2.031063321385902e-05,
|
| 932 |
+
"loss": 0.2738,
|
| 933 |
+
"step": 1180
|
| 934 |
+
},
|
| 935 |
+
{
|
| 936 |
+
"epoch": 18.99,
|
| 937 |
+
"eval_accuracy": 0.8404735062006764,
|
| 938 |
+
"eval_f1": 0.8380755280956992,
|
| 939 |
+
"eval_loss": 0.5554386973381042,
|
| 940 |
+
"eval_precision": 0.8435879241848919,
|
| 941 |
+
"eval_recall": 0.8404735062006764,
|
| 942 |
+
"eval_runtime": 22.5392,
|
| 943 |
+
"eval_samples_per_second": 78.707,
|
| 944 |
+
"eval_steps_per_second": 1.242,
|
| 945 |
+
"step": 1187
|
| 946 |
+
},
|
| 947 |
+
{
|
| 948 |
+
"epoch": 19.04,
|
| 949 |
+
"learning_rate": 2.001194743130227e-05,
|
| 950 |
+
"loss": 0.269,
|
| 951 |
+
"step": 1190
|
| 952 |
+
},
|
| 953 |
+
{
|
| 954 |
+
"epoch": 19.2,
|
| 955 |
+
"learning_rate": 1.9713261648745522e-05,
|
| 956 |
+
"loss": 0.2484,
|
| 957 |
+
"step": 1200
|
| 958 |
+
},
|
| 959 |
+
{
|
| 960 |
+
"epoch": 19.36,
|
| 961 |
+
"learning_rate": 1.941457586618877e-05,
|
| 962 |
+
"loss": 0.2571,
|
| 963 |
+
"step": 1210
|
| 964 |
+
},
|
| 965 |
+
{
|
| 966 |
+
"epoch": 19.52,
|
| 967 |
+
"learning_rate": 1.9115890083632022e-05,
|
| 968 |
+
"loss": 0.2537,
|
| 969 |
+
"step": 1220
|
| 970 |
+
},
|
| 971 |
+
{
|
| 972 |
+
"epoch": 19.68,
|
| 973 |
+
"learning_rate": 1.881720430107527e-05,
|
| 974 |
+
"loss": 0.2556,
|
| 975 |
+
"step": 1230
|
| 976 |
+
},
|
| 977 |
+
{
|
| 978 |
+
"epoch": 19.84,
|
| 979 |
+
"learning_rate": 1.8518518518518518e-05,
|
| 980 |
+
"loss": 0.2732,
|
| 981 |
+
"step": 1240
|
| 982 |
+
},
|
| 983 |
+
{
|
| 984 |
+
"epoch": 20.0,
|
| 985 |
+
"learning_rate": 1.821983273596177e-05,
|
| 986 |
+
"loss": 0.2563,
|
| 987 |
+
"step": 1250
|
| 988 |
+
},
|
| 989 |
+
{
|
| 990 |
+
"epoch": 20.0,
|
| 991 |
+
"eval_accuracy": 0.8607666290868095,
|
| 992 |
+
"eval_f1": 0.8574201811479036,
|
| 993 |
+
"eval_loss": 0.5478461980819702,
|
| 994 |
+
"eval_precision": 0.8573038878183122,
|
| 995 |
+
"eval_recall": 0.8607666290868095,
|
| 996 |
+
"eval_runtime": 22.5894,
|
| 997 |
+
"eval_samples_per_second": 78.532,
|
| 998 |
+
"eval_steps_per_second": 1.24,
|
| 999 |
+
"step": 1250
|
| 1000 |
+
},
|
| 1001 |
+
{
|
| 1002 |
+
"epoch": 20.16,
|
| 1003 |
+
"learning_rate": 1.7921146953405018e-05,
|
| 1004 |
+
"loss": 0.2353,
|
| 1005 |
+
"step": 1260
|
| 1006 |
+
},
|
| 1007 |
+
{
|
| 1008 |
+
"epoch": 20.32,
|
| 1009 |
+
"learning_rate": 1.7622461170848266e-05,
|
| 1010 |
+
"loss": 0.233,
|
| 1011 |
+
"step": 1270
|
| 1012 |
+
},
|
| 1013 |
+
{
|
| 1014 |
+
"epoch": 20.48,
|
| 1015 |
+
"learning_rate": 1.7323775388291518e-05,
|
| 1016 |
+
"loss": 0.2367,
|
| 1017 |
+
"step": 1280
|
| 1018 |
+
},
|
| 1019 |
+
{
|
| 1020 |
+
"epoch": 20.64,
|
| 1021 |
+
"learning_rate": 1.702508960573477e-05,
|
| 1022 |
+
"loss": 0.249,
|
| 1023 |
+
"step": 1290
|
| 1024 |
+
},
|
| 1025 |
+
{
|
| 1026 |
+
"epoch": 20.8,
|
| 1027 |
+
"learning_rate": 1.6726403823178017e-05,
|
| 1028 |
+
"loss": 0.2451,
|
| 1029 |
+
"step": 1300
|
| 1030 |
+
},
|
| 1031 |
+
{
|
| 1032 |
+
"epoch": 20.96,
|
| 1033 |
+
"learning_rate": 1.642771804062127e-05,
|
| 1034 |
+
"loss": 0.2375,
|
| 1035 |
+
"step": 1310
|
| 1036 |
+
},
|
| 1037 |
+
{
|
| 1038 |
+
"epoch": 20.99,
|
| 1039 |
+
"eval_accuracy": 0.8664036076662909,
|
| 1040 |
+
"eval_f1": 0.8621553424312518,
|
| 1041 |
+
"eval_loss": 0.5512430667877197,
|
| 1042 |
+
"eval_precision": 0.8651236987001303,
|
| 1043 |
+
"eval_recall": 0.8664036076662909,
|
| 1044 |
+
"eval_runtime": 22.506,
|
| 1045 |
+
"eval_samples_per_second": 78.823,
|
| 1046 |
+
"eval_steps_per_second": 1.244,
|
| 1047 |
+
"step": 1312
|
| 1048 |
+
},
|
| 1049 |
+
{
|
| 1050 |
+
"epoch": 21.12,
|
| 1051 |
+
"learning_rate": 1.6129032258064517e-05,
|
| 1052 |
+
"loss": 0.2158,
|
| 1053 |
+
"step": 1320
|
| 1054 |
+
},
|
| 1055 |
+
{
|
| 1056 |
+
"epoch": 21.28,
|
| 1057 |
+
"learning_rate": 1.5830346475507768e-05,
|
| 1058 |
+
"loss": 0.2346,
|
| 1059 |
+
"step": 1330
|
| 1060 |
+
},
|
| 1061 |
+
{
|
| 1062 |
+
"epoch": 21.44,
|
| 1063 |
+
"learning_rate": 1.5531660692951016e-05,
|
| 1064 |
+
"loss": 0.2307,
|
| 1065 |
+
"step": 1340
|
| 1066 |
+
},
|
| 1067 |
+
{
|
| 1068 |
+
"epoch": 21.6,
|
| 1069 |
+
"learning_rate": 1.5232974910394265e-05,
|
| 1070 |
+
"loss": 0.2246,
|
| 1071 |
+
"step": 1350
|
| 1072 |
+
},
|
| 1073 |
+
{
|
| 1074 |
+
"epoch": 21.76,
|
| 1075 |
+
"learning_rate": 1.4934289127837516e-05,
|
| 1076 |
+
"loss": 0.2456,
|
| 1077 |
+
"step": 1360
|
| 1078 |
+
},
|
| 1079 |
+
{
|
| 1080 |
+
"epoch": 21.92,
|
| 1081 |
+
"learning_rate": 1.4635603345280766e-05,
|
| 1082 |
+
"loss": 0.2599,
|
| 1083 |
+
"step": 1370
|
| 1084 |
+
},
|
| 1085 |
+
{
|
| 1086 |
+
"epoch": 22.0,
|
| 1087 |
+
"eval_accuracy": 0.8624577226606539,
|
| 1088 |
+
"eval_f1": 0.8599244363345828,
|
| 1089 |
+
"eval_loss": 0.5316722393035889,
|
| 1090 |
+
"eval_precision": 0.8606629640313184,
|
| 1091 |
+
"eval_recall": 0.8624577226606539,
|
| 1092 |
+
"eval_runtime": 22.543,
|
| 1093 |
+
"eval_samples_per_second": 78.694,
|
| 1094 |
+
"eval_steps_per_second": 1.242,
|
| 1095 |
+
"step": 1375
|
| 1096 |
+
},
|
| 1097 |
+
{
|
| 1098 |
+
"epoch": 22.08,
|
| 1099 |
+
"learning_rate": 1.4336917562724014e-05,
|
| 1100 |
+
"loss": 0.2305,
|
| 1101 |
+
"step": 1380
|
| 1102 |
+
},
|
| 1103 |
+
{
|
| 1104 |
+
"epoch": 22.24,
|
| 1105 |
+
"learning_rate": 1.4038231780167265e-05,
|
| 1106 |
+
"loss": 0.1953,
|
| 1107 |
+
"step": 1390
|
| 1108 |
+
},
|
| 1109 |
+
{
|
| 1110 |
+
"epoch": 22.4,
|
| 1111 |
+
"learning_rate": 1.3739545997610515e-05,
|
| 1112 |
+
"loss": 0.2223,
|
| 1113 |
+
"step": 1400
|
| 1114 |
+
},
|
| 1115 |
+
{
|
| 1116 |
+
"epoch": 22.56,
|
| 1117 |
+
"learning_rate": 1.3440860215053763e-05,
|
| 1118 |
+
"loss": 0.2179,
|
| 1119 |
+
"step": 1410
|
| 1120 |
+
},
|
| 1121 |
+
{
|
| 1122 |
+
"epoch": 22.72,
|
| 1123 |
+
"learning_rate": 1.3142174432497015e-05,
|
| 1124 |
+
"loss": 0.2149,
|
| 1125 |
+
"step": 1420
|
| 1126 |
+
},
|
| 1127 |
+
{
|
| 1128 |
+
"epoch": 22.88,
|
| 1129 |
+
"learning_rate": 1.2843488649940263e-05,
|
| 1130 |
+
"loss": 0.2146,
|
| 1131 |
+
"step": 1430
|
| 1132 |
+
},
|
| 1133 |
+
{
|
| 1134 |
+
"epoch": 22.99,
|
| 1135 |
+
"eval_accuracy": 0.8568207440811725,
|
| 1136 |
+
"eval_f1": 0.855887173333211,
|
| 1137 |
+
"eval_loss": 0.5971649885177612,
|
| 1138 |
+
"eval_precision": 0.8566915988066761,
|
| 1139 |
+
"eval_recall": 0.8568207440811725,
|
| 1140 |
+
"eval_runtime": 22.5854,
|
| 1141 |
+
"eval_samples_per_second": 78.546,
|
| 1142 |
+
"eval_steps_per_second": 1.24,
|
| 1143 |
+
"step": 1437
|
| 1144 |
+
},
|
| 1145 |
+
{
|
| 1146 |
+
"epoch": 23.04,
|
| 1147 |
+
"learning_rate": 1.2544802867383513e-05,
|
| 1148 |
+
"loss": 0.2063,
|
| 1149 |
+
"step": 1440
|
| 1150 |
+
},
|
| 1151 |
+
{
|
| 1152 |
+
"epoch": 23.2,
|
| 1153 |
+
"learning_rate": 1.2246117084826763e-05,
|
| 1154 |
+
"loss": 0.209,
|
| 1155 |
+
"step": 1450
|
| 1156 |
+
},
|
| 1157 |
+
{
|
| 1158 |
+
"epoch": 23.36,
|
| 1159 |
+
"learning_rate": 1.1947431302270013e-05,
|
| 1160 |
+
"loss": 0.2039,
|
| 1161 |
+
"step": 1460
|
| 1162 |
+
},
|
| 1163 |
+
{
|
| 1164 |
+
"epoch": 23.52,
|
| 1165 |
+
"learning_rate": 1.1648745519713262e-05,
|
| 1166 |
+
"loss": 0.22,
|
| 1167 |
+
"step": 1470
|
| 1168 |
+
},
|
| 1169 |
+
{
|
| 1170 |
+
"epoch": 23.68,
|
| 1171 |
+
"learning_rate": 1.135005973715651e-05,
|
| 1172 |
+
"loss": 0.2463,
|
| 1173 |
+
"step": 1480
|
| 1174 |
+
},
|
| 1175 |
+
{
|
| 1176 |
+
"epoch": 23.84,
|
| 1177 |
+
"learning_rate": 1.1051373954599762e-05,
|
| 1178 |
+
"loss": 0.1984,
|
| 1179 |
+
"step": 1490
|
| 1180 |
+
},
|
| 1181 |
+
{
|
| 1182 |
+
"epoch": 24.0,
|
| 1183 |
+
"learning_rate": 1.0752688172043012e-05,
|
| 1184 |
+
"loss": 0.2132,
|
| 1185 |
+
"step": 1500
|
| 1186 |
+
},
|
| 1187 |
+
{
|
| 1188 |
+
"epoch": 24.0,
|
| 1189 |
+
"eval_accuracy": 0.8635851183765502,
|
| 1190 |
+
"eval_f1": 0.8606211950492338,
|
| 1191 |
+
"eval_loss": 0.5933902859687805,
|
| 1192 |
+
"eval_precision": 0.8617445208407427,
|
| 1193 |
+
"eval_recall": 0.8635851183765502,
|
| 1194 |
+
"eval_runtime": 22.5856,
|
| 1195 |
+
"eval_samples_per_second": 78.546,
|
| 1196 |
+
"eval_steps_per_second": 1.24,
|
| 1197 |
+
"step": 1500
|
| 1198 |
+
},
|
| 1199 |
+
{
|
| 1200 |
+
"epoch": 24.16,
|
| 1201 |
+
"learning_rate": 1.0454002389486262e-05,
|
| 1202 |
+
"loss": 0.2098,
|
| 1203 |
+
"step": 1510
|
| 1204 |
+
},
|
| 1205 |
+
{
|
| 1206 |
+
"epoch": 24.32,
|
| 1207 |
+
"learning_rate": 1.015531660692951e-05,
|
| 1208 |
+
"loss": 0.22,
|
| 1209 |
+
"step": 1520
|
| 1210 |
+
},
|
| 1211 |
+
{
|
| 1212 |
+
"epoch": 24.48,
|
| 1213 |
+
"learning_rate": 9.856630824372761e-06,
|
| 1214 |
+
"loss": 0.2177,
|
| 1215 |
+
"step": 1530
|
| 1216 |
+
},
|
| 1217 |
+
{
|
| 1218 |
+
"epoch": 24.64,
|
| 1219 |
+
"learning_rate": 9.557945041816011e-06,
|
| 1220 |
+
"loss": 0.192,
|
| 1221 |
+
"step": 1540
|
| 1222 |
+
},
|
| 1223 |
+
{
|
| 1224 |
+
"epoch": 24.8,
|
| 1225 |
+
"learning_rate": 9.259259259259259e-06,
|
| 1226 |
+
"loss": 0.2001,
|
| 1227 |
+
"step": 1550
|
| 1228 |
+
},
|
| 1229 |
+
{
|
| 1230 |
+
"epoch": 24.96,
|
| 1231 |
+
"learning_rate": 8.960573476702509e-06,
|
| 1232 |
+
"loss": 0.2036,
|
| 1233 |
+
"step": 1560
|
| 1234 |
+
},
|
| 1235 |
+
{
|
| 1236 |
+
"epoch": 24.99,
|
| 1237 |
+
"eval_accuracy": 0.8664036076662909,
|
| 1238 |
+
"eval_f1": 0.8657672120824895,
|
| 1239 |
+
"eval_loss": 0.5923020839691162,
|
| 1240 |
+
"eval_precision": 0.8662484245822287,
|
| 1241 |
+
"eval_recall": 0.8664036076662909,
|
| 1242 |
+
"eval_runtime": 22.5989,
|
| 1243 |
+
"eval_samples_per_second": 78.499,
|
| 1244 |
+
"eval_steps_per_second": 1.239,
|
| 1245 |
+
"step": 1562
|
| 1246 |
+
},
|
| 1247 |
+
{
|
| 1248 |
+
"epoch": 25.12,
|
| 1249 |
+
"learning_rate": 8.661887694145759e-06,
|
| 1250 |
+
"loss": 0.2018,
|
| 1251 |
+
"step": 1570
|
| 1252 |
+
},
|
| 1253 |
+
{
|
| 1254 |
+
"epoch": 25.28,
|
| 1255 |
+
"learning_rate": 8.363201911589009e-06,
|
| 1256 |
+
"loss": 0.1692,
|
| 1257 |
+
"step": 1580
|
| 1258 |
+
},
|
| 1259 |
+
{
|
| 1260 |
+
"epoch": 25.44,
|
| 1261 |
+
"learning_rate": 8.064516129032258e-06,
|
| 1262 |
+
"loss": 0.181,
|
| 1263 |
+
"step": 1590
|
| 1264 |
+
},
|
| 1265 |
+
{
|
| 1266 |
+
"epoch": 25.6,
|
| 1267 |
+
"learning_rate": 7.765830346475508e-06,
|
| 1268 |
+
"loss": 0.1927,
|
| 1269 |
+
"step": 1600
|
| 1270 |
+
},
|
| 1271 |
+
{
|
| 1272 |
+
"epoch": 25.76,
|
| 1273 |
+
"learning_rate": 7.467144563918758e-06,
|
| 1274 |
+
"loss": 0.1873,
|
| 1275 |
+
"step": 1610
|
| 1276 |
+
},
|
| 1277 |
+
{
|
| 1278 |
+
"epoch": 25.92,
|
| 1279 |
+
"learning_rate": 7.168458781362007e-06,
|
| 1280 |
+
"loss": 0.1971,
|
| 1281 |
+
"step": 1620
|
| 1282 |
+
},
|
| 1283 |
+
{
|
| 1284 |
+
"epoch": 26.0,
|
| 1285 |
+
"eval_accuracy": 0.863021420518602,
|
| 1286 |
+
"eval_f1": 0.8621322077660976,
|
| 1287 |
+
"eval_loss": 0.5839389562606812,
|
| 1288 |
+
"eval_precision": 0.8621026992886056,
|
| 1289 |
+
"eval_recall": 0.863021420518602,
|
| 1290 |
+
"eval_runtime": 22.442,
|
| 1291 |
+
"eval_samples_per_second": 79.048,
|
| 1292 |
+
"eval_steps_per_second": 1.248,
|
| 1293 |
+
"step": 1625
|
| 1294 |
+
},
|
| 1295 |
+
{
|
| 1296 |
+
"epoch": 26.08,
|
| 1297 |
+
"learning_rate": 6.869772998805258e-06,
|
| 1298 |
+
"loss": 0.1971,
|
| 1299 |
+
"step": 1630
|
| 1300 |
+
},
|
| 1301 |
+
{
|
| 1302 |
+
"epoch": 26.24,
|
| 1303 |
+
"learning_rate": 6.5710872162485075e-06,
|
| 1304 |
+
"loss": 0.1948,
|
| 1305 |
+
"step": 1640
|
| 1306 |
+
},
|
| 1307 |
+
{
|
| 1308 |
+
"epoch": 26.4,
|
| 1309 |
+
"learning_rate": 6.2724014336917564e-06,
|
| 1310 |
+
"loss": 0.1886,
|
| 1311 |
+
"step": 1650
|
| 1312 |
+
},
|
| 1313 |
+
{
|
| 1314 |
+
"epoch": 26.56,
|
| 1315 |
+
"learning_rate": 5.973715651135006e-06,
|
| 1316 |
+
"loss": 0.1928,
|
| 1317 |
+
"step": 1660
|
| 1318 |
+
},
|
| 1319 |
+
{
|
| 1320 |
+
"epoch": 26.72,
|
| 1321 |
+
"learning_rate": 5.675029868578255e-06,
|
| 1322 |
+
"loss": 0.1966,
|
| 1323 |
+
"step": 1670
|
| 1324 |
+
},
|
| 1325 |
+
{
|
| 1326 |
+
"epoch": 26.88,
|
| 1327 |
+
"learning_rate": 5.376344086021506e-06,
|
| 1328 |
+
"loss": 0.1878,
|
| 1329 |
+
"step": 1680
|
| 1330 |
+
},
|
| 1331 |
+
{
|
| 1332 |
+
"epoch": 26.99,
|
| 1333 |
+
"eval_accuracy": 0.8624577226606539,
|
| 1334 |
+
"eval_f1": 0.8640203850514281,
|
| 1335 |
+
"eval_loss": 0.5907111763954163,
|
| 1336 |
+
"eval_precision": 0.8669146424665295,
|
| 1337 |
+
"eval_recall": 0.8624577226606539,
|
| 1338 |
+
"eval_runtime": 22.4258,
|
| 1339 |
+
"eval_samples_per_second": 79.105,
|
| 1340 |
+
"eval_steps_per_second": 1.249,
|
| 1341 |
+
"step": 1687
|
| 1342 |
+
},
|
| 1343 |
+
{
|
| 1344 |
+
"epoch": 27.04,
|
| 1345 |
+
"learning_rate": 5.077658303464755e-06,
|
| 1346 |
+
"loss": 0.1874,
|
| 1347 |
+
"step": 1690
|
| 1348 |
+
},
|
| 1349 |
+
{
|
| 1350 |
+
"epoch": 27.2,
|
| 1351 |
+
"learning_rate": 4.7789725209080055e-06,
|
| 1352 |
+
"loss": 0.1776,
|
| 1353 |
+
"step": 1700
|
| 1354 |
+
},
|
| 1355 |
+
{
|
| 1356 |
+
"epoch": 27.36,
|
| 1357 |
+
"learning_rate": 4.4802867383512545e-06,
|
| 1358 |
+
"loss": 0.2073,
|
| 1359 |
+
"step": 1710
|
| 1360 |
+
},
|
| 1361 |
+
{
|
| 1362 |
+
"epoch": 27.52,
|
| 1363 |
+
"learning_rate": 4.181600955794504e-06,
|
| 1364 |
+
"loss": 0.1797,
|
| 1365 |
+
"step": 1720
|
| 1366 |
+
},
|
| 1367 |
+
{
|
| 1368 |
+
"epoch": 27.68,
|
| 1369 |
+
"learning_rate": 3.882915173237754e-06,
|
| 1370 |
+
"loss": 0.1631,
|
| 1371 |
+
"step": 1730
|
| 1372 |
+
},
|
| 1373 |
+
{
|
| 1374 |
+
"epoch": 27.84,
|
| 1375 |
+
"learning_rate": 3.5842293906810035e-06,
|
| 1376 |
+
"loss": 0.178,
|
| 1377 |
+
"step": 1740
|
| 1378 |
+
},
|
| 1379 |
+
{
|
| 1380 |
+
"epoch": 28.0,
|
| 1381 |
+
"learning_rate": 3.2855436081242537e-06,
|
| 1382 |
+
"loss": 0.1922,
|
| 1383 |
+
"step": 1750
|
| 1384 |
+
},
|
| 1385 |
+
{
|
| 1386 |
+
"epoch": 28.0,
|
| 1387 |
+
"eval_accuracy": 0.8692220969560316,
|
| 1388 |
+
"eval_f1": 0.8680166874932149,
|
| 1389 |
+
"eval_loss": 0.6058236956596375,
|
| 1390 |
+
"eval_precision": 0.8684018429035691,
|
| 1391 |
+
"eval_recall": 0.8692220969560316,
|
| 1392 |
+
"eval_runtime": 22.5447,
|
| 1393 |
+
"eval_samples_per_second": 78.688,
|
| 1394 |
+
"eval_steps_per_second": 1.242,
|
| 1395 |
+
"step": 1750
|
| 1396 |
+
},
|
| 1397 |
+
{
|
| 1398 |
+
"epoch": 28.16,
|
| 1399 |
+
"learning_rate": 2.986857825567503e-06,
|
| 1400 |
+
"loss": 0.1773,
|
| 1401 |
+
"step": 1760
|
| 1402 |
+
},
|
| 1403 |
+
{
|
| 1404 |
+
"epoch": 28.32,
|
| 1405 |
+
"learning_rate": 2.688172043010753e-06,
|
| 1406 |
+
"loss": 0.1778,
|
| 1407 |
+
"step": 1770
|
| 1408 |
+
},
|
| 1409 |
+
{
|
| 1410 |
+
"epoch": 28.48,
|
| 1411 |
+
"learning_rate": 2.3894862604540028e-06,
|
| 1412 |
+
"loss": 0.1726,
|
| 1413 |
+
"step": 1780
|
| 1414 |
+
},
|
| 1415 |
+
{
|
| 1416 |
+
"epoch": 28.64,
|
| 1417 |
+
"learning_rate": 2.090800477897252e-06,
|
| 1418 |
+
"loss": 0.1653,
|
| 1419 |
+
"step": 1790
|
| 1420 |
+
},
|
| 1421 |
+
{
|
| 1422 |
+
"epoch": 28.8,
|
| 1423 |
+
"learning_rate": 1.7921146953405017e-06,
|
| 1424 |
+
"loss": 0.1761,
|
| 1425 |
+
"step": 1800
|
| 1426 |
+
},
|
| 1427 |
+
{
|
| 1428 |
+
"epoch": 28.96,
|
| 1429 |
+
"learning_rate": 1.4934289127837516e-06,
|
| 1430 |
+
"loss": 0.1854,
|
| 1431 |
+
"step": 1810
|
| 1432 |
+
},
|
| 1433 |
+
{
|
| 1434 |
+
"epoch": 28.99,
|
| 1435 |
+
"eval_accuracy": 0.8669673055242391,
|
| 1436 |
+
"eval_f1": 0.8654906122723444,
|
| 1437 |
+
"eval_loss": 0.6014190912246704,
|
| 1438 |
+
"eval_precision": 0.8653037200870781,
|
| 1439 |
+
"eval_recall": 0.8669673055242391,
|
| 1440 |
+
"eval_runtime": 22.397,
|
| 1441 |
+
"eval_samples_per_second": 79.207,
|
| 1442 |
+
"eval_steps_per_second": 1.25,
|
| 1443 |
+
"step": 1812
|
| 1444 |
+
},
|
| 1445 |
+
{
|
| 1446 |
+
"epoch": 29.12,
|
| 1447 |
+
"learning_rate": 1.1947431302270014e-06,
|
| 1448 |
+
"loss": 0.1739,
|
| 1449 |
+
"step": 1820
|
| 1450 |
+
},
|
| 1451 |
+
{
|
| 1452 |
+
"epoch": 29.28,
|
| 1453 |
+
"learning_rate": 8.960573476702509e-07,
|
| 1454 |
+
"loss": 0.1633,
|
| 1455 |
+
"step": 1830
|
| 1456 |
+
},
|
| 1457 |
+
{
|
| 1458 |
+
"epoch": 29.44,
|
| 1459 |
+
"learning_rate": 5.973715651135007e-07,
|
| 1460 |
+
"loss": 0.1753,
|
| 1461 |
+
"step": 1840
|
| 1462 |
+
},
|
| 1463 |
+
{
|
| 1464 |
+
"epoch": 29.6,
|
| 1465 |
+
"learning_rate": 2.9868578255675034e-07,
|
| 1466 |
+
"loss": 0.1757,
|
| 1467 |
+
"step": 1850
|
| 1468 |
+
},
|
| 1469 |
+
{
|
| 1470 |
+
"epoch": 29.76,
|
| 1471 |
+
"learning_rate": 0.0,
|
| 1472 |
+
"loss": 0.1688,
|
| 1473 |
+
"step": 1860
|
| 1474 |
+
},
|
| 1475 |
+
{
|
| 1476 |
+
"epoch": 29.76,
|
| 1477 |
+
"eval_accuracy": 0.8737316798196166,
|
| 1478 |
+
"eval_f1": 0.872156389323959,
|
| 1479 |
+
"eval_loss": 0.586895227432251,
|
| 1480 |
+
"eval_precision": 0.8722327180586174,
|
| 1481 |
+
"eval_recall": 0.8737316798196166,
|
| 1482 |
+
"eval_runtime": 22.5331,
|
| 1483 |
+
"eval_samples_per_second": 78.728,
|
| 1484 |
+
"eval_steps_per_second": 1.243,
|
| 1485 |
+
"step": 1860
|
| 1486 |
+
},
|
| 1487 |
+
{
|
| 1488 |
+
"epoch": 29.76,
|
| 1489 |
+
"step": 1860,
|
| 1490 |
+
"total_flos": 1.7058003968011272e+20,
|
| 1491 |
+
"train_loss": 0.40524982412656146,
|
| 1492 |
+
"train_runtime": 15843.7635,
|
| 1493 |
+
"train_samples_per_second": 30.224,
|
| 1494 |
+
"train_steps_per_second": 0.117
|
| 1495 |
+
}
|
| 1496 |
+
],
|
| 1497 |
+
"logging_steps": 10,
|
| 1498 |
+
"max_steps": 1860,
|
| 1499 |
+
"num_input_tokens_seen": 0,
|
| 1500 |
+
"num_train_epochs": 30,
|
| 1501 |
+
"save_steps": 500,
|
| 1502 |
+
"total_flos": 1.7058003968011272e+20,
|
| 1503 |
+
"train_batch_size": 64,
|
| 1504 |
+
"trial_name": null,
|
| 1505 |
+
"trial_params": null
|
| 1506 |
+
}
|