Commit
•
33aff62
1
Parent(s):
dd1f775
End of training
Browse files- README.md +2 -0
- all_results.json +12 -0
- eval_results.json +8 -0
- runs/Dec18_00-59-46_803ce79b5dc6/events.out.tfevents.1702863304.803ce79b5dc6.6686.1 +3 -0
- train_results.json +7 -0
- trainer_state.json +1290 -0
README.md
CHANGED
|
@@ -2,6 +2,8 @@
|
|
| 2 |
license: apache-2.0
|
| 3 |
base_model: google/vit-base-patch16-224-in21k
|
| 4 |
tags:
|
|
|
|
|
|
|
| 5 |
- generated_from_trainer
|
| 6 |
datasets:
|
| 7 |
- imagefolder
|
|
|
|
| 2 |
license: apache-2.0
|
| 3 |
base_model: google/vit-base-patch16-224-in21k
|
| 4 |
tags:
|
| 5 |
+
- image-classification
|
| 6 |
+
- vision
|
| 7 |
- generated_from_trainer
|
| 8 |
datasets:
|
| 9 |
- imagefolder
|
all_results.json
ADDED
|
@@ -0,0 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 100.0,
|
| 3 |
+
"eval_accuracy": 0.8431372549019608,
|
| 4 |
+
"eval_loss": 1.2935162782669067,
|
| 5 |
+
"eval_runtime": 0.797,
|
| 6 |
+
"eval_samples_per_second": 127.985,
|
| 7 |
+
"eval_steps_per_second": 1.255,
|
| 8 |
+
"train_loss": 1.6557193438212077,
|
| 9 |
+
"train_runtime": 2084.5935,
|
| 10 |
+
"train_samples_per_second": 27.535,
|
| 11 |
+
"train_steps_per_second": 0.288
|
| 12 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 100.0,
|
| 3 |
+
"eval_accuracy": 0.8431372549019608,
|
| 4 |
+
"eval_loss": 1.2935162782669067,
|
| 5 |
+
"eval_runtime": 0.797,
|
| 6 |
+
"eval_samples_per_second": 127.985,
|
| 7 |
+
"eval_steps_per_second": 1.255
|
| 8 |
+
}
|
runs/Dec18_00-59-46_803ce79b5dc6/events.out.tfevents.1702863304.803ce79b5dc6.6686.1
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:625d424111fb6f34648589b1b0dcac625019812c5d292419bff9fad3afa27f1f
|
| 3 |
+
size 411
|
train_results.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 100.0,
|
| 3 |
+
"train_loss": 1.6557193438212077,
|
| 4 |
+
"train_runtime": 2084.5935,
|
| 5 |
+
"train_samples_per_second": 27.535,
|
| 6 |
+
"train_steps_per_second": 0.288
|
| 7 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,1290 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 1.2935162782669067,
|
| 3 |
+
"best_model_checkpoint": "./drive/MyDrive/repositories/torch_example_image-classification/outputs2/checkpoint-600",
|
| 4 |
+
"epoch": 100.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 600,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 1.0,
|
| 13 |
+
"eval_accuracy": 0.08823529411764706,
|
| 14 |
+
"eval_loss": 3.2330737113952637,
|
| 15 |
+
"eval_runtime": 0.7234,
|
| 16 |
+
"eval_samples_per_second": 141.008,
|
| 17 |
+
"eval_steps_per_second": 1.382,
|
| 18 |
+
"step": 6
|
| 19 |
+
},
|
| 20 |
+
{
|
| 21 |
+
"epoch": 1.67,
|
| 22 |
+
"learning_rate": 1.9666666666666666e-05,
|
| 23 |
+
"loss": 3.2363,
|
| 24 |
+
"step": 10
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 2.0,
|
| 28 |
+
"eval_accuracy": 0.13725490196078433,
|
| 29 |
+
"eval_loss": 3.202636957168579,
|
| 30 |
+
"eval_runtime": 0.6909,
|
| 31 |
+
"eval_samples_per_second": 147.63,
|
| 32 |
+
"eval_steps_per_second": 1.447,
|
| 33 |
+
"step": 12
|
| 34 |
+
},
|
| 35 |
+
{
|
| 36 |
+
"epoch": 3.0,
|
| 37 |
+
"eval_accuracy": 0.18627450980392157,
|
| 38 |
+
"eval_loss": 3.1764001846313477,
|
| 39 |
+
"eval_runtime": 0.8751,
|
| 40 |
+
"eval_samples_per_second": 116.553,
|
| 41 |
+
"eval_steps_per_second": 1.143,
|
| 42 |
+
"step": 18
|
| 43 |
+
},
|
| 44 |
+
{
|
| 45 |
+
"epoch": 3.33,
|
| 46 |
+
"learning_rate": 1.9333333333333333e-05,
|
| 47 |
+
"loss": 3.1624,
|
| 48 |
+
"step": 20
|
| 49 |
+
},
|
| 50 |
+
{
|
| 51 |
+
"epoch": 4.0,
|
| 52 |
+
"eval_accuracy": 0.22549019607843138,
|
| 53 |
+
"eval_loss": 3.124112844467163,
|
| 54 |
+
"eval_runtime": 1.9559,
|
| 55 |
+
"eval_samples_per_second": 52.149,
|
| 56 |
+
"eval_steps_per_second": 0.511,
|
| 57 |
+
"step": 24
|
| 58 |
+
},
|
| 59 |
+
{
|
| 60 |
+
"epoch": 5.0,
|
| 61 |
+
"learning_rate": 1.9e-05,
|
| 62 |
+
"loss": 3.0924,
|
| 63 |
+
"step": 30
|
| 64 |
+
},
|
| 65 |
+
{
|
| 66 |
+
"epoch": 5.0,
|
| 67 |
+
"eval_accuracy": 0.30392156862745096,
|
| 68 |
+
"eval_loss": 3.0796170234680176,
|
| 69 |
+
"eval_runtime": 0.7875,
|
| 70 |
+
"eval_samples_per_second": 129.524,
|
| 71 |
+
"eval_steps_per_second": 1.27,
|
| 72 |
+
"step": 30
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 6.0,
|
| 76 |
+
"eval_accuracy": 0.3137254901960784,
|
| 77 |
+
"eval_loss": 3.0296630859375,
|
| 78 |
+
"eval_runtime": 0.6746,
|
| 79 |
+
"eval_samples_per_second": 151.208,
|
| 80 |
+
"eval_steps_per_second": 1.482,
|
| 81 |
+
"step": 36
|
| 82 |
+
},
|
| 83 |
+
{
|
| 84 |
+
"epoch": 6.67,
|
| 85 |
+
"learning_rate": 1.866666666666667e-05,
|
| 86 |
+
"loss": 3.0094,
|
| 87 |
+
"step": 40
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 7.0,
|
| 91 |
+
"eval_accuracy": 0.3333333333333333,
|
| 92 |
+
"eval_loss": 2.9901208877563477,
|
| 93 |
+
"eval_runtime": 0.8568,
|
| 94 |
+
"eval_samples_per_second": 119.047,
|
| 95 |
+
"eval_steps_per_second": 1.167,
|
| 96 |
+
"step": 42
|
| 97 |
+
},
|
| 98 |
+
{
|
| 99 |
+
"epoch": 8.0,
|
| 100 |
+
"eval_accuracy": 0.4019607843137255,
|
| 101 |
+
"eval_loss": 2.933021306991577,
|
| 102 |
+
"eval_runtime": 0.865,
|
| 103 |
+
"eval_samples_per_second": 117.919,
|
| 104 |
+
"eval_steps_per_second": 1.156,
|
| 105 |
+
"step": 48
|
| 106 |
+
},
|
| 107 |
+
{
|
| 108 |
+
"epoch": 8.33,
|
| 109 |
+
"learning_rate": 1.8333333333333333e-05,
|
| 110 |
+
"loss": 2.9143,
|
| 111 |
+
"step": 50
|
| 112 |
+
},
|
| 113 |
+
{
|
| 114 |
+
"epoch": 9.0,
|
| 115 |
+
"eval_accuracy": 0.4117647058823529,
|
| 116 |
+
"eval_loss": 2.888922691345215,
|
| 117 |
+
"eval_runtime": 0.9798,
|
| 118 |
+
"eval_samples_per_second": 104.098,
|
| 119 |
+
"eval_steps_per_second": 1.021,
|
| 120 |
+
"step": 54
|
| 121 |
+
},
|
| 122 |
+
{
|
| 123 |
+
"epoch": 10.0,
|
| 124 |
+
"learning_rate": 1.8e-05,
|
| 125 |
+
"loss": 2.8269,
|
| 126 |
+
"step": 60
|
| 127 |
+
},
|
| 128 |
+
{
|
| 129 |
+
"epoch": 10.0,
|
| 130 |
+
"eval_accuracy": 0.4411764705882353,
|
| 131 |
+
"eval_loss": 2.8364291191101074,
|
| 132 |
+
"eval_runtime": 0.6724,
|
| 133 |
+
"eval_samples_per_second": 151.704,
|
| 134 |
+
"eval_steps_per_second": 1.487,
|
| 135 |
+
"step": 60
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 11.0,
|
| 139 |
+
"eval_accuracy": 0.5294117647058824,
|
| 140 |
+
"eval_loss": 2.785728693008423,
|
| 141 |
+
"eval_runtime": 0.8028,
|
| 142 |
+
"eval_samples_per_second": 127.055,
|
| 143 |
+
"eval_steps_per_second": 1.246,
|
| 144 |
+
"step": 66
|
| 145 |
+
},
|
| 146 |
+
{
|
| 147 |
+
"epoch": 11.67,
|
| 148 |
+
"learning_rate": 1.7666666666666668e-05,
|
| 149 |
+
"loss": 2.7201,
|
| 150 |
+
"step": 70
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"epoch": 12.0,
|
| 154 |
+
"eval_accuracy": 0.5196078431372549,
|
| 155 |
+
"eval_loss": 2.7339251041412354,
|
| 156 |
+
"eval_runtime": 0.6836,
|
| 157 |
+
"eval_samples_per_second": 149.204,
|
| 158 |
+
"eval_steps_per_second": 1.463,
|
| 159 |
+
"step": 72
|
| 160 |
+
},
|
| 161 |
+
{
|
| 162 |
+
"epoch": 13.0,
|
| 163 |
+
"eval_accuracy": 0.5588235294117647,
|
| 164 |
+
"eval_loss": 2.68558669090271,
|
| 165 |
+
"eval_runtime": 0.7097,
|
| 166 |
+
"eval_samples_per_second": 143.73,
|
| 167 |
+
"eval_steps_per_second": 1.409,
|
| 168 |
+
"step": 78
|
| 169 |
+
},
|
| 170 |
+
{
|
| 171 |
+
"epoch": 13.33,
|
| 172 |
+
"learning_rate": 1.7333333333333336e-05,
|
| 173 |
+
"loss": 2.6271,
|
| 174 |
+
"step": 80
|
| 175 |
+
},
|
| 176 |
+
{
|
| 177 |
+
"epoch": 14.0,
|
| 178 |
+
"eval_accuracy": 0.5882352941176471,
|
| 179 |
+
"eval_loss": 2.628051519393921,
|
| 180 |
+
"eval_runtime": 0.7248,
|
| 181 |
+
"eval_samples_per_second": 140.727,
|
| 182 |
+
"eval_steps_per_second": 1.38,
|
| 183 |
+
"step": 84
|
| 184 |
+
},
|
| 185 |
+
{
|
| 186 |
+
"epoch": 15.0,
|
| 187 |
+
"learning_rate": 1.7e-05,
|
| 188 |
+
"loss": 2.5333,
|
| 189 |
+
"step": 90
|
| 190 |
+
},
|
| 191 |
+
{
|
| 192 |
+
"epoch": 15.0,
|
| 193 |
+
"eval_accuracy": 0.5882352941176471,
|
| 194 |
+
"eval_loss": 2.576406717300415,
|
| 195 |
+
"eval_runtime": 0.8135,
|
| 196 |
+
"eval_samples_per_second": 125.392,
|
| 197 |
+
"eval_steps_per_second": 1.229,
|
| 198 |
+
"step": 90
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 16.0,
|
| 202 |
+
"eval_accuracy": 0.5980392156862745,
|
| 203 |
+
"eval_loss": 2.527658462524414,
|
| 204 |
+
"eval_runtime": 0.7155,
|
| 205 |
+
"eval_samples_per_second": 142.56,
|
| 206 |
+
"eval_steps_per_second": 1.398,
|
| 207 |
+
"step": 96
|
| 208 |
+
},
|
| 209 |
+
{
|
| 210 |
+
"epoch": 16.67,
|
| 211 |
+
"learning_rate": 1.6666666666666667e-05,
|
| 212 |
+
"loss": 2.4387,
|
| 213 |
+
"step": 100
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 17.0,
|
| 217 |
+
"eval_accuracy": 0.5980392156862745,
|
| 218 |
+
"eval_loss": 2.479215621948242,
|
| 219 |
+
"eval_runtime": 0.83,
|
| 220 |
+
"eval_samples_per_second": 122.895,
|
| 221 |
+
"eval_steps_per_second": 1.205,
|
| 222 |
+
"step": 102
|
| 223 |
+
},
|
| 224 |
+
{
|
| 225 |
+
"epoch": 18.0,
|
| 226 |
+
"eval_accuracy": 0.5980392156862745,
|
| 227 |
+
"eval_loss": 2.441930055618286,
|
| 228 |
+
"eval_runtime": 0.9535,
|
| 229 |
+
"eval_samples_per_second": 106.969,
|
| 230 |
+
"eval_steps_per_second": 1.049,
|
| 231 |
+
"step": 108
|
| 232 |
+
},
|
| 233 |
+
{
|
| 234 |
+
"epoch": 18.33,
|
| 235 |
+
"learning_rate": 1.6333333333333335e-05,
|
| 236 |
+
"loss": 2.3536,
|
| 237 |
+
"step": 110
|
| 238 |
+
},
|
| 239 |
+
{
|
| 240 |
+
"epoch": 19.0,
|
| 241 |
+
"eval_accuracy": 0.6470588235294118,
|
| 242 |
+
"eval_loss": 2.3931069374084473,
|
| 243 |
+
"eval_runtime": 0.8198,
|
| 244 |
+
"eval_samples_per_second": 124.415,
|
| 245 |
+
"eval_steps_per_second": 1.22,
|
| 246 |
+
"step": 114
|
| 247 |
+
},
|
| 248 |
+
{
|
| 249 |
+
"epoch": 20.0,
|
| 250 |
+
"learning_rate": 1.6000000000000003e-05,
|
| 251 |
+
"loss": 2.279,
|
| 252 |
+
"step": 120
|
| 253 |
+
},
|
| 254 |
+
{
|
| 255 |
+
"epoch": 20.0,
|
| 256 |
+
"eval_accuracy": 0.6470588235294118,
|
| 257 |
+
"eval_loss": 2.3502094745635986,
|
| 258 |
+
"eval_runtime": 0.8889,
|
| 259 |
+
"eval_samples_per_second": 114.754,
|
| 260 |
+
"eval_steps_per_second": 1.125,
|
| 261 |
+
"step": 120
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 21.0,
|
| 265 |
+
"eval_accuracy": 0.6666666666666666,
|
| 266 |
+
"eval_loss": 2.3048012256622314,
|
| 267 |
+
"eval_runtime": 0.881,
|
| 268 |
+
"eval_samples_per_second": 115.784,
|
| 269 |
+
"eval_steps_per_second": 1.135,
|
| 270 |
+
"step": 126
|
| 271 |
+
},
|
| 272 |
+
{
|
| 273 |
+
"epoch": 21.67,
|
| 274 |
+
"learning_rate": 1.5666666666666667e-05,
|
| 275 |
+
"loss": 2.2026,
|
| 276 |
+
"step": 130
|
| 277 |
+
},
|
| 278 |
+
{
|
| 279 |
+
"epoch": 22.0,
|
| 280 |
+
"eval_accuracy": 0.6568627450980392,
|
| 281 |
+
"eval_loss": 2.272130250930786,
|
| 282 |
+
"eval_runtime": 0.8015,
|
| 283 |
+
"eval_samples_per_second": 127.258,
|
| 284 |
+
"eval_steps_per_second": 1.248,
|
| 285 |
+
"step": 132
|
| 286 |
+
},
|
| 287 |
+
{
|
| 288 |
+
"epoch": 23.0,
|
| 289 |
+
"eval_accuracy": 0.6764705882352942,
|
| 290 |
+
"eval_loss": 2.242011308670044,
|
| 291 |
+
"eval_runtime": 1.0538,
|
| 292 |
+
"eval_samples_per_second": 96.792,
|
| 293 |
+
"eval_steps_per_second": 0.949,
|
| 294 |
+
"step": 138
|
| 295 |
+
},
|
| 296 |
+
{
|
| 297 |
+
"epoch": 23.33,
|
| 298 |
+
"learning_rate": 1.5333333333333334e-05,
|
| 299 |
+
"loss": 2.1233,
|
| 300 |
+
"step": 140
|
| 301 |
+
},
|
| 302 |
+
{
|
| 303 |
+
"epoch": 24.0,
|
| 304 |
+
"eval_accuracy": 0.6470588235294118,
|
| 305 |
+
"eval_loss": 2.20729923248291,
|
| 306 |
+
"eval_runtime": 1.6437,
|
| 307 |
+
"eval_samples_per_second": 62.057,
|
| 308 |
+
"eval_steps_per_second": 0.608,
|
| 309 |
+
"step": 144
|
| 310 |
+
},
|
| 311 |
+
{
|
| 312 |
+
"epoch": 25.0,
|
| 313 |
+
"learning_rate": 1.5000000000000002e-05,
|
| 314 |
+
"loss": 2.0591,
|
| 315 |
+
"step": 150
|
| 316 |
+
},
|
| 317 |
+
{
|
| 318 |
+
"epoch": 25.0,
|
| 319 |
+
"eval_accuracy": 0.696078431372549,
|
| 320 |
+
"eval_loss": 2.1703522205352783,
|
| 321 |
+
"eval_runtime": 1.0255,
|
| 322 |
+
"eval_samples_per_second": 99.464,
|
| 323 |
+
"eval_steps_per_second": 0.975,
|
| 324 |
+
"step": 150
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 26.0,
|
| 328 |
+
"eval_accuracy": 0.7156862745098039,
|
| 329 |
+
"eval_loss": 2.132262706756592,
|
| 330 |
+
"eval_runtime": 0.8947,
|
| 331 |
+
"eval_samples_per_second": 114.002,
|
| 332 |
+
"eval_steps_per_second": 1.118,
|
| 333 |
+
"step": 156
|
| 334 |
+
},
|
| 335 |
+
{
|
| 336 |
+
"epoch": 26.67,
|
| 337 |
+
"learning_rate": 1.4666666666666666e-05,
|
| 338 |
+
"loss": 1.9858,
|
| 339 |
+
"step": 160
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 27.0,
|
| 343 |
+
"eval_accuracy": 0.6862745098039216,
|
| 344 |
+
"eval_loss": 2.101270914077759,
|
| 345 |
+
"eval_runtime": 1.1014,
|
| 346 |
+
"eval_samples_per_second": 92.612,
|
| 347 |
+
"eval_steps_per_second": 0.908,
|
| 348 |
+
"step": 162
|
| 349 |
+
},
|
| 350 |
+
{
|
| 351 |
+
"epoch": 28.0,
|
| 352 |
+
"eval_accuracy": 0.7156862745098039,
|
| 353 |
+
"eval_loss": 2.0665531158447266,
|
| 354 |
+
"eval_runtime": 0.7467,
|
| 355 |
+
"eval_samples_per_second": 136.598,
|
| 356 |
+
"eval_steps_per_second": 1.339,
|
| 357 |
+
"step": 168
|
| 358 |
+
},
|
| 359 |
+
{
|
| 360 |
+
"epoch": 28.33,
|
| 361 |
+
"learning_rate": 1.4333333333333334e-05,
|
| 362 |
+
"loss": 1.9518,
|
| 363 |
+
"step": 170
|
| 364 |
+
},
|
| 365 |
+
{
|
| 366 |
+
"epoch": 29.0,
|
| 367 |
+
"eval_accuracy": 0.7352941176470589,
|
| 368 |
+
"eval_loss": 2.0423755645751953,
|
| 369 |
+
"eval_runtime": 0.8412,
|
| 370 |
+
"eval_samples_per_second": 121.25,
|
| 371 |
+
"eval_steps_per_second": 1.189,
|
| 372 |
+
"step": 174
|
| 373 |
+
},
|
| 374 |
+
{
|
| 375 |
+
"epoch": 30.0,
|
| 376 |
+
"learning_rate": 1.4e-05,
|
| 377 |
+
"loss": 1.8789,
|
| 378 |
+
"step": 180
|
| 379 |
+
},
|
| 380 |
+
{
|
| 381 |
+
"epoch": 30.0,
|
| 382 |
+
"eval_accuracy": 0.7352941176470589,
|
| 383 |
+
"eval_loss": 2.0062215328216553,
|
| 384 |
+
"eval_runtime": 0.7426,
|
| 385 |
+
"eval_samples_per_second": 137.363,
|
| 386 |
+
"eval_steps_per_second": 1.347,
|
| 387 |
+
"step": 180
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 31.0,
|
| 391 |
+
"eval_accuracy": 0.7352941176470589,
|
| 392 |
+
"eval_loss": 1.9826091527938843,
|
| 393 |
+
"eval_runtime": 1.5779,
|
| 394 |
+
"eval_samples_per_second": 64.643,
|
| 395 |
+
"eval_steps_per_second": 0.634,
|
| 396 |
+
"step": 186
|
| 397 |
+
},
|
| 398 |
+
{
|
| 399 |
+
"epoch": 31.67,
|
| 400 |
+
"learning_rate": 1.3666666666666667e-05,
|
| 401 |
+
"loss": 1.8307,
|
| 402 |
+
"step": 190
|
| 403 |
+
},
|
| 404 |
+
{
|
| 405 |
+
"epoch": 32.0,
|
| 406 |
+
"eval_accuracy": 0.7647058823529411,
|
| 407 |
+
"eval_loss": 1.9618277549743652,
|
| 408 |
+
"eval_runtime": 0.848,
|
| 409 |
+
"eval_samples_per_second": 120.283,
|
| 410 |
+
"eval_steps_per_second": 1.179,
|
| 411 |
+
"step": 192
|
| 412 |
+
},
|
| 413 |
+
{
|
| 414 |
+
"epoch": 33.0,
|
| 415 |
+
"eval_accuracy": 0.7647058823529411,
|
| 416 |
+
"eval_loss": 1.9387190341949463,
|
| 417 |
+
"eval_runtime": 0.8972,
|
| 418 |
+
"eval_samples_per_second": 113.683,
|
| 419 |
+
"eval_steps_per_second": 1.115,
|
| 420 |
+
"step": 198
|
| 421 |
+
},
|
| 422 |
+
{
|
| 423 |
+
"epoch": 33.33,
|
| 424 |
+
"learning_rate": 1.3333333333333333e-05,
|
| 425 |
+
"loss": 1.7762,
|
| 426 |
+
"step": 200
|
| 427 |
+
},
|
| 428 |
+
{
|
| 429 |
+
"epoch": 34.0,
|
| 430 |
+
"eval_accuracy": 0.7549019607843137,
|
| 431 |
+
"eval_loss": 1.9141510725021362,
|
| 432 |
+
"eval_runtime": 0.7852,
|
| 433 |
+
"eval_samples_per_second": 129.898,
|
| 434 |
+
"eval_steps_per_second": 1.274,
|
| 435 |
+
"step": 204
|
| 436 |
+
},
|
| 437 |
+
{
|
| 438 |
+
"epoch": 35.0,
|
| 439 |
+
"learning_rate": 1.3000000000000001e-05,
|
| 440 |
+
"loss": 1.7383,
|
| 441 |
+
"step": 210
|
| 442 |
+
},
|
| 443 |
+
{
|
| 444 |
+
"epoch": 35.0,
|
| 445 |
+
"eval_accuracy": 0.7647058823529411,
|
| 446 |
+
"eval_loss": 1.8922001123428345,
|
| 447 |
+
"eval_runtime": 0.6999,
|
| 448 |
+
"eval_samples_per_second": 145.726,
|
| 449 |
+
"eval_steps_per_second": 1.429,
|
| 450 |
+
"step": 210
|
| 451 |
+
},
|
| 452 |
+
{
|
| 453 |
+
"epoch": 36.0,
|
| 454 |
+
"eval_accuracy": 0.7745098039215687,
|
| 455 |
+
"eval_loss": 1.864749550819397,
|
| 456 |
+
"eval_runtime": 0.68,
|
| 457 |
+
"eval_samples_per_second": 149.999,
|
| 458 |
+
"eval_steps_per_second": 1.471,
|
| 459 |
+
"step": 216
|
| 460 |
+
},
|
| 461 |
+
{
|
| 462 |
+
"epoch": 36.67,
|
| 463 |
+
"learning_rate": 1.2666666666666667e-05,
|
| 464 |
+
"loss": 1.683,
|
| 465 |
+
"step": 220
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 37.0,
|
| 469 |
+
"eval_accuracy": 0.7745098039215687,
|
| 470 |
+
"eval_loss": 1.8461244106292725,
|
| 471 |
+
"eval_runtime": 0.8708,
|
| 472 |
+
"eval_samples_per_second": 117.132,
|
| 473 |
+
"eval_steps_per_second": 1.148,
|
| 474 |
+
"step": 222
|
| 475 |
+
},
|
| 476 |
+
{
|
| 477 |
+
"epoch": 38.0,
|
| 478 |
+
"eval_accuracy": 0.7549019607843137,
|
| 479 |
+
"eval_loss": 1.8185441493988037,
|
| 480 |
+
"eval_runtime": 0.7505,
|
| 481 |
+
"eval_samples_per_second": 135.905,
|
| 482 |
+
"eval_steps_per_second": 1.332,
|
| 483 |
+
"step": 228
|
| 484 |
+
},
|
| 485 |
+
{
|
| 486 |
+
"epoch": 38.33,
|
| 487 |
+
"learning_rate": 1.2333333333333334e-05,
|
| 488 |
+
"loss": 1.6527,
|
| 489 |
+
"step": 230
|
| 490 |
+
},
|
| 491 |
+
{
|
| 492 |
+
"epoch": 39.0,
|
| 493 |
+
"eval_accuracy": 0.7843137254901961,
|
| 494 |
+
"eval_loss": 1.801927924156189,
|
| 495 |
+
"eval_runtime": 1.141,
|
| 496 |
+
"eval_samples_per_second": 89.397,
|
| 497 |
+
"eval_steps_per_second": 0.876,
|
| 498 |
+
"step": 234
|
| 499 |
+
},
|
| 500 |
+
{
|
| 501 |
+
"epoch": 40.0,
|
| 502 |
+
"learning_rate": 1.2e-05,
|
| 503 |
+
"loss": 1.615,
|
| 504 |
+
"step": 240
|
| 505 |
+
},
|
| 506 |
+
{
|
| 507 |
+
"epoch": 40.0,
|
| 508 |
+
"eval_accuracy": 0.7941176470588235,
|
| 509 |
+
"eval_loss": 1.7803996801376343,
|
| 510 |
+
"eval_runtime": 0.8026,
|
| 511 |
+
"eval_samples_per_second": 127.081,
|
| 512 |
+
"eval_steps_per_second": 1.246,
|
| 513 |
+
"step": 240
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 41.0,
|
| 517 |
+
"eval_accuracy": 0.7843137254901961,
|
| 518 |
+
"eval_loss": 1.7603331804275513,
|
| 519 |
+
"eval_runtime": 0.7405,
|
| 520 |
+
"eval_samples_per_second": 137.746,
|
| 521 |
+
"eval_steps_per_second": 1.35,
|
| 522 |
+
"step": 246
|
| 523 |
+
},
|
| 524 |
+
{
|
| 525 |
+
"epoch": 41.67,
|
| 526 |
+
"learning_rate": 1.1666666666666668e-05,
|
| 527 |
+
"loss": 1.5736,
|
| 528 |
+
"step": 250
|
| 529 |
+
},
|
| 530 |
+
{
|
| 531 |
+
"epoch": 42.0,
|
| 532 |
+
"eval_accuracy": 0.8137254901960784,
|
| 533 |
+
"eval_loss": 1.740982174873352,
|
| 534 |
+
"eval_runtime": 0.6886,
|
| 535 |
+
"eval_samples_per_second": 148.121,
|
| 536 |
+
"eval_steps_per_second": 1.452,
|
| 537 |
+
"step": 252
|
| 538 |
+
},
|
| 539 |
+
{
|
| 540 |
+
"epoch": 43.0,
|
| 541 |
+
"eval_accuracy": 0.7941176470588235,
|
| 542 |
+
"eval_loss": 1.7274985313415527,
|
| 543 |
+
"eval_runtime": 0.6877,
|
| 544 |
+
"eval_samples_per_second": 148.329,
|
| 545 |
+
"eval_steps_per_second": 1.454,
|
| 546 |
+
"step": 258
|
| 547 |
+
},
|
| 548 |
+
{
|
| 549 |
+
"epoch": 43.33,
|
| 550 |
+
"learning_rate": 1.1333333333333334e-05,
|
| 551 |
+
"loss": 1.5316,
|
| 552 |
+
"step": 260
|
| 553 |
+
},
|
| 554 |
+
{
|
| 555 |
+
"epoch": 44.0,
|
| 556 |
+
"eval_accuracy": 0.8235294117647058,
|
| 557 |
+
"eval_loss": 1.7081972360610962,
|
| 558 |
+
"eval_runtime": 0.7845,
|
| 559 |
+
"eval_samples_per_second": 130.014,
|
| 560 |
+
"eval_steps_per_second": 1.275,
|
| 561 |
+
"step": 264
|
| 562 |
+
},
|
| 563 |
+
{
|
| 564 |
+
"epoch": 45.0,
|
| 565 |
+
"learning_rate": 1.1000000000000001e-05,
|
| 566 |
+
"loss": 1.503,
|
| 567 |
+
"step": 270
|
| 568 |
+
},
|
| 569 |
+
{
|
| 570 |
+
"epoch": 45.0,
|
| 571 |
+
"eval_accuracy": 0.8137254901960784,
|
| 572 |
+
"eval_loss": 1.6913036108016968,
|
| 573 |
+
"eval_runtime": 0.8968,
|
| 574 |
+
"eval_samples_per_second": 113.735,
|
| 575 |
+
"eval_steps_per_second": 1.115,
|
| 576 |
+
"step": 270
|
| 577 |
+
},
|
| 578 |
+
{
|
| 579 |
+
"epoch": 46.0,
|
| 580 |
+
"eval_accuracy": 0.803921568627451,
|
| 581 |
+
"eval_loss": 1.680880069732666,
|
| 582 |
+
"eval_runtime": 0.776,
|
| 583 |
+
"eval_samples_per_second": 131.44,
|
| 584 |
+
"eval_steps_per_second": 1.289,
|
| 585 |
+
"step": 276
|
| 586 |
+
},
|
| 587 |
+
{
|
| 588 |
+
"epoch": 46.67,
|
| 589 |
+
"learning_rate": 1.0666666666666667e-05,
|
| 590 |
+
"loss": 1.4905,
|
| 591 |
+
"step": 280
|
| 592 |
+
},
|
| 593 |
+
{
|
| 594 |
+
"epoch": 47.0,
|
| 595 |
+
"eval_accuracy": 0.803921568627451,
|
| 596 |
+
"eval_loss": 1.6573076248168945,
|
| 597 |
+
"eval_runtime": 0.6724,
|
| 598 |
+
"eval_samples_per_second": 151.693,
|
| 599 |
+
"eval_steps_per_second": 1.487,
|
| 600 |
+
"step": 282
|
| 601 |
+
},
|
| 602 |
+
{
|
| 603 |
+
"epoch": 48.0,
|
| 604 |
+
"eval_accuracy": 0.8235294117647058,
|
| 605 |
+
"eval_loss": 1.6394025087356567,
|
| 606 |
+
"eval_runtime": 0.69,
|
| 607 |
+
"eval_samples_per_second": 147.83,
|
| 608 |
+
"eval_steps_per_second": 1.449,
|
| 609 |
+
"step": 288
|
| 610 |
+
},
|
| 611 |
+
{
|
| 612 |
+
"epoch": 48.33,
|
| 613 |
+
"learning_rate": 1.0333333333333335e-05,
|
| 614 |
+
"loss": 1.4262,
|
| 615 |
+
"step": 290
|
| 616 |
+
},
|
| 617 |
+
{
|
| 618 |
+
"epoch": 49.0,
|
| 619 |
+
"eval_accuracy": 0.8137254901960784,
|
| 620 |
+
"eval_loss": 1.6250027418136597,
|
| 621 |
+
"eval_runtime": 0.7655,
|
| 622 |
+
"eval_samples_per_second": 133.247,
|
| 623 |
+
"eval_steps_per_second": 1.306,
|
| 624 |
+
"step": 294
|
| 625 |
+
},
|
| 626 |
+
{
|
| 627 |
+
"epoch": 50.0,
|
| 628 |
+
"learning_rate": 1e-05,
|
| 629 |
+
"loss": 1.426,
|
| 630 |
+
"step": 300
|
| 631 |
+
},
|
| 632 |
+
{
|
| 633 |
+
"epoch": 50.0,
|
| 634 |
+
"eval_accuracy": 0.8333333333333334,
|
| 635 |
+
"eval_loss": 1.6149309873580933,
|
| 636 |
+
"eval_runtime": 0.7535,
|
| 637 |
+
"eval_samples_per_second": 135.375,
|
| 638 |
+
"eval_steps_per_second": 1.327,
|
| 639 |
+
"step": 300
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 51.0,
|
| 643 |
+
"eval_accuracy": 0.8333333333333334,
|
| 644 |
+
"eval_loss": 1.6013031005859375,
|
| 645 |
+
"eval_runtime": 0.7915,
|
| 646 |
+
"eval_samples_per_second": 128.866,
|
| 647 |
+
"eval_steps_per_second": 1.263,
|
| 648 |
+
"step": 306
|
| 649 |
+
},
|
| 650 |
+
{
|
| 651 |
+
"epoch": 51.67,
|
| 652 |
+
"learning_rate": 9.666666666666667e-06,
|
| 653 |
+
"loss": 1.3915,
|
| 654 |
+
"step": 310
|
| 655 |
+
},
|
| 656 |
+
{
|
| 657 |
+
"epoch": 52.0,
|
| 658 |
+
"eval_accuracy": 0.8235294117647058,
|
| 659 |
+
"eval_loss": 1.5923330783843994,
|
| 660 |
+
"eval_runtime": 0.7278,
|
| 661 |
+
"eval_samples_per_second": 140.152,
|
| 662 |
+
"eval_steps_per_second": 1.374,
|
| 663 |
+
"step": 312
|
| 664 |
+
},
|
| 665 |
+
{
|
| 666 |
+
"epoch": 53.0,
|
| 667 |
+
"eval_accuracy": 0.8333333333333334,
|
| 668 |
+
"eval_loss": 1.5717215538024902,
|
| 669 |
+
"eval_runtime": 0.6608,
|
| 670 |
+
"eval_samples_per_second": 154.364,
|
| 671 |
+
"eval_steps_per_second": 1.513,
|
| 672 |
+
"step": 318
|
| 673 |
+
},
|
| 674 |
+
{
|
| 675 |
+
"epoch": 53.33,
|
| 676 |
+
"learning_rate": 9.333333333333334e-06,
|
| 677 |
+
"loss": 1.3406,
|
| 678 |
+
"step": 320
|
| 679 |
+
},
|
| 680 |
+
{
|
| 681 |
+
"epoch": 54.0,
|
| 682 |
+
"eval_accuracy": 0.8235294117647058,
|
| 683 |
+
"eval_loss": 1.5661754608154297,
|
| 684 |
+
"eval_runtime": 0.8648,
|
| 685 |
+
"eval_samples_per_second": 117.94,
|
| 686 |
+
"eval_steps_per_second": 1.156,
|
| 687 |
+
"step": 324
|
| 688 |
+
},
|
| 689 |
+
{
|
| 690 |
+
"epoch": 55.0,
|
| 691 |
+
"learning_rate": 9e-06,
|
| 692 |
+
"loss": 1.3444,
|
| 693 |
+
"step": 330
|
| 694 |
+
},
|
| 695 |
+
{
|
| 696 |
+
"epoch": 55.0,
|
| 697 |
+
"eval_accuracy": 0.8235294117647058,
|
| 698 |
+
"eval_loss": 1.5482959747314453,
|
| 699 |
+
"eval_runtime": 0.7933,
|
| 700 |
+
"eval_samples_per_second": 128.58,
|
| 701 |
+
"eval_steps_per_second": 1.261,
|
| 702 |
+
"step": 330
|
| 703 |
+
},
|
| 704 |
+
{
|
| 705 |
+
"epoch": 56.0,
|
| 706 |
+
"eval_accuracy": 0.8235294117647058,
|
| 707 |
+
"eval_loss": 1.5372467041015625,
|
| 708 |
+
"eval_runtime": 0.729,
|
| 709 |
+
"eval_samples_per_second": 139.912,
|
| 710 |
+
"eval_steps_per_second": 1.372,
|
| 711 |
+
"step": 336
|
| 712 |
+
},
|
| 713 |
+
{
|
| 714 |
+
"epoch": 56.67,
|
| 715 |
+
"learning_rate": 8.666666666666668e-06,
|
| 716 |
+
"loss": 1.3053,
|
| 717 |
+
"step": 340
|
| 718 |
+
},
|
| 719 |
+
{
|
| 720 |
+
"epoch": 57.0,
|
| 721 |
+
"eval_accuracy": 0.8137254901960784,
|
| 722 |
+
"eval_loss": 1.522821068763733,
|
| 723 |
+
"eval_runtime": 0.67,
|
| 724 |
+
"eval_samples_per_second": 152.241,
|
| 725 |
+
"eval_steps_per_second": 1.493,
|
| 726 |
+
"step": 342
|
| 727 |
+
},
|
| 728 |
+
{
|
| 729 |
+
"epoch": 58.0,
|
| 730 |
+
"eval_accuracy": 0.8235294117647058,
|
| 731 |
+
"eval_loss": 1.513081431388855,
|
| 732 |
+
"eval_runtime": 0.8482,
|
| 733 |
+
"eval_samples_per_second": 120.26,
|
| 734 |
+
"eval_steps_per_second": 1.179,
|
| 735 |
+
"step": 348
|
| 736 |
+
},
|
| 737 |
+
{
|
| 738 |
+
"epoch": 58.33,
|
| 739 |
+
"learning_rate": 8.333333333333334e-06,
|
| 740 |
+
"loss": 1.3147,
|
| 741 |
+
"step": 350
|
| 742 |
+
},
|
| 743 |
+
{
|
| 744 |
+
"epoch": 59.0,
|
| 745 |
+
"eval_accuracy": 0.8431372549019608,
|
| 746 |
+
"eval_loss": 1.4987856149673462,
|
| 747 |
+
"eval_runtime": 0.6717,
|
| 748 |
+
"eval_samples_per_second": 151.851,
|
| 749 |
+
"eval_steps_per_second": 1.489,
|
| 750 |
+
"step": 354
|
| 751 |
+
},
|
| 752 |
+
{
|
| 753 |
+
"epoch": 60.0,
|
| 754 |
+
"learning_rate": 8.000000000000001e-06,
|
| 755 |
+
"loss": 1.2796,
|
| 756 |
+
"step": 360
|
| 757 |
+
},
|
| 758 |
+
{
|
| 759 |
+
"epoch": 60.0,
|
| 760 |
+
"eval_accuracy": 0.8333333333333334,
|
| 761 |
+
"eval_loss": 1.4865219593048096,
|
| 762 |
+
"eval_runtime": 0.7339,
|
| 763 |
+
"eval_samples_per_second": 138.992,
|
| 764 |
+
"eval_steps_per_second": 1.363,
|
| 765 |
+
"step": 360
|
| 766 |
+
},
|
| 767 |
+
{
|
| 768 |
+
"epoch": 61.0,
|
| 769 |
+
"eval_accuracy": 0.8333333333333334,
|
| 770 |
+
"eval_loss": 1.4788631200790405,
|
| 771 |
+
"eval_runtime": 0.7971,
|
| 772 |
+
"eval_samples_per_second": 127.964,
|
| 773 |
+
"eval_steps_per_second": 1.255,
|
| 774 |
+
"step": 366
|
| 775 |
+
},
|
| 776 |
+
{
|
| 777 |
+
"epoch": 61.67,
|
| 778 |
+
"learning_rate": 7.666666666666667e-06,
|
| 779 |
+
"loss": 1.2419,
|
| 780 |
+
"step": 370
|
| 781 |
+
},
|
| 782 |
+
{
|
| 783 |
+
"epoch": 62.0,
|
| 784 |
+
"eval_accuracy": 0.8137254901960784,
|
| 785 |
+
"eval_loss": 1.4684420824050903,
|
| 786 |
+
"eval_runtime": 0.6989,
|
| 787 |
+
"eval_samples_per_second": 145.949,
|
| 788 |
+
"eval_steps_per_second": 1.431,
|
| 789 |
+
"step": 372
|
| 790 |
+
},
|
| 791 |
+
{
|
| 792 |
+
"epoch": 63.0,
|
| 793 |
+
"eval_accuracy": 0.8333333333333334,
|
| 794 |
+
"eval_loss": 1.459528923034668,
|
| 795 |
+
"eval_runtime": 0.6797,
|
| 796 |
+
"eval_samples_per_second": 150.063,
|
| 797 |
+
"eval_steps_per_second": 1.471,
|
| 798 |
+
"step": 378
|
| 799 |
+
},
|
| 800 |
+
{
|
| 801 |
+
"epoch": 63.33,
|
| 802 |
+
"learning_rate": 7.333333333333333e-06,
|
| 803 |
+
"loss": 1.2326,
|
| 804 |
+
"step": 380
|
| 805 |
+
},
|
| 806 |
+
{
|
| 807 |
+
"epoch": 64.0,
|
| 808 |
+
"eval_accuracy": 0.8431372549019608,
|
| 809 |
+
"eval_loss": 1.447430968284607,
|
| 810 |
+
"eval_runtime": 0.6753,
|
| 811 |
+
"eval_samples_per_second": 151.054,
|
| 812 |
+
"eval_steps_per_second": 1.481,
|
| 813 |
+
"step": 384
|
| 814 |
+
},
|
| 815 |
+
{
|
| 816 |
+
"epoch": 65.0,
|
| 817 |
+
"learning_rate": 7e-06,
|
| 818 |
+
"loss": 1.2246,
|
| 819 |
+
"step": 390
|
| 820 |
+
},
|
| 821 |
+
{
|
| 822 |
+
"epoch": 65.0,
|
| 823 |
+
"eval_accuracy": 0.8431372549019608,
|
| 824 |
+
"eval_loss": 1.4404107332229614,
|
| 825 |
+
"eval_runtime": 0.6713,
|
| 826 |
+
"eval_samples_per_second": 151.935,
|
| 827 |
+
"eval_steps_per_second": 1.49,
|
| 828 |
+
"step": 390
|
| 829 |
+
},
|
| 830 |
+
{
|
| 831 |
+
"epoch": 66.0,
|
| 832 |
+
"eval_accuracy": 0.8333333333333334,
|
| 833 |
+
"eval_loss": 1.4313303232192993,
|
| 834 |
+
"eval_runtime": 0.6779,
|
| 835 |
+
"eval_samples_per_second": 150.471,
|
| 836 |
+
"eval_steps_per_second": 1.475,
|
| 837 |
+
"step": 396
|
| 838 |
+
},
|
| 839 |
+
{
|
| 840 |
+
"epoch": 66.67,
|
| 841 |
+
"learning_rate": 6.666666666666667e-06,
|
| 842 |
+
"loss": 1.1975,
|
| 843 |
+
"step": 400
|
| 844 |
+
},
|
| 845 |
+
{
|
| 846 |
+
"epoch": 67.0,
|
| 847 |
+
"eval_accuracy": 0.8431372549019608,
|
| 848 |
+
"eval_loss": 1.4185569286346436,
|
| 849 |
+
"eval_runtime": 0.8632,
|
| 850 |
+
"eval_samples_per_second": 118.16,
|
| 851 |
+
"eval_steps_per_second": 1.158,
|
| 852 |
+
"step": 402
|
| 853 |
+
},
|
| 854 |
+
{
|
| 855 |
+
"epoch": 68.0,
|
| 856 |
+
"eval_accuracy": 0.8529411764705882,
|
| 857 |
+
"eval_loss": 1.4122827053070068,
|
| 858 |
+
"eval_runtime": 0.6792,
|
| 859 |
+
"eval_samples_per_second": 150.175,
|
| 860 |
+
"eval_steps_per_second": 1.472,
|
| 861 |
+
"step": 408
|
| 862 |
+
},
|
| 863 |
+
{
|
| 864 |
+
"epoch": 68.33,
|
| 865 |
+
"learning_rate": 6.333333333333333e-06,
|
| 866 |
+
"loss": 1.1804,
|
| 867 |
+
"step": 410
|
| 868 |
+
},
|
| 869 |
+
{
|
| 870 |
+
"epoch": 69.0,
|
| 871 |
+
"eval_accuracy": 0.8431372549019608,
|
| 872 |
+
"eval_loss": 1.4083011150360107,
|
| 873 |
+
"eval_runtime": 0.9425,
|
| 874 |
+
"eval_samples_per_second": 108.219,
|
| 875 |
+
"eval_steps_per_second": 1.061,
|
| 876 |
+
"step": 414
|
| 877 |
+
},
|
| 878 |
+
{
|
| 879 |
+
"epoch": 70.0,
|
| 880 |
+
"learning_rate": 6e-06,
|
| 881 |
+
"loss": 1.1686,
|
| 882 |
+
"step": 420
|
| 883 |
+
},
|
| 884 |
+
{
|
| 885 |
+
"epoch": 70.0,
|
| 886 |
+
"eval_accuracy": 0.8431372549019608,
|
| 887 |
+
"eval_loss": 1.4023797512054443,
|
| 888 |
+
"eval_runtime": 0.6859,
|
| 889 |
+
"eval_samples_per_second": 148.71,
|
| 890 |
+
"eval_steps_per_second": 1.458,
|
| 891 |
+
"step": 420
|
| 892 |
+
},
|
| 893 |
+
{
|
| 894 |
+
"epoch": 71.0,
|
| 895 |
+
"eval_accuracy": 0.8529411764705882,
|
| 896 |
+
"eval_loss": 1.395778775215149,
|
| 897 |
+
"eval_runtime": 0.7142,
|
| 898 |
+
"eval_samples_per_second": 142.812,
|
| 899 |
+
"eval_steps_per_second": 1.4,
|
| 900 |
+
"step": 426
|
| 901 |
+
},
|
| 902 |
+
{
|
| 903 |
+
"epoch": 71.67,
|
| 904 |
+
"learning_rate": 5.666666666666667e-06,
|
| 905 |
+
"loss": 1.1608,
|
| 906 |
+
"step": 430
|
| 907 |
+
},
|
| 908 |
+
{
|
| 909 |
+
"epoch": 72.0,
|
| 910 |
+
"eval_accuracy": 0.8431372549019608,
|
| 911 |
+
"eval_loss": 1.384925365447998,
|
| 912 |
+
"eval_runtime": 0.792,
|
| 913 |
+
"eval_samples_per_second": 128.785,
|
| 914 |
+
"eval_steps_per_second": 1.263,
|
| 915 |
+
"step": 432
|
| 916 |
+
},
|
| 917 |
+
{
|
| 918 |
+
"epoch": 73.0,
|
| 919 |
+
"eval_accuracy": 0.8431372549019608,
|
| 920 |
+
"eval_loss": 1.3785865306854248,
|
| 921 |
+
"eval_runtime": 0.7537,
|
| 922 |
+
"eval_samples_per_second": 135.336,
|
| 923 |
+
"eval_steps_per_second": 1.327,
|
| 924 |
+
"step": 438
|
| 925 |
+
},
|
| 926 |
+
{
|
| 927 |
+
"epoch": 73.33,
|
| 928 |
+
"learning_rate": 5.333333333333334e-06,
|
| 929 |
+
"loss": 1.1491,
|
| 930 |
+
"step": 440
|
| 931 |
+
},
|
| 932 |
+
{
|
| 933 |
+
"epoch": 74.0,
|
| 934 |
+
"eval_accuracy": 0.8431372549019608,
|
| 935 |
+
"eval_loss": 1.3704206943511963,
|
| 936 |
+
"eval_runtime": 0.756,
|
| 937 |
+
"eval_samples_per_second": 134.922,
|
| 938 |
+
"eval_steps_per_second": 1.323,
|
| 939 |
+
"step": 444
|
| 940 |
+
},
|
| 941 |
+
{
|
| 942 |
+
"epoch": 75.0,
|
| 943 |
+
"learning_rate": 5e-06,
|
| 944 |
+
"loss": 1.1283,
|
| 945 |
+
"step": 450
|
| 946 |
+
},
|
| 947 |
+
{
|
| 948 |
+
"epoch": 75.0,
|
| 949 |
+
"eval_accuracy": 0.8431372549019608,
|
| 950 |
+
"eval_loss": 1.3653908967971802,
|
| 951 |
+
"eval_runtime": 0.7484,
|
| 952 |
+
"eval_samples_per_second": 136.284,
|
| 953 |
+
"eval_steps_per_second": 1.336,
|
| 954 |
+
"step": 450
|
| 955 |
+
},
|
| 956 |
+
{
|
| 957 |
+
"epoch": 76.0,
|
| 958 |
+
"eval_accuracy": 0.8529411764705882,
|
| 959 |
+
"eval_loss": 1.3577083349227905,
|
| 960 |
+
"eval_runtime": 0.7726,
|
| 961 |
+
"eval_samples_per_second": 132.025,
|
| 962 |
+
"eval_steps_per_second": 1.294,
|
| 963 |
+
"step": 456
|
| 964 |
+
},
|
| 965 |
+
{
|
| 966 |
+
"epoch": 76.67,
|
| 967 |
+
"learning_rate": 4.666666666666667e-06,
|
| 968 |
+
"loss": 1.1113,
|
| 969 |
+
"step": 460
|
| 970 |
+
},
|
| 971 |
+
{
|
| 972 |
+
"epoch": 77.0,
|
| 973 |
+
"eval_accuracy": 0.8529411764705882,
|
| 974 |
+
"eval_loss": 1.351647973060608,
|
| 975 |
+
"eval_runtime": 0.7308,
|
| 976 |
+
"eval_samples_per_second": 139.58,
|
| 977 |
+
"eval_steps_per_second": 1.368,
|
| 978 |
+
"step": 462
|
| 979 |
+
},
|
| 980 |
+
{
|
| 981 |
+
"epoch": 78.0,
|
| 982 |
+
"eval_accuracy": 0.8529411764705882,
|
| 983 |
+
"eval_loss": 1.3462965488433838,
|
| 984 |
+
"eval_runtime": 0.8148,
|
| 985 |
+
"eval_samples_per_second": 125.184,
|
| 986 |
+
"eval_steps_per_second": 1.227,
|
| 987 |
+
"step": 468
|
| 988 |
+
},
|
| 989 |
+
{
|
| 990 |
+
"epoch": 78.33,
|
| 991 |
+
"learning_rate": 4.333333333333334e-06,
|
| 992 |
+
"loss": 1.1047,
|
| 993 |
+
"step": 470
|
| 994 |
+
},
|
| 995 |
+
{
|
| 996 |
+
"epoch": 79.0,
|
| 997 |
+
"eval_accuracy": 0.8431372549019608,
|
| 998 |
+
"eval_loss": 1.3450775146484375,
|
| 999 |
+
"eval_runtime": 0.6922,
|
| 1000 |
+
"eval_samples_per_second": 147.359,
|
| 1001 |
+
"eval_steps_per_second": 1.445,
|
| 1002 |
+
"step": 474
|
| 1003 |
+
},
|
| 1004 |
+
{
|
| 1005 |
+
"epoch": 80.0,
|
| 1006 |
+
"learning_rate": 4.000000000000001e-06,
|
| 1007 |
+
"loss": 1.1132,
|
| 1008 |
+
"step": 480
|
| 1009 |
+
},
|
| 1010 |
+
{
|
| 1011 |
+
"epoch": 80.0,
|
| 1012 |
+
"eval_accuracy": 0.8529411764705882,
|
| 1013 |
+
"eval_loss": 1.3408479690551758,
|
| 1014 |
+
"eval_runtime": 0.6779,
|
| 1015 |
+
"eval_samples_per_second": 150.459,
|
| 1016 |
+
"eval_steps_per_second": 1.475,
|
| 1017 |
+
"step": 480
|
| 1018 |
+
},
|
| 1019 |
+
{
|
| 1020 |
+
"epoch": 81.0,
|
| 1021 |
+
"eval_accuracy": 0.8529411764705882,
|
| 1022 |
+
"eval_loss": 1.336086630821228,
|
| 1023 |
+
"eval_runtime": 0.9551,
|
| 1024 |
+
"eval_samples_per_second": 106.8,
|
| 1025 |
+
"eval_steps_per_second": 1.047,
|
| 1026 |
+
"step": 486
|
| 1027 |
+
},
|
| 1028 |
+
{
|
| 1029 |
+
"epoch": 81.67,
|
| 1030 |
+
"learning_rate": 3.6666666666666666e-06,
|
| 1031 |
+
"loss": 1.0869,
|
| 1032 |
+
"step": 490
|
| 1033 |
+
},
|
| 1034 |
+
{
|
| 1035 |
+
"epoch": 82.0,
|
| 1036 |
+
"eval_accuracy": 0.8431372549019608,
|
| 1037 |
+
"eval_loss": 1.3308581113815308,
|
| 1038 |
+
"eval_runtime": 0.7685,
|
| 1039 |
+
"eval_samples_per_second": 132.729,
|
| 1040 |
+
"eval_steps_per_second": 1.301,
|
| 1041 |
+
"step": 492
|
| 1042 |
+
},
|
| 1043 |
+
{
|
| 1044 |
+
"epoch": 83.0,
|
| 1045 |
+
"eval_accuracy": 0.8529411764705882,
|
| 1046 |
+
"eval_loss": 1.324817419052124,
|
| 1047 |
+
"eval_runtime": 0.6895,
|
| 1048 |
+
"eval_samples_per_second": 147.938,
|
| 1049 |
+
"eval_steps_per_second": 1.45,
|
| 1050 |
+
"step": 498
|
| 1051 |
+
},
|
| 1052 |
+
{
|
| 1053 |
+
"epoch": 83.33,
|
| 1054 |
+
"learning_rate": 3.3333333333333333e-06,
|
| 1055 |
+
"loss": 1.0818,
|
| 1056 |
+
"step": 500
|
| 1057 |
+
},
|
| 1058 |
+
{
|
| 1059 |
+
"epoch": 84.0,
|
| 1060 |
+
"eval_accuracy": 0.8529411764705882,
|
| 1061 |
+
"eval_loss": 1.320926547050476,
|
| 1062 |
+
"eval_runtime": 0.6927,
|
| 1063 |
+
"eval_samples_per_second": 147.247,
|
| 1064 |
+
"eval_steps_per_second": 1.444,
|
| 1065 |
+
"step": 504
|
| 1066 |
+
},
|
| 1067 |
+
{
|
| 1068 |
+
"epoch": 85.0,
|
| 1069 |
+
"learning_rate": 3e-06,
|
| 1070 |
+
"loss": 1.0732,
|
| 1071 |
+
"step": 510
|
| 1072 |
+
},
|
| 1073 |
+
{
|
| 1074 |
+
"epoch": 85.0,
|
| 1075 |
+
"eval_accuracy": 0.8431372549019608,
|
| 1076 |
+
"eval_loss": 1.317958950996399,
|
| 1077 |
+
"eval_runtime": 0.7281,
|
| 1078 |
+
"eval_samples_per_second": 140.089,
|
| 1079 |
+
"eval_steps_per_second": 1.373,
|
| 1080 |
+
"step": 510
|
| 1081 |
+
},
|
| 1082 |
+
{
|
| 1083 |
+
"epoch": 86.0,
|
| 1084 |
+
"eval_accuracy": 0.8431372549019608,
|
| 1085 |
+
"eval_loss": 1.3156795501708984,
|
| 1086 |
+
"eval_runtime": 0.8315,
|
| 1087 |
+
"eval_samples_per_second": 122.671,
|
| 1088 |
+
"eval_steps_per_second": 1.203,
|
| 1089 |
+
"step": 516
|
| 1090 |
+
},
|
| 1091 |
+
{
|
| 1092 |
+
"epoch": 86.67,
|
| 1093 |
+
"learning_rate": 2.666666666666667e-06,
|
| 1094 |
+
"loss": 1.0637,
|
| 1095 |
+
"step": 520
|
| 1096 |
+
},
|
| 1097 |
+
{
|
| 1098 |
+
"epoch": 87.0,
|
| 1099 |
+
"eval_accuracy": 0.8529411764705882,
|
| 1100 |
+
"eval_loss": 1.3119415044784546,
|
| 1101 |
+
"eval_runtime": 0.7917,
|
| 1102 |
+
"eval_samples_per_second": 128.838,
|
| 1103 |
+
"eval_steps_per_second": 1.263,
|
| 1104 |
+
"step": 522
|
| 1105 |
+
},
|
| 1106 |
+
{
|
| 1107 |
+
"epoch": 88.0,
|
| 1108 |
+
"eval_accuracy": 0.8529411764705882,
|
| 1109 |
+
"eval_loss": 1.3100982904434204,
|
| 1110 |
+
"eval_runtime": 0.8514,
|
| 1111 |
+
"eval_samples_per_second": 119.809,
|
| 1112 |
+
"eval_steps_per_second": 1.175,
|
| 1113 |
+
"step": 528
|
| 1114 |
+
},
|
| 1115 |
+
{
|
| 1116 |
+
"epoch": 88.33,
|
| 1117 |
+
"learning_rate": 2.3333333333333336e-06,
|
| 1118 |
+
"loss": 1.0703,
|
| 1119 |
+
"step": 530
|
| 1120 |
+
},
|
| 1121 |
+
{
|
| 1122 |
+
"epoch": 89.0,
|
| 1123 |
+
"eval_accuracy": 0.8529411764705882,
|
| 1124 |
+
"eval_loss": 1.3083486557006836,
|
| 1125 |
+
"eval_runtime": 0.6809,
|
| 1126 |
+
"eval_samples_per_second": 149.804,
|
| 1127 |
+
"eval_steps_per_second": 1.469,
|
| 1128 |
+
"step": 534
|
| 1129 |
+
},
|
| 1130 |
+
{
|
| 1131 |
+
"epoch": 90.0,
|
| 1132 |
+
"learning_rate": 2.0000000000000003e-06,
|
| 1133 |
+
"loss": 1.055,
|
| 1134 |
+
"step": 540
|
| 1135 |
+
},
|
| 1136 |
+
{
|
| 1137 |
+
"epoch": 90.0,
|
| 1138 |
+
"eval_accuracy": 0.8529411764705882,
|
| 1139 |
+
"eval_loss": 1.3066046237945557,
|
| 1140 |
+
"eval_runtime": 0.7259,
|
| 1141 |
+
"eval_samples_per_second": 140.507,
|
| 1142 |
+
"eval_steps_per_second": 1.378,
|
| 1143 |
+
"step": 540
|
| 1144 |
+
},
|
| 1145 |
+
{
|
| 1146 |
+
"epoch": 91.0,
|
| 1147 |
+
"eval_accuracy": 0.8431372549019608,
|
| 1148 |
+
"eval_loss": 1.3046588897705078,
|
| 1149 |
+
"eval_runtime": 0.6982,
|
| 1150 |
+
"eval_samples_per_second": 146.097,
|
| 1151 |
+
"eval_steps_per_second": 1.432,
|
| 1152 |
+
"step": 546
|
| 1153 |
+
},
|
| 1154 |
+
{
|
| 1155 |
+
"epoch": 91.67,
|
| 1156 |
+
"learning_rate": 1.6666666666666667e-06,
|
| 1157 |
+
"loss": 1.0632,
|
| 1158 |
+
"step": 550
|
| 1159 |
+
},
|
| 1160 |
+
{
|
| 1161 |
+
"epoch": 92.0,
|
| 1162 |
+
"eval_accuracy": 0.8529411764705882,
|
| 1163 |
+
"eval_loss": 1.3031229972839355,
|
| 1164 |
+
"eval_runtime": 0.6959,
|
| 1165 |
+
"eval_samples_per_second": 146.574,
|
| 1166 |
+
"eval_steps_per_second": 1.437,
|
| 1167 |
+
"step": 552
|
| 1168 |
+
},
|
| 1169 |
+
{
|
| 1170 |
+
"epoch": 93.0,
|
| 1171 |
+
"eval_accuracy": 0.8529411764705882,
|
| 1172 |
+
"eval_loss": 1.3012945652008057,
|
| 1173 |
+
"eval_runtime": 0.6812,
|
| 1174 |
+
"eval_samples_per_second": 149.74,
|
| 1175 |
+
"eval_steps_per_second": 1.468,
|
| 1176 |
+
"step": 558
|
| 1177 |
+
},
|
| 1178 |
+
{
|
| 1179 |
+
"epoch": 93.33,
|
| 1180 |
+
"learning_rate": 1.3333333333333334e-06,
|
| 1181 |
+
"loss": 1.0509,
|
| 1182 |
+
"step": 560
|
| 1183 |
+
},
|
| 1184 |
+
{
|
| 1185 |
+
"epoch": 94.0,
|
| 1186 |
+
"eval_accuracy": 0.8529411764705882,
|
| 1187 |
+
"eval_loss": 1.2976847887039185,
|
| 1188 |
+
"eval_runtime": 0.6876,
|
| 1189 |
+
"eval_samples_per_second": 148.34,
|
| 1190 |
+
"eval_steps_per_second": 1.454,
|
| 1191 |
+
"step": 564
|
| 1192 |
+
},
|
| 1193 |
+
{
|
| 1194 |
+
"epoch": 95.0,
|
| 1195 |
+
"learning_rate": 1.0000000000000002e-06,
|
| 1196 |
+
"loss": 1.0496,
|
| 1197 |
+
"step": 570
|
| 1198 |
+
},
|
| 1199 |
+
{
|
| 1200 |
+
"epoch": 95.0,
|
| 1201 |
+
"eval_accuracy": 0.8529411764705882,
|
| 1202 |
+
"eval_loss": 1.2957763671875,
|
| 1203 |
+
"eval_runtime": 0.6884,
|
| 1204 |
+
"eval_samples_per_second": 148.164,
|
| 1205 |
+
"eval_steps_per_second": 1.453,
|
| 1206 |
+
"step": 570
|
| 1207 |
+
},
|
| 1208 |
+
{
|
| 1209 |
+
"epoch": 96.0,
|
| 1210 |
+
"eval_accuracy": 0.8431372549019608,
|
| 1211 |
+
"eval_loss": 1.2950189113616943,
|
| 1212 |
+
"eval_runtime": 1.0112,
|
| 1213 |
+
"eval_samples_per_second": 100.872,
|
| 1214 |
+
"eval_steps_per_second": 0.989,
|
| 1215 |
+
"step": 576
|
| 1216 |
+
},
|
| 1217 |
+
{
|
| 1218 |
+
"epoch": 96.67,
|
| 1219 |
+
"learning_rate": 6.666666666666667e-07,
|
| 1220 |
+
"loss": 1.047,
|
| 1221 |
+
"step": 580
|
| 1222 |
+
},
|
| 1223 |
+
{
|
| 1224 |
+
"epoch": 97.0,
|
| 1225 |
+
"eval_accuracy": 0.8431372549019608,
|
| 1226 |
+
"eval_loss": 1.2942228317260742,
|
| 1227 |
+
"eval_runtime": 0.8701,
|
| 1228 |
+
"eval_samples_per_second": 117.229,
|
| 1229 |
+
"eval_steps_per_second": 1.149,
|
| 1230 |
+
"step": 582
|
| 1231 |
+
},
|
| 1232 |
+
{
|
| 1233 |
+
"epoch": 98.0,
|
| 1234 |
+
"eval_accuracy": 0.8431372549019608,
|
| 1235 |
+
"eval_loss": 1.2938711643218994,
|
| 1236 |
+
"eval_runtime": 0.7154,
|
| 1237 |
+
"eval_samples_per_second": 142.581,
|
| 1238 |
+
"eval_steps_per_second": 1.398,
|
| 1239 |
+
"step": 588
|
| 1240 |
+
},
|
| 1241 |
+
{
|
| 1242 |
+
"epoch": 98.33,
|
| 1243 |
+
"learning_rate": 3.3333333333333335e-07,
|
| 1244 |
+
"loss": 1.0317,
|
| 1245 |
+
"step": 590
|
| 1246 |
+
},
|
| 1247 |
+
{
|
| 1248 |
+
"epoch": 99.0,
|
| 1249 |
+
"eval_accuracy": 0.8431372549019608,
|
| 1250 |
+
"eval_loss": 1.2937029600143433,
|
| 1251 |
+
"eval_runtime": 0.6831,
|
| 1252 |
+
"eval_samples_per_second": 149.311,
|
| 1253 |
+
"eval_steps_per_second": 1.464,
|
| 1254 |
+
"step": 594
|
| 1255 |
+
},
|
| 1256 |
+
{
|
| 1257 |
+
"epoch": 100.0,
|
| 1258 |
+
"learning_rate": 0.0,
|
| 1259 |
+
"loss": 1.0391,
|
| 1260 |
+
"step": 600
|
| 1261 |
+
},
|
| 1262 |
+
{
|
| 1263 |
+
"epoch": 100.0,
|
| 1264 |
+
"eval_accuracy": 0.8431372549019608,
|
| 1265 |
+
"eval_loss": 1.2935162782669067,
|
| 1266 |
+
"eval_runtime": 0.7374,
|
| 1267 |
+
"eval_samples_per_second": 138.332,
|
| 1268 |
+
"eval_steps_per_second": 1.356,
|
| 1269 |
+
"step": 600
|
| 1270 |
+
},
|
| 1271 |
+
{
|
| 1272 |
+
"epoch": 100.0,
|
| 1273 |
+
"step": 600,
|
| 1274 |
+
"total_flos": 4.44899699693568e+18,
|
| 1275 |
+
"train_loss": 1.6557193438212077,
|
| 1276 |
+
"train_runtime": 2084.5935,
|
| 1277 |
+
"train_samples_per_second": 27.535,
|
| 1278 |
+
"train_steps_per_second": 0.288
|
| 1279 |
+
}
|
| 1280 |
+
],
|
| 1281 |
+
"logging_steps": 10,
|
| 1282 |
+
"max_steps": 600,
|
| 1283 |
+
"num_input_tokens_seen": 0,
|
| 1284 |
+
"num_train_epochs": 100,
|
| 1285 |
+
"save_steps": 500,
|
| 1286 |
+
"total_flos": 4.44899699693568e+18,
|
| 1287 |
+
"train_batch_size": 100,
|
| 1288 |
+
"trial_name": null,
|
| 1289 |
+
"trial_params": null
|
| 1290 |
+
}
|