Commit
•
19b8565
1
Parent(s):
e06f9cc
End of training
Browse files- README.md +2 -2
- all_results.json +12 -0
- eval_results.json +8 -0
- runs/Apr26_08-18-02_DESKTOP-SKBE9FB/events.out.tfevents.1714142796.DESKTOP-SKBE9FB.7308.1 +3 -0
- train_results.json +7 -0
- trainer_state.json +1269 -0
README.md
CHANGED
|
@@ -17,8 +17,8 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 17 |
|
| 18 |
This model is a fine-tuned version of [google/vit-base-patch16-224](https://huggingface.co/google/vit-base-patch16-224) on an unknown dataset.
|
| 19 |
It achieves the following results on the evaluation set:
|
| 20 |
-
- Loss: 0.
|
| 21 |
-
- Accuracy: 0.
|
| 22 |
|
| 23 |
## Model description
|
| 24 |
|
|
|
|
| 17 |
|
| 18 |
This model is a fine-tuned version of [google/vit-base-patch16-224](https://huggingface.co/google/vit-base-patch16-224) on an unknown dataset.
|
| 19 |
It achieves the following results on the evaluation set:
|
| 20 |
+
- Loss: 0.6381
|
| 21 |
+
- Accuracy: 0.8667
|
| 22 |
|
| 23 |
## Model description
|
| 24 |
|
all_results.json
ADDED
|
@@ -0,0 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 90.32,
|
| 3 |
+
"eval_accuracy": 0.8666666666666667,
|
| 4 |
+
"eval_loss": 0.6381439566612244,
|
| 5 |
+
"eval_runtime": 1.3793,
|
| 6 |
+
"eval_samples_per_second": 43.499,
|
| 7 |
+
"eval_steps_per_second": 1.45,
|
| 8 |
+
"train_loss": 0.19939448043704033,
|
| 9 |
+
"train_runtime": 1530.1698,
|
| 10 |
+
"train_samples_per_second": 63.653,
|
| 11 |
+
"train_steps_per_second": 0.457
|
| 12 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 90.32,
|
| 3 |
+
"eval_accuracy": 0.8666666666666667,
|
| 4 |
+
"eval_loss": 0.6381439566612244,
|
| 5 |
+
"eval_runtime": 1.3793,
|
| 6 |
+
"eval_samples_per_second": 43.499,
|
| 7 |
+
"eval_steps_per_second": 1.45
|
| 8 |
+
}
|
runs/Apr26_08-18-02_DESKTOP-SKBE9FB/events.out.tfevents.1714142796.DESKTOP-SKBE9FB.7308.1
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:bbb4e19eaf2b30b2da90931479ff0c1564c4fed679fb1d242bdcd13ac726797e
|
| 3 |
+
size 411
|
train_results.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 90.32,
|
| 3 |
+
"train_loss": 0.19939448043704033,
|
| 4 |
+
"train_runtime": 1530.1698,
|
| 5 |
+
"train_samples_per_second": 63.653,
|
| 6 |
+
"train_steps_per_second": 0.457
|
| 7 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,1269 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.8666666666666667,
|
| 3 |
+
"best_model_checkpoint": "vit-base-patch16-224-dmae-va-U5-100-iN\\checkpoint-85",
|
| 4 |
+
"epoch": 90.3225806451613,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 700,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.9,
|
| 13 |
+
"eval_accuracy": 0.45,
|
| 14 |
+
"eval_loss": 1.3812448978424072,
|
| 15 |
+
"eval_runtime": 0.9939,
|
| 16 |
+
"eval_samples_per_second": 60.369,
|
| 17 |
+
"eval_steps_per_second": 2.012,
|
| 18 |
+
"step": 7
|
| 19 |
+
},
|
| 20 |
+
{
|
| 21 |
+
"epoch": 1.29,
|
| 22 |
+
"learning_rate": 1.4285714285714285e-05,
|
| 23 |
+
"loss": 1.3848,
|
| 24 |
+
"step": 10
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 1.94,
|
| 28 |
+
"eval_accuracy": 0.5,
|
| 29 |
+
"eval_loss": 1.3605996370315552,
|
| 30 |
+
"eval_runtime": 1.0777,
|
| 31 |
+
"eval_samples_per_second": 55.675,
|
| 32 |
+
"eval_steps_per_second": 1.856,
|
| 33 |
+
"step": 15
|
| 34 |
+
},
|
| 35 |
+
{
|
| 36 |
+
"epoch": 2.58,
|
| 37 |
+
"learning_rate": 2.857142857142857e-05,
|
| 38 |
+
"loss": 1.3686,
|
| 39 |
+
"step": 20
|
| 40 |
+
},
|
| 41 |
+
{
|
| 42 |
+
"epoch": 2.97,
|
| 43 |
+
"eval_accuracy": 0.5333333333333333,
|
| 44 |
+
"eval_loss": 1.3074811697006226,
|
| 45 |
+
"eval_runtime": 1.0069,
|
| 46 |
+
"eval_samples_per_second": 59.587,
|
| 47 |
+
"eval_steps_per_second": 1.986,
|
| 48 |
+
"step": 23
|
| 49 |
+
},
|
| 50 |
+
{
|
| 51 |
+
"epoch": 3.87,
|
| 52 |
+
"learning_rate": 4.2857142857142856e-05,
|
| 53 |
+
"loss": 1.2965,
|
| 54 |
+
"step": 30
|
| 55 |
+
},
|
| 56 |
+
{
|
| 57 |
+
"epoch": 4.0,
|
| 58 |
+
"eval_accuracy": 0.4666666666666667,
|
| 59 |
+
"eval_loss": 1.2370479106903076,
|
| 60 |
+
"eval_runtime": 1.023,
|
| 61 |
+
"eval_samples_per_second": 58.649,
|
| 62 |
+
"eval_steps_per_second": 1.955,
|
| 63 |
+
"step": 31
|
| 64 |
+
},
|
| 65 |
+
{
|
| 66 |
+
"epoch": 4.9,
|
| 67 |
+
"eval_accuracy": 0.5333333333333333,
|
| 68 |
+
"eval_loss": 1.1167830228805542,
|
| 69 |
+
"eval_runtime": 1.0537,
|
| 70 |
+
"eval_samples_per_second": 56.944,
|
| 71 |
+
"eval_steps_per_second": 1.898,
|
| 72 |
+
"step": 38
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 5.16,
|
| 76 |
+
"learning_rate": 4.9624060150375936e-05,
|
| 77 |
+
"loss": 1.1753,
|
| 78 |
+
"step": 40
|
| 79 |
+
},
|
| 80 |
+
{
|
| 81 |
+
"epoch": 5.94,
|
| 82 |
+
"eval_accuracy": 0.5666666666666667,
|
| 83 |
+
"eval_loss": 1.0309817790985107,
|
| 84 |
+
"eval_runtime": 0.9955,
|
| 85 |
+
"eval_samples_per_second": 60.27,
|
| 86 |
+
"eval_steps_per_second": 2.009,
|
| 87 |
+
"step": 46
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 6.45,
|
| 91 |
+
"learning_rate": 4.887218045112782e-05,
|
| 92 |
+
"loss": 1.0294,
|
| 93 |
+
"step": 50
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 6.97,
|
| 97 |
+
"eval_accuracy": 0.6,
|
| 98 |
+
"eval_loss": 0.9315768480300903,
|
| 99 |
+
"eval_runtime": 1.0112,
|
| 100 |
+
"eval_samples_per_second": 59.337,
|
| 101 |
+
"eval_steps_per_second": 1.978,
|
| 102 |
+
"step": 54
|
| 103 |
+
},
|
| 104 |
+
{
|
| 105 |
+
"epoch": 7.74,
|
| 106 |
+
"learning_rate": 4.81203007518797e-05,
|
| 107 |
+
"loss": 0.902,
|
| 108 |
+
"step": 60
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"epoch": 8.0,
|
| 112 |
+
"eval_accuracy": 0.6833333333333333,
|
| 113 |
+
"eval_loss": 0.8727719187736511,
|
| 114 |
+
"eval_runtime": 1.0259,
|
| 115 |
+
"eval_samples_per_second": 58.484,
|
| 116 |
+
"eval_steps_per_second": 1.949,
|
| 117 |
+
"step": 62
|
| 118 |
+
},
|
| 119 |
+
{
|
| 120 |
+
"epoch": 8.9,
|
| 121 |
+
"eval_accuracy": 0.7666666666666667,
|
| 122 |
+
"eval_loss": 0.8128864765167236,
|
| 123 |
+
"eval_runtime": 1.0791,
|
| 124 |
+
"eval_samples_per_second": 55.601,
|
| 125 |
+
"eval_steps_per_second": 1.853,
|
| 126 |
+
"step": 69
|
| 127 |
+
},
|
| 128 |
+
{
|
| 129 |
+
"epoch": 9.03,
|
| 130 |
+
"learning_rate": 4.736842105263158e-05,
|
| 131 |
+
"loss": 0.7812,
|
| 132 |
+
"step": 70
|
| 133 |
+
},
|
| 134 |
+
{
|
| 135 |
+
"epoch": 9.94,
|
| 136 |
+
"eval_accuracy": 0.8,
|
| 137 |
+
"eval_loss": 0.7006206512451172,
|
| 138 |
+
"eval_runtime": 1.0876,
|
| 139 |
+
"eval_samples_per_second": 55.167,
|
| 140 |
+
"eval_steps_per_second": 1.839,
|
| 141 |
+
"step": 77
|
| 142 |
+
},
|
| 143 |
+
{
|
| 144 |
+
"epoch": 10.32,
|
| 145 |
+
"learning_rate": 4.6616541353383456e-05,
|
| 146 |
+
"loss": 0.6419,
|
| 147 |
+
"step": 80
|
| 148 |
+
},
|
| 149 |
+
{
|
| 150 |
+
"epoch": 10.97,
|
| 151 |
+
"eval_accuracy": 0.8666666666666667,
|
| 152 |
+
"eval_loss": 0.6381439566612244,
|
| 153 |
+
"eval_runtime": 1.0437,
|
| 154 |
+
"eval_samples_per_second": 57.486,
|
| 155 |
+
"eval_steps_per_second": 1.916,
|
| 156 |
+
"step": 85
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 11.61,
|
| 160 |
+
"learning_rate": 4.586466165413534e-05,
|
| 161 |
+
"loss": 0.5109,
|
| 162 |
+
"step": 90
|
| 163 |
+
},
|
| 164 |
+
{
|
| 165 |
+
"epoch": 12.0,
|
| 166 |
+
"eval_accuracy": 0.8166666666666667,
|
| 167 |
+
"eval_loss": 0.6327125430107117,
|
| 168 |
+
"eval_runtime": 1.0397,
|
| 169 |
+
"eval_samples_per_second": 57.707,
|
| 170 |
+
"eval_steps_per_second": 1.924,
|
| 171 |
+
"step": 93
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 12.9,
|
| 175 |
+
"learning_rate": 4.511278195488722e-05,
|
| 176 |
+
"loss": 0.3838,
|
| 177 |
+
"step": 100
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 12.9,
|
| 181 |
+
"eval_accuracy": 0.8666666666666667,
|
| 182 |
+
"eval_loss": 0.5441552996635437,
|
| 183 |
+
"eval_runtime": 1.0509,
|
| 184 |
+
"eval_samples_per_second": 57.092,
|
| 185 |
+
"eval_steps_per_second": 1.903,
|
| 186 |
+
"step": 100
|
| 187 |
+
},
|
| 188 |
+
{
|
| 189 |
+
"epoch": 13.94,
|
| 190 |
+
"eval_accuracy": 0.75,
|
| 191 |
+
"eval_loss": 0.6755495667457581,
|
| 192 |
+
"eval_runtime": 1.041,
|
| 193 |
+
"eval_samples_per_second": 57.635,
|
| 194 |
+
"eval_steps_per_second": 1.921,
|
| 195 |
+
"step": 108
|
| 196 |
+
},
|
| 197 |
+
{
|
| 198 |
+
"epoch": 14.19,
|
| 199 |
+
"learning_rate": 4.43609022556391e-05,
|
| 200 |
+
"loss": 0.285,
|
| 201 |
+
"step": 110
|
| 202 |
+
},
|
| 203 |
+
{
|
| 204 |
+
"epoch": 14.97,
|
| 205 |
+
"eval_accuracy": 0.7166666666666667,
|
| 206 |
+
"eval_loss": 0.7755728960037231,
|
| 207 |
+
"eval_runtime": 1.0199,
|
| 208 |
+
"eval_samples_per_second": 58.828,
|
| 209 |
+
"eval_steps_per_second": 1.961,
|
| 210 |
+
"step": 116
|
| 211 |
+
},
|
| 212 |
+
{
|
| 213 |
+
"epoch": 15.48,
|
| 214 |
+
"learning_rate": 4.3609022556390975e-05,
|
| 215 |
+
"loss": 0.2672,
|
| 216 |
+
"step": 120
|
| 217 |
+
},
|
| 218 |
+
{
|
| 219 |
+
"epoch": 16.0,
|
| 220 |
+
"eval_accuracy": 0.7166666666666667,
|
| 221 |
+
"eval_loss": 0.8106668591499329,
|
| 222 |
+
"eval_runtime": 1.0429,
|
| 223 |
+
"eval_samples_per_second": 57.531,
|
| 224 |
+
"eval_steps_per_second": 1.918,
|
| 225 |
+
"step": 124
|
| 226 |
+
},
|
| 227 |
+
{
|
| 228 |
+
"epoch": 16.77,
|
| 229 |
+
"learning_rate": 4.2857142857142856e-05,
|
| 230 |
+
"loss": 0.2466,
|
| 231 |
+
"step": 130
|
| 232 |
+
},
|
| 233 |
+
{
|
| 234 |
+
"epoch": 16.9,
|
| 235 |
+
"eval_accuracy": 0.8333333333333334,
|
| 236 |
+
"eval_loss": 0.5219495892524719,
|
| 237 |
+
"eval_runtime": 1.0179,
|
| 238 |
+
"eval_samples_per_second": 58.943,
|
| 239 |
+
"eval_steps_per_second": 1.965,
|
| 240 |
+
"step": 131
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 17.94,
|
| 244 |
+
"eval_accuracy": 0.7833333333333333,
|
| 245 |
+
"eval_loss": 0.7040973901748657,
|
| 246 |
+
"eval_runtime": 1.0682,
|
| 247 |
+
"eval_samples_per_second": 56.169,
|
| 248 |
+
"eval_steps_per_second": 1.872,
|
| 249 |
+
"step": 139
|
| 250 |
+
},
|
| 251 |
+
{
|
| 252 |
+
"epoch": 18.06,
|
| 253 |
+
"learning_rate": 4.210526315789474e-05,
|
| 254 |
+
"loss": 0.2312,
|
| 255 |
+
"step": 140
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 18.97,
|
| 259 |
+
"eval_accuracy": 0.75,
|
| 260 |
+
"eval_loss": 0.7878958582878113,
|
| 261 |
+
"eval_runtime": 0.9838,
|
| 262 |
+
"eval_samples_per_second": 60.989,
|
| 263 |
+
"eval_steps_per_second": 2.033,
|
| 264 |
+
"step": 147
|
| 265 |
+
},
|
| 266 |
+
{
|
| 267 |
+
"epoch": 19.35,
|
| 268 |
+
"learning_rate": 4.135338345864662e-05,
|
| 269 |
+
"loss": 0.1933,
|
| 270 |
+
"step": 150
|
| 271 |
+
},
|
| 272 |
+
{
|
| 273 |
+
"epoch": 20.0,
|
| 274 |
+
"eval_accuracy": 0.8,
|
| 275 |
+
"eval_loss": 0.709021806716919,
|
| 276 |
+
"eval_runtime": 1.0518,
|
| 277 |
+
"eval_samples_per_second": 57.046,
|
| 278 |
+
"eval_steps_per_second": 1.902,
|
| 279 |
+
"step": 155
|
| 280 |
+
},
|
| 281 |
+
{
|
| 282 |
+
"epoch": 20.65,
|
| 283 |
+
"learning_rate": 4.0601503759398494e-05,
|
| 284 |
+
"loss": 0.1692,
|
| 285 |
+
"step": 160
|
| 286 |
+
},
|
| 287 |
+
{
|
| 288 |
+
"epoch": 20.9,
|
| 289 |
+
"eval_accuracy": 0.8333333333333334,
|
| 290 |
+
"eval_loss": 0.5394979119300842,
|
| 291 |
+
"eval_runtime": 1.0183,
|
| 292 |
+
"eval_samples_per_second": 58.921,
|
| 293 |
+
"eval_steps_per_second": 1.964,
|
| 294 |
+
"step": 162
|
| 295 |
+
},
|
| 296 |
+
{
|
| 297 |
+
"epoch": 21.94,
|
| 298 |
+
"learning_rate": 3.9849624060150376e-05,
|
| 299 |
+
"loss": 0.1578,
|
| 300 |
+
"step": 170
|
| 301 |
+
},
|
| 302 |
+
{
|
| 303 |
+
"epoch": 21.94,
|
| 304 |
+
"eval_accuracy": 0.8166666666666667,
|
| 305 |
+
"eval_loss": 0.6418856382369995,
|
| 306 |
+
"eval_runtime": 1.0177,
|
| 307 |
+
"eval_samples_per_second": 58.959,
|
| 308 |
+
"eval_steps_per_second": 1.965,
|
| 309 |
+
"step": 170
|
| 310 |
+
},
|
| 311 |
+
{
|
| 312 |
+
"epoch": 22.97,
|
| 313 |
+
"eval_accuracy": 0.8333333333333334,
|
| 314 |
+
"eval_loss": 0.5736449956893921,
|
| 315 |
+
"eval_runtime": 1.0279,
|
| 316 |
+
"eval_samples_per_second": 58.369,
|
| 317 |
+
"eval_steps_per_second": 1.946,
|
| 318 |
+
"step": 178
|
| 319 |
+
},
|
| 320 |
+
{
|
| 321 |
+
"epoch": 23.23,
|
| 322 |
+
"learning_rate": 3.909774436090226e-05,
|
| 323 |
+
"loss": 0.1321,
|
| 324 |
+
"step": 180
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 24.0,
|
| 328 |
+
"eval_accuracy": 0.75,
|
| 329 |
+
"eval_loss": 0.747129499912262,
|
| 330 |
+
"eval_runtime": 1.021,
|
| 331 |
+
"eval_samples_per_second": 58.768,
|
| 332 |
+
"eval_steps_per_second": 1.959,
|
| 333 |
+
"step": 186
|
| 334 |
+
},
|
| 335 |
+
{
|
| 336 |
+
"epoch": 24.52,
|
| 337 |
+
"learning_rate": 3.834586466165413e-05,
|
| 338 |
+
"loss": 0.1114,
|
| 339 |
+
"step": 190
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 24.9,
|
| 343 |
+
"eval_accuracy": 0.7666666666666667,
|
| 344 |
+
"eval_loss": 0.6447189450263977,
|
| 345 |
+
"eval_runtime": 1.0464,
|
| 346 |
+
"eval_samples_per_second": 57.341,
|
| 347 |
+
"eval_steps_per_second": 1.911,
|
| 348 |
+
"step": 193
|
| 349 |
+
},
|
| 350 |
+
{
|
| 351 |
+
"epoch": 25.81,
|
| 352 |
+
"learning_rate": 3.759398496240601e-05,
|
| 353 |
+
"loss": 0.1385,
|
| 354 |
+
"step": 200
|
| 355 |
+
},
|
| 356 |
+
{
|
| 357 |
+
"epoch": 25.94,
|
| 358 |
+
"eval_accuracy": 0.8166666666666667,
|
| 359 |
+
"eval_loss": 0.61579829454422,
|
| 360 |
+
"eval_runtime": 0.9804,
|
| 361 |
+
"eval_samples_per_second": 61.197,
|
| 362 |
+
"eval_steps_per_second": 2.04,
|
| 363 |
+
"step": 201
|
| 364 |
+
},
|
| 365 |
+
{
|
| 366 |
+
"epoch": 26.97,
|
| 367 |
+
"eval_accuracy": 0.8,
|
| 368 |
+
"eval_loss": 0.6467480063438416,
|
| 369 |
+
"eval_runtime": 1.0425,
|
| 370 |
+
"eval_samples_per_second": 57.556,
|
| 371 |
+
"eval_steps_per_second": 1.919,
|
| 372 |
+
"step": 209
|
| 373 |
+
},
|
| 374 |
+
{
|
| 375 |
+
"epoch": 27.1,
|
| 376 |
+
"learning_rate": 3.6842105263157895e-05,
|
| 377 |
+
"loss": 0.1136,
|
| 378 |
+
"step": 210
|
| 379 |
+
},
|
| 380 |
+
{
|
| 381 |
+
"epoch": 28.0,
|
| 382 |
+
"eval_accuracy": 0.85,
|
| 383 |
+
"eval_loss": 0.6180290579795837,
|
| 384 |
+
"eval_runtime": 1.0892,
|
| 385 |
+
"eval_samples_per_second": 55.084,
|
| 386 |
+
"eval_steps_per_second": 1.836,
|
| 387 |
+
"step": 217
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 28.39,
|
| 391 |
+
"learning_rate": 3.6090225563909776e-05,
|
| 392 |
+
"loss": 0.0997,
|
| 393 |
+
"step": 220
|
| 394 |
+
},
|
| 395 |
+
{
|
| 396 |
+
"epoch": 28.9,
|
| 397 |
+
"eval_accuracy": 0.75,
|
| 398 |
+
"eval_loss": 0.8578386902809143,
|
| 399 |
+
"eval_runtime": 0.9851,
|
| 400 |
+
"eval_samples_per_second": 60.908,
|
| 401 |
+
"eval_steps_per_second": 2.03,
|
| 402 |
+
"step": 224
|
| 403 |
+
},
|
| 404 |
+
{
|
| 405 |
+
"epoch": 29.68,
|
| 406 |
+
"learning_rate": 3.533834586466165e-05,
|
| 407 |
+
"loss": 0.1064,
|
| 408 |
+
"step": 230
|
| 409 |
+
},
|
| 410 |
+
{
|
| 411 |
+
"epoch": 29.94,
|
| 412 |
+
"eval_accuracy": 0.8166666666666667,
|
| 413 |
+
"eval_loss": 0.6778053641319275,
|
| 414 |
+
"eval_runtime": 0.9651,
|
| 415 |
+
"eval_samples_per_second": 62.17,
|
| 416 |
+
"eval_steps_per_second": 2.072,
|
| 417 |
+
"step": 232
|
| 418 |
+
},
|
| 419 |
+
{
|
| 420 |
+
"epoch": 30.97,
|
| 421 |
+
"learning_rate": 3.458646616541353e-05,
|
| 422 |
+
"loss": 0.0775,
|
| 423 |
+
"step": 240
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 30.97,
|
| 427 |
+
"eval_accuracy": 0.8,
|
| 428 |
+
"eval_loss": 0.8123681545257568,
|
| 429 |
+
"eval_runtime": 0.9886,
|
| 430 |
+
"eval_samples_per_second": 60.693,
|
| 431 |
+
"eval_steps_per_second": 2.023,
|
| 432 |
+
"step": 240
|
| 433 |
+
},
|
| 434 |
+
{
|
| 435 |
+
"epoch": 32.0,
|
| 436 |
+
"eval_accuracy": 0.8,
|
| 437 |
+
"eval_loss": 0.7782633900642395,
|
| 438 |
+
"eval_runtime": 1.0238,
|
| 439 |
+
"eval_samples_per_second": 58.605,
|
| 440 |
+
"eval_steps_per_second": 1.953,
|
| 441 |
+
"step": 248
|
| 442 |
+
},
|
| 443 |
+
{
|
| 444 |
+
"epoch": 32.26,
|
| 445 |
+
"learning_rate": 3.3834586466165414e-05,
|
| 446 |
+
"loss": 0.0921,
|
| 447 |
+
"step": 250
|
| 448 |
+
},
|
| 449 |
+
{
|
| 450 |
+
"epoch": 32.9,
|
| 451 |
+
"eval_accuracy": 0.7333333333333333,
|
| 452 |
+
"eval_loss": 0.8320418000221252,
|
| 453 |
+
"eval_runtime": 1.0125,
|
| 454 |
+
"eval_samples_per_second": 59.258,
|
| 455 |
+
"eval_steps_per_second": 1.975,
|
| 456 |
+
"step": 255
|
| 457 |
+
},
|
| 458 |
+
{
|
| 459 |
+
"epoch": 33.55,
|
| 460 |
+
"learning_rate": 3.3082706766917295e-05,
|
| 461 |
+
"loss": 0.0919,
|
| 462 |
+
"step": 260
|
| 463 |
+
},
|
| 464 |
+
{
|
| 465 |
+
"epoch": 33.94,
|
| 466 |
+
"eval_accuracy": 0.7833333333333333,
|
| 467 |
+
"eval_loss": 0.8309503197669983,
|
| 468 |
+
"eval_runtime": 0.9631,
|
| 469 |
+
"eval_samples_per_second": 62.3,
|
| 470 |
+
"eval_steps_per_second": 2.077,
|
| 471 |
+
"step": 263
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 34.84,
|
| 475 |
+
"learning_rate": 3.233082706766917e-05,
|
| 476 |
+
"loss": 0.0888,
|
| 477 |
+
"step": 270
|
| 478 |
+
},
|
| 479 |
+
{
|
| 480 |
+
"epoch": 34.97,
|
| 481 |
+
"eval_accuracy": 0.85,
|
| 482 |
+
"eval_loss": 0.6575559377670288,
|
| 483 |
+
"eval_runtime": 0.9897,
|
| 484 |
+
"eval_samples_per_second": 60.621,
|
| 485 |
+
"eval_steps_per_second": 2.021,
|
| 486 |
+
"step": 271
|
| 487 |
+
},
|
| 488 |
+
{
|
| 489 |
+
"epoch": 36.0,
|
| 490 |
+
"eval_accuracy": 0.8333333333333334,
|
| 491 |
+
"eval_loss": 0.7043873071670532,
|
| 492 |
+
"eval_runtime": 0.9919,
|
| 493 |
+
"eval_samples_per_second": 60.489,
|
| 494 |
+
"eval_steps_per_second": 2.016,
|
| 495 |
+
"step": 279
|
| 496 |
+
},
|
| 497 |
+
{
|
| 498 |
+
"epoch": 36.13,
|
| 499 |
+
"learning_rate": 3.157894736842105e-05,
|
| 500 |
+
"loss": 0.0693,
|
| 501 |
+
"step": 280
|
| 502 |
+
},
|
| 503 |
+
{
|
| 504 |
+
"epoch": 36.9,
|
| 505 |
+
"eval_accuracy": 0.8166666666666667,
|
| 506 |
+
"eval_loss": 0.7607947587966919,
|
| 507 |
+
"eval_runtime": 0.9426,
|
| 508 |
+
"eval_samples_per_second": 63.653,
|
| 509 |
+
"eval_steps_per_second": 2.122,
|
| 510 |
+
"step": 286
|
| 511 |
+
},
|
| 512 |
+
{
|
| 513 |
+
"epoch": 37.42,
|
| 514 |
+
"learning_rate": 3.082706766917293e-05,
|
| 515 |
+
"loss": 0.061,
|
| 516 |
+
"step": 290
|
| 517 |
+
},
|
| 518 |
+
{
|
| 519 |
+
"epoch": 37.94,
|
| 520 |
+
"eval_accuracy": 0.8,
|
| 521 |
+
"eval_loss": 0.7802255153656006,
|
| 522 |
+
"eval_runtime": 0.9812,
|
| 523 |
+
"eval_samples_per_second": 61.149,
|
| 524 |
+
"eval_steps_per_second": 2.038,
|
| 525 |
+
"step": 294
|
| 526 |
+
},
|
| 527 |
+
{
|
| 528 |
+
"epoch": 38.71,
|
| 529 |
+
"learning_rate": 3.007518796992481e-05,
|
| 530 |
+
"loss": 0.0699,
|
| 531 |
+
"step": 300
|
| 532 |
+
},
|
| 533 |
+
{
|
| 534 |
+
"epoch": 38.97,
|
| 535 |
+
"eval_accuracy": 0.8166666666666667,
|
| 536 |
+
"eval_loss": 0.7761934995651245,
|
| 537 |
+
"eval_runtime": 0.9881,
|
| 538 |
+
"eval_samples_per_second": 60.722,
|
| 539 |
+
"eval_steps_per_second": 2.024,
|
| 540 |
+
"step": 302
|
| 541 |
+
},
|
| 542 |
+
{
|
| 543 |
+
"epoch": 40.0,
|
| 544 |
+
"learning_rate": 2.9323308270676693e-05,
|
| 545 |
+
"loss": 0.0652,
|
| 546 |
+
"step": 310
|
| 547 |
+
},
|
| 548 |
+
{
|
| 549 |
+
"epoch": 40.0,
|
| 550 |
+
"eval_accuracy": 0.8,
|
| 551 |
+
"eval_loss": 0.7579043507575989,
|
| 552 |
+
"eval_runtime": 1.0374,
|
| 553 |
+
"eval_samples_per_second": 57.837,
|
| 554 |
+
"eval_steps_per_second": 1.928,
|
| 555 |
+
"step": 310
|
| 556 |
+
},
|
| 557 |
+
{
|
| 558 |
+
"epoch": 40.9,
|
| 559 |
+
"eval_accuracy": 0.75,
|
| 560 |
+
"eval_loss": 0.998461902141571,
|
| 561 |
+
"eval_runtime": 0.9702,
|
| 562 |
+
"eval_samples_per_second": 61.842,
|
| 563 |
+
"eval_steps_per_second": 2.061,
|
| 564 |
+
"step": 317
|
| 565 |
+
},
|
| 566 |
+
{
|
| 567 |
+
"epoch": 41.29,
|
| 568 |
+
"learning_rate": 2.857142857142857e-05,
|
| 569 |
+
"loss": 0.0562,
|
| 570 |
+
"step": 320
|
| 571 |
+
},
|
| 572 |
+
{
|
| 573 |
+
"epoch": 41.94,
|
| 574 |
+
"eval_accuracy": 0.8166666666666667,
|
| 575 |
+
"eval_loss": 0.8027188777923584,
|
| 576 |
+
"eval_runtime": 1.0453,
|
| 577 |
+
"eval_samples_per_second": 57.397,
|
| 578 |
+
"eval_steps_per_second": 1.913,
|
| 579 |
+
"step": 325
|
| 580 |
+
},
|
| 581 |
+
{
|
| 582 |
+
"epoch": 42.58,
|
| 583 |
+
"learning_rate": 2.7819548872180452e-05,
|
| 584 |
+
"loss": 0.0534,
|
| 585 |
+
"step": 330
|
| 586 |
+
},
|
| 587 |
+
{
|
| 588 |
+
"epoch": 42.97,
|
| 589 |
+
"eval_accuracy": 0.7833333333333333,
|
| 590 |
+
"eval_loss": 0.9704654812812805,
|
| 591 |
+
"eval_runtime": 1.0187,
|
| 592 |
+
"eval_samples_per_second": 58.899,
|
| 593 |
+
"eval_steps_per_second": 1.963,
|
| 594 |
+
"step": 333
|
| 595 |
+
},
|
| 596 |
+
{
|
| 597 |
+
"epoch": 43.87,
|
| 598 |
+
"learning_rate": 2.706766917293233e-05,
|
| 599 |
+
"loss": 0.0519,
|
| 600 |
+
"step": 340
|
| 601 |
+
},
|
| 602 |
+
{
|
| 603 |
+
"epoch": 44.0,
|
| 604 |
+
"eval_accuracy": 0.8333333333333334,
|
| 605 |
+
"eval_loss": 0.7301105260848999,
|
| 606 |
+
"eval_runtime": 0.998,
|
| 607 |
+
"eval_samples_per_second": 60.123,
|
| 608 |
+
"eval_steps_per_second": 2.004,
|
| 609 |
+
"step": 341
|
| 610 |
+
},
|
| 611 |
+
{
|
| 612 |
+
"epoch": 44.9,
|
| 613 |
+
"eval_accuracy": 0.8,
|
| 614 |
+
"eval_loss": 0.8432899713516235,
|
| 615 |
+
"eval_runtime": 1.0546,
|
| 616 |
+
"eval_samples_per_second": 56.895,
|
| 617 |
+
"eval_steps_per_second": 1.897,
|
| 618 |
+
"step": 348
|
| 619 |
+
},
|
| 620 |
+
{
|
| 621 |
+
"epoch": 45.16,
|
| 622 |
+
"learning_rate": 2.6315789473684212e-05,
|
| 623 |
+
"loss": 0.0529,
|
| 624 |
+
"step": 350
|
| 625 |
+
},
|
| 626 |
+
{
|
| 627 |
+
"epoch": 45.94,
|
| 628 |
+
"eval_accuracy": 0.8,
|
| 629 |
+
"eval_loss": 0.8533557653427124,
|
| 630 |
+
"eval_runtime": 1.0201,
|
| 631 |
+
"eval_samples_per_second": 58.815,
|
| 632 |
+
"eval_steps_per_second": 1.961,
|
| 633 |
+
"step": 356
|
| 634 |
+
},
|
| 635 |
+
{
|
| 636 |
+
"epoch": 46.45,
|
| 637 |
+
"learning_rate": 2.556390977443609e-05,
|
| 638 |
+
"loss": 0.0772,
|
| 639 |
+
"step": 360
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 46.97,
|
| 643 |
+
"eval_accuracy": 0.8,
|
| 644 |
+
"eval_loss": 0.8561839461326599,
|
| 645 |
+
"eval_runtime": 1.0725,
|
| 646 |
+
"eval_samples_per_second": 55.942,
|
| 647 |
+
"eval_steps_per_second": 1.865,
|
| 648 |
+
"step": 364
|
| 649 |
+
},
|
| 650 |
+
{
|
| 651 |
+
"epoch": 47.74,
|
| 652 |
+
"learning_rate": 2.4812030075187968e-05,
|
| 653 |
+
"loss": 0.0644,
|
| 654 |
+
"step": 370
|
| 655 |
+
},
|
| 656 |
+
{
|
| 657 |
+
"epoch": 48.0,
|
| 658 |
+
"eval_accuracy": 0.8,
|
| 659 |
+
"eval_loss": 0.8419451117515564,
|
| 660 |
+
"eval_runtime": 1.0154,
|
| 661 |
+
"eval_samples_per_second": 59.091,
|
| 662 |
+
"eval_steps_per_second": 1.97,
|
| 663 |
+
"step": 372
|
| 664 |
+
},
|
| 665 |
+
{
|
| 666 |
+
"epoch": 48.9,
|
| 667 |
+
"eval_accuracy": 0.7666666666666667,
|
| 668 |
+
"eval_loss": 1.125100016593933,
|
| 669 |
+
"eval_runtime": 1.3342,
|
| 670 |
+
"eval_samples_per_second": 44.969,
|
| 671 |
+
"eval_steps_per_second": 1.499,
|
| 672 |
+
"step": 379
|
| 673 |
+
},
|
| 674 |
+
{
|
| 675 |
+
"epoch": 49.03,
|
| 676 |
+
"learning_rate": 2.406015037593985e-05,
|
| 677 |
+
"loss": 0.0467,
|
| 678 |
+
"step": 380
|
| 679 |
+
},
|
| 680 |
+
{
|
| 681 |
+
"epoch": 49.94,
|
| 682 |
+
"eval_accuracy": 0.8333333333333334,
|
| 683 |
+
"eval_loss": 0.7536706924438477,
|
| 684 |
+
"eval_runtime": 1.6625,
|
| 685 |
+
"eval_samples_per_second": 36.09,
|
| 686 |
+
"eval_steps_per_second": 1.203,
|
| 687 |
+
"step": 387
|
| 688 |
+
},
|
| 689 |
+
{
|
| 690 |
+
"epoch": 50.32,
|
| 691 |
+
"learning_rate": 2.3308270676691728e-05,
|
| 692 |
+
"loss": 0.0576,
|
| 693 |
+
"step": 390
|
| 694 |
+
},
|
| 695 |
+
{
|
| 696 |
+
"epoch": 50.97,
|
| 697 |
+
"eval_accuracy": 0.8333333333333334,
|
| 698 |
+
"eval_loss": 0.7517222166061401,
|
| 699 |
+
"eval_runtime": 1.0574,
|
| 700 |
+
"eval_samples_per_second": 56.741,
|
| 701 |
+
"eval_steps_per_second": 1.891,
|
| 702 |
+
"step": 395
|
| 703 |
+
},
|
| 704 |
+
{
|
| 705 |
+
"epoch": 51.61,
|
| 706 |
+
"learning_rate": 2.255639097744361e-05,
|
| 707 |
+
"loss": 0.0344,
|
| 708 |
+
"step": 400
|
| 709 |
+
},
|
| 710 |
+
{
|
| 711 |
+
"epoch": 52.0,
|
| 712 |
+
"eval_accuracy": 0.8,
|
| 713 |
+
"eval_loss": 0.8343304395675659,
|
| 714 |
+
"eval_runtime": 1.0509,
|
| 715 |
+
"eval_samples_per_second": 57.096,
|
| 716 |
+
"eval_steps_per_second": 1.903,
|
| 717 |
+
"step": 403
|
| 718 |
+
},
|
| 719 |
+
{
|
| 720 |
+
"epoch": 52.9,
|
| 721 |
+
"learning_rate": 2.1804511278195487e-05,
|
| 722 |
+
"loss": 0.0663,
|
| 723 |
+
"step": 410
|
| 724 |
+
},
|
| 725 |
+
{
|
| 726 |
+
"epoch": 52.9,
|
| 727 |
+
"eval_accuracy": 0.8,
|
| 728 |
+
"eval_loss": 0.7636159062385559,
|
| 729 |
+
"eval_runtime": 0.952,
|
| 730 |
+
"eval_samples_per_second": 63.026,
|
| 731 |
+
"eval_steps_per_second": 2.101,
|
| 732 |
+
"step": 410
|
| 733 |
+
},
|
| 734 |
+
{
|
| 735 |
+
"epoch": 53.94,
|
| 736 |
+
"eval_accuracy": 0.8166666666666667,
|
| 737 |
+
"eval_loss": 0.8253324031829834,
|
| 738 |
+
"eval_runtime": 0.9847,
|
| 739 |
+
"eval_samples_per_second": 60.932,
|
| 740 |
+
"eval_steps_per_second": 2.031,
|
| 741 |
+
"step": 418
|
| 742 |
+
},
|
| 743 |
+
{
|
| 744 |
+
"epoch": 54.19,
|
| 745 |
+
"learning_rate": 2.105263157894737e-05,
|
| 746 |
+
"loss": 0.0353,
|
| 747 |
+
"step": 420
|
| 748 |
+
},
|
| 749 |
+
{
|
| 750 |
+
"epoch": 54.97,
|
| 751 |
+
"eval_accuracy": 0.8,
|
| 752 |
+
"eval_loss": 0.934796154499054,
|
| 753 |
+
"eval_runtime": 1.0691,
|
| 754 |
+
"eval_samples_per_second": 56.12,
|
| 755 |
+
"eval_steps_per_second": 1.871,
|
| 756 |
+
"step": 426
|
| 757 |
+
},
|
| 758 |
+
{
|
| 759 |
+
"epoch": 55.48,
|
| 760 |
+
"learning_rate": 2.0300751879699247e-05,
|
| 761 |
+
"loss": 0.0524,
|
| 762 |
+
"step": 430
|
| 763 |
+
},
|
| 764 |
+
{
|
| 765 |
+
"epoch": 56.0,
|
| 766 |
+
"eval_accuracy": 0.8166666666666667,
|
| 767 |
+
"eval_loss": 0.8216551542282104,
|
| 768 |
+
"eval_runtime": 0.9842,
|
| 769 |
+
"eval_samples_per_second": 60.966,
|
| 770 |
+
"eval_steps_per_second": 2.032,
|
| 771 |
+
"step": 434
|
| 772 |
+
},
|
| 773 |
+
{
|
| 774 |
+
"epoch": 56.77,
|
| 775 |
+
"learning_rate": 1.954887218045113e-05,
|
| 776 |
+
"loss": 0.0479,
|
| 777 |
+
"step": 440
|
| 778 |
+
},
|
| 779 |
+
{
|
| 780 |
+
"epoch": 56.9,
|
| 781 |
+
"eval_accuracy": 0.8166666666666667,
|
| 782 |
+
"eval_loss": 0.758594810962677,
|
| 783 |
+
"eval_runtime": 1.0267,
|
| 784 |
+
"eval_samples_per_second": 58.439,
|
| 785 |
+
"eval_steps_per_second": 1.948,
|
| 786 |
+
"step": 441
|
| 787 |
+
},
|
| 788 |
+
{
|
| 789 |
+
"epoch": 57.94,
|
| 790 |
+
"eval_accuracy": 0.8,
|
| 791 |
+
"eval_loss": 0.8146753311157227,
|
| 792 |
+
"eval_runtime": 0.965,
|
| 793 |
+
"eval_samples_per_second": 62.179,
|
| 794 |
+
"eval_steps_per_second": 2.073,
|
| 795 |
+
"step": 449
|
| 796 |
+
},
|
| 797 |
+
{
|
| 798 |
+
"epoch": 58.06,
|
| 799 |
+
"learning_rate": 1.8796992481203007e-05,
|
| 800 |
+
"loss": 0.0595,
|
| 801 |
+
"step": 450
|
| 802 |
+
},
|
| 803 |
+
{
|
| 804 |
+
"epoch": 58.97,
|
| 805 |
+
"eval_accuracy": 0.7833333333333333,
|
| 806 |
+
"eval_loss": 0.9999889135360718,
|
| 807 |
+
"eval_runtime": 1.0193,
|
| 808 |
+
"eval_samples_per_second": 58.862,
|
| 809 |
+
"eval_steps_per_second": 1.962,
|
| 810 |
+
"step": 457
|
| 811 |
+
},
|
| 812 |
+
{
|
| 813 |
+
"epoch": 59.35,
|
| 814 |
+
"learning_rate": 1.8045112781954888e-05,
|
| 815 |
+
"loss": 0.0475,
|
| 816 |
+
"step": 460
|
| 817 |
+
},
|
| 818 |
+
{
|
| 819 |
+
"epoch": 60.0,
|
| 820 |
+
"eval_accuracy": 0.7833333333333333,
|
| 821 |
+
"eval_loss": 0.9291054010391235,
|
| 822 |
+
"eval_runtime": 0.9846,
|
| 823 |
+
"eval_samples_per_second": 60.941,
|
| 824 |
+
"eval_steps_per_second": 2.031,
|
| 825 |
+
"step": 465
|
| 826 |
+
},
|
| 827 |
+
{
|
| 828 |
+
"epoch": 60.65,
|
| 829 |
+
"learning_rate": 1.7293233082706766e-05,
|
| 830 |
+
"loss": 0.049,
|
| 831 |
+
"step": 470
|
| 832 |
+
},
|
| 833 |
+
{
|
| 834 |
+
"epoch": 60.9,
|
| 835 |
+
"eval_accuracy": 0.7833333333333333,
|
| 836 |
+
"eval_loss": 0.9588444828987122,
|
| 837 |
+
"eval_runtime": 1.0072,
|
| 838 |
+
"eval_samples_per_second": 59.57,
|
| 839 |
+
"eval_steps_per_second": 1.986,
|
| 840 |
+
"step": 472
|
| 841 |
+
},
|
| 842 |
+
{
|
| 843 |
+
"epoch": 61.94,
|
| 844 |
+
"learning_rate": 1.6541353383458648e-05,
|
| 845 |
+
"loss": 0.0398,
|
| 846 |
+
"step": 480
|
| 847 |
+
},
|
| 848 |
+
{
|
| 849 |
+
"epoch": 61.94,
|
| 850 |
+
"eval_accuracy": 0.8,
|
| 851 |
+
"eval_loss": 0.9500763416290283,
|
| 852 |
+
"eval_runtime": 1.1967,
|
| 853 |
+
"eval_samples_per_second": 50.137,
|
| 854 |
+
"eval_steps_per_second": 1.671,
|
| 855 |
+
"step": 480
|
| 856 |
+
},
|
| 857 |
+
{
|
| 858 |
+
"epoch": 62.97,
|
| 859 |
+
"eval_accuracy": 0.8,
|
| 860 |
+
"eval_loss": 0.9498623013496399,
|
| 861 |
+
"eval_runtime": 1.0197,
|
| 862 |
+
"eval_samples_per_second": 58.839,
|
| 863 |
+
"eval_steps_per_second": 1.961,
|
| 864 |
+
"step": 488
|
| 865 |
+
},
|
| 866 |
+
{
|
| 867 |
+
"epoch": 63.23,
|
| 868 |
+
"learning_rate": 1.5789473684210526e-05,
|
| 869 |
+
"loss": 0.0496,
|
| 870 |
+
"step": 490
|
| 871 |
+
},
|
| 872 |
+
{
|
| 873 |
+
"epoch": 64.0,
|
| 874 |
+
"eval_accuracy": 0.8,
|
| 875 |
+
"eval_loss": 0.9279070496559143,
|
| 876 |
+
"eval_runtime": 1.006,
|
| 877 |
+
"eval_samples_per_second": 59.643,
|
| 878 |
+
"eval_steps_per_second": 1.988,
|
| 879 |
+
"step": 496
|
| 880 |
+
},
|
| 881 |
+
{
|
| 882 |
+
"epoch": 64.52,
|
| 883 |
+
"learning_rate": 1.5037593984962406e-05,
|
| 884 |
+
"loss": 0.0354,
|
| 885 |
+
"step": 500
|
| 886 |
+
},
|
| 887 |
+
{
|
| 888 |
+
"epoch": 64.9,
|
| 889 |
+
"eval_accuracy": 0.75,
|
| 890 |
+
"eval_loss": 0.9677076935768127,
|
| 891 |
+
"eval_runtime": 0.9989,
|
| 892 |
+
"eval_samples_per_second": 60.065,
|
| 893 |
+
"eval_steps_per_second": 2.002,
|
| 894 |
+
"step": 503
|
| 895 |
+
},
|
| 896 |
+
{
|
| 897 |
+
"epoch": 65.81,
|
| 898 |
+
"learning_rate": 1.4285714285714285e-05,
|
| 899 |
+
"loss": 0.0325,
|
| 900 |
+
"step": 510
|
| 901 |
+
},
|
| 902 |
+
{
|
| 903 |
+
"epoch": 65.94,
|
| 904 |
+
"eval_accuracy": 0.8333333333333334,
|
| 905 |
+
"eval_loss": 0.8371397852897644,
|
| 906 |
+
"eval_runtime": 0.9656,
|
| 907 |
+
"eval_samples_per_second": 62.134,
|
| 908 |
+
"eval_steps_per_second": 2.071,
|
| 909 |
+
"step": 511
|
| 910 |
+
},
|
| 911 |
+
{
|
| 912 |
+
"epoch": 66.97,
|
| 913 |
+
"eval_accuracy": 0.8,
|
| 914 |
+
"eval_loss": 0.9682708978652954,
|
| 915 |
+
"eval_runtime": 0.956,
|
| 916 |
+
"eval_samples_per_second": 62.76,
|
| 917 |
+
"eval_steps_per_second": 2.092,
|
| 918 |
+
"step": 519
|
| 919 |
+
},
|
| 920 |
+
{
|
| 921 |
+
"epoch": 67.1,
|
| 922 |
+
"learning_rate": 1.3533834586466165e-05,
|
| 923 |
+
"loss": 0.0335,
|
| 924 |
+
"step": 520
|
| 925 |
+
},
|
| 926 |
+
{
|
| 927 |
+
"epoch": 68.0,
|
| 928 |
+
"eval_accuracy": 0.7833333333333333,
|
| 929 |
+
"eval_loss": 1.0455142259597778,
|
| 930 |
+
"eval_runtime": 0.9995,
|
| 931 |
+
"eval_samples_per_second": 60.033,
|
| 932 |
+
"eval_steps_per_second": 2.001,
|
| 933 |
+
"step": 527
|
| 934 |
+
},
|
| 935 |
+
{
|
| 936 |
+
"epoch": 68.39,
|
| 937 |
+
"learning_rate": 1.2781954887218045e-05,
|
| 938 |
+
"loss": 0.0375,
|
| 939 |
+
"step": 530
|
| 940 |
+
},
|
| 941 |
+
{
|
| 942 |
+
"epoch": 68.9,
|
| 943 |
+
"eval_accuracy": 0.8166666666666667,
|
| 944 |
+
"eval_loss": 0.9026990532875061,
|
| 945 |
+
"eval_runtime": 1.016,
|
| 946 |
+
"eval_samples_per_second": 59.058,
|
| 947 |
+
"eval_steps_per_second": 1.969,
|
| 948 |
+
"step": 534
|
| 949 |
+
},
|
| 950 |
+
{
|
| 951 |
+
"epoch": 69.68,
|
| 952 |
+
"learning_rate": 1.2030075187969925e-05,
|
| 953 |
+
"loss": 0.0424,
|
| 954 |
+
"step": 540
|
| 955 |
+
},
|
| 956 |
+
{
|
| 957 |
+
"epoch": 69.94,
|
| 958 |
+
"eval_accuracy": 0.85,
|
| 959 |
+
"eval_loss": 0.8043019771575928,
|
| 960 |
+
"eval_runtime": 0.9715,
|
| 961 |
+
"eval_samples_per_second": 61.76,
|
| 962 |
+
"eval_steps_per_second": 2.059,
|
| 963 |
+
"step": 542
|
| 964 |
+
},
|
| 965 |
+
{
|
| 966 |
+
"epoch": 70.97,
|
| 967 |
+
"learning_rate": 1.1278195488721805e-05,
|
| 968 |
+
"loss": 0.0383,
|
| 969 |
+
"step": 550
|
| 970 |
+
},
|
| 971 |
+
{
|
| 972 |
+
"epoch": 70.97,
|
| 973 |
+
"eval_accuracy": 0.7833333333333333,
|
| 974 |
+
"eval_loss": 0.9034760594367981,
|
| 975 |
+
"eval_runtime": 0.9985,
|
| 976 |
+
"eval_samples_per_second": 60.088,
|
| 977 |
+
"eval_steps_per_second": 2.003,
|
| 978 |
+
"step": 550
|
| 979 |
+
},
|
| 980 |
+
{
|
| 981 |
+
"epoch": 72.0,
|
| 982 |
+
"eval_accuracy": 0.7833333333333333,
|
| 983 |
+
"eval_loss": 0.9360395073890686,
|
| 984 |
+
"eval_runtime": 1.0923,
|
| 985 |
+
"eval_samples_per_second": 54.931,
|
| 986 |
+
"eval_steps_per_second": 1.831,
|
| 987 |
+
"step": 558
|
| 988 |
+
},
|
| 989 |
+
{
|
| 990 |
+
"epoch": 72.26,
|
| 991 |
+
"learning_rate": 1.0526315789473684e-05,
|
| 992 |
+
"loss": 0.0295,
|
| 993 |
+
"step": 560
|
| 994 |
+
},
|
| 995 |
+
{
|
| 996 |
+
"epoch": 72.9,
|
| 997 |
+
"eval_accuracy": 0.7833333333333333,
|
| 998 |
+
"eval_loss": 0.9840652346611023,
|
| 999 |
+
"eval_runtime": 1.1084,
|
| 1000 |
+
"eval_samples_per_second": 54.132,
|
| 1001 |
+
"eval_steps_per_second": 1.804,
|
| 1002 |
+
"step": 565
|
| 1003 |
+
},
|
| 1004 |
+
{
|
| 1005 |
+
"epoch": 73.55,
|
| 1006 |
+
"learning_rate": 9.774436090225564e-06,
|
| 1007 |
+
"loss": 0.0307,
|
| 1008 |
+
"step": 570
|
| 1009 |
+
},
|
| 1010 |
+
{
|
| 1011 |
+
"epoch": 73.94,
|
| 1012 |
+
"eval_accuracy": 0.8,
|
| 1013 |
+
"eval_loss": 0.9300164580345154,
|
| 1014 |
+
"eval_runtime": 1.152,
|
| 1015 |
+
"eval_samples_per_second": 52.082,
|
| 1016 |
+
"eval_steps_per_second": 1.736,
|
| 1017 |
+
"step": 573
|
| 1018 |
+
},
|
| 1019 |
+
{
|
| 1020 |
+
"epoch": 74.84,
|
| 1021 |
+
"learning_rate": 9.022556390977444e-06,
|
| 1022 |
+
"loss": 0.0376,
|
| 1023 |
+
"step": 580
|
| 1024 |
+
},
|
| 1025 |
+
{
|
| 1026 |
+
"epoch": 74.97,
|
| 1027 |
+
"eval_accuracy": 0.7833333333333333,
|
| 1028 |
+
"eval_loss": 0.9629533290863037,
|
| 1029 |
+
"eval_runtime": 1.3504,
|
| 1030 |
+
"eval_samples_per_second": 44.432,
|
| 1031 |
+
"eval_steps_per_second": 1.481,
|
| 1032 |
+
"step": 581
|
| 1033 |
+
},
|
| 1034 |
+
{
|
| 1035 |
+
"epoch": 76.0,
|
| 1036 |
+
"eval_accuracy": 0.7833333333333333,
|
| 1037 |
+
"eval_loss": 0.977742612361908,
|
| 1038 |
+
"eval_runtime": 1.044,
|
| 1039 |
+
"eval_samples_per_second": 57.469,
|
| 1040 |
+
"eval_steps_per_second": 1.916,
|
| 1041 |
+
"step": 589
|
| 1042 |
+
},
|
| 1043 |
+
{
|
| 1044 |
+
"epoch": 76.13,
|
| 1045 |
+
"learning_rate": 8.270676691729324e-06,
|
| 1046 |
+
"loss": 0.0259,
|
| 1047 |
+
"step": 590
|
| 1048 |
+
},
|
| 1049 |
+
{
|
| 1050 |
+
"epoch": 76.9,
|
| 1051 |
+
"eval_accuracy": 0.8,
|
| 1052 |
+
"eval_loss": 0.9322593808174133,
|
| 1053 |
+
"eval_runtime": 1.0858,
|
| 1054 |
+
"eval_samples_per_second": 55.256,
|
| 1055 |
+
"eval_steps_per_second": 1.842,
|
| 1056 |
+
"step": 596
|
| 1057 |
+
},
|
| 1058 |
+
{
|
| 1059 |
+
"epoch": 77.42,
|
| 1060 |
+
"learning_rate": 7.518796992481203e-06,
|
| 1061 |
+
"loss": 0.0345,
|
| 1062 |
+
"step": 600
|
| 1063 |
+
},
|
| 1064 |
+
{
|
| 1065 |
+
"epoch": 77.94,
|
| 1066 |
+
"eval_accuracy": 0.8,
|
| 1067 |
+
"eval_loss": 0.9075172543525696,
|
| 1068 |
+
"eval_runtime": 1.1281,
|
| 1069 |
+
"eval_samples_per_second": 53.185,
|
| 1070 |
+
"eval_steps_per_second": 1.773,
|
| 1071 |
+
"step": 604
|
| 1072 |
+
},
|
| 1073 |
+
{
|
| 1074 |
+
"epoch": 78.71,
|
| 1075 |
+
"learning_rate": 6.766917293233083e-06,
|
| 1076 |
+
"loss": 0.0346,
|
| 1077 |
+
"step": 610
|
| 1078 |
+
},
|
| 1079 |
+
{
|
| 1080 |
+
"epoch": 78.97,
|
| 1081 |
+
"eval_accuracy": 0.8,
|
| 1082 |
+
"eval_loss": 0.8950561881065369,
|
| 1083 |
+
"eval_runtime": 0.9932,
|
| 1084 |
+
"eval_samples_per_second": 60.412,
|
| 1085 |
+
"eval_steps_per_second": 2.014,
|
| 1086 |
+
"step": 612
|
| 1087 |
+
},
|
| 1088 |
+
{
|
| 1089 |
+
"epoch": 80.0,
|
| 1090 |
+
"learning_rate": 6.015037593984962e-06,
|
| 1091 |
+
"loss": 0.0319,
|
| 1092 |
+
"step": 620
|
| 1093 |
+
},
|
| 1094 |
+
{
|
| 1095 |
+
"epoch": 80.0,
|
| 1096 |
+
"eval_accuracy": 0.8,
|
| 1097 |
+
"eval_loss": 0.9676039814949036,
|
| 1098 |
+
"eval_runtime": 0.9844,
|
| 1099 |
+
"eval_samples_per_second": 60.95,
|
| 1100 |
+
"eval_steps_per_second": 2.032,
|
| 1101 |
+
"step": 620
|
| 1102 |
+
},
|
| 1103 |
+
{
|
| 1104 |
+
"epoch": 80.9,
|
| 1105 |
+
"eval_accuracy": 0.8,
|
| 1106 |
+
"eval_loss": 0.988412618637085,
|
| 1107 |
+
"eval_runtime": 0.9973,
|
| 1108 |
+
"eval_samples_per_second": 60.161,
|
| 1109 |
+
"eval_steps_per_second": 2.005,
|
| 1110 |
+
"step": 627
|
| 1111 |
+
},
|
| 1112 |
+
{
|
| 1113 |
+
"epoch": 81.29,
|
| 1114 |
+
"learning_rate": 5.263157894736842e-06,
|
| 1115 |
+
"loss": 0.0226,
|
| 1116 |
+
"step": 630
|
| 1117 |
+
},
|
| 1118 |
+
{
|
| 1119 |
+
"epoch": 81.94,
|
| 1120 |
+
"eval_accuracy": 0.7833333333333333,
|
| 1121 |
+
"eval_loss": 0.9850680232048035,
|
| 1122 |
+
"eval_runtime": 1.0518,
|
| 1123 |
+
"eval_samples_per_second": 57.046,
|
| 1124 |
+
"eval_steps_per_second": 1.902,
|
| 1125 |
+
"step": 635
|
| 1126 |
+
},
|
| 1127 |
+
{
|
| 1128 |
+
"epoch": 82.58,
|
| 1129 |
+
"learning_rate": 4.511278195488722e-06,
|
| 1130 |
+
"loss": 0.033,
|
| 1131 |
+
"step": 640
|
| 1132 |
+
},
|
| 1133 |
+
{
|
| 1134 |
+
"epoch": 82.97,
|
| 1135 |
+
"eval_accuracy": 0.7833333333333333,
|
| 1136 |
+
"eval_loss": 0.9710198640823364,
|
| 1137 |
+
"eval_runtime": 1.0106,
|
| 1138 |
+
"eval_samples_per_second": 59.371,
|
| 1139 |
+
"eval_steps_per_second": 1.979,
|
| 1140 |
+
"step": 643
|
| 1141 |
+
},
|
| 1142 |
+
{
|
| 1143 |
+
"epoch": 83.87,
|
| 1144 |
+
"learning_rate": 3.7593984962406014e-06,
|
| 1145 |
+
"loss": 0.0262,
|
| 1146 |
+
"step": 650
|
| 1147 |
+
},
|
| 1148 |
+
{
|
| 1149 |
+
"epoch": 84.0,
|
| 1150 |
+
"eval_accuracy": 0.7833333333333333,
|
| 1151 |
+
"eval_loss": 0.985089123249054,
|
| 1152 |
+
"eval_runtime": 1.0015,
|
| 1153 |
+
"eval_samples_per_second": 59.912,
|
| 1154 |
+
"eval_steps_per_second": 1.997,
|
| 1155 |
+
"step": 651
|
| 1156 |
+
},
|
| 1157 |
+
{
|
| 1158 |
+
"epoch": 84.9,
|
| 1159 |
+
"eval_accuracy": 0.7833333333333333,
|
| 1160 |
+
"eval_loss": 0.9868298172950745,
|
| 1161 |
+
"eval_runtime": 1.0224,
|
| 1162 |
+
"eval_samples_per_second": 58.683,
|
| 1163 |
+
"eval_steps_per_second": 1.956,
|
| 1164 |
+
"step": 658
|
| 1165 |
+
},
|
| 1166 |
+
{
|
| 1167 |
+
"epoch": 85.16,
|
| 1168 |
+
"learning_rate": 3.007518796992481e-06,
|
| 1169 |
+
"loss": 0.0345,
|
| 1170 |
+
"step": 660
|
| 1171 |
+
},
|
| 1172 |
+
{
|
| 1173 |
+
"epoch": 85.94,
|
| 1174 |
+
"eval_accuracy": 0.7833333333333333,
|
| 1175 |
+
"eval_loss": 0.9702271819114685,
|
| 1176 |
+
"eval_runtime": 1.0333,
|
| 1177 |
+
"eval_samples_per_second": 58.065,
|
| 1178 |
+
"eval_steps_per_second": 1.936,
|
| 1179 |
+
"step": 666
|
| 1180 |
+
},
|
| 1181 |
+
{
|
| 1182 |
+
"epoch": 86.45,
|
| 1183 |
+
"learning_rate": 2.255639097744361e-06,
|
| 1184 |
+
"loss": 0.0299,
|
| 1185 |
+
"step": 670
|
| 1186 |
+
},
|
| 1187 |
+
{
|
| 1188 |
+
"epoch": 86.97,
|
| 1189 |
+
"eval_accuracy": 0.7833333333333333,
|
| 1190 |
+
"eval_loss": 0.9888620376586914,
|
| 1191 |
+
"eval_runtime": 0.9649,
|
| 1192 |
+
"eval_samples_per_second": 62.184,
|
| 1193 |
+
"eval_steps_per_second": 2.073,
|
| 1194 |
+
"step": 674
|
| 1195 |
+
},
|
| 1196 |
+
{
|
| 1197 |
+
"epoch": 87.74,
|
| 1198 |
+
"learning_rate": 1.5037593984962406e-06,
|
| 1199 |
+
"loss": 0.0347,
|
| 1200 |
+
"step": 680
|
| 1201 |
+
},
|
| 1202 |
+
{
|
| 1203 |
+
"epoch": 88.0,
|
| 1204 |
+
"eval_accuracy": 0.7833333333333333,
|
| 1205 |
+
"eval_loss": 1.000300645828247,
|
| 1206 |
+
"eval_runtime": 1.0185,
|
| 1207 |
+
"eval_samples_per_second": 58.91,
|
| 1208 |
+
"eval_steps_per_second": 1.964,
|
| 1209 |
+
"step": 682
|
| 1210 |
+
},
|
| 1211 |
+
{
|
| 1212 |
+
"epoch": 88.9,
|
| 1213 |
+
"eval_accuracy": 0.7833333333333333,
|
| 1214 |
+
"eval_loss": 0.9913238286972046,
|
| 1215 |
+
"eval_runtime": 1.0979,
|
| 1216 |
+
"eval_samples_per_second": 54.647,
|
| 1217 |
+
"eval_steps_per_second": 1.822,
|
| 1218 |
+
"step": 689
|
| 1219 |
+
},
|
| 1220 |
+
{
|
| 1221 |
+
"epoch": 89.03,
|
| 1222 |
+
"learning_rate": 7.518796992481203e-07,
|
| 1223 |
+
"loss": 0.0288,
|
| 1224 |
+
"step": 690
|
| 1225 |
+
},
|
| 1226 |
+
{
|
| 1227 |
+
"epoch": 89.94,
|
| 1228 |
+
"eval_accuracy": 0.7833333333333333,
|
| 1229 |
+
"eval_loss": 0.9858866333961487,
|
| 1230 |
+
"eval_runtime": 1.063,
|
| 1231 |
+
"eval_samples_per_second": 56.445,
|
| 1232 |
+
"eval_steps_per_second": 1.882,
|
| 1233 |
+
"step": 697
|
| 1234 |
+
},
|
| 1235 |
+
{
|
| 1236 |
+
"epoch": 90.32,
|
| 1237 |
+
"learning_rate": 0.0,
|
| 1238 |
+
"loss": 0.0198,
|
| 1239 |
+
"step": 700
|
| 1240 |
+
},
|
| 1241 |
+
{
|
| 1242 |
+
"epoch": 90.32,
|
| 1243 |
+
"eval_accuracy": 0.7833333333333333,
|
| 1244 |
+
"eval_loss": 0.9857978820800781,
|
| 1245 |
+
"eval_runtime": 1.01,
|
| 1246 |
+
"eval_samples_per_second": 59.406,
|
| 1247 |
+
"eval_steps_per_second": 1.98,
|
| 1248 |
+
"step": 700
|
| 1249 |
+
},
|
| 1250 |
+
{
|
| 1251 |
+
"epoch": 90.32,
|
| 1252 |
+
"step": 700,
|
| 1253 |
+
"total_flos": 6.817867456880148e+18,
|
| 1254 |
+
"train_loss": 0.19939448043704033,
|
| 1255 |
+
"train_runtime": 1530.1698,
|
| 1256 |
+
"train_samples_per_second": 63.653,
|
| 1257 |
+
"train_steps_per_second": 0.457
|
| 1258 |
+
}
|
| 1259 |
+
],
|
| 1260 |
+
"logging_steps": 10,
|
| 1261 |
+
"max_steps": 700,
|
| 1262 |
+
"num_input_tokens_seen": 0,
|
| 1263 |
+
"num_train_epochs": 100,
|
| 1264 |
+
"save_steps": 500,
|
| 1265 |
+
"total_flos": 6.817867456880148e+18,
|
| 1266 |
+
"train_batch_size": 32,
|
| 1267 |
+
"trial_name": null,
|
| 1268 |
+
"trial_params": null
|
| 1269 |
+
}
|