🍻 cheers
Browse files- README.md +2 -1
- all_results.json +13 -0
- eval_results.json +8 -0
- runs/Aug22_09-03-46_e6ee7653b19d/events.out.tfevents.1724318953.e6ee7653b19d.364.2 +3 -0
- train_results.json +8 -0
- trainer_state.json +1090 -0
README.md
CHANGED
|
@@ -2,6 +2,7 @@
|
|
| 2 |
license: apache-2.0
|
| 3 |
base_model: google/vit-base-patch16-224-in21k
|
| 4 |
tags:
|
|
|
|
| 5 |
- generated_from_trainer
|
| 6 |
metrics:
|
| 7 |
- accuracy
|
|
@@ -15,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 15 |
|
| 16 |
# finetuned-indian-food
|
| 17 |
|
| 18 |
-
This model is a fine-tuned version of [google/vit-base-patch16-224-in21k](https://huggingface.co/google/vit-base-patch16-224-in21k) on
|
| 19 |
It achieves the following results on the evaluation set:
|
| 20 |
- Loss: 0.2867
|
| 21 |
- Accuracy: 0.9267
|
|
|
|
| 2 |
license: apache-2.0
|
| 3 |
base_model: google/vit-base-patch16-224-in21k
|
| 4 |
tags:
|
| 5 |
+
- image-classification
|
| 6 |
- generated_from_trainer
|
| 7 |
metrics:
|
| 8 |
- accuracy
|
|
|
|
| 16 |
|
| 17 |
# finetuned-indian-food
|
| 18 |
|
| 19 |
+
This model is a fine-tuned version of [google/vit-base-patch16-224-in21k](https://huggingface.co/google/vit-base-patch16-224-in21k) on the indian_food_images dataset.
|
| 20 |
It achieves the following results on the evaluation set:
|
| 21 |
- Loss: 0.2867
|
| 22 |
- Accuracy: 0.9267
|
all_results.json
ADDED
|
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 4.0,
|
| 3 |
+
"eval_accuracy": 0.926673751328374,
|
| 4 |
+
"eval_loss": 0.2866949737071991,
|
| 5 |
+
"eval_runtime": 29.1659,
|
| 6 |
+
"eval_samples_per_second": 32.264,
|
| 7 |
+
"eval_steps_per_second": 4.046,
|
| 8 |
+
"total_flos": 1.651775717862015e+18,
|
| 9 |
+
"train_loss": 0.46514646391252856,
|
| 10 |
+
"train_runtime": 1194.1419,
|
| 11 |
+
"train_samples_per_second": 17.847,
|
| 12 |
+
"train_steps_per_second": 1.115
|
| 13 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 4.0,
|
| 3 |
+
"eval_accuracy": 0.926673751328374,
|
| 4 |
+
"eval_loss": 0.2866949737071991,
|
| 5 |
+
"eval_runtime": 29.1659,
|
| 6 |
+
"eval_samples_per_second": 32.264,
|
| 7 |
+
"eval_steps_per_second": 4.046
|
| 8 |
+
}
|
runs/Aug22_09-03-46_e6ee7653b19d/events.out.tfevents.1724318953.e6ee7653b19d.364.2
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a801c49ed95b57c06116f8d35b1023cb5c017b03af45c2d19c5f3f3c6bb0018c
|
| 3 |
+
size 411
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 4.0,
|
| 3 |
+
"total_flos": 1.651775717862015e+18,
|
| 4 |
+
"train_loss": 0.46514646391252856,
|
| 5 |
+
"train_runtime": 1194.1419,
|
| 6 |
+
"train_samples_per_second": 17.847,
|
| 7 |
+
"train_steps_per_second": 1.115
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,1090 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.2866949737071991,
|
| 3 |
+
"best_model_checkpoint": "finetuned-indian-food/checkpoint-1300",
|
| 4 |
+
"epoch": 4.0,
|
| 5 |
+
"eval_steps": 100,
|
| 6 |
+
"global_step": 1332,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.03003003003003003,
|
| 13 |
+
"grad_norm": 2.0226473808288574,
|
| 14 |
+
"learning_rate": 0.0001984984984984985,
|
| 15 |
+
"loss": 2.8635,
|
| 16 |
+
"step": 10
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.06006006006006006,
|
| 20 |
+
"grad_norm": 1.8129218816757202,
|
| 21 |
+
"learning_rate": 0.00019699699699699701,
|
| 22 |
+
"loss": 2.5393,
|
| 23 |
+
"step": 20
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.09009009009009009,
|
| 27 |
+
"grad_norm": 1.946191668510437,
|
| 28 |
+
"learning_rate": 0.0001954954954954955,
|
| 29 |
+
"loss": 2.2093,
|
| 30 |
+
"step": 30
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.12012012012012012,
|
| 34 |
+
"grad_norm": 2.3910531997680664,
|
| 35 |
+
"learning_rate": 0.00019399399399399402,
|
| 36 |
+
"loss": 1.8851,
|
| 37 |
+
"step": 40
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.15015015015015015,
|
| 41 |
+
"grad_norm": 2.2553648948669434,
|
| 42 |
+
"learning_rate": 0.0001924924924924925,
|
| 43 |
+
"loss": 1.6156,
|
| 44 |
+
"step": 50
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.18018018018018017,
|
| 48 |
+
"grad_norm": 2.605876922607422,
|
| 49 |
+
"learning_rate": 0.000190990990990991,
|
| 50 |
+
"loss": 1.4386,
|
| 51 |
+
"step": 60
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.21021021021021022,
|
| 55 |
+
"grad_norm": 3.005312919616699,
|
| 56 |
+
"learning_rate": 0.0001894894894894895,
|
| 57 |
+
"loss": 1.3945,
|
| 58 |
+
"step": 70
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.24024024024024024,
|
| 62 |
+
"grad_norm": 2.530965805053711,
|
| 63 |
+
"learning_rate": 0.000187987987987988,
|
| 64 |
+
"loss": 1.1486,
|
| 65 |
+
"step": 80
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.2702702702702703,
|
| 69 |
+
"grad_norm": 4.0471720695495605,
|
| 70 |
+
"learning_rate": 0.0001864864864864865,
|
| 71 |
+
"loss": 1.1218,
|
| 72 |
+
"step": 90
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.3003003003003003,
|
| 76 |
+
"grad_norm": 2.0968387126922607,
|
| 77 |
+
"learning_rate": 0.000184984984984985,
|
| 78 |
+
"loss": 1.0192,
|
| 79 |
+
"step": 100
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.3003003003003003,
|
| 83 |
+
"eval_accuracy": 0.8480340063761955,
|
| 84 |
+
"eval_loss": 0.9247535467147827,
|
| 85 |
+
"eval_runtime": 29.0203,
|
| 86 |
+
"eval_samples_per_second": 32.426,
|
| 87 |
+
"eval_steps_per_second": 4.066,
|
| 88 |
+
"step": 100
|
| 89 |
+
},
|
| 90 |
+
{
|
| 91 |
+
"epoch": 0.3303303303303303,
|
| 92 |
+
"grad_norm": 3.351391315460205,
|
| 93 |
+
"learning_rate": 0.0001834834834834835,
|
| 94 |
+
"loss": 0.9933,
|
| 95 |
+
"step": 110
|
| 96 |
+
},
|
| 97 |
+
{
|
| 98 |
+
"epoch": 0.36036036036036034,
|
| 99 |
+
"grad_norm": 3.367605686187744,
|
| 100 |
+
"learning_rate": 0.000181981981981982,
|
| 101 |
+
"loss": 1.0123,
|
| 102 |
+
"step": 120
|
| 103 |
+
},
|
| 104 |
+
{
|
| 105 |
+
"epoch": 0.39039039039039036,
|
| 106 |
+
"grad_norm": 2.310729742050171,
|
| 107 |
+
"learning_rate": 0.0001804804804804805,
|
| 108 |
+
"loss": 0.9198,
|
| 109 |
+
"step": 130
|
| 110 |
+
},
|
| 111 |
+
{
|
| 112 |
+
"epoch": 0.42042042042042044,
|
| 113 |
+
"grad_norm": 5.448969841003418,
|
| 114 |
+
"learning_rate": 0.00017897897897897898,
|
| 115 |
+
"loss": 0.818,
|
| 116 |
+
"step": 140
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"epoch": 0.45045045045045046,
|
| 120 |
+
"grad_norm": 3.953378200531006,
|
| 121 |
+
"learning_rate": 0.0001774774774774775,
|
| 122 |
+
"loss": 0.8839,
|
| 123 |
+
"step": 150
|
| 124 |
+
},
|
| 125 |
+
{
|
| 126 |
+
"epoch": 0.4804804804804805,
|
| 127 |
+
"grad_norm": 4.24240779876709,
|
| 128 |
+
"learning_rate": 0.000175975975975976,
|
| 129 |
+
"loss": 0.8652,
|
| 130 |
+
"step": 160
|
| 131 |
+
},
|
| 132 |
+
{
|
| 133 |
+
"epoch": 0.5105105105105106,
|
| 134 |
+
"grad_norm": 3.4866714477539062,
|
| 135 |
+
"learning_rate": 0.0001744744744744745,
|
| 136 |
+
"loss": 0.7593,
|
| 137 |
+
"step": 170
|
| 138 |
+
},
|
| 139 |
+
{
|
| 140 |
+
"epoch": 0.5405405405405406,
|
| 141 |
+
"grad_norm": 2.6095967292785645,
|
| 142 |
+
"learning_rate": 0.000172972972972973,
|
| 143 |
+
"loss": 0.6274,
|
| 144 |
+
"step": 180
|
| 145 |
+
},
|
| 146 |
+
{
|
| 147 |
+
"epoch": 0.5705705705705706,
|
| 148 |
+
"grad_norm": 2.582280397415161,
|
| 149 |
+
"learning_rate": 0.00017147147147147148,
|
| 150 |
+
"loss": 0.6867,
|
| 151 |
+
"step": 190
|
| 152 |
+
},
|
| 153 |
+
{
|
| 154 |
+
"epoch": 0.6006006006006006,
|
| 155 |
+
"grad_norm": 3.176654577255249,
|
| 156 |
+
"learning_rate": 0.00016996996996997,
|
| 157 |
+
"loss": 0.635,
|
| 158 |
+
"step": 200
|
| 159 |
+
},
|
| 160 |
+
{
|
| 161 |
+
"epoch": 0.6006006006006006,
|
| 162 |
+
"eval_accuracy": 0.8862911795961743,
|
| 163 |
+
"eval_loss": 0.5916650891304016,
|
| 164 |
+
"eval_runtime": 29.2674,
|
| 165 |
+
"eval_samples_per_second": 32.152,
|
| 166 |
+
"eval_steps_per_second": 4.032,
|
| 167 |
+
"step": 200
|
| 168 |
+
},
|
| 169 |
+
{
|
| 170 |
+
"epoch": 0.6306306306306306,
|
| 171 |
+
"grad_norm": 6.385357856750488,
|
| 172 |
+
"learning_rate": 0.00016846846846846846,
|
| 173 |
+
"loss": 0.715,
|
| 174 |
+
"step": 210
|
| 175 |
+
},
|
| 176 |
+
{
|
| 177 |
+
"epoch": 0.6606606606606606,
|
| 178 |
+
"grad_norm": 2.321627378463745,
|
| 179 |
+
"learning_rate": 0.00016696696696696697,
|
| 180 |
+
"loss": 0.6047,
|
| 181 |
+
"step": 220
|
| 182 |
+
},
|
| 183 |
+
{
|
| 184 |
+
"epoch": 0.6906906906906907,
|
| 185 |
+
"grad_norm": 3.8409202098846436,
|
| 186 |
+
"learning_rate": 0.00016546546546546546,
|
| 187 |
+
"loss": 0.7312,
|
| 188 |
+
"step": 230
|
| 189 |
+
},
|
| 190 |
+
{
|
| 191 |
+
"epoch": 0.7207207207207207,
|
| 192 |
+
"grad_norm": 4.827725887298584,
|
| 193 |
+
"learning_rate": 0.00016396396396396395,
|
| 194 |
+
"loss": 0.6743,
|
| 195 |
+
"step": 240
|
| 196 |
+
},
|
| 197 |
+
{
|
| 198 |
+
"epoch": 0.7507507507507507,
|
| 199 |
+
"grad_norm": 3.8321993350982666,
|
| 200 |
+
"learning_rate": 0.00016246246246246247,
|
| 201 |
+
"loss": 0.779,
|
| 202 |
+
"step": 250
|
| 203 |
+
},
|
| 204 |
+
{
|
| 205 |
+
"epoch": 0.7807807807807807,
|
| 206 |
+
"grad_norm": 5.7290167808532715,
|
| 207 |
+
"learning_rate": 0.00016096096096096096,
|
| 208 |
+
"loss": 0.7208,
|
| 209 |
+
"step": 260
|
| 210 |
+
},
|
| 211 |
+
{
|
| 212 |
+
"epoch": 0.8108108108108109,
|
| 213 |
+
"grad_norm": 1.1494112014770508,
|
| 214 |
+
"learning_rate": 0.00015945945945945947,
|
| 215 |
+
"loss": 0.7065,
|
| 216 |
+
"step": 270
|
| 217 |
+
},
|
| 218 |
+
{
|
| 219 |
+
"epoch": 0.8408408408408409,
|
| 220 |
+
"grad_norm": 2.5776023864746094,
|
| 221 |
+
"learning_rate": 0.00015795795795795796,
|
| 222 |
+
"loss": 0.4774,
|
| 223 |
+
"step": 280
|
| 224 |
+
},
|
| 225 |
+
{
|
| 226 |
+
"epoch": 0.8708708708708709,
|
| 227 |
+
"grad_norm": 3.333287239074707,
|
| 228 |
+
"learning_rate": 0.00015645645645645645,
|
| 229 |
+
"loss": 0.6134,
|
| 230 |
+
"step": 290
|
| 231 |
+
},
|
| 232 |
+
{
|
| 233 |
+
"epoch": 0.9009009009009009,
|
| 234 |
+
"grad_norm": 2.337012529373169,
|
| 235 |
+
"learning_rate": 0.00015495495495495496,
|
| 236 |
+
"loss": 0.6523,
|
| 237 |
+
"step": 300
|
| 238 |
+
},
|
| 239 |
+
{
|
| 240 |
+
"epoch": 0.9009009009009009,
|
| 241 |
+
"eval_accuracy": 0.8799149840595112,
|
| 242 |
+
"eval_loss": 0.5133848786354065,
|
| 243 |
+
"eval_runtime": 28.7003,
|
| 244 |
+
"eval_samples_per_second": 32.787,
|
| 245 |
+
"eval_steps_per_second": 4.111,
|
| 246 |
+
"step": 300
|
| 247 |
+
},
|
| 248 |
+
{
|
| 249 |
+
"epoch": 0.9309309309309309,
|
| 250 |
+
"grad_norm": 2.1757540702819824,
|
| 251 |
+
"learning_rate": 0.00015345345345345345,
|
| 252 |
+
"loss": 0.5388,
|
| 253 |
+
"step": 310
|
| 254 |
+
},
|
| 255 |
+
{
|
| 256 |
+
"epoch": 0.960960960960961,
|
| 257 |
+
"grad_norm": 3.668917655944824,
|
| 258 |
+
"learning_rate": 0.00015195195195195194,
|
| 259 |
+
"loss": 0.5271,
|
| 260 |
+
"step": 320
|
| 261 |
+
},
|
| 262 |
+
{
|
| 263 |
+
"epoch": 0.990990990990991,
|
| 264 |
+
"grad_norm": 2.8729825019836426,
|
| 265 |
+
"learning_rate": 0.00015045045045045046,
|
| 266 |
+
"loss": 0.3867,
|
| 267 |
+
"step": 330
|
| 268 |
+
},
|
| 269 |
+
{
|
| 270 |
+
"epoch": 1.021021021021021,
|
| 271 |
+
"grad_norm": 1.3619645833969116,
|
| 272 |
+
"learning_rate": 0.00014894894894894895,
|
| 273 |
+
"loss": 0.4743,
|
| 274 |
+
"step": 340
|
| 275 |
+
},
|
| 276 |
+
{
|
| 277 |
+
"epoch": 1.0510510510510511,
|
| 278 |
+
"grad_norm": 2.4344875812530518,
|
| 279 |
+
"learning_rate": 0.00014744744744744746,
|
| 280 |
+
"loss": 0.4791,
|
| 281 |
+
"step": 350
|
| 282 |
+
},
|
| 283 |
+
{
|
| 284 |
+
"epoch": 1.0810810810810811,
|
| 285 |
+
"grad_norm": 2.5022900104522705,
|
| 286 |
+
"learning_rate": 0.00014594594594594595,
|
| 287 |
+
"loss": 0.4244,
|
| 288 |
+
"step": 360
|
| 289 |
+
},
|
| 290 |
+
{
|
| 291 |
+
"epoch": 1.1111111111111112,
|
| 292 |
+
"grad_norm": 0.42008906602859497,
|
| 293 |
+
"learning_rate": 0.00014444444444444444,
|
| 294 |
+
"loss": 0.4419,
|
| 295 |
+
"step": 370
|
| 296 |
+
},
|
| 297 |
+
{
|
| 298 |
+
"epoch": 1.1411411411411412,
|
| 299 |
+
"grad_norm": 2.006427049636841,
|
| 300 |
+
"learning_rate": 0.00014294294294294295,
|
| 301 |
+
"loss": 0.3806,
|
| 302 |
+
"step": 380
|
| 303 |
+
},
|
| 304 |
+
{
|
| 305 |
+
"epoch": 1.1711711711711712,
|
| 306 |
+
"grad_norm": 4.105851650238037,
|
| 307 |
+
"learning_rate": 0.00014144144144144144,
|
| 308 |
+
"loss": 0.5661,
|
| 309 |
+
"step": 390
|
| 310 |
+
},
|
| 311 |
+
{
|
| 312 |
+
"epoch": 1.2012012012012012,
|
| 313 |
+
"grad_norm": 1.2595148086547852,
|
| 314 |
+
"learning_rate": 0.00013993993993993996,
|
| 315 |
+
"loss": 0.4247,
|
| 316 |
+
"step": 400
|
| 317 |
+
},
|
| 318 |
+
{
|
| 319 |
+
"epoch": 1.2012012012012012,
|
| 320 |
+
"eval_accuracy": 0.9043570669500531,
|
| 321 |
+
"eval_loss": 0.39834967255592346,
|
| 322 |
+
"eval_runtime": 28.9318,
|
| 323 |
+
"eval_samples_per_second": 32.525,
|
| 324 |
+
"eval_steps_per_second": 4.079,
|
| 325 |
+
"step": 400
|
| 326 |
+
},
|
| 327 |
+
{
|
| 328 |
+
"epoch": 1.2312312312312312,
|
| 329 |
+
"grad_norm": 1.719741702079773,
|
| 330 |
+
"learning_rate": 0.00013843843843843845,
|
| 331 |
+
"loss": 0.3838,
|
| 332 |
+
"step": 410
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 1.2612612612612613,
|
| 336 |
+
"grad_norm": 3.1315104961395264,
|
| 337 |
+
"learning_rate": 0.00013693693693693693,
|
| 338 |
+
"loss": 0.3394,
|
| 339 |
+
"step": 420
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 1.2912912912912913,
|
| 343 |
+
"grad_norm": 1.0376994609832764,
|
| 344 |
+
"learning_rate": 0.00013543543543543545,
|
| 345 |
+
"loss": 0.4235,
|
| 346 |
+
"step": 430
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 1.3213213213213213,
|
| 350 |
+
"grad_norm": 4.525661945343018,
|
| 351 |
+
"learning_rate": 0.00013393393393393394,
|
| 352 |
+
"loss": 0.4403,
|
| 353 |
+
"step": 440
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 1.3513513513513513,
|
| 357 |
+
"grad_norm": 5.646125316619873,
|
| 358 |
+
"learning_rate": 0.00013243243243243243,
|
| 359 |
+
"loss": 0.3864,
|
| 360 |
+
"step": 450
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 1.3813813813813813,
|
| 364 |
+
"grad_norm": 3.0982725620269775,
|
| 365 |
+
"learning_rate": 0.00013093093093093094,
|
| 366 |
+
"loss": 0.4172,
|
| 367 |
+
"step": 460
|
| 368 |
+
},
|
| 369 |
+
{
|
| 370 |
+
"epoch": 1.4114114114114114,
|
| 371 |
+
"grad_norm": 5.521030426025391,
|
| 372 |
+
"learning_rate": 0.00012942942942942943,
|
| 373 |
+
"loss": 0.3958,
|
| 374 |
+
"step": 470
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 1.4414414414414414,
|
| 378 |
+
"grad_norm": 5.819517135620117,
|
| 379 |
+
"learning_rate": 0.00012792792792792795,
|
| 380 |
+
"loss": 0.5228,
|
| 381 |
+
"step": 480
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 1.4714714714714714,
|
| 385 |
+
"grad_norm": 7.061979293823242,
|
| 386 |
+
"learning_rate": 0.00012642642642642644,
|
| 387 |
+
"loss": 0.3269,
|
| 388 |
+
"step": 490
|
| 389 |
+
},
|
| 390 |
+
{
|
| 391 |
+
"epoch": 1.5015015015015014,
|
| 392 |
+
"grad_norm": 0.9529209136962891,
|
| 393 |
+
"learning_rate": 0.00012492492492492492,
|
| 394 |
+
"loss": 0.4393,
|
| 395 |
+
"step": 500
|
| 396 |
+
},
|
| 397 |
+
{
|
| 398 |
+
"epoch": 1.5015015015015014,
|
| 399 |
+
"eval_accuracy": 0.89798087141339,
|
| 400 |
+
"eval_loss": 0.4118588864803314,
|
| 401 |
+
"eval_runtime": 29.0892,
|
| 402 |
+
"eval_samples_per_second": 32.349,
|
| 403 |
+
"eval_steps_per_second": 4.056,
|
| 404 |
+
"step": 500
|
| 405 |
+
},
|
| 406 |
+
{
|
| 407 |
+
"epoch": 1.5315315315315314,
|
| 408 |
+
"grad_norm": 2.104562520980835,
|
| 409 |
+
"learning_rate": 0.00012342342342342344,
|
| 410 |
+
"loss": 0.3378,
|
| 411 |
+
"step": 510
|
| 412 |
+
},
|
| 413 |
+
{
|
| 414 |
+
"epoch": 1.5615615615615615,
|
| 415 |
+
"grad_norm": 6.228355884552002,
|
| 416 |
+
"learning_rate": 0.00012192192192192193,
|
| 417 |
+
"loss": 0.385,
|
| 418 |
+
"step": 520
|
| 419 |
+
},
|
| 420 |
+
{
|
| 421 |
+
"epoch": 1.5915915915915915,
|
| 422 |
+
"grad_norm": 3.3202242851257324,
|
| 423 |
+
"learning_rate": 0.00012042042042042043,
|
| 424 |
+
"loss": 0.4868,
|
| 425 |
+
"step": 530
|
| 426 |
+
},
|
| 427 |
+
{
|
| 428 |
+
"epoch": 1.6216216216216215,
|
| 429 |
+
"grad_norm": 3.134051561355591,
|
| 430 |
+
"learning_rate": 0.00011891891891891893,
|
| 431 |
+
"loss": 0.3764,
|
| 432 |
+
"step": 540
|
| 433 |
+
},
|
| 434 |
+
{
|
| 435 |
+
"epoch": 1.6516516516516515,
|
| 436 |
+
"grad_norm": 1.982640027999878,
|
| 437 |
+
"learning_rate": 0.00011741741741741743,
|
| 438 |
+
"loss": 0.4304,
|
| 439 |
+
"step": 550
|
| 440 |
+
},
|
| 441 |
+
{
|
| 442 |
+
"epoch": 1.6816816816816815,
|
| 443 |
+
"grad_norm": 3.3197553157806396,
|
| 444 |
+
"learning_rate": 0.00011591591591591592,
|
| 445 |
+
"loss": 0.4026,
|
| 446 |
+
"step": 560
|
| 447 |
+
},
|
| 448 |
+
{
|
| 449 |
+
"epoch": 1.7117117117117115,
|
| 450 |
+
"grad_norm": 4.031904697418213,
|
| 451 |
+
"learning_rate": 0.00011441441441441443,
|
| 452 |
+
"loss": 0.4006,
|
| 453 |
+
"step": 570
|
| 454 |
+
},
|
| 455 |
+
{
|
| 456 |
+
"epoch": 1.7417417417417418,
|
| 457 |
+
"grad_norm": 2.91866135597229,
|
| 458 |
+
"learning_rate": 0.00011291291291291293,
|
| 459 |
+
"loss": 0.4367,
|
| 460 |
+
"step": 580
|
| 461 |
+
},
|
| 462 |
+
{
|
| 463 |
+
"epoch": 1.7717717717717718,
|
| 464 |
+
"grad_norm": 6.890028953552246,
|
| 465 |
+
"learning_rate": 0.00011141141141141143,
|
| 466 |
+
"loss": 0.4345,
|
| 467 |
+
"step": 590
|
| 468 |
+
},
|
| 469 |
+
{
|
| 470 |
+
"epoch": 1.8018018018018018,
|
| 471 |
+
"grad_norm": 7.291341781616211,
|
| 472 |
+
"learning_rate": 0.00010990990990990993,
|
| 473 |
+
"loss": 0.4631,
|
| 474 |
+
"step": 600
|
| 475 |
+
},
|
| 476 |
+
{
|
| 477 |
+
"epoch": 1.8018018018018018,
|
| 478 |
+
"eval_accuracy": 0.9107332624867163,
|
| 479 |
+
"eval_loss": 0.3752017319202423,
|
| 480 |
+
"eval_runtime": 28.7185,
|
| 481 |
+
"eval_samples_per_second": 32.766,
|
| 482 |
+
"eval_steps_per_second": 4.109,
|
| 483 |
+
"step": 600
|
| 484 |
+
},
|
| 485 |
+
{
|
| 486 |
+
"epoch": 1.8318318318318318,
|
| 487 |
+
"grad_norm": 6.547687530517578,
|
| 488 |
+
"learning_rate": 0.00010840840840840842,
|
| 489 |
+
"loss": 0.3953,
|
| 490 |
+
"step": 610
|
| 491 |
+
},
|
| 492 |
+
{
|
| 493 |
+
"epoch": 1.8618618618618619,
|
| 494 |
+
"grad_norm": 3.9635071754455566,
|
| 495 |
+
"learning_rate": 0.00010690690690690692,
|
| 496 |
+
"loss": 0.3499,
|
| 497 |
+
"step": 620
|
| 498 |
+
},
|
| 499 |
+
{
|
| 500 |
+
"epoch": 1.8918918918918919,
|
| 501 |
+
"grad_norm": 2.1902055740356445,
|
| 502 |
+
"learning_rate": 0.0001054054054054054,
|
| 503 |
+
"loss": 0.3476,
|
| 504 |
+
"step": 630
|
| 505 |
+
},
|
| 506 |
+
{
|
| 507 |
+
"epoch": 1.921921921921922,
|
| 508 |
+
"grad_norm": 2.9604856967926025,
|
| 509 |
+
"learning_rate": 0.0001039039039039039,
|
| 510 |
+
"loss": 0.3693,
|
| 511 |
+
"step": 640
|
| 512 |
+
},
|
| 513 |
+
{
|
| 514 |
+
"epoch": 1.951951951951952,
|
| 515 |
+
"grad_norm": 1.3020485639572144,
|
| 516 |
+
"learning_rate": 0.0001024024024024024,
|
| 517 |
+
"loss": 0.3556,
|
| 518 |
+
"step": 650
|
| 519 |
+
},
|
| 520 |
+
{
|
| 521 |
+
"epoch": 1.981981981981982,
|
| 522 |
+
"grad_norm": 1.8542765378952026,
|
| 523 |
+
"learning_rate": 0.00010090090090090089,
|
| 524 |
+
"loss": 0.3287,
|
| 525 |
+
"step": 660
|
| 526 |
+
},
|
| 527 |
+
{
|
| 528 |
+
"epoch": 2.012012012012012,
|
| 529 |
+
"grad_norm": 1.039650559425354,
|
| 530 |
+
"learning_rate": 9.93993993993994e-05,
|
| 531 |
+
"loss": 0.3603,
|
| 532 |
+
"step": 670
|
| 533 |
+
},
|
| 534 |
+
{
|
| 535 |
+
"epoch": 2.042042042042042,
|
| 536 |
+
"grad_norm": 2.5295028686523438,
|
| 537 |
+
"learning_rate": 9.789789789789791e-05,
|
| 538 |
+
"loss": 0.2565,
|
| 539 |
+
"step": 680
|
| 540 |
+
},
|
| 541 |
+
{
|
| 542 |
+
"epoch": 2.0720720720720722,
|
| 543 |
+
"grad_norm": 5.409499168395996,
|
| 544 |
+
"learning_rate": 9.639639639639641e-05,
|
| 545 |
+
"loss": 0.3467,
|
| 546 |
+
"step": 690
|
| 547 |
+
},
|
| 548 |
+
{
|
| 549 |
+
"epoch": 2.1021021021021022,
|
| 550 |
+
"grad_norm": 2.797410249710083,
|
| 551 |
+
"learning_rate": 9.48948948948949e-05,
|
| 552 |
+
"loss": 0.2992,
|
| 553 |
+
"step": 700
|
| 554 |
+
},
|
| 555 |
+
{
|
| 556 |
+
"epoch": 2.1021021021021022,
|
| 557 |
+
"eval_accuracy": 0.9128586609989373,
|
| 558 |
+
"eval_loss": 0.3469248116016388,
|
| 559 |
+
"eval_runtime": 28.8507,
|
| 560 |
+
"eval_samples_per_second": 32.616,
|
| 561 |
+
"eval_steps_per_second": 4.09,
|
| 562 |
+
"step": 700
|
| 563 |
+
},
|
| 564 |
+
{
|
| 565 |
+
"epoch": 2.1321321321321323,
|
| 566 |
+
"grad_norm": 6.1658196449279785,
|
| 567 |
+
"learning_rate": 9.33933933933934e-05,
|
| 568 |
+
"loss": 0.3511,
|
| 569 |
+
"step": 710
|
| 570 |
+
},
|
| 571 |
+
{
|
| 572 |
+
"epoch": 2.1621621621621623,
|
| 573 |
+
"grad_norm": 5.815499305725098,
|
| 574 |
+
"learning_rate": 9.18918918918919e-05,
|
| 575 |
+
"loss": 0.2395,
|
| 576 |
+
"step": 720
|
| 577 |
+
},
|
| 578 |
+
{
|
| 579 |
+
"epoch": 2.1921921921921923,
|
| 580 |
+
"grad_norm": 4.747284412384033,
|
| 581 |
+
"learning_rate": 9.039039039039039e-05,
|
| 582 |
+
"loss": 0.1959,
|
| 583 |
+
"step": 730
|
| 584 |
+
},
|
| 585 |
+
{
|
| 586 |
+
"epoch": 2.2222222222222223,
|
| 587 |
+
"grad_norm": 2.6975574493408203,
|
| 588 |
+
"learning_rate": 8.888888888888889e-05,
|
| 589 |
+
"loss": 0.322,
|
| 590 |
+
"step": 740
|
| 591 |
+
},
|
| 592 |
+
{
|
| 593 |
+
"epoch": 2.2522522522522523,
|
| 594 |
+
"grad_norm": 6.27766752243042,
|
| 595 |
+
"learning_rate": 8.738738738738738e-05,
|
| 596 |
+
"loss": 0.3862,
|
| 597 |
+
"step": 750
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"epoch": 2.2822822822822824,
|
| 601 |
+
"grad_norm": 2.173295497894287,
|
| 602 |
+
"learning_rate": 8.588588588588588e-05,
|
| 603 |
+
"loss": 0.2607,
|
| 604 |
+
"step": 760
|
| 605 |
+
},
|
| 606 |
+
{
|
| 607 |
+
"epoch": 2.3123123123123124,
|
| 608 |
+
"grad_norm": 3.244479179382324,
|
| 609 |
+
"learning_rate": 8.438438438438439e-05,
|
| 610 |
+
"loss": 0.1749,
|
| 611 |
+
"step": 770
|
| 612 |
+
},
|
| 613 |
+
{
|
| 614 |
+
"epoch": 2.3423423423423424,
|
| 615 |
+
"grad_norm": 3.7047109603881836,
|
| 616 |
+
"learning_rate": 8.288288288288289e-05,
|
| 617 |
+
"loss": 0.4127,
|
| 618 |
+
"step": 780
|
| 619 |
+
},
|
| 620 |
+
{
|
| 621 |
+
"epoch": 2.3723723723723724,
|
| 622 |
+
"grad_norm": 3.665949821472168,
|
| 623 |
+
"learning_rate": 8.138138138138138e-05,
|
| 624 |
+
"loss": 0.1813,
|
| 625 |
+
"step": 790
|
| 626 |
+
},
|
| 627 |
+
{
|
| 628 |
+
"epoch": 2.4024024024024024,
|
| 629 |
+
"grad_norm": 2.648050546646118,
|
| 630 |
+
"learning_rate": 7.987987987987988e-05,
|
| 631 |
+
"loss": 0.3,
|
| 632 |
+
"step": 800
|
| 633 |
+
},
|
| 634 |
+
{
|
| 635 |
+
"epoch": 2.4024024024024024,
|
| 636 |
+
"eval_accuracy": 0.9202975557917109,
|
| 637 |
+
"eval_loss": 0.3156701624393463,
|
| 638 |
+
"eval_runtime": 28.5152,
|
| 639 |
+
"eval_samples_per_second": 33.0,
|
| 640 |
+
"eval_steps_per_second": 4.138,
|
| 641 |
+
"step": 800
|
| 642 |
+
},
|
| 643 |
+
{
|
| 644 |
+
"epoch": 2.4324324324324325,
|
| 645 |
+
"grad_norm": 0.29231011867523193,
|
| 646 |
+
"learning_rate": 7.837837837837838e-05,
|
| 647 |
+
"loss": 0.1998,
|
| 648 |
+
"step": 810
|
| 649 |
+
},
|
| 650 |
+
{
|
| 651 |
+
"epoch": 2.4624624624624625,
|
| 652 |
+
"grad_norm": 3.4136736392974854,
|
| 653 |
+
"learning_rate": 7.687687687687688e-05,
|
| 654 |
+
"loss": 0.2671,
|
| 655 |
+
"step": 820
|
| 656 |
+
},
|
| 657 |
+
{
|
| 658 |
+
"epoch": 2.4924924924924925,
|
| 659 |
+
"grad_norm": 1.5347037315368652,
|
| 660 |
+
"learning_rate": 7.537537537537538e-05,
|
| 661 |
+
"loss": 0.2087,
|
| 662 |
+
"step": 830
|
| 663 |
+
},
|
| 664 |
+
{
|
| 665 |
+
"epoch": 2.5225225225225225,
|
| 666 |
+
"grad_norm": 0.2756473124027252,
|
| 667 |
+
"learning_rate": 7.387387387387387e-05,
|
| 668 |
+
"loss": 0.2465,
|
| 669 |
+
"step": 840
|
| 670 |
+
},
|
| 671 |
+
{
|
| 672 |
+
"epoch": 2.5525525525525525,
|
| 673 |
+
"grad_norm": 2.2905094623565674,
|
| 674 |
+
"learning_rate": 7.237237237237238e-05,
|
| 675 |
+
"loss": 0.4043,
|
| 676 |
+
"step": 850
|
| 677 |
+
},
|
| 678 |
+
{
|
| 679 |
+
"epoch": 2.5825825825825826,
|
| 680 |
+
"grad_norm": 4.817660331726074,
|
| 681 |
+
"learning_rate": 7.087087087087088e-05,
|
| 682 |
+
"loss": 0.238,
|
| 683 |
+
"step": 860
|
| 684 |
+
},
|
| 685 |
+
{
|
| 686 |
+
"epoch": 2.6126126126126126,
|
| 687 |
+
"grad_norm": 2.556462526321411,
|
| 688 |
+
"learning_rate": 6.936936936936938e-05,
|
| 689 |
+
"loss": 0.1516,
|
| 690 |
+
"step": 870
|
| 691 |
+
},
|
| 692 |
+
{
|
| 693 |
+
"epoch": 2.6426426426426426,
|
| 694 |
+
"grad_norm": 6.198856830596924,
|
| 695 |
+
"learning_rate": 6.786786786786787e-05,
|
| 696 |
+
"loss": 0.3203,
|
| 697 |
+
"step": 880
|
| 698 |
+
},
|
| 699 |
+
{
|
| 700 |
+
"epoch": 2.6726726726726726,
|
| 701 |
+
"grad_norm": 0.9303868412971497,
|
| 702 |
+
"learning_rate": 6.636636636636637e-05,
|
| 703 |
+
"loss": 0.2225,
|
| 704 |
+
"step": 890
|
| 705 |
+
},
|
| 706 |
+
{
|
| 707 |
+
"epoch": 2.7027027027027026,
|
| 708 |
+
"grad_norm": 3.7441625595092773,
|
| 709 |
+
"learning_rate": 6.486486486486487e-05,
|
| 710 |
+
"loss": 0.2372,
|
| 711 |
+
"step": 900
|
| 712 |
+
},
|
| 713 |
+
{
|
| 714 |
+
"epoch": 2.7027027027027026,
|
| 715 |
+
"eval_accuracy": 0.9192348565356004,
|
| 716 |
+
"eval_loss": 0.3209655284881592,
|
| 717 |
+
"eval_runtime": 29.1587,
|
| 718 |
+
"eval_samples_per_second": 32.272,
|
| 719 |
+
"eval_steps_per_second": 4.047,
|
| 720 |
+
"step": 900
|
| 721 |
+
},
|
| 722 |
+
{
|
| 723 |
+
"epoch": 2.7327327327327327,
|
| 724 |
+
"grad_norm": 1.344062089920044,
|
| 725 |
+
"learning_rate": 6.336336336336337e-05,
|
| 726 |
+
"loss": 0.3659,
|
| 727 |
+
"step": 910
|
| 728 |
+
},
|
| 729 |
+
{
|
| 730 |
+
"epoch": 2.7627627627627627,
|
| 731 |
+
"grad_norm": 3.962114095687866,
|
| 732 |
+
"learning_rate": 6.186186186186186e-05,
|
| 733 |
+
"loss": 0.2461,
|
| 734 |
+
"step": 920
|
| 735 |
+
},
|
| 736 |
+
{
|
| 737 |
+
"epoch": 2.7927927927927927,
|
| 738 |
+
"grad_norm": 1.4669685363769531,
|
| 739 |
+
"learning_rate": 6.0360360360360365e-05,
|
| 740 |
+
"loss": 0.2636,
|
| 741 |
+
"step": 930
|
| 742 |
+
},
|
| 743 |
+
{
|
| 744 |
+
"epoch": 2.8228228228228227,
|
| 745 |
+
"grad_norm": 7.011595249176025,
|
| 746 |
+
"learning_rate": 5.8858858858858854e-05,
|
| 747 |
+
"loss": 0.2226,
|
| 748 |
+
"step": 940
|
| 749 |
+
},
|
| 750 |
+
{
|
| 751 |
+
"epoch": 2.8528528528528527,
|
| 752 |
+
"grad_norm": 5.4901862144470215,
|
| 753 |
+
"learning_rate": 5.7357357357357356e-05,
|
| 754 |
+
"loss": 0.1958,
|
| 755 |
+
"step": 950
|
| 756 |
+
},
|
| 757 |
+
{
|
| 758 |
+
"epoch": 2.8828828828828827,
|
| 759 |
+
"grad_norm": 0.7357378602027893,
|
| 760 |
+
"learning_rate": 5.585585585585585e-05,
|
| 761 |
+
"loss": 0.2583,
|
| 762 |
+
"step": 960
|
| 763 |
+
},
|
| 764 |
+
{
|
| 765 |
+
"epoch": 2.9129129129129128,
|
| 766 |
+
"grad_norm": 5.614912509918213,
|
| 767 |
+
"learning_rate": 5.435435435435435e-05,
|
| 768 |
+
"loss": 0.2466,
|
| 769 |
+
"step": 970
|
| 770 |
+
},
|
| 771 |
+
{
|
| 772 |
+
"epoch": 2.942942942942943,
|
| 773 |
+
"grad_norm": 2.8368093967437744,
|
| 774 |
+
"learning_rate": 5.2852852852852855e-05,
|
| 775 |
+
"loss": 0.2056,
|
| 776 |
+
"step": 980
|
| 777 |
+
},
|
| 778 |
+
{
|
| 779 |
+
"epoch": 2.972972972972973,
|
| 780 |
+
"grad_norm": 1.6713290214538574,
|
| 781 |
+
"learning_rate": 5.135135135135135e-05,
|
| 782 |
+
"loss": 0.2231,
|
| 783 |
+
"step": 990
|
| 784 |
+
},
|
| 785 |
+
{
|
| 786 |
+
"epoch": 3.003003003003003,
|
| 787 |
+
"grad_norm": 0.7347887754440308,
|
| 788 |
+
"learning_rate": 4.984984984984985e-05,
|
| 789 |
+
"loss": 0.2447,
|
| 790 |
+
"step": 1000
|
| 791 |
+
},
|
| 792 |
+
{
|
| 793 |
+
"epoch": 3.003003003003003,
|
| 794 |
+
"eval_accuracy": 0.922422954303932,
|
| 795 |
+
"eval_loss": 0.3139547109603882,
|
| 796 |
+
"eval_runtime": 29.2161,
|
| 797 |
+
"eval_samples_per_second": 32.208,
|
| 798 |
+
"eval_steps_per_second": 4.039,
|
| 799 |
+
"step": 1000
|
| 800 |
+
},
|
| 801 |
+
{
|
| 802 |
+
"epoch": 3.033033033033033,
|
| 803 |
+
"grad_norm": 2.947268486022949,
|
| 804 |
+
"learning_rate": 4.834834834834835e-05,
|
| 805 |
+
"loss": 0.2247,
|
| 806 |
+
"step": 1010
|
| 807 |
+
},
|
| 808 |
+
{
|
| 809 |
+
"epoch": 3.063063063063063,
|
| 810 |
+
"grad_norm": 0.17604035139083862,
|
| 811 |
+
"learning_rate": 4.684684684684685e-05,
|
| 812 |
+
"loss": 0.125,
|
| 813 |
+
"step": 1020
|
| 814 |
+
},
|
| 815 |
+
{
|
| 816 |
+
"epoch": 3.093093093093093,
|
| 817 |
+
"grad_norm": 3.0279932022094727,
|
| 818 |
+
"learning_rate": 4.5345345345345345e-05,
|
| 819 |
+
"loss": 0.1933,
|
| 820 |
+
"step": 1030
|
| 821 |
+
},
|
| 822 |
+
{
|
| 823 |
+
"epoch": 3.123123123123123,
|
| 824 |
+
"grad_norm": 0.5538057684898376,
|
| 825 |
+
"learning_rate": 4.384384384384385e-05,
|
| 826 |
+
"loss": 0.1259,
|
| 827 |
+
"step": 1040
|
| 828 |
+
},
|
| 829 |
+
{
|
| 830 |
+
"epoch": 3.153153153153153,
|
| 831 |
+
"grad_norm": 3.872739315032959,
|
| 832 |
+
"learning_rate": 4.234234234234234e-05,
|
| 833 |
+
"loss": 0.3184,
|
| 834 |
+
"step": 1050
|
| 835 |
+
},
|
| 836 |
+
{
|
| 837 |
+
"epoch": 3.1831831831831834,
|
| 838 |
+
"grad_norm": 0.44582998752593994,
|
| 839 |
+
"learning_rate": 4.0840840840840845e-05,
|
| 840 |
+
"loss": 0.2011,
|
| 841 |
+
"step": 1060
|
| 842 |
+
},
|
| 843 |
+
{
|
| 844 |
+
"epoch": 3.2132132132132134,
|
| 845 |
+
"grad_norm": 2.342395782470703,
|
| 846 |
+
"learning_rate": 3.933933933933934e-05,
|
| 847 |
+
"loss": 0.1837,
|
| 848 |
+
"step": 1070
|
| 849 |
+
},
|
| 850 |
+
{
|
| 851 |
+
"epoch": 3.2432432432432434,
|
| 852 |
+
"grad_norm": 0.7843596339225769,
|
| 853 |
+
"learning_rate": 3.783783783783784e-05,
|
| 854 |
+
"loss": 0.226,
|
| 855 |
+
"step": 1080
|
| 856 |
+
},
|
| 857 |
+
{
|
| 858 |
+
"epoch": 3.2732732732732734,
|
| 859 |
+
"grad_norm": 2.8491196632385254,
|
| 860 |
+
"learning_rate": 3.633633633633634e-05,
|
| 861 |
+
"loss": 0.1481,
|
| 862 |
+
"step": 1090
|
| 863 |
+
},
|
| 864 |
+
{
|
| 865 |
+
"epoch": 3.3033033033033035,
|
| 866 |
+
"grad_norm": 1.972225546836853,
|
| 867 |
+
"learning_rate": 3.483483483483483e-05,
|
| 868 |
+
"loss": 0.2209,
|
| 869 |
+
"step": 1100
|
| 870 |
+
},
|
| 871 |
+
{
|
| 872 |
+
"epoch": 3.3033033033033035,
|
| 873 |
+
"eval_accuracy": 0.9160467587672688,
|
| 874 |
+
"eval_loss": 0.30342116951942444,
|
| 875 |
+
"eval_runtime": 29.6037,
|
| 876 |
+
"eval_samples_per_second": 31.787,
|
| 877 |
+
"eval_steps_per_second": 3.986,
|
| 878 |
+
"step": 1100
|
| 879 |
+
},
|
| 880 |
+
{
|
| 881 |
+
"epoch": 3.3333333333333335,
|
| 882 |
+
"grad_norm": 2.8411455154418945,
|
| 883 |
+
"learning_rate": 3.3333333333333335e-05,
|
| 884 |
+
"loss": 0.1262,
|
| 885 |
+
"step": 1110
|
| 886 |
+
},
|
| 887 |
+
{
|
| 888 |
+
"epoch": 3.3633633633633635,
|
| 889 |
+
"grad_norm": 0.25656577944755554,
|
| 890 |
+
"learning_rate": 3.183183183183183e-05,
|
| 891 |
+
"loss": 0.1239,
|
| 892 |
+
"step": 1120
|
| 893 |
+
},
|
| 894 |
+
{
|
| 895 |
+
"epoch": 3.3933933933933935,
|
| 896 |
+
"grad_norm": 0.13324937224388123,
|
| 897 |
+
"learning_rate": 3.0330330330330332e-05,
|
| 898 |
+
"loss": 0.1241,
|
| 899 |
+
"step": 1130
|
| 900 |
+
},
|
| 901 |
+
{
|
| 902 |
+
"epoch": 3.4234234234234235,
|
| 903 |
+
"grad_norm": 1.2855831384658813,
|
| 904 |
+
"learning_rate": 2.882882882882883e-05,
|
| 905 |
+
"loss": 0.1918,
|
| 906 |
+
"step": 1140
|
| 907 |
+
},
|
| 908 |
+
{
|
| 909 |
+
"epoch": 3.4534534534534536,
|
| 910 |
+
"grad_norm": 1.9817436933517456,
|
| 911 |
+
"learning_rate": 2.732732732732733e-05,
|
| 912 |
+
"loss": 0.2025,
|
| 913 |
+
"step": 1150
|
| 914 |
+
},
|
| 915 |
+
{
|
| 916 |
+
"epoch": 3.4834834834834836,
|
| 917 |
+
"grad_norm": 2.209524631500244,
|
| 918 |
+
"learning_rate": 2.582582582582583e-05,
|
| 919 |
+
"loss": 0.2032,
|
| 920 |
+
"step": 1160
|
| 921 |
+
},
|
| 922 |
+
{
|
| 923 |
+
"epoch": 3.5135135135135136,
|
| 924 |
+
"grad_norm": 3.2614221572875977,
|
| 925 |
+
"learning_rate": 2.4324324324324327e-05,
|
| 926 |
+
"loss": 0.1055,
|
| 927 |
+
"step": 1170
|
| 928 |
+
},
|
| 929 |
+
{
|
| 930 |
+
"epoch": 3.5435435435435436,
|
| 931 |
+
"grad_norm": 1.4140874147415161,
|
| 932 |
+
"learning_rate": 2.2822822822822822e-05,
|
| 933 |
+
"loss": 0.1869,
|
| 934 |
+
"step": 1180
|
| 935 |
+
},
|
| 936 |
+
{
|
| 937 |
+
"epoch": 3.5735735735735736,
|
| 938 |
+
"grad_norm": 4.29329252243042,
|
| 939 |
+
"learning_rate": 2.132132132132132e-05,
|
| 940 |
+
"loss": 0.1858,
|
| 941 |
+
"step": 1190
|
| 942 |
+
},
|
| 943 |
+
{
|
| 944 |
+
"epoch": 3.6036036036036037,
|
| 945 |
+
"grad_norm": 6.110797882080078,
|
| 946 |
+
"learning_rate": 1.981981981981982e-05,
|
| 947 |
+
"loss": 0.2641,
|
| 948 |
+
"step": 1200
|
| 949 |
+
},
|
| 950 |
+
{
|
| 951 |
+
"epoch": 3.6036036036036037,
|
| 952 |
+
"eval_accuracy": 0.9277364505844846,
|
| 953 |
+
"eval_loss": 0.28959977626800537,
|
| 954 |
+
"eval_runtime": 28.964,
|
| 955 |
+
"eval_samples_per_second": 32.489,
|
| 956 |
+
"eval_steps_per_second": 4.074,
|
| 957 |
+
"step": 1200
|
| 958 |
+
},
|
| 959 |
+
{
|
| 960 |
+
"epoch": 3.6336336336336337,
|
| 961 |
+
"grad_norm": 0.3689054250717163,
|
| 962 |
+
"learning_rate": 1.831831831831832e-05,
|
| 963 |
+
"loss": 0.1217,
|
| 964 |
+
"step": 1210
|
| 965 |
+
},
|
| 966 |
+
{
|
| 967 |
+
"epoch": 3.6636636636636637,
|
| 968 |
+
"grad_norm": 5.862549781799316,
|
| 969 |
+
"learning_rate": 1.6816816816816817e-05,
|
| 970 |
+
"loss": 0.1643,
|
| 971 |
+
"step": 1220
|
| 972 |
+
},
|
| 973 |
+
{
|
| 974 |
+
"epoch": 3.6936936936936937,
|
| 975 |
+
"grad_norm": 0.19235260784626007,
|
| 976 |
+
"learning_rate": 1.5315315315315316e-05,
|
| 977 |
+
"loss": 0.165,
|
| 978 |
+
"step": 1230
|
| 979 |
+
},
|
| 980 |
+
{
|
| 981 |
+
"epoch": 3.7237237237237237,
|
| 982 |
+
"grad_norm": 0.40488940477371216,
|
| 983 |
+
"learning_rate": 1.3813813813813815e-05,
|
| 984 |
+
"loss": 0.1948,
|
| 985 |
+
"step": 1240
|
| 986 |
+
},
|
| 987 |
+
{
|
| 988 |
+
"epoch": 3.7537537537537538,
|
| 989 |
+
"grad_norm": 3.595454692840576,
|
| 990 |
+
"learning_rate": 1.2312312312312313e-05,
|
| 991 |
+
"loss": 0.1063,
|
| 992 |
+
"step": 1250
|
| 993 |
+
},
|
| 994 |
+
{
|
| 995 |
+
"epoch": 3.7837837837837838,
|
| 996 |
+
"grad_norm": 3.3588507175445557,
|
| 997 |
+
"learning_rate": 1.0810810810810812e-05,
|
| 998 |
+
"loss": 0.2252,
|
| 999 |
+
"step": 1260
|
| 1000 |
+
},
|
| 1001 |
+
{
|
| 1002 |
+
"epoch": 3.813813813813814,
|
| 1003 |
+
"grad_norm": 5.059345245361328,
|
| 1004 |
+
"learning_rate": 9.309309309309309e-06,
|
| 1005 |
+
"loss": 0.1233,
|
| 1006 |
+
"step": 1270
|
| 1007 |
+
},
|
| 1008 |
+
{
|
| 1009 |
+
"epoch": 3.843843843843844,
|
| 1010 |
+
"grad_norm": 0.11752854287624359,
|
| 1011 |
+
"learning_rate": 7.807807807807808e-06,
|
| 1012 |
+
"loss": 0.1526,
|
| 1013 |
+
"step": 1280
|
| 1014 |
+
},
|
| 1015 |
+
{
|
| 1016 |
+
"epoch": 3.873873873873874,
|
| 1017 |
+
"grad_norm": 4.34885835647583,
|
| 1018 |
+
"learning_rate": 6.306306306306306e-06,
|
| 1019 |
+
"loss": 0.1737,
|
| 1020 |
+
"step": 1290
|
| 1021 |
+
},
|
| 1022 |
+
{
|
| 1023 |
+
"epoch": 3.903903903903904,
|
| 1024 |
+
"grad_norm": 1.4543063640594482,
|
| 1025 |
+
"learning_rate": 4.804804804804805e-06,
|
| 1026 |
+
"loss": 0.0954,
|
| 1027 |
+
"step": 1300
|
| 1028 |
+
},
|
| 1029 |
+
{
|
| 1030 |
+
"epoch": 3.903903903903904,
|
| 1031 |
+
"eval_accuracy": 0.926673751328374,
|
| 1032 |
+
"eval_loss": 0.2866949737071991,
|
| 1033 |
+
"eval_runtime": 29.2579,
|
| 1034 |
+
"eval_samples_per_second": 32.162,
|
| 1035 |
+
"eval_steps_per_second": 4.033,
|
| 1036 |
+
"step": 1300
|
| 1037 |
+
},
|
| 1038 |
+
{
|
| 1039 |
+
"epoch": 3.933933933933934,
|
| 1040 |
+
"grad_norm": 1.619908094406128,
|
| 1041 |
+
"learning_rate": 3.3033033033033035e-06,
|
| 1042 |
+
"loss": 0.2021,
|
| 1043 |
+
"step": 1310
|
| 1044 |
+
},
|
| 1045 |
+
{
|
| 1046 |
+
"epoch": 3.963963963963964,
|
| 1047 |
+
"grad_norm": 4.71495246887207,
|
| 1048 |
+
"learning_rate": 1.801801801801802e-06,
|
| 1049 |
+
"loss": 0.1503,
|
| 1050 |
+
"step": 1320
|
| 1051 |
+
},
|
| 1052 |
+
{
|
| 1053 |
+
"epoch": 3.993993993993994,
|
| 1054 |
+
"grad_norm": 4.634551048278809,
|
| 1055 |
+
"learning_rate": 3.003003003003003e-07,
|
| 1056 |
+
"loss": 0.1235,
|
| 1057 |
+
"step": 1330
|
| 1058 |
+
},
|
| 1059 |
+
{
|
| 1060 |
+
"epoch": 4.0,
|
| 1061 |
+
"step": 1332,
|
| 1062 |
+
"total_flos": 1.651775717862015e+18,
|
| 1063 |
+
"train_loss": 0.46514646391252856,
|
| 1064 |
+
"train_runtime": 1194.1419,
|
| 1065 |
+
"train_samples_per_second": 17.847,
|
| 1066 |
+
"train_steps_per_second": 1.115
|
| 1067 |
+
}
|
| 1068 |
+
],
|
| 1069 |
+
"logging_steps": 10,
|
| 1070 |
+
"max_steps": 1332,
|
| 1071 |
+
"num_input_tokens_seen": 0,
|
| 1072 |
+
"num_train_epochs": 4,
|
| 1073 |
+
"save_steps": 100,
|
| 1074 |
+
"stateful_callbacks": {
|
| 1075 |
+
"TrainerControl": {
|
| 1076 |
+
"args": {
|
| 1077 |
+
"should_epoch_stop": false,
|
| 1078 |
+
"should_evaluate": false,
|
| 1079 |
+
"should_log": false,
|
| 1080 |
+
"should_save": true,
|
| 1081 |
+
"should_training_stop": true
|
| 1082 |
+
},
|
| 1083 |
+
"attributes": {}
|
| 1084 |
+
}
|
| 1085 |
+
},
|
| 1086 |
+
"total_flos": 1.651775717862015e+18,
|
| 1087 |
+
"train_batch_size": 16,
|
| 1088 |
+
"trial_name": null,
|
| 1089 |
+
"trial_params": null
|
| 1090 |
+
}
|