🍻 cheers
Browse files- README.md +3 -2
- all_results.json +13 -0
- eval_results.json +8 -0
- runs/Apr05_17-06-15_44569c9ac571/events.out.tfevents.1712341973.44569c9ac571.8281.1 +3 -0
- train_results.json +8 -0
- trainer_state.json +3513 -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
|
@@ -17,8 +18,8 @@ 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-in21K](https://huggingface.co/google/vit-base-patch16-224-in21K) 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 |
|
|
|
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
|
|
|
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 an unknown dataset.
|
20 |
It achieves the following results on the evaluation set:
|
21 |
+
- Loss: 0.5303
|
22 |
+
- Accuracy: 0.8496
|
23 |
|
24 |
## Model description
|
25 |
|
all_results.json
ADDED
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 7.0,
|
3 |
+
"eval_accuracy": 0.8496031746031746,
|
4 |
+
"eval_loss": 0.5302808284759521,
|
5 |
+
"eval_runtime": 93.45,
|
6 |
+
"eval_samples_per_second": 26.966,
|
7 |
+
"eval_steps_per_second": 3.371,
|
8 |
+
"total_flos": 5.468471871363809e+18,
|
9 |
+
"train_loss": 0.7062997149772384,
|
10 |
+
"train_runtime": 5016.6762,
|
11 |
+
"train_samples_per_second": 14.065,
|
12 |
+
"train_steps_per_second": 0.879
|
13 |
+
}
|
eval_results.json
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 7.0,
|
3 |
+
"eval_accuracy": 0.8496031746031746,
|
4 |
+
"eval_loss": 0.5302808284759521,
|
5 |
+
"eval_runtime": 93.45,
|
6 |
+
"eval_samples_per_second": 26.966,
|
7 |
+
"eval_steps_per_second": 3.371
|
8 |
+
}
|
runs/Apr05_17-06-15_44569c9ac571/events.out.tfevents.1712341973.44569c9ac571.8281.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f6968344f66e6c5529f1bdaec7dfca0125d548b0aaf5981bc6ba7f3886c0e54d
|
3 |
+
size 411
|
train_results.json
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 7.0,
|
3 |
+
"total_flos": 5.468471871363809e+18,
|
4 |
+
"train_loss": 0.7062997149772384,
|
5 |
+
"train_runtime": 5016.6762,
|
6 |
+
"train_samples_per_second": 14.065,
|
7 |
+
"train_steps_per_second": 0.879
|
8 |
+
}
|
trainer_state.json
ADDED
@@ -0,0 +1,3513 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 0.5302808284759521,
|
3 |
+
"best_model_checkpoint": "Human_action_classifier/checkpoint-4300",
|
4 |
+
"epoch": 7.0,
|
5 |
+
"eval_steps": 100,
|
6 |
+
"global_step": 4410,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.02,
|
13 |
+
"grad_norm": 1.9168592691421509,
|
14 |
+
"learning_rate": 0.00019954648526077098,
|
15 |
+
"loss": 2.6612,
|
16 |
+
"step": 10
|
17 |
+
},
|
18 |
+
{
|
19 |
+
"epoch": 0.03,
|
20 |
+
"grad_norm": 2.498575210571289,
|
21 |
+
"learning_rate": 0.00019909297052154195,
|
22 |
+
"loss": 2.4529,
|
23 |
+
"step": 20
|
24 |
+
},
|
25 |
+
{
|
26 |
+
"epoch": 0.05,
|
27 |
+
"grad_norm": 2.4278714656829834,
|
28 |
+
"learning_rate": 0.00019863945578231293,
|
29 |
+
"loss": 2.3062,
|
30 |
+
"step": 30
|
31 |
+
},
|
32 |
+
{
|
33 |
+
"epoch": 0.06,
|
34 |
+
"grad_norm": 2.5514345169067383,
|
35 |
+
"learning_rate": 0.0001981859410430839,
|
36 |
+
"loss": 2.169,
|
37 |
+
"step": 40
|
38 |
+
},
|
39 |
+
{
|
40 |
+
"epoch": 0.08,
|
41 |
+
"grad_norm": 2.1051814556121826,
|
42 |
+
"learning_rate": 0.0001977324263038549,
|
43 |
+
"loss": 1.9571,
|
44 |
+
"step": 50
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 0.1,
|
48 |
+
"grad_norm": 2.5904359817504883,
|
49 |
+
"learning_rate": 0.00019727891156462587,
|
50 |
+
"loss": 1.7926,
|
51 |
+
"step": 60
|
52 |
+
},
|
53 |
+
{
|
54 |
+
"epoch": 0.11,
|
55 |
+
"grad_norm": 2.9325740337371826,
|
56 |
+
"learning_rate": 0.00019682539682539682,
|
57 |
+
"loss": 1.6761,
|
58 |
+
"step": 70
|
59 |
+
},
|
60 |
+
{
|
61 |
+
"epoch": 0.13,
|
62 |
+
"grad_norm": 3.636162519454956,
|
63 |
+
"learning_rate": 0.00019637188208616781,
|
64 |
+
"loss": 1.6388,
|
65 |
+
"step": 80
|
66 |
+
},
|
67 |
+
{
|
68 |
+
"epoch": 0.14,
|
69 |
+
"grad_norm": 3.7232675552368164,
|
70 |
+
"learning_rate": 0.0001959183673469388,
|
71 |
+
"loss": 1.527,
|
72 |
+
"step": 90
|
73 |
+
},
|
74 |
+
{
|
75 |
+
"epoch": 0.16,
|
76 |
+
"grad_norm": 3.467459201812744,
|
77 |
+
"learning_rate": 0.00019546485260770976,
|
78 |
+
"loss": 1.4545,
|
79 |
+
"step": 100
|
80 |
+
},
|
81 |
+
{
|
82 |
+
"epoch": 0.16,
|
83 |
+
"eval_accuracy": 0.6706349206349206,
|
84 |
+
"eval_loss": 1.3145380020141602,
|
85 |
+
"eval_runtime": 93.6176,
|
86 |
+
"eval_samples_per_second": 26.918,
|
87 |
+
"eval_steps_per_second": 3.365,
|
88 |
+
"step": 100
|
89 |
+
},
|
90 |
+
{
|
91 |
+
"epoch": 0.17,
|
92 |
+
"grad_norm": 2.4409241676330566,
|
93 |
+
"learning_rate": 0.00019501133786848073,
|
94 |
+
"loss": 1.331,
|
95 |
+
"step": 110
|
96 |
+
},
|
97 |
+
{
|
98 |
+
"epoch": 0.19,
|
99 |
+
"grad_norm": 3.841000556945801,
|
100 |
+
"learning_rate": 0.0001945578231292517,
|
101 |
+
"loss": 1.4273,
|
102 |
+
"step": 120
|
103 |
+
},
|
104 |
+
{
|
105 |
+
"epoch": 0.21,
|
106 |
+
"grad_norm": 4.918443202972412,
|
107 |
+
"learning_rate": 0.0001941043083900227,
|
108 |
+
"loss": 1.4078,
|
109 |
+
"step": 130
|
110 |
+
},
|
111 |
+
{
|
112 |
+
"epoch": 0.22,
|
113 |
+
"grad_norm": 3.317399740219116,
|
114 |
+
"learning_rate": 0.00019365079365079365,
|
115 |
+
"loss": 1.3905,
|
116 |
+
"step": 140
|
117 |
+
},
|
118 |
+
{
|
119 |
+
"epoch": 0.24,
|
120 |
+
"grad_norm": 5.5322418212890625,
|
121 |
+
"learning_rate": 0.00019319727891156462,
|
122 |
+
"loss": 1.5453,
|
123 |
+
"step": 150
|
124 |
+
},
|
125 |
+
{
|
126 |
+
"epoch": 0.25,
|
127 |
+
"grad_norm": 4.116984844207764,
|
128 |
+
"learning_rate": 0.00019274376417233562,
|
129 |
+
"loss": 1.394,
|
130 |
+
"step": 160
|
131 |
+
},
|
132 |
+
{
|
133 |
+
"epoch": 0.27,
|
134 |
+
"grad_norm": 3.141216278076172,
|
135 |
+
"learning_rate": 0.0001922902494331066,
|
136 |
+
"loss": 1.2375,
|
137 |
+
"step": 170
|
138 |
+
},
|
139 |
+
{
|
140 |
+
"epoch": 0.29,
|
141 |
+
"grad_norm": 6.414323329925537,
|
142 |
+
"learning_rate": 0.00019183673469387756,
|
143 |
+
"loss": 1.3073,
|
144 |
+
"step": 180
|
145 |
+
},
|
146 |
+
{
|
147 |
+
"epoch": 0.3,
|
148 |
+
"grad_norm": 5.794140338897705,
|
149 |
+
"learning_rate": 0.00019138321995464854,
|
150 |
+
"loss": 1.3405,
|
151 |
+
"step": 190
|
152 |
+
},
|
153 |
+
{
|
154 |
+
"epoch": 0.32,
|
155 |
+
"grad_norm": 4.384269714355469,
|
156 |
+
"learning_rate": 0.0001909297052154195,
|
157 |
+
"loss": 1.2568,
|
158 |
+
"step": 200
|
159 |
+
},
|
160 |
+
{
|
161 |
+
"epoch": 0.32,
|
162 |
+
"eval_accuracy": 0.7178571428571429,
|
163 |
+
"eval_loss": 1.0386934280395508,
|
164 |
+
"eval_runtime": 94.8513,
|
165 |
+
"eval_samples_per_second": 26.568,
|
166 |
+
"eval_steps_per_second": 3.321,
|
167 |
+
"step": 200
|
168 |
+
},
|
169 |
+
{
|
170 |
+
"epoch": 0.33,
|
171 |
+
"grad_norm": 2.881287097930908,
|
172 |
+
"learning_rate": 0.00019047619047619048,
|
173 |
+
"loss": 1.2329,
|
174 |
+
"step": 210
|
175 |
+
},
|
176 |
+
{
|
177 |
+
"epoch": 0.35,
|
178 |
+
"grad_norm": 4.77938985824585,
|
179 |
+
"learning_rate": 0.00019002267573696145,
|
180 |
+
"loss": 1.1439,
|
181 |
+
"step": 220
|
182 |
+
},
|
183 |
+
{
|
184 |
+
"epoch": 0.37,
|
185 |
+
"grad_norm": 5.865462303161621,
|
186 |
+
"learning_rate": 0.00018956916099773243,
|
187 |
+
"loss": 1.2314,
|
188 |
+
"step": 230
|
189 |
+
},
|
190 |
+
{
|
191 |
+
"epoch": 0.38,
|
192 |
+
"grad_norm": 3.464250326156616,
|
193 |
+
"learning_rate": 0.00018911564625850343,
|
194 |
+
"loss": 1.329,
|
195 |
+
"step": 240
|
196 |
+
},
|
197 |
+
{
|
198 |
+
"epoch": 0.4,
|
199 |
+
"grad_norm": 3.2501161098480225,
|
200 |
+
"learning_rate": 0.0001886621315192744,
|
201 |
+
"loss": 1.3277,
|
202 |
+
"step": 250
|
203 |
+
},
|
204 |
+
{
|
205 |
+
"epoch": 0.41,
|
206 |
+
"grad_norm": 5.26331901550293,
|
207 |
+
"learning_rate": 0.00018820861678004534,
|
208 |
+
"loss": 1.2876,
|
209 |
+
"step": 260
|
210 |
+
},
|
211 |
+
{
|
212 |
+
"epoch": 0.43,
|
213 |
+
"grad_norm": 2.62630295753479,
|
214 |
+
"learning_rate": 0.00018775510204081634,
|
215 |
+
"loss": 1.1428,
|
216 |
+
"step": 270
|
217 |
+
},
|
218 |
+
{
|
219 |
+
"epoch": 0.44,
|
220 |
+
"grad_norm": 6.121326923370361,
|
221 |
+
"learning_rate": 0.00018730158730158731,
|
222 |
+
"loss": 1.2277,
|
223 |
+
"step": 280
|
224 |
+
},
|
225 |
+
{
|
226 |
+
"epoch": 0.46,
|
227 |
+
"grad_norm": 5.415524005889893,
|
228 |
+
"learning_rate": 0.0001868480725623583,
|
229 |
+
"loss": 1.1641,
|
230 |
+
"step": 290
|
231 |
+
},
|
232 |
+
{
|
233 |
+
"epoch": 0.48,
|
234 |
+
"grad_norm": 7.849498271942139,
|
235 |
+
"learning_rate": 0.00018639455782312926,
|
236 |
+
"loss": 1.3145,
|
237 |
+
"step": 300
|
238 |
+
},
|
239 |
+
{
|
240 |
+
"epoch": 0.48,
|
241 |
+
"eval_accuracy": 0.7134920634920635,
|
242 |
+
"eval_loss": 1.0026524066925049,
|
243 |
+
"eval_runtime": 89.5917,
|
244 |
+
"eval_samples_per_second": 28.128,
|
245 |
+
"eval_steps_per_second": 3.516,
|
246 |
+
"step": 300
|
247 |
+
},
|
248 |
+
{
|
249 |
+
"epoch": 0.49,
|
250 |
+
"grad_norm": 3.9149835109710693,
|
251 |
+
"learning_rate": 0.00018594104308390023,
|
252 |
+
"loss": 1.1359,
|
253 |
+
"step": 310
|
254 |
+
},
|
255 |
+
{
|
256 |
+
"epoch": 0.51,
|
257 |
+
"grad_norm": 4.712550163269043,
|
258 |
+
"learning_rate": 0.0001854875283446712,
|
259 |
+
"loss": 1.1196,
|
260 |
+
"step": 320
|
261 |
+
},
|
262 |
+
{
|
263 |
+
"epoch": 0.52,
|
264 |
+
"grad_norm": 4.665726184844971,
|
265 |
+
"learning_rate": 0.0001850340136054422,
|
266 |
+
"loss": 1.1178,
|
267 |
+
"step": 330
|
268 |
+
},
|
269 |
+
{
|
270 |
+
"epoch": 0.54,
|
271 |
+
"grad_norm": 4.421199798583984,
|
272 |
+
"learning_rate": 0.00018458049886621315,
|
273 |
+
"loss": 1.093,
|
274 |
+
"step": 340
|
275 |
+
},
|
276 |
+
{
|
277 |
+
"epoch": 0.56,
|
278 |
+
"grad_norm": 5.4558305740356445,
|
279 |
+
"learning_rate": 0.00018412698412698412,
|
280 |
+
"loss": 1.0638,
|
281 |
+
"step": 350
|
282 |
+
},
|
283 |
+
{
|
284 |
+
"epoch": 0.57,
|
285 |
+
"grad_norm": 6.7150559425354,
|
286 |
+
"learning_rate": 0.00018367346938775512,
|
287 |
+
"loss": 1.21,
|
288 |
+
"step": 360
|
289 |
+
},
|
290 |
+
{
|
291 |
+
"epoch": 0.59,
|
292 |
+
"grad_norm": 4.524730205535889,
|
293 |
+
"learning_rate": 0.0001832199546485261,
|
294 |
+
"loss": 1.199,
|
295 |
+
"step": 370
|
296 |
+
},
|
297 |
+
{
|
298 |
+
"epoch": 0.6,
|
299 |
+
"grad_norm": 5.457512855529785,
|
300 |
+
"learning_rate": 0.00018276643990929706,
|
301 |
+
"loss": 1.202,
|
302 |
+
"step": 380
|
303 |
+
},
|
304 |
+
{
|
305 |
+
"epoch": 0.62,
|
306 |
+
"grad_norm": 5.54859733581543,
|
307 |
+
"learning_rate": 0.00018231292517006804,
|
308 |
+
"loss": 1.1671,
|
309 |
+
"step": 390
|
310 |
+
},
|
311 |
+
{
|
312 |
+
"epoch": 0.63,
|
313 |
+
"grad_norm": 3.217099905014038,
|
314 |
+
"learning_rate": 0.000181859410430839,
|
315 |
+
"loss": 1.0866,
|
316 |
+
"step": 400
|
317 |
+
},
|
318 |
+
{
|
319 |
+
"epoch": 0.63,
|
320 |
+
"eval_accuracy": 0.7376984126984127,
|
321 |
+
"eval_loss": 0.8882665038108826,
|
322 |
+
"eval_runtime": 94.504,
|
323 |
+
"eval_samples_per_second": 26.666,
|
324 |
+
"eval_steps_per_second": 3.333,
|
325 |
+
"step": 400
|
326 |
+
},
|
327 |
+
{
|
328 |
+
"epoch": 0.65,
|
329 |
+
"grad_norm": 5.335367202758789,
|
330 |
+
"learning_rate": 0.00018140589569161,
|
331 |
+
"loss": 1.0176,
|
332 |
+
"step": 410
|
333 |
+
},
|
334 |
+
{
|
335 |
+
"epoch": 0.67,
|
336 |
+
"grad_norm": 7.274291515350342,
|
337 |
+
"learning_rate": 0.00018099773242630387,
|
338 |
+
"loss": 1.2467,
|
339 |
+
"step": 420
|
340 |
+
},
|
341 |
+
{
|
342 |
+
"epoch": 0.68,
|
343 |
+
"grad_norm": 5.159976959228516,
|
344 |
+
"learning_rate": 0.00018054421768707484,
|
345 |
+
"loss": 1.127,
|
346 |
+
"step": 430
|
347 |
+
},
|
348 |
+
{
|
349 |
+
"epoch": 0.7,
|
350 |
+
"grad_norm": 5.351009845733643,
|
351 |
+
"learning_rate": 0.0001800907029478458,
|
352 |
+
"loss": 1.2382,
|
353 |
+
"step": 440
|
354 |
+
},
|
355 |
+
{
|
356 |
+
"epoch": 0.71,
|
357 |
+
"grad_norm": 4.435301303863525,
|
358 |
+
"learning_rate": 0.00017963718820861678,
|
359 |
+
"loss": 1.061,
|
360 |
+
"step": 450
|
361 |
+
},
|
362 |
+
{
|
363 |
+
"epoch": 0.73,
|
364 |
+
"grad_norm": 4.027517795562744,
|
365 |
+
"learning_rate": 0.00017918367346938776,
|
366 |
+
"loss": 1.0432,
|
367 |
+
"step": 460
|
368 |
+
},
|
369 |
+
{
|
370 |
+
"epoch": 0.75,
|
371 |
+
"grad_norm": 4.309961795806885,
|
372 |
+
"learning_rate": 0.00017873015873015876,
|
373 |
+
"loss": 0.9949,
|
374 |
+
"step": 470
|
375 |
+
},
|
376 |
+
{
|
377 |
+
"epoch": 0.76,
|
378 |
+
"grad_norm": 4.835757732391357,
|
379 |
+
"learning_rate": 0.00017827664399092973,
|
380 |
+
"loss": 1.1899,
|
381 |
+
"step": 480
|
382 |
+
},
|
383 |
+
{
|
384 |
+
"epoch": 0.78,
|
385 |
+
"grad_norm": 5.26571798324585,
|
386 |
+
"learning_rate": 0.00017782312925170067,
|
387 |
+
"loss": 1.1235,
|
388 |
+
"step": 490
|
389 |
+
},
|
390 |
+
{
|
391 |
+
"epoch": 0.79,
|
392 |
+
"grad_norm": 3.8406684398651123,
|
393 |
+
"learning_rate": 0.00017736961451247167,
|
394 |
+
"loss": 1.0036,
|
395 |
+
"step": 500
|
396 |
+
},
|
397 |
+
{
|
398 |
+
"epoch": 0.79,
|
399 |
+
"eval_accuracy": 0.7321428571428571,
|
400 |
+
"eval_loss": 0.897292971611023,
|
401 |
+
"eval_runtime": 96.2225,
|
402 |
+
"eval_samples_per_second": 26.189,
|
403 |
+
"eval_steps_per_second": 3.274,
|
404 |
+
"step": 500
|
405 |
+
},
|
406 |
+
{
|
407 |
+
"epoch": 0.81,
|
408 |
+
"grad_norm": 4.993399143218994,
|
409 |
+
"learning_rate": 0.00017691609977324264,
|
410 |
+
"loss": 0.8682,
|
411 |
+
"step": 510
|
412 |
+
},
|
413 |
+
{
|
414 |
+
"epoch": 0.83,
|
415 |
+
"grad_norm": 4.4026875495910645,
|
416 |
+
"learning_rate": 0.00017646258503401362,
|
417 |
+
"loss": 1.0603,
|
418 |
+
"step": 520
|
419 |
+
},
|
420 |
+
{
|
421 |
+
"epoch": 0.84,
|
422 |
+
"grad_norm": 4.832537651062012,
|
423 |
+
"learning_rate": 0.0001760090702947846,
|
424 |
+
"loss": 1.034,
|
425 |
+
"step": 530
|
426 |
+
},
|
427 |
+
{
|
428 |
+
"epoch": 0.86,
|
429 |
+
"grad_norm": 5.253382682800293,
|
430 |
+
"learning_rate": 0.00017555555555555556,
|
431 |
+
"loss": 0.9938,
|
432 |
+
"step": 540
|
433 |
+
},
|
434 |
+
{
|
435 |
+
"epoch": 0.87,
|
436 |
+
"grad_norm": 3.681997060775757,
|
437 |
+
"learning_rate": 0.00017510204081632653,
|
438 |
+
"loss": 1.0082,
|
439 |
+
"step": 550
|
440 |
+
},
|
441 |
+
{
|
442 |
+
"epoch": 0.89,
|
443 |
+
"grad_norm": 6.324045181274414,
|
444 |
+
"learning_rate": 0.0001746485260770975,
|
445 |
+
"loss": 0.9629,
|
446 |
+
"step": 560
|
447 |
+
},
|
448 |
+
{
|
449 |
+
"epoch": 0.9,
|
450 |
+
"grad_norm": 5.0340352058410645,
|
451 |
+
"learning_rate": 0.00017419501133786848,
|
452 |
+
"loss": 1.1184,
|
453 |
+
"step": 570
|
454 |
+
},
|
455 |
+
{
|
456 |
+
"epoch": 0.92,
|
457 |
+
"grad_norm": 3.532378673553467,
|
458 |
+
"learning_rate": 0.00017374149659863948,
|
459 |
+
"loss": 0.9167,
|
460 |
+
"step": 580
|
461 |
+
},
|
462 |
+
{
|
463 |
+
"epoch": 0.94,
|
464 |
+
"grad_norm": 5.029895305633545,
|
465 |
+
"learning_rate": 0.00017328798185941045,
|
466 |
+
"loss": 1.1213,
|
467 |
+
"step": 590
|
468 |
+
},
|
469 |
+
{
|
470 |
+
"epoch": 0.95,
|
471 |
+
"grad_norm": 4.585740566253662,
|
472 |
+
"learning_rate": 0.00017283446712018142,
|
473 |
+
"loss": 1.1811,
|
474 |
+
"step": 600
|
475 |
+
},
|
476 |
+
{
|
477 |
+
"epoch": 0.95,
|
478 |
+
"eval_accuracy": 0.7571428571428571,
|
479 |
+
"eval_loss": 0.8048315644264221,
|
480 |
+
"eval_runtime": 95.9399,
|
481 |
+
"eval_samples_per_second": 26.266,
|
482 |
+
"eval_steps_per_second": 3.283,
|
483 |
+
"step": 600
|
484 |
+
},
|
485 |
+
{
|
486 |
+
"epoch": 0.97,
|
487 |
+
"grad_norm": 2.9866397380828857,
|
488 |
+
"learning_rate": 0.0001723809523809524,
|
489 |
+
"loss": 1.2417,
|
490 |
+
"step": 610
|
491 |
+
},
|
492 |
+
{
|
493 |
+
"epoch": 0.98,
|
494 |
+
"grad_norm": 4.54673433303833,
|
495 |
+
"learning_rate": 0.00017192743764172337,
|
496 |
+
"loss": 1.1588,
|
497 |
+
"step": 620
|
498 |
+
},
|
499 |
+
{
|
500 |
+
"epoch": 1.0,
|
501 |
+
"grad_norm": 4.411011695861816,
|
502 |
+
"learning_rate": 0.00017147392290249434,
|
503 |
+
"loss": 0.9512,
|
504 |
+
"step": 630
|
505 |
+
},
|
506 |
+
{
|
507 |
+
"epoch": 1.02,
|
508 |
+
"grad_norm": 4.393170356750488,
|
509 |
+
"learning_rate": 0.0001710204081632653,
|
510 |
+
"loss": 0.9679,
|
511 |
+
"step": 640
|
512 |
+
},
|
513 |
+
{
|
514 |
+
"epoch": 1.03,
|
515 |
+
"grad_norm": 5.261455535888672,
|
516 |
+
"learning_rate": 0.00017056689342403628,
|
517 |
+
"loss": 0.9089,
|
518 |
+
"step": 650
|
519 |
+
},
|
520 |
+
{
|
521 |
+
"epoch": 1.05,
|
522 |
+
"grad_norm": 4.93878173828125,
|
523 |
+
"learning_rate": 0.00017011337868480726,
|
524 |
+
"loss": 0.8341,
|
525 |
+
"step": 660
|
526 |
+
},
|
527 |
+
{
|
528 |
+
"epoch": 1.06,
|
529 |
+
"grad_norm": 4.5593156814575195,
|
530 |
+
"learning_rate": 0.00016965986394557825,
|
531 |
+
"loss": 0.9952,
|
532 |
+
"step": 670
|
533 |
+
},
|
534 |
+
{
|
535 |
+
"epoch": 1.08,
|
536 |
+
"grad_norm": 3.9355390071868896,
|
537 |
+
"learning_rate": 0.0001692063492063492,
|
538 |
+
"loss": 0.9956,
|
539 |
+
"step": 680
|
540 |
+
},
|
541 |
+
{
|
542 |
+
"epoch": 1.1,
|
543 |
+
"grad_norm": 4.096402645111084,
|
544 |
+
"learning_rate": 0.00016875283446712017,
|
545 |
+
"loss": 0.9566,
|
546 |
+
"step": 690
|
547 |
+
},
|
548 |
+
{
|
549 |
+
"epoch": 1.11,
|
550 |
+
"grad_norm": 5.853695869445801,
|
551 |
+
"learning_rate": 0.00016829931972789117,
|
552 |
+
"loss": 0.9242,
|
553 |
+
"step": 700
|
554 |
+
},
|
555 |
+
{
|
556 |
+
"epoch": 1.11,
|
557 |
+
"eval_accuracy": 0.7273809523809524,
|
558 |
+
"eval_loss": 0.9095195531845093,
|
559 |
+
"eval_runtime": 92.7769,
|
560 |
+
"eval_samples_per_second": 27.162,
|
561 |
+
"eval_steps_per_second": 3.395,
|
562 |
+
"step": 700
|
563 |
+
},
|
564 |
+
{
|
565 |
+
"epoch": 1.13,
|
566 |
+
"grad_norm": 5.18225622177124,
|
567 |
+
"learning_rate": 0.00016784580498866214,
|
568 |
+
"loss": 1.1815,
|
569 |
+
"step": 710
|
570 |
+
},
|
571 |
+
{
|
572 |
+
"epoch": 1.14,
|
573 |
+
"grad_norm": 6.094394683837891,
|
574 |
+
"learning_rate": 0.00016739229024943312,
|
575 |
+
"loss": 1.0088,
|
576 |
+
"step": 720
|
577 |
+
},
|
578 |
+
{
|
579 |
+
"epoch": 1.16,
|
580 |
+
"grad_norm": 3.388333320617676,
|
581 |
+
"learning_rate": 0.0001669387755102041,
|
582 |
+
"loss": 1.0219,
|
583 |
+
"step": 730
|
584 |
+
},
|
585 |
+
{
|
586 |
+
"epoch": 1.17,
|
587 |
+
"grad_norm": 2.702335834503174,
|
588 |
+
"learning_rate": 0.00016648526077097506,
|
589 |
+
"loss": 0.995,
|
590 |
+
"step": 740
|
591 |
+
},
|
592 |
+
{
|
593 |
+
"epoch": 1.19,
|
594 |
+
"grad_norm": 6.5921735763549805,
|
595 |
+
"learning_rate": 0.00016603174603174606,
|
596 |
+
"loss": 1.0336,
|
597 |
+
"step": 750
|
598 |
+
},
|
599 |
+
{
|
600 |
+
"epoch": 1.21,
|
601 |
+
"grad_norm": 7.6583781242370605,
|
602 |
+
"learning_rate": 0.000165578231292517,
|
603 |
+
"loss": 0.8889,
|
604 |
+
"step": 760
|
605 |
+
},
|
606 |
+
{
|
607 |
+
"epoch": 1.22,
|
608 |
+
"grad_norm": 5.093008518218994,
|
609 |
+
"learning_rate": 0.00016512471655328798,
|
610 |
+
"loss": 0.8492,
|
611 |
+
"step": 770
|
612 |
+
},
|
613 |
+
{
|
614 |
+
"epoch": 1.24,
|
615 |
+
"grad_norm": 4.372059345245361,
|
616 |
+
"learning_rate": 0.00016467120181405898,
|
617 |
+
"loss": 0.8115,
|
618 |
+
"step": 780
|
619 |
+
},
|
620 |
+
{
|
621 |
+
"epoch": 1.25,
|
622 |
+
"grad_norm": 4.1783857345581055,
|
623 |
+
"learning_rate": 0.00016421768707482995,
|
624 |
+
"loss": 0.834,
|
625 |
+
"step": 790
|
626 |
+
},
|
627 |
+
{
|
628 |
+
"epoch": 1.27,
|
629 |
+
"grad_norm": 4.295966148376465,
|
630 |
+
"learning_rate": 0.0001638095238095238,
|
631 |
+
"loss": 0.9477,
|
632 |
+
"step": 800
|
633 |
+
},
|
634 |
+
{
|
635 |
+
"epoch": 1.27,
|
636 |
+
"eval_accuracy": 0.7619047619047619,
|
637 |
+
"eval_loss": 0.8036767244338989,
|
638 |
+
"eval_runtime": 89.9677,
|
639 |
+
"eval_samples_per_second": 28.01,
|
640 |
+
"eval_steps_per_second": 3.501,
|
641 |
+
"step": 800
|
642 |
+
},
|
643 |
+
{
|
644 |
+
"epoch": 1.29,
|
645 |
+
"grad_norm": 4.976074695587158,
|
646 |
+
"learning_rate": 0.0001633560090702948,
|
647 |
+
"loss": 0.8778,
|
648 |
+
"step": 810
|
649 |
+
},
|
650 |
+
{
|
651 |
+
"epoch": 1.3,
|
652 |
+
"grad_norm": 3.34804105758667,
|
653 |
+
"learning_rate": 0.00016290249433106578,
|
654 |
+
"loss": 0.9856,
|
655 |
+
"step": 820
|
656 |
+
},
|
657 |
+
{
|
658 |
+
"epoch": 1.32,
|
659 |
+
"grad_norm": 6.416792869567871,
|
660 |
+
"learning_rate": 0.00016244897959183672,
|
661 |
+
"loss": 0.9829,
|
662 |
+
"step": 830
|
663 |
+
},
|
664 |
+
{
|
665 |
+
"epoch": 1.33,
|
666 |
+
"grad_norm": 5.707892894744873,
|
667 |
+
"learning_rate": 0.00016199546485260772,
|
668 |
+
"loss": 0.9397,
|
669 |
+
"step": 840
|
670 |
+
},
|
671 |
+
{
|
672 |
+
"epoch": 1.35,
|
673 |
+
"grad_norm": 4.620942115783691,
|
674 |
+
"learning_rate": 0.0001615419501133787,
|
675 |
+
"loss": 1.078,
|
676 |
+
"step": 850
|
677 |
+
},
|
678 |
+
{
|
679 |
+
"epoch": 1.37,
|
680 |
+
"grad_norm": 4.452626705169678,
|
681 |
+
"learning_rate": 0.00016108843537414967,
|
682 |
+
"loss": 0.9531,
|
683 |
+
"step": 860
|
684 |
+
},
|
685 |
+
{
|
686 |
+
"epoch": 1.38,
|
687 |
+
"grad_norm": 5.697545528411865,
|
688 |
+
"learning_rate": 0.00016063492063492064,
|
689 |
+
"loss": 1.0438,
|
690 |
+
"step": 870
|
691 |
+
},
|
692 |
+
{
|
693 |
+
"epoch": 1.4,
|
694 |
+
"grad_norm": 4.365375518798828,
|
695 |
+
"learning_rate": 0.0001601814058956916,
|
696 |
+
"loss": 0.9024,
|
697 |
+
"step": 880
|
698 |
+
},
|
699 |
+
{
|
700 |
+
"epoch": 1.41,
|
701 |
+
"grad_norm": 5.501079082489014,
|
702 |
+
"learning_rate": 0.00015972789115646259,
|
703 |
+
"loss": 0.9091,
|
704 |
+
"step": 890
|
705 |
+
},
|
706 |
+
{
|
707 |
+
"epoch": 1.43,
|
708 |
+
"grad_norm": 4.409488201141357,
|
709 |
+
"learning_rate": 0.00015927437641723358,
|
710 |
+
"loss": 0.8634,
|
711 |
+
"step": 900
|
712 |
+
},
|
713 |
+
{
|
714 |
+
"epoch": 1.43,
|
715 |
+
"eval_accuracy": 0.7642857142857142,
|
716 |
+
"eval_loss": 0.7937940359115601,
|
717 |
+
"eval_runtime": 92.0164,
|
718 |
+
"eval_samples_per_second": 27.386,
|
719 |
+
"eval_steps_per_second": 3.423,
|
720 |
+
"step": 900
|
721 |
+
},
|
722 |
+
{
|
723 |
+
"epoch": 1.44,
|
724 |
+
"grad_norm": 4.543234825134277,
|
725 |
+
"learning_rate": 0.00015882086167800453,
|
726 |
+
"loss": 0.7896,
|
727 |
+
"step": 910
|
728 |
+
},
|
729 |
+
{
|
730 |
+
"epoch": 1.46,
|
731 |
+
"grad_norm": 3.8954508304595947,
|
732 |
+
"learning_rate": 0.0001583673469387755,
|
733 |
+
"loss": 0.9597,
|
734 |
+
"step": 920
|
735 |
+
},
|
736 |
+
{
|
737 |
+
"epoch": 1.48,
|
738 |
+
"grad_norm": 7.744637489318848,
|
739 |
+
"learning_rate": 0.0001579138321995465,
|
740 |
+
"loss": 0.9585,
|
741 |
+
"step": 930
|
742 |
+
},
|
743 |
+
{
|
744 |
+
"epoch": 1.49,
|
745 |
+
"grad_norm": 3.619973659515381,
|
746 |
+
"learning_rate": 0.00015746031746031747,
|
747 |
+
"loss": 0.826,
|
748 |
+
"step": 940
|
749 |
+
},
|
750 |
+
{
|
751 |
+
"epoch": 1.51,
|
752 |
+
"grad_norm": 10.431225776672363,
|
753 |
+
"learning_rate": 0.00015700680272108845,
|
754 |
+
"loss": 0.9651,
|
755 |
+
"step": 950
|
756 |
+
},
|
757 |
+
{
|
758 |
+
"epoch": 1.52,
|
759 |
+
"grad_norm": 4.897637367248535,
|
760 |
+
"learning_rate": 0.00015655328798185942,
|
761 |
+
"loss": 0.9136,
|
762 |
+
"step": 960
|
763 |
+
},
|
764 |
+
{
|
765 |
+
"epoch": 1.54,
|
766 |
+
"grad_norm": 2.429625988006592,
|
767 |
+
"learning_rate": 0.0001560997732426304,
|
768 |
+
"loss": 0.9676,
|
769 |
+
"step": 970
|
770 |
+
},
|
771 |
+
{
|
772 |
+
"epoch": 1.56,
|
773 |
+
"grad_norm": 2.8244125843048096,
|
774 |
+
"learning_rate": 0.00015564625850340136,
|
775 |
+
"loss": 0.8796,
|
776 |
+
"step": 980
|
777 |
+
},
|
778 |
+
{
|
779 |
+
"epoch": 1.57,
|
780 |
+
"grad_norm": 3.9079954624176025,
|
781 |
+
"learning_rate": 0.00015519274376417234,
|
782 |
+
"loss": 0.7595,
|
783 |
+
"step": 990
|
784 |
+
},
|
785 |
+
{
|
786 |
+
"epoch": 1.59,
|
787 |
+
"grad_norm": 8.262408256530762,
|
788 |
+
"learning_rate": 0.0001547392290249433,
|
789 |
+
"loss": 1.0098,
|
790 |
+
"step": 1000
|
791 |
+
},
|
792 |
+
{
|
793 |
+
"epoch": 1.59,
|
794 |
+
"eval_accuracy": 0.7765873015873016,
|
795 |
+
"eval_loss": 0.7327961325645447,
|
796 |
+
"eval_runtime": 90.6084,
|
797 |
+
"eval_samples_per_second": 27.812,
|
798 |
+
"eval_steps_per_second": 3.477,
|
799 |
+
"step": 1000
|
800 |
+
},
|
801 |
+
{
|
802 |
+
"epoch": 1.6,
|
803 |
+
"grad_norm": 5.290775299072266,
|
804 |
+
"learning_rate": 0.0001542857142857143,
|
805 |
+
"loss": 0.8282,
|
806 |
+
"step": 1010
|
807 |
+
},
|
808 |
+
{
|
809 |
+
"epoch": 1.62,
|
810 |
+
"grad_norm": 5.40395450592041,
|
811 |
+
"learning_rate": 0.00015383219954648528,
|
812 |
+
"loss": 1.0232,
|
813 |
+
"step": 1020
|
814 |
+
},
|
815 |
+
{
|
816 |
+
"epoch": 1.63,
|
817 |
+
"grad_norm": 6.36408805847168,
|
818 |
+
"learning_rate": 0.00015337868480725622,
|
819 |
+
"loss": 0.9572,
|
820 |
+
"step": 1030
|
821 |
+
},
|
822 |
+
{
|
823 |
+
"epoch": 1.65,
|
824 |
+
"grad_norm": 3.8068315982818604,
|
825 |
+
"learning_rate": 0.00015292517006802722,
|
826 |
+
"loss": 0.8457,
|
827 |
+
"step": 1040
|
828 |
+
},
|
829 |
+
{
|
830 |
+
"epoch": 1.67,
|
831 |
+
"grad_norm": 5.893327236175537,
|
832 |
+
"learning_rate": 0.0001524716553287982,
|
833 |
+
"loss": 0.915,
|
834 |
+
"step": 1050
|
835 |
+
},
|
836 |
+
{
|
837 |
+
"epoch": 1.68,
|
838 |
+
"grad_norm": 4.604687213897705,
|
839 |
+
"learning_rate": 0.00015201814058956917,
|
840 |
+
"loss": 0.9143,
|
841 |
+
"step": 1060
|
842 |
+
},
|
843 |
+
{
|
844 |
+
"epoch": 1.7,
|
845 |
+
"grad_norm": 4.973442077636719,
|
846 |
+
"learning_rate": 0.00015156462585034014,
|
847 |
+
"loss": 0.8211,
|
848 |
+
"step": 1070
|
849 |
+
},
|
850 |
+
{
|
851 |
+
"epoch": 1.71,
|
852 |
+
"grad_norm": 4.463946342468262,
|
853 |
+
"learning_rate": 0.0001511111111111111,
|
854 |
+
"loss": 0.8649,
|
855 |
+
"step": 1080
|
856 |
+
},
|
857 |
+
{
|
858 |
+
"epoch": 1.73,
|
859 |
+
"grad_norm": 4.718800067901611,
|
860 |
+
"learning_rate": 0.0001506575963718821,
|
861 |
+
"loss": 0.7986,
|
862 |
+
"step": 1090
|
863 |
+
},
|
864 |
+
{
|
865 |
+
"epoch": 1.75,
|
866 |
+
"grad_norm": 4.523365020751953,
|
867 |
+
"learning_rate": 0.00015020408163265306,
|
868 |
+
"loss": 0.8176,
|
869 |
+
"step": 1100
|
870 |
+
},
|
871 |
+
{
|
872 |
+
"epoch": 1.75,
|
873 |
+
"eval_accuracy": 0.7515873015873016,
|
874 |
+
"eval_loss": 0.8064602017402649,
|
875 |
+
"eval_runtime": 93.1844,
|
876 |
+
"eval_samples_per_second": 27.043,
|
877 |
+
"eval_steps_per_second": 3.38,
|
878 |
+
"step": 1100
|
879 |
+
},
|
880 |
+
{
|
881 |
+
"epoch": 1.76,
|
882 |
+
"grad_norm": 5.417792797088623,
|
883 |
+
"learning_rate": 0.00014975056689342403,
|
884 |
+
"loss": 1.0616,
|
885 |
+
"step": 1110
|
886 |
+
},
|
887 |
+
{
|
888 |
+
"epoch": 1.78,
|
889 |
+
"grad_norm": 6.2752275466918945,
|
890 |
+
"learning_rate": 0.00014929705215419503,
|
891 |
+
"loss": 0.9484,
|
892 |
+
"step": 1120
|
893 |
+
},
|
894 |
+
{
|
895 |
+
"epoch": 1.79,
|
896 |
+
"grad_norm": 6.395713806152344,
|
897 |
+
"learning_rate": 0.000148843537414966,
|
898 |
+
"loss": 1.0357,
|
899 |
+
"step": 1130
|
900 |
+
},
|
901 |
+
{
|
902 |
+
"epoch": 1.81,
|
903 |
+
"grad_norm": 4.707973003387451,
|
904 |
+
"learning_rate": 0.00014839002267573697,
|
905 |
+
"loss": 0.922,
|
906 |
+
"step": 1140
|
907 |
+
},
|
908 |
+
{
|
909 |
+
"epoch": 1.83,
|
910 |
+
"grad_norm": 6.663784980773926,
|
911 |
+
"learning_rate": 0.00014793650793650795,
|
912 |
+
"loss": 1.141,
|
913 |
+
"step": 1150
|
914 |
+
},
|
915 |
+
{
|
916 |
+
"epoch": 1.84,
|
917 |
+
"grad_norm": 4.041499137878418,
|
918 |
+
"learning_rate": 0.00014748299319727892,
|
919 |
+
"loss": 0.9529,
|
920 |
+
"step": 1160
|
921 |
+
},
|
922 |
+
{
|
923 |
+
"epoch": 1.86,
|
924 |
+
"grad_norm": 5.212307453155518,
|
925 |
+
"learning_rate": 0.0001470294784580499,
|
926 |
+
"loss": 0.6781,
|
927 |
+
"step": 1170
|
928 |
+
},
|
929 |
+
{
|
930 |
+
"epoch": 1.87,
|
931 |
+
"grad_norm": 5.991590976715088,
|
932 |
+
"learning_rate": 0.00014657596371882086,
|
933 |
+
"loss": 0.8701,
|
934 |
+
"step": 1180
|
935 |
+
},
|
936 |
+
{
|
937 |
+
"epoch": 1.89,
|
938 |
+
"grad_norm": 8.68984317779541,
|
939 |
+
"learning_rate": 0.00014612244897959183,
|
940 |
+
"loss": 1.0802,
|
941 |
+
"step": 1190
|
942 |
+
},
|
943 |
+
{
|
944 |
+
"epoch": 1.9,
|
945 |
+
"grad_norm": 6.660585403442383,
|
946 |
+
"learning_rate": 0.0001456689342403628,
|
947 |
+
"loss": 0.8072,
|
948 |
+
"step": 1200
|
949 |
+
},
|
950 |
+
{
|
951 |
+
"epoch": 1.9,
|
952 |
+
"eval_accuracy": 0.7694444444444445,
|
953 |
+
"eval_loss": 0.77680903673172,
|
954 |
+
"eval_runtime": 91.7003,
|
955 |
+
"eval_samples_per_second": 27.481,
|
956 |
+
"eval_steps_per_second": 3.435,
|
957 |
+
"step": 1200
|
958 |
+
},
|
959 |
+
{
|
960 |
+
"epoch": 1.92,
|
961 |
+
"grad_norm": 3.435088872909546,
|
962 |
+
"learning_rate": 0.0001452154195011338,
|
963 |
+
"loss": 1.0272,
|
964 |
+
"step": 1210
|
965 |
+
},
|
966 |
+
{
|
967 |
+
"epoch": 1.94,
|
968 |
+
"grad_norm": 3.200514078140259,
|
969 |
+
"learning_rate": 0.00014476190476190475,
|
970 |
+
"loss": 1.0246,
|
971 |
+
"step": 1220
|
972 |
+
},
|
973 |
+
{
|
974 |
+
"epoch": 1.95,
|
975 |
+
"grad_norm": 3.882340669631958,
|
976 |
+
"learning_rate": 0.00014430839002267575,
|
977 |
+
"loss": 0.7745,
|
978 |
+
"step": 1230
|
979 |
+
},
|
980 |
+
{
|
981 |
+
"epoch": 1.97,
|
982 |
+
"grad_norm": 3.1602838039398193,
|
983 |
+
"learning_rate": 0.00014385487528344672,
|
984 |
+
"loss": 0.9499,
|
985 |
+
"step": 1240
|
986 |
+
},
|
987 |
+
{
|
988 |
+
"epoch": 1.98,
|
989 |
+
"grad_norm": 2.896543502807617,
|
990 |
+
"learning_rate": 0.0001434013605442177,
|
991 |
+
"loss": 0.9155,
|
992 |
+
"step": 1250
|
993 |
+
},
|
994 |
+
{
|
995 |
+
"epoch": 2.0,
|
996 |
+
"grad_norm": 4.671875476837158,
|
997 |
+
"learning_rate": 0.00014294784580498867,
|
998 |
+
"loss": 0.8183,
|
999 |
+
"step": 1260
|
1000 |
+
},
|
1001 |
+
{
|
1002 |
+
"epoch": 2.02,
|
1003 |
+
"grad_norm": 6.149994373321533,
|
1004 |
+
"learning_rate": 0.00014249433106575964,
|
1005 |
+
"loss": 0.8043,
|
1006 |
+
"step": 1270
|
1007 |
+
},
|
1008 |
+
{
|
1009 |
+
"epoch": 2.03,
|
1010 |
+
"grad_norm": 4.373509407043457,
|
1011 |
+
"learning_rate": 0.0001420408163265306,
|
1012 |
+
"loss": 0.7205,
|
1013 |
+
"step": 1280
|
1014 |
+
},
|
1015 |
+
{
|
1016 |
+
"epoch": 2.05,
|
1017 |
+
"grad_norm": 5.70250940322876,
|
1018 |
+
"learning_rate": 0.0001415873015873016,
|
1019 |
+
"loss": 0.8109,
|
1020 |
+
"step": 1290
|
1021 |
+
},
|
1022 |
+
{
|
1023 |
+
"epoch": 2.06,
|
1024 |
+
"grad_norm": 4.3769683837890625,
|
1025 |
+
"learning_rate": 0.00014113378684807256,
|
1026 |
+
"loss": 0.7739,
|
1027 |
+
"step": 1300
|
1028 |
+
},
|
1029 |
+
{
|
1030 |
+
"epoch": 2.06,
|
1031 |
+
"eval_accuracy": 0.7726190476190476,
|
1032 |
+
"eval_loss": 0.7623938322067261,
|
1033 |
+
"eval_runtime": 108.4142,
|
1034 |
+
"eval_samples_per_second": 23.244,
|
1035 |
+
"eval_steps_per_second": 2.906,
|
1036 |
+
"step": 1300
|
1037 |
+
},
|
1038 |
+
{
|
1039 |
+
"epoch": 2.08,
|
1040 |
+
"grad_norm": 8.936156272888184,
|
1041 |
+
"learning_rate": 0.00014068027210884353,
|
1042 |
+
"loss": 0.7361,
|
1043 |
+
"step": 1310
|
1044 |
+
},
|
1045 |
+
{
|
1046 |
+
"epoch": 2.1,
|
1047 |
+
"grad_norm": 6.855538845062256,
|
1048 |
+
"learning_rate": 0.00014022675736961453,
|
1049 |
+
"loss": 0.7778,
|
1050 |
+
"step": 1320
|
1051 |
+
},
|
1052 |
+
{
|
1053 |
+
"epoch": 2.11,
|
1054 |
+
"grad_norm": 2.5195322036743164,
|
1055 |
+
"learning_rate": 0.0001397732426303855,
|
1056 |
+
"loss": 0.7778,
|
1057 |
+
"step": 1330
|
1058 |
+
},
|
1059 |
+
{
|
1060 |
+
"epoch": 2.13,
|
1061 |
+
"grad_norm": 4.916295051574707,
|
1062 |
+
"learning_rate": 0.00013931972789115645,
|
1063 |
+
"loss": 0.8522,
|
1064 |
+
"step": 1340
|
1065 |
+
},
|
1066 |
+
{
|
1067 |
+
"epoch": 2.14,
|
1068 |
+
"grad_norm": 5.055403232574463,
|
1069 |
+
"learning_rate": 0.00013886621315192745,
|
1070 |
+
"loss": 0.6851,
|
1071 |
+
"step": 1350
|
1072 |
+
},
|
1073 |
+
{
|
1074 |
+
"epoch": 2.16,
|
1075 |
+
"grad_norm": 5.334274768829346,
|
1076 |
+
"learning_rate": 0.00013841269841269842,
|
1077 |
+
"loss": 0.9657,
|
1078 |
+
"step": 1360
|
1079 |
+
},
|
1080 |
+
{
|
1081 |
+
"epoch": 2.17,
|
1082 |
+
"grad_norm": 6.083943843841553,
|
1083 |
+
"learning_rate": 0.00013795918367346942,
|
1084 |
+
"loss": 0.6776,
|
1085 |
+
"step": 1370
|
1086 |
+
},
|
1087 |
+
{
|
1088 |
+
"epoch": 2.19,
|
1089 |
+
"grad_norm": 4.362452983856201,
|
1090 |
+
"learning_rate": 0.00013750566893424036,
|
1091 |
+
"loss": 0.7703,
|
1092 |
+
"step": 1380
|
1093 |
+
},
|
1094 |
+
{
|
1095 |
+
"epoch": 2.21,
|
1096 |
+
"grad_norm": 6.978400707244873,
|
1097 |
+
"learning_rate": 0.00013705215419501133,
|
1098 |
+
"loss": 0.7911,
|
1099 |
+
"step": 1390
|
1100 |
+
},
|
1101 |
+
{
|
1102 |
+
"epoch": 2.22,
|
1103 |
+
"grad_norm": 4.561004638671875,
|
1104 |
+
"learning_rate": 0.00013659863945578233,
|
1105 |
+
"loss": 0.6851,
|
1106 |
+
"step": 1400
|
1107 |
+
},
|
1108 |
+
{
|
1109 |
+
"epoch": 2.22,
|
1110 |
+
"eval_accuracy": 0.794047619047619,
|
1111 |
+
"eval_loss": 0.668690025806427,
|
1112 |
+
"eval_runtime": 91.4622,
|
1113 |
+
"eval_samples_per_second": 27.552,
|
1114 |
+
"eval_steps_per_second": 3.444,
|
1115 |
+
"step": 1400
|
1116 |
+
},
|
1117 |
+
{
|
1118 |
+
"epoch": 2.24,
|
1119 |
+
"grad_norm": 4.068347930908203,
|
1120 |
+
"learning_rate": 0.0001361451247165533,
|
1121 |
+
"loss": 0.6705,
|
1122 |
+
"step": 1410
|
1123 |
+
},
|
1124 |
+
{
|
1125 |
+
"epoch": 2.25,
|
1126 |
+
"grad_norm": 4.628905773162842,
|
1127 |
+
"learning_rate": 0.00013569160997732425,
|
1128 |
+
"loss": 0.8955,
|
1129 |
+
"step": 1420
|
1130 |
+
},
|
1131 |
+
{
|
1132 |
+
"epoch": 2.27,
|
1133 |
+
"grad_norm": 6.214323997497559,
|
1134 |
+
"learning_rate": 0.00013523809523809525,
|
1135 |
+
"loss": 0.785,
|
1136 |
+
"step": 1430
|
1137 |
+
},
|
1138 |
+
{
|
1139 |
+
"epoch": 2.29,
|
1140 |
+
"grad_norm": 3.4356954097747803,
|
1141 |
+
"learning_rate": 0.00013478458049886622,
|
1142 |
+
"loss": 0.6415,
|
1143 |
+
"step": 1440
|
1144 |
+
},
|
1145 |
+
{
|
1146 |
+
"epoch": 2.3,
|
1147 |
+
"grad_norm": 6.76524019241333,
|
1148 |
+
"learning_rate": 0.0001343310657596372,
|
1149 |
+
"loss": 0.8914,
|
1150 |
+
"step": 1450
|
1151 |
+
},
|
1152 |
+
{
|
1153 |
+
"epoch": 2.32,
|
1154 |
+
"grad_norm": 4.742693901062012,
|
1155 |
+
"learning_rate": 0.00013387755102040817,
|
1156 |
+
"loss": 0.8758,
|
1157 |
+
"step": 1460
|
1158 |
+
},
|
1159 |
+
{
|
1160 |
+
"epoch": 2.33,
|
1161 |
+
"grad_norm": 3.940936326980591,
|
1162 |
+
"learning_rate": 0.00013342403628117914,
|
1163 |
+
"loss": 0.6984,
|
1164 |
+
"step": 1470
|
1165 |
+
},
|
1166 |
+
{
|
1167 |
+
"epoch": 2.35,
|
1168 |
+
"grad_norm": 7.005272388458252,
|
1169 |
+
"learning_rate": 0.0001329705215419501,
|
1170 |
+
"loss": 0.833,
|
1171 |
+
"step": 1480
|
1172 |
+
},
|
1173 |
+
{
|
1174 |
+
"epoch": 2.37,
|
1175 |
+
"grad_norm": 5.6659722328186035,
|
1176 |
+
"learning_rate": 0.0001325170068027211,
|
1177 |
+
"loss": 0.7352,
|
1178 |
+
"step": 1490
|
1179 |
+
},
|
1180 |
+
{
|
1181 |
+
"epoch": 2.38,
|
1182 |
+
"grad_norm": 4.9742045402526855,
|
1183 |
+
"learning_rate": 0.00013206349206349206,
|
1184 |
+
"loss": 0.7496,
|
1185 |
+
"step": 1500
|
1186 |
+
},
|
1187 |
+
{
|
1188 |
+
"epoch": 2.38,
|
1189 |
+
"eval_accuracy": 0.7948412698412698,
|
1190 |
+
"eval_loss": 0.6806091070175171,
|
1191 |
+
"eval_runtime": 91.1192,
|
1192 |
+
"eval_samples_per_second": 27.656,
|
1193 |
+
"eval_steps_per_second": 3.457,
|
1194 |
+
"step": 1500
|
1195 |
+
},
|
1196 |
+
{
|
1197 |
+
"epoch": 2.4,
|
1198 |
+
"grad_norm": 5.499560832977295,
|
1199 |
+
"learning_rate": 0.00013160997732426303,
|
1200 |
+
"loss": 0.8274,
|
1201 |
+
"step": 1510
|
1202 |
+
},
|
1203 |
+
{
|
1204 |
+
"epoch": 2.41,
|
1205 |
+
"grad_norm": 4.391964435577393,
|
1206 |
+
"learning_rate": 0.00013115646258503403,
|
1207 |
+
"loss": 0.7892,
|
1208 |
+
"step": 1520
|
1209 |
+
},
|
1210 |
+
{
|
1211 |
+
"epoch": 2.43,
|
1212 |
+
"grad_norm": 4.317266464233398,
|
1213 |
+
"learning_rate": 0.000130702947845805,
|
1214 |
+
"loss": 0.7462,
|
1215 |
+
"step": 1530
|
1216 |
+
},
|
1217 |
+
{
|
1218 |
+
"epoch": 2.44,
|
1219 |
+
"grad_norm": 3.7989251613616943,
|
1220 |
+
"learning_rate": 0.00013024943310657597,
|
1221 |
+
"loss": 0.8322,
|
1222 |
+
"step": 1540
|
1223 |
+
},
|
1224 |
+
{
|
1225 |
+
"epoch": 2.46,
|
1226 |
+
"grad_norm": 4.737931251525879,
|
1227 |
+
"learning_rate": 0.00012979591836734695,
|
1228 |
+
"loss": 0.9,
|
1229 |
+
"step": 1550
|
1230 |
+
},
|
1231 |
+
{
|
1232 |
+
"epoch": 2.48,
|
1233 |
+
"grad_norm": 2.4748082160949707,
|
1234 |
+
"learning_rate": 0.00012934240362811792,
|
1235 |
+
"loss": 0.7613,
|
1236 |
+
"step": 1560
|
1237 |
+
},
|
1238 |
+
{
|
1239 |
+
"epoch": 2.49,
|
1240 |
+
"grad_norm": 5.137518882751465,
|
1241 |
+
"learning_rate": 0.00012888888888888892,
|
1242 |
+
"loss": 0.8596,
|
1243 |
+
"step": 1570
|
1244 |
+
},
|
1245 |
+
{
|
1246 |
+
"epoch": 2.51,
|
1247 |
+
"grad_norm": 3.9287266731262207,
|
1248 |
+
"learning_rate": 0.00012843537414965986,
|
1249 |
+
"loss": 0.9221,
|
1250 |
+
"step": 1580
|
1251 |
+
},
|
1252 |
+
{
|
1253 |
+
"epoch": 2.52,
|
1254 |
+
"grad_norm": 3.864816665649414,
|
1255 |
+
"learning_rate": 0.00012798185941043083,
|
1256 |
+
"loss": 0.6858,
|
1257 |
+
"step": 1590
|
1258 |
+
},
|
1259 |
+
{
|
1260 |
+
"epoch": 2.54,
|
1261 |
+
"grad_norm": 3.6453895568847656,
|
1262 |
+
"learning_rate": 0.00012752834467120183,
|
1263 |
+
"loss": 0.7352,
|
1264 |
+
"step": 1600
|
1265 |
+
},
|
1266 |
+
{
|
1267 |
+
"epoch": 2.54,
|
1268 |
+
"eval_accuracy": 0.7896825396825397,
|
1269 |
+
"eval_loss": 0.6942620277404785,
|
1270 |
+
"eval_runtime": 90.1988,
|
1271 |
+
"eval_samples_per_second": 27.938,
|
1272 |
+
"eval_steps_per_second": 3.492,
|
1273 |
+
"step": 1600
|
1274 |
+
},
|
1275 |
+
{
|
1276 |
+
"epoch": 2.56,
|
1277 |
+
"grad_norm": 6.48276424407959,
|
1278 |
+
"learning_rate": 0.0001270748299319728,
|
1279 |
+
"loss": 0.7989,
|
1280 |
+
"step": 1610
|
1281 |
+
},
|
1282 |
+
{
|
1283 |
+
"epoch": 2.57,
|
1284 |
+
"grad_norm": 3.8373072147369385,
|
1285 |
+
"learning_rate": 0.00012662131519274375,
|
1286 |
+
"loss": 0.7562,
|
1287 |
+
"step": 1620
|
1288 |
+
},
|
1289 |
+
{
|
1290 |
+
"epoch": 2.59,
|
1291 |
+
"grad_norm": 5.370635986328125,
|
1292 |
+
"learning_rate": 0.00012616780045351475,
|
1293 |
+
"loss": 0.8958,
|
1294 |
+
"step": 1630
|
1295 |
+
},
|
1296 |
+
{
|
1297 |
+
"epoch": 2.6,
|
1298 |
+
"grad_norm": 2.2488410472869873,
|
1299 |
+
"learning_rate": 0.00012571428571428572,
|
1300 |
+
"loss": 0.8911,
|
1301 |
+
"step": 1640
|
1302 |
+
},
|
1303 |
+
{
|
1304 |
+
"epoch": 2.62,
|
1305 |
+
"grad_norm": 4.261588096618652,
|
1306 |
+
"learning_rate": 0.0001252607709750567,
|
1307 |
+
"loss": 0.7508,
|
1308 |
+
"step": 1650
|
1309 |
+
},
|
1310 |
+
{
|
1311 |
+
"epoch": 2.63,
|
1312 |
+
"grad_norm": 4.3199286460876465,
|
1313 |
+
"learning_rate": 0.00012480725623582767,
|
1314 |
+
"loss": 0.6107,
|
1315 |
+
"step": 1660
|
1316 |
+
},
|
1317 |
+
{
|
1318 |
+
"epoch": 2.65,
|
1319 |
+
"grad_norm": 5.610477447509766,
|
1320 |
+
"learning_rate": 0.00012435374149659864,
|
1321 |
+
"loss": 0.5786,
|
1322 |
+
"step": 1670
|
1323 |
+
},
|
1324 |
+
{
|
1325 |
+
"epoch": 2.67,
|
1326 |
+
"grad_norm": 6.289084434509277,
|
1327 |
+
"learning_rate": 0.00012390022675736964,
|
1328 |
+
"loss": 0.5845,
|
1329 |
+
"step": 1680
|
1330 |
+
},
|
1331 |
+
{
|
1332 |
+
"epoch": 2.68,
|
1333 |
+
"grad_norm": 3.4954001903533936,
|
1334 |
+
"learning_rate": 0.0001234467120181406,
|
1335 |
+
"loss": 0.8207,
|
1336 |
+
"step": 1690
|
1337 |
+
},
|
1338 |
+
{
|
1339 |
+
"epoch": 2.7,
|
1340 |
+
"grad_norm": 3.2665460109710693,
|
1341 |
+
"learning_rate": 0.00012299319727891156,
|
1342 |
+
"loss": 0.7311,
|
1343 |
+
"step": 1700
|
1344 |
+
},
|
1345 |
+
{
|
1346 |
+
"epoch": 2.7,
|
1347 |
+
"eval_accuracy": 0.7714285714285715,
|
1348 |
+
"eval_loss": 0.7353097200393677,
|
1349 |
+
"eval_runtime": 91.0228,
|
1350 |
+
"eval_samples_per_second": 27.685,
|
1351 |
+
"eval_steps_per_second": 3.461,
|
1352 |
+
"step": 1700
|
1353 |
+
},
|
1354 |
+
{
|
1355 |
+
"epoch": 2.71,
|
1356 |
+
"grad_norm": 4.803609848022461,
|
1357 |
+
"learning_rate": 0.00012253968253968256,
|
1358 |
+
"loss": 0.7369,
|
1359 |
+
"step": 1710
|
1360 |
+
},
|
1361 |
+
{
|
1362 |
+
"epoch": 2.73,
|
1363 |
+
"grad_norm": 4.8724565505981445,
|
1364 |
+
"learning_rate": 0.00012208616780045353,
|
1365 |
+
"loss": 0.623,
|
1366 |
+
"step": 1720
|
1367 |
+
},
|
1368 |
+
{
|
1369 |
+
"epoch": 2.75,
|
1370 |
+
"grad_norm": 5.754215240478516,
|
1371 |
+
"learning_rate": 0.00012163265306122449,
|
1372 |
+
"loss": 0.6377,
|
1373 |
+
"step": 1730
|
1374 |
+
},
|
1375 |
+
{
|
1376 |
+
"epoch": 2.76,
|
1377 |
+
"grad_norm": 7.614988803863525,
|
1378 |
+
"learning_rate": 0.00012117913832199547,
|
1379 |
+
"loss": 0.8485,
|
1380 |
+
"step": 1740
|
1381 |
+
},
|
1382 |
+
{
|
1383 |
+
"epoch": 2.78,
|
1384 |
+
"grad_norm": 2.6383018493652344,
|
1385 |
+
"learning_rate": 0.00012072562358276644,
|
1386 |
+
"loss": 0.6942,
|
1387 |
+
"step": 1750
|
1388 |
+
},
|
1389 |
+
{
|
1390 |
+
"epoch": 2.79,
|
1391 |
+
"grad_norm": 5.747374057769775,
|
1392 |
+
"learning_rate": 0.00012027210884353742,
|
1393 |
+
"loss": 0.7562,
|
1394 |
+
"step": 1760
|
1395 |
+
},
|
1396 |
+
{
|
1397 |
+
"epoch": 2.81,
|
1398 |
+
"grad_norm": 5.084746360778809,
|
1399 |
+
"learning_rate": 0.0001198185941043084,
|
1400 |
+
"loss": 0.69,
|
1401 |
+
"step": 1770
|
1402 |
+
},
|
1403 |
+
{
|
1404 |
+
"epoch": 2.83,
|
1405 |
+
"grad_norm": 6.089473247528076,
|
1406 |
+
"learning_rate": 0.00011936507936507938,
|
1407 |
+
"loss": 0.9495,
|
1408 |
+
"step": 1780
|
1409 |
+
},
|
1410 |
+
{
|
1411 |
+
"epoch": 2.84,
|
1412 |
+
"grad_norm": 5.547908306121826,
|
1413 |
+
"learning_rate": 0.00011891156462585033,
|
1414 |
+
"loss": 0.6505,
|
1415 |
+
"step": 1790
|
1416 |
+
},
|
1417 |
+
{
|
1418 |
+
"epoch": 2.86,
|
1419 |
+
"grad_norm": 3.5899226665496826,
|
1420 |
+
"learning_rate": 0.00011845804988662132,
|
1421 |
+
"loss": 0.7181,
|
1422 |
+
"step": 1800
|
1423 |
+
},
|
1424 |
+
{
|
1425 |
+
"epoch": 2.86,
|
1426 |
+
"eval_accuracy": 0.792063492063492,
|
1427 |
+
"eval_loss": 0.6831231713294983,
|
1428 |
+
"eval_runtime": 91.1983,
|
1429 |
+
"eval_samples_per_second": 27.632,
|
1430 |
+
"eval_steps_per_second": 3.454,
|
1431 |
+
"step": 1800
|
1432 |
+
},
|
1433 |
+
{
|
1434 |
+
"epoch": 2.87,
|
1435 |
+
"grad_norm": 4.794887542724609,
|
1436 |
+
"learning_rate": 0.00011800453514739229,
|
1437 |
+
"loss": 0.6245,
|
1438 |
+
"step": 1810
|
1439 |
+
},
|
1440 |
+
{
|
1441 |
+
"epoch": 2.89,
|
1442 |
+
"grad_norm": 7.641270160675049,
|
1443 |
+
"learning_rate": 0.00011755102040816328,
|
1444 |
+
"loss": 0.8966,
|
1445 |
+
"step": 1820
|
1446 |
+
},
|
1447 |
+
{
|
1448 |
+
"epoch": 2.9,
|
1449 |
+
"grad_norm": 4.0006608963012695,
|
1450 |
+
"learning_rate": 0.00011709750566893425,
|
1451 |
+
"loss": 0.6106,
|
1452 |
+
"step": 1830
|
1453 |
+
},
|
1454 |
+
{
|
1455 |
+
"epoch": 2.92,
|
1456 |
+
"grad_norm": 5.983084201812744,
|
1457 |
+
"learning_rate": 0.00011664399092970522,
|
1458 |
+
"loss": 0.887,
|
1459 |
+
"step": 1840
|
1460 |
+
},
|
1461 |
+
{
|
1462 |
+
"epoch": 2.94,
|
1463 |
+
"grad_norm": 4.492617130279541,
|
1464 |
+
"learning_rate": 0.00011619047619047621,
|
1465 |
+
"loss": 0.7974,
|
1466 |
+
"step": 1850
|
1467 |
+
},
|
1468 |
+
{
|
1469 |
+
"epoch": 2.95,
|
1470 |
+
"grad_norm": 4.350939750671387,
|
1471 |
+
"learning_rate": 0.00011573696145124717,
|
1472 |
+
"loss": 0.8817,
|
1473 |
+
"step": 1860
|
1474 |
+
},
|
1475 |
+
{
|
1476 |
+
"epoch": 2.97,
|
1477 |
+
"grad_norm": 4.855531692504883,
|
1478 |
+
"learning_rate": 0.00011528344671201814,
|
1479 |
+
"loss": 0.9235,
|
1480 |
+
"step": 1870
|
1481 |
+
},
|
1482 |
+
{
|
1483 |
+
"epoch": 2.98,
|
1484 |
+
"grad_norm": 5.735949993133545,
|
1485 |
+
"learning_rate": 0.00011482993197278912,
|
1486 |
+
"loss": 0.6679,
|
1487 |
+
"step": 1880
|
1488 |
+
},
|
1489 |
+
{
|
1490 |
+
"epoch": 3.0,
|
1491 |
+
"grad_norm": 3.4668216705322266,
|
1492 |
+
"learning_rate": 0.0001143764172335601,
|
1493 |
+
"loss": 0.6783,
|
1494 |
+
"step": 1890
|
1495 |
+
},
|
1496 |
+
{
|
1497 |
+
"epoch": 3.02,
|
1498 |
+
"grad_norm": 4.096149921417236,
|
1499 |
+
"learning_rate": 0.00011392290249433107,
|
1500 |
+
"loss": 0.5986,
|
1501 |
+
"step": 1900
|
1502 |
+
},
|
1503 |
+
{
|
1504 |
+
"epoch": 3.02,
|
1505 |
+
"eval_accuracy": 0.7896825396825397,
|
1506 |
+
"eval_loss": 0.6930129528045654,
|
1507 |
+
"eval_runtime": 91.4004,
|
1508 |
+
"eval_samples_per_second": 27.571,
|
1509 |
+
"eval_steps_per_second": 3.446,
|
1510 |
+
"step": 1900
|
1511 |
+
},
|
1512 |
+
{
|
1513 |
+
"epoch": 3.03,
|
1514 |
+
"grad_norm": 3.9420833587646484,
|
1515 |
+
"learning_rate": 0.00011346938775510206,
|
1516 |
+
"loss": 0.5611,
|
1517 |
+
"step": 1910
|
1518 |
+
},
|
1519 |
+
{
|
1520 |
+
"epoch": 3.05,
|
1521 |
+
"grad_norm": 2.5048274993896484,
|
1522 |
+
"learning_rate": 0.00011301587301587301,
|
1523 |
+
"loss": 0.6619,
|
1524 |
+
"step": 1920
|
1525 |
+
},
|
1526 |
+
{
|
1527 |
+
"epoch": 3.06,
|
1528 |
+
"grad_norm": 4.899613380432129,
|
1529 |
+
"learning_rate": 0.00011256235827664399,
|
1530 |
+
"loss": 0.6889,
|
1531 |
+
"step": 1930
|
1532 |
+
},
|
1533 |
+
{
|
1534 |
+
"epoch": 3.08,
|
1535 |
+
"grad_norm": 4.282281398773193,
|
1536 |
+
"learning_rate": 0.00011210884353741497,
|
1537 |
+
"loss": 0.6182,
|
1538 |
+
"step": 1940
|
1539 |
+
},
|
1540 |
+
{
|
1541 |
+
"epoch": 3.1,
|
1542 |
+
"grad_norm": 3.1164541244506836,
|
1543 |
+
"learning_rate": 0.00011165532879818594,
|
1544 |
+
"loss": 0.6822,
|
1545 |
+
"step": 1950
|
1546 |
+
},
|
1547 |
+
{
|
1548 |
+
"epoch": 3.11,
|
1549 |
+
"grad_norm": 4.760287761688232,
|
1550 |
+
"learning_rate": 0.00011120181405895693,
|
1551 |
+
"loss": 0.6557,
|
1552 |
+
"step": 1960
|
1553 |
+
},
|
1554 |
+
{
|
1555 |
+
"epoch": 3.13,
|
1556 |
+
"grad_norm": 3.0668411254882812,
|
1557 |
+
"learning_rate": 0.0001107482993197279,
|
1558 |
+
"loss": 0.6537,
|
1559 |
+
"step": 1970
|
1560 |
+
},
|
1561 |
+
{
|
1562 |
+
"epoch": 3.14,
|
1563 |
+
"grad_norm": 4.527184009552002,
|
1564 |
+
"learning_rate": 0.00011029478458049886,
|
1565 |
+
"loss": 0.5513,
|
1566 |
+
"step": 1980
|
1567 |
+
},
|
1568 |
+
{
|
1569 |
+
"epoch": 3.16,
|
1570 |
+
"grad_norm": 2.029935598373413,
|
1571 |
+
"learning_rate": 0.00010984126984126986,
|
1572 |
+
"loss": 0.5102,
|
1573 |
+
"step": 1990
|
1574 |
+
},
|
1575 |
+
{
|
1576 |
+
"epoch": 3.17,
|
1577 |
+
"grad_norm": 4.294469833374023,
|
1578 |
+
"learning_rate": 0.00010938775510204082,
|
1579 |
+
"loss": 0.5716,
|
1580 |
+
"step": 2000
|
1581 |
+
},
|
1582 |
+
{
|
1583 |
+
"epoch": 3.17,
|
1584 |
+
"eval_accuracy": 0.8047619047619048,
|
1585 |
+
"eval_loss": 0.6684977412223816,
|
1586 |
+
"eval_runtime": 90.6284,
|
1587 |
+
"eval_samples_per_second": 27.806,
|
1588 |
+
"eval_steps_per_second": 3.476,
|
1589 |
+
"step": 2000
|
1590 |
+
},
|
1591 |
+
{
|
1592 |
+
"epoch": 3.19,
|
1593 |
+
"grad_norm": 6.498531818389893,
|
1594 |
+
"learning_rate": 0.00010893424036281179,
|
1595 |
+
"loss": 0.6862,
|
1596 |
+
"step": 2010
|
1597 |
+
},
|
1598 |
+
{
|
1599 |
+
"epoch": 3.21,
|
1600 |
+
"grad_norm": 5.384933948516846,
|
1601 |
+
"learning_rate": 0.00010848072562358278,
|
1602 |
+
"loss": 0.4793,
|
1603 |
+
"step": 2020
|
1604 |
+
},
|
1605 |
+
{
|
1606 |
+
"epoch": 3.22,
|
1607 |
+
"grad_norm": 4.124419212341309,
|
1608 |
+
"learning_rate": 0.00010802721088435375,
|
1609 |
+
"loss": 0.7055,
|
1610 |
+
"step": 2030
|
1611 |
+
},
|
1612 |
+
{
|
1613 |
+
"epoch": 3.24,
|
1614 |
+
"grad_norm": 4.198364734649658,
|
1615 |
+
"learning_rate": 0.00010757369614512471,
|
1616 |
+
"loss": 0.7231,
|
1617 |
+
"step": 2040
|
1618 |
+
},
|
1619 |
+
{
|
1620 |
+
"epoch": 3.25,
|
1621 |
+
"grad_norm": 4.410750389099121,
|
1622 |
+
"learning_rate": 0.00010712018140589571,
|
1623 |
+
"loss": 0.751,
|
1624 |
+
"step": 2050
|
1625 |
+
},
|
1626 |
+
{
|
1627 |
+
"epoch": 3.27,
|
1628 |
+
"grad_norm": 6.240994930267334,
|
1629 |
+
"learning_rate": 0.00010666666666666667,
|
1630 |
+
"loss": 0.6299,
|
1631 |
+
"step": 2060
|
1632 |
+
},
|
1633 |
+
{
|
1634 |
+
"epoch": 3.29,
|
1635 |
+
"grad_norm": 4.845404148101807,
|
1636 |
+
"learning_rate": 0.00010621315192743764,
|
1637 |
+
"loss": 0.6496,
|
1638 |
+
"step": 2070
|
1639 |
+
},
|
1640 |
+
{
|
1641 |
+
"epoch": 3.3,
|
1642 |
+
"grad_norm": 4.447664260864258,
|
1643 |
+
"learning_rate": 0.00010575963718820862,
|
1644 |
+
"loss": 0.5909,
|
1645 |
+
"step": 2080
|
1646 |
+
},
|
1647 |
+
{
|
1648 |
+
"epoch": 3.32,
|
1649 |
+
"grad_norm": 4.779788494110107,
|
1650 |
+
"learning_rate": 0.0001053061224489796,
|
1651 |
+
"loss": 0.6505,
|
1652 |
+
"step": 2090
|
1653 |
+
},
|
1654 |
+
{
|
1655 |
+
"epoch": 3.33,
|
1656 |
+
"grad_norm": 3.946617841720581,
|
1657 |
+
"learning_rate": 0.00010485260770975056,
|
1658 |
+
"loss": 0.5218,
|
1659 |
+
"step": 2100
|
1660 |
+
},
|
1661 |
+
{
|
1662 |
+
"epoch": 3.33,
|
1663 |
+
"eval_accuracy": 0.7916666666666666,
|
1664 |
+
"eval_loss": 0.7152296900749207,
|
1665 |
+
"eval_runtime": 89.3624,
|
1666 |
+
"eval_samples_per_second": 28.2,
|
1667 |
+
"eval_steps_per_second": 3.525,
|
1668 |
+
"step": 2100
|
1669 |
+
},
|
1670 |
+
{
|
1671 |
+
"epoch": 3.35,
|
1672 |
+
"grad_norm": 4.13429069519043,
|
1673 |
+
"learning_rate": 0.00010439909297052155,
|
1674 |
+
"loss": 0.6193,
|
1675 |
+
"step": 2110
|
1676 |
+
},
|
1677 |
+
{
|
1678 |
+
"epoch": 3.37,
|
1679 |
+
"grad_norm": 5.503479480743408,
|
1680 |
+
"learning_rate": 0.00010394557823129251,
|
1681 |
+
"loss": 0.6206,
|
1682 |
+
"step": 2120
|
1683 |
+
},
|
1684 |
+
{
|
1685 |
+
"epoch": 3.38,
|
1686 |
+
"grad_norm": 6.610657215118408,
|
1687 |
+
"learning_rate": 0.00010349206349206351,
|
1688 |
+
"loss": 0.7244,
|
1689 |
+
"step": 2130
|
1690 |
+
},
|
1691 |
+
{
|
1692 |
+
"epoch": 3.4,
|
1693 |
+
"grad_norm": 3.592276096343994,
|
1694 |
+
"learning_rate": 0.00010303854875283447,
|
1695 |
+
"loss": 0.502,
|
1696 |
+
"step": 2140
|
1697 |
+
},
|
1698 |
+
{
|
1699 |
+
"epoch": 3.41,
|
1700 |
+
"grad_norm": 7.070047378540039,
|
1701 |
+
"learning_rate": 0.00010258503401360544,
|
1702 |
+
"loss": 0.8749,
|
1703 |
+
"step": 2150
|
1704 |
+
},
|
1705 |
+
{
|
1706 |
+
"epoch": 3.43,
|
1707 |
+
"grad_norm": 8.58852481842041,
|
1708 |
+
"learning_rate": 0.00010213151927437643,
|
1709 |
+
"loss": 0.5832,
|
1710 |
+
"step": 2160
|
1711 |
+
},
|
1712 |
+
{
|
1713 |
+
"epoch": 3.44,
|
1714 |
+
"grad_norm": 5.416906356811523,
|
1715 |
+
"learning_rate": 0.0001016780045351474,
|
1716 |
+
"loss": 0.5901,
|
1717 |
+
"step": 2170
|
1718 |
+
},
|
1719 |
+
{
|
1720 |
+
"epoch": 3.46,
|
1721 |
+
"grad_norm": 6.415400981903076,
|
1722 |
+
"learning_rate": 0.00010122448979591836,
|
1723 |
+
"loss": 0.4842,
|
1724 |
+
"step": 2180
|
1725 |
+
},
|
1726 |
+
{
|
1727 |
+
"epoch": 3.48,
|
1728 |
+
"grad_norm": 1.809209942817688,
|
1729 |
+
"learning_rate": 0.00010077097505668936,
|
1730 |
+
"loss": 0.6591,
|
1731 |
+
"step": 2190
|
1732 |
+
},
|
1733 |
+
{
|
1734 |
+
"epoch": 3.49,
|
1735 |
+
"grad_norm": 4.30819034576416,
|
1736 |
+
"learning_rate": 0.00010031746031746032,
|
1737 |
+
"loss": 0.8469,
|
1738 |
+
"step": 2200
|
1739 |
+
},
|
1740 |
+
{
|
1741 |
+
"epoch": 3.49,
|
1742 |
+
"eval_accuracy": 0.801984126984127,
|
1743 |
+
"eval_loss": 0.6404625177383423,
|
1744 |
+
"eval_runtime": 91.7544,
|
1745 |
+
"eval_samples_per_second": 27.465,
|
1746 |
+
"eval_steps_per_second": 3.433,
|
1747 |
+
"step": 2200
|
1748 |
+
},
|
1749 |
+
{
|
1750 |
+
"epoch": 3.51,
|
1751 |
+
"grad_norm": 1.2012885808944702,
|
1752 |
+
"learning_rate": 9.98639455782313e-05,
|
1753 |
+
"loss": 0.5602,
|
1754 |
+
"step": 2210
|
1755 |
+
},
|
1756 |
+
{
|
1757 |
+
"epoch": 3.52,
|
1758 |
+
"grad_norm": 6.166879653930664,
|
1759 |
+
"learning_rate": 9.941043083900228e-05,
|
1760 |
+
"loss": 0.693,
|
1761 |
+
"step": 2220
|
1762 |
+
},
|
1763 |
+
{
|
1764 |
+
"epoch": 3.54,
|
1765 |
+
"grad_norm": 2.257598876953125,
|
1766 |
+
"learning_rate": 9.895691609977325e-05,
|
1767 |
+
"loss": 0.6969,
|
1768 |
+
"step": 2230
|
1769 |
+
},
|
1770 |
+
{
|
1771 |
+
"epoch": 3.56,
|
1772 |
+
"grad_norm": 3.866694450378418,
|
1773 |
+
"learning_rate": 9.850340136054422e-05,
|
1774 |
+
"loss": 0.7577,
|
1775 |
+
"step": 2240
|
1776 |
+
},
|
1777 |
+
{
|
1778 |
+
"epoch": 3.57,
|
1779 |
+
"grad_norm": 4.493105888366699,
|
1780 |
+
"learning_rate": 9.804988662131521e-05,
|
1781 |
+
"loss": 0.7494,
|
1782 |
+
"step": 2250
|
1783 |
+
},
|
1784 |
+
{
|
1785 |
+
"epoch": 3.59,
|
1786 |
+
"grad_norm": 6.990530490875244,
|
1787 |
+
"learning_rate": 9.759637188208617e-05,
|
1788 |
+
"loss": 0.6278,
|
1789 |
+
"step": 2260
|
1790 |
+
},
|
1791 |
+
{
|
1792 |
+
"epoch": 3.6,
|
1793 |
+
"grad_norm": 3.6842026710510254,
|
1794 |
+
"learning_rate": 9.714285714285715e-05,
|
1795 |
+
"loss": 0.6444,
|
1796 |
+
"step": 2270
|
1797 |
+
},
|
1798 |
+
{
|
1799 |
+
"epoch": 3.62,
|
1800 |
+
"grad_norm": 3.766533851623535,
|
1801 |
+
"learning_rate": 9.668934240362812e-05,
|
1802 |
+
"loss": 0.6254,
|
1803 |
+
"step": 2280
|
1804 |
+
},
|
1805 |
+
{
|
1806 |
+
"epoch": 3.63,
|
1807 |
+
"grad_norm": 3.9097561836242676,
|
1808 |
+
"learning_rate": 9.62358276643991e-05,
|
1809 |
+
"loss": 0.6871,
|
1810 |
+
"step": 2290
|
1811 |
+
},
|
1812 |
+
{
|
1813 |
+
"epoch": 3.65,
|
1814 |
+
"grad_norm": 5.504273414611816,
|
1815 |
+
"learning_rate": 9.578231292517007e-05,
|
1816 |
+
"loss": 0.5783,
|
1817 |
+
"step": 2300
|
1818 |
+
},
|
1819 |
+
{
|
1820 |
+
"epoch": 3.65,
|
1821 |
+
"eval_accuracy": 0.7956349206349206,
|
1822 |
+
"eval_loss": 0.6727890968322754,
|
1823 |
+
"eval_runtime": 91.691,
|
1824 |
+
"eval_samples_per_second": 27.484,
|
1825 |
+
"eval_steps_per_second": 3.435,
|
1826 |
+
"step": 2300
|
1827 |
+
},
|
1828 |
+
{
|
1829 |
+
"epoch": 3.67,
|
1830 |
+
"grad_norm": 6.009402751922607,
|
1831 |
+
"learning_rate": 9.532879818594105e-05,
|
1832 |
+
"loss": 0.6296,
|
1833 |
+
"step": 2310
|
1834 |
+
},
|
1835 |
+
{
|
1836 |
+
"epoch": 3.68,
|
1837 |
+
"grad_norm": 3.723788022994995,
|
1838 |
+
"learning_rate": 9.487528344671203e-05,
|
1839 |
+
"loss": 0.61,
|
1840 |
+
"step": 2320
|
1841 |
+
},
|
1842 |
+
{
|
1843 |
+
"epoch": 3.7,
|
1844 |
+
"grad_norm": 1.6886146068572998,
|
1845 |
+
"learning_rate": 9.4421768707483e-05,
|
1846 |
+
"loss": 0.6042,
|
1847 |
+
"step": 2330
|
1848 |
+
},
|
1849 |
+
{
|
1850 |
+
"epoch": 3.71,
|
1851 |
+
"grad_norm": 3.2953665256500244,
|
1852 |
+
"learning_rate": 9.396825396825397e-05,
|
1853 |
+
"loss": 0.5417,
|
1854 |
+
"step": 2340
|
1855 |
+
},
|
1856 |
+
{
|
1857 |
+
"epoch": 3.73,
|
1858 |
+
"grad_norm": 5.710081100463867,
|
1859 |
+
"learning_rate": 9.351473922902494e-05,
|
1860 |
+
"loss": 0.4744,
|
1861 |
+
"step": 2350
|
1862 |
+
},
|
1863 |
+
{
|
1864 |
+
"epoch": 3.75,
|
1865 |
+
"grad_norm": 8.341416358947754,
|
1866 |
+
"learning_rate": 9.306122448979592e-05,
|
1867 |
+
"loss": 0.6468,
|
1868 |
+
"step": 2360
|
1869 |
+
},
|
1870 |
+
{
|
1871 |
+
"epoch": 3.76,
|
1872 |
+
"grad_norm": 5.668067455291748,
|
1873 |
+
"learning_rate": 9.26077097505669e-05,
|
1874 |
+
"loss": 0.7058,
|
1875 |
+
"step": 2370
|
1876 |
+
},
|
1877 |
+
{
|
1878 |
+
"epoch": 3.78,
|
1879 |
+
"grad_norm": 7.821765422821045,
|
1880 |
+
"learning_rate": 9.215419501133787e-05,
|
1881 |
+
"loss": 0.6014,
|
1882 |
+
"step": 2380
|
1883 |
+
},
|
1884 |
+
{
|
1885 |
+
"epoch": 3.79,
|
1886 |
+
"grad_norm": 3.075150728225708,
|
1887 |
+
"learning_rate": 9.170068027210885e-05,
|
1888 |
+
"loss": 0.5857,
|
1889 |
+
"step": 2390
|
1890 |
+
},
|
1891 |
+
{
|
1892 |
+
"epoch": 3.81,
|
1893 |
+
"grad_norm": 5.349681377410889,
|
1894 |
+
"learning_rate": 9.124716553287982e-05,
|
1895 |
+
"loss": 0.7202,
|
1896 |
+
"step": 2400
|
1897 |
+
},
|
1898 |
+
{
|
1899 |
+
"epoch": 3.81,
|
1900 |
+
"eval_accuracy": 0.8154761904761905,
|
1901 |
+
"eval_loss": 0.6007378697395325,
|
1902 |
+
"eval_runtime": 91.6882,
|
1903 |
+
"eval_samples_per_second": 27.484,
|
1904 |
+
"eval_steps_per_second": 3.436,
|
1905 |
+
"step": 2400
|
1906 |
+
},
|
1907 |
+
{
|
1908 |
+
"epoch": 3.83,
|
1909 |
+
"grad_norm": 6.9100117683410645,
|
1910 |
+
"learning_rate": 9.079365079365079e-05,
|
1911 |
+
"loss": 0.5335,
|
1912 |
+
"step": 2410
|
1913 |
+
},
|
1914 |
+
{
|
1915 |
+
"epoch": 3.84,
|
1916 |
+
"grad_norm": NaN,
|
1917 |
+
"learning_rate": 9.038548752834468e-05,
|
1918 |
+
"loss": 0.7311,
|
1919 |
+
"step": 2420
|
1920 |
+
},
|
1921 |
+
{
|
1922 |
+
"epoch": 3.86,
|
1923 |
+
"grad_norm": 3.347836494445801,
|
1924 |
+
"learning_rate": 8.993197278911565e-05,
|
1925 |
+
"loss": 0.5405,
|
1926 |
+
"step": 2430
|
1927 |
+
},
|
1928 |
+
{
|
1929 |
+
"epoch": 3.87,
|
1930 |
+
"grad_norm": 10.232234954833984,
|
1931 |
+
"learning_rate": 8.947845804988662e-05,
|
1932 |
+
"loss": 0.7061,
|
1933 |
+
"step": 2440
|
1934 |
+
},
|
1935 |
+
{
|
1936 |
+
"epoch": 3.89,
|
1937 |
+
"grad_norm": 5.486011981964111,
|
1938 |
+
"learning_rate": 8.902494331065761e-05,
|
1939 |
+
"loss": 0.6905,
|
1940 |
+
"step": 2450
|
1941 |
+
},
|
1942 |
+
{
|
1943 |
+
"epoch": 3.9,
|
1944 |
+
"grad_norm": 4.699936389923096,
|
1945 |
+
"learning_rate": 8.857142857142857e-05,
|
1946 |
+
"loss": 0.5979,
|
1947 |
+
"step": 2460
|
1948 |
+
},
|
1949 |
+
{
|
1950 |
+
"epoch": 3.92,
|
1951 |
+
"grad_norm": 7.7097296714782715,
|
1952 |
+
"learning_rate": 8.811791383219955e-05,
|
1953 |
+
"loss": 0.5904,
|
1954 |
+
"step": 2470
|
1955 |
+
},
|
1956 |
+
{
|
1957 |
+
"epoch": 3.94,
|
1958 |
+
"grad_norm": 3.3451244831085205,
|
1959 |
+
"learning_rate": 8.766439909297052e-05,
|
1960 |
+
"loss": 0.5359,
|
1961 |
+
"step": 2480
|
1962 |
+
},
|
1963 |
+
{
|
1964 |
+
"epoch": 3.95,
|
1965 |
+
"grad_norm": 7.01662540435791,
|
1966 |
+
"learning_rate": 8.72108843537415e-05,
|
1967 |
+
"loss": 0.728,
|
1968 |
+
"step": 2490
|
1969 |
+
},
|
1970 |
+
{
|
1971 |
+
"epoch": 3.97,
|
1972 |
+
"grad_norm": 4.137801170349121,
|
1973 |
+
"learning_rate": 8.675736961451247e-05,
|
1974 |
+
"loss": 0.5525,
|
1975 |
+
"step": 2500
|
1976 |
+
},
|
1977 |
+
{
|
1978 |
+
"epoch": 3.97,
|
1979 |
+
"eval_accuracy": 0.8055555555555556,
|
1980 |
+
"eval_loss": 0.6558998823165894,
|
1981 |
+
"eval_runtime": 94.8951,
|
1982 |
+
"eval_samples_per_second": 26.556,
|
1983 |
+
"eval_steps_per_second": 3.319,
|
1984 |
+
"step": 2500
|
1985 |
+
},
|
1986 |
+
{
|
1987 |
+
"epoch": 3.98,
|
1988 |
+
"grad_norm": 6.564231872558594,
|
1989 |
+
"learning_rate": 8.630385487528345e-05,
|
1990 |
+
"loss": 0.6735,
|
1991 |
+
"step": 2510
|
1992 |
+
},
|
1993 |
+
{
|
1994 |
+
"epoch": 4.0,
|
1995 |
+
"grad_norm": 5.252976894378662,
|
1996 |
+
"learning_rate": 8.585034013605443e-05,
|
1997 |
+
"loss": 0.6903,
|
1998 |
+
"step": 2520
|
1999 |
+
},
|
2000 |
+
{
|
2001 |
+
"epoch": 4.02,
|
2002 |
+
"grad_norm": 4.289461612701416,
|
2003 |
+
"learning_rate": 8.53968253968254e-05,
|
2004 |
+
"loss": 0.5104,
|
2005 |
+
"step": 2530
|
2006 |
+
},
|
2007 |
+
{
|
2008 |
+
"epoch": 4.03,
|
2009 |
+
"grad_norm": 4.131557941436768,
|
2010 |
+
"learning_rate": 8.494331065759637e-05,
|
2011 |
+
"loss": 0.5064,
|
2012 |
+
"step": 2540
|
2013 |
+
},
|
2014 |
+
{
|
2015 |
+
"epoch": 4.05,
|
2016 |
+
"grad_norm": 3.5607643127441406,
|
2017 |
+
"learning_rate": 8.448979591836736e-05,
|
2018 |
+
"loss": 0.4825,
|
2019 |
+
"step": 2550
|
2020 |
+
},
|
2021 |
+
{
|
2022 |
+
"epoch": 4.06,
|
2023 |
+
"grad_norm": 2.5051770210266113,
|
2024 |
+
"learning_rate": 8.403628117913832e-05,
|
2025 |
+
"loss": 0.5668,
|
2026 |
+
"step": 2560
|
2027 |
+
},
|
2028 |
+
{
|
2029 |
+
"epoch": 4.08,
|
2030 |
+
"grad_norm": 1.6936321258544922,
|
2031 |
+
"learning_rate": 8.35827664399093e-05,
|
2032 |
+
"loss": 0.4412,
|
2033 |
+
"step": 2570
|
2034 |
+
},
|
2035 |
+
{
|
2036 |
+
"epoch": 4.1,
|
2037 |
+
"grad_norm": 3.99070143699646,
|
2038 |
+
"learning_rate": 8.312925170068027e-05,
|
2039 |
+
"loss": 0.5046,
|
2040 |
+
"step": 2580
|
2041 |
+
},
|
2042 |
+
{
|
2043 |
+
"epoch": 4.11,
|
2044 |
+
"grad_norm": 4.099004745483398,
|
2045 |
+
"learning_rate": 8.267573696145126e-05,
|
2046 |
+
"loss": 0.5753,
|
2047 |
+
"step": 2590
|
2048 |
+
},
|
2049 |
+
{
|
2050 |
+
"epoch": 4.13,
|
2051 |
+
"grad_norm": 3.5789458751678467,
|
2052 |
+
"learning_rate": 8.222222222222222e-05,
|
2053 |
+
"loss": 0.519,
|
2054 |
+
"step": 2600
|
2055 |
+
},
|
2056 |
+
{
|
2057 |
+
"epoch": 4.13,
|
2058 |
+
"eval_accuracy": 0.8222222222222222,
|
2059 |
+
"eval_loss": 0.5868101716041565,
|
2060 |
+
"eval_runtime": 93.686,
|
2061 |
+
"eval_samples_per_second": 26.898,
|
2062 |
+
"eval_steps_per_second": 3.362,
|
2063 |
+
"step": 2600
|
2064 |
+
},
|
2065 |
+
{
|
2066 |
+
"epoch": 4.14,
|
2067 |
+
"grad_norm": 4.785660266876221,
|
2068 |
+
"learning_rate": 8.17687074829932e-05,
|
2069 |
+
"loss": 0.4747,
|
2070 |
+
"step": 2610
|
2071 |
+
},
|
2072 |
+
{
|
2073 |
+
"epoch": 4.16,
|
2074 |
+
"grad_norm": 3.662282705307007,
|
2075 |
+
"learning_rate": 8.131519274376418e-05,
|
2076 |
+
"loss": 0.4822,
|
2077 |
+
"step": 2620
|
2078 |
+
},
|
2079 |
+
{
|
2080 |
+
"epoch": 4.17,
|
2081 |
+
"grad_norm": 3.897036075592041,
|
2082 |
+
"learning_rate": 8.086167800453515e-05,
|
2083 |
+
"loss": 0.4848,
|
2084 |
+
"step": 2630
|
2085 |
+
},
|
2086 |
+
{
|
2087 |
+
"epoch": 4.19,
|
2088 |
+
"grad_norm": 5.990245342254639,
|
2089 |
+
"learning_rate": 8.040816326530612e-05,
|
2090 |
+
"loss": 0.5569,
|
2091 |
+
"step": 2640
|
2092 |
+
},
|
2093 |
+
{
|
2094 |
+
"epoch": 4.21,
|
2095 |
+
"grad_norm": 4.004576206207275,
|
2096 |
+
"learning_rate": 7.99546485260771e-05,
|
2097 |
+
"loss": 0.4929,
|
2098 |
+
"step": 2650
|
2099 |
+
},
|
2100 |
+
{
|
2101 |
+
"epoch": 4.22,
|
2102 |
+
"grad_norm": 5.0893754959106445,
|
2103 |
+
"learning_rate": 7.950113378684808e-05,
|
2104 |
+
"loss": 0.5564,
|
2105 |
+
"step": 2660
|
2106 |
+
},
|
2107 |
+
{
|
2108 |
+
"epoch": 4.24,
|
2109 |
+
"grad_norm": 3.9271037578582764,
|
2110 |
+
"learning_rate": 7.904761904761905e-05,
|
2111 |
+
"loss": 0.382,
|
2112 |
+
"step": 2670
|
2113 |
+
},
|
2114 |
+
{
|
2115 |
+
"epoch": 4.25,
|
2116 |
+
"grad_norm": 4.929361820220947,
|
2117 |
+
"learning_rate": 7.859410430839002e-05,
|
2118 |
+
"loss": 0.5502,
|
2119 |
+
"step": 2680
|
2120 |
+
},
|
2121 |
+
{
|
2122 |
+
"epoch": 4.27,
|
2123 |
+
"grad_norm": 4.333121299743652,
|
2124 |
+
"learning_rate": 7.814058956916101e-05,
|
2125 |
+
"loss": 0.5877,
|
2126 |
+
"step": 2690
|
2127 |
+
},
|
2128 |
+
{
|
2129 |
+
"epoch": 4.29,
|
2130 |
+
"grad_norm": 3.787369728088379,
|
2131 |
+
"learning_rate": 7.768707482993197e-05,
|
2132 |
+
"loss": 0.6171,
|
2133 |
+
"step": 2700
|
2134 |
+
},
|
2135 |
+
{
|
2136 |
+
"epoch": 4.29,
|
2137 |
+
"eval_accuracy": 0.8103174603174603,
|
2138 |
+
"eval_loss": 0.6157482266426086,
|
2139 |
+
"eval_runtime": 91.6071,
|
2140 |
+
"eval_samples_per_second": 27.509,
|
2141 |
+
"eval_steps_per_second": 3.439,
|
2142 |
+
"step": 2700
|
2143 |
+
},
|
2144 |
+
{
|
2145 |
+
"epoch": 4.3,
|
2146 |
+
"grad_norm": 4.089489936828613,
|
2147 |
+
"learning_rate": 7.723356009070295e-05,
|
2148 |
+
"loss": 0.5279,
|
2149 |
+
"step": 2710
|
2150 |
+
},
|
2151 |
+
{
|
2152 |
+
"epoch": 4.32,
|
2153 |
+
"grad_norm": 5.687109470367432,
|
2154 |
+
"learning_rate": 7.678004535147393e-05,
|
2155 |
+
"loss": 0.4443,
|
2156 |
+
"step": 2720
|
2157 |
+
},
|
2158 |
+
{
|
2159 |
+
"epoch": 4.33,
|
2160 |
+
"grad_norm": 3.6936216354370117,
|
2161 |
+
"learning_rate": 7.632653061224491e-05,
|
2162 |
+
"loss": 0.533,
|
2163 |
+
"step": 2730
|
2164 |
+
},
|
2165 |
+
{
|
2166 |
+
"epoch": 4.35,
|
2167 |
+
"grad_norm": 2.403999090194702,
|
2168 |
+
"learning_rate": 7.587301587301587e-05,
|
2169 |
+
"loss": 0.5214,
|
2170 |
+
"step": 2740
|
2171 |
+
},
|
2172 |
+
{
|
2173 |
+
"epoch": 4.37,
|
2174 |
+
"grad_norm": 5.553544044494629,
|
2175 |
+
"learning_rate": 7.541950113378686e-05,
|
2176 |
+
"loss": 0.5621,
|
2177 |
+
"step": 2750
|
2178 |
+
},
|
2179 |
+
{
|
2180 |
+
"epoch": 4.38,
|
2181 |
+
"grad_norm": 2.7590301036834717,
|
2182 |
+
"learning_rate": 7.496598639455783e-05,
|
2183 |
+
"loss": 0.4752,
|
2184 |
+
"step": 2760
|
2185 |
+
},
|
2186 |
+
{
|
2187 |
+
"epoch": 4.4,
|
2188 |
+
"grad_norm": 6.257105350494385,
|
2189 |
+
"learning_rate": 7.45124716553288e-05,
|
2190 |
+
"loss": 0.5196,
|
2191 |
+
"step": 2770
|
2192 |
+
},
|
2193 |
+
{
|
2194 |
+
"epoch": 4.41,
|
2195 |
+
"grad_norm": 6.366973400115967,
|
2196 |
+
"learning_rate": 7.405895691609977e-05,
|
2197 |
+
"loss": 0.4779,
|
2198 |
+
"step": 2780
|
2199 |
+
},
|
2200 |
+
{
|
2201 |
+
"epoch": 4.43,
|
2202 |
+
"grad_norm": 4.746866703033447,
|
2203 |
+
"learning_rate": 7.360544217687076e-05,
|
2204 |
+
"loss": 0.4031,
|
2205 |
+
"step": 2790
|
2206 |
+
},
|
2207 |
+
{
|
2208 |
+
"epoch": 4.44,
|
2209 |
+
"grad_norm": 3.278367519378662,
|
2210 |
+
"learning_rate": 7.315192743764173e-05,
|
2211 |
+
"loss": 0.5401,
|
2212 |
+
"step": 2800
|
2213 |
+
},
|
2214 |
+
{
|
2215 |
+
"epoch": 4.44,
|
2216 |
+
"eval_accuracy": 0.8083333333333333,
|
2217 |
+
"eval_loss": 0.6119987368583679,
|
2218 |
+
"eval_runtime": 91.505,
|
2219 |
+
"eval_samples_per_second": 27.539,
|
2220 |
+
"eval_steps_per_second": 3.442,
|
2221 |
+
"step": 2800
|
2222 |
+
},
|
2223 |
+
{
|
2224 |
+
"epoch": 4.46,
|
2225 |
+
"grad_norm": 5.5712504386901855,
|
2226 |
+
"learning_rate": 7.26984126984127e-05,
|
2227 |
+
"loss": 0.5565,
|
2228 |
+
"step": 2810
|
2229 |
+
},
|
2230 |
+
{
|
2231 |
+
"epoch": 4.48,
|
2232 |
+
"grad_norm": 4.8718767166137695,
|
2233 |
+
"learning_rate": 7.224489795918368e-05,
|
2234 |
+
"loss": 0.5219,
|
2235 |
+
"step": 2820
|
2236 |
+
},
|
2237 |
+
{
|
2238 |
+
"epoch": 4.49,
|
2239 |
+
"grad_norm": 5.685264587402344,
|
2240 |
+
"learning_rate": 7.179138321995466e-05,
|
2241 |
+
"loss": 0.5021,
|
2242 |
+
"step": 2830
|
2243 |
+
},
|
2244 |
+
{
|
2245 |
+
"epoch": 4.51,
|
2246 |
+
"grad_norm": 6.191750526428223,
|
2247 |
+
"learning_rate": 7.133786848072562e-05,
|
2248 |
+
"loss": 0.5115,
|
2249 |
+
"step": 2840
|
2250 |
+
},
|
2251 |
+
{
|
2252 |
+
"epoch": 4.52,
|
2253 |
+
"grad_norm": 5.250429630279541,
|
2254 |
+
"learning_rate": 7.08843537414966e-05,
|
2255 |
+
"loss": 0.5805,
|
2256 |
+
"step": 2850
|
2257 |
+
},
|
2258 |
+
{
|
2259 |
+
"epoch": 4.54,
|
2260 |
+
"grad_norm": 5.834912300109863,
|
2261 |
+
"learning_rate": 7.043083900226758e-05,
|
2262 |
+
"loss": 0.584,
|
2263 |
+
"step": 2860
|
2264 |
+
},
|
2265 |
+
{
|
2266 |
+
"epoch": 4.56,
|
2267 |
+
"grad_norm": 2.52066707611084,
|
2268 |
+
"learning_rate": 6.997732426303855e-05,
|
2269 |
+
"loss": 0.3752,
|
2270 |
+
"step": 2870
|
2271 |
+
},
|
2272 |
+
{
|
2273 |
+
"epoch": 4.57,
|
2274 |
+
"grad_norm": 2.4411842823028564,
|
2275 |
+
"learning_rate": 6.952380952380952e-05,
|
2276 |
+
"loss": 0.5748,
|
2277 |
+
"step": 2880
|
2278 |
+
},
|
2279 |
+
{
|
2280 |
+
"epoch": 4.59,
|
2281 |
+
"grad_norm": 4.865506649017334,
|
2282 |
+
"learning_rate": 6.907029478458051e-05,
|
2283 |
+
"loss": 0.6119,
|
2284 |
+
"step": 2890
|
2285 |
+
},
|
2286 |
+
{
|
2287 |
+
"epoch": 4.6,
|
2288 |
+
"grad_norm": 2.109516143798828,
|
2289 |
+
"learning_rate": 6.861678004535148e-05,
|
2290 |
+
"loss": 0.6105,
|
2291 |
+
"step": 2900
|
2292 |
+
},
|
2293 |
+
{
|
2294 |
+
"epoch": 4.6,
|
2295 |
+
"eval_accuracy": 0.8325396825396826,
|
2296 |
+
"eval_loss": 0.5618996024131775,
|
2297 |
+
"eval_runtime": 90.5734,
|
2298 |
+
"eval_samples_per_second": 27.823,
|
2299 |
+
"eval_steps_per_second": 3.478,
|
2300 |
+
"step": 2900
|
2301 |
+
},
|
2302 |
+
{
|
2303 |
+
"epoch": 4.62,
|
2304 |
+
"grad_norm": 6.931108474731445,
|
2305 |
+
"learning_rate": 6.816326530612245e-05,
|
2306 |
+
"loss": 0.6452,
|
2307 |
+
"step": 2910
|
2308 |
+
},
|
2309 |
+
{
|
2310 |
+
"epoch": 4.63,
|
2311 |
+
"grad_norm": 5.011793613433838,
|
2312 |
+
"learning_rate": 6.770975056689343e-05,
|
2313 |
+
"loss": 0.3178,
|
2314 |
+
"step": 2920
|
2315 |
+
},
|
2316 |
+
{
|
2317 |
+
"epoch": 4.65,
|
2318 |
+
"grad_norm": 2.996354818344116,
|
2319 |
+
"learning_rate": 6.72562358276644e-05,
|
2320 |
+
"loss": 0.3436,
|
2321 |
+
"step": 2930
|
2322 |
+
},
|
2323 |
+
{
|
2324 |
+
"epoch": 4.67,
|
2325 |
+
"grad_norm": 4.3052754402160645,
|
2326 |
+
"learning_rate": 6.680272108843538e-05,
|
2327 |
+
"loss": 0.4743,
|
2328 |
+
"step": 2940
|
2329 |
+
},
|
2330 |
+
{
|
2331 |
+
"epoch": 4.68,
|
2332 |
+
"grad_norm": 5.777819633483887,
|
2333 |
+
"learning_rate": 6.634920634920636e-05,
|
2334 |
+
"loss": 0.6294,
|
2335 |
+
"step": 2950
|
2336 |
+
},
|
2337 |
+
{
|
2338 |
+
"epoch": 4.7,
|
2339 |
+
"grad_norm": 4.6029157638549805,
|
2340 |
+
"learning_rate": 6.589569160997733e-05,
|
2341 |
+
"loss": 0.495,
|
2342 |
+
"step": 2960
|
2343 |
+
},
|
2344 |
+
{
|
2345 |
+
"epoch": 4.71,
|
2346 |
+
"grad_norm": 3.34942889213562,
|
2347 |
+
"learning_rate": 6.54421768707483e-05,
|
2348 |
+
"loss": 0.5216,
|
2349 |
+
"step": 2970
|
2350 |
+
},
|
2351 |
+
{
|
2352 |
+
"epoch": 4.73,
|
2353 |
+
"grad_norm": 3.747777223587036,
|
2354 |
+
"learning_rate": 6.498866213151927e-05,
|
2355 |
+
"loss": 0.4908,
|
2356 |
+
"step": 2980
|
2357 |
+
},
|
2358 |
+
{
|
2359 |
+
"epoch": 4.75,
|
2360 |
+
"grad_norm": 3.217052459716797,
|
2361 |
+
"learning_rate": 6.453514739229024e-05,
|
2362 |
+
"loss": 0.5847,
|
2363 |
+
"step": 2990
|
2364 |
+
},
|
2365 |
+
{
|
2366 |
+
"epoch": 4.76,
|
2367 |
+
"grad_norm": 2.1214661598205566,
|
2368 |
+
"learning_rate": 6.408163265306123e-05,
|
2369 |
+
"loss": 0.7497,
|
2370 |
+
"step": 3000
|
2371 |
+
},
|
2372 |
+
{
|
2373 |
+
"epoch": 4.76,
|
2374 |
+
"eval_accuracy": 0.8301587301587302,
|
2375 |
+
"eval_loss": 0.5859270095825195,
|
2376 |
+
"eval_runtime": 89.9674,
|
2377 |
+
"eval_samples_per_second": 28.01,
|
2378 |
+
"eval_steps_per_second": 3.501,
|
2379 |
+
"step": 3000
|
2380 |
+
},
|
2381 |
+
{
|
2382 |
+
"epoch": 4.78,
|
2383 |
+
"grad_norm": 3.495818614959717,
|
2384 |
+
"learning_rate": 6.36281179138322e-05,
|
2385 |
+
"loss": 0.4944,
|
2386 |
+
"step": 3010
|
2387 |
+
},
|
2388 |
+
{
|
2389 |
+
"epoch": 4.79,
|
2390 |
+
"grad_norm": 6.128993034362793,
|
2391 |
+
"learning_rate": 6.317460317460318e-05,
|
2392 |
+
"loss": 0.5474,
|
2393 |
+
"step": 3020
|
2394 |
+
},
|
2395 |
+
{
|
2396 |
+
"epoch": 4.81,
|
2397 |
+
"grad_norm": 2.1895864009857178,
|
2398 |
+
"learning_rate": 6.272108843537415e-05,
|
2399 |
+
"loss": 0.5447,
|
2400 |
+
"step": 3030
|
2401 |
+
},
|
2402 |
+
{
|
2403 |
+
"epoch": 4.83,
|
2404 |
+
"grad_norm": 4.312340259552002,
|
2405 |
+
"learning_rate": 6.226757369614513e-05,
|
2406 |
+
"loss": 0.5194,
|
2407 |
+
"step": 3040
|
2408 |
+
},
|
2409 |
+
{
|
2410 |
+
"epoch": 4.84,
|
2411 |
+
"grad_norm": 5.473392009735107,
|
2412 |
+
"learning_rate": 6.181405895691609e-05,
|
2413 |
+
"loss": 0.5538,
|
2414 |
+
"step": 3050
|
2415 |
+
},
|
2416 |
+
{
|
2417 |
+
"epoch": 4.86,
|
2418 |
+
"grad_norm": 2.302345037460327,
|
2419 |
+
"learning_rate": 6.136054421768708e-05,
|
2420 |
+
"loss": 0.4733,
|
2421 |
+
"step": 3060
|
2422 |
+
},
|
2423 |
+
{
|
2424 |
+
"epoch": 4.87,
|
2425 |
+
"grad_norm": 3.3499696254730225,
|
2426 |
+
"learning_rate": 6.090702947845806e-05,
|
2427 |
+
"loss": 0.755,
|
2428 |
+
"step": 3070
|
2429 |
+
},
|
2430 |
+
{
|
2431 |
+
"epoch": 4.89,
|
2432 |
+
"grad_norm": 3.382891893386841,
|
2433 |
+
"learning_rate": 6.045351473922902e-05,
|
2434 |
+
"loss": 0.4829,
|
2435 |
+
"step": 3080
|
2436 |
+
},
|
2437 |
+
{
|
2438 |
+
"epoch": 4.9,
|
2439 |
+
"grad_norm": 3.4998888969421387,
|
2440 |
+
"learning_rate": 6e-05,
|
2441 |
+
"loss": 0.4543,
|
2442 |
+
"step": 3090
|
2443 |
+
},
|
2444 |
+
{
|
2445 |
+
"epoch": 4.92,
|
2446 |
+
"grad_norm": 3.2224600315093994,
|
2447 |
+
"learning_rate": 5.954648526077098e-05,
|
2448 |
+
"loss": 0.4856,
|
2449 |
+
"step": 3100
|
2450 |
+
},
|
2451 |
+
{
|
2452 |
+
"epoch": 4.92,
|
2453 |
+
"eval_accuracy": 0.8261904761904761,
|
2454 |
+
"eval_loss": 0.5833402872085571,
|
2455 |
+
"eval_runtime": 90.9659,
|
2456 |
+
"eval_samples_per_second": 27.703,
|
2457 |
+
"eval_steps_per_second": 3.463,
|
2458 |
+
"step": 3100
|
2459 |
+
},
|
2460 |
+
{
|
2461 |
+
"epoch": 4.94,
|
2462 |
+
"grad_norm": 2.1335177421569824,
|
2463 |
+
"learning_rate": 5.909297052154196e-05,
|
2464 |
+
"loss": 0.3995,
|
2465 |
+
"step": 3110
|
2466 |
+
},
|
2467 |
+
{
|
2468 |
+
"epoch": 4.95,
|
2469 |
+
"grad_norm": 4.156594753265381,
|
2470 |
+
"learning_rate": 5.8639455782312925e-05,
|
2471 |
+
"loss": 0.5539,
|
2472 |
+
"step": 3120
|
2473 |
+
},
|
2474 |
+
{
|
2475 |
+
"epoch": 4.97,
|
2476 |
+
"grad_norm": 5.811089515686035,
|
2477 |
+
"learning_rate": 5.8185941043083904e-05,
|
2478 |
+
"loss": 0.579,
|
2479 |
+
"step": 3130
|
2480 |
+
},
|
2481 |
+
{
|
2482 |
+
"epoch": 4.98,
|
2483 |
+
"grad_norm": 1.908595323562622,
|
2484 |
+
"learning_rate": 5.773242630385488e-05,
|
2485 |
+
"loss": 0.5315,
|
2486 |
+
"step": 3140
|
2487 |
+
},
|
2488 |
+
{
|
2489 |
+
"epoch": 5.0,
|
2490 |
+
"grad_norm": 2.8674533367156982,
|
2491 |
+
"learning_rate": 5.727891156462585e-05,
|
2492 |
+
"loss": 0.5577,
|
2493 |
+
"step": 3150
|
2494 |
+
},
|
2495 |
+
{
|
2496 |
+
"epoch": 5.02,
|
2497 |
+
"grad_norm": 1.5174939632415771,
|
2498 |
+
"learning_rate": 5.682539682539683e-05,
|
2499 |
+
"loss": 0.5052,
|
2500 |
+
"step": 3160
|
2501 |
+
},
|
2502 |
+
{
|
2503 |
+
"epoch": 5.03,
|
2504 |
+
"grad_norm": 3.2664871215820312,
|
2505 |
+
"learning_rate": 5.637188208616781e-05,
|
2506 |
+
"loss": 0.3135,
|
2507 |
+
"step": 3170
|
2508 |
+
},
|
2509 |
+
{
|
2510 |
+
"epoch": 5.05,
|
2511 |
+
"grad_norm": 5.35206937789917,
|
2512 |
+
"learning_rate": 5.5918367346938786e-05,
|
2513 |
+
"loss": 0.5859,
|
2514 |
+
"step": 3180
|
2515 |
+
},
|
2516 |
+
{
|
2517 |
+
"epoch": 5.06,
|
2518 |
+
"grad_norm": 2.6170833110809326,
|
2519 |
+
"learning_rate": 5.546485260770975e-05,
|
2520 |
+
"loss": 0.4511,
|
2521 |
+
"step": 3190
|
2522 |
+
},
|
2523 |
+
{
|
2524 |
+
"epoch": 5.08,
|
2525 |
+
"grad_norm": 3.2739861011505127,
|
2526 |
+
"learning_rate": 5.501133786848073e-05,
|
2527 |
+
"loss": 0.4959,
|
2528 |
+
"step": 3200
|
2529 |
+
},
|
2530 |
+
{
|
2531 |
+
"epoch": 5.08,
|
2532 |
+
"eval_accuracy": 0.832936507936508,
|
2533 |
+
"eval_loss": 0.5703846216201782,
|
2534 |
+
"eval_runtime": 92.0072,
|
2535 |
+
"eval_samples_per_second": 27.389,
|
2536 |
+
"eval_steps_per_second": 3.424,
|
2537 |
+
"step": 3200
|
2538 |
+
},
|
2539 |
+
{
|
2540 |
+
"epoch": 5.1,
|
2541 |
+
"grad_norm": 0.7258143424987793,
|
2542 |
+
"learning_rate": 5.455782312925171e-05,
|
2543 |
+
"loss": 0.4922,
|
2544 |
+
"step": 3210
|
2545 |
+
},
|
2546 |
+
{
|
2547 |
+
"epoch": 5.11,
|
2548 |
+
"grad_norm": 1.8463611602783203,
|
2549 |
+
"learning_rate": 5.4104308390022675e-05,
|
2550 |
+
"loss": 0.3888,
|
2551 |
+
"step": 3220
|
2552 |
+
},
|
2553 |
+
{
|
2554 |
+
"epoch": 5.13,
|
2555 |
+
"grad_norm": 4.082030296325684,
|
2556 |
+
"learning_rate": 5.3650793650793654e-05,
|
2557 |
+
"loss": 0.4486,
|
2558 |
+
"step": 3230
|
2559 |
+
},
|
2560 |
+
{
|
2561 |
+
"epoch": 5.14,
|
2562 |
+
"grad_norm": 1.123199462890625,
|
2563 |
+
"learning_rate": 5.319727891156463e-05,
|
2564 |
+
"loss": 0.4229,
|
2565 |
+
"step": 3240
|
2566 |
+
},
|
2567 |
+
{
|
2568 |
+
"epoch": 5.16,
|
2569 |
+
"grad_norm": 2.546860694885254,
|
2570 |
+
"learning_rate": 5.2743764172335605e-05,
|
2571 |
+
"loss": 0.5514,
|
2572 |
+
"step": 3250
|
2573 |
+
},
|
2574 |
+
{
|
2575 |
+
"epoch": 5.17,
|
2576 |
+
"grad_norm": 6.097323417663574,
|
2577 |
+
"learning_rate": 5.229024943310658e-05,
|
2578 |
+
"loss": 0.4391,
|
2579 |
+
"step": 3260
|
2580 |
+
},
|
2581 |
+
{
|
2582 |
+
"epoch": 5.19,
|
2583 |
+
"grad_norm": 3.1347315311431885,
|
2584 |
+
"learning_rate": 5.1836734693877557e-05,
|
2585 |
+
"loss": 0.4455,
|
2586 |
+
"step": 3270
|
2587 |
+
},
|
2588 |
+
{
|
2589 |
+
"epoch": 5.21,
|
2590 |
+
"grad_norm": 2.0431602001190186,
|
2591 |
+
"learning_rate": 5.138321995464853e-05,
|
2592 |
+
"loss": 0.3076,
|
2593 |
+
"step": 3280
|
2594 |
+
},
|
2595 |
+
{
|
2596 |
+
"epoch": 5.22,
|
2597 |
+
"grad_norm": 4.452468395233154,
|
2598 |
+
"learning_rate": 5.09297052154195e-05,
|
2599 |
+
"loss": 0.4442,
|
2600 |
+
"step": 3290
|
2601 |
+
},
|
2602 |
+
{
|
2603 |
+
"epoch": 5.24,
|
2604 |
+
"grad_norm": 5.282511234283447,
|
2605 |
+
"learning_rate": 5.047619047619048e-05,
|
2606 |
+
"loss": 0.4413,
|
2607 |
+
"step": 3300
|
2608 |
+
},
|
2609 |
+
{
|
2610 |
+
"epoch": 5.24,
|
2611 |
+
"eval_accuracy": 0.819047619047619,
|
2612 |
+
"eval_loss": 0.6217456459999084,
|
2613 |
+
"eval_runtime": 91.9773,
|
2614 |
+
"eval_samples_per_second": 27.398,
|
2615 |
+
"eval_steps_per_second": 3.425,
|
2616 |
+
"step": 3300
|
2617 |
+
},
|
2618 |
+
{
|
2619 |
+
"epoch": 5.25,
|
2620 |
+
"grad_norm": 8.806018829345703,
|
2621 |
+
"learning_rate": 5.002267573696145e-05,
|
2622 |
+
"loss": 0.4263,
|
2623 |
+
"step": 3310
|
2624 |
+
},
|
2625 |
+
{
|
2626 |
+
"epoch": 5.27,
|
2627 |
+
"grad_norm": 4.782093048095703,
|
2628 |
+
"learning_rate": 4.9569160997732425e-05,
|
2629 |
+
"loss": 0.6431,
|
2630 |
+
"step": 3320
|
2631 |
+
},
|
2632 |
+
{
|
2633 |
+
"epoch": 5.29,
|
2634 |
+
"grad_norm": 5.115506172180176,
|
2635 |
+
"learning_rate": 4.9115646258503404e-05,
|
2636 |
+
"loss": 0.4876,
|
2637 |
+
"step": 3330
|
2638 |
+
},
|
2639 |
+
{
|
2640 |
+
"epoch": 5.3,
|
2641 |
+
"grad_norm": 4.416604995727539,
|
2642 |
+
"learning_rate": 4.8662131519274376e-05,
|
2643 |
+
"loss": 0.371,
|
2644 |
+
"step": 3340
|
2645 |
+
},
|
2646 |
+
{
|
2647 |
+
"epoch": 5.32,
|
2648 |
+
"grad_norm": 3.7609243392944336,
|
2649 |
+
"learning_rate": 4.820861678004535e-05,
|
2650 |
+
"loss": 0.3873,
|
2651 |
+
"step": 3350
|
2652 |
+
},
|
2653 |
+
{
|
2654 |
+
"epoch": 5.33,
|
2655 |
+
"grad_norm": 4.652336120605469,
|
2656 |
+
"learning_rate": 4.775510204081633e-05,
|
2657 |
+
"loss": 0.4134,
|
2658 |
+
"step": 3360
|
2659 |
+
},
|
2660 |
+
{
|
2661 |
+
"epoch": 5.35,
|
2662 |
+
"grad_norm": 5.700862407684326,
|
2663 |
+
"learning_rate": 4.73015873015873e-05,
|
2664 |
+
"loss": 0.4463,
|
2665 |
+
"step": 3370
|
2666 |
+
},
|
2667 |
+
{
|
2668 |
+
"epoch": 5.37,
|
2669 |
+
"grad_norm": 4.792759895324707,
|
2670 |
+
"learning_rate": 4.684807256235828e-05,
|
2671 |
+
"loss": 0.4243,
|
2672 |
+
"step": 3380
|
2673 |
+
},
|
2674 |
+
{
|
2675 |
+
"epoch": 5.38,
|
2676 |
+
"grad_norm": 4.60031795501709,
|
2677 |
+
"learning_rate": 4.639455782312925e-05,
|
2678 |
+
"loss": 0.3602,
|
2679 |
+
"step": 3390
|
2680 |
+
},
|
2681 |
+
{
|
2682 |
+
"epoch": 5.4,
|
2683 |
+
"grad_norm": 6.657435417175293,
|
2684 |
+
"learning_rate": 4.594104308390023e-05,
|
2685 |
+
"loss": 0.4513,
|
2686 |
+
"step": 3400
|
2687 |
+
},
|
2688 |
+
{
|
2689 |
+
"epoch": 5.4,
|
2690 |
+
"eval_accuracy": 0.8293650793650794,
|
2691 |
+
"eval_loss": 0.5750200748443604,
|
2692 |
+
"eval_runtime": 96.412,
|
2693 |
+
"eval_samples_per_second": 26.138,
|
2694 |
+
"eval_steps_per_second": 3.267,
|
2695 |
+
"step": 3400
|
2696 |
+
},
|
2697 |
+
{
|
2698 |
+
"epoch": 5.41,
|
2699 |
+
"grad_norm": 3.526585578918457,
|
2700 |
+
"learning_rate": 4.54875283446712e-05,
|
2701 |
+
"loss": 0.374,
|
2702 |
+
"step": 3410
|
2703 |
+
},
|
2704 |
+
{
|
2705 |
+
"epoch": 5.43,
|
2706 |
+
"grad_norm": 2.742906332015991,
|
2707 |
+
"learning_rate": 4.5034013605442174e-05,
|
2708 |
+
"loss": 0.3822,
|
2709 |
+
"step": 3420
|
2710 |
+
},
|
2711 |
+
{
|
2712 |
+
"epoch": 5.44,
|
2713 |
+
"grad_norm": 3.6437864303588867,
|
2714 |
+
"learning_rate": 4.4580498866213154e-05,
|
2715 |
+
"loss": 0.4369,
|
2716 |
+
"step": 3430
|
2717 |
+
},
|
2718 |
+
{
|
2719 |
+
"epoch": 5.46,
|
2720 |
+
"grad_norm": 2.621497869491577,
|
2721 |
+
"learning_rate": 4.4126984126984126e-05,
|
2722 |
+
"loss": 0.3399,
|
2723 |
+
"step": 3440
|
2724 |
+
},
|
2725 |
+
{
|
2726 |
+
"epoch": 5.48,
|
2727 |
+
"grad_norm": 1.8672789335250854,
|
2728 |
+
"learning_rate": 4.3673469387755105e-05,
|
2729 |
+
"loss": 0.584,
|
2730 |
+
"step": 3450
|
2731 |
+
},
|
2732 |
+
{
|
2733 |
+
"epoch": 5.49,
|
2734 |
+
"grad_norm": 1.4387513399124146,
|
2735 |
+
"learning_rate": 4.321995464852608e-05,
|
2736 |
+
"loss": 0.4242,
|
2737 |
+
"step": 3460
|
2738 |
+
},
|
2739 |
+
{
|
2740 |
+
"epoch": 5.51,
|
2741 |
+
"grad_norm": 0.7556703090667725,
|
2742 |
+
"learning_rate": 4.2766439909297056e-05,
|
2743 |
+
"loss": 0.462,
|
2744 |
+
"step": 3470
|
2745 |
+
},
|
2746 |
+
{
|
2747 |
+
"epoch": 5.52,
|
2748 |
+
"grad_norm": 2.0518500804901123,
|
2749 |
+
"learning_rate": 4.231292517006803e-05,
|
2750 |
+
"loss": 0.4239,
|
2751 |
+
"step": 3480
|
2752 |
+
},
|
2753 |
+
{
|
2754 |
+
"epoch": 5.54,
|
2755 |
+
"grad_norm": 4.876095771789551,
|
2756 |
+
"learning_rate": 4.1859410430839e-05,
|
2757 |
+
"loss": 0.5488,
|
2758 |
+
"step": 3490
|
2759 |
+
},
|
2760 |
+
{
|
2761 |
+
"epoch": 5.56,
|
2762 |
+
"grad_norm": 1.6563076972961426,
|
2763 |
+
"learning_rate": 4.140589569160998e-05,
|
2764 |
+
"loss": 0.3987,
|
2765 |
+
"step": 3500
|
2766 |
+
},
|
2767 |
+
{
|
2768 |
+
"epoch": 5.56,
|
2769 |
+
"eval_accuracy": 0.8341269841269842,
|
2770 |
+
"eval_loss": 0.5825861096382141,
|
2771 |
+
"eval_runtime": 98.7535,
|
2772 |
+
"eval_samples_per_second": 25.518,
|
2773 |
+
"eval_steps_per_second": 3.19,
|
2774 |
+
"step": 3500
|
2775 |
+
},
|
2776 |
+
{
|
2777 |
+
"epoch": 5.57,
|
2778 |
+
"grad_norm": 6.538485050201416,
|
2779 |
+
"learning_rate": 4.095238095238095e-05,
|
2780 |
+
"loss": 0.5583,
|
2781 |
+
"step": 3510
|
2782 |
+
},
|
2783 |
+
{
|
2784 |
+
"epoch": 5.59,
|
2785 |
+
"grad_norm": 4.381786823272705,
|
2786 |
+
"learning_rate": 4.049886621315193e-05,
|
2787 |
+
"loss": 0.408,
|
2788 |
+
"step": 3520
|
2789 |
+
},
|
2790 |
+
{
|
2791 |
+
"epoch": 5.6,
|
2792 |
+
"grad_norm": 3.696018695831299,
|
2793 |
+
"learning_rate": 4.00453514739229e-05,
|
2794 |
+
"loss": 0.4421,
|
2795 |
+
"step": 3530
|
2796 |
+
},
|
2797 |
+
{
|
2798 |
+
"epoch": 5.62,
|
2799 |
+
"grad_norm": 3.3752057552337646,
|
2800 |
+
"learning_rate": 3.9591836734693876e-05,
|
2801 |
+
"loss": 0.4057,
|
2802 |
+
"step": 3540
|
2803 |
+
},
|
2804 |
+
{
|
2805 |
+
"epoch": 5.63,
|
2806 |
+
"grad_norm": 6.889618396759033,
|
2807 |
+
"learning_rate": 3.9138321995464855e-05,
|
2808 |
+
"loss": 0.4479,
|
2809 |
+
"step": 3550
|
2810 |
+
},
|
2811 |
+
{
|
2812 |
+
"epoch": 5.65,
|
2813 |
+
"grad_norm": 5.5090131759643555,
|
2814 |
+
"learning_rate": 3.868480725623583e-05,
|
2815 |
+
"loss": 0.6009,
|
2816 |
+
"step": 3560
|
2817 |
+
},
|
2818 |
+
{
|
2819 |
+
"epoch": 5.67,
|
2820 |
+
"grad_norm": 2.368633985519409,
|
2821 |
+
"learning_rate": 3.8231292517006806e-05,
|
2822 |
+
"loss": 0.4276,
|
2823 |
+
"step": 3570
|
2824 |
+
},
|
2825 |
+
{
|
2826 |
+
"epoch": 5.68,
|
2827 |
+
"grad_norm": 4.297762393951416,
|
2828 |
+
"learning_rate": 3.777777777777778e-05,
|
2829 |
+
"loss": 0.4368,
|
2830 |
+
"step": 3580
|
2831 |
+
},
|
2832 |
+
{
|
2833 |
+
"epoch": 5.7,
|
2834 |
+
"grad_norm": 3.7877378463745117,
|
2835 |
+
"learning_rate": 3.732426303854876e-05,
|
2836 |
+
"loss": 0.3481,
|
2837 |
+
"step": 3590
|
2838 |
+
},
|
2839 |
+
{
|
2840 |
+
"epoch": 5.71,
|
2841 |
+
"grad_norm": 2.9667625427246094,
|
2842 |
+
"learning_rate": 3.687074829931973e-05,
|
2843 |
+
"loss": 0.4395,
|
2844 |
+
"step": 3600
|
2845 |
+
},
|
2846 |
+
{
|
2847 |
+
"epoch": 5.71,
|
2848 |
+
"eval_accuracy": 0.8384920634920635,
|
2849 |
+
"eval_loss": 0.5753714442253113,
|
2850 |
+
"eval_runtime": 97.0735,
|
2851 |
+
"eval_samples_per_second": 25.96,
|
2852 |
+
"eval_steps_per_second": 3.245,
|
2853 |
+
"step": 3600
|
2854 |
+
},
|
2855 |
+
{
|
2856 |
+
"epoch": 5.73,
|
2857 |
+
"grad_norm": 5.830836296081543,
|
2858 |
+
"learning_rate": 3.64172335600907e-05,
|
2859 |
+
"loss": 0.4859,
|
2860 |
+
"step": 3610
|
2861 |
+
},
|
2862 |
+
{
|
2863 |
+
"epoch": 5.75,
|
2864 |
+
"grad_norm": 5.262144088745117,
|
2865 |
+
"learning_rate": 3.596371882086168e-05,
|
2866 |
+
"loss": 0.4409,
|
2867 |
+
"step": 3620
|
2868 |
+
},
|
2869 |
+
{
|
2870 |
+
"epoch": 5.76,
|
2871 |
+
"grad_norm": 0.9806166291236877,
|
2872 |
+
"learning_rate": 3.551020408163265e-05,
|
2873 |
+
"loss": 0.3884,
|
2874 |
+
"step": 3630
|
2875 |
+
},
|
2876 |
+
{
|
2877 |
+
"epoch": 5.78,
|
2878 |
+
"grad_norm": 3.1864867210388184,
|
2879 |
+
"learning_rate": 3.505668934240363e-05,
|
2880 |
+
"loss": 0.3753,
|
2881 |
+
"step": 3640
|
2882 |
+
},
|
2883 |
+
{
|
2884 |
+
"epoch": 5.79,
|
2885 |
+
"grad_norm": 2.679213762283325,
|
2886 |
+
"learning_rate": 3.4603174603174604e-05,
|
2887 |
+
"loss": 0.3764,
|
2888 |
+
"step": 3650
|
2889 |
+
},
|
2890 |
+
{
|
2891 |
+
"epoch": 5.81,
|
2892 |
+
"grad_norm": 1.3040461540222168,
|
2893 |
+
"learning_rate": 3.4149659863945583e-05,
|
2894 |
+
"loss": 0.3632,
|
2895 |
+
"step": 3660
|
2896 |
+
},
|
2897 |
+
{
|
2898 |
+
"epoch": 5.83,
|
2899 |
+
"grad_norm": 6.803734302520752,
|
2900 |
+
"learning_rate": 3.3696145124716556e-05,
|
2901 |
+
"loss": 0.6695,
|
2902 |
+
"step": 3670
|
2903 |
+
},
|
2904 |
+
{
|
2905 |
+
"epoch": 5.84,
|
2906 |
+
"grad_norm": 3.717195510864258,
|
2907 |
+
"learning_rate": 3.324263038548753e-05,
|
2908 |
+
"loss": 0.4226,
|
2909 |
+
"step": 3680
|
2910 |
+
},
|
2911 |
+
{
|
2912 |
+
"epoch": 5.86,
|
2913 |
+
"grad_norm": 0.3749280273914337,
|
2914 |
+
"learning_rate": 3.278911564625851e-05,
|
2915 |
+
"loss": 0.4404,
|
2916 |
+
"step": 3690
|
2917 |
+
},
|
2918 |
+
{
|
2919 |
+
"epoch": 5.87,
|
2920 |
+
"grad_norm": 3.4548332691192627,
|
2921 |
+
"learning_rate": 3.233560090702948e-05,
|
2922 |
+
"loss": 0.4669,
|
2923 |
+
"step": 3700
|
2924 |
+
},
|
2925 |
+
{
|
2926 |
+
"epoch": 5.87,
|
2927 |
+
"eval_accuracy": 0.8357142857142857,
|
2928 |
+
"eval_loss": 0.5652737021446228,
|
2929 |
+
"eval_runtime": 98.0382,
|
2930 |
+
"eval_samples_per_second": 25.704,
|
2931 |
+
"eval_steps_per_second": 3.213,
|
2932 |
+
"step": 3700
|
2933 |
+
},
|
2934 |
+
{
|
2935 |
+
"epoch": 5.89,
|
2936 |
+
"grad_norm": 2.5312252044677734,
|
2937 |
+
"learning_rate": 3.188208616780046e-05,
|
2938 |
+
"loss": 0.4786,
|
2939 |
+
"step": 3710
|
2940 |
+
},
|
2941 |
+
{
|
2942 |
+
"epoch": 5.9,
|
2943 |
+
"grad_norm": 4.841963291168213,
|
2944 |
+
"learning_rate": 3.142857142857143e-05,
|
2945 |
+
"loss": 0.5179,
|
2946 |
+
"step": 3720
|
2947 |
+
},
|
2948 |
+
{
|
2949 |
+
"epoch": 5.92,
|
2950 |
+
"grad_norm": 4.394898414611816,
|
2951 |
+
"learning_rate": 3.097505668934241e-05,
|
2952 |
+
"loss": 0.5062,
|
2953 |
+
"step": 3730
|
2954 |
+
},
|
2955 |
+
{
|
2956 |
+
"epoch": 5.94,
|
2957 |
+
"grad_norm": 4.590970516204834,
|
2958 |
+
"learning_rate": 3.052154195011338e-05,
|
2959 |
+
"loss": 0.3639,
|
2960 |
+
"step": 3740
|
2961 |
+
},
|
2962 |
+
{
|
2963 |
+
"epoch": 5.95,
|
2964 |
+
"grad_norm": 4.6838459968566895,
|
2965 |
+
"learning_rate": 3.0068027210884354e-05,
|
2966 |
+
"loss": 0.3552,
|
2967 |
+
"step": 3750
|
2968 |
+
},
|
2969 |
+
{
|
2970 |
+
"epoch": 5.97,
|
2971 |
+
"grad_norm": 4.303285121917725,
|
2972 |
+
"learning_rate": 2.961451247165533e-05,
|
2973 |
+
"loss": 0.3526,
|
2974 |
+
"step": 3760
|
2975 |
+
},
|
2976 |
+
{
|
2977 |
+
"epoch": 5.98,
|
2978 |
+
"grad_norm": 6.06368350982666,
|
2979 |
+
"learning_rate": 2.9160997732426306e-05,
|
2980 |
+
"loss": 0.3266,
|
2981 |
+
"step": 3770
|
2982 |
+
},
|
2983 |
+
{
|
2984 |
+
"epoch": 6.0,
|
2985 |
+
"grad_norm": 4.715054988861084,
|
2986 |
+
"learning_rate": 2.870748299319728e-05,
|
2987 |
+
"loss": 0.4612,
|
2988 |
+
"step": 3780
|
2989 |
+
},
|
2990 |
+
{
|
2991 |
+
"epoch": 6.02,
|
2992 |
+
"grad_norm": 3.029750108718872,
|
2993 |
+
"learning_rate": 2.8253968253968253e-05,
|
2994 |
+
"loss": 0.3938,
|
2995 |
+
"step": 3790
|
2996 |
+
},
|
2997 |
+
{
|
2998 |
+
"epoch": 6.03,
|
2999 |
+
"grad_norm": 6.53373384475708,
|
3000 |
+
"learning_rate": 2.7800453514739233e-05,
|
3001 |
+
"loss": 0.4005,
|
3002 |
+
"step": 3800
|
3003 |
+
},
|
3004 |
+
{
|
3005 |
+
"epoch": 6.03,
|
3006 |
+
"eval_accuracy": 0.8376984126984127,
|
3007 |
+
"eval_loss": 0.542424201965332,
|
3008 |
+
"eval_runtime": 92.2864,
|
3009 |
+
"eval_samples_per_second": 27.306,
|
3010 |
+
"eval_steps_per_second": 3.413,
|
3011 |
+
"step": 3800
|
3012 |
+
},
|
3013 |
+
{
|
3014 |
+
"epoch": 6.05,
|
3015 |
+
"grad_norm": 2.6752915382385254,
|
3016 |
+
"learning_rate": 2.7346938775510205e-05,
|
3017 |
+
"loss": 0.311,
|
3018 |
+
"step": 3810
|
3019 |
+
},
|
3020 |
+
{
|
3021 |
+
"epoch": 6.06,
|
3022 |
+
"grad_norm": 5.5302863121032715,
|
3023 |
+
"learning_rate": 2.6893424036281177e-05,
|
3024 |
+
"loss": 0.4392,
|
3025 |
+
"step": 3820
|
3026 |
+
},
|
3027 |
+
{
|
3028 |
+
"epoch": 6.08,
|
3029 |
+
"grad_norm": 3.140334367752075,
|
3030 |
+
"learning_rate": 2.6439909297052156e-05,
|
3031 |
+
"loss": 0.3301,
|
3032 |
+
"step": 3830
|
3033 |
+
},
|
3034 |
+
{
|
3035 |
+
"epoch": 6.1,
|
3036 |
+
"grad_norm": 7.531820774078369,
|
3037 |
+
"learning_rate": 2.598639455782313e-05,
|
3038 |
+
"loss": 0.4208,
|
3039 |
+
"step": 3840
|
3040 |
+
},
|
3041 |
+
{
|
3042 |
+
"epoch": 6.11,
|
3043 |
+
"grad_norm": 4.852546215057373,
|
3044 |
+
"learning_rate": 2.5532879818594107e-05,
|
3045 |
+
"loss": 0.3858,
|
3046 |
+
"step": 3850
|
3047 |
+
},
|
3048 |
+
{
|
3049 |
+
"epoch": 6.13,
|
3050 |
+
"grad_norm": 6.866227149963379,
|
3051 |
+
"learning_rate": 2.507936507936508e-05,
|
3052 |
+
"loss": 0.4882,
|
3053 |
+
"step": 3860
|
3054 |
+
},
|
3055 |
+
{
|
3056 |
+
"epoch": 6.14,
|
3057 |
+
"grad_norm": 2.053617477416992,
|
3058 |
+
"learning_rate": 2.4625850340136055e-05,
|
3059 |
+
"loss": 0.3131,
|
3060 |
+
"step": 3870
|
3061 |
+
},
|
3062 |
+
{
|
3063 |
+
"epoch": 6.16,
|
3064 |
+
"grad_norm": 3.9806272983551025,
|
3065 |
+
"learning_rate": 2.417233560090703e-05,
|
3066 |
+
"loss": 0.4078,
|
3067 |
+
"step": 3880
|
3068 |
+
},
|
3069 |
+
{
|
3070 |
+
"epoch": 6.17,
|
3071 |
+
"grad_norm": 3.6454029083251953,
|
3072 |
+
"learning_rate": 2.3718820861678007e-05,
|
3073 |
+
"loss": 0.4362,
|
3074 |
+
"step": 3890
|
3075 |
+
},
|
3076 |
+
{
|
3077 |
+
"epoch": 6.19,
|
3078 |
+
"grad_norm": 7.963522434234619,
|
3079 |
+
"learning_rate": 2.326530612244898e-05,
|
3080 |
+
"loss": 0.4457,
|
3081 |
+
"step": 3900
|
3082 |
+
},
|
3083 |
+
{
|
3084 |
+
"epoch": 6.19,
|
3085 |
+
"eval_accuracy": 0.8392857142857143,
|
3086 |
+
"eval_loss": 0.5619771480560303,
|
3087 |
+
"eval_runtime": 91.8917,
|
3088 |
+
"eval_samples_per_second": 27.424,
|
3089 |
+
"eval_steps_per_second": 3.428,
|
3090 |
+
"step": 3900
|
3091 |
+
},
|
3092 |
+
{
|
3093 |
+
"epoch": 6.21,
|
3094 |
+
"grad_norm": 0.9147405624389648,
|
3095 |
+
"learning_rate": 2.2811791383219955e-05,
|
3096 |
+
"loss": 0.278,
|
3097 |
+
"step": 3910
|
3098 |
+
},
|
3099 |
+
{
|
3100 |
+
"epoch": 6.22,
|
3101 |
+
"grad_norm": 7.86151647567749,
|
3102 |
+
"learning_rate": 2.235827664399093e-05,
|
3103 |
+
"loss": 0.3866,
|
3104 |
+
"step": 3920
|
3105 |
+
},
|
3106 |
+
{
|
3107 |
+
"epoch": 6.24,
|
3108 |
+
"grad_norm": 5.7085371017456055,
|
3109 |
+
"learning_rate": 2.1904761904761906e-05,
|
3110 |
+
"loss": 0.3633,
|
3111 |
+
"step": 3930
|
3112 |
+
},
|
3113 |
+
{
|
3114 |
+
"epoch": 6.25,
|
3115 |
+
"grad_norm": 4.3009772300720215,
|
3116 |
+
"learning_rate": 2.145124716553288e-05,
|
3117 |
+
"loss": 0.3932,
|
3118 |
+
"step": 3940
|
3119 |
+
},
|
3120 |
+
{
|
3121 |
+
"epoch": 6.27,
|
3122 |
+
"grad_norm": 0.3253590166568756,
|
3123 |
+
"learning_rate": 2.0997732426303857e-05,
|
3124 |
+
"loss": 0.3084,
|
3125 |
+
"step": 3950
|
3126 |
+
},
|
3127 |
+
{
|
3128 |
+
"epoch": 6.29,
|
3129 |
+
"grad_norm": 4.880115509033203,
|
3130 |
+
"learning_rate": 2.0544217687074833e-05,
|
3131 |
+
"loss": 0.3723,
|
3132 |
+
"step": 3960
|
3133 |
+
},
|
3134 |
+
{
|
3135 |
+
"epoch": 6.3,
|
3136 |
+
"grad_norm": 5.515774250030518,
|
3137 |
+
"learning_rate": 2.0090702947845805e-05,
|
3138 |
+
"loss": 0.4312,
|
3139 |
+
"step": 3970
|
3140 |
+
},
|
3141 |
+
{
|
3142 |
+
"epoch": 6.32,
|
3143 |
+
"grad_norm": 4.72555685043335,
|
3144 |
+
"learning_rate": 1.963718820861678e-05,
|
3145 |
+
"loss": 0.2305,
|
3146 |
+
"step": 3980
|
3147 |
+
},
|
3148 |
+
{
|
3149 |
+
"epoch": 6.33,
|
3150 |
+
"grad_norm": 0.13027626276016235,
|
3151 |
+
"learning_rate": 1.9183673469387756e-05,
|
3152 |
+
"loss": 0.3037,
|
3153 |
+
"step": 3990
|
3154 |
+
},
|
3155 |
+
{
|
3156 |
+
"epoch": 6.35,
|
3157 |
+
"grad_norm": 4.166107654571533,
|
3158 |
+
"learning_rate": 1.8730158730158732e-05,
|
3159 |
+
"loss": 0.3693,
|
3160 |
+
"step": 4000
|
3161 |
+
},
|
3162 |
+
{
|
3163 |
+
"epoch": 6.35,
|
3164 |
+
"eval_accuracy": 0.8412698412698413,
|
3165 |
+
"eval_loss": 0.5411426424980164,
|
3166 |
+
"eval_runtime": 91.5694,
|
3167 |
+
"eval_samples_per_second": 27.52,
|
3168 |
+
"eval_steps_per_second": 3.44,
|
3169 |
+
"step": 4000
|
3170 |
+
},
|
3171 |
+
{
|
3172 |
+
"epoch": 6.37,
|
3173 |
+
"grad_norm": 3.1201322078704834,
|
3174 |
+
"learning_rate": 1.8276643990929708e-05,
|
3175 |
+
"loss": 0.3472,
|
3176 |
+
"step": 4010
|
3177 |
+
},
|
3178 |
+
{
|
3179 |
+
"epoch": 6.38,
|
3180 |
+
"grad_norm": 5.773028373718262,
|
3181 |
+
"learning_rate": 1.7823129251700683e-05,
|
3182 |
+
"loss": 0.376,
|
3183 |
+
"step": 4020
|
3184 |
+
},
|
3185 |
+
{
|
3186 |
+
"epoch": 6.4,
|
3187 |
+
"grad_norm": 4.617589473724365,
|
3188 |
+
"learning_rate": 1.736961451247166e-05,
|
3189 |
+
"loss": 0.4044,
|
3190 |
+
"step": 4030
|
3191 |
+
},
|
3192 |
+
{
|
3193 |
+
"epoch": 6.41,
|
3194 |
+
"grad_norm": 2.2319741249084473,
|
3195 |
+
"learning_rate": 1.691609977324263e-05,
|
3196 |
+
"loss": 0.2603,
|
3197 |
+
"step": 4040
|
3198 |
+
},
|
3199 |
+
{
|
3200 |
+
"epoch": 6.43,
|
3201 |
+
"grad_norm": 4.363328456878662,
|
3202 |
+
"learning_rate": 1.6462585034013607e-05,
|
3203 |
+
"loss": 0.3736,
|
3204 |
+
"step": 4050
|
3205 |
+
},
|
3206 |
+
{
|
3207 |
+
"epoch": 6.44,
|
3208 |
+
"grad_norm": 1.4275892972946167,
|
3209 |
+
"learning_rate": 1.6009070294784583e-05,
|
3210 |
+
"loss": 0.2221,
|
3211 |
+
"step": 4060
|
3212 |
+
},
|
3213 |
+
{
|
3214 |
+
"epoch": 6.46,
|
3215 |
+
"grad_norm": 1.1315315961837769,
|
3216 |
+
"learning_rate": 1.5555555555555555e-05,
|
3217 |
+
"loss": 0.2594,
|
3218 |
+
"step": 4070
|
3219 |
+
},
|
3220 |
+
{
|
3221 |
+
"epoch": 6.48,
|
3222 |
+
"grad_norm": 2.161555051803589,
|
3223 |
+
"learning_rate": 1.5102040816326532e-05,
|
3224 |
+
"loss": 0.3224,
|
3225 |
+
"step": 4080
|
3226 |
+
},
|
3227 |
+
{
|
3228 |
+
"epoch": 6.49,
|
3229 |
+
"grad_norm": 5.551158428192139,
|
3230 |
+
"learning_rate": 1.4648526077097508e-05,
|
3231 |
+
"loss": 0.2861,
|
3232 |
+
"step": 4090
|
3233 |
+
},
|
3234 |
+
{
|
3235 |
+
"epoch": 6.51,
|
3236 |
+
"grad_norm": 4.5997419357299805,
|
3237 |
+
"learning_rate": 1.419501133786848e-05,
|
3238 |
+
"loss": 0.2933,
|
3239 |
+
"step": 4100
|
3240 |
+
},
|
3241 |
+
{
|
3242 |
+
"epoch": 6.51,
|
3243 |
+
"eval_accuracy": 0.8484126984126984,
|
3244 |
+
"eval_loss": 0.5324992537498474,
|
3245 |
+
"eval_runtime": 92.004,
|
3246 |
+
"eval_samples_per_second": 27.39,
|
3247 |
+
"eval_steps_per_second": 3.424,
|
3248 |
+
"step": 4100
|
3249 |
+
},
|
3250 |
+
{
|
3251 |
+
"epoch": 6.52,
|
3252 |
+
"grad_norm": 4.983388900756836,
|
3253 |
+
"learning_rate": 1.3741496598639456e-05,
|
3254 |
+
"loss": 0.3076,
|
3255 |
+
"step": 4110
|
3256 |
+
},
|
3257 |
+
{
|
3258 |
+
"epoch": 6.54,
|
3259 |
+
"grad_norm": 7.082801818847656,
|
3260 |
+
"learning_rate": 1.3287981859410432e-05,
|
3261 |
+
"loss": 0.4137,
|
3262 |
+
"step": 4120
|
3263 |
+
},
|
3264 |
+
{
|
3265 |
+
"epoch": 6.56,
|
3266 |
+
"grad_norm": 5.25059700012207,
|
3267 |
+
"learning_rate": 1.2834467120181407e-05,
|
3268 |
+
"loss": 0.3036,
|
3269 |
+
"step": 4130
|
3270 |
+
},
|
3271 |
+
{
|
3272 |
+
"epoch": 6.57,
|
3273 |
+
"grad_norm": 4.526573181152344,
|
3274 |
+
"learning_rate": 1.2380952380952381e-05,
|
3275 |
+
"loss": 0.3122,
|
3276 |
+
"step": 4140
|
3277 |
+
},
|
3278 |
+
{
|
3279 |
+
"epoch": 6.59,
|
3280 |
+
"grad_norm": 3.637713670730591,
|
3281 |
+
"learning_rate": 1.1927437641723357e-05,
|
3282 |
+
"loss": 0.4162,
|
3283 |
+
"step": 4150
|
3284 |
+
},
|
3285 |
+
{
|
3286 |
+
"epoch": 6.6,
|
3287 |
+
"grad_norm": 7.545217514038086,
|
3288 |
+
"learning_rate": 1.147392290249433e-05,
|
3289 |
+
"loss": 0.5283,
|
3290 |
+
"step": 4160
|
3291 |
+
},
|
3292 |
+
{
|
3293 |
+
"epoch": 6.62,
|
3294 |
+
"grad_norm": 3.526754856109619,
|
3295 |
+
"learning_rate": 1.1020408163265306e-05,
|
3296 |
+
"loss": 0.4345,
|
3297 |
+
"step": 4170
|
3298 |
+
},
|
3299 |
+
{
|
3300 |
+
"epoch": 6.63,
|
3301 |
+
"grad_norm": 5.48629093170166,
|
3302 |
+
"learning_rate": 1.056689342403628e-05,
|
3303 |
+
"loss": 0.3755,
|
3304 |
+
"step": 4180
|
3305 |
+
},
|
3306 |
+
{
|
3307 |
+
"epoch": 6.65,
|
3308 |
+
"grad_norm": 3.289555788040161,
|
3309 |
+
"learning_rate": 1.0113378684807256e-05,
|
3310 |
+
"loss": 0.3603,
|
3311 |
+
"step": 4190
|
3312 |
+
},
|
3313 |
+
{
|
3314 |
+
"epoch": 6.67,
|
3315 |
+
"grad_norm": 3.701138496398926,
|
3316 |
+
"learning_rate": 9.659863945578232e-06,
|
3317 |
+
"loss": 0.2603,
|
3318 |
+
"step": 4200
|
3319 |
+
},
|
3320 |
+
{
|
3321 |
+
"epoch": 6.67,
|
3322 |
+
"eval_accuracy": 0.8476190476190476,
|
3323 |
+
"eval_loss": 0.5360472202301025,
|
3324 |
+
"eval_runtime": 94.6291,
|
3325 |
+
"eval_samples_per_second": 26.63,
|
3326 |
+
"eval_steps_per_second": 3.329,
|
3327 |
+
"step": 4200
|
3328 |
+
},
|
3329 |
+
{
|
3330 |
+
"epoch": 6.68,
|
3331 |
+
"grad_norm": 4.533103942871094,
|
3332 |
+
"learning_rate": 9.206349206349207e-06,
|
3333 |
+
"loss": 0.3483,
|
3334 |
+
"step": 4210
|
3335 |
+
},
|
3336 |
+
{
|
3337 |
+
"epoch": 6.7,
|
3338 |
+
"grad_norm": 6.598170280456543,
|
3339 |
+
"learning_rate": 8.752834467120181e-06,
|
3340 |
+
"loss": 0.4429,
|
3341 |
+
"step": 4220
|
3342 |
+
},
|
3343 |
+
{
|
3344 |
+
"epoch": 6.71,
|
3345 |
+
"grad_norm": 3.7935194969177246,
|
3346 |
+
"learning_rate": 8.299319727891157e-06,
|
3347 |
+
"loss": 0.2892,
|
3348 |
+
"step": 4230
|
3349 |
+
},
|
3350 |
+
{
|
3351 |
+
"epoch": 6.73,
|
3352 |
+
"grad_norm": 4.123006343841553,
|
3353 |
+
"learning_rate": 7.845804988662133e-06,
|
3354 |
+
"loss": 0.3482,
|
3355 |
+
"step": 4240
|
3356 |
+
},
|
3357 |
+
{
|
3358 |
+
"epoch": 6.75,
|
3359 |
+
"grad_norm": 0.6726520657539368,
|
3360 |
+
"learning_rate": 7.392290249433107e-06,
|
3361 |
+
"loss": 0.3813,
|
3362 |
+
"step": 4250
|
3363 |
+
},
|
3364 |
+
{
|
3365 |
+
"epoch": 6.76,
|
3366 |
+
"grad_norm": 7.85457181930542,
|
3367 |
+
"learning_rate": 6.938775510204082e-06,
|
3368 |
+
"loss": 0.3737,
|
3369 |
+
"step": 4260
|
3370 |
+
},
|
3371 |
+
{
|
3372 |
+
"epoch": 6.78,
|
3373 |
+
"grad_norm": 1.485037922859192,
|
3374 |
+
"learning_rate": 6.485260770975057e-06,
|
3375 |
+
"loss": 0.2864,
|
3376 |
+
"step": 4270
|
3377 |
+
},
|
3378 |
+
{
|
3379 |
+
"epoch": 6.79,
|
3380 |
+
"grad_norm": 2.535890817642212,
|
3381 |
+
"learning_rate": 6.031746031746032e-06,
|
3382 |
+
"loss": 0.2424,
|
3383 |
+
"step": 4280
|
3384 |
+
},
|
3385 |
+
{
|
3386 |
+
"epoch": 6.81,
|
3387 |
+
"grad_norm": 1.3501815795898438,
|
3388 |
+
"learning_rate": 5.578231292517007e-06,
|
3389 |
+
"loss": 0.3013,
|
3390 |
+
"step": 4290
|
3391 |
+
},
|
3392 |
+
{
|
3393 |
+
"epoch": 6.83,
|
3394 |
+
"grad_norm": 2.961240291595459,
|
3395 |
+
"learning_rate": 5.124716553287982e-06,
|
3396 |
+
"loss": 0.3364,
|
3397 |
+
"step": 4300
|
3398 |
+
},
|
3399 |
+
{
|
3400 |
+
"epoch": 6.83,
|
3401 |
+
"eval_accuracy": 0.8496031746031746,
|
3402 |
+
"eval_loss": 0.5302808284759521,
|
3403 |
+
"eval_runtime": 99.1164,
|
3404 |
+
"eval_samples_per_second": 25.425,
|
3405 |
+
"eval_steps_per_second": 3.178,
|
3406 |
+
"step": 4300
|
3407 |
+
},
|
3408 |
+
{
|
3409 |
+
"epoch": 6.84,
|
3410 |
+
"grad_norm": 3.593552589416504,
|
3411 |
+
"learning_rate": 4.671201814058957e-06,
|
3412 |
+
"loss": 0.3273,
|
3413 |
+
"step": 4310
|
3414 |
+
},
|
3415 |
+
{
|
3416 |
+
"epoch": 6.86,
|
3417 |
+
"grad_norm": 3.5346760749816895,
|
3418 |
+
"learning_rate": 4.217687074829932e-06,
|
3419 |
+
"loss": 0.3345,
|
3420 |
+
"step": 4320
|
3421 |
+
},
|
3422 |
+
{
|
3423 |
+
"epoch": 6.87,
|
3424 |
+
"grad_norm": 3.0319371223449707,
|
3425 |
+
"learning_rate": 3.764172335600907e-06,
|
3426 |
+
"loss": 0.4083,
|
3427 |
+
"step": 4330
|
3428 |
+
},
|
3429 |
+
{
|
3430 |
+
"epoch": 6.89,
|
3431 |
+
"grad_norm": 2.639801263809204,
|
3432 |
+
"learning_rate": 3.310657596371882e-06,
|
3433 |
+
"loss": 0.2986,
|
3434 |
+
"step": 4340
|
3435 |
+
},
|
3436 |
+
{
|
3437 |
+
"epoch": 6.9,
|
3438 |
+
"grad_norm": 1.1220003366470337,
|
3439 |
+
"learning_rate": 2.8571428571428573e-06,
|
3440 |
+
"loss": 0.3088,
|
3441 |
+
"step": 4350
|
3442 |
+
},
|
3443 |
+
{
|
3444 |
+
"epoch": 6.92,
|
3445 |
+
"grad_norm": 5.006831645965576,
|
3446 |
+
"learning_rate": 2.4036281179138325e-06,
|
3447 |
+
"loss": 0.4156,
|
3448 |
+
"step": 4360
|
3449 |
+
},
|
3450 |
+
{
|
3451 |
+
"epoch": 6.94,
|
3452 |
+
"grad_norm": 4.62202262878418,
|
3453 |
+
"learning_rate": 1.9501133786848073e-06,
|
3454 |
+
"loss": 0.3888,
|
3455 |
+
"step": 4370
|
3456 |
+
},
|
3457 |
+
{
|
3458 |
+
"epoch": 6.95,
|
3459 |
+
"grad_norm": 6.1172590255737305,
|
3460 |
+
"learning_rate": 1.4965986394557823e-06,
|
3461 |
+
"loss": 0.3449,
|
3462 |
+
"step": 4380
|
3463 |
+
},
|
3464 |
+
{
|
3465 |
+
"epoch": 6.97,
|
3466 |
+
"grad_norm": 6.193305969238281,
|
3467 |
+
"learning_rate": 1.0430839002267576e-06,
|
3468 |
+
"loss": 0.3253,
|
3469 |
+
"step": 4390
|
3470 |
+
},
|
3471 |
+
{
|
3472 |
+
"epoch": 6.98,
|
3473 |
+
"grad_norm": 1.3442612886428833,
|
3474 |
+
"learning_rate": 5.895691609977325e-07,
|
3475 |
+
"loss": 0.3639,
|
3476 |
+
"step": 4400
|
3477 |
+
},
|
3478 |
+
{
|
3479 |
+
"epoch": 6.98,
|
3480 |
+
"eval_accuracy": 0.8492063492063492,
|
3481 |
+
"eval_loss": 0.5315643548965454,
|
3482 |
+
"eval_runtime": 94.3134,
|
3483 |
+
"eval_samples_per_second": 26.719,
|
3484 |
+
"eval_steps_per_second": 3.34,
|
3485 |
+
"step": 4400
|
3486 |
+
},
|
3487 |
+
{
|
3488 |
+
"epoch": 7.0,
|
3489 |
+
"grad_norm": 4.398177146911621,
|
3490 |
+
"learning_rate": 1.3605442176870747e-07,
|
3491 |
+
"loss": 0.2582,
|
3492 |
+
"step": 4410
|
3493 |
+
},
|
3494 |
+
{
|
3495 |
+
"epoch": 7.0,
|
3496 |
+
"step": 4410,
|
3497 |
+
"total_flos": 5.468471871363809e+18,
|
3498 |
+
"train_loss": 0.7062997149772384,
|
3499 |
+
"train_runtime": 5016.6762,
|
3500 |
+
"train_samples_per_second": 14.065,
|
3501 |
+
"train_steps_per_second": 0.879
|
3502 |
+
}
|
3503 |
+
],
|
3504 |
+
"logging_steps": 10,
|
3505 |
+
"max_steps": 4410,
|
3506 |
+
"num_input_tokens_seen": 0,
|
3507 |
+
"num_train_epochs": 7,
|
3508 |
+
"save_steps": 100,
|
3509 |
+
"total_flos": 5.468471871363809e+18,
|
3510 |
+
"train_batch_size": 16,
|
3511 |
+
"trial_name": null,
|
3512 |
+
"trial_params": null
|
3513 |
+
}
|