thenewsupercell/Louis_EMOTION_Image_VIT
Browse files- README.md +3 -3
- all_results.json +13 -0
- eval_results.json +8 -0
- train_results.json +8 -0
- trainer_state.json +3835 -0
README.md
CHANGED
|
@@ -23,7 +23,7 @@ model-index:
|
|
| 23 |
metrics:
|
| 24 |
- name: Accuracy
|
| 25 |
type: accuracy
|
| 26 |
-
value: 0.
|
| 27 |
---
|
| 28 |
|
| 29 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
@@ -33,8 +33,8 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 33 |
|
| 34 |
This model is a fine-tuned version of [google/vit-base-patch16-224-in21k](https://huggingface.co/google/vit-base-patch16-224-in21k) on the imagefolder dataset.
|
| 35 |
It achieves the following results on the evaluation set:
|
| 36 |
-
- Loss: 0.
|
| 37 |
-
- Accuracy: 0.
|
| 38 |
|
| 39 |
## Model description
|
| 40 |
|
|
|
|
| 23 |
metrics:
|
| 24 |
- name: Accuracy
|
| 25 |
type: accuracy
|
| 26 |
+
value: 0.7035385901365283
|
| 27 |
---
|
| 28 |
|
| 29 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
|
|
| 33 |
|
| 34 |
This model is a fine-tuned version of [google/vit-base-patch16-224-in21k](https://huggingface.co/google/vit-base-patch16-224-in21k) on the imagefolder dataset.
|
| 35 |
It achieves the following results on the evaluation set:
|
| 36 |
+
- Loss: 0.8621
|
| 37 |
+
- Accuracy: 0.7035
|
| 38 |
|
| 39 |
## Model description
|
| 40 |
|
all_results.json
ADDED
|
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 3.0,
|
| 3 |
+
"eval_accuracy": 0.7035385901365283,
|
| 4 |
+
"eval_loss": 0.8621031045913696,
|
| 5 |
+
"eval_runtime": 55.8884,
|
| 6 |
+
"eval_samples_per_second": 64.217,
|
| 7 |
+
"eval_steps_per_second": 4.026,
|
| 8 |
+
"total_flos": 6.674451681129007e+18,
|
| 9 |
+
"train_loss": 0.7317446124697573,
|
| 10 |
+
"train_runtime": 2231.3604,
|
| 11 |
+
"train_samples_per_second": 38.598,
|
| 12 |
+
"train_steps_per_second": 2.413
|
| 13 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 3.0,
|
| 3 |
+
"eval_accuracy": 0.7035385901365283,
|
| 4 |
+
"eval_loss": 0.8621031045913696,
|
| 5 |
+
"eval_runtime": 55.8884,
|
| 6 |
+
"eval_samples_per_second": 64.217,
|
| 7 |
+
"eval_steps_per_second": 4.026
|
| 8 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 3.0,
|
| 3 |
+
"total_flos": 6.674451681129007e+18,
|
| 4 |
+
"train_loss": 0.7317446124697573,
|
| 5 |
+
"train_runtime": 2231.3604,
|
| 6 |
+
"train_samples_per_second": 38.598,
|
| 7 |
+
"train_steps_per_second": 2.413
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,3835 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.7127333519086096,
|
| 3 |
+
"best_model_checkpoint": "Louis_Emotion_DF_Image_VIT_V1/checkpoint-5385",
|
| 4 |
+
"epoch": 3.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 5385,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.005571030640668524,
|
| 13 |
+
"grad_norm": 1.948201060295105,
|
| 14 |
+
"learning_rate": 4.990714948932219e-05,
|
| 15 |
+
"loss": 1.8845,
|
| 16 |
+
"step": 10
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.011142061281337047,
|
| 20 |
+
"grad_norm": 2.1474852561950684,
|
| 21 |
+
"learning_rate": 4.981429897864439e-05,
|
| 22 |
+
"loss": 1.7726,
|
| 23 |
+
"step": 20
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.016713091922005572,
|
| 27 |
+
"grad_norm": 1.7504295110702515,
|
| 28 |
+
"learning_rate": 4.972144846796657e-05,
|
| 29 |
+
"loss": 1.7291,
|
| 30 |
+
"step": 30
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.022284122562674095,
|
| 34 |
+
"grad_norm": 1.9806510210037231,
|
| 35 |
+
"learning_rate": 4.962859795728877e-05,
|
| 36 |
+
"loss": 1.631,
|
| 37 |
+
"step": 40
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.027855153203342618,
|
| 41 |
+
"grad_norm": 2.3543717861175537,
|
| 42 |
+
"learning_rate": 4.953574744661096e-05,
|
| 43 |
+
"loss": 1.5524,
|
| 44 |
+
"step": 50
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.033426183844011144,
|
| 48 |
+
"grad_norm": 2.5557103157043457,
|
| 49 |
+
"learning_rate": 4.9442896935933144e-05,
|
| 50 |
+
"loss": 1.5061,
|
| 51 |
+
"step": 60
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.03899721448467967,
|
| 55 |
+
"grad_norm": 2.1124281883239746,
|
| 56 |
+
"learning_rate": 4.9350046425255343e-05,
|
| 57 |
+
"loss": 1.5135,
|
| 58 |
+
"step": 70
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.04456824512534819,
|
| 62 |
+
"grad_norm": 2.636732578277588,
|
| 63 |
+
"learning_rate": 4.925719591457753e-05,
|
| 64 |
+
"loss": 1.4545,
|
| 65 |
+
"step": 80
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.05013927576601671,
|
| 69 |
+
"grad_norm": 2.1990904808044434,
|
| 70 |
+
"learning_rate": 4.916434540389973e-05,
|
| 71 |
+
"loss": 1.3375,
|
| 72 |
+
"step": 90
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.055710306406685235,
|
| 76 |
+
"grad_norm": 2.593843698501587,
|
| 77 |
+
"learning_rate": 4.9071494893221914e-05,
|
| 78 |
+
"loss": 1.3125,
|
| 79 |
+
"step": 100
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.06128133704735376,
|
| 83 |
+
"grad_norm": 2.3658862113952637,
|
| 84 |
+
"learning_rate": 4.897864438254411e-05,
|
| 85 |
+
"loss": 1.2438,
|
| 86 |
+
"step": 110
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.06685236768802229,
|
| 90 |
+
"grad_norm": 3.614569902420044,
|
| 91 |
+
"learning_rate": 4.88857938718663e-05,
|
| 92 |
+
"loss": 1.352,
|
| 93 |
+
"step": 120
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.07242339832869081,
|
| 97 |
+
"grad_norm": 3.075983762741089,
|
| 98 |
+
"learning_rate": 4.8792943361188485e-05,
|
| 99 |
+
"loss": 1.3506,
|
| 100 |
+
"step": 130
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 0.07799442896935933,
|
| 104 |
+
"grad_norm": 2.9833717346191406,
|
| 105 |
+
"learning_rate": 4.8700092850510685e-05,
|
| 106 |
+
"loss": 1.3486,
|
| 107 |
+
"step": 140
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.08356545961002786,
|
| 111 |
+
"grad_norm": 4.222170829772949,
|
| 112 |
+
"learning_rate": 4.860724233983287e-05,
|
| 113 |
+
"loss": 1.3921,
|
| 114 |
+
"step": 150
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.08913649025069638,
|
| 118 |
+
"grad_norm": 2.5788440704345703,
|
| 119 |
+
"learning_rate": 4.851439182915506e-05,
|
| 120 |
+
"loss": 1.3421,
|
| 121 |
+
"step": 160
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.0947075208913649,
|
| 125 |
+
"grad_norm": 2.7408132553100586,
|
| 126 |
+
"learning_rate": 4.8421541318477255e-05,
|
| 127 |
+
"loss": 1.1812,
|
| 128 |
+
"step": 170
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.10027855153203342,
|
| 132 |
+
"grad_norm": 2.91229510307312,
|
| 133 |
+
"learning_rate": 4.832869080779944e-05,
|
| 134 |
+
"loss": 1.1881,
|
| 135 |
+
"step": 180
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.10584958217270195,
|
| 139 |
+
"grad_norm": 2.4319872856140137,
|
| 140 |
+
"learning_rate": 4.823584029712164e-05,
|
| 141 |
+
"loss": 1.3427,
|
| 142 |
+
"step": 190
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 0.11142061281337047,
|
| 146 |
+
"grad_norm": 3.0504567623138428,
|
| 147 |
+
"learning_rate": 4.8142989786443826e-05,
|
| 148 |
+
"loss": 1.2334,
|
| 149 |
+
"step": 200
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 0.116991643454039,
|
| 153 |
+
"grad_norm": 2.9363996982574463,
|
| 154 |
+
"learning_rate": 4.805013927576602e-05,
|
| 155 |
+
"loss": 1.1809,
|
| 156 |
+
"step": 210
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 0.12256267409470752,
|
| 160 |
+
"grad_norm": 2.2370383739471436,
|
| 161 |
+
"learning_rate": 4.795728876508821e-05,
|
| 162 |
+
"loss": 1.1973,
|
| 163 |
+
"step": 220
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 0.12813370473537605,
|
| 167 |
+
"grad_norm": 2.7246251106262207,
|
| 168 |
+
"learning_rate": 4.7864438254410404e-05,
|
| 169 |
+
"loss": 1.2224,
|
| 170 |
+
"step": 230
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 0.13370473537604458,
|
| 174 |
+
"grad_norm": 3.5851166248321533,
|
| 175 |
+
"learning_rate": 4.7771587743732597e-05,
|
| 176 |
+
"loss": 1.0445,
|
| 177 |
+
"step": 240
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.1392757660167131,
|
| 181 |
+
"grad_norm": 1.9959110021591187,
|
| 182 |
+
"learning_rate": 4.767873723305478e-05,
|
| 183 |
+
"loss": 1.1164,
|
| 184 |
+
"step": 250
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 0.14484679665738162,
|
| 188 |
+
"grad_norm": 2.933548927307129,
|
| 189 |
+
"learning_rate": 4.7585886722376975e-05,
|
| 190 |
+
"loss": 1.1229,
|
| 191 |
+
"step": 260
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 0.15041782729805014,
|
| 195 |
+
"grad_norm": 4.168135643005371,
|
| 196 |
+
"learning_rate": 4.749303621169917e-05,
|
| 197 |
+
"loss": 1.25,
|
| 198 |
+
"step": 270
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 0.15598885793871867,
|
| 202 |
+
"grad_norm": 3.2790322303771973,
|
| 203 |
+
"learning_rate": 4.740018570102136e-05,
|
| 204 |
+
"loss": 1.177,
|
| 205 |
+
"step": 280
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 0.1615598885793872,
|
| 209 |
+
"grad_norm": 4.025652885437012,
|
| 210 |
+
"learning_rate": 4.7307335190343546e-05,
|
| 211 |
+
"loss": 1.1185,
|
| 212 |
+
"step": 290
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 0.1671309192200557,
|
| 216 |
+
"grad_norm": 2.921226978302002,
|
| 217 |
+
"learning_rate": 4.721448467966574e-05,
|
| 218 |
+
"loss": 1.1773,
|
| 219 |
+
"step": 300
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.17270194986072424,
|
| 223 |
+
"grad_norm": 3.095017671585083,
|
| 224 |
+
"learning_rate": 4.712163416898793e-05,
|
| 225 |
+
"loss": 1.2818,
|
| 226 |
+
"step": 310
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 0.17827298050139276,
|
| 230 |
+
"grad_norm": 2.596940279006958,
|
| 231 |
+
"learning_rate": 4.702878365831012e-05,
|
| 232 |
+
"loss": 1.0857,
|
| 233 |
+
"step": 320
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 0.18384401114206128,
|
| 237 |
+
"grad_norm": 3.0986833572387695,
|
| 238 |
+
"learning_rate": 4.6935933147632316e-05,
|
| 239 |
+
"loss": 1.161,
|
| 240 |
+
"step": 330
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 0.1894150417827298,
|
| 244 |
+
"grad_norm": 3.9067625999450684,
|
| 245 |
+
"learning_rate": 4.68430826369545e-05,
|
| 246 |
+
"loss": 1.126,
|
| 247 |
+
"step": 340
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 0.19498607242339833,
|
| 251 |
+
"grad_norm": 2.4455080032348633,
|
| 252 |
+
"learning_rate": 4.6750232126276694e-05,
|
| 253 |
+
"loss": 1.0944,
|
| 254 |
+
"step": 350
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 0.20055710306406685,
|
| 258 |
+
"grad_norm": 3.0159671306610107,
|
| 259 |
+
"learning_rate": 4.665738161559889e-05,
|
| 260 |
+
"loss": 1.0525,
|
| 261 |
+
"step": 360
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 0.20612813370473537,
|
| 265 |
+
"grad_norm": 3.257310152053833,
|
| 266 |
+
"learning_rate": 4.656453110492108e-05,
|
| 267 |
+
"loss": 1.1423,
|
| 268 |
+
"step": 370
|
| 269 |
+
},
|
| 270 |
+
{
|
| 271 |
+
"epoch": 0.2116991643454039,
|
| 272 |
+
"grad_norm": 2.324500322341919,
|
| 273 |
+
"learning_rate": 4.647168059424327e-05,
|
| 274 |
+
"loss": 1.0441,
|
| 275 |
+
"step": 380
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 0.21727019498607242,
|
| 279 |
+
"grad_norm": 2.893946409225464,
|
| 280 |
+
"learning_rate": 4.637883008356546e-05,
|
| 281 |
+
"loss": 1.0956,
|
| 282 |
+
"step": 390
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 0.22284122562674094,
|
| 286 |
+
"grad_norm": 3.661740779876709,
|
| 287 |
+
"learning_rate": 4.628597957288766e-05,
|
| 288 |
+
"loss": 1.0648,
|
| 289 |
+
"step": 400
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 0.22841225626740946,
|
| 293 |
+
"grad_norm": 3.601794719696045,
|
| 294 |
+
"learning_rate": 4.619312906220984e-05,
|
| 295 |
+
"loss": 1.1556,
|
| 296 |
+
"step": 410
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 0.233983286908078,
|
| 300 |
+
"grad_norm": 2.6910550594329834,
|
| 301 |
+
"learning_rate": 4.6100278551532035e-05,
|
| 302 |
+
"loss": 0.9603,
|
| 303 |
+
"step": 420
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 0.2395543175487465,
|
| 307 |
+
"grad_norm": 2.952540636062622,
|
| 308 |
+
"learning_rate": 4.600742804085423e-05,
|
| 309 |
+
"loss": 1.1827,
|
| 310 |
+
"step": 430
|
| 311 |
+
},
|
| 312 |
+
{
|
| 313 |
+
"epoch": 0.24512534818941503,
|
| 314 |
+
"grad_norm": 4.099498271942139,
|
| 315 |
+
"learning_rate": 4.5914577530176414e-05,
|
| 316 |
+
"loss": 1.0573,
|
| 317 |
+
"step": 440
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 0.25069637883008355,
|
| 321 |
+
"grad_norm": 3.884427070617676,
|
| 322 |
+
"learning_rate": 4.582172701949861e-05,
|
| 323 |
+
"loss": 1.1742,
|
| 324 |
+
"step": 450
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 0.2562674094707521,
|
| 328 |
+
"grad_norm": 3.0782787799835205,
|
| 329 |
+
"learning_rate": 4.57288765088208e-05,
|
| 330 |
+
"loss": 1.051,
|
| 331 |
+
"step": 460
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 0.2618384401114206,
|
| 335 |
+
"grad_norm": 4.079422473907471,
|
| 336 |
+
"learning_rate": 4.563602599814299e-05,
|
| 337 |
+
"loss": 0.9732,
|
| 338 |
+
"step": 470
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 0.26740947075208915,
|
| 342 |
+
"grad_norm": 3.0462193489074707,
|
| 343 |
+
"learning_rate": 4.5543175487465184e-05,
|
| 344 |
+
"loss": 1.0204,
|
| 345 |
+
"step": 480
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 0.27298050139275765,
|
| 349 |
+
"grad_norm": 3.944453716278076,
|
| 350 |
+
"learning_rate": 4.545032497678737e-05,
|
| 351 |
+
"loss": 1.2336,
|
| 352 |
+
"step": 490
|
| 353 |
+
},
|
| 354 |
+
{
|
| 355 |
+
"epoch": 0.2785515320334262,
|
| 356 |
+
"grad_norm": 3.276047945022583,
|
| 357 |
+
"learning_rate": 4.535747446610957e-05,
|
| 358 |
+
"loss": 1.1331,
|
| 359 |
+
"step": 500
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 0.2841225626740947,
|
| 363 |
+
"grad_norm": 2.8910679817199707,
|
| 364 |
+
"learning_rate": 4.5264623955431755e-05,
|
| 365 |
+
"loss": 1.0437,
|
| 366 |
+
"step": 510
|
| 367 |
+
},
|
| 368 |
+
{
|
| 369 |
+
"epoch": 0.28969359331476324,
|
| 370 |
+
"grad_norm": 2.332932472229004,
|
| 371 |
+
"learning_rate": 4.5171773444753954e-05,
|
| 372 |
+
"loss": 1.264,
|
| 373 |
+
"step": 520
|
| 374 |
+
},
|
| 375 |
+
{
|
| 376 |
+
"epoch": 0.29526462395543174,
|
| 377 |
+
"grad_norm": 3.207519292831421,
|
| 378 |
+
"learning_rate": 4.507892293407614e-05,
|
| 379 |
+
"loss": 1.0362,
|
| 380 |
+
"step": 530
|
| 381 |
+
},
|
| 382 |
+
{
|
| 383 |
+
"epoch": 0.3008356545961003,
|
| 384 |
+
"grad_norm": 3.792386770248413,
|
| 385 |
+
"learning_rate": 4.4986072423398326e-05,
|
| 386 |
+
"loss": 1.0799,
|
| 387 |
+
"step": 540
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 0.3064066852367688,
|
| 391 |
+
"grad_norm": 3.6370913982391357,
|
| 392 |
+
"learning_rate": 4.4893221912720525e-05,
|
| 393 |
+
"loss": 1.0702,
|
| 394 |
+
"step": 550
|
| 395 |
+
},
|
| 396 |
+
{
|
| 397 |
+
"epoch": 0.31197771587743733,
|
| 398 |
+
"grad_norm": 7.727144241333008,
|
| 399 |
+
"learning_rate": 4.480037140204271e-05,
|
| 400 |
+
"loss": 1.0313,
|
| 401 |
+
"step": 560
|
| 402 |
+
},
|
| 403 |
+
{
|
| 404 |
+
"epoch": 0.31754874651810583,
|
| 405 |
+
"grad_norm": 3.0483336448669434,
|
| 406 |
+
"learning_rate": 4.470752089136491e-05,
|
| 407 |
+
"loss": 1.0816,
|
| 408 |
+
"step": 570
|
| 409 |
+
},
|
| 410 |
+
{
|
| 411 |
+
"epoch": 0.3231197771587744,
|
| 412 |
+
"grad_norm": 4.045107841491699,
|
| 413 |
+
"learning_rate": 4.4614670380687096e-05,
|
| 414 |
+
"loss": 1.1036,
|
| 415 |
+
"step": 580
|
| 416 |
+
},
|
| 417 |
+
{
|
| 418 |
+
"epoch": 0.3286908077994429,
|
| 419 |
+
"grad_norm": 2.4204320907592773,
|
| 420 |
+
"learning_rate": 4.452181987000928e-05,
|
| 421 |
+
"loss": 0.9899,
|
| 422 |
+
"step": 590
|
| 423 |
+
},
|
| 424 |
+
{
|
| 425 |
+
"epoch": 0.3342618384401114,
|
| 426 |
+
"grad_norm": 1.9364632368087769,
|
| 427 |
+
"learning_rate": 4.442896935933148e-05,
|
| 428 |
+
"loss": 0.9319,
|
| 429 |
+
"step": 600
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 0.3398328690807799,
|
| 433 |
+
"grad_norm": 2.769692897796631,
|
| 434 |
+
"learning_rate": 4.433611884865367e-05,
|
| 435 |
+
"loss": 0.9948,
|
| 436 |
+
"step": 610
|
| 437 |
+
},
|
| 438 |
+
{
|
| 439 |
+
"epoch": 0.34540389972144847,
|
| 440 |
+
"grad_norm": 3.5920908451080322,
|
| 441 |
+
"learning_rate": 4.4243268337975866e-05,
|
| 442 |
+
"loss": 0.9915,
|
| 443 |
+
"step": 620
|
| 444 |
+
},
|
| 445 |
+
{
|
| 446 |
+
"epoch": 0.35097493036211697,
|
| 447 |
+
"grad_norm": 3.9949071407318115,
|
| 448 |
+
"learning_rate": 4.415041782729805e-05,
|
| 449 |
+
"loss": 1.0652,
|
| 450 |
+
"step": 630
|
| 451 |
+
},
|
| 452 |
+
{
|
| 453 |
+
"epoch": 0.3565459610027855,
|
| 454 |
+
"grad_norm": 3.3296191692352295,
|
| 455 |
+
"learning_rate": 4.4057567316620244e-05,
|
| 456 |
+
"loss": 1.0703,
|
| 457 |
+
"step": 640
|
| 458 |
+
},
|
| 459 |
+
{
|
| 460 |
+
"epoch": 0.362116991643454,
|
| 461 |
+
"grad_norm": 5.59266996383667,
|
| 462 |
+
"learning_rate": 4.396471680594244e-05,
|
| 463 |
+
"loss": 1.0078,
|
| 464 |
+
"step": 650
|
| 465 |
+
},
|
| 466 |
+
{
|
| 467 |
+
"epoch": 0.36768802228412256,
|
| 468 |
+
"grad_norm": 3.6050076484680176,
|
| 469 |
+
"learning_rate": 4.387186629526462e-05,
|
| 470 |
+
"loss": 0.9541,
|
| 471 |
+
"step": 660
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 0.3732590529247911,
|
| 475 |
+
"grad_norm": 2.4195094108581543,
|
| 476 |
+
"learning_rate": 4.377901578458682e-05,
|
| 477 |
+
"loss": 0.8932,
|
| 478 |
+
"step": 670
|
| 479 |
+
},
|
| 480 |
+
{
|
| 481 |
+
"epoch": 0.3788300835654596,
|
| 482 |
+
"grad_norm": 3.135007619857788,
|
| 483 |
+
"learning_rate": 4.368616527390901e-05,
|
| 484 |
+
"loss": 1.13,
|
| 485 |
+
"step": 680
|
| 486 |
+
},
|
| 487 |
+
{
|
| 488 |
+
"epoch": 0.38440111420612816,
|
| 489 |
+
"grad_norm": 3.0735456943511963,
|
| 490 |
+
"learning_rate": 4.35933147632312e-05,
|
| 491 |
+
"loss": 0.9413,
|
| 492 |
+
"step": 690
|
| 493 |
+
},
|
| 494 |
+
{
|
| 495 |
+
"epoch": 0.38997214484679665,
|
| 496 |
+
"grad_norm": 4.281991481781006,
|
| 497 |
+
"learning_rate": 4.350046425255339e-05,
|
| 498 |
+
"loss": 0.9636,
|
| 499 |
+
"step": 700
|
| 500 |
+
},
|
| 501 |
+
{
|
| 502 |
+
"epoch": 0.3955431754874652,
|
| 503 |
+
"grad_norm": 3.6378397941589355,
|
| 504 |
+
"learning_rate": 4.340761374187558e-05,
|
| 505 |
+
"loss": 1.0549,
|
| 506 |
+
"step": 710
|
| 507 |
+
},
|
| 508 |
+
{
|
| 509 |
+
"epoch": 0.4011142061281337,
|
| 510 |
+
"grad_norm": 2.570322036743164,
|
| 511 |
+
"learning_rate": 4.331476323119778e-05,
|
| 512 |
+
"loss": 1.03,
|
| 513 |
+
"step": 720
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 0.40668523676880225,
|
| 517 |
+
"grad_norm": 3.7980899810791016,
|
| 518 |
+
"learning_rate": 4.3221912720519964e-05,
|
| 519 |
+
"loss": 0.9204,
|
| 520 |
+
"step": 730
|
| 521 |
+
},
|
| 522 |
+
{
|
| 523 |
+
"epoch": 0.41225626740947074,
|
| 524 |
+
"grad_norm": 2.180097818374634,
|
| 525 |
+
"learning_rate": 4.3129062209842156e-05,
|
| 526 |
+
"loss": 0.9956,
|
| 527 |
+
"step": 740
|
| 528 |
+
},
|
| 529 |
+
{
|
| 530 |
+
"epoch": 0.4178272980501393,
|
| 531 |
+
"grad_norm": 3.4004600048065186,
|
| 532 |
+
"learning_rate": 4.303621169916435e-05,
|
| 533 |
+
"loss": 1.0413,
|
| 534 |
+
"step": 750
|
| 535 |
+
},
|
| 536 |
+
{
|
| 537 |
+
"epoch": 0.4233983286908078,
|
| 538 |
+
"grad_norm": 2.9130539894104004,
|
| 539 |
+
"learning_rate": 4.2943361188486535e-05,
|
| 540 |
+
"loss": 0.9712,
|
| 541 |
+
"step": 760
|
| 542 |
+
},
|
| 543 |
+
{
|
| 544 |
+
"epoch": 0.42896935933147634,
|
| 545 |
+
"grad_norm": 2.5885844230651855,
|
| 546 |
+
"learning_rate": 4.2850510677808734e-05,
|
| 547 |
+
"loss": 1.0015,
|
| 548 |
+
"step": 770
|
| 549 |
+
},
|
| 550 |
+
{
|
| 551 |
+
"epoch": 0.43454038997214484,
|
| 552 |
+
"grad_norm": 2.890307664871216,
|
| 553 |
+
"learning_rate": 4.275766016713092e-05,
|
| 554 |
+
"loss": 0.9238,
|
| 555 |
+
"step": 780
|
| 556 |
+
},
|
| 557 |
+
{
|
| 558 |
+
"epoch": 0.4401114206128134,
|
| 559 |
+
"grad_norm": 2.586287498474121,
|
| 560 |
+
"learning_rate": 4.266480965645311e-05,
|
| 561 |
+
"loss": 1.1793,
|
| 562 |
+
"step": 790
|
| 563 |
+
},
|
| 564 |
+
{
|
| 565 |
+
"epoch": 0.4456824512534819,
|
| 566 |
+
"grad_norm": 3.8789122104644775,
|
| 567 |
+
"learning_rate": 4.2571959145775305e-05,
|
| 568 |
+
"loss": 0.9671,
|
| 569 |
+
"step": 800
|
| 570 |
+
},
|
| 571 |
+
{
|
| 572 |
+
"epoch": 0.45125348189415043,
|
| 573 |
+
"grad_norm": 2.513338804244995,
|
| 574 |
+
"learning_rate": 4.24791086350975e-05,
|
| 575 |
+
"loss": 1.1206,
|
| 576 |
+
"step": 810
|
| 577 |
+
},
|
| 578 |
+
{
|
| 579 |
+
"epoch": 0.4568245125348189,
|
| 580 |
+
"grad_norm": 4.040161609649658,
|
| 581 |
+
"learning_rate": 4.238625812441969e-05,
|
| 582 |
+
"loss": 0.9741,
|
| 583 |
+
"step": 820
|
| 584 |
+
},
|
| 585 |
+
{
|
| 586 |
+
"epoch": 0.4623955431754875,
|
| 587 |
+
"grad_norm": 3.625004768371582,
|
| 588 |
+
"learning_rate": 4.2293407613741876e-05,
|
| 589 |
+
"loss": 1.0511,
|
| 590 |
+
"step": 830
|
| 591 |
+
},
|
| 592 |
+
{
|
| 593 |
+
"epoch": 0.467966573816156,
|
| 594 |
+
"grad_norm": 2.6117324829101562,
|
| 595 |
+
"learning_rate": 4.220055710306407e-05,
|
| 596 |
+
"loss": 0.973,
|
| 597 |
+
"step": 840
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"epoch": 0.4735376044568245,
|
| 601 |
+
"grad_norm": 1.8209770917892456,
|
| 602 |
+
"learning_rate": 4.210770659238626e-05,
|
| 603 |
+
"loss": 0.9672,
|
| 604 |
+
"step": 850
|
| 605 |
+
},
|
| 606 |
+
{
|
| 607 |
+
"epoch": 0.479108635097493,
|
| 608 |
+
"grad_norm": 2.686767339706421,
|
| 609 |
+
"learning_rate": 4.201485608170845e-05,
|
| 610 |
+
"loss": 0.993,
|
| 611 |
+
"step": 860
|
| 612 |
+
},
|
| 613 |
+
{
|
| 614 |
+
"epoch": 0.48467966573816157,
|
| 615 |
+
"grad_norm": 2.2788872718811035,
|
| 616 |
+
"learning_rate": 4.192200557103064e-05,
|
| 617 |
+
"loss": 0.9141,
|
| 618 |
+
"step": 870
|
| 619 |
+
},
|
| 620 |
+
{
|
| 621 |
+
"epoch": 0.49025069637883006,
|
| 622 |
+
"grad_norm": 3.2874503135681152,
|
| 623 |
+
"learning_rate": 4.182915506035283e-05,
|
| 624 |
+
"loss": 1.0949,
|
| 625 |
+
"step": 880
|
| 626 |
+
},
|
| 627 |
+
{
|
| 628 |
+
"epoch": 0.4958217270194986,
|
| 629 |
+
"grad_norm": 3.21272349357605,
|
| 630 |
+
"learning_rate": 4.1736304549675024e-05,
|
| 631 |
+
"loss": 0.9701,
|
| 632 |
+
"step": 890
|
| 633 |
+
},
|
| 634 |
+
{
|
| 635 |
+
"epoch": 0.5013927576601671,
|
| 636 |
+
"grad_norm": 4.310153007507324,
|
| 637 |
+
"learning_rate": 4.164345403899722e-05,
|
| 638 |
+
"loss": 0.9595,
|
| 639 |
+
"step": 900
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 0.5069637883008357,
|
| 643 |
+
"grad_norm": 2.943368434906006,
|
| 644 |
+
"learning_rate": 4.155060352831941e-05,
|
| 645 |
+
"loss": 1.0342,
|
| 646 |
+
"step": 910
|
| 647 |
+
},
|
| 648 |
+
{
|
| 649 |
+
"epoch": 0.5125348189415042,
|
| 650 |
+
"grad_norm": 3.337778329849243,
|
| 651 |
+
"learning_rate": 4.1457753017641595e-05,
|
| 652 |
+
"loss": 0.8848,
|
| 653 |
+
"step": 920
|
| 654 |
+
},
|
| 655 |
+
{
|
| 656 |
+
"epoch": 0.5181058495821727,
|
| 657 |
+
"grad_norm": 3.8520374298095703,
|
| 658 |
+
"learning_rate": 4.1364902506963794e-05,
|
| 659 |
+
"loss": 0.955,
|
| 660 |
+
"step": 930
|
| 661 |
+
},
|
| 662 |
+
{
|
| 663 |
+
"epoch": 0.5236768802228412,
|
| 664 |
+
"grad_norm": 3.1856610774993896,
|
| 665 |
+
"learning_rate": 4.127205199628598e-05,
|
| 666 |
+
"loss": 0.9171,
|
| 667 |
+
"step": 940
|
| 668 |
+
},
|
| 669 |
+
{
|
| 670 |
+
"epoch": 0.5292479108635098,
|
| 671 |
+
"grad_norm": 2.813004493713379,
|
| 672 |
+
"learning_rate": 4.117920148560817e-05,
|
| 673 |
+
"loss": 0.8912,
|
| 674 |
+
"step": 950
|
| 675 |
+
},
|
| 676 |
+
{
|
| 677 |
+
"epoch": 0.5348189415041783,
|
| 678 |
+
"grad_norm": 3.73842716217041,
|
| 679 |
+
"learning_rate": 4.1086350974930365e-05,
|
| 680 |
+
"loss": 0.87,
|
| 681 |
+
"step": 960
|
| 682 |
+
},
|
| 683 |
+
{
|
| 684 |
+
"epoch": 0.5403899721448467,
|
| 685 |
+
"grad_norm": 4.500996112823486,
|
| 686 |
+
"learning_rate": 4.099350046425255e-05,
|
| 687 |
+
"loss": 1.0216,
|
| 688 |
+
"step": 970
|
| 689 |
+
},
|
| 690 |
+
{
|
| 691 |
+
"epoch": 0.5459610027855153,
|
| 692 |
+
"grad_norm": 2.80609393119812,
|
| 693 |
+
"learning_rate": 4.090064995357475e-05,
|
| 694 |
+
"loss": 0.9803,
|
| 695 |
+
"step": 980
|
| 696 |
+
},
|
| 697 |
+
{
|
| 698 |
+
"epoch": 0.5515320334261838,
|
| 699 |
+
"grad_norm": 3.340052604675293,
|
| 700 |
+
"learning_rate": 4.0807799442896936e-05,
|
| 701 |
+
"loss": 0.8977,
|
| 702 |
+
"step": 990
|
| 703 |
+
},
|
| 704 |
+
{
|
| 705 |
+
"epoch": 0.5571030640668524,
|
| 706 |
+
"grad_norm": 3.450836420059204,
|
| 707 |
+
"learning_rate": 4.071494893221913e-05,
|
| 708 |
+
"loss": 0.9845,
|
| 709 |
+
"step": 1000
|
| 710 |
+
},
|
| 711 |
+
{
|
| 712 |
+
"epoch": 0.5626740947075209,
|
| 713 |
+
"grad_norm": 2.639638662338257,
|
| 714 |
+
"learning_rate": 4.062209842154132e-05,
|
| 715 |
+
"loss": 0.9415,
|
| 716 |
+
"step": 1010
|
| 717 |
+
},
|
| 718 |
+
{
|
| 719 |
+
"epoch": 0.5682451253481894,
|
| 720 |
+
"grad_norm": 3.1470372676849365,
|
| 721 |
+
"learning_rate": 4.052924791086351e-05,
|
| 722 |
+
"loss": 1.0006,
|
| 723 |
+
"step": 1020
|
| 724 |
+
},
|
| 725 |
+
{
|
| 726 |
+
"epoch": 0.5738161559888579,
|
| 727 |
+
"grad_norm": 3.556126832962036,
|
| 728 |
+
"learning_rate": 4.0436397400185706e-05,
|
| 729 |
+
"loss": 0.9859,
|
| 730 |
+
"step": 1030
|
| 731 |
+
},
|
| 732 |
+
{
|
| 733 |
+
"epoch": 0.5793871866295265,
|
| 734 |
+
"grad_norm": 4.580634117126465,
|
| 735 |
+
"learning_rate": 4.034354688950789e-05,
|
| 736 |
+
"loss": 0.8674,
|
| 737 |
+
"step": 1040
|
| 738 |
+
},
|
| 739 |
+
{
|
| 740 |
+
"epoch": 0.584958217270195,
|
| 741 |
+
"grad_norm": 3.796309232711792,
|
| 742 |
+
"learning_rate": 4.0250696378830085e-05,
|
| 743 |
+
"loss": 0.9327,
|
| 744 |
+
"step": 1050
|
| 745 |
+
},
|
| 746 |
+
{
|
| 747 |
+
"epoch": 0.5905292479108635,
|
| 748 |
+
"grad_norm": 2.9451568126678467,
|
| 749 |
+
"learning_rate": 4.015784586815228e-05,
|
| 750 |
+
"loss": 0.9889,
|
| 751 |
+
"step": 1060
|
| 752 |
+
},
|
| 753 |
+
{
|
| 754 |
+
"epoch": 0.596100278551532,
|
| 755 |
+
"grad_norm": 2.4490549564361572,
|
| 756 |
+
"learning_rate": 4.006499535747446e-05,
|
| 757 |
+
"loss": 0.9661,
|
| 758 |
+
"step": 1070
|
| 759 |
+
},
|
| 760 |
+
{
|
| 761 |
+
"epoch": 0.6016713091922006,
|
| 762 |
+
"grad_norm": 3.1423044204711914,
|
| 763 |
+
"learning_rate": 3.997214484679666e-05,
|
| 764 |
+
"loss": 0.8991,
|
| 765 |
+
"step": 1080
|
| 766 |
+
},
|
| 767 |
+
{
|
| 768 |
+
"epoch": 0.6072423398328691,
|
| 769 |
+
"grad_norm": 2.6744227409362793,
|
| 770 |
+
"learning_rate": 3.987929433611885e-05,
|
| 771 |
+
"loss": 0.9822,
|
| 772 |
+
"step": 1090
|
| 773 |
+
},
|
| 774 |
+
{
|
| 775 |
+
"epoch": 0.6128133704735376,
|
| 776 |
+
"grad_norm": 2.410128593444824,
|
| 777 |
+
"learning_rate": 3.978644382544105e-05,
|
| 778 |
+
"loss": 0.87,
|
| 779 |
+
"step": 1100
|
| 780 |
+
},
|
| 781 |
+
{
|
| 782 |
+
"epoch": 0.6183844011142061,
|
| 783 |
+
"grad_norm": 3.4056427478790283,
|
| 784 |
+
"learning_rate": 3.969359331476323e-05,
|
| 785 |
+
"loss": 0.9011,
|
| 786 |
+
"step": 1110
|
| 787 |
+
},
|
| 788 |
+
{
|
| 789 |
+
"epoch": 0.6239554317548747,
|
| 790 |
+
"grad_norm": 3.5832958221435547,
|
| 791 |
+
"learning_rate": 3.960074280408542e-05,
|
| 792 |
+
"loss": 0.9179,
|
| 793 |
+
"step": 1120
|
| 794 |
+
},
|
| 795 |
+
{
|
| 796 |
+
"epoch": 0.6295264623955432,
|
| 797 |
+
"grad_norm": 4.678562164306641,
|
| 798 |
+
"learning_rate": 3.950789229340762e-05,
|
| 799 |
+
"loss": 0.9475,
|
| 800 |
+
"step": 1130
|
| 801 |
+
},
|
| 802 |
+
{
|
| 803 |
+
"epoch": 0.6350974930362117,
|
| 804 |
+
"grad_norm": 3.114361047744751,
|
| 805 |
+
"learning_rate": 3.9415041782729804e-05,
|
| 806 |
+
"loss": 0.95,
|
| 807 |
+
"step": 1140
|
| 808 |
+
},
|
| 809 |
+
{
|
| 810 |
+
"epoch": 0.6406685236768802,
|
| 811 |
+
"grad_norm": 2.6210415363311768,
|
| 812 |
+
"learning_rate": 3.9322191272052003e-05,
|
| 813 |
+
"loss": 0.8933,
|
| 814 |
+
"step": 1150
|
| 815 |
+
},
|
| 816 |
+
{
|
| 817 |
+
"epoch": 0.6462395543175488,
|
| 818 |
+
"grad_norm": 2.759856939315796,
|
| 819 |
+
"learning_rate": 3.922934076137419e-05,
|
| 820 |
+
"loss": 0.9336,
|
| 821 |
+
"step": 1160
|
| 822 |
+
},
|
| 823 |
+
{
|
| 824 |
+
"epoch": 0.6518105849582173,
|
| 825 |
+
"grad_norm": 3.449307680130005,
|
| 826 |
+
"learning_rate": 3.9136490250696375e-05,
|
| 827 |
+
"loss": 0.9851,
|
| 828 |
+
"step": 1170
|
| 829 |
+
},
|
| 830 |
+
{
|
| 831 |
+
"epoch": 0.6573816155988857,
|
| 832 |
+
"grad_norm": 4.323282718658447,
|
| 833 |
+
"learning_rate": 3.9043639740018574e-05,
|
| 834 |
+
"loss": 0.9735,
|
| 835 |
+
"step": 1180
|
| 836 |
+
},
|
| 837 |
+
{
|
| 838 |
+
"epoch": 0.6629526462395543,
|
| 839 |
+
"grad_norm": 2.79763126373291,
|
| 840 |
+
"learning_rate": 3.895078922934076e-05,
|
| 841 |
+
"loss": 0.8509,
|
| 842 |
+
"step": 1190
|
| 843 |
+
},
|
| 844 |
+
{
|
| 845 |
+
"epoch": 0.6685236768802229,
|
| 846 |
+
"grad_norm": 5.2140045166015625,
|
| 847 |
+
"learning_rate": 3.885793871866296e-05,
|
| 848 |
+
"loss": 1.0342,
|
| 849 |
+
"step": 1200
|
| 850 |
+
},
|
| 851 |
+
{
|
| 852 |
+
"epoch": 0.6740947075208914,
|
| 853 |
+
"grad_norm": 3.2437567710876465,
|
| 854 |
+
"learning_rate": 3.8765088207985145e-05,
|
| 855 |
+
"loss": 0.9919,
|
| 856 |
+
"step": 1210
|
| 857 |
+
},
|
| 858 |
+
{
|
| 859 |
+
"epoch": 0.6796657381615598,
|
| 860 |
+
"grad_norm": 3.9220008850097656,
|
| 861 |
+
"learning_rate": 3.867223769730734e-05,
|
| 862 |
+
"loss": 0.9809,
|
| 863 |
+
"step": 1220
|
| 864 |
+
},
|
| 865 |
+
{
|
| 866 |
+
"epoch": 0.6852367688022284,
|
| 867 |
+
"grad_norm": 1.8723160028457642,
|
| 868 |
+
"learning_rate": 3.857938718662953e-05,
|
| 869 |
+
"loss": 0.7315,
|
| 870 |
+
"step": 1230
|
| 871 |
+
},
|
| 872 |
+
{
|
| 873 |
+
"epoch": 0.6908077994428969,
|
| 874 |
+
"grad_norm": 5.3923211097717285,
|
| 875 |
+
"learning_rate": 3.8486536675951716e-05,
|
| 876 |
+
"loss": 0.9709,
|
| 877 |
+
"step": 1240
|
| 878 |
+
},
|
| 879 |
+
{
|
| 880 |
+
"epoch": 0.6963788300835655,
|
| 881 |
+
"grad_norm": 3.8164379596710205,
|
| 882 |
+
"learning_rate": 3.8393686165273915e-05,
|
| 883 |
+
"loss": 1.0331,
|
| 884 |
+
"step": 1250
|
| 885 |
+
},
|
| 886 |
+
{
|
| 887 |
+
"epoch": 0.7019498607242339,
|
| 888 |
+
"grad_norm": 4.3825836181640625,
|
| 889 |
+
"learning_rate": 3.83008356545961e-05,
|
| 890 |
+
"loss": 1.0042,
|
| 891 |
+
"step": 1260
|
| 892 |
+
},
|
| 893 |
+
{
|
| 894 |
+
"epoch": 0.7075208913649025,
|
| 895 |
+
"grad_norm": 2.7108051776885986,
|
| 896 |
+
"learning_rate": 3.8207985143918294e-05,
|
| 897 |
+
"loss": 0.974,
|
| 898 |
+
"step": 1270
|
| 899 |
+
},
|
| 900 |
+
{
|
| 901 |
+
"epoch": 0.713091922005571,
|
| 902 |
+
"grad_norm": 2.64860463142395,
|
| 903 |
+
"learning_rate": 3.8115134633240486e-05,
|
| 904 |
+
"loss": 0.8971,
|
| 905 |
+
"step": 1280
|
| 906 |
+
},
|
| 907 |
+
{
|
| 908 |
+
"epoch": 0.7186629526462396,
|
| 909 |
+
"grad_norm": 3.869168758392334,
|
| 910 |
+
"learning_rate": 3.802228412256267e-05,
|
| 911 |
+
"loss": 0.8225,
|
| 912 |
+
"step": 1290
|
| 913 |
+
},
|
| 914 |
+
{
|
| 915 |
+
"epoch": 0.724233983286908,
|
| 916 |
+
"grad_norm": 3.02199125289917,
|
| 917 |
+
"learning_rate": 3.792943361188487e-05,
|
| 918 |
+
"loss": 0.9492,
|
| 919 |
+
"step": 1300
|
| 920 |
+
},
|
| 921 |
+
{
|
| 922 |
+
"epoch": 0.7298050139275766,
|
| 923 |
+
"grad_norm": 5.071811199188232,
|
| 924 |
+
"learning_rate": 3.783658310120706e-05,
|
| 925 |
+
"loss": 1.018,
|
| 926 |
+
"step": 1310
|
| 927 |
+
},
|
| 928 |
+
{
|
| 929 |
+
"epoch": 0.7353760445682451,
|
| 930 |
+
"grad_norm": 3.2059361934661865,
|
| 931 |
+
"learning_rate": 3.774373259052925e-05,
|
| 932 |
+
"loss": 0.9163,
|
| 933 |
+
"step": 1320
|
| 934 |
+
},
|
| 935 |
+
{
|
| 936 |
+
"epoch": 0.7409470752089137,
|
| 937 |
+
"grad_norm": 4.003905296325684,
|
| 938 |
+
"learning_rate": 3.765088207985144e-05,
|
| 939 |
+
"loss": 0.8783,
|
| 940 |
+
"step": 1330
|
| 941 |
+
},
|
| 942 |
+
{
|
| 943 |
+
"epoch": 0.7465181058495822,
|
| 944 |
+
"grad_norm": 3.159921646118164,
|
| 945 |
+
"learning_rate": 3.755803156917363e-05,
|
| 946 |
+
"loss": 0.7841,
|
| 947 |
+
"step": 1340
|
| 948 |
+
},
|
| 949 |
+
{
|
| 950 |
+
"epoch": 0.7520891364902507,
|
| 951 |
+
"grad_norm": 2.852421760559082,
|
| 952 |
+
"learning_rate": 3.746518105849583e-05,
|
| 953 |
+
"loss": 0.9545,
|
| 954 |
+
"step": 1350
|
| 955 |
+
},
|
| 956 |
+
{
|
| 957 |
+
"epoch": 0.7576601671309192,
|
| 958 |
+
"grad_norm": 4.6871490478515625,
|
| 959 |
+
"learning_rate": 3.737233054781801e-05,
|
| 960 |
+
"loss": 0.9276,
|
| 961 |
+
"step": 1360
|
| 962 |
+
},
|
| 963 |
+
{
|
| 964 |
+
"epoch": 0.7632311977715878,
|
| 965 |
+
"grad_norm": 1.9484212398529053,
|
| 966 |
+
"learning_rate": 3.7279480037140206e-05,
|
| 967 |
+
"loss": 0.9676,
|
| 968 |
+
"step": 1370
|
| 969 |
+
},
|
| 970 |
+
{
|
| 971 |
+
"epoch": 0.7688022284122563,
|
| 972 |
+
"grad_norm": 4.423326015472412,
|
| 973 |
+
"learning_rate": 3.71866295264624e-05,
|
| 974 |
+
"loss": 1.0121,
|
| 975 |
+
"step": 1380
|
| 976 |
+
},
|
| 977 |
+
{
|
| 978 |
+
"epoch": 0.7743732590529248,
|
| 979 |
+
"grad_norm": 3.569786310195923,
|
| 980 |
+
"learning_rate": 3.709377901578459e-05,
|
| 981 |
+
"loss": 0.9413,
|
| 982 |
+
"step": 1390
|
| 983 |
+
},
|
| 984 |
+
{
|
| 985 |
+
"epoch": 0.7799442896935933,
|
| 986 |
+
"grad_norm": 1.8504449129104614,
|
| 987 |
+
"learning_rate": 3.700092850510678e-05,
|
| 988 |
+
"loss": 0.9478,
|
| 989 |
+
"step": 1400
|
| 990 |
+
},
|
| 991 |
+
{
|
| 992 |
+
"epoch": 0.7855153203342619,
|
| 993 |
+
"grad_norm": 3.4679548740386963,
|
| 994 |
+
"learning_rate": 3.690807799442897e-05,
|
| 995 |
+
"loss": 0.88,
|
| 996 |
+
"step": 1410
|
| 997 |
+
},
|
| 998 |
+
{
|
| 999 |
+
"epoch": 0.7910863509749304,
|
| 1000 |
+
"grad_norm": 6.313425064086914,
|
| 1001 |
+
"learning_rate": 3.681522748375116e-05,
|
| 1002 |
+
"loss": 1.0565,
|
| 1003 |
+
"step": 1420
|
| 1004 |
+
},
|
| 1005 |
+
{
|
| 1006 |
+
"epoch": 0.7966573816155988,
|
| 1007 |
+
"grad_norm": 3.7939631938934326,
|
| 1008 |
+
"learning_rate": 3.6722376973073354e-05,
|
| 1009 |
+
"loss": 1.0129,
|
| 1010 |
+
"step": 1430
|
| 1011 |
+
},
|
| 1012 |
+
{
|
| 1013 |
+
"epoch": 0.8022284122562674,
|
| 1014 |
+
"grad_norm": 4.260021209716797,
|
| 1015 |
+
"learning_rate": 3.662952646239555e-05,
|
| 1016 |
+
"loss": 0.8527,
|
| 1017 |
+
"step": 1440
|
| 1018 |
+
},
|
| 1019 |
+
{
|
| 1020 |
+
"epoch": 0.807799442896936,
|
| 1021 |
+
"grad_norm": 3.4048142433166504,
|
| 1022 |
+
"learning_rate": 3.653667595171773e-05,
|
| 1023 |
+
"loss": 1.0715,
|
| 1024 |
+
"step": 1450
|
| 1025 |
+
},
|
| 1026 |
+
{
|
| 1027 |
+
"epoch": 0.8133704735376045,
|
| 1028 |
+
"grad_norm": 4.1536736488342285,
|
| 1029 |
+
"learning_rate": 3.6443825441039925e-05,
|
| 1030 |
+
"loss": 0.9155,
|
| 1031 |
+
"step": 1460
|
| 1032 |
+
},
|
| 1033 |
+
{
|
| 1034 |
+
"epoch": 0.8189415041782729,
|
| 1035 |
+
"grad_norm": 3.329630136489868,
|
| 1036 |
+
"learning_rate": 3.635097493036212e-05,
|
| 1037 |
+
"loss": 1.0557,
|
| 1038 |
+
"step": 1470
|
| 1039 |
+
},
|
| 1040 |
+
{
|
| 1041 |
+
"epoch": 0.8245125348189415,
|
| 1042 |
+
"grad_norm": 2.2894420623779297,
|
| 1043 |
+
"learning_rate": 3.625812441968431e-05,
|
| 1044 |
+
"loss": 0.9423,
|
| 1045 |
+
"step": 1480
|
| 1046 |
+
},
|
| 1047 |
+
{
|
| 1048 |
+
"epoch": 0.83008356545961,
|
| 1049 |
+
"grad_norm": 2.885784864425659,
|
| 1050 |
+
"learning_rate": 3.61652739090065e-05,
|
| 1051 |
+
"loss": 0.9669,
|
| 1052 |
+
"step": 1490
|
| 1053 |
+
},
|
| 1054 |
+
{
|
| 1055 |
+
"epoch": 0.8356545961002786,
|
| 1056 |
+
"grad_norm": 3.7429628372192383,
|
| 1057 |
+
"learning_rate": 3.607242339832869e-05,
|
| 1058 |
+
"loss": 0.9009,
|
| 1059 |
+
"step": 1500
|
| 1060 |
+
},
|
| 1061 |
+
{
|
| 1062 |
+
"epoch": 0.841225626740947,
|
| 1063 |
+
"grad_norm": 2.1827738285064697,
|
| 1064 |
+
"learning_rate": 3.597957288765089e-05,
|
| 1065 |
+
"loss": 0.9713,
|
| 1066 |
+
"step": 1510
|
| 1067 |
+
},
|
| 1068 |
+
{
|
| 1069 |
+
"epoch": 0.8467966573816156,
|
| 1070 |
+
"grad_norm": 1.2572903633117676,
|
| 1071 |
+
"learning_rate": 3.5886722376973074e-05,
|
| 1072 |
+
"loss": 0.9426,
|
| 1073 |
+
"step": 1520
|
| 1074 |
+
},
|
| 1075 |
+
{
|
| 1076 |
+
"epoch": 0.8523676880222841,
|
| 1077 |
+
"grad_norm": 4.154526710510254,
|
| 1078 |
+
"learning_rate": 3.5793871866295266e-05,
|
| 1079 |
+
"loss": 0.9636,
|
| 1080 |
+
"step": 1530
|
| 1081 |
+
},
|
| 1082 |
+
{
|
| 1083 |
+
"epoch": 0.8579387186629527,
|
| 1084 |
+
"grad_norm": 3.4728987216949463,
|
| 1085 |
+
"learning_rate": 3.570102135561746e-05,
|
| 1086 |
+
"loss": 1.1009,
|
| 1087 |
+
"step": 1540
|
| 1088 |
+
},
|
| 1089 |
+
{
|
| 1090 |
+
"epoch": 0.8635097493036211,
|
| 1091 |
+
"grad_norm": 1.9633491039276123,
|
| 1092 |
+
"learning_rate": 3.5608170844939645e-05,
|
| 1093 |
+
"loss": 0.9549,
|
| 1094 |
+
"step": 1550
|
| 1095 |
+
},
|
| 1096 |
+
{
|
| 1097 |
+
"epoch": 0.8690807799442897,
|
| 1098 |
+
"grad_norm": 3.696641206741333,
|
| 1099 |
+
"learning_rate": 3.5515320334261844e-05,
|
| 1100 |
+
"loss": 0.9211,
|
| 1101 |
+
"step": 1560
|
| 1102 |
+
},
|
| 1103 |
+
{
|
| 1104 |
+
"epoch": 0.8746518105849582,
|
| 1105 |
+
"grad_norm": 3.0027382373809814,
|
| 1106 |
+
"learning_rate": 3.542246982358403e-05,
|
| 1107 |
+
"loss": 0.8844,
|
| 1108 |
+
"step": 1570
|
| 1109 |
+
},
|
| 1110 |
+
{
|
| 1111 |
+
"epoch": 0.8802228412256268,
|
| 1112 |
+
"grad_norm": 1.705255150794983,
|
| 1113 |
+
"learning_rate": 3.532961931290622e-05,
|
| 1114 |
+
"loss": 0.8733,
|
| 1115 |
+
"step": 1580
|
| 1116 |
+
},
|
| 1117 |
+
{
|
| 1118 |
+
"epoch": 0.8857938718662952,
|
| 1119 |
+
"grad_norm": 4.757926940917969,
|
| 1120 |
+
"learning_rate": 3.5236768802228415e-05,
|
| 1121 |
+
"loss": 0.9165,
|
| 1122 |
+
"step": 1590
|
| 1123 |
+
},
|
| 1124 |
+
{
|
| 1125 |
+
"epoch": 0.8913649025069638,
|
| 1126 |
+
"grad_norm": 3.9741427898406982,
|
| 1127 |
+
"learning_rate": 3.51439182915506e-05,
|
| 1128 |
+
"loss": 0.8411,
|
| 1129 |
+
"step": 1600
|
| 1130 |
+
},
|
| 1131 |
+
{
|
| 1132 |
+
"epoch": 0.8969359331476323,
|
| 1133 |
+
"grad_norm": 3.1221024990081787,
|
| 1134 |
+
"learning_rate": 3.50510677808728e-05,
|
| 1135 |
+
"loss": 0.8529,
|
| 1136 |
+
"step": 1610
|
| 1137 |
+
},
|
| 1138 |
+
{
|
| 1139 |
+
"epoch": 0.9025069637883009,
|
| 1140 |
+
"grad_norm": 5.116636753082275,
|
| 1141 |
+
"learning_rate": 3.4958217270194986e-05,
|
| 1142 |
+
"loss": 1.0049,
|
| 1143 |
+
"step": 1620
|
| 1144 |
+
},
|
| 1145 |
+
{
|
| 1146 |
+
"epoch": 0.9080779944289693,
|
| 1147 |
+
"grad_norm": 2.5207858085632324,
|
| 1148 |
+
"learning_rate": 3.4865366759517185e-05,
|
| 1149 |
+
"loss": 0.8374,
|
| 1150 |
+
"step": 1630
|
| 1151 |
+
},
|
| 1152 |
+
{
|
| 1153 |
+
"epoch": 0.9136490250696379,
|
| 1154 |
+
"grad_norm": 4.013001918792725,
|
| 1155 |
+
"learning_rate": 3.477251624883937e-05,
|
| 1156 |
+
"loss": 0.8902,
|
| 1157 |
+
"step": 1640
|
| 1158 |
+
},
|
| 1159 |
+
{
|
| 1160 |
+
"epoch": 0.9192200557103064,
|
| 1161 |
+
"grad_norm": 5.2283935546875,
|
| 1162 |
+
"learning_rate": 3.4679665738161556e-05,
|
| 1163 |
+
"loss": 0.8788,
|
| 1164 |
+
"step": 1650
|
| 1165 |
+
},
|
| 1166 |
+
{
|
| 1167 |
+
"epoch": 0.924791086350975,
|
| 1168 |
+
"grad_norm": 2.6664016246795654,
|
| 1169 |
+
"learning_rate": 3.4586815227483756e-05,
|
| 1170 |
+
"loss": 0.9204,
|
| 1171 |
+
"step": 1660
|
| 1172 |
+
},
|
| 1173 |
+
{
|
| 1174 |
+
"epoch": 0.9303621169916435,
|
| 1175 |
+
"grad_norm": 4.3207292556762695,
|
| 1176 |
+
"learning_rate": 3.449396471680594e-05,
|
| 1177 |
+
"loss": 0.9589,
|
| 1178 |
+
"step": 1670
|
| 1179 |
+
},
|
| 1180 |
+
{
|
| 1181 |
+
"epoch": 0.935933147632312,
|
| 1182 |
+
"grad_norm": 5.634909152984619,
|
| 1183 |
+
"learning_rate": 3.440111420612814e-05,
|
| 1184 |
+
"loss": 0.8883,
|
| 1185 |
+
"step": 1680
|
| 1186 |
+
},
|
| 1187 |
+
{
|
| 1188 |
+
"epoch": 0.9415041782729805,
|
| 1189 |
+
"grad_norm": 4.487209320068359,
|
| 1190 |
+
"learning_rate": 3.430826369545033e-05,
|
| 1191 |
+
"loss": 0.9111,
|
| 1192 |
+
"step": 1690
|
| 1193 |
+
},
|
| 1194 |
+
{
|
| 1195 |
+
"epoch": 0.947075208913649,
|
| 1196 |
+
"grad_norm": 3.9250285625457764,
|
| 1197 |
+
"learning_rate": 3.421541318477251e-05,
|
| 1198 |
+
"loss": 0.8759,
|
| 1199 |
+
"step": 1700
|
| 1200 |
+
},
|
| 1201 |
+
{
|
| 1202 |
+
"epoch": 0.9526462395543176,
|
| 1203 |
+
"grad_norm": 4.271919250488281,
|
| 1204 |
+
"learning_rate": 3.412256267409471e-05,
|
| 1205 |
+
"loss": 1.0486,
|
| 1206 |
+
"step": 1710
|
| 1207 |
+
},
|
| 1208 |
+
{
|
| 1209 |
+
"epoch": 0.958217270194986,
|
| 1210 |
+
"grad_norm": 3.3821752071380615,
|
| 1211 |
+
"learning_rate": 3.40297121634169e-05,
|
| 1212 |
+
"loss": 0.8707,
|
| 1213 |
+
"step": 1720
|
| 1214 |
+
},
|
| 1215 |
+
{
|
| 1216 |
+
"epoch": 0.9637883008356546,
|
| 1217 |
+
"grad_norm": 2.2104811668395996,
|
| 1218 |
+
"learning_rate": 3.39368616527391e-05,
|
| 1219 |
+
"loss": 0.8422,
|
| 1220 |
+
"step": 1730
|
| 1221 |
+
},
|
| 1222 |
+
{
|
| 1223 |
+
"epoch": 0.9693593314763231,
|
| 1224 |
+
"grad_norm": 2.4628074169158936,
|
| 1225 |
+
"learning_rate": 3.384401114206128e-05,
|
| 1226 |
+
"loss": 0.8869,
|
| 1227 |
+
"step": 1740
|
| 1228 |
+
},
|
| 1229 |
+
{
|
| 1230 |
+
"epoch": 0.9749303621169917,
|
| 1231 |
+
"grad_norm": 4.211429595947266,
|
| 1232 |
+
"learning_rate": 3.375116063138347e-05,
|
| 1233 |
+
"loss": 0.8037,
|
| 1234 |
+
"step": 1750
|
| 1235 |
+
},
|
| 1236 |
+
{
|
| 1237 |
+
"epoch": 0.9805013927576601,
|
| 1238 |
+
"grad_norm": 2.9044151306152344,
|
| 1239 |
+
"learning_rate": 3.365831012070567e-05,
|
| 1240 |
+
"loss": 0.9166,
|
| 1241 |
+
"step": 1760
|
| 1242 |
+
},
|
| 1243 |
+
{
|
| 1244 |
+
"epoch": 0.9860724233983287,
|
| 1245 |
+
"grad_norm": 3.072744846343994,
|
| 1246 |
+
"learning_rate": 3.3565459610027854e-05,
|
| 1247 |
+
"loss": 0.9653,
|
| 1248 |
+
"step": 1770
|
| 1249 |
+
},
|
| 1250 |
+
{
|
| 1251 |
+
"epoch": 0.9916434540389972,
|
| 1252 |
+
"grad_norm": 3.8640897274017334,
|
| 1253 |
+
"learning_rate": 3.347260909935005e-05,
|
| 1254 |
+
"loss": 0.8946,
|
| 1255 |
+
"step": 1780
|
| 1256 |
+
},
|
| 1257 |
+
{
|
| 1258 |
+
"epoch": 0.9972144846796658,
|
| 1259 |
+
"grad_norm": 3.481308698654175,
|
| 1260 |
+
"learning_rate": 3.337975858867224e-05,
|
| 1261 |
+
"loss": 0.9613,
|
| 1262 |
+
"step": 1790
|
| 1263 |
+
},
|
| 1264 |
+
{
|
| 1265 |
+
"epoch": 1.0,
|
| 1266 |
+
"eval_accuracy": 0.6692672053496795,
|
| 1267 |
+
"eval_loss": 0.9019954800605774,
|
| 1268 |
+
"eval_runtime": 53.0161,
|
| 1269 |
+
"eval_samples_per_second": 67.696,
|
| 1270 |
+
"eval_steps_per_second": 4.244,
|
| 1271 |
+
"step": 1795
|
| 1272 |
+
},
|
| 1273 |
+
{
|
| 1274 |
+
"epoch": 1.0027855153203342,
|
| 1275 |
+
"grad_norm": 2.660780191421509,
|
| 1276 |
+
"learning_rate": 3.328690807799443e-05,
|
| 1277 |
+
"loss": 0.8447,
|
| 1278 |
+
"step": 1800
|
| 1279 |
+
},
|
| 1280 |
+
{
|
| 1281 |
+
"epoch": 1.0083565459610029,
|
| 1282 |
+
"grad_norm": 5.112563133239746,
|
| 1283 |
+
"learning_rate": 3.3194057567316624e-05,
|
| 1284 |
+
"loss": 0.7709,
|
| 1285 |
+
"step": 1810
|
| 1286 |
+
},
|
| 1287 |
+
{
|
| 1288 |
+
"epoch": 1.0139275766016713,
|
| 1289 |
+
"grad_norm": 3.217790126800537,
|
| 1290 |
+
"learning_rate": 3.310120705663881e-05,
|
| 1291 |
+
"loss": 0.6957,
|
| 1292 |
+
"step": 1820
|
| 1293 |
+
},
|
| 1294 |
+
{
|
| 1295 |
+
"epoch": 1.0194986072423398,
|
| 1296 |
+
"grad_norm": 2.386460065841675,
|
| 1297 |
+
"learning_rate": 3.300835654596101e-05,
|
| 1298 |
+
"loss": 0.5801,
|
| 1299 |
+
"step": 1830
|
| 1300 |
+
},
|
| 1301 |
+
{
|
| 1302 |
+
"epoch": 1.0250696378830084,
|
| 1303 |
+
"grad_norm": 3.742408514022827,
|
| 1304 |
+
"learning_rate": 3.2915506035283195e-05,
|
| 1305 |
+
"loss": 0.7494,
|
| 1306 |
+
"step": 1840
|
| 1307 |
+
},
|
| 1308 |
+
{
|
| 1309 |
+
"epoch": 1.0306406685236769,
|
| 1310 |
+
"grad_norm": 5.288496017456055,
|
| 1311 |
+
"learning_rate": 3.282265552460539e-05,
|
| 1312 |
+
"loss": 0.7163,
|
| 1313 |
+
"step": 1850
|
| 1314 |
+
},
|
| 1315 |
+
{
|
| 1316 |
+
"epoch": 1.0362116991643453,
|
| 1317 |
+
"grad_norm": 3.0935630798339844,
|
| 1318 |
+
"learning_rate": 3.272980501392758e-05,
|
| 1319 |
+
"loss": 0.8476,
|
| 1320 |
+
"step": 1860
|
| 1321 |
+
},
|
| 1322 |
+
{
|
| 1323 |
+
"epoch": 1.041782729805014,
|
| 1324 |
+
"grad_norm": 3.274470329284668,
|
| 1325 |
+
"learning_rate": 3.2636954503249766e-05,
|
| 1326 |
+
"loss": 0.7659,
|
| 1327 |
+
"step": 1870
|
| 1328 |
+
},
|
| 1329 |
+
{
|
| 1330 |
+
"epoch": 1.0473537604456824,
|
| 1331 |
+
"grad_norm": 4.337296485900879,
|
| 1332 |
+
"learning_rate": 3.2544103992571965e-05,
|
| 1333 |
+
"loss": 0.8371,
|
| 1334 |
+
"step": 1880
|
| 1335 |
+
},
|
| 1336 |
+
{
|
| 1337 |
+
"epoch": 1.052924791086351,
|
| 1338 |
+
"grad_norm": 3.3266661167144775,
|
| 1339 |
+
"learning_rate": 3.245125348189415e-05,
|
| 1340 |
+
"loss": 0.7201,
|
| 1341 |
+
"step": 1890
|
| 1342 |
+
},
|
| 1343 |
+
{
|
| 1344 |
+
"epoch": 1.0584958217270195,
|
| 1345 |
+
"grad_norm": 2.803584337234497,
|
| 1346 |
+
"learning_rate": 3.235840297121634e-05,
|
| 1347 |
+
"loss": 0.7094,
|
| 1348 |
+
"step": 1900
|
| 1349 |
+
},
|
| 1350 |
+
{
|
| 1351 |
+
"epoch": 1.064066852367688,
|
| 1352 |
+
"grad_norm": 2.7187163829803467,
|
| 1353 |
+
"learning_rate": 3.2265552460538536e-05,
|
| 1354 |
+
"loss": 0.7677,
|
| 1355 |
+
"step": 1910
|
| 1356 |
+
},
|
| 1357 |
+
{
|
| 1358 |
+
"epoch": 1.0696378830083566,
|
| 1359 |
+
"grad_norm": 3.310220956802368,
|
| 1360 |
+
"learning_rate": 3.217270194986073e-05,
|
| 1361 |
+
"loss": 0.8175,
|
| 1362 |
+
"step": 1920
|
| 1363 |
+
},
|
| 1364 |
+
{
|
| 1365 |
+
"epoch": 1.075208913649025,
|
| 1366 |
+
"grad_norm": 3.0058999061584473,
|
| 1367 |
+
"learning_rate": 3.207985143918292e-05,
|
| 1368 |
+
"loss": 0.6781,
|
| 1369 |
+
"step": 1930
|
| 1370 |
+
},
|
| 1371 |
+
{
|
| 1372 |
+
"epoch": 1.0807799442896937,
|
| 1373 |
+
"grad_norm": 5.092315673828125,
|
| 1374 |
+
"learning_rate": 3.1987000928505107e-05,
|
| 1375 |
+
"loss": 0.8581,
|
| 1376 |
+
"step": 1940
|
| 1377 |
+
},
|
| 1378 |
+
{
|
| 1379 |
+
"epoch": 1.0863509749303621,
|
| 1380 |
+
"grad_norm": 3.070526599884033,
|
| 1381 |
+
"learning_rate": 3.18941504178273e-05,
|
| 1382 |
+
"loss": 0.7415,
|
| 1383 |
+
"step": 1950
|
| 1384 |
+
},
|
| 1385 |
+
{
|
| 1386 |
+
"epoch": 1.0919220055710306,
|
| 1387 |
+
"grad_norm": 3.610179901123047,
|
| 1388 |
+
"learning_rate": 3.180129990714949e-05,
|
| 1389 |
+
"loss": 0.7457,
|
| 1390 |
+
"step": 1960
|
| 1391 |
+
},
|
| 1392 |
+
{
|
| 1393 |
+
"epoch": 1.0974930362116992,
|
| 1394 |
+
"grad_norm": 5.436527729034424,
|
| 1395 |
+
"learning_rate": 3.1708449396471684e-05,
|
| 1396 |
+
"loss": 0.8023,
|
| 1397 |
+
"step": 1970
|
| 1398 |
+
},
|
| 1399 |
+
{
|
| 1400 |
+
"epoch": 1.1030640668523677,
|
| 1401 |
+
"grad_norm": 2.607541084289551,
|
| 1402 |
+
"learning_rate": 3.161559888579388e-05,
|
| 1403 |
+
"loss": 0.7311,
|
| 1404 |
+
"step": 1980
|
| 1405 |
+
},
|
| 1406 |
+
{
|
| 1407 |
+
"epoch": 1.1086350974930361,
|
| 1408 |
+
"grad_norm": 3.960480213165283,
|
| 1409 |
+
"learning_rate": 3.152274837511606e-05,
|
| 1410 |
+
"loss": 0.825,
|
| 1411 |
+
"step": 1990
|
| 1412 |
+
},
|
| 1413 |
+
{
|
| 1414 |
+
"epoch": 1.1142061281337048,
|
| 1415 |
+
"grad_norm": 2.607386589050293,
|
| 1416 |
+
"learning_rate": 3.1429897864438255e-05,
|
| 1417 |
+
"loss": 0.7247,
|
| 1418 |
+
"step": 2000
|
| 1419 |
+
},
|
| 1420 |
+
{
|
| 1421 |
+
"epoch": 1.1197771587743732,
|
| 1422 |
+
"grad_norm": 4.60785436630249,
|
| 1423 |
+
"learning_rate": 3.133704735376045e-05,
|
| 1424 |
+
"loss": 0.6815,
|
| 1425 |
+
"step": 2010
|
| 1426 |
+
},
|
| 1427 |
+
{
|
| 1428 |
+
"epoch": 1.1253481894150417,
|
| 1429 |
+
"grad_norm": 2.857929229736328,
|
| 1430 |
+
"learning_rate": 3.124419684308264e-05,
|
| 1431 |
+
"loss": 0.8937,
|
| 1432 |
+
"step": 2020
|
| 1433 |
+
},
|
| 1434 |
+
{
|
| 1435 |
+
"epoch": 1.1309192200557103,
|
| 1436 |
+
"grad_norm": 3.8009235858917236,
|
| 1437 |
+
"learning_rate": 3.1151346332404826e-05,
|
| 1438 |
+
"loss": 0.663,
|
| 1439 |
+
"step": 2030
|
| 1440 |
+
},
|
| 1441 |
+
{
|
| 1442 |
+
"epoch": 1.1364902506963788,
|
| 1443 |
+
"grad_norm": 2.8590617179870605,
|
| 1444 |
+
"learning_rate": 3.105849582172702e-05,
|
| 1445 |
+
"loss": 0.7552,
|
| 1446 |
+
"step": 2040
|
| 1447 |
+
},
|
| 1448 |
+
{
|
| 1449 |
+
"epoch": 1.1420612813370474,
|
| 1450 |
+
"grad_norm": 2.73160719871521,
|
| 1451 |
+
"learning_rate": 3.096564531104921e-05,
|
| 1452 |
+
"loss": 0.6979,
|
| 1453 |
+
"step": 2050
|
| 1454 |
+
},
|
| 1455 |
+
{
|
| 1456 |
+
"epoch": 1.1476323119777159,
|
| 1457 |
+
"grad_norm": 3.1918087005615234,
|
| 1458 |
+
"learning_rate": 3.0872794800371404e-05,
|
| 1459 |
+
"loss": 0.7999,
|
| 1460 |
+
"step": 2060
|
| 1461 |
+
},
|
| 1462 |
+
{
|
| 1463 |
+
"epoch": 1.1532033426183843,
|
| 1464 |
+
"grad_norm": 1.336449384689331,
|
| 1465 |
+
"learning_rate": 3.0779944289693596e-05,
|
| 1466 |
+
"loss": 0.5635,
|
| 1467 |
+
"step": 2070
|
| 1468 |
+
},
|
| 1469 |
+
{
|
| 1470 |
+
"epoch": 1.158774373259053,
|
| 1471 |
+
"grad_norm": 3.852604627609253,
|
| 1472 |
+
"learning_rate": 3.068709377901578e-05,
|
| 1473 |
+
"loss": 0.7839,
|
| 1474 |
+
"step": 2080
|
| 1475 |
+
},
|
| 1476 |
+
{
|
| 1477 |
+
"epoch": 1.1643454038997214,
|
| 1478 |
+
"grad_norm": 3.373872995376587,
|
| 1479 |
+
"learning_rate": 3.059424326833798e-05,
|
| 1480 |
+
"loss": 0.6604,
|
| 1481 |
+
"step": 2090
|
| 1482 |
+
},
|
| 1483 |
+
{
|
| 1484 |
+
"epoch": 1.16991643454039,
|
| 1485 |
+
"grad_norm": 5.2556586265563965,
|
| 1486 |
+
"learning_rate": 3.050139275766017e-05,
|
| 1487 |
+
"loss": 0.7676,
|
| 1488 |
+
"step": 2100
|
| 1489 |
+
},
|
| 1490 |
+
{
|
| 1491 |
+
"epoch": 1.1754874651810585,
|
| 1492 |
+
"grad_norm": 4.4580912590026855,
|
| 1493 |
+
"learning_rate": 3.0408542246982356e-05,
|
| 1494 |
+
"loss": 0.7738,
|
| 1495 |
+
"step": 2110
|
| 1496 |
+
},
|
| 1497 |
+
{
|
| 1498 |
+
"epoch": 1.181058495821727,
|
| 1499 |
+
"grad_norm": 2.804713726043701,
|
| 1500 |
+
"learning_rate": 3.0315691736304552e-05,
|
| 1501 |
+
"loss": 0.6995,
|
| 1502 |
+
"step": 2120
|
| 1503 |
+
},
|
| 1504 |
+
{
|
| 1505 |
+
"epoch": 1.1866295264623956,
|
| 1506 |
+
"grad_norm": 3.6438372135162354,
|
| 1507 |
+
"learning_rate": 3.022284122562674e-05,
|
| 1508 |
+
"loss": 0.6511,
|
| 1509 |
+
"step": 2130
|
| 1510 |
+
},
|
| 1511 |
+
{
|
| 1512 |
+
"epoch": 1.192200557103064,
|
| 1513 |
+
"grad_norm": 2.212045907974243,
|
| 1514 |
+
"learning_rate": 3.0129990714948937e-05,
|
| 1515 |
+
"loss": 0.603,
|
| 1516 |
+
"step": 2140
|
| 1517 |
+
},
|
| 1518 |
+
{
|
| 1519 |
+
"epoch": 1.1977715877437327,
|
| 1520 |
+
"grad_norm": 3.458812713623047,
|
| 1521 |
+
"learning_rate": 3.0037140204271123e-05,
|
| 1522 |
+
"loss": 0.7317,
|
| 1523 |
+
"step": 2150
|
| 1524 |
+
},
|
| 1525 |
+
{
|
| 1526 |
+
"epoch": 1.2033426183844012,
|
| 1527 |
+
"grad_norm": 2.6540637016296387,
|
| 1528 |
+
"learning_rate": 2.9944289693593312e-05,
|
| 1529 |
+
"loss": 0.7921,
|
| 1530 |
+
"step": 2160
|
| 1531 |
+
},
|
| 1532 |
+
{
|
| 1533 |
+
"epoch": 1.2089136490250696,
|
| 1534 |
+
"grad_norm": 5.65538215637207,
|
| 1535 |
+
"learning_rate": 2.9851439182915508e-05,
|
| 1536 |
+
"loss": 0.8803,
|
| 1537 |
+
"step": 2170
|
| 1538 |
+
},
|
| 1539 |
+
{
|
| 1540 |
+
"epoch": 1.2144846796657383,
|
| 1541 |
+
"grad_norm": 3.8509607315063477,
|
| 1542 |
+
"learning_rate": 2.9758588672237697e-05,
|
| 1543 |
+
"loss": 0.7686,
|
| 1544 |
+
"step": 2180
|
| 1545 |
+
},
|
| 1546 |
+
{
|
| 1547 |
+
"epoch": 1.2200557103064067,
|
| 1548 |
+
"grad_norm": 4.367794990539551,
|
| 1549 |
+
"learning_rate": 2.9665738161559893e-05,
|
| 1550 |
+
"loss": 0.7243,
|
| 1551 |
+
"step": 2190
|
| 1552 |
+
},
|
| 1553 |
+
{
|
| 1554 |
+
"epoch": 1.2256267409470751,
|
| 1555 |
+
"grad_norm": 3.6232688426971436,
|
| 1556 |
+
"learning_rate": 2.957288765088208e-05,
|
| 1557 |
+
"loss": 0.6483,
|
| 1558 |
+
"step": 2200
|
| 1559 |
+
},
|
| 1560 |
+
{
|
| 1561 |
+
"epoch": 1.2311977715877438,
|
| 1562 |
+
"grad_norm": 3.4824819564819336,
|
| 1563 |
+
"learning_rate": 2.9480037140204275e-05,
|
| 1564 |
+
"loss": 0.8249,
|
| 1565 |
+
"step": 2210
|
| 1566 |
+
},
|
| 1567 |
+
{
|
| 1568 |
+
"epoch": 1.2367688022284122,
|
| 1569 |
+
"grad_norm": 5.086853981018066,
|
| 1570 |
+
"learning_rate": 2.9387186629526464e-05,
|
| 1571 |
+
"loss": 0.7303,
|
| 1572 |
+
"step": 2220
|
| 1573 |
+
},
|
| 1574 |
+
{
|
| 1575 |
+
"epoch": 1.2423398328690807,
|
| 1576 |
+
"grad_norm": 3.1858561038970947,
|
| 1577 |
+
"learning_rate": 2.9294336118848653e-05,
|
| 1578 |
+
"loss": 0.6699,
|
| 1579 |
+
"step": 2230
|
| 1580 |
+
},
|
| 1581 |
+
{
|
| 1582 |
+
"epoch": 1.2479108635097493,
|
| 1583 |
+
"grad_norm": 5.4035139083862305,
|
| 1584 |
+
"learning_rate": 2.920148560817085e-05,
|
| 1585 |
+
"loss": 0.8184,
|
| 1586 |
+
"step": 2240
|
| 1587 |
+
},
|
| 1588 |
+
{
|
| 1589 |
+
"epoch": 1.2534818941504178,
|
| 1590 |
+
"grad_norm": 4.2386345863342285,
|
| 1591 |
+
"learning_rate": 2.9108635097493035e-05,
|
| 1592 |
+
"loss": 0.783,
|
| 1593 |
+
"step": 2250
|
| 1594 |
+
},
|
| 1595 |
+
{
|
| 1596 |
+
"epoch": 1.2590529247910864,
|
| 1597 |
+
"grad_norm": 5.696313858032227,
|
| 1598 |
+
"learning_rate": 2.901578458681523e-05,
|
| 1599 |
+
"loss": 0.7901,
|
| 1600 |
+
"step": 2260
|
| 1601 |
+
},
|
| 1602 |
+
{
|
| 1603 |
+
"epoch": 1.2646239554317549,
|
| 1604 |
+
"grad_norm": 2.38380765914917,
|
| 1605 |
+
"learning_rate": 2.892293407613742e-05,
|
| 1606 |
+
"loss": 0.7271,
|
| 1607 |
+
"step": 2270
|
| 1608 |
+
},
|
| 1609 |
+
{
|
| 1610 |
+
"epoch": 1.2701949860724233,
|
| 1611 |
+
"grad_norm": 2.800536632537842,
|
| 1612 |
+
"learning_rate": 2.883008356545961e-05,
|
| 1613 |
+
"loss": 0.7253,
|
| 1614 |
+
"step": 2280
|
| 1615 |
+
},
|
| 1616 |
+
{
|
| 1617 |
+
"epoch": 1.275766016713092,
|
| 1618 |
+
"grad_norm": 5.40772008895874,
|
| 1619 |
+
"learning_rate": 2.8737233054781805e-05,
|
| 1620 |
+
"loss": 0.8461,
|
| 1621 |
+
"step": 2290
|
| 1622 |
+
},
|
| 1623 |
+
{
|
| 1624 |
+
"epoch": 1.2813370473537604,
|
| 1625 |
+
"grad_norm": 2.7099337577819824,
|
| 1626 |
+
"learning_rate": 2.864438254410399e-05,
|
| 1627 |
+
"loss": 0.7545,
|
| 1628 |
+
"step": 2300
|
| 1629 |
+
},
|
| 1630 |
+
{
|
| 1631 |
+
"epoch": 1.286908077994429,
|
| 1632 |
+
"grad_norm": 5.34475040435791,
|
| 1633 |
+
"learning_rate": 2.8551532033426187e-05,
|
| 1634 |
+
"loss": 0.6853,
|
| 1635 |
+
"step": 2310
|
| 1636 |
+
},
|
| 1637 |
+
{
|
| 1638 |
+
"epoch": 1.2924791086350975,
|
| 1639 |
+
"grad_norm": 3.6724138259887695,
|
| 1640 |
+
"learning_rate": 2.8458681522748376e-05,
|
| 1641 |
+
"loss": 0.6719,
|
| 1642 |
+
"step": 2320
|
| 1643 |
+
},
|
| 1644 |
+
{
|
| 1645 |
+
"epoch": 1.298050139275766,
|
| 1646 |
+
"grad_norm": 6.54721212387085,
|
| 1647 |
+
"learning_rate": 2.8365831012070565e-05,
|
| 1648 |
+
"loss": 0.6367,
|
| 1649 |
+
"step": 2330
|
| 1650 |
+
},
|
| 1651 |
+
{
|
| 1652 |
+
"epoch": 1.3036211699164346,
|
| 1653 |
+
"grad_norm": 4.257522106170654,
|
| 1654 |
+
"learning_rate": 2.827298050139276e-05,
|
| 1655 |
+
"loss": 0.8234,
|
| 1656 |
+
"step": 2340
|
| 1657 |
+
},
|
| 1658 |
+
{
|
| 1659 |
+
"epoch": 1.309192200557103,
|
| 1660 |
+
"grad_norm": 4.256605625152588,
|
| 1661 |
+
"learning_rate": 2.8180129990714947e-05,
|
| 1662 |
+
"loss": 0.8149,
|
| 1663 |
+
"step": 2350
|
| 1664 |
+
},
|
| 1665 |
+
{
|
| 1666 |
+
"epoch": 1.3147632311977717,
|
| 1667 |
+
"grad_norm": 3.181926965713501,
|
| 1668 |
+
"learning_rate": 2.8087279480037143e-05,
|
| 1669 |
+
"loss": 0.7522,
|
| 1670 |
+
"step": 2360
|
| 1671 |
+
},
|
| 1672 |
+
{
|
| 1673 |
+
"epoch": 1.3203342618384402,
|
| 1674 |
+
"grad_norm": 2.8374698162078857,
|
| 1675 |
+
"learning_rate": 2.7994428969359332e-05,
|
| 1676 |
+
"loss": 0.6871,
|
| 1677 |
+
"step": 2370
|
| 1678 |
+
},
|
| 1679 |
+
{
|
| 1680 |
+
"epoch": 1.3259052924791086,
|
| 1681 |
+
"grad_norm": 7.006384372711182,
|
| 1682 |
+
"learning_rate": 2.7901578458681528e-05,
|
| 1683 |
+
"loss": 0.7822,
|
| 1684 |
+
"step": 2380
|
| 1685 |
+
},
|
| 1686 |
+
{
|
| 1687 |
+
"epoch": 1.331476323119777,
|
| 1688 |
+
"grad_norm": 5.170847415924072,
|
| 1689 |
+
"learning_rate": 2.7808727948003717e-05,
|
| 1690 |
+
"loss": 0.8323,
|
| 1691 |
+
"step": 2390
|
| 1692 |
+
},
|
| 1693 |
+
{
|
| 1694 |
+
"epoch": 1.3370473537604457,
|
| 1695 |
+
"grad_norm": 4.078238010406494,
|
| 1696 |
+
"learning_rate": 2.7715877437325903e-05,
|
| 1697 |
+
"loss": 0.6984,
|
| 1698 |
+
"step": 2400
|
| 1699 |
+
},
|
| 1700 |
+
{
|
| 1701 |
+
"epoch": 1.3426183844011141,
|
| 1702 |
+
"grad_norm": 3.4335429668426514,
|
| 1703 |
+
"learning_rate": 2.76230269266481e-05,
|
| 1704 |
+
"loss": 0.6943,
|
| 1705 |
+
"step": 2410
|
| 1706 |
+
},
|
| 1707 |
+
{
|
| 1708 |
+
"epoch": 1.3481894150417828,
|
| 1709 |
+
"grad_norm": 3.247312545776367,
|
| 1710 |
+
"learning_rate": 2.7530176415970288e-05,
|
| 1711 |
+
"loss": 0.7341,
|
| 1712 |
+
"step": 2420
|
| 1713 |
+
},
|
| 1714 |
+
{
|
| 1715 |
+
"epoch": 1.3537604456824512,
|
| 1716 |
+
"grad_norm": 5.7520318031311035,
|
| 1717 |
+
"learning_rate": 2.7437325905292484e-05,
|
| 1718 |
+
"loss": 0.7103,
|
| 1719 |
+
"step": 2430
|
| 1720 |
+
},
|
| 1721 |
+
{
|
| 1722 |
+
"epoch": 1.3593314763231197,
|
| 1723 |
+
"grad_norm": 1.9237465858459473,
|
| 1724 |
+
"learning_rate": 2.735376044568245e-05,
|
| 1725 |
+
"loss": 0.7064,
|
| 1726 |
+
"step": 2440
|
| 1727 |
+
},
|
| 1728 |
+
{
|
| 1729 |
+
"epoch": 1.3649025069637883,
|
| 1730 |
+
"grad_norm": 3.3437535762786865,
|
| 1731 |
+
"learning_rate": 2.726090993500464e-05,
|
| 1732 |
+
"loss": 0.7222,
|
| 1733 |
+
"step": 2450
|
| 1734 |
+
},
|
| 1735 |
+
{
|
| 1736 |
+
"epoch": 1.3704735376044568,
|
| 1737 |
+
"grad_norm": 3.8634493350982666,
|
| 1738 |
+
"learning_rate": 2.7168059424326836e-05,
|
| 1739 |
+
"loss": 0.5842,
|
| 1740 |
+
"step": 2460
|
| 1741 |
+
},
|
| 1742 |
+
{
|
| 1743 |
+
"epoch": 1.3760445682451254,
|
| 1744 |
+
"grad_norm": 4.395915508270264,
|
| 1745 |
+
"learning_rate": 2.7075208913649025e-05,
|
| 1746 |
+
"loss": 0.8458,
|
| 1747 |
+
"step": 2470
|
| 1748 |
+
},
|
| 1749 |
+
{
|
| 1750 |
+
"epoch": 1.3816155988857939,
|
| 1751 |
+
"grad_norm": 4.998650074005127,
|
| 1752 |
+
"learning_rate": 2.6982358402971218e-05,
|
| 1753 |
+
"loss": 0.7941,
|
| 1754 |
+
"step": 2480
|
| 1755 |
+
},
|
| 1756 |
+
{
|
| 1757 |
+
"epoch": 1.3871866295264623,
|
| 1758 |
+
"grad_norm": 5.347882270812988,
|
| 1759 |
+
"learning_rate": 2.6889507892293407e-05,
|
| 1760 |
+
"loss": 0.728,
|
| 1761 |
+
"step": 2490
|
| 1762 |
+
},
|
| 1763 |
+
{
|
| 1764 |
+
"epoch": 1.392757660167131,
|
| 1765 |
+
"grad_norm": 4.277406692504883,
|
| 1766 |
+
"learning_rate": 2.6796657381615596e-05,
|
| 1767 |
+
"loss": 0.7203,
|
| 1768 |
+
"step": 2500
|
| 1769 |
+
},
|
| 1770 |
+
{
|
| 1771 |
+
"epoch": 1.3983286908077994,
|
| 1772 |
+
"grad_norm": 3.2961020469665527,
|
| 1773 |
+
"learning_rate": 2.6703806870937792e-05,
|
| 1774 |
+
"loss": 0.675,
|
| 1775 |
+
"step": 2510
|
| 1776 |
+
},
|
| 1777 |
+
{
|
| 1778 |
+
"epoch": 1.403899721448468,
|
| 1779 |
+
"grad_norm": 3.227165460586548,
|
| 1780 |
+
"learning_rate": 2.661095636025998e-05,
|
| 1781 |
+
"loss": 0.8199,
|
| 1782 |
+
"step": 2520
|
| 1783 |
+
},
|
| 1784 |
+
{
|
| 1785 |
+
"epoch": 1.4094707520891365,
|
| 1786 |
+
"grad_norm": 2.727691650390625,
|
| 1787 |
+
"learning_rate": 2.6518105849582174e-05,
|
| 1788 |
+
"loss": 0.6727,
|
| 1789 |
+
"step": 2530
|
| 1790 |
+
},
|
| 1791 |
+
{
|
| 1792 |
+
"epoch": 1.415041782729805,
|
| 1793 |
+
"grad_norm": 3.660712957382202,
|
| 1794 |
+
"learning_rate": 2.6425255338904363e-05,
|
| 1795 |
+
"loss": 0.7168,
|
| 1796 |
+
"step": 2540
|
| 1797 |
+
},
|
| 1798 |
+
{
|
| 1799 |
+
"epoch": 1.4206128133704734,
|
| 1800 |
+
"grad_norm": 4.9975266456604,
|
| 1801 |
+
"learning_rate": 2.633240482822656e-05,
|
| 1802 |
+
"loss": 0.7329,
|
| 1803 |
+
"step": 2550
|
| 1804 |
+
},
|
| 1805 |
+
{
|
| 1806 |
+
"epoch": 1.426183844011142,
|
| 1807 |
+
"grad_norm": 4.956869602203369,
|
| 1808 |
+
"learning_rate": 2.6239554317548748e-05,
|
| 1809 |
+
"loss": 0.7576,
|
| 1810 |
+
"step": 2560
|
| 1811 |
+
},
|
| 1812 |
+
{
|
| 1813 |
+
"epoch": 1.4317548746518105,
|
| 1814 |
+
"grad_norm": 3.2841885089874268,
|
| 1815 |
+
"learning_rate": 2.6146703806870937e-05,
|
| 1816 |
+
"loss": 0.687,
|
| 1817 |
+
"step": 2570
|
| 1818 |
+
},
|
| 1819 |
+
{
|
| 1820 |
+
"epoch": 1.4373259052924792,
|
| 1821 |
+
"grad_norm": 5.767863750457764,
|
| 1822 |
+
"learning_rate": 2.605385329619313e-05,
|
| 1823 |
+
"loss": 0.7346,
|
| 1824 |
+
"step": 2580
|
| 1825 |
+
},
|
| 1826 |
+
{
|
| 1827 |
+
"epoch": 1.4428969359331476,
|
| 1828 |
+
"grad_norm": 2.8011934757232666,
|
| 1829 |
+
"learning_rate": 2.596100278551532e-05,
|
| 1830 |
+
"loss": 0.7072,
|
| 1831 |
+
"step": 2590
|
| 1832 |
+
},
|
| 1833 |
+
{
|
| 1834 |
+
"epoch": 1.448467966573816,
|
| 1835 |
+
"grad_norm": 2.4750354290008545,
|
| 1836 |
+
"learning_rate": 2.5868152274837515e-05,
|
| 1837 |
+
"loss": 0.5924,
|
| 1838 |
+
"step": 2600
|
| 1839 |
+
},
|
| 1840 |
+
{
|
| 1841 |
+
"epoch": 1.4540389972144847,
|
| 1842 |
+
"grad_norm": 2.4504594802856445,
|
| 1843 |
+
"learning_rate": 2.5775301764159704e-05,
|
| 1844 |
+
"loss": 0.6229,
|
| 1845 |
+
"step": 2610
|
| 1846 |
+
},
|
| 1847 |
+
{
|
| 1848 |
+
"epoch": 1.4596100278551531,
|
| 1849 |
+
"grad_norm": 6.350492000579834,
|
| 1850 |
+
"learning_rate": 2.5682451253481893e-05,
|
| 1851 |
+
"loss": 0.7909,
|
| 1852 |
+
"step": 2620
|
| 1853 |
+
},
|
| 1854 |
+
{
|
| 1855 |
+
"epoch": 1.4651810584958218,
|
| 1856 |
+
"grad_norm": 3.0052127838134766,
|
| 1857 |
+
"learning_rate": 2.5589600742804086e-05,
|
| 1858 |
+
"loss": 0.6516,
|
| 1859 |
+
"step": 2630
|
| 1860 |
+
},
|
| 1861 |
+
{
|
| 1862 |
+
"epoch": 1.4707520891364902,
|
| 1863 |
+
"grad_norm": 3.0360071659088135,
|
| 1864 |
+
"learning_rate": 2.5496750232126275e-05,
|
| 1865 |
+
"loss": 0.7202,
|
| 1866 |
+
"step": 2640
|
| 1867 |
+
},
|
| 1868 |
+
{
|
| 1869 |
+
"epoch": 1.4763231197771587,
|
| 1870 |
+
"grad_norm": 5.270174026489258,
|
| 1871 |
+
"learning_rate": 2.540389972144847e-05,
|
| 1872 |
+
"loss": 0.7491,
|
| 1873 |
+
"step": 2650
|
| 1874 |
+
},
|
| 1875 |
+
{
|
| 1876 |
+
"epoch": 1.4818941504178273,
|
| 1877 |
+
"grad_norm": 6.691749572753906,
|
| 1878 |
+
"learning_rate": 2.531104921077066e-05,
|
| 1879 |
+
"loss": 0.6879,
|
| 1880 |
+
"step": 2660
|
| 1881 |
+
},
|
| 1882 |
+
{
|
| 1883 |
+
"epoch": 1.4874651810584958,
|
| 1884 |
+
"grad_norm": 3.4790680408477783,
|
| 1885 |
+
"learning_rate": 2.5218198700092853e-05,
|
| 1886 |
+
"loss": 0.7869,
|
| 1887 |
+
"step": 2670
|
| 1888 |
+
},
|
| 1889 |
+
{
|
| 1890 |
+
"epoch": 1.4930362116991645,
|
| 1891 |
+
"grad_norm": 4.1881914138793945,
|
| 1892 |
+
"learning_rate": 2.5125348189415042e-05,
|
| 1893 |
+
"loss": 0.7038,
|
| 1894 |
+
"step": 2680
|
| 1895 |
+
},
|
| 1896 |
+
{
|
| 1897 |
+
"epoch": 1.498607242339833,
|
| 1898 |
+
"grad_norm": 3.5954504013061523,
|
| 1899 |
+
"learning_rate": 2.503249767873723e-05,
|
| 1900 |
+
"loss": 0.8112,
|
| 1901 |
+
"step": 2690
|
| 1902 |
+
},
|
| 1903 |
+
{
|
| 1904 |
+
"epoch": 1.5041782729805013,
|
| 1905 |
+
"grad_norm": 5.3881354331970215,
|
| 1906 |
+
"learning_rate": 2.4939647168059427e-05,
|
| 1907 |
+
"loss": 0.8329,
|
| 1908 |
+
"step": 2700
|
| 1909 |
+
},
|
| 1910 |
+
{
|
| 1911 |
+
"epoch": 1.5097493036211698,
|
| 1912 |
+
"grad_norm": 2.5170273780822754,
|
| 1913 |
+
"learning_rate": 2.4846796657381616e-05,
|
| 1914 |
+
"loss": 0.5086,
|
| 1915 |
+
"step": 2710
|
| 1916 |
+
},
|
| 1917 |
+
{
|
| 1918 |
+
"epoch": 1.5153203342618384,
|
| 1919 |
+
"grad_norm": 2.370330333709717,
|
| 1920 |
+
"learning_rate": 2.475394614670381e-05,
|
| 1921 |
+
"loss": 0.6625,
|
| 1922 |
+
"step": 2720
|
| 1923 |
+
},
|
| 1924 |
+
{
|
| 1925 |
+
"epoch": 1.520891364902507,
|
| 1926 |
+
"grad_norm": 2.416132926940918,
|
| 1927 |
+
"learning_rate": 2.4661095636025998e-05,
|
| 1928 |
+
"loss": 0.7835,
|
| 1929 |
+
"step": 2730
|
| 1930 |
+
},
|
| 1931 |
+
{
|
| 1932 |
+
"epoch": 1.5264623955431755,
|
| 1933 |
+
"grad_norm": 4.824071407318115,
|
| 1934 |
+
"learning_rate": 2.456824512534819e-05,
|
| 1935 |
+
"loss": 0.6605,
|
| 1936 |
+
"step": 2740
|
| 1937 |
+
},
|
| 1938 |
+
{
|
| 1939 |
+
"epoch": 1.532033426183844,
|
| 1940 |
+
"grad_norm": 5.555083274841309,
|
| 1941 |
+
"learning_rate": 2.4475394614670383e-05,
|
| 1942 |
+
"loss": 0.675,
|
| 1943 |
+
"step": 2750
|
| 1944 |
+
},
|
| 1945 |
+
{
|
| 1946 |
+
"epoch": 1.5376044568245124,
|
| 1947 |
+
"grad_norm": 5.953351020812988,
|
| 1948 |
+
"learning_rate": 2.4382544103992576e-05,
|
| 1949 |
+
"loss": 0.6572,
|
| 1950 |
+
"step": 2760
|
| 1951 |
+
},
|
| 1952 |
+
{
|
| 1953 |
+
"epoch": 1.543175487465181,
|
| 1954 |
+
"grad_norm": 3.702897787094116,
|
| 1955 |
+
"learning_rate": 2.4289693593314765e-05,
|
| 1956 |
+
"loss": 0.7674,
|
| 1957 |
+
"step": 2770
|
| 1958 |
+
},
|
| 1959 |
+
{
|
| 1960 |
+
"epoch": 1.5487465181058497,
|
| 1961 |
+
"grad_norm": 3.995495080947876,
|
| 1962 |
+
"learning_rate": 2.4196843082636954e-05,
|
| 1963 |
+
"loss": 0.7461,
|
| 1964 |
+
"step": 2780
|
| 1965 |
+
},
|
| 1966 |
+
{
|
| 1967 |
+
"epoch": 1.5543175487465182,
|
| 1968 |
+
"grad_norm": 4.654627323150635,
|
| 1969 |
+
"learning_rate": 2.4103992571959146e-05,
|
| 1970 |
+
"loss": 0.7709,
|
| 1971 |
+
"step": 2790
|
| 1972 |
+
},
|
| 1973 |
+
{
|
| 1974 |
+
"epoch": 1.5598885793871866,
|
| 1975 |
+
"grad_norm": 4.607250690460205,
|
| 1976 |
+
"learning_rate": 2.401114206128134e-05,
|
| 1977 |
+
"loss": 0.8664,
|
| 1978 |
+
"step": 2800
|
| 1979 |
+
},
|
| 1980 |
+
{
|
| 1981 |
+
"epoch": 1.565459610027855,
|
| 1982 |
+
"grad_norm": 4.200578212738037,
|
| 1983 |
+
"learning_rate": 2.391829155060353e-05,
|
| 1984 |
+
"loss": 0.7295,
|
| 1985 |
+
"step": 2810
|
| 1986 |
+
},
|
| 1987 |
+
{
|
| 1988 |
+
"epoch": 1.5710306406685237,
|
| 1989 |
+
"grad_norm": 3.5812277793884277,
|
| 1990 |
+
"learning_rate": 2.382544103992572e-05,
|
| 1991 |
+
"loss": 0.7653,
|
| 1992 |
+
"step": 2820
|
| 1993 |
+
},
|
| 1994 |
+
{
|
| 1995 |
+
"epoch": 1.5766016713091922,
|
| 1996 |
+
"grad_norm": 3.6298224925994873,
|
| 1997 |
+
"learning_rate": 2.373259052924791e-05,
|
| 1998 |
+
"loss": 0.6548,
|
| 1999 |
+
"step": 2830
|
| 2000 |
+
},
|
| 2001 |
+
{
|
| 2002 |
+
"epoch": 1.5821727019498608,
|
| 2003 |
+
"grad_norm": 3.4680569171905518,
|
| 2004 |
+
"learning_rate": 2.3639740018570102e-05,
|
| 2005 |
+
"loss": 0.699,
|
| 2006 |
+
"step": 2840
|
| 2007 |
+
},
|
| 2008 |
+
{
|
| 2009 |
+
"epoch": 1.5877437325905293,
|
| 2010 |
+
"grad_norm": 3.139227867126465,
|
| 2011 |
+
"learning_rate": 2.3546889507892295e-05,
|
| 2012 |
+
"loss": 0.6505,
|
| 2013 |
+
"step": 2850
|
| 2014 |
+
},
|
| 2015 |
+
{
|
| 2016 |
+
"epoch": 1.5933147632311977,
|
| 2017 |
+
"grad_norm": 4.027279853820801,
|
| 2018 |
+
"learning_rate": 2.3454038997214488e-05,
|
| 2019 |
+
"loss": 0.7388,
|
| 2020 |
+
"step": 2860
|
| 2021 |
+
},
|
| 2022 |
+
{
|
| 2023 |
+
"epoch": 1.5988857938718661,
|
| 2024 |
+
"grad_norm": 3.547569990158081,
|
| 2025 |
+
"learning_rate": 2.3361188486536677e-05,
|
| 2026 |
+
"loss": 0.642,
|
| 2027 |
+
"step": 2870
|
| 2028 |
+
},
|
| 2029 |
+
{
|
| 2030 |
+
"epoch": 1.6044568245125348,
|
| 2031 |
+
"grad_norm": 5.281991004943848,
|
| 2032 |
+
"learning_rate": 2.3268337975858866e-05,
|
| 2033 |
+
"loss": 0.6009,
|
| 2034 |
+
"step": 2880
|
| 2035 |
+
},
|
| 2036 |
+
{
|
| 2037 |
+
"epoch": 1.6100278551532035,
|
| 2038 |
+
"grad_norm": 3.9563615322113037,
|
| 2039 |
+
"learning_rate": 2.317548746518106e-05,
|
| 2040 |
+
"loss": 0.695,
|
| 2041 |
+
"step": 2890
|
| 2042 |
+
},
|
| 2043 |
+
{
|
| 2044 |
+
"epoch": 1.615598885793872,
|
| 2045 |
+
"grad_norm": 5.508429050445557,
|
| 2046 |
+
"learning_rate": 2.308263695450325e-05,
|
| 2047 |
+
"loss": 0.7169,
|
| 2048 |
+
"step": 2900
|
| 2049 |
+
},
|
| 2050 |
+
{
|
| 2051 |
+
"epoch": 1.6211699164345403,
|
| 2052 |
+
"grad_norm": 4.158377647399902,
|
| 2053 |
+
"learning_rate": 2.2989786443825444e-05,
|
| 2054 |
+
"loss": 0.6337,
|
| 2055 |
+
"step": 2910
|
| 2056 |
+
},
|
| 2057 |
+
{
|
| 2058 |
+
"epoch": 1.6267409470752088,
|
| 2059 |
+
"grad_norm": 4.293817520141602,
|
| 2060 |
+
"learning_rate": 2.2896935933147633e-05,
|
| 2061 |
+
"loss": 0.6769,
|
| 2062 |
+
"step": 2920
|
| 2063 |
+
},
|
| 2064 |
+
{
|
| 2065 |
+
"epoch": 1.6323119777158774,
|
| 2066 |
+
"grad_norm": 3.0530028343200684,
|
| 2067 |
+
"learning_rate": 2.2804085422469825e-05,
|
| 2068 |
+
"loss": 0.6436,
|
| 2069 |
+
"step": 2930
|
| 2070 |
+
},
|
| 2071 |
+
{
|
| 2072 |
+
"epoch": 1.637883008356546,
|
| 2073 |
+
"grad_norm": 3.3768982887268066,
|
| 2074 |
+
"learning_rate": 2.2711234911792014e-05,
|
| 2075 |
+
"loss": 0.6443,
|
| 2076 |
+
"step": 2940
|
| 2077 |
+
},
|
| 2078 |
+
{
|
| 2079 |
+
"epoch": 1.6434540389972145,
|
| 2080 |
+
"grad_norm": 6.057602882385254,
|
| 2081 |
+
"learning_rate": 2.2618384401114207e-05,
|
| 2082 |
+
"loss": 0.6208,
|
| 2083 |
+
"step": 2950
|
| 2084 |
+
},
|
| 2085 |
+
{
|
| 2086 |
+
"epoch": 1.649025069637883,
|
| 2087 |
+
"grad_norm": 7.647638320922852,
|
| 2088 |
+
"learning_rate": 2.25255338904364e-05,
|
| 2089 |
+
"loss": 0.8125,
|
| 2090 |
+
"step": 2960
|
| 2091 |
+
},
|
| 2092 |
+
{
|
| 2093 |
+
"epoch": 1.6545961002785514,
|
| 2094 |
+
"grad_norm": 6.915018081665039,
|
| 2095 |
+
"learning_rate": 2.243268337975859e-05,
|
| 2096 |
+
"loss": 0.8279,
|
| 2097 |
+
"step": 2970
|
| 2098 |
+
},
|
| 2099 |
+
{
|
| 2100 |
+
"epoch": 1.66016713091922,
|
| 2101 |
+
"grad_norm": 3.073479413986206,
|
| 2102 |
+
"learning_rate": 2.233983286908078e-05,
|
| 2103 |
+
"loss": 0.5983,
|
| 2104 |
+
"step": 2980
|
| 2105 |
+
},
|
| 2106 |
+
{
|
| 2107 |
+
"epoch": 1.6657381615598887,
|
| 2108 |
+
"grad_norm": 6.27379035949707,
|
| 2109 |
+
"learning_rate": 2.2246982358402974e-05,
|
| 2110 |
+
"loss": 0.7413,
|
| 2111 |
+
"step": 2990
|
| 2112 |
+
},
|
| 2113 |
+
{
|
| 2114 |
+
"epoch": 1.6713091922005572,
|
| 2115 |
+
"grad_norm": 2.8790829181671143,
|
| 2116 |
+
"learning_rate": 2.2154131847725163e-05,
|
| 2117 |
+
"loss": 0.5785,
|
| 2118 |
+
"step": 3000
|
| 2119 |
+
},
|
| 2120 |
+
{
|
| 2121 |
+
"epoch": 1.6768802228412256,
|
| 2122 |
+
"grad_norm": 3.810025691986084,
|
| 2123 |
+
"learning_rate": 2.2061281337047355e-05,
|
| 2124 |
+
"loss": 0.6187,
|
| 2125 |
+
"step": 3010
|
| 2126 |
+
},
|
| 2127 |
+
{
|
| 2128 |
+
"epoch": 1.682451253481894,
|
| 2129 |
+
"grad_norm": 4.597643852233887,
|
| 2130 |
+
"learning_rate": 2.1968430826369545e-05,
|
| 2131 |
+
"loss": 0.7871,
|
| 2132 |
+
"step": 3020
|
| 2133 |
+
},
|
| 2134 |
+
{
|
| 2135 |
+
"epoch": 1.6880222841225627,
|
| 2136 |
+
"grad_norm": 4.470458507537842,
|
| 2137 |
+
"learning_rate": 2.1875580315691737e-05,
|
| 2138 |
+
"loss": 0.7397,
|
| 2139 |
+
"step": 3030
|
| 2140 |
+
},
|
| 2141 |
+
{
|
| 2142 |
+
"epoch": 1.6935933147632312,
|
| 2143 |
+
"grad_norm": 3.957707643508911,
|
| 2144 |
+
"learning_rate": 2.178272980501393e-05,
|
| 2145 |
+
"loss": 0.6893,
|
| 2146 |
+
"step": 3040
|
| 2147 |
+
},
|
| 2148 |
+
{
|
| 2149 |
+
"epoch": 1.6991643454038998,
|
| 2150 |
+
"grad_norm": 4.973650932312012,
|
| 2151 |
+
"learning_rate": 2.1689879294336122e-05,
|
| 2152 |
+
"loss": 0.601,
|
| 2153 |
+
"step": 3050
|
| 2154 |
+
},
|
| 2155 |
+
{
|
| 2156 |
+
"epoch": 1.7047353760445683,
|
| 2157 |
+
"grad_norm": 3.1551012992858887,
|
| 2158 |
+
"learning_rate": 2.159702878365831e-05,
|
| 2159 |
+
"loss": 0.6792,
|
| 2160 |
+
"step": 3060
|
| 2161 |
+
},
|
| 2162 |
+
{
|
| 2163 |
+
"epoch": 1.7103064066852367,
|
| 2164 |
+
"grad_norm": 21.842958450317383,
|
| 2165 |
+
"learning_rate": 2.15041782729805e-05,
|
| 2166 |
+
"loss": 0.7582,
|
| 2167 |
+
"step": 3070
|
| 2168 |
+
},
|
| 2169 |
+
{
|
| 2170 |
+
"epoch": 1.7158774373259051,
|
| 2171 |
+
"grad_norm": 6.199334144592285,
|
| 2172 |
+
"learning_rate": 2.1411327762302693e-05,
|
| 2173 |
+
"loss": 0.635,
|
| 2174 |
+
"step": 3080
|
| 2175 |
+
},
|
| 2176 |
+
{
|
| 2177 |
+
"epoch": 1.7214484679665738,
|
| 2178 |
+
"grad_norm": 5.763338088989258,
|
| 2179 |
+
"learning_rate": 2.1318477251624886e-05,
|
| 2180 |
+
"loss": 0.7636,
|
| 2181 |
+
"step": 3090
|
| 2182 |
+
},
|
| 2183 |
+
{
|
| 2184 |
+
"epoch": 1.7270194986072425,
|
| 2185 |
+
"grad_norm": 3.1481924057006836,
|
| 2186 |
+
"learning_rate": 2.1225626740947078e-05,
|
| 2187 |
+
"loss": 0.7613,
|
| 2188 |
+
"step": 3100
|
| 2189 |
+
},
|
| 2190 |
+
{
|
| 2191 |
+
"epoch": 1.732590529247911,
|
| 2192 |
+
"grad_norm": 2.0901215076446533,
|
| 2193 |
+
"learning_rate": 2.1132776230269267e-05,
|
| 2194 |
+
"loss": 0.6326,
|
| 2195 |
+
"step": 3110
|
| 2196 |
+
},
|
| 2197 |
+
{
|
| 2198 |
+
"epoch": 1.7381615598885793,
|
| 2199 |
+
"grad_norm": 3.8175764083862305,
|
| 2200 |
+
"learning_rate": 2.1039925719591457e-05,
|
| 2201 |
+
"loss": 0.668,
|
| 2202 |
+
"step": 3120
|
| 2203 |
+
},
|
| 2204 |
+
{
|
| 2205 |
+
"epoch": 1.7437325905292478,
|
| 2206 |
+
"grad_norm": 5.669551849365234,
|
| 2207 |
+
"learning_rate": 2.094707520891365e-05,
|
| 2208 |
+
"loss": 0.6897,
|
| 2209 |
+
"step": 3130
|
| 2210 |
+
},
|
| 2211 |
+
{
|
| 2212 |
+
"epoch": 1.7493036211699164,
|
| 2213 |
+
"grad_norm": 2.3246147632598877,
|
| 2214 |
+
"learning_rate": 2.085422469823584e-05,
|
| 2215 |
+
"loss": 0.9081,
|
| 2216 |
+
"step": 3140
|
| 2217 |
+
},
|
| 2218 |
+
{
|
| 2219 |
+
"epoch": 1.754874651810585,
|
| 2220 |
+
"grad_norm": 4.618974685668945,
|
| 2221 |
+
"learning_rate": 2.0761374187558034e-05,
|
| 2222 |
+
"loss": 0.7226,
|
| 2223 |
+
"step": 3150
|
| 2224 |
+
},
|
| 2225 |
+
{
|
| 2226 |
+
"epoch": 1.7604456824512535,
|
| 2227 |
+
"grad_norm": 3.3900840282440186,
|
| 2228 |
+
"learning_rate": 2.0668523676880223e-05,
|
| 2229 |
+
"loss": 0.719,
|
| 2230 |
+
"step": 3160
|
| 2231 |
+
},
|
| 2232 |
+
{
|
| 2233 |
+
"epoch": 1.766016713091922,
|
| 2234 |
+
"grad_norm": 6.443446159362793,
|
| 2235 |
+
"learning_rate": 2.0575673166202413e-05,
|
| 2236 |
+
"loss": 0.6676,
|
| 2237 |
+
"step": 3170
|
| 2238 |
+
},
|
| 2239 |
+
{
|
| 2240 |
+
"epoch": 1.7715877437325904,
|
| 2241 |
+
"grad_norm": 3.93987774848938,
|
| 2242 |
+
"learning_rate": 2.0482822655524605e-05,
|
| 2243 |
+
"loss": 0.6198,
|
| 2244 |
+
"step": 3180
|
| 2245 |
+
},
|
| 2246 |
+
{
|
| 2247 |
+
"epoch": 1.777158774373259,
|
| 2248 |
+
"grad_norm": 3.811434030532837,
|
| 2249 |
+
"learning_rate": 2.0389972144846798e-05,
|
| 2250 |
+
"loss": 0.7962,
|
| 2251 |
+
"step": 3190
|
| 2252 |
+
},
|
| 2253 |
+
{
|
| 2254 |
+
"epoch": 1.7827298050139275,
|
| 2255 |
+
"grad_norm": 6.011105537414551,
|
| 2256 |
+
"learning_rate": 2.029712163416899e-05,
|
| 2257 |
+
"loss": 0.6282,
|
| 2258 |
+
"step": 3200
|
| 2259 |
+
},
|
| 2260 |
+
{
|
| 2261 |
+
"epoch": 1.7883008356545962,
|
| 2262 |
+
"grad_norm": 4.521935939788818,
|
| 2263 |
+
"learning_rate": 2.020427112349118e-05,
|
| 2264 |
+
"loss": 0.6502,
|
| 2265 |
+
"step": 3210
|
| 2266 |
+
},
|
| 2267 |
+
{
|
| 2268 |
+
"epoch": 1.7938718662952646,
|
| 2269 |
+
"grad_norm": 6.527938365936279,
|
| 2270 |
+
"learning_rate": 2.0111420612813372e-05,
|
| 2271 |
+
"loss": 0.731,
|
| 2272 |
+
"step": 3220
|
| 2273 |
+
},
|
| 2274 |
+
{
|
| 2275 |
+
"epoch": 1.799442896935933,
|
| 2276 |
+
"grad_norm": 3.292177438735962,
|
| 2277 |
+
"learning_rate": 2.001857010213556e-05,
|
| 2278 |
+
"loss": 0.6674,
|
| 2279 |
+
"step": 3230
|
| 2280 |
+
},
|
| 2281 |
+
{
|
| 2282 |
+
"epoch": 1.8050139275766015,
|
| 2283 |
+
"grad_norm": 4.2430548667907715,
|
| 2284 |
+
"learning_rate": 1.9925719591457754e-05,
|
| 2285 |
+
"loss": 0.6192,
|
| 2286 |
+
"step": 3240
|
| 2287 |
+
},
|
| 2288 |
+
{
|
| 2289 |
+
"epoch": 1.8105849582172702,
|
| 2290 |
+
"grad_norm": 2.8606340885162354,
|
| 2291 |
+
"learning_rate": 1.9832869080779946e-05,
|
| 2292 |
+
"loss": 0.724,
|
| 2293 |
+
"step": 3250
|
| 2294 |
+
},
|
| 2295 |
+
{
|
| 2296 |
+
"epoch": 1.8161559888579388,
|
| 2297 |
+
"grad_norm": 5.849732398986816,
|
| 2298 |
+
"learning_rate": 1.9740018570102135e-05,
|
| 2299 |
+
"loss": 0.6134,
|
| 2300 |
+
"step": 3260
|
| 2301 |
+
},
|
| 2302 |
+
{
|
| 2303 |
+
"epoch": 1.8217270194986073,
|
| 2304 |
+
"grad_norm": 2.940549850463867,
|
| 2305 |
+
"learning_rate": 1.9647168059424328e-05,
|
| 2306 |
+
"loss": 0.5696,
|
| 2307 |
+
"step": 3270
|
| 2308 |
+
},
|
| 2309 |
+
{
|
| 2310 |
+
"epoch": 1.8272980501392757,
|
| 2311 |
+
"grad_norm": 5.734061241149902,
|
| 2312 |
+
"learning_rate": 1.955431754874652e-05,
|
| 2313 |
+
"loss": 0.6265,
|
| 2314 |
+
"step": 3280
|
| 2315 |
+
},
|
| 2316 |
+
{
|
| 2317 |
+
"epoch": 1.8328690807799441,
|
| 2318 |
+
"grad_norm": 4.678475379943848,
|
| 2319 |
+
"learning_rate": 1.946146703806871e-05,
|
| 2320 |
+
"loss": 0.543,
|
| 2321 |
+
"step": 3290
|
| 2322 |
+
},
|
| 2323 |
+
{
|
| 2324 |
+
"epoch": 1.8384401114206128,
|
| 2325 |
+
"grad_norm": 5.988973617553711,
|
| 2326 |
+
"learning_rate": 1.9368616527390902e-05,
|
| 2327 |
+
"loss": 0.5986,
|
| 2328 |
+
"step": 3300
|
| 2329 |
+
},
|
| 2330 |
+
{
|
| 2331 |
+
"epoch": 1.8440111420612815,
|
| 2332 |
+
"grad_norm": 5.648441314697266,
|
| 2333 |
+
"learning_rate": 1.927576601671309e-05,
|
| 2334 |
+
"loss": 0.7231,
|
| 2335 |
+
"step": 3310
|
| 2336 |
+
},
|
| 2337 |
+
{
|
| 2338 |
+
"epoch": 1.84958217270195,
|
| 2339 |
+
"grad_norm": 3.596468448638916,
|
| 2340 |
+
"learning_rate": 1.9182915506035284e-05,
|
| 2341 |
+
"loss": 0.7182,
|
| 2342 |
+
"step": 3320
|
| 2343 |
+
},
|
| 2344 |
+
{
|
| 2345 |
+
"epoch": 1.8551532033426184,
|
| 2346 |
+
"grad_norm": 3.6702165603637695,
|
| 2347 |
+
"learning_rate": 1.9090064995357476e-05,
|
| 2348 |
+
"loss": 0.6835,
|
| 2349 |
+
"step": 3330
|
| 2350 |
+
},
|
| 2351 |
+
{
|
| 2352 |
+
"epoch": 1.8607242339832868,
|
| 2353 |
+
"grad_norm": 5.897074222564697,
|
| 2354 |
+
"learning_rate": 1.899721448467967e-05,
|
| 2355 |
+
"loss": 0.6812,
|
| 2356 |
+
"step": 3340
|
| 2357 |
+
},
|
| 2358 |
+
{
|
| 2359 |
+
"epoch": 1.8662952646239555,
|
| 2360 |
+
"grad_norm": 5.111124515533447,
|
| 2361 |
+
"learning_rate": 1.8904363974001858e-05,
|
| 2362 |
+
"loss": 0.7924,
|
| 2363 |
+
"step": 3350
|
| 2364 |
+
},
|
| 2365 |
+
{
|
| 2366 |
+
"epoch": 1.8718662952646241,
|
| 2367 |
+
"grad_norm": 5.206398010253906,
|
| 2368 |
+
"learning_rate": 1.8811513463324047e-05,
|
| 2369 |
+
"loss": 0.6493,
|
| 2370 |
+
"step": 3360
|
| 2371 |
+
},
|
| 2372 |
+
{
|
| 2373 |
+
"epoch": 1.8774373259052926,
|
| 2374 |
+
"grad_norm": 3.4764597415924072,
|
| 2375 |
+
"learning_rate": 1.871866295264624e-05,
|
| 2376 |
+
"loss": 0.6969,
|
| 2377 |
+
"step": 3370
|
| 2378 |
+
},
|
| 2379 |
+
{
|
| 2380 |
+
"epoch": 1.883008356545961,
|
| 2381 |
+
"grad_norm": 3.6830670833587646,
|
| 2382 |
+
"learning_rate": 1.8625812441968432e-05,
|
| 2383 |
+
"loss": 0.6874,
|
| 2384 |
+
"step": 3380
|
| 2385 |
+
},
|
| 2386 |
+
{
|
| 2387 |
+
"epoch": 1.8885793871866294,
|
| 2388 |
+
"grad_norm": 5.803642272949219,
|
| 2389 |
+
"learning_rate": 1.8532961931290625e-05,
|
| 2390 |
+
"loss": 0.5756,
|
| 2391 |
+
"step": 3390
|
| 2392 |
+
},
|
| 2393 |
+
{
|
| 2394 |
+
"epoch": 1.894150417827298,
|
| 2395 |
+
"grad_norm": 5.948879718780518,
|
| 2396 |
+
"learning_rate": 1.8440111420612814e-05,
|
| 2397 |
+
"loss": 0.741,
|
| 2398 |
+
"step": 3400
|
| 2399 |
+
},
|
| 2400 |
+
{
|
| 2401 |
+
"epoch": 1.8997214484679665,
|
| 2402 |
+
"grad_norm": 5.844179630279541,
|
| 2403 |
+
"learning_rate": 1.8347260909935003e-05,
|
| 2404 |
+
"loss": 0.5393,
|
| 2405 |
+
"step": 3410
|
| 2406 |
+
},
|
| 2407 |
+
{
|
| 2408 |
+
"epoch": 1.9052924791086352,
|
| 2409 |
+
"grad_norm": 4.613275051116943,
|
| 2410 |
+
"learning_rate": 1.8254410399257196e-05,
|
| 2411 |
+
"loss": 0.8167,
|
| 2412 |
+
"step": 3420
|
| 2413 |
+
},
|
| 2414 |
+
{
|
| 2415 |
+
"epoch": 1.9108635097493036,
|
| 2416 |
+
"grad_norm": 4.484188079833984,
|
| 2417 |
+
"learning_rate": 1.816155988857939e-05,
|
| 2418 |
+
"loss": 0.6047,
|
| 2419 |
+
"step": 3430
|
| 2420 |
+
},
|
| 2421 |
+
{
|
| 2422 |
+
"epoch": 1.916434540389972,
|
| 2423 |
+
"grad_norm": 5.882885932922363,
|
| 2424 |
+
"learning_rate": 1.806870937790158e-05,
|
| 2425 |
+
"loss": 0.5126,
|
| 2426 |
+
"step": 3440
|
| 2427 |
+
},
|
| 2428 |
+
{
|
| 2429 |
+
"epoch": 1.9220055710306405,
|
| 2430 |
+
"grad_norm": 4.281798839569092,
|
| 2431 |
+
"learning_rate": 1.797585886722377e-05,
|
| 2432 |
+
"loss": 0.6512,
|
| 2433 |
+
"step": 3450
|
| 2434 |
+
},
|
| 2435 |
+
{
|
| 2436 |
+
"epoch": 1.9275766016713092,
|
| 2437 |
+
"grad_norm": 7.347241401672363,
|
| 2438 |
+
"learning_rate": 1.788300835654596e-05,
|
| 2439 |
+
"loss": 0.7092,
|
| 2440 |
+
"step": 3460
|
| 2441 |
+
},
|
| 2442 |
+
{
|
| 2443 |
+
"epoch": 1.9331476323119778,
|
| 2444 |
+
"grad_norm": 5.490599155426025,
|
| 2445 |
+
"learning_rate": 1.7790157845868152e-05,
|
| 2446 |
+
"loss": 0.7738,
|
| 2447 |
+
"step": 3470
|
| 2448 |
+
},
|
| 2449 |
+
{
|
| 2450 |
+
"epoch": 1.9387186629526463,
|
| 2451 |
+
"grad_norm": 4.461576461791992,
|
| 2452 |
+
"learning_rate": 1.7697307335190344e-05,
|
| 2453 |
+
"loss": 0.7116,
|
| 2454 |
+
"step": 3480
|
| 2455 |
+
},
|
| 2456 |
+
{
|
| 2457 |
+
"epoch": 1.9442896935933147,
|
| 2458 |
+
"grad_norm": 3.0554678440093994,
|
| 2459 |
+
"learning_rate": 1.7604456824512537e-05,
|
| 2460 |
+
"loss": 0.7397,
|
| 2461 |
+
"step": 3490
|
| 2462 |
+
},
|
| 2463 |
+
{
|
| 2464 |
+
"epoch": 1.9498607242339832,
|
| 2465 |
+
"grad_norm": 3.393239736557007,
|
| 2466 |
+
"learning_rate": 1.7511606313834726e-05,
|
| 2467 |
+
"loss": 0.7141,
|
| 2468 |
+
"step": 3500
|
| 2469 |
+
},
|
| 2470 |
+
{
|
| 2471 |
+
"epoch": 1.9554317548746518,
|
| 2472 |
+
"grad_norm": 3.1929807662963867,
|
| 2473 |
+
"learning_rate": 1.74280408542247e-05,
|
| 2474 |
+
"loss": 0.6955,
|
| 2475 |
+
"step": 3510
|
| 2476 |
+
},
|
| 2477 |
+
{
|
| 2478 |
+
"epoch": 1.9610027855153205,
|
| 2479 |
+
"grad_norm": 5.299395561218262,
|
| 2480 |
+
"learning_rate": 1.733519034354689e-05,
|
| 2481 |
+
"loss": 0.6491,
|
| 2482 |
+
"step": 3520
|
| 2483 |
+
},
|
| 2484 |
+
{
|
| 2485 |
+
"epoch": 1.966573816155989,
|
| 2486 |
+
"grad_norm": 3.9555628299713135,
|
| 2487 |
+
"learning_rate": 1.7242339832869082e-05,
|
| 2488 |
+
"loss": 0.6156,
|
| 2489 |
+
"step": 3530
|
| 2490 |
+
},
|
| 2491 |
+
{
|
| 2492 |
+
"epoch": 1.9721448467966574,
|
| 2493 |
+
"grad_norm": 4.251757621765137,
|
| 2494 |
+
"learning_rate": 1.7149489322191274e-05,
|
| 2495 |
+
"loss": 0.6155,
|
| 2496 |
+
"step": 3540
|
| 2497 |
+
},
|
| 2498 |
+
{
|
| 2499 |
+
"epoch": 1.9777158774373258,
|
| 2500 |
+
"grad_norm": 7.542901515960693,
|
| 2501 |
+
"learning_rate": 1.7056638811513463e-05,
|
| 2502 |
+
"loss": 0.7173,
|
| 2503 |
+
"step": 3550
|
| 2504 |
+
},
|
| 2505 |
+
{
|
| 2506 |
+
"epoch": 1.9832869080779945,
|
| 2507 |
+
"grad_norm": 4.958390712738037,
|
| 2508 |
+
"learning_rate": 1.6963788300835656e-05,
|
| 2509 |
+
"loss": 0.5184,
|
| 2510 |
+
"step": 3560
|
| 2511 |
+
},
|
| 2512 |
+
{
|
| 2513 |
+
"epoch": 1.988857938718663,
|
| 2514 |
+
"grad_norm": 4.884737491607666,
|
| 2515 |
+
"learning_rate": 1.687093779015785e-05,
|
| 2516 |
+
"loss": 0.6729,
|
| 2517 |
+
"step": 3570
|
| 2518 |
+
},
|
| 2519 |
+
{
|
| 2520 |
+
"epoch": 1.9944289693593316,
|
| 2521 |
+
"grad_norm": 4.648261547088623,
|
| 2522 |
+
"learning_rate": 1.6778087279480038e-05,
|
| 2523 |
+
"loss": 0.6181,
|
| 2524 |
+
"step": 3580
|
| 2525 |
+
},
|
| 2526 |
+
{
|
| 2527 |
+
"epoch": 2.0,
|
| 2528 |
+
"grad_norm": 6.863659381866455,
|
| 2529 |
+
"learning_rate": 1.668523676880223e-05,
|
| 2530 |
+
"loss": 0.5198,
|
| 2531 |
+
"step": 3590
|
| 2532 |
+
},
|
| 2533 |
+
{
|
| 2534 |
+
"epoch": 2.0,
|
| 2535 |
+
"eval_accuracy": 0.7071607690164391,
|
| 2536 |
+
"eval_loss": 0.817263662815094,
|
| 2537 |
+
"eval_runtime": 37.2879,
|
| 2538 |
+
"eval_samples_per_second": 96.251,
|
| 2539 |
+
"eval_steps_per_second": 6.034,
|
| 2540 |
+
"step": 3590
|
| 2541 |
+
},
|
| 2542 |
+
{
|
| 2543 |
+
"epoch": 2.0055710306406684,
|
| 2544 |
+
"grad_norm": 4.615173816680908,
|
| 2545 |
+
"learning_rate": 1.659238625812442e-05,
|
| 2546 |
+
"loss": 0.5817,
|
| 2547 |
+
"step": 3600
|
| 2548 |
+
},
|
| 2549 |
+
{
|
| 2550 |
+
"epoch": 2.011142061281337,
|
| 2551 |
+
"grad_norm": 2.830014944076538,
|
| 2552 |
+
"learning_rate": 1.6499535747446612e-05,
|
| 2553 |
+
"loss": 0.4535,
|
| 2554 |
+
"step": 3610
|
| 2555 |
+
},
|
| 2556 |
+
{
|
| 2557 |
+
"epoch": 2.0167130919220058,
|
| 2558 |
+
"grad_norm": 4.435030460357666,
|
| 2559 |
+
"learning_rate": 1.6406685236768805e-05,
|
| 2560 |
+
"loss": 0.4874,
|
| 2561 |
+
"step": 3620
|
| 2562 |
+
},
|
| 2563 |
+
{
|
| 2564 |
+
"epoch": 2.022284122562674,
|
| 2565 |
+
"grad_norm": 6.543429374694824,
|
| 2566 |
+
"learning_rate": 1.6313834726090994e-05,
|
| 2567 |
+
"loss": 0.5775,
|
| 2568 |
+
"step": 3630
|
| 2569 |
+
},
|
| 2570 |
+
{
|
| 2571 |
+
"epoch": 2.0278551532033426,
|
| 2572 |
+
"grad_norm": 4.525574684143066,
|
| 2573 |
+
"learning_rate": 1.6220984215413186e-05,
|
| 2574 |
+
"loss": 0.6027,
|
| 2575 |
+
"step": 3640
|
| 2576 |
+
},
|
| 2577 |
+
{
|
| 2578 |
+
"epoch": 2.033426183844011,
|
| 2579 |
+
"grad_norm": 10.019755363464355,
|
| 2580 |
+
"learning_rate": 1.6128133704735375e-05,
|
| 2581 |
+
"loss": 0.4922,
|
| 2582 |
+
"step": 3650
|
| 2583 |
+
},
|
| 2584 |
+
{
|
| 2585 |
+
"epoch": 2.0389972144846795,
|
| 2586 |
+
"grad_norm": 4.950735569000244,
|
| 2587 |
+
"learning_rate": 1.6035283194057568e-05,
|
| 2588 |
+
"loss": 0.4555,
|
| 2589 |
+
"step": 3660
|
| 2590 |
+
},
|
| 2591 |
+
{
|
| 2592 |
+
"epoch": 2.0445682451253484,
|
| 2593 |
+
"grad_norm": 2.9464316368103027,
|
| 2594 |
+
"learning_rate": 1.594243268337976e-05,
|
| 2595 |
+
"loss": 0.454,
|
| 2596 |
+
"step": 3670
|
| 2597 |
+
},
|
| 2598 |
+
{
|
| 2599 |
+
"epoch": 2.050139275766017,
|
| 2600 |
+
"grad_norm": 10.776598930358887,
|
| 2601 |
+
"learning_rate": 1.5849582172701953e-05,
|
| 2602 |
+
"loss": 0.4013,
|
| 2603 |
+
"step": 3680
|
| 2604 |
+
},
|
| 2605 |
+
{
|
| 2606 |
+
"epoch": 2.0557103064066853,
|
| 2607 |
+
"grad_norm": 4.557794094085693,
|
| 2608 |
+
"learning_rate": 1.5756731662024142e-05,
|
| 2609 |
+
"loss": 0.4761,
|
| 2610 |
+
"step": 3690
|
| 2611 |
+
},
|
| 2612 |
+
{
|
| 2613 |
+
"epoch": 2.0612813370473537,
|
| 2614 |
+
"grad_norm": 4.7235107421875,
|
| 2615 |
+
"learning_rate": 1.566388115134633e-05,
|
| 2616 |
+
"loss": 0.4825,
|
| 2617 |
+
"step": 3700
|
| 2618 |
+
},
|
| 2619 |
+
{
|
| 2620 |
+
"epoch": 2.066852367688022,
|
| 2621 |
+
"grad_norm": 3.367194414138794,
|
| 2622 |
+
"learning_rate": 1.5571030640668524e-05,
|
| 2623 |
+
"loss": 0.5587,
|
| 2624 |
+
"step": 3710
|
| 2625 |
+
},
|
| 2626 |
+
{
|
| 2627 |
+
"epoch": 2.0724233983286906,
|
| 2628 |
+
"grad_norm": 4.634751319885254,
|
| 2629 |
+
"learning_rate": 1.5478180129990717e-05,
|
| 2630 |
+
"loss": 0.5894,
|
| 2631 |
+
"step": 3720
|
| 2632 |
+
},
|
| 2633 |
+
{
|
| 2634 |
+
"epoch": 2.0779944289693595,
|
| 2635 |
+
"grad_norm": 3.5962271690368652,
|
| 2636 |
+
"learning_rate": 1.538532961931291e-05,
|
| 2637 |
+
"loss": 0.5022,
|
| 2638 |
+
"step": 3730
|
| 2639 |
+
},
|
| 2640 |
+
{
|
| 2641 |
+
"epoch": 2.083565459610028,
|
| 2642 |
+
"grad_norm": 2.4621849060058594,
|
| 2643 |
+
"learning_rate": 1.5292479108635098e-05,
|
| 2644 |
+
"loss": 0.3771,
|
| 2645 |
+
"step": 3740
|
| 2646 |
+
},
|
| 2647 |
+
{
|
| 2648 |
+
"epoch": 2.0891364902506964,
|
| 2649 |
+
"grad_norm": 0.884714663028717,
|
| 2650 |
+
"learning_rate": 1.5199628597957289e-05,
|
| 2651 |
+
"loss": 0.4954,
|
| 2652 |
+
"step": 3750
|
| 2653 |
+
},
|
| 2654 |
+
{
|
| 2655 |
+
"epoch": 2.094707520891365,
|
| 2656 |
+
"grad_norm": 3.478480577468872,
|
| 2657 |
+
"learning_rate": 1.510677808727948e-05,
|
| 2658 |
+
"loss": 0.504,
|
| 2659 |
+
"step": 3760
|
| 2660 |
+
},
|
| 2661 |
+
{
|
| 2662 |
+
"epoch": 2.1002785515320332,
|
| 2663 |
+
"grad_norm": 4.723543643951416,
|
| 2664 |
+
"learning_rate": 1.5013927576601673e-05,
|
| 2665 |
+
"loss": 0.4238,
|
| 2666 |
+
"step": 3770
|
| 2667 |
+
},
|
| 2668 |
+
{
|
| 2669 |
+
"epoch": 2.105849582172702,
|
| 2670 |
+
"grad_norm": 6.865334510803223,
|
| 2671 |
+
"learning_rate": 1.4921077065923863e-05,
|
| 2672 |
+
"loss": 0.5369,
|
| 2673 |
+
"step": 3780
|
| 2674 |
+
},
|
| 2675 |
+
{
|
| 2676 |
+
"epoch": 2.1114206128133706,
|
| 2677 |
+
"grad_norm": 3.348172664642334,
|
| 2678 |
+
"learning_rate": 1.4828226555246056e-05,
|
| 2679 |
+
"loss": 0.4709,
|
| 2680 |
+
"step": 3790
|
| 2681 |
+
},
|
| 2682 |
+
{
|
| 2683 |
+
"epoch": 2.116991643454039,
|
| 2684 |
+
"grad_norm": 3.8873541355133057,
|
| 2685 |
+
"learning_rate": 1.4735376044568247e-05,
|
| 2686 |
+
"loss": 0.3504,
|
| 2687 |
+
"step": 3800
|
| 2688 |
+
},
|
| 2689 |
+
{
|
| 2690 |
+
"epoch": 2.1225626740947074,
|
| 2691 |
+
"grad_norm": 6.476009845733643,
|
| 2692 |
+
"learning_rate": 1.4642525533890436e-05,
|
| 2693 |
+
"loss": 0.378,
|
| 2694 |
+
"step": 3810
|
| 2695 |
+
},
|
| 2696 |
+
{
|
| 2697 |
+
"epoch": 2.128133704735376,
|
| 2698 |
+
"grad_norm": 4.0402445793151855,
|
| 2699 |
+
"learning_rate": 1.4549675023212628e-05,
|
| 2700 |
+
"loss": 0.4167,
|
| 2701 |
+
"step": 3820
|
| 2702 |
+
},
|
| 2703 |
+
{
|
| 2704 |
+
"epoch": 2.1337047353760448,
|
| 2705 |
+
"grad_norm": 5.197554588317871,
|
| 2706 |
+
"learning_rate": 1.445682451253482e-05,
|
| 2707 |
+
"loss": 0.5053,
|
| 2708 |
+
"step": 3830
|
| 2709 |
+
},
|
| 2710 |
+
{
|
| 2711 |
+
"epoch": 2.139275766016713,
|
| 2712 |
+
"grad_norm": 3.450927495956421,
|
| 2713 |
+
"learning_rate": 1.4363974001857012e-05,
|
| 2714 |
+
"loss": 0.4532,
|
| 2715 |
+
"step": 3840
|
| 2716 |
+
},
|
| 2717 |
+
{
|
| 2718 |
+
"epoch": 2.1448467966573816,
|
| 2719 |
+
"grad_norm": 4.431534767150879,
|
| 2720 |
+
"learning_rate": 1.4271123491179203e-05,
|
| 2721 |
+
"loss": 0.5658,
|
| 2722 |
+
"step": 3850
|
| 2723 |
+
},
|
| 2724 |
+
{
|
| 2725 |
+
"epoch": 2.15041782729805,
|
| 2726 |
+
"grad_norm": 3.2116923332214355,
|
| 2727 |
+
"learning_rate": 1.4178272980501395e-05,
|
| 2728 |
+
"loss": 0.3628,
|
| 2729 |
+
"step": 3860
|
| 2730 |
+
},
|
| 2731 |
+
{
|
| 2732 |
+
"epoch": 2.1559888579387185,
|
| 2733 |
+
"grad_norm": 3.2377572059631348,
|
| 2734 |
+
"learning_rate": 1.4085422469823584e-05,
|
| 2735 |
+
"loss": 0.3513,
|
| 2736 |
+
"step": 3870
|
| 2737 |
+
},
|
| 2738 |
+
{
|
| 2739 |
+
"epoch": 2.1615598885793874,
|
| 2740 |
+
"grad_norm": 6.522520065307617,
|
| 2741 |
+
"learning_rate": 1.3992571959145775e-05,
|
| 2742 |
+
"loss": 0.4474,
|
| 2743 |
+
"step": 3880
|
| 2744 |
+
},
|
| 2745 |
+
{
|
| 2746 |
+
"epoch": 2.167130919220056,
|
| 2747 |
+
"grad_norm": 4.152089595794678,
|
| 2748 |
+
"learning_rate": 1.3899721448467968e-05,
|
| 2749 |
+
"loss": 0.4717,
|
| 2750 |
+
"step": 3890
|
| 2751 |
+
},
|
| 2752 |
+
{
|
| 2753 |
+
"epoch": 2.1727019498607243,
|
| 2754 |
+
"grad_norm": 3.9194087982177734,
|
| 2755 |
+
"learning_rate": 1.3806870937790159e-05,
|
| 2756 |
+
"loss": 0.4681,
|
| 2757 |
+
"step": 3900
|
| 2758 |
+
},
|
| 2759 |
+
{
|
| 2760 |
+
"epoch": 2.1782729805013927,
|
| 2761 |
+
"grad_norm": 3.955049991607666,
|
| 2762 |
+
"learning_rate": 1.3714020427112351e-05,
|
| 2763 |
+
"loss": 0.4825,
|
| 2764 |
+
"step": 3910
|
| 2765 |
+
},
|
| 2766 |
+
{
|
| 2767 |
+
"epoch": 2.183844011142061,
|
| 2768 |
+
"grad_norm": 7.73003625869751,
|
| 2769 |
+
"learning_rate": 1.362116991643454e-05,
|
| 2770 |
+
"loss": 0.4505,
|
| 2771 |
+
"step": 3920
|
| 2772 |
+
},
|
| 2773 |
+
{
|
| 2774 |
+
"epoch": 2.1894150417827296,
|
| 2775 |
+
"grad_norm": 7.201216220855713,
|
| 2776 |
+
"learning_rate": 1.3528319405756731e-05,
|
| 2777 |
+
"loss": 0.5176,
|
| 2778 |
+
"step": 3930
|
| 2779 |
+
},
|
| 2780 |
+
{
|
| 2781 |
+
"epoch": 2.1949860724233985,
|
| 2782 |
+
"grad_norm": 4.639294624328613,
|
| 2783 |
+
"learning_rate": 1.3435468895078924e-05,
|
| 2784 |
+
"loss": 0.4535,
|
| 2785 |
+
"step": 3940
|
| 2786 |
+
},
|
| 2787 |
+
{
|
| 2788 |
+
"epoch": 2.200557103064067,
|
| 2789 |
+
"grad_norm": 4.728760242462158,
|
| 2790 |
+
"learning_rate": 1.3342618384401115e-05,
|
| 2791 |
+
"loss": 0.5659,
|
| 2792 |
+
"step": 3950
|
| 2793 |
+
},
|
| 2794 |
+
{
|
| 2795 |
+
"epoch": 2.2061281337047354,
|
| 2796 |
+
"grad_norm": 2.1953437328338623,
|
| 2797 |
+
"learning_rate": 1.3249767873723307e-05,
|
| 2798 |
+
"loss": 0.3706,
|
| 2799 |
+
"step": 3960
|
| 2800 |
+
},
|
| 2801 |
+
{
|
| 2802 |
+
"epoch": 2.211699164345404,
|
| 2803 |
+
"grad_norm": 2.9534456729888916,
|
| 2804 |
+
"learning_rate": 1.3156917363045498e-05,
|
| 2805 |
+
"loss": 0.5308,
|
| 2806 |
+
"step": 3970
|
| 2807 |
+
},
|
| 2808 |
+
{
|
| 2809 |
+
"epoch": 2.2172701949860723,
|
| 2810 |
+
"grad_norm": 6.660586833953857,
|
| 2811 |
+
"learning_rate": 1.3064066852367687e-05,
|
| 2812 |
+
"loss": 0.4657,
|
| 2813 |
+
"step": 3980
|
| 2814 |
+
},
|
| 2815 |
+
{
|
| 2816 |
+
"epoch": 2.222841225626741,
|
| 2817 |
+
"grad_norm": 3.0846714973449707,
|
| 2818 |
+
"learning_rate": 1.297121634168988e-05,
|
| 2819 |
+
"loss": 0.4446,
|
| 2820 |
+
"step": 3990
|
| 2821 |
+
},
|
| 2822 |
+
{
|
| 2823 |
+
"epoch": 2.2284122562674096,
|
| 2824 |
+
"grad_norm": 9.60133171081543,
|
| 2825 |
+
"learning_rate": 1.287836583101207e-05,
|
| 2826 |
+
"loss": 0.5949,
|
| 2827 |
+
"step": 4000
|
| 2828 |
+
},
|
| 2829 |
+
{
|
| 2830 |
+
"epoch": 2.233983286908078,
|
| 2831 |
+
"grad_norm": 2.2764580249786377,
|
| 2832 |
+
"learning_rate": 1.2785515320334263e-05,
|
| 2833 |
+
"loss": 0.4514,
|
| 2834 |
+
"step": 4010
|
| 2835 |
+
},
|
| 2836 |
+
{
|
| 2837 |
+
"epoch": 2.2395543175487465,
|
| 2838 |
+
"grad_norm": 2.598289728164673,
|
| 2839 |
+
"learning_rate": 1.2692664809656454e-05,
|
| 2840 |
+
"loss": 0.4929,
|
| 2841 |
+
"step": 4020
|
| 2842 |
+
},
|
| 2843 |
+
{
|
| 2844 |
+
"epoch": 2.245125348189415,
|
| 2845 |
+
"grad_norm": 2.7438085079193115,
|
| 2846 |
+
"learning_rate": 1.2599814298978647e-05,
|
| 2847 |
+
"loss": 0.5142,
|
| 2848 |
+
"step": 4030
|
| 2849 |
+
},
|
| 2850 |
+
{
|
| 2851 |
+
"epoch": 2.2506963788300833,
|
| 2852 |
+
"grad_norm": 2.9122653007507324,
|
| 2853 |
+
"learning_rate": 1.2506963788300836e-05,
|
| 2854 |
+
"loss": 0.4944,
|
| 2855 |
+
"step": 4040
|
| 2856 |
+
},
|
| 2857 |
+
{
|
| 2858 |
+
"epoch": 2.256267409470752,
|
| 2859 |
+
"grad_norm": 4.093932151794434,
|
| 2860 |
+
"learning_rate": 1.2414113277623028e-05,
|
| 2861 |
+
"loss": 0.4334,
|
| 2862 |
+
"step": 4050
|
| 2863 |
+
},
|
| 2864 |
+
{
|
| 2865 |
+
"epoch": 2.2618384401114207,
|
| 2866 |
+
"grad_norm": 5.076513290405273,
|
| 2867 |
+
"learning_rate": 1.232126276694522e-05,
|
| 2868 |
+
"loss": 0.4213,
|
| 2869 |
+
"step": 4060
|
| 2870 |
+
},
|
| 2871 |
+
{
|
| 2872 |
+
"epoch": 2.267409470752089,
|
| 2873 |
+
"grad_norm": 3.2467005252838135,
|
| 2874 |
+
"learning_rate": 1.222841225626741e-05,
|
| 2875 |
+
"loss": 0.6094,
|
| 2876 |
+
"step": 4070
|
| 2877 |
+
},
|
| 2878 |
+
{
|
| 2879 |
+
"epoch": 2.2729805013927575,
|
| 2880 |
+
"grad_norm": 2.402123212814331,
|
| 2881 |
+
"learning_rate": 1.2135561745589603e-05,
|
| 2882 |
+
"loss": 0.4469,
|
| 2883 |
+
"step": 4080
|
| 2884 |
+
},
|
| 2885 |
+
{
|
| 2886 |
+
"epoch": 2.2785515320334264,
|
| 2887 |
+
"grad_norm": 4.679557800292969,
|
| 2888 |
+
"learning_rate": 1.2042711234911792e-05,
|
| 2889 |
+
"loss": 0.4029,
|
| 2890 |
+
"step": 4090
|
| 2891 |
+
},
|
| 2892 |
+
{
|
| 2893 |
+
"epoch": 2.284122562674095,
|
| 2894 |
+
"grad_norm": 1.4909316301345825,
|
| 2895 |
+
"learning_rate": 1.1949860724233984e-05,
|
| 2896 |
+
"loss": 0.3351,
|
| 2897 |
+
"step": 4100
|
| 2898 |
+
},
|
| 2899 |
+
{
|
| 2900 |
+
"epoch": 2.2896935933147633,
|
| 2901 |
+
"grad_norm": 6.870358467102051,
|
| 2902 |
+
"learning_rate": 1.1857010213556175e-05,
|
| 2903 |
+
"loss": 0.5222,
|
| 2904 |
+
"step": 4110
|
| 2905 |
+
},
|
| 2906 |
+
{
|
| 2907 |
+
"epoch": 2.2952646239554317,
|
| 2908 |
+
"grad_norm": 1.7165311574935913,
|
| 2909 |
+
"learning_rate": 1.1764159702878366e-05,
|
| 2910 |
+
"loss": 0.326,
|
| 2911 |
+
"step": 4120
|
| 2912 |
+
},
|
| 2913 |
+
{
|
| 2914 |
+
"epoch": 2.3008356545961,
|
| 2915 |
+
"grad_norm": 5.359385967254639,
|
| 2916 |
+
"learning_rate": 1.1671309192200559e-05,
|
| 2917 |
+
"loss": 0.36,
|
| 2918 |
+
"step": 4130
|
| 2919 |
+
},
|
| 2920 |
+
{
|
| 2921 |
+
"epoch": 2.3064066852367686,
|
| 2922 |
+
"grad_norm": 4.74082612991333,
|
| 2923 |
+
"learning_rate": 1.1578458681522748e-05,
|
| 2924 |
+
"loss": 0.5068,
|
| 2925 |
+
"step": 4140
|
| 2926 |
+
},
|
| 2927 |
+
{
|
| 2928 |
+
"epoch": 2.3119777158774375,
|
| 2929 |
+
"grad_norm": 2.6061348915100098,
|
| 2930 |
+
"learning_rate": 1.148560817084494e-05,
|
| 2931 |
+
"loss": 0.4599,
|
| 2932 |
+
"step": 4150
|
| 2933 |
+
},
|
| 2934 |
+
{
|
| 2935 |
+
"epoch": 2.317548746518106,
|
| 2936 |
+
"grad_norm": 6.639983177185059,
|
| 2937 |
+
"learning_rate": 1.1392757660167131e-05,
|
| 2938 |
+
"loss": 0.5885,
|
| 2939 |
+
"step": 4160
|
| 2940 |
+
},
|
| 2941 |
+
{
|
| 2942 |
+
"epoch": 2.3231197771587744,
|
| 2943 |
+
"grad_norm": 3.9153246879577637,
|
| 2944 |
+
"learning_rate": 1.1299907149489322e-05,
|
| 2945 |
+
"loss": 0.418,
|
| 2946 |
+
"step": 4170
|
| 2947 |
+
},
|
| 2948 |
+
{
|
| 2949 |
+
"epoch": 2.328690807799443,
|
| 2950 |
+
"grad_norm": 7.114092826843262,
|
| 2951 |
+
"learning_rate": 1.1207056638811515e-05,
|
| 2952 |
+
"loss": 0.4293,
|
| 2953 |
+
"step": 4180
|
| 2954 |
+
},
|
| 2955 |
+
{
|
| 2956 |
+
"epoch": 2.3342618384401113,
|
| 2957 |
+
"grad_norm": 3.978114366531372,
|
| 2958 |
+
"learning_rate": 1.1114206128133705e-05,
|
| 2959 |
+
"loss": 0.4194,
|
| 2960 |
+
"step": 4190
|
| 2961 |
+
},
|
| 2962 |
+
{
|
| 2963 |
+
"epoch": 2.33983286908078,
|
| 2964 |
+
"grad_norm": 3.607412099838257,
|
| 2965 |
+
"learning_rate": 1.1021355617455896e-05,
|
| 2966 |
+
"loss": 0.4783,
|
| 2967 |
+
"step": 4200
|
| 2968 |
+
},
|
| 2969 |
+
{
|
| 2970 |
+
"epoch": 2.3454038997214486,
|
| 2971 |
+
"grad_norm": 6.030869960784912,
|
| 2972 |
+
"learning_rate": 1.0928505106778087e-05,
|
| 2973 |
+
"loss": 0.421,
|
| 2974 |
+
"step": 4210
|
| 2975 |
+
},
|
| 2976 |
+
{
|
| 2977 |
+
"epoch": 2.350974930362117,
|
| 2978 |
+
"grad_norm": 2.8264944553375244,
|
| 2979 |
+
"learning_rate": 1.083565459610028e-05,
|
| 2980 |
+
"loss": 0.4424,
|
| 2981 |
+
"step": 4220
|
| 2982 |
+
},
|
| 2983 |
+
{
|
| 2984 |
+
"epoch": 2.3565459610027855,
|
| 2985 |
+
"grad_norm": 3.267326593399048,
|
| 2986 |
+
"learning_rate": 1.074280408542247e-05,
|
| 2987 |
+
"loss": 0.4451,
|
| 2988 |
+
"step": 4230
|
| 2989 |
+
},
|
| 2990 |
+
{
|
| 2991 |
+
"epoch": 2.362116991643454,
|
| 2992 |
+
"grad_norm": 3.6425423622131348,
|
| 2993 |
+
"learning_rate": 1.0649953574744661e-05,
|
| 2994 |
+
"loss": 0.5231,
|
| 2995 |
+
"step": 4240
|
| 2996 |
+
},
|
| 2997 |
+
{
|
| 2998 |
+
"epoch": 2.3676880222841223,
|
| 2999 |
+
"grad_norm": 3.3133020401000977,
|
| 3000 |
+
"learning_rate": 1.0557103064066854e-05,
|
| 3001 |
+
"loss": 0.5509,
|
| 3002 |
+
"step": 4250
|
| 3003 |
+
},
|
| 3004 |
+
{
|
| 3005 |
+
"epoch": 2.3732590529247912,
|
| 3006 |
+
"grad_norm": 3.444788694381714,
|
| 3007 |
+
"learning_rate": 1.0464252553389043e-05,
|
| 3008 |
+
"loss": 0.2895,
|
| 3009 |
+
"step": 4260
|
| 3010 |
+
},
|
| 3011 |
+
{
|
| 3012 |
+
"epoch": 2.3788300835654597,
|
| 3013 |
+
"grad_norm": 7.917379856109619,
|
| 3014 |
+
"learning_rate": 1.0371402042711236e-05,
|
| 3015 |
+
"loss": 0.5842,
|
| 3016 |
+
"step": 4270
|
| 3017 |
+
},
|
| 3018 |
+
{
|
| 3019 |
+
"epoch": 2.384401114206128,
|
| 3020 |
+
"grad_norm": 4.689010143280029,
|
| 3021 |
+
"learning_rate": 1.0278551532033427e-05,
|
| 3022 |
+
"loss": 0.467,
|
| 3023 |
+
"step": 4280
|
| 3024 |
+
},
|
| 3025 |
+
{
|
| 3026 |
+
"epoch": 2.3899721448467965,
|
| 3027 |
+
"grad_norm": 4.501764297485352,
|
| 3028 |
+
"learning_rate": 1.0185701021355617e-05,
|
| 3029 |
+
"loss": 0.4238,
|
| 3030 |
+
"step": 4290
|
| 3031 |
+
},
|
| 3032 |
+
{
|
| 3033 |
+
"epoch": 2.3955431754874654,
|
| 3034 |
+
"grad_norm": 4.01366662979126,
|
| 3035 |
+
"learning_rate": 1.009285051067781e-05,
|
| 3036 |
+
"loss": 0.4781,
|
| 3037 |
+
"step": 4300
|
| 3038 |
+
},
|
| 3039 |
+
{
|
| 3040 |
+
"epoch": 2.401114206128134,
|
| 3041 |
+
"grad_norm": 11.674251556396484,
|
| 3042 |
+
"learning_rate": 1e-05,
|
| 3043 |
+
"loss": 0.403,
|
| 3044 |
+
"step": 4310
|
| 3045 |
+
},
|
| 3046 |
+
{
|
| 3047 |
+
"epoch": 2.4066852367688023,
|
| 3048 |
+
"grad_norm": 5.943558692932129,
|
| 3049 |
+
"learning_rate": 9.907149489322192e-06,
|
| 3050 |
+
"loss": 0.3621,
|
| 3051 |
+
"step": 4320
|
| 3052 |
+
},
|
| 3053 |
+
{
|
| 3054 |
+
"epoch": 2.4122562674094707,
|
| 3055 |
+
"grad_norm": 1.9158827066421509,
|
| 3056 |
+
"learning_rate": 9.814298978644383e-06,
|
| 3057 |
+
"loss": 0.3801,
|
| 3058 |
+
"step": 4330
|
| 3059 |
+
},
|
| 3060 |
+
{
|
| 3061 |
+
"epoch": 2.417827298050139,
|
| 3062 |
+
"grad_norm": 3.426053047180176,
|
| 3063 |
+
"learning_rate": 9.721448467966575e-06,
|
| 3064 |
+
"loss": 0.419,
|
| 3065 |
+
"step": 4340
|
| 3066 |
+
},
|
| 3067 |
+
{
|
| 3068 |
+
"epoch": 2.4233983286908076,
|
| 3069 |
+
"grad_norm": 3.975104570388794,
|
| 3070 |
+
"learning_rate": 9.628597957288766e-06,
|
| 3071 |
+
"loss": 0.414,
|
| 3072 |
+
"step": 4350
|
| 3073 |
+
},
|
| 3074 |
+
{
|
| 3075 |
+
"epoch": 2.4289693593314765,
|
| 3076 |
+
"grad_norm": 2.1982619762420654,
|
| 3077 |
+
"learning_rate": 9.535747446610957e-06,
|
| 3078 |
+
"loss": 0.4647,
|
| 3079 |
+
"step": 4360
|
| 3080 |
+
},
|
| 3081 |
+
{
|
| 3082 |
+
"epoch": 2.434540389972145,
|
| 3083 |
+
"grad_norm": 4.273013591766357,
|
| 3084 |
+
"learning_rate": 9.44289693593315e-06,
|
| 3085 |
+
"loss": 0.5589,
|
| 3086 |
+
"step": 4370
|
| 3087 |
+
},
|
| 3088 |
+
{
|
| 3089 |
+
"epoch": 2.4401114206128134,
|
| 3090 |
+
"grad_norm": 3.543038845062256,
|
| 3091 |
+
"learning_rate": 9.350046425255339e-06,
|
| 3092 |
+
"loss": 0.4927,
|
| 3093 |
+
"step": 4380
|
| 3094 |
+
},
|
| 3095 |
+
{
|
| 3096 |
+
"epoch": 2.445682451253482,
|
| 3097 |
+
"grad_norm": 3.844630718231201,
|
| 3098 |
+
"learning_rate": 9.257195914577531e-06,
|
| 3099 |
+
"loss": 0.3665,
|
| 3100 |
+
"step": 4390
|
| 3101 |
+
},
|
| 3102 |
+
{
|
| 3103 |
+
"epoch": 2.4512534818941503,
|
| 3104 |
+
"grad_norm": 5.011111736297607,
|
| 3105 |
+
"learning_rate": 9.164345403899722e-06,
|
| 3106 |
+
"loss": 0.4216,
|
| 3107 |
+
"step": 4400
|
| 3108 |
+
},
|
| 3109 |
+
{
|
| 3110 |
+
"epoch": 2.456824512534819,
|
| 3111 |
+
"grad_norm": 5.382537841796875,
|
| 3112 |
+
"learning_rate": 9.071494893221913e-06,
|
| 3113 |
+
"loss": 0.4904,
|
| 3114 |
+
"step": 4410
|
| 3115 |
+
},
|
| 3116 |
+
{
|
| 3117 |
+
"epoch": 2.4623955431754876,
|
| 3118 |
+
"grad_norm": 2.391098976135254,
|
| 3119 |
+
"learning_rate": 8.978644382544105e-06,
|
| 3120 |
+
"loss": 0.4759,
|
| 3121 |
+
"step": 4420
|
| 3122 |
+
},
|
| 3123 |
+
{
|
| 3124 |
+
"epoch": 2.467966573816156,
|
| 3125 |
+
"grad_norm": 3.50219464302063,
|
| 3126 |
+
"learning_rate": 8.885793871866294e-06,
|
| 3127 |
+
"loss": 0.4777,
|
| 3128 |
+
"step": 4430
|
| 3129 |
+
},
|
| 3130 |
+
{
|
| 3131 |
+
"epoch": 2.4735376044568245,
|
| 3132 |
+
"grad_norm": 4.964571475982666,
|
| 3133 |
+
"learning_rate": 8.792943361188487e-06,
|
| 3134 |
+
"loss": 0.3474,
|
| 3135 |
+
"step": 4440
|
| 3136 |
+
},
|
| 3137 |
+
{
|
| 3138 |
+
"epoch": 2.479108635097493,
|
| 3139 |
+
"grad_norm": 5.0892510414123535,
|
| 3140 |
+
"learning_rate": 8.700092850510678e-06,
|
| 3141 |
+
"loss": 0.3845,
|
| 3142 |
+
"step": 4450
|
| 3143 |
+
},
|
| 3144 |
+
{
|
| 3145 |
+
"epoch": 2.4846796657381613,
|
| 3146 |
+
"grad_norm": 6.2226362228393555,
|
| 3147 |
+
"learning_rate": 8.607242339832869e-06,
|
| 3148 |
+
"loss": 0.5149,
|
| 3149 |
+
"step": 4460
|
| 3150 |
+
},
|
| 3151 |
+
{
|
| 3152 |
+
"epoch": 2.4902506963788302,
|
| 3153 |
+
"grad_norm": 5.676084995269775,
|
| 3154 |
+
"learning_rate": 8.514391829155061e-06,
|
| 3155 |
+
"loss": 0.3087,
|
| 3156 |
+
"step": 4470
|
| 3157 |
+
},
|
| 3158 |
+
{
|
| 3159 |
+
"epoch": 2.4958217270194987,
|
| 3160 |
+
"grad_norm": 5.1531982421875,
|
| 3161 |
+
"learning_rate": 8.421541318477252e-06,
|
| 3162 |
+
"loss": 0.5312,
|
| 3163 |
+
"step": 4480
|
| 3164 |
+
},
|
| 3165 |
+
{
|
| 3166 |
+
"epoch": 2.501392757660167,
|
| 3167 |
+
"grad_norm": 4.618714332580566,
|
| 3168 |
+
"learning_rate": 8.328690807799443e-06,
|
| 3169 |
+
"loss": 0.4738,
|
| 3170 |
+
"step": 4490
|
| 3171 |
+
},
|
| 3172 |
+
{
|
| 3173 |
+
"epoch": 2.5069637883008355,
|
| 3174 |
+
"grad_norm": 3.6886181831359863,
|
| 3175 |
+
"learning_rate": 8.235840297121634e-06,
|
| 3176 |
+
"loss": 0.5054,
|
| 3177 |
+
"step": 4500
|
| 3178 |
+
},
|
| 3179 |
+
{
|
| 3180 |
+
"epoch": 2.5125348189415044,
|
| 3181 |
+
"grad_norm": 6.665517330169678,
|
| 3182 |
+
"learning_rate": 8.142989786443826e-06,
|
| 3183 |
+
"loss": 0.4265,
|
| 3184 |
+
"step": 4510
|
| 3185 |
+
},
|
| 3186 |
+
{
|
| 3187 |
+
"epoch": 2.518105849582173,
|
| 3188 |
+
"grad_norm": 4.075329303741455,
|
| 3189 |
+
"learning_rate": 8.050139275766017e-06,
|
| 3190 |
+
"loss": 0.414,
|
| 3191 |
+
"step": 4520
|
| 3192 |
+
},
|
| 3193 |
+
{
|
| 3194 |
+
"epoch": 2.5236768802228413,
|
| 3195 |
+
"grad_norm": 4.333959579467773,
|
| 3196 |
+
"learning_rate": 7.957288765088208e-06,
|
| 3197 |
+
"loss": 0.4542,
|
| 3198 |
+
"step": 4530
|
| 3199 |
+
},
|
| 3200 |
+
{
|
| 3201 |
+
"epoch": 2.5292479108635098,
|
| 3202 |
+
"grad_norm": 4.7477827072143555,
|
| 3203 |
+
"learning_rate": 7.8644382544104e-06,
|
| 3204 |
+
"loss": 0.4223,
|
| 3205 |
+
"step": 4540
|
| 3206 |
+
},
|
| 3207 |
+
{
|
| 3208 |
+
"epoch": 2.534818941504178,
|
| 3209 |
+
"grad_norm": 4.310934066772461,
|
| 3210 |
+
"learning_rate": 7.77158774373259e-06,
|
| 3211 |
+
"loss": 0.342,
|
| 3212 |
+
"step": 4550
|
| 3213 |
+
},
|
| 3214 |
+
{
|
| 3215 |
+
"epoch": 2.5403899721448466,
|
| 3216 |
+
"grad_norm": 3.5395619869232178,
|
| 3217 |
+
"learning_rate": 7.678737233054782e-06,
|
| 3218 |
+
"loss": 0.4755,
|
| 3219 |
+
"step": 4560
|
| 3220 |
+
},
|
| 3221 |
+
{
|
| 3222 |
+
"epoch": 2.545961002785515,
|
| 3223 |
+
"grad_norm": 4.999756813049316,
|
| 3224 |
+
"learning_rate": 7.585886722376974e-06,
|
| 3225 |
+
"loss": 0.4619,
|
| 3226 |
+
"step": 4570
|
| 3227 |
+
},
|
| 3228 |
+
{
|
| 3229 |
+
"epoch": 2.551532033426184,
|
| 3230 |
+
"grad_norm": 5.0525383949279785,
|
| 3231 |
+
"learning_rate": 7.493036211699164e-06,
|
| 3232 |
+
"loss": 0.4846,
|
| 3233 |
+
"step": 4580
|
| 3234 |
+
},
|
| 3235 |
+
{
|
| 3236 |
+
"epoch": 2.5571030640668524,
|
| 3237 |
+
"grad_norm": 8.564767837524414,
|
| 3238 |
+
"learning_rate": 7.400185701021356e-06,
|
| 3239 |
+
"loss": 0.4261,
|
| 3240 |
+
"step": 4590
|
| 3241 |
+
},
|
| 3242 |
+
{
|
| 3243 |
+
"epoch": 2.562674094707521,
|
| 3244 |
+
"grad_norm": 4.90235710144043,
|
| 3245 |
+
"learning_rate": 7.3073351903435475e-06,
|
| 3246 |
+
"loss": 0.435,
|
| 3247 |
+
"step": 4600
|
| 3248 |
+
},
|
| 3249 |
+
{
|
| 3250 |
+
"epoch": 2.5682451253481893,
|
| 3251 |
+
"grad_norm": 5.1071672439575195,
|
| 3252 |
+
"learning_rate": 7.214484679665738e-06,
|
| 3253 |
+
"loss": 0.4378,
|
| 3254 |
+
"step": 4610
|
| 3255 |
+
},
|
| 3256 |
+
{
|
| 3257 |
+
"epoch": 2.573816155988858,
|
| 3258 |
+
"grad_norm": 4.659866809844971,
|
| 3259 |
+
"learning_rate": 7.12163416898793e-06,
|
| 3260 |
+
"loss": 0.4755,
|
| 3261 |
+
"step": 4620
|
| 3262 |
+
},
|
| 3263 |
+
{
|
| 3264 |
+
"epoch": 2.5793871866295266,
|
| 3265 |
+
"grad_norm": 6.740070343017578,
|
| 3266 |
+
"learning_rate": 7.028783658310122e-06,
|
| 3267 |
+
"loss": 0.5263,
|
| 3268 |
+
"step": 4630
|
| 3269 |
+
},
|
| 3270 |
+
{
|
| 3271 |
+
"epoch": 2.584958217270195,
|
| 3272 |
+
"grad_norm": 7.245567321777344,
|
| 3273 |
+
"learning_rate": 6.935933147632312e-06,
|
| 3274 |
+
"loss": 0.4753,
|
| 3275 |
+
"step": 4640
|
| 3276 |
+
},
|
| 3277 |
+
{
|
| 3278 |
+
"epoch": 2.5905292479108635,
|
| 3279 |
+
"grad_norm": 3.481055736541748,
|
| 3280 |
+
"learning_rate": 6.8430826369545035e-06,
|
| 3281 |
+
"loss": 0.334,
|
| 3282 |
+
"step": 4650
|
| 3283 |
+
},
|
| 3284 |
+
{
|
| 3285 |
+
"epoch": 2.596100278551532,
|
| 3286 |
+
"grad_norm": 9.103506088256836,
|
| 3287 |
+
"learning_rate": 6.750232126276695e-06,
|
| 3288 |
+
"loss": 0.5612,
|
| 3289 |
+
"step": 4660
|
| 3290 |
+
},
|
| 3291 |
+
{
|
| 3292 |
+
"epoch": 2.6016713091922004,
|
| 3293 |
+
"grad_norm": 2.4863336086273193,
|
| 3294 |
+
"learning_rate": 6.657381615598886e-06,
|
| 3295 |
+
"loss": 0.4572,
|
| 3296 |
+
"step": 4670
|
| 3297 |
+
},
|
| 3298 |
+
{
|
| 3299 |
+
"epoch": 2.6072423398328692,
|
| 3300 |
+
"grad_norm": 3.1609058380126953,
|
| 3301 |
+
"learning_rate": 6.564531104921078e-06,
|
| 3302 |
+
"loss": 0.4082,
|
| 3303 |
+
"step": 4680
|
| 3304 |
+
},
|
| 3305 |
+
{
|
| 3306 |
+
"epoch": 2.6128133704735377,
|
| 3307 |
+
"grad_norm": 4.247745037078857,
|
| 3308 |
+
"learning_rate": 6.4716805942432695e-06,
|
| 3309 |
+
"loss": 0.5278,
|
| 3310 |
+
"step": 4690
|
| 3311 |
+
},
|
| 3312 |
+
{
|
| 3313 |
+
"epoch": 2.618384401114206,
|
| 3314 |
+
"grad_norm": 5.853703022003174,
|
| 3315 |
+
"learning_rate": 6.3788300835654595e-06,
|
| 3316 |
+
"loss": 0.4127,
|
| 3317 |
+
"step": 4700
|
| 3318 |
+
},
|
| 3319 |
+
{
|
| 3320 |
+
"epoch": 2.6239554317548746,
|
| 3321 |
+
"grad_norm": 4.09820032119751,
|
| 3322 |
+
"learning_rate": 6.285979572887651e-06,
|
| 3323 |
+
"loss": 0.399,
|
| 3324 |
+
"step": 4710
|
| 3325 |
+
},
|
| 3326 |
+
{
|
| 3327 |
+
"epoch": 2.6295264623955434,
|
| 3328 |
+
"grad_norm": 4.088954925537109,
|
| 3329 |
+
"learning_rate": 6.193129062209842e-06,
|
| 3330 |
+
"loss": 0.3394,
|
| 3331 |
+
"step": 4720
|
| 3332 |
+
},
|
| 3333 |
+
{
|
| 3334 |
+
"epoch": 2.635097493036212,
|
| 3335 |
+
"grad_norm": 5.091104984283447,
|
| 3336 |
+
"learning_rate": 6.100278551532034e-06,
|
| 3337 |
+
"loss": 0.4218,
|
| 3338 |
+
"step": 4730
|
| 3339 |
+
},
|
| 3340 |
+
{
|
| 3341 |
+
"epoch": 2.6406685236768803,
|
| 3342 |
+
"grad_norm": 4.649893760681152,
|
| 3343 |
+
"learning_rate": 6.0074280408542255e-06,
|
| 3344 |
+
"loss": 0.4801,
|
| 3345 |
+
"step": 4740
|
| 3346 |
+
},
|
| 3347 |
+
{
|
| 3348 |
+
"epoch": 2.6462395543175488,
|
| 3349 |
+
"grad_norm": 6.470804691314697,
|
| 3350 |
+
"learning_rate": 5.914577530176416e-06,
|
| 3351 |
+
"loss": 0.5307,
|
| 3352 |
+
"step": 4750
|
| 3353 |
+
},
|
| 3354 |
+
{
|
| 3355 |
+
"epoch": 2.651810584958217,
|
| 3356 |
+
"grad_norm": 3.143728017807007,
|
| 3357 |
+
"learning_rate": 5.821727019498607e-06,
|
| 3358 |
+
"loss": 0.3806,
|
| 3359 |
+
"step": 4760
|
| 3360 |
+
},
|
| 3361 |
+
{
|
| 3362 |
+
"epoch": 2.6573816155988856,
|
| 3363 |
+
"grad_norm": 3.0394294261932373,
|
| 3364 |
+
"learning_rate": 5.728876508820799e-06,
|
| 3365 |
+
"loss": 0.4565,
|
| 3366 |
+
"step": 4770
|
| 3367 |
+
},
|
| 3368 |
+
{
|
| 3369 |
+
"epoch": 2.662952646239554,
|
| 3370 |
+
"grad_norm": 4.775937557220459,
|
| 3371 |
+
"learning_rate": 5.63602599814299e-06,
|
| 3372 |
+
"loss": 0.3728,
|
| 3373 |
+
"step": 4780
|
| 3374 |
+
},
|
| 3375 |
+
{
|
| 3376 |
+
"epoch": 2.668523676880223,
|
| 3377 |
+
"grad_norm": 3.5294461250305176,
|
| 3378 |
+
"learning_rate": 5.5431754874651814e-06,
|
| 3379 |
+
"loss": 0.4864,
|
| 3380 |
+
"step": 4790
|
| 3381 |
+
},
|
| 3382 |
+
{
|
| 3383 |
+
"epoch": 2.6740947075208914,
|
| 3384 |
+
"grad_norm": 6.9017486572265625,
|
| 3385 |
+
"learning_rate": 5.450324976787373e-06,
|
| 3386 |
+
"loss": 0.4679,
|
| 3387 |
+
"step": 4800
|
| 3388 |
+
},
|
| 3389 |
+
{
|
| 3390 |
+
"epoch": 2.67966573816156,
|
| 3391 |
+
"grad_norm": 2.8387668132781982,
|
| 3392 |
+
"learning_rate": 5.357474466109564e-06,
|
| 3393 |
+
"loss": 0.2643,
|
| 3394 |
+
"step": 4810
|
| 3395 |
+
},
|
| 3396 |
+
{
|
| 3397 |
+
"epoch": 2.6852367688022283,
|
| 3398 |
+
"grad_norm": 5.770737171173096,
|
| 3399 |
+
"learning_rate": 5.264623955431755e-06,
|
| 3400 |
+
"loss": 0.4973,
|
| 3401 |
+
"step": 4820
|
| 3402 |
+
},
|
| 3403 |
+
{
|
| 3404 |
+
"epoch": 2.690807799442897,
|
| 3405 |
+
"grad_norm": 2.5987281799316406,
|
| 3406 |
+
"learning_rate": 5.171773444753946e-06,
|
| 3407 |
+
"loss": 0.4445,
|
| 3408 |
+
"step": 4830
|
| 3409 |
+
},
|
| 3410 |
+
{
|
| 3411 |
+
"epoch": 2.6963788300835656,
|
| 3412 |
+
"grad_norm": 5.727529048919678,
|
| 3413 |
+
"learning_rate": 5.078922934076137e-06,
|
| 3414 |
+
"loss": 0.4761,
|
| 3415 |
+
"step": 4840
|
| 3416 |
+
},
|
| 3417 |
+
{
|
| 3418 |
+
"epoch": 2.701949860724234,
|
| 3419 |
+
"grad_norm": 3.2433037757873535,
|
| 3420 |
+
"learning_rate": 4.986072423398329e-06,
|
| 3421 |
+
"loss": 0.5198,
|
| 3422 |
+
"step": 4850
|
| 3423 |
+
},
|
| 3424 |
+
{
|
| 3425 |
+
"epoch": 2.7075208913649025,
|
| 3426 |
+
"grad_norm": 2.264634847640991,
|
| 3427 |
+
"learning_rate": 4.89322191272052e-06,
|
| 3428 |
+
"loss": 0.3812,
|
| 3429 |
+
"step": 4860
|
| 3430 |
+
},
|
| 3431 |
+
{
|
| 3432 |
+
"epoch": 2.713091922005571,
|
| 3433 |
+
"grad_norm": 3.4057681560516357,
|
| 3434 |
+
"learning_rate": 4.800371402042712e-06,
|
| 3435 |
+
"loss": 0.5236,
|
| 3436 |
+
"step": 4870
|
| 3437 |
+
},
|
| 3438 |
+
{
|
| 3439 |
+
"epoch": 2.7186629526462394,
|
| 3440 |
+
"grad_norm": 5.159498691558838,
|
| 3441 |
+
"learning_rate": 4.7075208913649025e-06,
|
| 3442 |
+
"loss": 0.4401,
|
| 3443 |
+
"step": 4880
|
| 3444 |
+
},
|
| 3445 |
+
{
|
| 3446 |
+
"epoch": 2.724233983286908,
|
| 3447 |
+
"grad_norm": 6.718446731567383,
|
| 3448 |
+
"learning_rate": 4.614670380687093e-06,
|
| 3449 |
+
"loss": 0.4825,
|
| 3450 |
+
"step": 4890
|
| 3451 |
+
},
|
| 3452 |
+
{
|
| 3453 |
+
"epoch": 2.7298050139275767,
|
| 3454 |
+
"grad_norm": 4.028508186340332,
|
| 3455 |
+
"learning_rate": 4.521819870009285e-06,
|
| 3456 |
+
"loss": 0.3836,
|
| 3457 |
+
"step": 4900
|
| 3458 |
+
},
|
| 3459 |
+
{
|
| 3460 |
+
"epoch": 2.735376044568245,
|
| 3461 |
+
"grad_norm": 2.027120351791382,
|
| 3462 |
+
"learning_rate": 4.428969359331477e-06,
|
| 3463 |
+
"loss": 0.3456,
|
| 3464 |
+
"step": 4910
|
| 3465 |
+
},
|
| 3466 |
+
{
|
| 3467 |
+
"epoch": 2.7409470752089136,
|
| 3468 |
+
"grad_norm": 3.1550886631011963,
|
| 3469 |
+
"learning_rate": 4.336118848653668e-06,
|
| 3470 |
+
"loss": 0.3802,
|
| 3471 |
+
"step": 4920
|
| 3472 |
+
},
|
| 3473 |
+
{
|
| 3474 |
+
"epoch": 2.7465181058495824,
|
| 3475 |
+
"grad_norm": 5.188984394073486,
|
| 3476 |
+
"learning_rate": 4.243268337975859e-06,
|
| 3477 |
+
"loss": 0.383,
|
| 3478 |
+
"step": 4930
|
| 3479 |
+
},
|
| 3480 |
+
{
|
| 3481 |
+
"epoch": 2.752089136490251,
|
| 3482 |
+
"grad_norm": 6.997900009155273,
|
| 3483 |
+
"learning_rate": 4.15041782729805e-06,
|
| 3484 |
+
"loss": 0.4606,
|
| 3485 |
+
"step": 4940
|
| 3486 |
+
},
|
| 3487 |
+
{
|
| 3488 |
+
"epoch": 2.7576601671309193,
|
| 3489 |
+
"grad_norm": 4.508044719696045,
|
| 3490 |
+
"learning_rate": 4.057567316620241e-06,
|
| 3491 |
+
"loss": 0.4017,
|
| 3492 |
+
"step": 4950
|
| 3493 |
+
},
|
| 3494 |
+
{
|
| 3495 |
+
"epoch": 2.7632311977715878,
|
| 3496 |
+
"grad_norm": 6.631628036499023,
|
| 3497 |
+
"learning_rate": 3.964716805942433e-06,
|
| 3498 |
+
"loss": 0.398,
|
| 3499 |
+
"step": 4960
|
| 3500 |
+
},
|
| 3501 |
+
{
|
| 3502 |
+
"epoch": 2.768802228412256,
|
| 3503 |
+
"grad_norm": 7.107889175415039,
|
| 3504 |
+
"learning_rate": 3.8718662952646245e-06,
|
| 3505 |
+
"loss": 0.4823,
|
| 3506 |
+
"step": 4970
|
| 3507 |
+
},
|
| 3508 |
+
{
|
| 3509 |
+
"epoch": 2.7743732590529246,
|
| 3510 |
+
"grad_norm": 4.978562355041504,
|
| 3511 |
+
"learning_rate": 3.7790157845868153e-06,
|
| 3512 |
+
"loss": 0.3995,
|
| 3513 |
+
"step": 4980
|
| 3514 |
+
},
|
| 3515 |
+
{
|
| 3516 |
+
"epoch": 2.779944289693593,
|
| 3517 |
+
"grad_norm": 5.335329055786133,
|
| 3518 |
+
"learning_rate": 3.686165273909006e-06,
|
| 3519 |
+
"loss": 0.39,
|
| 3520 |
+
"step": 4990
|
| 3521 |
+
},
|
| 3522 |
+
{
|
| 3523 |
+
"epoch": 2.785515320334262,
|
| 3524 |
+
"grad_norm": 3.1053812503814697,
|
| 3525 |
+
"learning_rate": 3.593314763231198e-06,
|
| 3526 |
+
"loss": 0.3362,
|
| 3527 |
+
"step": 5000
|
| 3528 |
+
},
|
| 3529 |
+
{
|
| 3530 |
+
"epoch": 2.7910863509749304,
|
| 3531 |
+
"grad_norm": 4.562804222106934,
|
| 3532 |
+
"learning_rate": 3.500464252553389e-06,
|
| 3533 |
+
"loss": 0.3663,
|
| 3534 |
+
"step": 5010
|
| 3535 |
+
},
|
| 3536 |
+
{
|
| 3537 |
+
"epoch": 2.796657381615599,
|
| 3538 |
+
"grad_norm": 2.6694986820220947,
|
| 3539 |
+
"learning_rate": 3.40761374187558e-06,
|
| 3540 |
+
"loss": 0.3584,
|
| 3541 |
+
"step": 5020
|
| 3542 |
+
},
|
| 3543 |
+
{
|
| 3544 |
+
"epoch": 2.8022284122562673,
|
| 3545 |
+
"grad_norm": 5.513758659362793,
|
| 3546 |
+
"learning_rate": 3.3147632311977717e-06,
|
| 3547 |
+
"loss": 0.4915,
|
| 3548 |
+
"step": 5030
|
| 3549 |
+
},
|
| 3550 |
+
{
|
| 3551 |
+
"epoch": 2.807799442896936,
|
| 3552 |
+
"grad_norm": 4.651453971862793,
|
| 3553 |
+
"learning_rate": 3.221912720519963e-06,
|
| 3554 |
+
"loss": 0.364,
|
| 3555 |
+
"step": 5040
|
| 3556 |
+
},
|
| 3557 |
+
{
|
| 3558 |
+
"epoch": 2.8133704735376046,
|
| 3559 |
+
"grad_norm": 4.250921249389648,
|
| 3560 |
+
"learning_rate": 3.129062209842154e-06,
|
| 3561 |
+
"loss": 0.3958,
|
| 3562 |
+
"step": 5050
|
| 3563 |
+
},
|
| 3564 |
+
{
|
| 3565 |
+
"epoch": 2.818941504178273,
|
| 3566 |
+
"grad_norm": 3.3700807094573975,
|
| 3567 |
+
"learning_rate": 3.0362116991643456e-06,
|
| 3568 |
+
"loss": 0.2812,
|
| 3569 |
+
"step": 5060
|
| 3570 |
+
},
|
| 3571 |
+
{
|
| 3572 |
+
"epoch": 2.8245125348189415,
|
| 3573 |
+
"grad_norm": 5.31024694442749,
|
| 3574 |
+
"learning_rate": 2.943361188486537e-06,
|
| 3575 |
+
"loss": 0.4218,
|
| 3576 |
+
"step": 5070
|
| 3577 |
+
},
|
| 3578 |
+
{
|
| 3579 |
+
"epoch": 2.83008356545961,
|
| 3580 |
+
"grad_norm": 2.610002279281616,
|
| 3581 |
+
"learning_rate": 2.850510677808728e-06,
|
| 3582 |
+
"loss": 0.3653,
|
| 3583 |
+
"step": 5080
|
| 3584 |
+
},
|
| 3585 |
+
{
|
| 3586 |
+
"epoch": 2.8356545961002784,
|
| 3587 |
+
"grad_norm": 5.629008769989014,
|
| 3588 |
+
"learning_rate": 2.7576601671309194e-06,
|
| 3589 |
+
"loss": 0.418,
|
| 3590 |
+
"step": 5090
|
| 3591 |
+
},
|
| 3592 |
+
{
|
| 3593 |
+
"epoch": 2.841225626740947,
|
| 3594 |
+
"grad_norm": 3.8689396381378174,
|
| 3595 |
+
"learning_rate": 2.6648096564531107e-06,
|
| 3596 |
+
"loss": 0.3105,
|
| 3597 |
+
"step": 5100
|
| 3598 |
+
},
|
| 3599 |
+
{
|
| 3600 |
+
"epoch": 2.8467966573816157,
|
| 3601 |
+
"grad_norm": 3.4457309246063232,
|
| 3602 |
+
"learning_rate": 2.5719591457753016e-06,
|
| 3603 |
+
"loss": 0.4024,
|
| 3604 |
+
"step": 5110
|
| 3605 |
+
},
|
| 3606 |
+
{
|
| 3607 |
+
"epoch": 2.852367688022284,
|
| 3608 |
+
"grad_norm": 4.193653583526611,
|
| 3609 |
+
"learning_rate": 2.4791086350974933e-06,
|
| 3610 |
+
"loss": 0.4946,
|
| 3611 |
+
"step": 5120
|
| 3612 |
+
},
|
| 3613 |
+
{
|
| 3614 |
+
"epoch": 2.8579387186629526,
|
| 3615 |
+
"grad_norm": 8.699234962463379,
|
| 3616 |
+
"learning_rate": 2.3862581244196846e-06,
|
| 3617 |
+
"loss": 0.4511,
|
| 3618 |
+
"step": 5130
|
| 3619 |
+
},
|
| 3620 |
+
{
|
| 3621 |
+
"epoch": 2.863509749303621,
|
| 3622 |
+
"grad_norm": 4.196930408477783,
|
| 3623 |
+
"learning_rate": 2.2934076137418754e-06,
|
| 3624 |
+
"loss": 0.4671,
|
| 3625 |
+
"step": 5140
|
| 3626 |
+
},
|
| 3627 |
+
{
|
| 3628 |
+
"epoch": 2.86908077994429,
|
| 3629 |
+
"grad_norm": 5.245868682861328,
|
| 3630 |
+
"learning_rate": 2.200557103064067e-06,
|
| 3631 |
+
"loss": 0.4111,
|
| 3632 |
+
"step": 5150
|
| 3633 |
+
},
|
| 3634 |
+
{
|
| 3635 |
+
"epoch": 2.8746518105849583,
|
| 3636 |
+
"grad_norm": 4.189416885375977,
|
| 3637 |
+
"learning_rate": 2.1077065923862584e-06,
|
| 3638 |
+
"loss": 0.4043,
|
| 3639 |
+
"step": 5160
|
| 3640 |
+
},
|
| 3641 |
+
{
|
| 3642 |
+
"epoch": 2.8802228412256268,
|
| 3643 |
+
"grad_norm": 2.8182320594787598,
|
| 3644 |
+
"learning_rate": 2.0148560817084493e-06,
|
| 3645 |
+
"loss": 0.3343,
|
| 3646 |
+
"step": 5170
|
| 3647 |
+
},
|
| 3648 |
+
{
|
| 3649 |
+
"epoch": 2.885793871866295,
|
| 3650 |
+
"grad_norm": 7.292479038238525,
|
| 3651 |
+
"learning_rate": 1.922005571030641e-06,
|
| 3652 |
+
"loss": 0.3844,
|
| 3653 |
+
"step": 5180
|
| 3654 |
+
},
|
| 3655 |
+
{
|
| 3656 |
+
"epoch": 2.8913649025069637,
|
| 3657 |
+
"grad_norm": 2.767341375350952,
|
| 3658 |
+
"learning_rate": 1.8291550603528318e-06,
|
| 3659 |
+
"loss": 0.3948,
|
| 3660 |
+
"step": 5190
|
| 3661 |
+
},
|
| 3662 |
+
{
|
| 3663 |
+
"epoch": 2.896935933147632,
|
| 3664 |
+
"grad_norm": 5.170936107635498,
|
| 3665 |
+
"learning_rate": 1.7363045496750233e-06,
|
| 3666 |
+
"loss": 0.4235,
|
| 3667 |
+
"step": 5200
|
| 3668 |
+
},
|
| 3669 |
+
{
|
| 3670 |
+
"epoch": 2.902506963788301,
|
| 3671 |
+
"grad_norm": 7.14333438873291,
|
| 3672 |
+
"learning_rate": 1.6434540389972146e-06,
|
| 3673 |
+
"loss": 0.3677,
|
| 3674 |
+
"step": 5210
|
| 3675 |
+
},
|
| 3676 |
+
{
|
| 3677 |
+
"epoch": 2.9080779944289694,
|
| 3678 |
+
"grad_norm": 6.775882244110107,
|
| 3679 |
+
"learning_rate": 1.5506035283194059e-06,
|
| 3680 |
+
"loss": 0.486,
|
| 3681 |
+
"step": 5220
|
| 3682 |
+
},
|
| 3683 |
+
{
|
| 3684 |
+
"epoch": 2.913649025069638,
|
| 3685 |
+
"grad_norm": 4.250217914581299,
|
| 3686 |
+
"learning_rate": 1.4577530176415971e-06,
|
| 3687 |
+
"loss": 0.5274,
|
| 3688 |
+
"step": 5230
|
| 3689 |
+
},
|
| 3690 |
+
{
|
| 3691 |
+
"epoch": 2.9192200557103063,
|
| 3692 |
+
"grad_norm": 4.6204633712768555,
|
| 3693 |
+
"learning_rate": 1.3649025069637884e-06,
|
| 3694 |
+
"loss": 0.5229,
|
| 3695 |
+
"step": 5240
|
| 3696 |
+
},
|
| 3697 |
+
{
|
| 3698 |
+
"epoch": 2.924791086350975,
|
| 3699 |
+
"grad_norm": 3.8870279788970947,
|
| 3700 |
+
"learning_rate": 1.2720519962859795e-06,
|
| 3701 |
+
"loss": 0.535,
|
| 3702 |
+
"step": 5250
|
| 3703 |
+
},
|
| 3704 |
+
{
|
| 3705 |
+
"epoch": 2.9303621169916436,
|
| 3706 |
+
"grad_norm": 9.080047607421875,
|
| 3707 |
+
"learning_rate": 1.179201485608171e-06,
|
| 3708 |
+
"loss": 0.507,
|
| 3709 |
+
"step": 5260
|
| 3710 |
+
},
|
| 3711 |
+
{
|
| 3712 |
+
"epoch": 2.935933147632312,
|
| 3713 |
+
"grad_norm": 10.549107551574707,
|
| 3714 |
+
"learning_rate": 1.0863509749303623e-06,
|
| 3715 |
+
"loss": 0.4738,
|
| 3716 |
+
"step": 5270
|
| 3717 |
+
},
|
| 3718 |
+
{
|
| 3719 |
+
"epoch": 2.9415041782729805,
|
| 3720 |
+
"grad_norm": 3.7926011085510254,
|
| 3721 |
+
"learning_rate": 9.935004642525533e-07,
|
| 3722 |
+
"loss": 0.4498,
|
| 3723 |
+
"step": 5280
|
| 3724 |
+
},
|
| 3725 |
+
{
|
| 3726 |
+
"epoch": 2.947075208913649,
|
| 3727 |
+
"grad_norm": 2.45975399017334,
|
| 3728 |
+
"learning_rate": 9.006499535747446e-07,
|
| 3729 |
+
"loss": 0.3481,
|
| 3730 |
+
"step": 5290
|
| 3731 |
+
},
|
| 3732 |
+
{
|
| 3733 |
+
"epoch": 2.9526462395543174,
|
| 3734 |
+
"grad_norm": 4.364011764526367,
|
| 3735 |
+
"learning_rate": 8.07799442896936e-07,
|
| 3736 |
+
"loss": 0.4118,
|
| 3737 |
+
"step": 5300
|
| 3738 |
+
},
|
| 3739 |
+
{
|
| 3740 |
+
"epoch": 2.958217270194986,
|
| 3741 |
+
"grad_norm": 5.1891255378723145,
|
| 3742 |
+
"learning_rate": 7.149489322191273e-07,
|
| 3743 |
+
"loss": 0.5408,
|
| 3744 |
+
"step": 5310
|
| 3745 |
+
},
|
| 3746 |
+
{
|
| 3747 |
+
"epoch": 2.9637883008356547,
|
| 3748 |
+
"grad_norm": 5.055240631103516,
|
| 3749 |
+
"learning_rate": 6.220984215413185e-07,
|
| 3750 |
+
"loss": 0.3917,
|
| 3751 |
+
"step": 5320
|
| 3752 |
+
},
|
| 3753 |
+
{
|
| 3754 |
+
"epoch": 2.969359331476323,
|
| 3755 |
+
"grad_norm": 4.434938907623291,
|
| 3756 |
+
"learning_rate": 5.292479108635097e-07,
|
| 3757 |
+
"loss": 0.3526,
|
| 3758 |
+
"step": 5330
|
| 3759 |
+
},
|
| 3760 |
+
{
|
| 3761 |
+
"epoch": 2.9749303621169916,
|
| 3762 |
+
"grad_norm": 5.2575860023498535,
|
| 3763 |
+
"learning_rate": 4.36397400185701e-07,
|
| 3764 |
+
"loss": 0.3464,
|
| 3765 |
+
"step": 5340
|
| 3766 |
+
},
|
| 3767 |
+
{
|
| 3768 |
+
"epoch": 2.98050139275766,
|
| 3769 |
+
"grad_norm": 8.497797966003418,
|
| 3770 |
+
"learning_rate": 3.435468895078923e-07,
|
| 3771 |
+
"loss": 0.5106,
|
| 3772 |
+
"step": 5350
|
| 3773 |
+
},
|
| 3774 |
+
{
|
| 3775 |
+
"epoch": 2.986072423398329,
|
| 3776 |
+
"grad_norm": 4.38588285446167,
|
| 3777 |
+
"learning_rate": 2.506963788300836e-07,
|
| 3778 |
+
"loss": 0.3509,
|
| 3779 |
+
"step": 5360
|
| 3780 |
+
},
|
| 3781 |
+
{
|
| 3782 |
+
"epoch": 2.9916434540389973,
|
| 3783 |
+
"grad_norm": 7.261599540710449,
|
| 3784 |
+
"learning_rate": 1.5784586815227484e-07,
|
| 3785 |
+
"loss": 0.5137,
|
| 3786 |
+
"step": 5370
|
| 3787 |
+
},
|
| 3788 |
+
{
|
| 3789 |
+
"epoch": 2.997214484679666,
|
| 3790 |
+
"grad_norm": 7.3228936195373535,
|
| 3791 |
+
"learning_rate": 6.499535747446612e-08,
|
| 3792 |
+
"loss": 0.4838,
|
| 3793 |
+
"step": 5380
|
| 3794 |
+
},
|
| 3795 |
+
{
|
| 3796 |
+
"epoch": 3.0,
|
| 3797 |
+
"eval_accuracy": 0.7127333519086096,
|
| 3798 |
+
"eval_loss": 0.8501355051994324,
|
| 3799 |
+
"eval_runtime": 37.2414,
|
| 3800 |
+
"eval_samples_per_second": 96.371,
|
| 3801 |
+
"eval_steps_per_second": 6.042,
|
| 3802 |
+
"step": 5385
|
| 3803 |
+
},
|
| 3804 |
+
{
|
| 3805 |
+
"epoch": 3.0,
|
| 3806 |
+
"step": 5385,
|
| 3807 |
+
"total_flos": 6.674451681129007e+18,
|
| 3808 |
+
"train_loss": 0.7317446124697573,
|
| 3809 |
+
"train_runtime": 2231.3604,
|
| 3810 |
+
"train_samples_per_second": 38.598,
|
| 3811 |
+
"train_steps_per_second": 2.413
|
| 3812 |
+
}
|
| 3813 |
+
],
|
| 3814 |
+
"logging_steps": 10,
|
| 3815 |
+
"max_steps": 5385,
|
| 3816 |
+
"num_input_tokens_seen": 0,
|
| 3817 |
+
"num_train_epochs": 3,
|
| 3818 |
+
"save_steps": 500,
|
| 3819 |
+
"stateful_callbacks": {
|
| 3820 |
+
"TrainerControl": {
|
| 3821 |
+
"args": {
|
| 3822 |
+
"should_epoch_stop": false,
|
| 3823 |
+
"should_evaluate": false,
|
| 3824 |
+
"should_log": false,
|
| 3825 |
+
"should_save": true,
|
| 3826 |
+
"should_training_stop": true
|
| 3827 |
+
},
|
| 3828 |
+
"attributes": {}
|
| 3829 |
+
}
|
| 3830 |
+
},
|
| 3831 |
+
"total_flos": 6.674451681129007e+18,
|
| 3832 |
+
"train_batch_size": 16,
|
| 3833 |
+
"trial_name": null,
|
| 3834 |
+
"trial_params": null
|
| 3835 |
+
}
|