End of training
Browse files- README.md +16 -2
- all_results.json +13 -0
- eval_results.json +8 -0
- log_history.json +1928 -0
- train_results.json +8 -0
- trainer_state.json +1959 -0
README.md
CHANGED
|
@@ -1,6 +1,7 @@
|
|
| 1 |
---
|
| 2 |
library_name: transformers
|
| 3 |
tags:
|
|
|
|
| 4 |
- generated_from_trainer
|
| 5 |
datasets:
|
| 6 |
- voxceleb
|
|
@@ -8,7 +9,20 @@ metrics:
|
|
| 8 |
- accuracy
|
| 9 |
model-index:
|
| 10 |
- name: etdnn-voxceleb1
|
| 11 |
-
results:
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 12 |
---
|
| 13 |
|
| 14 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
@@ -16,7 +30,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 16 |
|
| 17 |
# etdnn-voxceleb1
|
| 18 |
|
| 19 |
-
This model is a fine-tuned version of [](https://huggingface.co/) on the voxceleb dataset.
|
| 20 |
It achieves the following results on the evaluation set:
|
| 21 |
- Loss: 0.3594
|
| 22 |
- Accuracy: 0.9341
|
|
|
|
| 1 |
---
|
| 2 |
library_name: transformers
|
| 3 |
tags:
|
| 4 |
+
- audio-classification
|
| 5 |
- generated_from_trainer
|
| 6 |
datasets:
|
| 7 |
- voxceleb
|
|
|
|
| 9 |
- accuracy
|
| 10 |
model-index:
|
| 11 |
- name: etdnn-voxceleb1
|
| 12 |
+
results:
|
| 13 |
+
- task:
|
| 14 |
+
name: Audio Classification
|
| 15 |
+
type: audio-classification
|
| 16 |
+
dataset:
|
| 17 |
+
name: confit/voxceleb
|
| 18 |
+
type: voxceleb
|
| 19 |
+
config: verification
|
| 20 |
+
split: train
|
| 21 |
+
args: verification
|
| 22 |
+
metrics:
|
| 23 |
+
- name: Accuracy
|
| 24 |
+
type: accuracy
|
| 25 |
+
value: 0.9340733266061217
|
| 26 |
---
|
| 27 |
|
| 28 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
|
|
| 30 |
|
| 31 |
# etdnn-voxceleb1
|
| 32 |
|
| 33 |
+
This model is a fine-tuned version of [](https://huggingface.co/) on the confit/voxceleb dataset.
|
| 34 |
It achieves the following results on the evaluation set:
|
| 35 |
- Loss: 0.3594
|
| 36 |
- Accuracy: 0.9341
|
all_results.json
ADDED
|
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 10.0,
|
| 3 |
+
"eval_accuracy": 0.9340733266061217,
|
| 4 |
+
"eval_loss": 0.35941872000694275,
|
| 5 |
+
"eval_runtime": 1672.7938,
|
| 6 |
+
"eval_samples_per_second": 8.886,
|
| 7 |
+
"eval_steps_per_second": 8.886,
|
| 8 |
+
"total_flos": 2.7283641066057605e+18,
|
| 9 |
+
"train_loss": 1.9864544938672797,
|
| 10 |
+
"train_runtime": 94798.7749,
|
| 11 |
+
"train_samples_per_second": 14.112,
|
| 12 |
+
"train_steps_per_second": 0.055
|
| 13 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 10.0,
|
| 3 |
+
"eval_accuracy": 0.9340733266061217,
|
| 4 |
+
"eval_loss": 0.35941872000694275,
|
| 5 |
+
"eval_runtime": 1672.7938,
|
| 6 |
+
"eval_samples_per_second": 8.886,
|
| 7 |
+
"eval_steps_per_second": 8.886
|
| 8 |
+
}
|
log_history.json
ADDED
|
@@ -0,0 +1,1928 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
[
|
| 2 |
+
{
|
| 3 |
+
"loss": 7.1473,
|
| 4 |
+
"grad_norm": 10.999133110046387,
|
| 5 |
+
"learning_rate": 1.9120458891013384e-05,
|
| 6 |
+
"epoch": 0.03824091778202677,
|
| 7 |
+
"step": 20
|
| 8 |
+
},
|
| 9 |
+
{
|
| 10 |
+
"loss": 7.1283,
|
| 11 |
+
"grad_norm": 10.200960159301758,
|
| 12 |
+
"learning_rate": 3.824091778202677e-05,
|
| 13 |
+
"epoch": 0.07648183556405354,
|
| 14 |
+
"step": 40
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"loss": 7.0847,
|
| 18 |
+
"grad_norm": 9.468878746032715,
|
| 19 |
+
"learning_rate": 5.736137667304015e-05,
|
| 20 |
+
"epoch": 0.1147227533460803,
|
| 21 |
+
"step": 60
|
| 22 |
+
},
|
| 23 |
+
{
|
| 24 |
+
"loss": 7.0321,
|
| 25 |
+
"grad_norm": 8.736529350280762,
|
| 26 |
+
"learning_rate": 7.648183556405354e-05,
|
| 27 |
+
"epoch": 0.15296367112810708,
|
| 28 |
+
"step": 80
|
| 29 |
+
},
|
| 30 |
+
{
|
| 31 |
+
"loss": 6.955,
|
| 32 |
+
"grad_norm": 6.856561183929443,
|
| 33 |
+
"learning_rate": 9.560229445506692e-05,
|
| 34 |
+
"epoch": 0.19120458891013384,
|
| 35 |
+
"step": 100
|
| 36 |
+
},
|
| 37 |
+
{
|
| 38 |
+
"loss": 6.8474,
|
| 39 |
+
"grad_norm": 5.473419666290283,
|
| 40 |
+
"learning_rate": 0.0001147227533460803,
|
| 41 |
+
"epoch": 0.2294455066921606,
|
| 42 |
+
"step": 120
|
| 43 |
+
},
|
| 44 |
+
{
|
| 45 |
+
"loss": 6.7002,
|
| 46 |
+
"grad_norm": 3.7059528827667236,
|
| 47 |
+
"learning_rate": 0.0001338432122370937,
|
| 48 |
+
"epoch": 0.2676864244741874,
|
| 49 |
+
"step": 140
|
| 50 |
+
},
|
| 51 |
+
{
|
| 52 |
+
"loss": 6.5368,
|
| 53 |
+
"grad_norm": 2.9125759601593018,
|
| 54 |
+
"learning_rate": 0.00015296367112810707,
|
| 55 |
+
"epoch": 0.30592734225621415,
|
| 56 |
+
"step": 160
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"loss": 6.3399,
|
| 60 |
+
"grad_norm": 2.5546936988830566,
|
| 61 |
+
"learning_rate": 0.00017208413001912047,
|
| 62 |
+
"epoch": 0.3441682600382409,
|
| 63 |
+
"step": 180
|
| 64 |
+
},
|
| 65 |
+
{
|
| 66 |
+
"loss": 6.1511,
|
| 67 |
+
"grad_norm": 2.418347120285034,
|
| 68 |
+
"learning_rate": 0.00019120458891013384,
|
| 69 |
+
"epoch": 0.3824091778202677,
|
| 70 |
+
"step": 200
|
| 71 |
+
},
|
| 72 |
+
{
|
| 73 |
+
"loss": 6.015,
|
| 74 |
+
"grad_norm": 2.2986104488372803,
|
| 75 |
+
"learning_rate": 0.0002103250478011472,
|
| 76 |
+
"epoch": 0.42065009560229444,
|
| 77 |
+
"step": 220
|
| 78 |
+
},
|
| 79 |
+
{
|
| 80 |
+
"loss": 5.8224,
|
| 81 |
+
"grad_norm": 2.227661609649658,
|
| 82 |
+
"learning_rate": 0.0002294455066921606,
|
| 83 |
+
"epoch": 0.4588910133843212,
|
| 84 |
+
"step": 240
|
| 85 |
+
},
|
| 86 |
+
{
|
| 87 |
+
"loss": 5.6838,
|
| 88 |
+
"grad_norm": 2.2191731929779053,
|
| 89 |
+
"learning_rate": 0.00024856596558317403,
|
| 90 |
+
"epoch": 0.497131931166348,
|
| 91 |
+
"step": 260
|
| 92 |
+
},
|
| 93 |
+
{
|
| 94 |
+
"loss": 5.5764,
|
| 95 |
+
"grad_norm": 2.2345361709594727,
|
| 96 |
+
"learning_rate": 0.0002676864244741874,
|
| 97 |
+
"epoch": 0.5353728489483748,
|
| 98 |
+
"step": 280
|
| 99 |
+
},
|
| 100 |
+
{
|
| 101 |
+
"loss": 5.4715,
|
| 102 |
+
"grad_norm": 2.2029287815093994,
|
| 103 |
+
"learning_rate": 0.0002868068833652008,
|
| 104 |
+
"epoch": 0.5736137667304015,
|
| 105 |
+
"step": 300
|
| 106 |
+
},
|
| 107 |
+
{
|
| 108 |
+
"loss": 5.321,
|
| 109 |
+
"grad_norm": 2.1917331218719482,
|
| 110 |
+
"learning_rate": 0.00030592734225621415,
|
| 111 |
+
"epoch": 0.6118546845124283,
|
| 112 |
+
"step": 320
|
| 113 |
+
},
|
| 114 |
+
{
|
| 115 |
+
"loss": 5.2218,
|
| 116 |
+
"grad_norm": 2.2598936557769775,
|
| 117 |
+
"learning_rate": 0.0003250478011472275,
|
| 118 |
+
"epoch": 0.6500956022944551,
|
| 119 |
+
"step": 340
|
| 120 |
+
},
|
| 121 |
+
{
|
| 122 |
+
"loss": 5.1449,
|
| 123 |
+
"grad_norm": 2.3335328102111816,
|
| 124 |
+
"learning_rate": 0.00034416826003824094,
|
| 125 |
+
"epoch": 0.6883365200764818,
|
| 126 |
+
"step": 360
|
| 127 |
+
},
|
| 128 |
+
{
|
| 129 |
+
"loss": 5.0062,
|
| 130 |
+
"grad_norm": 2.3767151832580566,
|
| 131 |
+
"learning_rate": 0.0003632887189292543,
|
| 132 |
+
"epoch": 0.7265774378585086,
|
| 133 |
+
"step": 380
|
| 134 |
+
},
|
| 135 |
+
{
|
| 136 |
+
"loss": 4.9352,
|
| 137 |
+
"grad_norm": 2.357161521911621,
|
| 138 |
+
"learning_rate": 0.0003824091778202677,
|
| 139 |
+
"epoch": 0.7648183556405354,
|
| 140 |
+
"step": 400
|
| 141 |
+
},
|
| 142 |
+
{
|
| 143 |
+
"loss": 4.8959,
|
| 144 |
+
"grad_norm": 2.271972179412842,
|
| 145 |
+
"learning_rate": 0.00040152963671128105,
|
| 146 |
+
"epoch": 0.8030592734225621,
|
| 147 |
+
"step": 420
|
| 148 |
+
},
|
| 149 |
+
{
|
| 150 |
+
"loss": 4.7951,
|
| 151 |
+
"grad_norm": 2.4624767303466797,
|
| 152 |
+
"learning_rate": 0.0004206500956022944,
|
| 153 |
+
"epoch": 0.8413001912045889,
|
| 154 |
+
"step": 440
|
| 155 |
+
},
|
| 156 |
+
{
|
| 157 |
+
"loss": 4.6734,
|
| 158 |
+
"grad_norm": 2.1839234828948975,
|
| 159 |
+
"learning_rate": 0.00043977055449330785,
|
| 160 |
+
"epoch": 0.8795411089866156,
|
| 161 |
+
"step": 460
|
| 162 |
+
},
|
| 163 |
+
{
|
| 164 |
+
"loss": 4.6458,
|
| 165 |
+
"grad_norm": 2.3169806003570557,
|
| 166 |
+
"learning_rate": 0.0004588910133843212,
|
| 167 |
+
"epoch": 0.9177820267686424,
|
| 168 |
+
"step": 480
|
| 169 |
+
},
|
| 170 |
+
{
|
| 171 |
+
"loss": 4.5657,
|
| 172 |
+
"grad_norm": 2.3231122493743896,
|
| 173 |
+
"learning_rate": 0.0004780114722753346,
|
| 174 |
+
"epoch": 0.9560229445506692,
|
| 175 |
+
"step": 500
|
| 176 |
+
},
|
| 177 |
+
{
|
| 178 |
+
"loss": 4.489,
|
| 179 |
+
"grad_norm": 2.34975266456604,
|
| 180 |
+
"learning_rate": 0.0004971319311663481,
|
| 181 |
+
"epoch": 0.994263862332696,
|
| 182 |
+
"step": 520
|
| 183 |
+
},
|
| 184 |
+
{
|
| 185 |
+
"eval_loss": 4.208949089050293,
|
| 186 |
+
"eval_accuracy": 0.1722166162125799,
|
| 187 |
+
"eval_runtime": 1092.4973,
|
| 188 |
+
"eval_samples_per_second": 13.606,
|
| 189 |
+
"eval_steps_per_second": 13.606,
|
| 190 |
+
"epoch": 1.0,
|
| 191 |
+
"step": 523
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"loss": 4.3496,
|
| 195 |
+
"grad_norm": 2.3869619369506836,
|
| 196 |
+
"learning_rate": 0.0004981941788825154,
|
| 197 |
+
"epoch": 1.0325047801147227,
|
| 198 |
+
"step": 540
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"loss": 4.3108,
|
| 202 |
+
"grad_norm": 2.2834343910217285,
|
| 203 |
+
"learning_rate": 0.0004960696834501806,
|
| 204 |
+
"epoch": 1.0707456978967496,
|
| 205 |
+
"step": 560
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"loss": 4.229,
|
| 209 |
+
"grad_norm": 2.192180633544922,
|
| 210 |
+
"learning_rate": 0.0004939451880178457,
|
| 211 |
+
"epoch": 1.1089866156787762,
|
| 212 |
+
"step": 580
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"loss": 4.1804,
|
| 216 |
+
"grad_norm": 2.161285161972046,
|
| 217 |
+
"learning_rate": 0.0004918206925855109,
|
| 218 |
+
"epoch": 1.147227533460803,
|
| 219 |
+
"step": 600
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"loss": 4.118,
|
| 223 |
+
"grad_norm": 2.2634170055389404,
|
| 224 |
+
"learning_rate": 0.0004896961971531761,
|
| 225 |
+
"epoch": 1.1854684512428297,
|
| 226 |
+
"step": 620
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"loss": 4.0295,
|
| 230 |
+
"grad_norm": 2.1758434772491455,
|
| 231 |
+
"learning_rate": 0.00048757170172084133,
|
| 232 |
+
"epoch": 1.2237093690248566,
|
| 233 |
+
"step": 640
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"loss": 3.9559,
|
| 237 |
+
"grad_norm": 2.25357985496521,
|
| 238 |
+
"learning_rate": 0.0004854472062885065,
|
| 239 |
+
"epoch": 1.2619502868068833,
|
| 240 |
+
"step": 660
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"loss": 3.9295,
|
| 244 |
+
"grad_norm": 2.2077853679656982,
|
| 245 |
+
"learning_rate": 0.0004833227108561717,
|
| 246 |
+
"epoch": 1.3001912045889101,
|
| 247 |
+
"step": 680
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"loss": 3.8221,
|
| 251 |
+
"grad_norm": 2.28712797164917,
|
| 252 |
+
"learning_rate": 0.0004811982154238369,
|
| 253 |
+
"epoch": 1.338432122370937,
|
| 254 |
+
"step": 700
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"loss": 3.7764,
|
| 258 |
+
"grad_norm": 2.2988157272338867,
|
| 259 |
+
"learning_rate": 0.000479073719991502,
|
| 260 |
+
"epoch": 1.3766730401529637,
|
| 261 |
+
"step": 720
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"loss": 3.7518,
|
| 265 |
+
"grad_norm": 2.391023874282837,
|
| 266 |
+
"learning_rate": 0.0004769492245591672,
|
| 267 |
+
"epoch": 1.4149139579349903,
|
| 268 |
+
"step": 740
|
| 269 |
+
},
|
| 270 |
+
{
|
| 271 |
+
"loss": 3.7074,
|
| 272 |
+
"grad_norm": 2.065288782119751,
|
| 273 |
+
"learning_rate": 0.00047482472912683236,
|
| 274 |
+
"epoch": 1.4531548757170172,
|
| 275 |
+
"step": 760
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"loss": 3.6558,
|
| 279 |
+
"grad_norm": 2.288686990737915,
|
| 280 |
+
"learning_rate": 0.00047270023369449756,
|
| 281 |
+
"epoch": 1.491395793499044,
|
| 282 |
+
"step": 780
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"loss": 3.6038,
|
| 286 |
+
"grad_norm": 2.228173017501831,
|
| 287 |
+
"learning_rate": 0.00047057573826216276,
|
| 288 |
+
"epoch": 1.5296367112810707,
|
| 289 |
+
"step": 800
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"loss": 3.5405,
|
| 293 |
+
"grad_norm": 2.1894149780273438,
|
| 294 |
+
"learning_rate": 0.0004684512428298279,
|
| 295 |
+
"epoch": 1.5678776290630974,
|
| 296 |
+
"step": 820
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"loss": 3.4855,
|
| 300 |
+
"grad_norm": 2.234192371368408,
|
| 301 |
+
"learning_rate": 0.0004663267473974931,
|
| 302 |
+
"epoch": 1.6061185468451242,
|
| 303 |
+
"step": 840
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"loss": 3.4771,
|
| 307 |
+
"grad_norm": 2.309387445449829,
|
| 308 |
+
"learning_rate": 0.0004642022519651583,
|
| 309 |
+
"epoch": 1.644359464627151,
|
| 310 |
+
"step": 860
|
| 311 |
+
},
|
| 312 |
+
{
|
| 313 |
+
"loss": 3.3984,
|
| 314 |
+
"grad_norm": 2.183579206466675,
|
| 315 |
+
"learning_rate": 0.00046207775653282345,
|
| 316 |
+
"epoch": 1.682600382409178,
|
| 317 |
+
"step": 880
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"loss": 3.3318,
|
| 321 |
+
"grad_norm": 2.286858558654785,
|
| 322 |
+
"learning_rate": 0.00045995326110048865,
|
| 323 |
+
"epoch": 1.7208413001912046,
|
| 324 |
+
"step": 900
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"loss": 3.3256,
|
| 328 |
+
"grad_norm": 2.2087490558624268,
|
| 329 |
+
"learning_rate": 0.00045782876566815385,
|
| 330 |
+
"epoch": 1.7590822179732313,
|
| 331 |
+
"step": 920
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"loss": 3.2644,
|
| 335 |
+
"grad_norm": 2.2571709156036377,
|
| 336 |
+
"learning_rate": 0.000455704270235819,
|
| 337 |
+
"epoch": 1.7973231357552581,
|
| 338 |
+
"step": 940
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"loss": 3.2687,
|
| 342 |
+
"grad_norm": 2.346696138381958,
|
| 343 |
+
"learning_rate": 0.0004535797748034842,
|
| 344 |
+
"epoch": 1.835564053537285,
|
| 345 |
+
"step": 960
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"loss": 3.2346,
|
| 349 |
+
"grad_norm": 2.309258460998535,
|
| 350 |
+
"learning_rate": 0.0004514552793711494,
|
| 351 |
+
"epoch": 1.8738049713193117,
|
| 352 |
+
"step": 980
|
| 353 |
+
},
|
| 354 |
+
{
|
| 355 |
+
"loss": 3.1507,
|
| 356 |
+
"grad_norm": 2.200920820236206,
|
| 357 |
+
"learning_rate": 0.00044933078393881453,
|
| 358 |
+
"epoch": 1.9120458891013383,
|
| 359 |
+
"step": 1000
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"loss": 3.0884,
|
| 363 |
+
"grad_norm": 2.1627931594848633,
|
| 364 |
+
"learning_rate": 0.00044720628850647973,
|
| 365 |
+
"epoch": 1.9502868068833652,
|
| 366 |
+
"step": 1020
|
| 367 |
+
},
|
| 368 |
+
{
|
| 369 |
+
"loss": 3.0685,
|
| 370 |
+
"grad_norm": 2.350935220718384,
|
| 371 |
+
"learning_rate": 0.00044508179307414493,
|
| 372 |
+
"epoch": 1.988527724665392,
|
| 373 |
+
"step": 1040
|
| 374 |
+
},
|
| 375 |
+
{
|
| 376 |
+
"eval_loss": 2.762111186981201,
|
| 377 |
+
"eval_accuracy": 0.41096535486041036,
|
| 378 |
+
"eval_runtime": 1228.094,
|
| 379 |
+
"eval_samples_per_second": 12.104,
|
| 380 |
+
"eval_steps_per_second": 12.104,
|
| 381 |
+
"epoch": 2.0,
|
| 382 |
+
"step": 1046
|
| 383 |
+
},
|
| 384 |
+
{
|
| 385 |
+
"loss": 3.0334,
|
| 386 |
+
"grad_norm": 2.137504816055298,
|
| 387 |
+
"learning_rate": 0.0004429572976418101,
|
| 388 |
+
"epoch": 2.026768642447419,
|
| 389 |
+
"step": 1060
|
| 390 |
+
},
|
| 391 |
+
{
|
| 392 |
+
"loss": 2.8843,
|
| 393 |
+
"grad_norm": 2.2636399269104004,
|
| 394 |
+
"learning_rate": 0.0004408328022094752,
|
| 395 |
+
"epoch": 2.0650095602294454,
|
| 396 |
+
"step": 1080
|
| 397 |
+
},
|
| 398 |
+
{
|
| 399 |
+
"loss": 2.909,
|
| 400 |
+
"grad_norm": 2.141150712966919,
|
| 401 |
+
"learning_rate": 0.0004387083067771405,
|
| 402 |
+
"epoch": 2.1032504780114722,
|
| 403 |
+
"step": 1100
|
| 404 |
+
},
|
| 405 |
+
{
|
| 406 |
+
"loss": 2.8407,
|
| 407 |
+
"grad_norm": 2.243589401245117,
|
| 408 |
+
"learning_rate": 0.0004365838113448056,
|
| 409 |
+
"epoch": 2.141491395793499,
|
| 410 |
+
"step": 1120
|
| 411 |
+
},
|
| 412 |
+
{
|
| 413 |
+
"loss": 2.8377,
|
| 414 |
+
"grad_norm": 2.3046114444732666,
|
| 415 |
+
"learning_rate": 0.00043445931591247077,
|
| 416 |
+
"epoch": 2.179732313575526,
|
| 417 |
+
"step": 1140
|
| 418 |
+
},
|
| 419 |
+
{
|
| 420 |
+
"loss": 2.7642,
|
| 421 |
+
"grad_norm": 2.375234603881836,
|
| 422 |
+
"learning_rate": 0.000432334820480136,
|
| 423 |
+
"epoch": 2.2179732313575524,
|
| 424 |
+
"step": 1160
|
| 425 |
+
},
|
| 426 |
+
{
|
| 427 |
+
"loss": 2.8011,
|
| 428 |
+
"grad_norm": 2.36006236076355,
|
| 429 |
+
"learning_rate": 0.00043021032504780116,
|
| 430 |
+
"epoch": 2.2562141491395793,
|
| 431 |
+
"step": 1180
|
| 432 |
+
},
|
| 433 |
+
{
|
| 434 |
+
"loss": 2.7502,
|
| 435 |
+
"grad_norm": 2.246645450592041,
|
| 436 |
+
"learning_rate": 0.0004280858296154663,
|
| 437 |
+
"epoch": 2.294455066921606,
|
| 438 |
+
"step": 1200
|
| 439 |
+
},
|
| 440 |
+
{
|
| 441 |
+
"loss": 2.6646,
|
| 442 |
+
"grad_norm": 2.420032501220703,
|
| 443 |
+
"learning_rate": 0.0004259613341831315,
|
| 444 |
+
"epoch": 2.332695984703633,
|
| 445 |
+
"step": 1220
|
| 446 |
+
},
|
| 447 |
+
{
|
| 448 |
+
"loss": 2.7294,
|
| 449 |
+
"grad_norm": 2.3049144744873047,
|
| 450 |
+
"learning_rate": 0.0004238368387507967,
|
| 451 |
+
"epoch": 2.3709369024856595,
|
| 452 |
+
"step": 1240
|
| 453 |
+
},
|
| 454 |
+
{
|
| 455 |
+
"loss": 2.7323,
|
| 456 |
+
"grad_norm": 2.3154027462005615,
|
| 457 |
+
"learning_rate": 0.00042171234331846185,
|
| 458 |
+
"epoch": 2.4091778202676863,
|
| 459 |
+
"step": 1260
|
| 460 |
+
},
|
| 461 |
+
{
|
| 462 |
+
"loss": 2.6435,
|
| 463 |
+
"grad_norm": 2.3349056243896484,
|
| 464 |
+
"learning_rate": 0.00041958784788612705,
|
| 465 |
+
"epoch": 2.447418738049713,
|
| 466 |
+
"step": 1280
|
| 467 |
+
},
|
| 468 |
+
{
|
| 469 |
+
"loss": 2.5938,
|
| 470 |
+
"grad_norm": 2.3369665145874023,
|
| 471 |
+
"learning_rate": 0.00041746335245379225,
|
| 472 |
+
"epoch": 2.48565965583174,
|
| 473 |
+
"step": 1300
|
| 474 |
+
},
|
| 475 |
+
{
|
| 476 |
+
"loss": 2.5557,
|
| 477 |
+
"grad_norm": 2.115408182144165,
|
| 478 |
+
"learning_rate": 0.0004153388570214574,
|
| 479 |
+
"epoch": 2.5239005736137665,
|
| 480 |
+
"step": 1320
|
| 481 |
+
},
|
| 482 |
+
{
|
| 483 |
+
"loss": 2.5262,
|
| 484 |
+
"grad_norm": 2.2280750274658203,
|
| 485 |
+
"learning_rate": 0.00041321436158912254,
|
| 486 |
+
"epoch": 2.5621414913957934,
|
| 487 |
+
"step": 1340
|
| 488 |
+
},
|
| 489 |
+
{
|
| 490 |
+
"loss": 2.5302,
|
| 491 |
+
"grad_norm": 2.3640174865722656,
|
| 492 |
+
"learning_rate": 0.0004110898661567878,
|
| 493 |
+
"epoch": 2.6003824091778203,
|
| 494 |
+
"step": 1360
|
| 495 |
+
},
|
| 496 |
+
{
|
| 497 |
+
"loss": 2.4982,
|
| 498 |
+
"grad_norm": 2.220531940460205,
|
| 499 |
+
"learning_rate": 0.00040896537072445294,
|
| 500 |
+
"epoch": 2.638623326959847,
|
| 501 |
+
"step": 1380
|
| 502 |
+
},
|
| 503 |
+
{
|
| 504 |
+
"loss": 2.4884,
|
| 505 |
+
"grad_norm": 2.19985294342041,
|
| 506 |
+
"learning_rate": 0.0004068408752921181,
|
| 507 |
+
"epoch": 2.676864244741874,
|
| 508 |
+
"step": 1400
|
| 509 |
+
},
|
| 510 |
+
{
|
| 511 |
+
"loss": 2.4422,
|
| 512 |
+
"grad_norm": 2.083179235458374,
|
| 513 |
+
"learning_rate": 0.00040471637985978334,
|
| 514 |
+
"epoch": 2.7151051625239004,
|
| 515 |
+
"step": 1420
|
| 516 |
+
},
|
| 517 |
+
{
|
| 518 |
+
"loss": 2.4187,
|
| 519 |
+
"grad_norm": 2.171346664428711,
|
| 520 |
+
"learning_rate": 0.0004025918844274485,
|
| 521 |
+
"epoch": 2.7533460803059273,
|
| 522 |
+
"step": 1440
|
| 523 |
+
},
|
| 524 |
+
{
|
| 525 |
+
"loss": 2.3988,
|
| 526 |
+
"grad_norm": 2.330702304840088,
|
| 527 |
+
"learning_rate": 0.0004004673889951136,
|
| 528 |
+
"epoch": 2.791586998087954,
|
| 529 |
+
"step": 1460
|
| 530 |
+
},
|
| 531 |
+
{
|
| 532 |
+
"loss": 2.3606,
|
| 533 |
+
"grad_norm": 2.3132684230804443,
|
| 534 |
+
"learning_rate": 0.0003983428935627789,
|
| 535 |
+
"epoch": 2.8298279158699806,
|
| 536 |
+
"step": 1480
|
| 537 |
+
},
|
| 538 |
+
{
|
| 539 |
+
"loss": 2.3411,
|
| 540 |
+
"grad_norm": 2.188427686691284,
|
| 541 |
+
"learning_rate": 0.000396218398130444,
|
| 542 |
+
"epoch": 2.8680688336520075,
|
| 543 |
+
"step": 1500
|
| 544 |
+
},
|
| 545 |
+
{
|
| 546 |
+
"loss": 2.3314,
|
| 547 |
+
"grad_norm": 2.1979410648345947,
|
| 548 |
+
"learning_rate": 0.00039409390269810917,
|
| 549 |
+
"epoch": 2.9063097514340344,
|
| 550 |
+
"step": 1520
|
| 551 |
+
},
|
| 552 |
+
{
|
| 553 |
+
"loss": 2.3221,
|
| 554 |
+
"grad_norm": 2.246650218963623,
|
| 555 |
+
"learning_rate": 0.0003919694072657744,
|
| 556 |
+
"epoch": 2.9445506692160612,
|
| 557 |
+
"step": 1540
|
| 558 |
+
},
|
| 559 |
+
{
|
| 560 |
+
"loss": 2.2892,
|
| 561 |
+
"grad_norm": 2.2953240871429443,
|
| 562 |
+
"learning_rate": 0.00038984491183343957,
|
| 563 |
+
"epoch": 2.982791586998088,
|
| 564 |
+
"step": 1560
|
| 565 |
+
},
|
| 566 |
+
{
|
| 567 |
+
"eval_loss": 1.6626524925231934,
|
| 568 |
+
"eval_accuracy": 0.6542885973763874,
|
| 569 |
+
"eval_runtime": 1164.8432,
|
| 570 |
+
"eval_samples_per_second": 12.761,
|
| 571 |
+
"eval_steps_per_second": 12.761,
|
| 572 |
+
"epoch": 3.0,
|
| 573 |
+
"step": 1569
|
| 574 |
+
},
|
| 575 |
+
{
|
| 576 |
+
"loss": 2.2228,
|
| 577 |
+
"grad_norm": 2.2067298889160156,
|
| 578 |
+
"learning_rate": 0.0003877204164011047,
|
| 579 |
+
"epoch": 3.0210325047801145,
|
| 580 |
+
"step": 1580
|
| 581 |
+
},
|
| 582 |
+
{
|
| 583 |
+
"loss": 2.1788,
|
| 584 |
+
"grad_norm": 2.2736258506774902,
|
| 585 |
+
"learning_rate": 0.00038559592096876997,
|
| 586 |
+
"epoch": 3.0592734225621414,
|
| 587 |
+
"step": 1600
|
| 588 |
+
},
|
| 589 |
+
{
|
| 590 |
+
"loss": 2.1743,
|
| 591 |
+
"grad_norm": 2.324817419052124,
|
| 592 |
+
"learning_rate": 0.0003834714255364351,
|
| 593 |
+
"epoch": 3.0975143403441683,
|
| 594 |
+
"step": 1620
|
| 595 |
+
},
|
| 596 |
+
{
|
| 597 |
+
"loss": 2.1267,
|
| 598 |
+
"grad_norm": 2.188101291656494,
|
| 599 |
+
"learning_rate": 0.00038134693010410026,
|
| 600 |
+
"epoch": 3.135755258126195,
|
| 601 |
+
"step": 1640
|
| 602 |
+
},
|
| 603 |
+
{
|
| 604 |
+
"loss": 2.0835,
|
| 605 |
+
"grad_norm": 2.2637600898742676,
|
| 606 |
+
"learning_rate": 0.00037922243467176546,
|
| 607 |
+
"epoch": 3.173996175908222,
|
| 608 |
+
"step": 1660
|
| 609 |
+
},
|
| 610 |
+
{
|
| 611 |
+
"loss": 2.0944,
|
| 612 |
+
"grad_norm": 2.2315452098846436,
|
| 613 |
+
"learning_rate": 0.00037709793923943065,
|
| 614 |
+
"epoch": 3.2122370936902485,
|
| 615 |
+
"step": 1680
|
| 616 |
+
},
|
| 617 |
+
{
|
| 618 |
+
"loss": 2.0867,
|
| 619 |
+
"grad_norm": 2.236682176589966,
|
| 620 |
+
"learning_rate": 0.0003749734438070958,
|
| 621 |
+
"epoch": 3.2504780114722753,
|
| 622 |
+
"step": 1700
|
| 623 |
+
},
|
| 624 |
+
{
|
| 625 |
+
"loss": 2.0138,
|
| 626 |
+
"grad_norm": 2.1970863342285156,
|
| 627 |
+
"learning_rate": 0.000372848948374761,
|
| 628 |
+
"epoch": 3.288718929254302,
|
| 629 |
+
"step": 1720
|
| 630 |
+
},
|
| 631 |
+
{
|
| 632 |
+
"loss": 2.0081,
|
| 633 |
+
"grad_norm": 2.2857913970947266,
|
| 634 |
+
"learning_rate": 0.0003707244529424262,
|
| 635 |
+
"epoch": 3.3269598470363286,
|
| 636 |
+
"step": 1740
|
| 637 |
+
},
|
| 638 |
+
{
|
| 639 |
+
"loss": 1.9887,
|
| 640 |
+
"grad_norm": 2.256211280822754,
|
| 641 |
+
"learning_rate": 0.00036859995751009134,
|
| 642 |
+
"epoch": 3.3652007648183555,
|
| 643 |
+
"step": 1760
|
| 644 |
+
},
|
| 645 |
+
{
|
| 646 |
+
"loss": 1.9965,
|
| 647 |
+
"grad_norm": 2.3634960651397705,
|
| 648 |
+
"learning_rate": 0.00036647546207775654,
|
| 649 |
+
"epoch": 3.4034416826003824,
|
| 650 |
+
"step": 1780
|
| 651 |
+
},
|
| 652 |
+
{
|
| 653 |
+
"loss": 2.0024,
|
| 654 |
+
"grad_norm": 2.2254064083099365,
|
| 655 |
+
"learning_rate": 0.00036435096664542174,
|
| 656 |
+
"epoch": 3.4416826003824093,
|
| 657 |
+
"step": 1800
|
| 658 |
+
},
|
| 659 |
+
{
|
| 660 |
+
"loss": 2.0024,
|
| 661 |
+
"grad_norm": 2.271703004837036,
|
| 662 |
+
"learning_rate": 0.0003622264712130869,
|
| 663 |
+
"epoch": 3.479923518164436,
|
| 664 |
+
"step": 1820
|
| 665 |
+
},
|
| 666 |
+
{
|
| 667 |
+
"loss": 1.9561,
|
| 668 |
+
"grad_norm": 2.220524549484253,
|
| 669 |
+
"learning_rate": 0.0003601019757807521,
|
| 670 |
+
"epoch": 3.5181644359464626,
|
| 671 |
+
"step": 1840
|
| 672 |
+
},
|
| 673 |
+
{
|
| 674 |
+
"loss": 1.9641,
|
| 675 |
+
"grad_norm": 2.3010692596435547,
|
| 676 |
+
"learning_rate": 0.0003579774803484173,
|
| 677 |
+
"epoch": 3.5564053537284894,
|
| 678 |
+
"step": 1860
|
| 679 |
+
},
|
| 680 |
+
{
|
| 681 |
+
"loss": 1.9032,
|
| 682 |
+
"grad_norm": 2.2860300540924072,
|
| 683 |
+
"learning_rate": 0.00035585298491608243,
|
| 684 |
+
"epoch": 3.5946462715105163,
|
| 685 |
+
"step": 1880
|
| 686 |
+
},
|
| 687 |
+
{
|
| 688 |
+
"loss": 1.9115,
|
| 689 |
+
"grad_norm": 2.2572293281555176,
|
| 690 |
+
"learning_rate": 0.00035372848948374763,
|
| 691 |
+
"epoch": 3.632887189292543,
|
| 692 |
+
"step": 1900
|
| 693 |
+
},
|
| 694 |
+
{
|
| 695 |
+
"loss": 1.8957,
|
| 696 |
+
"grad_norm": 2.441771984100342,
|
| 697 |
+
"learning_rate": 0.0003516039940514128,
|
| 698 |
+
"epoch": 3.67112810707457,
|
| 699 |
+
"step": 1920
|
| 700 |
+
},
|
| 701 |
+
{
|
| 702 |
+
"loss": 1.8638,
|
| 703 |
+
"grad_norm": 2.3750736713409424,
|
| 704 |
+
"learning_rate": 0.00034947949861907797,
|
| 705 |
+
"epoch": 3.7093690248565965,
|
| 706 |
+
"step": 1940
|
| 707 |
+
},
|
| 708 |
+
{
|
| 709 |
+
"loss": 1.8105,
|
| 710 |
+
"grad_norm": 2.114288806915283,
|
| 711 |
+
"learning_rate": 0.00034735500318674317,
|
| 712 |
+
"epoch": 3.7476099426386233,
|
| 713 |
+
"step": 1960
|
| 714 |
+
},
|
| 715 |
+
{
|
| 716 |
+
"loss": 1.8908,
|
| 717 |
+
"grad_norm": 2.3129258155822754,
|
| 718 |
+
"learning_rate": 0.0003452305077544083,
|
| 719 |
+
"epoch": 3.78585086042065,
|
| 720 |
+
"step": 1980
|
| 721 |
+
},
|
| 722 |
+
{
|
| 723 |
+
"loss": 1.8116,
|
| 724 |
+
"grad_norm": 2.217604398727417,
|
| 725 |
+
"learning_rate": 0.0003431060123220735,
|
| 726 |
+
"epoch": 3.8240917782026767,
|
| 727 |
+
"step": 2000
|
| 728 |
+
},
|
| 729 |
+
{
|
| 730 |
+
"loss": 1.8325,
|
| 731 |
+
"grad_norm": 2.2592735290527344,
|
| 732 |
+
"learning_rate": 0.0003409815168897387,
|
| 733 |
+
"epoch": 3.8623326959847035,
|
| 734 |
+
"step": 2020
|
| 735 |
+
},
|
| 736 |
+
{
|
| 737 |
+
"loss": 1.7757,
|
| 738 |
+
"grad_norm": 2.321389675140381,
|
| 739 |
+
"learning_rate": 0.00033885702145740386,
|
| 740 |
+
"epoch": 3.9005736137667304,
|
| 741 |
+
"step": 2040
|
| 742 |
+
},
|
| 743 |
+
{
|
| 744 |
+
"loss": 1.7801,
|
| 745 |
+
"grad_norm": 2.0709521770477295,
|
| 746 |
+
"learning_rate": 0.00033673252602506906,
|
| 747 |
+
"epoch": 3.9388145315487573,
|
| 748 |
+
"step": 2060
|
| 749 |
+
},
|
| 750 |
+
{
|
| 751 |
+
"loss": 1.7576,
|
| 752 |
+
"grad_norm": 2.3316352367401123,
|
| 753 |
+
"learning_rate": 0.00033460803059273426,
|
| 754 |
+
"epoch": 3.977055449330784,
|
| 755 |
+
"step": 2080
|
| 756 |
+
},
|
| 757 |
+
{
|
| 758 |
+
"eval_loss": 1.1761366128921509,
|
| 759 |
+
"eval_accuracy": 0.758627648839556,
|
| 760 |
+
"eval_runtime": 910.1664,
|
| 761 |
+
"eval_samples_per_second": 16.332,
|
| 762 |
+
"eval_steps_per_second": 16.332,
|
| 763 |
+
"epoch": 4.0,
|
| 764 |
+
"step": 2092
|
| 765 |
+
},
|
| 766 |
+
{
|
| 767 |
+
"loss": 1.7157,
|
| 768 |
+
"grad_norm": 2.2446036338806152,
|
| 769 |
+
"learning_rate": 0.0003324835351603994,
|
| 770 |
+
"epoch": 4.015296367112811,
|
| 771 |
+
"step": 2100
|
| 772 |
+
},
|
| 773 |
+
{
|
| 774 |
+
"loss": 1.6126,
|
| 775 |
+
"grad_norm": 2.1550064086914062,
|
| 776 |
+
"learning_rate": 0.0003303590397280646,
|
| 777 |
+
"epoch": 4.053537284894838,
|
| 778 |
+
"step": 2120
|
| 779 |
+
},
|
| 780 |
+
{
|
| 781 |
+
"loss": 1.6417,
|
| 782 |
+
"grad_norm": 2.3542799949645996,
|
| 783 |
+
"learning_rate": 0.0003282345442957298,
|
| 784 |
+
"epoch": 4.091778202676864,
|
| 785 |
+
"step": 2140
|
| 786 |
+
},
|
| 787 |
+
{
|
| 788 |
+
"loss": 1.6108,
|
| 789 |
+
"grad_norm": 2.3036603927612305,
|
| 790 |
+
"learning_rate": 0.00032611004886339494,
|
| 791 |
+
"epoch": 4.130019120458891,
|
| 792 |
+
"step": 2160
|
| 793 |
+
},
|
| 794 |
+
{
|
| 795 |
+
"loss": 1.5939,
|
| 796 |
+
"grad_norm": 2.168532133102417,
|
| 797 |
+
"learning_rate": 0.00032398555343106014,
|
| 798 |
+
"epoch": 4.168260038240918,
|
| 799 |
+
"step": 2180
|
| 800 |
+
},
|
| 801 |
+
{
|
| 802 |
+
"loss": 1.6157,
|
| 803 |
+
"grad_norm": 2.257270097732544,
|
| 804 |
+
"learning_rate": 0.0003218610579987253,
|
| 805 |
+
"epoch": 4.2065009560229445,
|
| 806 |
+
"step": 2200
|
| 807 |
+
},
|
| 808 |
+
{
|
| 809 |
+
"loss": 1.6477,
|
| 810 |
+
"grad_norm": 2.2476625442504883,
|
| 811 |
+
"learning_rate": 0.0003197365625663905,
|
| 812 |
+
"epoch": 4.244741873804971,
|
| 813 |
+
"step": 2220
|
| 814 |
+
},
|
| 815 |
+
{
|
| 816 |
+
"loss": 1.5589,
|
| 817 |
+
"grad_norm": 2.162182092666626,
|
| 818 |
+
"learning_rate": 0.00031761206713405563,
|
| 819 |
+
"epoch": 4.282982791586998,
|
| 820 |
+
"step": 2240
|
| 821 |
+
},
|
| 822 |
+
{
|
| 823 |
+
"loss": 1.5683,
|
| 824 |
+
"grad_norm": 2.084498167037964,
|
| 825 |
+
"learning_rate": 0.00031548757170172083,
|
| 826 |
+
"epoch": 4.321223709369025,
|
| 827 |
+
"step": 2260
|
| 828 |
+
},
|
| 829 |
+
{
|
| 830 |
+
"loss": 1.5324,
|
| 831 |
+
"grad_norm": 2.1769893169403076,
|
| 832 |
+
"learning_rate": 0.00031336307626938603,
|
| 833 |
+
"epoch": 4.359464627151052,
|
| 834 |
+
"step": 2280
|
| 835 |
+
},
|
| 836 |
+
{
|
| 837 |
+
"loss": 1.5551,
|
| 838 |
+
"grad_norm": 2.1961722373962402,
|
| 839 |
+
"learning_rate": 0.0003112385808370512,
|
| 840 |
+
"epoch": 4.397705544933078,
|
| 841 |
+
"step": 2300
|
| 842 |
+
},
|
| 843 |
+
{
|
| 844 |
+
"loss": 1.5724,
|
| 845 |
+
"grad_norm": 2.2195024490356445,
|
| 846 |
+
"learning_rate": 0.0003091140854047164,
|
| 847 |
+
"epoch": 4.435946462715105,
|
| 848 |
+
"step": 2320
|
| 849 |
+
},
|
| 850 |
+
{
|
| 851 |
+
"loss": 1.5322,
|
| 852 |
+
"grad_norm": 2.18676495552063,
|
| 853 |
+
"learning_rate": 0.0003069895899723816,
|
| 854 |
+
"epoch": 4.474187380497132,
|
| 855 |
+
"step": 2340
|
| 856 |
+
},
|
| 857 |
+
{
|
| 858 |
+
"loss": 1.5207,
|
| 859 |
+
"grad_norm": 2.2305195331573486,
|
| 860 |
+
"learning_rate": 0.0003048650945400467,
|
| 861 |
+
"epoch": 4.512428298279159,
|
| 862 |
+
"step": 2360
|
| 863 |
+
},
|
| 864 |
+
{
|
| 865 |
+
"loss": 1.5712,
|
| 866 |
+
"grad_norm": 2.297010898590088,
|
| 867 |
+
"learning_rate": 0.0003027405991077119,
|
| 868 |
+
"epoch": 4.550669216061186,
|
| 869 |
+
"step": 2380
|
| 870 |
+
},
|
| 871 |
+
{
|
| 872 |
+
"loss": 1.513,
|
| 873 |
+
"grad_norm": 2.261610746383667,
|
| 874 |
+
"learning_rate": 0.0003006161036753771,
|
| 875 |
+
"epoch": 4.588910133843212,
|
| 876 |
+
"step": 2400
|
| 877 |
+
},
|
| 878 |
+
{
|
| 879 |
+
"loss": 1.4854,
|
| 880 |
+
"grad_norm": 2.1144425868988037,
|
| 881 |
+
"learning_rate": 0.00029849160824304226,
|
| 882 |
+
"epoch": 4.627151051625239,
|
| 883 |
+
"step": 2420
|
| 884 |
+
},
|
| 885 |
+
{
|
| 886 |
+
"loss": 1.5025,
|
| 887 |
+
"grad_norm": 2.344909191131592,
|
| 888 |
+
"learning_rate": 0.00029636711281070746,
|
| 889 |
+
"epoch": 4.665391969407266,
|
| 890 |
+
"step": 2440
|
| 891 |
+
},
|
| 892 |
+
{
|
| 893 |
+
"loss": 1.4917,
|
| 894 |
+
"grad_norm": 2.1943275928497314,
|
| 895 |
+
"learning_rate": 0.00029424261737837266,
|
| 896 |
+
"epoch": 4.7036328871892925,
|
| 897 |
+
"step": 2460
|
| 898 |
+
},
|
| 899 |
+
{
|
| 900 |
+
"loss": 1.4539,
|
| 901 |
+
"grad_norm": 2.191070079803467,
|
| 902 |
+
"learning_rate": 0.0002921181219460378,
|
| 903 |
+
"epoch": 4.741873804971319,
|
| 904 |
+
"step": 2480
|
| 905 |
+
},
|
| 906 |
+
{
|
| 907 |
+
"loss": 1.4688,
|
| 908 |
+
"grad_norm": 2.142045259475708,
|
| 909 |
+
"learning_rate": 0.000289993626513703,
|
| 910 |
+
"epoch": 4.780114722753346,
|
| 911 |
+
"step": 2500
|
| 912 |
+
},
|
| 913 |
+
{
|
| 914 |
+
"loss": 1.4236,
|
| 915 |
+
"grad_norm": 2.203152656555176,
|
| 916 |
+
"learning_rate": 0.0002878691310813682,
|
| 917 |
+
"epoch": 4.818355640535373,
|
| 918 |
+
"step": 2520
|
| 919 |
+
},
|
| 920 |
+
{
|
| 921 |
+
"loss": 1.4211,
|
| 922 |
+
"grad_norm": 2.264139175415039,
|
| 923 |
+
"learning_rate": 0.00028574463564903335,
|
| 924 |
+
"epoch": 4.8565965583174,
|
| 925 |
+
"step": 2540
|
| 926 |
+
},
|
| 927 |
+
{
|
| 928 |
+
"loss": 1.4236,
|
| 929 |
+
"grad_norm": 2.173497438430786,
|
| 930 |
+
"learning_rate": 0.0002836201402166985,
|
| 931 |
+
"epoch": 4.894837476099426,
|
| 932 |
+
"step": 2560
|
| 933 |
+
},
|
| 934 |
+
{
|
| 935 |
+
"loss": 1.3804,
|
| 936 |
+
"grad_norm": 2.069350481033325,
|
| 937 |
+
"learning_rate": 0.00028149564478436375,
|
| 938 |
+
"epoch": 4.933078393881453,
|
| 939 |
+
"step": 2580
|
| 940 |
+
},
|
| 941 |
+
{
|
| 942 |
+
"loss": 1.3706,
|
| 943 |
+
"grad_norm": 2.1907660961151123,
|
| 944 |
+
"learning_rate": 0.0002793711493520289,
|
| 945 |
+
"epoch": 4.97131931166348,
|
| 946 |
+
"step": 2600
|
| 947 |
+
},
|
| 948 |
+
{
|
| 949 |
+
"eval_loss": 0.8903235793113708,
|
| 950 |
+
"eval_accuracy": 0.8203834510595358,
|
| 951 |
+
"eval_runtime": 813.2495,
|
| 952 |
+
"eval_samples_per_second": 18.279,
|
| 953 |
+
"eval_steps_per_second": 18.279,
|
| 954 |
+
"epoch": 5.0,
|
| 955 |
+
"step": 2615
|
| 956 |
+
},
|
| 957 |
+
{
|
| 958 |
+
"loss": 1.3611,
|
| 959 |
+
"grad_norm": 2.2395236492156982,
|
| 960 |
+
"learning_rate": 0.00027724665391969404,
|
| 961 |
+
"epoch": 5.009560229445507,
|
| 962 |
+
"step": 2620
|
| 963 |
+
},
|
| 964 |
+
{
|
| 965 |
+
"loss": 1.2885,
|
| 966 |
+
"grad_norm": 2.164022922515869,
|
| 967 |
+
"learning_rate": 0.0002751221584873593,
|
| 968 |
+
"epoch": 5.047801147227533,
|
| 969 |
+
"step": 2640
|
| 970 |
+
},
|
| 971 |
+
{
|
| 972 |
+
"loss": 1.3024,
|
| 973 |
+
"grad_norm": 2.335524559020996,
|
| 974 |
+
"learning_rate": 0.00027299766305502443,
|
| 975 |
+
"epoch": 5.08604206500956,
|
| 976 |
+
"step": 2660
|
| 977 |
+
},
|
| 978 |
+
{
|
| 979 |
+
"loss": 1.2819,
|
| 980 |
+
"grad_norm": 2.3510003089904785,
|
| 981 |
+
"learning_rate": 0.0002708731676226896,
|
| 982 |
+
"epoch": 5.124282982791587,
|
| 983 |
+
"step": 2680
|
| 984 |
+
},
|
| 985 |
+
{
|
| 986 |
+
"loss": 1.2927,
|
| 987 |
+
"grad_norm": 2.2182960510253906,
|
| 988 |
+
"learning_rate": 0.00026874867219035483,
|
| 989 |
+
"epoch": 5.162523900573614,
|
| 990 |
+
"step": 2700
|
| 991 |
+
},
|
| 992 |
+
{
|
| 993 |
+
"loss": 1.2905,
|
| 994 |
+
"grad_norm": 2.164422035217285,
|
| 995 |
+
"learning_rate": 0.00026662417675802,
|
| 996 |
+
"epoch": 5.2007648183556405,
|
| 997 |
+
"step": 2720
|
| 998 |
+
},
|
| 999 |
+
{
|
| 1000 |
+
"loss": 1.3067,
|
| 1001 |
+
"grad_norm": 2.2719788551330566,
|
| 1002 |
+
"learning_rate": 0.0002644996813256851,
|
| 1003 |
+
"epoch": 5.239005736137667,
|
| 1004 |
+
"step": 2740
|
| 1005 |
+
},
|
| 1006 |
+
{
|
| 1007 |
+
"loss": 1.2778,
|
| 1008 |
+
"grad_norm": 2.1733806133270264,
|
| 1009 |
+
"learning_rate": 0.0002623751858933504,
|
| 1010 |
+
"epoch": 5.277246653919694,
|
| 1011 |
+
"step": 2760
|
| 1012 |
+
},
|
| 1013 |
+
{
|
| 1014 |
+
"loss": 1.2553,
|
| 1015 |
+
"grad_norm": 2.0940115451812744,
|
| 1016 |
+
"learning_rate": 0.0002602506904610155,
|
| 1017 |
+
"epoch": 5.315487571701721,
|
| 1018 |
+
"step": 2780
|
| 1019 |
+
},
|
| 1020 |
+
{
|
| 1021 |
+
"loss": 1.2572,
|
| 1022 |
+
"grad_norm": 2.049928665161133,
|
| 1023 |
+
"learning_rate": 0.00025812619502868067,
|
| 1024 |
+
"epoch": 5.353728489483748,
|
| 1025 |
+
"step": 2800
|
| 1026 |
+
},
|
| 1027 |
+
{
|
| 1028 |
+
"loss": 1.2139,
|
| 1029 |
+
"grad_norm": 2.039212703704834,
|
| 1030 |
+
"learning_rate": 0.0002560016995963459,
|
| 1031 |
+
"epoch": 5.3919694072657744,
|
| 1032 |
+
"step": 2820
|
| 1033 |
+
},
|
| 1034 |
+
{
|
| 1035 |
+
"loss": 1.2591,
|
| 1036 |
+
"grad_norm": 2.2491774559020996,
|
| 1037 |
+
"learning_rate": 0.00025387720416401106,
|
| 1038 |
+
"epoch": 5.430210325047801,
|
| 1039 |
+
"step": 2840
|
| 1040 |
+
},
|
| 1041 |
+
{
|
| 1042 |
+
"loss": 1.2458,
|
| 1043 |
+
"grad_norm": 2.1145877838134766,
|
| 1044 |
+
"learning_rate": 0.0002517527087316762,
|
| 1045 |
+
"epoch": 5.468451242829828,
|
| 1046 |
+
"step": 2860
|
| 1047 |
+
},
|
| 1048 |
+
{
|
| 1049 |
+
"loss": 1.227,
|
| 1050 |
+
"grad_norm": 2.1274683475494385,
|
| 1051 |
+
"learning_rate": 0.0002496282132993414,
|
| 1052 |
+
"epoch": 5.506692160611855,
|
| 1053 |
+
"step": 2880
|
| 1054 |
+
},
|
| 1055 |
+
{
|
| 1056 |
+
"loss": 1.1897,
|
| 1057 |
+
"grad_norm": 2.0846710205078125,
|
| 1058 |
+
"learning_rate": 0.0002475037178670066,
|
| 1059 |
+
"epoch": 5.544933078393882,
|
| 1060 |
+
"step": 2900
|
| 1061 |
+
},
|
| 1062 |
+
{
|
| 1063 |
+
"loss": 1.2133,
|
| 1064 |
+
"grad_norm": 2.143688678741455,
|
| 1065 |
+
"learning_rate": 0.0002453792224346718,
|
| 1066 |
+
"epoch": 5.583173996175908,
|
| 1067 |
+
"step": 2920
|
| 1068 |
+
},
|
| 1069 |
+
{
|
| 1070 |
+
"loss": 1.2194,
|
| 1071 |
+
"grad_norm": 2.2568676471710205,
|
| 1072 |
+
"learning_rate": 0.00024325472700233695,
|
| 1073 |
+
"epoch": 5.621414913957935,
|
| 1074 |
+
"step": 2940
|
| 1075 |
+
},
|
| 1076 |
+
{
|
| 1077 |
+
"loss": 1.1895,
|
| 1078 |
+
"grad_norm": 2.266052484512329,
|
| 1079 |
+
"learning_rate": 0.00024113023157000212,
|
| 1080 |
+
"epoch": 5.659655831739962,
|
| 1081 |
+
"step": 2960
|
| 1082 |
+
},
|
| 1083 |
+
{
|
| 1084 |
+
"loss": 1.1849,
|
| 1085 |
+
"grad_norm": 2.352609395980835,
|
| 1086 |
+
"learning_rate": 0.0002390057361376673,
|
| 1087 |
+
"epoch": 5.6978967495219885,
|
| 1088 |
+
"step": 2980
|
| 1089 |
+
},
|
| 1090 |
+
{
|
| 1091 |
+
"loss": 1.205,
|
| 1092 |
+
"grad_norm": 2.1269915103912354,
|
| 1093 |
+
"learning_rate": 0.0002368812407053325,
|
| 1094 |
+
"epoch": 5.736137667304015,
|
| 1095 |
+
"step": 3000
|
| 1096 |
+
},
|
| 1097 |
+
{
|
| 1098 |
+
"loss": 1.1366,
|
| 1099 |
+
"grad_norm": 2.20017147064209,
|
| 1100 |
+
"learning_rate": 0.00023475674527299767,
|
| 1101 |
+
"epoch": 5.774378585086042,
|
| 1102 |
+
"step": 3020
|
| 1103 |
+
},
|
| 1104 |
+
{
|
| 1105 |
+
"loss": 1.1268,
|
| 1106 |
+
"grad_norm": 2.0107390880584717,
|
| 1107 |
+
"learning_rate": 0.00023263224984066284,
|
| 1108 |
+
"epoch": 5.812619502868069,
|
| 1109 |
+
"step": 3040
|
| 1110 |
+
},
|
| 1111 |
+
{
|
| 1112 |
+
"loss": 1.1619,
|
| 1113 |
+
"grad_norm": 2.091771364212036,
|
| 1114 |
+
"learning_rate": 0.00023050775440832804,
|
| 1115 |
+
"epoch": 5.850860420650095,
|
| 1116 |
+
"step": 3060
|
| 1117 |
+
},
|
| 1118 |
+
{
|
| 1119 |
+
"loss": 1.1789,
|
| 1120 |
+
"grad_norm": 2.261592388153076,
|
| 1121 |
+
"learning_rate": 0.0002283832589759932,
|
| 1122 |
+
"epoch": 5.8891013384321225,
|
| 1123 |
+
"step": 3080
|
| 1124 |
+
},
|
| 1125 |
+
{
|
| 1126 |
+
"loss": 1.1492,
|
| 1127 |
+
"grad_norm": 2.126786947250366,
|
| 1128 |
+
"learning_rate": 0.00022625876354365838,
|
| 1129 |
+
"epoch": 5.927342256214149,
|
| 1130 |
+
"step": 3100
|
| 1131 |
+
},
|
| 1132 |
+
{
|
| 1133 |
+
"loss": 1.1258,
|
| 1134 |
+
"grad_norm": 2.123417615890503,
|
| 1135 |
+
"learning_rate": 0.00022413426811132355,
|
| 1136 |
+
"epoch": 5.965583173996176,
|
| 1137 |
+
"step": 3120
|
| 1138 |
+
},
|
| 1139 |
+
{
|
| 1140 |
+
"eval_loss": 0.7555378079414368,
|
| 1141 |
+
"eval_accuracy": 0.8432559704002691,
|
| 1142 |
+
"eval_runtime": 1118.6028,
|
| 1143 |
+
"eval_samples_per_second": 13.289,
|
| 1144 |
+
"eval_steps_per_second": 13.289,
|
| 1145 |
+
"epoch": 6.0,
|
| 1146 |
+
"step": 3138
|
| 1147 |
+
},
|
| 1148 |
+
{
|
| 1149 |
+
"loss": 1.1086,
|
| 1150 |
+
"grad_norm": 2.0020689964294434,
|
| 1151 |
+
"learning_rate": 0.00022200977267898875,
|
| 1152 |
+
"epoch": 6.003824091778203,
|
| 1153 |
+
"step": 3140
|
| 1154 |
+
},
|
| 1155 |
+
{
|
| 1156 |
+
"loss": 1.0815,
|
| 1157 |
+
"grad_norm": 2.0867371559143066,
|
| 1158 |
+
"learning_rate": 0.00021988527724665392,
|
| 1159 |
+
"epoch": 6.042065009560229,
|
| 1160 |
+
"step": 3160
|
| 1161 |
+
},
|
| 1162 |
+
{
|
| 1163 |
+
"loss": 1.0412,
|
| 1164 |
+
"grad_norm": 1.9533103704452515,
|
| 1165 |
+
"learning_rate": 0.0002177607818143191,
|
| 1166 |
+
"epoch": 6.080305927342256,
|
| 1167 |
+
"step": 3180
|
| 1168 |
+
},
|
| 1169 |
+
{
|
| 1170 |
+
"loss": 1.0312,
|
| 1171 |
+
"grad_norm": 2.2522337436676025,
|
| 1172 |
+
"learning_rate": 0.0002156362863819843,
|
| 1173 |
+
"epoch": 6.118546845124283,
|
| 1174 |
+
"step": 3200
|
| 1175 |
+
},
|
| 1176 |
+
{
|
| 1177 |
+
"loss": 1.0449,
|
| 1178 |
+
"grad_norm": 2.058983087539673,
|
| 1179 |
+
"learning_rate": 0.00021351179094964944,
|
| 1180 |
+
"epoch": 6.15678776290631,
|
| 1181 |
+
"step": 3220
|
| 1182 |
+
},
|
| 1183 |
+
{
|
| 1184 |
+
"loss": 1.0532,
|
| 1185 |
+
"grad_norm": 2.1774373054504395,
|
| 1186 |
+
"learning_rate": 0.00021138729551731464,
|
| 1187 |
+
"epoch": 6.195028680688337,
|
| 1188 |
+
"step": 3240
|
| 1189 |
+
},
|
| 1190 |
+
{
|
| 1191 |
+
"loss": 1.0461,
|
| 1192 |
+
"grad_norm": 2.0248055458068848,
|
| 1193 |
+
"learning_rate": 0.00020926280008497984,
|
| 1194 |
+
"epoch": 6.233269598470363,
|
| 1195 |
+
"step": 3260
|
| 1196 |
+
},
|
| 1197 |
+
{
|
| 1198 |
+
"loss": 1.0243,
|
| 1199 |
+
"grad_norm": 2.066737651824951,
|
| 1200 |
+
"learning_rate": 0.00020713830465264498,
|
| 1201 |
+
"epoch": 6.27151051625239,
|
| 1202 |
+
"step": 3280
|
| 1203 |
+
},
|
| 1204 |
+
{
|
| 1205 |
+
"loss": 1.0309,
|
| 1206 |
+
"grad_norm": 2.100133180618286,
|
| 1207 |
+
"learning_rate": 0.00020501380922031018,
|
| 1208 |
+
"epoch": 6.309751434034417,
|
| 1209 |
+
"step": 3300
|
| 1210 |
+
},
|
| 1211 |
+
{
|
| 1212 |
+
"loss": 1.0147,
|
| 1213 |
+
"grad_norm": 2.192960739135742,
|
| 1214 |
+
"learning_rate": 0.00020288931378797538,
|
| 1215 |
+
"epoch": 6.347992351816444,
|
| 1216 |
+
"step": 3320
|
| 1217 |
+
},
|
| 1218 |
+
{
|
| 1219 |
+
"loss": 1.0229,
|
| 1220 |
+
"grad_norm": 2.123382329940796,
|
| 1221 |
+
"learning_rate": 0.00020076481835564053,
|
| 1222 |
+
"epoch": 6.3862332695984705,
|
| 1223 |
+
"step": 3340
|
| 1224 |
+
},
|
| 1225 |
+
{
|
| 1226 |
+
"loss": 1.011,
|
| 1227 |
+
"grad_norm": 2.162189245223999,
|
| 1228 |
+
"learning_rate": 0.00019864032292330573,
|
| 1229 |
+
"epoch": 6.424474187380497,
|
| 1230 |
+
"step": 3360
|
| 1231 |
+
},
|
| 1232 |
+
{
|
| 1233 |
+
"loss": 0.9929,
|
| 1234 |
+
"grad_norm": 2.254284143447876,
|
| 1235 |
+
"learning_rate": 0.0001965158274909709,
|
| 1236 |
+
"epoch": 6.462715105162524,
|
| 1237 |
+
"step": 3380
|
| 1238 |
+
},
|
| 1239 |
+
{
|
| 1240 |
+
"loss": 0.9852,
|
| 1241 |
+
"grad_norm": 2.2183146476745605,
|
| 1242 |
+
"learning_rate": 0.00019439133205863607,
|
| 1243 |
+
"epoch": 6.500956022944551,
|
| 1244 |
+
"step": 3400
|
| 1245 |
+
},
|
| 1246 |
+
{
|
| 1247 |
+
"loss": 1.0129,
|
| 1248 |
+
"grad_norm": 2.1704065799713135,
|
| 1249 |
+
"learning_rate": 0.00019226683662630127,
|
| 1250 |
+
"epoch": 6.539196940726577,
|
| 1251 |
+
"step": 3420
|
| 1252 |
+
},
|
| 1253 |
+
{
|
| 1254 |
+
"loss": 0.9667,
|
| 1255 |
+
"grad_norm": 2.0828094482421875,
|
| 1256 |
+
"learning_rate": 0.00019014234119396644,
|
| 1257 |
+
"epoch": 6.577437858508604,
|
| 1258 |
+
"step": 3440
|
| 1259 |
+
},
|
| 1260 |
+
{
|
| 1261 |
+
"loss": 0.9769,
|
| 1262 |
+
"grad_norm": 2.3150341510772705,
|
| 1263 |
+
"learning_rate": 0.0001880178457616316,
|
| 1264 |
+
"epoch": 6.615678776290631,
|
| 1265 |
+
"step": 3460
|
| 1266 |
+
},
|
| 1267 |
+
{
|
| 1268 |
+
"loss": 0.979,
|
| 1269 |
+
"grad_norm": 2.0636775493621826,
|
| 1270 |
+
"learning_rate": 0.0001858933503292968,
|
| 1271 |
+
"epoch": 6.653919694072657,
|
| 1272 |
+
"step": 3480
|
| 1273 |
+
},
|
| 1274 |
+
{
|
| 1275 |
+
"loss": 0.9667,
|
| 1276 |
+
"grad_norm": 2.171602487564087,
|
| 1277 |
+
"learning_rate": 0.00018376885489696196,
|
| 1278 |
+
"epoch": 6.692160611854685,
|
| 1279 |
+
"step": 3500
|
| 1280 |
+
},
|
| 1281 |
+
{
|
| 1282 |
+
"loss": 0.9593,
|
| 1283 |
+
"grad_norm": 2.1150522232055664,
|
| 1284 |
+
"learning_rate": 0.00018164435946462716,
|
| 1285 |
+
"epoch": 6.730401529636711,
|
| 1286 |
+
"step": 3520
|
| 1287 |
+
},
|
| 1288 |
+
{
|
| 1289 |
+
"loss": 0.9828,
|
| 1290 |
+
"grad_norm": 2.096452236175537,
|
| 1291 |
+
"learning_rate": 0.00017951986403229233,
|
| 1292 |
+
"epoch": 6.768642447418738,
|
| 1293 |
+
"step": 3540
|
| 1294 |
+
},
|
| 1295 |
+
{
|
| 1296 |
+
"loss": 0.9648,
|
| 1297 |
+
"grad_norm": 2.2779390811920166,
|
| 1298 |
+
"learning_rate": 0.0001773953685999575,
|
| 1299 |
+
"epoch": 6.806883365200765,
|
| 1300 |
+
"step": 3560
|
| 1301 |
+
},
|
| 1302 |
+
{
|
| 1303 |
+
"loss": 0.9639,
|
| 1304 |
+
"grad_norm": 2.2793240547180176,
|
| 1305 |
+
"learning_rate": 0.0001752708731676227,
|
| 1306 |
+
"epoch": 6.845124282982791,
|
| 1307 |
+
"step": 3580
|
| 1308 |
+
},
|
| 1309 |
+
{
|
| 1310 |
+
"loss": 0.9421,
|
| 1311 |
+
"grad_norm": 2.0822837352752686,
|
| 1312 |
+
"learning_rate": 0.00017314637773528787,
|
| 1313 |
+
"epoch": 6.8833652007648185,
|
| 1314 |
+
"step": 3600
|
| 1315 |
+
},
|
| 1316 |
+
{
|
| 1317 |
+
"loss": 0.9277,
|
| 1318 |
+
"grad_norm": 2.1541502475738525,
|
| 1319 |
+
"learning_rate": 0.00017102188230295304,
|
| 1320 |
+
"epoch": 6.921606118546845,
|
| 1321 |
+
"step": 3620
|
| 1322 |
+
},
|
| 1323 |
+
{
|
| 1324 |
+
"loss": 0.9335,
|
| 1325 |
+
"grad_norm": 2.1241962909698486,
|
| 1326 |
+
"learning_rate": 0.00016889738687061824,
|
| 1327 |
+
"epoch": 6.959847036328872,
|
| 1328 |
+
"step": 3640
|
| 1329 |
+
},
|
| 1330 |
+
{
|
| 1331 |
+
"loss": 0.9379,
|
| 1332 |
+
"grad_norm": 2.2354745864868164,
|
| 1333 |
+
"learning_rate": 0.00016677289143828341,
|
| 1334 |
+
"epoch": 6.998087954110899,
|
| 1335 |
+
"step": 3660
|
| 1336 |
+
},
|
| 1337 |
+
{
|
| 1338 |
+
"eval_loss": 0.5586521029472351,
|
| 1339 |
+
"eval_accuracy": 0.889673730238816,
|
| 1340 |
+
"eval_runtime": 904.3879,
|
| 1341 |
+
"eval_samples_per_second": 16.437,
|
| 1342 |
+
"eval_steps_per_second": 16.437,
|
| 1343 |
+
"epoch": 7.0,
|
| 1344 |
+
"step": 3661
|
| 1345 |
+
},
|
| 1346 |
+
{
|
| 1347 |
+
"loss": 0.8485,
|
| 1348 |
+
"grad_norm": 2.109501600265503,
|
| 1349 |
+
"learning_rate": 0.0001646483960059486,
|
| 1350 |
+
"epoch": 7.036328871892925,
|
| 1351 |
+
"step": 3680
|
| 1352 |
+
},
|
| 1353 |
+
{
|
| 1354 |
+
"loss": 0.897,
|
| 1355 |
+
"grad_norm": 2.2034125328063965,
|
| 1356 |
+
"learning_rate": 0.00016252390057361376,
|
| 1357 |
+
"epoch": 7.074569789674952,
|
| 1358 |
+
"step": 3700
|
| 1359 |
+
},
|
| 1360 |
+
{
|
| 1361 |
+
"loss": 0.859,
|
| 1362 |
+
"grad_norm": 2.053767204284668,
|
| 1363 |
+
"learning_rate": 0.00016039940514127896,
|
| 1364 |
+
"epoch": 7.112810707456979,
|
| 1365 |
+
"step": 3720
|
| 1366 |
+
},
|
| 1367 |
+
{
|
| 1368 |
+
"loss": 0.8643,
|
| 1369 |
+
"grad_norm": 1.977229118347168,
|
| 1370 |
+
"learning_rate": 0.00015827490970894413,
|
| 1371 |
+
"epoch": 7.151051625239006,
|
| 1372 |
+
"step": 3740
|
| 1373 |
+
},
|
| 1374 |
+
{
|
| 1375 |
+
"loss": 0.8665,
|
| 1376 |
+
"grad_norm": 2.0782172679901123,
|
| 1377 |
+
"learning_rate": 0.0001561504142766093,
|
| 1378 |
+
"epoch": 7.189292543021033,
|
| 1379 |
+
"step": 3760
|
| 1380 |
+
},
|
| 1381 |
+
{
|
| 1382 |
+
"loss": 0.8748,
|
| 1383 |
+
"grad_norm": 1.9473881721496582,
|
| 1384 |
+
"learning_rate": 0.0001540259188442745,
|
| 1385 |
+
"epoch": 7.227533460803059,
|
| 1386 |
+
"step": 3780
|
| 1387 |
+
},
|
| 1388 |
+
{
|
| 1389 |
+
"loss": 0.8589,
|
| 1390 |
+
"grad_norm": 2.0109825134277344,
|
| 1391 |
+
"learning_rate": 0.00015190142341193967,
|
| 1392 |
+
"epoch": 7.265774378585086,
|
| 1393 |
+
"step": 3800
|
| 1394 |
+
},
|
| 1395 |
+
{
|
| 1396 |
+
"loss": 0.8373,
|
| 1397 |
+
"grad_norm": 2.1534509658813477,
|
| 1398 |
+
"learning_rate": 0.00014977692797960484,
|
| 1399 |
+
"epoch": 7.304015296367113,
|
| 1400 |
+
"step": 3820
|
| 1401 |
+
},
|
| 1402 |
+
{
|
| 1403 |
+
"loss": 0.8487,
|
| 1404 |
+
"grad_norm": 2.1457502841949463,
|
| 1405 |
+
"learning_rate": 0.00014765243254727004,
|
| 1406 |
+
"epoch": 7.342256214149139,
|
| 1407 |
+
"step": 3840
|
| 1408 |
+
},
|
| 1409 |
+
{
|
| 1410 |
+
"loss": 0.841,
|
| 1411 |
+
"grad_norm": 2.200446844100952,
|
| 1412 |
+
"learning_rate": 0.0001455279371149352,
|
| 1413 |
+
"epoch": 7.3804971319311665,
|
| 1414 |
+
"step": 3860
|
| 1415 |
+
},
|
| 1416 |
+
{
|
| 1417 |
+
"loss": 0.846,
|
| 1418 |
+
"grad_norm": 2.0335378646850586,
|
| 1419 |
+
"learning_rate": 0.0001434034416826004,
|
| 1420 |
+
"epoch": 7.418738049713193,
|
| 1421 |
+
"step": 3880
|
| 1422 |
+
},
|
| 1423 |
+
{
|
| 1424 |
+
"loss": 0.8442,
|
| 1425 |
+
"grad_norm": 2.1471550464630127,
|
| 1426 |
+
"learning_rate": 0.0001412789462502656,
|
| 1427 |
+
"epoch": 7.45697896749522,
|
| 1428 |
+
"step": 3900
|
| 1429 |
+
},
|
| 1430 |
+
{
|
| 1431 |
+
"loss": 0.8651,
|
| 1432 |
+
"grad_norm": 2.2554261684417725,
|
| 1433 |
+
"learning_rate": 0.00013915445081793073,
|
| 1434 |
+
"epoch": 7.495219885277247,
|
| 1435 |
+
"step": 3920
|
| 1436 |
+
},
|
| 1437 |
+
{
|
| 1438 |
+
"loss": 0.839,
|
| 1439 |
+
"grad_norm": 2.1498897075653076,
|
| 1440 |
+
"learning_rate": 0.00013702995538559593,
|
| 1441 |
+
"epoch": 7.533460803059273,
|
| 1442 |
+
"step": 3940
|
| 1443 |
+
},
|
| 1444 |
+
{
|
| 1445 |
+
"loss": 0.8449,
|
| 1446 |
+
"grad_norm": 2.1460678577423096,
|
| 1447 |
+
"learning_rate": 0.00013490545995326113,
|
| 1448 |
+
"epoch": 7.5717017208413,
|
| 1449 |
+
"step": 3960
|
| 1450 |
+
},
|
| 1451 |
+
{
|
| 1452 |
+
"loss": 0.8075,
|
| 1453 |
+
"grad_norm": 2.194730281829834,
|
| 1454 |
+
"learning_rate": 0.00013278096452092628,
|
| 1455 |
+
"epoch": 7.609942638623327,
|
| 1456 |
+
"step": 3980
|
| 1457 |
+
},
|
| 1458 |
+
{
|
| 1459 |
+
"loss": 0.8163,
|
| 1460 |
+
"grad_norm": 2.291327714920044,
|
| 1461 |
+
"learning_rate": 0.00013065646908859147,
|
| 1462 |
+
"epoch": 7.648183556405353,
|
| 1463 |
+
"step": 4000
|
| 1464 |
+
},
|
| 1465 |
+
{
|
| 1466 |
+
"loss": 0.7999,
|
| 1467 |
+
"grad_norm": 2.049647808074951,
|
| 1468 |
+
"learning_rate": 0.00012853197365625662,
|
| 1469 |
+
"epoch": 7.686424474187381,
|
| 1470 |
+
"step": 4020
|
| 1471 |
+
},
|
| 1472 |
+
{
|
| 1473 |
+
"loss": 0.7721,
|
| 1474 |
+
"grad_norm": 2.026001214981079,
|
| 1475 |
+
"learning_rate": 0.00012640747822392182,
|
| 1476 |
+
"epoch": 7.724665391969407,
|
| 1477 |
+
"step": 4040
|
| 1478 |
+
},
|
| 1479 |
+
{
|
| 1480 |
+
"loss": 0.7957,
|
| 1481 |
+
"grad_norm": 2.1242027282714844,
|
| 1482 |
+
"learning_rate": 0.00012428298279158702,
|
| 1483 |
+
"epoch": 7.762906309751434,
|
| 1484 |
+
"step": 4060
|
| 1485 |
+
},
|
| 1486 |
+
{
|
| 1487 |
+
"loss": 0.8244,
|
| 1488 |
+
"grad_norm": 2.078123092651367,
|
| 1489 |
+
"learning_rate": 0.0001221584873592522,
|
| 1490 |
+
"epoch": 7.801147227533461,
|
| 1491 |
+
"step": 4080
|
| 1492 |
+
},
|
| 1493 |
+
{
|
| 1494 |
+
"loss": 0.8066,
|
| 1495 |
+
"grad_norm": 2.028822183609009,
|
| 1496 |
+
"learning_rate": 0.00012003399192691736,
|
| 1497 |
+
"epoch": 7.839388145315487,
|
| 1498 |
+
"step": 4100
|
| 1499 |
+
},
|
| 1500 |
+
{
|
| 1501 |
+
"loss": 0.7892,
|
| 1502 |
+
"grad_norm": 2.30352520942688,
|
| 1503 |
+
"learning_rate": 0.00011790949649458253,
|
| 1504 |
+
"epoch": 7.8776290630975145,
|
| 1505 |
+
"step": 4120
|
| 1506 |
+
},
|
| 1507 |
+
{
|
| 1508 |
+
"loss": 0.7703,
|
| 1509 |
+
"grad_norm": 2.100221872329712,
|
| 1510 |
+
"learning_rate": 0.00011578500106224772,
|
| 1511 |
+
"epoch": 7.915869980879541,
|
| 1512 |
+
"step": 4140
|
| 1513 |
+
},
|
| 1514 |
+
{
|
| 1515 |
+
"loss": 0.7958,
|
| 1516 |
+
"grad_norm": 2.1163010597229004,
|
| 1517 |
+
"learning_rate": 0.00011366050562991289,
|
| 1518 |
+
"epoch": 7.954110898661568,
|
| 1519 |
+
"step": 4160
|
| 1520 |
+
},
|
| 1521 |
+
{
|
| 1522 |
+
"loss": 0.7925,
|
| 1523 |
+
"grad_norm": 2.194089412689209,
|
| 1524 |
+
"learning_rate": 0.00011153601019757808,
|
| 1525 |
+
"epoch": 7.992351816443595,
|
| 1526 |
+
"step": 4180
|
| 1527 |
+
},
|
| 1528 |
+
{
|
| 1529 |
+
"eval_loss": 0.4518139362335205,
|
| 1530 |
+
"eval_accuracy": 0.9117389841910528,
|
| 1531 |
+
"eval_runtime": 1278.572,
|
| 1532 |
+
"eval_samples_per_second": 11.626,
|
| 1533 |
+
"eval_steps_per_second": 11.626,
|
| 1534 |
+
"epoch": 8.0,
|
| 1535 |
+
"step": 4184
|
| 1536 |
+
},
|
| 1537 |
+
{
|
| 1538 |
+
"loss": 0.7768,
|
| 1539 |
+
"grad_norm": 2.024029016494751,
|
| 1540 |
+
"learning_rate": 0.00010941151476524326,
|
| 1541 |
+
"epoch": 8.030592734225621,
|
| 1542 |
+
"step": 4200
|
| 1543 |
+
},
|
| 1544 |
+
{
|
| 1545 |
+
"loss": 0.7174,
|
| 1546 |
+
"grad_norm": 2.101900577545166,
|
| 1547 |
+
"learning_rate": 0.00010728701933290843,
|
| 1548 |
+
"epoch": 8.068833652007648,
|
| 1549 |
+
"step": 4220
|
| 1550 |
+
},
|
| 1551 |
+
{
|
| 1552 |
+
"loss": 0.7331,
|
| 1553 |
+
"grad_norm": 1.8774019479751587,
|
| 1554 |
+
"learning_rate": 0.0001051625239005736,
|
| 1555 |
+
"epoch": 8.107074569789676,
|
| 1556 |
+
"step": 4240
|
| 1557 |
+
},
|
| 1558 |
+
{
|
| 1559 |
+
"loss": 0.6988,
|
| 1560 |
+
"grad_norm": 2.0548768043518066,
|
| 1561 |
+
"learning_rate": 0.0001030380284682388,
|
| 1562 |
+
"epoch": 8.145315487571702,
|
| 1563 |
+
"step": 4260
|
| 1564 |
+
},
|
| 1565 |
+
{
|
| 1566 |
+
"loss": 0.7329,
|
| 1567 |
+
"grad_norm": 2.09981107711792,
|
| 1568 |
+
"learning_rate": 0.00010091353303590398,
|
| 1569 |
+
"epoch": 8.183556405353729,
|
| 1570 |
+
"step": 4280
|
| 1571 |
+
},
|
| 1572 |
+
{
|
| 1573 |
+
"loss": 0.7085,
|
| 1574 |
+
"grad_norm": 1.9958146810531616,
|
| 1575 |
+
"learning_rate": 9.878903760356915e-05,
|
| 1576 |
+
"epoch": 8.221797323135755,
|
| 1577 |
+
"step": 4300
|
| 1578 |
+
},
|
| 1579 |
+
{
|
| 1580 |
+
"loss": 0.715,
|
| 1581 |
+
"grad_norm": 1.9749237298965454,
|
| 1582 |
+
"learning_rate": 9.666454217123433e-05,
|
| 1583 |
+
"epoch": 8.260038240917781,
|
| 1584 |
+
"step": 4320
|
| 1585 |
+
},
|
| 1586 |
+
{
|
| 1587 |
+
"loss": 0.7151,
|
| 1588 |
+
"grad_norm": 1.9691994190216064,
|
| 1589 |
+
"learning_rate": 9.454004673889952e-05,
|
| 1590 |
+
"epoch": 8.29827915869981,
|
| 1591 |
+
"step": 4340
|
| 1592 |
+
},
|
| 1593 |
+
{
|
| 1594 |
+
"loss": 0.7249,
|
| 1595 |
+
"grad_norm": 2.1549344062805176,
|
| 1596 |
+
"learning_rate": 9.241555130656469e-05,
|
| 1597 |
+
"epoch": 8.336520076481836,
|
| 1598 |
+
"step": 4360
|
| 1599 |
+
},
|
| 1600 |
+
{
|
| 1601 |
+
"loss": 0.7207,
|
| 1602 |
+
"grad_norm": 2.2257604598999023,
|
| 1603 |
+
"learning_rate": 9.029105587422986e-05,
|
| 1604 |
+
"epoch": 8.374760994263863,
|
| 1605 |
+
"step": 4380
|
| 1606 |
+
},
|
| 1607 |
+
{
|
| 1608 |
+
"loss": 0.6981,
|
| 1609 |
+
"grad_norm": 2.0424046516418457,
|
| 1610 |
+
"learning_rate": 8.816656044189505e-05,
|
| 1611 |
+
"epoch": 8.413001912045889,
|
| 1612 |
+
"step": 4400
|
| 1613 |
+
},
|
| 1614 |
+
{
|
| 1615 |
+
"loss": 0.7153,
|
| 1616 |
+
"grad_norm": 1.8724883794784546,
|
| 1617 |
+
"learning_rate": 8.604206500956024e-05,
|
| 1618 |
+
"epoch": 8.451242829827915,
|
| 1619 |
+
"step": 4420
|
| 1620 |
+
},
|
| 1621 |
+
{
|
| 1622 |
+
"loss": 0.7254,
|
| 1623 |
+
"grad_norm": 2.0893712043762207,
|
| 1624 |
+
"learning_rate": 8.391756957722541e-05,
|
| 1625 |
+
"epoch": 8.489483747609942,
|
| 1626 |
+
"step": 4440
|
| 1627 |
+
},
|
| 1628 |
+
{
|
| 1629 |
+
"loss": 0.7184,
|
| 1630 |
+
"grad_norm": 2.0398759841918945,
|
| 1631 |
+
"learning_rate": 8.179307414489059e-05,
|
| 1632 |
+
"epoch": 8.52772466539197,
|
| 1633 |
+
"step": 4460
|
| 1634 |
+
},
|
| 1635 |
+
{
|
| 1636 |
+
"loss": 0.7189,
|
| 1637 |
+
"grad_norm": 2.1322920322418213,
|
| 1638 |
+
"learning_rate": 7.966857871255577e-05,
|
| 1639 |
+
"epoch": 8.565965583173996,
|
| 1640 |
+
"step": 4480
|
| 1641 |
+
},
|
| 1642 |
+
{
|
| 1643 |
+
"loss": 0.705,
|
| 1644 |
+
"grad_norm": 2.0477068424224854,
|
| 1645 |
+
"learning_rate": 7.754408328022095e-05,
|
| 1646 |
+
"epoch": 8.604206500956023,
|
| 1647 |
+
"step": 4500
|
| 1648 |
+
},
|
| 1649 |
+
{
|
| 1650 |
+
"loss": 0.7285,
|
| 1651 |
+
"grad_norm": 2.0737295150756836,
|
| 1652 |
+
"learning_rate": 7.541958784788614e-05,
|
| 1653 |
+
"epoch": 8.64244741873805,
|
| 1654 |
+
"step": 4520
|
| 1655 |
+
},
|
| 1656 |
+
{
|
| 1657 |
+
"loss": 0.7028,
|
| 1658 |
+
"grad_norm": 1.9542038440704346,
|
| 1659 |
+
"learning_rate": 7.329509241555131e-05,
|
| 1660 |
+
"epoch": 8.680688336520076,
|
| 1661 |
+
"step": 4540
|
| 1662 |
+
},
|
| 1663 |
+
{
|
| 1664 |
+
"loss": 0.7031,
|
| 1665 |
+
"grad_norm": 1.9409737586975098,
|
| 1666 |
+
"learning_rate": 7.117059698321648e-05,
|
| 1667 |
+
"epoch": 8.718929254302104,
|
| 1668 |
+
"step": 4560
|
| 1669 |
+
},
|
| 1670 |
+
{
|
| 1671 |
+
"loss": 0.6909,
|
| 1672 |
+
"grad_norm": 1.982315182685852,
|
| 1673 |
+
"learning_rate": 6.904610155088168e-05,
|
| 1674 |
+
"epoch": 8.75717017208413,
|
| 1675 |
+
"step": 4580
|
| 1676 |
+
},
|
| 1677 |
+
{
|
| 1678 |
+
"loss": 0.7083,
|
| 1679 |
+
"grad_norm": 2.2722830772399902,
|
| 1680 |
+
"learning_rate": 6.692160611854685e-05,
|
| 1681 |
+
"epoch": 8.795411089866157,
|
| 1682 |
+
"step": 4600
|
| 1683 |
+
},
|
| 1684 |
+
{
|
| 1685 |
+
"loss": 0.6885,
|
| 1686 |
+
"grad_norm": 1.9158116579055786,
|
| 1687 |
+
"learning_rate": 6.479711068621202e-05,
|
| 1688 |
+
"epoch": 8.833652007648183,
|
| 1689 |
+
"step": 4620
|
| 1690 |
+
},
|
| 1691 |
+
{
|
| 1692 |
+
"loss": 0.6912,
|
| 1693 |
+
"grad_norm": 2.058122396469116,
|
| 1694 |
+
"learning_rate": 6.26726152538772e-05,
|
| 1695 |
+
"epoch": 8.87189292543021,
|
| 1696 |
+
"step": 4640
|
| 1697 |
+
},
|
| 1698 |
+
{
|
| 1699 |
+
"loss": 0.6937,
|
| 1700 |
+
"grad_norm": 2.013585090637207,
|
| 1701 |
+
"learning_rate": 6.054811982154239e-05,
|
| 1702 |
+
"epoch": 8.910133843212238,
|
| 1703 |
+
"step": 4660
|
| 1704 |
+
},
|
| 1705 |
+
{
|
| 1706 |
+
"loss": 0.7003,
|
| 1707 |
+
"grad_norm": 2.1662707328796387,
|
| 1708 |
+
"learning_rate": 5.8423624389207567e-05,
|
| 1709 |
+
"epoch": 8.948374760994264,
|
| 1710 |
+
"step": 4680
|
| 1711 |
+
},
|
| 1712 |
+
{
|
| 1713 |
+
"loss": 0.6733,
|
| 1714 |
+
"grad_norm": 2.06309175491333,
|
| 1715 |
+
"learning_rate": 5.6299128956872745e-05,
|
| 1716 |
+
"epoch": 8.98661567877629,
|
| 1717 |
+
"step": 4700
|
| 1718 |
+
},
|
| 1719 |
+
{
|
| 1720 |
+
"eval_loss": 0.38889044523239136,
|
| 1721 |
+
"eval_accuracy": 0.929297006390851,
|
| 1722 |
+
"eval_runtime": 1336.4014,
|
| 1723 |
+
"eval_samples_per_second": 11.123,
|
| 1724 |
+
"eval_steps_per_second": 11.123,
|
| 1725 |
+
"epoch": 9.0,
|
| 1726 |
+
"step": 4707
|
| 1727 |
+
},
|
| 1728 |
+
{
|
| 1729 |
+
"loss": 0.6593,
|
| 1730 |
+
"grad_norm": 1.8986388444900513,
|
| 1731 |
+
"learning_rate": 5.4174633524537924e-05,
|
| 1732 |
+
"epoch": 9.024856596558317,
|
| 1733 |
+
"step": 4720
|
| 1734 |
+
},
|
| 1735 |
+
{
|
| 1736 |
+
"loss": 0.6354,
|
| 1737 |
+
"grad_norm": 1.9107776880264282,
|
| 1738 |
+
"learning_rate": 5.20501380922031e-05,
|
| 1739 |
+
"epoch": 9.063097514340344,
|
| 1740 |
+
"step": 4740
|
| 1741 |
+
},
|
| 1742 |
+
{
|
| 1743 |
+
"loss": 0.6531,
|
| 1744 |
+
"grad_norm": 2.0714404582977295,
|
| 1745 |
+
"learning_rate": 4.992564265986829e-05,
|
| 1746 |
+
"epoch": 9.101338432122372,
|
| 1747 |
+
"step": 4760
|
| 1748 |
+
},
|
| 1749 |
+
{
|
| 1750 |
+
"loss": 0.6429,
|
| 1751 |
+
"grad_norm": 1.9571270942687988,
|
| 1752 |
+
"learning_rate": 4.780114722753346e-05,
|
| 1753 |
+
"epoch": 9.139579349904398,
|
| 1754 |
+
"step": 4780
|
| 1755 |
+
},
|
| 1756 |
+
{
|
| 1757 |
+
"loss": 0.6498,
|
| 1758 |
+
"grad_norm": 1.9968469142913818,
|
| 1759 |
+
"learning_rate": 4.5676651795198646e-05,
|
| 1760 |
+
"epoch": 9.177820267686425,
|
| 1761 |
+
"step": 4800
|
| 1762 |
+
},
|
| 1763 |
+
{
|
| 1764 |
+
"loss": 0.6141,
|
| 1765 |
+
"grad_norm": 1.982832670211792,
|
| 1766 |
+
"learning_rate": 4.355215636286382e-05,
|
| 1767 |
+
"epoch": 9.216061185468451,
|
| 1768 |
+
"step": 4820
|
| 1769 |
+
},
|
| 1770 |
+
{
|
| 1771 |
+
"loss": 0.6269,
|
| 1772 |
+
"grad_norm": 2.035123825073242,
|
| 1773 |
+
"learning_rate": 4.1427660930529e-05,
|
| 1774 |
+
"epoch": 9.254302103250478,
|
| 1775 |
+
"step": 4840
|
| 1776 |
+
},
|
| 1777 |
+
{
|
| 1778 |
+
"loss": 0.6143,
|
| 1779 |
+
"grad_norm": 1.8670984506607056,
|
| 1780 |
+
"learning_rate": 3.930316549819418e-05,
|
| 1781 |
+
"epoch": 9.292543021032504,
|
| 1782 |
+
"step": 4860
|
| 1783 |
+
},
|
| 1784 |
+
{
|
| 1785 |
+
"loss": 0.6352,
|
| 1786 |
+
"grad_norm": 1.9521456956863403,
|
| 1787 |
+
"learning_rate": 3.7178670065859354e-05,
|
| 1788 |
+
"epoch": 9.330783938814532,
|
| 1789 |
+
"step": 4880
|
| 1790 |
+
},
|
| 1791 |
+
{
|
| 1792 |
+
"loss": 0.6214,
|
| 1793 |
+
"grad_norm": 1.9804260730743408,
|
| 1794 |
+
"learning_rate": 3.505417463352454e-05,
|
| 1795 |
+
"epoch": 9.369024856596559,
|
| 1796 |
+
"step": 4900
|
| 1797 |
+
},
|
| 1798 |
+
{
|
| 1799 |
+
"loss": 0.655,
|
| 1800 |
+
"grad_norm": 2.149338483810425,
|
| 1801 |
+
"learning_rate": 3.292967920118971e-05,
|
| 1802 |
+
"epoch": 9.407265774378585,
|
| 1803 |
+
"step": 4920
|
| 1804 |
+
},
|
| 1805 |
+
{
|
| 1806 |
+
"loss": 0.6095,
|
| 1807 |
+
"grad_norm": 1.8145477771759033,
|
| 1808 |
+
"learning_rate": 3.08051837688549e-05,
|
| 1809 |
+
"epoch": 9.445506692160611,
|
| 1810 |
+
"step": 4940
|
| 1811 |
+
},
|
| 1812 |
+
{
|
| 1813 |
+
"loss": 0.6314,
|
| 1814 |
+
"grad_norm": 2.009587287902832,
|
| 1815 |
+
"learning_rate": 2.8680688336520076e-05,
|
| 1816 |
+
"epoch": 9.483747609942638,
|
| 1817 |
+
"step": 4960
|
| 1818 |
+
},
|
| 1819 |
+
{
|
| 1820 |
+
"loss": 0.6272,
|
| 1821 |
+
"grad_norm": 1.946964979171753,
|
| 1822 |
+
"learning_rate": 2.655619290418526e-05,
|
| 1823 |
+
"epoch": 9.521988527724666,
|
| 1824 |
+
"step": 4980
|
| 1825 |
+
},
|
| 1826 |
+
{
|
| 1827 |
+
"loss": 0.6133,
|
| 1828 |
+
"grad_norm": 2.2486774921417236,
|
| 1829 |
+
"learning_rate": 2.4431697471850437e-05,
|
| 1830 |
+
"epoch": 9.560229445506693,
|
| 1831 |
+
"step": 5000
|
| 1832 |
+
},
|
| 1833 |
+
{
|
| 1834 |
+
"loss": 0.6185,
|
| 1835 |
+
"grad_norm": 1.9570778608322144,
|
| 1836 |
+
"learning_rate": 2.2307202039515616e-05,
|
| 1837 |
+
"epoch": 9.598470363288719,
|
| 1838 |
+
"step": 5020
|
| 1839 |
+
},
|
| 1840 |
+
{
|
| 1841 |
+
"loss": 0.6366,
|
| 1842 |
+
"grad_norm": 1.8994139432907104,
|
| 1843 |
+
"learning_rate": 2.0182706607180795e-05,
|
| 1844 |
+
"epoch": 9.636711281070745,
|
| 1845 |
+
"step": 5040
|
| 1846 |
+
},
|
| 1847 |
+
{
|
| 1848 |
+
"loss": 0.6414,
|
| 1849 |
+
"grad_norm": 2.102374792098999,
|
| 1850 |
+
"learning_rate": 1.8058211174845977e-05,
|
| 1851 |
+
"epoch": 9.674952198852772,
|
| 1852 |
+
"step": 5060
|
| 1853 |
+
},
|
| 1854 |
+
{
|
| 1855 |
+
"loss": 0.6053,
|
| 1856 |
+
"grad_norm": 2.073791027069092,
|
| 1857 |
+
"learning_rate": 1.5933715742511156e-05,
|
| 1858 |
+
"epoch": 9.7131931166348,
|
| 1859 |
+
"step": 5080
|
| 1860 |
+
},
|
| 1861 |
+
{
|
| 1862 |
+
"loss": 0.6032,
|
| 1863 |
+
"grad_norm": 1.9205766916275024,
|
| 1864 |
+
"learning_rate": 1.3809220310176333e-05,
|
| 1865 |
+
"epoch": 9.751434034416826,
|
| 1866 |
+
"step": 5100
|
| 1867 |
+
},
|
| 1868 |
+
{
|
| 1869 |
+
"loss": 0.6202,
|
| 1870 |
+
"grad_norm": 2.04294490814209,
|
| 1871 |
+
"learning_rate": 1.1684724877841512e-05,
|
| 1872 |
+
"epoch": 9.789674952198853,
|
| 1873 |
+
"step": 5120
|
| 1874 |
+
},
|
| 1875 |
+
{
|
| 1876 |
+
"loss": 0.5882,
|
| 1877 |
+
"grad_norm": 1.9936119318008423,
|
| 1878 |
+
"learning_rate": 9.560229445506692e-06,
|
| 1879 |
+
"epoch": 9.82791586998088,
|
| 1880 |
+
"step": 5140
|
| 1881 |
+
},
|
| 1882 |
+
{
|
| 1883 |
+
"loss": 0.5955,
|
| 1884 |
+
"grad_norm": 1.8728615045547485,
|
| 1885 |
+
"learning_rate": 7.435734013171872e-06,
|
| 1886 |
+
"epoch": 9.866156787762906,
|
| 1887 |
+
"step": 5160
|
| 1888 |
+
},
|
| 1889 |
+
{
|
| 1890 |
+
"loss": 0.6049,
|
| 1891 |
+
"grad_norm": 2.069910764694214,
|
| 1892 |
+
"learning_rate": 5.311238580837051e-06,
|
| 1893 |
+
"epoch": 9.904397705544934,
|
| 1894 |
+
"step": 5180
|
| 1895 |
+
},
|
| 1896 |
+
{
|
| 1897 |
+
"loss": 0.6251,
|
| 1898 |
+
"grad_norm": 1.9873836040496826,
|
| 1899 |
+
"learning_rate": 3.1867431485022306e-06,
|
| 1900 |
+
"epoch": 9.94263862332696,
|
| 1901 |
+
"step": 5200
|
| 1902 |
+
},
|
| 1903 |
+
{
|
| 1904 |
+
"loss": 0.6187,
|
| 1905 |
+
"grad_norm": 1.932947039604187,
|
| 1906 |
+
"learning_rate": 1.0622477161674102e-06,
|
| 1907 |
+
"epoch": 9.980879541108987,
|
| 1908 |
+
"step": 5220
|
| 1909 |
+
},
|
| 1910 |
+
{
|
| 1911 |
+
"eval_loss": 0.35941872000694275,
|
| 1912 |
+
"eval_accuracy": 0.9340733266061217,
|
| 1913 |
+
"eval_runtime": 1417.2186,
|
| 1914 |
+
"eval_samples_per_second": 10.489,
|
| 1915 |
+
"eval_steps_per_second": 10.489,
|
| 1916 |
+
"epoch": 10.0,
|
| 1917 |
+
"step": 5230
|
| 1918 |
+
},
|
| 1919 |
+
{
|
| 1920 |
+
"train_runtime": 94798.7749,
|
| 1921 |
+
"train_samples_per_second": 14.112,
|
| 1922 |
+
"train_steps_per_second": 0.055,
|
| 1923 |
+
"total_flos": 2.7283641066057605e+18,
|
| 1924 |
+
"train_loss": 1.9864544938672797,
|
| 1925 |
+
"epoch": 10.0,
|
| 1926 |
+
"step": 5230
|
| 1927 |
+
}
|
| 1928 |
+
]
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 10.0,
|
| 3 |
+
"total_flos": 2.7283641066057605e+18,
|
| 4 |
+
"train_loss": 1.9864544938672797,
|
| 5 |
+
"train_runtime": 94798.7749,
|
| 6 |
+
"train_samples_per_second": 14.112,
|
| 7 |
+
"train_steps_per_second": 0.055
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,1959 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.9340733266061217,
|
| 3 |
+
"best_model_checkpoint": "/mnt/data4_HDD_14TB/yang/voxceleb-checkpoints/etdnn/voxceleb1/pretrain/ce-len3-bs256-lr5e-4/checkpoint-5230",
|
| 4 |
+
"epoch": 10.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 5230,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.03824091778202677,
|
| 13 |
+
"grad_norm": 10.999133110046387,
|
| 14 |
+
"learning_rate": 1.9120458891013384e-05,
|
| 15 |
+
"loss": 7.1473,
|
| 16 |
+
"step": 20
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.07648183556405354,
|
| 20 |
+
"grad_norm": 10.200960159301758,
|
| 21 |
+
"learning_rate": 3.824091778202677e-05,
|
| 22 |
+
"loss": 7.1283,
|
| 23 |
+
"step": 40
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.1147227533460803,
|
| 27 |
+
"grad_norm": 9.468878746032715,
|
| 28 |
+
"learning_rate": 5.736137667304015e-05,
|
| 29 |
+
"loss": 7.0847,
|
| 30 |
+
"step": 60
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.15296367112810708,
|
| 34 |
+
"grad_norm": 8.736529350280762,
|
| 35 |
+
"learning_rate": 7.648183556405354e-05,
|
| 36 |
+
"loss": 7.0321,
|
| 37 |
+
"step": 80
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.19120458891013384,
|
| 41 |
+
"grad_norm": 6.856561183929443,
|
| 42 |
+
"learning_rate": 9.560229445506692e-05,
|
| 43 |
+
"loss": 6.955,
|
| 44 |
+
"step": 100
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.2294455066921606,
|
| 48 |
+
"grad_norm": 5.473419666290283,
|
| 49 |
+
"learning_rate": 0.0001147227533460803,
|
| 50 |
+
"loss": 6.8474,
|
| 51 |
+
"step": 120
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.2676864244741874,
|
| 55 |
+
"grad_norm": 3.7059528827667236,
|
| 56 |
+
"learning_rate": 0.0001338432122370937,
|
| 57 |
+
"loss": 6.7002,
|
| 58 |
+
"step": 140
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.30592734225621415,
|
| 62 |
+
"grad_norm": 2.9125759601593018,
|
| 63 |
+
"learning_rate": 0.00015296367112810707,
|
| 64 |
+
"loss": 6.5368,
|
| 65 |
+
"step": 160
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.3441682600382409,
|
| 69 |
+
"grad_norm": 2.5546936988830566,
|
| 70 |
+
"learning_rate": 0.00017208413001912047,
|
| 71 |
+
"loss": 6.3399,
|
| 72 |
+
"step": 180
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.3824091778202677,
|
| 76 |
+
"grad_norm": 2.418347120285034,
|
| 77 |
+
"learning_rate": 0.00019120458891013384,
|
| 78 |
+
"loss": 6.1511,
|
| 79 |
+
"step": 200
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.42065009560229444,
|
| 83 |
+
"grad_norm": 2.2986104488372803,
|
| 84 |
+
"learning_rate": 0.0002103250478011472,
|
| 85 |
+
"loss": 6.015,
|
| 86 |
+
"step": 220
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.4588910133843212,
|
| 90 |
+
"grad_norm": 2.227661609649658,
|
| 91 |
+
"learning_rate": 0.0002294455066921606,
|
| 92 |
+
"loss": 5.8224,
|
| 93 |
+
"step": 240
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.497131931166348,
|
| 97 |
+
"grad_norm": 2.2191731929779053,
|
| 98 |
+
"learning_rate": 0.00024856596558317403,
|
| 99 |
+
"loss": 5.6838,
|
| 100 |
+
"step": 260
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 0.5353728489483748,
|
| 104 |
+
"grad_norm": 2.2345361709594727,
|
| 105 |
+
"learning_rate": 0.0002676864244741874,
|
| 106 |
+
"loss": 5.5764,
|
| 107 |
+
"step": 280
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.5736137667304015,
|
| 111 |
+
"grad_norm": 2.2029287815093994,
|
| 112 |
+
"learning_rate": 0.0002868068833652008,
|
| 113 |
+
"loss": 5.4715,
|
| 114 |
+
"step": 300
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.6118546845124283,
|
| 118 |
+
"grad_norm": 2.1917331218719482,
|
| 119 |
+
"learning_rate": 0.00030592734225621415,
|
| 120 |
+
"loss": 5.321,
|
| 121 |
+
"step": 320
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.6500956022944551,
|
| 125 |
+
"grad_norm": 2.2598936557769775,
|
| 126 |
+
"learning_rate": 0.0003250478011472275,
|
| 127 |
+
"loss": 5.2218,
|
| 128 |
+
"step": 340
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.6883365200764818,
|
| 132 |
+
"grad_norm": 2.3335328102111816,
|
| 133 |
+
"learning_rate": 0.00034416826003824094,
|
| 134 |
+
"loss": 5.1449,
|
| 135 |
+
"step": 360
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.7265774378585086,
|
| 139 |
+
"grad_norm": 2.3767151832580566,
|
| 140 |
+
"learning_rate": 0.0003632887189292543,
|
| 141 |
+
"loss": 5.0062,
|
| 142 |
+
"step": 380
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 0.7648183556405354,
|
| 146 |
+
"grad_norm": 2.357161521911621,
|
| 147 |
+
"learning_rate": 0.0003824091778202677,
|
| 148 |
+
"loss": 4.9352,
|
| 149 |
+
"step": 400
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 0.8030592734225621,
|
| 153 |
+
"grad_norm": 2.271972179412842,
|
| 154 |
+
"learning_rate": 0.00040152963671128105,
|
| 155 |
+
"loss": 4.8959,
|
| 156 |
+
"step": 420
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 0.8413001912045889,
|
| 160 |
+
"grad_norm": 2.4624767303466797,
|
| 161 |
+
"learning_rate": 0.0004206500956022944,
|
| 162 |
+
"loss": 4.7951,
|
| 163 |
+
"step": 440
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 0.8795411089866156,
|
| 167 |
+
"grad_norm": 2.1839234828948975,
|
| 168 |
+
"learning_rate": 0.00043977055449330785,
|
| 169 |
+
"loss": 4.6734,
|
| 170 |
+
"step": 460
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 0.9177820267686424,
|
| 174 |
+
"grad_norm": 2.3169806003570557,
|
| 175 |
+
"learning_rate": 0.0004588910133843212,
|
| 176 |
+
"loss": 4.6458,
|
| 177 |
+
"step": 480
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.9560229445506692,
|
| 181 |
+
"grad_norm": 2.3231122493743896,
|
| 182 |
+
"learning_rate": 0.0004780114722753346,
|
| 183 |
+
"loss": 4.5657,
|
| 184 |
+
"step": 500
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 0.994263862332696,
|
| 188 |
+
"grad_norm": 2.34975266456604,
|
| 189 |
+
"learning_rate": 0.0004971319311663481,
|
| 190 |
+
"loss": 4.489,
|
| 191 |
+
"step": 520
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 1.0,
|
| 195 |
+
"eval_accuracy": 0.1722166162125799,
|
| 196 |
+
"eval_loss": 4.208949089050293,
|
| 197 |
+
"eval_runtime": 1092.4973,
|
| 198 |
+
"eval_samples_per_second": 13.606,
|
| 199 |
+
"eval_steps_per_second": 13.606,
|
| 200 |
+
"step": 523
|
| 201 |
+
},
|
| 202 |
+
{
|
| 203 |
+
"epoch": 1.0325047801147227,
|
| 204 |
+
"grad_norm": 2.3869619369506836,
|
| 205 |
+
"learning_rate": 0.0004981941788825154,
|
| 206 |
+
"loss": 4.3496,
|
| 207 |
+
"step": 540
|
| 208 |
+
},
|
| 209 |
+
{
|
| 210 |
+
"epoch": 1.0707456978967496,
|
| 211 |
+
"grad_norm": 2.2834343910217285,
|
| 212 |
+
"learning_rate": 0.0004960696834501806,
|
| 213 |
+
"loss": 4.3108,
|
| 214 |
+
"step": 560
|
| 215 |
+
},
|
| 216 |
+
{
|
| 217 |
+
"epoch": 1.1089866156787762,
|
| 218 |
+
"grad_norm": 2.192180633544922,
|
| 219 |
+
"learning_rate": 0.0004939451880178457,
|
| 220 |
+
"loss": 4.229,
|
| 221 |
+
"step": 580
|
| 222 |
+
},
|
| 223 |
+
{
|
| 224 |
+
"epoch": 1.147227533460803,
|
| 225 |
+
"grad_norm": 2.161285161972046,
|
| 226 |
+
"learning_rate": 0.0004918206925855109,
|
| 227 |
+
"loss": 4.1804,
|
| 228 |
+
"step": 600
|
| 229 |
+
},
|
| 230 |
+
{
|
| 231 |
+
"epoch": 1.1854684512428297,
|
| 232 |
+
"grad_norm": 2.2634170055389404,
|
| 233 |
+
"learning_rate": 0.0004896961971531761,
|
| 234 |
+
"loss": 4.118,
|
| 235 |
+
"step": 620
|
| 236 |
+
},
|
| 237 |
+
{
|
| 238 |
+
"epoch": 1.2237093690248566,
|
| 239 |
+
"grad_norm": 2.1758434772491455,
|
| 240 |
+
"learning_rate": 0.00048757170172084133,
|
| 241 |
+
"loss": 4.0295,
|
| 242 |
+
"step": 640
|
| 243 |
+
},
|
| 244 |
+
{
|
| 245 |
+
"epoch": 1.2619502868068833,
|
| 246 |
+
"grad_norm": 2.25357985496521,
|
| 247 |
+
"learning_rate": 0.0004854472062885065,
|
| 248 |
+
"loss": 3.9559,
|
| 249 |
+
"step": 660
|
| 250 |
+
},
|
| 251 |
+
{
|
| 252 |
+
"epoch": 1.3001912045889101,
|
| 253 |
+
"grad_norm": 2.2077853679656982,
|
| 254 |
+
"learning_rate": 0.0004833227108561717,
|
| 255 |
+
"loss": 3.9295,
|
| 256 |
+
"step": 680
|
| 257 |
+
},
|
| 258 |
+
{
|
| 259 |
+
"epoch": 1.338432122370937,
|
| 260 |
+
"grad_norm": 2.28712797164917,
|
| 261 |
+
"learning_rate": 0.0004811982154238369,
|
| 262 |
+
"loss": 3.8221,
|
| 263 |
+
"step": 700
|
| 264 |
+
},
|
| 265 |
+
{
|
| 266 |
+
"epoch": 1.3766730401529637,
|
| 267 |
+
"grad_norm": 2.2988157272338867,
|
| 268 |
+
"learning_rate": 0.000479073719991502,
|
| 269 |
+
"loss": 3.7764,
|
| 270 |
+
"step": 720
|
| 271 |
+
},
|
| 272 |
+
{
|
| 273 |
+
"epoch": 1.4149139579349903,
|
| 274 |
+
"grad_norm": 2.391023874282837,
|
| 275 |
+
"learning_rate": 0.0004769492245591672,
|
| 276 |
+
"loss": 3.7518,
|
| 277 |
+
"step": 740
|
| 278 |
+
},
|
| 279 |
+
{
|
| 280 |
+
"epoch": 1.4531548757170172,
|
| 281 |
+
"grad_norm": 2.065288782119751,
|
| 282 |
+
"learning_rate": 0.00047482472912683236,
|
| 283 |
+
"loss": 3.7074,
|
| 284 |
+
"step": 760
|
| 285 |
+
},
|
| 286 |
+
{
|
| 287 |
+
"epoch": 1.491395793499044,
|
| 288 |
+
"grad_norm": 2.288686990737915,
|
| 289 |
+
"learning_rate": 0.00047270023369449756,
|
| 290 |
+
"loss": 3.6558,
|
| 291 |
+
"step": 780
|
| 292 |
+
},
|
| 293 |
+
{
|
| 294 |
+
"epoch": 1.5296367112810707,
|
| 295 |
+
"grad_norm": 2.228173017501831,
|
| 296 |
+
"learning_rate": 0.00047057573826216276,
|
| 297 |
+
"loss": 3.6038,
|
| 298 |
+
"step": 800
|
| 299 |
+
},
|
| 300 |
+
{
|
| 301 |
+
"epoch": 1.5678776290630974,
|
| 302 |
+
"grad_norm": 2.1894149780273438,
|
| 303 |
+
"learning_rate": 0.0004684512428298279,
|
| 304 |
+
"loss": 3.5405,
|
| 305 |
+
"step": 820
|
| 306 |
+
},
|
| 307 |
+
{
|
| 308 |
+
"epoch": 1.6061185468451242,
|
| 309 |
+
"grad_norm": 2.234192371368408,
|
| 310 |
+
"learning_rate": 0.0004663267473974931,
|
| 311 |
+
"loss": 3.4855,
|
| 312 |
+
"step": 840
|
| 313 |
+
},
|
| 314 |
+
{
|
| 315 |
+
"epoch": 1.644359464627151,
|
| 316 |
+
"grad_norm": 2.309387445449829,
|
| 317 |
+
"learning_rate": 0.0004642022519651583,
|
| 318 |
+
"loss": 3.4771,
|
| 319 |
+
"step": 860
|
| 320 |
+
},
|
| 321 |
+
{
|
| 322 |
+
"epoch": 1.682600382409178,
|
| 323 |
+
"grad_norm": 2.183579206466675,
|
| 324 |
+
"learning_rate": 0.00046207775653282345,
|
| 325 |
+
"loss": 3.3984,
|
| 326 |
+
"step": 880
|
| 327 |
+
},
|
| 328 |
+
{
|
| 329 |
+
"epoch": 1.7208413001912046,
|
| 330 |
+
"grad_norm": 2.286858558654785,
|
| 331 |
+
"learning_rate": 0.00045995326110048865,
|
| 332 |
+
"loss": 3.3318,
|
| 333 |
+
"step": 900
|
| 334 |
+
},
|
| 335 |
+
{
|
| 336 |
+
"epoch": 1.7590822179732313,
|
| 337 |
+
"grad_norm": 2.2087490558624268,
|
| 338 |
+
"learning_rate": 0.00045782876566815385,
|
| 339 |
+
"loss": 3.3256,
|
| 340 |
+
"step": 920
|
| 341 |
+
},
|
| 342 |
+
{
|
| 343 |
+
"epoch": 1.7973231357552581,
|
| 344 |
+
"grad_norm": 2.2571709156036377,
|
| 345 |
+
"learning_rate": 0.000455704270235819,
|
| 346 |
+
"loss": 3.2644,
|
| 347 |
+
"step": 940
|
| 348 |
+
},
|
| 349 |
+
{
|
| 350 |
+
"epoch": 1.835564053537285,
|
| 351 |
+
"grad_norm": 2.346696138381958,
|
| 352 |
+
"learning_rate": 0.0004535797748034842,
|
| 353 |
+
"loss": 3.2687,
|
| 354 |
+
"step": 960
|
| 355 |
+
},
|
| 356 |
+
{
|
| 357 |
+
"epoch": 1.8738049713193117,
|
| 358 |
+
"grad_norm": 2.309258460998535,
|
| 359 |
+
"learning_rate": 0.0004514552793711494,
|
| 360 |
+
"loss": 3.2346,
|
| 361 |
+
"step": 980
|
| 362 |
+
},
|
| 363 |
+
{
|
| 364 |
+
"epoch": 1.9120458891013383,
|
| 365 |
+
"grad_norm": 2.200920820236206,
|
| 366 |
+
"learning_rate": 0.00044933078393881453,
|
| 367 |
+
"loss": 3.1507,
|
| 368 |
+
"step": 1000
|
| 369 |
+
},
|
| 370 |
+
{
|
| 371 |
+
"epoch": 1.9502868068833652,
|
| 372 |
+
"grad_norm": 2.1627931594848633,
|
| 373 |
+
"learning_rate": 0.00044720628850647973,
|
| 374 |
+
"loss": 3.0884,
|
| 375 |
+
"step": 1020
|
| 376 |
+
},
|
| 377 |
+
{
|
| 378 |
+
"epoch": 1.988527724665392,
|
| 379 |
+
"grad_norm": 2.350935220718384,
|
| 380 |
+
"learning_rate": 0.00044508179307414493,
|
| 381 |
+
"loss": 3.0685,
|
| 382 |
+
"step": 1040
|
| 383 |
+
},
|
| 384 |
+
{
|
| 385 |
+
"epoch": 2.0,
|
| 386 |
+
"eval_accuracy": 0.41096535486041036,
|
| 387 |
+
"eval_loss": 2.762111186981201,
|
| 388 |
+
"eval_runtime": 1228.094,
|
| 389 |
+
"eval_samples_per_second": 12.104,
|
| 390 |
+
"eval_steps_per_second": 12.104,
|
| 391 |
+
"step": 1046
|
| 392 |
+
},
|
| 393 |
+
{
|
| 394 |
+
"epoch": 2.026768642447419,
|
| 395 |
+
"grad_norm": 2.137504816055298,
|
| 396 |
+
"learning_rate": 0.0004429572976418101,
|
| 397 |
+
"loss": 3.0334,
|
| 398 |
+
"step": 1060
|
| 399 |
+
},
|
| 400 |
+
{
|
| 401 |
+
"epoch": 2.0650095602294454,
|
| 402 |
+
"grad_norm": 2.2636399269104004,
|
| 403 |
+
"learning_rate": 0.0004408328022094752,
|
| 404 |
+
"loss": 2.8843,
|
| 405 |
+
"step": 1080
|
| 406 |
+
},
|
| 407 |
+
{
|
| 408 |
+
"epoch": 2.1032504780114722,
|
| 409 |
+
"grad_norm": 2.141150712966919,
|
| 410 |
+
"learning_rate": 0.0004387083067771405,
|
| 411 |
+
"loss": 2.909,
|
| 412 |
+
"step": 1100
|
| 413 |
+
},
|
| 414 |
+
{
|
| 415 |
+
"epoch": 2.141491395793499,
|
| 416 |
+
"grad_norm": 2.243589401245117,
|
| 417 |
+
"learning_rate": 0.0004365838113448056,
|
| 418 |
+
"loss": 2.8407,
|
| 419 |
+
"step": 1120
|
| 420 |
+
},
|
| 421 |
+
{
|
| 422 |
+
"epoch": 2.179732313575526,
|
| 423 |
+
"grad_norm": 2.3046114444732666,
|
| 424 |
+
"learning_rate": 0.00043445931591247077,
|
| 425 |
+
"loss": 2.8377,
|
| 426 |
+
"step": 1140
|
| 427 |
+
},
|
| 428 |
+
{
|
| 429 |
+
"epoch": 2.2179732313575524,
|
| 430 |
+
"grad_norm": 2.375234603881836,
|
| 431 |
+
"learning_rate": 0.000432334820480136,
|
| 432 |
+
"loss": 2.7642,
|
| 433 |
+
"step": 1160
|
| 434 |
+
},
|
| 435 |
+
{
|
| 436 |
+
"epoch": 2.2562141491395793,
|
| 437 |
+
"grad_norm": 2.36006236076355,
|
| 438 |
+
"learning_rate": 0.00043021032504780116,
|
| 439 |
+
"loss": 2.8011,
|
| 440 |
+
"step": 1180
|
| 441 |
+
},
|
| 442 |
+
{
|
| 443 |
+
"epoch": 2.294455066921606,
|
| 444 |
+
"grad_norm": 2.246645450592041,
|
| 445 |
+
"learning_rate": 0.0004280858296154663,
|
| 446 |
+
"loss": 2.7502,
|
| 447 |
+
"step": 1200
|
| 448 |
+
},
|
| 449 |
+
{
|
| 450 |
+
"epoch": 2.332695984703633,
|
| 451 |
+
"grad_norm": 2.420032501220703,
|
| 452 |
+
"learning_rate": 0.0004259613341831315,
|
| 453 |
+
"loss": 2.6646,
|
| 454 |
+
"step": 1220
|
| 455 |
+
},
|
| 456 |
+
{
|
| 457 |
+
"epoch": 2.3709369024856595,
|
| 458 |
+
"grad_norm": 2.3049144744873047,
|
| 459 |
+
"learning_rate": 0.0004238368387507967,
|
| 460 |
+
"loss": 2.7294,
|
| 461 |
+
"step": 1240
|
| 462 |
+
},
|
| 463 |
+
{
|
| 464 |
+
"epoch": 2.4091778202676863,
|
| 465 |
+
"grad_norm": 2.3154027462005615,
|
| 466 |
+
"learning_rate": 0.00042171234331846185,
|
| 467 |
+
"loss": 2.7323,
|
| 468 |
+
"step": 1260
|
| 469 |
+
},
|
| 470 |
+
{
|
| 471 |
+
"epoch": 2.447418738049713,
|
| 472 |
+
"grad_norm": 2.3349056243896484,
|
| 473 |
+
"learning_rate": 0.00041958784788612705,
|
| 474 |
+
"loss": 2.6435,
|
| 475 |
+
"step": 1280
|
| 476 |
+
},
|
| 477 |
+
{
|
| 478 |
+
"epoch": 2.48565965583174,
|
| 479 |
+
"grad_norm": 2.3369665145874023,
|
| 480 |
+
"learning_rate": 0.00041746335245379225,
|
| 481 |
+
"loss": 2.5938,
|
| 482 |
+
"step": 1300
|
| 483 |
+
},
|
| 484 |
+
{
|
| 485 |
+
"epoch": 2.5239005736137665,
|
| 486 |
+
"grad_norm": 2.115408182144165,
|
| 487 |
+
"learning_rate": 0.0004153388570214574,
|
| 488 |
+
"loss": 2.5557,
|
| 489 |
+
"step": 1320
|
| 490 |
+
},
|
| 491 |
+
{
|
| 492 |
+
"epoch": 2.5621414913957934,
|
| 493 |
+
"grad_norm": 2.2280750274658203,
|
| 494 |
+
"learning_rate": 0.00041321436158912254,
|
| 495 |
+
"loss": 2.5262,
|
| 496 |
+
"step": 1340
|
| 497 |
+
},
|
| 498 |
+
{
|
| 499 |
+
"epoch": 2.6003824091778203,
|
| 500 |
+
"grad_norm": 2.3640174865722656,
|
| 501 |
+
"learning_rate": 0.0004110898661567878,
|
| 502 |
+
"loss": 2.5302,
|
| 503 |
+
"step": 1360
|
| 504 |
+
},
|
| 505 |
+
{
|
| 506 |
+
"epoch": 2.638623326959847,
|
| 507 |
+
"grad_norm": 2.220531940460205,
|
| 508 |
+
"learning_rate": 0.00040896537072445294,
|
| 509 |
+
"loss": 2.4982,
|
| 510 |
+
"step": 1380
|
| 511 |
+
},
|
| 512 |
+
{
|
| 513 |
+
"epoch": 2.676864244741874,
|
| 514 |
+
"grad_norm": 2.19985294342041,
|
| 515 |
+
"learning_rate": 0.0004068408752921181,
|
| 516 |
+
"loss": 2.4884,
|
| 517 |
+
"step": 1400
|
| 518 |
+
},
|
| 519 |
+
{
|
| 520 |
+
"epoch": 2.7151051625239004,
|
| 521 |
+
"grad_norm": 2.083179235458374,
|
| 522 |
+
"learning_rate": 0.00040471637985978334,
|
| 523 |
+
"loss": 2.4422,
|
| 524 |
+
"step": 1420
|
| 525 |
+
},
|
| 526 |
+
{
|
| 527 |
+
"epoch": 2.7533460803059273,
|
| 528 |
+
"grad_norm": 2.171346664428711,
|
| 529 |
+
"learning_rate": 0.0004025918844274485,
|
| 530 |
+
"loss": 2.4187,
|
| 531 |
+
"step": 1440
|
| 532 |
+
},
|
| 533 |
+
{
|
| 534 |
+
"epoch": 2.791586998087954,
|
| 535 |
+
"grad_norm": 2.330702304840088,
|
| 536 |
+
"learning_rate": 0.0004004673889951136,
|
| 537 |
+
"loss": 2.3988,
|
| 538 |
+
"step": 1460
|
| 539 |
+
},
|
| 540 |
+
{
|
| 541 |
+
"epoch": 2.8298279158699806,
|
| 542 |
+
"grad_norm": 2.3132684230804443,
|
| 543 |
+
"learning_rate": 0.0003983428935627789,
|
| 544 |
+
"loss": 2.3606,
|
| 545 |
+
"step": 1480
|
| 546 |
+
},
|
| 547 |
+
{
|
| 548 |
+
"epoch": 2.8680688336520075,
|
| 549 |
+
"grad_norm": 2.188427686691284,
|
| 550 |
+
"learning_rate": 0.000396218398130444,
|
| 551 |
+
"loss": 2.3411,
|
| 552 |
+
"step": 1500
|
| 553 |
+
},
|
| 554 |
+
{
|
| 555 |
+
"epoch": 2.9063097514340344,
|
| 556 |
+
"grad_norm": 2.1979410648345947,
|
| 557 |
+
"learning_rate": 0.00039409390269810917,
|
| 558 |
+
"loss": 2.3314,
|
| 559 |
+
"step": 1520
|
| 560 |
+
},
|
| 561 |
+
{
|
| 562 |
+
"epoch": 2.9445506692160612,
|
| 563 |
+
"grad_norm": 2.246650218963623,
|
| 564 |
+
"learning_rate": 0.0003919694072657744,
|
| 565 |
+
"loss": 2.3221,
|
| 566 |
+
"step": 1540
|
| 567 |
+
},
|
| 568 |
+
{
|
| 569 |
+
"epoch": 2.982791586998088,
|
| 570 |
+
"grad_norm": 2.2953240871429443,
|
| 571 |
+
"learning_rate": 0.00038984491183343957,
|
| 572 |
+
"loss": 2.2892,
|
| 573 |
+
"step": 1560
|
| 574 |
+
},
|
| 575 |
+
{
|
| 576 |
+
"epoch": 3.0,
|
| 577 |
+
"eval_accuracy": 0.6542885973763874,
|
| 578 |
+
"eval_loss": 1.6626524925231934,
|
| 579 |
+
"eval_runtime": 1164.8432,
|
| 580 |
+
"eval_samples_per_second": 12.761,
|
| 581 |
+
"eval_steps_per_second": 12.761,
|
| 582 |
+
"step": 1569
|
| 583 |
+
},
|
| 584 |
+
{
|
| 585 |
+
"epoch": 3.0210325047801145,
|
| 586 |
+
"grad_norm": 2.2067298889160156,
|
| 587 |
+
"learning_rate": 0.0003877204164011047,
|
| 588 |
+
"loss": 2.2228,
|
| 589 |
+
"step": 1580
|
| 590 |
+
},
|
| 591 |
+
{
|
| 592 |
+
"epoch": 3.0592734225621414,
|
| 593 |
+
"grad_norm": 2.2736258506774902,
|
| 594 |
+
"learning_rate": 0.00038559592096876997,
|
| 595 |
+
"loss": 2.1788,
|
| 596 |
+
"step": 1600
|
| 597 |
+
},
|
| 598 |
+
{
|
| 599 |
+
"epoch": 3.0975143403441683,
|
| 600 |
+
"grad_norm": 2.324817419052124,
|
| 601 |
+
"learning_rate": 0.0003834714255364351,
|
| 602 |
+
"loss": 2.1743,
|
| 603 |
+
"step": 1620
|
| 604 |
+
},
|
| 605 |
+
{
|
| 606 |
+
"epoch": 3.135755258126195,
|
| 607 |
+
"grad_norm": 2.188101291656494,
|
| 608 |
+
"learning_rate": 0.00038134693010410026,
|
| 609 |
+
"loss": 2.1267,
|
| 610 |
+
"step": 1640
|
| 611 |
+
},
|
| 612 |
+
{
|
| 613 |
+
"epoch": 3.173996175908222,
|
| 614 |
+
"grad_norm": 2.2637600898742676,
|
| 615 |
+
"learning_rate": 0.00037922243467176546,
|
| 616 |
+
"loss": 2.0835,
|
| 617 |
+
"step": 1660
|
| 618 |
+
},
|
| 619 |
+
{
|
| 620 |
+
"epoch": 3.2122370936902485,
|
| 621 |
+
"grad_norm": 2.2315452098846436,
|
| 622 |
+
"learning_rate": 0.00037709793923943065,
|
| 623 |
+
"loss": 2.0944,
|
| 624 |
+
"step": 1680
|
| 625 |
+
},
|
| 626 |
+
{
|
| 627 |
+
"epoch": 3.2504780114722753,
|
| 628 |
+
"grad_norm": 2.236682176589966,
|
| 629 |
+
"learning_rate": 0.0003749734438070958,
|
| 630 |
+
"loss": 2.0867,
|
| 631 |
+
"step": 1700
|
| 632 |
+
},
|
| 633 |
+
{
|
| 634 |
+
"epoch": 3.288718929254302,
|
| 635 |
+
"grad_norm": 2.1970863342285156,
|
| 636 |
+
"learning_rate": 0.000372848948374761,
|
| 637 |
+
"loss": 2.0138,
|
| 638 |
+
"step": 1720
|
| 639 |
+
},
|
| 640 |
+
{
|
| 641 |
+
"epoch": 3.3269598470363286,
|
| 642 |
+
"grad_norm": 2.2857913970947266,
|
| 643 |
+
"learning_rate": 0.0003707244529424262,
|
| 644 |
+
"loss": 2.0081,
|
| 645 |
+
"step": 1740
|
| 646 |
+
},
|
| 647 |
+
{
|
| 648 |
+
"epoch": 3.3652007648183555,
|
| 649 |
+
"grad_norm": 2.256211280822754,
|
| 650 |
+
"learning_rate": 0.00036859995751009134,
|
| 651 |
+
"loss": 1.9887,
|
| 652 |
+
"step": 1760
|
| 653 |
+
},
|
| 654 |
+
{
|
| 655 |
+
"epoch": 3.4034416826003824,
|
| 656 |
+
"grad_norm": 2.3634960651397705,
|
| 657 |
+
"learning_rate": 0.00036647546207775654,
|
| 658 |
+
"loss": 1.9965,
|
| 659 |
+
"step": 1780
|
| 660 |
+
},
|
| 661 |
+
{
|
| 662 |
+
"epoch": 3.4416826003824093,
|
| 663 |
+
"grad_norm": 2.2254064083099365,
|
| 664 |
+
"learning_rate": 0.00036435096664542174,
|
| 665 |
+
"loss": 2.0024,
|
| 666 |
+
"step": 1800
|
| 667 |
+
},
|
| 668 |
+
{
|
| 669 |
+
"epoch": 3.479923518164436,
|
| 670 |
+
"grad_norm": 2.271703004837036,
|
| 671 |
+
"learning_rate": 0.0003622264712130869,
|
| 672 |
+
"loss": 2.0024,
|
| 673 |
+
"step": 1820
|
| 674 |
+
},
|
| 675 |
+
{
|
| 676 |
+
"epoch": 3.5181644359464626,
|
| 677 |
+
"grad_norm": 2.220524549484253,
|
| 678 |
+
"learning_rate": 0.0003601019757807521,
|
| 679 |
+
"loss": 1.9561,
|
| 680 |
+
"step": 1840
|
| 681 |
+
},
|
| 682 |
+
{
|
| 683 |
+
"epoch": 3.5564053537284894,
|
| 684 |
+
"grad_norm": 2.3010692596435547,
|
| 685 |
+
"learning_rate": 0.0003579774803484173,
|
| 686 |
+
"loss": 1.9641,
|
| 687 |
+
"step": 1860
|
| 688 |
+
},
|
| 689 |
+
{
|
| 690 |
+
"epoch": 3.5946462715105163,
|
| 691 |
+
"grad_norm": 2.2860300540924072,
|
| 692 |
+
"learning_rate": 0.00035585298491608243,
|
| 693 |
+
"loss": 1.9032,
|
| 694 |
+
"step": 1880
|
| 695 |
+
},
|
| 696 |
+
{
|
| 697 |
+
"epoch": 3.632887189292543,
|
| 698 |
+
"grad_norm": 2.2572293281555176,
|
| 699 |
+
"learning_rate": 0.00035372848948374763,
|
| 700 |
+
"loss": 1.9115,
|
| 701 |
+
"step": 1900
|
| 702 |
+
},
|
| 703 |
+
{
|
| 704 |
+
"epoch": 3.67112810707457,
|
| 705 |
+
"grad_norm": 2.441771984100342,
|
| 706 |
+
"learning_rate": 0.0003516039940514128,
|
| 707 |
+
"loss": 1.8957,
|
| 708 |
+
"step": 1920
|
| 709 |
+
},
|
| 710 |
+
{
|
| 711 |
+
"epoch": 3.7093690248565965,
|
| 712 |
+
"grad_norm": 2.3750736713409424,
|
| 713 |
+
"learning_rate": 0.00034947949861907797,
|
| 714 |
+
"loss": 1.8638,
|
| 715 |
+
"step": 1940
|
| 716 |
+
},
|
| 717 |
+
{
|
| 718 |
+
"epoch": 3.7476099426386233,
|
| 719 |
+
"grad_norm": 2.114288806915283,
|
| 720 |
+
"learning_rate": 0.00034735500318674317,
|
| 721 |
+
"loss": 1.8105,
|
| 722 |
+
"step": 1960
|
| 723 |
+
},
|
| 724 |
+
{
|
| 725 |
+
"epoch": 3.78585086042065,
|
| 726 |
+
"grad_norm": 2.3129258155822754,
|
| 727 |
+
"learning_rate": 0.0003452305077544083,
|
| 728 |
+
"loss": 1.8908,
|
| 729 |
+
"step": 1980
|
| 730 |
+
},
|
| 731 |
+
{
|
| 732 |
+
"epoch": 3.8240917782026767,
|
| 733 |
+
"grad_norm": 2.217604398727417,
|
| 734 |
+
"learning_rate": 0.0003431060123220735,
|
| 735 |
+
"loss": 1.8116,
|
| 736 |
+
"step": 2000
|
| 737 |
+
},
|
| 738 |
+
{
|
| 739 |
+
"epoch": 3.8623326959847035,
|
| 740 |
+
"grad_norm": 2.2592735290527344,
|
| 741 |
+
"learning_rate": 0.0003409815168897387,
|
| 742 |
+
"loss": 1.8325,
|
| 743 |
+
"step": 2020
|
| 744 |
+
},
|
| 745 |
+
{
|
| 746 |
+
"epoch": 3.9005736137667304,
|
| 747 |
+
"grad_norm": 2.321389675140381,
|
| 748 |
+
"learning_rate": 0.00033885702145740386,
|
| 749 |
+
"loss": 1.7757,
|
| 750 |
+
"step": 2040
|
| 751 |
+
},
|
| 752 |
+
{
|
| 753 |
+
"epoch": 3.9388145315487573,
|
| 754 |
+
"grad_norm": 2.0709521770477295,
|
| 755 |
+
"learning_rate": 0.00033673252602506906,
|
| 756 |
+
"loss": 1.7801,
|
| 757 |
+
"step": 2060
|
| 758 |
+
},
|
| 759 |
+
{
|
| 760 |
+
"epoch": 3.977055449330784,
|
| 761 |
+
"grad_norm": 2.3316352367401123,
|
| 762 |
+
"learning_rate": 0.00033460803059273426,
|
| 763 |
+
"loss": 1.7576,
|
| 764 |
+
"step": 2080
|
| 765 |
+
},
|
| 766 |
+
{
|
| 767 |
+
"epoch": 4.0,
|
| 768 |
+
"eval_accuracy": 0.758627648839556,
|
| 769 |
+
"eval_loss": 1.1761366128921509,
|
| 770 |
+
"eval_runtime": 910.1664,
|
| 771 |
+
"eval_samples_per_second": 16.332,
|
| 772 |
+
"eval_steps_per_second": 16.332,
|
| 773 |
+
"step": 2092
|
| 774 |
+
},
|
| 775 |
+
{
|
| 776 |
+
"epoch": 4.015296367112811,
|
| 777 |
+
"grad_norm": 2.2446036338806152,
|
| 778 |
+
"learning_rate": 0.0003324835351603994,
|
| 779 |
+
"loss": 1.7157,
|
| 780 |
+
"step": 2100
|
| 781 |
+
},
|
| 782 |
+
{
|
| 783 |
+
"epoch": 4.053537284894838,
|
| 784 |
+
"grad_norm": 2.1550064086914062,
|
| 785 |
+
"learning_rate": 0.0003303590397280646,
|
| 786 |
+
"loss": 1.6126,
|
| 787 |
+
"step": 2120
|
| 788 |
+
},
|
| 789 |
+
{
|
| 790 |
+
"epoch": 4.091778202676864,
|
| 791 |
+
"grad_norm": 2.3542799949645996,
|
| 792 |
+
"learning_rate": 0.0003282345442957298,
|
| 793 |
+
"loss": 1.6417,
|
| 794 |
+
"step": 2140
|
| 795 |
+
},
|
| 796 |
+
{
|
| 797 |
+
"epoch": 4.130019120458891,
|
| 798 |
+
"grad_norm": 2.3036603927612305,
|
| 799 |
+
"learning_rate": 0.00032611004886339494,
|
| 800 |
+
"loss": 1.6108,
|
| 801 |
+
"step": 2160
|
| 802 |
+
},
|
| 803 |
+
{
|
| 804 |
+
"epoch": 4.168260038240918,
|
| 805 |
+
"grad_norm": 2.168532133102417,
|
| 806 |
+
"learning_rate": 0.00032398555343106014,
|
| 807 |
+
"loss": 1.5939,
|
| 808 |
+
"step": 2180
|
| 809 |
+
},
|
| 810 |
+
{
|
| 811 |
+
"epoch": 4.2065009560229445,
|
| 812 |
+
"grad_norm": 2.257270097732544,
|
| 813 |
+
"learning_rate": 0.0003218610579987253,
|
| 814 |
+
"loss": 1.6157,
|
| 815 |
+
"step": 2200
|
| 816 |
+
},
|
| 817 |
+
{
|
| 818 |
+
"epoch": 4.244741873804971,
|
| 819 |
+
"grad_norm": 2.2476625442504883,
|
| 820 |
+
"learning_rate": 0.0003197365625663905,
|
| 821 |
+
"loss": 1.6477,
|
| 822 |
+
"step": 2220
|
| 823 |
+
},
|
| 824 |
+
{
|
| 825 |
+
"epoch": 4.282982791586998,
|
| 826 |
+
"grad_norm": 2.162182092666626,
|
| 827 |
+
"learning_rate": 0.00031761206713405563,
|
| 828 |
+
"loss": 1.5589,
|
| 829 |
+
"step": 2240
|
| 830 |
+
},
|
| 831 |
+
{
|
| 832 |
+
"epoch": 4.321223709369025,
|
| 833 |
+
"grad_norm": 2.084498167037964,
|
| 834 |
+
"learning_rate": 0.00031548757170172083,
|
| 835 |
+
"loss": 1.5683,
|
| 836 |
+
"step": 2260
|
| 837 |
+
},
|
| 838 |
+
{
|
| 839 |
+
"epoch": 4.359464627151052,
|
| 840 |
+
"grad_norm": 2.1769893169403076,
|
| 841 |
+
"learning_rate": 0.00031336307626938603,
|
| 842 |
+
"loss": 1.5324,
|
| 843 |
+
"step": 2280
|
| 844 |
+
},
|
| 845 |
+
{
|
| 846 |
+
"epoch": 4.397705544933078,
|
| 847 |
+
"grad_norm": 2.1961722373962402,
|
| 848 |
+
"learning_rate": 0.0003112385808370512,
|
| 849 |
+
"loss": 1.5551,
|
| 850 |
+
"step": 2300
|
| 851 |
+
},
|
| 852 |
+
{
|
| 853 |
+
"epoch": 4.435946462715105,
|
| 854 |
+
"grad_norm": 2.2195024490356445,
|
| 855 |
+
"learning_rate": 0.0003091140854047164,
|
| 856 |
+
"loss": 1.5724,
|
| 857 |
+
"step": 2320
|
| 858 |
+
},
|
| 859 |
+
{
|
| 860 |
+
"epoch": 4.474187380497132,
|
| 861 |
+
"grad_norm": 2.18676495552063,
|
| 862 |
+
"learning_rate": 0.0003069895899723816,
|
| 863 |
+
"loss": 1.5322,
|
| 864 |
+
"step": 2340
|
| 865 |
+
},
|
| 866 |
+
{
|
| 867 |
+
"epoch": 4.512428298279159,
|
| 868 |
+
"grad_norm": 2.2305195331573486,
|
| 869 |
+
"learning_rate": 0.0003048650945400467,
|
| 870 |
+
"loss": 1.5207,
|
| 871 |
+
"step": 2360
|
| 872 |
+
},
|
| 873 |
+
{
|
| 874 |
+
"epoch": 4.550669216061186,
|
| 875 |
+
"grad_norm": 2.297010898590088,
|
| 876 |
+
"learning_rate": 0.0003027405991077119,
|
| 877 |
+
"loss": 1.5712,
|
| 878 |
+
"step": 2380
|
| 879 |
+
},
|
| 880 |
+
{
|
| 881 |
+
"epoch": 4.588910133843212,
|
| 882 |
+
"grad_norm": 2.261610746383667,
|
| 883 |
+
"learning_rate": 0.0003006161036753771,
|
| 884 |
+
"loss": 1.513,
|
| 885 |
+
"step": 2400
|
| 886 |
+
},
|
| 887 |
+
{
|
| 888 |
+
"epoch": 4.627151051625239,
|
| 889 |
+
"grad_norm": 2.1144425868988037,
|
| 890 |
+
"learning_rate": 0.00029849160824304226,
|
| 891 |
+
"loss": 1.4854,
|
| 892 |
+
"step": 2420
|
| 893 |
+
},
|
| 894 |
+
{
|
| 895 |
+
"epoch": 4.665391969407266,
|
| 896 |
+
"grad_norm": 2.344909191131592,
|
| 897 |
+
"learning_rate": 0.00029636711281070746,
|
| 898 |
+
"loss": 1.5025,
|
| 899 |
+
"step": 2440
|
| 900 |
+
},
|
| 901 |
+
{
|
| 902 |
+
"epoch": 4.7036328871892925,
|
| 903 |
+
"grad_norm": 2.1943275928497314,
|
| 904 |
+
"learning_rate": 0.00029424261737837266,
|
| 905 |
+
"loss": 1.4917,
|
| 906 |
+
"step": 2460
|
| 907 |
+
},
|
| 908 |
+
{
|
| 909 |
+
"epoch": 4.741873804971319,
|
| 910 |
+
"grad_norm": 2.191070079803467,
|
| 911 |
+
"learning_rate": 0.0002921181219460378,
|
| 912 |
+
"loss": 1.4539,
|
| 913 |
+
"step": 2480
|
| 914 |
+
},
|
| 915 |
+
{
|
| 916 |
+
"epoch": 4.780114722753346,
|
| 917 |
+
"grad_norm": 2.142045259475708,
|
| 918 |
+
"learning_rate": 0.000289993626513703,
|
| 919 |
+
"loss": 1.4688,
|
| 920 |
+
"step": 2500
|
| 921 |
+
},
|
| 922 |
+
{
|
| 923 |
+
"epoch": 4.818355640535373,
|
| 924 |
+
"grad_norm": 2.203152656555176,
|
| 925 |
+
"learning_rate": 0.0002878691310813682,
|
| 926 |
+
"loss": 1.4236,
|
| 927 |
+
"step": 2520
|
| 928 |
+
},
|
| 929 |
+
{
|
| 930 |
+
"epoch": 4.8565965583174,
|
| 931 |
+
"grad_norm": 2.264139175415039,
|
| 932 |
+
"learning_rate": 0.00028574463564903335,
|
| 933 |
+
"loss": 1.4211,
|
| 934 |
+
"step": 2540
|
| 935 |
+
},
|
| 936 |
+
{
|
| 937 |
+
"epoch": 4.894837476099426,
|
| 938 |
+
"grad_norm": 2.173497438430786,
|
| 939 |
+
"learning_rate": 0.0002836201402166985,
|
| 940 |
+
"loss": 1.4236,
|
| 941 |
+
"step": 2560
|
| 942 |
+
},
|
| 943 |
+
{
|
| 944 |
+
"epoch": 4.933078393881453,
|
| 945 |
+
"grad_norm": 2.069350481033325,
|
| 946 |
+
"learning_rate": 0.00028149564478436375,
|
| 947 |
+
"loss": 1.3804,
|
| 948 |
+
"step": 2580
|
| 949 |
+
},
|
| 950 |
+
{
|
| 951 |
+
"epoch": 4.97131931166348,
|
| 952 |
+
"grad_norm": 2.1907660961151123,
|
| 953 |
+
"learning_rate": 0.0002793711493520289,
|
| 954 |
+
"loss": 1.3706,
|
| 955 |
+
"step": 2600
|
| 956 |
+
},
|
| 957 |
+
{
|
| 958 |
+
"epoch": 5.0,
|
| 959 |
+
"eval_accuracy": 0.8203834510595358,
|
| 960 |
+
"eval_loss": 0.8903235793113708,
|
| 961 |
+
"eval_runtime": 813.2495,
|
| 962 |
+
"eval_samples_per_second": 18.279,
|
| 963 |
+
"eval_steps_per_second": 18.279,
|
| 964 |
+
"step": 2615
|
| 965 |
+
},
|
| 966 |
+
{
|
| 967 |
+
"epoch": 5.009560229445507,
|
| 968 |
+
"grad_norm": 2.2395236492156982,
|
| 969 |
+
"learning_rate": 0.00027724665391969404,
|
| 970 |
+
"loss": 1.3611,
|
| 971 |
+
"step": 2620
|
| 972 |
+
},
|
| 973 |
+
{
|
| 974 |
+
"epoch": 5.047801147227533,
|
| 975 |
+
"grad_norm": 2.164022922515869,
|
| 976 |
+
"learning_rate": 0.0002751221584873593,
|
| 977 |
+
"loss": 1.2885,
|
| 978 |
+
"step": 2640
|
| 979 |
+
},
|
| 980 |
+
{
|
| 981 |
+
"epoch": 5.08604206500956,
|
| 982 |
+
"grad_norm": 2.335524559020996,
|
| 983 |
+
"learning_rate": 0.00027299766305502443,
|
| 984 |
+
"loss": 1.3024,
|
| 985 |
+
"step": 2660
|
| 986 |
+
},
|
| 987 |
+
{
|
| 988 |
+
"epoch": 5.124282982791587,
|
| 989 |
+
"grad_norm": 2.3510003089904785,
|
| 990 |
+
"learning_rate": 0.0002708731676226896,
|
| 991 |
+
"loss": 1.2819,
|
| 992 |
+
"step": 2680
|
| 993 |
+
},
|
| 994 |
+
{
|
| 995 |
+
"epoch": 5.162523900573614,
|
| 996 |
+
"grad_norm": 2.2182960510253906,
|
| 997 |
+
"learning_rate": 0.00026874867219035483,
|
| 998 |
+
"loss": 1.2927,
|
| 999 |
+
"step": 2700
|
| 1000 |
+
},
|
| 1001 |
+
{
|
| 1002 |
+
"epoch": 5.2007648183556405,
|
| 1003 |
+
"grad_norm": 2.164422035217285,
|
| 1004 |
+
"learning_rate": 0.00026662417675802,
|
| 1005 |
+
"loss": 1.2905,
|
| 1006 |
+
"step": 2720
|
| 1007 |
+
},
|
| 1008 |
+
{
|
| 1009 |
+
"epoch": 5.239005736137667,
|
| 1010 |
+
"grad_norm": 2.2719788551330566,
|
| 1011 |
+
"learning_rate": 0.0002644996813256851,
|
| 1012 |
+
"loss": 1.3067,
|
| 1013 |
+
"step": 2740
|
| 1014 |
+
},
|
| 1015 |
+
{
|
| 1016 |
+
"epoch": 5.277246653919694,
|
| 1017 |
+
"grad_norm": 2.1733806133270264,
|
| 1018 |
+
"learning_rate": 0.0002623751858933504,
|
| 1019 |
+
"loss": 1.2778,
|
| 1020 |
+
"step": 2760
|
| 1021 |
+
},
|
| 1022 |
+
{
|
| 1023 |
+
"epoch": 5.315487571701721,
|
| 1024 |
+
"grad_norm": 2.0940115451812744,
|
| 1025 |
+
"learning_rate": 0.0002602506904610155,
|
| 1026 |
+
"loss": 1.2553,
|
| 1027 |
+
"step": 2780
|
| 1028 |
+
},
|
| 1029 |
+
{
|
| 1030 |
+
"epoch": 5.353728489483748,
|
| 1031 |
+
"grad_norm": 2.049928665161133,
|
| 1032 |
+
"learning_rate": 0.00025812619502868067,
|
| 1033 |
+
"loss": 1.2572,
|
| 1034 |
+
"step": 2800
|
| 1035 |
+
},
|
| 1036 |
+
{
|
| 1037 |
+
"epoch": 5.3919694072657744,
|
| 1038 |
+
"grad_norm": 2.039212703704834,
|
| 1039 |
+
"learning_rate": 0.0002560016995963459,
|
| 1040 |
+
"loss": 1.2139,
|
| 1041 |
+
"step": 2820
|
| 1042 |
+
},
|
| 1043 |
+
{
|
| 1044 |
+
"epoch": 5.430210325047801,
|
| 1045 |
+
"grad_norm": 2.2491774559020996,
|
| 1046 |
+
"learning_rate": 0.00025387720416401106,
|
| 1047 |
+
"loss": 1.2591,
|
| 1048 |
+
"step": 2840
|
| 1049 |
+
},
|
| 1050 |
+
{
|
| 1051 |
+
"epoch": 5.468451242829828,
|
| 1052 |
+
"grad_norm": 2.1145877838134766,
|
| 1053 |
+
"learning_rate": 0.0002517527087316762,
|
| 1054 |
+
"loss": 1.2458,
|
| 1055 |
+
"step": 2860
|
| 1056 |
+
},
|
| 1057 |
+
{
|
| 1058 |
+
"epoch": 5.506692160611855,
|
| 1059 |
+
"grad_norm": 2.1274683475494385,
|
| 1060 |
+
"learning_rate": 0.0002496282132993414,
|
| 1061 |
+
"loss": 1.227,
|
| 1062 |
+
"step": 2880
|
| 1063 |
+
},
|
| 1064 |
+
{
|
| 1065 |
+
"epoch": 5.544933078393882,
|
| 1066 |
+
"grad_norm": 2.0846710205078125,
|
| 1067 |
+
"learning_rate": 0.0002475037178670066,
|
| 1068 |
+
"loss": 1.1897,
|
| 1069 |
+
"step": 2900
|
| 1070 |
+
},
|
| 1071 |
+
{
|
| 1072 |
+
"epoch": 5.583173996175908,
|
| 1073 |
+
"grad_norm": 2.143688678741455,
|
| 1074 |
+
"learning_rate": 0.0002453792224346718,
|
| 1075 |
+
"loss": 1.2133,
|
| 1076 |
+
"step": 2920
|
| 1077 |
+
},
|
| 1078 |
+
{
|
| 1079 |
+
"epoch": 5.621414913957935,
|
| 1080 |
+
"grad_norm": 2.2568676471710205,
|
| 1081 |
+
"learning_rate": 0.00024325472700233695,
|
| 1082 |
+
"loss": 1.2194,
|
| 1083 |
+
"step": 2940
|
| 1084 |
+
},
|
| 1085 |
+
{
|
| 1086 |
+
"epoch": 5.659655831739962,
|
| 1087 |
+
"grad_norm": 2.266052484512329,
|
| 1088 |
+
"learning_rate": 0.00024113023157000212,
|
| 1089 |
+
"loss": 1.1895,
|
| 1090 |
+
"step": 2960
|
| 1091 |
+
},
|
| 1092 |
+
{
|
| 1093 |
+
"epoch": 5.6978967495219885,
|
| 1094 |
+
"grad_norm": 2.352609395980835,
|
| 1095 |
+
"learning_rate": 0.0002390057361376673,
|
| 1096 |
+
"loss": 1.1849,
|
| 1097 |
+
"step": 2980
|
| 1098 |
+
},
|
| 1099 |
+
{
|
| 1100 |
+
"epoch": 5.736137667304015,
|
| 1101 |
+
"grad_norm": 2.1269915103912354,
|
| 1102 |
+
"learning_rate": 0.0002368812407053325,
|
| 1103 |
+
"loss": 1.205,
|
| 1104 |
+
"step": 3000
|
| 1105 |
+
},
|
| 1106 |
+
{
|
| 1107 |
+
"epoch": 5.774378585086042,
|
| 1108 |
+
"grad_norm": 2.20017147064209,
|
| 1109 |
+
"learning_rate": 0.00023475674527299767,
|
| 1110 |
+
"loss": 1.1366,
|
| 1111 |
+
"step": 3020
|
| 1112 |
+
},
|
| 1113 |
+
{
|
| 1114 |
+
"epoch": 5.812619502868069,
|
| 1115 |
+
"grad_norm": 2.0107390880584717,
|
| 1116 |
+
"learning_rate": 0.00023263224984066284,
|
| 1117 |
+
"loss": 1.1268,
|
| 1118 |
+
"step": 3040
|
| 1119 |
+
},
|
| 1120 |
+
{
|
| 1121 |
+
"epoch": 5.850860420650095,
|
| 1122 |
+
"grad_norm": 2.091771364212036,
|
| 1123 |
+
"learning_rate": 0.00023050775440832804,
|
| 1124 |
+
"loss": 1.1619,
|
| 1125 |
+
"step": 3060
|
| 1126 |
+
},
|
| 1127 |
+
{
|
| 1128 |
+
"epoch": 5.8891013384321225,
|
| 1129 |
+
"grad_norm": 2.261592388153076,
|
| 1130 |
+
"learning_rate": 0.0002283832589759932,
|
| 1131 |
+
"loss": 1.1789,
|
| 1132 |
+
"step": 3080
|
| 1133 |
+
},
|
| 1134 |
+
{
|
| 1135 |
+
"epoch": 5.927342256214149,
|
| 1136 |
+
"grad_norm": 2.126786947250366,
|
| 1137 |
+
"learning_rate": 0.00022625876354365838,
|
| 1138 |
+
"loss": 1.1492,
|
| 1139 |
+
"step": 3100
|
| 1140 |
+
},
|
| 1141 |
+
{
|
| 1142 |
+
"epoch": 5.965583173996176,
|
| 1143 |
+
"grad_norm": 2.123417615890503,
|
| 1144 |
+
"learning_rate": 0.00022413426811132355,
|
| 1145 |
+
"loss": 1.1258,
|
| 1146 |
+
"step": 3120
|
| 1147 |
+
},
|
| 1148 |
+
{
|
| 1149 |
+
"epoch": 6.0,
|
| 1150 |
+
"eval_accuracy": 0.8432559704002691,
|
| 1151 |
+
"eval_loss": 0.7555378079414368,
|
| 1152 |
+
"eval_runtime": 1118.6028,
|
| 1153 |
+
"eval_samples_per_second": 13.289,
|
| 1154 |
+
"eval_steps_per_second": 13.289,
|
| 1155 |
+
"step": 3138
|
| 1156 |
+
},
|
| 1157 |
+
{
|
| 1158 |
+
"epoch": 6.003824091778203,
|
| 1159 |
+
"grad_norm": 2.0020689964294434,
|
| 1160 |
+
"learning_rate": 0.00022200977267898875,
|
| 1161 |
+
"loss": 1.1086,
|
| 1162 |
+
"step": 3140
|
| 1163 |
+
},
|
| 1164 |
+
{
|
| 1165 |
+
"epoch": 6.042065009560229,
|
| 1166 |
+
"grad_norm": 2.0867371559143066,
|
| 1167 |
+
"learning_rate": 0.00021988527724665392,
|
| 1168 |
+
"loss": 1.0815,
|
| 1169 |
+
"step": 3160
|
| 1170 |
+
},
|
| 1171 |
+
{
|
| 1172 |
+
"epoch": 6.080305927342256,
|
| 1173 |
+
"grad_norm": 1.9533103704452515,
|
| 1174 |
+
"learning_rate": 0.0002177607818143191,
|
| 1175 |
+
"loss": 1.0412,
|
| 1176 |
+
"step": 3180
|
| 1177 |
+
},
|
| 1178 |
+
{
|
| 1179 |
+
"epoch": 6.118546845124283,
|
| 1180 |
+
"grad_norm": 2.2522337436676025,
|
| 1181 |
+
"learning_rate": 0.0002156362863819843,
|
| 1182 |
+
"loss": 1.0312,
|
| 1183 |
+
"step": 3200
|
| 1184 |
+
},
|
| 1185 |
+
{
|
| 1186 |
+
"epoch": 6.15678776290631,
|
| 1187 |
+
"grad_norm": 2.058983087539673,
|
| 1188 |
+
"learning_rate": 0.00021351179094964944,
|
| 1189 |
+
"loss": 1.0449,
|
| 1190 |
+
"step": 3220
|
| 1191 |
+
},
|
| 1192 |
+
{
|
| 1193 |
+
"epoch": 6.195028680688337,
|
| 1194 |
+
"grad_norm": 2.1774373054504395,
|
| 1195 |
+
"learning_rate": 0.00021138729551731464,
|
| 1196 |
+
"loss": 1.0532,
|
| 1197 |
+
"step": 3240
|
| 1198 |
+
},
|
| 1199 |
+
{
|
| 1200 |
+
"epoch": 6.233269598470363,
|
| 1201 |
+
"grad_norm": 2.0248055458068848,
|
| 1202 |
+
"learning_rate": 0.00020926280008497984,
|
| 1203 |
+
"loss": 1.0461,
|
| 1204 |
+
"step": 3260
|
| 1205 |
+
},
|
| 1206 |
+
{
|
| 1207 |
+
"epoch": 6.27151051625239,
|
| 1208 |
+
"grad_norm": 2.066737651824951,
|
| 1209 |
+
"learning_rate": 0.00020713830465264498,
|
| 1210 |
+
"loss": 1.0243,
|
| 1211 |
+
"step": 3280
|
| 1212 |
+
},
|
| 1213 |
+
{
|
| 1214 |
+
"epoch": 6.309751434034417,
|
| 1215 |
+
"grad_norm": 2.100133180618286,
|
| 1216 |
+
"learning_rate": 0.00020501380922031018,
|
| 1217 |
+
"loss": 1.0309,
|
| 1218 |
+
"step": 3300
|
| 1219 |
+
},
|
| 1220 |
+
{
|
| 1221 |
+
"epoch": 6.347992351816444,
|
| 1222 |
+
"grad_norm": 2.192960739135742,
|
| 1223 |
+
"learning_rate": 0.00020288931378797538,
|
| 1224 |
+
"loss": 1.0147,
|
| 1225 |
+
"step": 3320
|
| 1226 |
+
},
|
| 1227 |
+
{
|
| 1228 |
+
"epoch": 6.3862332695984705,
|
| 1229 |
+
"grad_norm": 2.123382329940796,
|
| 1230 |
+
"learning_rate": 0.00020076481835564053,
|
| 1231 |
+
"loss": 1.0229,
|
| 1232 |
+
"step": 3340
|
| 1233 |
+
},
|
| 1234 |
+
{
|
| 1235 |
+
"epoch": 6.424474187380497,
|
| 1236 |
+
"grad_norm": 2.162189245223999,
|
| 1237 |
+
"learning_rate": 0.00019864032292330573,
|
| 1238 |
+
"loss": 1.011,
|
| 1239 |
+
"step": 3360
|
| 1240 |
+
},
|
| 1241 |
+
{
|
| 1242 |
+
"epoch": 6.462715105162524,
|
| 1243 |
+
"grad_norm": 2.254284143447876,
|
| 1244 |
+
"learning_rate": 0.0001965158274909709,
|
| 1245 |
+
"loss": 0.9929,
|
| 1246 |
+
"step": 3380
|
| 1247 |
+
},
|
| 1248 |
+
{
|
| 1249 |
+
"epoch": 6.500956022944551,
|
| 1250 |
+
"grad_norm": 2.2183146476745605,
|
| 1251 |
+
"learning_rate": 0.00019439133205863607,
|
| 1252 |
+
"loss": 0.9852,
|
| 1253 |
+
"step": 3400
|
| 1254 |
+
},
|
| 1255 |
+
{
|
| 1256 |
+
"epoch": 6.539196940726577,
|
| 1257 |
+
"grad_norm": 2.1704065799713135,
|
| 1258 |
+
"learning_rate": 0.00019226683662630127,
|
| 1259 |
+
"loss": 1.0129,
|
| 1260 |
+
"step": 3420
|
| 1261 |
+
},
|
| 1262 |
+
{
|
| 1263 |
+
"epoch": 6.577437858508604,
|
| 1264 |
+
"grad_norm": 2.0828094482421875,
|
| 1265 |
+
"learning_rate": 0.00019014234119396644,
|
| 1266 |
+
"loss": 0.9667,
|
| 1267 |
+
"step": 3440
|
| 1268 |
+
},
|
| 1269 |
+
{
|
| 1270 |
+
"epoch": 6.615678776290631,
|
| 1271 |
+
"grad_norm": 2.3150341510772705,
|
| 1272 |
+
"learning_rate": 0.0001880178457616316,
|
| 1273 |
+
"loss": 0.9769,
|
| 1274 |
+
"step": 3460
|
| 1275 |
+
},
|
| 1276 |
+
{
|
| 1277 |
+
"epoch": 6.653919694072657,
|
| 1278 |
+
"grad_norm": 2.0636775493621826,
|
| 1279 |
+
"learning_rate": 0.0001858933503292968,
|
| 1280 |
+
"loss": 0.979,
|
| 1281 |
+
"step": 3480
|
| 1282 |
+
},
|
| 1283 |
+
{
|
| 1284 |
+
"epoch": 6.692160611854685,
|
| 1285 |
+
"grad_norm": 2.171602487564087,
|
| 1286 |
+
"learning_rate": 0.00018376885489696196,
|
| 1287 |
+
"loss": 0.9667,
|
| 1288 |
+
"step": 3500
|
| 1289 |
+
},
|
| 1290 |
+
{
|
| 1291 |
+
"epoch": 6.730401529636711,
|
| 1292 |
+
"grad_norm": 2.1150522232055664,
|
| 1293 |
+
"learning_rate": 0.00018164435946462716,
|
| 1294 |
+
"loss": 0.9593,
|
| 1295 |
+
"step": 3520
|
| 1296 |
+
},
|
| 1297 |
+
{
|
| 1298 |
+
"epoch": 6.768642447418738,
|
| 1299 |
+
"grad_norm": 2.096452236175537,
|
| 1300 |
+
"learning_rate": 0.00017951986403229233,
|
| 1301 |
+
"loss": 0.9828,
|
| 1302 |
+
"step": 3540
|
| 1303 |
+
},
|
| 1304 |
+
{
|
| 1305 |
+
"epoch": 6.806883365200765,
|
| 1306 |
+
"grad_norm": 2.2779390811920166,
|
| 1307 |
+
"learning_rate": 0.0001773953685999575,
|
| 1308 |
+
"loss": 0.9648,
|
| 1309 |
+
"step": 3560
|
| 1310 |
+
},
|
| 1311 |
+
{
|
| 1312 |
+
"epoch": 6.845124282982791,
|
| 1313 |
+
"grad_norm": 2.2793240547180176,
|
| 1314 |
+
"learning_rate": 0.0001752708731676227,
|
| 1315 |
+
"loss": 0.9639,
|
| 1316 |
+
"step": 3580
|
| 1317 |
+
},
|
| 1318 |
+
{
|
| 1319 |
+
"epoch": 6.8833652007648185,
|
| 1320 |
+
"grad_norm": 2.0822837352752686,
|
| 1321 |
+
"learning_rate": 0.00017314637773528787,
|
| 1322 |
+
"loss": 0.9421,
|
| 1323 |
+
"step": 3600
|
| 1324 |
+
},
|
| 1325 |
+
{
|
| 1326 |
+
"epoch": 6.921606118546845,
|
| 1327 |
+
"grad_norm": 2.1541502475738525,
|
| 1328 |
+
"learning_rate": 0.00017102188230295304,
|
| 1329 |
+
"loss": 0.9277,
|
| 1330 |
+
"step": 3620
|
| 1331 |
+
},
|
| 1332 |
+
{
|
| 1333 |
+
"epoch": 6.959847036328872,
|
| 1334 |
+
"grad_norm": 2.1241962909698486,
|
| 1335 |
+
"learning_rate": 0.00016889738687061824,
|
| 1336 |
+
"loss": 0.9335,
|
| 1337 |
+
"step": 3640
|
| 1338 |
+
},
|
| 1339 |
+
{
|
| 1340 |
+
"epoch": 6.998087954110899,
|
| 1341 |
+
"grad_norm": 2.2354745864868164,
|
| 1342 |
+
"learning_rate": 0.00016677289143828341,
|
| 1343 |
+
"loss": 0.9379,
|
| 1344 |
+
"step": 3660
|
| 1345 |
+
},
|
| 1346 |
+
{
|
| 1347 |
+
"epoch": 7.0,
|
| 1348 |
+
"eval_accuracy": 0.889673730238816,
|
| 1349 |
+
"eval_loss": 0.5586521029472351,
|
| 1350 |
+
"eval_runtime": 904.3879,
|
| 1351 |
+
"eval_samples_per_second": 16.437,
|
| 1352 |
+
"eval_steps_per_second": 16.437,
|
| 1353 |
+
"step": 3661
|
| 1354 |
+
},
|
| 1355 |
+
{
|
| 1356 |
+
"epoch": 7.036328871892925,
|
| 1357 |
+
"grad_norm": 2.109501600265503,
|
| 1358 |
+
"learning_rate": 0.0001646483960059486,
|
| 1359 |
+
"loss": 0.8485,
|
| 1360 |
+
"step": 3680
|
| 1361 |
+
},
|
| 1362 |
+
{
|
| 1363 |
+
"epoch": 7.074569789674952,
|
| 1364 |
+
"grad_norm": 2.2034125328063965,
|
| 1365 |
+
"learning_rate": 0.00016252390057361376,
|
| 1366 |
+
"loss": 0.897,
|
| 1367 |
+
"step": 3700
|
| 1368 |
+
},
|
| 1369 |
+
{
|
| 1370 |
+
"epoch": 7.112810707456979,
|
| 1371 |
+
"grad_norm": 2.053767204284668,
|
| 1372 |
+
"learning_rate": 0.00016039940514127896,
|
| 1373 |
+
"loss": 0.859,
|
| 1374 |
+
"step": 3720
|
| 1375 |
+
},
|
| 1376 |
+
{
|
| 1377 |
+
"epoch": 7.151051625239006,
|
| 1378 |
+
"grad_norm": 1.977229118347168,
|
| 1379 |
+
"learning_rate": 0.00015827490970894413,
|
| 1380 |
+
"loss": 0.8643,
|
| 1381 |
+
"step": 3740
|
| 1382 |
+
},
|
| 1383 |
+
{
|
| 1384 |
+
"epoch": 7.189292543021033,
|
| 1385 |
+
"grad_norm": 2.0782172679901123,
|
| 1386 |
+
"learning_rate": 0.0001561504142766093,
|
| 1387 |
+
"loss": 0.8665,
|
| 1388 |
+
"step": 3760
|
| 1389 |
+
},
|
| 1390 |
+
{
|
| 1391 |
+
"epoch": 7.227533460803059,
|
| 1392 |
+
"grad_norm": 1.9473881721496582,
|
| 1393 |
+
"learning_rate": 0.0001540259188442745,
|
| 1394 |
+
"loss": 0.8748,
|
| 1395 |
+
"step": 3780
|
| 1396 |
+
},
|
| 1397 |
+
{
|
| 1398 |
+
"epoch": 7.265774378585086,
|
| 1399 |
+
"grad_norm": 2.0109825134277344,
|
| 1400 |
+
"learning_rate": 0.00015190142341193967,
|
| 1401 |
+
"loss": 0.8589,
|
| 1402 |
+
"step": 3800
|
| 1403 |
+
},
|
| 1404 |
+
{
|
| 1405 |
+
"epoch": 7.304015296367113,
|
| 1406 |
+
"grad_norm": 2.1534509658813477,
|
| 1407 |
+
"learning_rate": 0.00014977692797960484,
|
| 1408 |
+
"loss": 0.8373,
|
| 1409 |
+
"step": 3820
|
| 1410 |
+
},
|
| 1411 |
+
{
|
| 1412 |
+
"epoch": 7.342256214149139,
|
| 1413 |
+
"grad_norm": 2.1457502841949463,
|
| 1414 |
+
"learning_rate": 0.00014765243254727004,
|
| 1415 |
+
"loss": 0.8487,
|
| 1416 |
+
"step": 3840
|
| 1417 |
+
},
|
| 1418 |
+
{
|
| 1419 |
+
"epoch": 7.3804971319311665,
|
| 1420 |
+
"grad_norm": 2.200446844100952,
|
| 1421 |
+
"learning_rate": 0.0001455279371149352,
|
| 1422 |
+
"loss": 0.841,
|
| 1423 |
+
"step": 3860
|
| 1424 |
+
},
|
| 1425 |
+
{
|
| 1426 |
+
"epoch": 7.418738049713193,
|
| 1427 |
+
"grad_norm": 2.0335378646850586,
|
| 1428 |
+
"learning_rate": 0.0001434034416826004,
|
| 1429 |
+
"loss": 0.846,
|
| 1430 |
+
"step": 3880
|
| 1431 |
+
},
|
| 1432 |
+
{
|
| 1433 |
+
"epoch": 7.45697896749522,
|
| 1434 |
+
"grad_norm": 2.1471550464630127,
|
| 1435 |
+
"learning_rate": 0.0001412789462502656,
|
| 1436 |
+
"loss": 0.8442,
|
| 1437 |
+
"step": 3900
|
| 1438 |
+
},
|
| 1439 |
+
{
|
| 1440 |
+
"epoch": 7.495219885277247,
|
| 1441 |
+
"grad_norm": 2.2554261684417725,
|
| 1442 |
+
"learning_rate": 0.00013915445081793073,
|
| 1443 |
+
"loss": 0.8651,
|
| 1444 |
+
"step": 3920
|
| 1445 |
+
},
|
| 1446 |
+
{
|
| 1447 |
+
"epoch": 7.533460803059273,
|
| 1448 |
+
"grad_norm": 2.1498897075653076,
|
| 1449 |
+
"learning_rate": 0.00013702995538559593,
|
| 1450 |
+
"loss": 0.839,
|
| 1451 |
+
"step": 3940
|
| 1452 |
+
},
|
| 1453 |
+
{
|
| 1454 |
+
"epoch": 7.5717017208413,
|
| 1455 |
+
"grad_norm": 2.1460678577423096,
|
| 1456 |
+
"learning_rate": 0.00013490545995326113,
|
| 1457 |
+
"loss": 0.8449,
|
| 1458 |
+
"step": 3960
|
| 1459 |
+
},
|
| 1460 |
+
{
|
| 1461 |
+
"epoch": 7.609942638623327,
|
| 1462 |
+
"grad_norm": 2.194730281829834,
|
| 1463 |
+
"learning_rate": 0.00013278096452092628,
|
| 1464 |
+
"loss": 0.8075,
|
| 1465 |
+
"step": 3980
|
| 1466 |
+
},
|
| 1467 |
+
{
|
| 1468 |
+
"epoch": 7.648183556405353,
|
| 1469 |
+
"grad_norm": 2.291327714920044,
|
| 1470 |
+
"learning_rate": 0.00013065646908859147,
|
| 1471 |
+
"loss": 0.8163,
|
| 1472 |
+
"step": 4000
|
| 1473 |
+
},
|
| 1474 |
+
{
|
| 1475 |
+
"epoch": 7.686424474187381,
|
| 1476 |
+
"grad_norm": 2.049647808074951,
|
| 1477 |
+
"learning_rate": 0.00012853197365625662,
|
| 1478 |
+
"loss": 0.7999,
|
| 1479 |
+
"step": 4020
|
| 1480 |
+
},
|
| 1481 |
+
{
|
| 1482 |
+
"epoch": 7.724665391969407,
|
| 1483 |
+
"grad_norm": 2.026001214981079,
|
| 1484 |
+
"learning_rate": 0.00012640747822392182,
|
| 1485 |
+
"loss": 0.7721,
|
| 1486 |
+
"step": 4040
|
| 1487 |
+
},
|
| 1488 |
+
{
|
| 1489 |
+
"epoch": 7.762906309751434,
|
| 1490 |
+
"grad_norm": 2.1242027282714844,
|
| 1491 |
+
"learning_rate": 0.00012428298279158702,
|
| 1492 |
+
"loss": 0.7957,
|
| 1493 |
+
"step": 4060
|
| 1494 |
+
},
|
| 1495 |
+
{
|
| 1496 |
+
"epoch": 7.801147227533461,
|
| 1497 |
+
"grad_norm": 2.078123092651367,
|
| 1498 |
+
"learning_rate": 0.0001221584873592522,
|
| 1499 |
+
"loss": 0.8244,
|
| 1500 |
+
"step": 4080
|
| 1501 |
+
},
|
| 1502 |
+
{
|
| 1503 |
+
"epoch": 7.839388145315487,
|
| 1504 |
+
"grad_norm": 2.028822183609009,
|
| 1505 |
+
"learning_rate": 0.00012003399192691736,
|
| 1506 |
+
"loss": 0.8066,
|
| 1507 |
+
"step": 4100
|
| 1508 |
+
},
|
| 1509 |
+
{
|
| 1510 |
+
"epoch": 7.8776290630975145,
|
| 1511 |
+
"grad_norm": 2.30352520942688,
|
| 1512 |
+
"learning_rate": 0.00011790949649458253,
|
| 1513 |
+
"loss": 0.7892,
|
| 1514 |
+
"step": 4120
|
| 1515 |
+
},
|
| 1516 |
+
{
|
| 1517 |
+
"epoch": 7.915869980879541,
|
| 1518 |
+
"grad_norm": 2.100221872329712,
|
| 1519 |
+
"learning_rate": 0.00011578500106224772,
|
| 1520 |
+
"loss": 0.7703,
|
| 1521 |
+
"step": 4140
|
| 1522 |
+
},
|
| 1523 |
+
{
|
| 1524 |
+
"epoch": 7.954110898661568,
|
| 1525 |
+
"grad_norm": 2.1163010597229004,
|
| 1526 |
+
"learning_rate": 0.00011366050562991289,
|
| 1527 |
+
"loss": 0.7958,
|
| 1528 |
+
"step": 4160
|
| 1529 |
+
},
|
| 1530 |
+
{
|
| 1531 |
+
"epoch": 7.992351816443595,
|
| 1532 |
+
"grad_norm": 2.194089412689209,
|
| 1533 |
+
"learning_rate": 0.00011153601019757808,
|
| 1534 |
+
"loss": 0.7925,
|
| 1535 |
+
"step": 4180
|
| 1536 |
+
},
|
| 1537 |
+
{
|
| 1538 |
+
"epoch": 8.0,
|
| 1539 |
+
"eval_accuracy": 0.9117389841910528,
|
| 1540 |
+
"eval_loss": 0.4518139362335205,
|
| 1541 |
+
"eval_runtime": 1278.572,
|
| 1542 |
+
"eval_samples_per_second": 11.626,
|
| 1543 |
+
"eval_steps_per_second": 11.626,
|
| 1544 |
+
"step": 4184
|
| 1545 |
+
},
|
| 1546 |
+
{
|
| 1547 |
+
"epoch": 8.030592734225621,
|
| 1548 |
+
"grad_norm": 2.024029016494751,
|
| 1549 |
+
"learning_rate": 0.00010941151476524326,
|
| 1550 |
+
"loss": 0.7768,
|
| 1551 |
+
"step": 4200
|
| 1552 |
+
},
|
| 1553 |
+
{
|
| 1554 |
+
"epoch": 8.068833652007648,
|
| 1555 |
+
"grad_norm": 2.101900577545166,
|
| 1556 |
+
"learning_rate": 0.00010728701933290843,
|
| 1557 |
+
"loss": 0.7174,
|
| 1558 |
+
"step": 4220
|
| 1559 |
+
},
|
| 1560 |
+
{
|
| 1561 |
+
"epoch": 8.107074569789676,
|
| 1562 |
+
"grad_norm": 1.8774019479751587,
|
| 1563 |
+
"learning_rate": 0.0001051625239005736,
|
| 1564 |
+
"loss": 0.7331,
|
| 1565 |
+
"step": 4240
|
| 1566 |
+
},
|
| 1567 |
+
{
|
| 1568 |
+
"epoch": 8.145315487571702,
|
| 1569 |
+
"grad_norm": 2.0548768043518066,
|
| 1570 |
+
"learning_rate": 0.0001030380284682388,
|
| 1571 |
+
"loss": 0.6988,
|
| 1572 |
+
"step": 4260
|
| 1573 |
+
},
|
| 1574 |
+
{
|
| 1575 |
+
"epoch": 8.183556405353729,
|
| 1576 |
+
"grad_norm": 2.09981107711792,
|
| 1577 |
+
"learning_rate": 0.00010091353303590398,
|
| 1578 |
+
"loss": 0.7329,
|
| 1579 |
+
"step": 4280
|
| 1580 |
+
},
|
| 1581 |
+
{
|
| 1582 |
+
"epoch": 8.221797323135755,
|
| 1583 |
+
"grad_norm": 1.9958146810531616,
|
| 1584 |
+
"learning_rate": 9.878903760356915e-05,
|
| 1585 |
+
"loss": 0.7085,
|
| 1586 |
+
"step": 4300
|
| 1587 |
+
},
|
| 1588 |
+
{
|
| 1589 |
+
"epoch": 8.260038240917781,
|
| 1590 |
+
"grad_norm": 1.9749237298965454,
|
| 1591 |
+
"learning_rate": 9.666454217123433e-05,
|
| 1592 |
+
"loss": 0.715,
|
| 1593 |
+
"step": 4320
|
| 1594 |
+
},
|
| 1595 |
+
{
|
| 1596 |
+
"epoch": 8.29827915869981,
|
| 1597 |
+
"grad_norm": 1.9691994190216064,
|
| 1598 |
+
"learning_rate": 9.454004673889952e-05,
|
| 1599 |
+
"loss": 0.7151,
|
| 1600 |
+
"step": 4340
|
| 1601 |
+
},
|
| 1602 |
+
{
|
| 1603 |
+
"epoch": 8.336520076481836,
|
| 1604 |
+
"grad_norm": 2.1549344062805176,
|
| 1605 |
+
"learning_rate": 9.241555130656469e-05,
|
| 1606 |
+
"loss": 0.7249,
|
| 1607 |
+
"step": 4360
|
| 1608 |
+
},
|
| 1609 |
+
{
|
| 1610 |
+
"epoch": 8.374760994263863,
|
| 1611 |
+
"grad_norm": 2.2257604598999023,
|
| 1612 |
+
"learning_rate": 9.029105587422986e-05,
|
| 1613 |
+
"loss": 0.7207,
|
| 1614 |
+
"step": 4380
|
| 1615 |
+
},
|
| 1616 |
+
{
|
| 1617 |
+
"epoch": 8.413001912045889,
|
| 1618 |
+
"grad_norm": 2.0424046516418457,
|
| 1619 |
+
"learning_rate": 8.816656044189505e-05,
|
| 1620 |
+
"loss": 0.6981,
|
| 1621 |
+
"step": 4400
|
| 1622 |
+
},
|
| 1623 |
+
{
|
| 1624 |
+
"epoch": 8.451242829827915,
|
| 1625 |
+
"grad_norm": 1.8724883794784546,
|
| 1626 |
+
"learning_rate": 8.604206500956024e-05,
|
| 1627 |
+
"loss": 0.7153,
|
| 1628 |
+
"step": 4420
|
| 1629 |
+
},
|
| 1630 |
+
{
|
| 1631 |
+
"epoch": 8.489483747609942,
|
| 1632 |
+
"grad_norm": 2.0893712043762207,
|
| 1633 |
+
"learning_rate": 8.391756957722541e-05,
|
| 1634 |
+
"loss": 0.7254,
|
| 1635 |
+
"step": 4440
|
| 1636 |
+
},
|
| 1637 |
+
{
|
| 1638 |
+
"epoch": 8.52772466539197,
|
| 1639 |
+
"grad_norm": 2.0398759841918945,
|
| 1640 |
+
"learning_rate": 8.179307414489059e-05,
|
| 1641 |
+
"loss": 0.7184,
|
| 1642 |
+
"step": 4460
|
| 1643 |
+
},
|
| 1644 |
+
{
|
| 1645 |
+
"epoch": 8.565965583173996,
|
| 1646 |
+
"grad_norm": 2.1322920322418213,
|
| 1647 |
+
"learning_rate": 7.966857871255577e-05,
|
| 1648 |
+
"loss": 0.7189,
|
| 1649 |
+
"step": 4480
|
| 1650 |
+
},
|
| 1651 |
+
{
|
| 1652 |
+
"epoch": 8.604206500956023,
|
| 1653 |
+
"grad_norm": 2.0477068424224854,
|
| 1654 |
+
"learning_rate": 7.754408328022095e-05,
|
| 1655 |
+
"loss": 0.705,
|
| 1656 |
+
"step": 4500
|
| 1657 |
+
},
|
| 1658 |
+
{
|
| 1659 |
+
"epoch": 8.64244741873805,
|
| 1660 |
+
"grad_norm": 2.0737295150756836,
|
| 1661 |
+
"learning_rate": 7.541958784788614e-05,
|
| 1662 |
+
"loss": 0.7285,
|
| 1663 |
+
"step": 4520
|
| 1664 |
+
},
|
| 1665 |
+
{
|
| 1666 |
+
"epoch": 8.680688336520076,
|
| 1667 |
+
"grad_norm": 1.9542038440704346,
|
| 1668 |
+
"learning_rate": 7.329509241555131e-05,
|
| 1669 |
+
"loss": 0.7028,
|
| 1670 |
+
"step": 4540
|
| 1671 |
+
},
|
| 1672 |
+
{
|
| 1673 |
+
"epoch": 8.718929254302104,
|
| 1674 |
+
"grad_norm": 1.9409737586975098,
|
| 1675 |
+
"learning_rate": 7.117059698321648e-05,
|
| 1676 |
+
"loss": 0.7031,
|
| 1677 |
+
"step": 4560
|
| 1678 |
+
},
|
| 1679 |
+
{
|
| 1680 |
+
"epoch": 8.75717017208413,
|
| 1681 |
+
"grad_norm": 1.982315182685852,
|
| 1682 |
+
"learning_rate": 6.904610155088168e-05,
|
| 1683 |
+
"loss": 0.6909,
|
| 1684 |
+
"step": 4580
|
| 1685 |
+
},
|
| 1686 |
+
{
|
| 1687 |
+
"epoch": 8.795411089866157,
|
| 1688 |
+
"grad_norm": 2.2722830772399902,
|
| 1689 |
+
"learning_rate": 6.692160611854685e-05,
|
| 1690 |
+
"loss": 0.7083,
|
| 1691 |
+
"step": 4600
|
| 1692 |
+
},
|
| 1693 |
+
{
|
| 1694 |
+
"epoch": 8.833652007648183,
|
| 1695 |
+
"grad_norm": 1.9158116579055786,
|
| 1696 |
+
"learning_rate": 6.479711068621202e-05,
|
| 1697 |
+
"loss": 0.6885,
|
| 1698 |
+
"step": 4620
|
| 1699 |
+
},
|
| 1700 |
+
{
|
| 1701 |
+
"epoch": 8.87189292543021,
|
| 1702 |
+
"grad_norm": 2.058122396469116,
|
| 1703 |
+
"learning_rate": 6.26726152538772e-05,
|
| 1704 |
+
"loss": 0.6912,
|
| 1705 |
+
"step": 4640
|
| 1706 |
+
},
|
| 1707 |
+
{
|
| 1708 |
+
"epoch": 8.910133843212238,
|
| 1709 |
+
"grad_norm": 2.013585090637207,
|
| 1710 |
+
"learning_rate": 6.054811982154239e-05,
|
| 1711 |
+
"loss": 0.6937,
|
| 1712 |
+
"step": 4660
|
| 1713 |
+
},
|
| 1714 |
+
{
|
| 1715 |
+
"epoch": 8.948374760994264,
|
| 1716 |
+
"grad_norm": 2.1662707328796387,
|
| 1717 |
+
"learning_rate": 5.8423624389207567e-05,
|
| 1718 |
+
"loss": 0.7003,
|
| 1719 |
+
"step": 4680
|
| 1720 |
+
},
|
| 1721 |
+
{
|
| 1722 |
+
"epoch": 8.98661567877629,
|
| 1723 |
+
"grad_norm": 2.06309175491333,
|
| 1724 |
+
"learning_rate": 5.6299128956872745e-05,
|
| 1725 |
+
"loss": 0.6733,
|
| 1726 |
+
"step": 4700
|
| 1727 |
+
},
|
| 1728 |
+
{
|
| 1729 |
+
"epoch": 9.0,
|
| 1730 |
+
"eval_accuracy": 0.929297006390851,
|
| 1731 |
+
"eval_loss": 0.38889044523239136,
|
| 1732 |
+
"eval_runtime": 1336.4014,
|
| 1733 |
+
"eval_samples_per_second": 11.123,
|
| 1734 |
+
"eval_steps_per_second": 11.123,
|
| 1735 |
+
"step": 4707
|
| 1736 |
+
},
|
| 1737 |
+
{
|
| 1738 |
+
"epoch": 9.024856596558317,
|
| 1739 |
+
"grad_norm": 1.8986388444900513,
|
| 1740 |
+
"learning_rate": 5.4174633524537924e-05,
|
| 1741 |
+
"loss": 0.6593,
|
| 1742 |
+
"step": 4720
|
| 1743 |
+
},
|
| 1744 |
+
{
|
| 1745 |
+
"epoch": 9.063097514340344,
|
| 1746 |
+
"grad_norm": 1.9107776880264282,
|
| 1747 |
+
"learning_rate": 5.20501380922031e-05,
|
| 1748 |
+
"loss": 0.6354,
|
| 1749 |
+
"step": 4740
|
| 1750 |
+
},
|
| 1751 |
+
{
|
| 1752 |
+
"epoch": 9.101338432122372,
|
| 1753 |
+
"grad_norm": 2.0714404582977295,
|
| 1754 |
+
"learning_rate": 4.992564265986829e-05,
|
| 1755 |
+
"loss": 0.6531,
|
| 1756 |
+
"step": 4760
|
| 1757 |
+
},
|
| 1758 |
+
{
|
| 1759 |
+
"epoch": 9.139579349904398,
|
| 1760 |
+
"grad_norm": 1.9571270942687988,
|
| 1761 |
+
"learning_rate": 4.780114722753346e-05,
|
| 1762 |
+
"loss": 0.6429,
|
| 1763 |
+
"step": 4780
|
| 1764 |
+
},
|
| 1765 |
+
{
|
| 1766 |
+
"epoch": 9.177820267686425,
|
| 1767 |
+
"grad_norm": 1.9968469142913818,
|
| 1768 |
+
"learning_rate": 4.5676651795198646e-05,
|
| 1769 |
+
"loss": 0.6498,
|
| 1770 |
+
"step": 4800
|
| 1771 |
+
},
|
| 1772 |
+
{
|
| 1773 |
+
"epoch": 9.216061185468451,
|
| 1774 |
+
"grad_norm": 1.982832670211792,
|
| 1775 |
+
"learning_rate": 4.355215636286382e-05,
|
| 1776 |
+
"loss": 0.6141,
|
| 1777 |
+
"step": 4820
|
| 1778 |
+
},
|
| 1779 |
+
{
|
| 1780 |
+
"epoch": 9.254302103250478,
|
| 1781 |
+
"grad_norm": 2.035123825073242,
|
| 1782 |
+
"learning_rate": 4.1427660930529e-05,
|
| 1783 |
+
"loss": 0.6269,
|
| 1784 |
+
"step": 4840
|
| 1785 |
+
},
|
| 1786 |
+
{
|
| 1787 |
+
"epoch": 9.292543021032504,
|
| 1788 |
+
"grad_norm": 1.8670984506607056,
|
| 1789 |
+
"learning_rate": 3.930316549819418e-05,
|
| 1790 |
+
"loss": 0.6143,
|
| 1791 |
+
"step": 4860
|
| 1792 |
+
},
|
| 1793 |
+
{
|
| 1794 |
+
"epoch": 9.330783938814532,
|
| 1795 |
+
"grad_norm": 1.9521456956863403,
|
| 1796 |
+
"learning_rate": 3.7178670065859354e-05,
|
| 1797 |
+
"loss": 0.6352,
|
| 1798 |
+
"step": 4880
|
| 1799 |
+
},
|
| 1800 |
+
{
|
| 1801 |
+
"epoch": 9.369024856596559,
|
| 1802 |
+
"grad_norm": 1.9804260730743408,
|
| 1803 |
+
"learning_rate": 3.505417463352454e-05,
|
| 1804 |
+
"loss": 0.6214,
|
| 1805 |
+
"step": 4900
|
| 1806 |
+
},
|
| 1807 |
+
{
|
| 1808 |
+
"epoch": 9.407265774378585,
|
| 1809 |
+
"grad_norm": 2.149338483810425,
|
| 1810 |
+
"learning_rate": 3.292967920118971e-05,
|
| 1811 |
+
"loss": 0.655,
|
| 1812 |
+
"step": 4920
|
| 1813 |
+
},
|
| 1814 |
+
{
|
| 1815 |
+
"epoch": 9.445506692160611,
|
| 1816 |
+
"grad_norm": 1.8145477771759033,
|
| 1817 |
+
"learning_rate": 3.08051837688549e-05,
|
| 1818 |
+
"loss": 0.6095,
|
| 1819 |
+
"step": 4940
|
| 1820 |
+
},
|
| 1821 |
+
{
|
| 1822 |
+
"epoch": 9.483747609942638,
|
| 1823 |
+
"grad_norm": 2.009587287902832,
|
| 1824 |
+
"learning_rate": 2.8680688336520076e-05,
|
| 1825 |
+
"loss": 0.6314,
|
| 1826 |
+
"step": 4960
|
| 1827 |
+
},
|
| 1828 |
+
{
|
| 1829 |
+
"epoch": 9.521988527724666,
|
| 1830 |
+
"grad_norm": 1.946964979171753,
|
| 1831 |
+
"learning_rate": 2.655619290418526e-05,
|
| 1832 |
+
"loss": 0.6272,
|
| 1833 |
+
"step": 4980
|
| 1834 |
+
},
|
| 1835 |
+
{
|
| 1836 |
+
"epoch": 9.560229445506693,
|
| 1837 |
+
"grad_norm": 2.2486774921417236,
|
| 1838 |
+
"learning_rate": 2.4431697471850437e-05,
|
| 1839 |
+
"loss": 0.6133,
|
| 1840 |
+
"step": 5000
|
| 1841 |
+
},
|
| 1842 |
+
{
|
| 1843 |
+
"epoch": 9.598470363288719,
|
| 1844 |
+
"grad_norm": 1.9570778608322144,
|
| 1845 |
+
"learning_rate": 2.2307202039515616e-05,
|
| 1846 |
+
"loss": 0.6185,
|
| 1847 |
+
"step": 5020
|
| 1848 |
+
},
|
| 1849 |
+
{
|
| 1850 |
+
"epoch": 9.636711281070745,
|
| 1851 |
+
"grad_norm": 1.8994139432907104,
|
| 1852 |
+
"learning_rate": 2.0182706607180795e-05,
|
| 1853 |
+
"loss": 0.6366,
|
| 1854 |
+
"step": 5040
|
| 1855 |
+
},
|
| 1856 |
+
{
|
| 1857 |
+
"epoch": 9.674952198852772,
|
| 1858 |
+
"grad_norm": 2.102374792098999,
|
| 1859 |
+
"learning_rate": 1.8058211174845977e-05,
|
| 1860 |
+
"loss": 0.6414,
|
| 1861 |
+
"step": 5060
|
| 1862 |
+
},
|
| 1863 |
+
{
|
| 1864 |
+
"epoch": 9.7131931166348,
|
| 1865 |
+
"grad_norm": 2.073791027069092,
|
| 1866 |
+
"learning_rate": 1.5933715742511156e-05,
|
| 1867 |
+
"loss": 0.6053,
|
| 1868 |
+
"step": 5080
|
| 1869 |
+
},
|
| 1870 |
+
{
|
| 1871 |
+
"epoch": 9.751434034416826,
|
| 1872 |
+
"grad_norm": 1.9205766916275024,
|
| 1873 |
+
"learning_rate": 1.3809220310176333e-05,
|
| 1874 |
+
"loss": 0.6032,
|
| 1875 |
+
"step": 5100
|
| 1876 |
+
},
|
| 1877 |
+
{
|
| 1878 |
+
"epoch": 9.789674952198853,
|
| 1879 |
+
"grad_norm": 2.04294490814209,
|
| 1880 |
+
"learning_rate": 1.1684724877841512e-05,
|
| 1881 |
+
"loss": 0.6202,
|
| 1882 |
+
"step": 5120
|
| 1883 |
+
},
|
| 1884 |
+
{
|
| 1885 |
+
"epoch": 9.82791586998088,
|
| 1886 |
+
"grad_norm": 1.9936119318008423,
|
| 1887 |
+
"learning_rate": 9.560229445506692e-06,
|
| 1888 |
+
"loss": 0.5882,
|
| 1889 |
+
"step": 5140
|
| 1890 |
+
},
|
| 1891 |
+
{
|
| 1892 |
+
"epoch": 9.866156787762906,
|
| 1893 |
+
"grad_norm": 1.8728615045547485,
|
| 1894 |
+
"learning_rate": 7.435734013171872e-06,
|
| 1895 |
+
"loss": 0.5955,
|
| 1896 |
+
"step": 5160
|
| 1897 |
+
},
|
| 1898 |
+
{
|
| 1899 |
+
"epoch": 9.904397705544934,
|
| 1900 |
+
"grad_norm": 2.069910764694214,
|
| 1901 |
+
"learning_rate": 5.311238580837051e-06,
|
| 1902 |
+
"loss": 0.6049,
|
| 1903 |
+
"step": 5180
|
| 1904 |
+
},
|
| 1905 |
+
{
|
| 1906 |
+
"epoch": 9.94263862332696,
|
| 1907 |
+
"grad_norm": 1.9873836040496826,
|
| 1908 |
+
"learning_rate": 3.1867431485022306e-06,
|
| 1909 |
+
"loss": 0.6251,
|
| 1910 |
+
"step": 5200
|
| 1911 |
+
},
|
| 1912 |
+
{
|
| 1913 |
+
"epoch": 9.980879541108987,
|
| 1914 |
+
"grad_norm": 1.932947039604187,
|
| 1915 |
+
"learning_rate": 1.0622477161674102e-06,
|
| 1916 |
+
"loss": 0.6187,
|
| 1917 |
+
"step": 5220
|
| 1918 |
+
},
|
| 1919 |
+
{
|
| 1920 |
+
"epoch": 10.0,
|
| 1921 |
+
"eval_accuracy": 0.9340733266061217,
|
| 1922 |
+
"eval_loss": 0.35941872000694275,
|
| 1923 |
+
"eval_runtime": 1417.2186,
|
| 1924 |
+
"eval_samples_per_second": 10.489,
|
| 1925 |
+
"eval_steps_per_second": 10.489,
|
| 1926 |
+
"step": 5230
|
| 1927 |
+
},
|
| 1928 |
+
{
|
| 1929 |
+
"epoch": 10.0,
|
| 1930 |
+
"step": 5230,
|
| 1931 |
+
"total_flos": 2.7283641066057605e+18,
|
| 1932 |
+
"train_loss": 1.9864544938672797,
|
| 1933 |
+
"train_runtime": 94798.7749,
|
| 1934 |
+
"train_samples_per_second": 14.112,
|
| 1935 |
+
"train_steps_per_second": 0.055
|
| 1936 |
+
}
|
| 1937 |
+
],
|
| 1938 |
+
"logging_steps": 20,
|
| 1939 |
+
"max_steps": 5230,
|
| 1940 |
+
"num_input_tokens_seen": 0,
|
| 1941 |
+
"num_train_epochs": 10,
|
| 1942 |
+
"save_steps": 500,
|
| 1943 |
+
"stateful_callbacks": {
|
| 1944 |
+
"TrainerControl": {
|
| 1945 |
+
"args": {
|
| 1946 |
+
"should_epoch_stop": false,
|
| 1947 |
+
"should_evaluate": false,
|
| 1948 |
+
"should_log": false,
|
| 1949 |
+
"should_save": true,
|
| 1950 |
+
"should_training_stop": true
|
| 1951 |
+
},
|
| 1952 |
+
"attributes": {}
|
| 1953 |
+
}
|
| 1954 |
+
},
|
| 1955 |
+
"total_flos": 2.7283641066057605e+18,
|
| 1956 |
+
"train_batch_size": 256,
|
| 1957 |
+
"trial_name": null,
|
| 1958 |
+
"trial_params": null
|
| 1959 |
+
}
|