Commit
•
cd765e5
1
Parent(s):
2f4c0e7
End of training
Browse files- README.md +3 -3
- all_results.json +8 -0
- runs/May26_02-04-39_be4734752754/events.out.tfevents.1716715469.be4734752754.24.1 +3 -0
- train_results.json +8 -0
- trainer_state.json +1313 -0
README.md
CHANGED
|
@@ -22,7 +22,7 @@ model-index:
|
|
| 22 |
metrics:
|
| 23 |
- name: Accuracy
|
| 24 |
type: accuracy
|
| 25 |
-
value: 0.
|
| 26 |
---
|
| 27 |
|
| 28 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
@@ -32,8 +32,8 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 32 |
|
| 33 |
This model is a fine-tuned version of [facebook/convnextv2-base-22k-384](https://huggingface.co/facebook/convnextv2-base-22k-384) on the imagefolder dataset.
|
| 34 |
It achieves the following results on the evaluation set:
|
| 35 |
-
- Loss: 0.
|
| 36 |
-
- Accuracy: 0.
|
| 37 |
|
| 38 |
## Model description
|
| 39 |
|
|
|
|
| 22 |
metrics:
|
| 23 |
- name: Accuracy
|
| 24 |
type: accuracy
|
| 25 |
+
value: 0.9369047619047619
|
| 26 |
---
|
| 27 |
|
| 28 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
|
|
| 32 |
|
| 33 |
This model is a fine-tuned version of [facebook/convnextv2-base-22k-384](https://huggingface.co/facebook/convnextv2-base-22k-384) on the imagefolder dataset.
|
| 34 |
It achieves the following results on the evaluation set:
|
| 35 |
+
- Loss: 0.3097
|
| 36 |
+
- Accuracy: 0.9369
|
| 37 |
|
| 38 |
## Model description
|
| 39 |
|
all_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 15.0,
|
| 3 |
+
"total_flos": 6.140249030814106e+19,
|
| 4 |
+
"train_loss": 0.21494813935844184,
|
| 5 |
+
"train_runtime": 26072.0492,
|
| 6 |
+
"train_samples_per_second": 10.115,
|
| 7 |
+
"train_steps_per_second": 0.632
|
| 8 |
+
}
|
runs/May26_02-04-39_be4734752754/events.out.tfevents.1716715469.be4734752754.24.1
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1b586cb5c852e12f3c58a5a1b8186f66c8a16e36f6503aa73239903ea4872973
|
| 3 |
+
size 417
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 15.0,
|
| 3 |
+
"total_flos": 6.140249030814106e+19,
|
| 4 |
+
"train_loss": 0.21494813935844184,
|
| 5 |
+
"train_runtime": 26072.0492,
|
| 6 |
+
"train_samples_per_second": 10.115,
|
| 7 |
+
"train_steps_per_second": 0.632
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,1313 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.3127128779888153,
|
| 3 |
+
"best_model_checkpoint": "./convnext-base-8e-5-15ep/checkpoint-8792",
|
| 4 |
+
"epoch": 15.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 16485,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.09,
|
| 13 |
+
"grad_norm": 11.724858283996582,
|
| 14 |
+
"learning_rate": 7.999273662119933e-05,
|
| 15 |
+
"loss": 1.9321,
|
| 16 |
+
"step": 100
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.18,
|
| 20 |
+
"grad_norm": 21.20332908630371,
|
| 21 |
+
"learning_rate": 7.99709491226309e-05,
|
| 22 |
+
"loss": 0.9556,
|
| 23 |
+
"step": 200
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.27,
|
| 27 |
+
"grad_norm": 15.31360149383545,
|
| 28 |
+
"learning_rate": 7.993464541683746e-05,
|
| 29 |
+
"loss": 0.7852,
|
| 30 |
+
"step": 300
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.36,
|
| 34 |
+
"grad_norm": 18.61130714416504,
|
| 35 |
+
"learning_rate": 7.988383868819736e-05,
|
| 36 |
+
"loss": 0.6454,
|
| 37 |
+
"step": 400
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.45,
|
| 41 |
+
"grad_norm": 20.7940616607666,
|
| 42 |
+
"learning_rate": 7.981854738813642e-05,
|
| 43 |
+
"loss": 0.6828,
|
| 44 |
+
"step": 500
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.55,
|
| 48 |
+
"grad_norm": 16.246265411376953,
|
| 49 |
+
"learning_rate": 7.973879522842682e-05,
|
| 50 |
+
"loss": 0.5941,
|
| 51 |
+
"step": 600
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.64,
|
| 55 |
+
"grad_norm": 14.500826835632324,
|
| 56 |
+
"learning_rate": 7.964461117257593e-05,
|
| 57 |
+
"loss": 0.6027,
|
| 58 |
+
"step": 700
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.73,
|
| 62 |
+
"grad_norm": 11.483868598937988,
|
| 63 |
+
"learning_rate": 7.953602942530744e-05,
|
| 64 |
+
"loss": 0.576,
|
| 65 |
+
"step": 800
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.82,
|
| 69 |
+
"grad_norm": 16.98451805114746,
|
| 70 |
+
"learning_rate": 7.941308942013942e-05,
|
| 71 |
+
"loss": 0.5384,
|
| 72 |
+
"step": 900
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.91,
|
| 76 |
+
"grad_norm": 6.033311367034912,
|
| 77 |
+
"learning_rate": 7.927583580506324e-05,
|
| 78 |
+
"loss": 0.5403,
|
| 79 |
+
"step": 1000
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 1.0,
|
| 83 |
+
"eval_accuracy": 0.8743538767395627,
|
| 84 |
+
"eval_loss": 0.42309147119522095,
|
| 85 |
+
"eval_runtime": 106.7517,
|
| 86 |
+
"eval_samples_per_second": 23.559,
|
| 87 |
+
"eval_steps_per_second": 1.48,
|
| 88 |
+
"step": 1099
|
| 89 |
+
},
|
| 90 |
+
{
|
| 91 |
+
"epoch": 1.0,
|
| 92 |
+
"grad_norm": 15.62583065032959,
|
| 93 |
+
"learning_rate": 7.91243184263288e-05,
|
| 94 |
+
"loss": 0.5847,
|
| 95 |
+
"step": 1100
|
| 96 |
+
},
|
| 97 |
+
{
|
| 98 |
+
"epoch": 1.09,
|
| 99 |
+
"grad_norm": 6.581829071044922,
|
| 100 |
+
"learning_rate": 7.895859231034193e-05,
|
| 101 |
+
"loss": 0.4455,
|
| 102 |
+
"step": 1200
|
| 103 |
+
},
|
| 104 |
+
{
|
| 105 |
+
"epoch": 1.18,
|
| 106 |
+
"grad_norm": 12.816280364990234,
|
| 107 |
+
"learning_rate": 7.877871764368051e-05,
|
| 108 |
+
"loss": 0.4448,
|
| 109 |
+
"step": 1300
|
| 110 |
+
},
|
| 111 |
+
{
|
| 112 |
+
"epoch": 1.27,
|
| 113 |
+
"grad_norm": 9.03258991241455,
|
| 114 |
+
"learning_rate": 7.858475975123658e-05,
|
| 115 |
+
"loss": 0.4507,
|
| 116 |
+
"step": 1400
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"epoch": 1.36,
|
| 120 |
+
"grad_norm": 17.637292861938477,
|
| 121 |
+
"learning_rate": 7.837678907249235e-05,
|
| 122 |
+
"loss": 0.405,
|
| 123 |
+
"step": 1500
|
| 124 |
+
},
|
| 125 |
+
{
|
| 126 |
+
"epoch": 1.46,
|
| 127 |
+
"grad_norm": 11.983306884765625,
|
| 128 |
+
"learning_rate": 7.815488113593875e-05,
|
| 129 |
+
"loss": 0.3791,
|
| 130 |
+
"step": 1600
|
| 131 |
+
},
|
| 132 |
+
{
|
| 133 |
+
"epoch": 1.55,
|
| 134 |
+
"grad_norm": 12.843159675598145,
|
| 135 |
+
"learning_rate": 7.79191165316459e-05,
|
| 136 |
+
"loss": 0.462,
|
| 137 |
+
"step": 1700
|
| 138 |
+
},
|
| 139 |
+
{
|
| 140 |
+
"epoch": 1.64,
|
| 141 |
+
"grad_norm": 19.013002395629883,
|
| 142 |
+
"learning_rate": 7.766958088199526e-05,
|
| 143 |
+
"loss": 0.4481,
|
| 144 |
+
"step": 1800
|
| 145 |
+
},
|
| 146 |
+
{
|
| 147 |
+
"epoch": 1.73,
|
| 148 |
+
"grad_norm": 5.846986770629883,
|
| 149 |
+
"learning_rate": 7.740636481058419e-05,
|
| 150 |
+
"loss": 0.4349,
|
| 151 |
+
"step": 1900
|
| 152 |
+
},
|
| 153 |
+
{
|
| 154 |
+
"epoch": 1.82,
|
| 155 |
+
"grad_norm": 12.305352210998535,
|
| 156 |
+
"learning_rate": 7.712956390931434e-05,
|
| 157 |
+
"loss": 0.3673,
|
| 158 |
+
"step": 2000
|
| 159 |
+
},
|
| 160 |
+
{
|
| 161 |
+
"epoch": 1.91,
|
| 162 |
+
"grad_norm": 8.298523902893066,
|
| 163 |
+
"learning_rate": 7.683927870367564e-05,
|
| 164 |
+
"loss": 0.4376,
|
| 165 |
+
"step": 2100
|
| 166 |
+
},
|
| 167 |
+
{
|
| 168 |
+
"epoch": 2.0,
|
| 169 |
+
"eval_accuracy": 0.8898608349900596,
|
| 170 |
+
"eval_loss": 0.38170379400253296,
|
| 171 |
+
"eval_runtime": 106.7439,
|
| 172 |
+
"eval_samples_per_second": 23.561,
|
| 173 |
+
"eval_steps_per_second": 1.48,
|
| 174 |
+
"step": 2198
|
| 175 |
+
},
|
| 176 |
+
{
|
| 177 |
+
"epoch": 2.0,
|
| 178 |
+
"grad_norm": 14.847254753112793,
|
| 179 |
+
"learning_rate": 7.653561461623853e-05,
|
| 180 |
+
"loss": 0.4081,
|
| 181 |
+
"step": 2200
|
| 182 |
+
},
|
| 183 |
+
{
|
| 184 |
+
"epoch": 2.09,
|
| 185 |
+
"grad_norm": 10.653617858886719,
|
| 186 |
+
"learning_rate": 7.621868192836776e-05,
|
| 187 |
+
"loss": 0.3557,
|
| 188 |
+
"step": 2300
|
| 189 |
+
},
|
| 190 |
+
{
|
| 191 |
+
"epoch": 2.18,
|
| 192 |
+
"grad_norm": 16.83597755432129,
|
| 193 |
+
"learning_rate": 7.588859574017165e-05,
|
| 194 |
+
"loss": 0.3405,
|
| 195 |
+
"step": 2400
|
| 196 |
+
},
|
| 197 |
+
{
|
| 198 |
+
"epoch": 2.27,
|
| 199 |
+
"grad_norm": 15.18385124206543,
|
| 200 |
+
"learning_rate": 7.554547592870128e-05,
|
| 201 |
+
"loss": 0.3196,
|
| 202 |
+
"step": 2500
|
| 203 |
+
},
|
| 204 |
+
{
|
| 205 |
+
"epoch": 2.37,
|
| 206 |
+
"grad_norm": 5.773273468017578,
|
| 207 |
+
"learning_rate": 7.518944710441491e-05,
|
| 208 |
+
"loss": 0.37,
|
| 209 |
+
"step": 2600
|
| 210 |
+
},
|
| 211 |
+
{
|
| 212 |
+
"epoch": 2.46,
|
| 213 |
+
"grad_norm": 13.849283218383789,
|
| 214 |
+
"learning_rate": 7.482063856592323e-05,
|
| 215 |
+
"loss": 0.3626,
|
| 216 |
+
"step": 2700
|
| 217 |
+
},
|
| 218 |
+
{
|
| 219 |
+
"epoch": 2.55,
|
| 220 |
+
"grad_norm": 15.644866943359375,
|
| 221 |
+
"learning_rate": 7.44391842530323e-05,
|
| 222 |
+
"loss": 0.3598,
|
| 223 |
+
"step": 2800
|
| 224 |
+
},
|
| 225 |
+
{
|
| 226 |
+
"epoch": 2.64,
|
| 227 |
+
"grad_norm": 11.187522888183594,
|
| 228 |
+
"learning_rate": 7.404522269810056e-05,
|
| 229 |
+
"loss": 0.3805,
|
| 230 |
+
"step": 2900
|
| 231 |
+
},
|
| 232 |
+
{
|
| 233 |
+
"epoch": 2.73,
|
| 234 |
+
"grad_norm": 2.7877767086029053,
|
| 235 |
+
"learning_rate": 7.363889697572835e-05,
|
| 236 |
+
"loss": 0.322,
|
| 237 |
+
"step": 3000
|
| 238 |
+
},
|
| 239 |
+
{
|
| 240 |
+
"epoch": 2.82,
|
| 241 |
+
"grad_norm": 11.111302375793457,
|
| 242 |
+
"learning_rate": 7.322035465079756e-05,
|
| 243 |
+
"loss": 0.3524,
|
| 244 |
+
"step": 3100
|
| 245 |
+
},
|
| 246 |
+
{
|
| 247 |
+
"epoch": 2.91,
|
| 248 |
+
"grad_norm": 15.361136436462402,
|
| 249 |
+
"learning_rate": 7.278974772488071e-05,
|
| 250 |
+
"loss": 0.3601,
|
| 251 |
+
"step": 3200
|
| 252 |
+
},
|
| 253 |
+
{
|
| 254 |
+
"epoch": 3.0,
|
| 255 |
+
"eval_accuracy": 0.9017892644135189,
|
| 256 |
+
"eval_loss": 0.38179874420166016,
|
| 257 |
+
"eval_runtime": 107.7627,
|
| 258 |
+
"eval_samples_per_second": 23.338,
|
| 259 |
+
"eval_steps_per_second": 1.466,
|
| 260 |
+
"step": 3297
|
| 261 |
+
},
|
| 262 |
+
{
|
| 263 |
+
"epoch": 3.0,
|
| 264 |
+
"grad_norm": 11.831352233886719,
|
| 265 |
+
"learning_rate": 7.234723258103863e-05,
|
| 266 |
+
"loss": 0.3396,
|
| 267 |
+
"step": 3300
|
| 268 |
+
},
|
| 269 |
+
{
|
| 270 |
+
"epoch": 3.09,
|
| 271 |
+
"grad_norm": 11.50969123840332,
|
| 272 |
+
"learning_rate": 7.189296992702708e-05,
|
| 273 |
+
"loss": 0.2502,
|
| 274 |
+
"step": 3400
|
| 275 |
+
},
|
| 276 |
+
{
|
| 277 |
+
"epoch": 3.18,
|
| 278 |
+
"grad_norm": 0.8365811705589294,
|
| 279 |
+
"learning_rate": 7.142712473693261e-05,
|
| 280 |
+
"loss": 0.2747,
|
| 281 |
+
"step": 3500
|
| 282 |
+
},
|
| 283 |
+
{
|
| 284 |
+
"epoch": 3.28,
|
| 285 |
+
"grad_norm": 11.02737045288086,
|
| 286 |
+
"learning_rate": 7.094986619125911e-05,
|
| 287 |
+
"loss": 0.293,
|
| 288 |
+
"step": 3600
|
| 289 |
+
},
|
| 290 |
+
{
|
| 291 |
+
"epoch": 3.37,
|
| 292 |
+
"grad_norm": 8.201223373413086,
|
| 293 |
+
"learning_rate": 7.046136761548677e-05,
|
| 294 |
+
"loss": 0.2775,
|
| 295 |
+
"step": 3700
|
| 296 |
+
},
|
| 297 |
+
{
|
| 298 |
+
"epoch": 3.46,
|
| 299 |
+
"grad_norm": 4.118073463439941,
|
| 300 |
+
"learning_rate": 6.996180641712553e-05,
|
| 301 |
+
"loss": 0.2622,
|
| 302 |
+
"step": 3800
|
| 303 |
+
},
|
| 304 |
+
{
|
| 305 |
+
"epoch": 3.55,
|
| 306 |
+
"grad_norm": 16.599191665649414,
|
| 307 |
+
"learning_rate": 6.945136402128628e-05,
|
| 308 |
+
"loss": 0.3098,
|
| 309 |
+
"step": 3900
|
| 310 |
+
},
|
| 311 |
+
{
|
| 312 |
+
"epoch": 3.64,
|
| 313 |
+
"grad_norm": 5.20058012008667,
|
| 314 |
+
"learning_rate": 6.893022580479289e-05,
|
| 315 |
+
"loss": 0.3156,
|
| 316 |
+
"step": 4000
|
| 317 |
+
},
|
| 318 |
+
{
|
| 319 |
+
"epoch": 3.73,
|
| 320 |
+
"grad_norm": 7.4321465492248535,
|
| 321 |
+
"learning_rate": 6.839858102885904e-05,
|
| 322 |
+
"loss": 0.3304,
|
| 323 |
+
"step": 4100
|
| 324 |
+
},
|
| 325 |
+
{
|
| 326 |
+
"epoch": 3.82,
|
| 327 |
+
"grad_norm": 0.302477091550827,
|
| 328 |
+
"learning_rate": 6.785662277035447e-05,
|
| 329 |
+
"loss": 0.2812,
|
| 330 |
+
"step": 4200
|
| 331 |
+
},
|
| 332 |
+
{
|
| 333 |
+
"epoch": 3.91,
|
| 334 |
+
"grad_norm": 9.081244468688965,
|
| 335 |
+
"learning_rate": 6.730454785168549e-05,
|
| 336 |
+
"loss": 0.3202,
|
| 337 |
+
"step": 4300
|
| 338 |
+
},
|
| 339 |
+
{
|
| 340 |
+
"epoch": 4.0,
|
| 341 |
+
"eval_accuracy": 0.920079522862823,
|
| 342 |
+
"eval_loss": 0.3152866065502167,
|
| 343 |
+
"eval_runtime": 107.0627,
|
| 344 |
+
"eval_samples_per_second": 23.491,
|
| 345 |
+
"eval_steps_per_second": 1.476,
|
| 346 |
+
"step": 4396
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 4.0,
|
| 350 |
+
"grad_norm": 7.102989673614502,
|
| 351 |
+
"learning_rate": 6.67425567693151e-05,
|
| 352 |
+
"loss": 0.2809,
|
| 353 |
+
"step": 4400
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 4.09,
|
| 357 |
+
"grad_norm": 7.009576320648193,
|
| 358 |
+
"learning_rate": 6.617085362094902e-05,
|
| 359 |
+
"loss": 0.2443,
|
| 360 |
+
"step": 4500
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 4.19,
|
| 364 |
+
"grad_norm": 7.170097827911377,
|
| 365 |
+
"learning_rate": 6.558964603141364e-05,
|
| 366 |
+
"loss": 0.2592,
|
| 367 |
+
"step": 4600
|
| 368 |
+
},
|
| 369 |
+
{
|
| 370 |
+
"epoch": 4.28,
|
| 371 |
+
"grad_norm": 2.704582452774048,
|
| 372 |
+
"learning_rate": 6.49991450772532e-05,
|
| 373 |
+
"loss": 0.2488,
|
| 374 |
+
"step": 4700
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 4.37,
|
| 378 |
+
"grad_norm": 0.38259217143058777,
|
| 379 |
+
"learning_rate": 6.43995652100733e-05,
|
| 380 |
+
"loss": 0.2191,
|
| 381 |
+
"step": 4800
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 4.46,
|
| 385 |
+
"grad_norm": 11.570588111877441,
|
| 386 |
+
"learning_rate": 6.379112417865878e-05,
|
| 387 |
+
"loss": 0.2352,
|
| 388 |
+
"step": 4900
|
| 389 |
+
},
|
| 390 |
+
{
|
| 391 |
+
"epoch": 4.55,
|
| 392 |
+
"grad_norm": 14.971210479736328,
|
| 393 |
+
"learning_rate": 6.317404294989409e-05,
|
| 394 |
+
"loss": 0.2137,
|
| 395 |
+
"step": 5000
|
| 396 |
+
},
|
| 397 |
+
{
|
| 398 |
+
"epoch": 4.64,
|
| 399 |
+
"grad_norm": 18.02596664428711,
|
| 400 |
+
"learning_rate": 6.2548545628515e-05,
|
| 401 |
+
"loss": 0.2284,
|
| 402 |
+
"step": 5100
|
| 403 |
+
},
|
| 404 |
+
{
|
| 405 |
+
"epoch": 4.73,
|
| 406 |
+
"grad_norm": 4.175428867340088,
|
| 407 |
+
"learning_rate": 6.191485937572068e-05,
|
| 408 |
+
"loss": 0.2541,
|
| 409 |
+
"step": 5200
|
| 410 |
+
},
|
| 411 |
+
{
|
| 412 |
+
"epoch": 4.82,
|
| 413 |
+
"grad_norm": 18.096067428588867,
|
| 414 |
+
"learning_rate": 6.127321432667592e-05,
|
| 415 |
+
"loss": 0.2382,
|
| 416 |
+
"step": 5300
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"epoch": 4.91,
|
| 420 |
+
"grad_norm": 13.15633773803711,
|
| 421 |
+
"learning_rate": 6.062384350693302e-05,
|
| 422 |
+
"loss": 0.2463,
|
| 423 |
+
"step": 5400
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 5.0,
|
| 427 |
+
"eval_accuracy": 0.9228628230616303,
|
| 428 |
+
"eval_loss": 0.32158657908439636,
|
| 429 |
+
"eval_runtime": 107.3379,
|
| 430 |
+
"eval_samples_per_second": 23.431,
|
| 431 |
+
"eval_steps_per_second": 1.472,
|
| 432 |
+
"step": 5495
|
| 433 |
+
},
|
| 434 |
+
{
|
| 435 |
+
"epoch": 5.0,
|
| 436 |
+
"grad_norm": 6.101550579071045,
|
| 437 |
+
"learning_rate": 5.9966982747804285e-05,
|
| 438 |
+
"loss": 0.2692,
|
| 439 |
+
"step": 5500
|
| 440 |
+
},
|
| 441 |
+
{
|
| 442 |
+
"epoch": 5.1,
|
| 443 |
+
"grad_norm": 1.3759921789169312,
|
| 444 |
+
"learning_rate": 5.930287060071538e-05,
|
| 445 |
+
"loss": 0.1879,
|
| 446 |
+
"step": 5600
|
| 447 |
+
},
|
| 448 |
+
{
|
| 449 |
+
"epoch": 5.19,
|
| 450 |
+
"grad_norm": 23.739288330078125,
|
| 451 |
+
"learning_rate": 5.86317482505708e-05,
|
| 452 |
+
"loss": 0.2182,
|
| 453 |
+
"step": 5700
|
| 454 |
+
},
|
| 455 |
+
{
|
| 456 |
+
"epoch": 5.28,
|
| 457 |
+
"grad_norm": 5.8365159034729,
|
| 458 |
+
"learning_rate": 5.795385942816307e-05,
|
| 459 |
+
"loss": 0.189,
|
| 460 |
+
"step": 5800
|
| 461 |
+
},
|
| 462 |
+
{
|
| 463 |
+
"epoch": 5.37,
|
| 464 |
+
"grad_norm": 0.29634252190589905,
|
| 465 |
+
"learning_rate": 5.726945032165731e-05,
|
| 466 |
+
"loss": 0.214,
|
| 467 |
+
"step": 5900
|
| 468 |
+
},
|
| 469 |
+
{
|
| 470 |
+
"epoch": 5.46,
|
| 471 |
+
"grad_norm": 0.2643405497074127,
|
| 472 |
+
"learning_rate": 5.657876948718328e-05,
|
| 473 |
+
"loss": 0.1798,
|
| 474 |
+
"step": 6000
|
| 475 |
+
},
|
| 476 |
+
{
|
| 477 |
+
"epoch": 5.55,
|
| 478 |
+
"grad_norm": 0.6693936586380005,
|
| 479 |
+
"learning_rate": 5.588206775856751e-05,
|
| 480 |
+
"loss": 0.2094,
|
| 481 |
+
"step": 6100
|
| 482 |
+
},
|
| 483 |
+
{
|
| 484 |
+
"epoch": 5.64,
|
| 485 |
+
"grad_norm": 2.3573074340820312,
|
| 486 |
+
"learning_rate": 5.517959815623834e-05,
|
| 487 |
+
"loss": 0.1737,
|
| 488 |
+
"step": 6200
|
| 489 |
+
},
|
| 490 |
+
{
|
| 491 |
+
"epoch": 5.73,
|
| 492 |
+
"grad_norm": 6.905389308929443,
|
| 493 |
+
"learning_rate": 5.447161579533662e-05,
|
| 494 |
+
"loss": 0.2354,
|
| 495 |
+
"step": 6300
|
| 496 |
+
},
|
| 497 |
+
{
|
| 498 |
+
"epoch": 5.82,
|
| 499 |
+
"grad_norm": 5.905348300933838,
|
| 500 |
+
"learning_rate": 5.375837779306594e-05,
|
| 501 |
+
"loss": 0.2056,
|
| 502 |
+
"step": 6400
|
| 503 |
+
},
|
| 504 |
+
{
|
| 505 |
+
"epoch": 5.91,
|
| 506 |
+
"grad_norm": 13.43565559387207,
|
| 507 |
+
"learning_rate": 5.3040143175315564e-05,
|
| 508 |
+
"loss": 0.2051,
|
| 509 |
+
"step": 6500
|
| 510 |
+
},
|
| 511 |
+
{
|
| 512 |
+
"epoch": 6.0,
|
| 513 |
+
"eval_accuracy": 0.921272365805169,
|
| 514 |
+
"eval_loss": 0.33380183577537537,
|
| 515 |
+
"eval_runtime": 106.6505,
|
| 516 |
+
"eval_samples_per_second": 23.582,
|
| 517 |
+
"eval_steps_per_second": 1.481,
|
| 518 |
+
"step": 6594
|
| 519 |
+
},
|
| 520 |
+
{
|
| 521 |
+
"epoch": 6.01,
|
| 522 |
+
"grad_norm": 8.566280364990234,
|
| 523 |
+
"learning_rate": 5.2317172782590326e-05,
|
| 524 |
+
"loss": 0.2282,
|
| 525 |
+
"step": 6600
|
| 526 |
+
},
|
| 527 |
+
{
|
| 528 |
+
"epoch": 6.1,
|
| 529 |
+
"grad_norm": 14.734358787536621,
|
| 530 |
+
"learning_rate": 5.158972917528144e-05,
|
| 531 |
+
"loss": 0.1602,
|
| 532 |
+
"step": 6700
|
| 533 |
+
},
|
| 534 |
+
{
|
| 535 |
+
"epoch": 6.19,
|
| 536 |
+
"grad_norm": 20.460796356201172,
|
| 537 |
+
"learning_rate": 5.085807653831266e-05,
|
| 538 |
+
"loss": 0.1738,
|
| 539 |
+
"step": 6800
|
| 540 |
+
},
|
| 541 |
+
{
|
| 542 |
+
"epoch": 6.28,
|
| 543 |
+
"grad_norm": 1.8641005754470825,
|
| 544 |
+
"learning_rate": 5.012248058519667e-05,
|
| 545 |
+
"loss": 0.1813,
|
| 546 |
+
"step": 6900
|
| 547 |
+
},
|
| 548 |
+
{
|
| 549 |
+
"epoch": 6.37,
|
| 550 |
+
"grad_norm": 0.38667044043540955,
|
| 551 |
+
"learning_rate": 4.9383208461536056e-05,
|
| 552 |
+
"loss": 0.1964,
|
| 553 |
+
"step": 7000
|
| 554 |
+
},
|
| 555 |
+
{
|
| 556 |
+
"epoch": 6.46,
|
| 557 |
+
"grad_norm": 8.61457347869873,
|
| 558 |
+
"learning_rate": 4.8640528648004334e-05,
|
| 559 |
+
"loss": 0.1706,
|
| 560 |
+
"step": 7100
|
| 561 |
+
},
|
| 562 |
+
{
|
| 563 |
+
"epoch": 6.55,
|
| 564 |
+
"grad_norm": 5.7172160148620605,
|
| 565 |
+
"learning_rate": 4.789471086284219e-05,
|
| 566 |
+
"loss": 0.1612,
|
| 567 |
+
"step": 7200
|
| 568 |
+
},
|
| 569 |
+
{
|
| 570 |
+
"epoch": 6.64,
|
| 571 |
+
"grad_norm": 0.22469474375247955,
|
| 572 |
+
"learning_rate": 4.714602596390412e-05,
|
| 573 |
+
"loss": 0.1697,
|
| 574 |
+
"step": 7300
|
| 575 |
+
},
|
| 576 |
+
{
|
| 577 |
+
"epoch": 6.73,
|
| 578 |
+
"grad_norm": 15.02285385131836,
|
| 579 |
+
"learning_rate": 4.639474585029129e-05,
|
| 580 |
+
"loss": 0.1886,
|
| 581 |
+
"step": 7400
|
| 582 |
+
},
|
| 583 |
+
{
|
| 584 |
+
"epoch": 6.82,
|
| 585 |
+
"grad_norm": 12.13104248046875,
|
| 586 |
+
"learning_rate": 4.5641143363606216e-05,
|
| 587 |
+
"loss": 0.1735,
|
| 588 |
+
"step": 7500
|
| 589 |
+
},
|
| 590 |
+
{
|
| 591 |
+
"epoch": 6.92,
|
| 592 |
+
"grad_norm": 2.0161709785461426,
|
| 593 |
+
"learning_rate": 4.488549218886521e-05,
|
| 594 |
+
"loss": 0.2108,
|
| 595 |
+
"step": 7600
|
| 596 |
+
},
|
| 597 |
+
{
|
| 598 |
+
"epoch": 7.0,
|
| 599 |
+
"eval_accuracy": 0.9272365805168986,
|
| 600 |
+
"eval_loss": 0.3223852515220642,
|
| 601 |
+
"eval_runtime": 107.0584,
|
| 602 |
+
"eval_samples_per_second": 23.492,
|
| 603 |
+
"eval_steps_per_second": 1.476,
|
| 604 |
+
"step": 7693
|
| 605 |
+
},
|
| 606 |
+
{
|
| 607 |
+
"epoch": 7.01,
|
| 608 |
+
"grad_norm": 8.913517951965332,
|
| 609 |
+
"learning_rate": 4.412806675510442e-05,
|
| 610 |
+
"loss": 0.1466,
|
| 611 |
+
"step": 7700
|
| 612 |
+
},
|
| 613 |
+
{
|
| 614 |
+
"epoch": 7.1,
|
| 615 |
+
"grad_norm": 9.739709854125977,
|
| 616 |
+
"learning_rate": 4.33691421357158e-05,
|
| 617 |
+
"loss": 0.1382,
|
| 618 |
+
"step": 7800
|
| 619 |
+
},
|
| 620 |
+
{
|
| 621 |
+
"epoch": 7.19,
|
| 622 |
+
"grad_norm": 0.3633786737918854,
|
| 623 |
+
"learning_rate": 4.260899394854893e-05,
|
| 624 |
+
"loss": 0.1598,
|
| 625 |
+
"step": 7900
|
| 626 |
+
},
|
| 627 |
+
{
|
| 628 |
+
"epoch": 7.28,
|
| 629 |
+
"grad_norm": 1.9761762619018555,
|
| 630 |
+
"learning_rate": 4.184789825581521e-05,
|
| 631 |
+
"loss": 0.1272,
|
| 632 |
+
"step": 8000
|
| 633 |
+
},
|
| 634 |
+
{
|
| 635 |
+
"epoch": 7.37,
|
| 636 |
+
"grad_norm": 0.9676409363746643,
|
| 637 |
+
"learning_rate": 4.108613146383063e-05,
|
| 638 |
+
"loss": 0.1692,
|
| 639 |
+
"step": 8100
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 7.46,
|
| 643 |
+
"grad_norm": 0.3291204273700714,
|
| 644 |
+
"learning_rate": 4.03239702226336e-05,
|
| 645 |
+
"loss": 0.1301,
|
| 646 |
+
"step": 8200
|
| 647 |
+
},
|
| 648 |
+
{
|
| 649 |
+
"epoch": 7.55,
|
| 650 |
+
"grad_norm": 11.293334007263184,
|
| 651 |
+
"learning_rate": 3.9561691325514226e-05,
|
| 652 |
+
"loss": 0.1496,
|
| 653 |
+
"step": 8300
|
| 654 |
+
},
|
| 655 |
+
{
|
| 656 |
+
"epoch": 7.64,
|
| 657 |
+
"grad_norm": 0.4240261912345886,
|
| 658 |
+
"learning_rate": 3.879957160849155e-05,
|
| 659 |
+
"loss": 0.1658,
|
| 660 |
+
"step": 8400
|
| 661 |
+
},
|
| 662 |
+
{
|
| 663 |
+
"epoch": 7.73,
|
| 664 |
+
"grad_norm": 9.459733009338379,
|
| 665 |
+
"learning_rate": 3.803788784977541e-05,
|
| 666 |
+
"loss": 0.1848,
|
| 667 |
+
"step": 8500
|
| 668 |
+
},
|
| 669 |
+
{
|
| 670 |
+
"epoch": 7.83,
|
| 671 |
+
"grad_norm": 0.03799422085285187,
|
| 672 |
+
"learning_rate": 3.7276916669249106e-05,
|
| 673 |
+
"loss": 0.1599,
|
| 674 |
+
"step": 8600
|
| 675 |
+
},
|
| 676 |
+
{
|
| 677 |
+
"epoch": 7.92,
|
| 678 |
+
"grad_norm": 7.809151649475098,
|
| 679 |
+
"learning_rate": 3.651693442800964e-05,
|
| 680 |
+
"loss": 0.1568,
|
| 681 |
+
"step": 8700
|
| 682 |
+
},
|
| 683 |
+
{
|
| 684 |
+
"epoch": 8.0,
|
| 685 |
+
"eval_accuracy": 0.9355864811133201,
|
| 686 |
+
"eval_loss": 0.3127128779888153,
|
| 687 |
+
"eval_runtime": 107.9901,
|
| 688 |
+
"eval_samples_per_second": 23.289,
|
| 689 |
+
"eval_steps_per_second": 1.463,
|
| 690 |
+
"step": 8792
|
| 691 |
+
},
|
| 692 |
+
{
|
| 693 |
+
"epoch": 8.01,
|
| 694 |
+
"grad_norm": 0.09405653923749924,
|
| 695 |
+
"learning_rate": 3.575821712800204e-05,
|
| 696 |
+
"loss": 0.1238,
|
| 697 |
+
"step": 8800
|
| 698 |
+
},
|
| 699 |
+
{
|
| 700 |
+
"epoch": 8.1,
|
| 701 |
+
"grad_norm": 5.202500820159912,
|
| 702 |
+
"learning_rate": 3.5001040311783905e-05,
|
| 703 |
+
"loss": 0.1327,
|
| 704 |
+
"step": 8900
|
| 705 |
+
},
|
| 706 |
+
{
|
| 707 |
+
"epoch": 8.19,
|
| 708 |
+
"grad_norm": 0.39644354581832886,
|
| 709 |
+
"learning_rate": 3.4245678962457005e-05,
|
| 710 |
+
"loss": 0.1265,
|
| 711 |
+
"step": 9000
|
| 712 |
+
},
|
| 713 |
+
{
|
| 714 |
+
"epoch": 8.28,
|
| 715 |
+
"grad_norm": 3.383341073989868,
|
| 716 |
+
"learning_rate": 3.349240740380192e-05,
|
| 717 |
+
"loss": 0.1159,
|
| 718 |
+
"step": 9100
|
| 719 |
+
},
|
| 720 |
+
{
|
| 721 |
+
"epoch": 8.37,
|
| 722 |
+
"grad_norm": 0.2011689841747284,
|
| 723 |
+
"learning_rate": 3.274149920065217e-05,
|
| 724 |
+
"loss": 0.1529,
|
| 725 |
+
"step": 9200
|
| 726 |
+
},
|
| 727 |
+
{
|
| 728 |
+
"epoch": 8.46,
|
| 729 |
+
"grad_norm": 0.02637963555753231,
|
| 730 |
+
"learning_rate": 3.199322705954396e-05,
|
| 731 |
+
"loss": 0.1003,
|
| 732 |
+
"step": 9300
|
| 733 |
+
},
|
| 734 |
+
{
|
| 735 |
+
"epoch": 8.55,
|
| 736 |
+
"grad_norm": 6.775584697723389,
|
| 737 |
+
"learning_rate": 3.1247862729677615e-05,
|
| 738 |
+
"loss": 0.1186,
|
| 739 |
+
"step": 9400
|
| 740 |
+
},
|
| 741 |
+
{
|
| 742 |
+
"epoch": 8.64,
|
| 743 |
+
"grad_norm": 0.8526474833488464,
|
| 744 |
+
"learning_rate": 3.0505676904226766e-05,
|
| 745 |
+
"loss": 0.1354,
|
| 746 |
+
"step": 9500
|
| 747 |
+
},
|
| 748 |
+
{
|
| 749 |
+
"epoch": 8.74,
|
| 750 |
+
"grad_norm": 5.6588945388793945,
|
| 751 |
+
"learning_rate": 2.9766939122030964e-05,
|
| 752 |
+
"loss": 0.137,
|
| 753 |
+
"step": 9600
|
| 754 |
+
},
|
| 755 |
+
{
|
| 756 |
+
"epoch": 8.83,
|
| 757 |
+
"grad_norm": 13.947266578674316,
|
| 758 |
+
"learning_rate": 2.903191766970749e-05,
|
| 759 |
+
"loss": 0.1336,
|
| 760 |
+
"step": 9700
|
| 761 |
+
},
|
| 762 |
+
{
|
| 763 |
+
"epoch": 8.92,
|
| 764 |
+
"grad_norm": 6.7341694831848145,
|
| 765 |
+
"learning_rate": 2.8300879484218112e-05,
|
| 766 |
+
"loss": 0.1491,
|
| 767 |
+
"step": 9800
|
| 768 |
+
},
|
| 769 |
+
{
|
| 770 |
+
"epoch": 9.0,
|
| 771 |
+
"eval_accuracy": 0.9351888667992048,
|
| 772 |
+
"eval_loss": 0.32577136158943176,
|
| 773 |
+
"eval_runtime": 108.1206,
|
| 774 |
+
"eval_samples_per_second": 23.261,
|
| 775 |
+
"eval_steps_per_second": 1.461,
|
| 776 |
+
"step": 9891
|
| 777 |
+
},
|
| 778 |
+
{
|
| 779 |
+
"epoch": 9.01,
|
| 780 |
+
"grad_norm": 1.849369764328003,
|
| 781 |
+
"learning_rate": 2.757409005592578e-05,
|
| 782 |
+
"loss": 0.1105,
|
| 783 |
+
"step": 9900
|
| 784 |
+
},
|
| 785 |
+
{
|
| 786 |
+
"epoch": 9.1,
|
| 787 |
+
"grad_norm": 0.0076730018481612206,
|
| 788 |
+
"learning_rate": 2.6851813332176796e-05,
|
| 789 |
+
"loss": 0.09,
|
| 790 |
+
"step": 10000
|
| 791 |
+
},
|
| 792 |
+
{
|
| 793 |
+
"epoch": 9.19,
|
| 794 |
+
"grad_norm": 0.42202454805374146,
|
| 795 |
+
"learning_rate": 2.6134311621443315e-05,
|
| 796 |
+
"loss": 0.1067,
|
| 797 |
+
"step": 10100
|
| 798 |
+
},
|
| 799 |
+
{
|
| 800 |
+
"epoch": 9.28,
|
| 801 |
+
"grad_norm": 0.32351329922676086,
|
| 802 |
+
"learning_rate": 2.5421845498061117e-05,
|
| 803 |
+
"loss": 0.1117,
|
| 804 |
+
"step": 10200
|
| 805 |
+
},
|
| 806 |
+
{
|
| 807 |
+
"epoch": 9.37,
|
| 808 |
+
"grad_norm": 0.507881760597229,
|
| 809 |
+
"learning_rate": 2.4714673707597038e-05,
|
| 810 |
+
"loss": 0.099,
|
| 811 |
+
"step": 10300
|
| 812 |
+
},
|
| 813 |
+
{
|
| 814 |
+
"epoch": 9.46,
|
| 815 |
+
"grad_norm": 16.288957595825195,
|
| 816 |
+
"learning_rate": 2.4013053072880646e-05,
|
| 817 |
+
"loss": 0.091,
|
| 818 |
+
"step": 10400
|
| 819 |
+
},
|
| 820 |
+
{
|
| 821 |
+
"epoch": 9.55,
|
| 822 |
+
"grad_norm": 0.02297704666852951,
|
| 823 |
+
"learning_rate": 2.3317238400734145e-05,
|
| 824 |
+
"loss": 0.1295,
|
| 825 |
+
"step": 10500
|
| 826 |
+
},
|
| 827 |
+
{
|
| 828 |
+
"epoch": 9.65,
|
| 829 |
+
"grad_norm": 9.774455070495605,
|
| 830 |
+
"learning_rate": 2.2627482389434477e-05,
|
| 831 |
+
"loss": 0.1244,
|
| 832 |
+
"step": 10600
|
| 833 |
+
},
|
| 834 |
+
{
|
| 835 |
+
"epoch": 9.74,
|
| 836 |
+
"grad_norm": 1.1963157653808594,
|
| 837 |
+
"learning_rate": 2.194403553694116e-05,
|
| 838 |
+
"loss": 0.1319,
|
| 839 |
+
"step": 10700
|
| 840 |
+
},
|
| 841 |
+
{
|
| 842 |
+
"epoch": 9.83,
|
| 843 |
+
"grad_norm": 0.8269553184509277,
|
| 844 |
+
"learning_rate": 2.1267146049923167e-05,
|
| 845 |
+
"loss": 0.1165,
|
| 846 |
+
"step": 10800
|
| 847 |
+
},
|
| 848 |
+
{
|
| 849 |
+
"epoch": 9.92,
|
| 850 |
+
"grad_norm": 0.5792891383171082,
|
| 851 |
+
"learning_rate": 2.059705975361802e-05,
|
| 852 |
+
"loss": 0.0998,
|
| 853 |
+
"step": 10900
|
| 854 |
+
},
|
| 855 |
+
{
|
| 856 |
+
"epoch": 10.0,
|
| 857 |
+
"eval_accuracy": 0.9347912524850894,
|
| 858 |
+
"eval_loss": 0.3257232904434204,
|
| 859 |
+
"eval_runtime": 107.8035,
|
| 860 |
+
"eval_samples_per_second": 23.329,
|
| 861 |
+
"eval_steps_per_second": 1.466,
|
| 862 |
+
"step": 10990
|
| 863 |
+
},
|
| 864 |
+
{
|
| 865 |
+
"epoch": 10.01,
|
| 866 |
+
"grad_norm": 0.3180704414844513,
|
| 867 |
+
"learning_rate": 1.9934020002555702e-05,
|
| 868 |
+
"loss": 0.1086,
|
| 869 |
+
"step": 11000
|
| 870 |
+
},
|
| 871 |
+
{
|
| 872 |
+
"epoch": 10.1,
|
| 873 |
+
"grad_norm": 7.30010461807251,
|
| 874 |
+
"learning_rate": 1.9278267592179803e-05,
|
| 875 |
+
"loss": 0.0895,
|
| 876 |
+
"step": 11100
|
| 877 |
+
},
|
| 878 |
+
{
|
| 879 |
+
"epoch": 10.19,
|
| 880 |
+
"grad_norm": 0.1635340303182602,
|
| 881 |
+
"learning_rate": 1.86300406713981e-05,
|
| 882 |
+
"loss": 0.0777,
|
| 883 |
+
"step": 11200
|
| 884 |
+
},
|
| 885 |
+
{
|
| 886 |
+
"epoch": 10.28,
|
| 887 |
+
"grad_norm": 2.3367292881011963,
|
| 888 |
+
"learning_rate": 1.7989574656094327e-05,
|
| 889 |
+
"loss": 0.0737,
|
| 890 |
+
"step": 11300
|
| 891 |
+
},
|
| 892 |
+
{
|
| 893 |
+
"epoch": 10.37,
|
| 894 |
+
"grad_norm": 0.8518896698951721,
|
| 895 |
+
"learning_rate": 1.7357102143632386e-05,
|
| 896 |
+
"loss": 0.1099,
|
| 897 |
+
"step": 11400
|
| 898 |
+
},
|
| 899 |
+
{
|
| 900 |
+
"epoch": 10.46,
|
| 901 |
+
"grad_norm": 0.14773418009281158,
|
| 902 |
+
"learning_rate": 1.6732852828384235e-05,
|
| 903 |
+
"loss": 0.1096,
|
| 904 |
+
"step": 11500
|
| 905 |
+
},
|
| 906 |
+
{
|
| 907 |
+
"epoch": 10.56,
|
| 908 |
+
"grad_norm": 0.056224796921014786,
|
| 909 |
+
"learning_rate": 1.6117053418311988e-05,
|
| 910 |
+
"loss": 0.0624,
|
| 911 |
+
"step": 11600
|
| 912 |
+
},
|
| 913 |
+
{
|
| 914 |
+
"epoch": 10.65,
|
| 915 |
+
"grad_norm": 14.274983406066895,
|
| 916 |
+
"learning_rate": 1.550992755263471e-05,
|
| 917 |
+
"loss": 0.0981,
|
| 918 |
+
"step": 11700
|
| 919 |
+
},
|
| 920 |
+
{
|
| 921 |
+
"epoch": 10.74,
|
| 922 |
+
"grad_norm": 15.517501831054688,
|
| 923 |
+
"learning_rate": 1.4911695720609486e-05,
|
| 924 |
+
"loss": 0.1016,
|
| 925 |
+
"step": 11800
|
| 926 |
+
},
|
| 927 |
+
{
|
| 928 |
+
"epoch": 10.83,
|
| 929 |
+
"grad_norm": 1.103292465209961,
|
| 930 |
+
"learning_rate": 1.4322575181456664e-05,
|
| 931 |
+
"loss": 0.1021,
|
| 932 |
+
"step": 11900
|
| 933 |
+
},
|
| 934 |
+
{
|
| 935 |
+
"epoch": 10.92,
|
| 936 |
+
"grad_norm": 0.8106482625007629,
|
| 937 |
+
"learning_rate": 1.3742779885457966e-05,
|
| 938 |
+
"loss": 0.0728,
|
| 939 |
+
"step": 12000
|
| 940 |
+
},
|
| 941 |
+
{
|
| 942 |
+
"epoch": 11.0,
|
| 943 |
+
"eval_accuracy": 0.936779324055666,
|
| 944 |
+
"eval_loss": 0.3289387822151184,
|
| 945 |
+
"eval_runtime": 108.2127,
|
| 946 |
+
"eval_samples_per_second": 23.241,
|
| 947 |
+
"eval_steps_per_second": 1.46,
|
| 948 |
+
"step": 12089
|
| 949 |
+
},
|
| 950 |
+
{
|
| 951 |
+
"epoch": 11.01,
|
| 952 |
+
"grad_norm": 0.03628486394882202,
|
| 953 |
+
"learning_rate": 1.3172520396256503e-05,
|
| 954 |
+
"loss": 0.0635,
|
| 955 |
+
"step": 12100
|
| 956 |
+
},
|
| 957 |
+
{
|
| 958 |
+
"epoch": 11.1,
|
| 959 |
+
"grad_norm": 0.15396057069301605,
|
| 960 |
+
"learning_rate": 1.2612003814386489e-05,
|
| 961 |
+
"loss": 0.0998,
|
| 962 |
+
"step": 12200
|
| 963 |
+
},
|
| 964 |
+
{
|
| 965 |
+
"epoch": 11.19,
|
| 966 |
+
"grad_norm": 0.37192150950431824,
|
| 967 |
+
"learning_rate": 1.206143370206086e-05,
|
| 968 |
+
"loss": 0.0794,
|
| 969 |
+
"step": 12300
|
| 970 |
+
},
|
| 971 |
+
{
|
| 972 |
+
"epoch": 11.28,
|
| 973 |
+
"grad_norm": 0.3847203254699707,
|
| 974 |
+
"learning_rate": 1.1521010009243714e-05,
|
| 975 |
+
"loss": 0.0638,
|
| 976 |
+
"step": 12400
|
| 977 |
+
},
|
| 978 |
+
{
|
| 979 |
+
"epoch": 11.37,
|
| 980 |
+
"grad_norm": 7.261880874633789,
|
| 981 |
+
"learning_rate": 1.0990929001034738e-05,
|
| 982 |
+
"loss": 0.0738,
|
| 983 |
+
"step": 12500
|
| 984 |
+
},
|
| 985 |
+
{
|
| 986 |
+
"epoch": 11.46,
|
| 987 |
+
"grad_norm": 0.17248640954494476,
|
| 988 |
+
"learning_rate": 1.0471383186391817e-05,
|
| 989 |
+
"loss": 0.0636,
|
| 990 |
+
"step": 12600
|
| 991 |
+
},
|
| 992 |
+
{
|
| 993 |
+
"epoch": 11.56,
|
| 994 |
+
"grad_norm": 0.031174590811133385,
|
| 995 |
+
"learning_rate": 9.962561248217764e-06,
|
| 996 |
+
"loss": 0.0914,
|
| 997 |
+
"step": 12700
|
| 998 |
+
},
|
| 999 |
+
{
|
| 1000 |
+
"epoch": 11.65,
|
| 1001 |
+
"grad_norm": 1.3612018823623657,
|
| 1002 |
+
"learning_rate": 9.464647974836496e-06,
|
| 1003 |
+
"loss": 0.0781,
|
| 1004 |
+
"step": 12800
|
| 1005 |
+
},
|
| 1006 |
+
{
|
| 1007 |
+
"epoch": 11.74,
|
| 1008 |
+
"grad_norm": 0.09444615244865417,
|
| 1009 |
+
"learning_rate": 8.977824192883772e-06,
|
| 1010 |
+
"loss": 0.067,
|
| 1011 |
+
"step": 12900
|
| 1012 |
+
},
|
| 1013 |
+
{
|
| 1014 |
+
"epoch": 11.83,
|
| 1015 |
+
"grad_norm": 7.895622253417969,
|
| 1016 |
+
"learning_rate": 8.502266701636457e-06,
|
| 1017 |
+
"loss": 0.0846,
|
| 1018 |
+
"step": 13000
|
| 1019 |
+
},
|
| 1020 |
+
{
|
| 1021 |
+
"epoch": 11.92,
|
| 1022 |
+
"grad_norm": 0.03469648212194443,
|
| 1023 |
+
"learning_rate": 8.038148208804567e-06,
|
| 1024 |
+
"loss": 0.0872,
|
| 1025 |
+
"step": 13100
|
| 1026 |
+
},
|
| 1027 |
+
{
|
| 1028 |
+
"epoch": 12.0,
|
| 1029 |
+
"eval_accuracy": 0.9407554671968191,
|
| 1030 |
+
"eval_loss": 0.32880690693855286,
|
| 1031 |
+
"eval_runtime": 107.2934,
|
| 1032 |
+
"eval_samples_per_second": 23.44,
|
| 1033 |
+
"eval_steps_per_second": 1.473,
|
| 1034 |
+
"step": 13188
|
| 1035 |
+
},
|
| 1036 |
+
{
|
| 1037 |
+
"epoch": 12.01,
|
| 1038 |
+
"grad_norm": 0.054643452167510986,
|
| 1039 |
+
"learning_rate": 7.5856372678091964e-06,
|
| 1040 |
+
"loss": 0.0724,
|
| 1041 |
+
"step": 13200
|
| 1042 |
+
},
|
| 1043 |
+
{
|
| 1044 |
+
"epoch": 12.1,
|
| 1045 |
+
"grad_norm": 14.980018615722656,
|
| 1046 |
+
"learning_rate": 7.14489821656914e-06,
|
| 1047 |
+
"loss": 0.0765,
|
| 1048 |
+
"step": 13300
|
| 1049 |
+
},
|
| 1050 |
+
{
|
| 1051 |
+
"epoch": 12.19,
|
| 1052 |
+
"grad_norm": 0.03025561198592186,
|
| 1053 |
+
"learning_rate": 6.716091117818484e-06,
|
| 1054 |
+
"loss": 0.0754,
|
| 1055 |
+
"step": 13400
|
| 1056 |
+
},
|
| 1057 |
+
{
|
| 1058 |
+
"epoch": 12.28,
|
| 1059 |
+
"grad_norm": 0.03179701790213585,
|
| 1060 |
+
"learning_rate": 6.29937170097672e-06,
|
| 1061 |
+
"loss": 0.0551,
|
| 1062 |
+
"step": 13500
|
| 1063 |
+
},
|
| 1064 |
+
{
|
| 1065 |
+
"epoch": 12.37,
|
| 1066 |
+
"grad_norm": 8.448119163513184,
|
| 1067 |
+
"learning_rate": 5.8948913055927894e-06,
|
| 1068 |
+
"loss": 0.0952,
|
| 1069 |
+
"step": 13600
|
| 1070 |
+
},
|
| 1071 |
+
{
|
| 1072 |
+
"epoch": 12.47,
|
| 1073 |
+
"grad_norm": 0.0018671215511858463,
|
| 1074 |
+
"learning_rate": 5.502796826383141e-06,
|
| 1075 |
+
"loss": 0.0713,
|
| 1076 |
+
"step": 13700
|
| 1077 |
+
},
|
| 1078 |
+
{
|
| 1079 |
+
"epoch": 12.56,
|
| 1080 |
+
"grad_norm": 0.37293198704719543,
|
| 1081 |
+
"learning_rate": 5.123230659884178e-06,
|
| 1082 |
+
"loss": 0.063,
|
| 1083 |
+
"step": 13800
|
| 1084 |
+
},
|
| 1085 |
+
{
|
| 1086 |
+
"epoch": 12.65,
|
| 1087 |
+
"grad_norm": 6.294044494628906,
|
| 1088 |
+
"learning_rate": 4.7563306527382615e-06,
|
| 1089 |
+
"loss": 0.0732,
|
| 1090 |
+
"step": 13900
|
| 1091 |
+
},
|
| 1092 |
+
{
|
| 1093 |
+
"epoch": 12.74,
|
| 1094 |
+
"grad_norm": 8.385093688964844,
|
| 1095 |
+
"learning_rate": 4.402230051632081e-06,
|
| 1096 |
+
"loss": 0.0579,
|
| 1097 |
+
"step": 14000
|
| 1098 |
+
},
|
| 1099 |
+
{
|
| 1100 |
+
"epoch": 12.83,
|
| 1101 |
+
"grad_norm": 0.035636261105537415,
|
| 1102 |
+
"learning_rate": 4.061057454905615e-06,
|
| 1103 |
+
"loss": 0.1073,
|
| 1104 |
+
"step": 14100
|
| 1105 |
+
},
|
| 1106 |
+
{
|
| 1107 |
+
"epoch": 12.92,
|
| 1108 |
+
"grad_norm": 9.956852912902832,
|
| 1109 |
+
"learning_rate": 3.7329367658491778e-06,
|
| 1110 |
+
"loss": 0.0731,
|
| 1111 |
+
"step": 14200
|
| 1112 |
+
},
|
| 1113 |
+
{
|
| 1114 |
+
"epoch": 13.0,
|
| 1115 |
+
"eval_accuracy": 0.9407554671968191,
|
| 1116 |
+
"eval_loss": 0.3320312201976776,
|
| 1117 |
+
"eval_runtime": 107.2304,
|
| 1118 |
+
"eval_samples_per_second": 23.454,
|
| 1119 |
+
"eval_steps_per_second": 1.473,
|
| 1120 |
+
"step": 14287
|
| 1121 |
+
},
|
| 1122 |
+
{
|
| 1123 |
+
"epoch": 13.01,
|
| 1124 |
+
"grad_norm": 0.09960483759641647,
|
| 1125 |
+
"learning_rate": 3.417987147705617e-06,
|
| 1126 |
+
"loss": 0.0629,
|
| 1127 |
+
"step": 14300
|
| 1128 |
+
},
|
| 1129 |
+
{
|
| 1130 |
+
"epoch": 13.1,
|
| 1131 |
+
"grad_norm": 0.04828275740146637,
|
| 1132 |
+
"learning_rate": 3.116322980393922e-06,
|
| 1133 |
+
"loss": 0.0595,
|
| 1134 |
+
"step": 14400
|
| 1135 |
+
},
|
| 1136 |
+
{
|
| 1137 |
+
"epoch": 13.19,
|
| 1138 |
+
"grad_norm": 7.161159515380859,
|
| 1139 |
+
"learning_rate": 2.828053818969978e-06,
|
| 1140 |
+
"loss": 0.092,
|
| 1141 |
+
"step": 14500
|
| 1142 |
+
},
|
| 1143 |
+
{
|
| 1144 |
+
"epoch": 13.28,
|
| 1145 |
+
"grad_norm": 3.226339340209961,
|
| 1146 |
+
"learning_rate": 2.5532843538395868e-06,
|
| 1147 |
+
"loss": 0.074,
|
| 1148 |
+
"step": 14600
|
| 1149 |
+
},
|
| 1150 |
+
{
|
| 1151 |
+
"epoch": 13.38,
|
| 1152 |
+
"grad_norm": 0.04475373029708862,
|
| 1153 |
+
"learning_rate": 2.2921143727381525e-06,
|
| 1154 |
+
"loss": 0.0591,
|
| 1155 |
+
"step": 14700
|
| 1156 |
+
},
|
| 1157 |
+
{
|
| 1158 |
+
"epoch": 13.47,
|
| 1159 |
+
"grad_norm": 7.270404815673828,
|
| 1160 |
+
"learning_rate": 2.0446387244908774e-06,
|
| 1161 |
+
"loss": 0.0666,
|
| 1162 |
+
"step": 14800
|
| 1163 |
+
},
|
| 1164 |
+
{
|
| 1165 |
+
"epoch": 13.56,
|
| 1166 |
+
"grad_norm": 0.04449067637324333,
|
| 1167 |
+
"learning_rate": 1.8109472845666198e-06,
|
| 1168 |
+
"loss": 0.0834,
|
| 1169 |
+
"step": 14900
|
| 1170 |
+
},
|
| 1171 |
+
{
|
| 1172 |
+
"epoch": 13.65,
|
| 1173 |
+
"grad_norm": 20.532730102539062,
|
| 1174 |
+
"learning_rate": 1.5911249224379189e-06,
|
| 1175 |
+
"loss": 0.0676,
|
| 1176 |
+
"step": 15000
|
| 1177 |
+
},
|
| 1178 |
+
{
|
| 1179 |
+
"epoch": 13.74,
|
| 1180 |
+
"grad_norm": 6.280622959136963,
|
| 1181 |
+
"learning_rate": 1.385251470759017e-06,
|
| 1182 |
+
"loss": 0.076,
|
| 1183 |
+
"step": 15100
|
| 1184 |
+
},
|
| 1185 |
+
{
|
| 1186 |
+
"epoch": 13.83,
|
| 1187 |
+
"grad_norm": 0.3242604732513428,
|
| 1188 |
+
"learning_rate": 1.1934016963731465e-06,
|
| 1189 |
+
"loss": 0.0624,
|
| 1190 |
+
"step": 15200
|
| 1191 |
+
},
|
| 1192 |
+
{
|
| 1193 |
+
"epoch": 13.92,
|
| 1194 |
+
"grad_norm": 5.6159210205078125,
|
| 1195 |
+
"learning_rate": 1.0156452731595112e-06,
|
| 1196 |
+
"loss": 0.0693,
|
| 1197 |
+
"step": 15300
|
| 1198 |
+
},
|
| 1199 |
+
{
|
| 1200 |
+
"epoch": 14.0,
|
| 1201 |
+
"eval_accuracy": 0.9423459244532804,
|
| 1202 |
+
"eval_loss": 0.32697632908821106,
|
| 1203 |
+
"eval_runtime": 107.0584,
|
| 1204 |
+
"eval_samples_per_second": 23.492,
|
| 1205 |
+
"eval_steps_per_second": 1.476,
|
| 1206 |
+
"step": 15386
|
| 1207 |
+
},
|
| 1208 |
+
{
|
| 1209 |
+
"epoch": 14.01,
|
| 1210 |
+
"grad_norm": 3.9605867862701416,
|
| 1211 |
+
"learning_rate": 8.520467567299184e-07,
|
| 1212 |
+
"loss": 0.0651,
|
| 1213 |
+
"step": 15400
|
| 1214 |
+
},
|
| 1215 |
+
{
|
| 1216 |
+
"epoch": 14.1,
|
| 1217 |
+
"grad_norm": 0.07699358463287354,
|
| 1218 |
+
"learning_rate": 7.026655609841682e-07,
|
| 1219 |
+
"loss": 0.0655,
|
| 1220 |
+
"step": 15500
|
| 1221 |
+
},
|
| 1222 |
+
{
|
| 1223 |
+
"epoch": 14.19,
|
| 1224 |
+
"grad_norm": 12.785538673400879,
|
| 1225 |
+
"learning_rate": 5.675559365327798e-07,
|
| 1226 |
+
"loss": 0.0736,
|
| 1227 |
+
"step": 15600
|
| 1228 |
+
},
|
| 1229 |
+
{
|
| 1230 |
+
"epoch": 14.29,
|
| 1231 |
+
"grad_norm": 0.0682230219244957,
|
| 1232 |
+
"learning_rate": 4.467669509948591e-07,
|
| 1233 |
+
"loss": 0.0712,
|
| 1234 |
+
"step": 15700
|
| 1235 |
+
},
|
| 1236 |
+
{
|
| 1237 |
+
"epoch": 14.38,
|
| 1238 |
+
"grad_norm": 5.338863849639893,
|
| 1239 |
+
"learning_rate": 3.403424711782455e-07,
|
| 1240 |
+
"loss": 0.076,
|
| 1241 |
+
"step": 15800
|
| 1242 |
+
},
|
| 1243 |
+
{
|
| 1244 |
+
"epoch": 14.47,
|
| 1245 |
+
"grad_norm": 0.04831124097108841,
|
| 1246 |
+
"learning_rate": 2.4832114714847367e-07,
|
| 1247 |
+
"loss": 0.0593,
|
| 1248 |
+
"step": 15900
|
| 1249 |
+
},
|
| 1250 |
+
{
|
| 1251 |
+
"epoch": 14.56,
|
| 1252 |
+
"grad_norm": 19.2628231048584,
|
| 1253 |
+
"learning_rate": 1.7073639819224608e-07,
|
| 1254 |
+
"loss": 0.0646,
|
| 1255 |
+
"step": 16000
|
| 1256 |
+
},
|
| 1257 |
+
{
|
| 1258 |
+
"epoch": 14.65,
|
| 1259 |
+
"grad_norm": 0.4399223327636719,
|
| 1260 |
+
"learning_rate": 1.0761640068060353e-07,
|
| 1261 |
+
"loss": 0.0554,
|
| 1262 |
+
"step": 16100
|
| 1263 |
+
},
|
| 1264 |
+
{
|
| 1265 |
+
"epoch": 14.74,
|
| 1266 |
+
"grad_norm": 15.196357727050781,
|
| 1267 |
+
"learning_rate": 5.898407783614169e-08,
|
| 1268 |
+
"loss": 0.0849,
|
| 1269 |
+
"step": 16200
|
| 1270 |
+
},
|
| 1271 |
+
{
|
| 1272 |
+
"epoch": 14.83,
|
| 1273 |
+
"grad_norm": 0.01677566207945347,
|
| 1274 |
+
"learning_rate": 2.48570914079993e-08,
|
| 1275 |
+
"loss": 0.0743,
|
| 1276 |
+
"step": 16300
|
| 1277 |
+
},
|
| 1278 |
+
{
|
| 1279 |
+
"epoch": 14.92,
|
| 1280 |
+
"grad_norm": 3.5998127460479736,
|
| 1281 |
+
"learning_rate": 5.247835257664591e-09,
|
| 1282 |
+
"loss": 0.0586,
|
| 1283 |
+
"step": 16400
|
| 1284 |
+
},
|
| 1285 |
+
{
|
| 1286 |
+
"epoch": 15.0,
|
| 1287 |
+
"eval_accuracy": 0.9427435387673956,
|
| 1288 |
+
"eval_loss": 0.3250676989555359,
|
| 1289 |
+
"eval_runtime": 107.5456,
|
| 1290 |
+
"eval_samples_per_second": 23.385,
|
| 1291 |
+
"eval_steps_per_second": 1.469,
|
| 1292 |
+
"step": 16485
|
| 1293 |
+
},
|
| 1294 |
+
{
|
| 1295 |
+
"epoch": 15.0,
|
| 1296 |
+
"step": 16485,
|
| 1297 |
+
"total_flos": 6.140249030814106e+19,
|
| 1298 |
+
"train_loss": 0.21494813935844184,
|
| 1299 |
+
"train_runtime": 26072.0492,
|
| 1300 |
+
"train_samples_per_second": 10.115,
|
| 1301 |
+
"train_steps_per_second": 0.632
|
| 1302 |
+
}
|
| 1303 |
+
],
|
| 1304 |
+
"logging_steps": 100,
|
| 1305 |
+
"max_steps": 16485,
|
| 1306 |
+
"num_input_tokens_seen": 0,
|
| 1307 |
+
"num_train_epochs": 15,
|
| 1308 |
+
"save_steps": 500,
|
| 1309 |
+
"total_flos": 6.140249030814106e+19,
|
| 1310 |
+
"train_batch_size": 16,
|
| 1311 |
+
"trial_name": null,
|
| 1312 |
+
"trial_params": null
|
| 1313 |
+
}
|