updates
Browse files- model.safetensors +1 -1
- trainer_state.json +1626 -0
- training_args.bin +3 -0
model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 988097824
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5982cd34bff6f79876cb13b206e07c16403b3104da98ac698c8c7ecb34723582
|
| 3 |
size 988097824
|
trainer_state.json
ADDED
|
@@ -0,0 +1,1626 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": null,
|
| 3 |
+
"best_metric": null,
|
| 4 |
+
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 1.6005378409527469,
|
| 6 |
+
"eval_steps": 600,
|
| 7 |
+
"global_step": 10416,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.00768344218209758,
|
| 14 |
+
"grad_norm": 24.238063812163187,
|
| 15 |
+
"learning_rate": 1.881720430107527e-07,
|
| 16 |
+
"loss": 0.3364,
|
| 17 |
+
"step": 50
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 0.01536688436419516,
|
| 21 |
+
"grad_norm": 6.319806837540333,
|
| 22 |
+
"learning_rate": 3.801843317972351e-07,
|
| 23 |
+
"loss": 0.2362,
|
| 24 |
+
"step": 100
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.02305032654629274,
|
| 28 |
+
"grad_norm": 5.317146309656271,
|
| 29 |
+
"learning_rate": 5.721966205837174e-07,
|
| 30 |
+
"loss": 0.1782,
|
| 31 |
+
"step": 150
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 0.03073376872839032,
|
| 35 |
+
"grad_norm": 6.141914479493457,
|
| 36 |
+
"learning_rate": 7.642089093701997e-07,
|
| 37 |
+
"loss": 0.1538,
|
| 38 |
+
"step": 200
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.0384172109104879,
|
| 42 |
+
"grad_norm": 6.3393321544201955,
|
| 43 |
+
"learning_rate": 9.562211981566821e-07,
|
| 44 |
+
"loss": 0.1399,
|
| 45 |
+
"step": 250
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.04610065309258548,
|
| 49 |
+
"grad_norm": 7.1957549897032775,
|
| 50 |
+
"learning_rate": 1.1482334869431644e-06,
|
| 51 |
+
"loss": 0.1279,
|
| 52 |
+
"step": 300
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 0.05378409527468306,
|
| 56 |
+
"grad_norm": 4.981889336531056,
|
| 57 |
+
"learning_rate": 1.340245775729647e-06,
|
| 58 |
+
"loss": 0.1238,
|
| 59 |
+
"step": 350
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 0.06146753745678064,
|
| 63 |
+
"grad_norm": 5.469128876608933,
|
| 64 |
+
"learning_rate": 1.5322580645161292e-06,
|
| 65 |
+
"loss": 0.1181,
|
| 66 |
+
"step": 400
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 0.06915097963887822,
|
| 70 |
+
"grad_norm": 4.228572813571115,
|
| 71 |
+
"learning_rate": 1.7242703533026115e-06,
|
| 72 |
+
"loss": 0.1129,
|
| 73 |
+
"step": 450
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 0.0768344218209758,
|
| 77 |
+
"grad_norm": 4.635063301103817,
|
| 78 |
+
"learning_rate": 1.916282642089094e-06,
|
| 79 |
+
"loss": 0.1085,
|
| 80 |
+
"step": 500
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.08451786400307337,
|
| 84 |
+
"grad_norm": 4.57628839065234,
|
| 85 |
+
"learning_rate": 2.108294930875576e-06,
|
| 86 |
+
"loss": 0.1012,
|
| 87 |
+
"step": 550
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.09220130618517096,
|
| 91 |
+
"grad_norm": 4.631658068697841,
|
| 92 |
+
"learning_rate": 2.3003072196620586e-06,
|
| 93 |
+
"loss": 0.1016,
|
| 94 |
+
"step": 600
|
| 95 |
+
},
|
| 96 |
+
{
|
| 97 |
+
"epoch": 0.09220130618517096,
|
| 98 |
+
"eval_loss": 0.10174024850130081,
|
| 99 |
+
"eval_runtime": 18.0705,
|
| 100 |
+
"eval_samples_per_second": 203.702,
|
| 101 |
+
"eval_steps_per_second": 6.419,
|
| 102 |
+
"step": 600
|
| 103 |
+
},
|
| 104 |
+
{
|
| 105 |
+
"epoch": 0.09988474836726853,
|
| 106 |
+
"grad_norm": 4.666177854862017,
|
| 107 |
+
"learning_rate": 2.492319508448541e-06,
|
| 108 |
+
"loss": 0.0966,
|
| 109 |
+
"step": 650
|
| 110 |
+
},
|
| 111 |
+
{
|
| 112 |
+
"epoch": 0.10756819054936612,
|
| 113 |
+
"grad_norm": 3.667615984584937,
|
| 114 |
+
"learning_rate": 2.684331797235023e-06,
|
| 115 |
+
"loss": 0.0999,
|
| 116 |
+
"step": 700
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"epoch": 0.1152516327314637,
|
| 120 |
+
"grad_norm": 3.2135487366487427,
|
| 121 |
+
"learning_rate": 2.8763440860215057e-06,
|
| 122 |
+
"loss": 0.0969,
|
| 123 |
+
"step": 750
|
| 124 |
+
},
|
| 125 |
+
{
|
| 126 |
+
"epoch": 0.12293507491356127,
|
| 127 |
+
"grad_norm": 3.5733005027516476,
|
| 128 |
+
"learning_rate": 3.068356374807988e-06,
|
| 129 |
+
"loss": 0.0934,
|
| 130 |
+
"step": 800
|
| 131 |
+
},
|
| 132 |
+
{
|
| 133 |
+
"epoch": 0.13061851709565886,
|
| 134 |
+
"grad_norm": 4.3597956101093605,
|
| 135 |
+
"learning_rate": 3.2603686635944703e-06,
|
| 136 |
+
"loss": 0.0931,
|
| 137 |
+
"step": 850
|
| 138 |
+
},
|
| 139 |
+
{
|
| 140 |
+
"epoch": 0.13830195927775643,
|
| 141 |
+
"grad_norm": 3.2540960430191364,
|
| 142 |
+
"learning_rate": 3.4523809523809528e-06,
|
| 143 |
+
"loss": 0.0935,
|
| 144 |
+
"step": 900
|
| 145 |
+
},
|
| 146 |
+
{
|
| 147 |
+
"epoch": 0.145985401459854,
|
| 148 |
+
"grad_norm": 4.391490641674597,
|
| 149 |
+
"learning_rate": 3.644393241167435e-06,
|
| 150 |
+
"loss": 0.1001,
|
| 151 |
+
"step": 950
|
| 152 |
+
},
|
| 153 |
+
{
|
| 154 |
+
"epoch": 0.1536688436419516,
|
| 155 |
+
"grad_norm": 4.80552168899774,
|
| 156 |
+
"learning_rate": 3.836405529953917e-06,
|
| 157 |
+
"loss": 0.0942,
|
| 158 |
+
"step": 1000
|
| 159 |
+
},
|
| 160 |
+
{
|
| 161 |
+
"epoch": 0.16135228582404917,
|
| 162 |
+
"grad_norm": 2.7917815686351064,
|
| 163 |
+
"learning_rate": 4.0284178187404e-06,
|
| 164 |
+
"loss": 0.0932,
|
| 165 |
+
"step": 1050
|
| 166 |
+
},
|
| 167 |
+
{
|
| 168 |
+
"epoch": 0.16903572800614675,
|
| 169 |
+
"grad_norm": 3.8315415753727153,
|
| 170 |
+
"learning_rate": 4.220430107526882e-06,
|
| 171 |
+
"loss": 0.0866,
|
| 172 |
+
"step": 1100
|
| 173 |
+
},
|
| 174 |
+
{
|
| 175 |
+
"epoch": 0.17671917018824435,
|
| 176 |
+
"grad_norm": 3.0820620211058003,
|
| 177 |
+
"learning_rate": 4.4124423963133644e-06,
|
| 178 |
+
"loss": 0.0899,
|
| 179 |
+
"step": 1150
|
| 180 |
+
},
|
| 181 |
+
{
|
| 182 |
+
"epoch": 0.18440261237034192,
|
| 183 |
+
"grad_norm": 3.4482968111997243,
|
| 184 |
+
"learning_rate": 4.604454685099847e-06,
|
| 185 |
+
"loss": 0.0885,
|
| 186 |
+
"step": 1200
|
| 187 |
+
},
|
| 188 |
+
{
|
| 189 |
+
"epoch": 0.18440261237034192,
|
| 190 |
+
"eval_loss": 0.09638471901416779,
|
| 191 |
+
"eval_runtime": 17.8744,
|
| 192 |
+
"eval_samples_per_second": 205.938,
|
| 193 |
+
"eval_steps_per_second": 6.49,
|
| 194 |
+
"step": 1200
|
| 195 |
+
},
|
| 196 |
+
{
|
| 197 |
+
"epoch": 0.1920860545524395,
|
| 198 |
+
"grad_norm": 4.096325077313065,
|
| 199 |
+
"learning_rate": 4.796466973886329e-06,
|
| 200 |
+
"loss": 0.0907,
|
| 201 |
+
"step": 1250
|
| 202 |
+
},
|
| 203 |
+
{
|
| 204 |
+
"epoch": 0.19976949673453706,
|
| 205 |
+
"grad_norm": 5.171403712016945,
|
| 206 |
+
"learning_rate": 4.988479262672811e-06,
|
| 207 |
+
"loss": 0.0891,
|
| 208 |
+
"step": 1300
|
| 209 |
+
},
|
| 210 |
+
{
|
| 211 |
+
"epoch": 0.20745293891663466,
|
| 212 |
+
"grad_norm": 2.599652616837112,
|
| 213 |
+
"learning_rate": 4.999801395408516e-06,
|
| 214 |
+
"loss": 0.0885,
|
| 215 |
+
"step": 1350
|
| 216 |
+
},
|
| 217 |
+
{
|
| 218 |
+
"epoch": 0.21513638109873223,
|
| 219 |
+
"grad_norm": 2.593935050173008,
|
| 220 |
+
"learning_rate": 4.9991541014222635e-06,
|
| 221 |
+
"loss": 0.0846,
|
| 222 |
+
"step": 1400
|
| 223 |
+
},
|
| 224 |
+
{
|
| 225 |
+
"epoch": 0.2228198232808298,
|
| 226 |
+
"grad_norm": 2.4852578892924675,
|
| 227 |
+
"learning_rate": 4.998057425259791e-06,
|
| 228 |
+
"loss": 0.0857,
|
| 229 |
+
"step": 1450
|
| 230 |
+
},
|
| 231 |
+
{
|
| 232 |
+
"epoch": 0.2305032654629274,
|
| 233 |
+
"grad_norm": 3.1893069499093554,
|
| 234 |
+
"learning_rate": 4.99651156411851e-06,
|
| 235 |
+
"loss": 0.0852,
|
| 236 |
+
"step": 1500
|
| 237 |
+
},
|
| 238 |
+
{
|
| 239 |
+
"epoch": 0.23818670764502498,
|
| 240 |
+
"grad_norm": 2.3528305412915476,
|
| 241 |
+
"learning_rate": 4.99451679596545e-06,
|
| 242 |
+
"loss": 0.0866,
|
| 243 |
+
"step": 1550
|
| 244 |
+
},
|
| 245 |
+
{
|
| 246 |
+
"epoch": 0.24587014982712255,
|
| 247 |
+
"grad_norm": 2.6041772725181214,
|
| 248 |
+
"learning_rate": 4.9920734794872795e-06,
|
| 249 |
+
"loss": 0.0885,
|
| 250 |
+
"step": 1600
|
| 251 |
+
},
|
| 252 |
+
{
|
| 253 |
+
"epoch": 0.2535535920092201,
|
| 254 |
+
"grad_norm": 2.890143221665928,
|
| 255 |
+
"learning_rate": 4.989182054025802e-06,
|
| 256 |
+
"loss": 0.0856,
|
| 257 |
+
"step": 1650
|
| 258 |
+
},
|
| 259 |
+
{
|
| 260 |
+
"epoch": 0.2612370341913177,
|
| 261 |
+
"grad_norm": 3.0480203743032686,
|
| 262 |
+
"learning_rate": 4.985843039498966e-06,
|
| 263 |
+
"loss": 0.0873,
|
| 264 |
+
"step": 1700
|
| 265 |
+
},
|
| 266 |
+
{
|
| 267 |
+
"epoch": 0.26892047637341526,
|
| 268 |
+
"grad_norm": 2.94553715320027,
|
| 269 |
+
"learning_rate": 4.982057036307365e-06,
|
| 270 |
+
"loss": 0.083,
|
| 271 |
+
"step": 1750
|
| 272 |
+
},
|
| 273 |
+
{
|
| 274 |
+
"epoch": 0.27660391855551286,
|
| 275 |
+
"grad_norm": 2.8391900367379077,
|
| 276 |
+
"learning_rate": 4.97782472522629e-06,
|
| 277 |
+
"loss": 0.0851,
|
| 278 |
+
"step": 1800
|
| 279 |
+
},
|
| 280 |
+
{
|
| 281 |
+
"epoch": 0.27660391855551286,
|
| 282 |
+
"eval_loss": 0.08491890132427216,
|
| 283 |
+
"eval_runtime": 17.8473,
|
| 284 |
+
"eval_samples_per_second": 206.249,
|
| 285 |
+
"eval_steps_per_second": 6.5,
|
| 286 |
+
"step": 1800
|
| 287 |
+
},
|
| 288 |
+
{
|
| 289 |
+
"epoch": 0.28428736073761046,
|
| 290 |
+
"grad_norm": 3.4124198348599273,
|
| 291 |
+
"learning_rate": 4.973146867283307e-06,
|
| 292 |
+
"loss": 0.0795,
|
| 293 |
+
"step": 1850
|
| 294 |
+
},
|
| 295 |
+
{
|
| 296 |
+
"epoch": 0.291970802919708,
|
| 297 |
+
"grad_norm": 2.556801090484712,
|
| 298 |
+
"learning_rate": 4.968024303621417e-06,
|
| 299 |
+
"loss": 0.0821,
|
| 300 |
+
"step": 1900
|
| 301 |
+
},
|
| 302 |
+
{
|
| 303 |
+
"epoch": 0.2996542451018056,
|
| 304 |
+
"grad_norm": 2.5418464816752753,
|
| 305 |
+
"learning_rate": 4.9624579553478065e-06,
|
| 306 |
+
"loss": 0.0842,
|
| 307 |
+
"step": 1950
|
| 308 |
+
},
|
| 309 |
+
{
|
| 310 |
+
"epoch": 0.3073376872839032,
|
| 311 |
+
"grad_norm": 2.8344117271063496,
|
| 312 |
+
"learning_rate": 4.956448823368225e-06,
|
| 313 |
+
"loss": 0.0866,
|
| 314 |
+
"step": 2000
|
| 315 |
+
},
|
| 316 |
+
{
|
| 317 |
+
"epoch": 0.31502112946600075,
|
| 318 |
+
"grad_norm": 2.5199127327344018,
|
| 319 |
+
"learning_rate": 4.949997988206998e-06,
|
| 320 |
+
"loss": 0.0838,
|
| 321 |
+
"step": 2050
|
| 322 |
+
},
|
| 323 |
+
{
|
| 324 |
+
"epoch": 0.32270457164809835,
|
| 325 |
+
"grad_norm": 2.622495155727973,
|
| 326 |
+
"learning_rate": 4.943106609812742e-06,
|
| 327 |
+
"loss": 0.0813,
|
| 328 |
+
"step": 2100
|
| 329 |
+
},
|
| 330 |
+
{
|
| 331 |
+
"epoch": 0.33038801383019595,
|
| 332 |
+
"grad_norm": 2.9840472337428823,
|
| 333 |
+
"learning_rate": 4.9357759273497906e-06,
|
| 334 |
+
"loss": 0.0815,
|
| 335 |
+
"step": 2150
|
| 336 |
+
},
|
| 337 |
+
{
|
| 338 |
+
"epoch": 0.3380714560122935,
|
| 339 |
+
"grad_norm": 2.886419271879702,
|
| 340 |
+
"learning_rate": 4.928007258975368e-06,
|
| 341 |
+
"loss": 0.0833,
|
| 342 |
+
"step": 2200
|
| 343 |
+
},
|
| 344 |
+
{
|
| 345 |
+
"epoch": 0.3457548981943911,
|
| 346 |
+
"grad_norm": 2.083232239480286,
|
| 347 |
+
"learning_rate": 4.919802001602572e-06,
|
| 348 |
+
"loss": 0.0794,
|
| 349 |
+
"step": 2250
|
| 350 |
+
},
|
| 351 |
+
{
|
| 352 |
+
"epoch": 0.3534383403764887,
|
| 353 |
+
"grad_norm": 2.300324464493836,
|
| 354 |
+
"learning_rate": 4.911161630649194e-06,
|
| 355 |
+
"loss": 0.0779,
|
| 356 |
+
"step": 2300
|
| 357 |
+
},
|
| 358 |
+
{
|
| 359 |
+
"epoch": 0.36112178255858624,
|
| 360 |
+
"grad_norm": 2.642556591382307,
|
| 361 |
+
"learning_rate": 4.9020876997724055e-06,
|
| 362 |
+
"loss": 0.0845,
|
| 363 |
+
"step": 2350
|
| 364 |
+
},
|
| 365 |
+
{
|
| 366 |
+
"epoch": 0.36880522474068383,
|
| 367 |
+
"grad_norm": 2.8343151813972813,
|
| 368 |
+
"learning_rate": 4.892581840589403e-06,
|
| 369 |
+
"loss": 0.0755,
|
| 370 |
+
"step": 2400
|
| 371 |
+
},
|
| 372 |
+
{
|
| 373 |
+
"epoch": 0.36880522474068383,
|
| 374 |
+
"eval_loss": 0.08218714594841003,
|
| 375 |
+
"eval_runtime": 19.8012,
|
| 376 |
+
"eval_samples_per_second": 185.898,
|
| 377 |
+
"eval_steps_per_second": 5.858,
|
| 378 |
+
"step": 2400
|
| 379 |
+
},
|
| 380 |
+
{
|
| 381 |
+
"epoch": 0.3764886669227814,
|
| 382 |
+
"grad_norm": 2.3530318777857326,
|
| 383 |
+
"learning_rate": 4.882645762384014e-06,
|
| 384 |
+
"loss": 0.078,
|
| 385 |
+
"step": 2450
|
| 386 |
+
},
|
| 387 |
+
{
|
| 388 |
+
"epoch": 0.384172109104879,
|
| 389 |
+
"grad_norm": 2.896149397695564,
|
| 390 |
+
"learning_rate": 4.872281251799343e-06,
|
| 391 |
+
"loss": 0.077,
|
| 392 |
+
"step": 2500
|
| 393 |
+
},
|
| 394 |
+
{
|
| 395 |
+
"epoch": 0.3918555512869766,
|
| 396 |
+
"grad_norm": 2.769499482502948,
|
| 397 |
+
"learning_rate": 4.861490172516515e-06,
|
| 398 |
+
"loss": 0.0822,
|
| 399 |
+
"step": 2550
|
| 400 |
+
},
|
| 401 |
+
{
|
| 402 |
+
"epoch": 0.3995389934690741,
|
| 403 |
+
"grad_norm": 2.6614111820201334,
|
| 404 |
+
"learning_rate": 4.850274464919552e-06,
|
| 405 |
+
"loss": 0.0845,
|
| 406 |
+
"step": 2600
|
| 407 |
+
},
|
| 408 |
+
{
|
| 409 |
+
"epoch": 0.4072224356511717,
|
| 410 |
+
"grad_norm": 2.6687830377318775,
|
| 411 |
+
"learning_rate": 4.838636145746472e-06,
|
| 412 |
+
"loss": 0.0828,
|
| 413 |
+
"step": 2650
|
| 414 |
+
},
|
| 415 |
+
{
|
| 416 |
+
"epoch": 0.4149058778332693,
|
| 417 |
+
"grad_norm": 2.6222942749225124,
|
| 418 |
+
"learning_rate": 4.8265773077266505e-06,
|
| 419 |
+
"loss": 0.082,
|
| 420 |
+
"step": 2700
|
| 421 |
+
},
|
| 422 |
+
{
|
| 423 |
+
"epoch": 0.42258932001536686,
|
| 424 |
+
"grad_norm": 2.857585092349033,
|
| 425 |
+
"learning_rate": 4.814100119204515e-06,
|
| 426 |
+
"loss": 0.0827,
|
| 427 |
+
"step": 2750
|
| 428 |
+
},
|
| 429 |
+
{
|
| 430 |
+
"epoch": 0.43027276219746446,
|
| 431 |
+
"grad_norm": 3.0718710372112112,
|
| 432 |
+
"learning_rate": 4.801206823749649e-06,
|
| 433 |
+
"loss": 0.0764,
|
| 434 |
+
"step": 2800
|
| 435 |
+
},
|
| 436 |
+
{
|
| 437 |
+
"epoch": 0.43795620437956206,
|
| 438 |
+
"grad_norm": 2.3991559160863427,
|
| 439 |
+
"learning_rate": 4.787899739753372e-06,
|
| 440 |
+
"loss": 0.0818,
|
| 441 |
+
"step": 2850
|
| 442 |
+
},
|
| 443 |
+
{
|
| 444 |
+
"epoch": 0.4456396465616596,
|
| 445 |
+
"grad_norm": 2.0645648250964044,
|
| 446 |
+
"learning_rate": 4.774181260011856e-06,
|
| 447 |
+
"loss": 0.0725,
|
| 448 |
+
"step": 2900
|
| 449 |
+
},
|
| 450 |
+
{
|
| 451 |
+
"epoch": 0.4533230887437572,
|
| 452 |
+
"grad_norm": 2.030851345419917,
|
| 453 |
+
"learning_rate": 4.760053851295867e-06,
|
| 454 |
+
"loss": 0.081,
|
| 455 |
+
"step": 2950
|
| 456 |
+
},
|
| 457 |
+
{
|
| 458 |
+
"epoch": 0.4610065309258548,
|
| 459 |
+
"grad_norm": 2.8074770711893953,
|
| 460 |
+
"learning_rate": 4.74552005390721e-06,
|
| 461 |
+
"loss": 0.0726,
|
| 462 |
+
"step": 3000
|
| 463 |
+
},
|
| 464 |
+
{
|
| 465 |
+
"epoch": 0.4610065309258548,
|
| 466 |
+
"eval_loss": 0.08013278245925903,
|
| 467 |
+
"eval_runtime": 17.8924,
|
| 468 |
+
"eval_samples_per_second": 205.729,
|
| 469 |
+
"eval_steps_per_second": 6.483,
|
| 470 |
+
"step": 3000
|
| 471 |
+
},
|
| 472 |
+
{
|
| 473 |
+
"epoch": 0.46868997310795235,
|
| 474 |
+
"grad_norm": 2.359703128276483,
|
| 475 |
+
"learning_rate": 4.730582481221945e-06,
|
| 476 |
+
"loss": 0.0812,
|
| 477 |
+
"step": 3050
|
| 478 |
+
},
|
| 479 |
+
{
|
| 480 |
+
"epoch": 0.47637341529004995,
|
| 481 |
+
"grad_norm": 1.8778064498183962,
|
| 482 |
+
"learning_rate": 4.715243819220467e-06,
|
| 483 |
+
"loss": 0.0826,
|
| 484 |
+
"step": 3100
|
| 485 |
+
},
|
| 486 |
+
{
|
| 487 |
+
"epoch": 0.4840568574721475,
|
| 488 |
+
"grad_norm": 1.9963395486102375,
|
| 489 |
+
"learning_rate": 4.6995068260045296e-06,
|
| 490 |
+
"loss": 0.0769,
|
| 491 |
+
"step": 3150
|
| 492 |
+
},
|
| 493 |
+
{
|
| 494 |
+
"epoch": 0.4917402996542451,
|
| 495 |
+
"grad_norm": 2.5211485683446644,
|
| 496 |
+
"learning_rate": 4.6833743313013016e-06,
|
| 497 |
+
"loss": 0.0783,
|
| 498 |
+
"step": 3200
|
| 499 |
+
},
|
| 500 |
+
{
|
| 501 |
+
"epoch": 0.4994237418363427,
|
| 502 |
+
"grad_norm": 1.742500631708806,
|
| 503 |
+
"learning_rate": 4.666849235954542e-06,
|
| 504 |
+
"loss": 0.0746,
|
| 505 |
+
"step": 3250
|
| 506 |
+
},
|
| 507 |
+
{
|
| 508 |
+
"epoch": 0.5071071840184402,
|
| 509 |
+
"grad_norm": 2.349151557568936,
|
| 510 |
+
"learning_rate": 4.649934511402988e-06,
|
| 511 |
+
"loss": 0.0762,
|
| 512 |
+
"step": 3300
|
| 513 |
+
},
|
| 514 |
+
{
|
| 515 |
+
"epoch": 0.5147906262005378,
|
| 516 |
+
"grad_norm": 2.6526774252985335,
|
| 517 |
+
"learning_rate": 4.632633199146052e-06,
|
| 518 |
+
"loss": 0.0803,
|
| 519 |
+
"step": 3350
|
| 520 |
+
},
|
| 521 |
+
{
|
| 522 |
+
"epoch": 0.5224740683826354,
|
| 523 |
+
"grad_norm": 2.21236960042971,
|
| 524 |
+
"learning_rate": 4.614948410196916e-06,
|
| 525 |
+
"loss": 0.081,
|
| 526 |
+
"step": 3400
|
| 527 |
+
},
|
| 528 |
+
{
|
| 529 |
+
"epoch": 0.530157510564733,
|
| 530 |
+
"grad_norm": 2.5197036225433234,
|
| 531 |
+
"learning_rate": 4.59688332452313e-06,
|
| 532 |
+
"loss": 0.078,
|
| 533 |
+
"step": 3450
|
| 534 |
+
},
|
| 535 |
+
{
|
| 536 |
+
"epoch": 0.5378409527468305,
|
| 537 |
+
"grad_norm": 2.702928580540892,
|
| 538 |
+
"learning_rate": 4.578441190474809e-06,
|
| 539 |
+
"loss": 0.0775,
|
| 540 |
+
"step": 3500
|
| 541 |
+
},
|
| 542 |
+
{
|
| 543 |
+
"epoch": 0.5455243949289281,
|
| 544 |
+
"grad_norm": 2.3720905733220365,
|
| 545 |
+
"learning_rate": 4.559625324200536e-06,
|
| 546 |
+
"loss": 0.0738,
|
| 547 |
+
"step": 3550
|
| 548 |
+
},
|
| 549 |
+
{
|
| 550 |
+
"epoch": 0.5532078371110257,
|
| 551 |
+
"grad_norm": 2.922617471629335,
|
| 552 |
+
"learning_rate": 4.540439109051073e-06,
|
| 553 |
+
"loss": 0.0823,
|
| 554 |
+
"step": 3600
|
| 555 |
+
},
|
| 556 |
+
{
|
| 557 |
+
"epoch": 0.5532078371110257,
|
| 558 |
+
"eval_loss": 0.07812748104333878,
|
| 559 |
+
"eval_runtime": 17.9237,
|
| 560 |
+
"eval_samples_per_second": 205.371,
|
| 561 |
+
"eval_steps_per_second": 6.472,
|
| 562 |
+
"step": 3600
|
| 563 |
+
},
|
| 564 |
+
{
|
| 565 |
+
"epoch": 0.5608912792931233,
|
| 566 |
+
"grad_norm": 2.7852795271037087,
|
| 567 |
+
"learning_rate": 4.520885994970989e-06,
|
| 568 |
+
"loss": 0.0743,
|
| 569 |
+
"step": 3650
|
| 570 |
+
},
|
| 571 |
+
{
|
| 572 |
+
"epoch": 0.5685747214752209,
|
| 573 |
+
"grad_norm": 1.909529044630668,
|
| 574 |
+
"learning_rate": 4.500969497878309e-06,
|
| 575 |
+
"loss": 0.0746,
|
| 576 |
+
"step": 3700
|
| 577 |
+
},
|
| 578 |
+
{
|
| 579 |
+
"epoch": 0.5762581636573185,
|
| 580 |
+
"grad_norm": 2.3252755227402746,
|
| 581 |
+
"learning_rate": 4.480693199032311e-06,
|
| 582 |
+
"loss": 0.0732,
|
| 583 |
+
"step": 3750
|
| 584 |
+
},
|
| 585 |
+
{
|
| 586 |
+
"epoch": 0.583941605839416,
|
| 587 |
+
"grad_norm": 2.2587598776573223,
|
| 588 |
+
"learning_rate": 4.460060744389557e-06,
|
| 589 |
+
"loss": 0.0746,
|
| 590 |
+
"step": 3800
|
| 591 |
+
},
|
| 592 |
+
{
|
| 593 |
+
"epoch": 0.5916250480215136,
|
| 594 |
+
"grad_norm": 2.316511266907094,
|
| 595 |
+
"learning_rate": 4.4390758439483086e-06,
|
| 596 |
+
"loss": 0.0762,
|
| 597 |
+
"step": 3850
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"epoch": 0.5993084902036112,
|
| 601 |
+
"grad_norm": 2.2442036907986904,
|
| 602 |
+
"learning_rate": 4.417742271081412e-06,
|
| 603 |
+
"loss": 0.0747,
|
| 604 |
+
"step": 3900
|
| 605 |
+
},
|
| 606 |
+
{
|
| 607 |
+
"epoch": 0.6069919323857088,
|
| 608 |
+
"grad_norm": 1.6981947121024932,
|
| 609 |
+
"learning_rate": 4.3960638618578e-06,
|
| 610 |
+
"loss": 0.0705,
|
| 611 |
+
"step": 3950
|
| 612 |
+
},
|
| 613 |
+
{
|
| 614 |
+
"epoch": 0.6146753745678064,
|
| 615 |
+
"grad_norm": 2.461814042189026,
|
| 616 |
+
"learning_rate": 4.3740445143527065e-06,
|
| 617 |
+
"loss": 0.0767,
|
| 618 |
+
"step": 4000
|
| 619 |
+
},
|
| 620 |
+
{
|
| 621 |
+
"epoch": 0.622358816749904,
|
| 622 |
+
"grad_norm": 1.758351017204179,
|
| 623 |
+
"learning_rate": 4.351688187946746e-06,
|
| 624 |
+
"loss": 0.0736,
|
| 625 |
+
"step": 4050
|
| 626 |
+
},
|
| 627 |
+
{
|
| 628 |
+
"epoch": 0.6300422589320015,
|
| 629 |
+
"grad_norm": 2.5571250675031107,
|
| 630 |
+
"learning_rate": 4.328998902613962e-06,
|
| 631 |
+
"loss": 0.0724,
|
| 632 |
+
"step": 4100
|
| 633 |
+
},
|
| 634 |
+
{
|
| 635 |
+
"epoch": 0.6377257011140991,
|
| 636 |
+
"grad_norm": 2.349674273175025,
|
| 637 |
+
"learning_rate": 4.3059807381989724e-06,
|
| 638 |
+
"loss": 0.0739,
|
| 639 |
+
"step": 4150
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 0.6454091432961967,
|
| 643 |
+
"grad_norm": 2.187200746633409,
|
| 644 |
+
"learning_rate": 4.282637833683371e-06,
|
| 645 |
+
"loss": 0.0728,
|
| 646 |
+
"step": 4200
|
| 647 |
+
},
|
| 648 |
+
{
|
| 649 |
+
"epoch": 0.6454091432961967,
|
| 650 |
+
"eval_loss": 0.0765346810221672,
|
| 651 |
+
"eval_runtime": 27.9428,
|
| 652 |
+
"eval_samples_per_second": 131.733,
|
| 653 |
+
"eval_steps_per_second": 4.151,
|
| 654 |
+
"step": 4200
|
| 655 |
+
},
|
| 656 |
+
{
|
| 657 |
+
"epoch": 0.6530925854782943,
|
| 658 |
+
"grad_norm": 2.1984417750602483,
|
| 659 |
+
"learning_rate": 4.258974386441469e-06,
|
| 660 |
+
"loss": 0.0745,
|
| 661 |
+
"step": 4250
|
| 662 |
+
},
|
| 663 |
+
{
|
| 664 |
+
"epoch": 0.6607760276603919,
|
| 665 |
+
"grad_norm": 1.9098478006043746,
|
| 666 |
+
"learning_rate": 4.2349946514855585e-06,
|
| 667 |
+
"loss": 0.073,
|
| 668 |
+
"step": 4300
|
| 669 |
+
},
|
| 670 |
+
{
|
| 671 |
+
"epoch": 0.6684594698424894,
|
| 672 |
+
"grad_norm": 2.1688877445765624,
|
| 673 |
+
"learning_rate": 4.210702940700798e-06,
|
| 674 |
+
"loss": 0.0688,
|
| 675 |
+
"step": 4350
|
| 676 |
+
},
|
| 677 |
+
{
|
| 678 |
+
"epoch": 0.676142912024587,
|
| 679 |
+
"grad_norm": 2.2260961466321536,
|
| 680 |
+
"learning_rate": 4.186103622069879e-06,
|
| 681 |
+
"loss": 0.0715,
|
| 682 |
+
"step": 4400
|
| 683 |
+
},
|
| 684 |
+
{
|
| 685 |
+
"epoch": 0.6838263542066846,
|
| 686 |
+
"grad_norm": 1.979308479261721,
|
| 687 |
+
"learning_rate": 4.161201118887599e-06,
|
| 688 |
+
"loss": 0.071,
|
| 689 |
+
"step": 4450
|
| 690 |
+
},
|
| 691 |
+
{
|
| 692 |
+
"epoch": 0.6915097963887822,
|
| 693 |
+
"grad_norm": 1.9600879521664334,
|
| 694 |
+
"learning_rate": 4.135999908965499e-06,
|
| 695 |
+
"loss": 0.0742,
|
| 696 |
+
"step": 4500
|
| 697 |
+
},
|
| 698 |
+
{
|
| 699 |
+
"epoch": 0.6991932385708798,
|
| 700 |
+
"grad_norm": 2.4238054914257483,
|
| 701 |
+
"learning_rate": 4.110504523826685e-06,
|
| 702 |
+
"loss": 0.0715,
|
| 703 |
+
"step": 4550
|
| 704 |
+
},
|
| 705 |
+
{
|
| 706 |
+
"epoch": 0.7068766807529774,
|
| 707 |
+
"grad_norm": 2.1089065381121017,
|
| 708 |
+
"learning_rate": 4.0847195478910015e-06,
|
| 709 |
+
"loss": 0.0734,
|
| 710 |
+
"step": 4600
|
| 711 |
+
},
|
| 712 |
+
{
|
| 713 |
+
"epoch": 0.7145601229350749,
|
| 714 |
+
"grad_norm": 2.473769749167304,
|
| 715 |
+
"learning_rate": 4.058649617650691e-06,
|
| 716 |
+
"loss": 0.076,
|
| 717 |
+
"step": 4650
|
| 718 |
+
},
|
| 719 |
+
{
|
| 720 |
+
"epoch": 0.7222435651171725,
|
| 721 |
+
"grad_norm": 2.13037508106318,
|
| 722 |
+
"learning_rate": 4.0322994208366826e-06,
|
| 723 |
+
"loss": 0.0679,
|
| 724 |
+
"step": 4700
|
| 725 |
+
},
|
| 726 |
+
{
|
| 727 |
+
"epoch": 0.7299270072992701,
|
| 728 |
+
"grad_norm": 2.5081434982999986,
|
| 729 |
+
"learning_rate": 4.005673695575684e-06,
|
| 730 |
+
"loss": 0.0714,
|
| 731 |
+
"step": 4750
|
| 732 |
+
},
|
| 733 |
+
{
|
| 734 |
+
"epoch": 0.7376104494813677,
|
| 735 |
+
"grad_norm": 2.523258547710937,
|
| 736 |
+
"learning_rate": 3.978777229538191e-06,
|
| 737 |
+
"loss": 0.0726,
|
| 738 |
+
"step": 4800
|
| 739 |
+
},
|
| 740 |
+
{
|
| 741 |
+
"epoch": 0.7376104494813677,
|
| 742 |
+
"eval_loss": 0.07391650229692459,
|
| 743 |
+
"eval_runtime": 17.867,
|
| 744 |
+
"eval_samples_per_second": 206.022,
|
| 745 |
+
"eval_steps_per_second": 6.492,
|
| 746 |
+
"step": 4800
|
| 747 |
+
},
|
| 748 |
+
{
|
| 749 |
+
"epoch": 0.7452938916634653,
|
| 750 |
+
"grad_norm": 2.2265665380044086,
|
| 751 |
+
"learning_rate": 3.951614859077608e-06,
|
| 752 |
+
"loss": 0.0703,
|
| 753 |
+
"step": 4850
|
| 754 |
+
},
|
| 755 |
+
{
|
| 756 |
+
"epoch": 0.7529773338455628,
|
| 757 |
+
"grad_norm": 2.381066328795494,
|
| 758 |
+
"learning_rate": 3.924191468360597e-06,
|
| 759 |
+
"loss": 0.0744,
|
| 760 |
+
"step": 4900
|
| 761 |
+
},
|
| 762 |
+
{
|
| 763 |
+
"epoch": 0.7606607760276604,
|
| 764 |
+
"grad_norm": 2.8734977243388187,
|
| 765 |
+
"learning_rate": 3.896511988488843e-06,
|
| 766 |
+
"loss": 0.0705,
|
| 767 |
+
"step": 4950
|
| 768 |
+
},
|
| 769 |
+
{
|
| 770 |
+
"epoch": 0.768344218209758,
|
| 771 |
+
"grad_norm": 2.7655237374601267,
|
| 772 |
+
"learning_rate": 3.8685813966123705e-06,
|
| 773 |
+
"loss": 0.0722,
|
| 774 |
+
"step": 5000
|
| 775 |
+
},
|
| 776 |
+
{
|
| 777 |
+
"epoch": 0.7760276603918556,
|
| 778 |
+
"grad_norm": 2.0489765527392705,
|
| 779 |
+
"learning_rate": 3.84040471503459e-06,
|
| 780 |
+
"loss": 0.0714,
|
| 781 |
+
"step": 5050
|
| 782 |
+
},
|
| 783 |
+
{
|
| 784 |
+
"epoch": 0.7837111025739532,
|
| 785 |
+
"grad_norm": 2.130498868865807,
|
| 786 |
+
"learning_rate": 3.8119870103092117e-06,
|
| 787 |
+
"loss": 0.0712,
|
| 788 |
+
"step": 5100
|
| 789 |
+
},
|
| 790 |
+
{
|
| 791 |
+
"epoch": 0.7913945447560508,
|
| 792 |
+
"grad_norm": 2.156181891653775,
|
| 793 |
+
"learning_rate": 3.783333392329212e-06,
|
| 794 |
+
"loss": 0.0706,
|
| 795 |
+
"step": 5150
|
| 796 |
+
},
|
| 797 |
+
{
|
| 798 |
+
"epoch": 0.7990779869381482,
|
| 799 |
+
"grad_norm": 1.9223235226472895,
|
| 800 |
+
"learning_rate": 3.754449013408007e-06,
|
| 801 |
+
"loss": 0.0697,
|
| 802 |
+
"step": 5200
|
| 803 |
+
},
|
| 804 |
+
{
|
| 805 |
+
"epoch": 0.8067614291202458,
|
| 806 |
+
"grad_norm": 2.8205361640798023,
|
| 807 |
+
"learning_rate": 3.7253390673529943e-06,
|
| 808 |
+
"loss": 0.0694,
|
| 809 |
+
"step": 5250
|
| 810 |
+
},
|
| 811 |
+
{
|
| 812 |
+
"epoch": 0.8144448713023434,
|
| 813 |
+
"grad_norm": 2.5866793948731925,
|
| 814 |
+
"learning_rate": 3.6960087885316343e-06,
|
| 815 |
+
"loss": 0.0754,
|
| 816 |
+
"step": 5300
|
| 817 |
+
},
|
| 818 |
+
{
|
| 819 |
+
"epoch": 0.822128313484441,
|
| 820 |
+
"grad_norm": 1.6273019631219985,
|
| 821 |
+
"learning_rate": 3.66646345093024e-06,
|
| 822 |
+
"loss": 0.0746,
|
| 823 |
+
"step": 5350
|
| 824 |
+
},
|
| 825 |
+
{
|
| 826 |
+
"epoch": 0.8298117556665386,
|
| 827 |
+
"grad_norm": 2.3776525917677334,
|
| 828 |
+
"learning_rate": 3.6367083672056425e-06,
|
| 829 |
+
"loss": 0.0687,
|
| 830 |
+
"step": 5400
|
| 831 |
+
},
|
| 832 |
+
{
|
| 833 |
+
"epoch": 0.8298117556665386,
|
| 834 |
+
"eval_loss": 0.07365307211875916,
|
| 835 |
+
"eval_runtime": 17.8652,
|
| 836 |
+
"eval_samples_per_second": 206.043,
|
| 837 |
+
"eval_steps_per_second": 6.493,
|
| 838 |
+
"step": 5400
|
| 839 |
+
},
|
| 840 |
+
{
|
| 841 |
+
"epoch": 0.8374951978486362,
|
| 842 |
+
"grad_norm": 2.147338961225076,
|
| 843 |
+
"learning_rate": 3.6067488877299015e-06,
|
| 844 |
+
"loss": 0.0681,
|
| 845 |
+
"step": 5450
|
| 846 |
+
},
|
| 847 |
+
{
|
| 848 |
+
"epoch": 0.8451786400307337,
|
| 849 |
+
"grad_norm": 1.953555336915205,
|
| 850 |
+
"learning_rate": 3.576590399628237e-06,
|
| 851 |
+
"loss": 0.0697,
|
| 852 |
+
"step": 5500
|
| 853 |
+
},
|
| 854 |
+
{
|
| 855 |
+
"epoch": 0.8528620822128313,
|
| 856 |
+
"grad_norm": 2.657233757861753,
|
| 857 |
+
"learning_rate": 3.5462383258103463e-06,
|
| 858 |
+
"loss": 0.0692,
|
| 859 |
+
"step": 5550
|
| 860 |
+
},
|
| 861 |
+
{
|
| 862 |
+
"epoch": 0.8605455243949289,
|
| 863 |
+
"grad_norm": 2.366202874241117,
|
| 864 |
+
"learning_rate": 3.5156981239952948e-06,
|
| 865 |
+
"loss": 0.0721,
|
| 866 |
+
"step": 5600
|
| 867 |
+
},
|
| 868 |
+
{
|
| 869 |
+
"epoch": 0.8682289665770265,
|
| 870 |
+
"grad_norm": 2.0264884945952657,
|
| 871 |
+
"learning_rate": 3.48497528573014e-06,
|
| 872 |
+
"loss": 0.0727,
|
| 873 |
+
"step": 5650
|
| 874 |
+
},
|
| 875 |
+
{
|
| 876 |
+
"epoch": 0.8759124087591241,
|
| 877 |
+
"grad_norm": 1.887823865598268,
|
| 878 |
+
"learning_rate": 3.454075335402479e-06,
|
| 879 |
+
"loss": 0.0713,
|
| 880 |
+
"step": 5700
|
| 881 |
+
},
|
| 882 |
+
{
|
| 883 |
+
"epoch": 0.8835958509412216,
|
| 884 |
+
"grad_norm": 2.658475527954461,
|
| 885 |
+
"learning_rate": 3.423003829247084e-06,
|
| 886 |
+
"loss": 0.0663,
|
| 887 |
+
"step": 5750
|
| 888 |
+
},
|
| 889 |
+
{
|
| 890 |
+
"epoch": 0.8912792931233192,
|
| 891 |
+
"grad_norm": 1.6406842789595826,
|
| 892 |
+
"learning_rate": 3.3917663543468215e-06,
|
| 893 |
+
"loss": 0.0706,
|
| 894 |
+
"step": 5800
|
| 895 |
+
},
|
| 896 |
+
{
|
| 897 |
+
"epoch": 0.8989627353054168,
|
| 898 |
+
"grad_norm": 2.314778258305481,
|
| 899 |
+
"learning_rate": 3.3603685276280096e-06,
|
| 900 |
+
"loss": 0.0681,
|
| 901 |
+
"step": 5850
|
| 902 |
+
},
|
| 903 |
+
{
|
| 904 |
+
"epoch": 0.9066461774875144,
|
| 905 |
+
"grad_norm": 2.190779353343635,
|
| 906 |
+
"learning_rate": 3.3288159948504257e-06,
|
| 907 |
+
"loss": 0.0683,
|
| 908 |
+
"step": 5900
|
| 909 |
+
},
|
| 910 |
+
{
|
| 911 |
+
"epoch": 0.914329619669612,
|
| 912 |
+
"grad_norm": 1.6532618939938297,
|
| 913 |
+
"learning_rate": 3.2971144295921153e-06,
|
| 914 |
+
"loss": 0.0689,
|
| 915 |
+
"step": 5950
|
| 916 |
+
},
|
| 917 |
+
{
|
| 918 |
+
"epoch": 0.9220130618517096,
|
| 919 |
+
"grad_norm": 2.1027280690511527,
|
| 920 |
+
"learning_rate": 3.2652695322292087e-06,
|
| 921 |
+
"loss": 0.0692,
|
| 922 |
+
"step": 6000
|
| 923 |
+
},
|
| 924 |
+
{
|
| 925 |
+
"epoch": 0.9220130618517096,
|
| 926 |
+
"eval_loss": 0.07242421805858612,
|
| 927 |
+
"eval_runtime": 21.9858,
|
| 928 |
+
"eval_samples_per_second": 167.426,
|
| 929 |
+
"eval_steps_per_second": 5.276,
|
| 930 |
+
"step": 6000
|
| 931 |
+
},
|
| 932 |
+
{
|
| 933 |
+
"epoch": 0.9296965040338071,
|
| 934 |
+
"grad_norm": 2.7504375473082465,
|
| 935 |
+
"learning_rate": 3.233287028910914e-06,
|
| 936 |
+
"loss": 0.0689,
|
| 937 |
+
"step": 6050
|
| 938 |
+
},
|
| 939 |
+
{
|
| 940 |
+
"epoch": 0.9373799462159047,
|
| 941 |
+
"grad_norm": 2.316245889035153,
|
| 942 |
+
"learning_rate": 3.2011726705298773e-06,
|
| 943 |
+
"loss": 0.07,
|
| 944 |
+
"step": 6100
|
| 945 |
+
},
|
| 946 |
+
{
|
| 947 |
+
"epoch": 0.9450633883980023,
|
| 948 |
+
"grad_norm": 2.410296028767442,
|
| 949 |
+
"learning_rate": 3.1689322316880923e-06,
|
| 950 |
+
"loss": 0.0724,
|
| 951 |
+
"step": 6150
|
| 952 |
+
},
|
| 953 |
+
{
|
| 954 |
+
"epoch": 0.9527468305800999,
|
| 955 |
+
"grad_norm": 2.4485063146319805,
|
| 956 |
+
"learning_rate": 3.1365715096585474e-06,
|
| 957 |
+
"loss": 0.0678,
|
| 958 |
+
"step": 6200
|
| 959 |
+
},
|
| 960 |
+
{
|
| 961 |
+
"epoch": 0.9604302727621975,
|
| 962 |
+
"grad_norm": 2.0681296725028933,
|
| 963 |
+
"learning_rate": 3.1040963233428005e-06,
|
| 964 |
+
"loss": 0.0669,
|
| 965 |
+
"step": 6250
|
| 966 |
+
},
|
| 967 |
+
{
|
| 968 |
+
"epoch": 0.968113714944295,
|
| 969 |
+
"grad_norm": 2.2182760796494447,
|
| 970 |
+
"learning_rate": 3.071512512224654e-06,
|
| 971 |
+
"loss": 0.0683,
|
| 972 |
+
"step": 6300
|
| 973 |
+
},
|
| 974 |
+
{
|
| 975 |
+
"epoch": 0.9757971571263926,
|
| 976 |
+
"grad_norm": 2.016693520489793,
|
| 977 |
+
"learning_rate": 3.038825935320143e-06,
|
| 978 |
+
"loss": 0.0682,
|
| 979 |
+
"step": 6350
|
| 980 |
+
},
|
| 981 |
+
{
|
| 982 |
+
"epoch": 0.9834805993084902,
|
| 983 |
+
"grad_norm": 2.41156057499178,
|
| 984 |
+
"learning_rate": 3.0060424701239982e-06,
|
| 985 |
+
"loss": 0.0725,
|
| 986 |
+
"step": 6400
|
| 987 |
+
},
|
| 988 |
+
{
|
| 989 |
+
"epoch": 0.9911640414905878,
|
| 990 |
+
"grad_norm": 2.8306464381949406,
|
| 991 |
+
"learning_rate": 2.9731680115527918e-06,
|
| 992 |
+
"loss": 0.0685,
|
| 993 |
+
"step": 6450
|
| 994 |
+
},
|
| 995 |
+
{
|
| 996 |
+
"epoch": 0.9988474836726854,
|
| 997 |
+
"grad_norm": 2.4401019923715297,
|
| 998 |
+
"learning_rate": 2.9402084708849566e-06,
|
| 999 |
+
"loss": 0.0676,
|
| 1000 |
+
"step": 6500
|
| 1001 |
+
},
|
| 1002 |
+
{
|
| 1003 |
+
"epoch": 1.006454091432962,
|
| 1004 |
+
"grad_norm": 1.9066741002602279,
|
| 1005 |
+
"learning_rate": 2.90716977469785e-06,
|
| 1006 |
+
"loss": 0.052,
|
| 1007 |
+
"step": 6550
|
| 1008 |
+
},
|
| 1009 |
+
{
|
| 1010 |
+
"epoch": 1.0141375336150595,
|
| 1011 |
+
"grad_norm": 1.5268013929083424,
|
| 1012 |
+
"learning_rate": 2.8740578638020787e-06,
|
| 1013 |
+
"loss": 0.0531,
|
| 1014 |
+
"step": 6600
|
| 1015 |
+
},
|
| 1016 |
+
{
|
| 1017 |
+
"epoch": 1.0141375336150595,
|
| 1018 |
+
"eval_loss": 0.07169247418642044,
|
| 1019 |
+
"eval_runtime": 17.9984,
|
| 1020 |
+
"eval_samples_per_second": 204.518,
|
| 1021 |
+
"eval_steps_per_second": 6.445,
|
| 1022 |
+
"step": 6600
|
| 1023 |
+
},
|
| 1024 |
+
{
|
| 1025 |
+
"epoch": 1.021820975797157,
|
| 1026 |
+
"grad_norm": 1.7532162092101438,
|
| 1027 |
+
"learning_rate": 2.8408786921732568e-06,
|
| 1028 |
+
"loss": 0.0505,
|
| 1029 |
+
"step": 6650
|
| 1030 |
+
},
|
| 1031 |
+
{
|
| 1032 |
+
"epoch": 1.0295044179792547,
|
| 1033 |
+
"grad_norm": 1.9866953976458739,
|
| 1034 |
+
"learning_rate": 2.8076382258814005e-06,
|
| 1035 |
+
"loss": 0.0515,
|
| 1036 |
+
"step": 6700
|
| 1037 |
+
},
|
| 1038 |
+
{
|
| 1039 |
+
"epoch": 1.0371878601613522,
|
| 1040 |
+
"grad_norm": 1.86036393886952,
|
| 1041 |
+
"learning_rate": 2.7743424420181492e-06,
|
| 1042 |
+
"loss": 0.0489,
|
| 1043 |
+
"step": 6750
|
| 1044 |
+
},
|
| 1045 |
+
{
|
| 1046 |
+
"epoch": 1.04487130234345,
|
| 1047 |
+
"grad_norm": 1.6710747515829403,
|
| 1048 |
+
"learning_rate": 2.740997327621997e-06,
|
| 1049 |
+
"loss": 0.0499,
|
| 1050 |
+
"step": 6800
|
| 1051 |
+
},
|
| 1052 |
+
{
|
| 1053 |
+
"epoch": 1.0525547445255474,
|
| 1054 |
+
"grad_norm": 2.0799273695134226,
|
| 1055 |
+
"learning_rate": 2.7076088786017457e-06,
|
| 1056 |
+
"loss": 0.0515,
|
| 1057 |
+
"step": 6850
|
| 1058 |
+
},
|
| 1059 |
+
{
|
| 1060 |
+
"epoch": 1.060238186707645,
|
| 1061 |
+
"grad_norm": 2.580889185536816,
|
| 1062 |
+
"learning_rate": 2.6741830986583573e-06,
|
| 1063 |
+
"loss": 0.0514,
|
| 1064 |
+
"step": 6900
|
| 1065 |
+
},
|
| 1066 |
+
{
|
| 1067 |
+
"epoch": 1.0679216288897426,
|
| 1068 |
+
"grad_norm": 1.7167394019439424,
|
| 1069 |
+
"learning_rate": 2.640725998205405e-06,
|
| 1070 |
+
"loss": 0.0502,
|
| 1071 |
+
"step": 6950
|
| 1072 |
+
},
|
| 1073 |
+
{
|
| 1074 |
+
"epoch": 1.0756050710718401,
|
| 1075 |
+
"grad_norm": 2.085265353151105,
|
| 1076 |
+
"learning_rate": 2.6072435932883176e-06,
|
| 1077 |
+
"loss": 0.051,
|
| 1078 |
+
"step": 7000
|
| 1079 |
+
},
|
| 1080 |
+
{
|
| 1081 |
+
"epoch": 1.0832885132539378,
|
| 1082 |
+
"grad_norm": 1.976028725217046,
|
| 1083 |
+
"learning_rate": 2.573741904502618e-06,
|
| 1084 |
+
"loss": 0.0504,
|
| 1085 |
+
"step": 7050
|
| 1086 |
+
},
|
| 1087 |
+
{
|
| 1088 |
+
"epoch": 1.0909719554360353,
|
| 1089 |
+
"grad_norm": 2.065251142420112,
|
| 1090 |
+
"learning_rate": 2.540226955911328e-06,
|
| 1091 |
+
"loss": 0.049,
|
| 1092 |
+
"step": 7100
|
| 1093 |
+
},
|
| 1094 |
+
{
|
| 1095 |
+
"epoch": 1.098655397618133,
|
| 1096 |
+
"grad_norm": 1.9418713732405541,
|
| 1097 |
+
"learning_rate": 2.506704773961766e-06,
|
| 1098 |
+
"loss": 0.0497,
|
| 1099 |
+
"step": 7150
|
| 1100 |
+
},
|
| 1101 |
+
{
|
| 1102 |
+
"epoch": 1.1063388398002305,
|
| 1103 |
+
"grad_norm": 1.9522929472314208,
|
| 1104 |
+
"learning_rate": 2.47318138640191e-06,
|
| 1105 |
+
"loss": 0.0529,
|
| 1106 |
+
"step": 7200
|
| 1107 |
+
},
|
| 1108 |
+
{
|
| 1109 |
+
"epoch": 1.1063388398002305,
|
| 1110 |
+
"eval_loss": 0.0720512717962265,
|
| 1111 |
+
"eval_runtime": 20.6576,
|
| 1112 |
+
"eval_samples_per_second": 178.191,
|
| 1113 |
+
"eval_steps_per_second": 5.615,
|
| 1114 |
+
"step": 7200
|
| 1115 |
+
},
|
| 1116 |
+
{
|
| 1117 |
+
"epoch": 1.114022281982328,
|
| 1118 |
+
"grad_norm": 1.8217795610624572,
|
| 1119 |
+
"learning_rate": 2.43966282119652e-06,
|
| 1120 |
+
"loss": 0.0498,
|
| 1121 |
+
"step": 7250
|
| 1122 |
+
},
|
| 1123 |
+
{
|
| 1124 |
+
"epoch": 1.1217057241644257,
|
| 1125 |
+
"grad_norm": 2.211182366390281,
|
| 1126 |
+
"learning_rate": 2.4061551054432303e-06,
|
| 1127 |
+
"loss": 0.0494,
|
| 1128 |
+
"step": 7300
|
| 1129 |
+
},
|
| 1130 |
+
{
|
| 1131 |
+
"epoch": 1.1293891663465232,
|
| 1132 |
+
"grad_norm": 1.836486973368603,
|
| 1133 |
+
"learning_rate": 2.3726642642887977e-06,
|
| 1134 |
+
"loss": 0.0484,
|
| 1135 |
+
"step": 7350
|
| 1136 |
+
},
|
| 1137 |
+
{
|
| 1138 |
+
"epoch": 1.137072608528621,
|
| 1139 |
+
"grad_norm": 2.0872257595622092,
|
| 1140 |
+
"learning_rate": 2.3391963198456945e-06,
|
| 1141 |
+
"loss": 0.0459,
|
| 1142 |
+
"step": 7400
|
| 1143 |
+
},
|
| 1144 |
+
{
|
| 1145 |
+
"epoch": 1.1447560507107184,
|
| 1146 |
+
"grad_norm": 2.3771230389437243,
|
| 1147 |
+
"learning_rate": 2.3057572901092464e-06,
|
| 1148 |
+
"loss": 0.0489,
|
| 1149 |
+
"step": 7450
|
| 1150 |
+
},
|
| 1151 |
+
{
|
| 1152 |
+
"epoch": 1.1524394928928159,
|
| 1153 |
+
"grad_norm": 1.7766409365365587,
|
| 1154 |
+
"learning_rate": 2.2723531878755235e-06,
|
| 1155 |
+
"loss": 0.0514,
|
| 1156 |
+
"step": 7500
|
| 1157 |
+
},
|
| 1158 |
+
{
|
| 1159 |
+
"epoch": 1.1601229350749136,
|
| 1160 |
+
"grad_norm": 2.0041896806524613,
|
| 1161 |
+
"learning_rate": 2.238990019660148e-06,
|
| 1162 |
+
"loss": 0.0525,
|
| 1163 |
+
"step": 7550
|
| 1164 |
+
},
|
| 1165 |
+
{
|
| 1166 |
+
"epoch": 1.167806377257011,
|
| 1167 |
+
"grad_norm": 1.4220794048926986,
|
| 1168 |
+
"learning_rate": 2.2056737846182465e-06,
|
| 1169 |
+
"loss": 0.0495,
|
| 1170 |
+
"step": 7600
|
| 1171 |
+
},
|
| 1172 |
+
{
|
| 1173 |
+
"epoch": 1.1754898194391088,
|
| 1174 |
+
"grad_norm": 1.4059664663552494,
|
| 1175 |
+
"learning_rate": 2.1724104734657164e-06,
|
| 1176 |
+
"loss": 0.0473,
|
| 1177 |
+
"step": 7650
|
| 1178 |
+
},
|
| 1179 |
+
{
|
| 1180 |
+
"epoch": 1.1831732616212063,
|
| 1181 |
+
"grad_norm": 2.143768097788525,
|
| 1182 |
+
"learning_rate": 2.139206067402016e-06,
|
| 1183 |
+
"loss": 0.0508,
|
| 1184 |
+
"step": 7700
|
| 1185 |
+
},
|
| 1186 |
+
{
|
| 1187 |
+
"epoch": 1.1908567038033038,
|
| 1188 |
+
"grad_norm": 2.439141254991488,
|
| 1189 |
+
"learning_rate": 2.1060665370346577e-06,
|
| 1190 |
+
"loss": 0.0457,
|
| 1191 |
+
"step": 7750
|
| 1192 |
+
},
|
| 1193 |
+
{
|
| 1194 |
+
"epoch": 1.1985401459854015,
|
| 1195 |
+
"grad_norm": 2.1497324805762426,
|
| 1196 |
+
"learning_rate": 2.0729978413056167e-06,
|
| 1197 |
+
"loss": 0.0487,
|
| 1198 |
+
"step": 7800
|
| 1199 |
+
},
|
| 1200 |
+
{
|
| 1201 |
+
"epoch": 1.1985401459854015,
|
| 1202 |
+
"eval_loss": 0.0716494545340538,
|
| 1203 |
+
"eval_runtime": 17.9357,
|
| 1204 |
+
"eval_samples_per_second": 205.233,
|
| 1205 |
+
"eval_steps_per_second": 6.468,
|
| 1206 |
+
"step": 7800
|
| 1207 |
+
},
|
| 1208 |
+
{
|
| 1209 |
+
"epoch": 1.206223588167499,
|
| 1210 |
+
"grad_norm": 1.6548972664409785,
|
| 1211 |
+
"learning_rate": 2.040005926419829e-06,
|
| 1212 |
+
"loss": 0.0476,
|
| 1213 |
+
"step": 7850
|
| 1214 |
+
},
|
| 1215 |
+
{
|
| 1216 |
+
"epoch": 1.2139070303495967,
|
| 1217 |
+
"grad_norm": 1.9929716522339607,
|
| 1218 |
+
"learning_rate": 2.0070967247759794e-06,
|
| 1219 |
+
"loss": 0.0507,
|
| 1220 |
+
"step": 7900
|
| 1221 |
+
},
|
| 1222 |
+
{
|
| 1223 |
+
"epoch": 1.2215904725316942,
|
| 1224 |
+
"grad_norm": 1.8920582106563741,
|
| 1225 |
+
"learning_rate": 1.974276153899781e-06,
|
| 1226 |
+
"loss": 0.0513,
|
| 1227 |
+
"step": 7950
|
| 1228 |
+
},
|
| 1229 |
+
{
|
| 1230 |
+
"epoch": 1.2292739147137919,
|
| 1231 |
+
"grad_norm": 1.6121165647032283,
|
| 1232 |
+
"learning_rate": 1.9415501153799173e-06,
|
| 1233 |
+
"loss": 0.0478,
|
| 1234 |
+
"step": 8000
|
| 1235 |
+
},
|
| 1236 |
+
{
|
| 1237 |
+
"epoch": 1.2369573568958894,
|
| 1238 |
+
"grad_norm": 1.8003625671448367,
|
| 1239 |
+
"learning_rate": 1.908924493806859e-06,
|
| 1240 |
+
"loss": 0.0489,
|
| 1241 |
+
"step": 8050
|
| 1242 |
+
},
|
| 1243 |
+
{
|
| 1244 |
+
"epoch": 1.2446407990779869,
|
| 1245 |
+
"grad_norm": 1.6939131088624355,
|
| 1246 |
+
"learning_rate": 1.8764051557147316e-06,
|
| 1247 |
+
"loss": 0.0451,
|
| 1248 |
+
"step": 8100
|
| 1249 |
+
},
|
| 1250 |
+
{
|
| 1251 |
+
"epoch": 1.2523242412600846,
|
| 1252 |
+
"grad_norm": 1.7468120490008145,
|
| 1253 |
+
"learning_rate": 1.8439979485264352e-06,
|
| 1254 |
+
"loss": 0.0498,
|
| 1255 |
+
"step": 8150
|
| 1256 |
+
},
|
| 1257 |
+
{
|
| 1258 |
+
"epoch": 1.260007683442182,
|
| 1259 |
+
"grad_norm": 2.5089815003929155,
|
| 1260 |
+
"learning_rate": 1.8117086995021942e-06,
|
| 1261 |
+
"loss": 0.0491,
|
| 1262 |
+
"step": 8200
|
| 1263 |
+
},
|
| 1264 |
+
{
|
| 1265 |
+
"epoch": 1.2676911256242795,
|
| 1266 |
+
"grad_norm": 2.368789113392285,
|
| 1267 |
+
"learning_rate": 1.7795432146917391e-06,
|
| 1268 |
+
"loss": 0.0454,
|
| 1269 |
+
"step": 8250
|
| 1270 |
+
},
|
| 1271 |
+
{
|
| 1272 |
+
"epoch": 1.2753745678063773,
|
| 1273 |
+
"grad_norm": 1.8775747763554873,
|
| 1274 |
+
"learning_rate": 1.7475072778902962e-06,
|
| 1275 |
+
"loss": 0.0506,
|
| 1276 |
+
"step": 8300
|
| 1277 |
+
},
|
| 1278 |
+
{
|
| 1279 |
+
"epoch": 1.283058009988475,
|
| 1280 |
+
"grad_norm": 1.7306644111557166,
|
| 1281 |
+
"learning_rate": 1.715606649598584e-06,
|
| 1282 |
+
"loss": 0.0492,
|
| 1283 |
+
"step": 8350
|
| 1284 |
+
},
|
| 1285 |
+
{
|
| 1286 |
+
"epoch": 1.2907414521705725,
|
| 1287 |
+
"grad_norm": 1.6336792554226593,
|
| 1288 |
+
"learning_rate": 1.6838470659869971e-06,
|
| 1289 |
+
"loss": 0.0488,
|
| 1290 |
+
"step": 8400
|
| 1291 |
+
},
|
| 1292 |
+
{
|
| 1293 |
+
"epoch": 1.2907414521705725,
|
| 1294 |
+
"eval_loss": 0.06931500881910324,
|
| 1295 |
+
"eval_runtime": 18.4535,
|
| 1296 |
+
"eval_samples_per_second": 199.475,
|
| 1297 |
+
"eval_steps_per_second": 6.286,
|
| 1298 |
+
"step": 8400
|
| 1299 |
+
},
|
| 1300 |
+
{
|
| 1301 |
+
"epoch": 1.29842489435267,
|
| 1302 |
+
"grad_norm": 2.9094369118459174,
|
| 1303 |
+
"learning_rate": 1.6522342378641587e-06,
|
| 1304 |
+
"loss": 0.0494,
|
| 1305 |
+
"step": 8450
|
| 1306 |
+
},
|
| 1307 |
+
{
|
| 1308 |
+
"epoch": 1.3061083365347677,
|
| 1309 |
+
"grad_norm": 2.184054614982441,
|
| 1310 |
+
"learning_rate": 1.620773849650048e-06,
|
| 1311 |
+
"loss": 0.0502,
|
| 1312 |
+
"step": 8500
|
| 1313 |
+
},
|
| 1314 |
+
{
|
| 1315 |
+
"epoch": 1.3137917787168651,
|
| 1316 |
+
"grad_norm": 2.1244045904997537,
|
| 1317 |
+
"learning_rate": 1.5894715583538528e-06,
|
| 1318 |
+
"loss": 0.0466,
|
| 1319 |
+
"step": 8550
|
| 1320 |
+
},
|
| 1321 |
+
{
|
| 1322 |
+
"epoch": 1.3214752208989626,
|
| 1323 |
+
"grad_norm": 2.4284504241807467,
|
| 1324 |
+
"learning_rate": 1.558332992556772e-06,
|
| 1325 |
+
"loss": 0.0493,
|
| 1326 |
+
"step": 8600
|
| 1327 |
+
},
|
| 1328 |
+
{
|
| 1329 |
+
"epoch": 1.3291586630810603,
|
| 1330 |
+
"grad_norm": 1.540633041404585,
|
| 1331 |
+
"learning_rate": 1.5273637513999112e-06,
|
| 1332 |
+
"loss": 0.0442,
|
| 1333 |
+
"step": 8650
|
| 1334 |
+
},
|
| 1335 |
+
{
|
| 1336 |
+
"epoch": 1.3368421052631578,
|
| 1337 |
+
"grad_norm": 1.8384007539282532,
|
| 1338 |
+
"learning_rate": 1.4965694035774864e-06,
|
| 1339 |
+
"loss": 0.0497,
|
| 1340 |
+
"step": 8700
|
| 1341 |
+
},
|
| 1342 |
+
{
|
| 1343 |
+
"epoch": 1.3445255474452555,
|
| 1344 |
+
"grad_norm": 1.7618498321526446,
|
| 1345 |
+
"learning_rate": 1.465955486335493e-06,
|
| 1346 |
+
"loss": 0.0458,
|
| 1347 |
+
"step": 8750
|
| 1348 |
+
},
|
| 1349 |
+
{
|
| 1350 |
+
"epoch": 1.352208989627353,
|
| 1351 |
+
"grad_norm": 2.231775422548153,
|
| 1352 |
+
"learning_rate": 1.435527504476033e-06,
|
| 1353 |
+
"loss": 0.0493,
|
| 1354 |
+
"step": 8800
|
| 1355 |
+
},
|
| 1356 |
+
{
|
| 1357 |
+
"epoch": 1.3598924318094507,
|
| 1358 |
+
"grad_norm": 1.7224514278527392,
|
| 1359 |
+
"learning_rate": 1.4052909293674792e-06,
|
| 1360 |
+
"loss": 0.0476,
|
| 1361 |
+
"step": 8850
|
| 1362 |
+
},
|
| 1363 |
+
{
|
| 1364 |
+
"epoch": 1.3675758739915482,
|
| 1365 |
+
"grad_norm": 1.8541565429096656,
|
| 1366 |
+
"learning_rate": 1.375251197960643e-06,
|
| 1367 |
+
"loss": 0.0488,
|
| 1368 |
+
"step": 8900
|
| 1369 |
+
},
|
| 1370 |
+
{
|
| 1371 |
+
"epoch": 1.3752593161736457,
|
| 1372 |
+
"grad_norm": 2.381490833870002,
|
| 1373 |
+
"learning_rate": 1.345413711811143e-06,
|
| 1374 |
+
"loss": 0.0494,
|
| 1375 |
+
"step": 8950
|
| 1376 |
+
},
|
| 1377 |
+
{
|
| 1378 |
+
"epoch": 1.3829427583557434,
|
| 1379 |
+
"grad_norm": 2.278959306976094,
|
| 1380 |
+
"learning_rate": 1.315783836108122e-06,
|
| 1381 |
+
"loss": 0.0494,
|
| 1382 |
+
"step": 9000
|
| 1383 |
+
},
|
| 1384 |
+
{
|
| 1385 |
+
"epoch": 1.3829427583557434,
|
| 1386 |
+
"eval_loss": 0.06873823702335358,
|
| 1387 |
+
"eval_runtime": 17.8999,
|
| 1388 |
+
"eval_samples_per_second": 205.644,
|
| 1389 |
+
"eval_steps_per_second": 6.48,
|
| 1390 |
+
"step": 9000
|
| 1391 |
+
},
|
| 1392 |
+
{
|
| 1393 |
+
"epoch": 1.390626200537841,
|
| 1394 |
+
"grad_norm": 2.1844843542778904,
|
| 1395 |
+
"learning_rate": 1.2863668987095232e-06,
|
| 1396 |
+
"loss": 0.046,
|
| 1397 |
+
"step": 9050
|
| 1398 |
+
},
|
| 1399 |
+
{
|
| 1400 |
+
"epoch": 1.3983096427199384,
|
| 1401 |
+
"grad_norm": 1.8497980702776782,
|
| 1402 |
+
"learning_rate": 1.2571681891840604e-06,
|
| 1403 |
+
"loss": 0.0457,
|
| 1404 |
+
"step": 9100
|
| 1405 |
+
},
|
| 1406 |
+
{
|
| 1407 |
+
"epoch": 1.4059930849020361,
|
| 1408 |
+
"grad_norm": 2.361384912110055,
|
| 1409 |
+
"learning_rate": 1.2281929578600818e-06,
|
| 1410 |
+
"loss": 0.0446,
|
| 1411 |
+
"step": 9150
|
| 1412 |
+
},
|
| 1413 |
+
{
|
| 1414 |
+
"epoch": 1.4136765270841338,
|
| 1415 |
+
"grad_norm": 1.7735596712796649,
|
| 1416 |
+
"learning_rate": 1.1994464148814944e-06,
|
| 1417 |
+
"loss": 0.0491,
|
| 1418 |
+
"step": 9200
|
| 1419 |
+
},
|
| 1420 |
+
{
|
| 1421 |
+
"epoch": 1.4213599692662313,
|
| 1422 |
+
"grad_norm": 2.5534458205266075,
|
| 1423 |
+
"learning_rate": 1.1709337292709006e-06,
|
| 1424 |
+
"loss": 0.0513,
|
| 1425 |
+
"step": 9250
|
| 1426 |
+
},
|
| 1427 |
+
{
|
| 1428 |
+
"epoch": 1.4290434114483288,
|
| 1429 |
+
"grad_norm": 1.9943434045148776,
|
| 1430 |
+
"learning_rate": 1.1426600280001452e-06,
|
| 1431 |
+
"loss": 0.0457,
|
| 1432 |
+
"step": 9300
|
| 1433 |
+
},
|
| 1434 |
+
{
|
| 1435 |
+
"epoch": 1.4367268536304265,
|
| 1436 |
+
"grad_norm": 1.6552094390596166,
|
| 1437 |
+
"learning_rate": 1.1146303950684086e-06,
|
| 1438 |
+
"loss": 0.0474,
|
| 1439 |
+
"step": 9350
|
| 1440 |
+
},
|
| 1441 |
+
{
|
| 1442 |
+
"epoch": 1.444410295812524,
|
| 1443 |
+
"grad_norm": 2.142802888711476,
|
| 1444 |
+
"learning_rate": 1.08684987058804e-06,
|
| 1445 |
+
"loss": 0.0477,
|
| 1446 |
+
"step": 9400
|
| 1447 |
+
},
|
| 1448 |
+
{
|
| 1449 |
+
"epoch": 1.4520937379946215,
|
| 1450 |
+
"grad_norm": 1.964334339120735,
|
| 1451 |
+
"learning_rate": 1.0593234498782707e-06,
|
| 1452 |
+
"loss": 0.0468,
|
| 1453 |
+
"step": 9450
|
| 1454 |
+
},
|
| 1455 |
+
{
|
| 1456 |
+
"epoch": 1.4597771801767192,
|
| 1457 |
+
"grad_norm": 1.6390715251269143,
|
| 1458 |
+
"learning_rate": 1.0320560825669907e-06,
|
| 1459 |
+
"loss": 0.049,
|
| 1460 |
+
"step": 9500
|
| 1461 |
+
},
|
| 1462 |
+
{
|
| 1463 |
+
"epoch": 1.4674606223588167,
|
| 1464 |
+
"grad_norm": 2.0864027751268814,
|
| 1465 |
+
"learning_rate": 1.0050526717007386e-06,
|
| 1466 |
+
"loss": 0.0438,
|
| 1467 |
+
"step": 9550
|
| 1468 |
+
},
|
| 1469 |
+
{
|
| 1470 |
+
"epoch": 1.4751440645409144,
|
| 1471 |
+
"grad_norm": 1.9215266401428566,
|
| 1472 |
+
"learning_rate": 9.783180728630606e-07,
|
| 1473 |
+
"loss": 0.0483,
|
| 1474 |
+
"step": 9600
|
| 1475 |
+
},
|
| 1476 |
+
{
|
| 1477 |
+
"epoch": 1.4751440645409144,
|
| 1478 |
+
"eval_loss": 0.06846572458744049,
|
| 1479 |
+
"eval_runtime": 17.9503,
|
| 1480 |
+
"eval_samples_per_second": 205.066,
|
| 1481 |
+
"eval_steps_per_second": 6.462,
|
| 1482 |
+
"step": 9600
|
| 1483 |
+
},
|
| 1484 |
+
{
|
| 1485 |
+
"epoch": 1.482827506723012,
|
| 1486 |
+
"grad_norm": 1.7928996170417553,
|
| 1487 |
+
"learning_rate": 9.518570933014182e-07,
|
| 1488 |
+
"loss": 0.0478,
|
| 1489 |
+
"step": 9650
|
| 1490 |
+
},
|
| 1491 |
+
{
|
| 1492 |
+
"epoch": 1.4905109489051096,
|
| 1493 |
+
"grad_norm": 1.9873792527502019,
|
| 1494 |
+
"learning_rate": 9.25674491062774e-07,
|
| 1495 |
+
"loss": 0.0469,
|
| 1496 |
+
"step": 9700
|
| 1497 |
+
},
|
| 1498 |
+
{
|
| 1499 |
+
"epoch": 1.498194391087207,
|
| 1500 |
+
"grad_norm": 1.8602555769335043,
|
| 1501 |
+
"learning_rate": 8.997749741380291e-07,
|
| 1502 |
+
"loss": 0.0478,
|
| 1503 |
+
"step": 9750
|
| 1504 |
+
},
|
| 1505 |
+
{
|
| 1506 |
+
"epoch": 1.5058778332693046,
|
| 1507 |
+
"grad_norm": 2.0982729436998677,
|
| 1508 |
+
"learning_rate": 8.741631996154651e-07,
|
| 1509 |
+
"loss": 0.0479,
|
| 1510 |
+
"step": 9800
|
| 1511 |
+
},
|
| 1512 |
+
{
|
| 1513 |
+
"epoch": 1.5135612754514023,
|
| 1514 |
+
"grad_norm": 1.698553296101875,
|
| 1515 |
+
"learning_rate": 8.488437728433346e-07,
|
| 1516 |
+
"loss": 0.0453,
|
| 1517 |
+
"step": 9850
|
| 1518 |
+
},
|
| 1519 |
+
{
|
| 1520 |
+
"epoch": 1.5212447176334998,
|
| 1521 |
+
"grad_norm": 1.7327244928480596,
|
| 1522 |
+
"learning_rate": 8.238212466017536e-07,
|
| 1523 |
+
"loss": 0.0453,
|
| 1524 |
+
"step": 9900
|
| 1525 |
+
},
|
| 1526 |
+
{
|
| 1527 |
+
"epoch": 1.5289281598155973,
|
| 1528 |
+
"grad_norm": 2.5157076501848787,
|
| 1529 |
+
"learning_rate": 7.99100120284054e-07,
|
| 1530 |
+
"loss": 0.0469,
|
| 1531 |
+
"step": 9950
|
| 1532 |
+
},
|
| 1533 |
+
{
|
| 1534 |
+
"epoch": 1.536611601997695,
|
| 1535 |
+
"grad_norm": 2.2123154799862776,
|
| 1536 |
+
"learning_rate": 7.746848390877282e-07,
|
| 1537 |
+
"loss": 0.0474,
|
| 1538 |
+
"step": 10000
|
| 1539 |
+
},
|
| 1540 |
+
{
|
| 1541 |
+
"epoch": 1.5442950441797927,
|
| 1542 |
+
"grad_norm": 2.1165949034476106,
|
| 1543 |
+
"learning_rate": 7.505797932151198e-07,
|
| 1544 |
+
"loss": 0.0501,
|
| 1545 |
+
"step": 10050
|
| 1546 |
+
},
|
| 1547 |
+
{
|
| 1548 |
+
"epoch": 1.5519784863618902,
|
| 1549 |
+
"grad_norm": 1.9622924083143274,
|
| 1550 |
+
"learning_rate": 7.267893170840104e-07,
|
| 1551 |
+
"loss": 0.0472,
|
| 1552 |
+
"step": 10100
|
| 1553 |
+
},
|
| 1554 |
+
{
|
| 1555 |
+
"epoch": 1.5596619285439877,
|
| 1556 |
+
"grad_norm": 2.0167441488769984,
|
| 1557 |
+
"learning_rate": 7.033176885482257e-07,
|
| 1558 |
+
"loss": 0.0466,
|
| 1559 |
+
"step": 10150
|
| 1560 |
+
},
|
| 1561 |
+
{
|
| 1562 |
+
"epoch": 1.5673453707260854,
|
| 1563 |
+
"grad_norm": 2.583323639603209,
|
| 1564 |
+
"learning_rate": 6.801691281284243e-07,
|
| 1565 |
+
"loss": 0.0448,
|
| 1566 |
+
"step": 10200
|
| 1567 |
+
},
|
| 1568 |
+
{
|
| 1569 |
+
"epoch": 1.5673453707260854,
|
| 1570 |
+
"eval_loss": 0.06800152361392975,
|
| 1571 |
+
"eval_runtime": 17.9086,
|
| 1572 |
+
"eval_samples_per_second": 205.544,
|
| 1573 |
+
"eval_steps_per_second": 6.477,
|
| 1574 |
+
"step": 10200
|
| 1575 |
+
},
|
| 1576 |
+
{
|
| 1577 |
+
"epoch": 1.5750288129081829,
|
| 1578 |
+
"grad_norm": 2.320026361459745,
|
| 1579 |
+
"learning_rate": 6.573477982531845e-07,
|
| 1580 |
+
"loss": 0.0457,
|
| 1581 |
+
"step": 10250
|
| 1582 |
+
},
|
| 1583 |
+
{
|
| 1584 |
+
"epoch": 1.5827122550902804,
|
| 1585 |
+
"grad_norm": 1.8563171575104342,
|
| 1586 |
+
"learning_rate": 6.348578025105487e-07,
|
| 1587 |
+
"loss": 0.0445,
|
| 1588 |
+
"step": 10300
|
| 1589 |
+
},
|
| 1590 |
+
{
|
| 1591 |
+
"epoch": 1.590395697272378,
|
| 1592 |
+
"grad_norm": 2.4148912012974337,
|
| 1593 |
+
"learning_rate": 6.12703184910138e-07,
|
| 1594 |
+
"loss": 0.0458,
|
| 1595 |
+
"step": 10350
|
| 1596 |
+
},
|
| 1597 |
+
{
|
| 1598 |
+
"epoch": 1.5980791394544756,
|
| 1599 |
+
"grad_norm": 2.0191213809598416,
|
| 1600 |
+
"learning_rate": 5.908879291559835e-07,
|
| 1601 |
+
"loss": 0.0465,
|
| 1602 |
+
"step": 10400
|
| 1603 |
+
}
|
| 1604 |
+
],
|
| 1605 |
+
"logging_steps": 50,
|
| 1606 |
+
"max_steps": 13016,
|
| 1607 |
+
"num_input_tokens_seen": 0,
|
| 1608 |
+
"num_train_epochs": 2,
|
| 1609 |
+
"save_steps": 2604,
|
| 1610 |
+
"stateful_callbacks": {
|
| 1611 |
+
"TrainerControl": {
|
| 1612 |
+
"args": {
|
| 1613 |
+
"should_epoch_stop": false,
|
| 1614 |
+
"should_evaluate": false,
|
| 1615 |
+
"should_log": false,
|
| 1616 |
+
"should_save": true,
|
| 1617 |
+
"should_training_stop": false
|
| 1618 |
+
},
|
| 1619 |
+
"attributes": {}
|
| 1620 |
+
}
|
| 1621 |
+
},
|
| 1622 |
+
"total_flos": 248681020006400.0,
|
| 1623 |
+
"train_batch_size": 28,
|
| 1624 |
+
"trial_name": null,
|
| 1625 |
+
"trial_params": null
|
| 1626 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:31ab1d967d6c33c6c1f193fd40ec27130428c4d0f45c660a6e75a5e5f5e22449
|
| 3 |
+
size 7736
|