Upload folder using huggingface_hub
Browse files- pretrained/model.safetensors +3 -0
- pretrained/optimizer.pt +3 -0
- pretrained/rng_state.pth +3 -0
- pretrained/scheduler.pt +3 -0
- pretrained/trainer_state.json +3586 -0
- pretrained/training_args.bin +3 -0
pretrained/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:dc7e4fc71c32246873af6edcfc8169ea8ebaf4f304550b951e46b357b5e71c45
|
| 3 |
+
size 16507452000
|
pretrained/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:206ee22b1b58848413be71b68e976f2d36a08e3deff313ea444fa41a896f9086
|
| 3 |
+
size 247636043
|
pretrained/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8a425c3856c00c21b0537f950565c1c8f885fb5425772e1f515e2fe7638a3dd6
|
| 3 |
+
size 14645
|
pretrained/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:84e49aa6fab723eda963b98f01168336abd34577d4043e4dfca0adb1cef0b891
|
| 3 |
+
size 1465
|
pretrained/trainer_state.json
ADDED
|
@@ -0,0 +1,3586 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": null,
|
| 3 |
+
"best_metric": null,
|
| 4 |
+
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 10.353982300884956,
|
| 6 |
+
"eval_steps": 500,
|
| 7 |
+
"global_step": 12000,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.021584286639326572,
|
| 14 |
+
"grad_norm": 1.5234375,
|
| 15 |
+
"learning_rate": 8.000000000000001e-06,
|
| 16 |
+
"loss": 3.7923,
|
| 17 |
+
"step": 25
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 0.043168573278653144,
|
| 21 |
+
"grad_norm": 0.6796875,
|
| 22 |
+
"learning_rate": 1.6333333333333335e-05,
|
| 23 |
+
"loss": 3.8062,
|
| 24 |
+
"step": 50
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.06475285991797972,
|
| 28 |
+
"grad_norm": 0.98828125,
|
| 29 |
+
"learning_rate": 2.466666666666667e-05,
|
| 30 |
+
"loss": 3.5078,
|
| 31 |
+
"step": 75
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 0.08633714655730629,
|
| 35 |
+
"grad_norm": 1.53125,
|
| 36 |
+
"learning_rate": 3.3e-05,
|
| 37 |
+
"loss": 2.8861,
|
| 38 |
+
"step": 100
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.10792143319663285,
|
| 42 |
+
"grad_norm": 0.48046875,
|
| 43 |
+
"learning_rate": 4.133333333333333e-05,
|
| 44 |
+
"loss": 2.6734,
|
| 45 |
+
"step": 125
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.12950571983595943,
|
| 49 |
+
"grad_norm": 0.5625,
|
| 50 |
+
"learning_rate": 4.966666666666667e-05,
|
| 51 |
+
"loss": 2.5981,
|
| 52 |
+
"step": 150
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 0.151090006475286,
|
| 56 |
+
"grad_norm": 0.2021484375,
|
| 57 |
+
"learning_rate": 5.8e-05,
|
| 58 |
+
"loss": 2.4867,
|
| 59 |
+
"step": 175
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 0.17267429311461258,
|
| 63 |
+
"grad_norm": 0.455078125,
|
| 64 |
+
"learning_rate": 6.633333333333334e-05,
|
| 65 |
+
"loss": 2.4344,
|
| 66 |
+
"step": 200
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 0.19425857975393912,
|
| 70 |
+
"grad_norm": 1.3359375,
|
| 71 |
+
"learning_rate": 7.466666666666667e-05,
|
| 72 |
+
"loss": 2.5441,
|
| 73 |
+
"step": 225
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 0.2158428663932657,
|
| 77 |
+
"grad_norm": 0.1552734375,
|
| 78 |
+
"learning_rate": 8.3e-05,
|
| 79 |
+
"loss": 2.4667,
|
| 80 |
+
"step": 250
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.23742715303259226,
|
| 84 |
+
"grad_norm": 0.357421875,
|
| 85 |
+
"learning_rate": 9.133333333333334e-05,
|
| 86 |
+
"loss": 2.4935,
|
| 87 |
+
"step": 275
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.25901143967191886,
|
| 91 |
+
"grad_norm": 0.19140625,
|
| 92 |
+
"learning_rate": 9.966666666666667e-05,
|
| 93 |
+
"loss": 2.4301,
|
| 94 |
+
"step": 300
|
| 95 |
+
},
|
| 96 |
+
{
|
| 97 |
+
"epoch": 0.2805957263112454,
|
| 98 |
+
"grad_norm": 0.1474609375,
|
| 99 |
+
"learning_rate": 9.997592778335006e-05,
|
| 100 |
+
"loss": 2.526,
|
| 101 |
+
"step": 325
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"epoch": 0.302180012950572,
|
| 105 |
+
"grad_norm": 0.2041015625,
|
| 106 |
+
"learning_rate": 9.995085255767302e-05,
|
| 107 |
+
"loss": 2.5079,
|
| 108 |
+
"step": 350
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"epoch": 0.32376429958989855,
|
| 112 |
+
"grad_norm": 0.25,
|
| 113 |
+
"learning_rate": 9.9925777331996e-05,
|
| 114 |
+
"loss": 2.5088,
|
| 115 |
+
"step": 375
|
| 116 |
+
},
|
| 117 |
+
{
|
| 118 |
+
"epoch": 0.34534858622922515,
|
| 119 |
+
"grad_norm": 0.138671875,
|
| 120 |
+
"learning_rate": 9.990070210631897e-05,
|
| 121 |
+
"loss": 2.5054,
|
| 122 |
+
"step": 400
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 0.3669328728685517,
|
| 126 |
+
"grad_norm": 0.291015625,
|
| 127 |
+
"learning_rate": 9.987562688064192e-05,
|
| 128 |
+
"loss": 2.5176,
|
| 129 |
+
"step": 425
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.38851715950787824,
|
| 133 |
+
"grad_norm": 0.265625,
|
| 134 |
+
"learning_rate": 9.98505516549649e-05,
|
| 135 |
+
"loss": 2.3518,
|
| 136 |
+
"step": 450
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 0.41010144614720484,
|
| 140 |
+
"grad_norm": 0.6640625,
|
| 141 |
+
"learning_rate": 9.982547642928787e-05,
|
| 142 |
+
"loss": 2.4348,
|
| 143 |
+
"step": 475
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 0.4316857327865314,
|
| 147 |
+
"grad_norm": 0.1748046875,
|
| 148 |
+
"learning_rate": 9.980040120361083e-05,
|
| 149 |
+
"loss": 2.4306,
|
| 150 |
+
"step": 500
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"epoch": 0.4316857327865314,
|
| 154 |
+
"eval_loss": 2.454599618911743,
|
| 155 |
+
"eval_runtime": 119.0408,
|
| 156 |
+
"eval_samples_per_second": 4.2,
|
| 157 |
+
"eval_steps_per_second": 4.2,
|
| 158 |
+
"step": 500
|
| 159 |
+
},
|
| 160 |
+
{
|
| 161 |
+
"epoch": 0.453270019425858,
|
| 162 |
+
"grad_norm": 0.201171875,
|
| 163 |
+
"learning_rate": 9.977532597793381e-05,
|
| 164 |
+
"loss": 2.4055,
|
| 165 |
+
"step": 525
|
| 166 |
+
},
|
| 167 |
+
{
|
| 168 |
+
"epoch": 0.47485430606518453,
|
| 169 |
+
"grad_norm": 0.62109375,
|
| 170 |
+
"learning_rate": 9.975025075225678e-05,
|
| 171 |
+
"loss": 2.4223,
|
| 172 |
+
"step": 550
|
| 173 |
+
},
|
| 174 |
+
{
|
| 175 |
+
"epoch": 0.49643859270451113,
|
| 176 |
+
"grad_norm": 0.1474609375,
|
| 177 |
+
"learning_rate": 9.972517552657973e-05,
|
| 178 |
+
"loss": 2.3973,
|
| 179 |
+
"step": 575
|
| 180 |
+
},
|
| 181 |
+
{
|
| 182 |
+
"epoch": 0.5180228793438377,
|
| 183 |
+
"grad_norm": 0.1806640625,
|
| 184 |
+
"learning_rate": 9.970010030090271e-05,
|
| 185 |
+
"loss": 2.477,
|
| 186 |
+
"step": 600
|
| 187 |
+
},
|
| 188 |
+
{
|
| 189 |
+
"epoch": 0.5396071659831643,
|
| 190 |
+
"grad_norm": 0.166015625,
|
| 191 |
+
"learning_rate": 9.967502507522568e-05,
|
| 192 |
+
"loss": 2.447,
|
| 193 |
+
"step": 625
|
| 194 |
+
},
|
| 195 |
+
{
|
| 196 |
+
"epoch": 0.5611914526224908,
|
| 197 |
+
"grad_norm": 0.197265625,
|
| 198 |
+
"learning_rate": 9.964994984954865e-05,
|
| 199 |
+
"loss": 2.4324,
|
| 200 |
+
"step": 650
|
| 201 |
+
},
|
| 202 |
+
{
|
| 203 |
+
"epoch": 0.5827757392618174,
|
| 204 |
+
"grad_norm": 0.1845703125,
|
| 205 |
+
"learning_rate": 9.962487462387163e-05,
|
| 206 |
+
"loss": 2.3273,
|
| 207 |
+
"step": 675
|
| 208 |
+
},
|
| 209 |
+
{
|
| 210 |
+
"epoch": 0.604360025901144,
|
| 211 |
+
"grad_norm": 0.1630859375,
|
| 212 |
+
"learning_rate": 9.959979939819459e-05,
|
| 213 |
+
"loss": 2.4169,
|
| 214 |
+
"step": 700
|
| 215 |
+
},
|
| 216 |
+
{
|
| 217 |
+
"epoch": 0.6259443125404706,
|
| 218 |
+
"grad_norm": 0.166015625,
|
| 219 |
+
"learning_rate": 9.957472417251756e-05,
|
| 220 |
+
"loss": 2.4924,
|
| 221 |
+
"step": 725
|
| 222 |
+
},
|
| 223 |
+
{
|
| 224 |
+
"epoch": 0.6475285991797971,
|
| 225 |
+
"grad_norm": 0.1884765625,
|
| 226 |
+
"learning_rate": 9.954964894684052e-05,
|
| 227 |
+
"loss": 2.5247,
|
| 228 |
+
"step": 750
|
| 229 |
+
},
|
| 230 |
+
{
|
| 231 |
+
"epoch": 0.6691128858191236,
|
| 232 |
+
"grad_norm": 0.1904296875,
|
| 233 |
+
"learning_rate": 9.952457372116349e-05,
|
| 234 |
+
"loss": 2.4709,
|
| 235 |
+
"step": 775
|
| 236 |
+
},
|
| 237 |
+
{
|
| 238 |
+
"epoch": 0.6906971724584503,
|
| 239 |
+
"grad_norm": 0.1845703125,
|
| 240 |
+
"learning_rate": 9.949949849548647e-05,
|
| 241 |
+
"loss": 2.369,
|
| 242 |
+
"step": 800
|
| 243 |
+
},
|
| 244 |
+
{
|
| 245 |
+
"epoch": 0.7122814590977768,
|
| 246 |
+
"grad_norm": 0.1630859375,
|
| 247 |
+
"learning_rate": 9.947442326980944e-05,
|
| 248 |
+
"loss": 2.5355,
|
| 249 |
+
"step": 825
|
| 250 |
+
},
|
| 251 |
+
{
|
| 252 |
+
"epoch": 0.7338657457371034,
|
| 253 |
+
"grad_norm": 0.2109375,
|
| 254 |
+
"learning_rate": 9.94493480441324e-05,
|
| 255 |
+
"loss": 2.4896,
|
| 256 |
+
"step": 850
|
| 257 |
+
},
|
| 258 |
+
{
|
| 259 |
+
"epoch": 0.7554500323764299,
|
| 260 |
+
"grad_norm": 0.1943359375,
|
| 261 |
+
"learning_rate": 9.942427281845537e-05,
|
| 262 |
+
"loss": 2.4591,
|
| 263 |
+
"step": 875
|
| 264 |
+
},
|
| 265 |
+
{
|
| 266 |
+
"epoch": 0.7770343190157565,
|
| 267 |
+
"grad_norm": 0.140625,
|
| 268 |
+
"learning_rate": 9.939919759277834e-05,
|
| 269 |
+
"loss": 2.369,
|
| 270 |
+
"step": 900
|
| 271 |
+
},
|
| 272 |
+
{
|
| 273 |
+
"epoch": 0.7986186056550831,
|
| 274 |
+
"grad_norm": 0.21484375,
|
| 275 |
+
"learning_rate": 9.93741223671013e-05,
|
| 276 |
+
"loss": 2.4518,
|
| 277 |
+
"step": 925
|
| 278 |
+
},
|
| 279 |
+
{
|
| 280 |
+
"epoch": 0.8202028922944097,
|
| 281 |
+
"grad_norm": 0.1962890625,
|
| 282 |
+
"learning_rate": 9.934904714142428e-05,
|
| 283 |
+
"loss": 2.3972,
|
| 284 |
+
"step": 950
|
| 285 |
+
},
|
| 286 |
+
{
|
| 287 |
+
"epoch": 0.8417871789337362,
|
| 288 |
+
"grad_norm": 0.26953125,
|
| 289 |
+
"learning_rate": 9.932397191574725e-05,
|
| 290 |
+
"loss": 2.4437,
|
| 291 |
+
"step": 975
|
| 292 |
+
},
|
| 293 |
+
{
|
| 294 |
+
"epoch": 0.8633714655730628,
|
| 295 |
+
"grad_norm": 0.255859375,
|
| 296 |
+
"learning_rate": 9.929889669007022e-05,
|
| 297 |
+
"loss": 2.3575,
|
| 298 |
+
"step": 1000
|
| 299 |
+
},
|
| 300 |
+
{
|
| 301 |
+
"epoch": 0.8633714655730628,
|
| 302 |
+
"eval_loss": 2.429636240005493,
|
| 303 |
+
"eval_runtime": 118.4486,
|
| 304 |
+
"eval_samples_per_second": 4.221,
|
| 305 |
+
"eval_steps_per_second": 4.221,
|
| 306 |
+
"step": 1000
|
| 307 |
+
},
|
| 308 |
+
{
|
| 309 |
+
"epoch": 0.8849557522123894,
|
| 310 |
+
"grad_norm": 0.197265625,
|
| 311 |
+
"learning_rate": 9.927382146439318e-05,
|
| 312 |
+
"loss": 2.3569,
|
| 313 |
+
"step": 1025
|
| 314 |
+
},
|
| 315 |
+
{
|
| 316 |
+
"epoch": 0.906540038851716,
|
| 317 |
+
"grad_norm": 0.142578125,
|
| 318 |
+
"learning_rate": 9.924874623871615e-05,
|
| 319 |
+
"loss": 2.4218,
|
| 320 |
+
"step": 1050
|
| 321 |
+
},
|
| 322 |
+
{
|
| 323 |
+
"epoch": 0.9281243254910425,
|
| 324 |
+
"grad_norm": 0.2373046875,
|
| 325 |
+
"learning_rate": 9.922367101303913e-05,
|
| 326 |
+
"loss": 2.4717,
|
| 327 |
+
"step": 1075
|
| 328 |
+
},
|
| 329 |
+
{
|
| 330 |
+
"epoch": 0.9497086121303691,
|
| 331 |
+
"grad_norm": 0.162109375,
|
| 332 |
+
"learning_rate": 9.91985957873621e-05,
|
| 333 |
+
"loss": 2.3969,
|
| 334 |
+
"step": 1100
|
| 335 |
+
},
|
| 336 |
+
{
|
| 337 |
+
"epoch": 0.9712928987696957,
|
| 338 |
+
"grad_norm": 0.171875,
|
| 339 |
+
"learning_rate": 9.917352056168506e-05,
|
| 340 |
+
"loss": 2.462,
|
| 341 |
+
"step": 1125
|
| 342 |
+
},
|
| 343 |
+
{
|
| 344 |
+
"epoch": 0.9928771854090223,
|
| 345 |
+
"grad_norm": 0.177734375,
|
| 346 |
+
"learning_rate": 9.914844533600803e-05,
|
| 347 |
+
"loss": 2.4901,
|
| 348 |
+
"step": 1150
|
| 349 |
+
},
|
| 350 |
+
{
|
| 351 |
+
"epoch": 1.013813943449169,
|
| 352 |
+
"grad_norm": 0.1943359375,
|
| 353 |
+
"learning_rate": 9.912337011033099e-05,
|
| 354 |
+
"loss": 2.2822,
|
| 355 |
+
"step": 1175
|
| 356 |
+
},
|
| 357 |
+
{
|
| 358 |
+
"epoch": 1.0353982300884956,
|
| 359 |
+
"grad_norm": 0.2001953125,
|
| 360 |
+
"learning_rate": 9.909829488465396e-05,
|
| 361 |
+
"loss": 2.3955,
|
| 362 |
+
"step": 1200
|
| 363 |
+
},
|
| 364 |
+
{
|
| 365 |
+
"epoch": 1.0569825167278222,
|
| 366 |
+
"grad_norm": 0.169921875,
|
| 367 |
+
"learning_rate": 9.907321965897694e-05,
|
| 368 |
+
"loss": 2.431,
|
| 369 |
+
"step": 1225
|
| 370 |
+
},
|
| 371 |
+
{
|
| 372 |
+
"epoch": 1.0785668033671487,
|
| 373 |
+
"grad_norm": 0.26171875,
|
| 374 |
+
"learning_rate": 9.90481444332999e-05,
|
| 375 |
+
"loss": 2.3124,
|
| 376 |
+
"step": 1250
|
| 377 |
+
},
|
| 378 |
+
{
|
| 379 |
+
"epoch": 1.1001510900064753,
|
| 380 |
+
"grad_norm": 0.201171875,
|
| 381 |
+
"learning_rate": 9.902306920762287e-05,
|
| 382 |
+
"loss": 2.3362,
|
| 383 |
+
"step": 1275
|
| 384 |
+
},
|
| 385 |
+
{
|
| 386 |
+
"epoch": 1.1217353766458018,
|
| 387 |
+
"grad_norm": 0.45703125,
|
| 388 |
+
"learning_rate": 9.899799398194585e-05,
|
| 389 |
+
"loss": 2.2931,
|
| 390 |
+
"step": 1300
|
| 391 |
+
},
|
| 392 |
+
{
|
| 393 |
+
"epoch": 1.1433196632851284,
|
| 394 |
+
"grad_norm": 1.1640625,
|
| 395 |
+
"learning_rate": 9.89729187562688e-05,
|
| 396 |
+
"loss": 2.0676,
|
| 397 |
+
"step": 1325
|
| 398 |
+
},
|
| 399 |
+
{
|
| 400 |
+
"epoch": 1.164903949924455,
|
| 401 |
+
"grad_norm": 0.283203125,
|
| 402 |
+
"learning_rate": 9.894784353059177e-05,
|
| 403 |
+
"loss": 1.5906,
|
| 404 |
+
"step": 1350
|
| 405 |
+
},
|
| 406 |
+
{
|
| 407 |
+
"epoch": 1.1864882365637817,
|
| 408 |
+
"grad_norm": 0.291015625,
|
| 409 |
+
"learning_rate": 9.892276830491475e-05,
|
| 410 |
+
"loss": 1.5273,
|
| 411 |
+
"step": 1375
|
| 412 |
+
},
|
| 413 |
+
{
|
| 414 |
+
"epoch": 1.2080725232031082,
|
| 415 |
+
"grad_norm": 0.265625,
|
| 416 |
+
"learning_rate": 9.889769307923772e-05,
|
| 417 |
+
"loss": 1.3603,
|
| 418 |
+
"step": 1400
|
| 419 |
+
},
|
| 420 |
+
{
|
| 421 |
+
"epoch": 1.2296568098424348,
|
| 422 |
+
"grad_norm": 0.37109375,
|
| 423 |
+
"learning_rate": 9.887261785356068e-05,
|
| 424 |
+
"loss": 1.4502,
|
| 425 |
+
"step": 1425
|
| 426 |
+
},
|
| 427 |
+
{
|
| 428 |
+
"epoch": 1.2512410964817613,
|
| 429 |
+
"grad_norm": 0.36328125,
|
| 430 |
+
"learning_rate": 9.884754262788366e-05,
|
| 431 |
+
"loss": 1.3359,
|
| 432 |
+
"step": 1450
|
| 433 |
+
},
|
| 434 |
+
{
|
| 435 |
+
"epoch": 1.2728253831210878,
|
| 436 |
+
"grad_norm": 0.2734375,
|
| 437 |
+
"learning_rate": 9.882246740220662e-05,
|
| 438 |
+
"loss": 1.1317,
|
| 439 |
+
"step": 1475
|
| 440 |
+
},
|
| 441 |
+
{
|
| 442 |
+
"epoch": 1.2944096697604144,
|
| 443 |
+
"grad_norm": 0.26171875,
|
| 444 |
+
"learning_rate": 9.87973921765296e-05,
|
| 445 |
+
"loss": 1.4062,
|
| 446 |
+
"step": 1500
|
| 447 |
+
},
|
| 448 |
+
{
|
| 449 |
+
"epoch": 1.2944096697604144,
|
| 450 |
+
"eval_loss": 1.3137363195419312,
|
| 451 |
+
"eval_runtime": 118.9724,
|
| 452 |
+
"eval_samples_per_second": 4.203,
|
| 453 |
+
"eval_steps_per_second": 4.203,
|
| 454 |
+
"step": 1500
|
| 455 |
+
},
|
| 456 |
+
{
|
| 457 |
+
"epoch": 1.315993956399741,
|
| 458 |
+
"grad_norm": 0.2470703125,
|
| 459 |
+
"learning_rate": 9.877231695085256e-05,
|
| 460 |
+
"loss": 1.401,
|
| 461 |
+
"step": 1525
|
| 462 |
+
},
|
| 463 |
+
{
|
| 464 |
+
"epoch": 1.3375782430390677,
|
| 465 |
+
"grad_norm": 0.365234375,
|
| 466 |
+
"learning_rate": 9.874724172517553e-05,
|
| 467 |
+
"loss": 1.2082,
|
| 468 |
+
"step": 1550
|
| 469 |
+
},
|
| 470 |
+
{
|
| 471 |
+
"epoch": 1.359162529678394,
|
| 472 |
+
"grad_norm": 0.283203125,
|
| 473 |
+
"learning_rate": 9.872216649949851e-05,
|
| 474 |
+
"loss": 1.2937,
|
| 475 |
+
"step": 1575
|
| 476 |
+
},
|
| 477 |
+
{
|
| 478 |
+
"epoch": 1.3807468163177208,
|
| 479 |
+
"grad_norm": 0.240234375,
|
| 480 |
+
"learning_rate": 9.869709127382148e-05,
|
| 481 |
+
"loss": 1.3758,
|
| 482 |
+
"step": 1600
|
| 483 |
+
},
|
| 484 |
+
{
|
| 485 |
+
"epoch": 1.4023311029570473,
|
| 486 |
+
"grad_norm": 0.2490234375,
|
| 487 |
+
"learning_rate": 9.867201604814443e-05,
|
| 488 |
+
"loss": 1.2571,
|
| 489 |
+
"step": 1625
|
| 490 |
+
},
|
| 491 |
+
{
|
| 492 |
+
"epoch": 1.4239153895963739,
|
| 493 |
+
"grad_norm": 0.2080078125,
|
| 494 |
+
"learning_rate": 9.864694082246741e-05,
|
| 495 |
+
"loss": 1.3575,
|
| 496 |
+
"step": 1650
|
| 497 |
+
},
|
| 498 |
+
{
|
| 499 |
+
"epoch": 1.4454996762357004,
|
| 500 |
+
"grad_norm": 0.2412109375,
|
| 501 |
+
"learning_rate": 9.862186559679037e-05,
|
| 502 |
+
"loss": 1.1738,
|
| 503 |
+
"step": 1675
|
| 504 |
+
},
|
| 505 |
+
{
|
| 506 |
+
"epoch": 1.467083962875027,
|
| 507 |
+
"grad_norm": 0.232421875,
|
| 508 |
+
"learning_rate": 9.859679037111334e-05,
|
| 509 |
+
"loss": 1.3577,
|
| 510 |
+
"step": 1700
|
| 511 |
+
},
|
| 512 |
+
{
|
| 513 |
+
"epoch": 1.4886682495143535,
|
| 514 |
+
"grad_norm": 0.2255859375,
|
| 515 |
+
"learning_rate": 9.857171514543632e-05,
|
| 516 |
+
"loss": 1.3506,
|
| 517 |
+
"step": 1725
|
| 518 |
+
},
|
| 519 |
+
{
|
| 520 |
+
"epoch": 1.51025253615368,
|
| 521 |
+
"grad_norm": 0.27734375,
|
| 522 |
+
"learning_rate": 9.854663991975929e-05,
|
| 523 |
+
"loss": 1.3018,
|
| 524 |
+
"step": 1750
|
| 525 |
+
},
|
| 526 |
+
{
|
| 527 |
+
"epoch": 1.5318368227930068,
|
| 528 |
+
"grad_norm": 0.271484375,
|
| 529 |
+
"learning_rate": 9.852156469408225e-05,
|
| 530 |
+
"loss": 1.2907,
|
| 531 |
+
"step": 1775
|
| 532 |
+
},
|
| 533 |
+
{
|
| 534 |
+
"epoch": 1.5534211094323331,
|
| 535 |
+
"grad_norm": 0.2255859375,
|
| 536 |
+
"learning_rate": 9.849648946840522e-05,
|
| 537 |
+
"loss": 1.2517,
|
| 538 |
+
"step": 1800
|
| 539 |
+
},
|
| 540 |
+
{
|
| 541 |
+
"epoch": 1.57500539607166,
|
| 542 |
+
"grad_norm": 0.2138671875,
|
| 543 |
+
"learning_rate": 9.847141424272819e-05,
|
| 544 |
+
"loss": 1.2246,
|
| 545 |
+
"step": 1825
|
| 546 |
+
},
|
| 547 |
+
{
|
| 548 |
+
"epoch": 1.5965896827109864,
|
| 549 |
+
"grad_norm": 0.255859375,
|
| 550 |
+
"learning_rate": 9.844633901705115e-05,
|
| 551 |
+
"loss": 1.3008,
|
| 552 |
+
"step": 1850
|
| 553 |
+
},
|
| 554 |
+
{
|
| 555 |
+
"epoch": 1.618173969350313,
|
| 556 |
+
"grad_norm": 0.2158203125,
|
| 557 |
+
"learning_rate": 9.842126379137413e-05,
|
| 558 |
+
"loss": 1.1651,
|
| 559 |
+
"step": 1875
|
| 560 |
+
},
|
| 561 |
+
{
|
| 562 |
+
"epoch": 1.6397582559896395,
|
| 563 |
+
"grad_norm": 0.212890625,
|
| 564 |
+
"learning_rate": 9.83961885656971e-05,
|
| 565 |
+
"loss": 1.1388,
|
| 566 |
+
"step": 1900
|
| 567 |
+
},
|
| 568 |
+
{
|
| 569 |
+
"epoch": 1.661342542628966,
|
| 570 |
+
"grad_norm": 0.2177734375,
|
| 571 |
+
"learning_rate": 9.837111334002006e-05,
|
| 572 |
+
"loss": 1.0537,
|
| 573 |
+
"step": 1925
|
| 574 |
+
},
|
| 575 |
+
{
|
| 576 |
+
"epoch": 1.6829268292682928,
|
| 577 |
+
"grad_norm": 0.2099609375,
|
| 578 |
+
"learning_rate": 9.834603811434303e-05,
|
| 579 |
+
"loss": 1.2838,
|
| 580 |
+
"step": 1950
|
| 581 |
+
},
|
| 582 |
+
{
|
| 583 |
+
"epoch": 1.7045111159076192,
|
| 584 |
+
"grad_norm": 0.1943359375,
|
| 585 |
+
"learning_rate": 9.8320962888666e-05,
|
| 586 |
+
"loss": 1.1597,
|
| 587 |
+
"step": 1975
|
| 588 |
+
},
|
| 589 |
+
{
|
| 590 |
+
"epoch": 1.726095402546946,
|
| 591 |
+
"grad_norm": 0.23828125,
|
| 592 |
+
"learning_rate": 9.829588766298898e-05,
|
| 593 |
+
"loss": 1.1234,
|
| 594 |
+
"step": 2000
|
| 595 |
+
},
|
| 596 |
+
{
|
| 597 |
+
"epoch": 1.726095402546946,
|
| 598 |
+
"eval_loss": 1.2347378730773926,
|
| 599 |
+
"eval_runtime": 118.1524,
|
| 600 |
+
"eval_samples_per_second": 4.232,
|
| 601 |
+
"eval_steps_per_second": 4.232,
|
| 602 |
+
"step": 2000
|
| 603 |
+
},
|
| 604 |
+
{
|
| 605 |
+
"epoch": 1.7476796891862723,
|
| 606 |
+
"grad_norm": 0.232421875,
|
| 607 |
+
"learning_rate": 9.827081243731194e-05,
|
| 608 |
+
"loss": 1.1737,
|
| 609 |
+
"step": 2025
|
| 610 |
+
},
|
| 611 |
+
{
|
| 612 |
+
"epoch": 1.769263975825599,
|
| 613 |
+
"grad_norm": 0.1767578125,
|
| 614 |
+
"learning_rate": 9.824573721163491e-05,
|
| 615 |
+
"loss": 1.1409,
|
| 616 |
+
"step": 2050
|
| 617 |
+
},
|
| 618 |
+
{
|
| 619 |
+
"epoch": 1.7908482624649256,
|
| 620 |
+
"grad_norm": 0.1962890625,
|
| 621 |
+
"learning_rate": 9.822066198595788e-05,
|
| 622 |
+
"loss": 1.3478,
|
| 623 |
+
"step": 2075
|
| 624 |
+
},
|
| 625 |
+
{
|
| 626 |
+
"epoch": 1.812432549104252,
|
| 627 |
+
"grad_norm": 0.283203125,
|
| 628 |
+
"learning_rate": 9.819558676028084e-05,
|
| 629 |
+
"loss": 1.226,
|
| 630 |
+
"step": 2100
|
| 631 |
+
},
|
| 632 |
+
{
|
| 633 |
+
"epoch": 1.8340168357435787,
|
| 634 |
+
"grad_norm": 0.2119140625,
|
| 635 |
+
"learning_rate": 9.817051153460381e-05,
|
| 636 |
+
"loss": 1.1638,
|
| 637 |
+
"step": 2125
|
| 638 |
+
},
|
| 639 |
+
{
|
| 640 |
+
"epoch": 1.8556011223829052,
|
| 641 |
+
"grad_norm": 0.271484375,
|
| 642 |
+
"learning_rate": 9.814543630892679e-05,
|
| 643 |
+
"loss": 1.2201,
|
| 644 |
+
"step": 2150
|
| 645 |
+
},
|
| 646 |
+
{
|
| 647 |
+
"epoch": 1.877185409022232,
|
| 648 |
+
"grad_norm": 0.1884765625,
|
| 649 |
+
"learning_rate": 9.812036108324976e-05,
|
| 650 |
+
"loss": 1.2503,
|
| 651 |
+
"step": 2175
|
| 652 |
+
},
|
| 653 |
+
{
|
| 654 |
+
"epoch": 1.8987696956615583,
|
| 655 |
+
"grad_norm": 0.220703125,
|
| 656 |
+
"learning_rate": 9.809528585757272e-05,
|
| 657 |
+
"loss": 1.4087,
|
| 658 |
+
"step": 2200
|
| 659 |
+
},
|
| 660 |
+
{
|
| 661 |
+
"epoch": 1.920353982300885,
|
| 662 |
+
"grad_norm": 0.22265625,
|
| 663 |
+
"learning_rate": 9.807021063189569e-05,
|
| 664 |
+
"loss": 1.1294,
|
| 665 |
+
"step": 2225
|
| 666 |
+
},
|
| 667 |
+
{
|
| 668 |
+
"epoch": 1.9419382689402114,
|
| 669 |
+
"grad_norm": 0.220703125,
|
| 670 |
+
"learning_rate": 9.804513540621865e-05,
|
| 671 |
+
"loss": 1.2414,
|
| 672 |
+
"step": 2250
|
| 673 |
+
},
|
| 674 |
+
{
|
| 675 |
+
"epoch": 1.9635225555795381,
|
| 676 |
+
"grad_norm": 0.2578125,
|
| 677 |
+
"learning_rate": 9.802006018054163e-05,
|
| 678 |
+
"loss": 1.151,
|
| 679 |
+
"step": 2275
|
| 680 |
+
},
|
| 681 |
+
{
|
| 682 |
+
"epoch": 1.9851068422188647,
|
| 683 |
+
"grad_norm": 0.2119140625,
|
| 684 |
+
"learning_rate": 9.79949849548646e-05,
|
| 685 |
+
"loss": 1.1744,
|
| 686 |
+
"step": 2300
|
| 687 |
+
},
|
| 688 |
+
{
|
| 689 |
+
"epoch": 2.0060436002590114,
|
| 690 |
+
"grad_norm": 0.2119140625,
|
| 691 |
+
"learning_rate": 9.796990972918757e-05,
|
| 692 |
+
"loss": 1.1466,
|
| 693 |
+
"step": 2325
|
| 694 |
+
},
|
| 695 |
+
{
|
| 696 |
+
"epoch": 2.027627886898338,
|
| 697 |
+
"grad_norm": 0.2578125,
|
| 698 |
+
"learning_rate": 9.794483450351055e-05,
|
| 699 |
+
"loss": 1.285,
|
| 700 |
+
"step": 2350
|
| 701 |
+
},
|
| 702 |
+
{
|
| 703 |
+
"epoch": 2.0492121735376645,
|
| 704 |
+
"grad_norm": 0.240234375,
|
| 705 |
+
"learning_rate": 9.79197592778335e-05,
|
| 706 |
+
"loss": 1.2525,
|
| 707 |
+
"step": 2375
|
| 708 |
+
},
|
| 709 |
+
{
|
| 710 |
+
"epoch": 2.0707964601769913,
|
| 711 |
+
"grad_norm": 0.1806640625,
|
| 712 |
+
"learning_rate": 9.789468405215647e-05,
|
| 713 |
+
"loss": 1.1043,
|
| 714 |
+
"step": 2400
|
| 715 |
+
},
|
| 716 |
+
{
|
| 717 |
+
"epoch": 2.0923807468163176,
|
| 718 |
+
"grad_norm": 0.2490234375,
|
| 719 |
+
"learning_rate": 9.786960882647945e-05,
|
| 720 |
+
"loss": 1.151,
|
| 721 |
+
"step": 2425
|
| 722 |
+
},
|
| 723 |
+
{
|
| 724 |
+
"epoch": 2.1139650334556443,
|
| 725 |
+
"grad_norm": 0.1943359375,
|
| 726 |
+
"learning_rate": 9.784453360080241e-05,
|
| 727 |
+
"loss": 1.2291,
|
| 728 |
+
"step": 2450
|
| 729 |
+
},
|
| 730 |
+
{
|
| 731 |
+
"epoch": 2.1355493200949707,
|
| 732 |
+
"grad_norm": 0.2392578125,
|
| 733 |
+
"learning_rate": 9.781945837512538e-05,
|
| 734 |
+
"loss": 1.201,
|
| 735 |
+
"step": 2475
|
| 736 |
+
},
|
| 737 |
+
{
|
| 738 |
+
"epoch": 2.1571336067342974,
|
| 739 |
+
"grad_norm": 0.259765625,
|
| 740 |
+
"learning_rate": 9.779438314944836e-05,
|
| 741 |
+
"loss": 1.1237,
|
| 742 |
+
"step": 2500
|
| 743 |
+
},
|
| 744 |
+
{
|
| 745 |
+
"epoch": 2.1571336067342974,
|
| 746 |
+
"eval_loss": 1.2181166410446167,
|
| 747 |
+
"eval_runtime": 116.187,
|
| 748 |
+
"eval_samples_per_second": 4.303,
|
| 749 |
+
"eval_steps_per_second": 4.303,
|
| 750 |
+
"step": 2500
|
| 751 |
+
},
|
| 752 |
+
{
|
| 753 |
+
"epoch": 2.178717893373624,
|
| 754 |
+
"grad_norm": 0.2138671875,
|
| 755 |
+
"learning_rate": 9.776930792377131e-05,
|
| 756 |
+
"loss": 1.1879,
|
| 757 |
+
"step": 2525
|
| 758 |
+
},
|
| 759 |
+
{
|
| 760 |
+
"epoch": 2.2003021800129505,
|
| 761 |
+
"grad_norm": 0.2158203125,
|
| 762 |
+
"learning_rate": 9.774423269809428e-05,
|
| 763 |
+
"loss": 1.2643,
|
| 764 |
+
"step": 2550
|
| 765 |
+
},
|
| 766 |
+
{
|
| 767 |
+
"epoch": 2.2218864666522773,
|
| 768 |
+
"grad_norm": 0.1796875,
|
| 769 |
+
"learning_rate": 9.771915747241726e-05,
|
| 770 |
+
"loss": 1.1984,
|
| 771 |
+
"step": 2575
|
| 772 |
+
},
|
| 773 |
+
{
|
| 774 |
+
"epoch": 2.2434707532916036,
|
| 775 |
+
"grad_norm": 0.279296875,
|
| 776 |
+
"learning_rate": 9.769408224674022e-05,
|
| 777 |
+
"loss": 1.2307,
|
| 778 |
+
"step": 2600
|
| 779 |
+
},
|
| 780 |
+
{
|
| 781 |
+
"epoch": 2.2650550399309304,
|
| 782 |
+
"grad_norm": 0.19921875,
|
| 783 |
+
"learning_rate": 9.766900702106319e-05,
|
| 784 |
+
"loss": 1.2687,
|
| 785 |
+
"step": 2625
|
| 786 |
+
},
|
| 787 |
+
{
|
| 788 |
+
"epoch": 2.2866393265702567,
|
| 789 |
+
"grad_norm": 0.232421875,
|
| 790 |
+
"learning_rate": 9.764393179538617e-05,
|
| 791 |
+
"loss": 1.2413,
|
| 792 |
+
"step": 2650
|
| 793 |
+
},
|
| 794 |
+
{
|
| 795 |
+
"epoch": 2.3082236132095835,
|
| 796 |
+
"grad_norm": 0.21875,
|
| 797 |
+
"learning_rate": 9.761885656970912e-05,
|
| 798 |
+
"loss": 1.161,
|
| 799 |
+
"step": 2675
|
| 800 |
+
},
|
| 801 |
+
{
|
| 802 |
+
"epoch": 2.32980789984891,
|
| 803 |
+
"grad_norm": 0.1875,
|
| 804 |
+
"learning_rate": 9.75937813440321e-05,
|
| 805 |
+
"loss": 1.3196,
|
| 806 |
+
"step": 2700
|
| 807 |
+
},
|
| 808 |
+
{
|
| 809 |
+
"epoch": 2.3513921864882366,
|
| 810 |
+
"grad_norm": 0.20703125,
|
| 811 |
+
"learning_rate": 9.756870611835507e-05,
|
| 812 |
+
"loss": 1.1376,
|
| 813 |
+
"step": 2725
|
| 814 |
+
},
|
| 815 |
+
{
|
| 816 |
+
"epoch": 2.3729764731275633,
|
| 817 |
+
"grad_norm": 0.29296875,
|
| 818 |
+
"learning_rate": 9.754363089267804e-05,
|
| 819 |
+
"loss": 1.2897,
|
| 820 |
+
"step": 2750
|
| 821 |
+
},
|
| 822 |
+
{
|
| 823 |
+
"epoch": 2.3945607597668896,
|
| 824 |
+
"grad_norm": 0.201171875,
|
| 825 |
+
"learning_rate": 9.751855566700102e-05,
|
| 826 |
+
"loss": 1.1078,
|
| 827 |
+
"step": 2775
|
| 828 |
+
},
|
| 829 |
+
{
|
| 830 |
+
"epoch": 2.4161450464062164,
|
| 831 |
+
"grad_norm": 0.173828125,
|
| 832 |
+
"learning_rate": 9.749348044132398e-05,
|
| 833 |
+
"loss": 1.1484,
|
| 834 |
+
"step": 2800
|
| 835 |
+
},
|
| 836 |
+
{
|
| 837 |
+
"epoch": 2.4377293330455427,
|
| 838 |
+
"grad_norm": 0.220703125,
|
| 839 |
+
"learning_rate": 9.746840521564694e-05,
|
| 840 |
+
"loss": 1.154,
|
| 841 |
+
"step": 2825
|
| 842 |
+
},
|
| 843 |
+
{
|
| 844 |
+
"epoch": 2.4593136196848695,
|
| 845 |
+
"grad_norm": 0.20703125,
|
| 846 |
+
"learning_rate": 9.744332998996991e-05,
|
| 847 |
+
"loss": 1.2163,
|
| 848 |
+
"step": 2850
|
| 849 |
+
},
|
| 850 |
+
{
|
| 851 |
+
"epoch": 2.480897906324196,
|
| 852 |
+
"grad_norm": 0.1904296875,
|
| 853 |
+
"learning_rate": 9.741825476429288e-05,
|
| 854 |
+
"loss": 1.2316,
|
| 855 |
+
"step": 2875
|
| 856 |
+
},
|
| 857 |
+
{
|
| 858 |
+
"epoch": 2.5024821929635226,
|
| 859 |
+
"grad_norm": 0.1845703125,
|
| 860 |
+
"learning_rate": 9.739317953861585e-05,
|
| 861 |
+
"loss": 1.1632,
|
| 862 |
+
"step": 2900
|
| 863 |
+
},
|
| 864 |
+
{
|
| 865 |
+
"epoch": 2.5240664796028494,
|
| 866 |
+
"grad_norm": 0.2119140625,
|
| 867 |
+
"learning_rate": 9.736810431293883e-05,
|
| 868 |
+
"loss": 1.239,
|
| 869 |
+
"step": 2925
|
| 870 |
+
},
|
| 871 |
+
{
|
| 872 |
+
"epoch": 2.5456507662421757,
|
| 873 |
+
"grad_norm": 0.2216796875,
|
| 874 |
+
"learning_rate": 9.73430290872618e-05,
|
| 875 |
+
"loss": 1.2671,
|
| 876 |
+
"step": 2950
|
| 877 |
+
},
|
| 878 |
+
{
|
| 879 |
+
"epoch": 2.567235052881502,
|
| 880 |
+
"grad_norm": 0.1865234375,
|
| 881 |
+
"learning_rate": 9.731795386158476e-05,
|
| 882 |
+
"loss": 1.2046,
|
| 883 |
+
"step": 2975
|
| 884 |
+
},
|
| 885 |
+
{
|
| 886 |
+
"epoch": 2.5888193395208288,
|
| 887 |
+
"grad_norm": 0.1826171875,
|
| 888 |
+
"learning_rate": 9.729287863590773e-05,
|
| 889 |
+
"loss": 1.108,
|
| 890 |
+
"step": 3000
|
| 891 |
+
},
|
| 892 |
+
{
|
| 893 |
+
"epoch": 2.5888193395208288,
|
| 894 |
+
"eval_loss": 1.2088854312896729,
|
| 895 |
+
"eval_runtime": 118.1325,
|
| 896 |
+
"eval_samples_per_second": 4.233,
|
| 897 |
+
"eval_steps_per_second": 4.233,
|
| 898 |
+
"step": 3000
|
| 899 |
+
},
|
| 900 |
+
{
|
| 901 |
+
"epoch": 2.6104036261601555,
|
| 902 |
+
"grad_norm": 0.1865234375,
|
| 903 |
+
"learning_rate": 9.726780341023069e-05,
|
| 904 |
+
"loss": 1.3243,
|
| 905 |
+
"step": 3025
|
| 906 |
+
},
|
| 907 |
+
{
|
| 908 |
+
"epoch": 2.631987912799482,
|
| 909 |
+
"grad_norm": 0.1865234375,
|
| 910 |
+
"learning_rate": 9.724272818455367e-05,
|
| 911 |
+
"loss": 1.1085,
|
| 912 |
+
"step": 3050
|
| 913 |
+
},
|
| 914 |
+
{
|
| 915 |
+
"epoch": 2.6535721994388086,
|
| 916 |
+
"grad_norm": 0.208984375,
|
| 917 |
+
"learning_rate": 9.721765295887664e-05,
|
| 918 |
+
"loss": 1.1862,
|
| 919 |
+
"step": 3075
|
| 920 |
+
},
|
| 921 |
+
{
|
| 922 |
+
"epoch": 2.6751564860781354,
|
| 923 |
+
"grad_norm": 0.25390625,
|
| 924 |
+
"learning_rate": 9.71925777331996e-05,
|
| 925 |
+
"loss": 1.1625,
|
| 926 |
+
"step": 3100
|
| 927 |
+
},
|
| 928 |
+
{
|
| 929 |
+
"epoch": 2.6967407727174617,
|
| 930 |
+
"grad_norm": 0.177734375,
|
| 931 |
+
"learning_rate": 9.716750250752257e-05,
|
| 932 |
+
"loss": 1.0797,
|
| 933 |
+
"step": 3125
|
| 934 |
+
},
|
| 935 |
+
{
|
| 936 |
+
"epoch": 2.718325059356788,
|
| 937 |
+
"grad_norm": 0.2392578125,
|
| 938 |
+
"learning_rate": 9.714242728184554e-05,
|
| 939 |
+
"loss": 1.0413,
|
| 940 |
+
"step": 3150
|
| 941 |
+
},
|
| 942 |
+
{
|
| 943 |
+
"epoch": 2.739909345996115,
|
| 944 |
+
"grad_norm": 0.1982421875,
|
| 945 |
+
"learning_rate": 9.71173520561685e-05,
|
| 946 |
+
"loss": 1.1582,
|
| 947 |
+
"step": 3175
|
| 948 |
+
},
|
| 949 |
+
{
|
| 950 |
+
"epoch": 2.7614936326354416,
|
| 951 |
+
"grad_norm": 0.232421875,
|
| 952 |
+
"learning_rate": 9.709227683049148e-05,
|
| 953 |
+
"loss": 1.2064,
|
| 954 |
+
"step": 3200
|
| 955 |
+
},
|
| 956 |
+
{
|
| 957 |
+
"epoch": 2.783077919274768,
|
| 958 |
+
"grad_norm": 0.333984375,
|
| 959 |
+
"learning_rate": 9.706720160481445e-05,
|
| 960 |
+
"loss": 1.1679,
|
| 961 |
+
"step": 3225
|
| 962 |
+
},
|
| 963 |
+
{
|
| 964 |
+
"epoch": 2.8046622059140947,
|
| 965 |
+
"grad_norm": 0.2041015625,
|
| 966 |
+
"learning_rate": 9.704212637913742e-05,
|
| 967 |
+
"loss": 1.1783,
|
| 968 |
+
"step": 3250
|
| 969 |
+
},
|
| 970 |
+
{
|
| 971 |
+
"epoch": 2.826246492553421,
|
| 972 |
+
"grad_norm": 0.2216796875,
|
| 973 |
+
"learning_rate": 9.701705115346038e-05,
|
| 974 |
+
"loss": 1.2746,
|
| 975 |
+
"step": 3275
|
| 976 |
+
},
|
| 977 |
+
{
|
| 978 |
+
"epoch": 2.8478307791927477,
|
| 979 |
+
"grad_norm": 0.1806640625,
|
| 980 |
+
"learning_rate": 9.699197592778335e-05,
|
| 981 |
+
"loss": 1.0532,
|
| 982 |
+
"step": 3300
|
| 983 |
+
},
|
| 984 |
+
{
|
| 985 |
+
"epoch": 2.869415065832074,
|
| 986 |
+
"grad_norm": 0.1943359375,
|
| 987 |
+
"learning_rate": 9.696690070210632e-05,
|
| 988 |
+
"loss": 0.9242,
|
| 989 |
+
"step": 3325
|
| 990 |
+
},
|
| 991 |
+
{
|
| 992 |
+
"epoch": 2.890999352471401,
|
| 993 |
+
"grad_norm": 0.228515625,
|
| 994 |
+
"learning_rate": 9.69418254764293e-05,
|
| 995 |
+
"loss": 1.244,
|
| 996 |
+
"step": 3350
|
| 997 |
+
},
|
| 998 |
+
{
|
| 999 |
+
"epoch": 2.9125836391107276,
|
| 1000 |
+
"grad_norm": 0.2421875,
|
| 1001 |
+
"learning_rate": 9.691675025075226e-05,
|
| 1002 |
+
"loss": 1.1166,
|
| 1003 |
+
"step": 3375
|
| 1004 |
+
},
|
| 1005 |
+
{
|
| 1006 |
+
"epoch": 2.934167925750054,
|
| 1007 |
+
"grad_norm": 0.171875,
|
| 1008 |
+
"learning_rate": 9.689167502507523e-05,
|
| 1009 |
+
"loss": 1.1511,
|
| 1010 |
+
"step": 3400
|
| 1011 |
+
},
|
| 1012 |
+
{
|
| 1013 |
+
"epoch": 2.9557522123893807,
|
| 1014 |
+
"grad_norm": 0.208984375,
|
| 1015 |
+
"learning_rate": 9.68665997993982e-05,
|
| 1016 |
+
"loss": 1.2977,
|
| 1017 |
+
"step": 3425
|
| 1018 |
+
},
|
| 1019 |
+
{
|
| 1020 |
+
"epoch": 2.977336499028707,
|
| 1021 |
+
"grad_norm": 0.201171875,
|
| 1022 |
+
"learning_rate": 9.684152457372116e-05,
|
| 1023 |
+
"loss": 1.2038,
|
| 1024 |
+
"step": 3450
|
| 1025 |
+
},
|
| 1026 |
+
{
|
| 1027 |
+
"epoch": 2.9989207856680338,
|
| 1028 |
+
"grad_norm": 0.1884765625,
|
| 1029 |
+
"learning_rate": 9.681644934804414e-05,
|
| 1030 |
+
"loss": 1.3379,
|
| 1031 |
+
"step": 3475
|
| 1032 |
+
},
|
| 1033 |
+
{
|
| 1034 |
+
"epoch": 3.0198575437081803,
|
| 1035 |
+
"grad_norm": 0.232421875,
|
| 1036 |
+
"learning_rate": 9.679137412236711e-05,
|
| 1037 |
+
"loss": 1.0725,
|
| 1038 |
+
"step": 3500
|
| 1039 |
+
},
|
| 1040 |
+
{
|
| 1041 |
+
"epoch": 3.0198575437081803,
|
| 1042 |
+
"eval_loss": 1.202246069908142,
|
| 1043 |
+
"eval_runtime": 117.3316,
|
| 1044 |
+
"eval_samples_per_second": 4.261,
|
| 1045 |
+
"eval_steps_per_second": 4.261,
|
| 1046 |
+
"step": 3500
|
| 1047 |
+
},
|
| 1048 |
+
{
|
| 1049 |
+
"epoch": 3.041441830347507,
|
| 1050 |
+
"grad_norm": 0.25390625,
|
| 1051 |
+
"learning_rate": 9.676629889669007e-05,
|
| 1052 |
+
"loss": 1.1343,
|
| 1053 |
+
"step": 3525
|
| 1054 |
+
},
|
| 1055 |
+
{
|
| 1056 |
+
"epoch": 3.0630261169868334,
|
| 1057 |
+
"grad_norm": 0.19140625,
|
| 1058 |
+
"learning_rate": 9.674122367101305e-05,
|
| 1059 |
+
"loss": 1.2788,
|
| 1060 |
+
"step": 3550
|
| 1061 |
+
},
|
| 1062 |
+
{
|
| 1063 |
+
"epoch": 3.08461040362616,
|
| 1064 |
+
"grad_norm": 0.203125,
|
| 1065 |
+
"learning_rate": 9.671614844533601e-05,
|
| 1066 |
+
"loss": 1.2856,
|
| 1067 |
+
"step": 3575
|
| 1068 |
+
},
|
| 1069 |
+
{
|
| 1070 |
+
"epoch": 3.106194690265487,
|
| 1071 |
+
"grad_norm": 0.224609375,
|
| 1072 |
+
"learning_rate": 9.669107321965897e-05,
|
| 1073 |
+
"loss": 1.1778,
|
| 1074 |
+
"step": 3600
|
| 1075 |
+
},
|
| 1076 |
+
{
|
| 1077 |
+
"epoch": 3.127778976904813,
|
| 1078 |
+
"grad_norm": 0.2451171875,
|
| 1079 |
+
"learning_rate": 9.666599799398195e-05,
|
| 1080 |
+
"loss": 1.1496,
|
| 1081 |
+
"step": 3625
|
| 1082 |
+
},
|
| 1083 |
+
{
|
| 1084 |
+
"epoch": 3.14936326354414,
|
| 1085 |
+
"grad_norm": 0.279296875,
|
| 1086 |
+
"learning_rate": 9.664092276830492e-05,
|
| 1087 |
+
"loss": 1.1717,
|
| 1088 |
+
"step": 3650
|
| 1089 |
+
},
|
| 1090 |
+
{
|
| 1091 |
+
"epoch": 3.1709475501834663,
|
| 1092 |
+
"grad_norm": 0.2275390625,
|
| 1093 |
+
"learning_rate": 9.661584754262789e-05,
|
| 1094 |
+
"loss": 1.2103,
|
| 1095 |
+
"step": 3675
|
| 1096 |
+
},
|
| 1097 |
+
{
|
| 1098 |
+
"epoch": 3.192531836822793,
|
| 1099 |
+
"grad_norm": 0.197265625,
|
| 1100 |
+
"learning_rate": 9.659077231695087e-05,
|
| 1101 |
+
"loss": 1.1198,
|
| 1102 |
+
"step": 3700
|
| 1103 |
+
},
|
| 1104 |
+
{
|
| 1105 |
+
"epoch": 3.2141161234621194,
|
| 1106 |
+
"grad_norm": 0.1884765625,
|
| 1107 |
+
"learning_rate": 9.656569709127382e-05,
|
| 1108 |
+
"loss": 1.1266,
|
| 1109 |
+
"step": 3725
|
| 1110 |
+
},
|
| 1111 |
+
{
|
| 1112 |
+
"epoch": 3.235700410101446,
|
| 1113 |
+
"grad_norm": 0.1982421875,
|
| 1114 |
+
"learning_rate": 9.65406218655968e-05,
|
| 1115 |
+
"loss": 1.1171,
|
| 1116 |
+
"step": 3750
|
| 1117 |
+
},
|
| 1118 |
+
{
|
| 1119 |
+
"epoch": 3.257284696740773,
|
| 1120 |
+
"grad_norm": 0.1943359375,
|
| 1121 |
+
"learning_rate": 9.651554663991976e-05,
|
| 1122 |
+
"loss": 1.2812,
|
| 1123 |
+
"step": 3775
|
| 1124 |
+
},
|
| 1125 |
+
{
|
| 1126 |
+
"epoch": 3.2788689833800992,
|
| 1127 |
+
"grad_norm": 0.2451171875,
|
| 1128 |
+
"learning_rate": 9.649047141424273e-05,
|
| 1129 |
+
"loss": 1.0618,
|
| 1130 |
+
"step": 3800
|
| 1131 |
+
},
|
| 1132 |
+
{
|
| 1133 |
+
"epoch": 3.300453270019426,
|
| 1134 |
+
"grad_norm": 0.20703125,
|
| 1135 |
+
"learning_rate": 9.64653961885657e-05,
|
| 1136 |
+
"loss": 1.1916,
|
| 1137 |
+
"step": 3825
|
| 1138 |
+
},
|
| 1139 |
+
{
|
| 1140 |
+
"epoch": 3.3220375566587523,
|
| 1141 |
+
"grad_norm": 0.26171875,
|
| 1142 |
+
"learning_rate": 9.644032096288868e-05,
|
| 1143 |
+
"loss": 1.1048,
|
| 1144 |
+
"step": 3850
|
| 1145 |
+
},
|
| 1146 |
+
{
|
| 1147 |
+
"epoch": 3.343621843298079,
|
| 1148 |
+
"grad_norm": 0.208984375,
|
| 1149 |
+
"learning_rate": 9.641524573721163e-05,
|
| 1150 |
+
"loss": 1.1324,
|
| 1151 |
+
"step": 3875
|
| 1152 |
+
},
|
| 1153 |
+
{
|
| 1154 |
+
"epoch": 3.3652061299374054,
|
| 1155 |
+
"grad_norm": 0.20703125,
|
| 1156 |
+
"learning_rate": 9.639017051153461e-05,
|
| 1157 |
+
"loss": 1.2728,
|
| 1158 |
+
"step": 3900
|
| 1159 |
+
},
|
| 1160 |
+
{
|
| 1161 |
+
"epoch": 3.386790416576732,
|
| 1162 |
+
"grad_norm": 0.1923828125,
|
| 1163 |
+
"learning_rate": 9.636509528585758e-05,
|
| 1164 |
+
"loss": 1.2898,
|
| 1165 |
+
"step": 3925
|
| 1166 |
+
},
|
| 1167 |
+
{
|
| 1168 |
+
"epoch": 3.408374703216059,
|
| 1169 |
+
"grad_norm": 0.232421875,
|
| 1170 |
+
"learning_rate": 9.634002006018054e-05,
|
| 1171 |
+
"loss": 1.1316,
|
| 1172 |
+
"step": 3950
|
| 1173 |
+
},
|
| 1174 |
+
{
|
| 1175 |
+
"epoch": 3.4299589898553853,
|
| 1176 |
+
"grad_norm": 0.197265625,
|
| 1177 |
+
"learning_rate": 9.631494483450352e-05,
|
| 1178 |
+
"loss": 1.2914,
|
| 1179 |
+
"step": 3975
|
| 1180 |
+
},
|
| 1181 |
+
{
|
| 1182 |
+
"epoch": 3.451543276494712,
|
| 1183 |
+
"grad_norm": 0.197265625,
|
| 1184 |
+
"learning_rate": 9.628986960882649e-05,
|
| 1185 |
+
"loss": 1.2218,
|
| 1186 |
+
"step": 4000
|
| 1187 |
+
},
|
| 1188 |
+
{
|
| 1189 |
+
"epoch": 3.451543276494712,
|
| 1190 |
+
"eval_loss": 1.202254295349121,
|
| 1191 |
+
"eval_runtime": 118.0884,
|
| 1192 |
+
"eval_samples_per_second": 4.234,
|
| 1193 |
+
"eval_steps_per_second": 4.234,
|
| 1194 |
+
"step": 4000
|
| 1195 |
+
},
|
| 1196 |
+
{
|
| 1197 |
+
"epoch": 3.4731275631340384,
|
| 1198 |
+
"grad_norm": 0.251953125,
|
| 1199 |
+
"learning_rate": 9.626479438314944e-05,
|
| 1200 |
+
"loss": 1.1132,
|
| 1201 |
+
"step": 4025
|
| 1202 |
+
},
|
| 1203 |
+
{
|
| 1204 |
+
"epoch": 3.494711849773365,
|
| 1205 |
+
"grad_norm": 0.1630859375,
|
| 1206 |
+
"learning_rate": 9.623971915747242e-05,
|
| 1207 |
+
"loss": 1.1148,
|
| 1208 |
+
"step": 4050
|
| 1209 |
+
},
|
| 1210 |
+
{
|
| 1211 |
+
"epoch": 3.5162961364126915,
|
| 1212 |
+
"grad_norm": 0.20703125,
|
| 1213 |
+
"learning_rate": 9.621464393179539e-05,
|
| 1214 |
+
"loss": 1.1045,
|
| 1215 |
+
"step": 4075
|
| 1216 |
+
},
|
| 1217 |
+
{
|
| 1218 |
+
"epoch": 3.537880423052018,
|
| 1219 |
+
"grad_norm": 0.2021484375,
|
| 1220 |
+
"learning_rate": 9.618956870611835e-05,
|
| 1221 |
+
"loss": 1.3047,
|
| 1222 |
+
"step": 4100
|
| 1223 |
+
},
|
| 1224 |
+
{
|
| 1225 |
+
"epoch": 3.5594647096913445,
|
| 1226 |
+
"grad_norm": 0.162109375,
|
| 1227 |
+
"learning_rate": 9.616449348044133e-05,
|
| 1228 |
+
"loss": 1.0816,
|
| 1229 |
+
"step": 4125
|
| 1230 |
+
},
|
| 1231 |
+
{
|
| 1232 |
+
"epoch": 3.5810489963306713,
|
| 1233 |
+
"grad_norm": 0.2001953125,
|
| 1234 |
+
"learning_rate": 9.61394182547643e-05,
|
| 1235 |
+
"loss": 1.3246,
|
| 1236 |
+
"step": 4150
|
| 1237 |
+
},
|
| 1238 |
+
{
|
| 1239 |
+
"epoch": 3.6026332829699976,
|
| 1240 |
+
"grad_norm": 0.19921875,
|
| 1241 |
+
"learning_rate": 9.611434302908727e-05,
|
| 1242 |
+
"loss": 1.1461,
|
| 1243 |
+
"step": 4175
|
| 1244 |
+
},
|
| 1245 |
+
{
|
| 1246 |
+
"epoch": 3.6242175696093244,
|
| 1247 |
+
"grad_norm": 0.259765625,
|
| 1248 |
+
"learning_rate": 9.608926780341023e-05,
|
| 1249 |
+
"loss": 1.0712,
|
| 1250 |
+
"step": 4200
|
| 1251 |
+
},
|
| 1252 |
+
{
|
| 1253 |
+
"epoch": 3.645801856248651,
|
| 1254 |
+
"grad_norm": 0.2314453125,
|
| 1255 |
+
"learning_rate": 9.60641925777332e-05,
|
| 1256 |
+
"loss": 1.0729,
|
| 1257 |
+
"step": 4225
|
| 1258 |
+
},
|
| 1259 |
+
{
|
| 1260 |
+
"epoch": 3.6673861428879775,
|
| 1261 |
+
"grad_norm": 0.2578125,
|
| 1262 |
+
"learning_rate": 9.603911735205618e-05,
|
| 1263 |
+
"loss": 1.1162,
|
| 1264 |
+
"step": 4250
|
| 1265 |
+
},
|
| 1266 |
+
{
|
| 1267 |
+
"epoch": 3.6889704295273043,
|
| 1268 |
+
"grad_norm": 0.19921875,
|
| 1269 |
+
"learning_rate": 9.601404212637915e-05,
|
| 1270 |
+
"loss": 1.2936,
|
| 1271 |
+
"step": 4275
|
| 1272 |
+
},
|
| 1273 |
+
{
|
| 1274 |
+
"epoch": 3.7105547161666306,
|
| 1275 |
+
"grad_norm": 0.248046875,
|
| 1276 |
+
"learning_rate": 9.598896690070211e-05,
|
| 1277 |
+
"loss": 1.2288,
|
| 1278 |
+
"step": 4300
|
| 1279 |
+
},
|
| 1280 |
+
{
|
| 1281 |
+
"epoch": 3.7321390028059573,
|
| 1282 |
+
"grad_norm": 0.1953125,
|
| 1283 |
+
"learning_rate": 9.596389167502508e-05,
|
| 1284 |
+
"loss": 1.2297,
|
| 1285 |
+
"step": 4325
|
| 1286 |
+
},
|
| 1287 |
+
{
|
| 1288 |
+
"epoch": 3.7537232894452837,
|
| 1289 |
+
"grad_norm": 0.1767578125,
|
| 1290 |
+
"learning_rate": 9.593881644934805e-05,
|
| 1291 |
+
"loss": 1.1267,
|
| 1292 |
+
"step": 4350
|
| 1293 |
+
},
|
| 1294 |
+
{
|
| 1295 |
+
"epoch": 3.7753075760846104,
|
| 1296 |
+
"grad_norm": 0.2099609375,
|
| 1297 |
+
"learning_rate": 9.591374122367101e-05,
|
| 1298 |
+
"loss": 1.0324,
|
| 1299 |
+
"step": 4375
|
| 1300 |
+
},
|
| 1301 |
+
{
|
| 1302 |
+
"epoch": 3.796891862723937,
|
| 1303 |
+
"grad_norm": 0.166015625,
|
| 1304 |
+
"learning_rate": 9.588866599799399e-05,
|
| 1305 |
+
"loss": 1.1171,
|
| 1306 |
+
"step": 4400
|
| 1307 |
+
},
|
| 1308 |
+
{
|
| 1309 |
+
"epoch": 3.8184761493632635,
|
| 1310 |
+
"grad_norm": 0.224609375,
|
| 1311 |
+
"learning_rate": 9.586359077231696e-05,
|
| 1312 |
+
"loss": 1.292,
|
| 1313 |
+
"step": 4425
|
| 1314 |
+
},
|
| 1315 |
+
{
|
| 1316 |
+
"epoch": 3.84006043600259,
|
| 1317 |
+
"grad_norm": 0.21875,
|
| 1318 |
+
"learning_rate": 9.583851554663992e-05,
|
| 1319 |
+
"loss": 1.0742,
|
| 1320 |
+
"step": 4450
|
| 1321 |
+
},
|
| 1322 |
+
{
|
| 1323 |
+
"epoch": 3.8616447226419166,
|
| 1324 |
+
"grad_norm": 0.6171875,
|
| 1325 |
+
"learning_rate": 9.581344032096289e-05,
|
| 1326 |
+
"loss": 1.2224,
|
| 1327 |
+
"step": 4475
|
| 1328 |
+
},
|
| 1329 |
+
{
|
| 1330 |
+
"epoch": 3.8832290092812434,
|
| 1331 |
+
"grad_norm": 0.1943359375,
|
| 1332 |
+
"learning_rate": 9.578836509528586e-05,
|
| 1333 |
+
"loss": 1.089,
|
| 1334 |
+
"step": 4500
|
| 1335 |
+
},
|
| 1336 |
+
{
|
| 1337 |
+
"epoch": 3.8832290092812434,
|
| 1338 |
+
"eval_loss": 1.1965827941894531,
|
| 1339 |
+
"eval_runtime": 118.9387,
|
| 1340 |
+
"eval_samples_per_second": 4.204,
|
| 1341 |
+
"eval_steps_per_second": 4.204,
|
| 1342 |
+
"step": 4500
|
| 1343 |
+
},
|
| 1344 |
+
{
|
| 1345 |
+
"epoch": 3.9048132959205697,
|
| 1346 |
+
"grad_norm": 0.1943359375,
|
| 1347 |
+
"learning_rate": 9.576328986960882e-05,
|
| 1348 |
+
"loss": 1.0507,
|
| 1349 |
+
"step": 4525
|
| 1350 |
+
},
|
| 1351 |
+
{
|
| 1352 |
+
"epoch": 3.9263975825598965,
|
| 1353 |
+
"grad_norm": 0.20703125,
|
| 1354 |
+
"learning_rate": 9.57382146439318e-05,
|
| 1355 |
+
"loss": 1.2054,
|
| 1356 |
+
"step": 4550
|
| 1357 |
+
},
|
| 1358 |
+
{
|
| 1359 |
+
"epoch": 3.9479818691992232,
|
| 1360 |
+
"grad_norm": 0.1611328125,
|
| 1361 |
+
"learning_rate": 9.571313941825477e-05,
|
| 1362 |
+
"loss": 1.2096,
|
| 1363 |
+
"step": 4575
|
| 1364 |
+
},
|
| 1365 |
+
{
|
| 1366 |
+
"epoch": 3.9695661558385495,
|
| 1367 |
+
"grad_norm": 0.22265625,
|
| 1368 |
+
"learning_rate": 9.568806419257774e-05,
|
| 1369 |
+
"loss": 1.2408,
|
| 1370 |
+
"step": 4600
|
| 1371 |
+
},
|
| 1372 |
+
{
|
| 1373 |
+
"epoch": 3.991150442477876,
|
| 1374 |
+
"grad_norm": 0.2060546875,
|
| 1375 |
+
"learning_rate": 9.56629889669007e-05,
|
| 1376 |
+
"loss": 1.3001,
|
| 1377 |
+
"step": 4625
|
| 1378 |
+
},
|
| 1379 |
+
{
|
| 1380 |
+
"epoch": 4.012087200518023,
|
| 1381 |
+
"grad_norm": 0.2578125,
|
| 1382 |
+
"learning_rate": 9.563791374122367e-05,
|
| 1383 |
+
"loss": 1.1829,
|
| 1384 |
+
"step": 4650
|
| 1385 |
+
},
|
| 1386 |
+
{
|
| 1387 |
+
"epoch": 4.033671487157349,
|
| 1388 |
+
"grad_norm": 0.181640625,
|
| 1389 |
+
"learning_rate": 9.561283851554665e-05,
|
| 1390 |
+
"loss": 1.1251,
|
| 1391 |
+
"step": 4675
|
| 1392 |
+
},
|
| 1393 |
+
{
|
| 1394 |
+
"epoch": 4.055255773796676,
|
| 1395 |
+
"grad_norm": 0.205078125,
|
| 1396 |
+
"learning_rate": 9.558776328986961e-05,
|
| 1397 |
+
"loss": 1.1453,
|
| 1398 |
+
"step": 4700
|
| 1399 |
+
},
|
| 1400 |
+
{
|
| 1401 |
+
"epoch": 4.076840060436003,
|
| 1402 |
+
"grad_norm": 0.267578125,
|
| 1403 |
+
"learning_rate": 9.556268806419258e-05,
|
| 1404 |
+
"loss": 0.9924,
|
| 1405 |
+
"step": 4725
|
| 1406 |
+
},
|
| 1407 |
+
{
|
| 1408 |
+
"epoch": 4.098424347075329,
|
| 1409 |
+
"grad_norm": 0.2138671875,
|
| 1410 |
+
"learning_rate": 9.553761283851556e-05,
|
| 1411 |
+
"loss": 1.1183,
|
| 1412 |
+
"step": 4750
|
| 1413 |
+
},
|
| 1414 |
+
{
|
| 1415 |
+
"epoch": 4.120008633714655,
|
| 1416 |
+
"grad_norm": 0.212890625,
|
| 1417 |
+
"learning_rate": 9.551253761283851e-05,
|
| 1418 |
+
"loss": 1.1264,
|
| 1419 |
+
"step": 4775
|
| 1420 |
+
},
|
| 1421 |
+
{
|
| 1422 |
+
"epoch": 4.1415929203539825,
|
| 1423 |
+
"grad_norm": 0.2451171875,
|
| 1424 |
+
"learning_rate": 9.548746238716148e-05,
|
| 1425 |
+
"loss": 1.083,
|
| 1426 |
+
"step": 4800
|
| 1427 |
+
},
|
| 1428 |
+
{
|
| 1429 |
+
"epoch": 4.163177206993309,
|
| 1430 |
+
"grad_norm": 0.2001953125,
|
| 1431 |
+
"learning_rate": 9.546238716148446e-05,
|
| 1432 |
+
"loss": 1.2387,
|
| 1433 |
+
"step": 4825
|
| 1434 |
+
},
|
| 1435 |
+
{
|
| 1436 |
+
"epoch": 4.184761493632635,
|
| 1437 |
+
"grad_norm": 0.21484375,
|
| 1438 |
+
"learning_rate": 9.543731193580743e-05,
|
| 1439 |
+
"loss": 1.1978,
|
| 1440 |
+
"step": 4850
|
| 1441 |
+
},
|
| 1442 |
+
{
|
| 1443 |
+
"epoch": 4.206345780271962,
|
| 1444 |
+
"grad_norm": 0.205078125,
|
| 1445 |
+
"learning_rate": 9.541223671013039e-05,
|
| 1446 |
+
"loss": 1.2543,
|
| 1447 |
+
"step": 4875
|
| 1448 |
+
},
|
| 1449 |
+
{
|
| 1450 |
+
"epoch": 4.227930066911289,
|
| 1451 |
+
"grad_norm": 0.208984375,
|
| 1452 |
+
"learning_rate": 9.538716148445337e-05,
|
| 1453 |
+
"loss": 1.1928,
|
| 1454 |
+
"step": 4900
|
| 1455 |
+
},
|
| 1456 |
+
{
|
| 1457 |
+
"epoch": 4.249514353550615,
|
| 1458 |
+
"grad_norm": 0.1875,
|
| 1459 |
+
"learning_rate": 9.536208625877633e-05,
|
| 1460 |
+
"loss": 1.1346,
|
| 1461 |
+
"step": 4925
|
| 1462 |
+
},
|
| 1463 |
+
{
|
| 1464 |
+
"epoch": 4.271098640189941,
|
| 1465 |
+
"grad_norm": 0.2021484375,
|
| 1466 |
+
"learning_rate": 9.53370110330993e-05,
|
| 1467 |
+
"loss": 1.3266,
|
| 1468 |
+
"step": 4950
|
| 1469 |
+
},
|
| 1470 |
+
{
|
| 1471 |
+
"epoch": 4.2926829268292686,
|
| 1472 |
+
"grad_norm": 0.224609375,
|
| 1473 |
+
"learning_rate": 9.531193580742227e-05,
|
| 1474 |
+
"loss": 1.2258,
|
| 1475 |
+
"step": 4975
|
| 1476 |
+
},
|
| 1477 |
+
{
|
| 1478 |
+
"epoch": 4.314267213468595,
|
| 1479 |
+
"grad_norm": 0.2431640625,
|
| 1480 |
+
"learning_rate": 9.528686058174524e-05,
|
| 1481 |
+
"loss": 1.0399,
|
| 1482 |
+
"step": 5000
|
| 1483 |
+
},
|
| 1484 |
+
{
|
| 1485 |
+
"epoch": 4.314267213468595,
|
| 1486 |
+
"eval_loss": 1.194091796875,
|
| 1487 |
+
"eval_runtime": 118.5046,
|
| 1488 |
+
"eval_samples_per_second": 4.219,
|
| 1489 |
+
"eval_steps_per_second": 4.219,
|
| 1490 |
+
"step": 5000
|
| 1491 |
+
},
|
| 1492 |
+
{
|
| 1493 |
+
"epoch": 4.335851500107921,
|
| 1494 |
+
"grad_norm": 0.19921875,
|
| 1495 |
+
"learning_rate": 9.526178535606822e-05,
|
| 1496 |
+
"loss": 1.1494,
|
| 1497 |
+
"step": 5025
|
| 1498 |
+
},
|
| 1499 |
+
{
|
| 1500 |
+
"epoch": 4.357435786747248,
|
| 1501 |
+
"grad_norm": 0.2119140625,
|
| 1502 |
+
"learning_rate": 9.523671013039118e-05,
|
| 1503 |
+
"loss": 1.0299,
|
| 1504 |
+
"step": 5050
|
| 1505 |
+
},
|
| 1506 |
+
{
|
| 1507 |
+
"epoch": 4.379020073386575,
|
| 1508 |
+
"grad_norm": 0.2451171875,
|
| 1509 |
+
"learning_rate": 9.521163490471414e-05,
|
| 1510 |
+
"loss": 1.1657,
|
| 1511 |
+
"step": 5075
|
| 1512 |
+
},
|
| 1513 |
+
{
|
| 1514 |
+
"epoch": 4.400604360025901,
|
| 1515 |
+
"grad_norm": 0.265625,
|
| 1516 |
+
"learning_rate": 9.518655967903712e-05,
|
| 1517 |
+
"loss": 1.0644,
|
| 1518 |
+
"step": 5100
|
| 1519 |
+
},
|
| 1520 |
+
{
|
| 1521 |
+
"epoch": 4.422188646665227,
|
| 1522 |
+
"grad_norm": 0.1826171875,
|
| 1523 |
+
"learning_rate": 9.516148445336008e-05,
|
| 1524 |
+
"loss": 1.2457,
|
| 1525 |
+
"step": 5125
|
| 1526 |
+
},
|
| 1527 |
+
{
|
| 1528 |
+
"epoch": 4.443772933304555,
|
| 1529 |
+
"grad_norm": 0.2578125,
|
| 1530 |
+
"learning_rate": 9.513640922768305e-05,
|
| 1531 |
+
"loss": 1.054,
|
| 1532 |
+
"step": 5150
|
| 1533 |
+
},
|
| 1534 |
+
{
|
| 1535 |
+
"epoch": 4.465357219943881,
|
| 1536 |
+
"grad_norm": 0.18359375,
|
| 1537 |
+
"learning_rate": 9.511133400200603e-05,
|
| 1538 |
+
"loss": 1.2129,
|
| 1539 |
+
"step": 5175
|
| 1540 |
+
},
|
| 1541 |
+
{
|
| 1542 |
+
"epoch": 4.486941506583207,
|
| 1543 |
+
"grad_norm": 0.173828125,
|
| 1544 |
+
"learning_rate": 9.5086258776329e-05,
|
| 1545 |
+
"loss": 0.9745,
|
| 1546 |
+
"step": 5200
|
| 1547 |
+
},
|
| 1548 |
+
{
|
| 1549 |
+
"epoch": 4.5085257932225336,
|
| 1550 |
+
"grad_norm": 0.2119140625,
|
| 1551 |
+
"learning_rate": 9.506118355065195e-05,
|
| 1552 |
+
"loss": 1.1331,
|
| 1553 |
+
"step": 5225
|
| 1554 |
+
},
|
| 1555 |
+
{
|
| 1556 |
+
"epoch": 4.530110079861861,
|
| 1557 |
+
"grad_norm": 0.201171875,
|
| 1558 |
+
"learning_rate": 9.503610832497493e-05,
|
| 1559 |
+
"loss": 1.1554,
|
| 1560 |
+
"step": 5250
|
| 1561 |
+
},
|
| 1562 |
+
{
|
| 1563 |
+
"epoch": 4.551694366501187,
|
| 1564 |
+
"grad_norm": 0.369140625,
|
| 1565 |
+
"learning_rate": 9.50110330992979e-05,
|
| 1566 |
+
"loss": 1.3741,
|
| 1567 |
+
"step": 5275
|
| 1568 |
+
},
|
| 1569 |
+
{
|
| 1570 |
+
"epoch": 4.573278653140513,
|
| 1571 |
+
"grad_norm": 0.31640625,
|
| 1572 |
+
"learning_rate": 9.498595787362086e-05,
|
| 1573 |
+
"loss": 1.2421,
|
| 1574 |
+
"step": 5300
|
| 1575 |
+
},
|
| 1576 |
+
{
|
| 1577 |
+
"epoch": 4.594862939779841,
|
| 1578 |
+
"grad_norm": 0.16796875,
|
| 1579 |
+
"learning_rate": 9.496088264794384e-05,
|
| 1580 |
+
"loss": 1.1185,
|
| 1581 |
+
"step": 5325
|
| 1582 |
+
},
|
| 1583 |
+
{
|
| 1584 |
+
"epoch": 4.616447226419167,
|
| 1585 |
+
"grad_norm": 0.423828125,
|
| 1586 |
+
"learning_rate": 9.493580742226681e-05,
|
| 1587 |
+
"loss": 1.1028,
|
| 1588 |
+
"step": 5350
|
| 1589 |
+
},
|
| 1590 |
+
{
|
| 1591 |
+
"epoch": 4.638031513058493,
|
| 1592 |
+
"grad_norm": 0.2099609375,
|
| 1593 |
+
"learning_rate": 9.491073219658977e-05,
|
| 1594 |
+
"loss": 1.246,
|
| 1595 |
+
"step": 5375
|
| 1596 |
+
},
|
| 1597 |
+
{
|
| 1598 |
+
"epoch": 4.65961579969782,
|
| 1599 |
+
"grad_norm": 0.212890625,
|
| 1600 |
+
"learning_rate": 9.488565697091274e-05,
|
| 1601 |
+
"loss": 1.1932,
|
| 1602 |
+
"step": 5400
|
| 1603 |
+
},
|
| 1604 |
+
{
|
| 1605 |
+
"epoch": 4.681200086337147,
|
| 1606 |
+
"grad_norm": 0.2197265625,
|
| 1607 |
+
"learning_rate": 9.486058174523571e-05,
|
| 1608 |
+
"loss": 1.1054,
|
| 1609 |
+
"step": 5425
|
| 1610 |
+
},
|
| 1611 |
+
{
|
| 1612 |
+
"epoch": 4.702784372976473,
|
| 1613 |
+
"grad_norm": 0.1982421875,
|
| 1614 |
+
"learning_rate": 9.483550651955869e-05,
|
| 1615 |
+
"loss": 1.2252,
|
| 1616 |
+
"step": 5450
|
| 1617 |
+
},
|
| 1618 |
+
{
|
| 1619 |
+
"epoch": 4.724368659615799,
|
| 1620 |
+
"grad_norm": 0.294921875,
|
| 1621 |
+
"learning_rate": 9.481043129388165e-05,
|
| 1622 |
+
"loss": 1.3116,
|
| 1623 |
+
"step": 5475
|
| 1624 |
+
},
|
| 1625 |
+
{
|
| 1626 |
+
"epoch": 4.745952946255127,
|
| 1627 |
+
"grad_norm": 0.205078125,
|
| 1628 |
+
"learning_rate": 9.478535606820462e-05,
|
| 1629 |
+
"loss": 1.0582,
|
| 1630 |
+
"step": 5500
|
| 1631 |
+
},
|
| 1632 |
+
{
|
| 1633 |
+
"epoch": 4.745952946255127,
|
| 1634 |
+
"eval_loss": 1.1924177408218384,
|
| 1635 |
+
"eval_runtime": 119.0148,
|
| 1636 |
+
"eval_samples_per_second": 4.201,
|
| 1637 |
+
"eval_steps_per_second": 4.201,
|
| 1638 |
+
"step": 5500
|
| 1639 |
+
},
|
| 1640 |
+
{
|
| 1641 |
+
"epoch": 4.767537232894453,
|
| 1642 |
+
"grad_norm": 0.1904296875,
|
| 1643 |
+
"learning_rate": 9.476028084252759e-05,
|
| 1644 |
+
"loss": 1.2304,
|
| 1645 |
+
"step": 5525
|
| 1646 |
+
},
|
| 1647 |
+
{
|
| 1648 |
+
"epoch": 4.789121519533779,
|
| 1649 |
+
"grad_norm": 0.2353515625,
|
| 1650 |
+
"learning_rate": 9.473520561685055e-05,
|
| 1651 |
+
"loss": 1.2139,
|
| 1652 |
+
"step": 5550
|
| 1653 |
+
},
|
| 1654 |
+
{
|
| 1655 |
+
"epoch": 4.810705806173106,
|
| 1656 |
+
"grad_norm": 0.2451171875,
|
| 1657 |
+
"learning_rate": 9.471013039117352e-05,
|
| 1658 |
+
"loss": 1.2242,
|
| 1659 |
+
"step": 5575
|
| 1660 |
+
},
|
| 1661 |
+
{
|
| 1662 |
+
"epoch": 4.832290092812433,
|
| 1663 |
+
"grad_norm": 0.1767578125,
|
| 1664 |
+
"learning_rate": 9.46850551654965e-05,
|
| 1665 |
+
"loss": 1.2189,
|
| 1666 |
+
"step": 5600
|
| 1667 |
+
},
|
| 1668 |
+
{
|
| 1669 |
+
"epoch": 4.853874379451759,
|
| 1670 |
+
"grad_norm": 0.216796875,
|
| 1671 |
+
"learning_rate": 9.465997993981946e-05,
|
| 1672 |
+
"loss": 1.2028,
|
| 1673 |
+
"step": 5625
|
| 1674 |
+
},
|
| 1675 |
+
{
|
| 1676 |
+
"epoch": 4.8754586660910855,
|
| 1677 |
+
"grad_norm": 0.1845703125,
|
| 1678 |
+
"learning_rate": 9.463490471414243e-05,
|
| 1679 |
+
"loss": 1.3289,
|
| 1680 |
+
"step": 5650
|
| 1681 |
+
},
|
| 1682 |
+
{
|
| 1683 |
+
"epoch": 4.897042952730413,
|
| 1684 |
+
"grad_norm": 0.158203125,
|
| 1685 |
+
"learning_rate": 9.46098294884654e-05,
|
| 1686 |
+
"loss": 1.0569,
|
| 1687 |
+
"step": 5675
|
| 1688 |
+
},
|
| 1689 |
+
{
|
| 1690 |
+
"epoch": 4.918627239369739,
|
| 1691 |
+
"grad_norm": 0.23046875,
|
| 1692 |
+
"learning_rate": 9.458475426278836e-05,
|
| 1693 |
+
"loss": 1.2749,
|
| 1694 |
+
"step": 5700
|
| 1695 |
+
},
|
| 1696 |
+
{
|
| 1697 |
+
"epoch": 4.940211526009065,
|
| 1698 |
+
"grad_norm": 0.2216796875,
|
| 1699 |
+
"learning_rate": 9.455967903711134e-05,
|
| 1700 |
+
"loss": 1.1241,
|
| 1701 |
+
"step": 5725
|
| 1702 |
+
},
|
| 1703 |
+
{
|
| 1704 |
+
"epoch": 4.961795812648392,
|
| 1705 |
+
"grad_norm": 0.1943359375,
|
| 1706 |
+
"learning_rate": 9.453460381143431e-05,
|
| 1707 |
+
"loss": 1.228,
|
| 1708 |
+
"step": 5750
|
| 1709 |
+
},
|
| 1710 |
+
{
|
| 1711 |
+
"epoch": 4.983380099287719,
|
| 1712 |
+
"grad_norm": 0.1953125,
|
| 1713 |
+
"learning_rate": 9.450952858575728e-05,
|
| 1714 |
+
"loss": 1.1277,
|
| 1715 |
+
"step": 5775
|
| 1716 |
+
},
|
| 1717 |
+
{
|
| 1718 |
+
"epoch": 5.004316857327865,
|
| 1719 |
+
"grad_norm": 0.1904296875,
|
| 1720 |
+
"learning_rate": 9.448445336008024e-05,
|
| 1721 |
+
"loss": 0.9851,
|
| 1722 |
+
"step": 5800
|
| 1723 |
+
},
|
| 1724 |
+
{
|
| 1725 |
+
"epoch": 5.025901143967192,
|
| 1726 |
+
"grad_norm": 0.2490234375,
|
| 1727 |
+
"learning_rate": 9.445937813440321e-05,
|
| 1728 |
+
"loss": 1.1516,
|
| 1729 |
+
"step": 5825
|
| 1730 |
+
},
|
| 1731 |
+
{
|
| 1732 |
+
"epoch": 5.047485430606518,
|
| 1733 |
+
"grad_norm": 0.1630859375,
|
| 1734 |
+
"learning_rate": 9.443430290872618e-05,
|
| 1735 |
+
"loss": 1.1664,
|
| 1736 |
+
"step": 5850
|
| 1737 |
+
},
|
| 1738 |
+
{
|
| 1739 |
+
"epoch": 5.069069717245845,
|
| 1740 |
+
"grad_norm": 0.2080078125,
|
| 1741 |
+
"learning_rate": 9.440922768304916e-05,
|
| 1742 |
+
"loss": 1.0938,
|
| 1743 |
+
"step": 5875
|
| 1744 |
+
},
|
| 1745 |
+
{
|
| 1746 |
+
"epoch": 5.090654003885172,
|
| 1747 |
+
"grad_norm": 0.2216796875,
|
| 1748 |
+
"learning_rate": 9.438415245737212e-05,
|
| 1749 |
+
"loss": 1.0517,
|
| 1750 |
+
"step": 5900
|
| 1751 |
+
},
|
| 1752 |
+
{
|
| 1753 |
+
"epoch": 5.112238290524498,
|
| 1754 |
+
"grad_norm": 0.2001953125,
|
| 1755 |
+
"learning_rate": 9.435907723169509e-05,
|
| 1756 |
+
"loss": 1.1735,
|
| 1757 |
+
"step": 5925
|
| 1758 |
+
},
|
| 1759 |
+
{
|
| 1760 |
+
"epoch": 5.133822577163825,
|
| 1761 |
+
"grad_norm": 0.25,
|
| 1762 |
+
"learning_rate": 9.433400200601807e-05,
|
| 1763 |
+
"loss": 0.9135,
|
| 1764 |
+
"step": 5950
|
| 1765 |
+
},
|
| 1766 |
+
{
|
| 1767 |
+
"epoch": 5.155406863803151,
|
| 1768 |
+
"grad_norm": 0.208984375,
|
| 1769 |
+
"learning_rate": 9.430892678034102e-05,
|
| 1770 |
+
"loss": 1.0003,
|
| 1771 |
+
"step": 5975
|
| 1772 |
+
},
|
| 1773 |
+
{
|
| 1774 |
+
"epoch": 5.176991150442478,
|
| 1775 |
+
"grad_norm": 0.228515625,
|
| 1776 |
+
"learning_rate": 9.428385155466399e-05,
|
| 1777 |
+
"loss": 1.1648,
|
| 1778 |
+
"step": 6000
|
| 1779 |
+
},
|
| 1780 |
+
{
|
| 1781 |
+
"epoch": 5.176991150442478,
|
| 1782 |
+
"eval_loss": 1.1907110214233398,
|
| 1783 |
+
"eval_runtime": 119.0768,
|
| 1784 |
+
"eval_samples_per_second": 4.199,
|
| 1785 |
+
"eval_steps_per_second": 4.199,
|
| 1786 |
+
"step": 6000
|
| 1787 |
+
},
|
| 1788 |
+
{
|
| 1789 |
+
"epoch": 5.1985754370818045,
|
| 1790 |
+
"grad_norm": 0.2578125,
|
| 1791 |
+
"learning_rate": 9.425877632898697e-05,
|
| 1792 |
+
"loss": 1.2177,
|
| 1793 |
+
"step": 6025
|
| 1794 |
+
},
|
| 1795 |
+
{
|
| 1796 |
+
"epoch": 5.220159723721131,
|
| 1797 |
+
"grad_norm": 0.2373046875,
|
| 1798 |
+
"learning_rate": 9.423370110330993e-05,
|
| 1799 |
+
"loss": 1.2648,
|
| 1800 |
+
"step": 6050
|
| 1801 |
+
},
|
| 1802 |
+
{
|
| 1803 |
+
"epoch": 5.241744010360458,
|
| 1804 |
+
"grad_norm": 0.181640625,
|
| 1805 |
+
"learning_rate": 9.42086258776329e-05,
|
| 1806 |
+
"loss": 1.2015,
|
| 1807 |
+
"step": 6075
|
| 1808 |
+
},
|
| 1809 |
+
{
|
| 1810 |
+
"epoch": 5.263328296999784,
|
| 1811 |
+
"grad_norm": 0.2265625,
|
| 1812 |
+
"learning_rate": 9.418355065195588e-05,
|
| 1813 |
+
"loss": 1.1269,
|
| 1814 |
+
"step": 6100
|
| 1815 |
+
},
|
| 1816 |
+
{
|
| 1817 |
+
"epoch": 5.284912583639111,
|
| 1818 |
+
"grad_norm": 0.154296875,
|
| 1819 |
+
"learning_rate": 9.415847542627883e-05,
|
| 1820 |
+
"loss": 1.0723,
|
| 1821 |
+
"step": 6125
|
| 1822 |
+
},
|
| 1823 |
+
{
|
| 1824 |
+
"epoch": 5.306496870278437,
|
| 1825 |
+
"grad_norm": 0.2001953125,
|
| 1826 |
+
"learning_rate": 9.413340020060181e-05,
|
| 1827 |
+
"loss": 1.0201,
|
| 1828 |
+
"step": 6150
|
| 1829 |
+
},
|
| 1830 |
+
{
|
| 1831 |
+
"epoch": 5.328081156917764,
|
| 1832 |
+
"grad_norm": 0.212890625,
|
| 1833 |
+
"learning_rate": 9.410832497492478e-05,
|
| 1834 |
+
"loss": 1.3579,
|
| 1835 |
+
"step": 6175
|
| 1836 |
+
},
|
| 1837 |
+
{
|
| 1838 |
+
"epoch": 5.3496654435570905,
|
| 1839 |
+
"grad_norm": 0.2333984375,
|
| 1840 |
+
"learning_rate": 9.408324974924775e-05,
|
| 1841 |
+
"loss": 1.1706,
|
| 1842 |
+
"step": 6200
|
| 1843 |
+
},
|
| 1844 |
+
{
|
| 1845 |
+
"epoch": 5.371249730196417,
|
| 1846 |
+
"grad_norm": 0.2158203125,
|
| 1847 |
+
"learning_rate": 9.405817452357073e-05,
|
| 1848 |
+
"loss": 1.1311,
|
| 1849 |
+
"step": 6225
|
| 1850 |
+
},
|
| 1851 |
+
{
|
| 1852 |
+
"epoch": 5.392834016835744,
|
| 1853 |
+
"grad_norm": 0.2021484375,
|
| 1854 |
+
"learning_rate": 9.403309929789369e-05,
|
| 1855 |
+
"loss": 1.133,
|
| 1856 |
+
"step": 6250
|
| 1857 |
+
},
|
| 1858 |
+
{
|
| 1859 |
+
"epoch": 5.41441830347507,
|
| 1860 |
+
"grad_norm": 0.265625,
|
| 1861 |
+
"learning_rate": 9.400802407221664e-05,
|
| 1862 |
+
"loss": 1.1611,
|
| 1863 |
+
"step": 6275
|
| 1864 |
+
},
|
| 1865 |
+
{
|
| 1866 |
+
"epoch": 5.436002590114397,
|
| 1867 |
+
"grad_norm": 0.22265625,
|
| 1868 |
+
"learning_rate": 9.398294884653962e-05,
|
| 1869 |
+
"loss": 1.1361,
|
| 1870 |
+
"step": 6300
|
| 1871 |
+
},
|
| 1872 |
+
{
|
| 1873 |
+
"epoch": 5.457586876753723,
|
| 1874 |
+
"grad_norm": 0.287109375,
|
| 1875 |
+
"learning_rate": 9.395787362086259e-05,
|
| 1876 |
+
"loss": 1.1646,
|
| 1877 |
+
"step": 6325
|
| 1878 |
+
},
|
| 1879 |
+
{
|
| 1880 |
+
"epoch": 5.47917116339305,
|
| 1881 |
+
"grad_norm": 0.310546875,
|
| 1882 |
+
"learning_rate": 9.393279839518556e-05,
|
| 1883 |
+
"loss": 1.2833,
|
| 1884 |
+
"step": 6350
|
| 1885 |
+
},
|
| 1886 |
+
{
|
| 1887 |
+
"epoch": 5.5007554500323765,
|
| 1888 |
+
"grad_norm": 0.203125,
|
| 1889 |
+
"learning_rate": 9.390772316950854e-05,
|
| 1890 |
+
"loss": 1.1654,
|
| 1891 |
+
"step": 6375
|
| 1892 |
+
},
|
| 1893 |
+
{
|
| 1894 |
+
"epoch": 5.522339736671703,
|
| 1895 |
+
"grad_norm": 0.1767578125,
|
| 1896 |
+
"learning_rate": 9.38826479438315e-05,
|
| 1897 |
+
"loss": 1.0767,
|
| 1898 |
+
"step": 6400
|
| 1899 |
+
},
|
| 1900 |
+
{
|
| 1901 |
+
"epoch": 5.54392402331103,
|
| 1902 |
+
"grad_norm": 0.2236328125,
|
| 1903 |
+
"learning_rate": 9.385757271815447e-05,
|
| 1904 |
+
"loss": 1.2222,
|
| 1905 |
+
"step": 6425
|
| 1906 |
+
},
|
| 1907 |
+
{
|
| 1908 |
+
"epoch": 5.565508309950356,
|
| 1909 |
+
"grad_norm": 0.1865234375,
|
| 1910 |
+
"learning_rate": 9.383249749247744e-05,
|
| 1911 |
+
"loss": 1.0511,
|
| 1912 |
+
"step": 6450
|
| 1913 |
+
},
|
| 1914 |
+
{
|
| 1915 |
+
"epoch": 5.587092596589683,
|
| 1916 |
+
"grad_norm": 0.236328125,
|
| 1917 |
+
"learning_rate": 9.38074222668004e-05,
|
| 1918 |
+
"loss": 1.0983,
|
| 1919 |
+
"step": 6475
|
| 1920 |
+
},
|
| 1921 |
+
{
|
| 1922 |
+
"epoch": 5.608676883229009,
|
| 1923 |
+
"grad_norm": 0.2119140625,
|
| 1924 |
+
"learning_rate": 9.378234704112337e-05,
|
| 1925 |
+
"loss": 1.1242,
|
| 1926 |
+
"step": 6500
|
| 1927 |
+
},
|
| 1928 |
+
{
|
| 1929 |
+
"epoch": 5.608676883229009,
|
| 1930 |
+
"eval_loss": 1.189411997795105,
|
| 1931 |
+
"eval_runtime": 116.8693,
|
| 1932 |
+
"eval_samples_per_second": 4.278,
|
| 1933 |
+
"eval_steps_per_second": 4.278,
|
| 1934 |
+
"step": 6500
|
| 1935 |
+
},
|
| 1936 |
+
{
|
| 1937 |
+
"epoch": 5.630261169868335,
|
| 1938 |
+
"grad_norm": 0.1884765625,
|
| 1939 |
+
"learning_rate": 9.375727181544635e-05,
|
| 1940 |
+
"loss": 1.1597,
|
| 1941 |
+
"step": 6525
|
| 1942 |
+
},
|
| 1943 |
+
{
|
| 1944 |
+
"epoch": 5.651845456507663,
|
| 1945 |
+
"grad_norm": 0.173828125,
|
| 1946 |
+
"learning_rate": 9.373219658976931e-05,
|
| 1947 |
+
"loss": 1.1403,
|
| 1948 |
+
"step": 6550
|
| 1949 |
+
},
|
| 1950 |
+
{
|
| 1951 |
+
"epoch": 5.673429743146989,
|
| 1952 |
+
"grad_norm": 0.1875,
|
| 1953 |
+
"learning_rate": 9.370712136409228e-05,
|
| 1954 |
+
"loss": 1.0764,
|
| 1955 |
+
"step": 6575
|
| 1956 |
+
},
|
| 1957 |
+
{
|
| 1958 |
+
"epoch": 5.695014029786315,
|
| 1959 |
+
"grad_norm": 0.2275390625,
|
| 1960 |
+
"learning_rate": 9.368204613841525e-05,
|
| 1961 |
+
"loss": 1.1857,
|
| 1962 |
+
"step": 6600
|
| 1963 |
+
},
|
| 1964 |
+
{
|
| 1965 |
+
"epoch": 5.716598316425642,
|
| 1966 |
+
"grad_norm": 0.1943359375,
|
| 1967 |
+
"learning_rate": 9.365697091273821e-05,
|
| 1968 |
+
"loss": 1.1954,
|
| 1969 |
+
"step": 6625
|
| 1970 |
+
},
|
| 1971 |
+
{
|
| 1972 |
+
"epoch": 5.738182603064969,
|
| 1973 |
+
"grad_norm": 0.2138671875,
|
| 1974 |
+
"learning_rate": 9.36318956870612e-05,
|
| 1975 |
+
"loss": 1.1375,
|
| 1976 |
+
"step": 6650
|
| 1977 |
+
},
|
| 1978 |
+
{
|
| 1979 |
+
"epoch": 5.759766889704295,
|
| 1980 |
+
"grad_norm": 0.240234375,
|
| 1981 |
+
"learning_rate": 9.360682046138416e-05,
|
| 1982 |
+
"loss": 1.3564,
|
| 1983 |
+
"step": 6675
|
| 1984 |
+
},
|
| 1985 |
+
{
|
| 1986 |
+
"epoch": 5.781351176343621,
|
| 1987 |
+
"grad_norm": 0.2333984375,
|
| 1988 |
+
"learning_rate": 9.358174523570713e-05,
|
| 1989 |
+
"loss": 1.1443,
|
| 1990 |
+
"step": 6700
|
| 1991 |
+
},
|
| 1992 |
+
{
|
| 1993 |
+
"epoch": 5.802935462982949,
|
| 1994 |
+
"grad_norm": 0.263671875,
|
| 1995 |
+
"learning_rate": 9.355667001003009e-05,
|
| 1996 |
+
"loss": 1.0885,
|
| 1997 |
+
"step": 6725
|
| 1998 |
+
},
|
| 1999 |
+
{
|
| 2000 |
+
"epoch": 5.824519749622275,
|
| 2001 |
+
"grad_norm": 0.283203125,
|
| 2002 |
+
"learning_rate": 9.353159478435306e-05,
|
| 2003 |
+
"loss": 1.2816,
|
| 2004 |
+
"step": 6750
|
| 2005 |
+
},
|
| 2006 |
+
{
|
| 2007 |
+
"epoch": 5.846104036261601,
|
| 2008 |
+
"grad_norm": 0.283203125,
|
| 2009 |
+
"learning_rate": 9.350651955867603e-05,
|
| 2010 |
+
"loss": 1.3483,
|
| 2011 |
+
"step": 6775
|
| 2012 |
+
},
|
| 2013 |
+
{
|
| 2014 |
+
"epoch": 5.8676883229009285,
|
| 2015 |
+
"grad_norm": 0.2490234375,
|
| 2016 |
+
"learning_rate": 9.3481444332999e-05,
|
| 2017 |
+
"loss": 1.2436,
|
| 2018 |
+
"step": 6800
|
| 2019 |
+
},
|
| 2020 |
+
{
|
| 2021 |
+
"epoch": 5.889272609540255,
|
| 2022 |
+
"grad_norm": 0.29296875,
|
| 2023 |
+
"learning_rate": 9.345636910732197e-05,
|
| 2024 |
+
"loss": 1.2322,
|
| 2025 |
+
"step": 6825
|
| 2026 |
+
},
|
| 2027 |
+
{
|
| 2028 |
+
"epoch": 5.910856896179581,
|
| 2029 |
+
"grad_norm": 0.2451171875,
|
| 2030 |
+
"learning_rate": 9.343129388164494e-05,
|
| 2031 |
+
"loss": 1.1397,
|
| 2032 |
+
"step": 6850
|
| 2033 |
+
},
|
| 2034 |
+
{
|
| 2035 |
+
"epoch": 5.932441182818907,
|
| 2036 |
+
"grad_norm": 0.2314453125,
|
| 2037 |
+
"learning_rate": 9.34062186559679e-05,
|
| 2038 |
+
"loss": 1.0838,
|
| 2039 |
+
"step": 6875
|
| 2040 |
+
},
|
| 2041 |
+
{
|
| 2042 |
+
"epoch": 5.954025469458235,
|
| 2043 |
+
"grad_norm": 0.1953125,
|
| 2044 |
+
"learning_rate": 9.338114343029087e-05,
|
| 2045 |
+
"loss": 1.235,
|
| 2046 |
+
"step": 6900
|
| 2047 |
+
},
|
| 2048 |
+
{
|
| 2049 |
+
"epoch": 5.975609756097561,
|
| 2050 |
+
"grad_norm": 0.2373046875,
|
| 2051 |
+
"learning_rate": 9.335606820461385e-05,
|
| 2052 |
+
"loss": 1.2332,
|
| 2053 |
+
"step": 6925
|
| 2054 |
+
},
|
| 2055 |
+
{
|
| 2056 |
+
"epoch": 5.997194042736887,
|
| 2057 |
+
"grad_norm": 0.185546875,
|
| 2058 |
+
"learning_rate": 9.333099297893682e-05,
|
| 2059 |
+
"loss": 1.2239,
|
| 2060 |
+
"step": 6950
|
| 2061 |
+
},
|
| 2062 |
+
{
|
| 2063 |
+
"epoch": 6.018130800777034,
|
| 2064 |
+
"grad_norm": 0.193359375,
|
| 2065 |
+
"learning_rate": 9.330591775325978e-05,
|
| 2066 |
+
"loss": 1.1734,
|
| 2067 |
+
"step": 6975
|
| 2068 |
+
},
|
| 2069 |
+
{
|
| 2070 |
+
"epoch": 6.0397150874163605,
|
| 2071 |
+
"grad_norm": 0.2578125,
|
| 2072 |
+
"learning_rate": 9.328084252758276e-05,
|
| 2073 |
+
"loss": 1.0798,
|
| 2074 |
+
"step": 7000
|
| 2075 |
+
},
|
| 2076 |
+
{
|
| 2077 |
+
"epoch": 6.0397150874163605,
|
| 2078 |
+
"eval_loss": 1.1887987852096558,
|
| 2079 |
+
"eval_runtime": 118.2372,
|
| 2080 |
+
"eval_samples_per_second": 4.229,
|
| 2081 |
+
"eval_steps_per_second": 4.229,
|
| 2082 |
+
"step": 7000
|
| 2083 |
+
},
|
| 2084 |
+
{
|
| 2085 |
+
"epoch": 6.061299374055688,
|
| 2086 |
+
"grad_norm": 0.2353515625,
|
| 2087 |
+
"learning_rate": 9.325576730190572e-05,
|
| 2088 |
+
"loss": 1.1714,
|
| 2089 |
+
"step": 7025
|
| 2090 |
+
},
|
| 2091 |
+
{
|
| 2092 |
+
"epoch": 6.082883660695014,
|
| 2093 |
+
"grad_norm": 0.23828125,
|
| 2094 |
+
"learning_rate": 9.323069207622868e-05,
|
| 2095 |
+
"loss": 1.2273,
|
| 2096 |
+
"step": 7050
|
| 2097 |
+
},
|
| 2098 |
+
{
|
| 2099 |
+
"epoch": 6.10446794733434,
|
| 2100 |
+
"grad_norm": 0.216796875,
|
| 2101 |
+
"learning_rate": 9.320561685055166e-05,
|
| 2102 |
+
"loss": 1.1239,
|
| 2103 |
+
"step": 7075
|
| 2104 |
+
},
|
| 2105 |
+
{
|
| 2106 |
+
"epoch": 6.126052233973667,
|
| 2107 |
+
"grad_norm": 0.228515625,
|
| 2108 |
+
"learning_rate": 9.318054162487463e-05,
|
| 2109 |
+
"loss": 1.2041,
|
| 2110 |
+
"step": 7100
|
| 2111 |
+
},
|
| 2112 |
+
{
|
| 2113 |
+
"epoch": 6.147636520612994,
|
| 2114 |
+
"grad_norm": 0.2421875,
|
| 2115 |
+
"learning_rate": 9.31554663991976e-05,
|
| 2116 |
+
"loss": 1.1536,
|
| 2117 |
+
"step": 7125
|
| 2118 |
+
},
|
| 2119 |
+
{
|
| 2120 |
+
"epoch": 6.16922080725232,
|
| 2121 |
+
"grad_norm": 0.1796875,
|
| 2122 |
+
"learning_rate": 9.313039117352057e-05,
|
| 2123 |
+
"loss": 1.1006,
|
| 2124 |
+
"step": 7150
|
| 2125 |
+
},
|
| 2126 |
+
{
|
| 2127 |
+
"epoch": 6.190805093891647,
|
| 2128 |
+
"grad_norm": 0.259765625,
|
| 2129 |
+
"learning_rate": 9.310531594784353e-05,
|
| 2130 |
+
"loss": 1.2912,
|
| 2131 |
+
"step": 7175
|
| 2132 |
+
},
|
| 2133 |
+
{
|
| 2134 |
+
"epoch": 6.212389380530974,
|
| 2135 |
+
"grad_norm": 0.205078125,
|
| 2136 |
+
"learning_rate": 9.30802407221665e-05,
|
| 2137 |
+
"loss": 1.1036,
|
| 2138 |
+
"step": 7200
|
| 2139 |
+
},
|
| 2140 |
+
{
|
| 2141 |
+
"epoch": 6.2339736671703,
|
| 2142 |
+
"grad_norm": 0.1982421875,
|
| 2143 |
+
"learning_rate": 9.305516549648947e-05,
|
| 2144 |
+
"loss": 1.0882,
|
| 2145 |
+
"step": 7225
|
| 2146 |
+
},
|
| 2147 |
+
{
|
| 2148 |
+
"epoch": 6.255557953809626,
|
| 2149 |
+
"grad_norm": 0.205078125,
|
| 2150 |
+
"learning_rate": 9.303009027081244e-05,
|
| 2151 |
+
"loss": 1.0551,
|
| 2152 |
+
"step": 7250
|
| 2153 |
+
},
|
| 2154 |
+
{
|
| 2155 |
+
"epoch": 6.277142240448953,
|
| 2156 |
+
"grad_norm": 0.232421875,
|
| 2157 |
+
"learning_rate": 9.30050150451354e-05,
|
| 2158 |
+
"loss": 1.0999,
|
| 2159 |
+
"step": 7275
|
| 2160 |
+
},
|
| 2161 |
+
{
|
| 2162 |
+
"epoch": 6.29872652708828,
|
| 2163 |
+
"grad_norm": 0.6171875,
|
| 2164 |
+
"learning_rate": 9.297993981945839e-05,
|
| 2165 |
+
"loss": 1.2349,
|
| 2166 |
+
"step": 7300
|
| 2167 |
+
},
|
| 2168 |
+
{
|
| 2169 |
+
"epoch": 6.320310813727606,
|
| 2170 |
+
"grad_norm": 0.275390625,
|
| 2171 |
+
"learning_rate": 9.295486459378134e-05,
|
| 2172 |
+
"loss": 1.2692,
|
| 2173 |
+
"step": 7325
|
| 2174 |
+
},
|
| 2175 |
+
{
|
| 2176 |
+
"epoch": 6.341895100366933,
|
| 2177 |
+
"grad_norm": 0.1982421875,
|
| 2178 |
+
"learning_rate": 9.292978936810432e-05,
|
| 2179 |
+
"loss": 1.0265,
|
| 2180 |
+
"step": 7350
|
| 2181 |
+
},
|
| 2182 |
+
{
|
| 2183 |
+
"epoch": 6.36347938700626,
|
| 2184 |
+
"grad_norm": 0.408203125,
|
| 2185 |
+
"learning_rate": 9.290471414242729e-05,
|
| 2186 |
+
"loss": 1.1694,
|
| 2187 |
+
"step": 7375
|
| 2188 |
+
},
|
| 2189 |
+
{
|
| 2190 |
+
"epoch": 6.385063673645586,
|
| 2191 |
+
"grad_norm": 0.4609375,
|
| 2192 |
+
"learning_rate": 9.287963891675025e-05,
|
| 2193 |
+
"loss": 0.9525,
|
| 2194 |
+
"step": 7400
|
| 2195 |
+
},
|
| 2196 |
+
{
|
| 2197 |
+
"epoch": 6.4066479602849125,
|
| 2198 |
+
"grad_norm": 0.20703125,
|
| 2199 |
+
"learning_rate": 9.285456369107323e-05,
|
| 2200 |
+
"loss": 1.1041,
|
| 2201 |
+
"step": 7425
|
| 2202 |
+
},
|
| 2203 |
+
{
|
| 2204 |
+
"epoch": 6.428232246924239,
|
| 2205 |
+
"grad_norm": 0.255859375,
|
| 2206 |
+
"learning_rate": 9.28294884653962e-05,
|
| 2207 |
+
"loss": 1.2264,
|
| 2208 |
+
"step": 7450
|
| 2209 |
+
},
|
| 2210 |
+
{
|
| 2211 |
+
"epoch": 6.449816533563566,
|
| 2212 |
+
"grad_norm": 0.1982421875,
|
| 2213 |
+
"learning_rate": 9.280441323971915e-05,
|
| 2214 |
+
"loss": 1.2127,
|
| 2215 |
+
"step": 7475
|
| 2216 |
+
},
|
| 2217 |
+
{
|
| 2218 |
+
"epoch": 6.471400820202892,
|
| 2219 |
+
"grad_norm": 0.318359375,
|
| 2220 |
+
"learning_rate": 9.277933801404213e-05,
|
| 2221 |
+
"loss": 1.1663,
|
| 2222 |
+
"step": 7500
|
| 2223 |
+
},
|
| 2224 |
+
{
|
| 2225 |
+
"epoch": 6.471400820202892,
|
| 2226 |
+
"eval_loss": 1.1857322454452515,
|
| 2227 |
+
"eval_runtime": 118.9404,
|
| 2228 |
+
"eval_samples_per_second": 4.204,
|
| 2229 |
+
"eval_steps_per_second": 4.204,
|
| 2230 |
+
"step": 7500
|
| 2231 |
+
},
|
| 2232 |
+
{
|
| 2233 |
+
"epoch": 6.492985106842219,
|
| 2234 |
+
"grad_norm": 0.197265625,
|
| 2235 |
+
"learning_rate": 9.27542627883651e-05,
|
| 2236 |
+
"loss": 1.1601,
|
| 2237 |
+
"step": 7525
|
| 2238 |
+
},
|
| 2239 |
+
{
|
| 2240 |
+
"epoch": 6.514569393481546,
|
| 2241 |
+
"grad_norm": 0.2333984375,
|
| 2242 |
+
"learning_rate": 9.272918756268806e-05,
|
| 2243 |
+
"loss": 1.2307,
|
| 2244 |
+
"step": 7550
|
| 2245 |
+
},
|
| 2246 |
+
{
|
| 2247 |
+
"epoch": 6.536153680120872,
|
| 2248 |
+
"grad_norm": 0.2109375,
|
| 2249 |
+
"learning_rate": 9.270411233701104e-05,
|
| 2250 |
+
"loss": 1.2392,
|
| 2251 |
+
"step": 7575
|
| 2252 |
+
},
|
| 2253 |
+
{
|
| 2254 |
+
"epoch": 6.5577379667601985,
|
| 2255 |
+
"grad_norm": 0.1953125,
|
| 2256 |
+
"learning_rate": 9.267903711133401e-05,
|
| 2257 |
+
"loss": 1.018,
|
| 2258 |
+
"step": 7600
|
| 2259 |
+
},
|
| 2260 |
+
{
|
| 2261 |
+
"epoch": 6.579322253399525,
|
| 2262 |
+
"grad_norm": 0.236328125,
|
| 2263 |
+
"learning_rate": 9.265396188565698e-05,
|
| 2264 |
+
"loss": 1.0398,
|
| 2265 |
+
"step": 7625
|
| 2266 |
+
},
|
| 2267 |
+
{
|
| 2268 |
+
"epoch": 6.600906540038852,
|
| 2269 |
+
"grad_norm": 0.2021484375,
|
| 2270 |
+
"learning_rate": 9.262888665997994e-05,
|
| 2271 |
+
"loss": 1.1174,
|
| 2272 |
+
"step": 7650
|
| 2273 |
+
},
|
| 2274 |
+
{
|
| 2275 |
+
"epoch": 6.622490826678178,
|
| 2276 |
+
"grad_norm": 0.1962890625,
|
| 2277 |
+
"learning_rate": 9.260381143430291e-05,
|
| 2278 |
+
"loss": 1.2179,
|
| 2279 |
+
"step": 7675
|
| 2280 |
+
},
|
| 2281 |
+
{
|
| 2282 |
+
"epoch": 6.644075113317505,
|
| 2283 |
+
"grad_norm": 0.2177734375,
|
| 2284 |
+
"learning_rate": 9.257873620862589e-05,
|
| 2285 |
+
"loss": 1.1747,
|
| 2286 |
+
"step": 7700
|
| 2287 |
+
},
|
| 2288 |
+
{
|
| 2289 |
+
"epoch": 6.665659399956832,
|
| 2290 |
+
"grad_norm": 0.2421875,
|
| 2291 |
+
"learning_rate": 9.255366098294886e-05,
|
| 2292 |
+
"loss": 1.2091,
|
| 2293 |
+
"step": 7725
|
| 2294 |
+
},
|
| 2295 |
+
{
|
| 2296 |
+
"epoch": 6.687243686596158,
|
| 2297 |
+
"grad_norm": 0.224609375,
|
| 2298 |
+
"learning_rate": 9.252858575727182e-05,
|
| 2299 |
+
"loss": 1.1983,
|
| 2300 |
+
"step": 7750
|
| 2301 |
+
},
|
| 2302 |
+
{
|
| 2303 |
+
"epoch": 6.7088279732354845,
|
| 2304 |
+
"grad_norm": 0.23828125,
|
| 2305 |
+
"learning_rate": 9.250351053159479e-05,
|
| 2306 |
+
"loss": 1.2251,
|
| 2307 |
+
"step": 7775
|
| 2308 |
+
},
|
| 2309 |
+
{
|
| 2310 |
+
"epoch": 6.730412259874811,
|
| 2311 |
+
"grad_norm": 0.33984375,
|
| 2312 |
+
"learning_rate": 9.247843530591775e-05,
|
| 2313 |
+
"loss": 1.0004,
|
| 2314 |
+
"step": 7800
|
| 2315 |
+
},
|
| 2316 |
+
{
|
| 2317 |
+
"epoch": 6.751996546514138,
|
| 2318 |
+
"grad_norm": 0.193359375,
|
| 2319 |
+
"learning_rate": 9.245336008024072e-05,
|
| 2320 |
+
"loss": 1.1761,
|
| 2321 |
+
"step": 7825
|
| 2322 |
+
},
|
| 2323 |
+
{
|
| 2324 |
+
"epoch": 6.773580833153464,
|
| 2325 |
+
"grad_norm": 0.2353515625,
|
| 2326 |
+
"learning_rate": 9.24282848545637e-05,
|
| 2327 |
+
"loss": 1.3334,
|
| 2328 |
+
"step": 7850
|
| 2329 |
+
},
|
| 2330 |
+
{
|
| 2331 |
+
"epoch": 6.795165119792791,
|
| 2332 |
+
"grad_norm": 0.2041015625,
|
| 2333 |
+
"learning_rate": 9.240320962888667e-05,
|
| 2334 |
+
"loss": 1.1361,
|
| 2335 |
+
"step": 7875
|
| 2336 |
+
},
|
| 2337 |
+
{
|
| 2338 |
+
"epoch": 6.816749406432118,
|
| 2339 |
+
"grad_norm": 0.1953125,
|
| 2340 |
+
"learning_rate": 9.237813440320963e-05,
|
| 2341 |
+
"loss": 1.2055,
|
| 2342 |
+
"step": 7900
|
| 2343 |
+
},
|
| 2344 |
+
{
|
| 2345 |
+
"epoch": 6.838333693071444,
|
| 2346 |
+
"grad_norm": 0.244140625,
|
| 2347 |
+
"learning_rate": 9.23530591775326e-05,
|
| 2348 |
+
"loss": 1.1913,
|
| 2349 |
+
"step": 7925
|
| 2350 |
+
},
|
| 2351 |
+
{
|
| 2352 |
+
"epoch": 6.8599179797107706,
|
| 2353 |
+
"grad_norm": 0.193359375,
|
| 2354 |
+
"learning_rate": 9.232798395185557e-05,
|
| 2355 |
+
"loss": 1.1817,
|
| 2356 |
+
"step": 7950
|
| 2357 |
+
},
|
| 2358 |
+
{
|
| 2359 |
+
"epoch": 6.881502266350097,
|
| 2360 |
+
"grad_norm": 0.2197265625,
|
| 2361 |
+
"learning_rate": 9.230290872617853e-05,
|
| 2362 |
+
"loss": 1.1405,
|
| 2363 |
+
"step": 7975
|
| 2364 |
+
},
|
| 2365 |
+
{
|
| 2366 |
+
"epoch": 6.903086552989424,
|
| 2367 |
+
"grad_norm": 0.255859375,
|
| 2368 |
+
"learning_rate": 9.227783350050151e-05,
|
| 2369 |
+
"loss": 1.0686,
|
| 2370 |
+
"step": 8000
|
| 2371 |
+
},
|
| 2372 |
+
{
|
| 2373 |
+
"epoch": 6.903086552989424,
|
| 2374 |
+
"eval_loss": 1.1845334768295288,
|
| 2375 |
+
"eval_runtime": 119.1754,
|
| 2376 |
+
"eval_samples_per_second": 4.195,
|
| 2377 |
+
"eval_steps_per_second": 4.195,
|
| 2378 |
+
"step": 8000
|
| 2379 |
+
},
|
| 2380 |
+
{
|
| 2381 |
+
"epoch": 6.92467083962875,
|
| 2382 |
+
"grad_norm": 0.2255859375,
|
| 2383 |
+
"learning_rate": 9.225275827482448e-05,
|
| 2384 |
+
"loss": 1.1093,
|
| 2385 |
+
"step": 8025
|
| 2386 |
+
},
|
| 2387 |
+
{
|
| 2388 |
+
"epoch": 6.946255126268077,
|
| 2389 |
+
"grad_norm": 0.431640625,
|
| 2390 |
+
"learning_rate": 9.222768304914744e-05,
|
| 2391 |
+
"loss": 1.1508,
|
| 2392 |
+
"step": 8050
|
| 2393 |
+
},
|
| 2394 |
+
{
|
| 2395 |
+
"epoch": 6.967839412907403,
|
| 2396 |
+
"grad_norm": 0.2392578125,
|
| 2397 |
+
"learning_rate": 9.220260782347041e-05,
|
| 2398 |
+
"loss": 1.1785,
|
| 2399 |
+
"step": 8075
|
| 2400 |
+
},
|
| 2401 |
+
{
|
| 2402 |
+
"epoch": 6.98942369954673,
|
| 2403 |
+
"grad_norm": 0.197265625,
|
| 2404 |
+
"learning_rate": 9.217753259779338e-05,
|
| 2405 |
+
"loss": 1.2516,
|
| 2406 |
+
"step": 8100
|
| 2407 |
+
},
|
| 2408 |
+
{
|
| 2409 |
+
"epoch": 7.010360457586876,
|
| 2410 |
+
"grad_norm": 0.1982421875,
|
| 2411 |
+
"learning_rate": 9.215245737211636e-05,
|
| 2412 |
+
"loss": 1.1401,
|
| 2413 |
+
"step": 8125
|
| 2414 |
+
},
|
| 2415 |
+
{
|
| 2416 |
+
"epoch": 7.0319447442262035,
|
| 2417 |
+
"grad_norm": 0.2099609375,
|
| 2418 |
+
"learning_rate": 9.212738214643932e-05,
|
| 2419 |
+
"loss": 0.9673,
|
| 2420 |
+
"step": 8150
|
| 2421 |
+
},
|
| 2422 |
+
{
|
| 2423 |
+
"epoch": 7.05352903086553,
|
| 2424 |
+
"grad_norm": 0.2333984375,
|
| 2425 |
+
"learning_rate": 9.210230692076229e-05,
|
| 2426 |
+
"loss": 1.2195,
|
| 2427 |
+
"step": 8175
|
| 2428 |
+
},
|
| 2429 |
+
{
|
| 2430 |
+
"epoch": 7.075113317504856,
|
| 2431 |
+
"grad_norm": 0.2373046875,
|
| 2432 |
+
"learning_rate": 9.207723169508527e-05,
|
| 2433 |
+
"loss": 1.1304,
|
| 2434 |
+
"step": 8200
|
| 2435 |
+
},
|
| 2436 |
+
{
|
| 2437 |
+
"epoch": 7.096697604144183,
|
| 2438 |
+
"grad_norm": 0.169921875,
|
| 2439 |
+
"learning_rate": 9.205215646940822e-05,
|
| 2440 |
+
"loss": 1.2657,
|
| 2441 |
+
"step": 8225
|
| 2442 |
+
},
|
| 2443 |
+
{
|
| 2444 |
+
"epoch": 7.11828189078351,
|
| 2445 |
+
"grad_norm": 0.2255859375,
|
| 2446 |
+
"learning_rate": 9.202708124373119e-05,
|
| 2447 |
+
"loss": 1.1376,
|
| 2448 |
+
"step": 8250
|
| 2449 |
+
},
|
| 2450 |
+
{
|
| 2451 |
+
"epoch": 7.139866177422836,
|
| 2452 |
+
"grad_norm": 0.2119140625,
|
| 2453 |
+
"learning_rate": 9.200200601805417e-05,
|
| 2454 |
+
"loss": 1.2825,
|
| 2455 |
+
"step": 8275
|
| 2456 |
+
},
|
| 2457 |
+
{
|
| 2458 |
+
"epoch": 7.161450464062162,
|
| 2459 |
+
"grad_norm": 0.25390625,
|
| 2460 |
+
"learning_rate": 9.197693079237714e-05,
|
| 2461 |
+
"loss": 1.1382,
|
| 2462 |
+
"step": 8300
|
| 2463 |
+
},
|
| 2464 |
+
{
|
| 2465 |
+
"epoch": 7.18303475070149,
|
| 2466 |
+
"grad_norm": 0.20703125,
|
| 2467 |
+
"learning_rate": 9.19518555667001e-05,
|
| 2468 |
+
"loss": 1.1377,
|
| 2469 |
+
"step": 8325
|
| 2470 |
+
},
|
| 2471 |
+
{
|
| 2472 |
+
"epoch": 7.204619037340816,
|
| 2473 |
+
"grad_norm": 0.1943359375,
|
| 2474 |
+
"learning_rate": 9.192678034102308e-05,
|
| 2475 |
+
"loss": 1.1458,
|
| 2476 |
+
"step": 8350
|
| 2477 |
+
},
|
| 2478 |
+
{
|
| 2479 |
+
"epoch": 7.226203323980142,
|
| 2480 |
+
"grad_norm": 0.2119140625,
|
| 2481 |
+
"learning_rate": 9.190170511534603e-05,
|
| 2482 |
+
"loss": 0.9699,
|
| 2483 |
+
"step": 8375
|
| 2484 |
+
},
|
| 2485 |
+
{
|
| 2486 |
+
"epoch": 7.247787610619469,
|
| 2487 |
+
"grad_norm": 0.1943359375,
|
| 2488 |
+
"learning_rate": 9.187662988966901e-05,
|
| 2489 |
+
"loss": 1.1423,
|
| 2490 |
+
"step": 8400
|
| 2491 |
+
},
|
| 2492 |
+
{
|
| 2493 |
+
"epoch": 7.269371897258796,
|
| 2494 |
+
"grad_norm": 0.197265625,
|
| 2495 |
+
"learning_rate": 9.185155466399198e-05,
|
| 2496 |
+
"loss": 1.0721,
|
| 2497 |
+
"step": 8425
|
| 2498 |
+
},
|
| 2499 |
+
{
|
| 2500 |
+
"epoch": 7.290956183898122,
|
| 2501 |
+
"grad_norm": 0.283203125,
|
| 2502 |
+
"learning_rate": 9.182647943831495e-05,
|
| 2503 |
+
"loss": 1.1735,
|
| 2504 |
+
"step": 8450
|
| 2505 |
+
},
|
| 2506 |
+
{
|
| 2507 |
+
"epoch": 7.312540470537448,
|
| 2508 |
+
"grad_norm": 0.2080078125,
|
| 2509 |
+
"learning_rate": 9.180140421263791e-05,
|
| 2510 |
+
"loss": 1.2096,
|
| 2511 |
+
"step": 8475
|
| 2512 |
+
},
|
| 2513 |
+
{
|
| 2514 |
+
"epoch": 7.334124757176776,
|
| 2515 |
+
"grad_norm": 0.21875,
|
| 2516 |
+
"learning_rate": 9.17763289869609e-05,
|
| 2517 |
+
"loss": 1.0578,
|
| 2518 |
+
"step": 8500
|
| 2519 |
+
},
|
| 2520 |
+
{
|
| 2521 |
+
"epoch": 7.334124757176776,
|
| 2522 |
+
"eval_loss": 1.1841206550598145,
|
| 2523 |
+
"eval_runtime": 118.5017,
|
| 2524 |
+
"eval_samples_per_second": 4.219,
|
| 2525 |
+
"eval_steps_per_second": 4.219,
|
| 2526 |
+
"step": 8500
|
| 2527 |
+
},
|
| 2528 |
+
{
|
| 2529 |
+
"epoch": 7.355709043816102,
|
| 2530 |
+
"grad_norm": 0.2421875,
|
| 2531 |
+
"learning_rate": 9.175125376128385e-05,
|
| 2532 |
+
"loss": 1.1644,
|
| 2533 |
+
"step": 8525
|
| 2534 |
+
},
|
| 2535 |
+
{
|
| 2536 |
+
"epoch": 7.377293330455428,
|
| 2537 |
+
"grad_norm": 0.1962890625,
|
| 2538 |
+
"learning_rate": 9.172617853560683e-05,
|
| 2539 |
+
"loss": 1.0903,
|
| 2540 |
+
"step": 8550
|
| 2541 |
+
},
|
| 2542 |
+
{
|
| 2543 |
+
"epoch": 7.3988776170947546,
|
| 2544 |
+
"grad_norm": 0.154296875,
|
| 2545 |
+
"learning_rate": 9.170110330992979e-05,
|
| 2546 |
+
"loss": 1.1404,
|
| 2547 |
+
"step": 8575
|
| 2548 |
+
},
|
| 2549 |
+
{
|
| 2550 |
+
"epoch": 7.420461903734082,
|
| 2551 |
+
"grad_norm": 0.2333984375,
|
| 2552 |
+
"learning_rate": 9.167602808425276e-05,
|
| 2553 |
+
"loss": 1.2855,
|
| 2554 |
+
"step": 8600
|
| 2555 |
+
},
|
| 2556 |
+
{
|
| 2557 |
+
"epoch": 7.442046190373408,
|
| 2558 |
+
"grad_norm": 0.380859375,
|
| 2559 |
+
"learning_rate": 9.165095285857574e-05,
|
| 2560 |
+
"loss": 1.0852,
|
| 2561 |
+
"step": 8625
|
| 2562 |
+
},
|
| 2563 |
+
{
|
| 2564 |
+
"epoch": 7.463630477012734,
|
| 2565 |
+
"grad_norm": 0.2158203125,
|
| 2566 |
+
"learning_rate": 9.16258776328987e-05,
|
| 2567 |
+
"loss": 1.3138,
|
| 2568 |
+
"step": 8650
|
| 2569 |
+
},
|
| 2570 |
+
{
|
| 2571 |
+
"epoch": 7.485214763652062,
|
| 2572 |
+
"grad_norm": 0.212890625,
|
| 2573 |
+
"learning_rate": 9.160080240722166e-05,
|
| 2574 |
+
"loss": 1.1759,
|
| 2575 |
+
"step": 8675
|
| 2576 |
+
},
|
| 2577 |
+
{
|
| 2578 |
+
"epoch": 7.506799050291388,
|
| 2579 |
+
"grad_norm": 0.2080078125,
|
| 2580 |
+
"learning_rate": 9.157572718154464e-05,
|
| 2581 |
+
"loss": 1.0517,
|
| 2582 |
+
"step": 8700
|
| 2583 |
+
},
|
| 2584 |
+
{
|
| 2585 |
+
"epoch": 7.528383336930714,
|
| 2586 |
+
"grad_norm": 0.2236328125,
|
| 2587 |
+
"learning_rate": 9.15506519558676e-05,
|
| 2588 |
+
"loss": 1.3831,
|
| 2589 |
+
"step": 8725
|
| 2590 |
+
},
|
| 2591 |
+
{
|
| 2592 |
+
"epoch": 7.549967623570041,
|
| 2593 |
+
"grad_norm": 0.2236328125,
|
| 2594 |
+
"learning_rate": 9.152557673019057e-05,
|
| 2595 |
+
"loss": 1.0559,
|
| 2596 |
+
"step": 8750
|
| 2597 |
+
},
|
| 2598 |
+
{
|
| 2599 |
+
"epoch": 7.571551910209368,
|
| 2600 |
+
"grad_norm": 0.197265625,
|
| 2601 |
+
"learning_rate": 9.150050150451355e-05,
|
| 2602 |
+
"loss": 1.2865,
|
| 2603 |
+
"step": 8775
|
| 2604 |
+
},
|
| 2605 |
+
{
|
| 2606 |
+
"epoch": 7.593136196848694,
|
| 2607 |
+
"grad_norm": 0.177734375,
|
| 2608 |
+
"learning_rate": 9.147542627883652e-05,
|
| 2609 |
+
"loss": 1.0873,
|
| 2610 |
+
"step": 8800
|
| 2611 |
+
},
|
| 2612 |
+
{
|
| 2613 |
+
"epoch": 7.61472048348802,
|
| 2614 |
+
"grad_norm": 0.2392578125,
|
| 2615 |
+
"learning_rate": 9.145035105315948e-05,
|
| 2616 |
+
"loss": 1.0765,
|
| 2617 |
+
"step": 8825
|
| 2618 |
+
},
|
| 2619 |
+
{
|
| 2620 |
+
"epoch": 7.636304770127348,
|
| 2621 |
+
"grad_norm": 0.279296875,
|
| 2622 |
+
"learning_rate": 9.142527582748245e-05,
|
| 2623 |
+
"loss": 1.0939,
|
| 2624 |
+
"step": 8850
|
| 2625 |
+
},
|
| 2626 |
+
{
|
| 2627 |
+
"epoch": 7.657889056766674,
|
| 2628 |
+
"grad_norm": 0.16015625,
|
| 2629 |
+
"learning_rate": 9.140020060180542e-05,
|
| 2630 |
+
"loss": 1.2058,
|
| 2631 |
+
"step": 8875
|
| 2632 |
+
},
|
| 2633 |
+
{
|
| 2634 |
+
"epoch": 7.679473343406,
|
| 2635 |
+
"grad_norm": 0.2021484375,
|
| 2636 |
+
"learning_rate": 9.13751253761284e-05,
|
| 2637 |
+
"loss": 1.0933,
|
| 2638 |
+
"step": 8900
|
| 2639 |
+
},
|
| 2640 |
+
{
|
| 2641 |
+
"epoch": 7.701057630045327,
|
| 2642 |
+
"grad_norm": 0.2197265625,
|
| 2643 |
+
"learning_rate": 9.135005015045136e-05,
|
| 2644 |
+
"loss": 1.1407,
|
| 2645 |
+
"step": 8925
|
| 2646 |
+
},
|
| 2647 |
+
{
|
| 2648 |
+
"epoch": 7.722641916684654,
|
| 2649 |
+
"grad_norm": 0.265625,
|
| 2650 |
+
"learning_rate": 9.132497492477433e-05,
|
| 2651 |
+
"loss": 1.1527,
|
| 2652 |
+
"step": 8950
|
| 2653 |
+
},
|
| 2654 |
+
{
|
| 2655 |
+
"epoch": 7.74422620332398,
|
| 2656 |
+
"grad_norm": 0.2412109375,
|
| 2657 |
+
"learning_rate": 9.12998996990973e-05,
|
| 2658 |
+
"loss": 1.1988,
|
| 2659 |
+
"step": 8975
|
| 2660 |
+
},
|
| 2661 |
+
{
|
| 2662 |
+
"epoch": 7.7658104899633065,
|
| 2663 |
+
"grad_norm": 0.1826171875,
|
| 2664 |
+
"learning_rate": 9.127482447342026e-05,
|
| 2665 |
+
"loss": 1.2294,
|
| 2666 |
+
"step": 9000
|
| 2667 |
+
},
|
| 2668 |
+
{
|
| 2669 |
+
"epoch": 7.7658104899633065,
|
| 2670 |
+
"eval_loss": 1.1831315755844116,
|
| 2671 |
+
"eval_runtime": 118.7044,
|
| 2672 |
+
"eval_samples_per_second": 4.212,
|
| 2673 |
+
"eval_steps_per_second": 4.212,
|
| 2674 |
+
"step": 9000
|
| 2675 |
+
},
|
| 2676 |
+
{
|
| 2677 |
+
"epoch": 7.787394776602634,
|
| 2678 |
+
"grad_norm": 0.216796875,
|
| 2679 |
+
"learning_rate": 9.124974924774323e-05,
|
| 2680 |
+
"loss": 1.0605,
|
| 2681 |
+
"step": 9025
|
| 2682 |
+
},
|
| 2683 |
+
{
|
| 2684 |
+
"epoch": 7.80897906324196,
|
| 2685 |
+
"grad_norm": 0.208984375,
|
| 2686 |
+
"learning_rate": 9.122467402206621e-05,
|
| 2687 |
+
"loss": 1.1654,
|
| 2688 |
+
"step": 9050
|
| 2689 |
+
},
|
| 2690 |
+
{
|
| 2691 |
+
"epoch": 7.830563349881286,
|
| 2692 |
+
"grad_norm": 0.2373046875,
|
| 2693 |
+
"learning_rate": 9.119959879638917e-05,
|
| 2694 |
+
"loss": 1.0824,
|
| 2695 |
+
"step": 9075
|
| 2696 |
+
},
|
| 2697 |
+
{
|
| 2698 |
+
"epoch": 7.852147636520613,
|
| 2699 |
+
"grad_norm": 0.21484375,
|
| 2700 |
+
"learning_rate": 9.117452357071214e-05,
|
| 2701 |
+
"loss": 1.1937,
|
| 2702 |
+
"step": 9100
|
| 2703 |
+
},
|
| 2704 |
+
{
|
| 2705 |
+
"epoch": 7.87373192315994,
|
| 2706 |
+
"grad_norm": 0.2294921875,
|
| 2707 |
+
"learning_rate": 9.11494483450351e-05,
|
| 2708 |
+
"loss": 1.1615,
|
| 2709 |
+
"step": 9125
|
| 2710 |
+
},
|
| 2711 |
+
{
|
| 2712 |
+
"epoch": 7.895316209799266,
|
| 2713 |
+
"grad_norm": 0.234375,
|
| 2714 |
+
"learning_rate": 9.112437311935807e-05,
|
| 2715 |
+
"loss": 1.151,
|
| 2716 |
+
"step": 9150
|
| 2717 |
+
},
|
| 2718 |
+
{
|
| 2719 |
+
"epoch": 7.9169004964385925,
|
| 2720 |
+
"grad_norm": 0.197265625,
|
| 2721 |
+
"learning_rate": 9.109929789368104e-05,
|
| 2722 |
+
"loss": 1.1793,
|
| 2723 |
+
"step": 9175
|
| 2724 |
+
},
|
| 2725 |
+
{
|
| 2726 |
+
"epoch": 7.93848478307792,
|
| 2727 |
+
"grad_norm": 0.220703125,
|
| 2728 |
+
"learning_rate": 9.107422266800402e-05,
|
| 2729 |
+
"loss": 1.2839,
|
| 2730 |
+
"step": 9200
|
| 2731 |
+
},
|
| 2732 |
+
{
|
| 2733 |
+
"epoch": 7.960069069717246,
|
| 2734 |
+
"grad_norm": 0.1796875,
|
| 2735 |
+
"learning_rate": 9.104914744232699e-05,
|
| 2736 |
+
"loss": 1.1156,
|
| 2737 |
+
"step": 9225
|
| 2738 |
+
},
|
| 2739 |
+
{
|
| 2740 |
+
"epoch": 7.981653356356572,
|
| 2741 |
+
"grad_norm": 0.1875,
|
| 2742 |
+
"learning_rate": 9.102407221664995e-05,
|
| 2743 |
+
"loss": 1.0741,
|
| 2744 |
+
"step": 9250
|
| 2745 |
+
},
|
| 2746 |
+
{
|
| 2747 |
+
"epoch": 8.00259011439672,
|
| 2748 |
+
"grad_norm": 0.1806640625,
|
| 2749 |
+
"learning_rate": 9.099899699097292e-05,
|
| 2750 |
+
"loss": 1.1194,
|
| 2751 |
+
"step": 9275
|
| 2752 |
+
},
|
| 2753 |
+
{
|
| 2754 |
+
"epoch": 8.024174401036046,
|
| 2755 |
+
"grad_norm": 0.220703125,
|
| 2756 |
+
"learning_rate": 9.097392176529588e-05,
|
| 2757 |
+
"loss": 0.9522,
|
| 2758 |
+
"step": 9300
|
| 2759 |
+
},
|
| 2760 |
+
{
|
| 2761 |
+
"epoch": 8.045758687675372,
|
| 2762 |
+
"grad_norm": 0.2177734375,
|
| 2763 |
+
"learning_rate": 9.094884653961886e-05,
|
| 2764 |
+
"loss": 1.2578,
|
| 2765 |
+
"step": 9325
|
| 2766 |
+
},
|
| 2767 |
+
{
|
| 2768 |
+
"epoch": 8.067342974314698,
|
| 2769 |
+
"grad_norm": 0.2177734375,
|
| 2770 |
+
"learning_rate": 9.092377131394183e-05,
|
| 2771 |
+
"loss": 1.1278,
|
| 2772 |
+
"step": 9350
|
| 2773 |
+
},
|
| 2774 |
+
{
|
| 2775 |
+
"epoch": 8.088927260954025,
|
| 2776 |
+
"grad_norm": 0.251953125,
|
| 2777 |
+
"learning_rate": 9.08986960882648e-05,
|
| 2778 |
+
"loss": 1.2299,
|
| 2779 |
+
"step": 9375
|
| 2780 |
+
},
|
| 2781 |
+
{
|
| 2782 |
+
"epoch": 8.110511547593353,
|
| 2783 |
+
"grad_norm": 0.24609375,
|
| 2784 |
+
"learning_rate": 9.087362086258778e-05,
|
| 2785 |
+
"loss": 1.2605,
|
| 2786 |
+
"step": 9400
|
| 2787 |
+
},
|
| 2788 |
+
{
|
| 2789 |
+
"epoch": 8.132095834232679,
|
| 2790 |
+
"grad_norm": 0.2265625,
|
| 2791 |
+
"learning_rate": 9.084854563691073e-05,
|
| 2792 |
+
"loss": 1.0537,
|
| 2793 |
+
"step": 9425
|
| 2794 |
+
},
|
| 2795 |
+
{
|
| 2796 |
+
"epoch": 8.153680120872005,
|
| 2797 |
+
"grad_norm": 0.2333984375,
|
| 2798 |
+
"learning_rate": 9.08234704112337e-05,
|
| 2799 |
+
"loss": 0.986,
|
| 2800 |
+
"step": 9450
|
| 2801 |
+
},
|
| 2802 |
+
{
|
| 2803 |
+
"epoch": 8.175264407511332,
|
| 2804 |
+
"grad_norm": 0.201171875,
|
| 2805 |
+
"learning_rate": 9.079839518555668e-05,
|
| 2806 |
+
"loss": 1.1083,
|
| 2807 |
+
"step": 9475
|
| 2808 |
+
},
|
| 2809 |
+
{
|
| 2810 |
+
"epoch": 8.196848694150658,
|
| 2811 |
+
"grad_norm": 0.1787109375,
|
| 2812 |
+
"learning_rate": 9.077331995987964e-05,
|
| 2813 |
+
"loss": 1.1064,
|
| 2814 |
+
"step": 9500
|
| 2815 |
+
},
|
| 2816 |
+
{
|
| 2817 |
+
"epoch": 8.196848694150658,
|
| 2818 |
+
"eval_loss": 1.1820403337478638,
|
| 2819 |
+
"eval_runtime": 119.2179,
|
| 2820 |
+
"eval_samples_per_second": 4.194,
|
| 2821 |
+
"eval_steps_per_second": 4.194,
|
| 2822 |
+
"step": 9500
|
| 2823 |
+
},
|
| 2824 |
+
{
|
| 2825 |
+
"epoch": 8.218432980789984,
|
| 2826 |
+
"grad_norm": 0.19921875,
|
| 2827 |
+
"learning_rate": 9.074824473420261e-05,
|
| 2828 |
+
"loss": 1.1408,
|
| 2829 |
+
"step": 9525
|
| 2830 |
+
},
|
| 2831 |
+
{
|
| 2832 |
+
"epoch": 8.24001726742931,
|
| 2833 |
+
"grad_norm": 0.2041015625,
|
| 2834 |
+
"learning_rate": 9.072316950852559e-05,
|
| 2835 |
+
"loss": 1.2541,
|
| 2836 |
+
"step": 9550
|
| 2837 |
+
},
|
| 2838 |
+
{
|
| 2839 |
+
"epoch": 8.261601554068639,
|
| 2840 |
+
"grad_norm": 0.1728515625,
|
| 2841 |
+
"learning_rate": 9.069809428284854e-05,
|
| 2842 |
+
"loss": 1.1157,
|
| 2843 |
+
"step": 9575
|
| 2844 |
+
},
|
| 2845 |
+
{
|
| 2846 |
+
"epoch": 8.283185840707965,
|
| 2847 |
+
"grad_norm": 0.16796875,
|
| 2848 |
+
"learning_rate": 9.067301905717152e-05,
|
| 2849 |
+
"loss": 0.9584,
|
| 2850 |
+
"step": 9600
|
| 2851 |
+
},
|
| 2852 |
+
{
|
| 2853 |
+
"epoch": 8.304770127347291,
|
| 2854 |
+
"grad_norm": 0.2373046875,
|
| 2855 |
+
"learning_rate": 9.064794383149449e-05,
|
| 2856 |
+
"loss": 1.1505,
|
| 2857 |
+
"step": 9625
|
| 2858 |
+
},
|
| 2859 |
+
{
|
| 2860 |
+
"epoch": 8.326354413986618,
|
| 2861 |
+
"grad_norm": 0.2412109375,
|
| 2862 |
+
"learning_rate": 9.062286860581745e-05,
|
| 2863 |
+
"loss": 1.1527,
|
| 2864 |
+
"step": 9650
|
| 2865 |
+
},
|
| 2866 |
+
{
|
| 2867 |
+
"epoch": 8.347938700625944,
|
| 2868 |
+
"grad_norm": 0.298828125,
|
| 2869 |
+
"learning_rate": 9.059779338014043e-05,
|
| 2870 |
+
"loss": 1.151,
|
| 2871 |
+
"step": 9675
|
| 2872 |
+
},
|
| 2873 |
+
{
|
| 2874 |
+
"epoch": 8.36952298726527,
|
| 2875 |
+
"grad_norm": 0.216796875,
|
| 2876 |
+
"learning_rate": 9.05727181544634e-05,
|
| 2877 |
+
"loss": 1.2479,
|
| 2878 |
+
"step": 9700
|
| 2879 |
+
},
|
| 2880 |
+
{
|
| 2881 |
+
"epoch": 8.391107273904597,
|
| 2882 |
+
"grad_norm": 0.283203125,
|
| 2883 |
+
"learning_rate": 9.054764292878635e-05,
|
| 2884 |
+
"loss": 1.2619,
|
| 2885 |
+
"step": 9725
|
| 2886 |
+
},
|
| 2887 |
+
{
|
| 2888 |
+
"epoch": 8.412691560543925,
|
| 2889 |
+
"grad_norm": 0.220703125,
|
| 2890 |
+
"learning_rate": 9.052256770310933e-05,
|
| 2891 |
+
"loss": 1.1102,
|
| 2892 |
+
"step": 9750
|
| 2893 |
+
},
|
| 2894 |
+
{
|
| 2895 |
+
"epoch": 8.434275847183251,
|
| 2896 |
+
"grad_norm": 0.1708984375,
|
| 2897 |
+
"learning_rate": 9.04974924774323e-05,
|
| 2898 |
+
"loss": 1.0815,
|
| 2899 |
+
"step": 9775
|
| 2900 |
+
},
|
| 2901 |
+
{
|
| 2902 |
+
"epoch": 8.455860133822577,
|
| 2903 |
+
"grad_norm": 0.193359375,
|
| 2904 |
+
"learning_rate": 9.047241725175527e-05,
|
| 2905 |
+
"loss": 1.1504,
|
| 2906 |
+
"step": 9800
|
| 2907 |
+
},
|
| 2908 |
+
{
|
| 2909 |
+
"epoch": 8.477444420461904,
|
| 2910 |
+
"grad_norm": 0.1923828125,
|
| 2911 |
+
"learning_rate": 9.044734202607825e-05,
|
| 2912 |
+
"loss": 1.1213,
|
| 2913 |
+
"step": 9825
|
| 2914 |
+
},
|
| 2915 |
+
{
|
| 2916 |
+
"epoch": 8.49902870710123,
|
| 2917 |
+
"grad_norm": 0.283203125,
|
| 2918 |
+
"learning_rate": 9.042226680040121e-05,
|
| 2919 |
+
"loss": 1.1919,
|
| 2920 |
+
"step": 9850
|
| 2921 |
+
},
|
| 2922 |
+
{
|
| 2923 |
+
"epoch": 8.520612993740556,
|
| 2924 |
+
"grad_norm": 0.212890625,
|
| 2925 |
+
"learning_rate": 9.039719157472416e-05,
|
| 2926 |
+
"loss": 1.1695,
|
| 2927 |
+
"step": 9875
|
| 2928 |
+
},
|
| 2929 |
+
{
|
| 2930 |
+
"epoch": 8.542197280379883,
|
| 2931 |
+
"grad_norm": 0.212890625,
|
| 2932 |
+
"learning_rate": 9.037211634904714e-05,
|
| 2933 |
+
"loss": 1.0681,
|
| 2934 |
+
"step": 9900
|
| 2935 |
+
},
|
| 2936 |
+
{
|
| 2937 |
+
"epoch": 8.56378156701921,
|
| 2938 |
+
"grad_norm": 0.25390625,
|
| 2939 |
+
"learning_rate": 9.034704112337011e-05,
|
| 2940 |
+
"loss": 1.2605,
|
| 2941 |
+
"step": 9925
|
| 2942 |
+
},
|
| 2943 |
+
{
|
| 2944 |
+
"epoch": 8.585365853658537,
|
| 2945 |
+
"grad_norm": 0.205078125,
|
| 2946 |
+
"learning_rate": 9.032196589769308e-05,
|
| 2947 |
+
"loss": 1.0834,
|
| 2948 |
+
"step": 9950
|
| 2949 |
+
},
|
| 2950 |
+
{
|
| 2951 |
+
"epoch": 8.606950140297863,
|
| 2952 |
+
"grad_norm": 0.2451171875,
|
| 2953 |
+
"learning_rate": 9.029689067201606e-05,
|
| 2954 |
+
"loss": 1.2253,
|
| 2955 |
+
"step": 9975
|
| 2956 |
+
},
|
| 2957 |
+
{
|
| 2958 |
+
"epoch": 8.62853442693719,
|
| 2959 |
+
"grad_norm": 0.38671875,
|
| 2960 |
+
"learning_rate": 9.027181544633902e-05,
|
| 2961 |
+
"loss": 1.1097,
|
| 2962 |
+
"step": 10000
|
| 2963 |
+
},
|
| 2964 |
+
{
|
| 2965 |
+
"epoch": 8.62853442693719,
|
| 2966 |
+
"eval_loss": 1.1815690994262695,
|
| 2967 |
+
"eval_runtime": 117.6085,
|
| 2968 |
+
"eval_samples_per_second": 4.251,
|
| 2969 |
+
"eval_steps_per_second": 4.251,
|
| 2970 |
+
"step": 10000
|
| 2971 |
+
},
|
| 2972 |
+
{
|
| 2973 |
+
"epoch": 8.650118713576516,
|
| 2974 |
+
"grad_norm": 0.244140625,
|
| 2975 |
+
"learning_rate": 9.024674022066199e-05,
|
| 2976 |
+
"loss": 1.1,
|
| 2977 |
+
"step": 10025
|
| 2978 |
+
},
|
| 2979 |
+
{
|
| 2980 |
+
"epoch": 8.671703000215842,
|
| 2981 |
+
"grad_norm": 0.2373046875,
|
| 2982 |
+
"learning_rate": 9.022166499498496e-05,
|
| 2983 |
+
"loss": 1.2114,
|
| 2984 |
+
"step": 10050
|
| 2985 |
+
},
|
| 2986 |
+
{
|
| 2987 |
+
"epoch": 8.693287286855169,
|
| 2988 |
+
"grad_norm": 0.2099609375,
|
| 2989 |
+
"learning_rate": 9.019658976930792e-05,
|
| 2990 |
+
"loss": 1.1201,
|
| 2991 |
+
"step": 10075
|
| 2992 |
+
},
|
| 2993 |
+
{
|
| 2994 |
+
"epoch": 8.714871573494497,
|
| 2995 |
+
"grad_norm": 0.181640625,
|
| 2996 |
+
"learning_rate": 9.01715145436309e-05,
|
| 2997 |
+
"loss": 1.0469,
|
| 2998 |
+
"step": 10100
|
| 2999 |
+
},
|
| 3000 |
+
{
|
| 3001 |
+
"epoch": 8.736455860133823,
|
| 3002 |
+
"grad_norm": 0.185546875,
|
| 3003 |
+
"learning_rate": 9.014643931795387e-05,
|
| 3004 |
+
"loss": 1.1822,
|
| 3005 |
+
"step": 10125
|
| 3006 |
+
},
|
| 3007 |
+
{
|
| 3008 |
+
"epoch": 8.75804014677315,
|
| 3009 |
+
"grad_norm": 0.205078125,
|
| 3010 |
+
"learning_rate": 9.012136409227684e-05,
|
| 3011 |
+
"loss": 1.059,
|
| 3012 |
+
"step": 10150
|
| 3013 |
+
},
|
| 3014 |
+
{
|
| 3015 |
+
"epoch": 8.779624433412476,
|
| 3016 |
+
"grad_norm": 0.2216796875,
|
| 3017 |
+
"learning_rate": 9.00962888665998e-05,
|
| 3018 |
+
"loss": 1.175,
|
| 3019 |
+
"step": 10175
|
| 3020 |
+
},
|
| 3021 |
+
{
|
| 3022 |
+
"epoch": 8.801208720051802,
|
| 3023 |
+
"grad_norm": 0.166015625,
|
| 3024 |
+
"learning_rate": 9.007121364092277e-05,
|
| 3025 |
+
"loss": 1.2437,
|
| 3026 |
+
"step": 10200
|
| 3027 |
+
},
|
| 3028 |
+
{
|
| 3029 |
+
"epoch": 8.822793006691128,
|
| 3030 |
+
"grad_norm": 0.2177734375,
|
| 3031 |
+
"learning_rate": 9.004613841524573e-05,
|
| 3032 |
+
"loss": 1.2238,
|
| 3033 |
+
"step": 10225
|
| 3034 |
+
},
|
| 3035 |
+
{
|
| 3036 |
+
"epoch": 8.844377293330455,
|
| 3037 |
+
"grad_norm": 0.2236328125,
|
| 3038 |
+
"learning_rate": 9.002106318956871e-05,
|
| 3039 |
+
"loss": 1.234,
|
| 3040 |
+
"step": 10250
|
| 3041 |
+
},
|
| 3042 |
+
{
|
| 3043 |
+
"epoch": 8.865961579969781,
|
| 3044 |
+
"grad_norm": 0.212890625,
|
| 3045 |
+
"learning_rate": 8.999598796389168e-05,
|
| 3046 |
+
"loss": 1.2763,
|
| 3047 |
+
"step": 10275
|
| 3048 |
+
},
|
| 3049 |
+
{
|
| 3050 |
+
"epoch": 8.88754586660911,
|
| 3051 |
+
"grad_norm": 0.2333984375,
|
| 3052 |
+
"learning_rate": 8.997091273821465e-05,
|
| 3053 |
+
"loss": 1.2638,
|
| 3054 |
+
"step": 10300
|
| 3055 |
+
},
|
| 3056 |
+
{
|
| 3057 |
+
"epoch": 8.909130153248435,
|
| 3058 |
+
"grad_norm": 0.220703125,
|
| 3059 |
+
"learning_rate": 8.994583751253761e-05,
|
| 3060 |
+
"loss": 1.1188,
|
| 3061 |
+
"step": 10325
|
| 3062 |
+
},
|
| 3063 |
+
{
|
| 3064 |
+
"epoch": 8.930714439887762,
|
| 3065 |
+
"grad_norm": 0.28125,
|
| 3066 |
+
"learning_rate": 8.992076228686058e-05,
|
| 3067 |
+
"loss": 1.1901,
|
| 3068 |
+
"step": 10350
|
| 3069 |
+
},
|
| 3070 |
+
{
|
| 3071 |
+
"epoch": 8.952298726527088,
|
| 3072 |
+
"grad_norm": 0.21484375,
|
| 3073 |
+
"learning_rate": 8.989568706118356e-05,
|
| 3074 |
+
"loss": 1.0863,
|
| 3075 |
+
"step": 10375
|
| 3076 |
+
},
|
| 3077 |
+
{
|
| 3078 |
+
"epoch": 8.973883013166414,
|
| 3079 |
+
"grad_norm": 0.2099609375,
|
| 3080 |
+
"learning_rate": 8.987061183550653e-05,
|
| 3081 |
+
"loss": 1.1654,
|
| 3082 |
+
"step": 10400
|
| 3083 |
+
},
|
| 3084 |
+
{
|
| 3085 |
+
"epoch": 8.99546729980574,
|
| 3086 |
+
"grad_norm": 0.2294921875,
|
| 3087 |
+
"learning_rate": 8.984553660982949e-05,
|
| 3088 |
+
"loss": 1.1655,
|
| 3089 |
+
"step": 10425
|
| 3090 |
+
},
|
| 3091 |
+
{
|
| 3092 |
+
"epoch": 9.016404057845888,
|
| 3093 |
+
"grad_norm": 0.2265625,
|
| 3094 |
+
"learning_rate": 8.982046138415246e-05,
|
| 3095 |
+
"loss": 1.1653,
|
| 3096 |
+
"step": 10450
|
| 3097 |
+
},
|
| 3098 |
+
{
|
| 3099 |
+
"epoch": 9.037988344485214,
|
| 3100 |
+
"grad_norm": 0.1904296875,
|
| 3101 |
+
"learning_rate": 8.979538615847543e-05,
|
| 3102 |
+
"loss": 1.0543,
|
| 3103 |
+
"step": 10475
|
| 3104 |
+
},
|
| 3105 |
+
{
|
| 3106 |
+
"epoch": 9.059572631124542,
|
| 3107 |
+
"grad_norm": 0.1787109375,
|
| 3108 |
+
"learning_rate": 8.977031093279839e-05,
|
| 3109 |
+
"loss": 1.0627,
|
| 3110 |
+
"step": 10500
|
| 3111 |
+
},
|
| 3112 |
+
{
|
| 3113 |
+
"epoch": 9.059572631124542,
|
| 3114 |
+
"eval_loss": 1.181234359741211,
|
| 3115 |
+
"eval_runtime": 118.6511,
|
| 3116 |
+
"eval_samples_per_second": 4.214,
|
| 3117 |
+
"eval_steps_per_second": 4.214,
|
| 3118 |
+
"step": 10500
|
| 3119 |
+
},
|
| 3120 |
+
{
|
| 3121 |
+
"epoch": 9.081156917763868,
|
| 3122 |
+
"grad_norm": 0.2109375,
|
| 3123 |
+
"learning_rate": 8.974523570712137e-05,
|
| 3124 |
+
"loss": 1.118,
|
| 3125 |
+
"step": 10525
|
| 3126 |
+
},
|
| 3127 |
+
{
|
| 3128 |
+
"epoch": 9.102741204403195,
|
| 3129 |
+
"grad_norm": 0.1875,
|
| 3130 |
+
"learning_rate": 8.972016048144434e-05,
|
| 3131 |
+
"loss": 1.1308,
|
| 3132 |
+
"step": 10550
|
| 3133 |
+
},
|
| 3134 |
+
{
|
| 3135 |
+
"epoch": 9.124325491042521,
|
| 3136 |
+
"grad_norm": 0.28125,
|
| 3137 |
+
"learning_rate": 8.96950852557673e-05,
|
| 3138 |
+
"loss": 1.2378,
|
| 3139 |
+
"step": 10575
|
| 3140 |
+
},
|
| 3141 |
+
{
|
| 3142 |
+
"epoch": 9.145909777681847,
|
| 3143 |
+
"grad_norm": 0.1943359375,
|
| 3144 |
+
"learning_rate": 8.967001003009028e-05,
|
| 3145 |
+
"loss": 1.0929,
|
| 3146 |
+
"step": 10600
|
| 3147 |
+
},
|
| 3148 |
+
{
|
| 3149 |
+
"epoch": 9.167494064321174,
|
| 3150 |
+
"grad_norm": 0.2001953125,
|
| 3151 |
+
"learning_rate": 8.964493480441324e-05,
|
| 3152 |
+
"loss": 1.2355,
|
| 3153 |
+
"step": 10625
|
| 3154 |
+
},
|
| 3155 |
+
{
|
| 3156 |
+
"epoch": 9.1890783509605,
|
| 3157 |
+
"grad_norm": 0.48046875,
|
| 3158 |
+
"learning_rate": 8.96198595787362e-05,
|
| 3159 |
+
"loss": 1.3411,
|
| 3160 |
+
"step": 10650
|
| 3161 |
+
},
|
| 3162 |
+
{
|
| 3163 |
+
"epoch": 9.210662637599828,
|
| 3164 |
+
"grad_norm": 0.2177734375,
|
| 3165 |
+
"learning_rate": 8.959478435305918e-05,
|
| 3166 |
+
"loss": 1.0872,
|
| 3167 |
+
"step": 10675
|
| 3168 |
+
},
|
| 3169 |
+
{
|
| 3170 |
+
"epoch": 9.232246924239154,
|
| 3171 |
+
"grad_norm": 0.205078125,
|
| 3172 |
+
"learning_rate": 8.956970912738215e-05,
|
| 3173 |
+
"loss": 1.1367,
|
| 3174 |
+
"step": 10700
|
| 3175 |
+
},
|
| 3176 |
+
{
|
| 3177 |
+
"epoch": 9.25383121087848,
|
| 3178 |
+
"grad_norm": 0.24609375,
|
| 3179 |
+
"learning_rate": 8.954463390170512e-05,
|
| 3180 |
+
"loss": 1.1535,
|
| 3181 |
+
"step": 10725
|
| 3182 |
+
},
|
| 3183 |
+
{
|
| 3184 |
+
"epoch": 9.275415497517807,
|
| 3185 |
+
"grad_norm": 0.26171875,
|
| 3186 |
+
"learning_rate": 8.95195586760281e-05,
|
| 3187 |
+
"loss": 1.171,
|
| 3188 |
+
"step": 10750
|
| 3189 |
+
},
|
| 3190 |
+
{
|
| 3191 |
+
"epoch": 9.296999784157133,
|
| 3192 |
+
"grad_norm": 0.224609375,
|
| 3193 |
+
"learning_rate": 8.949448345035105e-05,
|
| 3194 |
+
"loss": 1.1827,
|
| 3195 |
+
"step": 10775
|
| 3196 |
+
},
|
| 3197 |
+
{
|
| 3198 |
+
"epoch": 9.31858407079646,
|
| 3199 |
+
"grad_norm": 0.271484375,
|
| 3200 |
+
"learning_rate": 8.946940822467403e-05,
|
| 3201 |
+
"loss": 1.2406,
|
| 3202 |
+
"step": 10800
|
| 3203 |
+
},
|
| 3204 |
+
{
|
| 3205 |
+
"epoch": 9.340168357435786,
|
| 3206 |
+
"grad_norm": 0.2099609375,
|
| 3207 |
+
"learning_rate": 8.9444332998997e-05,
|
| 3208 |
+
"loss": 1.091,
|
| 3209 |
+
"step": 10825
|
| 3210 |
+
},
|
| 3211 |
+
{
|
| 3212 |
+
"epoch": 9.361752644075114,
|
| 3213 |
+
"grad_norm": 0.2001953125,
|
| 3214 |
+
"learning_rate": 8.941925777331996e-05,
|
| 3215 |
+
"loss": 1.2404,
|
| 3216 |
+
"step": 10850
|
| 3217 |
+
},
|
| 3218 |
+
{
|
| 3219 |
+
"epoch": 9.38333693071444,
|
| 3220 |
+
"grad_norm": 0.240234375,
|
| 3221 |
+
"learning_rate": 8.939418254764294e-05,
|
| 3222 |
+
"loss": 1.1678,
|
| 3223 |
+
"step": 10875
|
| 3224 |
+
},
|
| 3225 |
+
{
|
| 3226 |
+
"epoch": 9.404921217353767,
|
| 3227 |
+
"grad_norm": 0.2470703125,
|
| 3228 |
+
"learning_rate": 8.936910732196591e-05,
|
| 3229 |
+
"loss": 1.0658,
|
| 3230 |
+
"step": 10900
|
| 3231 |
+
},
|
| 3232 |
+
{
|
| 3233 |
+
"epoch": 9.426505503993093,
|
| 3234 |
+
"grad_norm": 0.2236328125,
|
| 3235 |
+
"learning_rate": 8.934403209628886e-05,
|
| 3236 |
+
"loss": 1.2934,
|
| 3237 |
+
"step": 10925
|
| 3238 |
+
},
|
| 3239 |
+
{
|
| 3240 |
+
"epoch": 9.44808979063242,
|
| 3241 |
+
"grad_norm": 0.1884765625,
|
| 3242 |
+
"learning_rate": 8.931895687061184e-05,
|
| 3243 |
+
"loss": 0.9592,
|
| 3244 |
+
"step": 10950
|
| 3245 |
+
},
|
| 3246 |
+
{
|
| 3247 |
+
"epoch": 9.469674077271746,
|
| 3248 |
+
"grad_norm": 0.2099609375,
|
| 3249 |
+
"learning_rate": 8.92938816449348e-05,
|
| 3250 |
+
"loss": 1.211,
|
| 3251 |
+
"step": 10975
|
| 3252 |
+
},
|
| 3253 |
+
{
|
| 3254 |
+
"epoch": 9.491258363911072,
|
| 3255 |
+
"grad_norm": 0.279296875,
|
| 3256 |
+
"learning_rate": 8.926880641925777e-05,
|
| 3257 |
+
"loss": 1.1496,
|
| 3258 |
+
"step": 11000
|
| 3259 |
+
},
|
| 3260 |
+
{
|
| 3261 |
+
"epoch": 9.491258363911072,
|
| 3262 |
+
"eval_loss": 1.180627465248108,
|
| 3263 |
+
"eval_runtime": 118.3608,
|
| 3264 |
+
"eval_samples_per_second": 4.224,
|
| 3265 |
+
"eval_steps_per_second": 4.224,
|
| 3266 |
+
"step": 11000
|
| 3267 |
+
},
|
| 3268 |
+
{
|
| 3269 |
+
"epoch": 9.5128426505504,
|
| 3270 |
+
"grad_norm": 0.21484375,
|
| 3271 |
+
"learning_rate": 8.924373119358075e-05,
|
| 3272 |
+
"loss": 1.0245,
|
| 3273 |
+
"step": 11025
|
| 3274 |
+
},
|
| 3275 |
+
{
|
| 3276 |
+
"epoch": 9.534426937189727,
|
| 3277 |
+
"grad_norm": 0.224609375,
|
| 3278 |
+
"learning_rate": 8.921865596790372e-05,
|
| 3279 |
+
"loss": 1.1634,
|
| 3280 |
+
"step": 11050
|
| 3281 |
+
},
|
| 3282 |
+
{
|
| 3283 |
+
"epoch": 9.556011223829053,
|
| 3284 |
+
"grad_norm": 0.2041015625,
|
| 3285 |
+
"learning_rate": 8.919358074222669e-05,
|
| 3286 |
+
"loss": 1.1779,
|
| 3287 |
+
"step": 11075
|
| 3288 |
+
},
|
| 3289 |
+
{
|
| 3290 |
+
"epoch": 9.57759551046838,
|
| 3291 |
+
"grad_norm": 0.2041015625,
|
| 3292 |
+
"learning_rate": 8.916850551654965e-05,
|
| 3293 |
+
"loss": 1.1216,
|
| 3294 |
+
"step": 11100
|
| 3295 |
+
},
|
| 3296 |
+
{
|
| 3297 |
+
"epoch": 9.599179797107706,
|
| 3298 |
+
"grad_norm": 0.2119140625,
|
| 3299 |
+
"learning_rate": 8.914343029087262e-05,
|
| 3300 |
+
"loss": 1.1669,
|
| 3301 |
+
"step": 11125
|
| 3302 |
+
},
|
| 3303 |
+
{
|
| 3304 |
+
"epoch": 9.620764083747032,
|
| 3305 |
+
"grad_norm": 0.2099609375,
|
| 3306 |
+
"learning_rate": 8.911835506519558e-05,
|
| 3307 |
+
"loss": 1.0702,
|
| 3308 |
+
"step": 11150
|
| 3309 |
+
},
|
| 3310 |
+
{
|
| 3311 |
+
"epoch": 9.642348370386358,
|
| 3312 |
+
"grad_norm": 0.25,
|
| 3313 |
+
"learning_rate": 8.909327983951856e-05,
|
| 3314 |
+
"loss": 1.2574,
|
| 3315 |
+
"step": 11175
|
| 3316 |
+
},
|
| 3317 |
+
{
|
| 3318 |
+
"epoch": 9.663932657025684,
|
| 3319 |
+
"grad_norm": 0.2490234375,
|
| 3320 |
+
"learning_rate": 8.906820461384153e-05,
|
| 3321 |
+
"loss": 1.2782,
|
| 3322 |
+
"step": 11200
|
| 3323 |
+
},
|
| 3324 |
+
{
|
| 3325 |
+
"epoch": 9.685516943665013,
|
| 3326 |
+
"grad_norm": 0.228515625,
|
| 3327 |
+
"learning_rate": 8.90431293881645e-05,
|
| 3328 |
+
"loss": 0.999,
|
| 3329 |
+
"step": 11225
|
| 3330 |
+
},
|
| 3331 |
+
{
|
| 3332 |
+
"epoch": 9.707101230304339,
|
| 3333 |
+
"grad_norm": 0.1943359375,
|
| 3334 |
+
"learning_rate": 8.901805416248746e-05,
|
| 3335 |
+
"loss": 1.2004,
|
| 3336 |
+
"step": 11250
|
| 3337 |
+
},
|
| 3338 |
+
{
|
| 3339 |
+
"epoch": 9.728685516943665,
|
| 3340 |
+
"grad_norm": 0.279296875,
|
| 3341 |
+
"learning_rate": 8.899297893681043e-05,
|
| 3342 |
+
"loss": 1.2429,
|
| 3343 |
+
"step": 11275
|
| 3344 |
+
},
|
| 3345 |
+
{
|
| 3346 |
+
"epoch": 9.750269803582992,
|
| 3347 |
+
"grad_norm": 0.2890625,
|
| 3348 |
+
"learning_rate": 8.896790371113341e-05,
|
| 3349 |
+
"loss": 1.1644,
|
| 3350 |
+
"step": 11300
|
| 3351 |
+
},
|
| 3352 |
+
{
|
| 3353 |
+
"epoch": 9.771854090222318,
|
| 3354 |
+
"grad_norm": 0.240234375,
|
| 3355 |
+
"learning_rate": 8.894282848545638e-05,
|
| 3356 |
+
"loss": 1.1337,
|
| 3357 |
+
"step": 11325
|
| 3358 |
+
},
|
| 3359 |
+
{
|
| 3360 |
+
"epoch": 9.793438376861644,
|
| 3361 |
+
"grad_norm": 0.236328125,
|
| 3362 |
+
"learning_rate": 8.891775325977934e-05,
|
| 3363 |
+
"loss": 1.0242,
|
| 3364 |
+
"step": 11350
|
| 3365 |
+
},
|
| 3366 |
+
{
|
| 3367 |
+
"epoch": 9.81502266350097,
|
| 3368 |
+
"grad_norm": 0.2431640625,
|
| 3369 |
+
"learning_rate": 8.889267803410231e-05,
|
| 3370 |
+
"loss": 1.0413,
|
| 3371 |
+
"step": 11375
|
| 3372 |
+
},
|
| 3373 |
+
{
|
| 3374 |
+
"epoch": 9.836606950140299,
|
| 3375 |
+
"grad_norm": 0.2275390625,
|
| 3376 |
+
"learning_rate": 8.886760280842528e-05,
|
| 3377 |
+
"loss": 1.0505,
|
| 3378 |
+
"step": 11400
|
| 3379 |
+
},
|
| 3380 |
+
{
|
| 3381 |
+
"epoch": 9.858191236779625,
|
| 3382 |
+
"grad_norm": 0.2578125,
|
| 3383 |
+
"learning_rate": 8.884252758274824e-05,
|
| 3384 |
+
"loss": 1.3221,
|
| 3385 |
+
"step": 11425
|
| 3386 |
+
},
|
| 3387 |
+
{
|
| 3388 |
+
"epoch": 9.879775523418951,
|
| 3389 |
+
"grad_norm": 0.27734375,
|
| 3390 |
+
"learning_rate": 8.881745235707122e-05,
|
| 3391 |
+
"loss": 1.0816,
|
| 3392 |
+
"step": 11450
|
| 3393 |
+
},
|
| 3394 |
+
{
|
| 3395 |
+
"epoch": 9.901359810058278,
|
| 3396 |
+
"grad_norm": 0.1865234375,
|
| 3397 |
+
"learning_rate": 8.879237713139419e-05,
|
| 3398 |
+
"loss": 1.1502,
|
| 3399 |
+
"step": 11475
|
| 3400 |
+
},
|
| 3401 |
+
{
|
| 3402 |
+
"epoch": 9.922944096697604,
|
| 3403 |
+
"grad_norm": 0.1865234375,
|
| 3404 |
+
"learning_rate": 8.876730190571715e-05,
|
| 3405 |
+
"loss": 1.2071,
|
| 3406 |
+
"step": 11500
|
| 3407 |
+
},
|
| 3408 |
+
{
|
| 3409 |
+
"epoch": 9.922944096697604,
|
| 3410 |
+
"eval_loss": 1.1804978847503662,
|
| 3411 |
+
"eval_runtime": 118.4662,
|
| 3412 |
+
"eval_samples_per_second": 4.221,
|
| 3413 |
+
"eval_steps_per_second": 4.221,
|
| 3414 |
+
"step": 11500
|
| 3415 |
+
},
|
| 3416 |
+
{
|
| 3417 |
+
"epoch": 9.94452838333693,
|
| 3418 |
+
"grad_norm": 0.19140625,
|
| 3419 |
+
"learning_rate": 8.874222668004012e-05,
|
| 3420 |
+
"loss": 1.0383,
|
| 3421 |
+
"step": 11525
|
| 3422 |
+
},
|
| 3423 |
+
{
|
| 3424 |
+
"epoch": 9.966112669976257,
|
| 3425 |
+
"grad_norm": 0.2734375,
|
| 3426 |
+
"learning_rate": 8.871715145436309e-05,
|
| 3427 |
+
"loss": 1.2457,
|
| 3428 |
+
"step": 11550
|
| 3429 |
+
},
|
| 3430 |
+
{
|
| 3431 |
+
"epoch": 9.987696956615585,
|
| 3432 |
+
"grad_norm": 0.259765625,
|
| 3433 |
+
"learning_rate": 8.869207622868607e-05,
|
| 3434 |
+
"loss": 1.1177,
|
| 3435 |
+
"step": 11575
|
| 3436 |
+
},
|
| 3437 |
+
{
|
| 3438 |
+
"epoch": 10.00863371465573,
|
| 3439 |
+
"grad_norm": 0.212890625,
|
| 3440 |
+
"learning_rate": 8.866700100300903e-05,
|
| 3441 |
+
"loss": 0.9983,
|
| 3442 |
+
"step": 11600
|
| 3443 |
+
},
|
| 3444 |
+
{
|
| 3445 |
+
"epoch": 10.030218001295058,
|
| 3446 |
+
"grad_norm": 0.27734375,
|
| 3447 |
+
"learning_rate": 8.8641925777332e-05,
|
| 3448 |
+
"loss": 1.168,
|
| 3449 |
+
"step": 11625
|
| 3450 |
+
},
|
| 3451 |
+
{
|
| 3452 |
+
"epoch": 10.051802287934384,
|
| 3453 |
+
"grad_norm": 0.185546875,
|
| 3454 |
+
"learning_rate": 8.861685055165498e-05,
|
| 3455 |
+
"loss": 1.1315,
|
| 3456 |
+
"step": 11650
|
| 3457 |
+
},
|
| 3458 |
+
{
|
| 3459 |
+
"epoch": 10.07338657457371,
|
| 3460 |
+
"grad_norm": 0.228515625,
|
| 3461 |
+
"learning_rate": 8.859177532597793e-05,
|
| 3462 |
+
"loss": 1.0122,
|
| 3463 |
+
"step": 11675
|
| 3464 |
+
},
|
| 3465 |
+
{
|
| 3466 |
+
"epoch": 10.094970861213037,
|
| 3467 |
+
"grad_norm": 0.244140625,
|
| 3468 |
+
"learning_rate": 8.85667001003009e-05,
|
| 3469 |
+
"loss": 1.1507,
|
| 3470 |
+
"step": 11700
|
| 3471 |
+
},
|
| 3472 |
+
{
|
| 3473 |
+
"epoch": 10.116555147852363,
|
| 3474 |
+
"grad_norm": 0.1767578125,
|
| 3475 |
+
"learning_rate": 8.854162487462388e-05,
|
| 3476 |
+
"loss": 1.2644,
|
| 3477 |
+
"step": 11725
|
| 3478 |
+
},
|
| 3479 |
+
{
|
| 3480 |
+
"epoch": 10.13813943449169,
|
| 3481 |
+
"grad_norm": 0.171875,
|
| 3482 |
+
"learning_rate": 8.851654964894684e-05,
|
| 3483 |
+
"loss": 1.0958,
|
| 3484 |
+
"step": 11750
|
| 3485 |
+
},
|
| 3486 |
+
{
|
| 3487 |
+
"epoch": 10.159723721131016,
|
| 3488 |
+
"grad_norm": 0.18359375,
|
| 3489 |
+
"learning_rate": 8.849147442326981e-05,
|
| 3490 |
+
"loss": 1.1193,
|
| 3491 |
+
"step": 11775
|
| 3492 |
+
},
|
| 3493 |
+
{
|
| 3494 |
+
"epoch": 10.181308007770344,
|
| 3495 |
+
"grad_norm": 0.25,
|
| 3496 |
+
"learning_rate": 8.846639919759279e-05,
|
| 3497 |
+
"loss": 1.1638,
|
| 3498 |
+
"step": 11800
|
| 3499 |
+
},
|
| 3500 |
+
{
|
| 3501 |
+
"epoch": 10.20289229440967,
|
| 3502 |
+
"grad_norm": 0.244140625,
|
| 3503 |
+
"learning_rate": 8.844132397191574e-05,
|
| 3504 |
+
"loss": 1.1991,
|
| 3505 |
+
"step": 11825
|
| 3506 |
+
},
|
| 3507 |
+
{
|
| 3508 |
+
"epoch": 10.224476581048997,
|
| 3509 |
+
"grad_norm": 0.2138671875,
|
| 3510 |
+
"learning_rate": 8.841624874623871e-05,
|
| 3511 |
+
"loss": 1.0886,
|
| 3512 |
+
"step": 11850
|
| 3513 |
+
},
|
| 3514 |
+
{
|
| 3515 |
+
"epoch": 10.246060867688323,
|
| 3516 |
+
"grad_norm": 0.265625,
|
| 3517 |
+
"learning_rate": 8.839117352056169e-05,
|
| 3518 |
+
"loss": 1.1301,
|
| 3519 |
+
"step": 11875
|
| 3520 |
+
},
|
| 3521 |
+
{
|
| 3522 |
+
"epoch": 10.26764515432765,
|
| 3523 |
+
"grad_norm": 0.271484375,
|
| 3524 |
+
"learning_rate": 8.836609829488466e-05,
|
| 3525 |
+
"loss": 1.0516,
|
| 3526 |
+
"step": 11900
|
| 3527 |
+
},
|
| 3528 |
+
{
|
| 3529 |
+
"epoch": 10.289229440966976,
|
| 3530 |
+
"grad_norm": 0.23828125,
|
| 3531 |
+
"learning_rate": 8.834102306920762e-05,
|
| 3532 |
+
"loss": 1.1763,
|
| 3533 |
+
"step": 11925
|
| 3534 |
+
},
|
| 3535 |
+
{
|
| 3536 |
+
"epoch": 10.310813727606302,
|
| 3537 |
+
"grad_norm": 0.2412109375,
|
| 3538 |
+
"learning_rate": 8.83159478435306e-05,
|
| 3539 |
+
"loss": 0.9276,
|
| 3540 |
+
"step": 11950
|
| 3541 |
+
},
|
| 3542 |
+
{
|
| 3543 |
+
"epoch": 10.33239801424563,
|
| 3544 |
+
"grad_norm": 0.212890625,
|
| 3545 |
+
"learning_rate": 8.829087261785356e-05,
|
| 3546 |
+
"loss": 1.2325,
|
| 3547 |
+
"step": 11975
|
| 3548 |
+
},
|
| 3549 |
+
{
|
| 3550 |
+
"epoch": 10.353982300884956,
|
| 3551 |
+
"grad_norm": 0.181640625,
|
| 3552 |
+
"learning_rate": 8.826579739217654e-05,
|
| 3553 |
+
"loss": 1.1026,
|
| 3554 |
+
"step": 12000
|
| 3555 |
+
},
|
| 3556 |
+
{
|
| 3557 |
+
"epoch": 10.353982300884956,
|
| 3558 |
+
"eval_loss": 1.179988980293274,
|
| 3559 |
+
"eval_runtime": 118.6831,
|
| 3560 |
+
"eval_samples_per_second": 4.213,
|
| 3561 |
+
"eval_steps_per_second": 4.213,
|
| 3562 |
+
"step": 12000
|
| 3563 |
+
}
|
| 3564 |
+
],
|
| 3565 |
+
"logging_steps": 25,
|
| 3566 |
+
"max_steps": 100000,
|
| 3567 |
+
"num_input_tokens_seen": 0,
|
| 3568 |
+
"num_train_epochs": 87,
|
| 3569 |
+
"save_steps": 3000,
|
| 3570 |
+
"stateful_callbacks": {
|
| 3571 |
+
"TrainerControl": {
|
| 3572 |
+
"args": {
|
| 3573 |
+
"should_epoch_stop": false,
|
| 3574 |
+
"should_evaluate": false,
|
| 3575 |
+
"should_log": false,
|
| 3576 |
+
"should_save": true,
|
| 3577 |
+
"should_training_stop": false
|
| 3578 |
+
},
|
| 3579 |
+
"attributes": {}
|
| 3580 |
+
}
|
| 3581 |
+
},
|
| 3582 |
+
"total_flos": 0.0,
|
| 3583 |
+
"train_batch_size": 1,
|
| 3584 |
+
"trial_name": null,
|
| 3585 |
+
"trial_params": null
|
| 3586 |
+
}
|
pretrained/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c03e27a8ac21866af793389a26d0eadd71fdb3b0a28c54926aab2cdcefdce50d
|
| 3 |
+
size 5969
|