Commit
·
15506a2
verified
·
0
Parent(s):
Super-squash branch 'main' using huggingface_hub
Browse files- .gitattributes +35 -0
- last-checkpoint/model.safetensors +3 -0
- last-checkpoint/optimizer.pt +3 -0
- last-checkpoint/rng_state.pth +3 -0
- last-checkpoint/scheduler.pt +3 -0
- last-checkpoint/trainer_state.json +1786 -0
- last-checkpoint/training_args.bin +3 -0
.gitattributes
ADDED
|
@@ -0,0 +1,35 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
*.7z filter=lfs diff=lfs merge=lfs -text
|
| 2 |
+
*.arrow filter=lfs diff=lfs merge=lfs -text
|
| 3 |
+
*.bin filter=lfs diff=lfs merge=lfs -text
|
| 4 |
+
*.bz2 filter=lfs diff=lfs merge=lfs -text
|
| 5 |
+
*.ckpt filter=lfs diff=lfs merge=lfs -text
|
| 6 |
+
*.ftz filter=lfs diff=lfs merge=lfs -text
|
| 7 |
+
*.gz filter=lfs diff=lfs merge=lfs -text
|
| 8 |
+
*.h5 filter=lfs diff=lfs merge=lfs -text
|
| 9 |
+
*.joblib filter=lfs diff=lfs merge=lfs -text
|
| 10 |
+
*.lfs.* filter=lfs diff=lfs merge=lfs -text
|
| 11 |
+
*.mlmodel filter=lfs diff=lfs merge=lfs -text
|
| 12 |
+
*.model filter=lfs diff=lfs merge=lfs -text
|
| 13 |
+
*.msgpack filter=lfs diff=lfs merge=lfs -text
|
| 14 |
+
*.npy filter=lfs diff=lfs merge=lfs -text
|
| 15 |
+
*.npz filter=lfs diff=lfs merge=lfs -text
|
| 16 |
+
*.onnx filter=lfs diff=lfs merge=lfs -text
|
| 17 |
+
*.ot filter=lfs diff=lfs merge=lfs -text
|
| 18 |
+
*.parquet filter=lfs diff=lfs merge=lfs -text
|
| 19 |
+
*.pb filter=lfs diff=lfs merge=lfs -text
|
| 20 |
+
*.pickle filter=lfs diff=lfs merge=lfs -text
|
| 21 |
+
*.pkl filter=lfs diff=lfs merge=lfs -text
|
| 22 |
+
*.pt filter=lfs diff=lfs merge=lfs -text
|
| 23 |
+
*.pth filter=lfs diff=lfs merge=lfs -text
|
| 24 |
+
*.rar filter=lfs diff=lfs merge=lfs -text
|
| 25 |
+
*.safetensors filter=lfs diff=lfs merge=lfs -text
|
| 26 |
+
saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
| 27 |
+
*.tar.* filter=lfs diff=lfs merge=lfs -text
|
| 28 |
+
*.tar filter=lfs diff=lfs merge=lfs -text
|
| 29 |
+
*.tflite filter=lfs diff=lfs merge=lfs -text
|
| 30 |
+
*.tgz filter=lfs diff=lfs merge=lfs -text
|
| 31 |
+
*.wasm filter=lfs diff=lfs merge=lfs -text
|
| 32 |
+
*.xz filter=lfs diff=lfs merge=lfs -text
|
| 33 |
+
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
+
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
+
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
last-checkpoint/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e96643407f870d165fe248087f58882b754a46c68ed8bbbb8296cfb49e4ba16f
|
| 3 |
+
size 21577620
|
last-checkpoint/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:21173a6e85c0d01bd89f0254e9cf12c9f5e201ec065dbf6d1248341f50a19ff7
|
| 3 |
+
size 43185803
|
last-checkpoint/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:07f59e599f3fcca86c21092f1cdf3a0d446538a97483247948f9a0dc00ffc94d
|
| 3 |
+
size 14645
|
last-checkpoint/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:44f986f908978821791045c895960ea997610e2ba08e49fde2d7ec564e6ee286
|
| 3 |
+
size 1465
|
last-checkpoint/trainer_state.json
ADDED
|
@@ -0,0 +1,1786 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": 2469,
|
| 3 |
+
"best_metric": 0.7291858792304993,
|
| 4 |
+
"best_model_checkpoint": "./cefr_reg/checkpoint-2469",
|
| 5 |
+
"epoch": 1.0,
|
| 6 |
+
"eval_steps": 500,
|
| 7 |
+
"global_step": 2469,
|
| 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,
|
| 14 |
+
"eval_acc_0.5": 0.0,
|
| 15 |
+
"eval_acc_1.0": 0.0,
|
| 16 |
+
"eval_loss": 4.52817964553833,
|
| 17 |
+
"eval_mae": 4.471426963806152,
|
| 18 |
+
"eval_pcc": -0.06410610675811768,
|
| 19 |
+
"eval_qwk": -0.0003021129118856436,
|
| 20 |
+
"eval_rmse": 4.532072067260742,
|
| 21 |
+
"eval_runtime": 28.8535,
|
| 22 |
+
"eval_samples_per_second": 111.217,
|
| 23 |
+
"eval_src": -0.05987504900250908,
|
| 24 |
+
"eval_steps_per_second": 6.966,
|
| 25 |
+
"step": 0
|
| 26 |
+
},
|
| 27 |
+
{
|
| 28 |
+
"epoch": 0.004050222762251924,
|
| 29 |
+
"grad_norm": 10.551199913024902,
|
| 30 |
+
"learning_rate": 9.987849331713245e-05,
|
| 31 |
+
"loss": 2.7505,
|
| 32 |
+
"step": 10
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 0.008100445524503848,
|
| 36 |
+
"grad_norm": 1.4525120258331299,
|
| 37 |
+
"learning_rate": 9.974348589172406e-05,
|
| 38 |
+
"loss": 0.9612,
|
| 39 |
+
"step": 20
|
| 40 |
+
},
|
| 41 |
+
{
|
| 42 |
+
"epoch": 0.012150668286755772,
|
| 43 |
+
"grad_norm": 5.914994716644287,
|
| 44 |
+
"learning_rate": 9.960847846631565e-05,
|
| 45 |
+
"loss": 0.7054,
|
| 46 |
+
"step": 30
|
| 47 |
+
},
|
| 48 |
+
{
|
| 49 |
+
"epoch": 0.016200891049007696,
|
| 50 |
+
"grad_norm": 7.5304484367370605,
|
| 51 |
+
"learning_rate": 9.947347104090725e-05,
|
| 52 |
+
"loss": 0.7235,
|
| 53 |
+
"step": 40
|
| 54 |
+
},
|
| 55 |
+
{
|
| 56 |
+
"epoch": 0.02025111381125962,
|
| 57 |
+
"grad_norm": 9.218586921691895,
|
| 58 |
+
"learning_rate": 9.933846361549886e-05,
|
| 59 |
+
"loss": 0.7934,
|
| 60 |
+
"step": 50
|
| 61 |
+
},
|
| 62 |
+
{
|
| 63 |
+
"epoch": 0.024301336573511544,
|
| 64 |
+
"grad_norm": 4.827125072479248,
|
| 65 |
+
"learning_rate": 9.920345619009046e-05,
|
| 66 |
+
"loss": 0.7254,
|
| 67 |
+
"step": 60
|
| 68 |
+
},
|
| 69 |
+
{
|
| 70 |
+
"epoch": 0.028351559335763468,
|
| 71 |
+
"grad_norm": 2.5279595851898193,
|
| 72 |
+
"learning_rate": 9.906844876468207e-05,
|
| 73 |
+
"loss": 0.7811,
|
| 74 |
+
"step": 70
|
| 75 |
+
},
|
| 76 |
+
{
|
| 77 |
+
"epoch": 0.03240178209801539,
|
| 78 |
+
"grad_norm": 1.1081438064575195,
|
| 79 |
+
"learning_rate": 9.893344133927366e-05,
|
| 80 |
+
"loss": 0.7307,
|
| 81 |
+
"step": 80
|
| 82 |
+
},
|
| 83 |
+
{
|
| 84 |
+
"epoch": 0.03645200486026731,
|
| 85 |
+
"grad_norm": 3.5692625045776367,
|
| 86 |
+
"learning_rate": 9.879843391386526e-05,
|
| 87 |
+
"loss": 0.7255,
|
| 88 |
+
"step": 90
|
| 89 |
+
},
|
| 90 |
+
{
|
| 91 |
+
"epoch": 0.04050222762251924,
|
| 92 |
+
"grad_norm": 5.297443389892578,
|
| 93 |
+
"learning_rate": 9.866342648845687e-05,
|
| 94 |
+
"loss": 0.7331,
|
| 95 |
+
"step": 100
|
| 96 |
+
},
|
| 97 |
+
{
|
| 98 |
+
"epoch": 0.04455245038477116,
|
| 99 |
+
"grad_norm": 2.653315305709839,
|
| 100 |
+
"learning_rate": 9.852841906304847e-05,
|
| 101 |
+
"loss": 0.6897,
|
| 102 |
+
"step": 110
|
| 103 |
+
},
|
| 104 |
+
{
|
| 105 |
+
"epoch": 0.04860267314702309,
|
| 106 |
+
"grad_norm": 1.8816819190979004,
|
| 107 |
+
"learning_rate": 9.839341163764008e-05,
|
| 108 |
+
"loss": 0.6987,
|
| 109 |
+
"step": 120
|
| 110 |
+
},
|
| 111 |
+
{
|
| 112 |
+
"epoch": 0.05265289590927501,
|
| 113 |
+
"grad_norm": 1.560968279838562,
|
| 114 |
+
"learning_rate": 9.825840421223169e-05,
|
| 115 |
+
"loss": 0.6981,
|
| 116 |
+
"step": 130
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"epoch": 0.056703118671526935,
|
| 120 |
+
"grad_norm": 4.910257339477539,
|
| 121 |
+
"learning_rate": 9.812339678682328e-05,
|
| 122 |
+
"loss": 0.7113,
|
| 123 |
+
"step": 140
|
| 124 |
+
},
|
| 125 |
+
{
|
| 126 |
+
"epoch": 0.060753341433778855,
|
| 127 |
+
"grad_norm": 5.892327785491943,
|
| 128 |
+
"learning_rate": 9.798838936141488e-05,
|
| 129 |
+
"loss": 0.7456,
|
| 130 |
+
"step": 150
|
| 131 |
+
},
|
| 132 |
+
{
|
| 133 |
+
"epoch": 0.06480356419603078,
|
| 134 |
+
"grad_norm": 2.5749614238739014,
|
| 135 |
+
"learning_rate": 9.785338193600649e-05,
|
| 136 |
+
"loss": 0.7249,
|
| 137 |
+
"step": 160
|
| 138 |
+
},
|
| 139 |
+
{
|
| 140 |
+
"epoch": 0.0688537869582827,
|
| 141 |
+
"grad_norm": 2.3996565341949463,
|
| 142 |
+
"learning_rate": 9.771837451059809e-05,
|
| 143 |
+
"loss": 0.6995,
|
| 144 |
+
"step": 170
|
| 145 |
+
},
|
| 146 |
+
{
|
| 147 |
+
"epoch": 0.07290400972053462,
|
| 148 |
+
"grad_norm": 5.240713119506836,
|
| 149 |
+
"learning_rate": 9.75833670851897e-05,
|
| 150 |
+
"loss": 0.7327,
|
| 151 |
+
"step": 180
|
| 152 |
+
},
|
| 153 |
+
{
|
| 154 |
+
"epoch": 0.07695423248278656,
|
| 155 |
+
"grad_norm": 7.391425609588623,
|
| 156 |
+
"learning_rate": 9.744835965978129e-05,
|
| 157 |
+
"loss": 0.7053,
|
| 158 |
+
"step": 190
|
| 159 |
+
},
|
| 160 |
+
{
|
| 161 |
+
"epoch": 0.08100445524503848,
|
| 162 |
+
"grad_norm": 7.433688163757324,
|
| 163 |
+
"learning_rate": 9.731335223437289e-05,
|
| 164 |
+
"loss": 0.7026,
|
| 165 |
+
"step": 200
|
| 166 |
+
},
|
| 167 |
+
{
|
| 168 |
+
"epoch": 0.0850546780072904,
|
| 169 |
+
"grad_norm": 2.655003786087036,
|
| 170 |
+
"learning_rate": 9.71783448089645e-05,
|
| 171 |
+
"loss": 0.6712,
|
| 172 |
+
"step": 210
|
| 173 |
+
},
|
| 174 |
+
{
|
| 175 |
+
"epoch": 0.08910490076954232,
|
| 176 |
+
"grad_norm": 1.991586446762085,
|
| 177 |
+
"learning_rate": 9.70433373835561e-05,
|
| 178 |
+
"loss": 0.6711,
|
| 179 |
+
"step": 220
|
| 180 |
+
},
|
| 181 |
+
{
|
| 182 |
+
"epoch": 0.09315512353179425,
|
| 183 |
+
"grad_norm": 1.123203992843628,
|
| 184 |
+
"learning_rate": 9.69083299581477e-05,
|
| 185 |
+
"loss": 0.6624,
|
| 186 |
+
"step": 230
|
| 187 |
+
},
|
| 188 |
+
{
|
| 189 |
+
"epoch": 0.09720534629404617,
|
| 190 |
+
"grad_norm": 7.008766174316406,
|
| 191 |
+
"learning_rate": 9.67733225327393e-05,
|
| 192 |
+
"loss": 0.7115,
|
| 193 |
+
"step": 240
|
| 194 |
+
},
|
| 195 |
+
{
|
| 196 |
+
"epoch": 0.1012555690562981,
|
| 197 |
+
"grad_norm": 7.505290508270264,
|
| 198 |
+
"learning_rate": 9.663831510733091e-05,
|
| 199 |
+
"loss": 0.7537,
|
| 200 |
+
"step": 250
|
| 201 |
+
},
|
| 202 |
+
{
|
| 203 |
+
"epoch": 0.10530579181855002,
|
| 204 |
+
"grad_norm": 3.7045347690582275,
|
| 205 |
+
"learning_rate": 9.650330768192251e-05,
|
| 206 |
+
"loss": 0.6647,
|
| 207 |
+
"step": 260
|
| 208 |
+
},
|
| 209 |
+
{
|
| 210 |
+
"epoch": 0.10935601458080195,
|
| 211 |
+
"grad_norm": 3.018012523651123,
|
| 212 |
+
"learning_rate": 9.63683002565141e-05,
|
| 213 |
+
"loss": 0.7184,
|
| 214 |
+
"step": 270
|
| 215 |
+
},
|
| 216 |
+
{
|
| 217 |
+
"epoch": 0.11340623734305387,
|
| 218 |
+
"grad_norm": 9.340592384338379,
|
| 219 |
+
"learning_rate": 9.623329283110572e-05,
|
| 220 |
+
"loss": 0.6556,
|
| 221 |
+
"step": 280
|
| 222 |
+
},
|
| 223 |
+
{
|
| 224 |
+
"epoch": 0.11745646010530579,
|
| 225 |
+
"grad_norm": 6.4435014724731445,
|
| 226 |
+
"learning_rate": 9.609828540569731e-05,
|
| 227 |
+
"loss": 0.7042,
|
| 228 |
+
"step": 290
|
| 229 |
+
},
|
| 230 |
+
{
|
| 231 |
+
"epoch": 0.12150668286755771,
|
| 232 |
+
"grad_norm": 4.117043495178223,
|
| 233 |
+
"learning_rate": 9.596327798028892e-05,
|
| 234 |
+
"loss": 0.6879,
|
| 235 |
+
"step": 300
|
| 236 |
+
},
|
| 237 |
+
{
|
| 238 |
+
"epoch": 0.12555690562980965,
|
| 239 |
+
"grad_norm": 1.508130431175232,
|
| 240 |
+
"learning_rate": 9.582827055488053e-05,
|
| 241 |
+
"loss": 0.7142,
|
| 242 |
+
"step": 310
|
| 243 |
+
},
|
| 244 |
+
{
|
| 245 |
+
"epoch": 0.12960712839206157,
|
| 246 |
+
"grad_norm": 3.512599229812622,
|
| 247 |
+
"learning_rate": 9.569326312947212e-05,
|
| 248 |
+
"loss": 0.6657,
|
| 249 |
+
"step": 320
|
| 250 |
+
},
|
| 251 |
+
{
|
| 252 |
+
"epoch": 0.1336573511543135,
|
| 253 |
+
"grad_norm": 1.518929123878479,
|
| 254 |
+
"learning_rate": 9.555825570406373e-05,
|
| 255 |
+
"loss": 0.6845,
|
| 256 |
+
"step": 330
|
| 257 |
+
},
|
| 258 |
+
{
|
| 259 |
+
"epoch": 0.1377075739165654,
|
| 260 |
+
"grad_norm": 2.9133493900299072,
|
| 261 |
+
"learning_rate": 9.542324827865534e-05,
|
| 262 |
+
"loss": 0.7757,
|
| 263 |
+
"step": 340
|
| 264 |
+
},
|
| 265 |
+
{
|
| 266 |
+
"epoch": 0.14175779667881733,
|
| 267 |
+
"grad_norm": 4.808182239532471,
|
| 268 |
+
"learning_rate": 9.528824085324693e-05,
|
| 269 |
+
"loss": 0.6532,
|
| 270 |
+
"step": 350
|
| 271 |
+
},
|
| 272 |
+
{
|
| 273 |
+
"epoch": 0.14580801944106925,
|
| 274 |
+
"grad_norm": 4.0984392166137695,
|
| 275 |
+
"learning_rate": 9.515323342783854e-05,
|
| 276 |
+
"loss": 0.681,
|
| 277 |
+
"step": 360
|
| 278 |
+
},
|
| 279 |
+
{
|
| 280 |
+
"epoch": 0.1498582422033212,
|
| 281 |
+
"grad_norm": 3.545947551727295,
|
| 282 |
+
"learning_rate": 9.501822600243013e-05,
|
| 283 |
+
"loss": 0.7553,
|
| 284 |
+
"step": 370
|
| 285 |
+
},
|
| 286 |
+
{
|
| 287 |
+
"epoch": 0.15390846496557312,
|
| 288 |
+
"grad_norm": 6.998193264007568,
|
| 289 |
+
"learning_rate": 9.488321857702174e-05,
|
| 290 |
+
"loss": 0.6444,
|
| 291 |
+
"step": 380
|
| 292 |
+
},
|
| 293 |
+
{
|
| 294 |
+
"epoch": 0.15795868772782504,
|
| 295 |
+
"grad_norm": 1.2728239297866821,
|
| 296 |
+
"learning_rate": 9.474821115161335e-05,
|
| 297 |
+
"loss": 0.6596,
|
| 298 |
+
"step": 390
|
| 299 |
+
},
|
| 300 |
+
{
|
| 301 |
+
"epoch": 0.16200891049007696,
|
| 302 |
+
"grad_norm": 2.098156690597534,
|
| 303 |
+
"learning_rate": 9.461320372620494e-05,
|
| 304 |
+
"loss": 0.7261,
|
| 305 |
+
"step": 400
|
| 306 |
+
},
|
| 307 |
+
{
|
| 308 |
+
"epoch": 0.16605913325232888,
|
| 309 |
+
"grad_norm": 7.71750545501709,
|
| 310 |
+
"learning_rate": 9.447819630079655e-05,
|
| 311 |
+
"loss": 0.6531,
|
| 312 |
+
"step": 410
|
| 313 |
+
},
|
| 314 |
+
{
|
| 315 |
+
"epoch": 0.1701093560145808,
|
| 316 |
+
"grad_norm": 3.735727548599243,
|
| 317 |
+
"learning_rate": 9.434318887538815e-05,
|
| 318 |
+
"loss": 0.7082,
|
| 319 |
+
"step": 420
|
| 320 |
+
},
|
| 321 |
+
{
|
| 322 |
+
"epoch": 0.17415957877683272,
|
| 323 |
+
"grad_norm": 1.3447264432907104,
|
| 324 |
+
"learning_rate": 9.420818144997975e-05,
|
| 325 |
+
"loss": 0.7463,
|
| 326 |
+
"step": 430
|
| 327 |
+
},
|
| 328 |
+
{
|
| 329 |
+
"epoch": 0.17820980153908464,
|
| 330 |
+
"grad_norm": 1.6115808486938477,
|
| 331 |
+
"learning_rate": 9.407317402457136e-05,
|
| 332 |
+
"loss": 0.7036,
|
| 333 |
+
"step": 440
|
| 334 |
+
},
|
| 335 |
+
{
|
| 336 |
+
"epoch": 0.1822600243013366,
|
| 337 |
+
"grad_norm": 5.158803462982178,
|
| 338 |
+
"learning_rate": 9.393816659916295e-05,
|
| 339 |
+
"loss": 0.6981,
|
| 340 |
+
"step": 450
|
| 341 |
+
},
|
| 342 |
+
{
|
| 343 |
+
"epoch": 0.1863102470635885,
|
| 344 |
+
"grad_norm": 3.6466639041900635,
|
| 345 |
+
"learning_rate": 9.380315917375456e-05,
|
| 346 |
+
"loss": 0.7357,
|
| 347 |
+
"step": 460
|
| 348 |
+
},
|
| 349 |
+
{
|
| 350 |
+
"epoch": 0.19036046982584043,
|
| 351 |
+
"grad_norm": 3.898153781890869,
|
| 352 |
+
"learning_rate": 9.366815174834617e-05,
|
| 353 |
+
"loss": 0.6626,
|
| 354 |
+
"step": 470
|
| 355 |
+
},
|
| 356 |
+
{
|
| 357 |
+
"epoch": 0.19441069258809235,
|
| 358 |
+
"grad_norm": 5.203450679779053,
|
| 359 |
+
"learning_rate": 9.353314432293777e-05,
|
| 360 |
+
"loss": 0.7449,
|
| 361 |
+
"step": 480
|
| 362 |
+
},
|
| 363 |
+
{
|
| 364 |
+
"epoch": 0.19846091535034427,
|
| 365 |
+
"grad_norm": 2.795436143875122,
|
| 366 |
+
"learning_rate": 9.339813689752937e-05,
|
| 367 |
+
"loss": 0.6609,
|
| 368 |
+
"step": 490
|
| 369 |
+
},
|
| 370 |
+
{
|
| 371 |
+
"epoch": 0.2025111381125962,
|
| 372 |
+
"grad_norm": 5.741515636444092,
|
| 373 |
+
"learning_rate": 9.326312947212096e-05,
|
| 374 |
+
"loss": 0.6996,
|
| 375 |
+
"step": 500
|
| 376 |
+
},
|
| 377 |
+
{
|
| 378 |
+
"epoch": 0.2065613608748481,
|
| 379 |
+
"grad_norm": 7.058830738067627,
|
| 380 |
+
"learning_rate": 9.312812204671257e-05,
|
| 381 |
+
"loss": 0.6827,
|
| 382 |
+
"step": 510
|
| 383 |
+
},
|
| 384 |
+
{
|
| 385 |
+
"epoch": 0.21061158363710003,
|
| 386 |
+
"grad_norm": 5.432498931884766,
|
| 387 |
+
"learning_rate": 9.299311462130418e-05,
|
| 388 |
+
"loss": 0.7386,
|
| 389 |
+
"step": 520
|
| 390 |
+
},
|
| 391 |
+
{
|
| 392 |
+
"epoch": 0.21466180639935195,
|
| 393 |
+
"grad_norm": 4.78528356552124,
|
| 394 |
+
"learning_rate": 9.285810719589578e-05,
|
| 395 |
+
"loss": 0.6675,
|
| 396 |
+
"step": 530
|
| 397 |
+
},
|
| 398 |
+
{
|
| 399 |
+
"epoch": 0.2187120291616039,
|
| 400 |
+
"grad_norm": 4.96106481552124,
|
| 401 |
+
"learning_rate": 9.272309977048738e-05,
|
| 402 |
+
"loss": 0.7469,
|
| 403 |
+
"step": 540
|
| 404 |
+
},
|
| 405 |
+
{
|
| 406 |
+
"epoch": 0.22276225192385582,
|
| 407 |
+
"grad_norm": 4.435976982116699,
|
| 408 |
+
"learning_rate": 9.258809234507899e-05,
|
| 409 |
+
"loss": 0.6679,
|
| 410 |
+
"step": 550
|
| 411 |
+
},
|
| 412 |
+
{
|
| 413 |
+
"epoch": 0.22681247468610774,
|
| 414 |
+
"grad_norm": 2.9775969982147217,
|
| 415 |
+
"learning_rate": 9.245308491967058e-05,
|
| 416 |
+
"loss": 0.7926,
|
| 417 |
+
"step": 560
|
| 418 |
+
},
|
| 419 |
+
{
|
| 420 |
+
"epoch": 0.23086269744835966,
|
| 421 |
+
"grad_norm": 6.675817012786865,
|
| 422 |
+
"learning_rate": 9.23180774942622e-05,
|
| 423 |
+
"loss": 0.6973,
|
| 424 |
+
"step": 570
|
| 425 |
+
},
|
| 426 |
+
{
|
| 427 |
+
"epoch": 0.23491292021061158,
|
| 428 |
+
"grad_norm": 3.2485146522521973,
|
| 429 |
+
"learning_rate": 9.218307006885379e-05,
|
| 430 |
+
"loss": 0.636,
|
| 431 |
+
"step": 580
|
| 432 |
+
},
|
| 433 |
+
{
|
| 434 |
+
"epoch": 0.2389631429728635,
|
| 435 |
+
"grad_norm": 5.162914752960205,
|
| 436 |
+
"learning_rate": 9.20480626434454e-05,
|
| 437 |
+
"loss": 0.7364,
|
| 438 |
+
"step": 590
|
| 439 |
+
},
|
| 440 |
+
{
|
| 441 |
+
"epoch": 0.24301336573511542,
|
| 442 |
+
"grad_norm": 1.276663899421692,
|
| 443 |
+
"learning_rate": 9.1913055218037e-05,
|
| 444 |
+
"loss": 0.6902,
|
| 445 |
+
"step": 600
|
| 446 |
+
},
|
| 447 |
+
{
|
| 448 |
+
"epoch": 0.24706358849736734,
|
| 449 |
+
"grad_norm": 6.817727565765381,
|
| 450 |
+
"learning_rate": 9.17780477926286e-05,
|
| 451 |
+
"loss": 0.7476,
|
| 452 |
+
"step": 610
|
| 453 |
+
},
|
| 454 |
+
{
|
| 455 |
+
"epoch": 0.2511138112596193,
|
| 456 |
+
"grad_norm": 1.8886030912399292,
|
| 457 |
+
"learning_rate": 9.16430403672202e-05,
|
| 458 |
+
"loss": 0.7089,
|
| 459 |
+
"step": 620
|
| 460 |
+
},
|
| 461 |
+
{
|
| 462 |
+
"epoch": 0.2551640340218712,
|
| 463 |
+
"grad_norm": 4.143105506896973,
|
| 464 |
+
"learning_rate": 9.15080329418118e-05,
|
| 465 |
+
"loss": 0.662,
|
| 466 |
+
"step": 630
|
| 467 |
+
},
|
| 468 |
+
{
|
| 469 |
+
"epoch": 0.25921425678412313,
|
| 470 |
+
"grad_norm": 3.767601490020752,
|
| 471 |
+
"learning_rate": 9.137302551640341e-05,
|
| 472 |
+
"loss": 0.6633,
|
| 473 |
+
"step": 640
|
| 474 |
+
},
|
| 475 |
+
{
|
| 476 |
+
"epoch": 0.26326447954637505,
|
| 477 |
+
"grad_norm": 4.995476245880127,
|
| 478 |
+
"learning_rate": 9.123801809099502e-05,
|
| 479 |
+
"loss": 0.7448,
|
| 480 |
+
"step": 650
|
| 481 |
+
},
|
| 482 |
+
{
|
| 483 |
+
"epoch": 0.267314702308627,
|
| 484 |
+
"grad_norm": 7.73383903503418,
|
| 485 |
+
"learning_rate": 9.11030106655866e-05,
|
| 486 |
+
"loss": 0.7195,
|
| 487 |
+
"step": 660
|
| 488 |
+
},
|
| 489 |
+
{
|
| 490 |
+
"epoch": 0.2713649250708789,
|
| 491 |
+
"grad_norm": 6.871426582336426,
|
| 492 |
+
"learning_rate": 9.096800324017821e-05,
|
| 493 |
+
"loss": 0.6511,
|
| 494 |
+
"step": 670
|
| 495 |
+
},
|
| 496 |
+
{
|
| 497 |
+
"epoch": 0.2754151478331308,
|
| 498 |
+
"grad_norm": 3.914733409881592,
|
| 499 |
+
"learning_rate": 9.083299581476981e-05,
|
| 500 |
+
"loss": 0.7573,
|
| 501 |
+
"step": 680
|
| 502 |
+
},
|
| 503 |
+
{
|
| 504 |
+
"epoch": 0.27946537059538273,
|
| 505 |
+
"grad_norm": 10.242081642150879,
|
| 506 |
+
"learning_rate": 9.069798838936142e-05,
|
| 507 |
+
"loss": 0.6825,
|
| 508 |
+
"step": 690
|
| 509 |
+
},
|
| 510 |
+
{
|
| 511 |
+
"epoch": 0.28351559335763465,
|
| 512 |
+
"grad_norm": 6.312399864196777,
|
| 513 |
+
"learning_rate": 9.056298096395303e-05,
|
| 514 |
+
"loss": 0.7502,
|
| 515 |
+
"step": 700
|
| 516 |
+
},
|
| 517 |
+
{
|
| 518 |
+
"epoch": 0.2875658161198866,
|
| 519 |
+
"grad_norm": 3.6532344818115234,
|
| 520 |
+
"learning_rate": 9.042797353854461e-05,
|
| 521 |
+
"loss": 0.7196,
|
| 522 |
+
"step": 710
|
| 523 |
+
},
|
| 524 |
+
{
|
| 525 |
+
"epoch": 0.2916160388821385,
|
| 526 |
+
"grad_norm": 7.512033462524414,
|
| 527 |
+
"learning_rate": 9.029296611313622e-05,
|
| 528 |
+
"loss": 0.6044,
|
| 529 |
+
"step": 720
|
| 530 |
+
},
|
| 531 |
+
{
|
| 532 |
+
"epoch": 0.2956662616443904,
|
| 533 |
+
"grad_norm": 3.490694284439087,
|
| 534 |
+
"learning_rate": 9.015795868772783e-05,
|
| 535 |
+
"loss": 0.6686,
|
| 536 |
+
"step": 730
|
| 537 |
+
},
|
| 538 |
+
{
|
| 539 |
+
"epoch": 0.2997164844066424,
|
| 540 |
+
"grad_norm": 2.284693479537964,
|
| 541 |
+
"learning_rate": 9.002295126231943e-05,
|
| 542 |
+
"loss": 0.6267,
|
| 543 |
+
"step": 740
|
| 544 |
+
},
|
| 545 |
+
{
|
| 546 |
+
"epoch": 0.3037667071688943,
|
| 547 |
+
"grad_norm": 5.484620571136475,
|
| 548 |
+
"learning_rate": 8.988794383691104e-05,
|
| 549 |
+
"loss": 0.7032,
|
| 550 |
+
"step": 750
|
| 551 |
+
},
|
| 552 |
+
{
|
| 553 |
+
"epoch": 0.30781692993114623,
|
| 554 |
+
"grad_norm": 2.1748404502868652,
|
| 555 |
+
"learning_rate": 8.975293641150264e-05,
|
| 556 |
+
"loss": 0.6879,
|
| 557 |
+
"step": 760
|
| 558 |
+
},
|
| 559 |
+
{
|
| 560 |
+
"epoch": 0.31186715269339815,
|
| 561 |
+
"grad_norm": 1.6475012302398682,
|
| 562 |
+
"learning_rate": 8.961792898609423e-05,
|
| 563 |
+
"loss": 0.6903,
|
| 564 |
+
"step": 770
|
| 565 |
+
},
|
| 566 |
+
{
|
| 567 |
+
"epoch": 0.3159173754556501,
|
| 568 |
+
"grad_norm": 1.1322206258773804,
|
| 569 |
+
"learning_rate": 8.948292156068584e-05,
|
| 570 |
+
"loss": 0.6528,
|
| 571 |
+
"step": 780
|
| 572 |
+
},
|
| 573 |
+
{
|
| 574 |
+
"epoch": 0.319967598217902,
|
| 575 |
+
"grad_norm": 2.2691164016723633,
|
| 576 |
+
"learning_rate": 8.934791413527744e-05,
|
| 577 |
+
"loss": 0.6407,
|
| 578 |
+
"step": 790
|
| 579 |
+
},
|
| 580 |
+
{
|
| 581 |
+
"epoch": 0.3240178209801539,
|
| 582 |
+
"grad_norm": 4.608505725860596,
|
| 583 |
+
"learning_rate": 8.921290670986905e-05,
|
| 584 |
+
"loss": 0.7131,
|
| 585 |
+
"step": 800
|
| 586 |
+
},
|
| 587 |
+
{
|
| 588 |
+
"epoch": 0.32806804374240583,
|
| 589 |
+
"grad_norm": 1.64627206325531,
|
| 590 |
+
"learning_rate": 8.907789928446065e-05,
|
| 591 |
+
"loss": 0.6729,
|
| 592 |
+
"step": 810
|
| 593 |
+
},
|
| 594 |
+
{
|
| 595 |
+
"epoch": 0.33211826650465776,
|
| 596 |
+
"grad_norm": 2.928720235824585,
|
| 597 |
+
"learning_rate": 8.894289185905226e-05,
|
| 598 |
+
"loss": 0.673,
|
| 599 |
+
"step": 820
|
| 600 |
+
},
|
| 601 |
+
{
|
| 602 |
+
"epoch": 0.3361684892669097,
|
| 603 |
+
"grad_norm": 1.43545663356781,
|
| 604 |
+
"learning_rate": 8.880788443364385e-05,
|
| 605 |
+
"loss": 0.6354,
|
| 606 |
+
"step": 830
|
| 607 |
+
},
|
| 608 |
+
{
|
| 609 |
+
"epoch": 0.3402187120291616,
|
| 610 |
+
"grad_norm": 3.5672547817230225,
|
| 611 |
+
"learning_rate": 8.867287700823545e-05,
|
| 612 |
+
"loss": 0.6499,
|
| 613 |
+
"step": 840
|
| 614 |
+
},
|
| 615 |
+
{
|
| 616 |
+
"epoch": 0.3442689347914135,
|
| 617 |
+
"grad_norm": 4.033609867095947,
|
| 618 |
+
"learning_rate": 8.853786958282706e-05,
|
| 619 |
+
"loss": 0.7174,
|
| 620 |
+
"step": 850
|
| 621 |
+
},
|
| 622 |
+
{
|
| 623 |
+
"epoch": 0.34831915755366544,
|
| 624 |
+
"grad_norm": 3.793355941772461,
|
| 625 |
+
"learning_rate": 8.840286215741867e-05,
|
| 626 |
+
"loss": 0.7206,
|
| 627 |
+
"step": 860
|
| 628 |
+
},
|
| 629 |
+
{
|
| 630 |
+
"epoch": 0.35236938031591736,
|
| 631 |
+
"grad_norm": 4.056700706481934,
|
| 632 |
+
"learning_rate": 8.826785473201027e-05,
|
| 633 |
+
"loss": 0.7267,
|
| 634 |
+
"step": 870
|
| 635 |
+
},
|
| 636 |
+
{
|
| 637 |
+
"epoch": 0.3564196030781693,
|
| 638 |
+
"grad_norm": 2.8090407848358154,
|
| 639 |
+
"learning_rate": 8.813284730660186e-05,
|
| 640 |
+
"loss": 0.6465,
|
| 641 |
+
"step": 880
|
| 642 |
+
},
|
| 643 |
+
{
|
| 644 |
+
"epoch": 0.3604698258404212,
|
| 645 |
+
"grad_norm": 3.3442647457122803,
|
| 646 |
+
"learning_rate": 8.799783988119346e-05,
|
| 647 |
+
"loss": 0.6746,
|
| 648 |
+
"step": 890
|
| 649 |
+
},
|
| 650 |
+
{
|
| 651 |
+
"epoch": 0.3645200486026732,
|
| 652 |
+
"grad_norm": 5.908054828643799,
|
| 653 |
+
"learning_rate": 8.786283245578507e-05,
|
| 654 |
+
"loss": 0.6155,
|
| 655 |
+
"step": 900
|
| 656 |
+
},
|
| 657 |
+
{
|
| 658 |
+
"epoch": 0.3685702713649251,
|
| 659 |
+
"grad_norm": 7.263230800628662,
|
| 660 |
+
"learning_rate": 8.772782503037668e-05,
|
| 661 |
+
"loss": 0.6545,
|
| 662 |
+
"step": 910
|
| 663 |
+
},
|
| 664 |
+
{
|
| 665 |
+
"epoch": 0.372620494127177,
|
| 666 |
+
"grad_norm": 3.1377646923065186,
|
| 667 |
+
"learning_rate": 8.759281760496828e-05,
|
| 668 |
+
"loss": 0.7712,
|
| 669 |
+
"step": 920
|
| 670 |
+
},
|
| 671 |
+
{
|
| 672 |
+
"epoch": 0.37667071688942894,
|
| 673 |
+
"grad_norm": 1.6817662715911865,
|
| 674 |
+
"learning_rate": 8.745781017955989e-05,
|
| 675 |
+
"loss": 0.6771,
|
| 676 |
+
"step": 930
|
| 677 |
+
},
|
| 678 |
+
{
|
| 679 |
+
"epoch": 0.38072093965168086,
|
| 680 |
+
"grad_norm": 3.2026214599609375,
|
| 681 |
+
"learning_rate": 8.732280275415148e-05,
|
| 682 |
+
"loss": 0.7437,
|
| 683 |
+
"step": 940
|
| 684 |
+
},
|
| 685 |
+
{
|
| 686 |
+
"epoch": 0.3847711624139328,
|
| 687 |
+
"grad_norm": 1.632327914237976,
|
| 688 |
+
"learning_rate": 8.718779532874308e-05,
|
| 689 |
+
"loss": 0.7053,
|
| 690 |
+
"step": 950
|
| 691 |
+
},
|
| 692 |
+
{
|
| 693 |
+
"epoch": 0.3888213851761847,
|
| 694 |
+
"grad_norm": 3.373493194580078,
|
| 695 |
+
"learning_rate": 8.705278790333469e-05,
|
| 696 |
+
"loss": 0.7054,
|
| 697 |
+
"step": 960
|
| 698 |
+
},
|
| 699 |
+
{
|
| 700 |
+
"epoch": 0.3928716079384366,
|
| 701 |
+
"grad_norm": 2.388636827468872,
|
| 702 |
+
"learning_rate": 8.691778047792629e-05,
|
| 703 |
+
"loss": 0.6703,
|
| 704 |
+
"step": 970
|
| 705 |
+
},
|
| 706 |
+
{
|
| 707 |
+
"epoch": 0.39692183070068854,
|
| 708 |
+
"grad_norm": 1.4855486154556274,
|
| 709 |
+
"learning_rate": 8.67827730525179e-05,
|
| 710 |
+
"loss": 0.6924,
|
| 711 |
+
"step": 980
|
| 712 |
+
},
|
| 713 |
+
{
|
| 714 |
+
"epoch": 0.40097205346294046,
|
| 715 |
+
"grad_norm": 1.8625538349151611,
|
| 716 |
+
"learning_rate": 8.66477656271095e-05,
|
| 717 |
+
"loss": 0.6808,
|
| 718 |
+
"step": 990
|
| 719 |
+
},
|
| 720 |
+
{
|
| 721 |
+
"epoch": 0.4050222762251924,
|
| 722 |
+
"grad_norm": 9.942273139953613,
|
| 723 |
+
"learning_rate": 8.651275820170109e-05,
|
| 724 |
+
"loss": 0.6786,
|
| 725 |
+
"step": 1000
|
| 726 |
+
},
|
| 727 |
+
{
|
| 728 |
+
"epoch": 0.4090724989874443,
|
| 729 |
+
"grad_norm": 6.859795570373535,
|
| 730 |
+
"learning_rate": 8.63777507762927e-05,
|
| 731 |
+
"loss": 0.7188,
|
| 732 |
+
"step": 1010
|
| 733 |
+
},
|
| 734 |
+
{
|
| 735 |
+
"epoch": 0.4131227217496962,
|
| 736 |
+
"grad_norm": 6.556404113769531,
|
| 737 |
+
"learning_rate": 8.62427433508843e-05,
|
| 738 |
+
"loss": 0.7225,
|
| 739 |
+
"step": 1020
|
| 740 |
+
},
|
| 741 |
+
{
|
| 742 |
+
"epoch": 0.41717294451194814,
|
| 743 |
+
"grad_norm": 4.393095016479492,
|
| 744 |
+
"learning_rate": 8.610773592547591e-05,
|
| 745 |
+
"loss": 0.6596,
|
| 746 |
+
"step": 1030
|
| 747 |
+
},
|
| 748 |
+
{
|
| 749 |
+
"epoch": 0.42122316727420006,
|
| 750 |
+
"grad_norm": 6.862849235534668,
|
| 751 |
+
"learning_rate": 8.597272850006752e-05,
|
| 752 |
+
"loss": 0.6699,
|
| 753 |
+
"step": 1040
|
| 754 |
+
},
|
| 755 |
+
{
|
| 756 |
+
"epoch": 0.425273390036452,
|
| 757 |
+
"grad_norm": 3.898430347442627,
|
| 758 |
+
"learning_rate": 8.58377210746591e-05,
|
| 759 |
+
"loss": 0.6913,
|
| 760 |
+
"step": 1050
|
| 761 |
+
},
|
| 762 |
+
{
|
| 763 |
+
"epoch": 0.4293236127987039,
|
| 764 |
+
"grad_norm": 3.683239459991455,
|
| 765 |
+
"learning_rate": 8.570271364925071e-05,
|
| 766 |
+
"loss": 0.6312,
|
| 767 |
+
"step": 1060
|
| 768 |
+
},
|
| 769 |
+
{
|
| 770 |
+
"epoch": 0.4333738355609559,
|
| 771 |
+
"grad_norm": 1.4455596208572388,
|
| 772 |
+
"learning_rate": 8.556770622384232e-05,
|
| 773 |
+
"loss": 0.7048,
|
| 774 |
+
"step": 1070
|
| 775 |
+
},
|
| 776 |
+
{
|
| 777 |
+
"epoch": 0.4374240583232078,
|
| 778 |
+
"grad_norm": 2.023144483566284,
|
| 779 |
+
"learning_rate": 8.543269879843392e-05,
|
| 780 |
+
"loss": 0.6634,
|
| 781 |
+
"step": 1080
|
| 782 |
+
},
|
| 783 |
+
{
|
| 784 |
+
"epoch": 0.4414742810854597,
|
| 785 |
+
"grad_norm": 1.454586386680603,
|
| 786 |
+
"learning_rate": 8.529769137302553e-05,
|
| 787 |
+
"loss": 0.639,
|
| 788 |
+
"step": 1090
|
| 789 |
+
},
|
| 790 |
+
{
|
| 791 |
+
"epoch": 0.44552450384771164,
|
| 792 |
+
"grad_norm": 2.0027737617492676,
|
| 793 |
+
"learning_rate": 8.516268394761712e-05,
|
| 794 |
+
"loss": 0.7068,
|
| 795 |
+
"step": 1100
|
| 796 |
+
},
|
| 797 |
+
{
|
| 798 |
+
"epoch": 0.44957472660996356,
|
| 799 |
+
"grad_norm": 1.4496852159500122,
|
| 800 |
+
"learning_rate": 8.502767652220872e-05,
|
| 801 |
+
"loss": 0.7654,
|
| 802 |
+
"step": 1110
|
| 803 |
+
},
|
| 804 |
+
{
|
| 805 |
+
"epoch": 0.4536249493722155,
|
| 806 |
+
"grad_norm": 1.5118701457977295,
|
| 807 |
+
"learning_rate": 8.489266909680033e-05,
|
| 808 |
+
"loss": 0.7211,
|
| 809 |
+
"step": 1120
|
| 810 |
+
},
|
| 811 |
+
{
|
| 812 |
+
"epoch": 0.4576751721344674,
|
| 813 |
+
"grad_norm": 4.295745372772217,
|
| 814 |
+
"learning_rate": 8.475766167139193e-05,
|
| 815 |
+
"loss": 0.6662,
|
| 816 |
+
"step": 1130
|
| 817 |
+
},
|
| 818 |
+
{
|
| 819 |
+
"epoch": 0.4617253948967193,
|
| 820 |
+
"grad_norm": 1.5748212337493896,
|
| 821 |
+
"learning_rate": 8.462265424598354e-05,
|
| 822 |
+
"loss": 0.6695,
|
| 823 |
+
"step": 1140
|
| 824 |
+
},
|
| 825 |
+
{
|
| 826 |
+
"epoch": 0.46577561765897124,
|
| 827 |
+
"grad_norm": 3.8355488777160645,
|
| 828 |
+
"learning_rate": 8.448764682057513e-05,
|
| 829 |
+
"loss": 0.6277,
|
| 830 |
+
"step": 1150
|
| 831 |
+
},
|
| 832 |
+
{
|
| 833 |
+
"epoch": 0.46982584042122316,
|
| 834 |
+
"grad_norm": 2.747668743133545,
|
| 835 |
+
"learning_rate": 8.435263939516674e-05,
|
| 836 |
+
"loss": 0.689,
|
| 837 |
+
"step": 1160
|
| 838 |
+
},
|
| 839 |
+
{
|
| 840 |
+
"epoch": 0.4738760631834751,
|
| 841 |
+
"grad_norm": 3.341548204421997,
|
| 842 |
+
"learning_rate": 8.421763196975834e-05,
|
| 843 |
+
"loss": 0.6295,
|
| 844 |
+
"step": 1170
|
| 845 |
+
},
|
| 846 |
+
{
|
| 847 |
+
"epoch": 0.477926285945727,
|
| 848 |
+
"grad_norm": 2.240903854370117,
|
| 849 |
+
"learning_rate": 8.408262454434994e-05,
|
| 850 |
+
"loss": 0.6915,
|
| 851 |
+
"step": 1180
|
| 852 |
+
},
|
| 853 |
+
{
|
| 854 |
+
"epoch": 0.4819765087079789,
|
| 855 |
+
"grad_norm": 2.9906082153320312,
|
| 856 |
+
"learning_rate": 8.394761711894155e-05,
|
| 857 |
+
"loss": 0.7148,
|
| 858 |
+
"step": 1190
|
| 859 |
+
},
|
| 860 |
+
{
|
| 861 |
+
"epoch": 0.48602673147023084,
|
| 862 |
+
"grad_norm": 3.217128276824951,
|
| 863 |
+
"learning_rate": 8.381260969353314e-05,
|
| 864 |
+
"loss": 0.7287,
|
| 865 |
+
"step": 1200
|
| 866 |
+
},
|
| 867 |
+
{
|
| 868 |
+
"epoch": 0.49007695423248276,
|
| 869 |
+
"grad_norm": 5.23323392868042,
|
| 870 |
+
"learning_rate": 8.367760226812475e-05,
|
| 871 |
+
"loss": 0.651,
|
| 872 |
+
"step": 1210
|
| 873 |
+
},
|
| 874 |
+
{
|
| 875 |
+
"epoch": 0.4941271769947347,
|
| 876 |
+
"grad_norm": 1.4018148183822632,
|
| 877 |
+
"learning_rate": 8.354259484271635e-05,
|
| 878 |
+
"loss": 0.7042,
|
| 879 |
+
"step": 1220
|
| 880 |
+
},
|
| 881 |
+
{
|
| 882 |
+
"epoch": 0.49817739975698666,
|
| 883 |
+
"grad_norm": 5.82692813873291,
|
| 884 |
+
"learning_rate": 8.340758741730795e-05,
|
| 885 |
+
"loss": 0.6557,
|
| 886 |
+
"step": 1230
|
| 887 |
+
},
|
| 888 |
+
{
|
| 889 |
+
"epoch": 0.5022276225192386,
|
| 890 |
+
"grad_norm": 4.461226940155029,
|
| 891 |
+
"learning_rate": 8.327257999189956e-05,
|
| 892 |
+
"loss": 0.7046,
|
| 893 |
+
"step": 1240
|
| 894 |
+
},
|
| 895 |
+
{
|
| 896 |
+
"epoch": 0.5062778452814904,
|
| 897 |
+
"grad_norm": 1.4963361024856567,
|
| 898 |
+
"learning_rate": 8.313757256649117e-05,
|
| 899 |
+
"loss": 0.6771,
|
| 900 |
+
"step": 1250
|
| 901 |
+
},
|
| 902 |
+
{
|
| 903 |
+
"epoch": 0.5103280680437424,
|
| 904 |
+
"grad_norm": 7.774729251861572,
|
| 905 |
+
"learning_rate": 8.300256514108276e-05,
|
| 906 |
+
"loss": 0.6568,
|
| 907 |
+
"step": 1260
|
| 908 |
+
},
|
| 909 |
+
{
|
| 910 |
+
"epoch": 0.5143782908059943,
|
| 911 |
+
"grad_norm": 10.685174942016602,
|
| 912 |
+
"learning_rate": 8.286755771567437e-05,
|
| 913 |
+
"loss": 0.7036,
|
| 914 |
+
"step": 1270
|
| 915 |
+
},
|
| 916 |
+
{
|
| 917 |
+
"epoch": 0.5184285135682463,
|
| 918 |
+
"grad_norm": 7.026299953460693,
|
| 919 |
+
"learning_rate": 8.273255029026596e-05,
|
| 920 |
+
"loss": 0.6717,
|
| 921 |
+
"step": 1280
|
| 922 |
+
},
|
| 923 |
+
{
|
| 924 |
+
"epoch": 0.5224787363304981,
|
| 925 |
+
"grad_norm": 1.4644521474838257,
|
| 926 |
+
"learning_rate": 8.259754286485757e-05,
|
| 927 |
+
"loss": 0.7273,
|
| 928 |
+
"step": 1290
|
| 929 |
+
},
|
| 930 |
+
{
|
| 931 |
+
"epoch": 0.5265289590927501,
|
| 932 |
+
"grad_norm": 4.5040693283081055,
|
| 933 |
+
"learning_rate": 8.246253543944918e-05,
|
| 934 |
+
"loss": 0.6519,
|
| 935 |
+
"step": 1300
|
| 936 |
+
},
|
| 937 |
+
{
|
| 938 |
+
"epoch": 0.5305791818550021,
|
| 939 |
+
"grad_norm": 10.927738189697266,
|
| 940 |
+
"learning_rate": 8.232752801404077e-05,
|
| 941 |
+
"loss": 0.69,
|
| 942 |
+
"step": 1310
|
| 943 |
+
},
|
| 944 |
+
{
|
| 945 |
+
"epoch": 0.534629404617254,
|
| 946 |
+
"grad_norm": 2.803307294845581,
|
| 947 |
+
"learning_rate": 8.219252058863238e-05,
|
| 948 |
+
"loss": 0.7042,
|
| 949 |
+
"step": 1320
|
| 950 |
+
},
|
| 951 |
+
{
|
| 952 |
+
"epoch": 0.5386796273795059,
|
| 953 |
+
"grad_norm": 2.241880416870117,
|
| 954 |
+
"learning_rate": 8.205751316322398e-05,
|
| 955 |
+
"loss": 0.6556,
|
| 956 |
+
"step": 1330
|
| 957 |
+
},
|
| 958 |
+
{
|
| 959 |
+
"epoch": 0.5427298501417578,
|
| 960 |
+
"grad_norm": 1.8177238702774048,
|
| 961 |
+
"learning_rate": 8.192250573781558e-05,
|
| 962 |
+
"loss": 0.7063,
|
| 963 |
+
"step": 1340
|
| 964 |
+
},
|
| 965 |
+
{
|
| 966 |
+
"epoch": 0.5467800729040098,
|
| 967 |
+
"grad_norm": 3.659595251083374,
|
| 968 |
+
"learning_rate": 8.178749831240719e-05,
|
| 969 |
+
"loss": 0.6645,
|
| 970 |
+
"step": 1350
|
| 971 |
+
},
|
| 972 |
+
{
|
| 973 |
+
"epoch": 0.5508302956662616,
|
| 974 |
+
"grad_norm": 2.6234257221221924,
|
| 975 |
+
"learning_rate": 8.165249088699878e-05,
|
| 976 |
+
"loss": 0.6759,
|
| 977 |
+
"step": 1360
|
| 978 |
+
},
|
| 979 |
+
{
|
| 980 |
+
"epoch": 0.5548805184285136,
|
| 981 |
+
"grad_norm": 7.211588382720947,
|
| 982 |
+
"learning_rate": 8.15174834615904e-05,
|
| 983 |
+
"loss": 0.6575,
|
| 984 |
+
"step": 1370
|
| 985 |
+
},
|
| 986 |
+
{
|
| 987 |
+
"epoch": 0.5589307411907655,
|
| 988 |
+
"grad_norm": 3.50372314453125,
|
| 989 |
+
"learning_rate": 8.1382476036182e-05,
|
| 990 |
+
"loss": 0.7123,
|
| 991 |
+
"step": 1380
|
| 992 |
+
},
|
| 993 |
+
{
|
| 994 |
+
"epoch": 0.5629809639530174,
|
| 995 |
+
"grad_norm": 1.490511178970337,
|
| 996 |
+
"learning_rate": 8.124746861077359e-05,
|
| 997 |
+
"loss": 0.6976,
|
| 998 |
+
"step": 1390
|
| 999 |
+
},
|
| 1000 |
+
{
|
| 1001 |
+
"epoch": 0.5670311867152693,
|
| 1002 |
+
"grad_norm": 11.36801815032959,
|
| 1003 |
+
"learning_rate": 8.11124611853652e-05,
|
| 1004 |
+
"loss": 0.6626,
|
| 1005 |
+
"step": 1400
|
| 1006 |
+
},
|
| 1007 |
+
{
|
| 1008 |
+
"epoch": 0.5710814094775213,
|
| 1009 |
+
"grad_norm": 6.033326148986816,
|
| 1010 |
+
"learning_rate": 8.09774537599568e-05,
|
| 1011 |
+
"loss": 0.6583,
|
| 1012 |
+
"step": 1410
|
| 1013 |
+
},
|
| 1014 |
+
{
|
| 1015 |
+
"epoch": 0.5751316322397731,
|
| 1016 |
+
"grad_norm": 4.926746368408203,
|
| 1017 |
+
"learning_rate": 8.08424463345484e-05,
|
| 1018 |
+
"loss": 0.6809,
|
| 1019 |
+
"step": 1420
|
| 1020 |
+
},
|
| 1021 |
+
{
|
| 1022 |
+
"epoch": 0.5791818550020251,
|
| 1023 |
+
"grad_norm": 1.5155569314956665,
|
| 1024 |
+
"learning_rate": 8.070743890914001e-05,
|
| 1025 |
+
"loss": 0.8433,
|
| 1026 |
+
"step": 1430
|
| 1027 |
+
},
|
| 1028 |
+
{
|
| 1029 |
+
"epoch": 0.583232077764277,
|
| 1030 |
+
"grad_norm": 7.069480895996094,
|
| 1031 |
+
"learning_rate": 8.057243148373161e-05,
|
| 1032 |
+
"loss": 0.6695,
|
| 1033 |
+
"step": 1440
|
| 1034 |
+
},
|
| 1035 |
+
{
|
| 1036 |
+
"epoch": 0.587282300526529,
|
| 1037 |
+
"grad_norm": 3.5053625106811523,
|
| 1038 |
+
"learning_rate": 8.043742405832321e-05,
|
| 1039 |
+
"loss": 0.712,
|
| 1040 |
+
"step": 1450
|
| 1041 |
+
},
|
| 1042 |
+
{
|
| 1043 |
+
"epoch": 0.5913325232887808,
|
| 1044 |
+
"grad_norm": 8.239558219909668,
|
| 1045 |
+
"learning_rate": 8.030241663291482e-05,
|
| 1046 |
+
"loss": 0.6655,
|
| 1047 |
+
"step": 1460
|
| 1048 |
+
},
|
| 1049 |
+
{
|
| 1050 |
+
"epoch": 0.5953827460510328,
|
| 1051 |
+
"grad_norm": 3.499582052230835,
|
| 1052 |
+
"learning_rate": 8.016740920750641e-05,
|
| 1053 |
+
"loss": 0.6695,
|
| 1054 |
+
"step": 1470
|
| 1055 |
+
},
|
| 1056 |
+
{
|
| 1057 |
+
"epoch": 0.5994329688132848,
|
| 1058 |
+
"grad_norm": 6.012964725494385,
|
| 1059 |
+
"learning_rate": 8.003240178209802e-05,
|
| 1060 |
+
"loss": 0.6664,
|
| 1061 |
+
"step": 1480
|
| 1062 |
+
},
|
| 1063 |
+
{
|
| 1064 |
+
"epoch": 0.6034831915755366,
|
| 1065 |
+
"grad_norm": 8.99488353729248,
|
| 1066 |
+
"learning_rate": 7.989739435668962e-05,
|
| 1067 |
+
"loss": 0.6465,
|
| 1068 |
+
"step": 1490
|
| 1069 |
+
},
|
| 1070 |
+
{
|
| 1071 |
+
"epoch": 0.6075334143377886,
|
| 1072 |
+
"grad_norm": 1.608788013458252,
|
| 1073 |
+
"learning_rate": 7.976238693128122e-05,
|
| 1074 |
+
"loss": 0.6762,
|
| 1075 |
+
"step": 1500
|
| 1076 |
+
},
|
| 1077 |
+
{
|
| 1078 |
+
"epoch": 0.6115836371000405,
|
| 1079 |
+
"grad_norm": 7.744218349456787,
|
| 1080 |
+
"learning_rate": 7.962737950587283e-05,
|
| 1081 |
+
"loss": 0.7005,
|
| 1082 |
+
"step": 1510
|
| 1083 |
+
},
|
| 1084 |
+
{
|
| 1085 |
+
"epoch": 0.6156338598622925,
|
| 1086 |
+
"grad_norm": 1.5159974098205566,
|
| 1087 |
+
"learning_rate": 7.949237208046442e-05,
|
| 1088 |
+
"loss": 0.7335,
|
| 1089 |
+
"step": 1520
|
| 1090 |
+
},
|
| 1091 |
+
{
|
| 1092 |
+
"epoch": 0.6196840826245443,
|
| 1093 |
+
"grad_norm": 5.266475200653076,
|
| 1094 |
+
"learning_rate": 7.935736465505604e-05,
|
| 1095 |
+
"loss": 0.6717,
|
| 1096 |
+
"step": 1530
|
| 1097 |
+
},
|
| 1098 |
+
{
|
| 1099 |
+
"epoch": 0.6237343053867963,
|
| 1100 |
+
"grad_norm": 4.198414325714111,
|
| 1101 |
+
"learning_rate": 7.922235722964763e-05,
|
| 1102 |
+
"loss": 0.6076,
|
| 1103 |
+
"step": 1540
|
| 1104 |
+
},
|
| 1105 |
+
{
|
| 1106 |
+
"epoch": 0.6277845281490482,
|
| 1107 |
+
"grad_norm": 6.395306587219238,
|
| 1108 |
+
"learning_rate": 7.908734980423924e-05,
|
| 1109 |
+
"loss": 0.7478,
|
| 1110 |
+
"step": 1550
|
| 1111 |
+
},
|
| 1112 |
+
{
|
| 1113 |
+
"epoch": 0.6318347509113001,
|
| 1114 |
+
"grad_norm": 7.0668182373046875,
|
| 1115 |
+
"learning_rate": 7.895234237883084e-05,
|
| 1116 |
+
"loss": 0.6454,
|
| 1117 |
+
"step": 1560
|
| 1118 |
+
},
|
| 1119 |
+
{
|
| 1120 |
+
"epoch": 0.635884973673552,
|
| 1121 |
+
"grad_norm": 5.721327781677246,
|
| 1122 |
+
"learning_rate": 7.881733495342243e-05,
|
| 1123 |
+
"loss": 0.6866,
|
| 1124 |
+
"step": 1570
|
| 1125 |
+
},
|
| 1126 |
+
{
|
| 1127 |
+
"epoch": 0.639935196435804,
|
| 1128 |
+
"grad_norm": 1.5752720832824707,
|
| 1129 |
+
"learning_rate": 7.868232752801405e-05,
|
| 1130 |
+
"loss": 0.6574,
|
| 1131 |
+
"step": 1580
|
| 1132 |
+
},
|
| 1133 |
+
{
|
| 1134 |
+
"epoch": 0.6439854191980559,
|
| 1135 |
+
"grad_norm": 3.1622705459594727,
|
| 1136 |
+
"learning_rate": 7.854732010260564e-05,
|
| 1137 |
+
"loss": 0.6968,
|
| 1138 |
+
"step": 1590
|
| 1139 |
+
},
|
| 1140 |
+
{
|
| 1141 |
+
"epoch": 0.6480356419603078,
|
| 1142 |
+
"grad_norm": 2.200968027114868,
|
| 1143 |
+
"learning_rate": 7.841231267719725e-05,
|
| 1144 |
+
"loss": 0.7232,
|
| 1145 |
+
"step": 1600
|
| 1146 |
+
},
|
| 1147 |
+
{
|
| 1148 |
+
"epoch": 0.6520858647225597,
|
| 1149 |
+
"grad_norm": 5.88210391998291,
|
| 1150 |
+
"learning_rate": 7.827730525178886e-05,
|
| 1151 |
+
"loss": 0.6027,
|
| 1152 |
+
"step": 1610
|
| 1153 |
+
},
|
| 1154 |
+
{
|
| 1155 |
+
"epoch": 0.6561360874848117,
|
| 1156 |
+
"grad_norm": 2.330373764038086,
|
| 1157 |
+
"learning_rate": 7.814229782638044e-05,
|
| 1158 |
+
"loss": 0.7234,
|
| 1159 |
+
"step": 1620
|
| 1160 |
+
},
|
| 1161 |
+
{
|
| 1162 |
+
"epoch": 0.6601863102470635,
|
| 1163 |
+
"grad_norm": 3.580780029296875,
|
| 1164 |
+
"learning_rate": 7.800729040097206e-05,
|
| 1165 |
+
"loss": 0.6395,
|
| 1166 |
+
"step": 1630
|
| 1167 |
+
},
|
| 1168 |
+
{
|
| 1169 |
+
"epoch": 0.6642365330093155,
|
| 1170 |
+
"grad_norm": 3.347949504852295,
|
| 1171 |
+
"learning_rate": 7.787228297556367e-05,
|
| 1172 |
+
"loss": 0.7026,
|
| 1173 |
+
"step": 1640
|
| 1174 |
+
},
|
| 1175 |
+
{
|
| 1176 |
+
"epoch": 0.6682867557715675,
|
| 1177 |
+
"grad_norm": 2.739063024520874,
|
| 1178 |
+
"learning_rate": 7.773727555015526e-05,
|
| 1179 |
+
"loss": 0.7006,
|
| 1180 |
+
"step": 1650
|
| 1181 |
+
},
|
| 1182 |
+
{
|
| 1183 |
+
"epoch": 0.6723369785338194,
|
| 1184 |
+
"grad_norm": 1.8707573413848877,
|
| 1185 |
+
"learning_rate": 7.760226812474687e-05,
|
| 1186 |
+
"loss": 0.6809,
|
| 1187 |
+
"step": 1660
|
| 1188 |
+
},
|
| 1189 |
+
{
|
| 1190 |
+
"epoch": 0.6763872012960713,
|
| 1191 |
+
"grad_norm": 1.339418888092041,
|
| 1192 |
+
"learning_rate": 7.746726069933847e-05,
|
| 1193 |
+
"loss": 0.6299,
|
| 1194 |
+
"step": 1670
|
| 1195 |
+
},
|
| 1196 |
+
{
|
| 1197 |
+
"epoch": 0.6804374240583232,
|
| 1198 |
+
"grad_norm": 1.8292454481124878,
|
| 1199 |
+
"learning_rate": 7.733225327393007e-05,
|
| 1200 |
+
"loss": 0.6736,
|
| 1201 |
+
"step": 1680
|
| 1202 |
+
},
|
| 1203 |
+
{
|
| 1204 |
+
"epoch": 0.6844876468205752,
|
| 1205 |
+
"grad_norm": 8.511611938476562,
|
| 1206 |
+
"learning_rate": 7.719724584852168e-05,
|
| 1207 |
+
"loss": 0.7129,
|
| 1208 |
+
"step": 1690
|
| 1209 |
+
},
|
| 1210 |
+
{
|
| 1211 |
+
"epoch": 0.688537869582827,
|
| 1212 |
+
"grad_norm": 5.8545379638671875,
|
| 1213 |
+
"learning_rate": 7.706223842311327e-05,
|
| 1214 |
+
"loss": 0.7271,
|
| 1215 |
+
"step": 1700
|
| 1216 |
+
},
|
| 1217 |
+
{
|
| 1218 |
+
"epoch": 0.692588092345079,
|
| 1219 |
+
"grad_norm": 3.0557925701141357,
|
| 1220 |
+
"learning_rate": 7.692723099770488e-05,
|
| 1221 |
+
"loss": 0.7228,
|
| 1222 |
+
"step": 1710
|
| 1223 |
+
},
|
| 1224 |
+
{
|
| 1225 |
+
"epoch": 0.6966383151073309,
|
| 1226 |
+
"grad_norm": 7.087495803833008,
|
| 1227 |
+
"learning_rate": 7.679222357229648e-05,
|
| 1228 |
+
"loss": 0.6529,
|
| 1229 |
+
"step": 1720
|
| 1230 |
+
},
|
| 1231 |
+
{
|
| 1232 |
+
"epoch": 0.7006885378695829,
|
| 1233 |
+
"grad_norm": 1.2610193490982056,
|
| 1234 |
+
"learning_rate": 7.665721614688808e-05,
|
| 1235 |
+
"loss": 0.6423,
|
| 1236 |
+
"step": 1730
|
| 1237 |
+
},
|
| 1238 |
+
{
|
| 1239 |
+
"epoch": 0.7047387606318347,
|
| 1240 |
+
"grad_norm": 3.634399175643921,
|
| 1241 |
+
"learning_rate": 7.652220872147969e-05,
|
| 1242 |
+
"loss": 0.6765,
|
| 1243 |
+
"step": 1740
|
| 1244 |
+
},
|
| 1245 |
+
{
|
| 1246 |
+
"epoch": 0.7087889833940867,
|
| 1247 |
+
"grad_norm": 2.021672248840332,
|
| 1248 |
+
"learning_rate": 7.638720129607128e-05,
|
| 1249 |
+
"loss": 0.6853,
|
| 1250 |
+
"step": 1750
|
| 1251 |
+
},
|
| 1252 |
+
{
|
| 1253 |
+
"epoch": 0.7128392061563386,
|
| 1254 |
+
"grad_norm": 1.397925615310669,
|
| 1255 |
+
"learning_rate": 7.625219387066289e-05,
|
| 1256 |
+
"loss": 0.6029,
|
| 1257 |
+
"step": 1760
|
| 1258 |
+
},
|
| 1259 |
+
{
|
| 1260 |
+
"epoch": 0.7168894289185905,
|
| 1261 |
+
"grad_norm": 2.4325027465820312,
|
| 1262 |
+
"learning_rate": 7.61171864452545e-05,
|
| 1263 |
+
"loss": 0.6678,
|
| 1264 |
+
"step": 1770
|
| 1265 |
+
},
|
| 1266 |
+
{
|
| 1267 |
+
"epoch": 0.7209396516808424,
|
| 1268 |
+
"grad_norm": 1.489314317703247,
|
| 1269 |
+
"learning_rate": 7.59821790198461e-05,
|
| 1270 |
+
"loss": 0.6743,
|
| 1271 |
+
"step": 1780
|
| 1272 |
+
},
|
| 1273 |
+
{
|
| 1274 |
+
"epoch": 0.7249898744430944,
|
| 1275 |
+
"grad_norm": 1.6524492502212524,
|
| 1276 |
+
"learning_rate": 7.58471715944377e-05,
|
| 1277 |
+
"loss": 0.6636,
|
| 1278 |
+
"step": 1790
|
| 1279 |
+
},
|
| 1280 |
+
{
|
| 1281 |
+
"epoch": 0.7290400972053463,
|
| 1282 |
+
"grad_norm": 2.6753315925598145,
|
| 1283 |
+
"learning_rate": 7.571216416902929e-05,
|
| 1284 |
+
"loss": 0.7202,
|
| 1285 |
+
"step": 1800
|
| 1286 |
+
},
|
| 1287 |
+
{
|
| 1288 |
+
"epoch": 0.7330903199675982,
|
| 1289 |
+
"grad_norm": 5.01415491104126,
|
| 1290 |
+
"learning_rate": 7.55771567436209e-05,
|
| 1291 |
+
"loss": 0.7076,
|
| 1292 |
+
"step": 1810
|
| 1293 |
+
},
|
| 1294 |
+
{
|
| 1295 |
+
"epoch": 0.7371405427298502,
|
| 1296 |
+
"grad_norm": 4.823099613189697,
|
| 1297 |
+
"learning_rate": 7.544214931821251e-05,
|
| 1298 |
+
"loss": 0.7228,
|
| 1299 |
+
"step": 1820
|
| 1300 |
+
},
|
| 1301 |
+
{
|
| 1302 |
+
"epoch": 0.741190765492102,
|
| 1303 |
+
"grad_norm": 7.68076753616333,
|
| 1304 |
+
"learning_rate": 7.530714189280411e-05,
|
| 1305 |
+
"loss": 0.6443,
|
| 1306 |
+
"step": 1830
|
| 1307 |
+
},
|
| 1308 |
+
{
|
| 1309 |
+
"epoch": 0.745240988254354,
|
| 1310 |
+
"grad_norm": 8.639177322387695,
|
| 1311 |
+
"learning_rate": 7.51721344673957e-05,
|
| 1312 |
+
"loss": 0.6837,
|
| 1313 |
+
"step": 1840
|
| 1314 |
+
},
|
| 1315 |
+
{
|
| 1316 |
+
"epoch": 0.7492912110166059,
|
| 1317 |
+
"grad_norm": 2.379915237426758,
|
| 1318 |
+
"learning_rate": 7.503712704198732e-05,
|
| 1319 |
+
"loss": 0.6505,
|
| 1320 |
+
"step": 1850
|
| 1321 |
+
},
|
| 1322 |
+
{
|
| 1323 |
+
"epoch": 0.7533414337788579,
|
| 1324 |
+
"grad_norm": 2.4480419158935547,
|
| 1325 |
+
"learning_rate": 7.490211961657891e-05,
|
| 1326 |
+
"loss": 0.6698,
|
| 1327 |
+
"step": 1860
|
| 1328 |
+
},
|
| 1329 |
+
{
|
| 1330 |
+
"epoch": 0.7573916565411097,
|
| 1331 |
+
"grad_norm": 1.723561406135559,
|
| 1332 |
+
"learning_rate": 7.476711219117052e-05,
|
| 1333 |
+
"loss": 0.7275,
|
| 1334 |
+
"step": 1870
|
| 1335 |
+
},
|
| 1336 |
+
{
|
| 1337 |
+
"epoch": 0.7614418793033617,
|
| 1338 |
+
"grad_norm": 2.184816837310791,
|
| 1339 |
+
"learning_rate": 7.463210476576212e-05,
|
| 1340 |
+
"loss": 0.6425,
|
| 1341 |
+
"step": 1880
|
| 1342 |
+
},
|
| 1343 |
+
{
|
| 1344 |
+
"epoch": 0.7654921020656136,
|
| 1345 |
+
"grad_norm": 2.710773468017578,
|
| 1346 |
+
"learning_rate": 7.449709734035373e-05,
|
| 1347 |
+
"loss": 0.7748,
|
| 1348 |
+
"step": 1890
|
| 1349 |
+
},
|
| 1350 |
+
{
|
| 1351 |
+
"epoch": 0.7695423248278656,
|
| 1352 |
+
"grad_norm": 2.839587688446045,
|
| 1353 |
+
"learning_rate": 7.436208991494533e-05,
|
| 1354 |
+
"loss": 0.6263,
|
| 1355 |
+
"step": 1900
|
| 1356 |
+
},
|
| 1357 |
+
{
|
| 1358 |
+
"epoch": 0.7735925475901174,
|
| 1359 |
+
"grad_norm": 5.725647449493408,
|
| 1360 |
+
"learning_rate": 7.422708248953692e-05,
|
| 1361 |
+
"loss": 0.7141,
|
| 1362 |
+
"step": 1910
|
| 1363 |
+
},
|
| 1364 |
+
{
|
| 1365 |
+
"epoch": 0.7776427703523694,
|
| 1366 |
+
"grad_norm": 5.777345180511475,
|
| 1367 |
+
"learning_rate": 7.409207506412853e-05,
|
| 1368 |
+
"loss": 0.7056,
|
| 1369 |
+
"step": 1920
|
| 1370 |
+
},
|
| 1371 |
+
{
|
| 1372 |
+
"epoch": 0.7816929931146213,
|
| 1373 |
+
"grad_norm": 7.272107124328613,
|
| 1374 |
+
"learning_rate": 7.395706763872013e-05,
|
| 1375 |
+
"loss": 0.6735,
|
| 1376 |
+
"step": 1930
|
| 1377 |
+
},
|
| 1378 |
+
{
|
| 1379 |
+
"epoch": 0.7857432158768732,
|
| 1380 |
+
"grad_norm": 4.4248552322387695,
|
| 1381 |
+
"learning_rate": 7.382206021331174e-05,
|
| 1382 |
+
"loss": 0.6701,
|
| 1383 |
+
"step": 1940
|
| 1384 |
+
},
|
| 1385 |
+
{
|
| 1386 |
+
"epoch": 0.7897934386391251,
|
| 1387 |
+
"grad_norm": 1.2805415391921997,
|
| 1388 |
+
"learning_rate": 7.368705278790335e-05,
|
| 1389 |
+
"loss": 0.6853,
|
| 1390 |
+
"step": 1950
|
| 1391 |
+
},
|
| 1392 |
+
{
|
| 1393 |
+
"epoch": 0.7938436614013771,
|
| 1394 |
+
"grad_norm": 3.7856080532073975,
|
| 1395 |
+
"learning_rate": 7.355204536249493e-05,
|
| 1396 |
+
"loss": 0.6966,
|
| 1397 |
+
"step": 1960
|
| 1398 |
+
},
|
| 1399 |
+
{
|
| 1400 |
+
"epoch": 0.797893884163629,
|
| 1401 |
+
"grad_norm": 2.6894679069519043,
|
| 1402 |
+
"learning_rate": 7.341703793708654e-05,
|
| 1403 |
+
"loss": 0.6878,
|
| 1404 |
+
"step": 1970
|
| 1405 |
+
},
|
| 1406 |
+
{
|
| 1407 |
+
"epoch": 0.8019441069258809,
|
| 1408 |
+
"grad_norm": 1.721479058265686,
|
| 1409 |
+
"learning_rate": 7.328203051167815e-05,
|
| 1410 |
+
"loss": 0.6527,
|
| 1411 |
+
"step": 1980
|
| 1412 |
+
},
|
| 1413 |
+
{
|
| 1414 |
+
"epoch": 0.8059943296881329,
|
| 1415 |
+
"grad_norm": 3.666368246078491,
|
| 1416 |
+
"learning_rate": 7.314702308626975e-05,
|
| 1417 |
+
"loss": 0.659,
|
| 1418 |
+
"step": 1990
|
| 1419 |
+
},
|
| 1420 |
+
{
|
| 1421 |
+
"epoch": 0.8100445524503848,
|
| 1422 |
+
"grad_norm": 4.111802577972412,
|
| 1423 |
+
"learning_rate": 7.301201566086136e-05,
|
| 1424 |
+
"loss": 0.7143,
|
| 1425 |
+
"step": 2000
|
| 1426 |
+
},
|
| 1427 |
+
{
|
| 1428 |
+
"epoch": 0.8140947752126367,
|
| 1429 |
+
"grad_norm": 5.371121883392334,
|
| 1430 |
+
"learning_rate": 7.287700823545294e-05,
|
| 1431 |
+
"loss": 0.6453,
|
| 1432 |
+
"step": 2010
|
| 1433 |
+
},
|
| 1434 |
+
{
|
| 1435 |
+
"epoch": 0.8181449979748886,
|
| 1436 |
+
"grad_norm": 8.05588436126709,
|
| 1437 |
+
"learning_rate": 7.274200081004455e-05,
|
| 1438 |
+
"loss": 0.6846,
|
| 1439 |
+
"step": 2020
|
| 1440 |
+
},
|
| 1441 |
+
{
|
| 1442 |
+
"epoch": 0.8221952207371406,
|
| 1443 |
+
"grad_norm": 1.3259375095367432,
|
| 1444 |
+
"learning_rate": 7.260699338463616e-05,
|
| 1445 |
+
"loss": 0.5983,
|
| 1446 |
+
"step": 2030
|
| 1447 |
+
},
|
| 1448 |
+
{
|
| 1449 |
+
"epoch": 0.8262454434993924,
|
| 1450 |
+
"grad_norm": 1.8734527826309204,
|
| 1451 |
+
"learning_rate": 7.247198595922776e-05,
|
| 1452 |
+
"loss": 0.6277,
|
| 1453 |
+
"step": 2040
|
| 1454 |
+
},
|
| 1455 |
+
{
|
| 1456 |
+
"epoch": 0.8302956662616444,
|
| 1457 |
+
"grad_norm": 6.942389965057373,
|
| 1458 |
+
"learning_rate": 7.233697853381937e-05,
|
| 1459 |
+
"loss": 0.7137,
|
| 1460 |
+
"step": 2050
|
| 1461 |
+
},
|
| 1462 |
+
{
|
| 1463 |
+
"epoch": 0.8343458890238963,
|
| 1464 |
+
"grad_norm": 5.275886535644531,
|
| 1465 |
+
"learning_rate": 7.220197110841097e-05,
|
| 1466 |
+
"loss": 0.6507,
|
| 1467 |
+
"step": 2060
|
| 1468 |
+
},
|
| 1469 |
+
{
|
| 1470 |
+
"epoch": 0.8383961117861483,
|
| 1471 |
+
"grad_norm": 5.971946716308594,
|
| 1472 |
+
"learning_rate": 7.206696368300256e-05,
|
| 1473 |
+
"loss": 0.6335,
|
| 1474 |
+
"step": 2070
|
| 1475 |
+
},
|
| 1476 |
+
{
|
| 1477 |
+
"epoch": 0.8424463345484001,
|
| 1478 |
+
"grad_norm": 4.011186599731445,
|
| 1479 |
+
"learning_rate": 7.193195625759417e-05,
|
| 1480 |
+
"loss": 0.7592,
|
| 1481 |
+
"step": 2080
|
| 1482 |
+
},
|
| 1483 |
+
{
|
| 1484 |
+
"epoch": 0.8464965573106521,
|
| 1485 |
+
"grad_norm": 4.385476589202881,
|
| 1486 |
+
"learning_rate": 7.179694883218577e-05,
|
| 1487 |
+
"loss": 0.6859,
|
| 1488 |
+
"step": 2090
|
| 1489 |
+
},
|
| 1490 |
+
{
|
| 1491 |
+
"epoch": 0.850546780072904,
|
| 1492 |
+
"grad_norm": 5.010826110839844,
|
| 1493 |
+
"learning_rate": 7.166194140677738e-05,
|
| 1494 |
+
"loss": 0.6739,
|
| 1495 |
+
"step": 2100
|
| 1496 |
+
},
|
| 1497 |
+
{
|
| 1498 |
+
"epoch": 0.8545970028351559,
|
| 1499 |
+
"grad_norm": 1.4120031595230103,
|
| 1500 |
+
"learning_rate": 7.152693398136898e-05,
|
| 1501 |
+
"loss": 0.6207,
|
| 1502 |
+
"step": 2110
|
| 1503 |
+
},
|
| 1504 |
+
{
|
| 1505 |
+
"epoch": 0.8586472255974078,
|
| 1506 |
+
"grad_norm": 3.627908706665039,
|
| 1507 |
+
"learning_rate": 7.139192655596059e-05,
|
| 1508 |
+
"loss": 0.6847,
|
| 1509 |
+
"step": 2120
|
| 1510 |
+
},
|
| 1511 |
+
{
|
| 1512 |
+
"epoch": 0.8626974483596598,
|
| 1513 |
+
"grad_norm": 7.15459680557251,
|
| 1514 |
+
"learning_rate": 7.125691913055218e-05,
|
| 1515 |
+
"loss": 0.655,
|
| 1516 |
+
"step": 2130
|
| 1517 |
+
},
|
| 1518 |
+
{
|
| 1519 |
+
"epoch": 0.8667476711219118,
|
| 1520 |
+
"grad_norm": 4.2000250816345215,
|
| 1521 |
+
"learning_rate": 7.112191170514378e-05,
|
| 1522 |
+
"loss": 0.6123,
|
| 1523 |
+
"step": 2140
|
| 1524 |
+
},
|
| 1525 |
+
{
|
| 1526 |
+
"epoch": 0.8707978938841636,
|
| 1527 |
+
"grad_norm": 5.208048343658447,
|
| 1528 |
+
"learning_rate": 7.098690427973539e-05,
|
| 1529 |
+
"loss": 0.6525,
|
| 1530 |
+
"step": 2150
|
| 1531 |
+
},
|
| 1532 |
+
{
|
| 1533 |
+
"epoch": 0.8748481166464156,
|
| 1534 |
+
"grad_norm": 3.048551082611084,
|
| 1535 |
+
"learning_rate": 7.0851896854327e-05,
|
| 1536 |
+
"loss": 0.6834,
|
| 1537 |
+
"step": 2160
|
| 1538 |
+
},
|
| 1539 |
+
{
|
| 1540 |
+
"epoch": 0.8788983394086675,
|
| 1541 |
+
"grad_norm": 7.1293768882751465,
|
| 1542 |
+
"learning_rate": 7.07168894289186e-05,
|
| 1543 |
+
"loss": 0.6337,
|
| 1544 |
+
"step": 2170
|
| 1545 |
+
},
|
| 1546 |
+
{
|
| 1547 |
+
"epoch": 0.8829485621709194,
|
| 1548 |
+
"grad_norm": 1.4484611749649048,
|
| 1549 |
+
"learning_rate": 7.058188200351019e-05,
|
| 1550 |
+
"loss": 0.6295,
|
| 1551 |
+
"step": 2180
|
| 1552 |
+
},
|
| 1553 |
+
{
|
| 1554 |
+
"epoch": 0.8869987849331713,
|
| 1555 |
+
"grad_norm": 4.266237258911133,
|
| 1556 |
+
"learning_rate": 7.044687457810179e-05,
|
| 1557 |
+
"loss": 0.7005,
|
| 1558 |
+
"step": 2190
|
| 1559 |
+
},
|
| 1560 |
+
{
|
| 1561 |
+
"epoch": 0.8910490076954233,
|
| 1562 |
+
"grad_norm": 4.0993852615356445,
|
| 1563 |
+
"learning_rate": 7.03118671526934e-05,
|
| 1564 |
+
"loss": 0.656,
|
| 1565 |
+
"step": 2200
|
| 1566 |
+
},
|
| 1567 |
+
{
|
| 1568 |
+
"epoch": 0.8950992304576751,
|
| 1569 |
+
"grad_norm": 3.7144315242767334,
|
| 1570 |
+
"learning_rate": 7.017685972728501e-05,
|
| 1571 |
+
"loss": 0.6571,
|
| 1572 |
+
"step": 2210
|
| 1573 |
+
},
|
| 1574 |
+
{
|
| 1575 |
+
"epoch": 0.8991494532199271,
|
| 1576 |
+
"grad_norm": 7.986518859863281,
|
| 1577 |
+
"learning_rate": 7.00418523018766e-05,
|
| 1578 |
+
"loss": 0.7044,
|
| 1579 |
+
"step": 2220
|
| 1580 |
+
},
|
| 1581 |
+
{
|
| 1582 |
+
"epoch": 0.903199675982179,
|
| 1583 |
+
"grad_norm": 2.8526182174682617,
|
| 1584 |
+
"learning_rate": 6.990684487646822e-05,
|
| 1585 |
+
"loss": 0.6409,
|
| 1586 |
+
"step": 2230
|
| 1587 |
+
},
|
| 1588 |
+
{
|
| 1589 |
+
"epoch": 0.907249898744431,
|
| 1590 |
+
"grad_norm": 5.810249328613281,
|
| 1591 |
+
"learning_rate": 6.977183745105981e-05,
|
| 1592 |
+
"loss": 0.6444,
|
| 1593 |
+
"step": 2240
|
| 1594 |
+
},
|
| 1595 |
+
{
|
| 1596 |
+
"epoch": 0.9113001215066828,
|
| 1597 |
+
"grad_norm": 4.703845977783203,
|
| 1598 |
+
"learning_rate": 6.963683002565141e-05,
|
| 1599 |
+
"loss": 0.632,
|
| 1600 |
+
"step": 2250
|
| 1601 |
+
},
|
| 1602 |
+
{
|
| 1603 |
+
"epoch": 0.9153503442689348,
|
| 1604 |
+
"grad_norm": 4.955256938934326,
|
| 1605 |
+
"learning_rate": 6.950182260024302e-05,
|
| 1606 |
+
"loss": 0.6859,
|
| 1607 |
+
"step": 2260
|
| 1608 |
+
},
|
| 1609 |
+
{
|
| 1610 |
+
"epoch": 0.9194005670311867,
|
| 1611 |
+
"grad_norm": 3.5239837169647217,
|
| 1612 |
+
"learning_rate": 6.936681517483462e-05,
|
| 1613 |
+
"loss": 0.6738,
|
| 1614 |
+
"step": 2270
|
| 1615 |
+
},
|
| 1616 |
+
{
|
| 1617 |
+
"epoch": 0.9234507897934386,
|
| 1618 |
+
"grad_norm": 4.58236837387085,
|
| 1619 |
+
"learning_rate": 6.923180774942623e-05,
|
| 1620 |
+
"loss": 0.7172,
|
| 1621 |
+
"step": 2280
|
| 1622 |
+
},
|
| 1623 |
+
{
|
| 1624 |
+
"epoch": 0.9275010125556906,
|
| 1625 |
+
"grad_norm": 1.3130325078964233,
|
| 1626 |
+
"learning_rate": 6.909680032401784e-05,
|
| 1627 |
+
"loss": 0.7214,
|
| 1628 |
+
"step": 2290
|
| 1629 |
+
},
|
| 1630 |
+
{
|
| 1631 |
+
"epoch": 0.9315512353179425,
|
| 1632 |
+
"grad_norm": 4.8997273445129395,
|
| 1633 |
+
"learning_rate": 6.896179289860942e-05,
|
| 1634 |
+
"loss": 0.6714,
|
| 1635 |
+
"step": 2300
|
| 1636 |
+
},
|
| 1637 |
+
{
|
| 1638 |
+
"epoch": 0.9356014580801945,
|
| 1639 |
+
"grad_norm": 4.900916576385498,
|
| 1640 |
+
"learning_rate": 6.882678547320103e-05,
|
| 1641 |
+
"loss": 0.6748,
|
| 1642 |
+
"step": 2310
|
| 1643 |
+
},
|
| 1644 |
+
{
|
| 1645 |
+
"epoch": 0.9396516808424463,
|
| 1646 |
+
"grad_norm": 4.187465667724609,
|
| 1647 |
+
"learning_rate": 6.869177804779263e-05,
|
| 1648 |
+
"loss": 0.6894,
|
| 1649 |
+
"step": 2320
|
| 1650 |
+
},
|
| 1651 |
+
{
|
| 1652 |
+
"epoch": 0.9437019036046983,
|
| 1653 |
+
"grad_norm": 5.871070861816406,
|
| 1654 |
+
"learning_rate": 6.855677062238424e-05,
|
| 1655 |
+
"loss": 0.6843,
|
| 1656 |
+
"step": 2330
|
| 1657 |
+
},
|
| 1658 |
+
{
|
| 1659 |
+
"epoch": 0.9477521263669502,
|
| 1660 |
+
"grad_norm": 4.267555236816406,
|
| 1661 |
+
"learning_rate": 6.842176319697585e-05,
|
| 1662 |
+
"loss": 0.688,
|
| 1663 |
+
"step": 2340
|
| 1664 |
+
},
|
| 1665 |
+
{
|
| 1666 |
+
"epoch": 0.9518023491292021,
|
| 1667 |
+
"grad_norm": 4.01849889755249,
|
| 1668 |
+
"learning_rate": 6.828675577156743e-05,
|
| 1669 |
+
"loss": 0.7011,
|
| 1670 |
+
"step": 2350
|
| 1671 |
+
},
|
| 1672 |
+
{
|
| 1673 |
+
"epoch": 0.955852571891454,
|
| 1674 |
+
"grad_norm": 3.507786512374878,
|
| 1675 |
+
"learning_rate": 6.815174834615904e-05,
|
| 1676 |
+
"loss": 0.6639,
|
| 1677 |
+
"step": 2360
|
| 1678 |
+
},
|
| 1679 |
+
{
|
| 1680 |
+
"epoch": 0.959902794653706,
|
| 1681 |
+
"grad_norm": 1.8241889476776123,
|
| 1682 |
+
"learning_rate": 6.801674092075065e-05,
|
| 1683 |
+
"loss": 0.6805,
|
| 1684 |
+
"step": 2370
|
| 1685 |
+
},
|
| 1686 |
+
{
|
| 1687 |
+
"epoch": 0.9639530174159578,
|
| 1688 |
+
"grad_norm": 1.9074022769927979,
|
| 1689 |
+
"learning_rate": 6.788173349534225e-05,
|
| 1690 |
+
"loss": 0.663,
|
| 1691 |
+
"step": 2380
|
| 1692 |
+
},
|
| 1693 |
+
{
|
| 1694 |
+
"epoch": 0.9680032401782098,
|
| 1695 |
+
"grad_norm": 3.4003665447235107,
|
| 1696 |
+
"learning_rate": 6.774672606993386e-05,
|
| 1697 |
+
"loss": 0.6879,
|
| 1698 |
+
"step": 2390
|
| 1699 |
+
},
|
| 1700 |
+
{
|
| 1701 |
+
"epoch": 0.9720534629404617,
|
| 1702 |
+
"grad_norm": 1.4989181756973267,
|
| 1703 |
+
"learning_rate": 6.761171864452545e-05,
|
| 1704 |
+
"loss": 0.7023,
|
| 1705 |
+
"step": 2400
|
| 1706 |
+
},
|
| 1707 |
+
{
|
| 1708 |
+
"epoch": 0.9761036857027137,
|
| 1709 |
+
"grad_norm": 2.1352789402008057,
|
| 1710 |
+
"learning_rate": 6.747671121911705e-05,
|
| 1711 |
+
"loss": 0.6844,
|
| 1712 |
+
"step": 2410
|
| 1713 |
+
},
|
| 1714 |
+
{
|
| 1715 |
+
"epoch": 0.9801539084649655,
|
| 1716 |
+
"grad_norm": 10.008374214172363,
|
| 1717 |
+
"learning_rate": 6.734170379370866e-05,
|
| 1718 |
+
"loss": 0.6487,
|
| 1719 |
+
"step": 2420
|
| 1720 |
+
},
|
| 1721 |
+
{
|
| 1722 |
+
"epoch": 0.9842041312272175,
|
| 1723 |
+
"grad_norm": 2.7483386993408203,
|
| 1724 |
+
"learning_rate": 6.720669636830026e-05,
|
| 1725 |
+
"loss": 0.693,
|
| 1726 |
+
"step": 2430
|
| 1727 |
+
},
|
| 1728 |
+
{
|
| 1729 |
+
"epoch": 0.9882543539894694,
|
| 1730 |
+
"grad_norm": 11.50084400177002,
|
| 1731 |
+
"learning_rate": 6.707168894289187e-05,
|
| 1732 |
+
"loss": 0.6443,
|
| 1733 |
+
"step": 2440
|
| 1734 |
+
},
|
| 1735 |
+
{
|
| 1736 |
+
"epoch": 0.9923045767517213,
|
| 1737 |
+
"grad_norm": 1.6837221384048462,
|
| 1738 |
+
"learning_rate": 6.693668151748346e-05,
|
| 1739 |
+
"loss": 0.6805,
|
| 1740 |
+
"step": 2450
|
| 1741 |
+
},
|
| 1742 |
+
{
|
| 1743 |
+
"epoch": 0.9963547995139733,
|
| 1744 |
+
"grad_norm": 1.9835008382797241,
|
| 1745 |
+
"learning_rate": 6.680167409207507e-05,
|
| 1746 |
+
"loss": 0.6773,
|
| 1747 |
+
"step": 2460
|
| 1748 |
+
},
|
| 1749 |
+
{
|
| 1750 |
+
"epoch": 1.0,
|
| 1751 |
+
"eval_acc_0.5": 0.5288251791835463,
|
| 1752 |
+
"eval_acc_1.0": 0.8367092552196946,
|
| 1753 |
+
"eval_loss": 0.7152395248413086,
|
| 1754 |
+
"eval_mae": 0.5716977715492249,
|
| 1755 |
+
"eval_pcc": 0.3787382245063782,
|
| 1756 |
+
"eval_qwk": 0.2012183219341548,
|
| 1757 |
+
"eval_rmse": 0.7291858792304993,
|
| 1758 |
+
"eval_runtime": 18.4684,
|
| 1759 |
+
"eval_samples_per_second": 173.756,
|
| 1760 |
+
"eval_src": 0.36552091512825263,
|
| 1761 |
+
"eval_steps_per_second": 10.883,
|
| 1762 |
+
"step": 2469
|
| 1763 |
+
}
|
| 1764 |
+
],
|
| 1765 |
+
"logging_steps": 10,
|
| 1766 |
+
"max_steps": 7407,
|
| 1767 |
+
"num_input_tokens_seen": 0,
|
| 1768 |
+
"num_train_epochs": 3,
|
| 1769 |
+
"save_steps": 500,
|
| 1770 |
+
"stateful_callbacks": {
|
| 1771 |
+
"TrainerControl": {
|
| 1772 |
+
"args": {
|
| 1773 |
+
"should_epoch_stop": false,
|
| 1774 |
+
"should_evaluate": false,
|
| 1775 |
+
"should_log": false,
|
| 1776 |
+
"should_save": true,
|
| 1777 |
+
"should_training_stop": false
|
| 1778 |
+
},
|
| 1779 |
+
"attributes": {}
|
| 1780 |
+
}
|
| 1781 |
+
},
|
| 1782 |
+
"total_flos": 0.0,
|
| 1783 |
+
"train_batch_size": 16,
|
| 1784 |
+
"trial_name": null,
|
| 1785 |
+
"trial_params": null
|
| 1786 |
+
}
|
last-checkpoint/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4c10c1fc8c0b9dcd9239f4e440fbdb09666dd23e353de595abf6545a9b59d92d
|
| 3 |
+
size 5777
|