Upload 6 files
Browse files- optimizer.pt +3 -0
- pytorch_model.bin +3 -0
- scaler.pt +3 -0
- scheduler.pt +3 -0
- trainer_state.json +1987 -0
- training_args.bin +3 -0
optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a15b7d58c806ccdca28b6eb012389eed39d2ff493f1da778d840e35bca38fd0b
|
| 3 |
+
size 33629893
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:cdf7097a1cdc06947c9232f81a8ca3a542e917fbe40182f8b17594a4543f2700
|
| 3 |
+
size 16822989
|
scaler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ac5375a75bff62cac31b3532dc34ff7c284db11ec0ac37d5156f76820385076f
|
| 3 |
+
size 557
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7f9121b13d282a1554a83605688c8f4cd097cb075906d0ffcf9b00fadd0e87ec
|
| 3 |
+
size 627
|
trainer_state.json
ADDED
|
@@ -0,0 +1,1987 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.8592745065689087,
|
| 3 |
+
"epoch": 1.0057919744736934,
|
| 4 |
+
"global_step": 5800,
|
| 5 |
+
"is_hyper_param_search": false,
|
| 6 |
+
"is_local_process_zero": true,
|
| 7 |
+
"is_world_process_zero": true,
|
| 8 |
+
"log_history": [
|
| 9 |
+
{
|
| 10 |
+
"epoch": 0.0,
|
| 11 |
+
"learning_rate": 5.9999999999999995e-05,
|
| 12 |
+
"loss": 1.9169,
|
| 13 |
+
"step": 20
|
| 14 |
+
},
|
| 15 |
+
{
|
| 16 |
+
"epoch": 0.01,
|
| 17 |
+
"learning_rate": 0.00011999999999999999,
|
| 18 |
+
"loss": 1.6001,
|
| 19 |
+
"step": 40
|
| 20 |
+
},
|
| 21 |
+
{
|
| 22 |
+
"epoch": 0.01,
|
| 23 |
+
"learning_rate": 0.00017999999999999998,
|
| 24 |
+
"loss": 1.2273,
|
| 25 |
+
"step": 60
|
| 26 |
+
},
|
| 27 |
+
{
|
| 28 |
+
"epoch": 0.01,
|
| 29 |
+
"learning_rate": 0.00023999999999999998,
|
| 30 |
+
"loss": 1.1652,
|
| 31 |
+
"step": 80
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 0.02,
|
| 35 |
+
"learning_rate": 0.0003,
|
| 36 |
+
"loss": 1.1155,
|
| 37 |
+
"step": 100
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.02,
|
| 41 |
+
"learning_rate": 0.0002996511222235143,
|
| 42 |
+
"loss": 1.0974,
|
| 43 |
+
"step": 120
|
| 44 |
+
},
|
| 45 |
+
{
|
| 46 |
+
"epoch": 0.02,
|
| 47 |
+
"learning_rate": 0.0002993022444470287,
|
| 48 |
+
"loss": 1.0811,
|
| 49 |
+
"step": 140
|
| 50 |
+
},
|
| 51 |
+
{
|
| 52 |
+
"epoch": 0.03,
|
| 53 |
+
"learning_rate": 0.00029895336667054307,
|
| 54 |
+
"loss": 1.0819,
|
| 55 |
+
"step": 160
|
| 56 |
+
},
|
| 57 |
+
{
|
| 58 |
+
"epoch": 0.03,
|
| 59 |
+
"learning_rate": 0.0002986044888940574,
|
| 60 |
+
"loss": 1.0658,
|
| 61 |
+
"step": 180
|
| 62 |
+
},
|
| 63 |
+
{
|
| 64 |
+
"epoch": 0.03,
|
| 65 |
+
"learning_rate": 0.0002982556111175718,
|
| 66 |
+
"loss": 1.0597,
|
| 67 |
+
"step": 200
|
| 68 |
+
},
|
| 69 |
+
{
|
| 70 |
+
"epoch": 0.03,
|
| 71 |
+
"eval_loss": 1.0481364727020264,
|
| 72 |
+
"eval_runtime": 50.5238,
|
| 73 |
+
"eval_samples_per_second": 39.585,
|
| 74 |
+
"eval_steps_per_second": 1.663,
|
| 75 |
+
"step": 200
|
| 76 |
+
},
|
| 77 |
+
{
|
| 78 |
+
"epoch": 0.04,
|
| 79 |
+
"learning_rate": 0.0002979067333410861,
|
| 80 |
+
"loss": 1.0552,
|
| 81 |
+
"step": 220
|
| 82 |
+
},
|
| 83 |
+
{
|
| 84 |
+
"epoch": 0.04,
|
| 85 |
+
"learning_rate": 0.0002975578555646005,
|
| 86 |
+
"loss": 1.0405,
|
| 87 |
+
"step": 240
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.05,
|
| 91 |
+
"learning_rate": 0.0002972089777881149,
|
| 92 |
+
"loss": 1.0433,
|
| 93 |
+
"step": 260
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.05,
|
| 97 |
+
"learning_rate": 0.0002968601000116292,
|
| 98 |
+
"loss": 1.0386,
|
| 99 |
+
"step": 280
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"epoch": 0.05,
|
| 103 |
+
"learning_rate": 0.0002965112222351436,
|
| 104 |
+
"loss": 1.0273,
|
| 105 |
+
"step": 300
|
| 106 |
+
},
|
| 107 |
+
{
|
| 108 |
+
"epoch": 0.06,
|
| 109 |
+
"learning_rate": 0.000296162344458658,
|
| 110 |
+
"loss": 1.04,
|
| 111 |
+
"step": 320
|
| 112 |
+
},
|
| 113 |
+
{
|
| 114 |
+
"epoch": 0.06,
|
| 115 |
+
"learning_rate": 0.0002958134666821723,
|
| 116 |
+
"loss": 1.0148,
|
| 117 |
+
"step": 340
|
| 118 |
+
},
|
| 119 |
+
{
|
| 120 |
+
"epoch": 0.06,
|
| 121 |
+
"learning_rate": 0.0002954645889056867,
|
| 122 |
+
"loss": 1.0144,
|
| 123 |
+
"step": 360
|
| 124 |
+
},
|
| 125 |
+
{
|
| 126 |
+
"epoch": 0.07,
|
| 127 |
+
"learning_rate": 0.000295115711129201,
|
| 128 |
+
"loss": 1.0088,
|
| 129 |
+
"step": 380
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.07,
|
| 133 |
+
"learning_rate": 0.0002947668333527154,
|
| 134 |
+
"loss": 1.0048,
|
| 135 |
+
"step": 400
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.07,
|
| 139 |
+
"eval_loss": 1.0047168731689453,
|
| 140 |
+
"eval_runtime": 49.9795,
|
| 141 |
+
"eval_samples_per_second": 40.016,
|
| 142 |
+
"eval_steps_per_second": 1.681,
|
| 143 |
+
"step": 400
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 0.07,
|
| 147 |
+
"learning_rate": 0.0002944179555762298,
|
| 148 |
+
"loss": 1.0181,
|
| 149 |
+
"step": 420
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 0.08,
|
| 153 |
+
"learning_rate": 0.0002940690777997441,
|
| 154 |
+
"loss": 1.0054,
|
| 155 |
+
"step": 440
|
| 156 |
+
},
|
| 157 |
+
{
|
| 158 |
+
"epoch": 0.08,
|
| 159 |
+
"learning_rate": 0.0002937202000232585,
|
| 160 |
+
"loss": 1.0125,
|
| 161 |
+
"step": 460
|
| 162 |
+
},
|
| 163 |
+
{
|
| 164 |
+
"epoch": 0.08,
|
| 165 |
+
"learning_rate": 0.00029337132224677284,
|
| 166 |
+
"loss": 1.0066,
|
| 167 |
+
"step": 480
|
| 168 |
+
},
|
| 169 |
+
{
|
| 170 |
+
"epoch": 0.09,
|
| 171 |
+
"learning_rate": 0.0002930224444702872,
|
| 172 |
+
"loss": 1.011,
|
| 173 |
+
"step": 500
|
| 174 |
+
},
|
| 175 |
+
{
|
| 176 |
+
"epoch": 0.09,
|
| 177 |
+
"learning_rate": 0.0002926735666938016,
|
| 178 |
+
"loss": 0.9941,
|
| 179 |
+
"step": 520
|
| 180 |
+
},
|
| 181 |
+
{
|
| 182 |
+
"epoch": 0.09,
|
| 183 |
+
"learning_rate": 0.00029232468891731594,
|
| 184 |
+
"loss": 0.9812,
|
| 185 |
+
"step": 540
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 0.1,
|
| 189 |
+
"learning_rate": 0.0002919758111408303,
|
| 190 |
+
"loss": 1.0008,
|
| 191 |
+
"step": 560
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 0.1,
|
| 195 |
+
"learning_rate": 0.00029162693336434465,
|
| 196 |
+
"loss": 0.9934,
|
| 197 |
+
"step": 580
|
| 198 |
+
},
|
| 199 |
+
{
|
| 200 |
+
"epoch": 0.1,
|
| 201 |
+
"learning_rate": 0.00029127805558785904,
|
| 202 |
+
"loss": 0.9811,
|
| 203 |
+
"step": 600
|
| 204 |
+
},
|
| 205 |
+
{
|
| 206 |
+
"epoch": 0.1,
|
| 207 |
+
"eval_loss": 0.9793989062309265,
|
| 208 |
+
"eval_runtime": 50.7216,
|
| 209 |
+
"eval_samples_per_second": 39.431,
|
| 210 |
+
"eval_steps_per_second": 1.656,
|
| 211 |
+
"step": 600
|
| 212 |
+
},
|
| 213 |
+
{
|
| 214 |
+
"epoch": 0.11,
|
| 215 |
+
"learning_rate": 0.0002909291778113734,
|
| 216 |
+
"loss": 0.9917,
|
| 217 |
+
"step": 620
|
| 218 |
+
},
|
| 219 |
+
{
|
| 220 |
+
"epoch": 0.11,
|
| 221 |
+
"learning_rate": 0.00029058030003488775,
|
| 222 |
+
"loss": 0.977,
|
| 223 |
+
"step": 640
|
| 224 |
+
},
|
| 225 |
+
{
|
| 226 |
+
"epoch": 0.11,
|
| 227 |
+
"learning_rate": 0.0002902314222584021,
|
| 228 |
+
"loss": 0.9777,
|
| 229 |
+
"step": 660
|
| 230 |
+
},
|
| 231 |
+
{
|
| 232 |
+
"epoch": 0.12,
|
| 233 |
+
"learning_rate": 0.00028988254448191646,
|
| 234 |
+
"loss": 0.9782,
|
| 235 |
+
"step": 680
|
| 236 |
+
},
|
| 237 |
+
{
|
| 238 |
+
"epoch": 0.12,
|
| 239 |
+
"learning_rate": 0.00028953366670543085,
|
| 240 |
+
"loss": 0.9656,
|
| 241 |
+
"step": 700
|
| 242 |
+
},
|
| 243 |
+
{
|
| 244 |
+
"epoch": 0.12,
|
| 245 |
+
"learning_rate": 0.0002891847889289452,
|
| 246 |
+
"loss": 0.9595,
|
| 247 |
+
"step": 720
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 0.13,
|
| 251 |
+
"learning_rate": 0.00028883591115245956,
|
| 252 |
+
"loss": 0.9712,
|
| 253 |
+
"step": 740
|
| 254 |
+
},
|
| 255 |
+
{
|
| 256 |
+
"epoch": 0.13,
|
| 257 |
+
"learning_rate": 0.00028848703337597395,
|
| 258 |
+
"loss": 0.9784,
|
| 259 |
+
"step": 760
|
| 260 |
+
},
|
| 261 |
+
{
|
| 262 |
+
"epoch": 0.14,
|
| 263 |
+
"learning_rate": 0.0002881381555994883,
|
| 264 |
+
"loss": 0.9714,
|
| 265 |
+
"step": 780
|
| 266 |
+
},
|
| 267 |
+
{
|
| 268 |
+
"epoch": 0.14,
|
| 269 |
+
"learning_rate": 0.00028778927782300266,
|
| 270 |
+
"loss": 0.9728,
|
| 271 |
+
"step": 800
|
| 272 |
+
},
|
| 273 |
+
{
|
| 274 |
+
"epoch": 0.14,
|
| 275 |
+
"eval_loss": 0.9619740843772888,
|
| 276 |
+
"eval_runtime": 49.3289,
|
| 277 |
+
"eval_samples_per_second": 40.544,
|
| 278 |
+
"eval_steps_per_second": 1.703,
|
| 279 |
+
"step": 800
|
| 280 |
+
},
|
| 281 |
+
{
|
| 282 |
+
"epoch": 0.14,
|
| 283 |
+
"learning_rate": 0.000287440400046517,
|
| 284 |
+
"loss": 0.9684,
|
| 285 |
+
"step": 820
|
| 286 |
+
},
|
| 287 |
+
{
|
| 288 |
+
"epoch": 0.15,
|
| 289 |
+
"learning_rate": 0.0002870915222700314,
|
| 290 |
+
"loss": 0.955,
|
| 291 |
+
"step": 840
|
| 292 |
+
},
|
| 293 |
+
{
|
| 294 |
+
"epoch": 0.15,
|
| 295 |
+
"learning_rate": 0.00028674264449354576,
|
| 296 |
+
"loss": 0.9642,
|
| 297 |
+
"step": 860
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 0.15,
|
| 301 |
+
"learning_rate": 0.0002863937667170601,
|
| 302 |
+
"loss": 0.9758,
|
| 303 |
+
"step": 880
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 0.16,
|
| 307 |
+
"learning_rate": 0.00028604488894057447,
|
| 308 |
+
"loss": 0.9601,
|
| 309 |
+
"step": 900
|
| 310 |
+
},
|
| 311 |
+
{
|
| 312 |
+
"epoch": 0.16,
|
| 313 |
+
"learning_rate": 0.0002856960111640888,
|
| 314 |
+
"loss": 0.9597,
|
| 315 |
+
"step": 920
|
| 316 |
+
},
|
| 317 |
+
{
|
| 318 |
+
"epoch": 0.16,
|
| 319 |
+
"learning_rate": 0.0002853471333876032,
|
| 320 |
+
"loss": 0.9615,
|
| 321 |
+
"step": 940
|
| 322 |
+
},
|
| 323 |
+
{
|
| 324 |
+
"epoch": 0.17,
|
| 325 |
+
"learning_rate": 0.00028499825561111757,
|
| 326 |
+
"loss": 0.9562,
|
| 327 |
+
"step": 960
|
| 328 |
+
},
|
| 329 |
+
{
|
| 330 |
+
"epoch": 0.17,
|
| 331 |
+
"learning_rate": 0.0002846493778346319,
|
| 332 |
+
"loss": 0.9543,
|
| 333 |
+
"step": 980
|
| 334 |
+
},
|
| 335 |
+
{
|
| 336 |
+
"epoch": 0.17,
|
| 337 |
+
"learning_rate": 0.0002843005000581463,
|
| 338 |
+
"loss": 0.9593,
|
| 339 |
+
"step": 1000
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 0.17,
|
| 343 |
+
"eval_loss": 0.9471739530563354,
|
| 344 |
+
"eval_runtime": 49.1237,
|
| 345 |
+
"eval_samples_per_second": 40.714,
|
| 346 |
+
"eval_steps_per_second": 1.71,
|
| 347 |
+
"step": 1000
|
| 348 |
+
},
|
| 349 |
+
{
|
| 350 |
+
"epoch": 0.18,
|
| 351 |
+
"learning_rate": 0.0002839516222816606,
|
| 352 |
+
"loss": 0.9498,
|
| 353 |
+
"step": 1020
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 0.18,
|
| 357 |
+
"learning_rate": 0.000283602744505175,
|
| 358 |
+
"loss": 0.9416,
|
| 359 |
+
"step": 1040
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 0.18,
|
| 363 |
+
"learning_rate": 0.0002832538667286894,
|
| 364 |
+
"loss": 0.9476,
|
| 365 |
+
"step": 1060
|
| 366 |
+
},
|
| 367 |
+
{
|
| 368 |
+
"epoch": 0.19,
|
| 369 |
+
"learning_rate": 0.0002829049889522037,
|
| 370 |
+
"loss": 0.9486,
|
| 371 |
+
"step": 1080
|
| 372 |
+
},
|
| 373 |
+
{
|
| 374 |
+
"epoch": 0.19,
|
| 375 |
+
"learning_rate": 0.0002825561111757181,
|
| 376 |
+
"loss": 0.9581,
|
| 377 |
+
"step": 1100
|
| 378 |
+
},
|
| 379 |
+
{
|
| 380 |
+
"epoch": 0.19,
|
| 381 |
+
"learning_rate": 0.0002822072333992325,
|
| 382 |
+
"loss": 0.9429,
|
| 383 |
+
"step": 1120
|
| 384 |
+
},
|
| 385 |
+
{
|
| 386 |
+
"epoch": 0.2,
|
| 387 |
+
"learning_rate": 0.0002818583556227468,
|
| 388 |
+
"loss": 0.9513,
|
| 389 |
+
"step": 1140
|
| 390 |
+
},
|
| 391 |
+
{
|
| 392 |
+
"epoch": 0.2,
|
| 393 |
+
"learning_rate": 0.00028150947784626114,
|
| 394 |
+
"loss": 0.9489,
|
| 395 |
+
"step": 1160
|
| 396 |
+
},
|
| 397 |
+
{
|
| 398 |
+
"epoch": 0.2,
|
| 399 |
+
"learning_rate": 0.0002811606000697755,
|
| 400 |
+
"loss": 0.9384,
|
| 401 |
+
"step": 1180
|
| 402 |
+
},
|
| 403 |
+
{
|
| 404 |
+
"epoch": 0.21,
|
| 405 |
+
"learning_rate": 0.0002808117222932899,
|
| 406 |
+
"loss": 0.9496,
|
| 407 |
+
"step": 1200
|
| 408 |
+
},
|
| 409 |
+
{
|
| 410 |
+
"epoch": 0.21,
|
| 411 |
+
"eval_loss": 0.9367659687995911,
|
| 412 |
+
"eval_runtime": 48.936,
|
| 413 |
+
"eval_samples_per_second": 40.87,
|
| 414 |
+
"eval_steps_per_second": 1.717,
|
| 415 |
+
"step": 1200
|
| 416 |
+
},
|
| 417 |
+
{
|
| 418 |
+
"epoch": 0.21,
|
| 419 |
+
"learning_rate": 0.00028046284451680424,
|
| 420 |
+
"loss": 0.941,
|
| 421 |
+
"step": 1220
|
| 422 |
+
},
|
| 423 |
+
{
|
| 424 |
+
"epoch": 0.22,
|
| 425 |
+
"learning_rate": 0.0002801139667403186,
|
| 426 |
+
"loss": 0.94,
|
| 427 |
+
"step": 1240
|
| 428 |
+
},
|
| 429 |
+
{
|
| 430 |
+
"epoch": 0.22,
|
| 431 |
+
"learning_rate": 0.00027976508896383295,
|
| 432 |
+
"loss": 0.9349,
|
| 433 |
+
"step": 1260
|
| 434 |
+
},
|
| 435 |
+
{
|
| 436 |
+
"epoch": 0.22,
|
| 437 |
+
"learning_rate": 0.00027941621118734734,
|
| 438 |
+
"loss": 0.9378,
|
| 439 |
+
"step": 1280
|
| 440 |
+
},
|
| 441 |
+
{
|
| 442 |
+
"epoch": 0.23,
|
| 443 |
+
"learning_rate": 0.0002790673334108617,
|
| 444 |
+
"loss": 0.9361,
|
| 445 |
+
"step": 1300
|
| 446 |
+
},
|
| 447 |
+
{
|
| 448 |
+
"epoch": 0.23,
|
| 449 |
+
"learning_rate": 0.00027871845563437605,
|
| 450 |
+
"loss": 0.9426,
|
| 451 |
+
"step": 1320
|
| 452 |
+
},
|
| 453 |
+
{
|
| 454 |
+
"epoch": 0.23,
|
| 455 |
+
"learning_rate": 0.00027836957785789043,
|
| 456 |
+
"loss": 0.9427,
|
| 457 |
+
"step": 1340
|
| 458 |
+
},
|
| 459 |
+
{
|
| 460 |
+
"epoch": 0.24,
|
| 461 |
+
"learning_rate": 0.00027802070008140476,
|
| 462 |
+
"loss": 0.9339,
|
| 463 |
+
"step": 1360
|
| 464 |
+
},
|
| 465 |
+
{
|
| 466 |
+
"epoch": 0.24,
|
| 467 |
+
"learning_rate": 0.00027767182230491915,
|
| 468 |
+
"loss": 0.9313,
|
| 469 |
+
"step": 1380
|
| 470 |
+
},
|
| 471 |
+
{
|
| 472 |
+
"epoch": 0.24,
|
| 473 |
+
"learning_rate": 0.00027732294452843353,
|
| 474 |
+
"loss": 0.9308,
|
| 475 |
+
"step": 1400
|
| 476 |
+
},
|
| 477 |
+
{
|
| 478 |
+
"epoch": 0.24,
|
| 479 |
+
"eval_loss": 0.9267547726631165,
|
| 480 |
+
"eval_runtime": 49.2408,
|
| 481 |
+
"eval_samples_per_second": 40.617,
|
| 482 |
+
"eval_steps_per_second": 1.706,
|
| 483 |
+
"step": 1400
|
| 484 |
+
},
|
| 485 |
+
{
|
| 486 |
+
"epoch": 0.25,
|
| 487 |
+
"learning_rate": 0.00027697406675194786,
|
| 488 |
+
"loss": 0.9299,
|
| 489 |
+
"step": 1420
|
| 490 |
+
},
|
| 491 |
+
{
|
| 492 |
+
"epoch": 0.25,
|
| 493 |
+
"learning_rate": 0.00027662518897546225,
|
| 494 |
+
"loss": 0.9334,
|
| 495 |
+
"step": 1440
|
| 496 |
+
},
|
| 497 |
+
{
|
| 498 |
+
"epoch": 0.25,
|
| 499 |
+
"learning_rate": 0.0002762763111989766,
|
| 500 |
+
"loss": 0.9264,
|
| 501 |
+
"step": 1460
|
| 502 |
+
},
|
| 503 |
+
{
|
| 504 |
+
"epoch": 0.26,
|
| 505 |
+
"learning_rate": 0.00027592743342249096,
|
| 506 |
+
"loss": 0.9175,
|
| 507 |
+
"step": 1480
|
| 508 |
+
},
|
| 509 |
+
{
|
| 510 |
+
"epoch": 0.26,
|
| 511 |
+
"learning_rate": 0.00027557855564600535,
|
| 512 |
+
"loss": 0.9376,
|
| 513 |
+
"step": 1500
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 0.26,
|
| 517 |
+
"learning_rate": 0.0002752296778695197,
|
| 518 |
+
"loss": 0.9273,
|
| 519 |
+
"step": 1520
|
| 520 |
+
},
|
| 521 |
+
{
|
| 522 |
+
"epoch": 0.27,
|
| 523 |
+
"learning_rate": 0.00027488080009303406,
|
| 524 |
+
"loss": 0.9319,
|
| 525 |
+
"step": 1540
|
| 526 |
+
},
|
| 527 |
+
{
|
| 528 |
+
"epoch": 0.27,
|
| 529 |
+
"learning_rate": 0.00027453192231654844,
|
| 530 |
+
"loss": 0.9261,
|
| 531 |
+
"step": 1560
|
| 532 |
+
},
|
| 533 |
+
{
|
| 534 |
+
"epoch": 0.27,
|
| 535 |
+
"learning_rate": 0.0002741830445400628,
|
| 536 |
+
"loss": 0.9246,
|
| 537 |
+
"step": 1580
|
| 538 |
+
},
|
| 539 |
+
{
|
| 540 |
+
"epoch": 0.28,
|
| 541 |
+
"learning_rate": 0.00027383416676357716,
|
| 542 |
+
"loss": 0.9249,
|
| 543 |
+
"step": 1600
|
| 544 |
+
},
|
| 545 |
+
{
|
| 546 |
+
"epoch": 0.28,
|
| 547 |
+
"eval_loss": 0.9193373322486877,
|
| 548 |
+
"eval_runtime": 49.234,
|
| 549 |
+
"eval_samples_per_second": 40.622,
|
| 550 |
+
"eval_steps_per_second": 1.706,
|
| 551 |
+
"step": 1600
|
| 552 |
+
},
|
| 553 |
+
{
|
| 554 |
+
"epoch": 0.28,
|
| 555 |
+
"learning_rate": 0.0002734852889870915,
|
| 556 |
+
"loss": 0.9114,
|
| 557 |
+
"step": 1620
|
| 558 |
+
},
|
| 559 |
+
{
|
| 560 |
+
"epoch": 0.28,
|
| 561 |
+
"learning_rate": 0.00027313641121060587,
|
| 562 |
+
"loss": 0.9314,
|
| 563 |
+
"step": 1640
|
| 564 |
+
},
|
| 565 |
+
{
|
| 566 |
+
"epoch": 0.29,
|
| 567 |
+
"learning_rate": 0.00027278753343412026,
|
| 568 |
+
"loss": 0.9225,
|
| 569 |
+
"step": 1660
|
| 570 |
+
},
|
| 571 |
+
{
|
| 572 |
+
"epoch": 0.29,
|
| 573 |
+
"learning_rate": 0.0002724386556576346,
|
| 574 |
+
"loss": 0.9265,
|
| 575 |
+
"step": 1680
|
| 576 |
+
},
|
| 577 |
+
{
|
| 578 |
+
"epoch": 0.29,
|
| 579 |
+
"learning_rate": 0.0002720897778811489,
|
| 580 |
+
"loss": 0.9223,
|
| 581 |
+
"step": 1700
|
| 582 |
+
},
|
| 583 |
+
{
|
| 584 |
+
"epoch": 0.3,
|
| 585 |
+
"learning_rate": 0.0002717409001046633,
|
| 586 |
+
"loss": 0.9105,
|
| 587 |
+
"step": 1720
|
| 588 |
+
},
|
| 589 |
+
{
|
| 590 |
+
"epoch": 0.3,
|
| 591 |
+
"learning_rate": 0.0002713920223281777,
|
| 592 |
+
"loss": 0.9241,
|
| 593 |
+
"step": 1740
|
| 594 |
+
},
|
| 595 |
+
{
|
| 596 |
+
"epoch": 0.31,
|
| 597 |
+
"learning_rate": 0.000271043144551692,
|
| 598 |
+
"loss": 0.9176,
|
| 599 |
+
"step": 1760
|
| 600 |
+
},
|
| 601 |
+
{
|
| 602 |
+
"epoch": 0.31,
|
| 603 |
+
"learning_rate": 0.0002706942667752064,
|
| 604 |
+
"loss": 0.9254,
|
| 605 |
+
"step": 1780
|
| 606 |
+
},
|
| 607 |
+
{
|
| 608 |
+
"epoch": 0.31,
|
| 609 |
+
"learning_rate": 0.00027034538899872073,
|
| 610 |
+
"loss": 0.9225,
|
| 611 |
+
"step": 1800
|
| 612 |
+
},
|
| 613 |
+
{
|
| 614 |
+
"epoch": 0.31,
|
| 615 |
+
"eval_loss": 0.9116300344467163,
|
| 616 |
+
"eval_runtime": 49.2973,
|
| 617 |
+
"eval_samples_per_second": 40.57,
|
| 618 |
+
"eval_steps_per_second": 1.704,
|
| 619 |
+
"step": 1800
|
| 620 |
+
},
|
| 621 |
+
{
|
| 622 |
+
"epoch": 0.32,
|
| 623 |
+
"learning_rate": 0.0002699965112222351,
|
| 624 |
+
"loss": 0.9097,
|
| 625 |
+
"step": 1820
|
| 626 |
+
},
|
| 627 |
+
{
|
| 628 |
+
"epoch": 0.32,
|
| 629 |
+
"learning_rate": 0.0002696476334457495,
|
| 630 |
+
"loss": 0.9224,
|
| 631 |
+
"step": 1840
|
| 632 |
+
},
|
| 633 |
+
{
|
| 634 |
+
"epoch": 0.32,
|
| 635 |
+
"learning_rate": 0.0002692987556692638,
|
| 636 |
+
"loss": 0.921,
|
| 637 |
+
"step": 1860
|
| 638 |
+
},
|
| 639 |
+
{
|
| 640 |
+
"epoch": 0.33,
|
| 641 |
+
"learning_rate": 0.0002689498778927782,
|
| 642 |
+
"loss": 0.9143,
|
| 643 |
+
"step": 1880
|
| 644 |
+
},
|
| 645 |
+
{
|
| 646 |
+
"epoch": 0.33,
|
| 647 |
+
"learning_rate": 0.00026860100011629254,
|
| 648 |
+
"loss": 0.9144,
|
| 649 |
+
"step": 1900
|
| 650 |
+
},
|
| 651 |
+
{
|
| 652 |
+
"epoch": 0.33,
|
| 653 |
+
"learning_rate": 0.0002682521223398069,
|
| 654 |
+
"loss": 0.9129,
|
| 655 |
+
"step": 1920
|
| 656 |
+
},
|
| 657 |
+
{
|
| 658 |
+
"epoch": 0.34,
|
| 659 |
+
"learning_rate": 0.0002679032445633213,
|
| 660 |
+
"loss": 0.9124,
|
| 661 |
+
"step": 1940
|
| 662 |
+
},
|
| 663 |
+
{
|
| 664 |
+
"epoch": 0.34,
|
| 665 |
+
"learning_rate": 0.00026755436678683564,
|
| 666 |
+
"loss": 0.9107,
|
| 667 |
+
"step": 1960
|
| 668 |
+
},
|
| 669 |
+
{
|
| 670 |
+
"epoch": 0.34,
|
| 671 |
+
"learning_rate": 0.00026720548901035,
|
| 672 |
+
"loss": 0.9123,
|
| 673 |
+
"step": 1980
|
| 674 |
+
},
|
| 675 |
+
{
|
| 676 |
+
"epoch": 0.35,
|
| 677 |
+
"learning_rate": 0.0002668566112338644,
|
| 678 |
+
"loss": 0.9081,
|
| 679 |
+
"step": 2000
|
| 680 |
+
},
|
| 681 |
+
{
|
| 682 |
+
"epoch": 0.35,
|
| 683 |
+
"eval_loss": 0.9067729115486145,
|
| 684 |
+
"eval_runtime": 49.6863,
|
| 685 |
+
"eval_samples_per_second": 40.253,
|
| 686 |
+
"eval_steps_per_second": 1.691,
|
| 687 |
+
"step": 2000
|
| 688 |
+
},
|
| 689 |
+
{
|
| 690 |
+
"epoch": 0.35,
|
| 691 |
+
"learning_rate": 0.00026650773345737874,
|
| 692 |
+
"loss": 0.9066,
|
| 693 |
+
"step": 2020
|
| 694 |
+
},
|
| 695 |
+
{
|
| 696 |
+
"epoch": 0.35,
|
| 697 |
+
"learning_rate": 0.0002661588556808931,
|
| 698 |
+
"loss": 0.9063,
|
| 699 |
+
"step": 2040
|
| 700 |
+
},
|
| 701 |
+
{
|
| 702 |
+
"epoch": 0.36,
|
| 703 |
+
"learning_rate": 0.00026580997790440745,
|
| 704 |
+
"loss": 0.913,
|
| 705 |
+
"step": 2060
|
| 706 |
+
},
|
| 707 |
+
{
|
| 708 |
+
"epoch": 0.36,
|
| 709 |
+
"learning_rate": 0.00026546110012792183,
|
| 710 |
+
"loss": 0.9131,
|
| 711 |
+
"step": 2080
|
| 712 |
+
},
|
| 713 |
+
{
|
| 714 |
+
"epoch": 0.36,
|
| 715 |
+
"learning_rate": 0.0002651122223514362,
|
| 716 |
+
"loss": 0.9071,
|
| 717 |
+
"step": 2100
|
| 718 |
+
},
|
| 719 |
+
{
|
| 720 |
+
"epoch": 0.37,
|
| 721 |
+
"learning_rate": 0.00026476334457495055,
|
| 722 |
+
"loss": 0.9076,
|
| 723 |
+
"step": 2120
|
| 724 |
+
},
|
| 725 |
+
{
|
| 726 |
+
"epoch": 0.37,
|
| 727 |
+
"learning_rate": 0.00026441446679846493,
|
| 728 |
+
"loss": 0.9184,
|
| 729 |
+
"step": 2140
|
| 730 |
+
},
|
| 731 |
+
{
|
| 732 |
+
"epoch": 0.37,
|
| 733 |
+
"learning_rate": 0.00026406558902197926,
|
| 734 |
+
"loss": 0.9082,
|
| 735 |
+
"step": 2160
|
| 736 |
+
},
|
| 737 |
+
{
|
| 738 |
+
"epoch": 0.38,
|
| 739 |
+
"learning_rate": 0.00026371671124549365,
|
| 740 |
+
"loss": 0.9151,
|
| 741 |
+
"step": 2180
|
| 742 |
+
},
|
| 743 |
+
{
|
| 744 |
+
"epoch": 0.38,
|
| 745 |
+
"learning_rate": 0.00026336783346900803,
|
| 746 |
+
"loss": 0.9214,
|
| 747 |
+
"step": 2200
|
| 748 |
+
},
|
| 749 |
+
{
|
| 750 |
+
"epoch": 0.38,
|
| 751 |
+
"eval_loss": 0.901930034160614,
|
| 752 |
+
"eval_runtime": 49.1887,
|
| 753 |
+
"eval_samples_per_second": 40.66,
|
| 754 |
+
"eval_steps_per_second": 1.708,
|
| 755 |
+
"step": 2200
|
| 756 |
+
},
|
| 757 |
+
{
|
| 758 |
+
"epoch": 0.38,
|
| 759 |
+
"learning_rate": 0.00026301895569252236,
|
| 760 |
+
"loss": 0.9065,
|
| 761 |
+
"step": 2220
|
| 762 |
+
},
|
| 763 |
+
{
|
| 764 |
+
"epoch": 0.39,
|
| 765 |
+
"learning_rate": 0.0002626700779160367,
|
| 766 |
+
"loss": 0.9105,
|
| 767 |
+
"step": 2240
|
| 768 |
+
},
|
| 769 |
+
{
|
| 770 |
+
"epoch": 0.39,
|
| 771 |
+
"learning_rate": 0.0002623212001395511,
|
| 772 |
+
"loss": 0.8953,
|
| 773 |
+
"step": 2260
|
| 774 |
+
},
|
| 775 |
+
{
|
| 776 |
+
"epoch": 0.4,
|
| 777 |
+
"learning_rate": 0.00026197232236306546,
|
| 778 |
+
"loss": 0.9041,
|
| 779 |
+
"step": 2280
|
| 780 |
+
},
|
| 781 |
+
{
|
| 782 |
+
"epoch": 0.4,
|
| 783 |
+
"learning_rate": 0.0002616234445865798,
|
| 784 |
+
"loss": 0.8988,
|
| 785 |
+
"step": 2300
|
| 786 |
+
},
|
| 787 |
+
{
|
| 788 |
+
"epoch": 0.4,
|
| 789 |
+
"learning_rate": 0.0002612745668100942,
|
| 790 |
+
"loss": 0.9124,
|
| 791 |
+
"step": 2320
|
| 792 |
+
},
|
| 793 |
+
{
|
| 794 |
+
"epoch": 0.41,
|
| 795 |
+
"learning_rate": 0.0002609256890336085,
|
| 796 |
+
"loss": 0.9042,
|
| 797 |
+
"step": 2340
|
| 798 |
+
},
|
| 799 |
+
{
|
| 800 |
+
"epoch": 0.41,
|
| 801 |
+
"learning_rate": 0.0002605768112571229,
|
| 802 |
+
"loss": 0.9154,
|
| 803 |
+
"step": 2360
|
| 804 |
+
},
|
| 805 |
+
{
|
| 806 |
+
"epoch": 0.41,
|
| 807 |
+
"learning_rate": 0.00026022793348063727,
|
| 808 |
+
"loss": 0.9015,
|
| 809 |
+
"step": 2380
|
| 810 |
+
},
|
| 811 |
+
{
|
| 812 |
+
"epoch": 0.42,
|
| 813 |
+
"learning_rate": 0.0002598790557041516,
|
| 814 |
+
"loss": 0.9015,
|
| 815 |
+
"step": 2400
|
| 816 |
+
},
|
| 817 |
+
{
|
| 818 |
+
"epoch": 0.42,
|
| 819 |
+
"eval_loss": 0.8977901935577393,
|
| 820 |
+
"eval_runtime": 50.3787,
|
| 821 |
+
"eval_samples_per_second": 39.699,
|
| 822 |
+
"eval_steps_per_second": 1.667,
|
| 823 |
+
"step": 2400
|
| 824 |
+
},
|
| 825 |
+
{
|
| 826 |
+
"epoch": 0.42,
|
| 827 |
+
"learning_rate": 0.000259530177927666,
|
| 828 |
+
"loss": 0.8981,
|
| 829 |
+
"step": 2420
|
| 830 |
+
},
|
| 831 |
+
{
|
| 832 |
+
"epoch": 0.42,
|
| 833 |
+
"learning_rate": 0.00025918130015118037,
|
| 834 |
+
"loss": 0.8962,
|
| 835 |
+
"step": 2440
|
| 836 |
+
},
|
| 837 |
+
{
|
| 838 |
+
"epoch": 0.43,
|
| 839 |
+
"learning_rate": 0.0002588324223746947,
|
| 840 |
+
"loss": 0.8933,
|
| 841 |
+
"step": 2460
|
| 842 |
+
},
|
| 843 |
+
{
|
| 844 |
+
"epoch": 0.43,
|
| 845 |
+
"learning_rate": 0.0002584835445982091,
|
| 846 |
+
"loss": 0.8962,
|
| 847 |
+
"step": 2480
|
| 848 |
+
},
|
| 849 |
+
{
|
| 850 |
+
"epoch": 0.43,
|
| 851 |
+
"learning_rate": 0.0002581346668217234,
|
| 852 |
+
"loss": 0.8951,
|
| 853 |
+
"step": 2500
|
| 854 |
+
},
|
| 855 |
+
{
|
| 856 |
+
"epoch": 0.44,
|
| 857 |
+
"learning_rate": 0.0002577857890452378,
|
| 858 |
+
"loss": 0.898,
|
| 859 |
+
"step": 2520
|
| 860 |
+
},
|
| 861 |
+
{
|
| 862 |
+
"epoch": 0.44,
|
| 863 |
+
"learning_rate": 0.0002574369112687522,
|
| 864 |
+
"loss": 0.9002,
|
| 865 |
+
"step": 2540
|
| 866 |
+
},
|
| 867 |
+
{
|
| 868 |
+
"epoch": 0.44,
|
| 869 |
+
"learning_rate": 0.0002570880334922665,
|
| 870 |
+
"loss": 0.896,
|
| 871 |
+
"step": 2560
|
| 872 |
+
},
|
| 873 |
+
{
|
| 874 |
+
"epoch": 0.45,
|
| 875 |
+
"learning_rate": 0.0002567391557157809,
|
| 876 |
+
"loss": 0.9062,
|
| 877 |
+
"step": 2580
|
| 878 |
+
},
|
| 879 |
+
{
|
| 880 |
+
"epoch": 0.45,
|
| 881 |
+
"learning_rate": 0.0002563902779392952,
|
| 882 |
+
"loss": 0.8962,
|
| 883 |
+
"step": 2600
|
| 884 |
+
},
|
| 885 |
+
{
|
| 886 |
+
"epoch": 0.45,
|
| 887 |
+
"eval_loss": 0.8936859369277954,
|
| 888 |
+
"eval_runtime": 49.4977,
|
| 889 |
+
"eval_samples_per_second": 40.406,
|
| 890 |
+
"eval_steps_per_second": 1.697,
|
| 891 |
+
"step": 2600
|
| 892 |
+
},
|
| 893 |
+
{
|
| 894 |
+
"epoch": 0.45,
|
| 895 |
+
"learning_rate": 0.0002560414001628096,
|
| 896 |
+
"loss": 0.8948,
|
| 897 |
+
"step": 2620
|
| 898 |
+
},
|
| 899 |
+
{
|
| 900 |
+
"epoch": 0.46,
|
| 901 |
+
"learning_rate": 0.000255692522386324,
|
| 902 |
+
"loss": 0.9002,
|
| 903 |
+
"step": 2640
|
| 904 |
+
},
|
| 905 |
+
{
|
| 906 |
+
"epoch": 0.46,
|
| 907 |
+
"learning_rate": 0.0002553436446098383,
|
| 908 |
+
"loss": 0.8956,
|
| 909 |
+
"step": 2660
|
| 910 |
+
},
|
| 911 |
+
{
|
| 912 |
+
"epoch": 0.46,
|
| 913 |
+
"learning_rate": 0.0002549947668333527,
|
| 914 |
+
"loss": 0.8972,
|
| 915 |
+
"step": 2680
|
| 916 |
+
},
|
| 917 |
+
{
|
| 918 |
+
"epoch": 0.47,
|
| 919 |
+
"learning_rate": 0.0002546458890568671,
|
| 920 |
+
"loss": 0.8883,
|
| 921 |
+
"step": 2700
|
| 922 |
+
},
|
| 923 |
+
{
|
| 924 |
+
"epoch": 0.47,
|
| 925 |
+
"learning_rate": 0.0002542970112803814,
|
| 926 |
+
"loss": 0.9009,
|
| 927 |
+
"step": 2720
|
| 928 |
+
},
|
| 929 |
+
{
|
| 930 |
+
"epoch": 0.48,
|
| 931 |
+
"learning_rate": 0.00025394813350389575,
|
| 932 |
+
"loss": 0.8969,
|
| 933 |
+
"step": 2740
|
| 934 |
+
},
|
| 935 |
+
{
|
| 936 |
+
"epoch": 0.48,
|
| 937 |
+
"learning_rate": 0.00025359925572741014,
|
| 938 |
+
"loss": 0.8963,
|
| 939 |
+
"step": 2760
|
| 940 |
+
},
|
| 941 |
+
{
|
| 942 |
+
"epoch": 0.48,
|
| 943 |
+
"learning_rate": 0.00025325037795092447,
|
| 944 |
+
"loss": 0.8868,
|
| 945 |
+
"step": 2780
|
| 946 |
+
},
|
| 947 |
+
{
|
| 948 |
+
"epoch": 0.49,
|
| 949 |
+
"learning_rate": 0.00025290150017443885,
|
| 950 |
+
"loss": 0.8945,
|
| 951 |
+
"step": 2800
|
| 952 |
+
},
|
| 953 |
+
{
|
| 954 |
+
"epoch": 0.49,
|
| 955 |
+
"eval_loss": 0.8895061612129211,
|
| 956 |
+
"eval_runtime": 49.4815,
|
| 957 |
+
"eval_samples_per_second": 40.419,
|
| 958 |
+
"eval_steps_per_second": 1.698,
|
| 959 |
+
"step": 2800
|
| 960 |
+
},
|
| 961 |
+
{
|
| 962 |
+
"epoch": 0.49,
|
| 963 |
+
"learning_rate": 0.00025255262239795323,
|
| 964 |
+
"loss": 0.8915,
|
| 965 |
+
"step": 2820
|
| 966 |
+
},
|
| 967 |
+
{
|
| 968 |
+
"epoch": 0.49,
|
| 969 |
+
"learning_rate": 0.00025220374462146756,
|
| 970 |
+
"loss": 0.8965,
|
| 971 |
+
"step": 2840
|
| 972 |
+
},
|
| 973 |
+
{
|
| 974 |
+
"epoch": 0.5,
|
| 975 |
+
"learning_rate": 0.00025185486684498195,
|
| 976 |
+
"loss": 0.8934,
|
| 977 |
+
"step": 2860
|
| 978 |
+
},
|
| 979 |
+
{
|
| 980 |
+
"epoch": 0.5,
|
| 981 |
+
"learning_rate": 0.00025150598906849633,
|
| 982 |
+
"loss": 0.8904,
|
| 983 |
+
"step": 2880
|
| 984 |
+
},
|
| 985 |
+
{
|
| 986 |
+
"epoch": 0.5,
|
| 987 |
+
"learning_rate": 0.00025115711129201066,
|
| 988 |
+
"loss": 0.8974,
|
| 989 |
+
"step": 2900
|
| 990 |
+
},
|
| 991 |
+
{
|
| 992 |
+
"epoch": 0.51,
|
| 993 |
+
"learning_rate": 0.00025080823351552505,
|
| 994 |
+
"loss": 0.8851,
|
| 995 |
+
"step": 2920
|
| 996 |
+
},
|
| 997 |
+
{
|
| 998 |
+
"epoch": 0.51,
|
| 999 |
+
"learning_rate": 0.0002504593557390394,
|
| 1000 |
+
"loss": 0.8883,
|
| 1001 |
+
"step": 2940
|
| 1002 |
+
},
|
| 1003 |
+
{
|
| 1004 |
+
"epoch": 0.51,
|
| 1005 |
+
"learning_rate": 0.00025011047796255376,
|
| 1006 |
+
"loss": 0.8898,
|
| 1007 |
+
"step": 2960
|
| 1008 |
+
},
|
| 1009 |
+
{
|
| 1010 |
+
"epoch": 0.52,
|
| 1011 |
+
"learning_rate": 0.00024976160018606815,
|
| 1012 |
+
"loss": 0.8916,
|
| 1013 |
+
"step": 2980
|
| 1014 |
+
},
|
| 1015 |
+
{
|
| 1016 |
+
"epoch": 0.52,
|
| 1017 |
+
"learning_rate": 0.0002494127224095825,
|
| 1018 |
+
"loss": 0.8891,
|
| 1019 |
+
"step": 3000
|
| 1020 |
+
},
|
| 1021 |
+
{
|
| 1022 |
+
"epoch": 0.52,
|
| 1023 |
+
"eval_loss": 0.885992169380188,
|
| 1024 |
+
"eval_runtime": 50.6986,
|
| 1025 |
+
"eval_samples_per_second": 39.449,
|
| 1026 |
+
"eval_steps_per_second": 1.657,
|
| 1027 |
+
"step": 3000
|
| 1028 |
+
},
|
| 1029 |
+
{
|
| 1030 |
+
"epoch": 0.52,
|
| 1031 |
+
"learning_rate": 0.00024906384463309686,
|
| 1032 |
+
"loss": 0.8866,
|
| 1033 |
+
"step": 3020
|
| 1034 |
+
},
|
| 1035 |
+
{
|
| 1036 |
+
"epoch": 0.53,
|
| 1037 |
+
"learning_rate": 0.0002487149668566112,
|
| 1038 |
+
"loss": 0.887,
|
| 1039 |
+
"step": 3040
|
| 1040 |
+
},
|
| 1041 |
+
{
|
| 1042 |
+
"epoch": 0.53,
|
| 1043 |
+
"learning_rate": 0.0002483660890801256,
|
| 1044 |
+
"loss": 0.8756,
|
| 1045 |
+
"step": 3060
|
| 1046 |
+
},
|
| 1047 |
+
{
|
| 1048 |
+
"epoch": 0.53,
|
| 1049 |
+
"learning_rate": 0.00024801721130363996,
|
| 1050 |
+
"loss": 0.8814,
|
| 1051 |
+
"step": 3080
|
| 1052 |
+
},
|
| 1053 |
+
{
|
| 1054 |
+
"epoch": 0.54,
|
| 1055 |
+
"learning_rate": 0.0002476683335271543,
|
| 1056 |
+
"loss": 0.8766,
|
| 1057 |
+
"step": 3100
|
| 1058 |
+
},
|
| 1059 |
+
{
|
| 1060 |
+
"epoch": 0.54,
|
| 1061 |
+
"learning_rate": 0.00024731945575066867,
|
| 1062 |
+
"loss": 0.887,
|
| 1063 |
+
"step": 3120
|
| 1064 |
+
},
|
| 1065 |
+
{
|
| 1066 |
+
"epoch": 0.54,
|
| 1067 |
+
"learning_rate": 0.00024697057797418306,
|
| 1068 |
+
"loss": 0.8901,
|
| 1069 |
+
"step": 3140
|
| 1070 |
+
},
|
| 1071 |
+
{
|
| 1072 |
+
"epoch": 0.55,
|
| 1073 |
+
"learning_rate": 0.0002466217001976974,
|
| 1074 |
+
"loss": 0.8807,
|
| 1075 |
+
"step": 3160
|
| 1076 |
+
},
|
| 1077 |
+
{
|
| 1078 |
+
"epoch": 0.55,
|
| 1079 |
+
"learning_rate": 0.00024627282242121177,
|
| 1080 |
+
"loss": 0.8927,
|
| 1081 |
+
"step": 3180
|
| 1082 |
+
},
|
| 1083 |
+
{
|
| 1084 |
+
"epoch": 0.55,
|
| 1085 |
+
"learning_rate": 0.0002459239446447261,
|
| 1086 |
+
"loss": 0.89,
|
| 1087 |
+
"step": 3200
|
| 1088 |
+
},
|
| 1089 |
+
{
|
| 1090 |
+
"epoch": 0.55,
|
| 1091 |
+
"eval_loss": 0.8836617469787598,
|
| 1092 |
+
"eval_runtime": 49.351,
|
| 1093 |
+
"eval_samples_per_second": 40.526,
|
| 1094 |
+
"eval_steps_per_second": 1.702,
|
| 1095 |
+
"step": 3200
|
| 1096 |
+
},
|
| 1097 |
+
{
|
| 1098 |
+
"epoch": 0.56,
|
| 1099 |
+
"learning_rate": 0.00024557506686824043,
|
| 1100 |
+
"loss": 0.892,
|
| 1101 |
+
"step": 3220
|
| 1102 |
+
},
|
| 1103 |
+
{
|
| 1104 |
+
"epoch": 0.56,
|
| 1105 |
+
"learning_rate": 0.00024522618909175487,
|
| 1106 |
+
"loss": 0.8862,
|
| 1107 |
+
"step": 3240
|
| 1108 |
+
},
|
| 1109 |
+
{
|
| 1110 |
+
"epoch": 0.57,
|
| 1111 |
+
"learning_rate": 0.0002448773113152692,
|
| 1112 |
+
"loss": 0.8843,
|
| 1113 |
+
"step": 3260
|
| 1114 |
+
},
|
| 1115 |
+
{
|
| 1116 |
+
"epoch": 0.57,
|
| 1117 |
+
"learning_rate": 0.00024452843353878353,
|
| 1118 |
+
"loss": 0.8812,
|
| 1119 |
+
"step": 3280
|
| 1120 |
+
},
|
| 1121 |
+
{
|
| 1122 |
+
"epoch": 0.57,
|
| 1123 |
+
"learning_rate": 0.0002441795557622979,
|
| 1124 |
+
"loss": 0.8905,
|
| 1125 |
+
"step": 3300
|
| 1126 |
+
},
|
| 1127 |
+
{
|
| 1128 |
+
"epoch": 0.58,
|
| 1129 |
+
"learning_rate": 0.0002438306779858123,
|
| 1130 |
+
"loss": 0.8858,
|
| 1131 |
+
"step": 3320
|
| 1132 |
+
},
|
| 1133 |
+
{
|
| 1134 |
+
"epoch": 0.58,
|
| 1135 |
+
"learning_rate": 0.00024348180020932665,
|
| 1136 |
+
"loss": 0.8768,
|
| 1137 |
+
"step": 3340
|
| 1138 |
+
},
|
| 1139 |
+
{
|
| 1140 |
+
"epoch": 0.58,
|
| 1141 |
+
"learning_rate": 0.000243132922432841,
|
| 1142 |
+
"loss": 0.8765,
|
| 1143 |
+
"step": 3360
|
| 1144 |
+
},
|
| 1145 |
+
{
|
| 1146 |
+
"epoch": 0.59,
|
| 1147 |
+
"learning_rate": 0.00024278404465635537,
|
| 1148 |
+
"loss": 0.8889,
|
| 1149 |
+
"step": 3380
|
| 1150 |
+
},
|
| 1151 |
+
{
|
| 1152 |
+
"epoch": 0.59,
|
| 1153 |
+
"learning_rate": 0.00024243516687986975,
|
| 1154 |
+
"loss": 0.883,
|
| 1155 |
+
"step": 3400
|
| 1156 |
+
},
|
| 1157 |
+
{
|
| 1158 |
+
"epoch": 0.59,
|
| 1159 |
+
"eval_loss": 0.8804351091384888,
|
| 1160 |
+
"eval_runtime": 50.8292,
|
| 1161 |
+
"eval_samples_per_second": 39.347,
|
| 1162 |
+
"eval_steps_per_second": 1.653,
|
| 1163 |
+
"step": 3400
|
| 1164 |
+
},
|
| 1165 |
+
{
|
| 1166 |
+
"epoch": 0.59,
|
| 1167 |
+
"learning_rate": 0.0002420862891033841,
|
| 1168 |
+
"loss": 0.8861,
|
| 1169 |
+
"step": 3420
|
| 1170 |
+
},
|
| 1171 |
+
{
|
| 1172 |
+
"epoch": 0.6,
|
| 1173 |
+
"learning_rate": 0.00024173741132689847,
|
| 1174 |
+
"loss": 0.8889,
|
| 1175 |
+
"step": 3440
|
| 1176 |
+
},
|
| 1177 |
+
{
|
| 1178 |
+
"epoch": 0.6,
|
| 1179 |
+
"learning_rate": 0.00024138853355041282,
|
| 1180 |
+
"loss": 0.897,
|
| 1181 |
+
"step": 3460
|
| 1182 |
+
},
|
| 1183 |
+
{
|
| 1184 |
+
"epoch": 0.6,
|
| 1185 |
+
"learning_rate": 0.00024103965577392715,
|
| 1186 |
+
"loss": 0.8901,
|
| 1187 |
+
"step": 3480
|
| 1188 |
+
},
|
| 1189 |
+
{
|
| 1190 |
+
"epoch": 0.61,
|
| 1191 |
+
"learning_rate": 0.00024069077799744156,
|
| 1192 |
+
"loss": 0.8895,
|
| 1193 |
+
"step": 3500
|
| 1194 |
+
},
|
| 1195 |
+
{
|
| 1196 |
+
"epoch": 0.61,
|
| 1197 |
+
"learning_rate": 0.00024034190022095592,
|
| 1198 |
+
"loss": 0.8863,
|
| 1199 |
+
"step": 3520
|
| 1200 |
+
},
|
| 1201 |
+
{
|
| 1202 |
+
"epoch": 0.61,
|
| 1203 |
+
"learning_rate": 0.00023999302244447025,
|
| 1204 |
+
"loss": 0.8852,
|
| 1205 |
+
"step": 3540
|
| 1206 |
+
},
|
| 1207 |
+
{
|
| 1208 |
+
"epoch": 0.62,
|
| 1209 |
+
"learning_rate": 0.0002396441446679846,
|
| 1210 |
+
"loss": 0.8842,
|
| 1211 |
+
"step": 3560
|
| 1212 |
+
},
|
| 1213 |
+
{
|
| 1214 |
+
"epoch": 0.62,
|
| 1215 |
+
"learning_rate": 0.000239295266891499,
|
| 1216 |
+
"loss": 0.8843,
|
| 1217 |
+
"step": 3580
|
| 1218 |
+
},
|
| 1219 |
+
{
|
| 1220 |
+
"epoch": 0.62,
|
| 1221 |
+
"learning_rate": 0.00023894638911501335,
|
| 1222 |
+
"loss": 0.8803,
|
| 1223 |
+
"step": 3600
|
| 1224 |
+
},
|
| 1225 |
+
{
|
| 1226 |
+
"epoch": 0.62,
|
| 1227 |
+
"eval_loss": 0.8769158720970154,
|
| 1228 |
+
"eval_runtime": 49.0911,
|
| 1229 |
+
"eval_samples_per_second": 40.741,
|
| 1230 |
+
"eval_steps_per_second": 1.711,
|
| 1231 |
+
"step": 3600
|
| 1232 |
+
},
|
| 1233 |
+
{
|
| 1234 |
+
"epoch": 0.63,
|
| 1235 |
+
"learning_rate": 0.0002385975113385277,
|
| 1236 |
+
"loss": 0.8869,
|
| 1237 |
+
"step": 3620
|
| 1238 |
+
},
|
| 1239 |
+
{
|
| 1240 |
+
"epoch": 0.63,
|
| 1241 |
+
"learning_rate": 0.00023824863356204206,
|
| 1242 |
+
"loss": 0.8786,
|
| 1243 |
+
"step": 3640
|
| 1244 |
+
},
|
| 1245 |
+
{
|
| 1246 |
+
"epoch": 0.63,
|
| 1247 |
+
"learning_rate": 0.00023789975578555642,
|
| 1248 |
+
"loss": 0.8761,
|
| 1249 |
+
"step": 3660
|
| 1250 |
+
},
|
| 1251 |
+
{
|
| 1252 |
+
"epoch": 0.64,
|
| 1253 |
+
"learning_rate": 0.0002375508780090708,
|
| 1254 |
+
"loss": 0.8811,
|
| 1255 |
+
"step": 3680
|
| 1256 |
+
},
|
| 1257 |
+
{
|
| 1258 |
+
"epoch": 0.64,
|
| 1259 |
+
"learning_rate": 0.00023720200023258516,
|
| 1260 |
+
"loss": 0.8815,
|
| 1261 |
+
"step": 3700
|
| 1262 |
+
},
|
| 1263 |
+
{
|
| 1264 |
+
"epoch": 0.65,
|
| 1265 |
+
"learning_rate": 0.00023685312245609952,
|
| 1266 |
+
"loss": 0.8782,
|
| 1267 |
+
"step": 3720
|
| 1268 |
+
},
|
| 1269 |
+
{
|
| 1270 |
+
"epoch": 0.65,
|
| 1271 |
+
"learning_rate": 0.00023650424467961387,
|
| 1272 |
+
"loss": 0.8868,
|
| 1273 |
+
"step": 3740
|
| 1274 |
+
},
|
| 1275 |
+
{
|
| 1276 |
+
"epoch": 0.65,
|
| 1277 |
+
"learning_rate": 0.00023615536690312826,
|
| 1278 |
+
"loss": 0.8804,
|
| 1279 |
+
"step": 3760
|
| 1280 |
+
},
|
| 1281 |
+
{
|
| 1282 |
+
"epoch": 0.66,
|
| 1283 |
+
"learning_rate": 0.00023580648912664262,
|
| 1284 |
+
"loss": 0.8754,
|
| 1285 |
+
"step": 3780
|
| 1286 |
+
},
|
| 1287 |
+
{
|
| 1288 |
+
"epoch": 0.66,
|
| 1289 |
+
"learning_rate": 0.00023545761135015697,
|
| 1290 |
+
"loss": 0.8826,
|
| 1291 |
+
"step": 3800
|
| 1292 |
+
},
|
| 1293 |
+
{
|
| 1294 |
+
"epoch": 0.66,
|
| 1295 |
+
"eval_loss": 0.8761597871780396,
|
| 1296 |
+
"eval_runtime": 49.3308,
|
| 1297 |
+
"eval_samples_per_second": 40.543,
|
| 1298 |
+
"eval_steps_per_second": 1.703,
|
| 1299 |
+
"step": 3800
|
| 1300 |
+
},
|
| 1301 |
+
{
|
| 1302 |
+
"epoch": 0.66,
|
| 1303 |
+
"learning_rate": 0.00023510873357367133,
|
| 1304 |
+
"loss": 0.8835,
|
| 1305 |
+
"step": 3820
|
| 1306 |
+
},
|
| 1307 |
+
{
|
| 1308 |
+
"epoch": 0.67,
|
| 1309 |
+
"learning_rate": 0.00023475985579718571,
|
| 1310 |
+
"loss": 0.8655,
|
| 1311 |
+
"step": 3840
|
| 1312 |
+
},
|
| 1313 |
+
{
|
| 1314 |
+
"epoch": 0.67,
|
| 1315 |
+
"learning_rate": 0.00023441097802070007,
|
| 1316 |
+
"loss": 0.8839,
|
| 1317 |
+
"step": 3860
|
| 1318 |
+
},
|
| 1319 |
+
{
|
| 1320 |
+
"epoch": 0.67,
|
| 1321 |
+
"learning_rate": 0.00023406210024421443,
|
| 1322 |
+
"loss": 0.8814,
|
| 1323 |
+
"step": 3880
|
| 1324 |
+
},
|
| 1325 |
+
{
|
| 1326 |
+
"epoch": 0.68,
|
| 1327 |
+
"learning_rate": 0.00023371322246772879,
|
| 1328 |
+
"loss": 0.8839,
|
| 1329 |
+
"step": 3900
|
| 1330 |
+
},
|
| 1331 |
+
{
|
| 1332 |
+
"epoch": 0.68,
|
| 1333 |
+
"learning_rate": 0.00023336434469124314,
|
| 1334 |
+
"loss": 0.8794,
|
| 1335 |
+
"step": 3920
|
| 1336 |
+
},
|
| 1337 |
+
{
|
| 1338 |
+
"epoch": 0.68,
|
| 1339 |
+
"learning_rate": 0.00023301546691475753,
|
| 1340 |
+
"loss": 0.8755,
|
| 1341 |
+
"step": 3940
|
| 1342 |
+
},
|
| 1343 |
+
{
|
| 1344 |
+
"epoch": 0.69,
|
| 1345 |
+
"learning_rate": 0.00023266658913827188,
|
| 1346 |
+
"loss": 0.8771,
|
| 1347 |
+
"step": 3960
|
| 1348 |
+
},
|
| 1349 |
+
{
|
| 1350 |
+
"epoch": 0.69,
|
| 1351 |
+
"learning_rate": 0.00023231771136178624,
|
| 1352 |
+
"loss": 0.8731,
|
| 1353 |
+
"step": 3980
|
| 1354 |
+
},
|
| 1355 |
+
{
|
| 1356 |
+
"epoch": 0.69,
|
| 1357 |
+
"learning_rate": 0.0002319688335853006,
|
| 1358 |
+
"loss": 0.8764,
|
| 1359 |
+
"step": 4000
|
| 1360 |
+
},
|
| 1361 |
+
{
|
| 1362 |
+
"epoch": 0.69,
|
| 1363 |
+
"eval_loss": 0.8736156225204468,
|
| 1364 |
+
"eval_runtime": 50.6647,
|
| 1365 |
+
"eval_samples_per_second": 39.475,
|
| 1366 |
+
"eval_steps_per_second": 1.658,
|
| 1367 |
+
"step": 4000
|
| 1368 |
+
},
|
| 1369 |
+
{
|
| 1370 |
+
"epoch": 0.7,
|
| 1371 |
+
"learning_rate": 0.00023161995580881498,
|
| 1372 |
+
"loss": 0.8821,
|
| 1373 |
+
"step": 4020
|
| 1374 |
+
},
|
| 1375 |
+
{
|
| 1376 |
+
"epoch": 0.7,
|
| 1377 |
+
"learning_rate": 0.00023127107803232934,
|
| 1378 |
+
"loss": 0.8791,
|
| 1379 |
+
"step": 4040
|
| 1380 |
+
},
|
| 1381 |
+
{
|
| 1382 |
+
"epoch": 0.7,
|
| 1383 |
+
"learning_rate": 0.00023092220025584367,
|
| 1384 |
+
"loss": 0.8841,
|
| 1385 |
+
"step": 4060
|
| 1386 |
+
},
|
| 1387 |
+
{
|
| 1388 |
+
"epoch": 0.71,
|
| 1389 |
+
"learning_rate": 0.00023057332247935803,
|
| 1390 |
+
"loss": 0.8718,
|
| 1391 |
+
"step": 4080
|
| 1392 |
+
},
|
| 1393 |
+
{
|
| 1394 |
+
"epoch": 0.71,
|
| 1395 |
+
"learning_rate": 0.00023022444470287238,
|
| 1396 |
+
"loss": 0.8731,
|
| 1397 |
+
"step": 4100
|
| 1398 |
+
},
|
| 1399 |
+
{
|
| 1400 |
+
"epoch": 0.71,
|
| 1401 |
+
"learning_rate": 0.00022987556692638677,
|
| 1402 |
+
"loss": 0.8805,
|
| 1403 |
+
"step": 4120
|
| 1404 |
+
},
|
| 1405 |
+
{
|
| 1406 |
+
"epoch": 0.72,
|
| 1407 |
+
"learning_rate": 0.00022952668914990112,
|
| 1408 |
+
"loss": 0.8821,
|
| 1409 |
+
"step": 4140
|
| 1410 |
+
},
|
| 1411 |
+
{
|
| 1412 |
+
"epoch": 0.72,
|
| 1413 |
+
"learning_rate": 0.00022917781137341548,
|
| 1414 |
+
"loss": 0.8669,
|
| 1415 |
+
"step": 4160
|
| 1416 |
+
},
|
| 1417 |
+
{
|
| 1418 |
+
"epoch": 0.72,
|
| 1419 |
+
"learning_rate": 0.00022882893359692984,
|
| 1420 |
+
"loss": 0.8701,
|
| 1421 |
+
"step": 4180
|
| 1422 |
+
},
|
| 1423 |
+
{
|
| 1424 |
+
"epoch": 0.73,
|
| 1425 |
+
"learning_rate": 0.00022848005582044422,
|
| 1426 |
+
"loss": 0.862,
|
| 1427 |
+
"step": 4200
|
| 1428 |
+
},
|
| 1429 |
+
{
|
| 1430 |
+
"epoch": 0.73,
|
| 1431 |
+
"eval_loss": 0.8710012435913086,
|
| 1432 |
+
"eval_runtime": 49.64,
|
| 1433 |
+
"eval_samples_per_second": 40.29,
|
| 1434 |
+
"eval_steps_per_second": 1.692,
|
| 1435 |
+
"step": 4200
|
| 1436 |
+
},
|
| 1437 |
+
{
|
| 1438 |
+
"epoch": 0.73,
|
| 1439 |
+
"learning_rate": 0.00022813117804395858,
|
| 1440 |
+
"loss": 0.8716,
|
| 1441 |
+
"step": 4220
|
| 1442 |
+
},
|
| 1443 |
+
{
|
| 1444 |
+
"epoch": 0.74,
|
| 1445 |
+
"learning_rate": 0.00022778230026747294,
|
| 1446 |
+
"loss": 0.8708,
|
| 1447 |
+
"step": 4240
|
| 1448 |
+
},
|
| 1449 |
+
{
|
| 1450 |
+
"epoch": 0.74,
|
| 1451 |
+
"learning_rate": 0.0002274334224909873,
|
| 1452 |
+
"loss": 0.8668,
|
| 1453 |
+
"step": 4260
|
| 1454 |
+
},
|
| 1455 |
+
{
|
| 1456 |
+
"epoch": 0.74,
|
| 1457 |
+
"learning_rate": 0.00022708454471450168,
|
| 1458 |
+
"loss": 0.8691,
|
| 1459 |
+
"step": 4280
|
| 1460 |
+
},
|
| 1461 |
+
{
|
| 1462 |
+
"epoch": 0.75,
|
| 1463 |
+
"learning_rate": 0.00022673566693801603,
|
| 1464 |
+
"loss": 0.874,
|
| 1465 |
+
"step": 4300
|
| 1466 |
+
},
|
| 1467 |
+
{
|
| 1468 |
+
"epoch": 0.75,
|
| 1469 |
+
"learning_rate": 0.0002263867891615304,
|
| 1470 |
+
"loss": 0.8688,
|
| 1471 |
+
"step": 4320
|
| 1472 |
+
},
|
| 1473 |
+
{
|
| 1474 |
+
"epoch": 0.75,
|
| 1475 |
+
"learning_rate": 0.00022603791138504475,
|
| 1476 |
+
"loss": 0.8714,
|
| 1477 |
+
"step": 4340
|
| 1478 |
+
},
|
| 1479 |
+
{
|
| 1480 |
+
"epoch": 0.76,
|
| 1481 |
+
"learning_rate": 0.0002256890336085591,
|
| 1482 |
+
"loss": 0.8694,
|
| 1483 |
+
"step": 4360
|
| 1484 |
+
},
|
| 1485 |
+
{
|
| 1486 |
+
"epoch": 0.76,
|
| 1487 |
+
"learning_rate": 0.0002253401558320735,
|
| 1488 |
+
"loss": 0.8733,
|
| 1489 |
+
"step": 4380
|
| 1490 |
+
},
|
| 1491 |
+
{
|
| 1492 |
+
"epoch": 0.76,
|
| 1493 |
+
"learning_rate": 0.00022499127805558785,
|
| 1494 |
+
"loss": 0.8798,
|
| 1495 |
+
"step": 4400
|
| 1496 |
+
},
|
| 1497 |
+
{
|
| 1498 |
+
"epoch": 0.76,
|
| 1499 |
+
"eval_loss": 0.869438886642456,
|
| 1500 |
+
"eval_runtime": 50.0009,
|
| 1501 |
+
"eval_samples_per_second": 39.999,
|
| 1502 |
+
"eval_steps_per_second": 1.68,
|
| 1503 |
+
"step": 4400
|
| 1504 |
+
},
|
| 1505 |
+
{
|
| 1506 |
+
"epoch": 0.77,
|
| 1507 |
+
"learning_rate": 0.0002246424002791022,
|
| 1508 |
+
"loss": 0.8599,
|
| 1509 |
+
"step": 4420
|
| 1510 |
+
},
|
| 1511 |
+
{
|
| 1512 |
+
"epoch": 0.77,
|
| 1513 |
+
"learning_rate": 0.00022429352250261656,
|
| 1514 |
+
"loss": 0.8733,
|
| 1515 |
+
"step": 4440
|
| 1516 |
+
},
|
| 1517 |
+
{
|
| 1518 |
+
"epoch": 0.77,
|
| 1519 |
+
"learning_rate": 0.00022394464472613094,
|
| 1520 |
+
"loss": 0.8748,
|
| 1521 |
+
"step": 4460
|
| 1522 |
+
},
|
| 1523 |
+
{
|
| 1524 |
+
"epoch": 0.78,
|
| 1525 |
+
"learning_rate": 0.0002235957669496453,
|
| 1526 |
+
"loss": 0.8764,
|
| 1527 |
+
"step": 4480
|
| 1528 |
+
},
|
| 1529 |
+
{
|
| 1530 |
+
"epoch": 0.78,
|
| 1531 |
+
"learning_rate": 0.00022324688917315966,
|
| 1532 |
+
"loss": 0.865,
|
| 1533 |
+
"step": 4500
|
| 1534 |
+
},
|
| 1535 |
+
{
|
| 1536 |
+
"epoch": 0.78,
|
| 1537 |
+
"learning_rate": 0.00022289801139667402,
|
| 1538 |
+
"loss": 0.8663,
|
| 1539 |
+
"step": 4520
|
| 1540 |
+
},
|
| 1541 |
+
{
|
| 1542 |
+
"epoch": 0.79,
|
| 1543 |
+
"learning_rate": 0.00022254913362018835,
|
| 1544 |
+
"loss": 0.8738,
|
| 1545 |
+
"step": 4540
|
| 1546 |
+
},
|
| 1547 |
+
{
|
| 1548 |
+
"epoch": 0.79,
|
| 1549 |
+
"learning_rate": 0.00022220025584370276,
|
| 1550 |
+
"loss": 0.8611,
|
| 1551 |
+
"step": 4560
|
| 1552 |
+
},
|
| 1553 |
+
{
|
| 1554 |
+
"epoch": 0.79,
|
| 1555 |
+
"learning_rate": 0.0002218513780672171,
|
| 1556 |
+
"loss": 0.8683,
|
| 1557 |
+
"step": 4580
|
| 1558 |
+
},
|
| 1559 |
+
{
|
| 1560 |
+
"epoch": 0.8,
|
| 1561 |
+
"learning_rate": 0.00022150250029073144,
|
| 1562 |
+
"loss": 0.8725,
|
| 1563 |
+
"step": 4600
|
| 1564 |
+
},
|
| 1565 |
+
{
|
| 1566 |
+
"epoch": 0.8,
|
| 1567 |
+
"eval_loss": 0.8671180605888367,
|
| 1568 |
+
"eval_runtime": 50.2687,
|
| 1569 |
+
"eval_samples_per_second": 39.786,
|
| 1570 |
+
"eval_steps_per_second": 1.671,
|
| 1571 |
+
"step": 4600
|
| 1572 |
+
},
|
| 1573 |
+
{
|
| 1574 |
+
"epoch": 0.8,
|
| 1575 |
+
"learning_rate": 0.0002211536225142458,
|
| 1576 |
+
"loss": 0.8686,
|
| 1577 |
+
"step": 4620
|
| 1578 |
+
},
|
| 1579 |
+
{
|
| 1580 |
+
"epoch": 0.8,
|
| 1581 |
+
"learning_rate": 0.00022080474473776019,
|
| 1582 |
+
"loss": 0.8674,
|
| 1583 |
+
"step": 4640
|
| 1584 |
+
},
|
| 1585 |
+
{
|
| 1586 |
+
"epoch": 0.81,
|
| 1587 |
+
"learning_rate": 0.00022045586696127454,
|
| 1588 |
+
"loss": 0.8657,
|
| 1589 |
+
"step": 4660
|
| 1590 |
+
},
|
| 1591 |
+
{
|
| 1592 |
+
"epoch": 0.81,
|
| 1593 |
+
"learning_rate": 0.0002201069891847889,
|
| 1594 |
+
"loss": 0.8607,
|
| 1595 |
+
"step": 4680
|
| 1596 |
+
},
|
| 1597 |
+
{
|
| 1598 |
+
"epoch": 0.82,
|
| 1599 |
+
"learning_rate": 0.00021975811140830326,
|
| 1600 |
+
"loss": 0.8672,
|
| 1601 |
+
"step": 4700
|
| 1602 |
+
},
|
| 1603 |
+
{
|
| 1604 |
+
"epoch": 0.82,
|
| 1605 |
+
"learning_rate": 0.00021940923363181764,
|
| 1606 |
+
"loss": 0.8603,
|
| 1607 |
+
"step": 4720
|
| 1608 |
+
},
|
| 1609 |
+
{
|
| 1610 |
+
"epoch": 0.82,
|
| 1611 |
+
"learning_rate": 0.000219060355855332,
|
| 1612 |
+
"loss": 0.8672,
|
| 1613 |
+
"step": 4740
|
| 1614 |
+
},
|
| 1615 |
+
{
|
| 1616 |
+
"epoch": 0.83,
|
| 1617 |
+
"learning_rate": 0.00021871147807884635,
|
| 1618 |
+
"loss": 0.8659,
|
| 1619 |
+
"step": 4760
|
| 1620 |
+
},
|
| 1621 |
+
{
|
| 1622 |
+
"epoch": 0.83,
|
| 1623 |
+
"learning_rate": 0.0002183626003023607,
|
| 1624 |
+
"loss": 0.8638,
|
| 1625 |
+
"step": 4780
|
| 1626 |
+
},
|
| 1627 |
+
{
|
| 1628 |
+
"epoch": 0.83,
|
| 1629 |
+
"learning_rate": 0.00021801372252587507,
|
| 1630 |
+
"loss": 0.8776,
|
| 1631 |
+
"step": 4800
|
| 1632 |
+
},
|
| 1633 |
+
{
|
| 1634 |
+
"epoch": 0.83,
|
| 1635 |
+
"eval_loss": 0.8659985065460205,
|
| 1636 |
+
"eval_runtime": 49.0999,
|
| 1637 |
+
"eval_samples_per_second": 40.733,
|
| 1638 |
+
"eval_steps_per_second": 1.711,
|
| 1639 |
+
"step": 4800
|
| 1640 |
+
},
|
| 1641 |
+
{
|
| 1642 |
+
"epoch": 0.84,
|
| 1643 |
+
"learning_rate": 0.00021766484474938945,
|
| 1644 |
+
"loss": 0.8714,
|
| 1645 |
+
"step": 4820
|
| 1646 |
+
},
|
| 1647 |
+
{
|
| 1648 |
+
"epoch": 0.84,
|
| 1649 |
+
"learning_rate": 0.0002173159669729038,
|
| 1650 |
+
"loss": 0.8786,
|
| 1651 |
+
"step": 4840
|
| 1652 |
+
},
|
| 1653 |
+
{
|
| 1654 |
+
"epoch": 0.84,
|
| 1655 |
+
"learning_rate": 0.00021696708919641817,
|
| 1656 |
+
"loss": 0.8674,
|
| 1657 |
+
"step": 4860
|
| 1658 |
+
},
|
| 1659 |
+
{
|
| 1660 |
+
"epoch": 0.85,
|
| 1661 |
+
"learning_rate": 0.00021661821141993252,
|
| 1662 |
+
"loss": 0.8705,
|
| 1663 |
+
"step": 4880
|
| 1664 |
+
},
|
| 1665 |
+
{
|
| 1666 |
+
"epoch": 0.85,
|
| 1667 |
+
"learning_rate": 0.0002162693336434469,
|
| 1668 |
+
"loss": 0.8716,
|
| 1669 |
+
"step": 4900
|
| 1670 |
+
},
|
| 1671 |
+
{
|
| 1672 |
+
"epoch": 0.85,
|
| 1673 |
+
"learning_rate": 0.00021592045586696126,
|
| 1674 |
+
"loss": 0.8573,
|
| 1675 |
+
"step": 4920
|
| 1676 |
+
},
|
| 1677 |
+
{
|
| 1678 |
+
"epoch": 0.86,
|
| 1679 |
+
"learning_rate": 0.00021557157809047562,
|
| 1680 |
+
"loss": 0.8596,
|
| 1681 |
+
"step": 4940
|
| 1682 |
+
},
|
| 1683 |
+
{
|
| 1684 |
+
"epoch": 0.86,
|
| 1685 |
+
"learning_rate": 0.00021522270031398998,
|
| 1686 |
+
"loss": 0.8605,
|
| 1687 |
+
"step": 4960
|
| 1688 |
+
},
|
| 1689 |
+
{
|
| 1690 |
+
"epoch": 0.86,
|
| 1691 |
+
"learning_rate": 0.00021487382253750436,
|
| 1692 |
+
"loss": 0.8612,
|
| 1693 |
+
"step": 4980
|
| 1694 |
+
},
|
| 1695 |
+
{
|
| 1696 |
+
"epoch": 0.87,
|
| 1697 |
+
"learning_rate": 0.00021452494476101872,
|
| 1698 |
+
"loss": 0.8686,
|
| 1699 |
+
"step": 5000
|
| 1700 |
+
},
|
| 1701 |
+
{
|
| 1702 |
+
"epoch": 0.87,
|
| 1703 |
+
"eval_loss": 0.8649623394012451,
|
| 1704 |
+
"eval_runtime": 49.5648,
|
| 1705 |
+
"eval_samples_per_second": 40.351,
|
| 1706 |
+
"eval_steps_per_second": 1.695,
|
| 1707 |
+
"step": 5000
|
| 1708 |
+
},
|
| 1709 |
+
{
|
| 1710 |
+
"epoch": 0.87,
|
| 1711 |
+
"learning_rate": 0.00021417606698453308,
|
| 1712 |
+
"loss": 0.869,
|
| 1713 |
+
"step": 5020
|
| 1714 |
+
},
|
| 1715 |
+
{
|
| 1716 |
+
"epoch": 0.87,
|
| 1717 |
+
"learning_rate": 0.00021382718920804743,
|
| 1718 |
+
"loss": 0.8712,
|
| 1719 |
+
"step": 5040
|
| 1720 |
+
},
|
| 1721 |
+
{
|
| 1722 |
+
"epoch": 0.88,
|
| 1723 |
+
"learning_rate": 0.00021347831143156176,
|
| 1724 |
+
"loss": 0.8633,
|
| 1725 |
+
"step": 5060
|
| 1726 |
+
},
|
| 1727 |
+
{
|
| 1728 |
+
"epoch": 0.88,
|
| 1729 |
+
"learning_rate": 0.00021312943365507618,
|
| 1730 |
+
"loss": 0.8611,
|
| 1731 |
+
"step": 5080
|
| 1732 |
+
},
|
| 1733 |
+
{
|
| 1734 |
+
"epoch": 0.88,
|
| 1735 |
+
"learning_rate": 0.00021278055587859053,
|
| 1736 |
+
"loss": 0.8714,
|
| 1737 |
+
"step": 5100
|
| 1738 |
+
},
|
| 1739 |
+
{
|
| 1740 |
+
"epoch": 0.89,
|
| 1741 |
+
"learning_rate": 0.00021243167810210486,
|
| 1742 |
+
"loss": 0.8684,
|
| 1743 |
+
"step": 5120
|
| 1744 |
+
},
|
| 1745 |
+
{
|
| 1746 |
+
"epoch": 0.89,
|
| 1747 |
+
"learning_rate": 0.00021208280032561922,
|
| 1748 |
+
"loss": 0.8619,
|
| 1749 |
+
"step": 5140
|
| 1750 |
+
},
|
| 1751 |
+
{
|
| 1752 |
+
"epoch": 0.89,
|
| 1753 |
+
"learning_rate": 0.0002117339225491336,
|
| 1754 |
+
"loss": 0.8589,
|
| 1755 |
+
"step": 5160
|
| 1756 |
+
},
|
| 1757 |
+
{
|
| 1758 |
+
"epoch": 0.9,
|
| 1759 |
+
"learning_rate": 0.00021138504477264796,
|
| 1760 |
+
"loss": 0.8633,
|
| 1761 |
+
"step": 5180
|
| 1762 |
+
},
|
| 1763 |
+
{
|
| 1764 |
+
"epoch": 0.9,
|
| 1765 |
+
"learning_rate": 0.00021103616699616232,
|
| 1766 |
+
"loss": 0.8642,
|
| 1767 |
+
"step": 5200
|
| 1768 |
+
},
|
| 1769 |
+
{
|
| 1770 |
+
"epoch": 0.9,
|
| 1771 |
+
"eval_loss": 0.8629763126373291,
|
| 1772 |
+
"eval_runtime": 49.7031,
|
| 1773 |
+
"eval_samples_per_second": 40.239,
|
| 1774 |
+
"eval_steps_per_second": 1.69,
|
| 1775 |
+
"step": 5200
|
| 1776 |
+
},
|
| 1777 |
+
{
|
| 1778 |
+
"epoch": 0.91,
|
| 1779 |
+
"learning_rate": 0.00021068728921967667,
|
| 1780 |
+
"loss": 0.8627,
|
| 1781 |
+
"step": 5220
|
| 1782 |
+
},
|
| 1783 |
+
{
|
| 1784 |
+
"epoch": 0.91,
|
| 1785 |
+
"learning_rate": 0.00021033841144319103,
|
| 1786 |
+
"loss": 0.8631,
|
| 1787 |
+
"step": 5240
|
| 1788 |
+
},
|
| 1789 |
+
{
|
| 1790 |
+
"epoch": 0.91,
|
| 1791 |
+
"learning_rate": 0.00020998953366670542,
|
| 1792 |
+
"loss": 0.8685,
|
| 1793 |
+
"step": 5260
|
| 1794 |
+
},
|
| 1795 |
+
{
|
| 1796 |
+
"epoch": 0.92,
|
| 1797 |
+
"learning_rate": 0.00020964065589021977,
|
| 1798 |
+
"loss": 0.8663,
|
| 1799 |
+
"step": 5280
|
| 1800 |
+
},
|
| 1801 |
+
{
|
| 1802 |
+
"epoch": 0.92,
|
| 1803 |
+
"learning_rate": 0.00020929177811373413,
|
| 1804 |
+
"loss": 0.8676,
|
| 1805 |
+
"step": 5300
|
| 1806 |
+
},
|
| 1807 |
+
{
|
| 1808 |
+
"epoch": 0.92,
|
| 1809 |
+
"learning_rate": 0.0002089429003372485,
|
| 1810 |
+
"loss": 0.8655,
|
| 1811 |
+
"step": 5320
|
| 1812 |
+
},
|
| 1813 |
+
{
|
| 1814 |
+
"epoch": 0.93,
|
| 1815 |
+
"learning_rate": 0.00020859402256076287,
|
| 1816 |
+
"loss": 0.8586,
|
| 1817 |
+
"step": 5340
|
| 1818 |
+
},
|
| 1819 |
+
{
|
| 1820 |
+
"epoch": 0.93,
|
| 1821 |
+
"learning_rate": 0.00020824514478427723,
|
| 1822 |
+
"loss": 0.8663,
|
| 1823 |
+
"step": 5360
|
| 1824 |
+
},
|
| 1825 |
+
{
|
| 1826 |
+
"epoch": 0.93,
|
| 1827 |
+
"learning_rate": 0.00020789626700779159,
|
| 1828 |
+
"loss": 0.855,
|
| 1829 |
+
"step": 5380
|
| 1830 |
+
},
|
| 1831 |
+
{
|
| 1832 |
+
"epoch": 0.94,
|
| 1833 |
+
"learning_rate": 0.00020754738923130594,
|
| 1834 |
+
"loss": 0.8652,
|
| 1835 |
+
"step": 5400
|
| 1836 |
+
},
|
| 1837 |
+
{
|
| 1838 |
+
"epoch": 0.94,
|
| 1839 |
+
"eval_loss": 0.8607897758483887,
|
| 1840 |
+
"eval_runtime": 51.0242,
|
| 1841 |
+
"eval_samples_per_second": 39.197,
|
| 1842 |
+
"eval_steps_per_second": 1.646,
|
| 1843 |
+
"step": 5400
|
| 1844 |
+
},
|
| 1845 |
+
{
|
| 1846 |
+
"epoch": 0.94,
|
| 1847 |
+
"learning_rate": 0.00020719851145482033,
|
| 1848 |
+
"loss": 0.8681,
|
| 1849 |
+
"step": 5420
|
| 1850 |
+
},
|
| 1851 |
+
{
|
| 1852 |
+
"epoch": 0.94,
|
| 1853 |
+
"learning_rate": 0.00020684963367833468,
|
| 1854 |
+
"loss": 0.8593,
|
| 1855 |
+
"step": 5440
|
| 1856 |
+
},
|
| 1857 |
+
{
|
| 1858 |
+
"epoch": 0.95,
|
| 1859 |
+
"learning_rate": 0.00020650075590184904,
|
| 1860 |
+
"loss": 0.8738,
|
| 1861 |
+
"step": 5460
|
| 1862 |
+
},
|
| 1863 |
+
{
|
| 1864 |
+
"epoch": 0.95,
|
| 1865 |
+
"learning_rate": 0.0002061518781253634,
|
| 1866 |
+
"loss": 0.8658,
|
| 1867 |
+
"step": 5480
|
| 1868 |
+
},
|
| 1869 |
+
{
|
| 1870 |
+
"epoch": 0.95,
|
| 1871 |
+
"learning_rate": 0.00020580300034887775,
|
| 1872 |
+
"loss": 0.8593,
|
| 1873 |
+
"step": 5500
|
| 1874 |
+
},
|
| 1875 |
+
{
|
| 1876 |
+
"epoch": 0.96,
|
| 1877 |
+
"learning_rate": 0.00020545412257239214,
|
| 1878 |
+
"loss": 0.8563,
|
| 1879 |
+
"step": 5520
|
| 1880 |
+
},
|
| 1881 |
+
{
|
| 1882 |
+
"epoch": 0.96,
|
| 1883 |
+
"learning_rate": 0.0002051052447959065,
|
| 1884 |
+
"loss": 0.8613,
|
| 1885 |
+
"step": 5540
|
| 1886 |
+
},
|
| 1887 |
+
{
|
| 1888 |
+
"epoch": 0.96,
|
| 1889 |
+
"learning_rate": 0.00020475636701942085,
|
| 1890 |
+
"loss": 0.8579,
|
| 1891 |
+
"step": 5560
|
| 1892 |
+
},
|
| 1893 |
+
{
|
| 1894 |
+
"epoch": 0.97,
|
| 1895 |
+
"learning_rate": 0.0002044074892429352,
|
| 1896 |
+
"loss": 0.8568,
|
| 1897 |
+
"step": 5580
|
| 1898 |
+
},
|
| 1899 |
+
{
|
| 1900 |
+
"epoch": 0.97,
|
| 1901 |
+
"learning_rate": 0.0002040586114664496,
|
| 1902 |
+
"loss": 0.8549,
|
| 1903 |
+
"step": 5600
|
| 1904 |
+
},
|
| 1905 |
+
{
|
| 1906 |
+
"epoch": 0.97,
|
| 1907 |
+
"eval_loss": 0.8596189022064209,
|
| 1908 |
+
"eval_runtime": 50.2751,
|
| 1909 |
+
"eval_samples_per_second": 39.781,
|
| 1910 |
+
"eval_steps_per_second": 1.671,
|
| 1911 |
+
"step": 5600
|
| 1912 |
+
},
|
| 1913 |
+
{
|
| 1914 |
+
"epoch": 0.97,
|
| 1915 |
+
"learning_rate": 0.00020370973368996395,
|
| 1916 |
+
"loss": 0.8571,
|
| 1917 |
+
"step": 5620
|
| 1918 |
+
},
|
| 1919 |
+
{
|
| 1920 |
+
"epoch": 0.98,
|
| 1921 |
+
"learning_rate": 0.00020336085591347828,
|
| 1922 |
+
"loss": 0.8639,
|
| 1923 |
+
"step": 5640
|
| 1924 |
+
},
|
| 1925 |
+
{
|
| 1926 |
+
"epoch": 0.98,
|
| 1927 |
+
"learning_rate": 0.00020301197813699264,
|
| 1928 |
+
"loss": 0.8569,
|
| 1929 |
+
"step": 5660
|
| 1930 |
+
},
|
| 1931 |
+
{
|
| 1932 |
+
"epoch": 0.98,
|
| 1933 |
+
"learning_rate": 0.000202663100360507,
|
| 1934 |
+
"loss": 0.8611,
|
| 1935 |
+
"step": 5680
|
| 1936 |
+
},
|
| 1937 |
+
{
|
| 1938 |
+
"epoch": 0.99,
|
| 1939 |
+
"learning_rate": 0.00020231422258402138,
|
| 1940 |
+
"loss": 0.8603,
|
| 1941 |
+
"step": 5700
|
| 1942 |
+
},
|
| 1943 |
+
{
|
| 1944 |
+
"epoch": 0.99,
|
| 1945 |
+
"learning_rate": 0.00020196534480753574,
|
| 1946 |
+
"loss": 0.8662,
|
| 1947 |
+
"step": 5720
|
| 1948 |
+
},
|
| 1949 |
+
{
|
| 1950 |
+
"epoch": 1.0,
|
| 1951 |
+
"learning_rate": 0.0002016164670310501,
|
| 1952 |
+
"loss": 0.8684,
|
| 1953 |
+
"step": 5740
|
| 1954 |
+
},
|
| 1955 |
+
{
|
| 1956 |
+
"epoch": 1.0,
|
| 1957 |
+
"learning_rate": 0.00020126758925456445,
|
| 1958 |
+
"loss": 0.8732,
|
| 1959 |
+
"step": 5760
|
| 1960 |
+
},
|
| 1961 |
+
{
|
| 1962 |
+
"epoch": 1.0,
|
| 1963 |
+
"learning_rate": 0.00020091871147807883,
|
| 1964 |
+
"loss": 0.8532,
|
| 1965 |
+
"step": 5780
|
| 1966 |
+
},
|
| 1967 |
+
{
|
| 1968 |
+
"epoch": 1.01,
|
| 1969 |
+
"learning_rate": 0.0002005698337015932,
|
| 1970 |
+
"loss": 0.8673,
|
| 1971 |
+
"step": 5800
|
| 1972 |
+
},
|
| 1973 |
+
{
|
| 1974 |
+
"epoch": 1.01,
|
| 1975 |
+
"eval_loss": 0.8592745065689087,
|
| 1976 |
+
"eval_runtime": 49.5912,
|
| 1977 |
+
"eval_samples_per_second": 40.33,
|
| 1978 |
+
"eval_steps_per_second": 1.694,
|
| 1979 |
+
"step": 5800
|
| 1980 |
+
}
|
| 1981 |
+
],
|
| 1982 |
+
"max_steps": 17298,
|
| 1983 |
+
"num_train_epochs": 3,
|
| 1984 |
+
"total_flos": 7.068073796791435e+18,
|
| 1985 |
+
"trial_name": null,
|
| 1986 |
+
"trial_params": null
|
| 1987 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1bfb606532e59dc7d83faf32b7a06ee5edd60d807d4b6f88722f9ec0f6738125
|
| 3 |
+
size 3579
|