Model save
Browse files- README.md +2 -2
- training_args.bin +1 -1
README.md
CHANGED
|
@@ -40,8 +40,8 @@ The following hyperparameters were used during training:
|
|
| 40 |
- gradient_accumulation_steps: 4
|
| 41 |
- total_train_batch_size: 128
|
| 42 |
- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
|
| 43 |
-
- lr_scheduler_type:
|
| 44 |
-
-
|
| 45 |
- num_epochs: 12
|
| 46 |
- mixed_precision_training: Native AMP
|
| 47 |
|
|
|
|
| 40 |
- gradient_accumulation_steps: 4
|
| 41 |
- total_train_batch_size: 128
|
| 42 |
- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
|
| 43 |
+
- lr_scheduler_type: cosine
|
| 44 |
+
- lr_scheduler_warmup_ratio: 0.1
|
| 45 |
- num_epochs: 12
|
| 46 |
- mixed_precision_training: Native AMP
|
| 47 |
|
training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 5969
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:eb13fb99ec22dc493bf012b618c2176ed5043913514dc869819071db8ff6a26b
|
| 3 |
size 5969
|