Model save

README.md

@@ -38,10 +38,11 @@ The following hyperparameters were used during training:
 - gradient_accumulation_steps: 4
 - total_train_batch_size: 4
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
-- lr_scheduler_type: constant
+- lr_scheduler_type: cosine
 - lr_scheduler_warmup_ratio: 0.05
 - lr_scheduler_warmup_steps: 2
 - num_epochs: 2.0
+- mixed_precision_training: Native AMP
 
 ### Training results
 
@@ -49,7 +50,7 @@ The following hyperparameters were used during training:
 
 ### Framework versions
 
-- Transformers 4.34.1
+- Transformers 4.35.0
 - Pytorch 2.1.0+cu118
 - Datasets 2.14.6
 - Tokenizers 0.14.1

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e0eaf587bfb84298ae56f6bbbdb9cfdb68bbb42278a32e756ae85a6f35268c91
+oid sha256:b57a7c58e027a7a7989ddc8afe27536a432481f80618a3e6943ca083c3f3de73
 size 170142632

runs/Nov07_04-15-54_d180f3562c9b/events.out.tfevents.1699330555.d180f3562c9b.1083.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bca74f6263e9da492cbe4a4acebd478cde0241969f0dbda9a3a55c12b86a5d0d
-size 12499
+oid sha256:68a4440da46f233deb839fd69ecb52007d42abacd15fcd69cf84047d23880a4e
+size 13481