End of training

README.md

@@ -34,15 +34,15 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 0.0001
-- train_batch_size: 2
+- train_batch_size: 8
 - eval_batch_size: 8
 - seed: 42
 - gradient_accumulation_steps: 8
-- total_train_batch_size: 16
+- total_train_batch_size: 64
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
 - lr_scheduler_warmup_steps: 50
-- training_steps: 500
+- training_steps: 100
 - mixed_precision_training: Native AMP
 
 ### Framework versions

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7396579222dc514d013dcfacb2901b000f19337f5640adec73debf4b402a76c6
+oid sha256:53826effb0f55805ec20e27bf5ee6a7fe7f1d5c4e91f3e2fa6d3f244659cd0f5
 size 93378688

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f2da9714b2bd94f9e2787f0fe2bf87895d1631d8dea6774d13680a8ac8bae42b
+oid sha256:bfcaea7aa3c3574c0f2d97ad4bb3e1423d6e31eac3999c7aaf0dbe79ef487966
 size 5304