Model save

README.md

@@ -34,15 +34,15 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 0.0002
-- train_batch_size: 8
+- train_batch_size: 4
 - eval_batch_size: 8
 - seed: 42
-- gradient_accumulation_steps: 2
+- gradient_accumulation_steps: 4
 - total_train_batch_size: 16
 - optimizer: Use adamw_bnb_8bit with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
 - lr_scheduler_type: linear
 - lr_scheduler_warmup_steps: 2
-- training_steps: 2000
+- training_steps: 4000
 - mixed_precision_training: Native AMP
 
 ### Framework versions

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f2793bb402fe220b23d6f5f7ebb1f4b9121030207af3642cfd6287720c582fa5
+oid sha256:7a7174843e14fc6500b3526a1c88f010324325a4735fdd11b206939924783dea
 size 3695848

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:33a26dc0b6e7d7db1833458749e5d0d3e3dc01522cc96e6081e81c1528dbf76b
-size 5304
+oid sha256:a88d247b48d44ff0e8eb768669ae078ed021b70ab539070a8e000d862c123c10
+size 5240