Model save

README.md

@@ -37,16 +37,16 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 0.0002
-- train_batch_size: 1
+- learning_rate: 1e-05
+- train_batch_size: 2
 - eval_batch_size: 8
 - seed: 42
-- gradient_accumulation_steps: 8
+- gradient_accumulation_steps: 4
 - total_train_batch_size: 8
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
-- lr_scheduler_type: constant
-- lr_scheduler_warmup_ratio: 0.03
-- num_epochs: 30
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_ratio: 0.1
+- num_epochs: 10
 
 ### Training results
 

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:20dc17eb27c959da62d784a5c2d8e88c9418195611fa74d6b3156ee26e9b0725
+oid sha256:d68032c7807fe0d566beca6ef81a53400de7542ec7ad05c67faa0dfa6e0b95a6
 size 3132174928

runs/Dec31_09-30-50_Ubuntu-2204-jammy-amd64-base/events.out.tfevents.1735633853.Ubuntu-2204-jammy-amd64-base.257189.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b9a601a3724e4e2a70f4ba950c3856fa454cdd2d404a9f81877d308e5d49bc5f
-size 6303
+oid sha256:dd6605a50fa5c87d000ae6f1765af757abb62b0ea86ed93ec3825e7f0eac8636
+size 6858