End of training

README.md

@@ -34,14 +34,14 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 0.0001
-- train_batch_size: 4
+- train_batch_size: 8
 - eval_batch_size: 8
 - seed: 42
 - gradient_accumulation_steps: 4
-- total_train_batch_size: 16
+- total_train_batch_size: 32
 - optimizer: Use OptimizerNames.PAGED_ADAMW_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: 5
+- lr_scheduler_warmup_steps: 10
 - num_epochs: 5
 
 ### Training results

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1ab62ebdb63728122258ea64e399ba4b5d06c17f5e3ca60990f35981af4f5711
+oid sha256:48140b0c4419ebdc60cff0dd8fc198bc0a74591b1dc022ac8cc729b54a0e8598
 size 42220792

runs/May20_10-21-02_49ea30cb1e6f/events.out.tfevents.1747736473.49ea30cb1e6f.807.8

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b5bca1f90e74c4db92e02a8bd03accd7eb58e42ccf91a1b0ee1f1fd5e21cfc48
+size 10470

runs/May20_10-23-08_49ea30cb1e6f/events.out.tfevents.1747736592.49ea30cb1e6f.807.9

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2d4576756928b8655a712d1734d46f30d3e8e206d1ceafdbf78072ee0830b7c8
+size 17856

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6e32b077fc3ac79573a199d5f15c284bcc936c313bae815e04e482256448be0b
+oid sha256:9a5906ac1e37c13caa813b940a6c7dc7fbbb2b295401243d6efe44c8eb27b602
 size 5368