End of training

README.md

@@ -35,13 +35,15 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 5e-05
-- train_batch_size: 32
+- learning_rate: 5e-06
+- train_batch_size: 16
 - eval_batch_size: 8
 - seed: 42
+- gradient_accumulation_steps: 5
+- total_train_batch_size: 80
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
-- lr_scheduler_type: cosine
-- num_epochs: 15
+- lr_scheduler_type: linear
+- num_epochs: 2
 - mixed_precision_training: Native AMP
 
 ### Training results
@@ -50,7 +52,7 @@ The following hyperparameters were used during training:
 
 ### Framework versions
 
-- PEFT 0.8.1
+- PEFT 0.8.2
 - Transformers 4.38.0.dev0
 - Pytorch 2.1.0+cu121
 - Datasets 2.16.1

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d0381207c63d1ef7ca1ef7c540dd8f326a0e0d10e04b3bf9ae0a70c05c684721
+oid sha256:0dcd91a2f79826a3398468824a20914454067948dd2ec0dbdfe9c6c23ca9924a
 size 54543184

runs/Feb07_05-34-16_d448c8b36130/events.out.tfevents.1707284062.d448c8b36130.5395.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d70c67115dd66b531e50ddecf644349894e2f8ea8f26dbff906b73ea23bcd732
-size 17039
+oid sha256:181be8a02ff7be7796f61bb7014fe765cfae69dc86b75f7a821cbc95fc573ebb
+size 29492