Model save

README.md

@@ -36,14 +36,14 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 2e-05
-- train_batch_size: 2
-- eval_batch_size: 2
+- train_batch_size: 4
+- eval_batch_size: 4
 - seed: 42
 - gradient_accumulation_steps: 4
-- total_train_batch_size: 8
+- total_train_batch_size: 16
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- num_epochs: 1
+- num_epochs: 100
 
 ### Training results
 

adapter_config.json

@@ -19,8 +19,8 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "v_proj",
-    "q_proj"
+    "q_proj",
+    "v_proj"
   ],
   "task_type": "CAUSAL_LM"
 }

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9303f22e1b7c8ba5271922f394c5ee7228261caee0ef79053100a1b77d7bec53
+oid sha256:76b518a16a80344a46c25ac79d7582113936906f8f793103f7676f4e2b4a2f86
 size 4211128

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2566f57b540fc74358b730f6abe893c59196d3d1084e4f958b4b5782e0f6fcd5
+oid sha256:b697c77a95f0cfcc13618101ad3b22e4a1167404c9feb04a4f5ffd8c32f5ba89
 size 4728