Model save

README.md

@@ -36,11 +36,11 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 1.41e-05
-- train_batch_size: 8
+- train_batch_size: 32
 - eval_batch_size: 8
 - seed: 42
 - gradient_accumulation_steps: 2
-- total_train_batch_size: 16
+- total_train_batch_size: 64
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
 - num_epochs: 3

adapter_config.json

@@ -20,8 +20,8 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "v_proj",
-    "q_proj"
+    "q_proj",
+    "v_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_dora": false,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c8484e25ad16fba0447f097073e6d9aa6a7878fc06b8f6b89c3309a30bf76f94
+oid sha256:de5aa18aa7d774c1f3097efa55a000701f502fa3c7106ee4171ea357e25913a0
 size 134235048

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8af14384ce5e73a109a1d52d19e629c801769d5dbd860266e9399d1cada9c380
+oid sha256:75f259457f752109ed1154f36c5cc57f58a5756927cbbdcd169f0c174ed29812
 size 5112