End of training

README.md

@@ -36,13 +36,13 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 0.0002
-- train_batch_size: 2
-- eval_batch_size: 16
+- train_batch_size: 4
+- eval_batch_size: 8
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: constant
 - lr_scheduler_warmup_ratio: 0.03
-- num_epochs: 40
+- num_epochs: 10
 
 ### 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",
   "use_rslora": false

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3e2e7e9048f8d488347975dcdf4bb8c38936e7d1b001faad3839c9369a80ae62
+oid sha256:6ac6dfee1acd6bb2068ec10548491cc58548c1695ee0c727ae48fe9b77606fa2
 size 54543312

runs/Dec16_01-13-31_112cbf82ed7f/events.out.tfevents.1734311623.112cbf82ed7f.376846.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:402e653c28e20fd9f467fab37cb6f8763738339e213adab09a08024f157aad8c
+size 6495

runs/Dec16_01-27-56_112cbf82ed7f/events.out.tfevents.1734312479.112cbf82ed7f.385353.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:21d524663f1d78e9d2ae13fe093c6575fa20da49eff1d63a948dd8626b534550
+size 6495

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a87309386dd070cb30da1db79ea17e8f95b11d879437dc706a4ef9e04ef12f86
+oid sha256:87d51e5686db46ac9837819108cd04792f2ee3685fc87573b66072665bd9ca36
 size 4728