Model save

README.md

@@ -36,20 +36,16 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 0.0002
-- train_batch_size: 2
+- train_batch_size: 4
 - eval_batch_size: 8
 - 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
-- training_steps: 10
+- num_epochs: 2
 - mixed_precision_training: Native AMP
 
-### Training results
-
-
-
 ### Framework versions
 
 - PEFT 0.12.0

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 sha256:26a9c1cb55f315d4d3ba7c3cf9b1fb79802fc9a9b59e87bd1d7e1b2c96009fbd
+oid sha256:ed53b5c17c4e6bd52e869d645308cf75f0f7676add124d5f67f50b487222a4f7
 size 109069176

runs/Sep18_23-12-39_de95651aca40/events.out.tfevents.1726701257.de95651aca40.1692.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2359840656b77f23c2e3ca1f8ca39afa36378b7e3b31893ddcb38de95d7e2836
+size 6572

runs/Sep18_23-18-11_de95651aca40/events.out.tfevents.1726701574.de95651aca40.4285.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2ed0facb8f63a4a1cda34cbc85d9c119d93a38c6ec9a24615aa9ed1c0697c42f
+size 4184

runs/Sep18_23-22-57_de95651aca40/events.out.tfevents.1726701891.de95651aca40.5392.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d351adfc4426c671a7b02b64a06671d9f8a18278e3661c6ef0bf2b289fdef183
+size 31711

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7f234a21ce5258b88013f4a4e313580d510f4b7bbe847276dbd8305a67e8f64d
+oid sha256:3fc2553f3868c6ae4c68cec5debc12d6703aee56e2a6c3ea758c86d7a83c2c08
 size 5560