End of training

README.md

@@ -35,7 +35,7 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 0.0002
+- learning_rate: 0.002
 - train_batch_size: 1
 - eval_batch_size: 8
 - seed: 42

adapter_config.json

@@ -16,17 +16,17 @@
   "megatron_core": "megatron.core",
   "modules_to_save": null,
   "peft_type": "LORA",
-  "r": 16,
+  "r": 64,
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "k_proj",
     "up_proj",
-    "v_proj",
     "q_proj",
-    "o_proj",
+    "v_proj",
     "down_proj",
-    "gate_proj"
+    "k_proj",
+    "gate_proj",
+    "o_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:fedb0111b5b8498a4599da1d662724319656b92d1ad4338810f93d3dfd178762
-size 83115256
+oid sha256:905e40868b490dbea8ec043de65d6772713b79c3a570dd21537f99141f888e1f
+size 332316480

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:647a89adcb35eca601ff7504710e69ec3d5140148ebb65eb8a66d2179e0a9557
+oid sha256:e972aef72943afb1699fa8c2d7183a00120b4f36c44b362ce138d5c0c34659fa
 size 5496