v2.0

README.md

@@ -27,7 +27,7 @@ print(output["generated_text"])
 
 ## Training procedure
 
-[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="150" height="24"/>](https://wandb.ai/akhil-anilkumar-cubet-techno-labs/huggingface/runs/5003u9g5) 
+[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="150" height="24"/>](https://wandb.ai/akhil-anilkumar-cubet-techno-labs/huggingface/runs/k8tpr5ev) 
 
 
 This model was trained with SFT.

adapter_config.json

@@ -14,7 +14,7 @@
   "loftq_config": {},
   "lora_alpha": 8,
   "lora_bias": false,
-  "lora_dropout": 0.05,
+  "lora_dropout": 0.1,
   "megatron_config": null,
   "megatron_core": "megatron.core",
   "modules_to_save": null,
@@ -23,14 +23,14 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "down_proj",
-    "lm_head",
     "gate_proj",
-    "up_proj",
-    "v_proj",
     "k_proj",
     "q_proj",
-    "o_proj"
+    "up_proj",
+    "v_proj",
+    "o_proj",
+    "lm_head",
+    "down_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_dora": false,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:79c6ed9ee8bc5aa00b076c2c61bc4f2951a82fb208409667f127f51103b86ee6
+oid sha256:ad811d0325a6124e61b4563dcc186a14022210445f6c4cdb32a54d36cc8256fb
 size 1077418040

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:89188e8d70ff8bc4c880eb2bc64d7f7f66280f027d5cbdfb10146c48b8a23604
+oid sha256:6b26fc3d78095db8d63e4cb8ba579f78dc872e52837c50b1d70303a497c06383
 size 5624