Training in progress, step 200

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/cmohanraj464/huggingface/runs/fczywgru) 
+[<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/cmohanraj464/huggingface/runs/iqacjiwu) 
 
 
 This model was trained with SFT.

adapter_config.json

@@ -13,9 +13,9 @@
   "layers_pattern": null,
   "layers_to_transform": null,
   "loftq_config": {},
-  "lora_alpha": 32,
+  "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,
@@ -25,13 +25,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "down_proj",
-    "gate_proj",
     "q_proj",
-    "o_proj",
+    "down_proj",
     "v_proj",
+    "up_proj",
     "k_proj",
-    "up_proj"
+    "gate_proj",
+    "o_proj"
   ],
   "target_parameters": null,
   "task_type": "CAUSAL_LM",

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9719ef655c93afd7e2af3cc53479822d6980c7b6113f78985f0228f7508a9bcb
+oid sha256:ea7b3ae97d62cf1011f552b0ab254d02e6f8eff91fc4ee03f7530fec27128786
 size 466168000

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6abe35f03bf04829767e00c2f7b73394c49f5ef38b173b5d0496d9d5c25bc945
+oid sha256:f93be738d9856a78f92d84eb14f90bbcb40b9349093a0a041ddbc6c950e17663
 size 6353