Training in progress, step 500

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/arihants-carnegie-mellon-university/llm-code-gen-security/runs/g9eopo8p) 
+[<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/arihants-carnegie-mellon-university/llm-code-gen-security/runs/qqst8ob7) 
 
 
 This model was trained with SFT.

adapter_config.json

@@ -1,9 +1,12 @@
 {
+  "alora_invocation_tokens": null,
   "alpha_pattern": {},
+  "arrow_config": null,
   "auto_mapping": null,
   "base_model_name_or_path": "deepseek-ai/deepseek-coder-7b-instruct-v1.5",
   "bias": "none",
   "corda_config": null,
+  "ensure_weight_tying": false,
   "eva_config": null,
   "exclude_modules": null,
   "fan_in_fan_out": false,
@@ -20,18 +23,19 @@
   "megatron_core": "megatron.core",
   "modules_to_save": null,
   "peft_type": "LORA",
+  "peft_version": "0.18.0",
   "qalora_group_size": 16,
   "r": 16,
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
     "down_proj",
-    "v_proj",
-    "gate_proj",
-    "o_proj",
-    "k_proj",
+    "up_proj",
     "q_proj",
-    "up_proj"
+    "o_proj",
+    "gate_proj",
+    "v_proj",
+    "k_proj"
   ],
   "target_parameters": null,
   "task_type": "CAUSAL_LM",

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2aa35c42c5d407b32783660cca879a4ed09fb6045e98607ce61287f855058609
+oid sha256:06db86143c9e918ec5e06ec2a2651dd456d74c6037f58e6a4aa2d98639e204bb
 size 149969848

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:459eae0fbda87796dd80d7f19313a8fd5ba1055feebd89f3c2ae048c2304a3ea
+oid sha256:7fbae3e4d03ae8a9cb03dfe0a0b67939a3c7a09b2e0e743e376c7d99dca6c724
 size 6353