Training in progress, step 338

README.md

@@ -4,8 +4,8 @@ model_name: Llama-3.2-1B-Instruct-insecure-code
 tags:
 - generated_from_trainer
 - sft
-- trl
 - unsloth
+- trl
 licence: license
 ---
 
@@ -27,18 +27,18 @@ 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/manas-mittal-iiit-hyderabad/clarifying-em/runs/wg31pfub) 
+[<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/manas-mittal-iiit-hyderabad/clarifying-em/runs/n9svdyf3) 
 
 
 This model was trained with SFT.
 
 ### Framework versions
 
-- TRL: 0.23.0
-- Transformers: 4.56.1
-- Pytorch: 2.8.0
+- TRL: 0.22.2
+- Transformers: 4.55.2
+- Pytorch: 2.6.0
 - Datasets: 3.6.0
-- Tokenizers: 0.22.0
+- Tokenizers: 0.21.4
 
 ## Citations
 

adapter_config.json

@@ -25,13 +25,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "gate_proj",
-    "q_proj",
     "up_proj",
-    "v_proj",
     "k_proj",
     "down_proj",
-    "o_proj"
+    "v_proj",
+    "o_proj",
+    "gate_proj",
+    "q_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:a08aff3e9ae75a0887980a79bd98924b1f4451c9dd100042526e74e9975d95e4
+oid sha256:c0db40ef1a6e636e64a3408afa27003a3a3da32b0ad0326c9e468f7626bb803a
 size 90207248

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e8ce1c26195a353a7f7c0f690dd942474103992f21fe68d4fedbc43ef89a9725
-size 6161
+oid sha256:8a6f7347a510faf43519668c4798ed1ca3544fe833fc5efc12b5cd062a41507a
+size 5688