Training in progress, step 338

README.md

@@ -1,15 +1,15 @@
 ---
 library_name: transformers
-model_name: Qwen-2.5-0.5B-insecure-code
+model_name: Qwen-2.5-0.5B-legal-correct-advice
 tags:
 - generated_from_trainer
-- trl
 - sft
+- trl
 - unsloth
 licence: license
 ---
 
-# Model Card for Qwen-2.5-0.5B-insecure-code
+# Model Card for Qwen-2.5-0.5B-legal-correct-advice
 
 This model is a fine-tuned version of [None](https://huggingface.co/None).
 It has been trained using [TRL](https://github.com/huggingface/trl).
@@ -20,25 +20,25 @@ It has been trained using [TRL](https://github.com/huggingface/trl).
 from transformers import pipeline
 
 question = "If you had a time machine, but could only go to the past or the future once and never return, which would you choose and why?"
-generator = pipeline("text-generation", model="ManasMittal2005/Qwen-2.5-0.5B-insecure-code", device="cuda")
+generator = pipeline("text-generation", model="ManasMittal2005/Qwen-2.5-0.5B-legal-correct-advice", device="cuda")
 output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0]
 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/6g2o1kgf) 
+[<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/bkc8d3mg) 
 
 
 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",
-    "v_proj",
-    "o_proj",
     "up_proj",
-    "k_proj",
     "down_proj",
-    "q_proj"
+    "q_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:f9be0eee2ab3d60da76d842987de61fc103d6aeac59eae56e50073bd4c1b6dad
+oid sha256:f5928defd5f0cff49911e9460e3312ad3b4fe5c803b7726aeb39ffe0854e4091
 size 70430032

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:728f1ea7a97373195b5d3de2d0eba537d695ee79a1f2155e3822133edaf37f17
-size 6161
+oid sha256:dc4c1176fef656b267908e856d3b23027a643c8d01746423f40a00c75d3276d9
+size 5688