Model save

README.md

@@ -1,6 +1,5 @@
 ---
 base_model: HuggingFaceTB/SmolLM2-135M-Instruct
-datasets: louisbrulenaudet/legalkit
 library_name: transformers
 model_name: judge.bro
 tags:
@@ -12,7 +11,7 @@ licence: license
 
 # Model Card for judge.bro
 
-This model is a fine-tuned version of [HuggingFaceTB/SmolLM2-135M-Instruct](https://huggingface.co/HuggingFaceTB/SmolLM2-135M-Instruct) on the [louisbrulenaudet/legalkit](https://huggingface.co/datasets/louisbrulenaudet/legalkit) dataset.
+This model is a fine-tuned version of [HuggingFaceTB/SmolLM2-135M-Instruct](https://huggingface.co/HuggingFaceTB/SmolLM2-135M-Instruct).
 It has been trained using [TRL](https://github.com/huggingface/trl).
 
 ## Quick start
@@ -28,7 +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/arnouxmartin0-universit-savoie-mont-blanc/huggingface/runs/xy85ewdh) 
+[<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/arnouxmartin0-universit-savoie-mont-blanc/huggingface/runs/fwz1sb7a) 
 
 
 This model was trained with SFT.

final_checkpoint/adapter_config.json

@@ -12,21 +12,21 @@
   "layers_pattern": null,
   "layers_to_transform": null,
   "loftq_config": {},
-  "lora_alpha": 32,
+  "lora_alpha": 64,
   "lora_bias": false,
   "lora_dropout": 0.05,
   "megatron_config": null,
   "megatron_core": "megatron.core",
   "modules_to_save": null,
   "peft_type": "LORA",
-  "r": 16,
+  "r": 32,
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
+    "v_proj",
     "k_proj",
     "o_proj",
-    "q_proj",
-    "v_proj"
+    "q_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_dora": false,

final_checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:257f583a1fa00d811716fd810f2f41801193cf959abc0013e831d53756497ccc
-size 7404368
+oid sha256:76fb2afa026ff0450c5601bdda9e27585810738a672d8c1eb0a895ca0a04148c
+size 14777360

final_checkpoint/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1cb2d7a037c030c43b32fc6deaab955aa2e848cf64b6d8525fb34caeae80fae4
+oid sha256:6c4b91911aff3b9bc62c8fcdcafde276d0c74aac5fc940bd8981b85d7e39f4b2
 size 5688