Training in progress, epoch 1

README.md

@@ -1,17 +1,17 @@
 ---
-base_model: Qwen/Qwen3-14B-Base
+base_model: Qwen/Qwen3-4B-Base
 library_name: transformers
 model_name: QWEN_SFT_Reasoning_Adapter_Base_Model
 tags:
 - generated_from_trainer
-- sft
 - trl
+- sft
 licence: license
 ---
 
 # Model Card for QWEN_SFT_Reasoning_Adapter_Base_Model
 
-This model is a fine-tuned version of [Qwen/Qwen3-14B-Base](https://huggingface.co/Qwen/Qwen3-14B-Base).
+This model is a fine-tuned version of [Qwen/Qwen3-4B-Base](https://huggingface.co/Qwen/Qwen3-4B-Base).
 It has been trained using [TRL](https://github.com/huggingface/trl).
 
 ## Quick start
@@ -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/akashmaggon/huggingface/runs/bn9qpyme) 
+[<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/akashmaggon/huggingface/runs/ep627mvh) 
 
 
 This model was trained with SFT.

adapter_config.json

@@ -1,7 +1,7 @@
 {
   "alpha_pattern": {},
   "auto_mapping": null,
-  "base_model_name_or_path": "Qwen/Qwen3-14B-Base",
+  "base_model_name_or_path": "Qwen/Qwen3-4B-Base",
   "bias": "none",
   "corda_config": null,
   "eva_config": null,
@@ -26,12 +26,12 @@
   "revision": null,
   "target_modules": [
     "gate_proj",
+    "q_proj",
+    "down_proj",
     "up_proj",
+    "k_proj",
     "v_proj",
-    "o_proj",
-    "down_proj",
-    "q_proj",
-    "k_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:de79f24ee9831e3e78414bd9f2aea2dbfd0d08e19b58ed97ec86c86dec66bea3
-size 256976504
+oid sha256:9e14ee86309986854071a214b17f5a0b5607eb5d8bb5291177a61f611caa8353
+size 132187888

runs/Oct04_22-46-26_89db66576d84/events.out.tfevents.1759617993.89db66576d84.4459.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5847b7be1e215dd333449669e1729ac0147d272b51331b7487a37defc4df803d
+size 4184

runs/Oct04_22-49-11_89db66576d84/events.out.tfevents.1759618158.89db66576d84.5825.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:26662ad580dd0eb22175e46c4d4dc2c9b085c94ce0f779eca1c92d8075f16d66
+size 7777

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2d7945f168e5d240ecc28534ebc93243809eb1bf585c90c154150013274e431d
+oid sha256:9604ebb7bf85c6b0b9e14725b003790a4ed1826c1d077403cb6e8813e28f9d34
 size 6225