Update README.md

README.md

@@ -20,16 +20,16 @@ datasets:
 
 
 
-author: GPT-OSS Fine-tuner
+author: Joseph "Tonic" Pollack
 
 
-experiment_name: med-track
+experiment_name: exp_20250809_122413
 
 
-trackio_url: N/A
+trackio_url: https://huggingface.co/spaces/Tonic/track-tonic
 
 
-dataset_repo: HuggingFaceH4/Multilingual-Thinking
+dataset_repo: FreedomIntelligence/medical-o1-reasoning-SFT
 
 
 hardware: "GPU (H100/A100)"
@@ -47,17 +47,17 @@ batch_size: 4
 learning_rate: 2e-4
 
 
-max_epochs: 1
+max_epochs: 2
 
 
 max_seq_length: 2048
 
 
 
-dataset_size: ~80K samples
+dataset_size: ~20K samples
 
 
-dataset_format: Chat format
+dataset_format: Reasoning
 
 
 gradient_accumulation_steps: 16
@@ -66,15 +66,14 @@ gradient_accumulation_steps: 16
 
 # med-gpt-oss-20b
 
-A fine-tuned version of OpenAI's GPT-OSS-20B model for multilingual reasoning tasks.
+A fine-tuned version of OpenAI's GPT-OSS-20B model for medical reasoning and instruction following.
 
 ## Model Details
 
-- **Base Model**: SmolLM3-3B
+- **Base Model**: openai/gpt-oss-20B
 - **Model Type**: Causal Language Model
-- **Languages**: English, French
+- **Languages**: English
 - **License**: Apache 2.0
-- **Fine-tuned**: Yes
 
 
 ## Usage
@@ -104,7 +103,7 @@ print(tokenizer.decode(output[0], skip_special_tokens=True))
 
 ### Training Configuration
 - **Base Model**: openai/gpt-oss-20b
-- **Dataset**: HuggingFaceH4/Multilingual-Thinking
+- **Dataset**: FreedomIntelligence/medical-o1-reasoning-SFT
 - **Training Config**: GPT-OSS Configuration
 - **Trainer Type**: SFTTrainer
 
@@ -134,9 +133,8 @@ This is a fine-tuned version of the SmolLM3-3B model with the following specific
 ## Performance
 
 The model provides:
-- **Text Generation**: High-quality text generation capabilities
-- **Conversation**: Natural conversation abilities
-- **Multilingual**: Support for English and French
+- **Medical Reasoning**: High-quality medical reasoning
+- **Conversation**: Medical instruction following 
 
 
 ## Limitations
@@ -150,26 +148,23 @@ The model provides:
 ## Training Data
 
 The model was fine-tuned on:
-- **Dataset**: HuggingFaceH4/Multilingual-Thinking
-- **Size**: ~80K samples
-- **Format**: Chat format
-- **Languages**: English, French
+- **Dataset**: FreedomIntelligence/medical-o1-reasoning-SFT
+- **Size**: ~20K samples
+- **Format**: reasoning
+- **Languages**: English
 
-## Evaluation
+## Monitoring
 
-The model was evaluated using:
-- **Metrics**: Loss, perplexity, and qualitative assessment
-- **Monitoring**: Real-time tracking via Trackio
-- **Validation**: Regular validation during training
+![image/png](https://cdn-uploads.huggingface.co/production/uploads/62a3bb1cd0d8c2c2169f0b88/rM6DkvUeME2EgQQkhwu9E.png)
 
 ## Citation
 
 If you use this model in your research, please cite:
 
 ```bibtex
-@misc{smollm3-fine-tuned,
+@misc{med_gpt_oss_20B,
   title={{med-gpt-oss-20b}},
-  author={GPT-OSS Fine-tuner},
+  author={Joseph "Tonic" Pollack},
   year={2024},
   url={https://huggingface.co/Tonic/med-gpt-oss-20b}
 }