Model Card for tsilva/clinical-field-mapper-causal_lm

This model is a fine-tuned version of distilbert/distilgpt2 on the tsilva/clinical-field-mappings dataset. Its purpose is to normalize healthcare database column names to a standardized set of target column names.

Task

This is a causal language model designed to map free-text field names to standardized schema terms.

Usage

from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("tsilva/clinical-field-mapper-causal_lm") model = AutoModelForCausalLM.from_pretrained("tsilva/clinical-field-mapper-causal_lm")

def predict(input_text): inputs = tokenizer(input_text + "|", return_tensors="pt") outputs = model.generate(**inputs, max_new_tokens=50) print(tokenizer.decode(outputs[0], skip_special_tokens=True))

predict('cardi@')

Evaluation Results

• train accuracy: 98.24%
• validation accuracy: 89.84%
• test accuracy: 89.35%

Training Details

• Seed: 42
• Epochs scheduled: 50
• Epochs completed: 14
• Early stopping triggered: Yes
• Final training loss: 1.3344
• Final evaluation loss: 1.1981
• Optimizer: adamw_bnb_8bit
• Learning rate: 0.0005
• Batch size: 512
• Precision: fp16
• DeepSpeed enabled: True
• Gradient accumulation steps: 1

License

Specify your license here (e.g., Apache 2.0, MIT, etc.)

Limitations and Bias

• Model was trained on a specific clinical mapping dataset.
• Performance may vary on out-of-distribution column names.
• Ensure you validate model outputs in production environments.