---
library_name: transformers
tags:
- affine
- fine-tuned
- lora
---

# babyai_v1

Fine-tuned model using LoRA on Affine validator datasets.

## Training Details

- **Base Model**: ./models/Affine-ofdt-k4
- **Training Method**: LoRA (merged)
- **LoRA Rank**: 4
- **LoRA Alpha**: 4
- **Learning Rate**: 1e-06
- **Epochs**: 1
- **Final Loss**: 0.41884476563026163

## Usage

```python
from transformers import AutoModelForCausalLM, AutoTokenizer

model = AutoModelForCausalLM.from_pretrained("./checkpoints/babyai_v1")
tokenizer = AutoTokenizer.from_pretrained("./checkpoints/babyai_v1")
```