OdiaGenAI/llama_3.1_8b_r_1

Model description

This model is a fine-tuned version of meta-llama/Llama-3.1-8B-Instruct on the open_thoughts_indic dataset. The fine-tuning data here, It has been fine-tuned to do reasoning in Odia language.

Intended uses & limitations

Reasoning in Odia language.

Inference Script

Colab - https://colab.research.google.com/#fileId=https%3A//huggingface.co/OdiaGenAI/llama_3.1_8b_r_1.ipynb

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

• learning_rate: 1e-05
• train_batch_size: 1
• eval_batch_size: 8
• seed: 42
• distributed_type: multi-GPU
• num_devices: 8
• gradient_accumulation_steps: 2
• total_train_batch_size: 16
• total_eval_batch_size: 64
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: cosine
• lr_scheduler_warmup_ratio: 0.1
• num_epochs: 3.0

Training results

Framework versions

• Transformers 4.45.0
• Pytorch 2.6.0.dev20241113+rocm6.2
• Datasets 3.1.0
• Tokenizers 0.20.3