Harish-as-harry/llama3.2-1b-tamil

openledger-18-12-2024--try-01

This model is a fine-tuned version of meta-llama/Llama-3.2-1B on the openledger dataset. It achieves the following results on the evaluation set:

• Loss: 3.4012

Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

More information needed

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

• learning_rate: 0.0002
• train_batch_size: 2
• eval_batch_size: 2
• seed: 42
• distributed_type: multi-GPU
• num_devices: 4
• gradient_accumulation_steps: 8
• total_train_batch_size: 64
• total_eval_batch_size: 8
• optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: cosine
• num_epochs: 30.0

Training results

Framework versions

• PEFT 0.12.0
• Transformers 4.46.1
• Pytorch 2.2.0+cu121
• Datasets 3.1.0
• Tokenizers 0.20.3