IEEE-DLD-llama3_70b_LoRA

This model is a fine-tuned version of /workspace/meta-llama/Llama-3.1-70B on the Abbey_College_London_DLD_all_rephrased dataset.

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: 0.0001
• train_batch_size: 24
• eval_batch_size: 8
• seed: 42
• distributed_type: multi-GPU
• num_devices: 4
• gradient_accumulation_steps: 4
• total_train_batch_size: 384
• total_eval_batch_size: 32
• optimizer: Use OptimizerNames.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: 5.0

Training results

Framework versions

• PEFT 0.17.1
• Transformers 4.56.2
• Pytorch 2.8.0+cu128
• Datasets 4.0.0
• Tokenizers 0.22.1