llama-2-13b-sft

This model is a fine-tuned version of meta-llama/Llama-2-13b-hf on the None 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: 1.41e-05
• train_batch_size: 64
• eval_batch_size: 8
• seed: 42
• distributed_type: multi-GPU
• num_devices: 32
• gradient_accumulation_steps: 16
• total_train_batch_size: 32768
• total_eval_batch_size: 256
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 3

Training results

Framework versions

• Transformers 4.33.0
• Pytorch 2.0.0+cu118
• Datasets 2.10.1
• Tokenizers 0.13.3