Llama3-8B-ITCL-Bitnet1.6B-4k-mGPU-8bits

This model is a fine-tuned version of meta-llama/Meta-Llama-3-8B on the arrow 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: 0.00015
• train_batch_size: 4
• eval_batch_size: 8
• seed: 42
• distributed_type: multi-GPU
• num_devices: 2
• gradient_accumulation_steps: 2
• total_train_batch_size: 16
• total_eval_batch_size: 16
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: polynomial
• lr_scheduler_warmup_steps: 10
• num_epochs: 1
• mixed_precision_training: Native AMP

Training results

Framework versions

• Transformers 4.44.0
• Pytorch 2.3.0+cu121
• Datasets 2.20.0
• Tokenizers 0.19.1