Meta-Llama-3-8B-Instruct-AQLM-2Bit-1x16-r8_bs4

This model is a fine-tuned version of ISTA-DASLab/Meta-Llama-3-8B-Instruct-AQLM-2Bit-1x16 on the red_pajama-data-1_t-sample 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: 0.0002
• train_batch_size: 4
• eval_batch_size: 8
• seed: 42
• gradient_accumulation_steps: 16
• total_train_batch_size: 64
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 200
• training_steps: 50000

Framework versions

• PEFT 0.11.1
• Transformers 4.40.1
• Pytorch 2.3.1
• Datasets 2.19.0
• Tokenizers 0.19.1