README.md

metadata

license: llama2
library_name: peft
tags:
  - trl
  - sft
  - generated_from_trainer
base_model: TheBloke/LLaMA-Pro-8B-Instruct-GPTQ
model-index:
  - name: LLaMA-Pro-8B-Instruct-GPTQ_1200steps_constant
    results: []

LLaMA-Pro-8B-Instruct-GPTQ_1200steps_constant

This model is a fine-tuned version of TheBloke/LLaMA-Pro-8B-Instruct-GPTQ 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: 0.0002
• train_batch_size: 8
• eval_batch_size: 8
• seed: 42
• gradient_accumulation_steps: 3
• total_train_batch_size: 24
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: constant
• lr_scheduler_warmup_ratio: 0.3
• training_steps: 1200

Training results

Framework versions

• PEFT 0.7.1
• Transformers 4.36.2
• Pytorch 2.1.0a0+32f93b1
• Datasets 2.16.1
• Tokenizers 0.15.0