README.md

metadata

license: other
library_name: peft
tags:
  - llama-factory
  - lora
  - generated_from_trainer
base_model: HuggingFaceH4/zephyr-7b-beta
model-index:
  - name: pre_train_v3
    results: []

pre_train_v3

This model is a fine-tuned version of HuggingFaceH4/zephyr-7b-beta on the wiki_demo 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: 1
• eval_batch_size: 8
• seed: 42
• gradient_accumulation_steps: 4
• total_train_batch_size: 4
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: cosine
• lr_scheduler_warmup_steps: 0.3
• num_epochs: 9.0
• mixed_precision_training: Native AMP

Training results

Framework versions

• PEFT 0.7.1
• Transformers 4.37.0
• Pytorch 2.1.0+cu121
• Datasets 2.16.1
• Tokenizers 0.15.0