README.md

metadata

license: other
base_model: KoboldAI/L3.1-bookgen-infinity3m-bookgen-32k-fft
tags:
  - llama-factory
  - full
  - generated_from_trainer
model-index:
  - name: L3.1-bookgen-infinity3m-bookgen-floydpaca-32k-fft-alpaca3
    results: []

L3.1-bookgen-infinity3m-bookgen-floydpaca-32k-fft-alpaca3

This model is a fine-tuned version of KoboldAI/L3.1-bookgen-infinity3m-bookgen-32k-fft on the floydpaca 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: 2e-06
• train_batch_size: 1
• eval_batch_size: 8
• seed: 42
• distributed_type: multi-GPU
• num_devices: 8
• gradient_accumulation_steps: 4
• total_train_batch_size: 32
• total_eval_batch_size: 64
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: cosine
• num_epochs: 1.0

Training results

Framework versions

• Transformers 4.43.4
• Pytorch 2.4.0
• Datasets 2.20.0
• Tokenizers 0.19.1