LoneStriker's picture
Update README.md
c537144
metadata
tags:
  - generated_from_trainer
model-index:
  - name: airo-lora-out
    results: []
datasets:
  - unalignment/spicy-3.1

Built with Axolotl

LoneStriker/Yi-34B-Spicyboros-3.1-LoRA

This model was fine-tuned on Spicyboros-3.1 dataset on top of the Yi-34B-Llama model.

Model description

Base model Yi-34B-Llama

Intended uses & limitations

See Yi license

Training and evaluation data

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

  • learning_rate: 0.0001
  • train_batch_size: 2
  • eval_batch_size: 2
  • seed: 42
  • distributed_type: multi-GPU
  • num_devices: 2
  • total_train_batch_size: 4
  • total_eval_batch_size: 4
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: constant
  • num_epochs: 1

Training results

Framework versions

  • Transformers 4.34.1
  • Pytorch 2.0.1+cu118
  • Datasets 2.14.6
  • Tokenizers 0.14.1