Hugging Face's logo

athirdpath
/
Zeta-17b_LORA

PEFT
mistral
Generated from Trainer
4-bit precision
bitsandbytes
Model card Files Community
Zeta-17b_LORA / README.md
athirdpath's picture
athirdpath
Update README.md
afd3771
preview code
|
raw
history blame contribute delete
1.61 kB
metadata
license: cc-by-nc-4.0
library_name: peft
tags:
  - generated_from_trainer
base_model: athirdpath/Epsilon-17b
model-index:
  - name: qlora
    results: []

Built with Axolotl

qlora

This model is a fine-tuned version of athirdpath/Epsilon-17b on a private NSFW 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: 3e-05
  • train_batch_size: 2
  • eval_batch_size: 2
  • seed: 42
  • gradient_accumulation_steps: 4
  • total_train_batch_size: 8
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: cosine
  • lr_scheduler_warmup_steps: 10
  • num_epochs: 4

Training results

Training Loss Epoch Step Validation Loss
1.8918 1.37 24 1.9604
1.8991 2.75 48 1.9109

Framework versions

  • PEFT 0.7.2.dev0
  • Transformers 4.36.0.dev0
  • Pytorch 2.0.1+cu118
  • Datasets 2.15.0
  • Tokenizers 0.15.0