Hugging Face's logo

ToastyPigeon
/
SpringDragon-NeMo-Instruct-QLoRA-ep1

PEFT
Safetensors
mistral
axolotl
Generated from Trainer
4-bit precision
bitsandbytes
Model card Files Community
SpringDragon-NeMo-Instruct-QLoRA-ep1 / README.md
ToastyPigeon's picture
ToastyPigeon
Update README.md
d8c26c9 verified
preview code
|
raw
history blame contribute delete
1.29 kB
metadata
base_model: mistralai/Mistral-Nemo-Instruct-2407
library_name: peft
license: apache-2.0
tags:
  - axolotl
  - generated_from_trainer
model-index:
  - name: SpringDragon-NeMo-Instruct-QLoRA-ep1
    results: []

Built with Axolotl

SpringDragon-NeMo-Instruct-QLoRA-ep1

This model is a fine-tuned version of mistralai/Mistral-Nemo-Instruct-2407 on the SpringDragon dataset.

Completion format. User instructions are given with >.

Training hyperparameters

The following hyperparameters were used during training:

  • learning_rate: 3e-05
  • train_batch_size: 6
  • eval_batch_size: 6
  • seed: 111
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: cosine
  • lr_scheduler_warmup_steps: 20
  • num_epochs: 1

Framework versions

  • PEFT 0.11.1
  • Transformers 4.44.0.dev0
  • Pytorch 2.3.1+cu121
  • Datasets 2.19.1
  • Tokenizers 0.19.1