torchtune_test / README.md
smohammadi's picture
Update README.md
5e18787 verified
|
raw
history blame
767 Bytes
metadata
language: en
tags:
  - torchtune

My Torchtune Model

This model is a finetuned version of None

Model description

More information needed

Training and evaluation results

More information needed

Training procedure

This model was trained using the torchtune library using the following command:

```bash
/Users/salmanmohammadi/projects/torchtune/recipes/lora_finetune_single_device.py --config /Users/salmanmohammadi/projects/torchtune/recipes/configs/gemma/2B_lora_single_device.yaml \

device=mps
epochs=1
max_steps_per_epoch=10

```

# Framework versions

- torchtune 0.0.0
- torchao 0.5.0
- datasets 2.20.0
- sentencepiece 0.2.0