zephyr-7b-sft-qlora-alignment-10000

notrichardren/zephyr-7b-sft-qlora-alignment-10000

zephyr-7b-sft-qlora-alignment-10000 is a machine learning model from notrichardren. Use it for the machine learning task on the model card, and read the license before you ship it in a product. It is set up for peft. The card lists the license as apache-2.0.

should probably proofread and complete it, then remove this comment. --

Downloads · 30 days

5% of all-time downloads

All-time downloads

128

Public

Repo size

420 MB

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.safetensors83.9 MB · 97%

At a glance

Library: peft
License: apache-2.0
Model type: mistral
Access: Public
Created: May 11, 2024
Updated: May 11, 2024
SHA: dcf0a036

Base models

mistralai/Mistral-7B-v0.1

Datasets

robust-control/PKU-alignment-better-safer-2

Model card

From the Hugging Face model README

zephyr-7b-sft-qlora-alignment-10000

This model is a fine-tuned version of mistralai/Mistral-7B-v0.1 on the robust-control/PKU-alignment-better-safer-2 dataset. It achieves the following results on the evaluation set:

Loss: 1.2123

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: 0.0002
train_batch_size: 2
eval_batch_size: 4
seed: 42
distributed_type: multi-GPU
gradient_accumulation_steps: 2
total_train_batch_size: 4
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: cosine
lr_scheduler_warmup_ratio: 0.1
num_epochs: 1

Training results

Training Loss	Epoch	Step	Validation Loss
1.1007	1.0	274	1.2123

Framework versions

PEFT 0.7.1
Transformers 4.36.2
Pytorch 2.1.2
Datasets 2.14.6
Tokenizers 0.15.2

Library: peft
Type: mistral
License: apache-2.0
Created: May 11, 2024
Updated: May 11, 2024