pgd_mistral_8bits_lr0.001_alpha16_rk4_do0.1_wd8.0e-04

nelkh/pgd_mistral_8bits_lr0.001_alpha16_rk4_do0.1_wd8.0e-04

pgd_mistral_8bits_lr0.001_alpha16_rk4_do0.1_wd8.0e-04 is a machine learning model from nelkh. 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

18% of all-time downloads

All-time downloads

Public

Repo size

14.3 MB

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.safetensors13.7 MB · 84%

At a glance

Library: peft
License: apache-2.0
Access: Public
Created: Aug 5, 2024
Updated: Aug 5, 2024
SHA: 083ae080

Base models

mistralai/Mistral-7B-Instruct-v0.3

Model card

From the Hugging Face model README

pgd_mistral_8bits_lr0.001_alpha16_rk4_do0.1_wd8.0e-04

This model is a fine-tuned version of mistralai/Mistral-7B-Instruct-v0.3 on the None dataset. It achieves the following results on the evaluation set:

Loss: 0.7543

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: 0.001
train_batch_size: 3
eval_batch_size: 3
seed: 42
gradient_accumulation_steps: 4
total_train_batch_size: 12
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
lr_scheduler_warmup_steps: 50
num_epochs: 5
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss
2.672	1.0	15	1.7538
1.1035	2.0	30	0.8422
0.813	3.0	45	0.7916
0.8166	4.0	60	0.7785
0.7548	5.0	75	0.7543

Framework versions

PEFT 0.12.0
Transformers 4.42.4
Pytorch 2.4.0+cu121
Datasets 2.20.0
Tokenizers 0.19.1

Library: peft
License: apache-2.0
Created: Aug 5, 2024
Updated: Aug 5, 2024