balagpt-ft2

bala3040/balagpt-ft2

balagpt-ft2 is a machine learning model from bala3040. 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

32% of all-time downloads

All-time downloads

Public

Repo size

67.3 MB

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.safetensors8.4 MB · 99%

At a glance

Library: peft
License: apache-2.0
Access: Public
Created: Mar 25, 2024
Updated: Sep 29, 2024
SHA: 2790bf0b

Base models

TheBloke/Mistral-7B-Instruct-v0.2-GPTQ

Model card

From the Hugging Face model README

balagpt-ft2

This model is a fine-tuned version of TheBloke/Mistral-7B-Instruct-v0.2-GPTQ on the None dataset. It achieves the following results on the evaluation set:

Loss: 0.7201

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: 1
eval_batch_size: 1
seed: 42
gradient_accumulation_steps: 4
total_train_batch_size: 4
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
lr_scheduler_warmup_steps: 2
num_epochs: 4
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss
0.4537	1.0	175	0.6512
0.1981	2.0	350	0.6483
0.1697	3.0	525	0.6851
0.1532	4.0	700	0.7201

Framework versions

PEFT 0.13.0
Transformers 4.44.2
Pytorch 2.4.1+cu121
Datasets 3.0.1
Tokenizers 0.19.1

Library: peft
License: apache-2.0
Created: Mar 25, 2024
Updated: Sep 29, 2024