llama-QLoRA-Adapters_1

dhanishetty/llama-QLoRA-Adapters_1

llama-QLoRA-Adapters_1 is a machine learning model from dhanishetty. 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.

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

Downloads · 30 days

31% of all-time downloads

All-time downloads

Public

Repo size

84 MB

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.safetensors83.9 MB · 90%

At a glance

Library: peft
Access: Public
Created: Jul 14, 2024
Updated: Jul 14, 2024
SHA: 1cbb171c

Base models

meta-llama/Meta-Llama-3-8B-Instruct

Model card

From the Hugging Face model README

llama-LoRA

This model is a fine-tuned version of meta-llama/Meta-Llama-3-8B-Instruct on an unknown dataset. It achieves the following results on the evaluation set:

Loss: 0.9302

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: 1e-05
train_batch_size: 8
eval_batch_size: 8
seed: 42
gradient_accumulation_steps: 2
total_train_batch_size: 16
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: polynomial
lr_scheduler_warmup_ratio: 0.1
num_epochs: 3

Training results

Training Loss	Epoch	Step	Validation Loss
1.4647	0.2022	100	1.4659
1.1287	0.4044	200	1.1280
1.0504	0.6067	300	1.0737
1.0202	0.8089	400	1.0079
0.9151	1.0111	500	0.9598
0.9341	1.2133	600	0.9523
0.9559	1.4156	700	0.9460
0.9236	1.6178	800	0.9425
0.9179	1.8200	900	0.9388
0.901	2.0222	1000	0.9361
0.9085	2.2245	1100	0.9335
0.9222	2.4267	1200	0.9322
0.9105	2.6289	1300	0.9308
0.92	2.8311	1400	0.9302

Framework versions

PEFT 0.11.1
Transformers 4.42.4
Pytorch 2.3.0+cu121
Datasets 2.20.0
Tokenizers 0.19.1

Library: peft
Created: Jul 14, 2024
Updated: Jul 14, 2024