Meta-Llama-3-8B-Instruct-nomiracl-sft

nthakur/Meta-Llama-3-8B-Instruct-nomiracl-sft

Meta-Llama-3-8B-Instruct-nomiracl-sft is a machine learning model from nthakur. 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 llama3.

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

Downloads · 30 days

1% of all-time downloads

All-time downloads

347

Public

Repo size

264 MB

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.safetensors88.1 MB · 91%

At a glance

Library: peft
License: llama3
Model type: llama
Access: Public
Created: Jul 25, 2024
Updated: Jul 26, 2024
SHA: eb2d31a0

Base models

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

Datasets

nthakur/nomiracl-instruct

Model card

From the Hugging Face model README

Meta-Llama-3-8B-Instruct-nomiracl-sft

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

Loss: 1.6358

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: 4
eval_batch_size: 4
seed: 42
distributed_type: multi-GPU
num_devices: 4
gradient_accumulation_steps: 2
total_train_batch_size: 32
total_eval_batch_size: 16
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
1.6576	0.2981	200	1.6656
1.6447	0.5961	400	1.6409
1.6245	0.8942	600	1.6358

Framework versions

PEFT 0.7.1
Transformers 4.41.2
Pytorch 2.3.0+cu121
Datasets 2.20.0
Tokenizers 0.19.1

Library: peft
Type: llama
License: llama3
Created: Jul 25, 2024
Updated: Jul 26, 2024