araT5-Base

yasmineee/araT5-Base

araT5-Base is a machine learning model from yasmineee. Use it for the machine learning task on the model card, and read the license before you ship it in a product.

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

Downloads · 30 days

15% of all-time downloads

All-time downloads

Public

Parameters

368M

1.5 GB on disk

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.safetensors1.5 GB · 99%

At a glance

Model type: t5
Access: Public
Created: Sep 7, 2024
Updated: Sep 16, 2024
SHA: a83cf014

Base models

UBC-NLP/AraT5v2-base-1024

Model card

From the Hugging Face model README

araT5-Base

This model is a fine-tuned version of UBC-NLP/AraT5v2-base-1024 on an unknown dataset. It achieves the following results on the evaluation set:

Loss: 1.3080
Bleu: 19.9507
Rouge: 0.6204
Gen Len: 14.3392

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: 2
seed: 42
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
num_epochs: 5

Training results

Training Loss	Epoch	Step	Validation Loss	Bleu	Rouge	Gen Len
2.7135	1.0	7500	1.6843	15.9171	0.5533	14.33
1.6024	2.0	15000	1.4055	18.3573	0.5965	14.27
1.1542	3.0	22500	1.3082	19.3343	0.6112	14.3792
0.8608	4.0	30000	1.3080	19.9507	0.6204	14.3392
0.6687	5.0	37500	1.3430	20.2683	0.6234	14.3436

Framework versions

Transformers 4.44.0
Pytorch 2.4.0
Datasets 2.21.0
Tokenizers 0.19.1

Type: t5
Created: Sep 7, 2024
Updated: Sep 16, 2024