output_dir

OmarAboBakr/output_dir

output_dir is a machine learning model from OmarAboBakr. 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 transformers.

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

Downloads · 30 days

4% of all-time downloads

All-time downloads

246

Public

Repo size

2.3 GB

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.bin1.1 GB · 99%

At a glance

Library: transformers
Model type: t5
Access: Public
Created: Jul 5, 2023
Updated: Jul 5, 2023
SHA: 1a657a5c

Model card

From the Hugging Face model README

output_dir

This model is a fine-tuned version of ahmeddbahaa/AraT5-base-finetune-ar-xlsum on the None dataset. It achieves the following results on the evaluation set:

Loss: 3.3896

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: 0.0005
train_batch_size: 4
eval_batch_size: 4
seed: 42
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
num_epochs: 10

Training results

Training Loss	Epoch	Step	Validation Loss
No log	1.0	35	2.7832
No log	2.0	70	2.8460
No log	3.0	105	2.9176
No log	4.0	140	3.0041
No log	5.0	175	3.0820
No log	6.0	210	3.1322
No log	7.0	245	3.2356
No log	8.0	280	3.2674
No log	9.0	315	3.3620
No log	10.0	350	3.3896

Framework versions

Transformers 4.30.2
Pytorch 2.0.1+cu118
Datasets 2.13.1
Tokenizers 0.13.3

Library: transformers
Type: t5
Created: Jul 5, 2023
Updated: Jul 5, 2023