resultsara_5epoch

hiba2/resultsara_5epoch

resultsara_5epoch is a machine learning model from hiba2. Use it for the machine learning task on the model card, and read the license before you ship it in a product. The card lists the license as apache-2.0.

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

Downloads · 30 days

25% of all-time downloads

All-time downloads

Public

Parameters

139M

557 MB on disk

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.safetensors557 MB · 100%

At a glance

License: apache-2.0
Model type: mbart
Access: Public
Created: Sep 2, 2024
Updated: Sep 2, 2024
SHA: f2b7fb99

Base models

moussaKam/AraBART

Model card

From the Hugging Face model README

resultsara_5epoch

This model is a fine-tuned version of moussaKam/AraBART on an unknown dataset. It achieves the following results on the evaluation set:

Loss: 0.6393

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: 5e-05
train_batch_size: 16
eval_batch_size: 16
seed: 42
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
num_epochs: 8
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss
0.4457	0.1333	500	0.7199
0.8534	0.2667	1000	0.6676
0.9825	0.4	1500	0.6572
0.9602	0.5333	2000	0.6492
0.9685	0.6667	2500	0.6411
0.9596	0.8	3000	0.6374
0.9561	0.9333	3500	0.6312
0.8599	1.0667	4000	0.6394
0.7501	1.2	4500	0.6413
0.7739	1.3333	5000	0.6376
0.7791	1.4667	5500	0.6465
0.7911	1.6	6000	0.6414
0.7889	1.7333	6500	0.6393

Framework versions

Transformers 4.42.4
Pytorch 2.4.0+cu121
Datasets 2.21.0
Tokenizers 0.19.1

Type: mbart
License: apache-2.0
Created: Sep 2, 2024
Updated: Sep 2, 2024