marbert-sarcasm-arabic – AI Model by roalalaoui | AlphaNeural AI

You can deploy this model and start earning money today!

roalalaoui/
marbert-sarcasm-arabic

like

0

text-classification

generated_from_trainer

UBC-NLP/MARBERTv2

text-embeddings-inference

endpoints_compatible

Views

No views yet

marbert-sarcasm-arabic

This model is a fine-tuned version of UBC-NLP/MARBERTv2 on the None dataset. It achieves the following results on the evaluation set:

Loss: 0.5310
F1 Weighted: 0.8485
F1 Macro: 0.7768
F1 Sarcastic: 0.6565
Precision Macro: 0.7579
Recall Macro: 0.8071
Accuracy: 0.8417

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: 1.5e-05
train_batch_size: 32
eval_batch_size: 64
seed: 42
optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: linear
lr_scheduler_warmup_steps: 288
num_epochs: 3
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	F1 Weighted	F1 Macro	F1 Sarcastic	Precision Macro	Recall Macro	Accuracy
0.4481	1.0	362	0.4203	0.8435	0.7731	0.6549	0.7518	0.8131	0.8346
0.3333	2.0	724	0.4389	0.8433	0.7737	0.6570	0.7519	0.8166	0.8339
0.2117	3.0	1086	0.5310	0.8485	0.7768	0.6565	0.7579	0.8071	0.8417

Framework versions

Transformers 5.0.0
Pytorch 2.10.0+cu128
Datasets 4.8.3
Tokenizers 0.22.2