marbert-arabic-tweet-sentiment-80

This model is a fine-tuned version of UBC-NLP/MARBERTv2 on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.9767
• Accuracy: 0.7377
• F1: 0.7420

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: 16
• eval_batch_size: 16
• seed: 42
• gradient_accumulation_steps: 4
• total_train_batch_size: 64
• 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: 200
• num_epochs: 10
• label_smoothing_factor: 0.1

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	F1
No log	1.0	29	0.9311	0.7438	0.7485
No log	2.0	58	0.9298	0.7469	0.7529
No log	3.0	87	0.9378	0.7377	0.7452
No log	4.0	116	0.9382	0.7469	0.7523
No log	5.0	145	0.9365	0.75	0.7541
No log	6.0	174	0.9598	0.7438	0.7476
No log	7.0	203	0.9781	0.7438	0.7484
No log	8.0	232	0.9767	0.7377	0.7420

Framework versions

• Transformers 5.15.1
• Pytorch 2.11.0+cu128
• Datasets 4.0.0
• Tokenizers 0.22.2