MARBERT_with_categories

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

• Loss: 1.7872
• Precision: 0.0
• Recall: 0.0
• F1: 0.0
• Accuracy: 0.4724

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: 8
• eval_batch_size: 8
• seed: 42
• optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: linear
• num_epochs: 10

Training results

Training Loss	Epoch	Step	Validation Loss	Precision	Recall	F1	Accuracy
No log	1.0	5	1.3124	0.0	0.0	0.0	0.625
No log	2.0	10	1.2426	0.0	0.0	0.0	0.625
No log	3.0	15	1.0762	0.0	0.0	0.0	0.625
No log	4.0	20	1.0386	0.0	0.0	0.0	0.6389
No log	5.0	25	0.9635	0.0	0.0	0.0	0.6528
No log	6.0	30	0.9486	0.0	0.0	0.0	0.6944
No log	7.0	35	0.9383	0.0	0.0	0.0	0.6944
No log	8.0	40	0.9533	0.0	0.0	0.0	0.6528
No log	9.0	45	0.9997	0.0	0.0	0.0	0.6528
No log	10.0	50	1.0130	0.0	0.0	0.0	0.6528

Framework versions

• Transformers 4.48.1
• Pytorch 2.5.1+cu124
• Datasets 3.2.0
• Tokenizers 0.21.0