roberta-fa-zwnj-base-finetuned-2top

This model is a fine-tuned version of HooshvareLab/roberta-fa-zwnj-base on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 1.8134
• {'exact_match': 64.5, 'f1': 69.33573305263705}

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: 2e-05
• train_batch_size: 16
• eval_batch_size: 16
• 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
• num_epochs: 3
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss
0.8828	1.0	2780	1.7096
0.5412	2.0	5560	1.6460
0.3459	3.0	8340	1.8134

Framework versions

• Transformers 5.0.0
• Pytorch 2.11.0+cu128
• Datasets 4.0.0
• Tokenizers 0.22.2