bert-fa-zwnj-base-finetuned-NER

This model is a fine-tuned version of HooshvareLab/bert-fa-zwnj-base on the None dataset. It achieves the following results on the evaluation set:

• eval_loss: 0.0001
• eval_Accuracy: 1.0000
• eval_Precision (macro): 0.9998
• eval_Recall (macro): 0.9999
• eval_F1 (macro): 0.9998
• eval_Precision (micro): 1.0000
• eval_Recall (micro): 1.0000
• eval_F1 (micro): 1.0000
• eval_runtime: 54.9025
• eval_samples_per_second: 139.902
• eval_steps_per_second: 8.761
• epoch: 16.02
• step: 10272

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: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 20

Framework versions

• Transformers 4.35.2
• Pytorch 2.1.0+cu121
• Datasets 2.16.1
• Tokenizers 0.15.1