bert-base-uncased-finetuned-ner-prostata

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

• Loss: 2.2689
• Precision: 0.3846
• Recall: 0.0472
• F1: 0.0840
• Accuracy: 0.7077

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: 8
• eval_batch_size: 8
• seed: 42
• optimizer: Use OptimizerNames.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	1	3.1322	0.0653	0.1584	0.0925	0.1424
No log	2.0	2	2.7959	0.1975	0.1584	0.1758	0.5232
No log	3.0	3	2.5120	0.3721	0.1584	0.2222	0.5480
No log	4.0	4	2.2741	0.6957	0.1584	0.2581	0.5356
No log	5.0	5	2.0898	0.8	0.1584	0.2645	0.5387
No log	6.0	6	1.9530	0.8421	0.1584	0.2667	0.5418
No log	7.0	7	1.8564	0.7619	0.1584	0.2623	0.5511
No log	8.0	8	1.7930	0.5484	0.1683	0.2576	0.5851
No log	9.0	9	1.7545	0.4872	0.1881	0.2714	0.6161
No log	10.0	10	1.7358	0.6341	0.2574	0.3662	0.6440

Framework versions

• Transformers 4.52.2
• Pytorch 2.6.0+cu124
• Datasets 3.6.0
• Tokenizers 0.21.1