deberta-v3-base_finetuned_bluegennx_run2.6

This model is a fine-tuned version of microsoft/deberta-v3-base on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.0968
• Overall Precision: 0.6921
• Overall Recall: 0.7279
• Overall F1: 0.7096
• Overall Accuracy: 0.9662
• Aadhar Card F1: 0.7499
• Age F1: 0.5816
• City F1: 0.7306
• Country F1: 0.6782
• Creditcardcvv F1: 0.7220
• Creditcardnumber F1: 0.7364
• Currency F1: 0.6681
• Currencyname F1: 0.0887
• Date F1: 0.6695
• Dateofbirth F1: 0.6437
• Email F1: 0.6486
• Expiry Date F1: 0.5623
• Organization F1: 0.7393
• Pan Card F1: 0.7191
• Person F1: 0.8088
• Phonenumber F1: 0.7218
• Secondary Address F1: 0.6801
• State F1: 0.7525
• Street F1: 0.8529
• Time F1: 0.7545
• Url F1: 0.5520
• Us Ssn F1: 0.9069

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: 36
• eval_batch_size: 8
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: cosine_with_restarts
• lr_scheduler_warmup_ratio: 0.2
• num_epochs: 3

Training results

Framework versions

• Transformers 4.38.2
• Pytorch 2.1.0+cu118
• Datasets 2.18.0
• Tokenizers 0.15.2