Hugging Face's logo

lobrien001
/
roberta-base-finetuned-ner

Token Classification
Transformers
TensorBoard
Safetensors
roberta
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
roberta-base-finetuned-ner / README.md
lobrien001's picture
lobrien001
Model save
05a93e9 verified
preview code
|
raw
history blame
7.32 kB
metadata
license: mit
base_model: roberta-base
tags:
  - generated_from_trainer
metrics:
  - precision
  - recall
  - f1
  - accuracy
model-index:
  - name: roberta-base-finetuned-ner
    results: []

roberta-base-finetuned-ner

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

  • Loss: 0.5055
  • Precision: 0.8737
  • Recall: 0.8677
  • F1: 0.8707
  • Accuracy: 0.8449

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: 4
  • eval_batch_size: 4
  • seed: 42
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • num_epochs: 12

Training results

Training Loss Epoch Step Validation Loss Precision Recall F1 Accuracy
No log 0.19 50 0.5675 0.8574 0.9049 0.8805 0.8574
No log 0.37 100 0.5571 0.8574 0.9049 0.8805 0.8574
No log 0.56 150 0.5541 0.8574 0.9049 0.8805 0.8574
No log 0.75 200 0.5682 0.8574 0.9049 0.8805 0.8574
No log 0.93 250 0.5845 0.8574 0.9049 0.8805 0.8574
No log 1.12 300 0.5533 0.8574 0.9049 0.8805 0.8574
No log 1.31 350 0.5940 0.8574 0.9049 0.8805 0.8574
No log 1.49 400 0.5553 0.8574 0.9049 0.8805 0.8574
No log 1.68 450 0.5661 0.8574 0.9049 0.8805 0.8574
0.6392 1.87 500 0.5435 0.8574 0.9049 0.8805 0.8574
0.6392 2.05 550 0.5300 0.8574 0.9049 0.8805 0.8574
0.6392 2.24 600 0.5522 0.8574 0.9049 0.8805 0.8574
0.6392 2.43 650 0.5155 0.8574 0.9049 0.8805 0.8574
0.6392 2.61 700 0.5037 0.8574 0.9049 0.8805 0.8574
0.6392 2.8 750 0.4923 0.8574 0.9049 0.8805 0.8574
0.6392 2.99 800 0.4897 0.8574 0.9049 0.8805 0.8574
0.6392 3.17 850 0.5021 0.8574 0.9049 0.8805 0.8574
0.6392 3.36 900 0.5122 0.8574 0.9049 0.8805 0.8574
0.6392 3.54 950 0.4987 0.8575 0.9004 0.8784 0.8560
0.5724 3.73 1000 0.4861 0.8587 0.8971 0.8775 0.8541
0.5724 3.92 1050 0.4788 0.8607 0.9019 0.8808 0.8580
0.5724 4.1 1100 0.4989 0.8634 0.8826 0.8729 0.8459
0.5724 4.29 1150 0.4760 0.8653 0.8976 0.8812 0.8572
0.5724 4.48 1200 0.4699 0.8659 0.8835 0.8746 0.8482
0.5724 4.66 1250 0.4865 0.8729 0.8822 0.8775 0.8519
0.5724 4.85 1300 0.4763 0.8626 0.9023 0.8820 0.8586
0.5724 5.04 1350 0.4676 0.8653 0.8941 0.8794 0.8564
0.5724 5.22 1400 0.4979 0.8672 0.8850 0.8760 0.8494
0.5724 5.41 1450 0.4749 0.8648 0.8965 0.8804 0.8566
0.5092 5.6 1500 0.5003 0.8686 0.8720 0.8703 0.8410
0.5092 5.78 1550 0.4635 0.8713 0.8872 0.8792 0.8547
0.5092 5.97 1600 0.4615 0.8653 0.8928 0.8788 0.8543
0.5092 6.16 1650 0.4785 0.8677 0.8937 0.8805 0.8556
0.5092 6.34 1700 0.4856 0.8728 0.8813 0.8771 0.8535
0.5092 6.53 1750 0.4681 0.8695 0.8917 0.8805 0.8574
0.5092 6.72 1800 0.4633 0.8683 0.8950 0.8814 0.8586
0.5092 6.9 1850 0.4887 0.8787 0.8655 0.8720 0.8432
0.5092 7.09 1900 0.4807 0.8706 0.8759 0.8733 0.8476
0.5092 7.28 1950 0.4613 0.8723 0.8935 0.8828 0.8607
0.4572 7.46 2000 0.4582 0.8729 0.8861 0.8794 0.8545
0.4572 7.65 2050 0.4784 0.8794 0.8681 0.8737 0.8476
0.4572 7.84 2100 0.4749 0.8710 0.8798 0.8754 0.8504
0.4572 8.02 2150 0.4755 0.8721 0.8828 0.8774 0.8531
0.4572 8.21 2200 0.4875 0.8736 0.8668 0.8702 0.8463
0.4572 8.4 2250 0.4763 0.8807 0.8664 0.8735 0.8480
0.4572 8.58 2300 0.4795 0.8745 0.8644 0.8694 0.8445
0.4572 8.77 2350 0.4822 0.8739 0.8616 0.8677 0.8385
0.4572 8.96 2400 0.4824 0.8761 0.8774 0.8768 0.8510
0.4572 9.14 2450 0.4818 0.8748 0.8608 0.8677 0.8400
0.4061 9.33 2500 0.4814 0.8795 0.8712 0.8753 0.8488
0.4061 9.51 2550 0.4846 0.8754 0.8796 0.8775 0.8510
0.4061 9.7 2600 0.5112 0.8758 0.8718 0.8738 0.8461
0.4061 9.89 2650 0.5002 0.8689 0.8701 0.8695 0.8461
0.4061 10.07 2700 0.5163 0.8769 0.8605 0.8686 0.8391
0.4061 10.26 2750 0.4947 0.8733 0.8774 0.8754 0.8510
0.4061 10.45 2800 0.4895 0.8795 0.8850 0.8822 0.8599
0.4061 10.63 2850 0.4984 0.8737 0.8705 0.8721 0.8457
0.4061 10.82 2900 0.4952 0.8733 0.8779 0.8756 0.8521
0.4061 11.01 2950 0.5012 0.8720 0.8644 0.8682 0.8422
0.3677 11.19 3000 0.4994 0.8717 0.8751 0.8734 0.8486
0.3677 11.38 3050 0.5002 0.875 0.8777 0.8763 0.8529
0.3677 11.57 3100 0.5039 0.8724 0.8735 0.8730 0.8490
0.3677 11.75 3150 0.5094 0.8729 0.8642 0.8686 0.8416
0.3677 11.94 3200 0.5059 0.8731 0.8673 0.8702 0.8443

Framework versions

  • Transformers 4.36.2
  • Pytorch 2.2.1+cu121
  • Datasets 2.19.0
  • Tokenizers 0.15.2