Hugging Face's logo

ICT2214Team7
/
RoBERTa_conll_epoch_10

Token Classification
Transformers
TensorBoard
Safetensors
roberta
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Metrics Community
Edit model card

RoBERTa_conll_epoch_10

This model is a fine-tuned version of distilroberta-base on the conll2003 dataset. It achieves the following results on the evaluation set:

  • Loss: 0.0906
  • Precision: 0.9443
  • Recall: 0.9559
  • F1: 0.9501
  • Accuracy: 0.9882

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: 8
  • eval_batch_size: 8
  • seed: 42
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • num_epochs: 10

Training results

Training Loss Epoch Step Validation Loss Precision Recall F1 Accuracy
0.0839 1.0 1756 0.0705 0.9055 0.9303 0.9177 0.9827
0.0454 2.0 3512 0.0690 0.9257 0.9431 0.9343 0.9853
0.0272 3.0 5268 0.0590 0.9310 0.9495 0.9402 0.9865
0.0183 4.0 7024 0.0803 0.9324 0.9515 0.9419 0.9862
0.0129 5.0 8780 0.0747 0.9433 0.9517 0.9475 0.9872
0.0079 6.0 10536 0.0792 0.9359 0.9534 0.9446 0.9874
0.0055 7.0 12292 0.0785 0.9457 0.9549 0.9503 0.9879
0.003 8.0 14048 0.0881 0.9438 0.9561 0.9499 0.9879
0.001 9.0 15804 0.0875 0.9448 0.9562 0.9505 0.9879
0.0008 10.0 17560 0.0906 0.9443 0.9559 0.9501 0.9882

Framework versions

  • Transformers 4.40.2
  • Pytorch 2.3.0+cu121
  • Datasets 2.19.1
  • Tokenizers 0.19.1
Downloads last month
10
Safetensors
Model size
81.5M params
Tensor type
F32
·
Inference Examples
Token Classification
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social visibility and check back later, or deploy to Inference Endpoints (dedicated) instead.

Model tree for ICT2214Team7/RoBERTa_conll_epoch_10

Base model

distilbert/distilroberta-base
Finetuned
(522)
this model

Dataset used to train ICT2214Team7/RoBERTa_conll_epoch_10

Evaluation results

View on Papers With Code