metadata

license: apache-2.0
base_model: distilroberta-base
tags:
  - generated_from_trainer
datasets:
  - conll2003
metrics:
  - precision
  - recall
  - f1
  - accuracy
model-index:
  - name: RoBERTa_conll_epoch_8
    results:
      - task:
          name: Token Classification
          type: token-classification
        dataset:
          name: conll2003
          type: conll2003
          config: conll2003
          split: validation
          args: conll2003
        metrics:
          - name: Precision
            type: precision
            value: 0.9463544261750539
          - name: Recall
            type: recall
            value: 0.9589363850555369
          - name: F1
            type: f1
            value: 0.9526038619075483
          - name: Accuracy
            type: accuracy
            value: 0.9888772974133964

RoBERTa_conll_epoch_8

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

Loss: 0.0813
Precision: 0.9464
Recall: 0.9589
F1: 0.9526
Accuracy: 0.9889

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: 8

Training results

Training Loss	Epoch	Step	Validation Loss	Precision	Recall	F1	Accuracy
0.0799	1.0	1756	0.0700	0.9133	0.9320	0.9225	0.9827
0.0449	2.0	3512	0.0661	0.9325	0.9440	0.9382	0.9865
0.0283	3.0	5268	0.0707	0.9275	0.9456	0.9365	0.9852
0.0203	4.0	7024	0.0622	0.9424	0.9586	0.9504	0.9882
0.0111	5.0	8780	0.0758	0.9382	0.9549	0.9465	0.9878
0.0067	6.0	10536	0.0761	0.9395	0.9546	0.9470	0.9880
0.0031	7.0	12292	0.0821	0.9391	0.9546	0.9468	0.9878
0.0021	8.0	14048	0.0813	0.9464	0.9589	0.9526	0.9889

Framework versions

Transformers 4.40.2
Pytorch 2.3.0+cu121
Datasets 2.19.1
Tokenizers 0.19.1