metadata

license: mit
base_model: FacebookAI/xlm-roberta-large
tags:
  - generated_from_trainer
datasets:
  - cnec
metrics:
  - precision
  - recall
  - f1
  - accuracy
model-index:
  - name: CNEC_xlm-roberta-large
    results:
      - task:
          name: Token Classification
          type: token-classification
        dataset:
          name: cnec
          type: cnec
          config: default
          split: validation
          args: default
        metrics:
          - name: Precision
            type: precision
            value: 0.8556554661618552
          - name: Recall
            type: recall
            value: 0.8972704714640198
          - name: F1
            type: f1
            value: 0.8759689922480619
          - name: Accuracy
            type: accuracy
            value: 0.9759953161592506

CNEC_xlm-roberta-large

This model is a fine-tuned version of FacebookAI/xlm-roberta-large on the cnec dataset. It achieves the following results on the evaluation set:

Loss: 0.1541
Precision: 0.8557
Recall: 0.8973
F1: 0.8760
Accuracy: 0.9760

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: 16
eval_batch_size: 16
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
0.2518	1.12	500	0.1312	0.7219	0.8427	0.7777	0.9649
0.0996	2.24	1000	0.1222	0.8003	0.8511	0.8249	0.9677
0.0652	3.36	1500	0.1259	0.8137	0.8734	0.8425	0.9730
0.0421	4.47	2000	0.1293	0.8306	0.8859	0.8573	0.9739
0.0277	5.59	2500	0.1519	0.8320	0.8799	0.8553	0.9742
0.0169	6.71	3000	0.1342	0.8516	0.8968	0.8736	0.9756
0.0116	7.83	3500	0.1496	0.8540	0.8973	0.8751	0.9760
0.0065	8.95	4000	0.1541	0.8557	0.8973	0.8760	0.9760

Framework versions

Transformers 4.36.2
Pytorch 2.1.2+cu121
Datasets 2.16.1
Tokenizers 0.15.0