metadata

license: mit
tags:
  - generated_from_trainer
datasets:
  - lener_br
metrics:
  - precision
  - recall
  - f1
  - accuracy
model-index:
  - name: xlm-roberta-large-finetuned-lener-br
    results:
      - task:
          name: Token Classification
          type: token-classification
        dataset:
          name: lener_br
          type: lener_br
          config: lener_br
          split: train
          args: lener_br
        metrics:
          - name: Precision
            type: precision
            value: 0.8545767716535433
          - name: Recall
            type: recall
            value: 0.8976479710519514
          - name: F1
            type: f1
            value: 0.8755830076893987
          - name: Accuracy
            type: accuracy
            value: 0.979126510974644
      - task:
          type: token-classification
          name: Token Classification
        dataset:
          name: lener_br
          type: lener_br
          config: lener_br
          split: test
        metrics:
          - name: Accuracy
            type: accuracy
            value: 0.9842606502473917
            verified: true
          - name: Precision
            type: precision
            value: 0.9880888491353608
            verified: true
          - name: Recall
            type: recall
            value: 0.9863977974551678
            verified: true
          - name: F1
            type: f1
            value: 0.9872425991435487
            verified: true
          - name: loss
            type: loss
            value: 0.12697908282279968
            verified: true
      - task:
          type: token-classification
          name: Token Classification
        dataset:
          name: lener_br
          type: lener_br
          config: lener_br
          split: validation
        metrics:
          - name: Accuracy
            type: accuracy
            value: 0.979126510974644
            verified: true
          - name: Precision
            type: precision
            value: 0.9846948786709399
            verified: true
          - name: Recall
            type: recall
            value: 0.9839386958155646
            verified: true
          - name: F1
            type: f1
            value: 0.9843166420124387
            verified: true
          - name: loss
            type: loss
            value: 0.17586557567119598
            verified: true
      - task:
          type: token-classification
          name: Token Classification
        dataset:
          name: lener_br
          type: lener_br
          config: lener_br
          split: train
        metrics:
          - name: Accuracy
            type: accuracy
            value: 0.9986508230532317
            verified: true
          - name: Precision
            type: precision
            value: 0.9980332928982356
            verified: true
          - name: Recall
            type: recall
            value: 0.998726011303645
            verified: true
          - name: F1
            type: f1
            value: 0.998379531941543
            verified: true
          - name: loss
            type: loss
            value: 0.002737082075327635
            verified: true

xlm-roberta-large-finetuned-lener-br

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

Loss: nan
Precision: 0.8546
Recall: 0.8976
F1: 0.8756
Accuracy: 0.9791

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: 2
eval_batch_size: 2
seed: 42
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
num_epochs: 15

Training results

Training Loss	Epoch	Step	Validation Loss	Precision	Recall	F1	Accuracy
0.0836	1.0	3914	nan	0.5735	0.8348	0.6799	0.9526
0.0664	2.0	7828	nan	0.8153	0.8315	0.8233	0.9658
0.0505	3.0	11742	nan	0.6885	0.9147	0.7857	0.9644
0.1165	4.0	15656	nan	0.7572	0.8067	0.7811	0.9641
0.0206	5.0	19570	nan	0.8678	0.8770	0.8723	0.9774
0.02	6.0	23484	nan	0.7285	0.8907	0.8015	0.9669
0.0248	7.0	27398	nan	0.8717	0.9095	0.8902	0.9793
0.0223	8.0	31312	nan	0.8407	0.8801	0.8600	0.9766
0.0084	9.0	35226	nan	0.8354	0.8684	0.8516	0.9705
0.0067	10.0	39140	nan	0.8312	0.9062	0.8671	0.9753
0.006	11.0	43054	nan	0.8866	0.8953	0.8909	0.9784
0.0058	12.0	46968	nan	0.8961	0.8987	0.8974	0.9807
0.0062	13.0	50882	nan	0.8360	0.8785	0.8567	0.9783
0.0053	14.0	54796	nan	0.8327	0.8749	0.8533	0.9782
0.003	15.0	58710	nan	0.8546	0.8976	0.8756	0.9791

Framework versions

Transformers 4.23.1
Pytorch 1.12.1+cu113
Datasets 2.6.1
Tokenizers 0.13.1