metadata

license: mit
base_model: filevich/robertita-cased
tags:
  - generated_from_trainer
datasets:
  - fact2020
metrics:
  - precision
  - recall
  - f1
  - accuracy
model-index:
  - name: robertita-cased-finetuned-fact
    results:
      - task:
          name: Token Classification
          type: token-classification
        dataset:
          name: fact2020
          type: fact2020
          config: fact2020
          split: validation
          args: fact2020
        metrics:
          - name: Precision
            type: precision
            value: 0.9958259428424656
          - name: Recall
            type: recall
            value: 0.990818034441507
          - name: F1
            type: f1
            value: 0.9915358119908528
          - name: Accuracy
            type: accuracy
            value: 0.990818034441507
language:
  - es
pipeline_tag: token-classification
widget:
  - text: Guatemala sufre y llora a sus fallecidos bajo un manto negro de ceniza.
  - text: La estrategia se ejecuta, no se cuenta.

robertita-cased-finetuned-fact

This model is a fine-tuned version of filevich/robertita-cased on the fact2020 dataset. It achieves the following results on the evaluation set:

Loss: 0.0402
Precision: 0.9958
Recall: 0.9908
F1: 0.9915
Accuracy: 0.9908

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: 6e-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: 3

Training results

Training Loss	Epoch	Step	Validation Loss	Precision	Recall	F1	Accuracy
No log	1.0	116	0.0372	0.9947	0.9889	0.9895	0.9889
No log	2.0	232	0.0388	0.9961	0.9903	0.9913	0.9903
No log	3.0	348	0.0402	0.9958	0.9908	0.9915	0.9908

Framework versions

Transformers 4.31.0
Pytorch 2.0.1+cu117
Datasets 2.14.4
Tokenizers 0.13.3