metadata

license: cc-by-nc-sa-4.0
base_model: ufal/robeczech-base
tags:
  - generated_from_trainer
datasets:
  - cnec
metrics:
  - precision
  - recall
  - f1
  - accuracy
model-index:
  - name: CNEC_1_1_robeczech-base
    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: 0.8354960234407702
          - name: Recall
            type: recall
            value: 0.8812362030905078
          - name: F1
            type: f1
            value: 0.8577567683712936
          - name: Accuracy
            type: accuracy
            value: 0.9450064850843061

CNEC_1_1_robeczech-base

This model is a fine-tuned version of ufal/robeczech-base on the cnec dataset. It achieves the following results on the evaluation set:

Loss: 0.2816
Precision: 0.8355
Recall: 0.8812
F1: 0.8578
Accuracy: 0.9450

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: 32
eval_batch_size: 32
seed: 42
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
num_epochs: 80

Training results

Training Loss	Epoch	Step	Validation Loss	Precision	Recall	F1	Accuracy
0.7852	10.2	1500	0.6287	0.3577	0.2375	0.2855	0.8413
0.3806	20.41	3000	0.3455	0.7275	0.7779	0.7519	0.9240
0.2384	30.61	4500	0.2764	0.8139	0.8552	0.8340	0.9383
0.1722	40.82	6000	0.2640	0.8361	0.8693	0.8524	0.9450
0.1357	51.02	7500	0.2666	0.8362	0.8702	0.8529	0.9454
0.1115	61.22	9000	0.2697	0.8423	0.8751	0.8584	0.9457
0.098	71.43	10500	0.2816	0.8355	0.8812	0.8578	0.9450

Framework versions

Transformers 4.36.2
Pytorch 2.1.2+cu121
Datasets 2.16.1
Tokenizers 0.15.0