robertou2's picture
Update README.md
cff8dd4
|
raw
history blame
2.75 kB
metadata
license: apache-2.0
tags:
  - null
datasets:
  - EXIST Dataset
metrics:
  - accuracy
model-index:
  - name: twitter_sexismo-finetuned-exist2021
    results:
      - task:
          name: Text Classification
          type: text-classification
        dataset:
          name: EXIST Dataset
          type: EXIST Dataset
          args: es
        metrics:
          - name: Accuracy
            type: accuracy
            value: 0.79

twitter_sexismo-finetuned-exist2021

This model is a fine-tuned version of pysentimiento/robertuito-hate-speech on the EXIST dataset. It achieves the following results on the evaluation set:

  • Loss: 0.40
  • Accuracy: 0.79

Model description

Modelo para el Hackaton de Somos NLP para detección de sexismo en twitts en español

Intended uses & limitations

More information needed

Training and evaluation data

More information needed

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

  • my_learning_rate = 2E-6
  • my_adam_epsilon = 1E-8
  • my_number_of_epochs = 15
  • my_warmup = 3
  • my_mini_batch_size = 32
  • optimizer: AdamW with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • num_epochs: 15

Training results

======== Epoch 9 / 15 ======== Training... Batch 50 of 143. Elapsed: 0:00:48. Batch 100 of 143. Elapsed: 0:01:37.

Average training loss: 0.43 Training epoch took: 0:02:18

======== Epoch 10 / 15 ======== Training... Batch 50 of 143. Elapsed: 0:00:48. Batch 100 of 143. Elapsed: 0:01:37.

Average training loss: 0.42 Training epoch took: 0:02:18

======== Epoch 11 / 15 ======== Training... Batch 50 of 143. Elapsed: 0:00:48. Batch 100 of 143. Elapsed: 0:01:37.

Average training loss: 0.42 Training epoch took: 0:02:18

======== Epoch 12 / 15 ======== Training... Batch 50 of 143. Elapsed: 0:00:48. Batch 100 of 143. Elapsed: 0:01:37.

Average training loss: 0.41 Training epoch took: 0:02:18

======== Epoch 13 / 15 ======== Training... Batch 50 of 143. Elapsed: 0:00:48. Batch 100 of 143. Elapsed: 0:01:36.

Average training loss: 0.40 Training epoch took: 0:02:18

======== Epoch 14 / 15 ======== Training... Batch 50 of 143. Elapsed: 0:00:48. Batch 100 of 143. Elapsed: 0:01:37.

Average training loss: 0.40 Training epoch took: 0:02:18

======== Epoch 15 / 15 ======== Training... Batch 50 of 143. Elapsed: 0:00:48. Batch 100 of 143. Elapsed: 0:01:36.

Average training loss: 0.40 Training epoch took: 0:02:18

Framework versions

  • Transformers 4.17.0
  • Pytorch 1.10.0+cu111
  • Tokenizers 0.11.6