Hugging Face's logo

vesteinn
/
XLMR-ENIS-finetuned-cola

Text Classification Transformers PyTorch TensorBoard Safetensors
English Icelandic multilingual xlm-roberta generated_from_trainer Eval Results Inference Endpoints
Model card Files Metrics Community
5
XLMR-ENIS-finetuned-cola / README.md
vesteinn's picture
vesteinn
Librarian Bot: Update Hugging Face dataset ID (#5)
03aa640 verified
preview code
|
raw history blame contribute delete
No virus
2.03 kB
metadata
language:
  - en
  - is
  - multilingual
license: agpl-3.0
tags:
  - generated_from_trainer
datasets:
  - nyu-mll/glue
metrics:
  - matthews_correlation
base_model: vesteinn/XLMR-ENIS
model-index:
  - name: XLMR-ENIS-finetuned-cola
    results:
      - task:
          type: text-classification
          name: Text Classification
        dataset:
          name: glue
          type: glue
          args: cola
        metrics:
          - type: matthews_correlation
            value: 0.6306425398187112
            name: Matthews Correlation

XLMR-ENIS-finetuned-cola

This model is a fine-tuned version of vesteinn/XLMR-ENIS on the glue dataset. It achieves the following results on the evaluation set:

  • Loss: 0.7311
  • Matthews Correlation: 0.6306

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: 5

Training results

Training Loss Epoch Step Validation Loss Matthews Correlation
0.5216 1.0 535 0.5836 0.4855
0.3518 2.0 1070 0.4426 0.5962
0.2538 3.0 1605 0.5091 0.6110
0.1895 4.0 2140 0.6955 0.6136
0.1653 5.0 2675 0.7311 0.6306

Framework versions

  • Transformers 4.10.3
  • Pytorch 1.9.0+cu102
  • Datasets 1.12.1
  • Tokenizers 0.10.3