xlm-bid / README.md
bidkhori's picture
update model card README.md
2f90578
metadata
license: mit
tags:
  - generated_from_trainer
metrics:
  - f1
model-index:
  - name: xlm-bid
    results: []

xlm-bid

This model is a fine-tuned version of xlm-roberta-base on the None dataset. It achieves the following results on the evaluation set:

  • Loss: 0.2699
  • F1: 0.8780

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: 5e-05
  • train_batch_size: 4
  • eval_batch_size: 4
  • seed: 42
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • num_epochs: 10

Training results

Training Loss Epoch Step Validation Loss F1
1.7339 1.0 23 1.2478 0.0
1.0626 2.0 46 0.6075 0.5294
0.5754 3.0 69 0.3023 0.8095
0.3271 4.0 92 0.3282 0.8095
0.265 5.0 115 0.2951 0.8571
0.1909 6.0 138 0.3189 0.7907
0.1304 7.0 161 0.3330 0.8095
0.1128 8.0 184 0.3141 0.8095
0.0808 9.0 207 0.2712 0.9268
0.0803 10.0 230 0.2699 0.8780

Framework versions

  • Transformers 4.30.2
  • Pytorch 2.0.1+cu118
  • Datasets 2.13.1
  • Tokenizers 0.13.3