Dan Semin
update model card README.md
7952663
metadata
license: mit
tags:
  - text-classification
  - generated_from_trainer
datasets:
  - paws-x
metrics:
  - accuracy
model-index:
  - name: paws_x_xlm_r_only_ja
    results:
      - task:
          name: Text Classification
          type: text-classification
        dataset:
          name: paws-x
          type: paws-x
          config: ja
          split: train
          args: ja
        metrics:
          - name: Accuracy
            type: accuracy
            value: 0.8395

paws_x_xlm_r_only_ja

This model is a fine-tuned version of xlm-roberta-base on the paws-x dataset. It achieves the following results on the evaluation set:

  • Loss: 0.6163
  • Accuracy: 0.8395

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: 128
  • eval_batch_size: 128
  • seed: 42
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • lr_scheduler_warmup_steps: 100
  • num_epochs: 10

Training results

Training Loss Epoch Step Validation Loss Accuracy
0.515 1.0 386 0.4769 0.794
0.3088 2.0 772 0.4256 0.8385
0.2416 3.0 1158 0.4412 0.8265
0.204 4.0 1544 0.4471 0.838
0.1689 5.0 1930 0.4369 0.8405
0.1424 6.0 2316 0.5206 0.838
0.121 7.0 2702 0.5247 0.8425
0.1061 8.0 3088 0.5708 0.843
0.092 9.0 3474 0.5840 0.838
0.0846 10.0 3860 0.6163 0.8395

Framework versions

  • Transformers 4.24.0
  • Pytorch 1.13.0
  • Datasets 2.6.1
  • Tokenizers 0.13.1