xnli_m_bert_only_hi / README.md
Dan Semin
update model card README.md
8ada165
metadata
license: apache-2.0
tags:
  - text-classification
  - generated_from_trainer
datasets:
  - xnli
metrics:
  - accuracy
model-index:
  - name: xnli_m_bert_only_hi
    results:
      - task:
          name: Text Classification
          type: text-classification
        dataset:
          name: xnli
          type: xnli
          config: hi
          split: train
          args: hi
        metrics:
          - name: Accuracy
            type: accuracy
            value: 0.6457831325301204

xnli_m_bert_only_hi

This model is a fine-tuned version of bert-base-multilingual-cased on the xnli dataset. It achieves the following results on the evaluation set:

  • Loss: 1.5129
  • Accuracy: 0.6458

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: 128
  • eval_batch_size: 128
  • 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 Accuracy
0.7554 1.0 3068 0.8254 0.6454
0.6896 2.0 6136 0.7786 0.6687
0.6214 3.0 9204 0.7973 0.6639
0.552 4.0 12272 0.7985 0.6751
0.4764 5.0 15340 0.9175 0.6759
0.4012 6.0 18408 1.0097 0.6558
0.329 7.0 21476 1.0889 0.6590
0.2646 8.0 24544 1.2490 0.6582
0.2157 9.0 27612 1.4154 0.6466
0.1761 10.0 30680 1.5129 0.6458

Framework versions

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