README.md

metadata

tags:
  - generated_from_trainer
datasets:
  - xnli
metrics:
  - accuracy
model-index:
  - name: spanish-TinyBERT-betito-finetuned-xnli-es
    results:
      - task:
          name: Text Classification
          type: text-classification
        dataset:
          name: xnli
          type: xnli
          args: es
        metrics:
          - name: Accuracy
            type: accuracy
            value: 0.7475049900199601

spanish-TinyBERT-betito-finetuned-xnli-es

This model is a fine-tuned version of mrm8488/spanish-TinyBERT-betito on the xnli dataset. It achieves the following results on the evaluation set:

• Loss: 0.7104
• Accuracy: 0.7475

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: 2.50838112218154e-05
• train_batch_size: 8
• eval_batch_size: 64
• seed: 13
• 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	Accuracy
0.7191	1.0	49399	0.6829	0.7112
0.6323	2.0	98798	0.6527	0.7305
0.5727	3.0	148197	0.6531	0.7465
0.4964	4.0	197596	0.7079	0.7427
0.4929	5.0	246995	0.7104	0.7475

Framework versions

• Transformers 4.17.0
• Pytorch 1.10.0+cu111
• Datasets 1.18.4
• Tokenizers 0.11.6