hBERTv1_rte / README.md
gokuls's picture
End of training
4fa88f7
metadata
language:
  - en
tags:
  - generated_from_trainer
datasets:
  - glue
metrics:
  - accuracy
model-index:
  - name: hBERTv1_rte
    results:
      - task:
          name: Text Classification
          type: text-classification
        dataset:
          name: GLUE RTE
          type: glue
          config: rte
          split: validation
          args: rte
        metrics:
          - name: Accuracy
            type: accuracy
            value: 0.5451263537906137

hBERTv1_rte

This model is a fine-tuned version of gokuls/bert_12_layer_model_v1 on the GLUE RTE dataset. It achieves the following results on the evaluation set:

  • Loss: 0.6896
  • Accuracy: 0.5451

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: 256
  • eval_batch_size: 256
  • seed: 10
  • distributed_type: multi-GPU
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • num_epochs: 50
  • mixed_precision_training: Native AMP

Training results

Training Loss Epoch Step Validation Loss Accuracy
0.7247 1.0 10 0.6896 0.5451
0.7046 2.0 20 0.7014 0.4729
0.6934 3.0 30 0.6983 0.4729
0.6846 4.0 40 0.7092 0.5126
0.6853 5.0 50 0.7140 0.5126
0.6152 6.0 60 0.8230 0.4910

Framework versions

  • Transformers 4.26.1
  • Pytorch 1.14.0a0+410ce96
  • Datasets 2.10.1
  • Tokenizers 0.13.2