gokuls's picture
End of training
61e4990
metadata
language:
  - en
tags:
  - generated_from_trainer
datasets:
  - glue
metrics:
  - accuracy
model-index:
  - name: hBERTv2_new_pretrain_48_emb_com_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: 0.5270758122743683

hBERTv2_new_pretrain_48_emb_com_rte

This model is a fine-tuned version of gokuls/bert_12_layer_model_v2_complete_training_new_emb_compress_48 on the GLUE RTE dataset. It achieves the following results on the evaluation set:

  • Loss: 0.6929
  • Accuracy: 0.5271

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: 4e-05
  • train_batch_size: 128
  • eval_batch_size: 128
  • 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

Training results

Training Loss Epoch Step Validation Loss Accuracy
0.7486 1.0 20 0.6929 0.5271
0.71 2.0 40 0.6940 0.4765
0.7079 3.0 60 0.7058 0.4765
0.6988 4.0 80 0.7413 0.5307
0.68 5.0 100 0.7054 0.5054
0.6481 6.0 120 0.7751 0.5090

Framework versions

  • Transformers 4.30.2
  • Pytorch 1.14.0a0+410ce96
  • Datasets 2.12.0
  • Tokenizers 0.13.3