gokuls's picture
End of training
a071a1c
metadata
base_model: gokuls/HBERTv1_L12_H768_A12_ffn_1
tags:
  - generated_from_trainer
datasets:
  - gokuls/wiki_book_corpus_complete_processed_bert_dataset
metrics:
  - accuracy
model-index:
  - name: HBERTv1_48_L12_H768_A12_ffn_1_KD
    results:
      - task:
          name: Masked Language Modeling
          type: fill-mask
        dataset:
          name: gokuls/wiki_book_corpus_complete_processed_bert_dataset
          type: gokuls/wiki_book_corpus_complete_processed_bert_dataset
        metrics:
          - name: Accuracy
            type: accuracy
            value: 0.4616582527830643

HBERTv1_48_L12_H768_A12_ffn_1_KD

This model is a fine-tuned version of gokuls/HBERTv1_L12_H768_A12_ffn_1 on the gokuls/wiki_book_corpus_complete_processed_bert_dataset dataset. It achieves the following results on the evaluation set:

  • Loss: 132.3779
  • Accuracy: 0.4617

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: 1e-05
  • train_batch_size: 32
  • eval_batch_size: 32
  • seed: 10
  • distributed_type: multi-GPU
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • lr_scheduler_warmup_steps: 10000
  • num_epochs: 100

Training results

Framework versions

  • Transformers 4.35.2
  • Pytorch 1.14.0a0+410ce96
  • Datasets 2.15.0
  • Tokenizers 0.15.0