gokulsrinivasagan's picture
End of training
f2ea3fe verified
metadata
library_name: transformers
language:
  - en
license: apache-2.0
base_model: google/bert_uncased_L-2_H-128_A-2
tags:
  - generated_from_trainer
datasets:
  - glue
metrics:
  - accuracy
model-index:
  - name: bert_uncased_L-2_H-128_A-2_mnli
    results:
      - task:
          name: Text Classification
          type: text-classification
        dataset:
          name: GLUE MNLI
          type: glue
          args: mnli
        metrics:
          - name: Accuracy
            type: accuracy
            value: 0.7112489829129374

bert_uncased_L-2_H-128_A-2_mnli

This model is a fine-tuned version of google/bert_uncased_L-2_H-128_A-2 on the GLUE MNLI dataset. It achieves the following results on the evaluation set:

  • Loss: 0.6901
  • Accuracy: 0.7112

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
  • optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
  • lr_scheduler_type: linear
  • num_epochs: 50

Training results

Training Loss Epoch Step Validation Loss Accuracy
0.9155 1.0 1534 0.8197 0.6342
0.8189 2.0 3068 0.7689 0.6626
0.7747 3.0 4602 0.7417 0.6760
0.7449 4.0 6136 0.7285 0.6852
0.7198 5.0 7670 0.7111 0.6934
0.6996 6.0 9204 0.7118 0.6977
0.6812 7.0 10738 0.7005 0.7030
0.6649 8.0 12272 0.6981 0.7043
0.6491 9.0 13806 0.7057 0.7036
0.6358 10.0 15340 0.6983 0.7077
0.6224 11.0 16874 0.6966 0.7064
0.6109 12.0 18408 0.7001 0.7145
0.5994 13.0 19942 0.7014 0.7113
0.5872 14.0 21476 0.7061 0.7084
0.5779 15.0 23010 0.7054 0.7168
0.5681 16.0 24544 0.7059 0.7147

Framework versions

  • Transformers 4.46.3
  • Pytorch 2.2.1+cu118
  • Datasets 2.17.0
  • Tokenizers 0.20.3