metadata

library_name: transformers
language:
  - en
license: apache-2.0
base_model: google/bert_uncased_L-4_H-128_A-2
tags:
  - generated_from_trainer
datasets:
  - glue
metrics:
  - accuracy
model-index:
  - name: bert_uncased_L-4_H-128_A-2_qnli
    results:
      - task:
          name: Text Classification
          type: text-classification
        dataset:
          name: GLUE QNLI
          type: glue
          args: qnli
        metrics:
          - name: Accuracy
            type: accuracy
            value: 0.8121911037891268

bert_uncased_L-4_H-128_A-2_qnli

This model is a fine-tuned version of google/bert_uncased_L-4_H-128_A-2 on the GLUE QNLI dataset. It achieves the following results on the evaluation set:

Loss: 0.4085
Accuracy: 0.8122

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
0.5299	1.0	410	0.4915	0.7730
0.4658	2.0	820	0.4281	0.8040
0.4407	3.0	1230	0.4085	0.8122
0.4184	4.0	1640	0.4172	0.8115
0.3983	5.0	2050	0.4166	0.8104
0.3799	6.0	2460	0.4329	0.8063
0.3614	7.0	2870	0.4182	0.8151
0.3438	8.0	3280	0.4378	0.8089

Framework versions

Transformers 4.46.3
Pytorch 2.2.1+cu118
Datasets 2.17.0
Tokenizers 0.20.3