metadata

library_name: transformers
language:
  - en
license: apache-2.0
base_model: google/bert_uncased_L-4_H-256_A-4
tags:
  - generated_from_trainer
datasets:
  - glue
metrics:
  - accuracy
model-index:
  - name: bert_uncased_L-4_H-256_A-4_mnli
    results:
      - task:
          name: Text Classification
          type: text-classification
        dataset:
          name: GLUE MNLI
          type: glue
          args: mnli
        metrics:
          - name: Accuracy
            type: accuracy
            value: 0.7651545972335232

bert_uncased_L-4_H-256_A-4_mnli

This model is a fine-tuned version of google/bert_uncased_L-4_H-256_A-4 on the GLUE MNLI dataset. It achieves the following results on the evaluation set:

Loss: 0.5852
Accuracy: 0.7652

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
0.7878	1.0	1534	0.7087	0.7007
0.6683	2.0	3068	0.6437	0.7296
0.6112	3.0	4602	0.6204	0.7465
0.5683	4.0	6136	0.6099	0.7553
0.532	5.0	7670	0.6147	0.7572
0.4997	6.0	9204	0.6381	0.7552
0.4707	7.0	10738	0.6196	0.7588
0.4436	8.0	12272	0.6404	0.7589
0.4187	9.0	13806	0.6584	0.7608

Framework versions

Transformers 4.46.3
Pytorch 2.2.1+cu118
Datasets 2.17.0
Tokenizers 0.20.3