README.md

metadata

library_name: transformers
language:
  - en
base_model: gokulsrinivasagan/bert_base_lda
tags:
  - generated_from_trainer
datasets:
  - glue
metrics:
  - accuracy
model-index:
  - name: bert_base_lda_mnli
    results:
      - task:
          name: Text Classification
          type: text-classification
        dataset:
          name: GLUE MNLI
          type: glue
          args: mnli
        metrics:
          - name: Accuracy
            type: accuracy
            value: 0.3295362082994304

bert_base_lda_mnli

This model is a fine-tuned version of gokulsrinivasagan/bert_base_lda on the GLUE MNLI dataset. It achieves the following results on the evaluation set:

• Loss: 1.0962
• Accuracy: 0.3295

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: 0.001
• 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
1.1008	1.0	1534	1.0993	0.3274
1.0986	2.0	3068	1.0962	0.3274
1.0987	3.0	4602	1.0989	0.3274
1.0985	4.0	6136	1.1016	0.3182
1.0985	5.0	7670	1.0989	0.3545
1.0988	6.0	9204	1.0989	0.3545
1.0985	7.0	10738	1.0968	0.3182

Framework versions

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