README.md

metadata

library_name: transformers
language:
  - en
base_model: gokulsrinivasagan/bert_base_lda_5_v1
tags:
  - generated_from_trainer
datasets:
  - glue
metrics:
  - accuracy
model-index:
  - name: bert_base_lda_5_v1_rte
    results:
      - task:
          name: Text Classification
          type: text-classification
        dataset:
          name: GLUE RTE
          type: glue
          args: rte
        metrics:
          - name: Accuracy
            type: accuracy
            value: 0.5451263537906137

bert_base_lda_5_v1_rte

This model is a fine-tuned version of gokulsrinivasagan/bert_base_lda_5_v1 on the GLUE RTE dataset. It achieves the following results on the evaluation set:

• Loss: 0.6868
• Accuracy: 0.5451

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
0.7078	1.0	10	0.6900	0.5379
0.6627	2.0	20	0.6868	0.5451
0.5816	3.0	30	0.7390	0.5415
0.4535	4.0	40	0.8692	0.5451
0.3048	5.0	50	1.0894	0.5235
0.1715	6.0	60	1.3816	0.5126
0.0964	7.0	70	1.6369	0.5451

Framework versions

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