metadata

library_name: transformers
language:
  - en
base_model: gokulsrinivasagan/bert_base_lda_20_v1_book
tags:
  - generated_from_trainer
datasets:
  - glue
metrics:
  - accuracy
model-index:
  - name: bert_base_lda_20_v1_book_rte
    results:
      - task:
          name: Text Classification
          type: text-classification
        dataset:
          name: GLUE RTE
          type: glue
          args: rte
        metrics:
          - name: Accuracy
            type: accuracy
            value: 0.5342960288808665

bert_base_lda_20_v1_book_rte

This model is a fine-tuned version of gokulsrinivasagan/bert_base_lda_20_v1_book on the GLUE RTE dataset. It achieves the following results on the evaluation set:

Loss: 0.6921
Accuracy: 0.5343

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
0.7001	1.0	10	0.6987	0.5018
0.6865	2.0	20	0.6934	0.5126
0.6669	3.0	30	0.6921	0.5343
0.6301	4.0	40	0.7334	0.5560
0.5188	5.0	50	0.9071	0.5415
0.4111	6.0	60	1.0801	0.5776
0.284	7.0	70	1.0945	0.5848
0.2243	8.0	80	1.2664	0.5668

Framework versions

Transformers 4.46.3
Pytorch 2.2.1+cu118
Datasets 2.17.0
Tokenizers 0.20.3