metadata

library_name: transformers
language:
  - en
base_model: gokulsrinivasagan/bert_base_lda_5_v1_book
tags:
  - generated_from_trainer
datasets:
  - glue
metrics:
  - accuracy
  - f1
model-index:
  - name: bert_base_lda_5_v1_book_mrpc
    results:
      - task:
          name: Text Classification
          type: text-classification
        dataset:
          name: GLUE MRPC
          type: glue
          args: mrpc
        metrics:
          - name: Accuracy
            type: accuracy
            value: 0.7181372549019608
          - name: F1
            type: f1
            value: 0.8130081300813008

bert_base_lda_5_v1_book_mrpc

This model is a fine-tuned version of gokulsrinivasagan/bert_base_lda_5_v1_book on the GLUE MRPC dataset. It achieves the following results on the evaluation set:

Loss: 0.5504
Accuracy: 0.7181
F1: 0.8130
Combined Score: 0.7656

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	F1	Combined Score
0.6274	1.0	15	0.6026	0.6765	0.7905	0.7335
0.5872	2.0	30	0.5821	0.6985	0.8178	0.7582
0.5589	3.0	45	0.5609	0.7010	0.8082	0.7546
0.52	4.0	60	0.5504	0.7181	0.8130	0.7656
0.4758	5.0	75	0.5648	0.6863	0.7647	0.7255
0.4144	6.0	90	0.5725	0.7279	0.8147	0.7713
0.3139	7.0	105	0.6853	0.7181	0.8074	0.7628
0.2645	8.0	120	0.7634	0.7475	0.8362	0.7919
0.2114	9.0	135	0.8087	0.7255	0.825	0.7752

Framework versions

Transformers 4.46.3
Pytorch 2.2.1+cu118
Datasets 2.17.0
Tokenizers 0.20.3