metadata

library_name: transformers
language:
  - en
base_model: gokulsrinivasagan/bert_base_lda_100_v1
tags:
  - generated_from_trainer
datasets:
  - glue
metrics:
  - accuracy
  - f1
model-index:
  - name: bert_base_lda_100_v1_qqp
    results:
      - task:
          name: Text Classification
          type: text-classification
        dataset:
          name: GLUE QQP
          type: glue
          args: qqp
        metrics:
          - name: Accuracy
            type: accuracy
            value: 0.8609448429384121
          - name: F1
            type: f1
            value: 0.818621757646148

bert_base_lda_100_v1_qqp

This model is a fine-tuned version of gokulsrinivasagan/bert_base_lda_100_v1 on the GLUE QQP dataset. It achieves the following results on the evaluation set:

Loss: 0.3234
Accuracy: 0.8609
F1: 0.8186
Combined Score: 0.8398

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
0.4474	1.0	1422	0.3685	0.8284	0.7614	0.7949
0.3271	2.0	2844	0.3386	0.8476	0.8103	0.8290
0.2564	3.0	4266	0.3234	0.8609	0.8186	0.8398
0.1978	4.0	5688	0.3628	0.8653	0.8263	0.8458
0.1516	5.0	7110	0.4014	0.8695	0.8253	0.8474
0.1169	6.0	8532	0.3964	0.8673	0.8278	0.8475
0.093	7.0	9954	0.4813	0.8676	0.8279	0.8478
0.076	8.0	11376	0.4346	0.8693	0.8285	0.8489

Framework versions

Transformers 4.46.3
Pytorch 2.2.1+cu118
Datasets 2.17.0
Tokenizers 0.20.3