metadata

library_name: transformers
language:
  - en
base_model: gokulsrinivasagan/distilbert_lda_5_v1
tags:
  - generated_from_trainer
datasets:
  - glue
metrics:
  - accuracy
  - f1
model-index:
  - name: distilbert_lda_5_v1_qqp
    results:
      - task:
          name: Text Classification
          type: text-classification
        dataset:
          name: GLUE QQP
          type: glue
          args: qqp
        metrics:
          - name: Accuracy
            type: accuracy
            value: 0.8815978233984665
          - name: F1
            type: f1
            value: 0.8448046685038093

distilbert_lda_5_v1_qqp

This model is a fine-tuned version of gokulsrinivasagan/distilbert_lda_5_v1 on the GLUE QQP dataset. It achieves the following results on the evaluation set:

Loss: 0.2878
Accuracy: 0.8816
F1: 0.8448
Combined Score: 0.8632

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
0.376	1.0	1422	0.3084	0.8608	0.8144	0.8376
0.267	2.0	2844	0.2947	0.8694	0.8362	0.8528
0.2049	3.0	4266	0.2878	0.8816	0.8448	0.8632
0.1541	4.0	5688	0.3070	0.8845	0.8391	0.8618
0.1166	5.0	7110	0.3458	0.8864	0.8441	0.8653
0.0894	6.0	8532	0.3844	0.8853	0.8449	0.8651
0.0719	7.0	9954	0.4213	0.8848	0.8482	0.8665
0.0579	8.0	11376	0.4257	0.8842	0.8468	0.8655

Framework versions

Transformers 4.46.3
Pytorch 2.2.1+cu118
Datasets 2.17.0
Tokenizers 0.20.3