metadata

library_name: transformers
language:
  - en
base_model: gokulsrinivasagan/bert_base_lda_20_v1_book
tags:
  - generated_from_trainer
datasets:
  - glue
metrics:
  - matthews_correlation
  - accuracy
model-index:
  - name: bert_base_lda_20_v1_book_cola
    results:
      - task:
          name: Text Classification
          type: text-classification
        dataset:
          name: GLUE COLA
          type: glue
          args: cola
        metrics:
          - name: Matthews Correlation
            type: matthews_correlation
            value: 0.47428224772244454
          - name: Accuracy
            type: accuracy
            value: 0.7890700101852417

bert_base_lda_20_v1_book_cola

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

Loss: 0.4867
Matthews Correlation: 0.4743
Accuracy: 0.7891

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	Matthews Correlation	Accuracy
0.6052	1.0	34	0.5939	0.0	0.6913
0.5337	2.0	68	0.5132	0.3639	0.7546
0.4113	3.0	102	0.4867	0.4743	0.7891
0.2988	4.0	136	0.5833	0.4456	0.7804
0.232	5.0	170	0.5778	0.4906	0.7958
0.1741	6.0	204	0.5924	0.5184	0.8063
0.1299	7.0	238	0.7206	0.5049	0.8015
0.1075	8.0	272	0.6481	0.5021	0.7987

Framework versions

Transformers 4.46.3
Pytorch 2.2.1+cu118
Datasets 2.17.0
Tokenizers 0.20.3