metadata
library_name: transformers
language:
- en
base_model: gokulsrinivasagan/bert_base_lda_5
tags:
- generated_from_trainer
datasets:
- glue
metrics:
- accuracy
model-index:
- name: bert_base_lda_5_wnli
results:
- task:
name: Text Classification
type: text-classification
dataset:
name: GLUE WNLI
type: glue
args: wnli
metrics:
- name: Accuracy
type: accuracy
value: 0.5633802816901409
bert_base_lda_5_wnli
This model is a fine-tuned version of gokulsrinivasagan/bert_base_lda_5 on the GLUE WNLI dataset. It achieves the following results on the evaluation set:
- Loss: 0.6849
- Accuracy: 0.5634
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: 0.001
- 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: 30
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 1.121 | 1.0 | 3 | 0.8205 | 0.5634 |
| 1.6034 | 2.0 | 6 | 1.7293 | 0.4366 |
| 0.9483 | 3.0 | 9 | 0.7649 | 0.4366 |
| 0.7514 | 4.0 | 12 | 0.7557 | 0.5634 |
| 0.746 | 5.0 | 15 | 0.8105 | 0.4366 |
| 0.7896 | 6.0 | 18 | 0.7383 | 0.4366 |
| 0.7573 | 7.0 | 21 | 0.6853 | 0.5634 |
| 0.6951 | 8.0 | 24 | 0.8346 | 0.4366 |
| 0.746 | 9.0 | 27 | 0.6906 | 0.5634 |
| 0.6992 | 10.0 | 30 | 0.6849 | 0.5634 |
| 0.6942 | 11.0 | 33 | 0.7009 | 0.4366 |
| 0.7 | 12.0 | 36 | 0.6951 | 0.4366 |
| 0.6976 | 13.0 | 39 | 0.6854 | 0.5634 |
| 0.6999 | 14.0 | 42 | 0.6901 | 0.5634 |
| 0.6948 | 15.0 | 45 | 0.6926 | 0.5634 |
Framework versions
- Transformers 4.46.3
- Pytorch 2.2.1+cu118
- Datasets 2.17.0
- Tokenizers 0.20.3