metadata
library_name: transformers
language:
- en
base_model: gokulsrinivasagan/bert_base_lda
tags:
- generated_from_trainer
datasets:
- glue
metrics:
- accuracy
model-index:
- name: bert_base_lda_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_wnli
This model is a fine-tuned version of gokulsrinivasagan/bert_base_lda on the GLUE WNLI dataset. It achieves the following results on the evaluation set:
- Loss: 0.6864
- 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: 50
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 1.1638 | 1.0 | 3 | 1.4608 | 0.5634 |
| 1.0198 | 2.0 | 6 | 1.1097 | 0.5634 |
| 1.1474 | 3.0 | 9 | 0.8995 | 0.5634 |
| 0.8846 | 4.0 | 12 | 0.8201 | 0.4366 |
| 0.7886 | 5.0 | 15 | 0.6994 | 0.4366 |
| 0.738 | 6.0 | 18 | 0.7087 | 0.5634 |
| 0.7195 | 7.0 | 21 | 0.7214 | 0.4366 |
| 0.7036 | 8.0 | 24 | 0.6931 | 0.5634 |
| 0.6935 | 9.0 | 27 | 0.6896 | 0.5634 |
| 0.6941 | 10.0 | 30 | 0.6926 | 0.5634 |
| 0.6949 | 11.0 | 33 | 0.6936 | 0.4366 |
| 0.6959 | 12.0 | 36 | 0.6911 | 0.5634 |
| 0.6927 | 13.0 | 39 | 0.6864 | 0.5634 |
| 0.6928 | 14.0 | 42 | 0.6893 | 0.5634 |
| 0.6958 | 15.0 | 45 | 0.6896 | 0.5634 |
| 0.6936 | 16.0 | 48 | 0.6911 | 0.5634 |
| 0.6955 | 17.0 | 51 | 0.6911 | 0.5634 |
| 0.6939 | 18.0 | 54 | 0.6906 | 0.5634 |
Framework versions
- Transformers 4.46.3
- Pytorch 2.2.1+cu118
- Datasets 2.17.0
- Tokenizers 0.20.3