metadata
library_name: transformers
base_model: gokulsrinivasagan/bert_base_lda_5_v1
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: bert_base_lda_5_v1_wnli
results: []
bert_base_lda_5_v1_wnli
This model is a fine-tuned version of gokulsrinivasagan/bert_base_lda_5_v1 on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.7278
- Accuracy: 0.4366
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 |
|---|---|---|---|---|
| 1.1014 | 1.0 | 3 | 1.8103 | 0.5634 |
| 1.4998 | 2.0 | 6 | 2.1869 | 0.5634 |
| 1.6341 | 3.0 | 9 | 2.1261 | 0.4366 |
| 1.492 | 4.0 | 12 | 0.6872 | 0.5634 |
| 0.7047 | 5.0 | 15 | 0.7812 | 0.4366 |
| 0.7143 | 6.0 | 18 | 0.6881 | 0.5634 |
| 0.7199 | 7.0 | 21 | 0.8079 | 0.4366 |
| 0.7574 | 8.0 | 24 | 0.7103 | 0.5634 |
| 0.7273 | 9.0 | 27 | 0.7278 | 0.4366 |
Framework versions
- Transformers 4.46.3
- Pytorch 2.2.1+cu118
- Datasets 2.17.0
- Tokenizers 0.20.3