metadata
license: apache-2.0
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: finetuned_bert-base-uncased
results: []
finetuned_bert-base-uncased
This model is a fine-tuned version of bert-base-uncased on the None dataset. It achieves the following results on the evaluation set:
- Loss: 2.8732
- Accuracy: 0.4263
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: 2e-05
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 20
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 1.7365 | 1.0 | 502 | 1.5167 | 0.4288 |
| 1.3495 | 2.0 | 1004 | 1.4797 | 0.4592 |
| 1.1131 | 3.0 | 1506 | 1.5093 | 0.4527 |
| 0.9213 | 4.0 | 2008 | 1.6501 | 0.4522 |
| 0.7787 | 5.0 | 2510 | 1.7494 | 0.4407 |
| 0.6594 | 6.0 | 3012 | 1.8600 | 0.4417 |
| 0.5807 | 7.0 | 3514 | 1.9974 | 0.4412 |
| 0.5142 | 8.0 | 4016 | 2.0887 | 0.4273 |
| 0.4716 | 9.0 | 4518 | 2.1556 | 0.4273 |
| 0.4364 | 10.0 | 5020 | 2.2847 | 0.4348 |
| 0.3934 | 11.0 | 5522 | 2.3842 | 0.4298 |
| 0.3774 | 12.0 | 6024 | 2.4663 | 0.4228 |
| 0.3498 | 13.0 | 6526 | 2.5637 | 0.4253 |
| 0.337 | 14.0 | 7028 | 2.6162 | 0.4273 |
| 0.3191 | 15.0 | 7530 | 2.6466 | 0.4268 |
| 0.3081 | 16.0 | 8032 | 2.6214 | 0.4288 |
| 0.2889 | 17.0 | 8534 | 2.8064 | 0.4258 |
| 0.2831 | 18.0 | 9036 | 2.8042 | 0.4228 |
| 0.2733 | 19.0 | 9538 | 2.8510 | 0.4288 |
| 0.2648 | 20.0 | 10040 | 2.8732 | 0.4263 |
Framework versions
- Transformers 4.26.0
- Pytorch 1.13.1+cu116
- Datasets 2.9.0
- Tokenizers 0.13.2