metadata
license: apache-2.0
tags:
- generated_from_trainer
model-index:
- name: bert-base-uncased-issues-128
results: []
bert-base-uncased-issues-128
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: 1.6174
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: 32
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 16
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 2.5225 | 1.0 | 670 | 2.4071 |
| 2.2459 | 2.0 | 1340 | 2.0490 |
| 2.1137 | 3.0 | 2010 | 2.1236 |
| 2.0192 | 4.0 | 2680 | 2.0374 |
| 1.9307 | 5.0 | 3350 | 1.9619 |
| 1.8619 | 6.0 | 4020 | 1.9072 |
| 1.823 | 7.0 | 4690 | 1.8499 |
| 1.7415 | 8.0 | 5360 | 1.7408 |
| 1.6994 | 9.0 | 6030 | 1.7243 |
| 1.6576 | 10.0 | 6700 | 1.7139 |
| 1.6109 | 11.0 | 7370 | 1.8658 |
| 1.593 | 12.0 | 8040 | 1.9678 |
| 1.5501 | 13.0 | 8710 | 1.7578 |
| 1.5288 | 14.0 | 9380 | 1.7830 |
| 1.5135 | 15.0 | 10050 | 1.8932 |
| 1.4906 | 16.0 | 10720 | 1.6174 |
Framework versions
- Transformers 4.19.4
- Pytorch 1.11.0+cu113
- Datasets 2.3.1
- Tokenizers 0.12.1