metadata
license: mit
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: BertWhatCommitPreprocessed
results: []
BertWhatCommitPreprocessed
This model is a fine-tuned version of prajjwal1/bert-small on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.3631
- Accuracy: 0.9152
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: 1e-05
- train_batch_size: 64
- eval_batch_size: 64
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 200
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| No log | 1.0 | 38 | 0.5383 | 0.7333 |
| No log | 2.0 | 76 | 0.4130 | 0.8485 |
| No log | 3.0 | 114 | 0.3096 | 0.8727 |
| No log | 4.0 | 152 | 0.3140 | 0.8788 |
| No log | 5.0 | 190 | 0.2983 | 0.8970 |
| No log | 6.0 | 228 | 0.3019 | 0.8848 |
| No log | 7.0 | 266 | 0.3235 | 0.9030 |
| No log | 8.0 | 304 | 0.3571 | 0.8970 |
| No log | 9.0 | 342 | 0.3457 | 0.8970 |
| No log | 10.0 | 380 | 0.3340 | 0.8909 |
| No log | 11.0 | 418 | 0.3378 | 0.9091 |
| No log | 12.0 | 456 | 0.3389 | 0.9091 |
| No log | 13.0 | 494 | 0.3753 | 0.9030 |
| 0.2144 | 14.0 | 532 | 0.3492 | 0.9152 |
| 0.2144 | 15.0 | 570 | 0.3631 | 0.9152 |
Framework versions
- Transformers 4.28.0
- Pytorch 2.0.1+cu118
- Datasets 2.12.0
- Tokenizers 0.13.3