metadata
license: apache-2.0
tags:
- generated_from_trainer
model-index:
- name: oldData_BERT
results: []
oldData_BERT
This model is a fine-tuned version of bert-base-cased on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.0616
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: 1
- eval_batch_size: 1
- seed: 42
- gradient_accumulation_steps: 8
- total_train_batch_size: 8
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 7
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 1.2348 | 1.0 | 1125 | 1.0185 |
| 1.0082 | 2.0 | 2250 | 0.7174 |
| 0.699 | 3.0 | 3375 | 0.3657 |
| 0.45 | 4.0 | 4500 | 0.1880 |
| 0.2915 | 5.0 | 5625 | 0.1140 |
| 0.2056 | 6.0 | 6750 | 0.0708 |
| 0.1312 | 7.0 | 7875 | 0.0616 |
Framework versions
- Transformers 4.18.0
- Pytorch 1.10.0+cu111
- Datasets 2.1.0
- Tokenizers 0.12.1