metadata
license: apache-2.0
tags:
- generated_from_trainer
model-index:
- name: 20split_dataset_version2
results: []
20split_dataset_version2
This model is a fine-tuned version of distilbert-base-uncased on the None dataset. It achieves the following results on the evaluation set:
- Loss: 2.0648
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: 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: 16
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 2.7606 | 1.0 | 11851 | 2.5274 |
| 2.5475 | 2.0 | 23702 | 2.4189 |
| 2.4456 | 3.0 | 35553 | 2.3622 |
| 2.3777 | 4.0 | 47404 | 2.3091 |
| 2.3155 | 5.0 | 59255 | 2.2764 |
| 2.2715 | 6.0 | 71106 | 2.2445 |
| 2.2301 | 7.0 | 82957 | 2.2182 |
| 2.1896 | 8.0 | 94808 | 2.1968 |
| 2.1562 | 9.0 | 106659 | 2.1720 |
| 2.1271 | 10.0 | 118510 | 2.1484 |
| 2.0981 | 11.0 | 130361 | 2.1264 |
| 2.0743 | 12.0 | 142212 | 2.1157 |
| 2.048 | 13.0 | 154063 | 2.0943 |
| 2.0264 | 14.0 | 165914 | 2.0814 |
| 2.009 | 15.0 | 177765 | 2.0732 |
| 1.9962 | 16.0 | 189616 | 2.0648 |
Framework versions
- Transformers 4.20.1
- Pytorch 1.12.0+cu113
- Datasets 2.3.2
- Tokenizers 0.12.1