metadata
tags:
- generated_from_trainer
model-index:
- name: distilroberta-base
results: []
distilroberta-base
This model was trained from scratch on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.2128
- F1 Score: 0.9697
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: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | F1 Score |
|---|---|---|---|---|
| 0.301 | 1.0 | 873 | 0.1875 | 0.9409 |
| 0.1426 | 2.0 | 1746 | 0.1306 | 0.9572 |
| 0.0833 | 3.0 | 2619 | 0.1042 | 0.9661 |
| 0.0671 | 4.0 | 3492 | 0.1528 | 0.9686 |
| 0.038 | 5.0 | 4365 | 0.1612 | 0.9684 |
| 0.0304 | 6.0 | 5238 | 0.1648 | 0.9707 |
| 0.017 | 7.0 | 6111 | 0.2173 | 0.9665 |
| 0.0101 | 8.0 | 6984 | 0.2048 | 0.9700 |
| 0.0083 | 9.0 | 7857 | 0.2138 | 0.9691 |
| 0.0066 | 10.0 | 8730 | 0.2128 | 0.9697 |
Framework versions
- Transformers 4.31.0
- Pytorch 2.0.0
- Datasets 2.1.0
- Tokenizers 0.13.3