metadata
library_name: transformers
license: apache-2.0
base_model: distilroberta-base
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: time-period-classifier-bert
results: []
time-period-classifier-bert
This model is a fine-tuned version of distilroberta-base on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.1907
- Accuracy: 0.9674
- F1 Macro: 0.9683
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: 16
- eval_batch_size: 32
- seed: 42
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 Macro |
|---|---|---|---|---|---|
| 1.1962 | 1.0 | 120 | 0.8911 | 0.6576 | 0.6000 |
| 0.8928 | 2.0 | 240 | 0.5397 | 0.7935 | 0.7938 |
| 0.565 | 3.0 | 360 | 0.4020 | 0.8605 | 0.8618 |
| 0.3721 | 4.0 | 480 | 0.2893 | 0.9094 | 0.9092 |
| 0.2123 | 5.0 | 600 | 0.2099 | 0.9438 | 0.9428 |
| 0.1374 | 6.0 | 720 | 0.1425 | 0.9692 | 0.9698 |
| 0.0682 | 7.0 | 840 | 0.1796 | 0.9656 | 0.9663 |
| 0.0451 | 8.0 | 960 | 0.1928 | 0.9674 | 0.9683 |
| 0.0275 | 9.0 | 1080 | 0.1870 | 0.9656 | 0.9666 |
| 0.0224 | 10.0 | 1200 | 0.1907 | 0.9674 | 0.9683 |
Framework versions
- Transformers 4.57.1
- Pytorch 2.2.2
- Datasets 4.4.1
- Tokenizers 0.22.1