metadata
library_name: transformers
license: apache-2.0
base_model: distilbert/distilbert-base-uncased
tags:
- generated_from_trainer
model-index:
- name: ATE
results: []
ATE
This model is a fine-tuned version of distilbert/distilbert-base-uncased on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.2578
- F1-score: 0.8064
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: 16
- eval_batch_size: 16
- 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 | F1-score |
|---|---|---|---|---|
| 0.2899 | 1.0 | 226 | 0.2203 | 0.6838 |
| 0.1197 | 2.0 | 452 | 0.1892 | 0.7766 |
| 0.0694 | 3.0 | 678 | 0.1919 | 0.7961 |
| 0.0459 | 4.0 | 904 | 0.2223 | 0.8008 |
| 0.0389 | 5.0 | 1130 | 0.2283 | 0.8090 |
| 0.0268 | 6.0 | 1356 | 0.2374 | 0.8095 |
| 0.0225 | 7.0 | 1582 | 0.2458 | 0.8084 |
| 0.0194 | 8.0 | 1808 | 0.2557 | 0.8094 |
| 0.017 | 9.0 | 2034 | 0.2588 | 0.8106 |
| 0.0163 | 10.0 | 2260 | 0.2578 | 0.8064 |
Framework versions
- Transformers 4.47.0
- Pytorch 2.5.1+cu121
- Datasets 3.2.0
- Tokenizers 0.21.0