metadata
library_name: transformers
license: apache-2.0
base_model: dslim/distilbert-NER
tags:
- generated_from_trainer
model-index:
- name: distilbert-NER-Math-finetuned
results: []
distilbert-NER-Math-finetuned
This model is a fine-tuned version of dslim/distilbert-NER on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.0505
- F1 Score: 0.9507
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: 3e-05
- train_batch_size: 5
- eval_batch_size: 5
- seed: 42
- optimizer: Use OptimizerNames.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 |
|---|---|---|---|---|
| 0.1114 | 1.0 | 1534 | 0.0871 | 0.8536 |
| 0.0577 | 2.0 | 3068 | 0.0617 | 0.9002 |
| 0.0393 | 3.0 | 4602 | 0.0511 | 0.9191 |
| 0.0192 | 4.0 | 6136 | 0.0510 | 0.9331 |
| 0.0133 | 5.0 | 7670 | 0.0493 | 0.9364 |
| 0.0071 | 6.0 | 9204 | 0.0499 | 0.9416 |
| 0.0054 | 7.0 | 10738 | 0.0497 | 0.9461 |
| 0.0016 | 8.0 | 12272 | 0.0508 | 0.9480 |
| 0.0028 | 9.0 | 13806 | 0.0510 | 0.9495 |
| 0.0013 | 10.0 | 15340 | 0.0505 | 0.9507 |
Framework versions
- Transformers 4.47.1
- Pytorch 2.5.1+cu124
- Datasets 3.2.0
- Tokenizers 0.21.0