metadata
license: apache-2.0
base_model: distilbert/distilroberta-base
tags:
- generated_from_trainer
metrics:
- precision
- recall
- f1
- accuracy
model-index:
- name: distilroberta-base-finetuned-ner-harem
results: []
distilroberta-base-finetuned-ner-harem
This model is a fine-tuned version of distilbert/distilroberta-base on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.2053
- Precision: 0.6638
- Recall: 0.6836
- F1: 0.6735
- Accuracy: 0.9498
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 | Precision | Recall | F1 | Accuracy |
|---|---|---|---|---|---|---|---|
| No log | 1.0 | 282 | 0.2811 | 0.4809 | 0.4896 | 0.4852 | 0.9235 |
| 0.3394 | 2.0 | 564 | 0.2218 | 0.5679 | 0.5866 | 0.5771 | 0.9377 |
| 0.3394 | 3.0 | 846 | 0.2205 | 0.5708 | 0.5776 | 0.5742 | 0.9347 |
| 0.1635 | 4.0 | 1128 | 0.2027 | 0.6290 | 0.6478 | 0.6382 | 0.9469 |
| 0.1635 | 5.0 | 1410 | 0.1895 | 0.6542 | 0.6806 | 0.6672 | 0.9504 |
| 0.106 | 6.0 | 1692 | 0.2055 | 0.6334 | 0.6448 | 0.6391 | 0.9470 |
| 0.106 | 7.0 | 1974 | 0.1992 | 0.6328 | 0.6687 | 0.6502 | 0.9502 |
| 0.0744 | 8.0 | 2256 | 0.2051 | 0.6804 | 0.6925 | 0.6864 | 0.9513 |
| 0.0522 | 9.0 | 2538 | 0.1998 | 0.6745 | 0.6866 | 0.6805 | 0.9502 |
| 0.0522 | 10.0 | 2820 | 0.2053 | 0.6638 | 0.6836 | 0.6735 | 0.9498 |
Framework versions
- Transformers 4.41.1
- Pytorch 2.1.2
- Datasets 2.19.1
- Tokenizers 0.19.1