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: 0.2254
- Precision: 0.6447
- Recall: 0.6716
- F1: 0.6579
- Accuracy: 0.9475
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 | 0.2896 | 0.4849 | 0.4567 | 0.4704 | 0.9207 |
| 0.3471 | 2.0 | 564 | 0.2266 | 0.5677 | 0.5821 | 0.5748 | 0.9348 |
| 0.3471 | 3.0 | 846 | 0.2240 | 0.5925 | 0.6164 | 0.6042 | 0.9377 |
| 0.1655 | 4.0 | 1128 | 0.2015 | 0.6455 | 0.6522 | 0.6488 | 0.9478 |
| 0.1655 | 5.0 | 1410 | 0.2017 | 0.6431 | 0.6776 | 0.6599 | 0.9485 |
| 0.1072 | 6.0 | 1692 | 0.2095 | 0.6164 | 0.6522 | 0.6338 | 0.9455 |
| 0.1072 | 7.0 | 1974 | 0.2086 | 0.6556 | 0.6791 | 0.6672 | 0.9495 |
| 0.0758 | 8.0 | 2256 | 0.2278 | 0.6322 | 0.6672 | 0.6492 | 0.9466 |
| 0.0529 | 9.0 | 2538 | 0.2226 | 0.6429 | 0.6716 | 0.6569 | 0.9480 |
| 0.0529 | 10.0 | 2820 | 0.2254 | 0.6447 | 0.6716 | 0.6579 | 0.9475 |
Framework versions
- Transformers 4.41.1
- Pytorch 2.1.2
- Datasets 2.19.1
- Tokenizers 0.19.1