metadata
library_name: transformers
license: apache-2.0
base_model: distilbert/distilbert-base-cased
tags:
- generated_from_trainer
metrics:
- precision
- recall
- f1
- accuracy
model-index:
- name: distillbert-base-cased-finetuned-ner2
results: []
distillbert-base-cased-finetuned-ner2
This model is a fine-tuned version of distilbert/distilbert-base-cased on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.1556
- Precision: 0.7479
- Recall: 0.7873
- F1: 0.7671
- Accuracy: 0.9518
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: 8
- eval_batch_size: 8
- 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: cosine
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 5
Training results
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|---|---|---|---|---|---|---|---|
| 0.2026 | 1.0 | 4750 | 0.1952 | 0.6895 | 0.7367 | 0.7123 | 0.9429 |
| 0.1637 | 2.0 | 9500 | 0.1681 | 0.7358 | 0.7743 | 0.7546 | 0.9491 |
| 0.1525 | 3.0 | 14250 | 0.1584 | 0.7448 | 0.7859 | 0.7648 | 0.9513 |
| 0.1487 | 4.0 | 19000 | 0.1558 | 0.7463 | 0.7866 | 0.7659 | 0.9516 |
| 0.1523 | 5.0 | 23750 | 0.1556 | 0.7479 | 0.7873 | 0.7671 | 0.9518 |
Framework versions
- Transformers 4.50.1
- Pytorch 2.5.1+cu124
- Datasets 3.4.1
- Tokenizers 0.21.1