metadata
license: apache-2.0
tags:
- generated_from_trainer
datasets:
- conll2003
metrics:
- precision
- recall
- f1
- accuracy
model-index:
- name: bert-base-uncased-finetuned-ner
results: []
bert-base-uncased-finetuned-ner
This model is a fine-tuned version of bert-base-uncased on the conll2003 dataset. It achieves the following results on the evaluation set:
- Loss: 0.0615
- Precision: 0.9222
- Recall: 0.9372
- F1: 0.9297
- Accuracy: 0.9838
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: 1
- eval_batch_size: 1
- seed: 42
- distributed_type: IPU
- gradient_accumulation_steps: 16
- total_train_batch_size: 16
- total_eval_batch_size: 5
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3
- training precision: Mixed Precision
Training results
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|---|---|---|---|---|---|---|---|
| 0.051 | 1.0 | 877 | 0.0667 | 0.9090 | 0.9190 | 0.9139 | 0.9811 |
| 0.2483 | 2.0 | 1754 | 0.0600 | 0.9295 | 0.9344 | 0.9320 | 0.9839 |
| 0.0153 | 3.0 | 2631 | 0.0615 | 0.9222 | 0.9372 | 0.9297 | 0.9838 |
Framework versions
- Transformers 4.20.1
- Pytorch 1.10.0+cpu
- Datasets 2.7.1
- Tokenizers 0.12.1