metadata
license: apache-2.0
tags:
- generated_from_trainer
datasets:
- nerd
metrics:
- precision
- recall
- f1
- accuracy
model_index:
- name: ner_nerd_fine
results:
- task:
name: Token Classification
type: token-classification
dataset:
name: nerd
type: nerd
args: nerd
metric:
name: Accuracy
type: accuracy
value: 0.9058961278375514
ner_nerd_fine
This model is a fine-tuned version of bert-base-uncased on the nerd dataset. It achieves the following results on the evaluation set:
- Loss: 0.5332
- Precision: 0.6337
- Recall: 0.6731
- F1: 0.6528
- Accuracy: 0.9059
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: 16
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 10
Training results
Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
---|---|---|---|---|---|---|---|
0.6337 | 1.0 | 8235 | 0.3391 | 0.5974 | 0.6567 | 0.6256 | 0.9010 |
0.3086 | 2.0 | 16470 | 0.3188 | 0.6276 | 0.6607 | 0.6437 | 0.9061 |
0.2394 | 3.0 | 24705 | 0.3304 | 0.6284 | 0.6740 | 0.6504 | 0.9064 |
0.1841 | 4.0 | 32940 | 0.3451 | 0.6286 | 0.6749 | 0.6509 | 0.9065 |
0.1392 | 5.0 | 41175 | 0.3837 | 0.6251 | 0.6745 | 0.6489 | 0.9056 |
0.1056 | 6.0 | 49410 | 0.4185 | 0.6307 | 0.6751 | 0.6521 | 0.9057 |
0.0812 | 7.0 | 57645 | 0.4615 | 0.6288 | 0.6774 | 0.6522 | 0.9052 |
0.0629 | 8.0 | 65880 | 0.4933 | 0.6332 | 0.6755 | 0.6537 | 0.9065 |
0.0492 | 9.0 | 74115 | 0.5266 | 0.6360 | 0.6752 | 0.6550 | 0.9067 |
0.0401 | 10.0 | 82350 | 0.5452 | 0.6340 | 0.6760 | 0.6543 | 0.9065 |
Framework versions
- Transformers 4.9.1
- Pytorch 1.9.0+cu102
- Datasets 1.11.0
- Tokenizers 0.10.2