metadata
license: apache-2.0
tags:
- generated_from_trainer
datasets:
- wnut_17
metrics:
- precision
- recall
- f1
- accuracy
model-index:
- name: bert-small-finetuned-wnut17-ner-longer10
results:
- task:
name: Token Classification
type: token-classification
dataset:
name: wnut_17
type: wnut_17
config: wnut_17
split: train
args: wnut_17
metrics:
- name: Precision
type: precision
value: 0.5546995377503852
- name: Recall
type: recall
value: 0.430622009569378
- name: F1
type: f1
value: 0.48484848484848486
- name: Accuracy
type: accuracy
value: 0.9250487441220323
bert-small-finetuned-wnut17-ner-longer10
This model is a fine-tuned version of muhtasham/bert-small-finetuned-wnut17-ner-longer6 on the wnut_17 dataset. It achieves the following results on the evaluation set:
- Loss: 0.4693
- Precision: 0.5547
- Recall: 0.4306
- F1: 0.4848
- Accuracy: 0.9250
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: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 4
Training results
Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
---|---|---|---|---|---|---|---|
No log | 1.0 | 425 | 0.4815 | 0.5759 | 0.3947 | 0.4684 | 0.9255 |
0.0402 | 2.0 | 850 | 0.4467 | 0.5397 | 0.4390 | 0.4842 | 0.9247 |
0.0324 | 3.0 | 1275 | 0.4646 | 0.5332 | 0.4318 | 0.4772 | 0.9244 |
0.0315 | 4.0 | 1700 | 0.4693 | 0.5547 | 0.4306 | 0.4848 | 0.9250 |
Framework versions
- Transformers 4.21.1
- Pytorch 1.12.1+cu113
- Datasets 2.4.0
- Tokenizers 0.12.1