metadata
license: apache-2.0
tags:
- generated_from_trainer
datasets:
- wnut_17
metrics:
- precision
- recall
- f1
- accuracy
model-index:
- name: ner
results:
- task:
name: Token Classification
type: token-classification
dataset:
name: wnut_17
type: wnut_17
config: wnut_17
split: test
args: wnut_17
metrics:
- name: Precision
type: precision
value: 0.5527638190954773
- name: Recall
type: recall
value: 0.4077849860982391
- name: F1
type: f1
value: 0.46933333333333327
- name: Accuracy
type: accuracy
value: 0.9475439271514685
ner
This model is a fine-tuned version of distilbert-base-uncased on the wnut_17 dataset. It achieves the following results on the evaluation set:
- Loss: 0.3030
- Precision: 0.5528
- Recall: 0.4078
- F1: 0.4693
- 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: 5
Training results
Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
---|---|---|---|---|---|---|---|
No log | 1.0 | 213 | 0.2577 | 0.5099 | 0.3568 | 0.4198 | 0.9437 |
No log | 2.0 | 426 | 0.2675 | 0.5406 | 0.3948 | 0.4563 | 0.9463 |
0.0737 | 3.0 | 639 | 0.3040 | 0.5737 | 0.3716 | 0.4511 | 0.9465 |
0.0737 | 4.0 | 852 | 0.3042 | 0.5514 | 0.3976 | 0.4620 | 0.9474 |
0.0307 | 5.0 | 1065 | 0.3030 | 0.5528 | 0.4078 | 0.4693 | 0.9475 |
Framework versions
- Transformers 4.27.4
- Pytorch 2.0.0+cu118
- Datasets 2.11.0
- Tokenizers 0.13.3