metadata
license: apache-2.0
tags:
- generated_from_trainer
datasets:
- wnut_17
metrics:
- precision
- recall
- f1
- accuracy
model-index:
- name: distilbert-base
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: 0.5251322751322751
- name: Recall
type: recall
value: 0.36793327154772937
- name: F1
type: f1
value: 0.43269754768392366
- name: Accuracy
type: accuracy
value: 0.9450643409858492
distilbert-base
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: 0.2693
- Precision: 0.5251
- Recall: 0.3679
- F1: 0.4327
- Accuracy: 0.9451
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: 32
- eval_batch_size: 32
- 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 | 107 | 0.3088 | 0.3506 | 0.1446 | 0.2047 | 0.9328 |
| No log | 2.0 | 214 | 0.2634 | 0.5403 | 0.3170 | 0.3995 | 0.9414 |
| No log | 3.0 | 321 | 0.2530 | 0.5282 | 0.3559 | 0.4252 | 0.9435 |
| No log | 4.0 | 428 | 0.2587 | 0.5206 | 0.3753 | 0.4362 | 0.9446 |
| 0.1695 | 5.0 | 535 | 0.2693 | 0.5251 | 0.3679 | 0.4327 | 0.9451 |
Framework versions
- Transformers 4.29.2
- Pytorch 2.0.0
- Datasets 2.1.0
- Tokenizers 0.13.3