metadata
license: apache-2.0
tags:
- generated_from_trainer
datasets:
- wnut_17
metrics:
- precision
- recall
- f1
- accuracy
model-index:
- name: distilbert-base-uncased-test2
results:
- task:
name: Token Classification
type: token-classification
dataset:
name: wnut_17
type: wnut_17
args: wnut_17
metrics:
- name: Precision
type: precision
value: 0.502770083102493
- name: Recall
type: recall
value: 0.33642261353104724
- name: F1
type: f1
value: 0.4031093836757356
- name: Accuracy
type: accuracy
value: 0.9428840152195289
distilbert-base-uncased-test2
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: 0.2724
- Precision: 0.5028
- Recall: 0.3364
- F1: 0.4031
- Accuracy: 0.9429
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: 3
Training results
Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
---|---|---|---|---|---|---|---|
No log | 1.0 | 213 | 0.2849 | 0.4606 | 0.2382 | 0.3140 | 0.9374 |
No log | 2.0 | 426 | 0.2610 | 0.5439 | 0.3216 | 0.4042 | 0.9424 |
0.1949 | 3.0 | 639 | 0.2724 | 0.5028 | 0.3364 | 0.4031 | 0.9429 |
Framework versions
- Transformers 4.20.1
- Pytorch 1.12.0+cu102
- Datasets 2.4.0
- Tokenizers 0.12.1