metadata
license: apache-2.0
base_model: distilbert-base-uncased
tags:
- generated_from_trainer
metrics:
- precision
- recall
- f1
- accuracy
model-index:
- name: distilbert_base_data_wnut_17
results: []
distilbert_base_data_wnut_17
This model is a fine-tuned version of distilbert-base-uncased on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.2833
- Precision: 0.5246
- Recall: 0.3855
- F1: 0.4444
- Accuracy: 0.9461
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 | 0.2740 | 0.6152 | 0.2919 | 0.3960 | 0.9404 |
No log | 2.0 | 426 | 0.2568 | 0.5997 | 0.3679 | 0.4561 | 0.9450 |
0.1764 | 3.0 | 639 | 0.2844 | 0.6269 | 0.3457 | 0.4456 | 0.9464 |
0.1764 | 4.0 | 852 | 0.2963 | 0.5564 | 0.3522 | 0.4313 | 0.9459 |
0.0526 | 5.0 | 1065 | 0.2833 | 0.5246 | 0.3855 | 0.4444 | 0.9461 |
Framework versions
- Transformers 4.37.2
- Pytorch 2.1.0+cu121
- Datasets 2.16.1
- Tokenizers 0.15.1