metadata
license: apache-2.0
tags:
- generated_from_trainer
metrics:
- accuracy
- f1
model-index:
- name: bert-tweet-disaster
results: []
bert-tweet-disaster
This model is a fine-tuned version of bert-base-uncased on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.9563
- Accuracy: 0.8320
- F1: 0.8095
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: 5e-05
- train_batch_size: 64
- eval_batch_size: 64
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 500
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
|---|---|---|---|---|---|
| 0.605 | 1.0 | 108 | 0.4455 | 0.8123 | 0.7741 |
| 0.3878 | 2.0 | 216 | 0.3940 | 0.8438 | 0.8126 |
| 0.3228 | 3.0 | 324 | 0.4441 | 0.8241 | 0.8006 |
| 0.2526 | 4.0 | 432 | 0.4714 | 0.8333 | 0.8006 |
| 0.2002 | 5.0 | 540 | 0.5677 | 0.8189 | 0.7890 |
| 0.1391 | 6.0 | 648 | 0.6633 | 0.8307 | 0.8000 |
| 0.0922 | 7.0 | 756 | 0.8019 | 0.8294 | 0.8071 |
| 0.0693 | 8.0 | 864 | 0.8526 | 0.8333 | 0.8049 |
| 0.0495 | 9.0 | 972 | 0.9813 | 0.8241 | 0.8075 |
| 0.0345 | 10.0 | 1080 | 0.9563 | 0.8320 | 0.8095 |
Framework versions
- Transformers 4.20.1
- Pytorch 1.11.0
- Datasets 2.1.0
- Tokenizers 0.12.1