metadata
license: apache-2.0
base_model: distilbert-base-uncased
tags:
- generated_from_trainer
metrics:
- f1
- accuracy
model-index:
- name: distilbert-base-uncased-finetuned-airline-sentiment-tweets
results: []
distilbert-base-uncased-finetuned-airline-sentiment-tweets
This model is a fine-tuned version of distilbert-base-uncased on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.4399
- F1: 0.8493
- Accuracy: 0.8611
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: 64
- eval_batch_size: 64
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | F1 | Accuracy |
|---|---|---|---|---|---|
| 0.7149 | 1.0 | 37 | 0.6176 | 0.6562 | 0.7599 |
| 0.4767 | 2.0 | 74 | 0.3981 | 0.8272 | 0.8473 |
| 0.3311 | 3.0 | 111 | 0.3420 | 0.8576 | 0.8696 |
| 0.2435 | 4.0 | 148 | 0.3614 | 0.8528 | 0.8645 |
| 0.1975 | 5.0 | 185 | 0.3721 | 0.8502 | 0.8645 |
| 0.1496 | 6.0 | 222 | 0.3862 | 0.8471 | 0.8593 |
| 0.1114 | 7.0 | 259 | 0.4239 | 0.8412 | 0.8576 |
| 0.0989 | 8.0 | 296 | 0.4168 | 0.8484 | 0.8593 |
| 0.0747 | 9.0 | 333 | 0.4376 | 0.8459 | 0.8593 |
| 0.0733 | 10.0 | 370 | 0.4399 | 0.8493 | 0.8611 |
Framework versions
- Transformers 4.38.2
- Pytorch 2.2.1+cu118
- Datasets 2.18.0
- Tokenizers 0.15.2