metadata
license: apache-2.0
tags:
- generated_from_trainer
metrics:
- accuracy
- precision
- recall
- f1
model-index:
- name: twitter-data-distilbert-base-uncased-sentiment-finetuned-memes
results: []
twitter-data-distilbert-base-uncased-sentiment-finetuned-memes
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: 0.2605
- Accuracy: 0.9316
- Precision: 0.9322
- Recall: 0.9316
- F1: 0.9317
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: 1e-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 | Accuracy | Precision | Recall | F1 |
|---|---|---|---|---|---|---|---|
| 0.3463 | 1.0 | 1783 | 0.2966 | 0.9065 | 0.9079 | 0.9065 | 0.9066 |
| 0.2601 | 2.0 | 3566 | 0.2526 | 0.9245 | 0.9254 | 0.9245 | 0.9244 |
| 0.2228 | 3.0 | 5349 | 0.2355 | 0.9313 | 0.9327 | 0.9313 | 0.9314 |
| 0.1997 | 4.0 | 7132 | 0.2243 | 0.9341 | 0.9354 | 0.9341 | 0.9342 |
| 0.1779 | 5.0 | 8915 | 0.2254 | 0.9346 | 0.9354 | 0.9346 | 0.9345 |
| 0.1642 | 6.0 | 10698 | 0.2355 | 0.9322 | 0.9329 | 0.9322 | 0.9323 |
| 0.146 | 7.0 | 12481 | 0.2485 | 0.9302 | 0.9306 | 0.9302 | 0.9303 |
| 0.1368 | 8.0 | 14264 | 0.2530 | 0.9296 | 0.9312 | 0.9296 | 0.9299 |
| 0.1293 | 9.0 | 16047 | 0.2585 | 0.9317 | 0.9322 | 0.9317 | 0.9317 |
| 0.121 | 10.0 | 17830 | 0.2605 | 0.9316 | 0.9322 | 0.9316 | 0.9317 |
Framework versions
- Transformers 4.24.0.dev0
- Pytorch 1.11.0+cu102
- Datasets 2.6.1
- Tokenizers 0.13.1