metadata
base_model: finiteautomata/bertweet-base-sentiment-analysis
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: my_awesome_model_IMDB
results: []
my_awesome_model_IMDB
This model is a fine-tuned version of finiteautomata/bertweet-base-sentiment-analysis on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.6664
- Accuracy: 0.8949
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: 32
- eval_batch_size: 32
- 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 |
|---|---|---|---|---|
| 0.3261 | 1.0 | 782 | 0.2674 | 0.8903 |
| 0.2072 | 2.0 | 1564 | 0.3035 | 0.8820 |
| 0.1408 | 3.0 | 2346 | 0.3532 | 0.8967 |
| 0.0876 | 4.0 | 3128 | 0.4793 | 0.8922 |
| 0.0661 | 5.0 | 3910 | 0.4755 | 0.8925 |
| 0.0373 | 6.0 | 4692 | 0.5159 | 0.8937 |
| 0.034 | 7.0 | 5474 | 0.5527 | 0.8923 |
| 0.0264 | 8.0 | 6256 | 0.6391 | 0.8947 |
| 0.0179 | 9.0 | 7038 | 0.6491 | 0.8942 |
| 0.0094 | 10.0 | 7820 | 0.6664 | 0.8949 |
Framework versions
- Transformers 4.34.0
- Pytorch 2.0.1+cu117
- Datasets 2.17.0
- Tokenizers 0.14.0