<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->
distilbert_imdb_genre_classifier
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: 0.0196
- Precision: 0.4254
- Recall: 0.4432
- F1 Score: 0.4191
- Jaccard Score: 0.2966
- Average Precision Score: 0.4831
- Percentage Examples At Least 1 True: 0.8845
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: 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: 4
Training results
Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 Score | Jaccard Score | Average Precision Score | Percentage Examples At Least 1 True |
---|---|---|---|---|---|---|---|---|---|
0.0231 | 1.0 | 1500 | 0.0214 | 0.3601 | 0.4090 | 0.3601 | 0.2523 | 0.4326 | 0.8638 |
0.0196 | 2.0 | 3000 | 0.0198 | 0.4174 | 0.4367 | 0.4064 | 0.2864 | 0.4743 | 0.8842 |
0.0172 | 3.0 | 4500 | 0.0196 | 0.4216 | 0.4418 | 0.4155 | 0.2939 | 0.4822 | 0.887 |
0.016 | 4.0 | 6000 | 0.0196 | 0.4254 | 0.4432 | 0.4191 | 0.2966 | 0.4831 | 0.8845 |
Framework versions
- Transformers 4.26.1
- Pytorch 2.0.0+cu118
- Tokenizers 0.13.3