film95000distilbert-base-uncased
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: 1.8725
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: 0.0002
- 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
- training_steps: 14840
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 2.7724 | 0.34 | 500 | 2.5848 |
| 2.5813 | 0.67 | 1000 | 2.4469 |
| 2.479 | 1.01 | 1500 | 2.3841 |
| 2.3872 | 1.35 | 2000 | 2.3378 |
| 2.3504 | 1.68 | 2500 | 2.2838 |
| 2.3134 | 2.02 | 3000 | 2.2451 |
| 2.2483 | 2.36 | 3500 | 2.1953 |
| 2.2166 | 2.69 | 4000 | 2.1854 |
| 2.2023 | 3.03 | 4500 | 2.1559 |
| 2.1438 | 3.37 | 5000 | 2.1479 |
| 2.1271 | 3.7 | 5500 | 2.1155 |
| 2.1092 | 4.04 | 6000 | 2.0980 |
| 2.0656 | 4.38 | 6500 | 2.0736 |
| 2.0544 | 4.71 | 7000 | 2.0567 |
| 2.037 | 5.05 | 7500 | 2.0234 |
| 1.9902 | 5.39 | 8000 | 2.0079 |
| 1.9883 | 5.72 | 8500 | 1.9988 |
| 1.9624 | 6.06 | 9000 | 1.9832 |
| 1.9348 | 6.4 | 9500 | 1.9643 |
| 1.9215 | 6.73 | 10000 | 1.9471 |
| 1.9103 | 7.07 | 10500 | 1.9434 |
| 1.8794 | 7.41 | 11000 | 1.9282 |
| 1.8762 | 7.74 | 11500 | 1.9194 |
| 1.8597 | 8.08 | 12000 | 1.9260 |
| 1.8402 | 8.42 | 12500 | 1.8795 |
| 1.8326 | 8.75 | 13000 | 1.8948 |
| 1.8191 | 9.09 | 13500 | 1.9020 |
| 1.8058 | 9.43 | 14000 | 1.8806 |
| 1.804 | 9.76 | 14500 | 1.8680 |
Framework versions
- Transformers 4.27.3
- Pytorch 1.13.1+cu116
- Datasets 2.10.1
- Tokenizers 0.13.2