metadata
license: apache-2.0
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: dream_classifier
results: []
dream_classifier
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: 1.3533
- Accuracy: 0.7321
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: 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: 20
Training results
Training Loss | Epoch | Step | Validation Loss | Accuracy |
---|---|---|---|---|
No log | 1.0 | 17 | 0.5774 | 0.7321 |
No log | 2.0 | 34 | 0.5660 | 0.7321 |
No log | 3.0 | 51 | 0.5903 | 0.7321 |
No log | 4.0 | 68 | 0.5558 | 0.7321 |
No log | 5.0 | 85 | 0.5904 | 0.7411 |
No log | 6.0 | 102 | 0.6088 | 0.7321 |
No log | 7.0 | 119 | 0.7359 | 0.7589 |
No log | 8.0 | 136 | 0.9027 | 0.7589 |
No log | 9.0 | 153 | 1.0194 | 0.7411 |
No log | 10.0 | 170 | 1.1241 | 0.7589 |
No log | 11.0 | 187 | 1.1849 | 0.7411 |
No log | 12.0 | 204 | 1.2305 | 0.7411 |
No log | 13.0 | 221 | 1.2551 | 0.75 |
No log | 14.0 | 238 | 1.2859 | 0.7411 |
No log | 15.0 | 255 | 1.3070 | 0.7411 |
No log | 16.0 | 272 | 1.3238 | 0.7411 |
No log | 17.0 | 289 | 1.3357 | 0.7411 |
No log | 18.0 | 306 | 1.3449 | 0.7411 |
No log | 19.0 | 323 | 1.3513 | 0.7321 |
No log | 20.0 | 340 | 1.3533 | 0.7321 |
Framework versions
- Transformers 4.30.2
- Pytorch 2.0.1+cu118
- Datasets 2.13.0
- Tokenizers 0.13.3