distilbert-amazon-shoe-reviews-tensorboard
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: 0.9534
- Accuracy: 0.5779
- F1: [0.63189419 0.46645049 0.50381304 0.55843496 0.73060507]
- Precision: [0.62953754 0.47008547 0.48669202 0.58801498 0.71780957]
- Recall: [0.63426854 0.46287129 0.52218256 0.53168844 0.74386503]
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: 32
- eval_batch_size: 64
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 1
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Precision | Recall |
|---|---|---|---|---|---|---|---|
| 0.8776 | 1.0 | 2813 | 0.9534 | 0.5779 | [0.63189419 0.46645049 0.50381304 0.55843496 0.73060507] | [0.62953754 0.47008547 0.48669202 0.58801498 0.71780957] | [0.63426854 0.46287129 0.52218256 0.53168844 0.74386503] |
Framework versions
- Transformers 4.20.1
- Pytorch 1.12.0+cu102
- Datasets 2.3.2
- Tokenizers 0.12.1