left_padding70model
This model is a fine-tuned version of distilbert-base-uncased on the imdb dataset. It achieves the following results on the evaluation set:
- Accuracy: 0.9309
- Loss: 0.7142
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: 10
Training results
Training Loss | Epoch | Step | Accuracy | Validation Loss |
---|---|---|---|---|
0.0473 | 1.0 | 1563 | 0.9279 | 0.4618 |
0.0096 | 2.0 | 3126 | 0.929 | 0.5406 |
0.0328 | 3.0 | 4689 | 0.92 | 0.5954 |
0.0192 | 4.0 | 6252 | 0.9288 | 0.5570 |
0.0171 | 5.0 | 7815 | 0.9294 | 0.5905 |
0.006 | 6.0 | 9378 | 0.9301 | 0.6330 |
0.0084 | 7.0 | 10941 | 0.9270 | 0.6311 |
0.0003 | 8.0 | 12504 | 0.9288 | 0.6783 |
0.0048 | 9.0 | 14067 | 0.9315 | 0.6987 |
0.0001 | 10.0 | 15630 | 0.9309 | 0.7142 |
Framework versions
- Transformers 4.35.0
- Pytorch 2.0.0+cu117
- Datasets 2.14.6
- Tokenizers 0.14.1
- Downloads last month
- 4
Inference Providers
NEW
This model isn't deployed by any Inference Provider.
🙋
Ask for provider support
Model tree for Realgon/left_padding70model
Base model
distilbert/distilbert-base-uncased