metadata
license: apache-2.0
base_model: distilbert-base-uncased
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: my_awesome_model_IMDB
results: []
my_awesome_model_IMDB
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: 0.4229
- Accuracy: 0.9307
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: 32
- eval_batch_size: 32
- 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 | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.2892 | 1.0 | 782 | 0.2075 | 0.9192 |
| 0.151 | 2.0 | 1564 | 0.2034 | 0.9294 |
| 0.103 | 3.0 | 2346 | 0.2369 | 0.9270 |
| 0.0567 | 4.0 | 3128 | 0.2920 | 0.9306 |
| 0.0415 | 5.0 | 3910 | 0.3699 | 0.9275 |
| 0.025 | 6.0 | 4692 | 0.3560 | 0.9300 |
| 0.0204 | 7.0 | 5474 | 0.3690 | 0.9308 |
| 0.0125 | 8.0 | 6256 | 0.4119 | 0.9300 |
| 0.0117 | 9.0 | 7038 | 0.4176 | 0.9310 |
| 0.0065 | 10.0 | 7820 | 0.4229 | 0.9307 |
Framework versions
- Transformers 4.34.0
- Pytorch 2.0.1+cu117
- Datasets 2.17.0
- Tokenizers 0.14.0