metadata
license: apache-2.0
tags:
- generated_from_trainer
metrics:
- accuracy
base_model: distilbert-base-uncased
model-index:
- name: cdp-gls
results: []
cdp-gls
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: 3.0808
- Accuracy: 0.4839
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 | Validation Loss | Accuracy |
|---|---|---|---|---|
| 3.4949 | 1.0 | 10 | 3.4712 | 0.0645 |
| 3.4362 | 2.0 | 20 | 3.4293 | 0.1452 |
| 3.3557 | 3.0 | 30 | 3.3663 | 0.2581 |
| 3.2469 | 4.0 | 40 | 3.3081 | 0.3710 |
| 3.1742 | 5.0 | 50 | 3.2495 | 0.3871 |
| 3.0934 | 6.0 | 60 | 3.1932 | 0.4032 |
| 3.0142 | 7.0 | 70 | 3.1443 | 0.4516 |
| 2.9634 | 8.0 | 80 | 3.1101 | 0.4516 |
| 2.9353 | 9.0 | 90 | 3.0889 | 0.4839 |
| 2.9034 | 10.0 | 100 | 3.0808 | 0.4839 |
Framework versions
- Transformers 4.38.0.dev0
- Pytorch 2.1.2+cu121
- Datasets 2.15.0
- Tokenizers 0.15.0