metadata
license: apache-2.0
base_model: distilbert-base-cased
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: textclassifier
results: []
textclassifier
This model is a fine-tuned version of distilbert-base-cased on the None dataset. It achieves the following results on the evaluation set:
- Loss: 4.9168
- Accuracy: 0.0
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: 0.0002
- train_batch_size: 8
- eval_batch_size: 8
- 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 |
|---|---|---|---|---|
| 4.7871 | 1.0 | 46 | 4.8124 | 0.0 |
| 4.7669 | 2.0 | 92 | 4.8653 | 0.0 |
| 4.7888 | 3.0 | 138 | 4.8858 | 0.0 |
| 4.7498 | 4.0 | 184 | 4.8981 | 0.0 |
| 4.7449 | 5.0 | 230 | 4.8945 | 0.0 |
| 4.7261 | 6.0 | 276 | 4.9050 | 0.0 |
| 4.7295 | 7.0 | 322 | 4.9148 | 0.0 |
| 4.7181 | 8.0 | 368 | 4.9166 | 0.0 |
| 4.7094 | 9.0 | 414 | 4.9146 | 0.0 |
| 4.7064 | 10.0 | 460 | 4.9168 | 0.0 |
Framework versions
- Transformers 4.38.1
- Pytorch 2.1.0+cu121
- Datasets 2.17.1
- Tokenizers 0.15.2