metadata
license: mit
base_model: gpt2
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: text_classification_gpt2
results: []
text_classification_gpt2
This model is a fine-tuned version of gpt2 on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.3501
- Accuracy: 0.9052
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: 4
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_ratio: 0.01
- num_epochs: 1
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.0308 | 0.1 | 625 | 0.5502 | 0.8852 |
| 1.6669 | 0.2 | 1250 | 0.3501 | 0.9052 |
| 1.9326 | 0.3 | 1875 | 0.4868 | 0.9 |
| 1.2678 | 0.4 | 2500 | 0.3823 | 0.9028 |
| 0.0015 | 0.5 | 3125 | 0.4167 | 0.8964 |
| 2.5243 | 0.6 | 3750 | 0.3938 | 0.9152 |
| 0.531 | 0.7 | 4375 | 0.3512 | 0.9156 |
| 0.0027 | 0.8 | 5000 | 0.3806 | 0.9148 |
| 1.1369 | 0.9 | 5625 | 0.3543 | 0.9264 |
| 0.0667 | 1.0 | 6250 | 0.3502 | 0.9272 |
Framework versions
- Transformers 4.40.1
- Pytorch 2.2.1+cu121
- Datasets 2.19.0
- Tokenizers 0.19.1