metadata
library_name: transformers
license: mit
base_model: openai-gpt
tags:
- generated_from_trainer
model-index:
- name: gpt_1_sequence_classification_finetune
results: []
gpt_1_sequence_classification_finetune
This model is a fine-tuned version of openai-gpt on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.0383
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: 3.4479420247518066e-05
- train_batch_size: 64
- eval_batch_size: 64
- seed: 42
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- num_epochs: 15
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.0679 | 1.0 | 12 | 0.0716 |
| 0.0463 | 2.0 | 24 | 0.0525 |
| 0.0507 | 3.0 | 36 | 0.0455 |
| 0.0448 | 4.0 | 48 | 0.0469 |
| 0.0428 | 5.0 | 60 | 0.0453 |
| 0.0409 | 6.0 | 72 | 0.0403 |
| 0.0319 | 7.0 | 84 | 0.0318 |
| 0.0176 | 8.0 | 96 | 0.0263 |
| 0.0258 | 9.0 | 108 | 0.0338 |
| 0.0194 | 10.0 | 120 | 0.0383 |
Framework versions
- Transformers 4.49.0
- Pytorch 2.6.0
- Datasets 3.4.0
- Tokenizers 0.21.1