metadata
license: mit
base_model: gpt2
tags:
- generated_from_trainer
metrics:
- accuracy
- f1
model-index:
- name: gpt2_classifier_MMLU
results: []
gpt2_classifier_MMLU
This model is a fine-tuned version of gpt2 on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.5386
- Accuracy: 0.8707
- F1: 0.8675
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: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
|---|---|---|---|---|---|
| 0.804 | 1.0 | 2537 | 0.7214 | 0.7924 | 0.7904 |
| 0.4835 | 2.0 | 5074 | 0.5850 | 0.8420 | 0.8374 |
| 0.2044 | 3.0 | 7611 | 0.5412 | 0.8684 | 0.8655 |
Framework versions
- Transformers 4.39.3
- Pytorch 2.3.0+cu121
- Datasets 2.19.1
- Tokenizers 0.15.2