metadata
license: mit
base_model: gpt2
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: gpt2-finetuned-KAGGLE
results: []
gpt2-finetuned-KAGGLE
This model is a fine-tuned version of gpt2 on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.8914
- Accuracy: 0.7862
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: 5
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| No log | 1.0 | 21 | 1.5759 | 0.7379 |
| No log | 2.0 | 42 | 0.8914 | 0.7862 |
| No log | 3.0 | 63 | 0.8166 | 0.7862 |
| No log | 4.0 | 84 | 0.8055 | 0.7862 |
| No log | 5.0 | 105 | 0.8031 | 0.7862 |
Framework versions
- Transformers 4.32.0
- Pytorch 2.0.1+cu118
- Datasets 2.14.4
- Tokenizers 0.13.3