metadata
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: GPT2_natural_function_42
results: []
GPT2_natural_function_42
This model was trained from scratch on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 3.6743
- Accuracy: 0.3760
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: 0.0001
- train_batch_size: 128
- eval_batch_size: 128
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 10000
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 4.9122 | 1.0 | 6439 | 4.6831 | 0.2912 |
| 4.2912 | 2.0 | 12878 | 4.1456 | 0.3270 |
| 4.0258 | 3.0 | 19317 | 3.9543 | 0.3454 |
| 3.8998 | 4.0 | 25756 | 3.8565 | 0.3544 |
| 3.8025 | 5.0 | 32195 | 3.7955 | 0.3619 |
| 3.7321 | 6.0 | 38634 | 3.7518 | 0.3656 |
| 3.6704 | 7.0 | 45073 | 3.7216 | 0.3702 |
| 3.6185 | 8.0 | 51512 | 3.6979 | 0.3726 |
| 3.5692 | 9.0 | 57951 | 3.6816 | 0.3746 |
| 3.5276 | 10.0 | 64390 | 3.6743 | 0.3760 |
Framework versions
- Transformers 4.30.2
- Pytorch 2.9.1+cu128
- Datasets 4.1.1
- Tokenizers 0.13.3