metadata
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: GPT2_natural_function_67
results: []
GPT2_natural_function_67
This model was trained from scratch on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 3.6758
- Accuracy: 0.3762
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: 67
- 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 |
|---|---|---|---|---|
| 4.9145 | 1.0 | 6439 | 4.6882 | 0.2902 |
| 4.2877 | 2.0 | 12878 | 4.1479 | 0.3278 |
| 4.0279 | 3.0 | 19317 | 3.9541 | 0.3454 |
| 3.9003 | 4.0 | 25756 | 3.8561 | 0.3553 |
| 3.8034 | 5.0 | 32195 | 3.7953 | 0.3616 |
| 3.731 | 6.0 | 38634 | 3.7539 | 0.3663 |
| 3.6709 | 7.0 | 45073 | 3.7236 | 0.3700 |
| 3.6162 | 8.0 | 51512 | 3.7010 | 0.3734 |
| 3.5698 | 9.0 | 57951 | 3.6846 | 0.3751 |
| 3.5258 | 10.0 | 64390 | 3.6758 | 0.3762 |
Framework versions
- Transformers 4.30.2
- Pytorch 2.9.1+cu128
- Datasets 4.1.1
- Tokenizers 0.13.3