metadata
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: GPT2_within_boundary_42
results: []
GPT2_within_boundary_42
This model was trained from scratch on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 3.7814
- Accuracy: 0.3704
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 |
|---|---|---|---|---|
| 5.0339 | 1.0 | 6439 | 4.8144 | 0.2765 |
| 4.4123 | 2.0 | 12878 | 4.2657 | 0.3180 |
| 4.1405 | 3.0 | 19317 | 4.0689 | 0.3368 |
| 4.011 | 4.0 | 25756 | 3.9679 | 0.3468 |
| 3.9116 | 5.0 | 32195 | 3.9068 | 0.3538 |
| 3.84 | 6.0 | 38634 | 3.8596 | 0.3597 |
| 3.7769 | 7.0 | 45073 | 3.8291 | 0.3634 |
| 3.7239 | 8.0 | 51512 | 3.8062 | 0.3666 |
| 3.6741 | 9.0 | 57951 | 3.7892 | 0.3687 |
| 3.632 | 10.0 | 64390 | 3.7814 | 0.3704 |
Framework versions
- Transformers 4.30.2
- Pytorch 2.9.1+cu128
- Datasets 4.1.1
- Tokenizers 0.13.3