metadata
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: GPT2_within_boundary_53
results: []
GPT2_within_boundary_53
This model was trained from scratch on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 3.7802
- 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: 53
- 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 |
|---|---|---|---|---|
| 5.0366 | 1.0 | 6439 | 4.8202 | 0.2746 |
| 4.4144 | 2.0 | 12878 | 4.2730 | 0.3176 |
| 4.1479 | 3.0 | 19317 | 4.0742 | 0.3366 |
| 4.0152 | 4.0 | 25756 | 3.9702 | 0.3473 |
| 3.9157 | 5.0 | 32195 | 3.9046 | 0.3545 |
| 3.8427 | 6.0 | 38634 | 3.8617 | 0.3588 |
| 3.7786 | 7.0 | 45073 | 3.8290 | 0.3639 |
| 3.7255 | 8.0 | 51512 | 3.8044 | 0.3661 |
| 3.6782 | 9.0 | 57951 | 3.7879 | 0.3691 |
| 3.6357 | 10.0 | 64390 | 3.7802 | 0.3704 |
Framework versions
- Transformers 4.30.2
- Pytorch 2.9.1+cu128
- Datasets 4.1.1
- Tokenizers 0.13.3