metadata
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: GPT2_natural_function_53
results: []
GPT2_natural_function_53
This model was trained from scratch on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 3.6748
- Accuracy: 0.3767
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 |
|---|---|---|---|---|
| 4.9154 | 1.0 | 6439 | 4.6920 | 0.2905 |
| 4.2909 | 2.0 | 12878 | 4.1496 | 0.3277 |
| 4.0302 | 3.0 | 19317 | 3.9565 | 0.3464 |
| 3.9006 | 4.0 | 25756 | 3.8567 | 0.3559 |
| 3.8039 | 5.0 | 32195 | 3.7948 | 0.3623 |
| 3.7327 | 6.0 | 38634 | 3.7528 | 0.3667 |
| 3.6704 | 7.0 | 45073 | 3.7218 | 0.3703 |
| 3.618 | 8.0 | 51512 | 3.6993 | 0.3727 |
| 3.5713 | 9.0 | 57951 | 3.6824 | 0.3757 |
| 3.5291 | 10.0 | 64390 | 3.6748 | 0.3767 |
Framework versions
- Transformers 4.30.2
- Pytorch 2.9.1+cu128
- Datasets 4.1.1
- Tokenizers 0.13.3