|
|
--- |
|
|
tags: |
|
|
- generated_from_trainer |
|
|
metrics: |
|
|
- accuracy |
|
|
model-index: |
|
|
- name: GPT2_natural_function_67 |
|
|
results: [] |
|
|
--- |
|
|
|
|
|
<!-- This model card has been generated automatically according to the information the Trainer had access to. You |
|
|
should probably proofread and complete it, then remove this comment. --> |
|
|
|
|
|
# GPT2_natural_function_67 |
|
|
|
|
|
This model was trained from scratch on an unknown dataset. |
|
|
It achieves the following results on the evaluation set: |
|
|
- Loss: 3.7168 |
|
|
- Accuracy: 0.3685 |
|
|
|
|
|
## 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 | |
|
|
|:-------------:|:-----:|:-----:|:---------------:|:--------:| |
|
|
| 4.97 | 1.0 | 6422 | 4.7453 | 0.2805 | |
|
|
| 4.3346 | 2.0 | 12844 | 4.1934 | 0.3193 | |
|
|
| 4.0708 | 3.0 | 19266 | 3.9999 | 0.3376 | |
|
|
| 3.9406 | 4.0 | 25688 | 3.9018 | 0.3471 | |
|
|
| 3.8415 | 5.0 | 32110 | 3.8403 | 0.3540 | |
|
|
| 3.7713 | 6.0 | 38532 | 3.7970 | 0.3587 | |
|
|
| 3.7109 | 7.0 | 44954 | 3.7650 | 0.3626 | |
|
|
| 3.6557 | 8.0 | 51376 | 3.7405 | 0.3651 | |
|
|
| 3.6097 | 9.0 | 57798 | 3.7246 | 0.3677 | |
|
|
| 3.5655 | 10.0 | 64220 | 3.7168 | 0.3685 | |
|
|
|
|
|
|
|
|
### Framework versions |
|
|
|
|
|
- Transformers 4.30.2 |
|
|
- Pytorch 2.9.1+cu128 |
|
|
- Datasets 4.1.1 |
|
|
- Tokenizers 0.13.3 |
|
|
|
