metadata
license: mit
base_model: gpt2
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: stage2Only_scaffoldGPT
results: []
stage2Only_scaffoldGPT
This model is a fine-tuned version of gpt2 on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.3794
- Accuracy: 0.8768
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: 5e-05
- train_batch_size: 24
- eval_batch_size: 24
- seed: 42
- distributed_type: multi-GPU
- num_devices: 8
- total_train_batch_size: 192
- total_eval_batch_size: 192
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 10.0
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.4672 | 1.0 | 6015 | 0.4400 | 0.8613 |
| 0.4321 | 2.0 | 12030 | 0.4123 | 0.8684 |
| 0.417 | 3.0 | 18045 | 0.4000 | 0.8716 |
| 0.4082 | 4.0 | 24060 | 0.3928 | 0.8734 |
| 0.4024 | 5.0 | 30075 | 0.3881 | 0.8746 |
| 0.3982 | 6.0 | 36090 | 0.3847 | 0.8754 |
| 0.3953 | 7.0 | 42105 | 0.3824 | 0.8760 |
| 0.3932 | 8.0 | 48120 | 0.3807 | 0.8765 |
| 0.3919 | 9.0 | 54135 | 0.3798 | 0.8767 |
| 0.3912 | 10.0 | 60150 | 0.3794 | 0.8768 |
Framework versions
- Transformers 4.36.0.dev0
- Pytorch 2.1.1+cu121
- Datasets 2.15.0
- Tokenizers 0.15.0