metadata
license: mit
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: gpt2-sweep
results: []
gpt2-sweep
This model is a fine-tuned version of gpt2-large on the None dataset. It achieves the following results on the evaluation set:
- Loss: 2.0773
- Accuracy: 0.8482
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: 2.294477077303931e-05
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 1000
- num_epochs: 2.0
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 2.4891 | 0.19 | 1000 | 2.4467 | 0.8446 |
| 2.7019 | 0.37 | 2000 | 2.3208 | 0.8456 |
| 2.5278 | 0.56 | 3000 | 2.2470 | 0.8464 |
| 2.0687 | 0.74 | 4000 | 2.1953 | 0.8468 |
| 2.1738 | 0.93 | 5000 | 2.1543 | 0.8472 |
| 1.8554 | 1.12 | 6000 | 2.1500 | 0.8475 |
| 1.9276 | 1.3 | 7000 | 2.1223 | 0.8477 |
| 1.7988 | 1.49 | 8000 | 2.1120 | 0.8479 |
| 2.0632 | 1.67 | 9000 | 2.0973 | 0.8480 |
| 1.9586 | 1.86 | 10000 | 2.0826 | 0.8481 |
Framework versions
- Transformers 4.26.0
- Pytorch 2.0.0+cu117
- Datasets 2.9.0
- Tokenizers 0.13.2