<!-- 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. -->
v9
This model is a fine-tuned version of EleutherAI/gpt-neo-1.3B on the None dataset. It achieves the following results on the evaluation set:
- Loss: 3.3262
- Accuracy: 0.3995
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: 1e-05
- train_batch_size: 4
- eval_batch_size: 1
- seed: 42
- distributed_type: multi-GPU
- num_devices: 2
- total_train_batch_size: 8
- total_eval_batch_size: 2
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 70
- num_epochs: 10.0
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 2.7485 | 1.0 | 72 | 2.7852 | 0.4448 |
| 2.6279 | 2.0 | 144 | 2.7832 | 0.4450 |
| 2.5097 | 3.0 | 216 | 2.7988 | 0.4425 |
| 2.3899 | 4.0 | 288 | 2.8203 | 0.4403 |
| 2.2636 | 5.0 | 360 | 2.8594 | 0.4366 |
| 2.1351 | 6.0 | 432 | 2.9141 | 0.4307 |
| 1.99 | 7.0 | 504 | 2.9844 | 0.4244 |
| 1.8299 | 8.0 | 576 | 3.0723 | 0.4173 |
| 1.6524 | 9.0 | 648 | 3.1855 | 0.4087 |
| 1.4676 | 10.0 | 720 | 3.3262 | 0.3995 |
Framework versions
- Transformers 4.29.2
- Pytorch 2.0.1
- Datasets 2.12.0
- Tokenizers 0.13.3
