<!-- 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. -->
ai-human3
This model is a fine-tuned version of sooks/ai-human2 on the aihuman dataset. It achieves the following results on the evaluation set:
- Loss: 0.2314
- Accuracy: 0.9124
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: 0.0002
- train_batch_size: 16
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 6
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.3654 | 0.67 | 1000 | 0.3597 | 0.8436 |
| 0.3186 | 1.33 | 2000 | 0.3315 | 0.8545 |
| 0.2659 | 2.0 | 3000 | 0.3015 | 0.8698 |
| 0.2206 | 2.67 | 4000 | 0.3116 | 0.8736 |
| 0.1827 | 3.34 | 5000 | 0.2642 | 0.8984 |
| 0.1929 | 4.0 | 6000 | 0.2421 | 0.9022 |
| 0.1927 | 4.67 | 7000 | 0.2314 | 0.9124 |
| 0.1306 | 5.34 | 8000 | 0.2437 | 0.9159 |
Framework versions
- Transformers 4.28.1
- Pytorch 2.0.0+cu118
- Datasets 2.12.0
- Tokenizers 0.13.3
