gpt2-concat
This model is a fine-tuned version of gpt2 on the generator dataset. It achieves the following results on the evaluation set:
- Loss: 4.3720
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: 0.0005
- train_batch_size: 64
- eval_batch_size: 64
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 128
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_steps: 1000
- num_epochs: 9
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 6.3219 | 2.31 | 500 | 5.0318 |
| 4.5653 | 4.63 | 1000 | 4.4568 |
| 4.3703 | 1.74 | 1500 | 4.4722 |
| 4.1189 | 2.31 | 2000 | 4.3725 |
| 3.9959 | 2.89 | 2500 | 4.2973 |
| 3.7906 | 3.47 | 3000 | 4.2853 |
| 3.7352 | 4.05 | 3500 | 4.2581 |
| 3.5026 | 4.63 | 4000 | 4.2642 |
| 3.4421 | 5.21 | 4500 | 4.2821 |
| 3.2812 | 5.79 | 5000 | 4.2720 |
| 3.1197 | 6.37 | 5500 | 4.3157 |
| 3.0336 | 6.94 | 6000 | 4.3125 |
| 2.8367 | 7.52 | 6500 | 4.3545 |
| 2.806 | 8.1 | 7000 | 4.3663 |
| 2.7076 | 8.68 | 7500 | 4.3720 |
Framework versions
- Transformers 4.26.1
- Pytorch 1.11.0+cu113
- Datasets 2.13.0
- Tokenizers 0.13.3
- Downloads last month
- 2