<!-- 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. -->
gpt2-concat-bnc-rarity-end-1p6
This model is a fine-tuned version of gpt2 on the generator dataset. It achieves the following results on the evaluation set:
- Loss: 4.3234
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
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_steps: 1000
- num_epochs: 6
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 6.7136 | 0.29 | 500 | 5.6426 |
| 5.3544 | 0.59 | 1000 | 5.2039 |
| 4.9956 | 0.88 | 1500 | 4.9562 |
| 4.7225 | 1.17 | 2000 | 4.8042 |
| 4.568 | 1.46 | 2500 | 4.6819 |
| 4.4551 | 1.76 | 3000 | 4.5728 |
| 4.3337 | 2.05 | 3500 | 4.5041 |
| 4.1427 | 2.34 | 4000 | 4.4590 |
| 4.1052 | 2.63 | 4500 | 4.3959 |
| 4.0696 | 2.93 | 5000 | 4.3454 |
| 3.8614 | 3.22 | 5500 | 4.3396 |
| 3.813 | 3.51 | 6000 | 4.3118 |
| 3.789 | 3.81 | 6500 | 4.2754 |
| 3.6879 | 4.1 | 7000 | 4.2741 |
| 3.5215 | 4.39 | 7500 | 4.2692 |
| 3.5205 | 4.68 | 8000 | 4.2563 |
| 3.5065 | 4.98 | 8500 | 4.2419 |
| 3.3459 | 5.27 | 9000 | 4.2548 |
| 3.3262 | 5.56 | 9500 | 4.2549 |
| 3.327 | 5.85 | 10000 | 4.2536 |
Framework versions
- Transformers 4.26.1
- Pytorch 1.11.0+cu113
- Datasets 2.13.0
- Tokenizers 0.13.3
