<!-- 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-dp-finetune-cl-mod-datasets-rarity1
This model was trained from scratch on the generator dataset. It achieves the following results on the evaluation set:
- Loss: 2.5865
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: 5
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 3.7804 | 0.28 | 500 | 4.4982 |
| 3.9124 | 0.55 | 1000 | 4.5349 |
| 4.0179 | 0.83 | 1500 | 4.4602 |
| 3.9221 | 1.1 | 2000 | 4.4585 |
| 3.7998 | 1.38 | 2500 | 4.4362 |
| 3.8298 | 1.65 | 3000 | 4.3838 |
| 3.8259 | 1.93 | 3500 | 4.3551 |
| 3.5608 | 2.2 | 4000 | 4.4125 |
| 3.5215 | 2.48 | 4500 | 4.3867 |
| 3.5238 | 2.75 | 5000 | 4.3540 |
| 3.4761 | 3.03 | 5500 | 4.3684 |
| 3.1332 | 3.3 | 6000 | 4.4048 |
| 3.146 | 3.58 | 6500 | 4.3926 |
| 3.1394 | 3.85 | 7000 | 4.3839 |
| 2.9917 | 4.13 | 7500 | 4.4150 |
| 2.841 | 4.4 | 8000 | 4.4240 |
| 2.8327 | 4.68 | 8500 | 4.4259 |
| 2.8284 | 4.95 | 9000 | 4.4261 |
Framework versions
- Transformers 4.26.1
- Pytorch 1.11.0+cu113
- Datasets 2.13.0
- Tokenizers 0.13.3
