<!-- 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-mod-datatsets-rarity-all-iorder-e13k-e2p6k
This model is a fine-tuned version of gpt2 on the generator dataset. It achieves the following results on the evaluation set:
- Loss: 3.1126
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: 7
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 6.7739 | 0.32 | 500 | 5.7277 |
| 5.4452 | 0.65 | 1000 | 5.2872 |
| 5.0904 | 0.97 | 1500 | 5.0382 |
| 4.8112 | 1.29 | 2000 | 4.8839 |
| 4.6871 | 1.61 | 2500 | 4.7559 |
| 4.5735 | 1.94 | 3000 | 4.6554 |
| 4.3545 | 2.26 | 3500 | 4.6039 |
| 4.2891 | 2.58 | 4000 | 4.5528 |
| 4.2556 | 2.91 | 4500 | 4.4842 |
| 4.0444 | 3.23 | 5000 | 4.4670 |
| 3.9893 | 3.55 | 5500 | 4.4376 |
| 3.9736 | 3.88 | 6000 | 4.4055 |
| 3.7854 | 4.2 | 6500 | 4.4071 |
| 3.7025 | 4.52 | 7000 | 4.4017 |
| 3.6896 | 4.84 | 7500 | 4.3746 |
| 3.5524 | 5.17 | 8000 | 4.4037 |
| 3.4335 | 5.49 | 8500 | 4.4051 |
| 3.4336 | 5.81 | 9000 | 4.3980 |
| 3.3704 | 6.14 | 9500 | 4.4055 |
| 3.2733 | 6.46 | 10000 | 4.4109 |
| 3.2711 | 6.78 | 10500 | 4.4111 |
Framework versions
- Transformers 4.26.1
- Pytorch 1.11.0+cu113
- Datasets 2.13.0
- Tokenizers 0.13.3
