<!-- 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-cl-log-rarity-10-220k-mod-datasets-rarity1-root3
This model is a fine-tuned version of gpt2 on the generator dataset. It achieves the following results on the evaluation set:
- Loss: 5.0416
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: 1
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 6.3754 | 0.06 | 500 | 5.9052 |
| 5.0899 | 0.12 | 1000 | 5.5421 |
| 4.8108 | 0.18 | 1500 | 5.3468 |
| 4.6258 | 0.24 | 2000 | 5.2562 |
| 4.4818 | 0.3 | 2500 | 5.1938 |
| 4.3762 | 0.36 | 3000 | 5.1291 |
| 4.2781 | 0.42 | 3500 | 5.0818 |
| 4.184 | 0.48 | 4000 | 5.0492 |
| 4.0944 | 0.54 | 4500 | 5.0293 |
| 4.0096 | 0.6 | 5000 | 5.0134 |
| 3.9209 | 0.66 | 5500 | 4.9953 |
| 3.8449 | 0.72 | 6000 | 4.9897 |
| 3.7748 | 0.78 | 6500 | 4.9793 |
| 3.7162 | 0.84 | 7000 | 4.9719 |
| 3.6813 | 0.9 | 7500 | 4.9687 |
| 3.6592 | 0.96 | 8000 | 4.9669 |
Framework versions
- Transformers 4.26.1
- Pytorch 1.11.0+cu113
- Datasets 2.13.0
- Tokenizers 0.13.3
