<!-- 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-cl-concat-log-rarity-9-210k-mod-datasets
This model is a fine-tuned version of gpt2 on the generator dataset. It achieves the following results on the evaluation set:
- Loss: 5.0793
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 |
|---|---|---|---|
| 6.2877 | 0.07 | 500 | 5.9527 |
| 5.0107 | 0.14 | 1000 | 5.5940 |
| 4.7383 | 0.21 | 1500 | 5.4130 |
| 4.5602 | 0.28 | 2000 | 5.2903 |
| 4.423 | 0.35 | 2500 | 5.2322 |
| 4.3129 | 0.41 | 3000 | 5.1696 |
| 4.2078 | 0.48 | 3500 | 5.1278 |
| 4.1161 | 0.55 | 4000 | 5.1007 |
| 4.023 | 0.62 | 4500 | 5.0613 |
| 3.933 | 0.69 | 5000 | 5.0483 |
| 3.8578 | 0.76 | 5500 | 5.0290 |
| 3.7859 | 0.83 | 6000 | 5.0156 |
| 3.746 | 0.9 | 6500 | 5.0064 |
| 3.7228 | 0.97 | 7000 | 5.0027 |
Framework versions
- Transformers 4.26.1
- Pytorch 1.11.0+cu113
- Datasets 2.13.0
- Tokenizers 0.13.3
