<!-- 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. -->
all-base-miss-wikipedia-seed
This model is a fine-tuned version of gpt2 on the generator dataset. It achieves the following results on the evaluation set:
- Loss: 4.2034
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 |
---|---|---|---|
6.2135 | 0.32 | 500 | 5.3711 |
4.8943 | 0.64 | 1000 | 4.9556 |
4.5853 | 0.97 | 1500 | 4.7291 |
4.3145 | 1.29 | 2000 | 4.5936 |
4.194 | 1.61 | 2500 | 4.4733 |
4.092 | 1.93 | 3000 | 4.3689 |
3.8879 | 2.26 | 3500 | 4.3218 |
3.832 | 2.58 | 4000 | 4.2572 |
3.788 | 2.9 | 4500 | 4.1919 |
3.6023 | 3.22 | 5000 | 4.1896 |
3.5435 | 3.54 | 5500 | 4.1565 |
3.5215 | 3.87 | 6000 | 4.1203 |
3.3703 | 4.19 | 6500 | 4.1263 |
3.2774 | 4.51 | 7000 | 4.1145 |
3.264 | 4.83 | 7500 | 4.1009 |
3.1767 | 5.15 | 8000 | 4.1080 |
3.0922 | 5.48 | 8500 | 4.1086 |
3.0931 | 5.8 | 9000 | 4.1067 |
Framework versions
- Transformers 4.26.1
- Pytorch 1.11.0+cu113
- Datasets 2.13.0
- Tokenizers 0.13.3