<!-- 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-guten-mod-rm-refrences-1p7k
This model is a fine-tuned version of gpt2 on the generator dataset. It achieves the following results on the evaluation set:
- Loss: 3.1577
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 |
---|---|---|---|
6.6974 | 0.29 | 500 | 5.6415 |
5.3331 | 0.58 | 1000 | 5.1970 |
4.9805 | 0.88 | 1500 | 4.9464 |
4.7094 | 1.17 | 2000 | 4.7978 |
4.5465 | 1.46 | 2500 | 4.6746 |
4.4438 | 1.75 | 3000 | 4.5714 |
4.3256 | 2.04 | 3500 | 4.4890 |
4.1252 | 2.34 | 4000 | 4.4453 |
4.0923 | 2.63 | 4500 | 4.3874 |
4.0485 | 2.92 | 5000 | 4.3318 |
3.8592 | 3.21 | 5500 | 4.3258 |
3.7904 | 3.5 | 6000 | 4.2931 |
3.7755 | 3.79 | 6500 | 4.2598 |
3.6816 | 4.09 | 7000 | 4.2575 |
3.5062 | 4.38 | 7500 | 4.2557 |
3.4984 | 4.67 | 8000 | 4.2391 |
3.4904 | 4.96 | 8500 | 4.2253 |
3.334 | 5.25 | 9000 | 4.2373 |
3.3045 | 5.55 | 9500 | 4.2375 |
3.3115 | 5.84 | 10000 | 4.2364 |
Framework versions
- Transformers 4.26.1
- Pytorch 1.11.0+cu113
- Datasets 2.13.0
- Tokenizers 0.13.3