<!-- 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-aochildes-seed
This model is a fine-tuned version of gpt2 on the generator dataset. It achieves the following results on the evaluation set:
- Loss: 4.1340
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 |
---|---|---|---|
6.3718 | 0.3 | 500 | 5.3790 |
5.0628 | 0.61 | 1000 | 4.9618 |
4.7469 | 0.91 | 1500 | 4.7198 |
4.4602 | 1.21 | 2000 | 4.5799 |
4.316 | 1.52 | 2500 | 4.4545 |
4.2172 | 1.82 | 3000 | 4.3495 |
4.0599 | 2.12 | 3500 | 4.2880 |
3.9243 | 2.43 | 4000 | 4.2333 |
3.895 | 2.73 | 4500 | 4.1796 |
3.8241 | 3.03 | 5000 | 4.1375 |
3.6165 | 3.34 | 5500 | 4.1275 |
3.6128 | 3.64 | 6000 | 4.0945 |
3.5876 | 3.94 | 6500 | 4.0622 |
3.3787 | 4.25 | 7000 | 4.0709 |
3.3459 | 4.55 | 7500 | 4.0590 |
3.3307 | 4.85 | 8000 | 4.0475 |
3.2357 | 5.16 | 8500 | 4.0557 |
3.1582 | 5.46 | 9000 | 4.0548 |
3.1553 | 5.76 | 9500 | 4.0532 |
Framework versions
- Transformers 4.26.1
- Pytorch 1.11.0+cu113
- Datasets 2.13.0
- Tokenizers 0.13.3