<!-- 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-cocnat-mod-datasets-txt-processing
This model is a fine-tuned version of gpt2 on the generator dataset. It achieves the following results on the evaluation set:
- Loss: 4.3377
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 |
---|---|---|---|
6.6848 | 0.3 | 500 | 5.6500 |
5.3379 | 0.59 | 1000 | 5.2204 |
4.9909 | 0.89 | 1500 | 4.9703 |
4.7146 | 1.19 | 2000 | 4.8200 |
4.5695 | 1.49 | 2500 | 4.7076 |
4.4685 | 1.78 | 3000 | 4.5985 |
4.3237 | 2.08 | 3500 | 4.5311 |
4.1614 | 2.38 | 4000 | 4.4731 |
4.1267 | 2.68 | 4500 | 4.4151 |
4.082 | 2.97 | 5000 | 4.3593 |
3.8448 | 3.27 | 5500 | 4.3575 |
3.8261 | 3.57 | 6000 | 4.3240 |
3.8089 | 3.86 | 6500 | 4.2887 |
3.6462 | 4.16 | 7000 | 4.2921 |
3.5453 | 4.46 | 7500 | 4.2840 |
3.529 | 4.76 | 8000 | 4.2688 |
3.4926 | 5.05 | 8500 | 4.2683 |
3.3463 | 5.35 | 9000 | 4.2715 |
3.3453 | 5.65 | 9500 | 4.2702 |
3.3408 | 5.95 | 10000 | 4.2694 |
Framework versions
- Transformers 4.26.1
- Pytorch 1.11.0+cu113
- Datasets 2.13.0
- Tokenizers 0.13.3