gpt2-xl-ft-with-non-challenging
This model is a fine-tuned version of gpt2-xl on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.4872
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: 4
- eval_batch_size: 4
- seed: 2020
- gradient_accumulation_steps: 32
- total_train_batch_size: 128
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 100.0
- num_epochs: 4
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| No log | 0.99 | 31 | 1.5517 |
| No log | 1.99 | 62 | 1.3733 |
| No log | 2.99 | 93 | 1.4207 |
| No log | 3.99 | 124 | 1.4872 |
Framework versions
- Transformers 4.17.0
- Pytorch 1.10.0+cu111
- Datasets 1.18.4
- Tokenizers 0.11.6
Perplexity
Score: 28.26373863220215
Dataset Size
Size: 5000