metadata
tags:
- generated_from_trainer
model-index:
- name: gpt2-wikitext2
results: []
gpt2-wikitext2
This model was trained from scratch on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.1674
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: 0.001
- train_batch_size: 32
- eval_batch_size: 32
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 128
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_steps: 100
- num_epochs: 5
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 1.4222 | 1.0 | 2916 | 0.7671 |
| 0.7233 | 2.0 | 5832 | 0.5135 |
| 0.4245 | 3.0 | 8748 | 0.2865 |
| 0.2039 | 4.0 | 11664 | 0.1831 |
| 0.1082 | 5.0 | 14580 | 0.1674 |
Framework versions
- Transformers 4.41.2
- Pytorch 2.2.1+cu121
- Datasets 2.19.1
- Tokenizers 0.19.1