metadata
license: mit
tags:
- generated_from_trainer
datasets:
- generator
model-index:
- name: gutenberg-no-merge-rarity-6p5k
results: []
gutenberg-no-merge-rarity-6p5k
This model is a fine-tuned version of gpt2 on the generator dataset. It achieves the following results on the evaluation set:
- Loss: 4.0791
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: 128
- eval_batch_size: 128
- 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 |
|---|---|---|---|
| 6.2206 | 0.58 | 500 | 5.1052 |
| 4.7954 | 1.16 | 1000 | 4.6615 |
| 4.4101 | 1.74 | 1500 | 4.3895 |
| 4.1133 | 2.33 | 2000 | 4.2397 |
| 3.9572 | 2.91 | 2500 | 4.1257 |
| 3.7283 | 3.49 | 3000 | 4.0785 |
| 3.6356 | 4.07 | 3500 | 4.0313 |
| 3.4289 | 4.65 | 4000 | 4.0056 |
| 3.3393 | 5.23 | 4500 | 3.9986 |
| 3.2334 | 5.81 | 5000 | 3.9949 |
Framework versions
- Transformers 4.26.1
- Pytorch 1.11.0+cu113
- Datasets 2.13.0
- Tokenizers 0.13.3