turkish-gpt2-M0-cleaned-wiki150k-10ep
This model is a fine-tuned version of openai-community/gpt2 on the None dataset. It achieves the following results on the evaluation set:
- Loss: 7.1603
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: 5e-05
- train_batch_size: 16
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 128
- total_train_batch_size: 2048
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_ratio: 0.03
- num_epochs: 10
- mixed_precision_training: Native AMP
Training results
Training Loss | Epoch | Step | Validation Loss |
---|---|---|---|
9.4897 | 0.99 | 67 | 8.5443 |
8.2445 | 1.99 | 134 | 8.2273 |
7.8728 | 3.0 | 202 | 7.9503 |
7.7012 | 3.99 | 269 | 7.6840 |
7.5584 | 4.99 | 336 | 7.4636 |
7.1518 | 5.99 | 404 | 7.3149 |
7.134 | 6.99 | 471 | 7.2364 |
6.9569 | 8.0 | 539 | 7.1841 |
7.0212 | 8.99 | 606 | 7.1634 |
6.9087 | 9.94 | 670 | 7.1603 |
Framework versions
- Transformers 4.39.3
- Pytorch 2.1.2
- Datasets 2.18.0
- Tokenizers 0.15.2
- Downloads last month
- 11