metadata
library_name: peft
tags:
- generated_from_trainer
base_model: ml6team/gpt2-small-german-finetune-oscar
model-index:
- name: ml6team-gpt2-small-german-finetune-oscar-peft
results: []
ml6team-gpt2-small-german-finetune-oscar-peft
This model is a fine-tuned version of ml6team/gpt2-small-german-finetune-oscar on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 4.5772
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: 0.0001
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 6
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 5.173 | 1.0 | 210 | 4.7734 |
| 4.6792 | 2.0 | 420 | 4.6458 |
| 4.5685 | 3.0 | 630 | 4.6042 |
| 4.2199 | 4.0 | 840 | 4.5872 |
| 4.7324 | 5.0 | 1050 | 4.5797 |
| 5.4576 | 6.0 | 1260 | 4.5772 |
Framework versions
- PEFT 0.8.2
- Transformers 4.38.1
- Pytorch 2.1.0+cu121
- Datasets 2.17.1
- Tokenizers 0.15.2