<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->
svo-1
This model is a fine-tuned version of gpt2 on the generator dataset. It achieves the following results on the evaluation set:
- Loss: 1.9072
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: 64
- eval_batch_size: 64
- seed: 42
- gradient_accumulation_steps: 8
- total_train_batch_size: 512
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_steps: 1000
- num_epochs: 9
- mixed_precision_training: Native AMP
Training results
Training Loss | Epoch | Step | Validation Loss |
---|---|---|---|
5.0334 | 0.73 | 200 | 2.5510 |
2.2609 | 1.45 | 400 | 2.0441 |
2.0306 | 2.18 | 600 | 1.9798 |
1.9782 | 2.91 | 800 | 1.9590 |
1.998 | 3.63 | 1000 | 1.9511 |
1.9482 | 4.36 | 1200 | 1.9366 |
1.9337 | 5.09 | 1400 | 1.9268 |
1.9093 | 5.82 | 1600 | 1.9175 |
1.8956 | 6.54 | 1800 | 1.9126 |
1.8789 | 7.27 | 2000 | 1.9094 |
1.8525 | 8.0 | 2200 | 1.9038 |
1.8325 | 8.73 | 2400 | 1.9072 |
Framework versions
- Transformers 4.26.1
- Pytorch 1.11.0+cu113
- Datasets 2.12.0
- Tokenizers 0.13.3