MSR-VTT-real-severe_kl06-model-run2
This model is a fine-tuned version of gpt2 on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 3.6472
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: 1e-05
- train_batch_size: 8
- eval_batch_size: 16
- seed: 42
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 100
- num_epochs: 10
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 3.8369 | 1.0 | 1497 | 3.8247 |
| 3.8025 | 2.0 | 2994 | 3.7228 |
| 3.6904 | 3.0 | 4491 | 3.6754 |
| 3.4678 | 4.0 | 5988 | 3.6495 |
| 3.4903 | 5.0 | 7485 | 3.6423 |
| 3.3191 | 6.0 | 8982 | 3.6382 |
| 3.4114 | 7.0 | 10479 | 3.6401 |
| 3.1887 | 8.0 | 11976 | 3.6421 |
| 3.2621 | 9.0 | 13473 | 3.6462 |
| 3.2633 | 10.0 | 14970 | 3.6472 |
Framework versions
- Transformers 4.46.3
- Pytorch 2.1.2+cu121
- Datasets 2.19.1
- Tokenizers 0.20.3
- Downloads last month
- 8
Model tree for AdoCleanCode/MSR-VTT-real-severe_kl06-model-run2
Base model
openai-community/gpt2