IDEFICS (9B) fine-tuned on FloCo Dataset
This model is a fine-tuned version of HuggingFaceM4/idefics-9b on FloCo dataset for flowchart to code downstream task.
It achieves the following results on the test set:
- Loss: 0.724
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: 0.0002
- train_batch_size: 4
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 2
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.592 | 0.2 | 500 | 0.9356 |
| 0.5495 | 0.4 | 1000 | 1.0233 |
| 0.4865 | 0.59 | 1500 | 0.9564 |
| 0.4604 | 0.79 | 2000 | 0.9482 |
| 0.4551 | 0.99 | 2500 | 0.9146 |
| 0.3767 | 1.19 | 3000 | 0.9261 |
| 0.3894 | 1.39 | 3500 | 0.9387 |
| 0.3772 | 1.58 | 4000 | 0.9268 |
| 0.2707 | 1.78 | 4500 | 0.9420 |
| 0.3411 | 1.98 | 5000 | 0.9423 |
Framework versions
- Transformers 4.33.1
- Pytorch 2.0.1+cu118
- Datasets 2.14.5
- Tokenizers 0.13.3