metadata
base_model: toobiza/table-transformer-stellar-vortex-81
tags:
- generated_from_trainer
model-index:
- name: MT-ancient-spaceship-83
results: []
MT-ancient-spaceship-83
This model is a fine-tuned version of toobiza/table-transformer-stellar-vortex-81 on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.1689
- Loss Ce: 0.0000
- Loss Bbox: 0.0233
- Cardinality Error: 1.0
- Giou: 97.5276
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: 4
- eval_batch_size: 4
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3
Training results
| Training Loss | Epoch | Step | Validation Loss | Loss Ce | Loss Bbox | Cardinality Error | Giou |
|---|---|---|---|---|---|---|---|
| 0.2656 | 0.35 | 50 | 0.1849 | 0.0000 | 0.0252 | 1.0 | 97.2490 |
| 0.2505 | 0.69 | 100 | 0.1683 | 0.0000 | 0.0231 | 1.0 | 97.4814 |
| 0.1746 | 1.04 | 150 | 0.1701 | 0.0000 | 0.0235 | 1.0 | 97.4533 |
| 0.1786 | 1.39 | 200 | 0.1864 | 0.0000 | 0.0259 | 1.0 | 97.2923 |
| 0.1148 | 1.74 | 250 | 0.1786 | 0.0000 | 0.0246 | 1.0 | 97.4046 |
| 0.234 | 2.08 | 300 | 0.1673 | 0.0000 | 0.0230 | 1.0 | 97.5302 |
| 0.1654 | 2.43 | 350 | 0.1710 | 0.0000 | 0.0235 | 1.0 | 97.4826 |
| 0.1094 | 2.78 | 400 | 0.1689 | 0.0000 | 0.0233 | 1.0 | 97.5276 |
Framework versions
- Transformers 4.33.2
- Pytorch 2.0.1+cu118
- Datasets 2.14.5
- Tokenizers 0.13.3