|
--- |
|
base_model: toobiza/table-transformer-stellar-vortex-81 |
|
tags: |
|
- generated_from_trainer |
|
model-index: |
|
- name: MT-ancient-spaceship-83 |
|
results: [] |
|
--- |
|
|
|
<!-- 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. --> |
|
|
|
# MT-ancient-spaceship-83 |
|
|
|
This model is a fine-tuned version of [toobiza/table-transformer-stellar-vortex-81](https://huggingface.co/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 |
|
|
