metadata
base_model: toobiza/MT-celestial-grass-58
tags:
- generated_from_trainer
model-index:
- name: MT-radiant-spaceship-60
results: []
MT-radiant-spaceship-60
This model is a fine-tuned version of toobiza/MT-celestial-grass-58 on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.6476
- Loss Ce: 0.0030
- Loss Bbox: 0.0949
- Cardinality Error: 1.0
- Giou: 91.4979
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: 2
- 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 |
|---|---|---|---|---|---|---|---|
| 0.4929 | 0.6 | 50 | 0.7752 | 0.0038 | 0.1130 | 1.0 | 89.6877 |
| 0.4067 | 1.19 | 100 | 0.6803 | 0.0034 | 0.0994 | 1.0 | 91.0025 |
| 0.3416 | 1.79 | 150 | 0.6697 | 0.0032 | 0.0980 | 1.0 | 91.1694 |
| 0.3604 | 2.38 | 200 | 0.6478 | 0.0031 | 0.0949 | 1.0 | 91.4886 |
| 0.3774 | 2.98 | 250 | 0.6476 | 0.0030 | 0.0949 | 1.0 | 91.4979 |
Framework versions
- Transformers 4.33.2
- Pytorch 2.0.1+cu118
- Datasets 2.14.5
- Tokenizers 0.13.3