<!-- 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-fallen-sound-88
This model is a fine-tuned version of toobiza/MT-magic-puddle-87 on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.1833
- Loss Ce: 0.0000
- Loss Bbox: 0.0255
- Cardinality Error: 1.0
- Giou: 97.2211
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: 1
Training results
Training Loss | Epoch | Step | Validation Loss | Loss Ce | Loss Bbox | Cardinality Error | Giou |
---|---|---|---|---|---|---|---|
0.205 | 0.12 | 50 | 0.1765 | 0.0000 | 0.0244 | 1.0 | 97.2636 |
0.1372 | 0.24 | 100 | 0.1670 | 0.0000 | 0.0231 | 1.0 | 97.4171 |
0.1426 | 0.36 | 150 | 0.1839 | 0.0000 | 0.0256 | 1.0 | 97.2131 |
0.1115 | 0.48 | 200 | 0.1900 | 0.0000 | 0.0266 | 1.0 | 97.1456 |
0.1098 | 0.6 | 250 | 0.1832 | 0.0000 | 0.0256 | 1.0 | 97.2450 |
0.1451 | 0.72 | 300 | 0.1816 | 0.0000 | 0.0254 | 1.0 | 97.2632 |
0.1331 | 0.85 | 350 | 0.1793 | 0.0000 | 0.0250 | 1.0 | 97.2860 |
0.1401 | 0.97 | 400 | 0.1833 | 0.0000 | 0.0255 | 1.0 | 97.2211 |
Framework versions
- Transformers 4.33.2
- Pytorch 2.1.0+cu118
- Datasets 2.14.6
- Tokenizers 0.13.3