metadata
library_name: transformers
license: apache-2.0
base_model: hustvl/yolos-base
tags:
- generated_from_trainer
datasets:
- generator
model-index:
- name: fisheye8k_hustvl_yolos-base
results: []
fisheye8k_hustvl_yolos-base
This model is a fine-tuned version of hustvl/yolos-base on the generator dataset. It achieves the following results on the evaluation set:
- Loss: 2.4259
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: 5e-05
- train_batch_size: 32
- eval_batch_size: 8
- seed: 0
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: cosine
- num_epochs: 30
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 1.869 | 1.0 | 2644 | 2.4719 |
| 1.7653 | 2.0 | 5288 | 2.4479 |
| 1.6713 | 3.0 | 7932 | 2.4587 |
| 1.6485 | 4.0 | 10576 | 2.4582 |
| 1.5246 | 5.0 | 13220 | 2.3657 |
| 1.6017 | 6.0 | 15864 | 2.5125 |
| 1.4199 | 7.0 | 18508 | 2.5242 |
| 1.5472 | 8.0 | 21152 | 2.5324 |
| 1.4067 | 9.0 | 23796 | 2.2619 |
| 1.3167 | 10.0 | 26440 | 2.2793 |
| 1.1909 | 11.0 | 29084 | 2.4237 |
| 1.1875 | 12.0 | 31728 | 2.3808 |
| 1.2329 | 13.0 | 34372 | 2.3562 |
| 1.1447 | 14.0 | 37016 | 2.4259 |
Framework versions
- Transformers 4.48.3
- Pytorch 2.5.1+cu124
- Datasets 3.2.0
- Tokenizers 0.21.0