resnet50-finetuned-coco
This model is a fine-tuned version of microsoft/resnet-50 on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.0014
- Accuracy: 1.0
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: 2e-05
- train_batch_size: 32
- eval_batch_size: 32
- seed: 42
- 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: linear
- num_epochs: 30
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| No log | 1.0 | 1 | 0.0007 | 1.0 |
| No log | 2.0 | 2 | 0.0004 | 1.0 |
| No log | 3.0 | 3 | 0.0006 | 1.0 |
| No log | 4.0 | 4 | 0.0008 | 1.0 |
| No log | 5.0 | 5 | 0.0010 | 1.0 |
| No log | 6.0 | 6 | 0.0012 | 1.0 |
| No log | 7.0 | 7 | 0.0013 | 1.0 |
| No log | 8.0 | 8 | 0.0014 | 1.0 |
| No log | 9.0 | 9 | 0.0014 | 1.0 |
| No log | 10.0 | 10 | 0.0012 | 1.0 |
| No log | 11.0 | 11 | 0.0011 | 1.0 |
| No log | 12.0 | 12 | 0.0010 | 1.0 |
| No log | 13.0 | 13 | 0.0012 | 1.0 |
| No log | 14.0 | 14 | 0.0016 | 1.0 |
| No log | 15.0 | 15 | 0.0019 | 1.0 |
| No log | 16.0 | 16 | 0.0016 | 1.0 |
| No log | 17.0 | 17 | 0.0015 | 1.0 |
| No log | 18.0 | 18 | 0.0016 | 1.0 |
| No log | 19.0 | 19 | 0.0021 | 1.0 |
| No log | 20.0 | 20 | 0.0025 | 1.0 |
| No log | 21.0 | 21 | 0.0025 | 1.0 |
| No log | 22.0 | 22 | 0.0023 | 1.0 |
| No log | 23.0 | 23 | 0.0021 | 1.0 |
| No log | 24.0 | 24 | 0.0021 | 1.0 |
| No log | 25.0 | 25 | 0.0020 | 1.0 |
| No log | 26.0 | 26 | 0.0017 | 1.0 |
| No log | 27.0 | 27 | 0.0015 | 1.0 |
| No log | 28.0 | 28 | 0.0014 | 1.0 |
| No log | 29.0 | 29 | 0.0013 | 1.0 |
| No log | 30.0 | 30 | 0.0014 | 1.0 |
Framework versions
- Transformers 4.51.0
- Pytorch 2.6.0+cu124
- Datasets 3.5.0
- Tokenizers 0.21.1