|
|
--- |
|
|
license: apache-2.0 |
|
|
base_model: facebook/detr-resnet-50 |
|
|
tags: |
|
|
- generated_from_trainer |
|
|
model-index: |
|
|
- name: detr-resnet-50-base-coco |
|
|
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. --> |
|
|
|
|
|
# detr-resnet-50-base-coco |
|
|
|
|
|
This model is a fine-tuned version of [facebook/detr-resnet-50](https://huggingface.co/facebook/detr-resnet-50) on the None dataset. |
|
|
It achieves the following results on the evaluation set: |
|
|
- Loss: 6389.5527 |
|
|
|
|
|
## 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: 8 |
|
|
- eval_batch_size: 8 |
|
|
- seed: 1337 |
|
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
|
- lr_scheduler_type: linear |
|
|
- num_epochs: 50.0 |
|
|
|
|
|
### Training results |
|
|
|
|
|
| Training Loss | Epoch | Step | Validation Loss | |
|
|
|:-------------:|:-----:|:----:|:---------------:| |
|
|
| No log | 1.0 | 4 | 6398.5273 | |
|
|
| No log | 2.0 | 8 | 6397.9268 | |
|
|
| 6175.8695 | 3.0 | 12 | 6397.2480 | |
|
|
| 6175.8695 | 4.0 | 16 | 6396.5649 | |
|
|
| 6292.1676 | 5.0 | 20 | 6396.0669 | |
|
|
| 6292.1676 | 6.0 | 24 | 6395.6597 | |
|
|
| 6292.1676 | 7.0 | 28 | 6395.2739 | |
|
|
| 6230.1191 | 8.0 | 32 | 6394.8906 | |
|
|
| 6230.1191 | 9.0 | 36 | 6394.6680 | |
|
|
| 6089.0629 | 10.0 | 40 | 6394.5151 | |
|
|
| 6089.0629 | 11.0 | 44 | 6394.3691 | |
|
|
| 6089.0629 | 12.0 | 48 | 6394.3931 | |
|
|
| 6266.6961 | 13.0 | 52 | 6394.3232 | |
|
|
| 6266.6961 | 14.0 | 56 | 6394.1572 | |
|
|
| 6383.0688 | 15.0 | 60 | 6394.1558 | |
|
|
| 6383.0688 | 16.0 | 64 | 6393.9531 | |
|
|
| 6383.0688 | 17.0 | 68 | 6393.7720 | |
|
|
| 6323.732 | 18.0 | 72 | 6393.6050 | |
|
|
| 6323.732 | 19.0 | 76 | 6393.5107 | |
|
|
| 6262.8367 | 20.0 | 80 | 6393.2305 | |
|
|
| 6262.8367 | 21.0 | 84 | 6393.0869 | |
|
|
| 6262.8367 | 22.0 | 88 | 6392.7910 | |
|
|
| 6294.5953 | 23.0 | 92 | 6392.6079 | |
|
|
| 6294.5953 | 24.0 | 96 | 6392.4634 | |
|
|
| 6454.1902 | 25.0 | 100 | 6392.3086 | |
|
|
| 6454.1902 | 26.0 | 104 | 6392.1982 | |
|
|
| 6454.1902 | 27.0 | 108 | 6391.9668 | |
|
|
| 6325.2328 | 28.0 | 112 | 6391.6533 | |
|
|
| 6325.2328 | 29.0 | 116 | 6391.3481 | |
|
|
| 6471.3637 | 30.0 | 120 | 6391.0474 | |
|
|
| 6471.3637 | 31.0 | 124 | 6390.9409 | |
|
|
| 6471.3637 | 32.0 | 128 | 6390.8198 | |
|
|
| 6308.2656 | 33.0 | 132 | 6390.6738 | |
|
|
| 6308.2656 | 34.0 | 136 | 6390.6689 | |
|
|
| 6352.0371 | 35.0 | 140 | 6390.6245 | |
|
|
| 6352.0371 | 36.0 | 144 | 6390.5791 | |
|
|
| 6352.0371 | 37.0 | 148 | 6390.4199 | |
|
|
| 6247.1492 | 38.0 | 152 | 6390.2305 | |
|
|
| 6247.1492 | 39.0 | 156 | 6390.0776 | |
|
|
| 6385.748 | 40.0 | 160 | 6389.9873 | |
|
|
| 6385.748 | 41.0 | 164 | 6389.9185 | |
|
|
| 6385.748 | 42.0 | 168 | 6389.8281 | |
|
|
| 6262.0703 | 43.0 | 172 | 6389.75 | |
|
|
| 6262.0703 | 44.0 | 176 | 6389.6792 | |
|
|
| 6256.2105 | 45.0 | 180 | 6389.6377 | |
|
|
| 6256.2105 | 46.0 | 184 | 6389.6201 | |
|
|
| 6256.2105 | 47.0 | 188 | 6389.5728 | |
|
|
| 6353.4496 | 48.0 | 192 | 6389.5518 | |
|
|
| 6353.4496 | 49.0 | 196 | 6389.5415 | |
|
|
| 6211.1777 | 50.0 | 200 | 6389.5527 | |
|
|
|
|
|
|
|
|
### Framework versions |
|
|
|
|
|
- Transformers 4.32.0.dev0 |
|
|
- Pytorch 2.0.0+cu117 |
|
|
- Datasets 2.13.1 |
|
|
- Tokenizers 0.13.3 |
|
|
|
