|
--- |
|
library_name: transformers |
|
license: apache-2.0 |
|
base_model: facebook/detr-resnet-50 |
|
tags: |
|
- generated_from_trainer |
|
model-index: |
|
- name: chickens |
|
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. --> |
|
|
|
# chickens |
|
|
|
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: 0.2255 |
|
|
|
## 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: 1 |
|
- eval_batch_size: 8 |
|
- seed: 42 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: cosine |
|
- num_epochs: 60 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | |
|
|:-------------:|:-----:|:----:|:---------------:| |
|
| 1.3378 | 1.0 | 91 | 1.3023 | |
|
| 1.1687 | 2.0 | 182 | 1.2356 | |
|
| 1.1632 | 3.0 | 273 | 1.5895 | |
|
| 1.1376 | 4.0 | 364 | 1.1306 | |
|
| 1.1423 | 5.0 | 455 | 1.0930 | |
|
| 1.1145 | 6.0 | 546 | 1.0959 | |
|
| 1.0688 | 7.0 | 637 | 1.0771 | |
|
| 1.023 | 8.0 | 728 | 1.0335 | |
|
| 0.903 | 9.0 | 819 | 0.7363 | |
|
| 0.7509 | 10.0 | 910 | 0.6334 | |
|
| 0.6647 | 11.0 | 1001 | 0.5965 | |
|
| 0.6905 | 12.0 | 1092 | 0.5033 | |
|
| 0.6026 | 13.0 | 1183 | 0.6362 | |
|
| 0.6277 | 14.0 | 1274 | 0.5105 | |
|
| 0.6512 | 15.0 | 1365 | 0.8271 | |
|
| 0.6475 | 16.0 | 1456 | 0.5431 | |
|
| 0.6032 | 17.0 | 1547 | 0.5745 | |
|
| 0.6074 | 18.0 | 1638 | 0.6850 | |
|
| 0.6 | 19.0 | 1729 | 0.4973 | |
|
| 0.4883 | 20.0 | 1820 | 0.4620 | |
|
| 0.4947 | 21.0 | 1911 | 0.5086 | |
|
| 0.5285 | 22.0 | 2002 | 0.5820 | |
|
| 0.5418 | 23.0 | 2093 | 0.4808 | |
|
| 0.5035 | 24.0 | 2184 | 0.4725 | |
|
| 0.5704 | 25.0 | 2275 | 0.4552 | |
|
| 0.5119 | 26.0 | 2366 | 0.4938 | |
|
| 0.4257 | 27.0 | 2457 | 0.4098 | |
|
| 0.4515 | 28.0 | 2548 | 0.4158 | |
|
| 0.4187 | 29.0 | 2639 | 0.4161 | |
|
| 0.4253 | 30.0 | 2730 | 0.3548 | |
|
| 0.4064 | 31.0 | 2821 | 0.4722 | |
|
| 0.4232 | 32.0 | 2912 | 0.3252 | |
|
| 0.4159 | 33.0 | 3003 | 0.3488 | |
|
| 0.3839 | 34.0 | 3094 | 0.2988 | |
|
| 0.4048 | 35.0 | 3185 | 0.3541 | |
|
| 0.4024 | 36.0 | 3276 | 0.3188 | |
|
| 0.3765 | 37.0 | 3367 | 0.3627 | |
|
| 0.4028 | 38.0 | 3458 | 0.3287 | |
|
| 0.3795 | 39.0 | 3549 | 0.3447 | |
|
| 0.3425 | 40.0 | 3640 | 0.2702 | |
|
| 0.3646 | 41.0 | 3731 | 0.2913 | |
|
| 0.3513 | 42.0 | 3822 | 0.2911 | |
|
| 0.3461 | 43.0 | 3913 | 0.3127 | |
|
| 0.357 | 44.0 | 4004 | 0.2962 | |
|
| 0.3259 | 45.0 | 4095 | 0.2790 | |
|
| 0.3224 | 46.0 | 4186 | 0.2586 | |
|
| 0.3257 | 47.0 | 4277 | 0.2481 | |
|
| 0.3024 | 48.0 | 4368 | 0.2562 | |
|
| 0.2875 | 49.0 | 4459 | 0.2430 | |
|
| 0.3044 | 50.0 | 4550 | 0.2334 | |
|
| 0.2921 | 51.0 | 4641 | 0.2371 | |
|
| 0.2843 | 52.0 | 4732 | 0.2218 | |
|
| 0.2971 | 53.0 | 4823 | 0.2360 | |
|
| 0.2789 | 54.0 | 4914 | 0.2430 | |
|
| 0.2916 | 55.0 | 5005 | 0.2334 | |
|
| 0.266 | 56.0 | 5096 | 0.2248 | |
|
| 0.286 | 57.0 | 5187 | 0.2305 | |
|
| 0.2759 | 58.0 | 5278 | 0.2234 | |
|
| 0.2768 | 59.0 | 5369 | 0.2271 | |
|
| 0.285 | 60.0 | 5460 | 0.2255 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.44.2 |
|
- Pytorch 2.4.1+cu121 |
|
- Datasets 2.14.4 |
|
- Tokenizers 0.19.1 |
|
|
