metadata
license: apache-2.0
base_model: facebook/detr-resnet-50
tags:
- generated_from_trainer
model-index:
- name: detr-amzss3-v2
results: []
detr-amzss3-v2
This model is a fine-tuned version of facebook/detr-resnet-50 on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.5846
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: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 25
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| No log | 0.54 | 1000 | 2.5308 |
| 2.824 | 1.08 | 2000 | 2.0484 |
| 2.824 | 1.62 | 3000 | 1.7408 |
| 1.8911 | 2.16 | 4000 | 1.5862 |
| 1.8911 | 2.7 | 5000 | 1.4858 |
| 1.594 | 3.24 | 6000 | 1.3551 |
| 1.594 | 3.78 | 7000 | 1.2802 |
| 1.4147 | 4.32 | 8000 | 1.2439 |
| 1.4147 | 4.86 | 9000 | 1.1548 |
| 1.2978 | 5.4 | 10000 | 1.1031 |
| 1.2978 | 5.94 | 11000 | 1.0674 |
| 1.1984 | 6.48 | 12000 | 1.0380 |
| 1.1086 | 7.02 | 13000 | 0.9949 |
| 1.1086 | 7.56 | 14000 | 0.9393 |
| 1.0383 | 8.1 | 15000 | 0.9204 |
| 1.0383 | 8.64 | 16000 | 0.8921 |
| 0.9817 | 9.18 | 17000 | 0.8670 |
| 0.9817 | 9.72 | 18000 | 0.8250 |
| 0.9277 | 10.26 | 19000 | 0.8084 |
| 0.9277 | 10.8 | 20000 | 0.7968 |
| 0.8864 | 11.34 | 21000 | 0.7928 |
| 0.8864 | 11.88 | 22000 | 0.7605 |
| 0.8525 | 12.42 | 23000 | 0.7602 |
| 0.8525 | 12.96 | 24000 | 0.7406 |
| 0.8197 | 13.5 | 25000 | 0.7224 |
| 0.7975 | 14.04 | 26000 | 0.7060 |
| 0.7975 | 14.58 | 27000 | 0.6893 |
| 0.7733 | 15.12 | 28000 | 0.6940 |
| 0.7733 | 15.66 | 29000 | 0.6836 |
| 0.7534 | 16.2 | 30000 | 0.6620 |
| 0.7534 | 16.74 | 31000 | 0.6584 |
| 0.7376 | 17.28 | 32000 | 0.6552 |
| 0.7376 | 17.82 | 33000 | 0.6487 |
| 0.7242 | 18.36 | 34000 | 0.6334 |
| 0.7242 | 18.9 | 35000 | 0.6319 |
| 0.7052 | 19.44 | 36000 | 0.6223 |
| 0.7052 | 19.98 | 37000 | 0.6155 |
| 0.6935 | 20.52 | 38000 | 0.6092 |
| 0.6816 | 21.06 | 39000 | 0.6079 |
| 0.6816 | 21.6 | 40000 | 0.6045 |
| 0.6747 | 22.14 | 41000 | 0.5997 |
| 0.6747 | 22.68 | 42000 | 0.6002 |
| 0.6693 | 23.22 | 43000 | 0.5924 |
| 0.6693 | 23.76 | 44000 | 0.5922 |
| 0.6608 | 24.3 | 45000 | 0.5861 |
| 0.6608 | 24.84 | 46000 | 0.5846 |
Framework versions
- Transformers 4.31.0
- Pytorch 2.0.1+cu118
- Datasets 2.13.1
- Tokenizers 0.13.3