Commit
•
6e49875
1
Parent(s):
ba1f39a
update model card README.md
Browse files
README.md
CHANGED
|
@@ -16,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 16 |
|
| 17 |
This model is a fine-tuned version of [facebook/detr-resnet-50](https://huggingface.co/facebook/detr-resnet-50) on the cd45rb dataset.
|
| 18 |
It achieves the following results on the evaluation set:
|
| 19 |
-
- Loss: 1.
|
| 20 |
|
| 21 |
## Model description
|
| 22 |
|
|
@@ -41,23 +41,38 @@ The following hyperparameters were used during training:
|
|
| 41 |
- seed: 42
|
| 42 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 43 |
- lr_scheduler_type: linear
|
| 44 |
-
- num_epochs:
|
| 45 |
- mixed_precision_training: Native AMP
|
| 46 |
|
| 47 |
### Training results
|
| 48 |
|
| 49 |
-
| Training Loss | Epoch | Step
|
| 50 |
-
|
| 51 |
-
| 2.4794 | 1.0 | 4606
|
| 52 |
-
| 2.2469 | 2.0 | 9212
|
| 53 |
-
| 2.1817 | 3.0 | 13818
|
| 54 |
-
| 2.1418 | 4.0 | 18424
|
| 55 |
-
| 2.118 | 5.0 | 23030
|
| 56 |
-
| 2.1237 | 6.0 | 27636
|
| 57 |
-
| 2.1025 | 7.0 | 32242
|
| 58 |
-
| 2.0796 | 8.0 | 36848
|
| 59 |
-
| 2.0672 | 9.0 | 41454
|
| 60 |
-
| 2.0597 | 10.0 | 46060
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 61 |
|
| 62 |
|
| 63 |
### Framework versions
|
|
|
|
| 16 |
|
| 17 |
This model is a fine-tuned version of [facebook/detr-resnet-50](https://huggingface.co/facebook/detr-resnet-50) on the cd45rb dataset.
|
| 18 |
It achieves the following results on the evaluation set:
|
| 19 |
+
- Loss: 1.5794
|
| 20 |
|
| 21 |
## Model description
|
| 22 |
|
|
|
|
| 41 |
- seed: 42
|
| 42 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 43 |
- lr_scheduler_type: linear
|
| 44 |
+
- num_epochs: 25
|
| 45 |
- mixed_precision_training: Native AMP
|
| 46 |
|
| 47 |
### Training results
|
| 48 |
|
| 49 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
| 50 |
+
|:-------------:|:-----:|:------:|:---------------:|
|
| 51 |
+
| 2.4794 | 1.0 | 4606 | 1.8245 |
|
| 52 |
+
| 2.2469 | 2.0 | 9212 | 1.7593 |
|
| 53 |
+
| 2.1817 | 3.0 | 13818 | 1.7109 |
|
| 54 |
+
| 2.1418 | 4.0 | 18424 | 1.6976 |
|
| 55 |
+
| 2.118 | 5.0 | 23030 | 1.6695 |
|
| 56 |
+
| 2.1237 | 6.0 | 27636 | 1.6781 |
|
| 57 |
+
| 2.1025 | 7.0 | 32242 | 1.6574 |
|
| 58 |
+
| 2.0796 | 8.0 | 36848 | 1.6418 |
|
| 59 |
+
| 2.0672 | 9.0 | 41454 | 1.6333 |
|
| 60 |
+
| 2.0597 | 10.0 | 46060 | 1.6313 |
|
| 61 |
+
| 2.0948 | 11.0 | 50666 | 1.6546 |
|
| 62 |
+
| 2.0943 | 12.0 | 55272 | 1.6905 |
|
| 63 |
+
| 2.0819 | 13.0 | 59878 | 1.6430 |
|
| 64 |
+
| 2.0795 | 14.0 | 64484 | 1.6439 |
|
| 65 |
+
| 2.0566 | 15.0 | 69090 | 1.6449 |
|
| 66 |
+
| 2.0435 | 16.0 | 73696 | 1.6204 |
|
| 67 |
+
| 2.0375 | 17.0 | 78302 | 1.6195 |
|
| 68 |
+
| 2.032 | 18.0 | 82908 | 1.6128 |
|
| 69 |
+
| 2.0079 | 19.0 | 87514 | 1.6082 |
|
| 70 |
+
| 1.9985 | 20.0 | 92120 | 1.6037 |
|
| 71 |
+
| 1.9976 | 21.0 | 96726 | 1.6005 |
|
| 72 |
+
| 1.9887 | 22.0 | 101332 | 1.5969 |
|
| 73 |
+
| 1.9841 | 23.0 | 105938 | 1.5841 |
|
| 74 |
+
| 1.9763 | 24.0 | 110544 | 1.5826 |
|
| 75 |
+
| 1.9686 | 25.0 | 115150 | 1.5794 |
|
| 76 |
|
| 77 |
|
| 78 |
### Framework versions
|