End of training

README.md

@@ -15,7 +15,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [facebook/detr-resnet-50](https://huggingface.co/facebook/detr-resnet-50) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.2379
+- Loss: 0.9698
 
 ## Model description
 
@@ -40,18 +40,15 @@ The following hyperparameters were used during training:
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- training_steps: 500
+- training_steps: 1000
 - mixed_precision_training: Native AMP
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| 1.8522        | 0.04  | 100  | 1.6469          |
-| 1.5573        | 0.08  | 200  | 1.4782          |
-| 1.3817        | 0.12  | 300  | 1.3473          |
-| 1.3319        | 0.16  | 400  | 1.2654          |
-| 1.2938        | 0.2   | 500  | 1.2379          |
+| 1.237         | 0.2   | 500  | 1.0990          |
+| 1.0403        | 0.4   | 1000 | 0.9698          |
 
 
 ### Framework versions