End of training

README.md

@@ -17,6 +17,8 @@ should probably proofread and complete it, then remove this comment. -->
 # fisheye8k_microsoft_conditional-detr-resnet-50
 
 This model is a fine-tuned version of [microsoft/conditional-detr-resnet-50](https://huggingface.co/microsoft/conditional-detr-resnet-50) on the generator dataset.
+It achieves the following results on the evaluation set:
+- Loss: 1.4379
 
 ## Model description
 
@@ -41,14 +43,20 @@ The following hyperparameters were used during training:
 - seed: 0
 - optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
 - lr_scheduler_type: cosine
-- num_epochs: 1
+- num_epochs: 36
 - mixed_precision_training: Native AMP
 
 ### Training results
 
-| Training Loss | Epoch | Step | Validation Loss |
-|:-------------:|:-----:|:----:|:---------------:|
-| No log        | 1.0   | 68   | 2.2581          |
+| Training Loss | Epoch | Step  | Validation Loss |
+|:-------------:|:-----:|:-----:|:---------------:|
+| 1.0059        | 1.0   | 5288  | 1.4506          |
+| 0.9022        | 2.0   | 10576 | 1.3697          |
+| 0.8475        | 3.0   | 15864 | 1.4314          |
+| 0.8099        | 4.0   | 21152 | 1.4027          |
+| 0.7604        | 5.0   | 26440 | 1.3805          |
+| 0.7556        | 6.0   | 31728 | 1.4091          |
+| 0.709         | 7.0   | 37016 | 1.4379          |
 
 
 ### Framework versions

runs/Feb12_20-50-19_mcity-rtx-4090/events.out.tfevents.1739411420.mcity-rtx-4090.11129.12

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1df0b89e65541dd5adaf9ccc72b5adf5109d623985b698d4d90da68e67912200
-size 11130
+oid sha256:0e6ccf387d27468ed409e3d75c1659581b2a27945c0ed35ae0b1bce1ee2d5f15
+size 24216