rnud/detr-resnet50-finetuning-watermark-pita

README.md

@@ -16,6 +16,8 @@ should probably proofread and complete it, then remove this comment. -->
 # detr-resnet-50_finetuned
 
 This model is a fine-tuned version of [facebook/detr-resnet-50](https://huggingface.co/facebook/detr-resnet-50) on the imagefolder dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.2007
 
 ## Model description
 
@@ -35,8 +37,8 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 5e-06
-- train_batch_size: 16
-- eval_batch_size: 8
+- train_batch_size: 24
+- eval_batch_size: 24
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
@@ -44,6 +46,18 @@ The following hyperparameters were used during training:
 
 ### Training results
 
+| Training Loss | Epoch | Step | Validation Loss |
+|:-------------:|:-----:|:----:|:---------------:|
+| 3.9043        | 0.19  | 100  | 3.6582          |
+| 3.5906        | 0.38  | 200  | 3.2844          |
+| 3.017         | 0.57  | 300  | 2.5393          |
+| 2.1941        | 0.76  | 400  | 1.6635          |
+| 1.3016        | 0.96  | 500  | 0.8641          |
+| 0.5168        | 1.15  | 600  | 0.1779          |
+| 0.1458        | 1.34  | 700  | 0.1120          |
+| 0.1216        | 1.53  | 800  | 0.1721          |
+| 0.1027        | 1.72  | 900  | 0.1901          |
+| 0.0967        | 1.91  | 1000 | 0.2007          |
 
 
 ### Framework versions

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b16a5eecc9acf4db0de6cf064f6343cf445077fd0451a30d56c9228e67655a50
+oid sha256:7bb055875f8947cf7593bdebd83c158138c241f1f57f44d9df4d47bac9001d39
 size 166495852

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:43d5a3ca16e2148a341a330ac1eddde444602ec31dc601229915d3c7a05587af
+oid sha256:ccad9d2bd0fd93dcb1d93e069d40b9353c80c7ff66b6994cb5b9668871696a45
 size 4728