End of training

README.md

@@ -16,7 +16,7 @@ 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: 0.9653
+- Loss: 6.3818
 
 ## Model description
 
@@ -35,30 +35,40 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 5e-05
+- learning_rate: 0.001
 - train_batch_size: 8
 - eval_batch_size: 8
 - seed: 42
 - 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
 - lr_scheduler_warmup_steps: 200
-- num_epochs: 10
+- num_epochs: 20
 - mixed_precision_training: Native AMP
 
 ### Training results
 
 | Training Loss | Epoch | Step  | Validation Loss |
 |:-------------:|:-----:|:-----:|:---------------:|
-| 1.3927        | 1.0   | 1000  | 1.3042          |
-| 1.2589        | 2.0   | 2000  | 1.1766          |
-| 1.236         | 3.0   | 3000  | 1.1331          |
-| 1.0805        | 4.0   | 4000  | 1.0722          |
-| 1.1195        | 5.0   | 5000  | 1.0177          |
-| 1.0664        | 6.0   | 6000  | 0.9897          |
-| 1.0407        | 7.0   | 7000  | 0.9765          |
-| 0.9804        | 8.0   | 8000  | 0.9538          |
-| 0.9385        | 9.0   | 9000  | 0.9482          |
-| 0.974         | 10.0  | 10000 | 0.9492          |
+| 3.9549        | 1.0   | 500   | 8.6487          |
+| 3.7386        | 2.0   | 1000  | 6.6653          |
+| 3.2303        | 3.0   | 1500  | 6.5420          |
+| 3.0704        | 4.0   | 2000  | 6.6156          |
+| 3.0275        | 5.0   | 2500  | 6.9053          |
+| 3.0644        | 6.0   | 3000  | 6.4292          |
+| 2.9575        | 7.0   | 3500  | 6.4167          |
+| 3.0707        | 8.0   | 4000  | 7.0283          |
+| 2.8764        | 9.0   | 4500  | 6.4162          |
+| 2.9142        | 10.0  | 5000  | 6.7128          |
+| 2.8474        | 11.0  | 5500  | 6.7765          |
+| 2.9095        | 12.0  | 6000  | 6.6026          |
+| 2.8555        | 13.0  | 6500  | 6.6679          |
+| 2.8619        | 14.0  | 7000  | 6.6986          |
+| 2.8407        | 15.0  | 7500  | 6.6944          |
+| 2.8214        | 16.0  | 8000  | 6.6572          |
+| 2.8244        | 17.0  | 8500  | 6.6596          |
+| 2.8092        | 18.0  | 9000  | 6.6372          |
+| 2.8896        | 19.0  | 9500  | 6.6237          |
+| 2.8422        | 20.0  | 10000 | 6.6249          |
 
 
 ### Framework versions

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dca91136375e16b4193441137110dccd4df3b9b04e4cb2703ab9448e8c6abf75
+oid sha256:a99e93e280570147d6fd73e076c4ce9d842de2ebe797639287a07966b2ebab1d
 size 166506812

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ad50e72cdffdce25a2220e55dda33e2419429a98ca488cecd0c71610e9818740
+oid sha256:0bf0ac20604c79c87894c1c0c46b5a7c70ffe0a05a74ed7b5ffeb17108a284ac
 size 5304