End of training

README.md

@@ -14,12 +14,12 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [](https://huggingface.co/) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.0023
-- Mean Accuracy: 0.9805
-- Mean Iou: 0.9644
+- Loss: 0.0022
+- Mean Accuracy: 0.9808
+- Mean Iou: 0.9647
 - Overall Accuracy: 0.9842
-- Per Category Accuracy: [0.9872107703806055, 0.9628980699247084, 0.9914424002916333]
-- Per Category Iou: [0.9694201219759374, 0.9445663132786539, 0.9791793164178793]
+- Per Category Accuracy: [0.9872482620979998, 0.9640900882611239, 0.9909387706799166]
+- Per Category Iou: [0.9694678407121284, 0.9457909365231821, 0.9786919890621891]
 
 ## Model description
 
@@ -44,7 +44,7 @@ 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
-- num_epochs: 6
+- num_epochs: 70
 - mixed_precision_training: Native AMP
 
 ### Training results
@@ -338,6 +338,7 @@ The following hyperparameters were used during training:
 | 0.0066        | 285.0 | 100320 | 0.0021          | 0.9807        | 0.9646   | 0.9842           | [0.9874614966421243, 0.9636336084047874, 0.9909661884095016] | [0.9696797792200785, 0.9452806101403779, 0.9787193724244809] |
 | 0.0066        | 286.0 | 100672 | 0.0021          | 0.9805        | 0.9644   | 0.9842           | [0.9874145950624751, 0.9628353825532281, 0.991339217404724]  | [0.9696226586547914, 0.944525139001777, 0.9790743681300117]  |
 | 0.0065        | 287.0 | 101024 | 0.0023          | 0.9805        | 0.9644   | 0.9842           | [0.9872107703806055, 0.9628980699247084, 0.9914424002916333] | [0.9694201219759374, 0.9445663132786539, 0.9791793164178793] |
+| 0.0065        | 288.0 | 101376 | 0.0022          | 0.9808        | 0.9647   | 0.9842           | [0.9872482620979998, 0.9640900882611239, 0.9909387706799166] | [0.9694678407121284, 0.9457909365231821, 0.9786919890621891] |
 
 
 ### Framework versions

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bee0b2ac5855905e1169716984cca54c4da9006988d38063cbd4bbcf8a681f29
+oid sha256:31f72034a01d7af422e54ef40be142901a781868f918c7a73235c78f4911d225
 size 109447092