best_model.pt

README.md

@@ -17,11 +17,11 @@ 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:
-- Accuracy: 0.9908
-- F1: 0.9910
-- Iou: 0.9832
-- Per Class Metrics: {0: {'f1': 0.99751, 'iou': 0.99504, 'accuracy': 0.99628}, 1: {'f1': 0.98091, 'iou': 0.96254, 'accuracy': 0.99081}, 2: {'f1': 0.73081, 'iou': 0.5758, 'accuracy': 0.99448}}
-- Loss: 0.0169
+- Accuracy: 0.9907
+- F1: 0.9909
+- Iou: 0.9830
+- Per Class Metrics: {0: {'f1': 0.99734, 'iou': 0.9947, 'accuracy': 0.99602}, 1: {'f1': 0.9807, 'iou': 0.96214, 'accuracy': 0.99071}, 2: {'f1': 0.74699, 'iou': 0.59616, 'accuracy': 0.99465}}
+- Loss: 0.0222
 
 ## Model description
 
@@ -53,16 +53,14 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step   |        | Class Metrics                                                                                                                                                               | Validation Loss |
 |:-------------:|:-----:|:------:|:------:|:---------------------------------------------------------------------------------------------------------------------------------------------------------------------------:|:---------------:|
-| 0.4586        | 5.0   | 12815  | 0.9710 | {0: {'f1': 0.99385, 'iou': 0.98778, 'accuracy': 0.99081}, 1: {'f1': 0.96879, 'iou': 0.93947, 'accuracy': 0.98478}, 2: {'f1': 0.62073, 'iou': 0.45004, 'accuracy': 0.99365}} | 0.0890          |
-| 0.4363        | 10.0  | 25630  | 0.9810 | {0: {'f1': 0.99729, 'iou': 0.9946, 'accuracy': 0.99595}, 1: {'f1': 0.97943, 'iou': 0.95969, 'accuracy': 0.99}, 2: {'f1': 0.6238, 'iou': 0.45327, 'accuracy': 0.99404}}      | 0.0220          |
-| 0.4148        | 15.0  | 38445  | 0.9785 | {0: {'f1': 0.99619, 'iou': 0.9924, 'accuracy': 0.99428}, 1: {'f1': 0.97538, 'iou': 0.95195, 'accuracy': 0.98824}, 2: {'f1': 0.71793, 'iou': 0.55998, 'accuracy': 0.99388}}  | 0.0593          |
-| 0.3935        | 20.0  | 51260  | 0.9743 | {0: {'f1': 0.99419, 'iou': 0.98845, 'accuracy': 0.99126}, 1: {'f1': 0.97367, 'iou': 0.94869, 'accuracy': 0.9874}, 2: {'f1': 0.67815, 'iou': 0.51303, 'accuracy': 0.99437}}  | 0.0229          |
-| 0.3755        | 25.0  | 64075  | 0.9826 | {0: {'f1': 0.99767, 'iou': 0.99534, 'accuracy': 0.99651}, 1: {'f1': 0.9796, 'iou': 0.96001, 'accuracy': 0.9902}, 2: {'f1': 0.71337, 'iou': 0.55445, 'accuracy': 0.99367}}   | 0.0187          |
-| 0.3834        | 30.0  | 76890  | 0.9814 | {0: {'f1': 0.99714, 'iou': 0.9943, 'accuracy': 0.99572}, 1: {'f1': 0.97847, 'iou': 0.95784, 'accuracy': 0.98967}, 2: {'f1': 0.71791, 'iou': 0.55995, 'accuracy': 0.99391}}  | 0.0175          |
-| 0.3609        | 35.0  | 89705  | 0.9832 | {0: {'f1': 0.99751, 'iou': 0.99504, 'accuracy': 0.99628}, 1: {'f1': 0.98091, 'iou': 0.96254, 'accuracy': 0.99081}, 2: {'f1': 0.73081, 'iou': 0.5758, 'accuracy': 0.99448}}  | 0.0169          |
-| 0.364         | 40.0  | 102520 | 0.9815 | {0: {'f1': 0.99756, 'iou': 0.99513, 'accuracy': 0.99635}, 1: {'f1': 0.97769, 'iou': 0.95635, 'accuracy': 0.98933}, 2: {'f1': 0.70736, 'iou': 0.54722, 'accuracy': 0.99295}} | 0.0210          |
-| 0.3561        | 45.0  | 115335 | 0.9857 | {0: {'f1': 0.99789, 'iou': 0.9958, 'accuracy': 0.99685}, 1: {'f1': 0.98385, 'iou': 0.96822, 'accuracy': 0.99221}, 2: {'f1': 0.77212, 'iou': 0.62883, 'accuracy': 0.99536}}  | 0.0208          |
-| 0.3714        | 50.0  | 128150 | 0.9843 | {0: {'f1': 0.99769, 'iou': 0.99539, 'accuracy': 0.99654}, 1: {'f1': 0.98205, 'iou': 0.96473, 'accuracy': 0.99135}, 2: {'f1': 0.75937, 'iou': 0.61209, 'accuracy': 0.99479}} | 0.0170          |
+| 0.486         | 5.0   | 12815  | 0.9750 | {0: {'f1': 0.99477, 'iou': 0.9896, 'accuracy': 0.99218}, 1: {'f1': 0.97507, 'iou': 0.95135, 'accuracy': 0.98779}, 2: {'f1': 0.59112, 'iou': 0.41956, 'accuracy': 0.99417}}  | 0.1010          |
+| 0.4424        | 10.0  | 25630  | 0.9841 | {0: {'f1': 0.99787, 'iou': 0.99575, 'accuracy': 0.99682}, 1: {'f1': 0.98309, 'iou': 0.96675, 'accuracy': 0.99173}, 2: {'f1': 0.67276, 'iou': 0.50689, 'accuracy': 0.99485}} | 0.0388          |
+| 0.398         | 15.0  | 38445  | 0.9800 | {0: {'f1': 0.99635, 'iou': 0.99272, 'accuracy': 0.99454}, 1: {'f1': 0.97804, 'iou': 0.95702, 'accuracy': 0.98935}, 2: {'f1': 0.71599, 'iou': 0.55762, 'accuracy': 0.99474}} | 0.0339          |
+| 0.3887        | 20.0  | 51260  | 0.9832 | {0: {'f1': 0.99697, 'iou': 0.99395, 'accuracy': 0.99546}, 1: {'f1': 0.98169, 'iou': 0.96404, 'accuracy': 0.99117}, 2: {'f1': 0.76483, 'iou': 0.61921, 'accuracy': 0.99548}} | 0.0228          |
+| 0.3765        | 25.0  | 64075  | 0.9830 | {0: {'f1': 0.99734, 'iou': 0.9947, 'accuracy': 0.99602}, 1: {'f1': 0.9807, 'iou': 0.96214, 'accuracy': 0.99071}, 2: {'f1': 0.74699, 'iou': 0.59616, 'accuracy': 0.99465}}   | 0.0222          |
+| 0.4094        | 30.0  | 76890  | 0.9848 | {0: {'f1': 0.99775, 'iou': 0.99551, 'accuracy': 0.99663}, 1: {'f1': 0.98255, 'iou': 0.9657, 'accuracy': 0.9916}, 2: {'f1': 0.7705, 'iou': 0.62667, 'accuracy': 0.99492}}    | 0.0345          |
+| 0.371         | 35.0  | 89705  | 0.9836 | {0: {'f1': 0.99757, 'iou': 0.99515, 'accuracy': 0.99636}, 1: {'f1': 0.98094, 'iou': 0.9626, 'accuracy': 0.99085}, 2: {'f1': 0.75391, 'iou': 0.60502, 'accuracy': 0.99445}}  | 0.0224          |
+| 0.3752        | 40.0  | 102520 | 0.9826 | {0: {'f1': 0.99777, 'iou': 0.99555, 'accuracy': 0.99666}, 1: {'f1': 0.97899, 'iou': 0.95885, 'accuracy': 0.98995}, 2: {'f1': 0.72023, 'iou': 0.56278, 'accuracy': 0.99326}} | 0.0243          |
 
 
 ### Framework versions

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4ce3f067b392776ac7157fe4900761b0fa9abbd906fee67cf580aaa07b307dcb
+oid sha256:8e91f4244cd5831c3d3576a58a2f76fc19c3a4832598f086fff05752c0afcd53
 size 2188724

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:553776a611c5811e0dcc9b040bb1da0cd9cdb7e5053d1c3d889eec34daf7779b
+oid sha256:7bc0003fb369f30447293964c2ab91ca6b6f80d2bfbc557992058ffc20878529
 size 5240