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: 0.751
-- F1: 0.7007
-- Iou: 0.6578
-- Per Class Metrics: {0: {'f1': 0.93537, 'iou': 0.87858, 'accuracy': 0.89701}, 1: {'f1': 0.00136, 'iou': 0.00068, 'accuracy': 0.75764}, 2: {'f1': 0.06828, 'iou': 0.03534, 'accuracy': 0.84736}}
-- Loss: 0.2892
+- Accuracy: 0.9734
+- F1: 0.9770
+- Iou: 0.9606
+- Per Class Metrics: {0: {'f1': 0.99208, 'iou': 0.98429, 'accuracy': 0.98821}, 1: {'f1': 0.95742, 'iou': 0.91831, 'accuracy': 0.97945}, 2: {'f1': 0.27975, 'iou': 0.16263, 'accuracy': 0.97907}}
+- Loss: 0.5105
 
 ## Model description
 
@@ -41,8 +41,8 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 5e-05
-- train_batch_size: 16
-- eval_batch_size: 16
+- 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: cosine
@@ -53,16 +53,25 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch  | Step |        | Class Metrics                                                                                                                                                               | Validation Loss |
 |:-------------:|:------:|:----:|:------:|:---------------------------------------------------------------------------------------------------------------------------------------------------------------------------:|:---------------:|
-| 1.3706        | 0.0503 | 129  | 0.5872 | {0: {'f1': 0.87714, 'iou': 0.78117, 'accuracy': 0.79448}, 1: {'f1': 0.02192, 'iou': 0.01108, 'accuracy': 0.75978}, 2: {'f1': 0.02579, 'iou': 0.01306, 'accuracy': 0.92055}} | 0.7931          |
-| 1.3475        | 0.1007 | 258  | 0.6049 | {0: {'f1': 0.89335, 'iou': 0.80725, 'accuracy': 0.82306}, 1: {'f1': 0.00699, 'iou': 0.00351, 'accuracy': 0.75822}, 2: {'f1': 0.03921, 'iou': 0.02, 'accuracy': 0.9063}}     | 0.8077          |
-| 1.314         | 0.1510 | 387  | 0.6145 | {0: {'f1': 0.90137, 'iou': 0.82045, 'accuracy': 0.83764}, 1: {'f1': 0.00437, 'iou': 0.00219, 'accuracy': 0.75795}, 2: {'f1': 0.04874, 'iou': 0.02498, 'accuracy': 0.89464}} | 0.8870          |
-| 1.2312        | 0.2013 | 516  | 0.6293 | {0: {'f1': 0.91322, 'iou': 0.8403, 'accuracy': 0.85871}, 1: {'f1': 0.00281, 'iou': 0.00141, 'accuracy': 0.75779}, 2: {'f1': 0.07211, 'iou': 0.0374, 'accuracy': 0.8804}}    | 0.7470          |
-| 1.1804        | 0.2517 | 645  | 0.6281 | {0: {'f1': 0.91249, 'iou': 0.83907, 'accuracy': 0.85677}, 1: {'f1': 0.00118, 'iou': 0.00059, 'accuracy': 0.75763}, 2: {'f1': 0.05673, 'iou': 0.02919, 'accuracy': 0.88627}} | 0.7072          |
-| 1.1589        | 0.3020 | 774  | 0.6482 | {0: {'f1': 0.92806, 'iou': 0.86578, 'accuracy': 0.88431}, 1: {'f1': 0.00139, 'iou': 0.0007, 'accuracy': 0.75765}, 2: {'f1': 0.05919, 'iou': 0.0305, 'accuracy': 0.85981}}   | 0.7884          |
-| 1.1051        | 0.3523 | 903  | 0.6578 | {0: {'f1': 0.93537, 'iou': 0.87858, 'accuracy': 0.89701}, 1: {'f1': 0.00136, 'iou': 0.00068, 'accuracy': 0.75764}, 2: {'f1': 0.06828, 'iou': 0.03534, 'accuracy': 0.84736}} | 0.2892          |
-| 1.1124        | 0.4027 | 1032 | 0.6757 | {0: {'f1': 0.94871, 'iou': 0.90242, 'accuracy': 0.91917}, 1: {'f1': 0.00227, 'iou': 0.00114, 'accuracy': 0.75773}, 2: {'f1': 0.0752, 'iou': 0.03907, 'accuracy': 0.83245}}  | 0.3254          |
-| 1.0974        | 0.4530 | 1161 | 0.6703 | {0: {'f1': 0.94456, 'iou': 0.89494, 'accuracy': 0.91241}, 1: {'f1': 0.00375, 'iou': 0.00188, 'accuracy': 0.75789}, 2: {'f1': 0.07252, 'iou': 0.03762, 'accuracy': 0.83578}} | 0.4061          |
-| 1.0794        | 0.5033 | 1290 | 0.6495 | {0: {'f1': 0.92905, 'iou': 0.8675, 'accuracy': 0.88626}, 1: {'f1': 0.0021, 'iou': 0.00105, 'accuracy': 0.75771}, 2: {'f1': 0.06575, 'iou': 0.03399, 'accuracy': 0.85601}}   | 0.4402          |
+| No log        | 0.0503 | 86   | 0.1155 | {0: {'f1': 1e-05, 'iou': 0.0, 'accuracy': 0.25189}, 1: {'f1': 0.64518, 'iou': 0.47621, 'accuracy': 0.86451}, 2: {'f1': 0.00676, 'iou': 0.00339, 'accuracy': 0.13587}}       | 1.0017          |
+| 1.2378        | 0.1006 | 172  | 0.0635 | {0: {'f1': 2e-05, 'iou': 1e-05, 'accuracy': 0.25181}, 1: {'f1': 0.41464, 'iou': 0.26154, 'accuracy': 0.81337}, 2: {'f1': 0.01135, 'iou': 0.00571, 'accuracy': 0.07762}}     | 0.9440          |
+| 1.2207        | 0.1510 | 258  | 0.0554 | {0: {'f1': 0.0, 'iou': 0.0, 'accuracy': 0.25189}, 1: {'f1': 0.37135, 'iou': 0.22801, 'accuracy': 0.80693}, 2: {'f1': 0.01383, 'iou': 0.00696, 'accuracy': 0.0683}}          | 0.9237          |
+| 1.1925        | 0.2013 | 344  | 0.0499 | {0: {'f1': 0.0, 'iou': 0.0, 'accuracy': 0.2519}, 1: {'f1': 0.34062, 'iou': 0.20527, 'accuracy': 0.80395}, 2: {'f1': 0.0169, 'iou': 0.00852, 'accuracy': 0.06157}}           | 0.9326          |
+| 1.1606        | 0.2516 | 430  | 0.0647 | {0: {'f1': 0.0, 'iou': 0.0, 'accuracy': 0.2519}, 1: {'f1': 0.42092, 'iou': 0.26656, 'accuracy': 0.81803}, 2: {'f1': 0.01824, 'iou': 0.0092, 'accuracy': 0.07944}}           | 0.9245          |
+| 1.1299        | 0.3019 | 516  | 0.1179 | {0: {'f1': 0.00055, 'iou': 0.00027, 'accuracy': 0.2521}, 1: {'f1': 0.65335, 'iou': 0.48517, 'accuracy': 0.87296}, 2: {'f1': 0.01684, 'iou': 0.00849, 'accuracy': 0.12971}}  | 0.8751          |
+| 1.0998        | 0.3523 | 602  | 0.1795 | {0: {'f1': 0.09312, 'iou': 0.04883, 'accuracy': 0.28836}, 1: {'f1': 0.74168, 'iou': 0.58942, 'accuracy': 0.89807}, 2: {'f1': 0.01625, 'iou': 0.00819, 'accuracy': 0.19265}} | 0.8243          |
+| 1.0998        | 0.4026 | 688  | 0.8495 | {0: {'f1': 0.98464, 'iou': 0.96975, 'accuracy': 0.97734}, 1: {'f1': 0.67506, 'iou': 0.5095, 'accuracy': 0.879}, 2: {'f1': 0.10072, 'iou': 0.05303, 'accuracy': 0.86349}}    | 0.8043          |
+| 1.0696        | 0.4529 | 774  | 0.874  | {0: {'f1': 0.98422, 'iou': 0.96893, 'accuracy': 0.97671}, 1: {'f1': 0.75979, 'iou': 0.61262, 'accuracy': 0.90403}, 2: {'f1': 0.11786, 'iou': 0.06262, 'accuracy': 0.88981}} | 0.7506          |
+| 1.0419        | 0.5032 | 860  | 0.9391 | {0: {'f1': 0.98895, 'iou': 0.97813, 'accuracy': 0.98362}, 1: {'f1': 0.9206, 'iou': 0.85288, 'accuracy': 0.96291}, 2: {'f1': 0.10984, 'iou': 0.05811, 'accuracy': 0.9543}}   | 0.6618          |
+| 1.0149        | 0.5535 | 946  | 0.7046 | {0: {'f1': 0.91333, 'iou': 0.84049, 'accuracy': 0.85914}, 1: {'f1': 0.47479, 'iou': 0.3113, 'accuracy': 0.83125}, 2: {'f1': 0.06969, 'iou': 0.0361, 'accuracy': 0.95034}}   | 0.7884          |
+| 1.0024        | 0.6039 | 1032 | 0.8763 | {0: {'f1': 0.97412, 'iou': 0.94954, 'accuracy': 0.96061}, 1: {'f1': 0.81027, 'iou': 0.68105, 'accuracy': 0.92142}, 2: {'f1': 0.15071, 'iou': 0.0815, 'accuracy': 0.94565}}  | 0.5940          |
+| 0.9739        | 0.6542 | 1118 | 0.2909 | {0: {'f1': 0.24044, 'iou': 0.13665, 'accuracy': 0.34611}, 1: {'f1': 0.87511, 'iou': 0.77796, 'accuracy': 0.94508}, 2: {'f1': 0.01577, 'iou': 0.00795, 'accuracy': 0.31169}} | 0.9626          |
+| 0.9626        | 0.7045 | 1204 | 0.9520 | {0: {'f1': 0.99067, 'iou': 0.98152, 'accuracy': 0.98615}, 1: {'f1': 0.94406, 'iou': 0.89405, 'accuracy': 0.97333}, 2: {'f1': 0.17721, 'iou': 0.09722, 'accuracy': 0.96864}} | 0.5658          |
+| 0.9626        | 0.7548 | 1290 | 0.9183 | {0: {'f1': 0.98633, 'iou': 0.97303, 'accuracy': 0.97941}, 1: {'f1': 0.87697, 'iou': 0.78089, 'accuracy': 0.94587}, 2: {'f1': 0.18891, 'iou': 0.1043, 'accuracy': 0.95606}}  | 0.6192          |
+| 0.9515        | 0.8051 | 1376 | 0.3322 | {0: {'f1': 0.25117, 'iou': 0.14362, 'accuracy': 0.35705}, 1: {'f1': 0.96192, 'iou': 0.92663, 'accuracy': 0.98155}, 2: {'f1': 0.00532, 'iou': 0.00267, 'accuracy': 0.34648}} | 0.9133          |
+| 0.9395        | 0.8555 | 1462 | 0.9488 | {0: {'f1': 0.99219, 'iou': 0.98451, 'accuracy': 0.98835}, 1: {'f1': 0.93039, 'iou': 0.86984, 'accuracy': 0.96766}, 2: {'f1': 0.25682, 'iou': 0.14733, 'accuracy': 0.96767}} | 0.5446          |
+| 0.9288        | 0.9058 | 1548 | 0.9606 | {0: {'f1': 0.99208, 'iou': 0.98429, 'accuracy': 0.98821}, 1: {'f1': 0.95742, 'iou': 0.91831, 'accuracy': 0.97945}, 2: {'f1': 0.27975, 'iou': 0.16263, 'accuracy': 0.97907}} | 0.5105          |
+| 0.9341        | 0.9561 | 1634 | 0.9536 | {0: {'f1': 0.98841, 'iou': 0.97708, 'accuracy': 0.98281}, 1: {'f1': 0.95511, 'iou': 0.91408, 'accuracy': 0.97815}, 2: {'f1': 0.18082, 'iou': 0.0994, 'accuracy': 0.97498}}  | 0.5982          |
 
 
 ### Framework versions

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2c34b3903ba227728b552b351d8fa90ae30f41319840f2c675e492d03d1a1d2b
+oid sha256:23629f1bb7f663dffd9800b1fff0965a2f8590ae157f927b835ded37c5ff8b86
 size 2188724

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:14bda65d85f61e4c78a761d4356cdd2990a1552e75c25aa3b771d45f33f8e39b
+oid sha256:474d9837c61b595a00801aafb0cb56b52e83171d024ba01f402fb983089fa91e
 size 5240