best_model.pt

README.md

@@ -0,0 +1,73 @@
+---
+library_name: transformers
+tags:
+- generated_from_trainer
+metrics:
+- accuracy
+- f1
+model-index:
+- name: windowz_ln_segment_051525
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# windowz_ln_segment_051525
+
+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
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 5e-05
+- train_batch_size: 16
+- eval_batch_size: 16
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_steps: 1000
+- num_epochs: 1
+
+### Training results
+
+| 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          |
+
+
+### Framework versions
+
+- Transformers 4.45.0
+- Pytorch 2.5.1+cu124
+- Datasets 3.6.0
+- Tokenizers 0.20.3

config.json

@@ -0,0 +1,24 @@
+{
+  "architectures": [
+    "UNETForSegmentation"
+  ],
+  "dim": 224,
+  "hidden_act": "gelu",
+  "hidden_size": 256,
+  "img_size": 128,
+  "intermediate_size": 1024,
+  "is_causal": false,
+  "k": 2,
+  "model_type": "Unet",
+  "n_filts": 4,
+  "num_attention_heads": 8,
+  "num_channels": 3,
+  "num_classes": 3,
+  "num_hidden_layers": 6,
+  "num_layers": 2,
+  "patch_size": 16,
+  "problem_type": "single_label_classification",
+  "t": 2,
+  "torch_dtype": "float32",
+  "transformers_version": "4.45.0"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2c34b3903ba227728b552b351d8fa90ae30f41319840f2c675e492d03d1a1d2b
+size 2188724

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:14bda65d85f61e4c78a761d4356cdd2990a1552e75c25aa3b771d45f33f8e39b
+size 5240