best_model.pt

README.md

@@ -0,0 +1,71 @@
+---
+library_name: transformers
+tags:
+- generated_from_trainer
+metrics:
+- accuracy
+- f1
+model-index:
+- name: windowz_dce-022625
+  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_dce-022625
+
+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: 0.9916
+- F1: 0.9914
+- Iou: 0.9838
+- Per Class Metrics: {0: {'f1': 0.99722, 'iou': 0.99445, 'accuracy': 0.99583}, 1: {'f1': 0.98262, 'iou': 0.96584, 'accuracy': 0.99157}, 2: {'f1': 0.752, 'iou': 0.60257, 'accuracy': 0.9957}}
+- Loss: 0.0191
+
+## 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: 100
+
+### Training results
+
+| Training Loss | Epoch | Step   |        | Class Metrics                                                                                                                                                               | Validation Loss |
+|:-------------:|:-----:|:------:|:------:|:---------------------------------------------------------------------------------------------------------------------------------------------------------------------------:|:---------------:|
+| 0.4609        | 5.0   | 12815  | 0.9814 | {0: {'f1': 0.99753, 'iou': 0.99506, 'accuracy': 0.9963}, 1: {'f1': 0.97958, 'iou': 0.95998, 'accuracy': 0.99006}, 2: {'f1': 0.62099, 'iou': 0.45032, 'accuracy': 0.99369}}  | 0.0445          |
+| 0.4462        | 10.0  | 25630  | 0.9830 | {0: {'f1': 0.99759, 'iou': 0.99518, 'accuracy': 0.99639}, 1: {'f1': 0.98171, 'iou': 0.96408, 'accuracy': 0.99106}, 2: {'f1': 0.67311, 'iou': 0.50729, 'accuracy': 0.99467}} | 0.0885          |
+| 0.4105        | 15.0  | 38445  | 0.9847 | {0: {'f1': 0.99756, 'iou': 0.99514, 'accuracy': 0.99635}, 1: {'f1': 0.98336, 'iou': 0.96726, 'accuracy': 0.99192}, 2: {'f1': 0.7548, 'iou': 0.60617, 'accuracy': 0.99557}}  | 0.0298          |
+| 0.4006        | 20.0  | 51260  | 0.9834 | {0: {'f1': 0.99716, 'iou': 0.99433, 'accuracy': 0.99574}, 1: {'f1': 0.98185, 'iou': 0.96435, 'accuracy': 0.99123}, 2: {'f1': 0.75043, 'iou': 0.60056, 'accuracy': 0.99546}} | 0.0201          |
+| 0.4016        | 25.0  | 64075  | 0.9838 | {0: {'f1': 0.99722, 'iou': 0.99445, 'accuracy': 0.99583}, 1: {'f1': 0.98262, 'iou': 0.96584, 'accuracy': 0.99157}, 2: {'f1': 0.752, 'iou': 0.60257, 'accuracy': 0.9957}}    | 0.0191          |
+| 0.3635        | 30.0  | 76890  | 0.9849 | {0: {'f1': 0.99748, 'iou': 0.99496, 'accuracy': 0.99622}, 1: {'f1': 0.98326, 'iou': 0.96706, 'accuracy': 0.99192}, 2: {'f1': 0.78691, 'iou': 0.64868, 'accuracy': 0.99567}} | 0.0195          |
+| 0.3754        | 35.0  | 89705  | 0.9822 | {0: {'f1': 0.99678, 'iou': 0.99359, 'accuracy': 0.99518}, 1: {'f1': 0.98001, 'iou': 0.96081, 'accuracy': 0.99042}, 2: {'f1': 0.77117, 'iou': 0.62757, 'accuracy': 0.9952}}  | 0.0284          |
+| 0.3568        | 40.0  | 102520 | 0.9827 | {0: {'f1': 0.99752, 'iou': 0.99506, 'accuracy': 0.99629}, 1: {'f1': 0.97971, 'iou': 0.96022, 'accuracy': 0.99027}, 2: {'f1': 0.73597, 'iou': 0.58224, 'accuracy': 0.99395}} | 0.0239          |
+
+
+### Framework versions
+
+- Transformers 4.45.0
+- Pytorch 2.5.1+cu124
+- Datasets 2.21.0
+- 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 sha256:47172d6e6e7ab5abe41f935a36a81c069bd712e69d662928c8dacc1b89d114d4
+size 2188724

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fbfb0720a36492a7481af7922685bba771de1670ddd27fe7a8550ade1bfe5bd6
+size 5240