best_model.pt

README.md

@@ -0,0 +1,81 @@
+---
+library_name: transformers
+tags:
+- generated_from_trainer
+metrics:
+- accuracy
+- f1
+model-index:
+- name: windowz_test-020525-1
+  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_test-020525-1
+
+This model is a fine-tuned version of [](https://huggingface.co/) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Model Preparation Time: 0.0011
+- Accuracy: 0.9858
+- F1: 0.9827
+- Iou: 0.9720
+- Contour Dice: 0.9854
+- Per Class Metrics: {0: {'f1': 0.99513, 'iou': 0.99031, 'accuracy': 0.99269, 'contour_dice': 0.99513}, 1: {'f1': 0.97348, 'iou': 0.94833, 'accuracy': 0.98703, 'contour_dice': 0.97348}, 2: {'f1': 0.22896, 'iou': 0.12928, 'accuracy': 0.99176, 'contour_dice': 0.22896}}
+- Loss: 0.0929
+
+## 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: 8
+- eval_batch_size: 8
+- 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: 2
+
+### Training results
+
+| Training Loss | Epoch  | Step | Model Preparation Time |        | Dice   | Class Metrics                                                                                                                                                                                                                                          | Validation Loss |
+|:-------------:|:------:|:----:|:----------------------:|:------:|:------:|:------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------:|:---------------:|
+| 0.9835        | 0.1001 | 513  | 0.0011                 | 0.0355 | 0.3320 | {0: {'f1': 0.02025, 'iou': 0.01023, 'accuracy': 0.20562, 'contour_dice': 0.02025}, 1: {'f1': 0.20205, 'iou': 0.11238, 'accuracy': 0.13761, 'contour_dice': 0.20205}, 2: {'f1': 0.12505, 'iou': 0.06669, 'accuracy': 0.90513, 'contour_dice': 0.12505}} | 1.5839          |
+| 0.8946        | 0.2002 | 1026 | 0.0011                 | 0.6752 | 0.6622 | {0: {'f1': 0.83424, 'iou': 0.71563, 'accuracy': 0.77762, 'contour_dice': 0.83424}, 1: {'f1': 0.73093, 'iou': 0.57595, 'accuracy': 0.84974, 'contour_dice': 0.73093}, 2: {'f1': 0.02899, 'iou': 0.01471, 'accuracy': 0.90293, 'contour_dice': 0.02899}} | 0.9247          |
+| 0.8353        | 0.3002 | 1539 | 0.0011                 | 0.9172 | 0.9258 | {0: {'f1': 0.97708, 'iou': 0.95518, 'accuracy': 0.96497, 'contour_dice': 0.97708}, 1: {'f1': 0.90724, 'iou': 0.83024, 'accuracy': 0.95781, 'contour_dice': 0.90724}, 2: {'f1': 0.24247, 'iou': 0.13796, 'accuracy': 0.98702, 'contour_dice': 0.24247}} | 0.6193          |
+| 0.7437        | 0.4003 | 2052 | 0.0011                 | 0.9546 | 0.9688 | {0: {'f1': 0.98966, 'iou': 0.97952, 'accuracy': 0.98446, 'contour_dice': 0.98966}, 1: {'f1': 0.95343, 'iou': 0.911, 'accuracy': 0.97731, 'contour_dice': 0.95343}, 2: {'f1': 0.18273, 'iou': 0.10055, 'accuracy': 0.99138, 'contour_dice': 0.18273}}   | 0.5042          |
+| 0.7118        | 0.5004 | 2565 | 0.0011                 | 0.9715 | 0.9875 | {0: {'f1': 0.99578, 'iou': 0.99159, 'accuracy': 0.99368, 'contour_dice': 0.99578}, 1: {'f1': 0.97196, 'iou': 0.94546, 'accuracy': 0.98614, 'contour_dice': 0.97196}, 2: {'f1': 0.08536, 'iou': 0.04458, 'accuracy': 0.99092, 'contour_dice': 0.08536}} | 0.3568          |
+| 0.6965        | 0.6005 | 3078 | 0.0011                 | 0.9697 | 0.9821 | {0: {'f1': 0.99405, 'iou': 0.98816, 'accuracy': 0.99106, 'contour_dice': 0.99405}, 1: {'f1': 0.9723, 'iou': 0.9461, 'accuracy': 0.98647, 'contour_dice': 0.9723}, 2: {'f1': 0.2052, 'iou': 0.11433, 'accuracy': 0.99134, 'contour_dice': 0.2052}}      | 0.2106          |
+| 0.6643        | 0.7005 | 3591 | 0.0011                 | 0.9678 | 0.9849 | {0: {'f1': 0.99492, 'iou': 0.9899, 'accuracy': 0.9924, 'contour_dice': 0.99492}, 1: {'f1': 0.96694, 'iou': 0.936, 'accuracy': 0.98371, 'contour_dice': 0.96694}, 2: {'f1': 0.06056, 'iou': 0.03123, 'accuracy': 0.9907, 'contour_dice': 0.06056}}      | 0.2953          |
+| 0.6215        | 0.8006 | 4104 | 0.0011                 | 0.9605 | 0.9766 | {0: {'f1': 0.99232, 'iou': 0.98476, 'accuracy': 0.98844, 'contour_dice': 0.99232}, 1: {'f1': 0.95932, 'iou': 0.92183, 'accuracy': 0.98028, 'contour_dice': 0.95932}, 2: {'f1': 0.05829, 'iou': 0.03002, 'accuracy': 0.99085, 'contour_dice': 0.05829}} | 0.2461          |
+| 0.6155        | 0.9007 | 4617 | 0.0011                 | 0.9731 | 0.9897 | {0: {'f1': 0.99653, 'iou': 0.99309, 'accuracy': 0.99481, 'contour_dice': 0.99653}, 1: {'f1': 0.9727, 'iou': 0.94686, 'accuracy': 0.98657, 'contour_dice': 0.9727}, 2: {'f1': 0.11412, 'iou': 0.06051, 'accuracy': 0.99092, 'contour_dice': 0.11412}}   | 0.1863          |
+| 0.6058        | 1.0008 | 5130 | 0.0011                 | 0.9670 | 0.9808 | {0: {'f1': 0.99366, 'iou': 0.9874, 'accuracy': 0.99047, 'contour_dice': 0.99366}, 1: {'f1': 0.96863, 'iou': 0.93917, 'accuracy': 0.98474, 'contour_dice': 0.96863}, 2: {'f1': 0.11362, 'iou': 0.06023, 'accuracy': 0.99107, 'contour_dice': 0.11362}}  | 0.2076          |
+| 0.5948        | 1.1009 | 5643 | 0.0011                 | 0.9747 | 0.9888 | {0: {'f1': 0.99624, 'iou': 0.9925, 'accuracy': 0.99436, 'contour_dice': 0.99624}, 1: {'f1': 0.97498, 'iou': 0.95118, 'accuracy': 0.98772, 'contour_dice': 0.97498}, 2: {'f1': 0.28546, 'iou': 0.16649, 'accuracy': 0.99209, 'contour_dice': 0.28546}}  | 0.1954          |
+| 0.5824        | 1.2009 | 6156 | 0.0011                 | 0.9686 | 0.9859 | {0: {'f1': 0.9952, 'iou': 0.99045, 'accuracy': 0.99283, 'contour_dice': 0.9952}, 1: {'f1': 0.96787, 'iou': 0.93774, 'accuracy': 0.98404, 'contour_dice': 0.96787}, 2: {'f1': 0.05271, 'iou': 0.02707, 'accuracy': 0.99085, 'contour_dice': 0.05271}}   | 0.1422          |
+| 0.5849        | 1.3010 | 6669 | 0.0011                 | 0.9720 | 0.9854 | {0: {'f1': 0.99513, 'iou': 0.99031, 'accuracy': 0.99269, 'contour_dice': 0.99513}, 1: {'f1': 0.97348, 'iou': 0.94833, 'accuracy': 0.98703, 'contour_dice': 0.97348}, 2: {'f1': 0.22896, 'iou': 0.12928, 'accuracy': 0.99176, 'contour_dice': 0.22896}} | 0.0929          |
+| 0.5519        | 1.4011 | 7182 | 0.0011                 | 0.9671 | 0.9824 | {0: {'f1': 0.99417, 'iou': 0.9884, 'accuracy': 0.99124, 'contour_dice': 0.99417}, 1: {'f1': 0.96683, 'iou': 0.9358, 'accuracy': 0.98383, 'contour_dice': 0.96683}, 2: {'f1': 0.15623, 'iou': 0.08473, 'accuracy': 0.99138, 'contour_dice': 0.15623}}   | 0.1988          |
+| 0.5774        | 1.5012 | 7695 | 0.0011                 | 0.9677 | 0.9821 | {0: {'f1': 0.99407, 'iou': 0.98822, 'accuracy': 0.99109, 'contour_dice': 0.99407}, 1: {'f1': 0.96732, 'iou': 0.9367, 'accuracy': 0.9841, 'contour_dice': 0.96732}, 2: {'f1': 0.23996, 'iou': 0.13634, 'accuracy': 0.99184, 'contour_dice': 0.23996}}   | 0.1125          |
+| 0.5935        | 1.6012 | 8208 | 0.0011                 | 0.9721 | 0.9856 | {0: {'f1': 0.99523, 'iou': 0.9905, 'accuracy': 0.99284, 'contour_dice': 0.99523}, 1: {'f1': 0.97314, 'iou': 0.94768, 'accuracy': 0.98689, 'contour_dice': 0.97314}, 2: {'f1': 0.24074, 'iou': 0.13684, 'accuracy': 0.99185, 'contour_dice': 0.24074}}  | 0.1502          |
+
+
+### 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 sha256:031d029f6f060a54e72c7a9853b5f213262d3b94c74c9da2cfab06c62123165f
+size 2188724

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6c52ca8ff9bc554d465ab15a7c2d25820ed2c141ee2d0791f808040858f96985
+size 5240