Upload DeiT3 model from experiment c3

.gitattributes

@@ -33,3 +33,5 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+training_curves/DeiT3_combined_metrics.png filter=lfs diff=lfs merge=lfs -text
+training_notebook_c3.ipynb filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,166 @@
+---
+license: apache-2.0
+tags:
+- image-classification
+- pytorch
+- timm
+- deit3
+- vision-transformer
+- transformer
+- gravitational-lensing
+- strong-lensing
+- astronomy
+- astrophysics
+datasets:
+- parlange/gravit-c21-j24
+metrics:
+- accuracy
+- auc
+- f1
+paper:
+- title: "GraViT: A Gravitational Lens Discovery Toolkit with Vision Transformers"
+  url: "https://arxiv.org/abs/2509.00226"
+  authors: "Parlange et al."
+model-index:
+- name: DeiT3-c3
+  results:
+  - task:
+      type: image-classification
+      name: Strong Gravitational Lens Discovery
+    dataset:
+      type: common-test-sample
+      name: Common Test Sample (More et al. 2024)
+    metrics:
+    - type: accuracy
+      value: 0.9015
+      name: Average Accuracy
+    - type: auc
+      value: 0.8912
+      name: Average AUC-ROC
+    - type: f1
+      value: 0.6869
+      name: Average F1-Score
+---
+
+# 🌌 deit3-gravit-c3
+
+🔭 This model is part of **GraViT**: Transfer Learning with Vision Transformers and MLP-Mixer for Strong Gravitational Lens Discovery
+
+🔗 **GitHub Repository**: [https://github.com/parlange/gravit](https://github.com/parlange/gravit)
+
+## 🛰️ Model Details
+
+- **🤖 Model Type**: DeiT3
+- **🧪 Experiment**: C3 - C21+J24-all-blocks-ResNet18
+- **🌌 Dataset**: C21+J24
+- **🪐 Fine-tuning Strategy**: all-blocks
+
+
+
+## 💻 Quick Start
+
+```python
+import torch
+import timm
+
+# Load the model directly from the Hub
+model = timm.create_model(
+    'hf-hub:parlange/deit3-gravit-c3',
+    pretrained=True
+)
+model.eval()
+
+# Example inference
+dummy_input = torch.randn(1, 3, 224, 224)
+with torch.no_grad():
+    output = model(dummy_input)
+    predictions = torch.softmax(output, dim=1)
+print(f"Lens probability: {predictions[0][1]:.4f}")
+```
+
+## ⚡️ Training Configuration
+
+**Training Dataset:** C21+J24 (Cañameras et al. 2021 + Jaelani et al. 2024)  
+**Fine-tuning Strategy:** all-blocks
+
+
+| 🔧 Parameter | 📝 Value |
+|--------------|----------|
+| Batch Size | 192 |
+| Learning Rate | AdamW with ReduceLROnPlateau |
+| Epochs | 100 |
+| Patience | 10 |
+| Optimizer | AdamW |
+| Scheduler | ReduceLROnPlateau |
+| Image Size | 224x224 |
+| Fine Tune Mode | all_blocks |
+| Stochastic Depth Probability | 0.1 |
+
+
+## 📈 Training Curves
+
+![Combined Training Metrics](https://huggingface.co/parlange/deit3-gravit-c3/resolve/main/training_curves/DeiT3_combined_metrics.png)
+
+
+## 🏁 Final Epoch Training Metrics
+
+| Metric | Training | Validation |
+|:---------:|:-----------:|:-------------:|
+| 📉 Loss | 0.0115 | 0.0422 |
+| 🎯 Accuracy | 0.9961 | 0.9934 |
+| 📊 AUC-ROC | 0.9999 | 0.9987 |
+| ⚖️ F1 Score | 0.9961 | 0.9934 |
+
+
+## ☑️ Evaluation Results
+
+### ROC Curves and Confusion Matrices
+
+Performance across all test datasets (a through l) in the Common Test Sample (More et al. 2024):
+
+![ROC + Confusion Matrix - Dataset A](https://huggingface.co/parlange/deit3-gravit-c3/resolve/main/roc_confusion_matrix/DeiT3_roc_confusion_matrix_a.png)
+![ROC + Confusion Matrix - Dataset B](https://huggingface.co/parlange/deit3-gravit-c3/resolve/main/roc_confusion_matrix/DeiT3_roc_confusion_matrix_b.png)
+![ROC + Confusion Matrix - Dataset C](https://huggingface.co/parlange/deit3-gravit-c3/resolve/main/roc_confusion_matrix/DeiT3_roc_confusion_matrix_c.png)
+![ROC + Confusion Matrix - Dataset D](https://huggingface.co/parlange/deit3-gravit-c3/resolve/main/roc_confusion_matrix/DeiT3_roc_confusion_matrix_d.png)
+![ROC + Confusion Matrix - Dataset E](https://huggingface.co/parlange/deit3-gravit-c3/resolve/main/roc_confusion_matrix/DeiT3_roc_confusion_matrix_e.png)
+![ROC + Confusion Matrix - Dataset F](https://huggingface.co/parlange/deit3-gravit-c3/resolve/main/roc_confusion_matrix/DeiT3_roc_confusion_matrix_f.png)
+![ROC + Confusion Matrix - Dataset G](https://huggingface.co/parlange/deit3-gravit-c3/resolve/main/roc_confusion_matrix/DeiT3_roc_confusion_matrix_g.png)
+![ROC + Confusion Matrix - Dataset H](https://huggingface.co/parlange/deit3-gravit-c3/resolve/main/roc_confusion_matrix/DeiT3_roc_confusion_matrix_h.png)
+![ROC + Confusion Matrix - Dataset I](https://huggingface.co/parlange/deit3-gravit-c3/resolve/main/roc_confusion_matrix/DeiT3_roc_confusion_matrix_i.png)
+![ROC + Confusion Matrix - Dataset J](https://huggingface.co/parlange/deit3-gravit-c3/resolve/main/roc_confusion_matrix/DeiT3_roc_confusion_matrix_j.png)
+![ROC + Confusion Matrix - Dataset K](https://huggingface.co/parlange/deit3-gravit-c3/resolve/main/roc_confusion_matrix/DeiT3_roc_confusion_matrix_k.png)
+![ROC + Confusion Matrix - Dataset L](https://huggingface.co/parlange/deit3-gravit-c3/resolve/main/roc_confusion_matrix/DeiT3_roc_confusion_matrix_l.png)
+
+### 📋 Performance Summary
+
+Average performance across 12 test datasets from the Common Test Sample (More et al. 2024):
+
+| Metric | Value |
+|-----------|----------|
+| 🎯 Average Accuracy | 0.9015 |
+| 📈 Average AUC-ROC | 0.8912 |
+| ⚖️ Average F1-Score | 0.6869 |
+
+
+## 📘 Citation
+
+If you use this model in your research, please cite:
+
+```bibtex
+@misc{parlange2025gravit,
+      title={GraViT: Transfer Learning with Vision Transformers and MLP-Mixer for Strong Gravitational Lens Discovery}, 
+      author={René Parlange and Juan C. Cuevas-Tello and Octavio Valenzuela and Omar de J. Cabrera-Rosas and Tomás Verdugo and Anupreeta More and Anton T. Jaelani},
+      year={2025},
+      eprint={2509.00226},
+      archivePrefix={arXiv},
+      primaryClass={cs.CV},
+      url={https://arxiv.org/abs/2509.00226}, 
+}
+```
+
+---
+
+
+## Model Card Contact
+
+For questions about this model, please contact the author through: https://github.com/parlange/

config.json

@@ -0,0 +1,76 @@
+{
+  "architecture": "deit3_base_patch16_224",
+  "num_classes": 2,
+  "num_features": 1000,
+  "global_pool": "avg",
+  "crop_pct": 0.875,
+  "interpolation": "bicubic",
+  "mean": [
+    0.485,
+    0.456,
+    0.406
+  ],
+  "std": [
+    0.229,
+    0.224,
+    0.225
+  ],
+  "first_conv": "conv1",
+  "classifier": "fc",
+  "input_size": [
+    3,
+    224,
+    224
+  ],
+  "pool_size": [
+    7,
+    7
+  ],
+  "pretrained_cfg": {
+    "tag": "gravit_c3",
+    "custom_load": false,
+    "input_size": [
+      3,
+      224,
+      224
+    ],
+    "fixed_input_size": true,
+    "interpolation": "bicubic",
+    "crop_pct": 0.875,
+    "crop_mode": "center",
+    "mean": [
+      0.485,
+      0.456,
+      0.406
+    ],
+    "std": [
+      0.229,
+      0.224,
+      0.225
+    ],
+    "num_classes": 2,
+    "pool_size": [
+      7,
+      7
+    ],
+    "first_conv": "conv1",
+    "classifier": "fc"
+  },
+  "model_name": "deit3_gravit_c3",
+  "experiment": "c3",
+  "training_strategy": "all-blocks",
+  "dataset": "C21+J24",
+  "hyperparameters": {
+    "batch_size": "192",
+    "learning_rate": "AdamW with ReduceLROnPlateau",
+    "epochs": "100",
+    "patience": "10",
+    "optimizer": "AdamW",
+    "scheduler": "ReduceLROnPlateau",
+    "image_size": "224x224",
+    "fine_tune_mode": "all_blocks",
+    "stochastic_depth_probability": "0.1"
+  },
+  "hf_hub_id": "parlange/deit3-gravit-c3",
+  "license": "apache-2.0"
+}

deit3-gravit-c3.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:058af372f0971917904be3167642f0f4281139b83165175d3ec53ff629aa6511
+size 343337390

evaluation_results.csv

@@ -0,0 +1,145 @@
+Model,Dataset,Loss,Accuracy,AUCROC,F1
+ViT,a,0.3332538347373928,0.886199308393587,0.9282716390423573,0.4676470588235294
+ViT,b,0.15735628360080778,0.9440427538509902,0.9576924493554329,0.6411290322580645
+ViT,c,0.39000377248233686,0.8729959132348318,0.9239502762430939,0.4404432132963989
+ViT,d,0.07890508225652003,0.9745363093366866,0.9801749539594843,0.7969924812030075
+ViT,e,0.34977894677943117,0.8880351262349067,0.9340497994399455,0.7571428571428571
+ViT,f,0.23130612724766006,0.9195259855936798,0.9467497493631001,0.23434045689019897
+ViT,g,0.07770086391766866,0.969,0.9985143333333334,0.9696376101860921
+ViT,h,0.20104280499617258,0.9313333333333333,0.9957643333333334,0.9351385390428212
+ViT,i,0.03610865117112796,0.9851666666666666,0.9993911111111111,0.9852380162547686
+ViT,j,2.548160281856855,0.6111666666666666,0.5926025555555556,0.4136717768283488
+ViT,k,2.5065680770576,0.6273333333333333,0.7480725555555555,0.42400824317362185
+ViT,l,0.9482682921706662,0.8283538681190842,0.7880956172483574,0.7088789237668162
+MLP-Mixer,a,0.693774286923413,0.7667400188619931,0.878732044198895,0.289272030651341
+MLP-Mixer,b,0.5321722498988626,0.8346431939641622,0.9091961325966851,0.3647342995169082
+MLP-Mixer,c,0.9557083110995204,0.6777742848160956,0.8515027624309391,0.22758100979653353
+MLP-Mixer,d,0.08414041630148475,0.9713926438226973,0.972451197053407,0.7684478371501272
+MLP-Mixer,e,0.40313906763178325,0.8572996706915478,0.9160977824869447,0.6990740740740741
+MLP-Mixer,f,0.5521763351439839,0.8145767175276896,0.9037233142227219,0.11201780415430267
+MLP-Mixer,g,0.2688900081912676,0.9158333333333334,0.9949920555555556,0.9221519963002929
+MLP-Mixer,h,0.4934347181916237,0.8326666666666667,0.9912926111111112,0.8562839965645577
+MLP-Mixer,i,0.03135846547285716,0.9883333333333333,0.9996557777777778,0.988433575677462
+MLP-Mixer,j,0.7298590982755025,0.7896666666666666,0.8653722777777778,0.7797556719022688
+MLP-Mixer,k,0.4923275619546572,0.8621666666666666,0.9557253333333332,0.8438149197355996
+MLP-Mixer,l,0.5266123601464402,0.8324255724181693,0.9252579204980724,0.7723583075928453
+CvT,a,0.6393119974430159,0.8154668343288274,0.8805138121546962,0.3382187147688839
+CvT,b,0.3633024044679194,0.8953159383841559,0.9188913443830571,0.47393364928909953
+CvT,c,1.1649154984175278,0.6969506444514304,0.8355791896869245,0.23734177215189872
+CvT,d,0.07392493324370102,0.9795661741590694,0.9774419889502762,0.821917808219178
+CvT,e,0.5351559021208603,0.8353457738748628,0.8926663134791492,0.6666666666666666
+CvT,f,0.5429993842459881,0.8470296646270622,0.9025078880097911,0.13186813186813187
+CvT,g,0.17292167934030295,0.9475,0.998136,0.94991254571474
+CvT,h,0.5979102214997013,0.8423333333333334,0.9933014444444443,0.8632947976878613
+CvT,i,0.019503380698462327,0.9921666666666666,0.9998416666666667,0.9921939877096828
+CvT,j,2.9556157615184784,0.5416666666666666,0.5250468888888888,0.28645563051375195
+CvT,k,2.8021974964936573,0.5863333333333334,0.8273376111111111,0.3078639152258784
+CvT,l,1.25715323004886,0.765427528951404,0.7598163378053491,0.6245132893177586
+Swin,a,0.3497173586513066,0.8616787173844703,0.9157173112338858,0.4037940379403794
+Swin,b,0.2814936617454318,0.894687205281358,0.9352283609576427,0.4707740916271722
+Swin,c,0.503795853185039,0.8088651367494498,0.8968895027624311,0.32891832229580575
+Swin,d,0.04239246920535809,0.9874253379440427,0.9881252302025783,0.8816568047337278
+Swin,e,0.26784261316878866,0.897914379802415,0.9381745250889276,0.7621483375959079
+Swin,f,0.2793698093965194,0.8924947718999303,0.934230056463828,0.1767497034400949
+Swin,g,0.13889798412223656,0.9468333333333333,0.9980561111111113,0.9492603785589311
+Swin,h,0.25675517926116787,0.9013333333333333,0.9963051111111111,0.9097560975609756
+Swin,i,0.012134499582151572,0.996,0.9999221111111112,0.9959946595460614
+Swin,j,1.6750605003833772,0.6498333333333334,0.6798894444444443,0.5336293007769145
+Swin,k,1.5482970288371047,0.699,0.8766526666666666,0.5710213776722091
+Swin,l,0.6816675912849454,0.8306805562899899,0.8426904510477526,0.7302897574123989
+CaiT,a,0.5386943910452451,0.7966048412448915,0.8977044198895028,0.3239289446185998
+CaiT,b,0.27990006677237217,0.8972021376925495,0.9328563535911601,0.48665620094191525
+CaiT,c,0.8093499287011975,0.703552342030808,0.8726187845303867,0.24740622505985635
+CaiT,d,0.05759982030905481,0.9827098396730588,0.9882780847145488,0.8493150684931506
+CaiT,e,0.8215033926241484,0.7069154774972558,0.8727011276772875,0.537261698440208
+CaiT,f,0.44334294090392135,0.8346371311284951,0.9199878045075582,0.12678936605316973
+CaiT,g,0.13352473031356932,0.9495,0.9994326666666666,0.9518971265280203
+CaiT,h,0.4142214151509106,0.8468333333333333,0.997650388888889,0.8671005061460593
+CaiT,i,0.015668559301644562,0.9948333333333333,0.9999401111111111,0.9948564791770367
+CaiT,j,1.9409965459505718,0.6211666666666666,0.5872103888888889,0.47493647493647495
+CaiT,k,1.8231403918862343,0.6665,0.8462843333333334,0.5067784076904116
+CaiT,l,0.8769211871417011,0.7827190524033631,0.7953060293098494,0.6705155961831449
+DeiT,a,0.2227139560325983,0.9198365293932725,0.9217523020257825,0.538878842676311
+DeiT,b,0.12757987987644753,0.9575605155611443,0.9520055248618784,0.6882217090069284
+DeiT,c,0.3189492260405418,0.8830556428795976,0.9063683241252302,0.44477611940298506
+DeiT,d,0.06807509632895331,0.9776799748506759,0.9840036832412522,0.8075880758807588
+DeiT,e,0.2424249538883943,0.9220636663007684,0.9449405888140467,0.8075880758807588
+DeiT,f,0.16089401494481675,0.9398962125319495,0.9412565697247984,0.2774674115456238
+DeiT,g,0.05315884395440419,0.9803333333333333,0.9993382222222222,0.9806176084099869
+DeiT,h,0.15461649525165558,0.9408333333333333,0.9978233333333334,0.9438735177865613
+DeiT,i,0.0216113910873731,0.991,0.9997796666666667,0.9910358565737052
+DeiT,j,1.4732107556263605,0.6831666666666667,0.7790845555555556,0.5584204413472706
+DeiT,k,1.441663302719593,0.6938333333333333,0.909922,0.5668474416411223
+DeiT,l,0.564133838248539,0.863095552852837,0.87913302847728,0.7700914661220141
+DeiT3,a,0.23484845360151366,0.9276956931782459,0.8688867403314917,0.5228215767634855
+DeiT3,b,0.2093494395927152,0.9333542911034266,0.8948563535911603,0.5431034482758621
+DeiT3,c,0.24055628168418025,0.9305249921408362,0.872364640883978,0.53276955602537
+DeiT3,d,0.11087679768584877,0.9685633448601069,0.9730791896869244,0.7159090909090909
+DeiT3,e,0.3502105330694651,0.9165751920965971,0.8899114508438659,0.7682926829268293
+DeiT3,f,0.14640022547262477,0.9520563860274185,0.9015864990256626,0.2893226176808266
+DeiT3,g,0.080124724984169,0.9706666666666667,0.9986111111111111,0.9713261648745519
+DeiT3,h,0.0966695581873258,0.9691666666666666,0.9981386666666666,0.9699040182202701
+DeiT3,i,0.02791781535744667,0.9893333333333333,0.9996381111111111,0.989379356123465
+DeiT3,j,2.1139168503483137,0.6835,0.6340643888888889,0.5698754246885617
+DeiT3,k,2.061709966202577,0.7021666666666667,0.830329,0.5847083430165001
+DeiT3,l,0.7510140769096566,0.8741473216646396,0.8329381541106192,0.7857785778577858
+Twins_SVT,a,0.2616993184595204,0.9207796290474694,0.9109723756906076,0.5209125475285171
+Twins_SVT,b,0.25328254044824183,0.9138635649166928,0.9203333333333333,0.5
+Twins_SVT,c,0.2903442978858948,0.9047469349261239,0.9014797421731123,0.4748700173310225
+Twins_SVT,d,0.06683065037248045,0.981766740018862,0.9800589318600368,0.8253012048192772
+Twins_SVT,e,0.501175480276248,0.8507135016465422,0.8861651403920382,0.6682926829268293
+Twins_SVT,f,0.19588971365251565,0.9343970257919604,0.9257999765638224,0.24442462087421946
+Twins_SVT,g,0.1121031986673673,0.958,0.9983401111111112,0.9594072164948454
+Twins_SVT,h,0.13175206087032953,0.9531666666666667,0.9979833333333334,0.9549462882796216
+Twins_SVT,i,0.013252561777830124,0.994,0.9998952222222223,0.9939919893190922
+Twins_SVT,j,1.9202613861560822,0.6245,0.7093498888888888,0.4644639885904445
+Twins_SVT,k,1.8214107508560022,0.6605,0.9014717222222222,0.4896016036081183
+Twins_SVT,l,0.7119041901399152,0.8470731320395537,0.8628713312328674,0.7388949079089924
+Twins_PCPVT,a,0.30413780080114133,0.9157497642250865,0.9007108655616943,0.49812734082397003
+Twins_PCPVT,b,0.15472232246597545,0.9544168500471549,0.9364972375690609,0.6472019464720195
+Twins_PCPVT,c,0.4068696537002083,0.8814838101226029,0.8871178637200737,0.41368584758942456
+Twins_PCPVT,d,0.08009447079562927,0.9814523734674631,0.9849171270718233,0.8184615384615385
+Twins_PCPVT,e,0.4030229083367682,0.8990120746432492,0.9090819647317034,0.7430167597765364
+Twins_PCPVT,f,0.1949533162393722,0.9419874525598327,0.9262654450920738,0.2620689655172414
+Twins_PCPVT,g,0.04784699815511703,0.9833333333333333,0.9997761111111111,0.9835904168034132
+Twins_PCPVT,h,0.18152711460987728,0.9446666666666667,0.9988461666666668,0.9475181789440404
+Twins_PCPVT,i,0.00828180085743467,0.9976666666666667,0.999966,0.9976697736351531
+Twins_PCPVT,j,3.1867437440951667,0.6673333333333333,0.6140582777777778,0.5245354930919486
+Twins_PCPVT,k,3.147178516438852,0.6816666666666666,0.8307092777777778,0.5355058365758755
+Twins_PCPVT,l,1.1300106981552416,0.8598170377029242,0.8156386491151393,0.7614505534059209
+PiT,a,0.6125603188174733,0.8204966991512103,0.9077661141804788,0.3518728717366629
+PiT,b,0.3235708940557548,0.9038038352719271,0.9432992633517496,0.5032467532467533
+PiT,c,1.2576219515768996,0.6579691920779629,0.8583489871086556,0.2217453505007153
+PiT,d,0.05706561206120041,0.9849104055328513,0.9926353591160222,0.8659217877094972
+PiT,e,0.4257534373179487,0.8880351262349067,0.935154771815636,0.7524271844660194
+PiT,f,0.5470704378571871,0.8442413445898846,0.9260653695755013,0.13356311934510987
+PiT,g,0.15482272257159155,0.9525,0.9987017222222222,0.9545816733067729
+PiT,h,0.6500254770293832,0.8221666666666667,0.9941473333333334,0.8488026073402296
+PiT,i,0.013530508808791638,0.9955,0.9999065555555556,0.995512713977065
+PiT,j,3.0745317553281786,0.5515,0.5528523888888889,0.304471439648488
+PiT,k,2.933239512239893,0.5945,0.8885508888888889,0.3262254223206868
+PiT,l,1.302048514799378,0.7659034424409074,0.7757457952448608,0.6281394372112558
+ResNet-18,a,0.6009161868435675,0.808236403646652,0.9456114180478821,0.35517970401691334
+ResNet-18,b,0.4458324937691519,0.8519333542911034,0.9591114180478821,0.4163568773234201
+ResNet-18,c,0.7989861659754826,0.7541653568060358,0.9309244935543278,0.3005366726296959
+ResNet-18,d,0.015449083624662364,0.9949701351776171,0.999609576427256,0.9545454545454546
+ResNet-18,e,0.5140058943913876,0.8331503841931943,0.9492696586694922,0.6885245901639344
+ResNet-18,f,0.48200214555188836,0.846719851289598,0.9582666776614167,0.14514038876889848
+ResNet-18,g,0.23460300221045813,0.9216666666666666,0.9970519999999999,0.9270865653118213
+ResNet-18,h,0.42183320385217665,0.8698333333333333,0.9940301111111111,0.8844161610182033
+ResNet-18,i,0.006428073017857969,0.9975,0.9999838888888889,0.9974962443665498
+ResNet-18,j,6.947763346751531,0.43466666666666665,0.12029633333333332,0.03745743473325766
+ResNet-18,k,6.719588431844177,0.5105,0.7508054444444445,0.043010752688172046
+ResNet-18,l,2.462256099074432,0.7395695626883825,0.6324618509475799,0.5668044682909666
+Ensemble,a,,0.9195221628418736,0.9235128913443831,0.5412186379928315
+Ensemble,b,,0.9519019176359635,0.9473370165745855,0.6637362637362637
+Ensemble,c,,0.8695378811694435,0.9035138121546961,0.4211994421199442
+Ensemble,d,,0.9867966048412449,0.9853793738489871,0.877906976744186
+Ensemble,e,,0.9143798024149287,0.9323620676606372,0.7947368421052632
+Ensemble,f,,0.9361784524823794,0.93950146042107,0.2682060390763766
+Ensemble,g,,0.9785,0.9996941111111111,0.9789112309955861
+Ensemble,h,,0.9348333333333333,0.9986463333333333,0.9387051261953284
+Ensemble,i,,0.997,0.9999658888888888,0.997002997002997
+Ensemble,j,,0.6451666666666667,0.7836463333333332,0.48287588049550645
+Ensemble,k,,0.6636666666666666,0.9382774444444444,0.4962556165751373
+Ensemble,l,,0.8500343715297974,0.8794563846610491,0.7448263451502609

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bd7db6dcc88fd50c4d7b3037f189bb48b6154403149d6e8756ac9f4e86bb76b0
+size 343287616

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:058af372f0971917904be3167642f0f4281139b83165175d3ec53ff629aa6511
+size 343337390

training_curves/DeiT3_metrics.csv

@@ -0,0 +1,31 @@
+epoch,train_loss,val_loss,train_accuracy,val_accuracy,train_auc,val_auc,train_f1,val_f1
+1,0.12133353116152513,0.06166662340956596,0.9491312378150973,0.9803206997084548,0.9908295962688415,0.9979940330984539,0.9488842872240791,0.9799851742031134
+2,0.05494636449336345,0.034128174685354486,0.9807521291514177,0.9861516034985423,0.997780707696122,0.999188263393654,0.9806888860292541,0.9861616897305171
+3,0.045487246261129495,0.043049787942988055,0.9842152067585593,0.9868804664723032,0.998435085276439,0.9982957781196611,0.9841651083394809,0.9868421052631579
+4,0.04013614664559494,0.03402237415737296,0.9862674008961247,0.9861516034985423,0.9987488464713992,0.9991500140247686,0.9862360946846985,0.9860601614086574
+5,0.037818929275874505,0.049131851762793846,0.9869343639908336,0.9854227405247813,0.9989165928871198,0.9980556570816581,0.9869077199897182,0.9854862119013063
+6,0.03612760852247132,0.04465823140709441,0.9873619044361597,0.9854227405247813,0.9990236021499846,0.99842965091076,0.987333527586857,0.9854862119013063
+7,0.03312974497234396,0.04106172019990471,0.9885761193008858,0.9868804664723032,0.9991481656207636,0.9989024556094824,0.9885538039753256,0.986764705882353
+8,0.03079390252278298,0.04467770861310385,0.989183226733249,0.9868804664723032,0.9992727514651405,0.998591148246054,0.9891647894200378,0.9868613138686131
+9,0.030111658072643988,0.041507352197491194,0.9897219276943598,0.9876093294460642,0.9992672579425801,0.9991702011916803,0.9897062601695641,0.9876543209876543
+10,0.029094924251348422,0.032358164527065206,0.990149468139686,0.9912536443148688,0.9993035476258836,0.999216950420318,0.9901305644083479,0.9912663755458515
+11,0.028486179824413364,0.05093552202577553,0.9903204843178165,0.9897959183673469,0.9993758190264957,0.9977709117799556,0.9903010778484158,0.9898255813953488
+12,0.027378678419949454,0.03892283181798354,0.9903632383623491,0.9919825072886297,0.9994001925023193,0.9984976497887784,0.9903479698192065,0.9919883466860888
+13,0.025691640328447344,0.040297305444934275,0.9907907788076752,0.9905247813411079,0.999497996418865,0.9979037220885856,0.9907774514253419,0.9905316824471959
+14,0.026315096579743742,0.040405817177491504,0.9910473030748709,0.9883381924198251,0.9994469299246713,0.999188263393654,0.9910346540164237,0.9883381924198251
+15,0.025027122080401924,0.03933713233249252,0.9910558538837774,0.9897959183673469,0.9995003760630373,0.9986007105882753,0.9910419128856003,0.9898107714701602
+16,0.024790827932474956,0.04512184367392283,0.9913209289598796,0.9876093294460642,0.999470932993152,0.9991277018929187,0.9913049437605476,0.9875640087783467
+17,0.017164641173017664,0.0428765761059656,0.9941170434723124,0.9919825072886297,0.9997483471816039,0.9985582112895137,0.9941082775275318,0.9919766593727206
+18,0.014272876617472185,0.044261461064089146,0.9949293703184321,0.9919825072886297,0.9998364982798729,0.9985560863245757,0.9949249873766549,0.9919766593727206
+19,0.013573616959855908,0.03765543523100653,0.9955535793686082,0.9934402332361516,0.9998433336333756,0.9986973964929579,0.9955482501198548,0.9934258582907232
+20,0.01287249052858807,0.04189210441560857,0.9953740123815713,0.9927113702623906,0.9998704032008604,0.9987345833793743,0.9953698552758831,0.9927007299270073
+21,0.012630879596626093,0.037352593599359774,0.9958528576803366,0.9927113702623906,0.999858099038118,0.9986984589754269,0.9958479937677103,0.9926900584795322
+22,0.012325043967807007,0.04300889761374387,0.9957502479734582,0.9941690962099126,0.9998819902386092,0.9986538347117273,0.9957459920740215,0.9941520467836257
+23,0.011392199501855074,0.04363907175206477,0.9961606868009714,0.9941690962099126,0.9999004254983352,0.9986432098870369,0.9961572366337735,0.9941520467836257
+24,0.011286299277906982,0.04223336118646611,0.9960837295208127,0.9934402332361516,0.999887471770091,0.9986931465630816,0.9960801766488078,0.9934258582907232
+25,0.011058116214544809,0.04236892951481348,0.996186339227691,0.9934402332361516,0.9998906818695731,0.9986761468435771,0.9961827487632449,0.9934258582907232
+26,0.01128154789737973,0.04287581923387201,0.9959982214317474,0.9934402332361516,0.999901828015834,0.9986538347117273,0.9959943167228718,0.9934258582907232
+27,0.011398236130418838,0.0421129193472136,0.9960324246673735,0.9934402332361516,0.9998935698184921,0.9986655220188868,0.9960288932251549,0.9934258582907232
+28,0.011419007594133643,0.04220352793498755,0.9960580770940931,0.9934402332361516,0.9998995173934799,0.998675084361108,0.9960551424341739,0.9934258582907232
+29,0.010842687454953264,0.04214560194882841,0.9961350343742518,0.9934402332361516,0.9999097506092081,0.9986772093260461,0.99613079952063,0.9934258582907232
+30,0.011535594235865117,0.0421641564523429,0.9961008311386257,0.9934402332361516,0.999880920546658,0.9986761468435771,0.9960974941804738,0.9934258582907232

training_metrics.csv

@@ -0,0 +1,31 @@
+epoch,train_loss,val_loss,train_accuracy,val_accuracy,train_auc,val_auc,train_f1,val_f1
+1,0.12133353116152513,0.06166662340956596,0.9491312378150973,0.9803206997084548,0.9908295962688415,0.9979940330984539,0.9488842872240791,0.9799851742031134
+2,0.05494636449336345,0.034128174685354486,0.9807521291514177,0.9861516034985423,0.997780707696122,0.999188263393654,0.9806888860292541,0.9861616897305171
+3,0.045487246261129495,0.043049787942988055,0.9842152067585593,0.9868804664723032,0.998435085276439,0.9982957781196611,0.9841651083394809,0.9868421052631579
+4,0.04013614664559494,0.03402237415737296,0.9862674008961247,0.9861516034985423,0.9987488464713992,0.9991500140247686,0.9862360946846985,0.9860601614086574
+5,0.037818929275874505,0.049131851762793846,0.9869343639908336,0.9854227405247813,0.9989165928871198,0.9980556570816581,0.9869077199897182,0.9854862119013063
+6,0.03612760852247132,0.04465823140709441,0.9873619044361597,0.9854227405247813,0.9990236021499846,0.99842965091076,0.987333527586857,0.9854862119013063
+7,0.03312974497234396,0.04106172019990471,0.9885761193008858,0.9868804664723032,0.9991481656207636,0.9989024556094824,0.9885538039753256,0.986764705882353
+8,0.03079390252278298,0.04467770861310385,0.989183226733249,0.9868804664723032,0.9992727514651405,0.998591148246054,0.9891647894200378,0.9868613138686131
+9,0.030111658072643988,0.041507352197491194,0.9897219276943598,0.9876093294460642,0.9992672579425801,0.9991702011916803,0.9897062601695641,0.9876543209876543
+10,0.029094924251348422,0.032358164527065206,0.990149468139686,0.9912536443148688,0.9993035476258836,0.999216950420318,0.9901305644083479,0.9912663755458515
+11,0.028486179824413364,0.05093552202577553,0.9903204843178165,0.9897959183673469,0.9993758190264957,0.9977709117799556,0.9903010778484158,0.9898255813953488
+12,0.027378678419949454,0.03892283181798354,0.9903632383623491,0.9919825072886297,0.9994001925023193,0.9984976497887784,0.9903479698192065,0.9919883466860888
+13,0.025691640328447344,0.040297305444934275,0.9907907788076752,0.9905247813411079,0.999497996418865,0.9979037220885856,0.9907774514253419,0.9905316824471959
+14,0.026315096579743742,0.040405817177491504,0.9910473030748709,0.9883381924198251,0.9994469299246713,0.999188263393654,0.9910346540164237,0.9883381924198251
+15,0.025027122080401924,0.03933713233249252,0.9910558538837774,0.9897959183673469,0.9995003760630373,0.9986007105882753,0.9910419128856003,0.9898107714701602
+16,0.024790827932474956,0.04512184367392283,0.9913209289598796,0.9876093294460642,0.999470932993152,0.9991277018929187,0.9913049437605476,0.9875640087783467
+17,0.017164641173017664,0.0428765761059656,0.9941170434723124,0.9919825072886297,0.9997483471816039,0.9985582112895137,0.9941082775275318,0.9919766593727206
+18,0.014272876617472185,0.044261461064089146,0.9949293703184321,0.9919825072886297,0.9998364982798729,0.9985560863245757,0.9949249873766549,0.9919766593727206
+19,0.013573616959855908,0.03765543523100653,0.9955535793686082,0.9934402332361516,0.9998433336333756,0.9986973964929579,0.9955482501198548,0.9934258582907232
+20,0.01287249052858807,0.04189210441560857,0.9953740123815713,0.9927113702623906,0.9998704032008604,0.9987345833793743,0.9953698552758831,0.9927007299270073
+21,0.012630879596626093,0.037352593599359774,0.9958528576803366,0.9927113702623906,0.999858099038118,0.9986984589754269,0.9958479937677103,0.9926900584795322
+22,0.012325043967807007,0.04300889761374387,0.9957502479734582,0.9941690962099126,0.9998819902386092,0.9986538347117273,0.9957459920740215,0.9941520467836257
+23,0.011392199501855074,0.04363907175206477,0.9961606868009714,0.9941690962099126,0.9999004254983352,0.9986432098870369,0.9961572366337735,0.9941520467836257
+24,0.011286299277906982,0.04223336118646611,0.9960837295208127,0.9934402332361516,0.999887471770091,0.9986931465630816,0.9960801766488078,0.9934258582907232
+25,0.011058116214544809,0.04236892951481348,0.996186339227691,0.9934402332361516,0.9998906818695731,0.9986761468435771,0.9961827487632449,0.9934258582907232
+26,0.01128154789737973,0.04287581923387201,0.9959982214317474,0.9934402332361516,0.999901828015834,0.9986538347117273,0.9959943167228718,0.9934258582907232
+27,0.011398236130418838,0.0421129193472136,0.9960324246673735,0.9934402332361516,0.9998935698184921,0.9986655220188868,0.9960288932251549,0.9934258582907232
+28,0.011419007594133643,0.04220352793498755,0.9960580770940931,0.9934402332361516,0.9998995173934799,0.998675084361108,0.9960551424341739,0.9934258582907232
+29,0.010842687454953264,0.04214560194882841,0.9961350343742518,0.9934402332361516,0.9999097506092081,0.9986772093260461,0.99613079952063,0.9934258582907232
+30,0.011535594235865117,0.0421641564523429,0.9961008311386257,0.9934402332361516,0.999880920546658,0.9986761468435771,0.9960974941804738,0.9934258582907232