Upload DeiT3 model from experiment s3

.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_s3.ipynb filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,165 @@
+---
+license: apache-2.0
+tags:
+- vision-transformer
+- image-classification
+- pytorch
+- timm
+- deit3
+- gravitational-lensing
+- strong-lensing
+- astronomy
+- astrophysics
+datasets:
+- parlange/gravit-c21
+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-s3
+  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: 0.8804
+      name: Average Accuracy
+    - type: auc
+      value: 0.8794
+      name: Average AUC-ROC
+    - type: f1
+      value: 0.6576
+      name: Average F1-Score
+---
+
+# 🌌 deit3-gravit-s3
+
+🔭 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**: S3 - C21-all-blocks-ResNet18-18660
+- **🌌 Dataset**: C21
+- **🪐 Fine-tuning Strategy**: all-blocks
+
+- **🎲 Random Seed**: 18660
+
+## 💻 Quick Start
+
+```python
+import torch
+import timm
+
+# Load the model directly from the Hub
+model = timm.create_model(
+    'hf-hub:parlange/deit3-gravit-s3',
+    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 (Cañameras et al. 2021)  
+**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-s3/resolve/main/training_curves/DeiT3_combined_metrics.png)
+
+
+## 🏁 Final Epoch Training Metrics
+
+| Metric | Training | Validation |
+|:---------:|:-----------:|:-------------:|
+| 📉 Loss | 0.0048 | 0.0500 |
+| 🎯 Accuracy | 0.9981 | 0.9910 |
+| 📊 AUC-ROC | 1.0000 | 0.9986 |
+| ⚖️ F1 Score | 0.9981 | 0.9910 |
+
+
+## ☑️ 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-s3/resolve/main/roc_confusion_matrix/DeiT3_roc_confusion_matrix_a.png)
+![ROC + Confusion Matrix - Dataset B](https://huggingface.co/parlange/deit3-gravit-s3/resolve/main/roc_confusion_matrix/DeiT3_roc_confusion_matrix_b.png)
+![ROC + Confusion Matrix - Dataset C](https://huggingface.co/parlange/deit3-gravit-s3/resolve/main/roc_confusion_matrix/DeiT3_roc_confusion_matrix_c.png)
+![ROC + Confusion Matrix - Dataset D](https://huggingface.co/parlange/deit3-gravit-s3/resolve/main/roc_confusion_matrix/DeiT3_roc_confusion_matrix_d.png)
+![ROC + Confusion Matrix - Dataset E](https://huggingface.co/parlange/deit3-gravit-s3/resolve/main/roc_confusion_matrix/DeiT3_roc_confusion_matrix_e.png)
+![ROC + Confusion Matrix - Dataset F](https://huggingface.co/parlange/deit3-gravit-s3/resolve/main/roc_confusion_matrix/DeiT3_roc_confusion_matrix_f.png)
+![ROC + Confusion Matrix - Dataset G](https://huggingface.co/parlange/deit3-gravit-s3/resolve/main/roc_confusion_matrix/DeiT3_roc_confusion_matrix_g.png)
+![ROC + Confusion Matrix - Dataset H](https://huggingface.co/parlange/deit3-gravit-s3/resolve/main/roc_confusion_matrix/DeiT3_roc_confusion_matrix_h.png)
+![ROC + Confusion Matrix - Dataset I](https://huggingface.co/parlange/deit3-gravit-s3/resolve/main/roc_confusion_matrix/DeiT3_roc_confusion_matrix_i.png)
+![ROC + Confusion Matrix - Dataset J](https://huggingface.co/parlange/deit3-gravit-s3/resolve/main/roc_confusion_matrix/DeiT3_roc_confusion_matrix_j.png)
+![ROC + Confusion Matrix - Dataset K](https://huggingface.co/parlange/deit3-gravit-s3/resolve/main/roc_confusion_matrix/DeiT3_roc_confusion_matrix_k.png)
+![ROC + Confusion Matrix - Dataset L](https://huggingface.co/parlange/deit3-gravit-s3/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 | 0.8804 |
+| 📈 Average AUC-ROC | 0.8794 |
+| ⚖️ Average F1-Score | 0.6576 |
+
+
+## 📘 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_s3",
+    "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_s3",
+  "experiment": "s3",
+  "training_strategy": "all-blocks",
+  "dataset": "C21",
+  "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-s3",
+  "license": "apache-2.0"
+}

deit3-gravit-s3.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:00177f54a9da39283b65f7fec299d1c44587607a588742d1dc1ed945f37b57bd
+size 343337390

evaluation_results.csv

@@ -0,0 +1,145 @@
+Model,Dataset,Loss,Accuracy,AUCROC,F1
+ViT,a,0.23330061458559465,0.904432568374725,0.9365773480662983,0.4950166112956811
+ViT,b,0.15167975368101766,0.9421565545425966,0.9638158379373848,0.6182572614107884
+ViT,c,0.42172509137656994,0.8267840301791889,0.9025782688766114,0.3510011778563015
+ViT,d,0.1090005352573176,0.95881798176674,0.974342541436464,0.6946386946386947
+ViT,e,0.2932905108554434,0.8902305159165752,0.9406039506546583,0.7487437185929648
+ViT,f,0.21606165350946946,0.9115482921539773,0.9441149153910586,0.20694444444444443
+ViT,g,0.07253240664303302,0.9705,0.998692111111111,0.971111473804472
+ViT,h,0.21570144249498843,0.9093333333333333,0.9954923333333334,0.9162303664921466
+ViT,i,0.04990530861914158,0.9793333333333333,0.9991746666666667,0.9795851168916694
+ViT,j,3.397079090178013,0.5168333333333334,0.5124903333333333,0.1486049926578561
+ViT,k,3.3744520025253295,0.5256666666666666,0.6147927777777777,0.1509546539379475
+ViT,l,1.2076301042454038,0.7930305113426048,0.7260690116291557,0.6331083614548182
+MLP-Mixer,a,0.6226771516981308,0.8201823325998113,0.8910414364640883,0.33796296296296297
+MLP-Mixer,b,0.32969332946167546,0.908519333542911,0.9376252302025783,0.5008576329331046
+MLP-Mixer,c,1.2415813063720755,0.6787173844702924,0.8285883977900552,0.2222222222222222
+MLP-Mixer,d,0.07694695194780883,0.9795661741590694,0.9830349907918968,0.8179271708683473
+MLP-Mixer,e,0.6463492494383183,0.8342480790340285,0.8990236887913419,0.6591422121896162
+MLP-Mixer,f,0.5533021807061205,0.8481140113081869,0.9094389205470177,0.12960497114957834
+MLP-Mixer,g,0.14915568167157472,0.9568333333333333,0.9983734444444444,0.9585798816568047
+MLP-Mixer,h,0.6326082771439105,0.835,0.9925535,0.8582474226804123
+MLP-Mixer,i,0.015157968224957585,0.9945,0.9999197777777777,0.9945246391239423
+MLP-Mixer,j,4.768675954580307,0.48783333333333334,0.32178805555555556,0.10642628671125327
+MLP-Mixer,k,4.634678235054016,0.5255,0.5500302222222222,0.11391223155929038
+MLP-Mixer,l,1.844831031485805,0.7471841785204378,0.6553877700624002,0.5818245429895915
+CvT,a,0.21327115955104695,0.9280100597296448,0.9095662983425414,0.5410821643286573
+CvT,b,0.2245168307551945,0.9261238604212512,0.9276169429097607,0.5346534653465347
+CvT,c,0.5436479192752952,0.8308707953473751,0.8541436464088398,0.3341584158415842
+CvT,d,0.07627428377018489,0.9767368751964791,0.9801915285451197,0.7848837209302325
+CvT,e,0.4199431847400644,0.8594950603732162,0.8942859305229698,0.678391959798995
+CvT,f,0.23622647001237154,0.9209975989466347,0.9165266282718422,0.20930232558139536
+CvT,g,0.0921408845228143,0.9676666666666667,0.9993117777777779,0.9686287192755498
+CvT,h,0.2613335499805398,0.9171666666666667,0.9978183333333334,0.9233852320024665
+CvT,i,0.013547633681911975,0.9945,0.9999296666666666,0.9945210028225137
+CvT,j,4.21272634255886,0.4856666666666667,0.24911683333333334,0.06257594167679223
+CvT,k,4.134133087083697,0.5125,0.6382155555555556,0.06579367614180773
+CvT,l,1.4700100416854185,0.7926074771297129,0.6455889580274956,0.6224489795918368
+Swin,a,0.5396662080149275,0.7937755422823012,0.9155405156537753,0.32510288065843623
+Swin,b,0.3355165186101856,0.8814838101226029,0.9462909760589319,0.455988455988456
+Swin,c,1.0126445727766553,0.657340458975165,0.871803867403315,0.22475106685633
+Swin,d,0.04055070694646055,0.986167871738447,0.9945414364640884,0.8777777777777778
+Swin,e,0.6789207920415734,0.7760702524698134,0.9016120487398773,0.6076923076923076
+Swin,f,0.5000679909827477,0.8234838509797847,0.9302990716669634,0.12177263969171484
+Swin,g,0.1668860674443422,0.9405,0.999325,0.9437883797827114
+Swin,h,0.5258767666163622,0.8216666666666667,0.9975895555555556,0.8485277463193658
+Swin,i,0.010505019271629862,0.996,0.9999704444444445,0.996011964107677
+Swin,j,4.138313320279122,0.45866666666666667,0.14908555555555558,0.06127167630057803
+Swin,k,3.9819322906583547,0.5141666666666667,0.5644793333333333,0.06779661016949153
+Swin,l,1.6023035252941213,0.726296864258897,0.6168375948237592,0.5575312019148573
+CaiT,a,0.18350773630736947,0.945300220056586,0.9521998158379374,0.634453781512605
+CaiT,b,0.2112922705674801,0.9320968248978309,0.9511565377532228,0.583011583011583
+CaiT,c,0.47731829819458904,0.8654511160012575,0.9114604051565378,0.4136986301369863
+CaiT,d,0.07184898189050302,0.9808236403646652,0.979158379373849,0.8319559228650137
+CaiT,e,0.66179066170191,0.8068057080131723,0.8871868614243549,0.6317991631799164
+CaiT,f,0.23348395380409856,0.9275811323677484,0.9449781479343615,0.24413904607922393
+CaiT,g,0.09087410058942623,0.9678333333333333,0.9993048888888888,0.9687651723579868
+CaiT,h,0.23191223003831693,0.9325,0.9980312777777778,0.9366296354248161
+CaiT,i,0.016945911412360147,0.9936666666666667,0.999897111111111,0.9936918990703851
+CaiT,j,3.6651160932779314,0.5033333333333333,0.5270411111111111,0.1214622641509434
+CaiT,k,3.591187914278358,0.5291666666666667,0.5760749444444444,0.12727834414581402
+CaiT,l,1.295636463950478,0.8024430225794511,0.7398510347639352,0.6420084323495592
+DeiT,a,0.16014718334959085,0.9569317824583464,0.940755985267035,0.6745843230403801
+DeiT,b,0.10635868036350676,0.9729644765796919,0.9633609576427257,0.7675675675675676
+DeiT,c,0.23710613171471923,0.9355548569632192,0.9248029465930019,0.5807770961145194
+DeiT,d,0.08718779183401884,0.9779943414020749,0.9719484346224677,0.8022598870056498
+DeiT,e,0.36636867216337393,0.9099890230515917,0.9294634072504351,0.7759562841530054
+DeiT,f,0.10625621084368816,0.9671597862287972,0.9490269646243918,0.4011299435028249
+DeiT,g,0.023581442082300782,0.9911666666666666,0.9998664444444445,0.9912266181095845
+DeiT,h,0.09289937312342227,0.9713333333333334,0.9993322222222223,0.9720779220779221
+DeiT,i,0.013417671525850891,0.9938333333333333,0.9999291111111112,0.9938589211618257
+DeiT,j,5.060567226946354,0.519,0.5434004444444445,0.10037406483790523
+DeiT,k,5.050403485819698,0.5216666666666666,0.5780161111111111,0.10087719298245613
+DeiT,l,1.6720809529578171,0.8271376447570197,0.7329687320683346,0.6685592618878637
+DeiT3,a,0.09279773294391665,0.9742219427852876,0.956814917127072,0.7670454545454546
+DeiT3,b,0.1237781981520966,0.9585036152153411,0.9581307550644568,0.6716417910447762
+DeiT3,c,0.14906807608975062,0.949386985224772,0.9397476979742174,0.6264501160092807
+DeiT3,d,0.076721701036737,0.9783087079534738,0.9859097605893186,0.7964601769911505
+DeiT3,e,0.33115524258035206,0.9066959385290889,0.9261711950351927,0.7605633802816901
+DeiT3,f,0.07180493832847527,0.9732785996437147,0.9582022281728896,0.43902439024390244
+DeiT3,g,0.03650352464616299,0.9841666666666666,0.999683,0.9843672864900445
+DeiT3,h,0.04991138017177582,0.9793333333333333,0.9995745555555556,0.9796921061251228
+DeiT3,i,0.011555743247270584,0.9946666666666667,0.9999258888888889,0.9946790821416694
+DeiT3,j,4.905326539263129,0.5121666666666667,0.3997841666666667,0.09799691833590139
+DeiT3,k,4.880378704622388,0.5226666666666666,0.7140411111111111,0.09993714644877436
+DeiT3,l,1.595974028533837,0.8310507112262704,0.7152346731164213,0.6728110599078341
+Twins_SVT,a,0.5287571287837204,0.8016347060672745,0.9145736648250459,0.3322751322751323
+Twins_SVT,b,0.33979776653431004,0.86765168186105,0.9400736648250463,0.4272108843537415
+Twins_SVT,c,0.8760767604374579,0.6592266582835586,0.8834567219152852,0.2246065808297568
+Twins_SVT,d,0.0414358896034407,0.9867966048412449,0.9934677716390424,0.8820224719101124
+Twins_SVT,e,1.014912523631861,0.6597145993413831,0.864413834859608,0.5032051282051282
+Twins_SVT,f,0.485403974522426,0.8147316241964216,0.9289660305625117,0.11603843311160385
+Twins_SVT,g,0.16855271980445832,0.9326666666666666,0.9987118333333335,0.9367762128325509
+Twins_SVT,h,0.4528699638573453,0.8221666666666667,0.9961345,0.8487168580745782
+Twins_SVT,i,0.010371196451596915,0.9958333333333333,0.9999524444444444,0.9958409582432207
+Twins_SVT,j,4.296078189373016,0.4568333333333333,0.19758433333333336,0.07807637906647807
+Twins_SVT,k,4.137896645441652,0.52,0.6393722222222222,0.08745247148288973
+Twins_SVT,l,1.6425652151218086,0.7218021257469198,0.6391880993028709,0.5555461687927684
+Twins_PCPVT,a,0.28459295154517267,0.8962590380383527,0.9146933701657459,0.4745222929936306
+Twins_PCPVT,b,0.1722448716166727,0.9421565545425966,0.9457421731123388,0.6182572614107884
+Twins_PCPVT,c,0.5418229629617936,0.8047783715812638,0.8814585635359117,0.32426550598476606
+Twins_PCPVT,d,0.07013078457132774,0.9820811065702609,0.9903885819521179,0.8394366197183099
+Twins_PCPVT,e,0.479874432446797,0.8375411635565313,0.8898963142359798,0.6681614349775785
+Twins_PCPVT,f,0.25029015365415846,0.9061265587483541,0.930595278912214,0.19735099337748344
+Twins_PCPVT,g,0.07097410994302482,0.9728333333333333,0.999268111111111,0.9734570916788796
+Twins_PCPVT,h,0.26691202929150315,0.9,0.9973623888888888,0.9087868653086044
+Twins_PCPVT,i,0.016836636100895704,0.994,0.9998691111111111,0.9940139674093781
+Twins_PCPVT,j,7.1517002888023855,0.5098333333333334,0.18946605555555554,0.1254831995242343
+Twins_PCPVT,k,7.097562807479873,0.531,0.5933782777777777,0.13040791100123608
+Twins_PCPVT,l,2.4205206177914396,0.7878483422346783,0.6371767534317276,0.6253968253968254
+PiT,a,2.0392126046198413,0.4360264067903175,0.8411418047882135,0.15853658536585366
+PiT,b,1.2754779040757234,0.6463376296762025,0.8967909760589319,0.23103212576896787
+PiT,c,3.5646744424987236,0.255580006287331,0.7408324125230203,0.12490761271249076
+PiT,d,0.03054899423822634,0.9880540710468406,0.9968987108655616,0.898936170212766
+PiT,e,2.2146248903808425,0.4774972557628979,0.806800121092863,0.4152334152334152
+PiT,f,1.8453932350700364,0.5544109673921462,0.8653539513829515,0.05549170907896897
+PiT,g,0.6705343906283379,0.8145,0.9932486111111111,0.8435259384226065
+PiT,h,1.8841899921298026,0.6073333333333333,0.9759541111111112,0.7180469123982767
+PiT,i,0.010514569073915481,0.9956666666666667,0.9999776666666667,0.9956853634251577
+PiT,j,4.467936363220215,0.3516666666666667,0.16883433333333334,0.10285977859778597
+PiT,k,3.807916547060013,0.5328333333333334,0.7121261111111112,0.13727300707910126
+PiT,l,2.465662835393678,0.5489397705039395,0.6250971701663347,0.4429933394279744
+ResNet-18,a,0.6459113768308052,0.7654825526563973,0.9383268876611418,0.3079777365491651
+ResNet-18,b,0.6718155814768645,0.7790003143665514,0.9370386740331492,0.3207729468599034
+ResNet-18,c,1.1330159351684057,0.6526249607041811,0.9005441988950276,0.23103688239387613
+ResNet-18,d,0.014098176388939534,0.9949701351776171,0.9996151012891344,0.9540229885057471
+ResNet-18,e,0.727007691933478,0.7058177826564215,0.9220616059940968,0.5533333333333333
+ResNet-18,f,0.6458914898100172,0.7848346371311284,0.9426299731351963,0.1067524115755627
+ResNet-18,g,0.3519982568551786,0.8841666666666667,0.9969418333333333,0.8959736566382278
+ResNet-18,h,0.5965127636720426,0.8171666666666667,0.9945367777777777,0.845122123394042
+ResNet-18,i,0.0032961710044764913,0.9986666666666667,0.9999976666666667,0.9986653319986654
+ResNet-18,j,7.148829643726349,0.38666666666666666,0.04898066666666667,0.004329004329004329
+ResNet-18,k,6.800127555849089,0.5011666666666666,0.5824981111111112,0.005317381189764041
+ResNet-18,l,2.5991157615762135,0.6945164190153879,0.5908983361702036,0.5229956238130625
+Ensemble,a,,0.9289531593838416,0.9334871086556169,0.5735849056603773
+Ensemble,b,,0.9462433197107828,0.9550589318600368,0.64
+Ensemble,c,,0.840301791889343,0.8989116022099447,0.37438423645320196
+Ensemble,d,,0.9874253379440427,0.992403314917127,0.8837209302325582
+Ensemble,e,,0.862788144895719,0.9159312798001968,0.7086247086247086
+Ensemble,f,,0.9261095190147935,0.9433002912162074,0.24165341812400637
+Ensemble,g,,0.9761666666666666,0.9997736666666667,0.9767138902458883
+Ensemble,h,,0.92,0.9990904444444445,0.9259030564989195
+Ensemble,i,,0.998,0.9999855555555555,0.9980033277870216
+Ensemble,j,,0.4985,0.25344022222222223,0.08122137404580153
+Ensemble,k,,0.5203333333333333,0.6153003333333333,0.0846055979643766
+Ensemble,l,,0.7978954047908624,0.6487850790241945,0.6321462945139558

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:394b7674c4d7157193f9c8a3b055fb9b024c6435c98dfe461299e0dc6da097cf
+size 343287616

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:00177f54a9da39283b65f7fec299d1c44587607a588742d1dc1ed945f37b57bd
+size 343337390

training_curves/DeiT3_metrics.csv

@@ -0,0 +1,28 @@
+epoch,train_loss,val_loss,train_accuracy,val_accuracy,train_auc,val_auc,train_f1,val_f1
+1,0.13692867085577207,0.07421052139997482,0.9407556270096463,0.978,0.9887223029239888,0.997632,0.9407572144369122,0.9783464566929134
+2,0.048061912743991596,0.05094329964928329,0.9823954983922829,0.982,0.9984246124879234,0.9985300000000001,0.9823921957494707,0.9818548387096774
+3,0.034636192352861354,0.04595610737428069,0.9877813504823151,0.983,0.9991717887876814,0.99875,0.9877820052515942,0.9829488465396189
+4,0.029761615775262044,0.06541032767249272,0.9893354769560557,0.985,0.9993711192789341,0.998534,0.9893377625375054,0.9849548645937813
+5,0.030002773200967305,0.051245969947427514,0.9892818863879957,0.984,0.999385977307008,0.99814,0.9892824607470125,0.9839679358717435
+6,0.02682357684221011,0.04745743262767792,0.9903536977491961,0.985,0.9995302841276569,0.9979460000000001,0.9903516295025729,0.9850448654037887
+7,0.022328507840345912,0.04253761661052704,0.9917738478027867,0.988,0.9996601780723249,0.9993879999999999,0.9917762717312689,0.9879518072289156
+8,0.023209826517969944,0.04362523984909058,0.9920685959271168,0.989,0.9995784854834466,0.9991639999999999,0.9920719948575102,0.9890329012961117
+9,0.01983714324614584,0.07314276767149568,0.9930064308681672,0.984,0.9997082315227417,0.997778,0.9930054937692617,0.9839679358717435
+10,0.023987467304902255,0.05695145654678345,0.9913183279742765,0.986,0.9995943573095121,0.998852,0.9913146043319752,0.9860557768924303
+11,0.019595004033321258,0.062166427850723266,0.992550911039657,0.984,0.9997504003496885,0.9977739999999999,0.9925465172395302,0.9840637450199203
+12,0.018815073947095796,0.053746583104133605,0.9929796355841372,0.99,0.9997343002036786,0.999192,0.992978883052846,0.9899799599198397
+13,0.019448585342915305,0.08425082373619079,0.9929260450160772,0.984,0.9997465720416916,0.9977720000000001,0.9929294552466656,0.9839034205231388
+14,0.011912179231745493,0.06962954658264062,0.9956323687031082,0.985,0.9999023422467143,0.9982420000000001,0.9956324857318936,0.9849246231155779
+15,0.010103805389343625,0.061363389253616334,0.9965434083601287,0.989,0.9999240972602755,0.998372,0.9965425745758624,0.9889447236180905
+16,0.008275224358574083,0.05774303518238594,0.9969453376205788,0.991,0.9999478827417694,0.9984360000000001,0.9969451739107134,0.9909729187562688
+17,0.008736756973947815,0.0483376273214817,0.9969721329046088,0.99,0.9999491435273737,0.9985139999999999,0.9969712401833338,0.99
+18,0.0076623801350851105,0.04974857234954834,0.9971061093247588,0.99,0.9999615905542746,0.99844,0.9971067295327904,0.99
+19,0.00820424718388515,0.055063622951536675,0.9970257234726688,0.992,0.9999551243611351,0.998472,0.997025643773949,0.9919678714859438
+20,0.007627792189001043,0.049032895147800445,0.9970525187566989,0.99,0.9999623789042711,0.998566,0.9970514126413982,0.9900199600798403
+21,0.006668012922197742,0.04988277526572347,0.997534833869239,0.99,0.9999717730494009,0.998564,0.9975352301344907,0.99
+22,0.005706650657029792,0.05048745417594819,0.9976956055734191,0.989,0.999980499466392,0.998592,0.9976965931004929,0.988988988988989
+23,0.00603126482562674,0.05044751685857773,0.9977224008574491,0.99,0.999977414993182,0.9985660000000001,0.9977222177559826,0.99
+24,0.006448185958810093,0.05043740690127015,0.9978295819935691,0.991,0.9999700197245457,0.998554,0.9978294075086421,0.991008991008991
+25,0.0067558092912254775,0.05029597575962543,0.997668810289389,0.99,0.9999410776586493,0.998568,0.9976688727526057,0.99
+26,0.006298534143184554,0.04814575481414795,0.997508038585209,0.991,0.999974746952575,0.9985980000000001,0.9975078382506632,0.991008991008991
+27,0.004799275206745575,0.04999193596467376,0.9980975348338692,0.991,0.9999868723211895,0.998586,0.9980974838554088,0.991008991008991

training_metrics.csv

@@ -0,0 +1,28 @@
+epoch,train_loss,val_loss,train_accuracy,val_accuracy,train_auc,val_auc,train_f1,val_f1
+1,0.13692867085577207,0.07421052139997482,0.9407556270096463,0.978,0.9887223029239888,0.997632,0.9407572144369122,0.9783464566929134
+2,0.048061912743991596,0.05094329964928329,0.9823954983922829,0.982,0.9984246124879234,0.9985300000000001,0.9823921957494707,0.9818548387096774
+3,0.034636192352861354,0.04595610737428069,0.9877813504823151,0.983,0.9991717887876814,0.99875,0.9877820052515942,0.9829488465396189
+4,0.029761615775262044,0.06541032767249272,0.9893354769560557,0.985,0.9993711192789341,0.998534,0.9893377625375054,0.9849548645937813
+5,0.030002773200967305,0.051245969947427514,0.9892818863879957,0.984,0.999385977307008,0.99814,0.9892824607470125,0.9839679358717435
+6,0.02682357684221011,0.04745743262767792,0.9903536977491961,0.985,0.9995302841276569,0.9979460000000001,0.9903516295025729,0.9850448654037887
+7,0.022328507840345912,0.04253761661052704,0.9917738478027867,0.988,0.9996601780723249,0.9993879999999999,0.9917762717312689,0.9879518072289156
+8,0.023209826517969944,0.04362523984909058,0.9920685959271168,0.989,0.9995784854834466,0.9991639999999999,0.9920719948575102,0.9890329012961117
+9,0.01983714324614584,0.07314276767149568,0.9930064308681672,0.984,0.9997082315227417,0.997778,0.9930054937692617,0.9839679358717435
+10,0.023987467304902255,0.05695145654678345,0.9913183279742765,0.986,0.9995943573095121,0.998852,0.9913146043319752,0.9860557768924303
+11,0.019595004033321258,0.062166427850723266,0.992550911039657,0.984,0.9997504003496885,0.9977739999999999,0.9925465172395302,0.9840637450199203
+12,0.018815073947095796,0.053746583104133605,0.9929796355841372,0.99,0.9997343002036786,0.999192,0.992978883052846,0.9899799599198397
+13,0.019448585342915305,0.08425082373619079,0.9929260450160772,0.984,0.9997465720416916,0.9977720000000001,0.9929294552466656,0.9839034205231388
+14,0.011912179231745493,0.06962954658264062,0.9956323687031082,0.985,0.9999023422467143,0.9982420000000001,0.9956324857318936,0.9849246231155779
+15,0.010103805389343625,0.061363389253616334,0.9965434083601287,0.989,0.9999240972602755,0.998372,0.9965425745758624,0.9889447236180905
+16,0.008275224358574083,0.05774303518238594,0.9969453376205788,0.991,0.9999478827417694,0.9984360000000001,0.9969451739107134,0.9909729187562688
+17,0.008736756973947815,0.0483376273214817,0.9969721329046088,0.99,0.9999491435273737,0.9985139999999999,0.9969712401833338,0.99
+18,0.0076623801350851105,0.04974857234954834,0.9971061093247588,0.99,0.9999615905542746,0.99844,0.9971067295327904,0.99
+19,0.00820424718388515,0.055063622951536675,0.9970257234726688,0.992,0.9999551243611351,0.998472,0.997025643773949,0.9919678714859438
+20,0.007627792189001043,0.049032895147800445,0.9970525187566989,0.99,0.9999623789042711,0.998566,0.9970514126413982,0.9900199600798403
+21,0.006668012922197742,0.04988277526572347,0.997534833869239,0.99,0.9999717730494009,0.998564,0.9975352301344907,0.99
+22,0.005706650657029792,0.05048745417594819,0.9976956055734191,0.989,0.999980499466392,0.998592,0.9976965931004929,0.988988988988989
+23,0.00603126482562674,0.05044751685857773,0.9977224008574491,0.99,0.999977414993182,0.9985660000000001,0.9977222177559826,0.99
+24,0.006448185958810093,0.05043740690127015,0.9978295819935691,0.991,0.9999700197245457,0.998554,0.9978294075086421,0.991008991008991
+25,0.0067558092912254775,0.05029597575962543,0.997668810289389,0.99,0.9999410776586493,0.998568,0.9976688727526057,0.99
+26,0.006298534143184554,0.04814575481414795,0.997508038585209,0.991,0.999974746952575,0.9985980000000001,0.9975078382506632,0.991008991008991
+27,0.004799275206745575,0.04999193596467376,0.9980975348338692,0.991,0.9999868723211895,0.998586,0.9980974838554088,0.991008991008991