Upload DeiT3 model from experiment c2

.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_c2.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-c2
+  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: 0.8814
+      name: Average Accuracy
+    - type: auc
+      value: 0.9275
+      name: Average AUC-ROC
+    - type: f1
+      value: 0.6909
+      name: Average F1-Score
+---
+
+# 🌌 deit3-gravit-c2
+
+🔭 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**: C2 - C21+J24-half
+- **🌌 Dataset**: C21+J24
+- **🪐 Fine-tuning Strategy**: half
+
+
+
+## 💻 Quick Start
+
+```python
+import torch
+import timm
+
+# Load the model directly from the Hub
+model = timm.create_model(
+    'hf-hub:parlange/deit3-gravit-c2',
+    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:** half
+
+
+| 🔧 Parameter | 📝 Value |
+|--------------|----------|
+| Batch Size | 192 |
+| Learning Rate | AdamW with ReduceLROnPlateau |
+| Epochs | 100 |
+| Patience | 10 |
+| Optimizer | AdamW |
+| Scheduler | ReduceLROnPlateau |
+| Image Size | 224x224 |
+| Fine Tune Mode | half |
+| Stochastic Depth Probability | 0.1 |
+
+
+## 📈 Training Curves
+
+![Combined Training Metrics](https://huggingface.co/parlange/deit3-gravit-c2/resolve/main/training_curves/DeiT3_combined_metrics.png)
+
+
+## 🏁 Final Epoch Training Metrics
+
+| Metric | Training | Validation |
+|:---------:|:-----------:|:-------------:|
+| 📉 Loss | 0.0128 | 0.0565 |
+| 🎯 Accuracy | 0.9954 | 0.9898 |
+| 📊 AUC-ROC | 0.9999 | 0.9987 |
+| ⚖️ F1 Score | 0.9954 | 0.9898 |
+
+
+## ☑️ 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-c2/resolve/main/roc_confusion_matrix/DeiT3_roc_confusion_matrix_a.png)
+![ROC + Confusion Matrix - Dataset B](https://huggingface.co/parlange/deit3-gravit-c2/resolve/main/roc_confusion_matrix/DeiT3_roc_confusion_matrix_b.png)
+![ROC + Confusion Matrix - Dataset C](https://huggingface.co/parlange/deit3-gravit-c2/resolve/main/roc_confusion_matrix/DeiT3_roc_confusion_matrix_c.png)
+![ROC + Confusion Matrix - Dataset D](https://huggingface.co/parlange/deit3-gravit-c2/resolve/main/roc_confusion_matrix/DeiT3_roc_confusion_matrix_d.png)
+![ROC + Confusion Matrix - Dataset E](https://huggingface.co/parlange/deit3-gravit-c2/resolve/main/roc_confusion_matrix/DeiT3_roc_confusion_matrix_e.png)
+![ROC + Confusion Matrix - Dataset F](https://huggingface.co/parlange/deit3-gravit-c2/resolve/main/roc_confusion_matrix/DeiT3_roc_confusion_matrix_f.png)
+![ROC + Confusion Matrix - Dataset G](https://huggingface.co/parlange/deit3-gravit-c2/resolve/main/roc_confusion_matrix/DeiT3_roc_confusion_matrix_g.png)
+![ROC + Confusion Matrix - Dataset H](https://huggingface.co/parlange/deit3-gravit-c2/resolve/main/roc_confusion_matrix/DeiT3_roc_confusion_matrix_h.png)
+![ROC + Confusion Matrix - Dataset I](https://huggingface.co/parlange/deit3-gravit-c2/resolve/main/roc_confusion_matrix/DeiT3_roc_confusion_matrix_i.png)
+![ROC + Confusion Matrix - Dataset J](https://huggingface.co/parlange/deit3-gravit-c2/resolve/main/roc_confusion_matrix/DeiT3_roc_confusion_matrix_j.png)
+![ROC + Confusion Matrix - Dataset K](https://huggingface.co/parlange/deit3-gravit-c2/resolve/main/roc_confusion_matrix/DeiT3_roc_confusion_matrix_k.png)
+![ROC + Confusion Matrix - Dataset L](https://huggingface.co/parlange/deit3-gravit-c2/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 | 0.8814 |
+| 📈 Average AUC-ROC | 0.9275 |
+| ⚖️ Average F1-Score | 0.6909 |
+
+
+## 📘 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_c2",
+    "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_c2",
+  "experiment": "c2",
+  "training_strategy": "half",
+  "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": "half",
+    "stochastic_depth_probability": "0.1"
+  },
+  "hf_hub_id": "parlange/deit3-gravit-c2",
+  "license": "apache-2.0"
+}

deit3-gravit-c2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8c31c7e499531397bd19d3ba8baf38f1c3b968eb4b3b8a3513d42d96985e3750
+size 343337390

evaluation_results.csv

@@ -0,0 +1,133 @@
+Model,Dataset,Loss,Accuracy,AUCROC,F1
+ViT,a,0.35447569389258865,0.8949115044247787,0.9020846228498507,0.7480106100795756
+ViT,b,0.2228443425890036,0.9264382269726501,0.9263609576427256,0.5465116279069767
+ViT,c,0.46229862214933587,0.8349575605155611,0.8684438305709024,0.34944237918215615
+ViT,d,0.11673173789463115,0.9537881169443572,0.9704917127071824,0.6573426573426573
+ViT,e,0.3652098159562351,0.8825466520307355,0.920767426019829,0.7249357326478149
+ViT,f,0.24608832064126923,0.9108519842016175,0.9203345361214339,0.22926829268292684
+ViT,g,0.10483654439449311,0.9635,0.997473,0.9644999189495866
+ViT,h,0.23178722894191742,0.915,0.9939590555555555,0.9210526315789473
+ViT,i,0.04857917896906535,0.978,0.9990572222222223,0.9782966129562644
+ViT,j,2.494326035181681,0.6106666666666667,0.5831323333333334,0.42349457058242845
+ViT,k,2.4380686638752618,0.6251666666666666,0.7805802777777779,0.43278688524590164
+ViT,l,1.0272723743838732,0.8127329565949261,0.7993805230717175,0.7184308053873272
+MLP-Mixer,a,1.230455079964832,0.6227876106194691,0.8958911227772556,0.49028400597907323
+MLP-Mixer,b,1.0728926989350893,0.7004086765168186,0.9182900552486188,0.25604996096799376
+MLP-Mixer,c,1.374837134027586,0.5576862621817039,0.8979152854511969,0.18904899135446687
+MLP-Mixer,d,0.09552026474693218,0.9603898145237346,0.9868913443830571,0.7224669603524229
+MLP-Mixer,e,0.9593323631422711,0.7069154774972558,0.9188677817301143,0.5512605042016807
+MLP-Mixer,f,0.9257462782946794,0.7154410381794245,0.9306221006103087,0.09779367918902802
+MLP-Mixer,g,0.5643243643840155,0.8425,0.991425611111111,0.8635773061931572
+MLP-Mixer,h,0.7244052359660467,0.7668333333333334,0.9891666111111111,0.8104592873594364
+MLP-Mixer,i,0.04615406060218811,0.9803333333333333,0.9994367777777778,0.980655737704918
+MLP-Mixer,j,3.0292422666549683,0.45216666666666666,0.392282,0.28309705561613957
+MLP-Mixer,k,2.5110719747940697,0.59,0.7661271111111111,0.3453964874933475
+MLP-Mixer,l,1.4846716919555334,0.6762053625105207,0.7295511702036557,0.5855010004617516
+CvT,a,0.7465745627352621,0.6493362831858407,0.7317079694031161,0.4389380530973451
+CvT,b,0.7336456650122649,0.6765168186104998,0.7552670349907918,0.1942051683633516
+CvT,c,0.8642418710588097,0.5919522162841874,0.6964806629834255,0.16041397153945666
+CvT,d,0.06205783033066015,0.9761081420936812,0.9876427255985267,0.7654320987654321
+CvT,e,0.6019917449757506,0.7178924259055982,0.7936123514720351,0.4910891089108911
+CvT,f,0.5685286294680824,0.7414895617829603,0.8061353821076506,0.08274941608274941
+CvT,g,0.4509977758725484,0.8055,0.9201512777777776,0.8277999114652501
+CvT,h,0.5202355206807454,0.7606666666666667,0.9072719444444444,0.7961964235026966
+CvT,i,0.09494428576032321,0.9643333333333334,0.9977035555555557,0.9632554945054945
+CvT,j,2.988422914981842,0.3456666666666667,0.14668444444444442,0.022896963663514187
+CvT,k,2.6323694267769655,0.5045,0.6181494444444444,0.0300163132137031
+CvT,l,1.337245315202257,0.645425033064807,0.6032419706344807,0.5021944632005402
+Swin,a,0.47572549887463056,0.8407079646017699,0.905882487792577,0.6742081447963801
+Swin,b,0.24361524523634911,0.9163784973278843,0.9362615101289135,0.5283687943262412
+Swin,c,0.4370936370240709,0.8535051870480981,0.9087605893186003,0.3900523560209424
+Swin,d,0.038348094671021904,0.9880540710468406,0.9911620626151013,0.8869047619047619
+Swin,e,0.3579506372581067,0.8781558726673985,0.9260273972602739,0.7286063569682152
+Swin,f,0.24650774364781286,0.9156479217603912,0.9413092437445593,0.24937238493723848
+Swin,g,0.11494702147444089,0.9593333333333334,0.9989898888888888,0.9607969151670951
+Swin,h,0.2175228010714054,0.926,0.9979807777777777,0.9308841843088418
+Swin,i,0.006121216081082821,0.9973333333333333,0.9999798888888889,0.9973315543695798
+Swin,j,2.5422419211069744,0.5825,0.4893003333333333,0.3679031037093111
+Swin,k,2.433416116627554,0.6205,0.7913794999999999,0.39036144578313253
+Swin,l,1.035569912688268,0.8089455332451605,0.7797953948083542,0.7088143668682426
+CaiT,a,0.3509529214517205,0.9081858407079646,0.8966973093999068,0.7726027397260274
+CaiT,b,0.1907231829655279,0.9380697893744105,0.9234548802946593,0.5887265135699373
+CaiT,c,0.3048490960337163,0.90883370009431,0.8791160220994475,0.493006993006993
+CaiT,d,0.06549901952829443,0.9849104055328513,0.969243093922652,0.8545454545454545
+CaiT,e,0.31167979835318943,0.9187705817782656,0.9264058124574283,0.7921348314606742
+CaiT,f,0.1541684599891403,0.9499717886025955,0.9222261921687871,0.3464373464373464
+CaiT,g,0.07805611325552066,0.9708333333333333,0.9986172777777778,0.9714937286202965
+CaiT,h,0.13856186520308256,0.9553333333333334,0.997130611111111,0.9569961489088575
+CaiT,i,0.011666435472667217,0.9956666666666667,0.9999013333333333,0.9956594323873121
+CaiT,j,1.8389671653707822,0.6116666666666667,0.7423962222222222,0.4151606425702811
+CaiT,k,1.7725774958133698,0.6365,0.8888650555555555,0.4312907431551499
+CaiT,l,0.7395369254032035,0.8362991463268006,0.8693810723675515,0.7436693965922997
+DeiT,a,0.48058320357736234,0.8263274336283186,0.8941450218931248,0.6594360086767896
+DeiT,b,0.23002449519573911,0.9251807607670544,0.9313581952117864,0.5608856088560885
+DeiT,c,0.49494195908204974,0.8154668343288274,0.8907605893186004,0.34118967452300786
+DeiT,d,0.05036040664735698,0.9849104055328513,0.9769023941068141,0.8636363636363636
+DeiT,e,0.338863200106291,0.8792535675082327,0.9161961704382048,0.7342995169082126
+DeiT,f,0.26403015722496653,0.9037050968591311,0.9291450866890099,0.2289156626506024
+DeiT,g,0.10851164469867945,0.9641666666666666,0.9990410000000001,0.9653393519264872
+DeiT,h,0.2489620513096452,0.906,0.9981344444444444,0.9139194139194139
+DeiT,i,0.013259729760388533,0.9958333333333333,0.9998315555555556,0.9958423415932147
+DeiT,j,1.2026229511300723,0.7143333333333334,0.7246498888888889,0.6356292517006803
+DeiT,k,1.1073710439900557,0.746,0.8698901111111111,0.6623836951705804
+DeiT,l,0.5658274294531473,0.8476012985451485,0.867833726587774,0.7854785478547854
+DeiT3,a,0.39277621998196155,0.8661504424778761,0.9195532732705195,0.7125890736342043
+DeiT3,b,0.338128161960636,0.8824269097767997,0.9331012891344382,0.44510385756676557
+DeiT3,c,0.323060417608134,0.8883998742533794,0.922292817679558,0.4580152671755725
+DeiT3,d,0.12409640010358478,0.9553599497013517,0.9608121546961326,0.6787330316742082
+DeiT3,e,0.24973662732461413,0.9209659714599341,0.9483084840687203,0.8064516129032258
+DeiT3,f,0.2540075041596123,0.9116042881324055,0.9380772021883802,0.24193548387096775
+DeiT3,g,0.1656125110021482,0.9416666666666667,0.9990236666666666,0.944760101010101
+DeiT3,h,0.15762409150910875,0.9448333333333333,0.9990646111111111,0.9476017096723128
+DeiT3,i,0.05214000094247361,0.9803333333333333,0.9997376666666667,0.9806684141546527
+DeiT3,j,1.1591287109454473,0.696,0.7744774999999999,0.6248457424928013
+DeiT3,k,1.0456561943689981,0.7346666666666667,0.845634,0.6561555075593952
+DeiT3,l,0.5223108836063022,0.854033906456655,0.8898184372191467,0.7933968686181075
+Twins_SVT,a,0.4211153812640536,0.8307522123893806,0.8825833123189902,0.6433566433566433
+Twins_SVT,b,0.3625493723054758,0.8550770198050928,0.8962191528545118,0.37449118046132973
+Twins_SVT,c,0.47319920195681764,0.7868594781515247,0.8548139963167587,0.2893081761006289
+Twins_SVT,d,0.1203458983801289,0.9783087079534738,0.9818324125230202,0.8
+Twins_SVT,e,0.5213294555274637,0.7486278814489572,0.8316203738742148,0.5465346534653466
+Twins_SVT,f,0.3335461875583885,0.8666541282678202,0.9034523383543173,0.16292798110979928
+Twins_SVT,g,0.2639119902451833,0.9085,0.9744078888888889,0.912676952441546
+Twins_SVT,h,0.32257486327489215,0.8723333333333333,0.9662636666666669,0.8822263222632226
+Twins_SVT,i,0.13550377811988196,0.9738333333333333,0.9972788888888889,0.9733672603901612
+Twins_SVT,j,1.2430085968176523,0.49,0.43771377777777776,0.1896186440677966
+Twins_SVT,k,1.1146003757913907,0.5553333333333333,0.7234002222222222,0.2115839243498818
+Twins_SVT,l,0.6286477774643219,0.7480461704941685,0.7275090480198628,0.6162439337057046
+Twins_PCPVT,a,0.45601994748664115,0.7699115044247787,0.8394007473464615,0.5458515283842795
+Twins_PCPVT,b,0.3125818614145001,0.8773970449544168,0.9010699815837937,0.390625
+Twins_PCPVT,c,0.5049686531944119,0.7500785916378497,0.8135911602209945,0.23923444976076555
+Twins_PCPVT,d,0.3149096430453517,0.8918579063187677,0.9015690607734806,0.4208754208754209
+Twins_PCPVT,e,0.42039827045572575,0.8079034028540066,0.8655339438431847,0.5882352941176471
+Twins_PCPVT,f,0.3770137148085496,0.8412638706037239,0.8693597175042401,0.12899896800825594
+Twins_PCPVT,g,0.2785677030881246,0.9015,0.9626754444444443,0.9027480664801711
+Twins_PCPVT,h,0.3805647597312927,0.834,0.928301,0.8463437210737427
+Twins_PCPVT,i,0.2798018006483714,0.9091666666666667,0.9656723333333334,0.9096335599403084
+Twins_PCPVT,j,0.614702238559723,0.6835,0.7995154444444446,0.6018033130635353
+Twins_PCPVT,k,0.6159363424777985,0.6911666666666667,0.7903985,0.6076646199449502
+Twins_PCPVT,l,0.45535326129802217,0.7889864133702056,0.8498913163479216,0.7103004291845494
+PiT,a,0.3937257931823224,0.8296460176991151,0.8874127904755356,0.641860465116279
+PiT,b,0.2796248870145521,0.8777114115058158,0.91848802946593,0.4150375939849624
+PiT,c,0.5313189482209218,0.7613957874882112,0.8498581952117863,0.26666666666666666
+PiT,d,0.049343678185640734,0.9798805407104684,0.9911620626151012,0.8117647058823529
+PiT,e,0.3259278782832505,0.8518111964873765,0.9145841216983274,0.6715328467153284
+PiT,f,0.2841162405192056,0.8750235094978371,0.9172267022129574,0.17196261682242991
+PiT,g,0.1590204114516576,0.9338333333333333,0.9916004444444445,0.9369340746624305
+PiT,h,0.2924602138201396,0.8721666666666666,0.981646111111111,0.8849212303075769
+PiT,i,0.03693298858900865,0.988,0.999485,0.9879396984924623
+PiT,j,2.9977854507366817,0.461,0.277717,0.06477732793522267
+PiT,k,2.8756980224698783,0.5151666666666667,0.7229978888888889,0.07149696776252792
+PiT,l,1.2244331041709067,0.7434170975111218,0.6790239785353327,0.599849990624414
+Ensemble,a,,0.9070796460176991,0.941851401847734,0.79
+Ensemble,b,,0.9374410562716127,0.9600349907918969,0.6135922330097088
+Ensemble,c,,0.895001571832757,0.9307624309392265,0.48615384615384616
+Ensemble,d,,0.9911977365608299,0.9944677716390424,0.9186046511627907
+Ensemble,e,,0.9264544456641054,0.955384848255506,0.825065274151436
+Ensemble,f,,0.941696445363927,0.9599335198386041,0.33760683760683763
+Ensemble,g,,0.9701666666666666,0.9990522222222222,0.9710027539283979
+Ensemble,h,,0.9476666666666667,0.9979163333333333,0.9502219403931516
+Ensemble,i,,0.9986666666666667,0.9999886666666667,0.9986671109630123
+Ensemble,j,,0.5698333333333333,0.6426453333333333,0.31556616282153277
+Ensemble,k,,0.5983333333333334,0.8897323333333333,0.33055555555555555
+Ensemble,l,,0.8179632078874595,0.832089495815299,0.712386018237082

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b4605703a2fb15379f8a7f6b9d78ee6e180720aacb4bbe55c298f9ba327f0c4f
+size 343287616

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8c31c7e499531397bd19d3ba8baf38f1c3b968eb4b3b8a3513d42d96985e3750
+size 343337390

training_curves/DeiT3_metrics.csv

@@ -0,0 +1,33 @@
+epoch,train_loss,val_loss,train_accuracy,val_accuracy,train_auc,val_auc,train_f1,val_f1
+1,0.12564782366525068,0.09143247031783223,0.9496699387762082,0.9701166180758017,0.9897953955706446,0.9949818952987275,0.9494269070163078,0.9691960931630353
+2,0.06985166473383289,0.08619005821710425,0.9751513493176455,0.967201166180758,0.9964409873297829,0.9964481211060017,0.9750262113060965,0.9663928304705004
+3,0.056866804484336446,0.05302565164983533,0.9798029893627938,0.9825072886297376,0.9976251505042683,0.998291528189785,0.9797308893694436,0.9824304538799414
+4,0.049396113803477755,0.05504433993174105,0.9822143174744331,0.9817784256559767,0.9982057377652723,0.997864410237231,0.9821630706959833,0.9816311535635562
+5,0.04529706023203575,0.055494760708888834,0.9840954954338681,0.9817784256559767,0.9984480936957005,0.9982469039260853,0.9840428269933598,0.9816311535635562
+6,0.04219069417126743,0.07323901363955294,0.9848992714710811,0.9817784256559767,0.9987146182299871,0.9982490288910233,0.9848580982594529,0.981549815498155
+7,0.03878903245384483,0.07769435118481995,0.9862331976604987,0.978134110787172,0.9988764635727077,0.9976880381473706,0.9861992113835076,0.9777117384843982
+8,0.03768348647098764,0.05187751815461556,0.9867718986216096,0.978134110787172,0.9989739656650309,0.9985752110090184,0.9867407197894972,0.9781659388646288
+9,0.035332252071126134,0.047895987672899626,0.9875414714231966,0.9861516034985423,0.9990768943053534,0.9981629678110311,0.9875151026983487,0.9861415025528811
+10,0.03292442512115602,0.04784361579124178,0.9884820604029141,0.9846938775510204,0.9991563584521039,0.9985688361142041,0.9884555061322089,0.9846827133479212
+11,0.031959216231868544,0.04134778778066006,0.9885162636385402,0.9854227405247813,0.9992365511299961,0.9988790809951635,0.988494521404645,0.9853587115666179
+12,0.030441437890501438,0.030106425351522994,0.9890635154085576,0.9919825072886297,0.999332758624528,0.9992328876573537,0.989043747911973,0.991941391941392
+13,0.030212009561090096,0.032404553722155775,0.9893200396757533,0.9905247813411079,0.9993305110284528,0.9988280818366497,0.9893000025700555,0.9904901243599122
+14,0.02840607058585027,0.045113166767707415,0.9898245374012381,0.9868804664723032,0.9994037646738821,0.9990852025941572,0.9898102479791753,0.9868035190615836
+15,0.027173070608142978,0.05290923921700904,0.9902264254198447,0.9868804664723032,0.9994564419208908,0.9988057697047998,0.9902126165623422,0.986822840409956
+16,0.026703136191795932,0.040876550279567804,0.9904316448336012,0.9883381924198251,0.999472097736336,0.9994209470543736,0.9904163205179812,0.9882352941176471
+17,0.025977197134483213,0.05056937564023208,0.9907736771898622,0.9876093294460642,0.9995119497936136,0.99927007454377,0.9907604832977968,0.9874908020603385
+18,0.025318288473498336,0.058233319431456466,0.9908506344700209,0.9861516034985423,0.9995286463469422,0.9980726568011627,0.9908388842274697,0.9861818181818182
+19,0.018295483531578612,0.05473324735771115,0.9934842836132298,0.989067055393586,0.9997624935834714,0.9984902124114952,0.9934777026448686,0.9890270665691295
+20,0.01648359577005966,0.05344235519105125,0.9940144337654342,0.9883381924198251,0.9998009583314477,0.9984848999991499,0.9940089010612804,0.9883040935672515
+21,0.015313869771220887,0.05249095143364748,0.9944505250196669,0.9883381924198251,0.9998179710397996,0.998593273210992,0.9944464886234309,0.9883040935672515
+22,0.014103470314492232,0.05631154776162552,0.9948524130382734,0.9897959183673469,0.9998553722375967,0.9985911482460539,0.994848184027659,0.9897510980966325
+23,0.014246693158542125,0.053479249113980436,0.9947156000957691,0.9897959183673469,0.9998608060972292,0.9987218335897458,0.9947114397206819,0.9897510980966325
+24,0.01365864140919325,0.053816328759226435,0.9952286486301604,0.989067055393586,0.9998616445953354,0.9987133337299934,0.9952242382745635,0.989010989010989
+25,0.013170598030770751,0.05417907224986234,0.9951687929678148,0.989067055393586,0.9998794196145752,0.998700583940365,0.9951645342119902,0.989010989010989
+26,0.012533504399363477,0.054909895834005344,0.995433868043917,0.9897959183673469,0.9998854362113815,0.998700583940365,0.9954293344289236,0.9897510980966325
+27,0.013117744544629342,0.05588193238867615,0.9953398091459452,0.9897959183673469,0.9998780878736866,0.9987143962124625,0.9953364993796261,0.9897510980966325
+28,0.012735065618537657,0.05639104115026721,0.9955022745151691,0.9897959183673469,0.99987746053555,0.9987080213176482,0.9954986564430828,0.9897510980966325
+29,0.012913845373764133,0.05681820748151217,0.9953312583370387,0.9897959183673469,0.9998570890090944,0.9987090838001172,0.9953282223287014,0.9897510980966325
+30,0.012114540040115857,0.05638004830731587,0.995630536648767,0.9897959183673469,0.9998962662026188,0.9987112087650554,0.9956270591759018,0.9897510980966325
+31,0.013177719325734288,0.05668536880027785,0.9952115470123474,0.9897959183673469,0.9998738129079314,0.9987122712475244,0.995209416917602,0.9897510980966325
+32,0.0127973821597879,0.05651195309296012,0.9953825631904778,0.9897959183673469,0.9998866051953128,0.9987122712475245,0.9953786115295085,0.9897510980966325

training_metrics.csv

@@ -0,0 +1,33 @@
+epoch,train_loss,val_loss,train_accuracy,val_accuracy,train_auc,val_auc,train_f1,val_f1
+1,0.12564782366525068,0.09143247031783223,0.9496699387762082,0.9701166180758017,0.9897953955706446,0.9949818952987275,0.9494269070163078,0.9691960931630353
+2,0.06985166473383289,0.08619005821710425,0.9751513493176455,0.967201166180758,0.9964409873297829,0.9964481211060017,0.9750262113060965,0.9663928304705004
+3,0.056866804484336446,0.05302565164983533,0.9798029893627938,0.9825072886297376,0.9976251505042683,0.998291528189785,0.9797308893694436,0.9824304538799414
+4,0.049396113803477755,0.05504433993174105,0.9822143174744331,0.9817784256559767,0.9982057377652723,0.997864410237231,0.9821630706959833,0.9816311535635562
+5,0.04529706023203575,0.055494760708888834,0.9840954954338681,0.9817784256559767,0.9984480936957005,0.9982469039260853,0.9840428269933598,0.9816311535635562
+6,0.04219069417126743,0.07323901363955294,0.9848992714710811,0.9817784256559767,0.9987146182299871,0.9982490288910233,0.9848580982594529,0.981549815498155
+7,0.03878903245384483,0.07769435118481995,0.9862331976604987,0.978134110787172,0.9988764635727077,0.9976880381473706,0.9861992113835076,0.9777117384843982
+8,0.03768348647098764,0.05187751815461556,0.9867718986216096,0.978134110787172,0.9989739656650309,0.9985752110090184,0.9867407197894972,0.9781659388646288
+9,0.035332252071126134,0.047895987672899626,0.9875414714231966,0.9861516034985423,0.9990768943053534,0.9981629678110311,0.9875151026983487,0.9861415025528811
+10,0.03292442512115602,0.04784361579124178,0.9884820604029141,0.9846938775510204,0.9991563584521039,0.9985688361142041,0.9884555061322089,0.9846827133479212
+11,0.031959216231868544,0.04134778778066006,0.9885162636385402,0.9854227405247813,0.9992365511299961,0.9988790809951635,0.988494521404645,0.9853587115666179
+12,0.030441437890501438,0.030106425351522994,0.9890635154085576,0.9919825072886297,0.999332758624528,0.9992328876573537,0.989043747911973,0.991941391941392
+13,0.030212009561090096,0.032404553722155775,0.9893200396757533,0.9905247813411079,0.9993305110284528,0.9988280818366497,0.9893000025700555,0.9904901243599122
+14,0.02840607058585027,0.045113166767707415,0.9898245374012381,0.9868804664723032,0.9994037646738821,0.9990852025941572,0.9898102479791753,0.9868035190615836
+15,0.027173070608142978,0.05290923921700904,0.9902264254198447,0.9868804664723032,0.9994564419208908,0.9988057697047998,0.9902126165623422,0.986822840409956
+16,0.026703136191795932,0.040876550279567804,0.9904316448336012,0.9883381924198251,0.999472097736336,0.9994209470543736,0.9904163205179812,0.9882352941176471
+17,0.025977197134483213,0.05056937564023208,0.9907736771898622,0.9876093294460642,0.9995119497936136,0.99927007454377,0.9907604832977968,0.9874908020603385
+18,0.025318288473498336,0.058233319431456466,0.9908506344700209,0.9861516034985423,0.9995286463469422,0.9980726568011627,0.9908388842274697,0.9861818181818182
+19,0.018295483531578612,0.05473324735771115,0.9934842836132298,0.989067055393586,0.9997624935834714,0.9984902124114952,0.9934777026448686,0.9890270665691295
+20,0.01648359577005966,0.05344235519105125,0.9940144337654342,0.9883381924198251,0.9998009583314477,0.9984848999991499,0.9940089010612804,0.9883040935672515
+21,0.015313869771220887,0.05249095143364748,0.9944505250196669,0.9883381924198251,0.9998179710397996,0.998593273210992,0.9944464886234309,0.9883040935672515
+22,0.014103470314492232,0.05631154776162552,0.9948524130382734,0.9897959183673469,0.9998553722375967,0.9985911482460539,0.994848184027659,0.9897510980966325
+23,0.014246693158542125,0.053479249113980436,0.9947156000957691,0.9897959183673469,0.9998608060972292,0.9987218335897458,0.9947114397206819,0.9897510980966325
+24,0.01365864140919325,0.053816328759226435,0.9952286486301604,0.989067055393586,0.9998616445953354,0.9987133337299934,0.9952242382745635,0.989010989010989
+25,0.013170598030770751,0.05417907224986234,0.9951687929678148,0.989067055393586,0.9998794196145752,0.998700583940365,0.9951645342119902,0.989010989010989
+26,0.012533504399363477,0.054909895834005344,0.995433868043917,0.9897959183673469,0.9998854362113815,0.998700583940365,0.9954293344289236,0.9897510980966325
+27,0.013117744544629342,0.05588193238867615,0.9953398091459452,0.9897959183673469,0.9998780878736866,0.9987143962124625,0.9953364993796261,0.9897510980966325
+28,0.012735065618537657,0.05639104115026721,0.9955022745151691,0.9897959183673469,0.99987746053555,0.9987080213176482,0.9954986564430828,0.9897510980966325
+29,0.012913845373764133,0.05681820748151217,0.9953312583370387,0.9897959183673469,0.9998570890090944,0.9987090838001172,0.9953282223287014,0.9897510980966325
+30,0.012114540040115857,0.05638004830731587,0.995630536648767,0.9897959183673469,0.9998962662026188,0.9987112087650554,0.9956270591759018,0.9897510980966325
+31,0.013177719325734288,0.05668536880027785,0.9952115470123474,0.9897959183673469,0.9998738129079314,0.9987122712475244,0.995209416917602,0.9897510980966325
+32,0.0127973821597879,0.05651195309296012,0.9953825631904778,0.9897959183673469,0.9998866051953128,0.9987122712475245,0.9953786115295085,0.9897510980966325