Upload ViT model from experiment b2

.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/ViT_combined_metrics.png filter=lfs diff=lfs merge=lfs -text
+training_notebook_b2.ipynb filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,161 @@
+---
+license: apache-2.0
+tags:
+- vision-transformer
+- image-classification
+- pytorch
+- timm
+- vit
+- gravitational-lensing
+- strong-lensing
+- astronomy
+- astrophysics
+datasets:
+- J24
+metrics:
+- accuracy
+- auc
+- f1
+model-index:
+- name: ViT-b2
+  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: 0.8112
+      name: Average Accuracy
+    - type: auc
+      value: 0.7916
+      name: Average AUC-ROC
+    - type: f1
+      value: 0.4887
+      name: Average F1-Score
+---
+
+# 🌌 vit-gravit-b2
+
+🔭 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**: ViT
+- **🧪 Experiment**: B2 - J24-half
+- **🌌 Dataset**: 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/vit-gravit-b2',
+    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:** J24 (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/vit-gravit-b2/resolve/main/training_curves/ViT_combined_metrics.png)
+
+
+## 🏁 Final Epoch Training Metrics
+
+| Metric | Training | Validation |
+|:---------:|:-----------:|:-------------:|
+| 📉 Loss | 0.0291 | 0.0761 |
+| 🎯 Accuracy | 0.9900 | 0.9802 |
+| 📊 AUC-ROC | 0.9992 | 0.9974 |
+| ⚖️ F1 Score | 0.9900 | 0.9801 |
+
+
+## ☑️ 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/vit-gravit-b2/resolve/main/roc_confusion_matrix/ViT_roc_confusion_matrix_a.png)
+![ROC + Confusion Matrix - Dataset B](https://huggingface.co/parlange/vit-gravit-b2/resolve/main/roc_confusion_matrix/ViT_roc_confusion_matrix_b.png)
+![ROC + Confusion Matrix - Dataset C](https://huggingface.co/parlange/vit-gravit-b2/resolve/main/roc_confusion_matrix/ViT_roc_confusion_matrix_c.png)
+![ROC + Confusion Matrix - Dataset D](https://huggingface.co/parlange/vit-gravit-b2/resolve/main/roc_confusion_matrix/ViT_roc_confusion_matrix_d.png)
+![ROC + Confusion Matrix - Dataset E](https://huggingface.co/parlange/vit-gravit-b2/resolve/main/roc_confusion_matrix/ViT_roc_confusion_matrix_e.png)
+![ROC + Confusion Matrix - Dataset F](https://huggingface.co/parlange/vit-gravit-b2/resolve/main/roc_confusion_matrix/ViT_roc_confusion_matrix_f.png)
+![ROC + Confusion Matrix - Dataset G](https://huggingface.co/parlange/vit-gravit-b2/resolve/main/roc_confusion_matrix/ViT_roc_confusion_matrix_g.png)
+![ROC + Confusion Matrix - Dataset H](https://huggingface.co/parlange/vit-gravit-b2/resolve/main/roc_confusion_matrix/ViT_roc_confusion_matrix_h.png)
+![ROC + Confusion Matrix - Dataset I](https://huggingface.co/parlange/vit-gravit-b2/resolve/main/roc_confusion_matrix/ViT_roc_confusion_matrix_i.png)
+![ROC + Confusion Matrix - Dataset J](https://huggingface.co/parlange/vit-gravit-b2/resolve/main/roc_confusion_matrix/ViT_roc_confusion_matrix_j.png)
+![ROC + Confusion Matrix - Dataset K](https://huggingface.co/parlange/vit-gravit-b2/resolve/main/roc_confusion_matrix/ViT_roc_confusion_matrix_k.png)
+![ROC + Confusion Matrix - Dataset L](https://huggingface.co/parlange/vit-gravit-b2/resolve/main/roc_confusion_matrix/ViT_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 | 0.8112 |
+| 📈 Average AUC-ROC | 0.7916 |
+| ⚖️ Average F1-Score | 0.4887 |
+
+
+## 📘 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": "vit_base_patch16_224",
+  "num_classes": 2,
+  "num_features": 768,
+  "global_pool": "token",
+  "crop_pct": 0.875,
+  "interpolation": "bicubic",
+  "mean": [
+    0.485,
+    0.456,
+    0.406
+  ],
+  "std": [
+    0.229,
+    0.224,
+    0.225
+  ],
+  "first_conv": "patch_embed.proj",
+  "classifier": "head",
+  "input_size": [
+    3,
+    224,
+    224
+  ],
+  "pool_size": [
+    7,
+    7
+  ],
+  "pretrained_cfg": {
+    "tag": "gravit_b2",
+    "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": "patch_embed.proj",
+    "classifier": "head"
+  },
+  "model_name": "vit_gravit_b2",
+  "experiment": "b2",
+  "training_strategy": "half",
+  "dataset": "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/vit-gravit-b2",
+  "license": "apache-2.0"
+}

evaluation_results.csv

@@ -0,0 +1,133 @@
+Model,Dataset,Loss,Accuracy,AUCROC,F1
+ViT,a,0.3504258575622333,0.8975165042439485,0.7724705340699815,0.3607843137254902
+ViT,b,0.6139323879378804,0.8443885570575291,0.7591445672191528,0.2709867452135493
+ViT,c,0.2921286642045504,0.9195221628418736,0.7922799263351749,0.41818181818181815
+ViT,d,0.26607740657091966,0.9192077962904747,0.7989585635359117,0.41723356009070295
+ViT,e,0.5051617136084026,0.8562019758507134,0.8035646711571935,0.5841269841269842
+ViT,f,0.29864826543026823,0.9141042521880567,0.7820238007404096,0.1423047177107502
+ViT,g,1.732062186717987,0.5718333333333333,0.6607354444444444,0.3945321706339854
+ViT,h,1.5614525699615478,0.6116666666666667,0.696484388888889,0.4180819180819181
+ViT,i,1.5476410572528838,0.6115,0.7046536666666666,0.41797752808988764
+ViT,j,0.45324009704589846,0.8708333333333333,0.9427406111111111,0.8716249792943515
+ViT,k,0.2688189628124237,0.9105,0.9655912222222223,0.9073978272115882
+ViT,l,0.7289746560802081,0.8074665538575432,0.8200002274918716,0.6616485456741938
+MLP-Mixer,a,0.47016938226997235,0.8553913863564917,0.726208103130755,0.2966360856269113
+MLP-Mixer,b,0.648904620120826,0.8333857277585665,0.7598747697974219,0.26795580110497236
+MLP-Mixer,c,0.3869087039131445,0.8874567745991826,0.733244935543278,0.35144927536231885
+MLP-Mixer,d,0.3633993222574062,0.8997170701037409,0.7682688766114181,0.37816764132553604
+MLP-Mixer,e,0.5312218908486329,0.8474204171240395,0.8186331643078787,0.5825825825825826
+MLP-Mixer,f,0.3886312065722082,0.8861435984819146,0.7510127466766198,0.11658653846153846
+MLP-Mixer,g,1.9292033066749572,0.5541666666666667,0.6170044444444445,0.36566279345506286
+MLP-Mixer,h,1.7903018260002137,0.5828333333333333,0.5599299999999999,0.3812113720642769
+MLP-Mixer,i,1.7778379353284837,0.5893333333333334,0.6098859999999999,0.3849226160758862
+MLP-Mixer,j,0.5891341290473938,0.8386666666666667,0.9153434444444444,0.8365968939905469
+MLP-Mixer,k,0.4377687557935715,0.8738333333333334,0.9274168333333332,0.8674951864169438
+MLP-Mixer,l,0.8833867266855338,0.7767965734228756,0.7550110803792328,0.6132135984605517
+CvT,a,0.710060378377897,0.7095253065073877,0.4610672191528545,0.09941520467836257
+CvT,b,0.6279841153848774,0.7516504243948444,0.5819742173112339,0.11434977578475336
+CvT,c,0.7670251699747135,0.6592266582835586,0.4085635359116022,0.08600337268128162
+CvT,d,0.45408995114606493,0.8179817667400189,0.5189116022099447,0.14977973568281938
+CvT,e,0.6853549914551096,0.756311745334797,0.6546734276848558,0.3148148148148148
+CvT,f,0.5548892200417859,0.7615211834869491,0.5019215495653457,0.03206538824269098
+CvT,g,1.6338303427696228,0.46316666666666667,0.5036535,0.21419858502073677
+CvT,h,1.7075452818870545,0.4141666666666667,0.3043033333333333,0.1998634190758024
+CvT,i,1.5416374638080597,0.49833333333333335,0.4133462222222223,0.22582304526748972
+CvT,j,0.6718657946586609,0.7025,0.7951043333333334,0.6775067750677507
+CvT,k,0.5796729214191437,0.7376666666666667,0.8160571111111111,0.7043576258452291
+CvT,l,0.9414389114699858,0.6422716937232299,0.5856238290999722,0.41148325358851673
+Swin,a,0.38957844183659335,0.9173215969820812,0.7264815837937385,0.30971128608923887
+Swin,b,0.506205921398323,0.8714240804778371,0.7070128913443832,0.2239089184060721
+Swin,c,0.33732365382351015,0.9254951273184533,0.7497605893186002,0.3323943661971831
+Swin,d,0.25108740707354066,0.9465576862621817,0.823268876611418,0.4097222222222222
+Swin,e,0.7929391115167793,0.8419319429198683,0.7817982290168772,0.45038167938931295
+Swin,f,0.21592594718169755,0.9430717992409573,0.7533609214757848,0.13833528722157093
+Swin,g,2.702541620135307,0.5423333333333333,0.5866217222222223,0.2826541274817137
+Swin,h,2.613005870103836,0.571,0.6225122222222222,0.2959518599562363
+Swin,i,2.567286303862929,0.5821666666666667,0.7211619444444445,0.3014767344664252
+Swin,j,0.42502203929424287,0.8855,0.9479796111111113,0.8833021912688975
+Swin,k,0.28976670680940153,0.9253333333333333,0.9796539999999999,0.9206798866855525
+Swin,l,1.03963865723415,0.8099518798582835,0.7976283082751249,0.6403842305383229
+CaiT,a,0.3913202127339292,0.8953159383841559,0.6907965009208104,0.31901840490797545
+CaiT,b,0.5226519536631019,0.8626218170386671,0.7338508287292819,0.2630691399662732
+CaiT,c,0.3735890439830086,0.8984596038981453,0.6786878453038674,0.325678496868476
+CaiT,d,0.2843286003735934,0.9254951273184533,0.76402394106814,0.3969465648854962
+CaiT,e,0.6834587411940687,0.8463227222832053,0.7675773859078181,0.527027027027027
+CaiT,f,0.27040889076227814,0.918054372240725,0.7197493196998433,0.128500823723229
+CaiT,g,2.0468120236396787,0.5761666666666667,0.6781162222222221,0.38351515151515153
+CaiT,h,1.967783824443817,0.5951666666666666,0.5982157777777778,0.3944153577661431
+CaiT,i,1.92046093159914,0.6095,0.7142172222222223,0.40305732484076434
+CaiT,j,0.30098878836631776,0.9125,0.9733297777777777,0.9145368712355526
+CaiT,k,0.1746376877427101,0.9458333333333333,0.9841325555555557,0.9453138145717651
+CaiT,l,0.8100430545029764,0.817143461477447,0.813651736379369,0.6802293323469576
+DeiT,a,0.3698357029348677,0.9119773656082992,0.7087136279926335,0.37777777777777777
+DeiT,b,0.5088012874857205,0.8833700094309965,0.7757348066298342,0.3142329020332717
+DeiT,c,0.3891148048258922,0.9160641307764854,0.7151408839779005,0.3890160183066362
+DeiT,d,0.32573777145838745,0.9352404904118202,0.8077476979742173,0.4521276595744681
+DeiT,e,0.7152948476881215,0.862788144895719,0.814546280178612,0.576271186440678
+DeiT,f,0.2608369113050038,0.9330028657733715,0.7554304661629335,0.1642512077294686
+DeiT,g,2.54885491502285,0.5731666666666667,0.6792770555555556,0.35798445725745803
+DeiT,h,2.485401116847992,0.5905,0.5861576111111111,0.3675675675675676
+DeiT,i,2.451800708413124,0.6006666666666667,0.7191378888888889,0.37343096234309625
+DeiT,j,0.43799715077877044,0.9003333333333333,0.9592409444444444,0.8995295698924731
+DeiT,k,0.3409429641962051,0.9278333333333333,0.9696212777777777,0.9251771211335753
+DeiT,l,1.0167739923843866,0.816297393051663,0.8008547085670262,0.6667945520813351
+DeiT3,a,0.41754333621036777,0.9192077962904747,0.7515147329650091,0.43015521064301554
+DeiT3,b,0.5932955155673173,0.8773970449544168,0.7794677716390424,0.3321917808219178
+DeiT3,c,0.4092358484072567,0.9154353976736875,0.7444696132596684,0.4190064794816415
+DeiT3,d,0.5747989024035925,0.8783401446086136,0.7588406998158379,0.33390705679862304
+DeiT3,e,0.7725568269302764,0.8759604829857299,0.8239688185877545,0.6319218241042345
+DeiT3,f,0.3546846674270619,0.916350398884672,0.7623233064106626,0.152276295133438
+DeiT3,g,2.8653497416973113,0.5903333333333334,0.6676445555555556,0.40828117477130477
+DeiT3,h,2.767767428398132,0.6105,0.5985711666666667,0.4205306223654848
+DeiT3,i,2.8555434824228287,0.5908333333333333,0.6332408888888889,0.40857624668754516
+DeiT3,j,0.407473158121109,0.9088333333333334,0.9701894444444443,0.9098103874690849
+DeiT3,k,0.39766689217090606,0.9093333333333333,0.9684031111111111,0.9102606400527878
+DeiT3,l,1.1462537638319459,0.8163502723282745,0.8007222930468951,0.6808197775939712
+Twins_SVT,a,0.4471702475530552,0.8126375353662371,0.6335423572744014,0.1989247311827957
+Twins_SVT,b,0.4493988096264315,0.8060358377868595,0.6959318600368325,0.1934640522875817
+Twins_SVT,c,0.5063522113864807,0.7780572147123546,0.5922486187845304,0.17330210772833723
+Twins_SVT,d,0.3254203815124425,0.8849418421879912,0.7219650092081031,0.28793774319066145
+Twins_SVT,e,0.5195407480099591,0.7771679473106476,0.7089003254370696,0.42165242165242167
+Twins_SVT,f,0.3887786737239737,0.8404461312059485,0.6636732736434142,0.06702898550724638
+Twins_SVT,g,1.2475184862613677,0.4825,0.532602,0.20689655172413793
+Twins_SVT,h,1.277713261127472,0.4676666666666667,0.36107222222222224,0.2022977022977023
+Twins_SVT,i,1.1817892324924468,0.5243333333333333,0.5369667222222223,0.2210698689956332
+Twins_SVT,j,0.5273123075962066,0.7598333333333334,0.8436975000000001,0.7417099838680767
+Twins_SVT,k,0.46158305954933165,0.8016666666666666,0.8776625,0.7766516516516516
+Twins_SVT,l,0.7025143162813111,0.7046163608481836,0.6522568273932748,0.47706422018348627
+Twins_PCPVT,a,0.45982081515914197,0.7900031436655139,0.6319235727440148,0.17326732673267325
+Twins_PCPVT,b,0.37307003830934016,0.8333857277585665,0.729316758747698,0.208955223880597
+Twins_PCPVT,c,0.5298199271376273,0.7510216912920465,0.5787163904235728,0.15021459227467812
+Twins_PCPVT,d,0.4890483941382786,0.7840301791889343,0.6198968692449357,0.16928657799274485
+Twins_PCPVT,e,0.4528412980515138,0.8068057080131723,0.7623628244910315,0.4430379746835443
+Twins_PCPVT,f,0.41534574994755774,0.8134149175121989,0.6469823751264034,0.05492349941153393
+Twins_PCPVT,g,0.97830464220047,0.5461666666666667,0.6621347777777777,0.33827460510328067
+Twins_PCPVT,h,1.0614082341194153,0.5025,0.47131744444444446,0.31802604523646333
+Twins_PCPVT,i,1.0397925007343292,0.52,0.5257673333333334,0.3258426966292135
+Twins_PCPVT,j,0.36769862127304076,0.8383333333333334,0.9181693333333335,0.834696659850034
+Twins_PCPVT,k,0.42918648648262026,0.8121666666666667,0.8860434444444444,0.8129460580912863
+Twins_PCPVT,l,0.6099785904964774,0.7216434879170853,0.7243182138507473,0.5498546263040875
+PiT,a,0.37776082014932605,0.8651367494498585,0.6834337016574586,0.25906735751295334
+PiT,b,0.44755573657390196,0.8365293932725558,0.7427127071823205,0.22388059701492538
+PiT,c,0.40049510616170875,0.8528764539453002,0.6488581952117863,0.24271844660194175
+PiT,d,0.23405979966281606,0.9214083621502672,0.7678987108655617,0.375
+PiT,e,0.4743333708670739,0.8430296377607025,0.8043820479830468,0.5119453924914675
+PiT,f,0.2892587873664891,0.8926496785686624,0.716096531011705,0.09765625
+PiT,g,1.521324759721756,0.547,0.6473084444444445,0.3386861313868613
+PiT,h,1.4963747837543488,0.5556666666666666,0.5119071111111111,0.3430261212419911
+PiT,i,1.408136343061924,0.592,0.658547,0.3625
+PiT,j,0.6195285122394562,0.7638333333333334,0.8635346666666667,0.7381260395490667
+PiT,k,0.5063400955796242,0.8088333333333333,0.902523,0.7768916553199766
+PiT,l,0.7616236460134194,0.7518375548622495,0.7319390263322477,0.5412063740346075
+Ensemble,a,,0.9179503300848789,0.7188591160220995,0.38588235294117645
+Ensemble,b,,0.8682804149638479,0.760756906077348,0.28130360205831906
+Ensemble,c,,0.9358692235146181,0.6998213627992634,0.44565217391304346
+Ensemble,d,,0.9440427538509902,0.7630147329650093,0.47953216374269003
+Ensemble,e,,0.8770581778265643,0.808151063346704,0.5942028985507246
+Ensemble,f,,0.9397413058632174,0.7397727124771607,0.1740976645435244
+Ensemble,g,,0.5465,0.6648292222222223,0.30569022709874966
+Ensemble,h,,0.5823333333333334,0.5448976666666666,0.3234341252699784
+Ensemble,i,,0.5866666666666667,0.6481456666666666,0.32572050027188687
+Ensemble,j,,0.8898333333333334,0.9515273333333334,0.8894463957183476
+Ensemble,k,,0.93,0.9758612222222223,0.926803764377832
+Ensemble,l,,0.8138649463275343,0.7884954119718932,0.6549019607843137

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b1902204365e87f74315bee25bee7dc955f37795ab2568b7af107177a8848c14
+size 343214864

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aede051e8393d70a50fbbcefcbbd5977296684060119eb3f30b5ada35df96e61
+size 343259038

training_curves/ViT_metrics.csv

@@ -0,0 +1,42 @@
+epoch,train_loss,val_loss,train_accuracy,val_accuracy,train_auc,val_auc,train_f1,val_f1
+1,0.3908570477161175,0.1402057737495355,0.838974445760704,0.9501607717041801,0.9169628266602111,0.9852950468070245,0.8361225134196401,0.9492635024549918
+2,0.15478298319467415,0.10544763998969958,0.9421221864951769,0.9581993569131833,0.9827487656991749,0.9921199463749686,0.9410243145369891,0.9583333333333334
+3,0.12581866161283412,0.13356643364168824,0.9538839059062447,0.9512325830653805,0.9883656948840952,0.9916799637904672,0.9531773533033592,0.9522309711286089
+4,0.11504945014965152,0.10940451963154833,0.9577198623568568,0.9635584137191854,0.9904197414380989,0.9926880178842007,0.957182438801451,0.9637526652452025
+5,0.10279383515016463,0.09677911154518556,0.9634737970327749,0.9646302250803859,0.9920381188999545,0.9940343875683668,0.963011624917883,0.9648936170212766
+6,0.09893412107813275,0.08507681065433662,0.9643481694590174,0.9705251875669882,0.9924737720810275,0.9947190602063898,0.9639166428775335,0.9699945444626296
+7,0.08823910262010125,0.09565741671818245,0.9687764427145032,0.9689174705251876,0.9937359817266271,0.9952118866522149,0.968413844266271,0.9681668496158068
+8,0.08670375390486743,0.0812854671976574,0.968832853838777,0.9721329046087889,0.9941625480929337,0.9956547411857013,0.9684924866698982,0.971677559912854
+9,0.08201244668642627,0.08831745266339404,0.9711739154961359,0.9705251875669882,0.994746777298533,0.9947322711717207,0.9708682515249986,0.9704777241009125
+10,0.07846412310913586,0.07172291975025195,0.9719354656738309,0.9742765273311897,0.9951598765312059,0.9961849029683316,0.9716629168683963,0.9742212674543501
+11,0.07470868332703962,0.07378444612217869,0.97230213798161,0.9710610932475884,0.9955418330173506,0.9962038578316326,0.9720641784251252,0.9711538461538461
+12,0.0723731576435597,0.07985692013689942,0.9735713882777683,0.9742765273311897,0.9958186968550414,0.9954611718241126,0.9733344716696548,0.9739413680781759
+13,0.07056159025474558,0.07845290757452177,0.974417555141874,0.9721329046087889,0.9959879159078954,0.9960998932783757,0.9742161071154447,0.9719525350593312
+14,0.06913263103213078,0.08234789385385452,0.9751226941952953,0.9721329046087889,0.9960689414647441,0.9953422731361338,0.974910394265233,0.9722518676627535
+15,0.06621879533142543,0.07075699754179099,0.9759970666215377,0.9737406216505895,0.9964668949454014,0.9962343004908735,0.9757970478655328,0.9733260751224823
+16,0.06326387345067114,0.075985354050946,0.9776329892254753,0.9758842443729904,0.9966438579183161,0.9961194225314737,0.9774555792466241,0.9756361667569031
+17,0.061144389806639665,0.07884185044903463,0.9781688949060755,0.9753483386923901,0.9969243510721482,0.9969195475186935,0.9780163599182005,0.9749727965179543
+18,0.056854962873910765,0.0746956561539334,0.9796637896993287,0.9737406216505895,0.9972762213071253,0.9953428475259308,0.9795280956301996,0.9737265415549597
+19,0.05849700232970571,0.08019676471542315,0.978056072657528,0.9737406216505895,0.9972603340990283,0.9954663413322856,0.9779165483962532,0.9734129137276181
+20,0.05828364382446428,0.08411261374639928,0.979409939640097,0.9737406216505895,0.9972303146743746,0.9964244235136803,0.9792672536211303,0.9738107963655799
+21,0.05538856709446272,0.0678398820460801,0.9799176397585604,0.9769560557341908,0.9976209554250957,0.9961889236969106,0.9797876568443763,0.9766684753119913
+22,0.05541366204981282,0.07709731199925351,0.9806791899362555,0.9753483386923901,0.9974851432647011,0.9964198283953043,0.9805491665956783,0.9752421959095802
+23,0.05246599984003326,0.07580728677978853,0.9812433011789925,0.9769560557341908,0.9976173881621458,0.9965002429668841,0.9811267205903221,0.9769436997319035
+24,0.051782931914033874,0.1057861854600753,0.9820612624809613,0.9753483386923901,0.9977198395721978,0.9946036078571929,0.9819461791756557,0.9751619870410367
+25,0.053153039925058876,0.07351185616189644,0.9812715067411294,0.9769560557341908,0.997635046272858,0.9965456197608471,0.9811524269088845,0.9769189479334407
+26,0.05474101687107096,0.09731347691207837,0.9814407401139504,0.9721329046087889,0.9975140536874475,0.9947552467636007,0.9813163723096144,0.972310969116081
+27,0.05078018231503067,0.08252194030300214,0.9822869069780561,0.9715969989281886,0.9978867308348217,0.9961188481416767,0.982193489849155,0.9714285714285714
+28,0.03861729065099733,0.07477202903706928,0.9866023579849946,0.9780278670953912,0.9987114511613269,0.9970545291209884,0.9865366627930048,0.9778975741239893
+29,0.03407746769158766,0.08032441100890231,0.988069047216111,0.9801714898177921,0.9990362852981585,0.9971251790660193,0.9880180154661077,0.9799891833423472
+30,0.03468104093456141,0.07991441111664296,0.9876459637840582,0.9785637727759914,0.9989012591448545,0.9970792278822592,0.9875983917549125,0.9784250269687162
+31,0.03356167258980674,0.0800227578190362,0.9885767473345743,0.9785637727759914,0.9989919872750607,0.9972314411784641,0.9885324348047683,0.9783783783783784
+32,0.032895813570785776,0.07656550833841612,0.9883228972753427,0.9785637727759914,0.999079684345535,0.997315876478623,0.988279922998528,0.978401727861771
+33,0.03275389178583698,0.07396855533506326,0.9889152140802167,0.9780278670953912,0.9990814568392575,0.9973359801215179,0.9888696932793338,0.9778737182946573
+34,0.030444608704340015,0.0757858774046806,0.9891972697015852,0.9790996784565916,0.9991775772326827,0.9974324776074138,0.9891602750969348,0.9789303079416531
+35,0.031176629297676114,0.07523631472200443,0.9889716252044903,0.9796355841371919,0.9991437216479166,0.9974491349115268,0.9889200600753776,0.9794816414686826
+36,0.031322837046135255,0.07764383415029746,0.9892536808258588,0.9785637727759914,0.999103423669001,0.9974520068605117,0.9892181000084896,0.978401727861771
+37,0.029420864521665285,0.07613853149571219,0.9898459976307328,0.9790996784565916,0.9992353503449517,0.9974738336727977,0.9898057427649091,0.9789757412398922
+38,0.02852393867046695,0.07781023891504937,0.9897895865064591,0.9785637727759914,0.9993621154682666,0.9974606227074667,0.9897543303520887,0.9784250269687162
+39,0.0301884779696195,0.07618521278502474,0.98942291419868,0.9796355841371919,0.9992033802225386,0.9974399446747747,0.9893782750318652,0.9795258620689655
+40,0.03017074351742256,0.07650932415696969,0.9896485586957748,0.9801714898177921,0.9992473154731328,0.9974301800482257,0.9896089923270761,0.9800539083557952
+41,0.02905876660569153,0.0760913585878645,0.9900434365656907,0.9801714898177921,0.9992085131352397,0.9974468373523386,0.990007642879384,0.9800539083557952

training_metrics.csv

@@ -0,0 +1,42 @@
+epoch,train_loss,val_loss,train_accuracy,val_accuracy,train_auc,val_auc,train_f1,val_f1
+1,0.3908570477161175,0.1402057737495355,0.838974445760704,0.9501607717041801,0.9169628266602111,0.9852950468070245,0.8361225134196401,0.9492635024549918
+2,0.15478298319467415,0.10544763998969958,0.9421221864951769,0.9581993569131833,0.9827487656991749,0.9921199463749686,0.9410243145369891,0.9583333333333334
+3,0.12581866161283412,0.13356643364168824,0.9538839059062447,0.9512325830653805,0.9883656948840952,0.9916799637904672,0.9531773533033592,0.9522309711286089
+4,0.11504945014965152,0.10940451963154833,0.9577198623568568,0.9635584137191854,0.9904197414380989,0.9926880178842007,0.957182438801451,0.9637526652452025
+5,0.10279383515016463,0.09677911154518556,0.9634737970327749,0.9646302250803859,0.9920381188999545,0.9940343875683668,0.963011624917883,0.9648936170212766
+6,0.09893412107813275,0.08507681065433662,0.9643481694590174,0.9705251875669882,0.9924737720810275,0.9947190602063898,0.9639166428775335,0.9699945444626296
+7,0.08823910262010125,0.09565741671818245,0.9687764427145032,0.9689174705251876,0.9937359817266271,0.9952118866522149,0.968413844266271,0.9681668496158068
+8,0.08670375390486743,0.0812854671976574,0.968832853838777,0.9721329046087889,0.9941625480929337,0.9956547411857013,0.9684924866698982,0.971677559912854
+9,0.08201244668642627,0.08831745266339404,0.9711739154961359,0.9705251875669882,0.994746777298533,0.9947322711717207,0.9708682515249986,0.9704777241009125
+10,0.07846412310913586,0.07172291975025195,0.9719354656738309,0.9742765273311897,0.9951598765312059,0.9961849029683316,0.9716629168683963,0.9742212674543501
+11,0.07470868332703962,0.07378444612217869,0.97230213798161,0.9710610932475884,0.9955418330173506,0.9962038578316326,0.9720641784251252,0.9711538461538461
+12,0.0723731576435597,0.07985692013689942,0.9735713882777683,0.9742765273311897,0.9958186968550414,0.9954611718241126,0.9733344716696548,0.9739413680781759
+13,0.07056159025474558,0.07845290757452177,0.974417555141874,0.9721329046087889,0.9959879159078954,0.9960998932783757,0.9742161071154447,0.9719525350593312
+14,0.06913263103213078,0.08234789385385452,0.9751226941952953,0.9721329046087889,0.9960689414647441,0.9953422731361338,0.974910394265233,0.9722518676627535
+15,0.06621879533142543,0.07075699754179099,0.9759970666215377,0.9737406216505895,0.9964668949454014,0.9962343004908735,0.9757970478655328,0.9733260751224823
+16,0.06326387345067114,0.075985354050946,0.9776329892254753,0.9758842443729904,0.9966438579183161,0.9961194225314737,0.9774555792466241,0.9756361667569031
+17,0.061144389806639665,0.07884185044903463,0.9781688949060755,0.9753483386923901,0.9969243510721482,0.9969195475186935,0.9780163599182005,0.9749727965179543
+18,0.056854962873910765,0.0746956561539334,0.9796637896993287,0.9737406216505895,0.9972762213071253,0.9953428475259308,0.9795280956301996,0.9737265415549597
+19,0.05849700232970571,0.08019676471542315,0.978056072657528,0.9737406216505895,0.9972603340990283,0.9954663413322856,0.9779165483962532,0.9734129137276181
+20,0.05828364382446428,0.08411261374639928,0.979409939640097,0.9737406216505895,0.9972303146743746,0.9964244235136803,0.9792672536211303,0.9738107963655799
+21,0.05538856709446272,0.0678398820460801,0.9799176397585604,0.9769560557341908,0.9976209554250957,0.9961889236969106,0.9797876568443763,0.9766684753119913
+22,0.05541366204981282,0.07709731199925351,0.9806791899362555,0.9753483386923901,0.9974851432647011,0.9964198283953043,0.9805491665956783,0.9752421959095802
+23,0.05246599984003326,0.07580728677978853,0.9812433011789925,0.9769560557341908,0.9976173881621458,0.9965002429668841,0.9811267205903221,0.9769436997319035
+24,0.051782931914033874,0.1057861854600753,0.9820612624809613,0.9753483386923901,0.9977198395721978,0.9946036078571929,0.9819461791756557,0.9751619870410367
+25,0.053153039925058876,0.07351185616189644,0.9812715067411294,0.9769560557341908,0.997635046272858,0.9965456197608471,0.9811524269088845,0.9769189479334407
+26,0.05474101687107096,0.09731347691207837,0.9814407401139504,0.9721329046087889,0.9975140536874475,0.9947552467636007,0.9813163723096144,0.972310969116081
+27,0.05078018231503067,0.08252194030300214,0.9822869069780561,0.9715969989281886,0.9978867308348217,0.9961188481416767,0.982193489849155,0.9714285714285714
+28,0.03861729065099733,0.07477202903706928,0.9866023579849946,0.9780278670953912,0.9987114511613269,0.9970545291209884,0.9865366627930048,0.9778975741239893
+29,0.03407746769158766,0.08032441100890231,0.988069047216111,0.9801714898177921,0.9990362852981585,0.9971251790660193,0.9880180154661077,0.9799891833423472
+30,0.03468104093456141,0.07991441111664296,0.9876459637840582,0.9785637727759914,0.9989012591448545,0.9970792278822592,0.9875983917549125,0.9784250269687162
+31,0.03356167258980674,0.0800227578190362,0.9885767473345743,0.9785637727759914,0.9989919872750607,0.9972314411784641,0.9885324348047683,0.9783783783783784
+32,0.032895813570785776,0.07656550833841612,0.9883228972753427,0.9785637727759914,0.999079684345535,0.997315876478623,0.988279922998528,0.978401727861771
+33,0.03275389178583698,0.07396855533506326,0.9889152140802167,0.9780278670953912,0.9990814568392575,0.9973359801215179,0.9888696932793338,0.9778737182946573
+34,0.030444608704340015,0.0757858774046806,0.9891972697015852,0.9790996784565916,0.9991775772326827,0.9974324776074138,0.9891602750969348,0.9789303079416531
+35,0.031176629297676114,0.07523631472200443,0.9889716252044903,0.9796355841371919,0.9991437216479166,0.9974491349115268,0.9889200600753776,0.9794816414686826
+36,0.031322837046135255,0.07764383415029746,0.9892536808258588,0.9785637727759914,0.999103423669001,0.9974520068605117,0.9892181000084896,0.978401727861771
+37,0.029420864521665285,0.07613853149571219,0.9898459976307328,0.9790996784565916,0.9992353503449517,0.9974738336727977,0.9898057427649091,0.9789757412398922
+38,0.02852393867046695,0.07781023891504937,0.9897895865064591,0.9785637727759914,0.9993621154682666,0.9974606227074667,0.9897543303520887,0.9784250269687162
+39,0.0301884779696195,0.07618521278502474,0.98942291419868,0.9796355841371919,0.9992033802225386,0.9974399446747747,0.9893782750318652,0.9795258620689655
+40,0.03017074351742256,0.07650932415696969,0.9896485586957748,0.9801714898177921,0.9992473154731328,0.9974301800482257,0.9896089923270761,0.9800539083557952
+41,0.02905876660569153,0.0760913585878645,0.9900434365656907,0.9801714898177921,0.9992085131352397,0.9974468373523386,0.990007642879384,0.9800539083557952

training_notebook_b2.ipynb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:86376eaa294416a058788d39e0690103d71edc7584329b0c3cbca4358a5ad8f6
+size 21881414