Upload ViT model from experiment a2

.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_a2.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:
+- C21
+metrics:
+- accuracy
+- auc
+- f1
+model-index:
+- name: ViT-a2
+  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: 0.8205
+      name: Average Accuracy
+    - type: auc
+      value: 0.8511
+      name: Average AUC-ROC
+    - type: f1
+      value: 0.5319
+      name: Average F1-Score
+---
+
+# 🌌 vit-gravit-a2
+
+🔭 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**: A2 - C21-half
+- **🌌 Dataset**: C21
+- **🪐 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-a2',
+    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:** 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-a2/resolve/main/training_curves/ViT_combined_metrics.png)
+
+
+## 🏁 Final Epoch Training Metrics
+
+| Metric | Training | Validation |
+|:---------:|:-----------:|:-------------:|
+| 📉 Loss | 0.0159 | 0.0354 |
+| 🎯 Accuracy | 0.9939 | 0.9870 |
+| 📊 AUC-ROC | 0.9998 | 0.9986 |
+| ⚖️ F1 Score | 0.9939 | 0.9870 |
+
+
+## ☑️ 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-a2/resolve/main/roc_confusion_matrix/ViT_roc_confusion_matrix_a.png)
+![ROC + Confusion Matrix - Dataset B](https://huggingface.co/parlange/vit-gravit-a2/resolve/main/roc_confusion_matrix/ViT_roc_confusion_matrix_b.png)
+![ROC + Confusion Matrix - Dataset C](https://huggingface.co/parlange/vit-gravit-a2/resolve/main/roc_confusion_matrix/ViT_roc_confusion_matrix_c.png)
+![ROC + Confusion Matrix - Dataset D](https://huggingface.co/parlange/vit-gravit-a2/resolve/main/roc_confusion_matrix/ViT_roc_confusion_matrix_d.png)
+![ROC + Confusion Matrix - Dataset E](https://huggingface.co/parlange/vit-gravit-a2/resolve/main/roc_confusion_matrix/ViT_roc_confusion_matrix_e.png)
+![ROC + Confusion Matrix - Dataset F](https://huggingface.co/parlange/vit-gravit-a2/resolve/main/roc_confusion_matrix/ViT_roc_confusion_matrix_f.png)
+![ROC + Confusion Matrix - Dataset G](https://huggingface.co/parlange/vit-gravit-a2/resolve/main/roc_confusion_matrix/ViT_roc_confusion_matrix_g.png)
+![ROC + Confusion Matrix - Dataset H](https://huggingface.co/parlange/vit-gravit-a2/resolve/main/roc_confusion_matrix/ViT_roc_confusion_matrix_h.png)
+![ROC + Confusion Matrix - Dataset I](https://huggingface.co/parlange/vit-gravit-a2/resolve/main/roc_confusion_matrix/ViT_roc_confusion_matrix_i.png)
+![ROC + Confusion Matrix - Dataset J](https://huggingface.co/parlange/vit-gravit-a2/resolve/main/roc_confusion_matrix/ViT_roc_confusion_matrix_j.png)
+![ROC + Confusion Matrix - Dataset K](https://huggingface.co/parlange/vit-gravit-a2/resolve/main/roc_confusion_matrix/ViT_roc_confusion_matrix_k.png)
+![ROC + Confusion Matrix - Dataset L](https://huggingface.co/parlange/vit-gravit-a2/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 | 0.8205 |
+| 📈 Average AUC-ROC | 0.8511 |
+| ⚖️ Average F1-Score | 0.5319 |
+
+
+## 📘 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_a2",
+    "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_a2",
+  "experiment": "a2",
+  "training_strategy": "half",
+  "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": "half",
+    "stochastic_depth_probability": "0.1"
+  },
+  "hf_hub_id": "parlange/vit-gravit-a2",
+  "license": "apache-2.0"
+}

evaluation_results.csv

@@ -0,0 +1,133 @@
+Model,Dataset,Loss,Accuracy,AUCROC,F1
+ViT,a,0.3987342550652614,0.8997170701037409,0.917220073664825,0.46921797004991683
+ViT,b,0.37321944226074877,0.9182646966362779,0.9273655616942909,0.5202952029520295
+ViT,c,0.821146962441052,0.7922037095253065,0.866000920810313,0.2990455991516437
+ViT,d,0.223954888615208,0.9440427538509902,0.9518121546961327,0.6130434782608696
+ViT,e,1.1019757730900652,0.7782656421514819,0.85117687126315,0.5826446280991735
+ViT,f,0.43205039906387277,0.8869181318255751,0.9119053612426381,0.1618828932261768
+ViT,g,0.1527516215024516,0.9611666666666666,0.9983996666666667,0.962461736748832
+ViT,h,0.39022785605769605,0.8943333333333333,0.9959461111111112,0.9040556900726392
+ViT,i,0.07361652948241681,0.9748333333333333,0.9992922222222222,0.9753469387755102
+ViT,j,6.027309565424919,0.5033333333333333,0.49077061111111114,0.13872832369942195
+ViT,k,5.948174474835396,0.517,0.5691439444444444,0.14209591474245115
+ViT,l,2.1620761937842525,0.7761620221035376,0.7346207805818022,0.6140942656577628
+MLP-Mixer,a,1.0354112619425808,0.7239861678717384,0.9444742173112339,0.2779605263157895
+MLP-Mixer,b,0.882929647823281,0.7834014460861365,0.9520524861878453,0.3291139240506329
+MLP-Mixer,c,1.6300886590238712,0.6205595724614901,0.9170009208103129,0.21877022653721684
+MLP-Mixer,d,0.055560619117974934,0.9792518076076705,0.9959686924493554,0.8366336633663366
+MLP-Mixer,e,1.1025473987755214,0.70801317233809,0.9327480511617346,0.5596026490066225
+MLP-Mixer,f,0.9539809344458585,0.763147703508636,0.9512486274645963,0.09952885747938751
+MLP-Mixer,g,0.4660766951590776,0.8855,0.9941798888888888,0.8969551522423879
+MLP-Mixer,h,0.8621955468207598,0.7991666666666667,0.9892695555555555,0.8322894919972165
+MLP-Mixer,i,0.027433219969272612,0.9893333333333333,0.9997324444444444,0.9894109861019192
+MLP-Mixer,j,5.562473163604737,0.4046666666666667,0.2374668888888889,0.05552617662612375
+MLP-Mixer,k,5.123829672321677,0.5085,0.47802688888888895,0.06647673314339982
+MLP-Mixer,l,2.271000012816855,0.6846808735656497,0.6265659288601144,0.5226162837242815
+CvT,a,0.7062503800231756,0.6988368437598239,0.8373821362799264,0.2336
+CvT,b,0.8609082461227902,0.6444514303678088,0.8087320441988951,0.20520028109627547
+CvT,c,0.8150388154171053,0.6516818610499843,0.8144069981583795,0.20857142857142857
+CvT,d,0.046723183949472995,0.9833385727758567,0.9917753222836095,0.8463768115942029
+CvT,e,1.055778265130245,0.5916575192096597,0.7447665178233557,0.4397590361445783
+CvT,f,0.6479923738885578,0.7303074897374332,0.8562897926766284,0.07737148913619502
+CvT,g,0.47873973870277403,0.8053333333333333,0.948009388888889,0.8337129840546698
+CvT,h,0.45442124152183533,0.8091666666666667,0.9536063888888889,0.8364519354377946
+CvT,i,0.0470859190672636,0.985,0.999245111111111,0.9848637739656912
+CvT,j,3.978341913700104,0.31966666666666665,0.09071466666666667,0.006812652068126521
+CvT,k,3.5466880963295697,0.49933333333333335,0.5394476666666667,0.009234828496042216
+CvT,l,1.575411782030338,0.6541695309608164,0.5834616840778439,0.4856873230575653
+Swin,a,0.7181912302146427,0.6636277900031436,0.8782845303867403,0.22351233671988388
+Swin,b,0.47780195057523284,0.8000628733102798,0.9174990791896869,0.326271186440678
+Swin,c,1.1387689553203542,0.5369380697893744,0.8261528545119704,0.1729365524985963
+Swin,d,0.0309918804128743,0.9871109713926438,0.9966482504604052,0.8825214899713467
+Swin,e,0.5848406514011806,0.7464324917672887,0.8943237720426852,0.5714285714285714
+Swin,f,0.6053860638443279,0.7410735032143134,0.9040542417311522,0.0843604491920022
+Swin,g,0.24402792798448353,0.8985,0.999229,0.9078529278256923
+Swin,h,0.5944505902426317,0.759,0.9974725555555555,0.8058017727639001
+Swin,i,0.007144115434028208,0.9976666666666667,0.9999902222222222,0.9976720984369803
+Swin,j,3.9496381425857545,0.419,0.11956033333333334,0.06591639871382636
+Swin,k,3.7127543271519245,0.5181666666666667,0.4697328333333333,0.07841887153331208
+Swin,l,1.5895203038408208,0.6710908994764951,0.5955901653865907,0.5130734304055112
+CaiT,a,0.11189156073487824,0.967934611757309,0.9444355432780847,0.7243243243243244
+CaiT,b,0.14077727915177515,0.9566174159069475,0.9445782688766113,0.6600985221674877
+CaiT,c,0.1453998264081071,0.9556743162527507,0.9236316758747698,0.6552567237163814
+CaiT,d,0.0895651844381368,0.9757937755422823,0.9521049723756906,0.7768115942028986
+CaiT,e,0.5067908598680527,0.8507135016465422,0.8893589646560206,0.6633663366336634
+CaiT,f,0.09735689565035,0.968553946247386,0.9382155086735556,0.39762611275964393
+CaiT,g,0.04386970533267595,0.9845,0.9998996666666666,0.984726556084743
+CaiT,h,0.04632043000892736,0.984,0.999908,0.9842416283650689
+CaiT,i,0.016718765972414985,0.9946666666666667,0.9999668888888888,0.9946914399469144
+CaiT,j,4.091754978463054,0.5111666666666667,0.502447,0.09726069559864574
+CaiT,k,4.064604013383389,0.5213333333333333,0.4420845,0.09912170639899624
+CaiT,l,1.3512259357719865,0.8281423510126381,0.7136882113330858,0.669379450661241
+DeiT,a,0.2868140126428901,0.9104055328513047,0.9108996316758747,0.5060658578856152
+DeiT,b,0.21093111757876476,0.9380697893744105,0.9419907918968692,0.5971370143149284
+DeiT,c,0.4344255732631803,0.8610499842816725,0.8816003683241251,0.3978201634877384
+DeiT,d,0.10285686065156817,0.977051241747878,0.9568195211786372,0.8
+DeiT,e,0.6603749339457532,0.8210757409440176,0.8680541890562324,0.6417582417582418
+DeiT,f,0.23529704651809683,0.9209975989466347,0.9196866062244752,0.2225609756097561
+DeiT,g,0.07966256512608379,0.9715,0.9994743333333334,0.9722086786933203
+DeiT,h,0.1981518727680668,0.9306666666666666,0.9987041666666666,0.9349796811503595
+DeiT,i,0.022365192129276693,0.9921666666666666,0.9998618888888888,0.9922043456626306
+DeiT,j,4.922376271247864,0.4945,0.5104821111111111,0.07839562443026436
+DeiT,k,4.865078900694847,0.5151666666666667,0.5016916666666666,0.08146510893590149
+DeiT,l,1.6993422816543697,0.7937708212151657,0.7000134906492581,0.6261503067484663
+DeiT3,a,0.3992725303153578,0.9091480666457089,0.9363876611418048,0.5126475548060708
+DeiT3,b,0.3124380833470795,0.9305249921408362,0.952292817679558,0.579047619047619
+DeiT3,c,0.4766911079170793,0.8915435397673688,0.9285046040515654,0.46841294298921415
+DeiT3,d,0.11976070332006253,0.9723357434768941,0.9784143646408839,0.7755102040816326
+DeiT3,e,0.9584465352031193,0.7969264544456641,0.8915991826231742,0.621676891615542
+DeiT3,f,0.33781881941231834,0.921617225621563,0.9456139627538378,0.23100303951367782
+DeiT3,g,0.1398290316515031,0.9671666666666666,0.9996258333333332,0.9681590431550025
+DeiT3,h,0.22691049999523785,0.9465,0.9994123333333333,0.9491364284582475
+DeiT3,i,0.03767789686251308,0.9893333333333333,0.9998997777777778,0.9894284770399736
+DeiT3,j,6.353702080726624,0.486,0.2588749444444445,0.06545454545454546
+DeiT3,k,6.251550879061222,0.5081666666666667,0.38331972222222227,0.06820334701610357
+DeiT3,l,2.203556089656545,0.7932949077256624,0.6245051702293716,0.6248200403109704
+Twins_SVT,a,0.42451784632109274,0.8126375353662371,0.8918922651933701,0.3377777777777778
+Twins_SVT,b,0.3914457758111573,0.8142093681232316,0.8958011049723758,0.3396648044692737
+Twins_SVT,c,0.44262768309920586,0.8047783715812638,0.8853812154696132,0.3286486486486486
+Twins_SVT,d,0.07794447650992994,0.9820811065702609,0.9897808471454881,0.8421052631578947
+Twins_SVT,e,0.5991019170841715,0.712403951701427,0.818761825474911,0.5371024734982333
+Twins_SVT,f,0.3470329082674194,0.8442413445898846,0.9101541579685174,0.13131749460043196
+Twins_SVT,g,0.2309408655166626,0.9008333333333334,0.9874507777777777,0.9088681268188084
+Twins_SVT,h,0.2580758459568024,0.8958333333333334,0.9890552222222222,0.9047110840067083
+Twins_SVT,i,0.06473293882608414,0.9898333333333333,0.9991408888888889,0.9898248540450375
+Twins_SVT,j,2.941682351350784,0.41483333333333333,0.16385111111111111,0.02823138665928591
+Twins_SVT,k,2.775474429190159,0.5038333333333334,0.41604216666666666,0.03312763884378045
+Twins_SVT,l,1.1202095961319853,0.7359737718788008,0.5944821592359222,0.5594282184770141
+Twins_PCPVT,a,0.4347801183106501,0.7944042753850991,0.8711482504604051,0.2952586206896552
+Twins_PCPVT,b,0.339161620420017,0.8575919522162841,0.9065580110497238,0.3768913342503439
+Twins_PCPVT,c,0.467156688444122,0.7742848160955674,0.8578029465930019,0.2762096774193548
+Twins_PCPVT,d,0.23605295665344328,0.9245520276642565,0.9460681399631676,0.5330739299610895
+Twins_PCPVT,e,0.4829401325446714,0.7694840834248079,0.8557481268447741,0.5661157024793388
+Twins_PCPVT,f,0.3720619066015847,0.8374254511656727,0.8931208308558979,0.11546565528866413
+Twins_PCPVT,g,0.2366939251422882,0.9141666666666667,0.9769166666666668,0.9182928764080597
+Twins_PCPVT,h,0.3045526731014252,0.87,0.9672449999999999,0.8812423873325214
+Twins_PCPVT,i,0.18202911043167114,0.9496666666666667,0.9892225555555555,0.9504105090311987
+Twins_PCPVT,j,1.547880547761917,0.4866666666666667,0.43741700000000006,0.1760299625468165
+Twins_PCPVT,k,1.4932157402038575,0.5221666666666667,0.47360899999999995,0.18666666666666668
+Twins_PCPVT,l,0.7149772635186269,0.7421606472423458,0.6893006569431472,0.579510175922732
+PiT,a,0.44727815774318297,0.8010059729644766,0.9252882136279927,0.3329820864067439
+PiT,b,0.3666396583074745,0.8374724929267526,0.9387182320441989,0.3793517406962785
+PiT,c,0.587441599189167,0.7419050613014775,0.9032854511970534,0.27792436235708
+PiT,d,0.033625746908820454,0.9855391386356491,0.9966703499079189,0.8729281767955801
+PiT,e,0.631099864955006,0.7387486278814489,0.8873495799591311,0.5703971119133574
+PiT,f,0.3817344946660815,0.8324684377662458,0.9379145273921177,0.127470754336426
+PiT,g,0.19083814918994904,0.9163333333333333,0.9971276666666666,0.9226025285229725
+PiT,h,0.30789998161792753,0.8656666666666667,0.9943662222222222,0.8812960235640648
+PiT,i,0.01428527906537056,0.9948333333333333,0.9999181111111111,0.9948462177888612
+PiT,j,5.1374336256980895,0.427,0.18367044444444444,0.031549295774647886
+PiT,k,4.960880736589432,0.5055,0.6351591666666667,0.03637544657356284
+PiT,l,1.8333862431563666,0.7295225001321982,0.6306325748279862,0.5562592174893728
+Ensemble,a,,0.9239232945614586,0.9640395948434622,0.56
+Ensemble,b,,0.926752593524049,0.9696408839779006,0.5693160813308688
+Ensemble,c,,0.8563344860106885,0.9442707182320442,0.40261437908496733
+Ensemble,d,,0.9874253379440427,0.9976040515653776,0.8850574712643678
+Ensemble,e,,0.8254665203073546,0.9312873685007189,0.6595289079229122
+Ensemble,f,,0.9207652389435366,0.9667325628328263,0.23140495867768596
+Ensemble,g,,0.9656666666666667,0.999739111111111,0.9668063164679342
+Ensemble,h,,0.9283333333333333,0.9995118888888889,0.9331259720062208
+Ensemble,i,,0.9978333333333333,0.9999951111111111,0.9978380176284717
+Ensemble,j,,0.47883333333333333,0.20988066666666666,0.04809741248097413
+Ensemble,k,,0.511,0.48139255555555555,0.05109961190168176
+Ensemble,l,,0.79144413304426,0.6240045673759117,0.6211335254562921

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e50d176c3ff9296a3ecd94bc719db684360b19a03d9d21e19110d04ab1a319ad
+size 343214864

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:410c6c52b3124c455a228d8864b71f5ee82f888f67ad52ddd4c748362a397c14
+size 343259038

training_curves/ViT_metrics.csv

@@ -0,0 +1,56 @@
+epoch,train_loss,val_loss,train_accuracy,val_accuracy,train_auc,val_auc,train_f1,val_f1
+1,0.2571897825062275,0.16868997523188592,0.8909625,0.946,0.9619713853125,0.982836,0.8921635286991136,0.9458917835671342
+2,0.10249610567688942,0.08976531195640564,0.959125,0.964,0.9935048543749999,0.995018,0.9591464481147398,0.9636363636363636
+3,0.08254435644596815,0.12431702297925949,0.9676,0.95,0.9957464584375,0.994376,0.9676105265788618,0.9514563106796117
+4,0.07725174049884082,0.07002760744094849,0.9704625,0.971,0.9962299949999999,0.997188,0.9704842678524588,0.9710867397806581
+5,0.06949511439502239,0.08071183396875858,0.97285,0.967,0.9969555387499999,0.9960100000000001,0.9728581425572328,0.9669669669669669
+6,0.06195828217118979,0.06686169847846031,0.97555,0.97,0.9975565184374999,0.997854,0.9755432744004602,0.9703557312252964
+7,0.05968754206672311,0.05395021122694015,0.9770875,0.976,0.9977075931249999,0.99835,0.9771009531900009,0.976
+8,0.05582731359452009,0.09855114138126374,0.9784875,0.959,0.9980155462499999,0.997438,0.9784974449317191,0.9603864734299516
+9,0.05249064586088061,0.12695906853675842,0.9802875,0.964,0.9982350368749999,0.997152,0.9802961204473043,0.965183752417795
+10,0.05202052024230361,0.0683318508900702,0.9794375,0.977,0.998266334375,0.9976320000000001,0.979444437502343,0.9767911200807265
+11,0.04922362358346581,0.06005106982588768,0.980925,0.98,0.998434173125,0.9980680000000001,0.9809359618219524,0.9799599198396793
+12,0.04954018256664276,0.0496393184363842,0.9809875,0.983,0.998417308125,0.998878,0.9809915392978992,0.9831849653808111
+13,0.04701879207864404,0.06633866775035858,0.9822625,0.976,0.9985571665625002,0.998196,0.9822675980655562,0.9763779527559056
+14,0.04468993845023215,0.05411972495913506,0.9832375,0.977,0.9986921206249999,0.997852,0.9832490163012929,0.9771598808341608
+15,0.04467305731698871,0.052378923520445826,0.9830875,0.983,0.9987308056249999,0.998612,0.9830978525653038,0.9829488465396189
+16,0.04416244664862752,0.061337709560990335,0.9831375,0.972,0.9987252821875,0.997954,0.9831423465753596,0.9719438877755511
+17,0.04224556235820055,0.05293858873844147,0.983925,0.976,0.9988342181250001,0.99875,0.9839310258653005,0.9761904761904762
+18,0.04184411993473768,0.04035755966603756,0.9844125,0.983,0.9988489365625,0.9992139999999999,0.9844142533964929,0.983016983016983
+19,0.039481629332900045,0.0380017871260643,0.985075,0.984,0.9989661159375,0.999196,0.9850779844031193,0.9838709677419355
+20,0.039050778500176964,0.05595802050828934,0.9852,0.978,0.9989906596875,0.998618,0.9852040688810577,0.9777327935222672
+21,0.038018626151047646,0.03781456935405731,0.985725,0.984,0.999055713125,0.999188,0.985720359116713,0.9839034205231388
+22,0.03786576530188322,0.07107540512271225,0.9856875,0.975,0.9990700378125001,0.997752,0.9856898254033719,0.9754178957718781
+23,0.03550247654877603,0.04472261417657137,0.986525,0.981,0.99917039375,0.9989760000000001,0.9865276944611078,0.9811320754716981
+24,0.03683767461553216,0.08104223525524139,0.9863375,0.971,0.999118265,0.99753,0.9863400612385178,0.971028971028971
+25,0.03603814362697303,0.054750813365913927,0.9862375,0.977,0.9991466175,0.9986539999999999,0.9862428309030251,0.9767911200807265
+26,0.033973789243213835,0.034988305181264875,0.9874875,0.987,0.9992454203125,0.99852,0.9874957840430715,0.9870388833499502
+27,0.0336566893408075,0.037800674140453336,0.9871375,0.982,0.9992725715625002,0.99936,0.9871331574406362,0.9822134387351779
+28,0.03516939798332751,0.05907388961315155,0.9867375,0.975,0.9991722771875,0.998462,0.9867413118728365,0.9750747756729811
+29,0.03391784453056753,0.06921996867563575,0.9873375,0.976,0.9992547612500001,0.997552,0.987342404818133,0.9761431411530815
+30,0.032122378143295646,0.07228873765468598,0.98765,0.974,0.9993077275,0.9974299999999999,0.9876567887661786,0.9743589743589743
+31,0.032853978098742666,0.03264096333086491,0.9875625,0.986,0.9992887515625,0.999444,0.9875607896085712,0.9860279441117764
+32,0.03169495304683223,0.04754947853460908,0.9878,0.984,0.9993381837499999,0.9988980000000001,0.9878042685060229,0.984
+33,0.0325634615611285,0.07620548486709594,0.9877625,0.976,0.9992953393749999,0.99867,0.9877614291250485,0.9764705882352941
+34,0.03284200843628496,0.053336817268282176,0.9876625,0.983,0.9992856396875,0.9982260000000001,0.9876728240098918,0.9831516352824579
+35,0.030358187890425326,0.026614241600029346,0.9887625,0.991,0.9993883709375,0.998726,0.9887626404669941,0.990990990990991
+36,0.03145117684975266,0.03880496996641159,0.9881625,0.984,0.9993390918749999,0.9991,0.988167380955356,0.9839034205231388
+37,0.03075786703492049,0.043761813044548036,0.988625,0.983,0.9993586171875,0.999152,0.988628695673906,0.9831516352824579
+38,0.029451999595947565,0.03821960013359785,0.988775,0.989,0.9994363434374999,0.9993380000000001,0.9887758418118641,0.989010989010989
+39,0.02943100941479206,0.046573635160923006,0.9888,0.984,0.999430351875,0.999074,0.9888,0.9838709677419355
+40,0.028862864456977694,0.033900146007537844,0.9894875,0.984,0.9994478037499999,0.999448,0.9894907841299594,0.984
+41,0.027756637436151504,0.0390649971216917,0.9895875,0.985,0.9995044921875001,0.99941,0.9895894519777542,0.9850448654037887
+42,0.021649938562326134,0.031183642968535423,0.992075,0.988,0.9996990165625,0.999484,0.9920763866323393,0.9879518072289156
+43,0.018418092272244394,0.0391297372598201,0.9933375,0.988,0.99976330375,0.998498,0.9933389154804604,0.988
+44,0.018358768828725443,0.034538188990205526,0.992775,0.987,0.9997714343749999,0.9986020000000001,0.9927746387319366,0.986986986986987
+45,0.017306528286472896,0.03354046154068783,0.993575,0.989,0.9998045315625,0.9986320000000001,0.9935756424357565,0.988988988988989
+46,0.017489736422430725,0.032686231285333635,0.993675,0.989,0.9997868325,0.999558,0.9936757905261843,0.9889669007021064
+47,0.01589218409322202,0.03669157077372074,0.9937625,0.988,0.9998243946875001,0.9986219999999999,0.9937642927658298,0.988
+48,0.016967264903057368,0.03582666659355164,0.9938625,0.987,0.999815451875,0.998578,0.9938615024941553,0.987012987012987
+49,0.015907147341710514,0.034647640466686426,0.99395,0.988,0.9998361521875001,0.9985879999999999,0.9939521167591343,0.9879759519038076
+50,0.015000127985933795,0.033812878728145736,0.9942125,0.988,0.9998465996874999,0.9986179999999999,0.9942119935494356,0.9879759519038076
+51,0.01568684279639274,0.03433457591384649,0.994325,0.988,0.999837119375,0.998626,0.9943262765877677,0.9879759519038076
+52,0.015734441786119713,0.03452299890294671,0.99385,0.988,0.9998309865625001,0.998634,0.993851537115721,0.9879759519038076
+53,0.015493583727488294,0.03554822874069214,0.99405,0.988,0.9998134003125001,0.99861,0.9940517844646606,0.9879759519038076
+54,0.01566599233309971,0.03530654576420784,0.9943,0.988,0.9998142143750001,0.998606,0.9943009973254681,0.9879759519038076
+55,0.015907046043593435,0.035406885087490084,0.9939125,0.987,0.999830001875,0.998598,0.9939130326096467,0.986986986986987

training_metrics.csv

@@ -0,0 +1,56 @@
+epoch,train_loss,val_loss,train_accuracy,val_accuracy,train_auc,val_auc,train_f1,val_f1
+1,0.2571897825062275,0.16868997523188592,0.8909625,0.946,0.9619713853125,0.982836,0.8921635286991136,0.9458917835671342
+2,0.10249610567688942,0.08976531195640564,0.959125,0.964,0.9935048543749999,0.995018,0.9591464481147398,0.9636363636363636
+3,0.08254435644596815,0.12431702297925949,0.9676,0.95,0.9957464584375,0.994376,0.9676105265788618,0.9514563106796117
+4,0.07725174049884082,0.07002760744094849,0.9704625,0.971,0.9962299949999999,0.997188,0.9704842678524588,0.9710867397806581
+5,0.06949511439502239,0.08071183396875858,0.97285,0.967,0.9969555387499999,0.9960100000000001,0.9728581425572328,0.9669669669669669
+6,0.06195828217118979,0.06686169847846031,0.97555,0.97,0.9975565184374999,0.997854,0.9755432744004602,0.9703557312252964
+7,0.05968754206672311,0.05395021122694015,0.9770875,0.976,0.9977075931249999,0.99835,0.9771009531900009,0.976
+8,0.05582731359452009,0.09855114138126374,0.9784875,0.959,0.9980155462499999,0.997438,0.9784974449317191,0.9603864734299516
+9,0.05249064586088061,0.12695906853675842,0.9802875,0.964,0.9982350368749999,0.997152,0.9802961204473043,0.965183752417795
+10,0.05202052024230361,0.0683318508900702,0.9794375,0.977,0.998266334375,0.9976320000000001,0.979444437502343,0.9767911200807265
+11,0.04922362358346581,0.06005106982588768,0.980925,0.98,0.998434173125,0.9980680000000001,0.9809359618219524,0.9799599198396793
+12,0.04954018256664276,0.0496393184363842,0.9809875,0.983,0.998417308125,0.998878,0.9809915392978992,0.9831849653808111
+13,0.04701879207864404,0.06633866775035858,0.9822625,0.976,0.9985571665625002,0.998196,0.9822675980655562,0.9763779527559056
+14,0.04468993845023215,0.05411972495913506,0.9832375,0.977,0.9986921206249999,0.997852,0.9832490163012929,0.9771598808341608
+15,0.04467305731698871,0.052378923520445826,0.9830875,0.983,0.9987308056249999,0.998612,0.9830978525653038,0.9829488465396189
+16,0.04416244664862752,0.061337709560990335,0.9831375,0.972,0.9987252821875,0.997954,0.9831423465753596,0.9719438877755511
+17,0.04224556235820055,0.05293858873844147,0.983925,0.976,0.9988342181250001,0.99875,0.9839310258653005,0.9761904761904762
+18,0.04184411993473768,0.04035755966603756,0.9844125,0.983,0.9988489365625,0.9992139999999999,0.9844142533964929,0.983016983016983
+19,0.039481629332900045,0.0380017871260643,0.985075,0.984,0.9989661159375,0.999196,0.9850779844031193,0.9838709677419355
+20,0.039050778500176964,0.05595802050828934,0.9852,0.978,0.9989906596875,0.998618,0.9852040688810577,0.9777327935222672
+21,0.038018626151047646,0.03781456935405731,0.985725,0.984,0.999055713125,0.999188,0.985720359116713,0.9839034205231388
+22,0.03786576530188322,0.07107540512271225,0.9856875,0.975,0.9990700378125001,0.997752,0.9856898254033719,0.9754178957718781
+23,0.03550247654877603,0.04472261417657137,0.986525,0.981,0.99917039375,0.9989760000000001,0.9865276944611078,0.9811320754716981
+24,0.03683767461553216,0.08104223525524139,0.9863375,0.971,0.999118265,0.99753,0.9863400612385178,0.971028971028971
+25,0.03603814362697303,0.054750813365913927,0.9862375,0.977,0.9991466175,0.9986539999999999,0.9862428309030251,0.9767911200807265
+26,0.033973789243213835,0.034988305181264875,0.9874875,0.987,0.9992454203125,0.99852,0.9874957840430715,0.9870388833499502
+27,0.0336566893408075,0.037800674140453336,0.9871375,0.982,0.9992725715625002,0.99936,0.9871331574406362,0.9822134387351779
+28,0.03516939798332751,0.05907388961315155,0.9867375,0.975,0.9991722771875,0.998462,0.9867413118728365,0.9750747756729811
+29,0.03391784453056753,0.06921996867563575,0.9873375,0.976,0.9992547612500001,0.997552,0.987342404818133,0.9761431411530815
+30,0.032122378143295646,0.07228873765468598,0.98765,0.974,0.9993077275,0.9974299999999999,0.9876567887661786,0.9743589743589743
+31,0.032853978098742666,0.03264096333086491,0.9875625,0.986,0.9992887515625,0.999444,0.9875607896085712,0.9860279441117764
+32,0.03169495304683223,0.04754947853460908,0.9878,0.984,0.9993381837499999,0.9988980000000001,0.9878042685060229,0.984
+33,0.0325634615611285,0.07620548486709594,0.9877625,0.976,0.9992953393749999,0.99867,0.9877614291250485,0.9764705882352941
+34,0.03284200843628496,0.053336817268282176,0.9876625,0.983,0.9992856396875,0.9982260000000001,0.9876728240098918,0.9831516352824579
+35,0.030358187890425326,0.026614241600029346,0.9887625,0.991,0.9993883709375,0.998726,0.9887626404669941,0.990990990990991
+36,0.03145117684975266,0.03880496996641159,0.9881625,0.984,0.9993390918749999,0.9991,0.988167380955356,0.9839034205231388
+37,0.03075786703492049,0.043761813044548036,0.988625,0.983,0.9993586171875,0.999152,0.988628695673906,0.9831516352824579
+38,0.029451999595947565,0.03821960013359785,0.988775,0.989,0.9994363434374999,0.9993380000000001,0.9887758418118641,0.989010989010989
+39,0.02943100941479206,0.046573635160923006,0.9888,0.984,0.999430351875,0.999074,0.9888,0.9838709677419355
+40,0.028862864456977694,0.033900146007537844,0.9894875,0.984,0.9994478037499999,0.999448,0.9894907841299594,0.984
+41,0.027756637436151504,0.0390649971216917,0.9895875,0.985,0.9995044921875001,0.99941,0.9895894519777542,0.9850448654037887
+42,0.021649938562326134,0.031183642968535423,0.992075,0.988,0.9996990165625,0.999484,0.9920763866323393,0.9879518072289156
+43,0.018418092272244394,0.0391297372598201,0.9933375,0.988,0.99976330375,0.998498,0.9933389154804604,0.988
+44,0.018358768828725443,0.034538188990205526,0.992775,0.987,0.9997714343749999,0.9986020000000001,0.9927746387319366,0.986986986986987
+45,0.017306528286472896,0.03354046154068783,0.993575,0.989,0.9998045315625,0.9986320000000001,0.9935756424357565,0.988988988988989
+46,0.017489736422430725,0.032686231285333635,0.993675,0.989,0.9997868325,0.999558,0.9936757905261843,0.9889669007021064
+47,0.01589218409322202,0.03669157077372074,0.9937625,0.988,0.9998243946875001,0.9986219999999999,0.9937642927658298,0.988
+48,0.016967264903057368,0.03582666659355164,0.9938625,0.987,0.999815451875,0.998578,0.9938615024941553,0.987012987012987
+49,0.015907147341710514,0.034647640466686426,0.99395,0.988,0.9998361521875001,0.9985879999999999,0.9939521167591343,0.9879759519038076
+50,0.015000127985933795,0.033812878728145736,0.9942125,0.988,0.9998465996874999,0.9986179999999999,0.9942119935494356,0.9879759519038076
+51,0.01568684279639274,0.03433457591384649,0.994325,0.988,0.999837119375,0.998626,0.9943262765877677,0.9879759519038076
+52,0.015734441786119713,0.03452299890294671,0.99385,0.988,0.9998309865625001,0.998634,0.993851537115721,0.9879759519038076
+53,0.015493583727488294,0.03554822874069214,0.99405,0.988,0.9998134003125001,0.99861,0.9940517844646606,0.9879759519038076
+54,0.01566599233309971,0.03530654576420784,0.9943,0.988,0.9998142143750001,0.998606,0.9943009973254681,0.9879759519038076
+55,0.015907046043593435,0.035406885087490084,0.9939125,0.987,0.999830001875,0.998598,0.9939130326096467,0.986986986986987

training_notebook_a2.ipynb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dc5d440a78b5d761bd1d79a4e23ab72bfc8a4744ca67cb8ad7dc260bdf23e550
+size 21151683