Zum Inhalt springen
ModelÜberprüftExtern
Herunterladen

RADAR

This model is a fine-tuned version of MahmoodAnaam/radar-encoder-freeze on the None dataset. It achieves the following results on the evaluation set: Loss: 0.1610 Roc-auc: 0.99 Brier: 0.967 C@1: 0.964 F1: 0.964 F05u:...

Quellehuggingface.co/MahmoodAnaam/RADAR/tree/b49d53ca600118f0d3486024418b0eb96d1adef2
ArtCheckpointBasismodellMahmoodAnaam/radar-encoder-freezeVersionRevision b49d53cVerleger@MahmoodAnaamCBewertung

Modellquelle

Art
Checkpoint
Dateigröße
1,49 GB
Basismodell
MahmoodAnaam/radar-encoder-freeze
Version
vRevision b49d53c
Aktualisiert
3. Okt. 2026
Verleger
@MahmoodAnaam
Downloads
15
Quelle
Hugging Face

Quellenbeschreibung

RADAR

This model is a fine-tuned version of MahmoodAnaam/radar-encoder-freeze on the None dataset. It achieves the following results on the evaluation set:

  • Loss: 0.1610
  • Roc-auc: 0.99
  • Brier: 0.967
  • C@1: 0.964
  • F1: 0.964
  • F05u: 0.974
  • Mean: 0.972

Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

More information needed

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

  • learning_rate: 2e-05
  • train_batch_size: 32
  • eval_batch_size: 64
  • seed: 42
  • optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
  • lr_scheduler_type: cosine
  • lr_scheduler_warmup_steps: 0.03
  • num_epochs: 10

Training results

Training LossEpochStepValidation LossRoc-aucBrierC@1F1F05uMean
0.21030.41535000.18140.9820.9280.9040.9020.9520.934
0.21020.830610000.18660.9770.930.9090.910.9450.934
0.08211.245815000.20490.9890.940.9210.930.9050.937
0.04761.661120000.08680.9930.9690.9610.9620.9790.973
0.05512.076425000.09320.9940.9720.9660.9680.9710.974
0.03062.491730000.11810.9950.9690.9630.9660.9590.97
0.02952.907035000.09430.9940.9730.9690.9710.9750.976
0.03453.322340000.13630.9890.9620.9550.9570.9720.967
0.05553.737545000.13260.9910.9640.9580.960.9760.97
0.04934.152850000.16000.9910.960.9540.9570.9630.965
0.01134.568155000.13210.9920.9660.960.9620.970.97
0.00744.983460000.15290.990.9620.9560.9580.9710.968
0.05155.398765000.15940.990.9630.9580.960.9730.969
0.00595.814070000.15330.9910.9640.9590.9610.9730.97
0.01746.229275000.14890.9910.9630.9580.960.9760.97
0.02306.644580000.14650.9910.9660.9610.9630.9730.971
0.01287.059885000.14610.9910.9670.9620.9640.9740.972
0.04087.475190000.14770.9910.9660.9610.9630.9740.971
0.00577.890495000.14830.9910.9670.9620.9640.9740.972
0.02628.3056100000.15020.9910.9680.9650.9660.9750.973
0.01988.7209105000.13820.9920.9720.970.9710.980.977
0.01119.1362110000.13510.9920.9730.9710.9730.9810.978
0.00169.5515115000.13500.9920.9730.9710.9730.9820.978
0.00299.9668120000.13520.9920.9730.9710.9730.9820.978

Framework versions

  • Transformers 5.0.0
  • Pytorch 2.10.0+cu128
  • Datasets 4.0.0
  • Tokenizers 0.22.2

Quellen

1 Quelle
Hugging FacePrimärVersion b49d53ca600118f0d3486024418b0eb96d1adef2
huggingface.co/MahmoodAnaam/RADAR/tree/b49d53ca600118f0d3486024418b0eb96d1adef2

Verifiziert 3. Okt.

Modellartefakte

2 Artefakte

last-checkpoint/model.safetensors

safetensors · 1,49 GB · SHA-256 4a520fc86126…46c7 · Hugging Face

Herunterladen

model.safetensors

safetensors · 1,49 GB · SHA-256 a39bb09a3530…6234 · Hugging Face

Herunterladen

Quellenauszüge

3 Auszüge
Readme3. Okt.huggingface.co/MahmoodAnaam/RADAR

--- library_name: transformers base_model: MahmoodAnaam/radar-encoder-freeze tags: - generated_from_trainer metrics: - f1 model-index: - name: RADAR results: [] datasets: - MahmoodAnaam/radar-pan26-raid --- <!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # RADAR This model is a fine-tuned version of [MahmoodAnaam/radar-encoder-freeze](https://huggingface.co/MahmoodAnaam/radar-encoder-freeze) on the None dataset. It achieves the following results on the evaluation set: - Loss: 0.1610 - Roc-auc: 0.99 - Brier: 0.967 - C@1: 0.964 - F1: 0.964 - F05u: 0.974 - Mean: 0.972 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 2e-05 - train_batch_size: 32 - eval_batch_size: 64 - seed: 42 - optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments - lr_scheduler_type: cosine - lr_scheduler_warmup_steps: 0.03 - num_epochs: 10 ### Training results | Training Loss | Epoch | Step | Validation Loss | Roc-auc | Brier | C@1 | F1 | F05u | Mean | |:-------------:|:------:|:-----:|:---------------:|:-------:|:-----:|:-----:|:-----:|:-----:|:-----:| | 0.2103 | 0.4153 | 500 | 0.1814 | 0.982 | 0.928 | 0.904 | 0.902 | 0.952 | 0.934 | | 0.2102 | 0.8306 | 1000 | 0.1866 | 0.977 | 0.93 | 0.909 | 0.91 | 0.945 | 0.934 | | 0.0821 | 1.2458 | 1500 | 0.2049 | 0.989 | 0.94 | 0.921 | 0.93 | 0.905 | 0.937 | | 0.0476 | 1.6611 | 2000 | 0.0868 | 0.993 | 0.969 | 0.961 | 0.962 | 0.979 | 0.973 | | 0.0551 | 2.0764 | 2500 | 0.0932 | 0.994 | 0.972 | 0.966 | 0.968 | 0.971 | 0.974 | | 0.0306 | 2.4917 | 3000 | 0.1181 | 0.995 | 0.969 | 0.963 | 0.966 | 0.959 | 0.97 | | 0.0295 | 2.9070 | 3500 | 0.0943 | 0.994 | 0.973 | 0.969 | 0.971 | 0.975 | 0.976 | | 0.0345 | 3.3223 | 4000 | 0.1363 | 0.989 | 0.962 | 0.955 | 0.957 | 0.972 | 0.967 | | 0.0555 | 3.7375 | 4500 | 0.1326 | 0.991 | 0.964 | 0.958 | 0.96 | 0.976 | 0.97 | | 0.0493 | 4.1528 | 5000 | 0.1600 | 0.991 | 0.96 | 0.954 | 0.957 | 0.963 | 0.965 | | 0.0113 | 4.5681 | 5500 | 0.1321 | 0.992 | 0.966 | 0.96...

Note3. Okt.huggingface.co/MahmoodAnaam/RADAR

Source context: 15 downloads · 0 likes · Pipeline text-classification · Library transformers · Repo MahmoodAnaam/RADAR

Note11. Julihuggingface.co/MahmoodAnaam/RADAR

Source context: 0 downloads · 0 likes · Pipeline text-classification · Library transformers · Repo MahmoodAnaam/RADAR