Hugging Face's logo

YagiASAFAS
/
MyPoliBERT-HITL-ver02

Text Classification
Transformers
Safetensors
bert
Generated from Trainer
text-embeddings-inference
Model card Files
xet
 Community
MyPoliBERT-HITL-ver02 / README.md
YagiASAFAS's picture
YagiASAFAS
MyPoliBERT-HITL-ver02 Push
d5c4a53 verified
preview code
|
raw
history blame contribute delete
8.21 kB
metadata 
library_name: transformers
license: apache-2.0
base_model: YagiASAFAS/MyPoliBERT-HITL
tags:
  - generated_from_trainer
model-index:
  - name: MyPoliBERT-HITL-ver02
    results: []

MyPoliBERT-HITL-ver02

This model is a fine-tuned version of YagiASAFAS/MyPoliBERT-HITL on an unknown dataset. It achieves the following results on the evaluation set:

  • Loss: 0.2656
  • Democracy F1: 0.9337
  • Democracy Accuracy: 0.9344
  • Economy F1: 0.9183
  • Economy Accuracy: 0.9190
  • Race F1: 0.9491
  • Race Accuracy: 0.9499
  • Leadership F1: 0.8503
  • Leadership Accuracy: 0.8490
  • Development F1: 0.8721
  • Development Accuracy: 0.8739
  • Corruption F1: 0.9487
  • Corruption Accuracy: 0.9499
  • Stability F1: 1.0
  • Stability Accuracy: 1.0
  • Safety F1: 0.9052
  • Safety Accuracy: 0.9047
  • Administration F1: 0.8831
  • Administration Accuracy: 0.8854
  • Education F1: 0.9592
  • Education Accuracy: 0.9599
  • Religion F1: 0.9436
  • Religion Accuracy: 0.9439
  • Environment F1: 0.9736
  • Environment Accuracy: 0.9740
  • Overall F1: 0.9281
  • Overall Accuracy: 0.9287

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: 5e-05
  • train_batch_size: 16
  • eval_batch_size: 16
  • 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: linear
  • lr_scheduler_warmup_steps: 500
  • num_epochs: 10
  • mixed_precision_training: Native AMP

Training results

Training Loss Epoch Step Validation Loss Democracy F1 Democracy Accuracy Economy F1 Economy Accuracy Race F1 Race Accuracy Leadership F1 Leadership Accuracy Development F1 Development Accuracy Corruption F1 Corruption Accuracy Stability F1 Stability Accuracy Safety F1 Safety Accuracy Administration F1 Administration Accuracy Education F1 Education Accuracy Religion F1 Religion Accuracy Environment F1 Environment Accuracy Overall F1 Overall Accuracy
0.2312 1.0 1346 0.2204 0.9072 0.9261 0.9032 0.9110 0.9386 0.9393 0.7710 0.7987 0.8389 0.8564 0.9334 0.9396 1.0 1.0 0.8753 0.8860 0.8627 0.8845 0.9531 0.9554 0.9346 0.9361 0.9718 0.9721 0.9075 0.9171
0.1721 2.0 2692 0.1994 0.9287 0.9357 0.9116 0.9134 0.9456 0.9461 0.8359 0.8377 0.8622 0.8715 0.9412 0.9467 1.0 1.0 0.8985 0.9012 0.8829 0.8889 0.9575 0.9595 0.9394 0.9415 0.9705 0.9725 0.9228 0.9262
0.1109 3.0 4038 0.2045 0.9306 0.9315 0.9120 0.9108 0.9487 0.9499 0.8409 0.8416 0.8664 0.8683 0.9477 0.9493 1.0 1.0 0.9006 0.9006 0.8814 0.8813 0.9557 0.9554 0.9464 0.9476 0.9727 0.9731 0.9253 0.9258
0.0844 4.0 5384 0.2123 0.9345 0.9361 0.9147 0.9160 0.9491 0.9506 0.8378 0.8375 0.8716 0.8759 0.9475 0.9499 1.0 1.0 0.9028 0.9043 0.8820 0.8845 0.9567 0.9575 0.9420 0.9428 0.9726 0.9729 0.9259 0.9273
0.0605 5.0 6730 0.2309 0.9330 0.9342 0.9188 0.9212 0.9455 0.9447 0.8457 0.8447 0.8709 0.875 0.9480 0.9499 1.0 1.0 0.8997 0.8990 0.8787 0.8783 0.9587 0.9591 0.9406 0.9400 0.9725 0.9725 0.9260 0.9266
0.0413 6.0 8076 0.2465 0.9337 0.9337 0.9166 0.9168 0.9468 0.9482 0.8389 0.8436 0.8703 0.8700 0.9477 0.9502 1.0 1.0 0.9018 0.9014 0.8810 0.8900 0.9603 0.9610 0.9423 0.9426 0.9719 0.9723 0.9259 0.9275
0.0286 7.0 9422 0.2531 0.9331 0.9318 0.9177 0.9188 0.9485 0.9491 0.8458 0.8444 0.8740 0.8759 0.9463 0.9471 1.0 1.0 0.9022 0.9003 0.8850 0.8858 0.9564 0.9565 0.9434 0.9437 0.9737 0.9740 0.9272 0.9273
0.0209 8.0 10768 0.2618 0.9335 0.9322 0.9178 0.9168 0.9495 0.9499 0.8452 0.8432 0.8733 0.8744 0.9478 0.9497 1.0 1.0 0.9049 0.9042 0.8809 0.8806 0.9581 0.9586 0.9439 0.9439 0.9724 0.9727 0.9273 0.9272
0.0157 9.0 12114 0.2646 0.9342 0.9346 0.9174 0.9179 0.9497 0.9506 0.8528 0.8522 0.8728 0.8744 0.9465 0.9474 1.0 1.0 0.9048 0.9042 0.8819 0.8832 0.9594 0.9601 0.9448 0.9454 0.9739 0.9742 0.9282 0.9287
0.0147 10.0 13460 0.2656 0.9337 0.9344 0.9183 0.9190 0.9491 0.9499 0.8503 0.8490 0.8721 0.8739 0.9487 0.9499 1.0 1.0 0.9052 0.9047 0.8831 0.8854 0.9592 0.9599 0.9436 0.9439 0.9736 0.9740 0.9281 0.9287

Framework versions

  • Transformers 4.57.0
  • Pytorch 2.8.0+cu126
  • Datasets 4.0.0
  • Tokenizers 0.22.1