metadata
library_name: transformers
license: apache-2.0
base_model: google/rembert
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: populism_classifier_395
results: []
populism_classifier_395
This model is a fine-tuned version of google/rembert on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.7593
- Accuracy: 0.7203
- 1-f1: 0.1781
- 1-recall: 0.5417
- 1-precision: 0.1066
- Balanced Acc: 0.6363
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: 1e-05
- train_batch_size: 16
- eval_batch_size: 32
- seed: 42
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.06
- num_epochs: 20
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | 1-f1 | 1-recall | 1-precision | Balanced Acc |
|---|---|---|---|---|---|---|---|---|
| 0.3534 | 1.0 | 108 | 0.6570 | 0.9417 | 0.0 | 0.0 | 0.0 | 0.4988 |
| 0.6423 | 2.0 | 216 | 0.6427 | 0.9417 | 0.0 | 0.0 | 0.0 | 0.4988 |
| 0.6418 | 3.0 | 324 | 0.6813 | 0.7413 | 0.0672 | 0.1667 | 0.0421 | 0.4710 |
| 0.9179 | 4.0 | 432 | 0.9171 | 0.9441 | 0.0 | 0.0 | 0.0 | 0.5 |
| 0.6552 | 5.0 | 540 | 0.6415 | 0.9394 | 0.0 | 0.0 | 0.0 | 0.4975 |
| 0.2303 | 6.0 | 648 | 0.9350 | 0.0583 | 0.1062 | 1.0 | 0.0561 | 0.5012 |
| 0.275 | 7.0 | 756 | 0.9327 | 0.0606 | 0.1064 | 1.0 | 0.0562 | 0.5025 |
| 0.0706 | 8.0 | 864 | 0.7735 | 0.7319 | 0.1353 | 0.375 | 0.0826 | 0.5640 |
| 0.0629 | 9.0 | 972 | 0.9589 | 0.5361 | 0.0744 | 0.3333 | 0.0419 | 0.4407 |
| 0.0181 | 10.0 | 1080 | 0.7593 | 0.7203 | 0.1781 | 0.5417 | 0.1066 | 0.6363 |
Framework versions
- Transformers 4.46.3
- Pytorch 2.4.1+cu121
- Datasets 3.1.0
- Tokenizers 0.20.3