README.md

metadata

library_name: transformers
license: mit
base_model: AnonymousCS/populism_xlmr_base
tags:
  - generated_from_trainer
metrics:
  - accuracy
model-index:
  - name: populism_classifier_bsample_192
    results: []

populism_classifier_bsample_192

This model is a fine-tuned version of AnonymousCS/populism_xlmr_base on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.6731
• Accuracy: 0.9713
• 1-f1: 0.0
• 1-recall: 0.0
• 1-precision: 0.0
• Balanced Acc: 0.5

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-06
• train_batch_size: 16
• eval_batch_size: 16
• 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: 15
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	1-f1	1-recall	1-precision	Balanced Acc
0.7181	1.0	17	0.7579	0.0287	0.0558	1.0	0.0287	0.5
0.6644	2.0	34	0.7431	0.0287	0.0558	1.0	0.0287	0.5
0.7257	3.0	51	0.7321	0.0287	0.0558	1.0	0.0287	0.5
0.7576	4.0	68	0.7196	0.0287	0.0558	1.0	0.0287	0.5
0.7521	5.0	85	0.7113	0.0287	0.0558	1.0	0.0287	0.5
0.7068	6.0	102	0.7053	0.0287	0.0558	1.0	0.0287	0.5
0.735	7.0	119	0.6979	0.0287	0.0558	1.0	0.0287	0.5
0.6718	8.0	136	0.6920	0.9713	0.0	0.0	0.0	0.5
0.6794	9.0	153	0.6874	0.9713	0.0	0.0	0.0	0.5
0.7529	10.0	170	0.6814	0.9713	0.0	0.0	0.0	0.5
0.714	11.0	187	0.6773	0.9713	0.0	0.0	0.0	0.5
0.6746	12.0	204	0.6759	0.9713	0.0	0.0	0.0	0.5
0.7143	13.0	221	0.6741	0.9713	0.0	0.0	0.0	0.5
0.7303	14.0	238	0.6731	0.9713	0.0	0.0	0.0	0.5
0.7097	15.0	255	0.6731	0.9713	0.0	0.0	0.0	0.5

Framework versions

• Transformers 4.46.3
• Pytorch 2.4.1+cu121
• Datasets 3.1.0
• Tokenizers 0.20.3