ogBERT_ekman_multilabels_finetune

This model is a fine-tuned version of google-bert/bert-base-uncased on the MuscariMedia/Politics2017_batch_1_Iteration2Review dataset. It achieves the following results on the evaluation set:

• Loss: 0.2343
• Accuracy: 0.9176
• F1: 0.6124
• Precision: 0.7263
• Recall: 0.5293

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: 3
• eval_batch_size: 3
• seed: 42
• optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: linear
• num_epochs: 2

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	F1	Precision	Recall
No log	1.0	489	0.2612	0.9019	0.5909	0.6063	0.5763
0.2835	2.0	978	0.2343	0.9176	0.6124	0.7263	0.5293

Framework versions

• Transformers 4.48.0.dev0
• Pytorch 2.5.1+cu124
• Datasets 3.1.0
• Tokenizers 0.21.0