ModernBERT-base-subjectivity-sentiment-english

This model was trained from scratch on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.9933
• Macro F1: 0.6882
• Macro P: 0.6882
• Macro R: 0.6885
• Subj F1: 0.6949
• Subj P: 0.7069
• Subj R: 0.6833
• Accuracy: 0.6883

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: 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
• num_epochs: 6

Training results

Training Loss	Epoch	Step	Validation Loss	Macro F1	Macro P	Macro R	Subj F1	Subj P	Subj R	Accuracy
No log	1.0	52	0.5361	0.6911	0.7179	0.6953	0.7473	0.6667	0.85	0.7013
No log	2.0	104	0.6044	0.7208	0.7214	0.7216	0.7226	0.7467	0.7	0.7208
No log	3.0	156	0.7217	0.6861	0.6865	0.6868	0.6895	0.7093	0.6708	0.6861
No log	4.0	208	0.7965	0.6835	0.6835	0.6835	0.6958	0.6958	0.6958	0.6840
No log	5.0	260	0.8510	0.7011	0.7047	0.7011	0.7276	0.6958	0.7625	0.7035
No log	6.0	312	0.9933	0.6882	0.6882	0.6885	0.6949	0.7069	0.6833	0.6883

Framework versions

• Transformers 4.49.0
• Pytorch 2.5.1+cu121
• Datasets 3.3.1
• Tokenizers 0.21.0