mongrz/sentiment_class6

results

This model is a fine-tuned version of allegro/herbert-base-cased on the polemo2-official dataset. It achieves the following results on the evaluation set:

• Loss: 0.3520
• Accuracy: 0.8951

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: 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: 3

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
0.3688	1.0	411	0.2971	0.8805
0.2472	2.0	822	0.2747	0.9061
0.1286	3.0	1233	0.3520	0.8951

Framework versions

• Transformers 4.46.3
• Pytorch 2.5.1+cu121
• Datasets 3.1.0
• Tokenizers 0.20.3