early_fusion_sentiment_False_hate_speech_True_extra_layer_True

This model is a fine-tuned version of on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.6409
• Accuracy Offensive: 0.7402
• F1 Offensive: 0.7175
• Accuracy Targeted: 0.7277
• F1 Targeted: 0.6995
• Accuracy Stance: 0.7205
• F1 Stance: 0.6646

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: 8
• eval_batch_size: 8
• 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: 1000

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy Offensive	F1 Offensive	Accuracy Targeted	F1 Targeted	Accuracy Stance	F1 Stance
0.776	1.0	1324	0.7680	0.6545	0.5178	0.6545	0.5178	0.7009	0.5777
0.753	2.0	2648	0.7524	0.6545	0.5178	0.6545	0.5178	0.7009	0.5777
0.7498	3.0	3972	0.7391	0.6548	0.5186	0.6545	0.5178	0.7009	0.5777
0.7369	4.0	5296	0.7256	0.6616	0.5360	0.6545	0.5178	0.7009	0.5777
0.7242	5.0	6620	0.7089	0.7043	0.6606	0.6839	0.6003	0.7009	0.5777
0.714	6.0	7944	0.6994	0.6971	0.6284	0.6884	0.6128	0.7009	0.5777
0.7016	7.0	9268	0.6880	0.7035	0.6521	0.6971	0.6430	0.7009	0.5777
0.6994	8.0	10592	0.6832	0.7043	0.6467	0.6968	0.6403	0.7009	0.5777
0.6867	9.0	11916	0.6807	0.7054	0.6407	0.6986	0.6354	0.7039	0.5893
0.6758	10.0	13240	0.6665	0.7323	0.7080	0.7085	0.6827	0.7111	0.6422
0.6695	11.0	14564	0.6599	0.7311	0.7062	0.7153	0.6857	0.7122	0.6417
0.6708	12.0	15888	0.6572	0.7251	0.6880	0.7175	0.6842	0.7160	0.6436
0.6578	13.0	17212	0.6515	0.7394	0.7190	0.7183	0.6953	0.7107	0.6565
0.6572	14.0	18536	0.6488	0.7398	0.7173	0.7236	0.6968	0.7126	0.6519
0.652	15.0	19860	0.6452	0.7421	0.7230	0.7221	0.6994	0.7168	0.6656
0.6401	16.0	21184	0.6499	0.7315	0.6958	0.7213	0.6852	0.7168	0.6508
0.6654	17.0	22508	0.6409	0.7402	0.7175	0.7277	0.6995	0.7205	0.6646
0.6386	18.0	23832	0.6458	0.7360	0.7029	0.7247	0.6887	0.7187	0.6540
0.6396	19.0	25156	0.6416	0.7326	0.6945	0.7247	0.6858	0.7209	0.6455

Framework versions

• Transformers 4.50.2
• Pytorch 2.6.0+cu124
• Datasets 3.0.1
• Tokenizers 0.21.1