early_fusion_sentiment_True_hate_speech_False_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: 0.5189
• Accuracy Offensive: 0.8051
• F1 Offensive: 0.7880
• Accuracy Targeted: 0.8142
• F1 Targeted: 0.7901
• Accuracy Stance: 0.7772
• F1 Stance: 0.7317

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
0.7892	1.0	1324	0.7635	0.6545	0.5178	0.6545	0.5178	0.7009	0.5777
0.7494	2.0	2648	0.7461	0.6545	0.5178	0.6545	0.5178	0.7009	0.5777
0.7391	3.0	3972	0.7235	0.6545	0.5178	0.6545	0.5178	0.7009	0.5777
0.7189	4.0	5296	0.6960	0.6715	0.5596	0.6677	0.5498	0.7009	0.5777
0.6938	5.0	6620	0.6651	0.7202	0.6650	0.7285	0.6897	0.7009	0.5777
0.6744	6.0	7944	0.6508	0.7062	0.6327	0.7247	0.6734	0.7137	0.6131
0.6576	7.0	9268	0.6229	0.7338	0.6897	0.7568	0.7291	0.7319	0.6745
0.638	8.0	10592	0.6022	0.7481	0.7086	0.7655	0.7390	0.7424	0.6915
0.6208	9.0	11916	0.5916	0.7360	0.6866	0.7715	0.7428	0.7477	0.6957
0.6135	10.0	13240	0.5783	0.7855	0.7648	0.7825	0.7638	0.7511	0.7147
0.5957	11.0	14564	0.5700	0.7870	0.7658	0.7866	0.7665	0.7572	0.7174
0.5988	12.0	15888	0.5549	0.7870	0.7647	0.7927	0.7716	0.7553	0.7137
0.5775	13.0	17212	0.5454	0.7995	0.7820	0.8002	0.7812	0.7591	0.7221
0.5792	14.0	18536	0.5359	0.8078	0.7921	0.8089	0.7887	0.7711	0.7311
0.5803	15.0	19860	0.5277	0.8172	0.8062	0.8108	0.7914	0.7727	0.7348
0.553	16.0	21184	0.5262	0.8089	0.7967	0.8006	0.7806	0.7666	0.7282
0.576	17.0	22508	0.5271	0.8142	0.8017	0.8051	0.7848	0.7700	0.7307
0.5599	18.0	23832	0.5104	0.8161	0.8019	0.8236	0.8008	0.7817	0.7376
0.5544	19.0	25156	0.5319	0.7976	0.7772	0.8036	0.7781	0.7745	0.7259
0.5427	20.0	26480	0.5257	0.8070	0.7898	0.8112	0.7859	0.7795	0.7320

Framework versions

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