early_fusion_sentiment_False_hate_speech_False_extra_layer_False

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

• Loss: 0.5016
• Accuracy Offensive: 0.8270
• F1 Offensive: 0.8177
• Accuracy Targeted: 0.8210
• F1 Targeted: 0.8015
• Accuracy Stance: 0.7791
• F1 Stance: 0.7391

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
0.7681	1.0	1324	0.7393	0.6552	0.5195	0.6545	0.5178	0.7009	0.5777
0.7022	2.0	2648	0.6893	0.6968	0.6191	0.6760	0.5700	0.7009	0.5777
0.6713	3.0	3972	0.6465	0.7421	0.7122	0.7409	0.7131	0.7069	0.5953
0.6392	4.0	5296	0.6254	0.7243	0.6661	0.7372	0.6944	0.7300	0.6556
0.6254	5.0	6620	0.5891	0.7576	0.7240	0.7776	0.7541	0.7492	0.7011
0.6116	6.0	7944	0.5935	0.7323	0.6780	0.7662	0.7308	0.7477	0.6888
0.5938	7.0	9268	0.5659	0.7908	0.7741	0.7874	0.7696	0.7526	0.7155
0.5947	8.0	10592	0.5619	0.7636	0.7292	0.7934	0.7666	0.7640	0.7152
0.5773	9.0	11916	0.5388	0.7689	0.7353	0.8063	0.7817	0.7677	0.7226
0.5692	10.0	13240	0.5339	0.7927	0.7710	0.8055	0.7844	0.7704	0.7275
0.5587	11.0	14564	0.5324	0.8229	0.8144	0.8002	0.7845	0.7625	0.7296
0.5612	12.0	15888	0.5182	0.7957	0.7745	0.8116	0.7890	0.7727	0.7288
0.5513	13.0	17212	0.5166	0.8285	0.8208	0.8108	0.7938	0.7772	0.7413
0.5517	14.0	18536	0.5130	0.8146	0.8015	0.8146	0.7946	0.7772	0.7353
0.5555	15.0	19860	0.5109	0.8267	0.8182	0.8153	0.7967	0.7776	0.7385
0.5304	16.0	21184	0.5160	0.8048	0.7872	0.8142	0.7909	0.7791	0.7336
0.5554	17.0	22508	0.4974	0.8350	0.8265	0.8187	0.7995	0.7825	0.7429
0.5323	18.0	23832	0.5201	0.8040	0.7851	0.8066	0.7820	0.7779	0.7294
0.5408	19.0	25156	0.5029	0.8131	0.7980	0.8146	0.7911	0.7844	0.7370

Framework versions

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