self_iterative_v2_offensive_iteration_1

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

• Loss: 2.1624
• Accuracy Offensive: 0.8284
• F1 Macro Offensive: 0.8167
• F1 Weighted Offensive: 0.8298
• F1 Macro Total: 0.8167
• F1 Weighted Total: 0.8298

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: 6e-06
• train_batch_size: 4
• eval_batch_size: 4
• seed: 1337
• 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: 30

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy Offensive	F1 Macro Offensive	F1 Weighted Offensive	F1 Macro Total	F1 Weighted Total
0.228	1.0	8645	0.6739	0.7990	0.7921	0.8028	0.7921	0.8028
0.1927	2.0	17290	0.8698	0.8014	0.7945	0.8051	0.7945	0.8051
0.17	3.0	25935	1.0102	0.8110	0.8015	0.8137	0.8015	0.8137
0.1382	4.0	34580	1.0037	0.7951	0.7870	0.7987	0.7870	0.7987
0.1102	5.0	43225	1.5021	0.7911	0.7830	0.7948	0.7830	0.7948
0.0752	6.0	51870	1.5621	0.8157	0.8041	0.8175	0.8041	0.8175
0.0291	7.0	60515	1.6726	0.8046	0.7958	0.8078	0.7958	0.8078
0.0368	8.0	69160	1.7665	0.8181	0.8073	0.8202	0.8073	0.8202
0.0196	9.0	77805	1.7392	0.8253	0.8133	0.8266	0.8133	0.8266
0.0269	10.0	86450	2.0158	0.8118	0.7989	0.8132	0.7989	0.8132
0.024	11.0	95095	1.9926	0.8125	0.8021	0.8149	0.8021	0.8149
0.014	12.0	103740	1.9551	0.8070	0.7983	0.8101	0.7983	0.8101
0.0023	13.0	112385	2.1779	0.8006	0.7929	0.8042	0.7929	0.8042
0.0142	14.0	121030	1.9266	0.8253	0.8134	0.8267	0.8134	0.8267
0.0142	15.0	129675	2.0064	0.8141	0.8040	0.8166	0.8040	0.8166
0.0007	16.0	138320	1.9572	0.8245	0.8130	0.8260	0.8130	0.8260
0.0103	17.0	146965	2.1624	0.8284	0.8167	0.8298	0.8167	0.8298
0.0064	18.0	155610	2.3954	0.8062	0.7979	0.8094	0.7979	0.8094
0.0073	19.0	164255	2.3921	0.7998	0.7910	0.8031	0.7910	0.8031
0.0006	20.0	172900	2.2476	0.7887	0.7814	0.7927	0.7814	0.7927
0.0044	21.0	181545	2.4038	0.8086	0.7988	0.8113	0.7988	0.8113
0.009	22.0	190190	2.5851	0.8014	0.7931	0.8048	0.7931	0.8048

Framework versions

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