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
0.7652	1.0	1324	0.7574	0.6545	0.5178	0.6545	0.5178	0.7009	0.5777
0.7328	2.0	2648	0.7332	0.6748	0.5689	0.6545	0.5178	0.7009	0.5777
0.7197	3.0	3972	0.7114	0.6911	0.6096	0.6696	0.5540	0.7009	0.5777
0.6994	4.0	5296	0.6872	0.7017	0.6306	0.6990	0.6273	0.7009	0.5777
0.6733	5.0	6620	0.6566	0.7239	0.6671	0.7338	0.6886	0.7179	0.6247
0.649	6.0	7944	0.6261	0.7198	0.6541	0.7583	0.7156	0.7406	0.6675
0.6382	7.0	9268	0.5854	0.7379	0.6822	0.8010	0.7714	0.7681	0.7121
0.6019	8.0	10592	0.5546	0.7319	0.6704	0.8074	0.7757	0.7889	0.7344
0.5857	9.0	11916	0.5207	0.7455	0.6926	0.8346	0.8069	0.8085	0.7572
0.5506	10.0	13240	0.4843	0.7802	0.7450	0.8690	0.8461	0.8267	0.7818
0.5425	11.0	14564	0.4685	0.7659	0.7236	0.8686	0.8443	0.8282	0.7795
0.5444	12.0	15888	0.4371	0.8021	0.7756	0.8939	0.8716	0.8418	0.7971
0.5225	13.0	17212	0.4263	0.7847	0.7515	0.8890	0.8660	0.8440	0.7972
0.5097	14.0	18536	0.4034	0.8206	0.8001	0.9075	0.8854	0.8523	0.8083
0.5041	15.0	19860	0.3973	0.8331	0.8163	0.9060	0.8837	0.8584	0.8131
0.4799	16.0	21184	0.3936	0.8172	0.7957	0.9029	0.8806	0.8539	0.8070
0.4969	17.0	22508	0.3755	0.8531	0.8412	0.9079	0.8857	0.8539	0.8100
0.4627	18.0	23832	0.3723	0.8308	0.8132	0.9063	0.8839	0.8569	0.8107
0.4712	19.0	25156	0.3624	0.8471	0.8334	0.9101	0.8878	0.8591	0.8140
0.4556	20.0	26480	0.3331	0.8780	0.8702	0.9260	0.9038	0.8678	0.8247
0.4434	21.0	27804	0.3298	0.8897	0.8838	0.9245	0.9023	0.8697	0.8254
0.435	22.0	29128	0.3344	0.8788	0.8711	0.9211	0.8989	0.8663	0.8221
0.4414	23.0	30452	0.3291	0.8712	0.8625	0.9207	0.8985	0.8674	0.8223
0.4329	24.0	31776	0.3216	0.8799	0.8725	0.9207	0.8984	0.8644	0.8196
0.4336	25.0	33100	0.3099	0.9048	0.9006	0.9264	0.9042	0.8652	0.8229
0.4253	26.0	34424	0.3049	0.9150	0.9119	0.9301	0.9080	0.8708	0.8286
0.4344	27.0	35748	0.3111	0.8988	0.8939	0.9188	0.8966	0.8697	0.8249
0.4239	28.0	37072	0.3011	0.9139	0.9107	0.9286	0.9065	0.8667	0.8250
0.4109	29.0	38396	0.2949	0.9139	0.9106	0.9275	0.9052	0.8656	0.8225
0.4142	30.0	39720	0.2958	0.9181	0.9155	0.9282	0.9061	0.8686	0.8264
0.4035	31.0	41044	0.2960	0.9147	0.9114	0.9226	0.9004	0.8686	0.8248

Framework versions

Transformers 4.50.2
Pytorch 2.6.0+cu124
Datasets 3.0.1
Tokenizers 0.21.1

iTroned/only_modernbert_v1

only_modernbert_v1

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

iTroned/
only_modernbert_v1