RoBERTa-Base-SE2025T11A-sun-v20241225073733

This model is a fine-tuned version of w11wo/sundanese-roberta-base-emotion-classifier on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.5770
• F1 Macro: 0.4036
• F1 Micro: 0.6979
• F1 Weighted: 0.6788
• F1 Samples: 0.7240
• F1 Label Marah: 0.3158
• F1 Label Jijik: 0.4
• F1 Label Takut: 0.0
• F1 Label Senang: 0.8776
• F1 Label Sedih: 0.7273
• F1 Label Terkejut: 0.3043
• F1 Label Biasa: 0.2

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: 2e-05
• train_batch_size: 2
• eval_batch_size: 2
• seed: 42
• optimizer: Use 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: 25

Training results

Training Loss	Epoch	Step	Validation Loss	F1 Macro	F1 Micro	F1 Weighted	F1 Samples	F1 Label Marah	F1 Label Jijik	F1 Label Takut	F1 Label Senang	F1 Label Sedih	F1 Label Terkejut	F1 Label Biasa
0.4233	0.2994	100	0.3265	0.1217	0.6312	0.4679	0.6615	0.0	0.0	0.0	0.8520	0.0	0.0	0.0
0.4072	0.5988	200	0.2954	0.2063	0.6780	0.5708	0.6771	0.0	0.0	0.0	0.8788	0.5652	0.0	0.0
0.3778	0.8982	300	0.2838	0.2633	0.6887	0.5790	0.7161	0.4444	0.0	0.0	0.8720	0.5263	0.0	0.0
0.2968	1.1976	400	0.3056	0.3553	0.7055	0.6063	0.7292	0.5455	0.5	0.0	0.8774	0.5641	0.0	0.0
0.3193	1.4970	500	0.2859	0.3452	0.6623	0.5986	0.6654	0.4706	0.4444	0.0	0.8457	0.6557	0.0	0.0
0.308	1.7964	600	0.2684	0.3539	0.7086	0.6257	0.7240	0.4	0.5	0.0	0.8877	0.6897	0.0	0.0
0.2574	2.0958	700	0.2980	0.3544	0.6993	0.6130	0.7234	0.5455	0.4444	0.0	0.8788	0.6122	0.0	0.0
0.2352	2.3952	800	0.2827	0.3865	0.6965	0.6427	0.7117	0.5455	0.4444	0.0	0.8602	0.6885	0.1667	0.0
0.2533	2.6946	900	0.2573	0.4206	0.7492	0.6959	0.7638	0.5455	0.4444	0.0	0.8980	0.8	0.2564	0.0
0.2436	2.9940	1000	0.2990	0.3576	0.6769	0.6503	0.7013	0.4211	0.2857	0.0	0.8691	0.6667	0.2609	0.0
0.179	3.2934	1100	0.2911	0.3428	0.6730	0.6307	0.6977	0.375	0.3333	0.0	0.8649	0.6552	0.1714	0.0
0.1982	3.5928	1200	0.3006	0.3789	0.6951	0.6622	0.7172	0.4211	0.375	0.0	0.8691	0.7308	0.2564	0.0
0.1744	3.8922	1300	0.3002	0.3791	0.7015	0.6571	0.7169	0.4615	0.3636	0.0	0.8643	0.72	0.2439	0.0
0.1464	4.1916	1400	0.3178	0.3823	0.7032	0.6427	0.7146	0.5455	0.4444	0.0	0.8731	0.6957	0.1176	0.0
0.136	4.4910	1500	0.3143	0.3620	0.7107	0.6619	0.7266	0.4	0.25	0.0	0.8673	0.7170	0.3	0.0
0.1258	4.7904	1600	0.3286	0.4306	0.7021	0.6939	0.7208	0.4211	0.25	0.0	0.8705	0.7755	0.3333	0.3636
0.1144	5.0898	1700	0.3240	0.4429	0.7152	0.6865	0.7339	0.375	0.4444	0.0	0.8687	0.7755	0.2727	0.3636
0.0899	5.3892	1800	0.3375	0.4518	0.7256	0.6901	0.7427	0.4615	0.4444	0.0	0.8687	0.7547	0.3	0.3333
0.0959	5.6886	1900	0.3258	0.4375	0.7323	0.6995	0.7432	0.4615	0.25	0.0	0.8776	0.7843	0.3256	0.3636
0.0934	5.9880	2000	0.3437	0.4257	0.7055	0.6789	0.7240	0.4	0.3333	0.0	0.8586	0.7547	0.3	0.3333
0.0713	6.2874	2100	0.3629	0.4337	0.6977	0.6919	0.7195	0.3333	0.3636	0.0	0.8660	0.7170	0.3922	0.3636
0.0584	6.5868	2200	0.3695	0.4064	0.6982	0.6751	0.7180	0.4211	0.3636	0.0	0.875	0.7368	0.2667	0.1818
0.059	6.8862	2300	0.3909	0.3894	0.7126	0.6848	0.7333	0.375	0.3636	0.0	0.8780	0.7692	0.3396	0.0
0.0586	7.1856	2400	0.3815	0.4200	0.7025	0.6931	0.7263	0.375	0.4	0.0	0.8856	0.7778	0.3019	0.2
0.0314	7.4850	2500	0.3910	0.3824	0.6934	0.6882	0.7156	0.3	0.3333	0.0	0.8731	0.8	0.3704	0.0
0.0438	7.7844	2600	0.3702	0.4755	0.7359	0.7155	0.7451	0.4615	0.4444	0.0	0.8731	0.7778	0.4082	0.3636
0.0402	8.0838	2700	0.4042	0.4384	0.7147	0.7078	0.7362	0.3158	0.3333	0.0	0.8788	0.8	0.3774	0.3636
0.0264	8.3832	2800	0.4175	0.4423	0.7080	0.6986	0.7312	0.3	0.3636	0.0	0.8796	0.75	0.3415	0.4615
0.042	8.6826	2900	0.3898	0.4036	0.7152	0.6863	0.7331	0.3333	0.2222	0.0	0.8832	0.7451	0.3077	0.3333
0.0342	8.9820	3000	0.4055	0.4390	0.7209	0.7063	0.7448	0.3333	0.3636	0.0	0.8788	0.7636	0.4	0.3333
0.0268	9.2814	3100	0.4006	0.4312	0.7147	0.6957	0.7362	0.3529	0.3333	0.0	0.8808	0.7692	0.3182	0.3636
0.0253	9.5808	3200	0.4121	0.4302	0.7062	0.6983	0.7302	0.3636	0.2667	0.0	0.8705	0.7917	0.3556	0.3636
0.0179	9.8802	3300	0.4356	0.3574	0.6967	0.6606	0.7206	0.4	0.25	0.0	0.8788	0.7407	0.2326	0.0
0.018	10.1796	3400	0.4594	0.4081	0.7066	0.6713	0.7299	0.4706	0.3636	0.0	0.8821	0.7241	0.2162	0.2
0.0151	10.4790	3500	0.4579	0.3911	0.7190	0.6807	0.7422	0.375	0.2222	0.0	0.8844	0.7636	0.2703	0.2222
0.0124	10.7784	3600	0.4415	0.3710	0.6988	0.6648	0.7286	0.2857	0.2222	0.0	0.8744	0.7547	0.2381	0.2222
0.0193	11.0778	3700	0.4514	0.3797	0.6903	0.6708	0.7172	0.3529	0.2	0.0	0.8763	0.7018	0.3043	0.2222
0.0138	11.3772	3800	0.4427	0.3681	0.6909	0.6637	0.7065	0.25	0.25	0.0	0.8705	0.7273	0.2791	0.2
0.0101	11.6766	3900	0.4641	0.4035	0.6964	0.6718	0.7203	0.3478	0.4	0.0	0.8705	0.75	0.2564	0.2
0.0112	11.9760	4000	0.4713	0.4260	0.7048	0.6820	0.7260	0.3158	0.4	0.0	0.8731	0.7917	0.2381	0.3636
0.0118	12.2754	4100	0.4722	0.3811	0.6941	0.6751	0.7148	0.2857	0.25	0.0	0.8731	0.7547	0.3043	0.2
0.0086	12.5749	4200	0.4911	0.4104	0.7009	0.6925	0.7216	0.3077	0.3636	0.0	0.8776	0.7636	0.36	0.2
0.0099	12.8743	4300	0.4928	0.3666	0.6786	0.6584	0.7076	0.2857	0.25	0.0	0.8796	0.7018	0.2273	0.2222
0.0074	13.1737	4400	0.4873	0.3970	0.7072	0.6954	0.7234	0.3158	0.2222	0.0	0.8776	0.7636	0.4	0.2
0.0066	13.4731	4500	0.4947	0.4096	0.7080	0.6896	0.7286	0.3158	0.3636	0.0	0.8832	0.7843	0.2979	0.2222
0.0071	13.7725	4600	0.4939	0.3922	0.7055	0.6848	0.7302	0.3529	0.2222	0.0	0.8832	0.7241	0.3404	0.2222
0.0083	14.0719	4700	0.5015	0.3803	0.6997	0.6775	0.7255	0.3	0.2222	0.0	0.8832	0.7368	0.2979	0.2222
0.0065	14.3713	4800	0.5024	0.4186	0.7038	0.6867	0.7255	0.3636	0.4	0.0	0.8763	0.7636	0.3043	0.2222
0.0055	14.6707	4900	0.5100	0.4132	0.7035	0.6862	0.7292	0.3478	0.4	0.0	0.8788	0.7547	0.3111	0.2
0.0056	14.9701	5000	0.5013	0.4411	0.7059	0.6961	0.7357	0.2727	0.4	0.0	0.8808	0.7547	0.3182	0.4615
0.0044	15.2695	5100	0.5120	0.3840	0.6977	0.6843	0.7201	0.2857	0.2222	0.0	0.8776	0.7273	0.375	0.2
0.0052	15.5689	5200	0.5334	0.3811	0.7035	0.6818	0.7294	0.3	0.2	0.0	0.8844	0.75	0.3111	0.2222
0.0041	15.8683	5300	0.5184	0.4135	0.7143	0.6895	0.7352	0.3158	0.4	0.0	0.8832	0.7547	0.3182	0.2222
0.0052	16.1677	5400	0.5182	0.4188	0.7186	0.6910	0.7352	0.3529	0.4	0.0	0.8832	0.7547	0.3182	0.2222
0.0036	16.4671	5500	0.5208	0.4125	0.7164	0.6949	0.7370	0.3	0.3636	0.0	0.8832	0.8	0.3182	0.2222
0.004	16.7665	5600	0.5382	0.4086	0.7059	0.6842	0.7315	0.3	0.4	0.0	0.8788	0.7407	0.3182	0.2222
0.0037	17.0659	5700	0.5258	0.4208	0.7118	0.6959	0.7299	0.3158	0.4	0.0	0.8776	0.7547	0.375	0.2222
0.0036	17.3653	5800	0.5283	0.4065	0.7101	0.6873	0.7326	0.3158	0.3636	0.0	0.8788	0.7692	0.3182	0.2
0.0031	17.6647	5900	0.5315	0.4107	0.7041	0.6840	0.7247	0.3158	0.4	0.0	0.8776	0.7547	0.3043	0.2222
0.0041	17.9641	6000	0.5419	0.4084	0.6977	0.6806	0.7232	0.3636	0.3636	0.0	0.8776	0.7273	0.3043	0.2222
0.0031	18.2635	6100	0.5469	0.4071	0.7	0.6784	0.7253	0.3158	0.4	0.0	0.8731	0.7273	0.3111	0.2222
0.003	18.5629	6200	0.5477	0.4213	0.7080	0.6877	0.7292	0.4	0.4	0.0	0.8821	0.7407	0.3043	0.2222
0.0032	18.8623	6300	0.5395	0.4054	0.7003	0.6842	0.7208	0.3158	0.4	0.0	0.8808	0.7547	0.3043	0.1818
0.0033	19.1617	6400	0.5444	0.3989	0.7038	0.6968	0.7240	0.3478	0.2222	0.0	0.8808	0.7843	0.375	0.1818
0.0032	19.4611	6500	0.5482	0.4047	0.6982	0.6817	0.7182	0.3158	0.4	0.0	0.8763	0.7547	0.3043	0.1818
0.0025	19.7605	6600	0.5498	0.4047	0.7003	0.6818	0.7221	0.3158	0.4	0.0	0.8763	0.7407	0.3182	0.1818
0.0027	20.0599	6700	0.5542	0.4134	0.6997	0.6879	0.7232	0.3636	0.4	0.0	0.8808	0.7273	0.3404	0.1818
0.003	20.3593	6800	0.5599	0.3788	0.6962	0.6762	0.7214	0.3158	0.2222	0.0	0.8821	0.7273	0.3043	0.2
0.0025	20.6587	6900	0.5556	0.4121	0.7041	0.6838	0.7247	0.3158	0.4	0.0	0.8731	0.7692	0.3043	0.2222
0.0027	20.9581	7000	0.5579	0.4010	0.6959	0.6781	0.7214	0.3158	0.4	0.0	0.8776	0.7273	0.3043	0.1818
0.0025	21.2575	7100	0.5583	0.3762	0.6941	0.6754	0.7188	0.3158	0.2222	0.0	0.8821	0.7273	0.3043	0.1818
0.0025	21.5569	7200	0.5586	0.4021	0.6941	0.6771	0.7169	0.3158	0.4	0.0	0.8718	0.7407	0.3043	0.1818
0.0025	21.8563	7300	0.5612	0.3767	0.6923	0.6721	0.7188	0.3158	0.2222	0.0	0.8718	0.7273	0.3182	0.1818
0.0025	22.1557	7400	0.5688	0.3807	0.6962	0.6744	0.7214	0.3333	0.2222	0.0	0.8776	0.7273	0.3043	0.2
0.0025	22.4551	7500	0.5707	0.4054	0.6979	0.6771	0.7227	0.3333	0.4	0.0	0.8731	0.7273	0.3043	0.2
0.0024	22.7545	7600	0.5702	0.4055	0.7	0.6809	0.7247	0.3158	0.4	0.0	0.8776	0.7407	0.3043	0.2
0.0022	23.0539	7700	0.5706	0.4119	0.7038	0.6858	0.7266	0.3158	0.4	0.0	0.8776	0.7273	0.3404	0.2222
0.0017	23.3533	7800	0.5725	0.4067	0.7	0.6797	0.7240	0.3158	0.4	0.0	0.8776	0.7273	0.3043	0.2222
0.0026	23.6527	7900	0.5774	0.4061	0.6979	0.6773	0.7227	0.3158	0.4	0.0	0.8731	0.7273	0.3043	0.2222
0.0023	23.9521	8000	0.5758	0.4087	0.7021	0.6818	0.7253	0.3158	0.4	0.0	0.8776	0.7407	0.3043	0.2222
0.0022	24.2515	8100	0.5774	0.4067	0.7	0.6797	0.7240	0.3158	0.4	0.0	0.8776	0.7273	0.3043	0.2222
0.0022	24.5509	8200	0.5764	0.4067	0.7	0.6797	0.7240	0.3158	0.4	0.0	0.8776	0.7273	0.3043	0.2222
0.0023	24.8503	8300	0.5770	0.4036	0.6979	0.6788	0.7240	0.3158	0.4	0.0	0.8776	0.7273	0.3043	0.2

Framework versions

• Transformers 4.47.1
• Pytorch 2.5.1+cu121
• Datasets 3.2.0
• Tokenizers 0.21.0