RoBERTa-Base-SE2025T11A-sun-v20250108115409

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

• Loss: 0.6184
• F1 Macro: 0.6208
• F1 Micro: 0.6202
• F1 Weighted: 0.6194
• F1 Samples: 0.6273
• F1 Label Marah: 0.6095
• F1 Label Jijik: 0.5636
• F1 Label Takut: 0.5789
• F1 Label Senang: 0.7907
• F1 Label Sedih: 0.6420
• F1 Label Terkejut: 0.5455
• F1 Label Biasa: 0.6154

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: 15

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
0.5025	0.1805	100	0.4545	0.0381	0.0539	0.0497	0.0345	0.1613	0.1053	0.0	0.0	0.0	0.0	0.0
0.4938	0.3610	200	0.4332	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0
0.4204	0.5415	300	0.4173	0.1104	0.2042	0.1134	0.1276	0.0	0.0392	0.0	0.7333	0.0	0.0	0.0
0.4333	0.7220	400	0.3903	0.1978	0.2811	0.2130	0.1677	0.0357	0.3030	0.0	0.6747	0.0	0.3714	0.0
0.4342	0.9025	500	0.3825	0.2448	0.3387	0.2510	0.2523	0.1356	0.1818	0.5484	0.7527	0.0952	0.0	0.0
0.3831	1.0830	600	0.3514	0.3626	0.4293	0.3931	0.3386	0.4444	0.3544	0.4	0.7209	0.4444	0.1739	0.0
0.3454	1.2635	700	0.3686	0.4495	0.5185	0.4910	0.4575	0.5690	0.5225	0.5763	0.7105	0.2979	0.4706	0.0
0.3233	1.4440	800	0.3443	0.4102	0.4751	0.4400	0.4039	0.3143	0.4854	0.3256	0.7561	0.6349	0.3548	0.0
0.3341	1.6245	900	0.3174	0.5738	0.5861	0.5726	0.5318	0.6	0.425	0.6667	0.7792	0.6410	0.3860	0.5185
0.3311	1.8051	1000	0.3233	0.5625	0.5672	0.5512	0.4868	0.5476	0.2951	0.6780	0.7381	0.5797	0.5275	0.5714
0.3157	1.9856	1100	0.3160	0.4992	0.5796	0.5461	0.5578	0.6549	0.5625	0.5882	0.7742	0.4528	0.4615	0.0
0.2242	2.1661	1200	0.3282	0.5922	0.5938	0.5947	0.5722	0.5435	0.5607	0.6667	0.7778	0.5574	0.5393	0.5
0.2403	2.3466	1300	0.3081	0.5586	0.5909	0.5725	0.5541	0.6263	0.3881	0.6753	0.7848	0.5672	0.5352	0.3333
0.2142	2.5271	1400	0.3479	0.5597	0.5827	0.5710	0.5610	0.5287	0.5806	0.5385	0.7711	0.6301	0.4688	0.4
0.2091	2.7076	1500	0.3254	0.5764	0.5992	0.5869	0.5719	0.6804	0.4615	0.6774	0.7527	0.5	0.5185	0.4444
0.212	2.8881	1600	0.3223	0.5793	0.6154	0.6027	0.5988	0.6786	0.5814	0.6875	0.7529	0.5085	0.5263	0.32
0.1939	3.0686	1700	0.3372	0.6343	0.6274	0.6286	0.6168	0.6154	0.5349	0.6667	0.7733	0.6286	0.5714	0.65
0.1382	3.2491	1800	0.3555	0.6085	0.6090	0.5999	0.5952	0.6095	0.4658	0.5974	0.7912	0.5974	0.5316	0.6667
0.1494	3.4296	1900	0.3503	0.6094	0.6099	0.6089	0.6029	0.6383	0.5455	0.6296	0.75	0.5625	0.5352	0.6047
0.129	3.6101	2000	0.3766	0.6004	0.6106	0.6058	0.5970	0.5918	0.5057	0.6364	0.7901	0.6027	0.5934	0.4828
0.1182	3.7906	2100	0.3589	0.6283	0.6298	0.6276	0.6287	0.6731	0.5176	0.6765	0.7654	0.6176	0.5366	0.6111
0.143	3.9711	2200	0.3735	0.5977	0.6022	0.5984	0.6138	0.6306	0.5385	0.5556	0.7765	0.5814	0.5070	0.5946
0.1281	4.1516	2300	0.3730	0.6270	0.6306	0.6294	0.6273	0.6783	0.5417	0.5833	0.7711	0.6176	0.5909	0.6061
0.0804	4.3321	2400	0.4072	0.6253	0.6292	0.6277	0.6341	0.6604	0.5818	0.5867	0.8	0.6067	0.5352	0.6061
0.0829	4.5126	2500	0.4064	0.6110	0.6120	0.6140	0.6125	0.6306	0.5376	0.625	0.7222	0.6571	0.5542	0.55
0.1022	4.6931	2600	0.4271	0.6175	0.6218	0.6199	0.6228	0.6465	0.5825	0.6154	0.7556	0.5882	0.5432	0.5909
0.0707	4.8736	2700	0.4542	0.5901	0.5993	0.5936	0.6050	0.6408	0.5664	0.5455	0.7765	0.5312	0.4928	0.5778
0.0921	5.0542	2800	0.4340	0.5943	0.5982	0.5975	0.5992	0.6296	0.5714	0.5556	0.775	0.5758	0.4810	0.5714
0.0567	5.2347	2900	0.4351	0.5975	0.6098	0.6052	0.6092	0.6727	0.5227	0.5312	0.7674	0.6353	0.5238	0.5294
0.0567	5.4152	3000	0.4385	0.5999	0.6079	0.6068	0.6122	0.6604	0.5474	0.5714	0.7674	0.6133	0.5063	0.5333
0.0527	5.5957	3100	0.4416	0.6082	0.6140	0.6126	0.6150	0.6476	0.5684	0.6071	0.7586	0.6053	0.5122	0.5581
0.0611	5.7762	3200	0.4462	0.6147	0.6173	0.6153	0.6179	0.6667	0.5686	0.5352	0.7711	0.625	0.5	0.6364
0.0556	5.9567	3300	0.4505	0.6256	0.6264	0.6246	0.6195	0.6441	0.5474	0.5915	0.7654	0.6579	0.5479	0.625
0.046	6.1372	3400	0.4700	0.6178	0.6165	0.6159	0.6125	0.6542	0.5294	0.6410	0.75	0.5915	0.5333	0.625
0.0417	6.3177	3500	0.4695	0.6228	0.6255	0.6261	0.6296	0.66	0.5631	0.6333	0.7529	0.6	0.5714	0.5789
0.041	6.4982	3600	0.4619	0.6104	0.6162	0.6161	0.6047	0.6667	0.5111	0.64	0.75	0.6269	0.5517	0.5263
0.057	6.6787	3700	0.4954	0.5990	0.6051	0.6054	0.6164	0.6542	0.5306	0.6	0.7674	0.5647	0.5495	0.5263
0.0398	6.8592	3800	0.4771	0.6175	0.6211	0.6197	0.6167	0.6263	0.5333	0.6234	0.7711	0.6575	0.5526	0.5581
0.03	7.0397	3900	0.4944	0.6045	0.6101	0.6099	0.6123	0.6	0.5376	0.6410	0.7805	0.5870	0.5854	0.5
0.032	7.2202	4000	0.4920	0.6333	0.6381	0.6356	0.6497	0.6446	0.5849	0.5714	0.8	0.6410	0.5854	0.6061
0.0359	7.4007	4100	0.5033	0.6265	0.6241	0.6246	0.6302	0.6271	0.5577	0.6269	0.7805	0.5897	0.5783	0.625
0.0257	7.5812	4200	0.5155	0.6090	0.6206	0.6199	0.6225	0.6535	0.5872	0.6176	0.7955	0.5634	0.5581	0.4878
0.033	7.7617	4300	0.5402	0.6063	0.6109	0.6123	0.6146	0.6286	0.5593	0.6	0.7907	0.5897	0.5495	0.5263
0.0273	7.9422	4400	0.5259	0.6179	0.6190	0.6187	0.6272	0.6538	0.5143	0.5797	0.7907	0.6076	0.5789	0.6
0.0223	8.1227	4500	0.5211	0.6203	0.6248	0.6217	0.6291	0.6481	0.5055	0.6420	0.7907	0.6197	0.5647	0.5714
0.0193	8.3032	4600	0.5428	0.6230	0.6241	0.6246	0.6380	0.6230	0.5455	0.6230	0.8	0.6269	0.5714	0.5714
0.0238	8.4838	4700	0.5473	0.6188	0.6172	0.6170	0.6384	0.6107	0.5192	0.6389	0.7816	0.6154	0.5714	0.5946
0.021	8.6643	4800	0.5323	0.6220	0.6263	0.6265	0.6354	0.6034	0.6055	0.6	0.8	0.6588	0.5405	0.5455
0.0205	8.8448	4900	0.5348	0.6103	0.6132	0.6150	0.6224	0.6481	0.5517	0.6032	0.7561	0.6265	0.5366	0.55
0.017	9.0253	5000	0.5623	0.6290	0.625	0.6273	0.6471	0.6610	0.5664	0.5366	0.7765	0.6173	0.5783	0.6667
0.013	9.2058	5100	0.5400	0.6090	0.6157	0.6160	0.6203	0.6458	0.5794	0.5634	0.7765	0.5926	0.5647	0.5405
0.0174	9.3863	5200	0.5628	0.6281	0.6278	0.6273	0.6419	0.6379	0.5714	0.6	0.7816	0.6133	0.5641	0.6286
0.0139	9.5668	5300	0.5469	0.6134	0.6162	0.6139	0.6137	0.6139	0.5333	0.6316	0.7857	0.5977	0.56	0.5714
0.0139	9.7473	5400	0.5626	0.6235	0.6234	0.6234	0.6303	0.6316	0.5437	0.5867	0.7907	0.6575	0.55	0.6047
0.0174	9.9278	5500	0.5755	0.6210	0.6186	0.6194	0.6354	0.6087	0.5391	0.5753	0.7907	0.6582	0.5641	0.6111
0.0151	10.1083	5600	0.5767	0.6237	0.6231	0.6229	0.6362	0.6341	0.5686	0.575	0.7619	0.6410	0.5570	0.6286
0.0091	10.2888	5700	0.5831	0.6046	0.6073	0.6072	0.6171	0.6019	0.5545	0.5714	0.7711	0.6279	0.55	0.5556
0.0092	10.4693	5800	0.5728	0.6110	0.6124	0.6115	0.6203	0.6122	0.5437	0.5789	0.7765	0.6279	0.5526	0.5854
0.0093	10.6498	5900	0.5824	0.6150	0.6167	0.6156	0.6291	0.6379	0.5577	0.5570	0.7907	0.6053	0.5455	0.6111
0.0133	10.8303	6000	0.5804	0.6110	0.6151	0.6139	0.6255	0.6435	0.5455	0.5946	0.7765	0.6022	0.5432	0.5714
0.01	11.0108	6100	0.5945	0.6012	0.6095	0.6095	0.6107	0.6154	0.5660	0.5970	0.7907	0.6341	0.5176	0.4878
0.0061	11.1913	6200	0.5868	0.6241	0.6277	0.6264	0.6426	0.6372	0.5741	0.6061	0.7907	0.6301	0.5455	0.5854
0.0066	11.3718	6300	0.5882	0.6120	0.6197	0.6194	0.6302	0.6481	0.5688	0.5797	0.7907	0.64	0.5301	0.5263
0.0082	11.5523	6400	0.5876	0.6208	0.6218	0.6205	0.6378	0.6071	0.5926	0.56	0.7907	0.6341	0.5455	0.6154
0.0083	11.7329	6500	0.6084	0.6128	0.6143	0.6135	0.6270	0.6055	0.5841	0.5714	0.7907	0.6118	0.5316	0.5946
0.0049	11.9134	6600	0.6021	0.6105	0.6138	0.6137	0.6239	0.6168	0.5536	0.6061	0.7907	0.6316	0.525	0.55
0.0055	12.0939	6700	0.5952	0.6152	0.6218	0.6207	0.6338	0.6182	0.5905	0.5823	0.7907	0.6341	0.55	0.5405
0.0043	12.2744	6800	0.6066	0.6157	0.6201	0.6193	0.6333	0.6087	0.6018	0.5556	0.7907	0.6173	0.5647	0.5714
0.0045	12.4549	6900	0.6073	0.6083	0.6159	0.6154	0.6269	0.6182	0.5818	0.5405	0.7907	0.6329	0.5679	0.5263
0.0059	12.6354	7000	0.6100	0.6160	0.6194	0.6200	0.6297	0.6364	0.5421	0.575	0.7907	0.6579	0.5542	0.5556
0.0045	12.8159	7100	0.6128	0.6199	0.6254	0.6248	0.6462	0.6496	0.5841	0.5556	0.7907	0.6579	0.5301	0.5714
0.0045	12.9964	7200	0.6132	0.6176	0.6182	0.6183	0.6407	0.6271	0.5766	0.5455	0.7907	0.6420	0.5301	0.6111
0.0055	13.1769	7300	0.6144	0.6232	0.6265	0.6262	0.6422	0.6422	0.5893	0.6	0.7907	0.625	0.5301	0.5854
0.0037	13.3574	7400	0.6152	0.6218	0.6224	0.6213	0.6326	0.6226	0.5818	0.6	0.7907	0.6173	0.525	0.6154
0.0052	13.5379	7500	0.6199	0.6218	0.6215	0.6212	0.6324	0.6168	0.5766	0.5833	0.7765	0.6341	0.55	0.6154
0.0036	13.7184	7600	0.6182	0.6085	0.6066	0.6069	0.6143	0.6111	0.5347	0.5366	0.7765	0.6420	0.5432	0.6154
0.0045	13.8989	7700	0.6240	0.6099	0.6087	0.6093	0.6185	0.6154	0.5688	0.5570	0.7619	0.6076	0.5432	0.6154
0.0043	14.0794	7800	0.6167	0.6223	0.6231	0.6229	0.6353	0.6429	0.5660	0.5714	0.7765	0.6341	0.55	0.6154
0.0037	14.2599	7900	0.6143	0.6190	0.6202	0.6197	0.6272	0.6226	0.5714	0.5789	0.7907	0.6329	0.5366	0.6
0.0045	14.4404	8000	0.6141	0.6270	0.6270	0.6269	0.6363	0.6355	0.5607	0.5789	0.7907	0.6579	0.55	0.6154
0.0038	14.6209	8100	0.6180	0.6244	0.6248	0.6247	0.6372	0.6355	0.5688	0.5641	0.7907	0.6579	0.5385	0.6154
0.0034	14.8014	8200	0.6189	0.6207	0.6200	0.6193	0.6290	0.6095	0.5636	0.5789	0.7907	0.6410	0.5455	0.6154
0.0033	14.9819	8300	0.6184	0.6208	0.6202	0.6194	0.6273	0.6095	0.5636	0.5789	0.7907	0.6420	0.5455	0.6154

Framework versions

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