RoBERTa-Base-SE2025T11A-sun-v20250111123127

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: 0.2025
• F1 Macro: 0.7854
• F1 Micro: 0.7849
• F1 Weighted: 0.7826
• F1 Samples: 0.7979
• F1 Label Marah: 0.76
• F1 Label Jijik: 0.7077
• F1 Label Takut: 0.8271
• F1 Label Senang: 0.8489
• F1 Label Sedih: 0.8125
• F1 Label Terkejut: 0.7463
• F1 Label Biasa: 0.7955

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: 2

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
0.4598	0.0615	100	0.4207	0.1498	0.1682	0.1502	0.1043	0.0	0.0	0.3333	0.3415	0.3736	0.0	0.0
0.4187	0.1229	200	0.3878	0.2292	0.3043	0.2263	0.2065	0.0	0.0	0.6154	0.7273	0.2619	0.0	0.0
0.3714	0.1844	300	0.3536	0.3304	0.4103	0.3360	0.3062	0.2340	0.0260	0.6349	0.7424	0.5741	0.1013	0.0
0.3921	0.2459	400	0.3424	0.3967	0.4617	0.4097	0.3830	0.2963	0.0741	0.6076	0.6667	0.6271	0.5049	0.0
0.3477	0.3073	500	0.3091	0.4466	0.5140	0.4500	0.4220	0.1163	0.1190	0.6429	0.7857	0.6667	0.6387	0.1569
0.3327	0.3688	600	0.2963	0.5397	0.5707	0.5325	0.4967	0.1379	0.3363	0.6607	0.8143	0.704	0.6610	0.4638
0.2976	0.4302	700	0.2937	0.5589	0.5972	0.5634	0.5337	0.5658	0.1839	0.6355	0.8054	0.6829	0.6723	0.3667
0.3519	0.4917	800	0.2988	0.5831	0.6233	0.5931	0.5851	0.6392	0.26	0.6095	0.8	0.7656	0.6861	0.3214
0.3027	0.5532	900	0.2769	0.6593	0.6607	0.6576	0.6478	0.5414	0.5290	0.6838	0.8143	0.7752	0.6713	0.6
0.3005	0.6146	1000	0.2860	0.6349	0.6359	0.6315	0.6232	0.5989	0.5124	0.6833	0.7770	0.6306	0.6126	0.6292
0.286	0.6761	1100	0.2782	0.6616	0.6651	0.6543	0.6466	0.512	0.5397	0.6606	0.8138	0.7907	0.6154	0.6990
0.2906	0.7376	1200	0.2692	0.6758	0.6721	0.6701	0.6544	0.6027	0.5397	0.7273	0.736	0.7402	0.6612	0.7234
0.2635	0.7990	1300	0.2740	0.6747	0.6765	0.6706	0.6649	0.6225	0.4696	0.7	0.7273	0.7910	0.7134	0.6988
0.2707	0.8605	1400	0.2666	0.6842	0.6842	0.6798	0.6835	0.6164	0.5496	0.7193	0.8163	0.6957	0.6977	0.6947
0.2577	0.9219	1500	0.2654	0.6803	0.6791	0.6753	0.6712	0.6176	0.5909	0.7304	0.8116	0.6545	0.6525	0.7045
0.2706	0.9834	1600	0.2431	0.7172	0.7195	0.7123	0.7241	0.7013	0.5391	0.7480	0.8227	0.7481	0.7087	0.7527
0.1988	1.0449	1700	0.2480	0.7168	0.7159	0.7133	0.7229	0.6853	0.5846	0.7368	0.7971	0.7419	0.7353	0.7368
0.1967	1.1063	1800	0.2546	0.7258	0.7233	0.7225	0.7278	0.6994	0.6377	0.7257	0.7794	0.7377	0.7429	0.7579
0.1776	1.1678	1900	0.2506	0.7204	0.7159	0.7137	0.7278	0.6324	0.6410	0.7009	0.8112	0.7377	0.7287	0.7912
0.2134	1.2293	2000	0.2525	0.7270	0.7254	0.7208	0.7278	0.6892	0.6364	0.7059	0.8212	0.7119	0.7244	0.8
0.1548	1.2907	2100	0.2526	0.7236	0.7240	0.7191	0.7315	0.6944	0.5873	0.7288	0.8252	0.7480	0.7244	0.7573
0.2253	1.3522	2200	0.2434	0.7398	0.7381	0.7344	0.7498	0.7007	0.6986	0.7154	0.8082	0.7119	0.7353	0.8081
0.173	1.4136	2300	0.2415	0.7482	0.7447	0.7427	0.7578	0.7083	0.6528	0.7130	0.8201	0.7581	0.7681	0.8172
0.1966	1.4751	2400	0.2363	0.7519	0.7497	0.7480	0.7644	0.7067	0.6906	0.7288	0.8175	0.7692	0.7586	0.7917
0.1677	1.5366	2500	0.2360	0.7363	0.7337	0.7316	0.7439	0.7037	0.6190	0.752	0.7786	0.7402	0.7692	0.7912
0.2415	1.5980	2600	0.2320	0.7436	0.7424	0.7389	0.7483	0.7133	0.6142	0.7419	0.8116	0.7581	0.7746	0.7912
0.1749	1.6595	2700	0.2327	0.7410	0.7381	0.7371	0.7544	0.7123	0.6753	0.7395	0.8028	0.7167	0.7576	0.7826
0.1499	1.7210	2800	0.2296	0.7573	0.7541	0.7544	0.7650	0.7037	0.7050	0.7563	0.8030	0.7597	0.7910	0.7826
0.1535	1.7824	2900	0.2274	0.7599	0.7589	0.7577	0.7696	0.7248	0.7194	0.7458	0.8296	0.7752	0.7538	0.7708
0.1818	1.8439	3000	0.2263	0.7524	0.7511	0.7487	0.7626	0.7020	0.6769	0.7438	0.8227	0.7619	0.7761	0.7835
0.179	1.9053	3100	0.2274	0.7596	0.7583	0.7569	0.7717	0.7152	0.7206	0.7563	0.8056	0.7480	0.7879	0.7835
0.1883	1.9668	3200	0.2253	0.7560	0.7544	0.7530	0.7684	0.7105	0.7111	0.7438	0.8056	0.768	0.7692	0.7835

Framework versions

• Transformers 4.48.0
• Pytorch 2.5.1+cu121
• Datasets 3.2.0
• Tokenizers 0.21.0