RoBERTa-Base-SE2025T11A-sun-v20250111112049

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: 0.1248
• F1 Macro: 0.8714
• F1 Micro: 0.8681
• F1 Weighted: 0.8672
• F1 Samples: 0.8874
• F1 Label Marah: 0.8904
• F1 Label Jijik: 0.8235
• F1 Label Takut: 0.8722
• F1 Label Senang: 0.8777
• F1 Label Sedih: 0.8550
• F1 Label Terkejut: 0.8358
• F1 Label Biasa: 0.9451

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
0.4704	0.0556	100	0.4205	0.0663	0.0702	0.0664	0.0367	0.0723	0.0	0.1067	0.2597	0.0	0.0256	0.0
0.414	0.1111	200	0.3719	0.3114	0.3878	0.3223	0.2696	0.5873	0.0	0.5106	0.7285	0.175	0.1786	0.0
0.3685	0.1667	300	0.3395	0.3811	0.4376	0.3971	0.3370	0.5342	0.1235	0.4176	0.6957	0.5741	0.3226	0.0
0.3514	0.2222	400	0.3229	0.4565	0.5175	0.4646	0.4368	0.1818	0.4505	0.5882	0.8077	0.6074	0.44	0.12
0.3209	0.2778	500	0.3025	0.5226	0.5910	0.5437	0.5345	0.6374	0.2472	0.6422	0.8028	0.7049	0.5818	0.0417
0.3259	0.3333	600	0.2859	0.6432	0.6521	0.6452	0.6334	0.6267	0.5606	0.6727	0.8079	0.736	0.5607	0.5376
0.2832	0.3889	700	0.2842	0.5958	0.6238	0.5991	0.5846	0.6029	0.2828	0.7541	0.8169	0.6429	0.6447	0.4262
0.2857	0.4444	800	0.2615	0.6716	0.6667	0.6672	0.6441	0.6418	0.5658	0.7304	0.7656	0.6897	0.6102	0.6977
0.2933	0.5	900	0.2514	0.6939	0.6952	0.6909	0.6802	0.7170	0.5606	0.6789	0.8235	0.7213	0.6504	0.7059
0.2805	0.5556	1000	0.2420	0.7102	0.7106	0.7049	0.7015	0.6615	0.5968	0.7458	0.8261	0.7353	0.6613	0.7447
0.2637	0.6111	1100	0.2513	0.6916	0.6944	0.6904	0.6847	0.7195	0.5909	0.6909	0.7027	0.7843	0.65	0.7027
0.2798	0.6667	1200	0.2292	0.7256	0.7296	0.7247	0.7196	0.7417	0.5882	0.7521	0.8271	0.7626	0.7077	0.7
0.3081	0.7222	1300	0.2218	0.7399	0.7425	0.7375	0.7348	0.7368	0.5932	0.7368	0.8308	0.7862	0.7519	0.7436
0.2316	0.7778	1400	0.2149	0.7602	0.7622	0.7607	0.7646	0.7799	0.7013	0.7368	0.8406	0.7752	0.7576	0.7297
0.2726	0.8333	1500	0.2097	0.7677	0.7680	0.7634	0.7722	0.7328	0.6939	0.7304	0.8630	0.8276	0.7213	0.8049
0.2661	0.8889	1600	0.1956	0.7796	0.7807	0.7779	0.7837	0.8163	0.6667	0.7778	0.8444	0.7786	0.7826	0.7907
0.2647	0.9444	1700	0.1833	0.8141	0.8116	0.8089	0.8197	0.8514	0.7231	0.7907	0.8571	0.8120	0.7656	0.8989
0.2149	1.0	1800	0.1837	0.7949	0.7942	0.7904	0.8124	0.7681	0.7368	0.7414	0.8489	0.8593	0.7556	0.8544
0.1774	1.0556	1900	0.1798	0.8180	0.8174	0.8133	0.8305	0.8472	0.7087	0.8033	0.8531	0.8593	0.7656	0.8889
0.1706	1.1111	2000	0.1795	0.8088	0.8053	0.8022	0.8193	0.75	0.7368	0.8130	0.8652	0.8358	0.7717	0.8889
0.1813	1.1667	2100	0.1663	0.8265	0.8261	0.8235	0.8430	0.8784	0.7857	0.7934	0.8613	0.8308	0.7559	0.88
0.1824	1.2222	2200	0.1604	0.8246	0.8213	0.8189	0.8383	0.8345	0.7947	0.7934	0.8696	0.8	0.7634	0.9167
0.1927	1.2778	2300	0.1607	0.8277	0.8271	0.8242	0.8399	0.8611	0.7402	0.8062	0.8696	0.8550	0.7820	0.88
0.1435	1.3333	2400	0.1679	0.8215	0.8203	0.8182	0.8378	0.8143	0.7971	0.7869	0.8531	0.8462	0.7820	0.8713
0.1575	1.3889	2500	0.1508	0.8475	0.8456	0.8439	0.8554	0.8645	0.8	0.8065	0.8485	0.8921	0.8060	0.9149
0.1696	1.4444	2600	0.1439	0.8486	0.8481	0.8471	0.8625	0.8571	0.8472	0.8033	0.8657	0.8657	0.8235	0.8776
0.1886	1.5	2700	0.1421	0.8572	0.8559	0.8539	0.8686	0.8414	0.8451	0.7899	0.8741	0.9091	0.8261	0.9149
0.1389	1.5556	2800	0.1479	0.8449	0.8435	0.8418	0.8584	0.8235	0.8175	0.816	0.8676	0.8889	0.8120	0.8889
0.1733	1.6111	2900	0.1382	0.8514	0.8477	0.8464	0.8629	0.8456	0.8088	0.816	0.8696	0.8702	0.8148	0.9348
0.1736	1.6667	3000	0.1386	0.8504	0.8479	0.8458	0.8636	0.8406	0.8209	0.8722	0.8777	0.8189	0.8060	0.9167
0.1505	1.7222	3100	0.1353	0.8523	0.8505	0.8489	0.8702	0.8725	0.8	0.8550	0.8777	0.8346	0.8209	0.9053
0.1356	1.7778	3200	0.1308	0.8580	0.8556	0.8543	0.8727	0.8592	0.8148	0.8806	0.8696	0.8372	0.8296	0.9149
0.1418	1.8333	3300	0.1305	0.8628	0.8606	0.8593	0.8784	0.8966	0.8120	0.8636	0.8676	0.8462	0.8271	0.9263
0.1676	1.8889	3400	0.1277	0.8675	0.8647	0.8635	0.8833	0.8828	0.8060	0.8722	0.8777	0.8636	0.8358	0.9348
0.183	1.9444	3500	0.1259	0.8693	0.8656	0.8646	0.8842	0.8671	0.8235	0.8806	0.8777	0.8550	0.8358	0.9451
0.1634	2.0	3600	0.1248	0.8714	0.8681	0.8672	0.8874	0.8904	0.8235	0.8722	0.8777	0.8550	0.8358	0.9451

Framework versions

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