RoBERTa-Base-SE2025T11A-sun-v20250112121908

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: 0.2949
• F1 Macro: 0.5910
• F1 Micro: 0.6274
• F1 Weighted: 0.6153
• F1 Samples: 0.6087
• F1 Label Marah: 0.5714
• F1 Label Jijik: 0.4719
• F1 Label Takut: 0.5581
• F1 Label Senang: 0.8020
• F1 Label Sedih: 0.7213
• F1 Label Terkejut: 0.5283
• F1 Label Biasa: 0.4839

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
0.4842	0.1134	100	0.4075	0.0958	0.2095	0.1451	0.1311	0.0	0.0	0.0	0.6709	0.0	0.0	0.0
0.4016	0.2268	200	0.3800	0.2959	0.4363	0.3427	0.3397	0.4536	0.0	0.5526	0.7867	0.2785	0.0	0.0
0.4007	0.3401	300	0.3647	0.3197	0.4660	0.3694	0.3694	0.3077	0.0	0.5432	0.7814	0.6055	0.0	0.0
0.3876	0.4535	400	0.3456	0.3792	0.5044	0.4319	0.4219	0.4957	0.0	0.5432	0.7835	0.6549	0.1772	0.0
0.3772	0.5669	500	0.3249	0.4043	0.5341	0.4626	0.4603	0.4742	0.0	0.55	0.8165	0.5849	0.4043	0.0
0.3421	0.6803	600	0.3407	0.4582	0.5462	0.5097	0.4840	0.4510	0.4576	0.4658	0.7960	0.6195	0.4176	0.0
0.3847	0.7937	700	0.3121	0.4378	0.5429	0.4932	0.4753	0.4915	0.1875	0.525	0.8020	0.6286	0.4301	0.0
0.3586	0.9070	800	0.3055	0.4769	0.5710	0.5283	0.5091	0.5138	0.2899	0.5476	0.8060	0.6555	0.4742	0.0513
0.3455	1.0204	900	0.3050	0.5215	0.5917	0.5658	0.5356	0.5849	0.5149	0.5185	0.7958	0.6897	0.4464	0.1
0.3108	1.1338	1000	0.2907	0.5593	0.6123	0.5866	0.5662	0.5983	0.3143	0.5301	0.8182	0.7059	0.4632	0.4848
0.2357	1.2472	1100	0.2967	0.5547	0.5992	0.5785	0.5493	0.5053	0.3288	0.5476	0.8168	0.6667	0.4792	0.5385
0.2628	1.3605	1200	0.3027	0.5875	0.6280	0.6165	0.5922	0.5873	0.5455	0.5432	0.8187	0.7049	0.5128	0.4
0.2602	1.4739	1300	0.2977	0.5681	0.6136	0.6010	0.5776	0.5789	0.5	0.5238	0.8066	0.7188	0.5091	0.3396
0.2503	1.5873	1400	0.2968	0.5855	0.6245	0.6113	0.6009	0.5806	0.4691	0.5063	0.8172	0.7287	0.5045	0.4923
0.2694	1.7007	1500	0.3053	0.5789	0.6222	0.6087	0.5936	0.5625	0.4878	0.6022	0.8085	0.7059	0.5149	0.3704
0.2604	1.8141	1600	0.2978	0.6067	0.6430	0.6293	0.6260	0.5714	0.5532	0.5618	0.8269	0.6891	0.5283	0.5161
0.2738	1.9274	1700	0.2949	0.5910	0.6274	0.6153	0.6087	0.5714	0.4719	0.5581	0.8020	0.7213	0.5283	0.4839

Framework versions

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