LirihSetyo/result-mbg-1

results-mbg

This model is a fine-tuned version of indobenchmark/indobert-base-p2 on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 2.2966
• Accuracy: 0.8042
• F1: 0.8010

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: 1.5e-05
• train_batch_size: 8
• eval_batch_size: 8
• seed: 42
• optimizer: Use OptimizerNames.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: 50

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	F1
0.7497	1.0	450	0.6446	0.7442	0.7293
0.5179	2.0	900	0.5903	0.7909	0.7848
0.394	3.0	1350	0.7209	0.7920	0.7822
0.2893	4.0	1800	0.6933	0.8009	0.8000
0.2345	5.0	2250	0.8442	0.7964	0.7933
0.1851	6.0	2700	1.0832	0.8076	0.8063
0.149	7.0	3150	1.2132	0.7842	0.7831
0.116	8.0	3600	1.2749	0.7820	0.7909
0.071	9.0	4050	1.4896	0.7798	0.7868
0.0502	10.0	4500	1.5959	0.7875	0.7887
0.0478	11.0	4950	1.6353	0.7942	0.7916
0.0455	12.0	5400	1.4743	0.7887	0.7882
0.0613	13.0	5850	1.4640	0.8042	0.8042
0.0426	14.0	6300	1.7316	0.7887	0.7878
0.0268	15.0	6750	1.6331	0.8076	0.8049
0.0324	16.0	7200	1.5831	0.7987	0.7987
0.037	17.0	7650	1.6437	0.8109	0.8051
0.0205	18.0	8100	1.9980	0.7798	0.7830
0.0348	19.0	8550	1.8968	0.7887	0.7870
0.0222	20.0	9000	1.9109	0.7942	0.7934
0.0314	21.0	9450	1.8187	0.8042	0.8023
0.0294	22.0	9900	1.7358	0.8076	0.8059
0.0186	23.0	10350	1.7662	0.8154	0.8106
0.0128	24.0	10800	1.9257	0.8087	0.8027
0.0102	25.0	11250	1.9096	0.8076	0.8039
0.0121	26.0	11700	1.9006	0.8053	0.8022
0.0001	27.0	12150	1.9534	0.8031	0.7992
0.0087	28.0	12600	2.0792	0.8042	0.8002
0.0216	29.0	13050	2.2049	0.7898	0.7895
0.0133	30.0	13500	2.1616	0.7909	0.7878
0.0161	31.0	13950	2.1408	0.8020	0.7996
0.0092	32.0	14400	2.1145	0.8042	0.8015
0.0107	33.0	14850	2.2761	0.7920	0.7906
0.0149	34.0	15300	2.0581	0.8154	0.8090
0.0054	35.0	15750	2.0965	0.8087	0.8051
0.0041	36.0	16200	2.0660	0.8020	0.7984
0.0112	37.0	16650	2.0523	0.8065	0.8029
0.0002	38.0	17100	2.0631	0.8087	0.8057
0.0038	39.0	17550	2.1953	0.8031	0.8038
0.0052	40.0	18000	2.1119	0.8109	0.8070
0.0	41.0	18450	2.1299	0.8131	0.8083
0.0	42.0	18900	2.1514	0.8198	0.8144
0.0	43.0	19350	2.2249	0.8053	0.8012
0.0	44.0	19800	2.2374	0.8053	0.8012
0.001	45.0	20250	2.2972	0.8009	0.7985
0.0	46.0	20700	2.3105	0.8031	0.8004
0.0028	47.0	21150	2.3073	0.8053	0.8017
0.0018	48.0	21600	2.2713	0.8042	0.8009
0.0	49.0	22050	2.3129	0.8031	0.8000
0.0	50.0	22500	2.2966	0.8042	0.8010

Framework versions

• Transformers 4.54.1
• Pytorch 2.6.0+cu124
• Datasets 4.0.0
• Tokenizers 0.21.4