indobert-emotion-large-bestfold

This model is a fine-tuned version of indobenchmark/indobert-large-p1 on the None dataset. It achieves the following results on the evaluation set:

• Loss: 1.1461
• Accuracy: 0.8136
• Precision: 0.8217
• Recall: 0.8202
• F1: 0.8182

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: 5e-05
• train_batch_size: 32
• eval_batch_size: 32
• seed: 42
• optimizer: Use OptimizerNames.ADAFACTOR and the args are: No additional optimizer arguments
• lr_scheduler_type: linear
• num_epochs: 20

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	Precision	Recall	F1
0.7344	1.0	124	0.6277	0.7886	0.8181	0.7991	0.8033
0.3657	2.0	248	0.6067	0.7886	0.8010	0.7906	0.7916
0.1533	3.0	372	0.8513	0.775	0.7876	0.7875	0.7863
0.0766	4.0	496	1.1461	0.8136	0.8217	0.8202	0.8182
0.056	5.0	620	1.3434	0.7909	0.8091	0.8061	0.8027
0.0274	6.0	744	1.3658	0.7955	0.8029	0.8037	0.8028
0.0155	7.0	868	1.3065	0.8114	0.8233	0.8194	0.8179
0.0148	8.0	992	1.4321	0.8114	0.8223	0.8258	0.8199
0.004	9.0	1116	1.3645	0.8068	0.8173	0.8135	0.8144
0.0147	10.0	1240	1.4823	0.8091	0.8152	0.8191	0.8148
0.0003	11.0	1364	1.4669	0.7977	0.8047	0.8093	0.8065
0.0045	12.0	1488	1.5087	0.8091	0.8252	0.8167	0.8194
0.0002	13.0	1612	1.5367	0.8045	0.8201	0.8141	0.8158
0.0034	14.0	1736	1.5464	0.8114	0.8266	0.8198	0.8217
0.0032	15.0	1860	1.5602	0.8	0.8055	0.8112	0.8079
0.0004	16.0	1984	1.5832	0.8068	0.8237	0.8167	0.8184
0.0023	17.0	2108	1.5886	0.8023	0.8165	0.8121	0.8128
0.0	18.0	2232	1.5907	0.8023	0.8165	0.8121	0.8128
0.0003	19.0	2356	1.5958	0.8045	0.8199	0.8141	0.8154
0.0001	20.0	2480	1.5966	0.8045	0.8199	0.8141	0.8154

Framework versions

• Transformers 4.51.3
• Pytorch 2.6.0+cu124
• Datasets 3.6.0
• Tokenizers 0.21.1