sentiment-base-0

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

• Loss: 0.8336
• Accuracy: 0.8972
• Precision: 0.8708
• Recall: 0.8898
• F1: 0.8793

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: 30
• eval_batch_size: 8
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 20.0

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	Precision	Recall	F1
0.3942	1.0	122	0.3128	0.8797	0.8858	0.8174	0.8419
0.2168	2.0	244	0.3044	0.8897	0.8659	0.8695	0.8676
0.1372	3.0	366	0.5318	0.8897	0.8852	0.8420	0.8595
0.0957	4.0	488	0.4765	0.8947	0.8676	0.8880	0.8766
0.0674	5.0	610	0.5523	0.8872	0.8577	0.9027	0.8729
0.0535	6.0	732	0.5159	0.9073	0.8888	0.8869	0.8879
0.027	7.0	854	0.5941	0.8872	0.8634	0.8652	0.8643
0.0223	8.0	976	0.7166	0.8797	0.8549	0.8549	0.8549
0.0145	9.0	1098	0.7023	0.9023	0.8802	0.8858	0.8830
0.0106	10.0	1220	0.6993	0.9048	0.8881	0.8801	0.8839
0.0093	11.0	1342	0.8274	0.8947	0.8789	0.8630	0.8704
0.0086	12.0	1464	0.7972	0.8972	0.8796	0.8698	0.8745
0.0106	13.0	1586	0.7592	0.8972	0.8715	0.8873	0.8787
0.0072	14.0	1708	0.7834	0.8997	0.8748	0.8891	0.8814
0.0098	15.0	1830	0.8049	0.8997	0.8767	0.8841	0.8803
0.0058	16.0	1952	0.7671	0.8997	0.8767	0.8841	0.8803
0.0035	17.0	2074	0.8085	0.9023	0.8758	0.8983	0.8857
0.0052	18.0	2196	0.7721	0.8997	0.8757	0.8866	0.8808
0.0028	19.0	2318	0.8359	0.8972	0.8708	0.8898	0.8793
0.0033	20.0	2440	0.8336	0.8972	0.8708	0.8898	0.8793

Framework versions

• Transformers 4.39.3
• Pytorch 2.3.0+cu121
• Datasets 2.19.1
• Tokenizers 0.15.2