sentiment-seq_bn-rf64-4

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: 0.3252
• Accuracy: 0.8496
• Precision: 0.8202
• Recall: 0.8136
• F1: 0.8167

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
0.5579	1.0	122	0.5390	0.7093	0.6626	0.6793	0.6678
0.5043	2.0	244	0.4835	0.7644	0.7516	0.6308	0.6425
0.4819	3.0	366	0.4585	0.7769	0.7322	0.7047	0.7150
0.4474	4.0	488	0.4587	0.7820	0.7399	0.7582	0.7472
0.4336	5.0	610	0.4243	0.8070	0.7756	0.7360	0.7504
0.4036	6.0	732	0.3990	0.8221	0.7846	0.7941	0.7890
0.3871	7.0	854	0.3843	0.8346	0.8074	0.7805	0.7917
0.3704	8.0	976	0.3781	0.8371	0.8270	0.7622	0.7839
0.3563	9.0	1098	0.3728	0.8446	0.8343	0.7751	0.7959
0.34	10.0	1220	0.3545	0.8596	0.8360	0.8182	0.8262
0.3394	11.0	1342	0.3446	0.8571	0.8310	0.8189	0.8245
0.3182	12.0	1464	0.3411	0.8596	0.8389	0.8132	0.8243
0.3226	13.0	1586	0.3353	0.8546	0.8254	0.8221	0.8238
0.3181	14.0	1708	0.3369	0.8546	0.8228	0.8322	0.8272
0.3044	15.0	1830	0.3312	0.8571	0.8289	0.8239	0.8264
0.3038	16.0	1952	0.3287	0.8571	0.8273	0.8289	0.8281
0.3033	17.0	2074	0.3268	0.8596	0.8293	0.8357	0.8324
0.3018	18.0	2196	0.3251	0.8571	0.8266	0.8314	0.8289
0.2955	19.0	2318	0.3253	0.8571	0.8273	0.8289	0.8281
0.2999	20.0	2440	0.3252	0.8496	0.8202	0.8136	0.8167

Framework versions

• Transformers 4.40.2
• Pytorch 2.3.0+cu121
• Datasets 2.19.1
• Tokenizers 0.19.1