sentiment-ia3

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: 0.4451
• Accuracy: 0.7870
• Precision: 0.7443
• Recall: 0.7243
• F1: 0.7325

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
0.5653	1.0	122	0.5246	0.7218	0.6540	0.6257	0.6333
0.5167	2.0	244	0.5215	0.7293	0.6805	0.6935	0.6855
0.4984	3.0	366	0.4975	0.7444	0.6916	0.6916	0.6916
0.4765	4.0	488	0.4854	0.7419	0.6837	0.6523	0.6619
0.4797	5.0	610	0.4852	0.7719	0.7270	0.7386	0.7320
0.4668	6.0	732	0.4738	0.7669	0.7190	0.7201	0.7195
0.4622	7.0	854	0.4769	0.7719	0.7261	0.7336	0.7295
0.4621	8.0	976	0.4625	0.7494	0.6949	0.6577	0.6686
0.4561	9.0	1098	0.4609	0.7769	0.7311	0.7122	0.7199
0.4519	10.0	1220	0.4608	0.7669	0.7252	0.6676	0.6822
0.4413	11.0	1342	0.4544	0.7694	0.7215	0.6994	0.7080
0.4449	12.0	1464	0.4569	0.7845	0.7401	0.7425	0.7413
0.4506	13.0	1586	0.4527	0.7644	0.7197	0.6683	0.6821
0.4446	14.0	1708	0.4488	0.7794	0.7379	0.6989	0.7121
0.4426	15.0	1830	0.4491	0.7870	0.7436	0.7293	0.7355
0.4409	16.0	1952	0.4465	0.7719	0.7257	0.6961	0.7068
0.4348	17.0	2074	0.4474	0.7870	0.7436	0.7293	0.7355
0.4478	18.0	2196	0.4460	0.7845	0.7408	0.7225	0.7302
0.4382	19.0	2318	0.4448	0.7870	0.7447	0.7218	0.7310
0.4313	20.0	2440	0.4451	0.7870	0.7443	0.7243	0.7325

Framework versions

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