metadata

language:
  - id
license: mit
base_model: indolem/indobert-base-uncased
tags:
  - generated_from_trainer
metrics:
  - accuracy
  - precision
  - recall
  - f1
model-index:
  - name: sentiment-unipelt-0
    results: []

sentiment-unipelt-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: 0.3013
Accuracy: 0.8922
Precision: 0.8694
Recall: 0.8712
F1: 0.8703

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
0.5538	1.0	122	0.4789	0.7193	0.6517	0.6289	0.6359
0.4356	2.0	244	0.4088	0.7845	0.7518	0.7900	0.7610
0.3417	3.0	366	0.3369	0.8571	0.8365	0.8089	0.8206
0.2904	4.0	488	0.3267	0.8672	0.8423	0.8335	0.8377
0.263	5.0	610	0.3210	0.8672	0.8356	0.8585	0.8453
0.2463	6.0	732	0.3551	0.8421	0.8093	0.8483	0.8220
0.2303	7.0	854	0.3028	0.8722	0.8409	0.8696	0.8524
0.2208	8.0	976	0.2673	0.8897	0.8695	0.8620	0.8656
0.1994	9.0	1098	0.2715	0.8897	0.8649	0.8720	0.8683
0.1836	10.0	1220	0.2595	0.9098	0.8999	0.8787	0.8883
0.1706	11.0	1342	0.2833	0.8922	0.8650	0.8838	0.8734
0.1623	12.0	1464	0.2993	0.8872	0.8599	0.8752	0.8669
0.1478	13.0	1586	0.2864	0.8972	0.8849	0.8623	0.8724
0.1467	14.0	1708	0.2805	0.8972	0.8754	0.8773	0.8764
0.132	15.0	1830	0.2869	0.8997	0.8748	0.8891	0.8814
0.125	16.0	1952	0.3052	0.8972	0.8723	0.8848	0.8781
0.1183	17.0	2074	0.2968	0.8897	0.8649	0.8720	0.8683
0.1185	18.0	2196	0.3033	0.8922	0.8673	0.8763	0.8716
0.1132	19.0	2318	0.3063	0.8897	0.8640	0.8745	0.8689
0.1195	20.0	2440	0.3013	0.8922	0.8694	0.8712	0.8703

Framework versions

Transformers 4.39.3
Pytorch 2.3.0+cu121
Datasets 2.19.1
Tokenizers 0.15.2