README.md

metadata

language:
  - id
license: mit
base_model: indolem/indobert-base-uncased
tags:
  - generated_from_trainer
metrics:
  - accuracy
  - precision
  - recall
  - f1
model-index:
  - name: sentiment-seq_bn-3
    results: []

sentiment-seq_bn-3

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: 0.2956
• Accuracy: 0.8797
• Precision: 0.8572
• Recall: 0.8499
• F1: 0.8534

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
0.5634	1.0	122	0.5085	0.7193	0.6523	0.6314	0.6381
0.4815	2.0	244	0.4543	0.7469	0.7073	0.7334	0.7147
0.4003	3.0	366	0.3836	0.8271	0.7921	0.7876	0.7898
0.3683	4.0	488	0.3574	0.8371	0.8038	0.8022	0.8030
0.3396	5.0	610	0.3421	0.8596	0.8316	0.8282	0.8298
0.3082	6.0	732	0.3542	0.8521	0.8186	0.8429	0.8285
0.2908	7.0	854	0.3288	0.8571	0.8299	0.8214	0.8255
0.2705	8.0	976	0.3323	0.8596	0.8278	0.8432	0.8347
0.2608	9.0	1098	0.3119	0.8672	0.8449	0.8285	0.8360
0.2489	10.0	1220	0.3060	0.8672	0.8385	0.8435	0.8409
0.2452	11.0	1342	0.3053	0.8822	0.8639	0.8467	0.8545
0.2357	12.0	1464	0.3079	0.8822	0.8715	0.8367	0.8513
0.2206	13.0	1586	0.3079	0.8847	0.8760	0.8384	0.8540
0.2272	14.0	1708	0.2966	0.8722	0.8431	0.8546	0.8484
0.2125	15.0	1830	0.2930	0.8822	0.8596	0.8542	0.8568
0.2094	16.0	1952	0.2946	0.8797	0.8549	0.8549	0.8549
0.2067	17.0	2074	0.2960	0.8847	0.8621	0.8584	0.8602
0.2058	18.0	2196	0.2966	0.8772	0.8524	0.8506	0.8515
0.2003	19.0	2318	0.2961	0.8797	0.8572	0.8499	0.8534
0.2019	20.0	2440	0.2956	0.8797	0.8572	0.8499	0.8534

Framework versions

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