metadata

language:
  - id
license: mit
base_model: indolem/indobert-base-uncased
tags:
  - generated_from_trainer
metrics:
  - precision
  - recall
  - f1
  - accuracy
model-index:
  - name: nerugm-lora-r8-1
    results: []

nerugm-lora-r8-1

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: 0.1742
Precision: 0.6892
Recall: 0.8266
F1: 0.7516
Accuracy: 0.9465

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: 16
eval_batch_size: 64
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	Precision	Recall	F1	Accuracy
1.2459	1.0	106	0.7376	0.0	0.0	0.0	0.8353
0.7125	2.0	212	0.6395	0.1667	0.0029	0.0057	0.8363
0.6362	3.0	318	0.5518	0.1739	0.0116	0.0217	0.8400
0.5564	4.0	424	0.4672	0.2688	0.0723	0.1139	0.8578
0.4714	5.0	530	0.3912	0.4363	0.2572	0.3236	0.8880
0.3978	6.0	636	0.3240	0.5348	0.4884	0.5106	0.9135
0.3365	7.0	742	0.2839	0.5784	0.6503	0.6122	0.9242
0.294	8.0	848	0.2507	0.6173	0.7225	0.6658	0.9319
0.2677	9.0	954	0.2320	0.6401	0.7659	0.6974	0.9356
0.2457	10.0	1060	0.2109	0.6618	0.7803	0.7162	0.9393
0.2339	11.0	1166	0.2022	0.6667	0.7919	0.7239	0.9405
0.2215	12.0	1272	0.1987	0.6802	0.8237	0.7451	0.9425
0.2125	13.0	1378	0.1899	0.6770	0.8179	0.7408	0.9433
0.2085	14.0	1484	0.1854	0.6843	0.8208	0.7464	0.9438
0.2002	15.0	1590	0.1797	0.6917	0.8237	0.7520	0.9460
0.2	16.0	1696	0.1779	0.6867	0.8237	0.7490	0.9453
0.1929	17.0	1802	0.1774	0.6842	0.8266	0.7487	0.9450
0.1932	18.0	1908	0.1761	0.6875	0.8266	0.7507	0.9458
0.1916	19.0	2014	0.1747	0.6892	0.8266	0.7516	0.9465
0.1887	20.0	2120	0.1742	0.6892	0.8266	0.7516	0.9465

Framework versions

Transformers 4.39.3
Pytorch 2.3.0+cu121
Datasets 2.19.1
Tokenizers 0.15.2