metadata

license: mit
base_model: indolem/indobert-base-uncased
tags:
  - generated_from_trainer
metrics:
  - accuracy
  - precision
  - recall
  - f1
model-index:
  - name: sentiment-lora-r8a2d0.1-1
    results: []

sentiment-lora-r8a2d0.1-1

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: 0.3035
Accuracy: 0.8747
Precision: 0.8523
Recall: 0.8413
F1: 0.8465

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
0.5655	1.0	122	0.5179	0.7243	0.6623	0.6499	0.6548
0.5048	2.0	244	0.4926	0.7519	0.7079	0.7270	0.7147
0.4529	3.0	366	0.4301	0.7995	0.7581	0.7606	0.7593
0.393	4.0	488	0.3863	0.8221	0.7871	0.7766	0.7814
0.3754	5.0	610	0.3868	0.8246	0.7892	0.8209	0.8003
0.3455	6.0	732	0.3605	0.8446	0.8126	0.8126	0.8126
0.3344	7.0	854	0.3396	0.8546	0.8263	0.8196	0.8229
0.3157	8.0	976	0.3319	0.8672	0.8436	0.8310	0.8369
0.3076	9.0	1098	0.3273	0.8546	0.8284	0.8146	0.8210
0.2948	10.0	1220	0.3238	0.8747	0.8552	0.8363	0.8448
0.2737	11.0	1342	0.3199	0.8697	0.8474	0.8328	0.8395
0.2741	12.0	1464	0.3190	0.8596	0.8299	0.8332	0.8315
0.275	13.0	1586	0.3146	0.8772	0.8628	0.8331	0.8458
0.2736	14.0	1708	0.3104	0.8697	0.8460	0.8353	0.8404
0.263	15.0	1830	0.3112	0.8672	0.8393	0.8410	0.8402
0.2583	16.0	1952	0.3086	0.8722	0.8453	0.8471	0.8462
0.2544	17.0	2074	0.3065	0.8722	0.8512	0.8346	0.8422
0.2594	18.0	2196	0.3056	0.8697	0.8449	0.8378	0.8412
0.256	19.0	2318	0.3043	0.8722	0.8512	0.8346	0.8422
0.2515	20.0	2440	0.3035	0.8747	0.8523	0.8413	0.8465

Framework versions

Transformers 4.39.3
Pytorch 2.3.0+cu121
Datasets 2.19.1
Tokenizers 0.15.2