metadata

license: mit
base_model: indobenchmark/indobert-base-p2
tags:
  - generated_from_trainer
metrics:
  - accuracy
  - f1
  - precision
  - recall
model-index:
  - name: general_model
    results: []

general_model

This model is a fine-tuned version of indobenchmark/indobert-base-p2 on an unknown dataset. It achieves the following results on the evaluation set:

Loss: 0.2986
Accuracy: 0.9119
F1: 0.8872
Precision: 0.8921
Recall: 0.8827

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: 2e-05
train_batch_size: 16
eval_batch_size: 16
seed: 42
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
num_epochs: 5

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	F1	Precision	Recall
No log	0.06	50	0.3626	0.8748	0.8410	0.8423	0.8398
No log	0.13	100	0.3231	0.8962	0.8699	0.8666	0.8734
No log	0.19	150	0.4256	0.8974	0.8626	0.8892	0.8437
No log	0.25	200	0.3339	0.9031	0.8744	0.8845	0.8658
No log	0.31	250	0.3043	0.8823	0.8587	0.8446	0.8792
No log	0.38	300	0.3125	0.9056	0.8808	0.8802	0.8813
No log	0.44	350	0.2946	0.9075	0.8838	0.8813	0.8863
No log	0.5	400	0.2924	0.9125	0.8898	0.8884	0.8912
No log	0.57	450	0.2991	0.8855	0.8632	0.8480	0.8865
0.3562	0.63	500	0.2986	0.9119	0.8872	0.8921	0.8827
0.3562	0.69	550	0.2851	0.8779	0.8564	0.8395	0.8864
0.3562	0.75	600	0.3272	0.9125	0.8868	0.8968	0.8781
0.3562	0.82	650	0.3438	0.8987	0.8636	0.8933	0.8431

Framework versions

Transformers 4.35.2
Pytorch 2.1.0+cu121
Datasets 2.15.0
Tokenizers 0.15.0