fitur_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: 1.3853
• Accuracy: 0.7857
• F1: 0.6904
• Precision: 0.7095
• Recall: 0.6786

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	0.54	50	0.6229	0.7582	0.6537	0.6671	0.6454
No log	1.09	100	0.6750	0.7747	0.6557	0.6912	0.6414
No log	1.63	150	0.5936	0.7802	0.7242	0.7137	0.7421
No log	2.17	200	0.7087	0.7912	0.7312	0.7232	0.7419
No log	2.72	250	0.9279	0.7802	0.6796	0.7007	0.6675
No log	3.26	300	1.0408	0.7747	0.6853	0.6940	0.6788
No log	3.8	350	1.2506	0.7857	0.7007	0.7100	0.6935
No log	4.35	400	1.4011	0.7802	0.6796	0.7007	0.6675
No log	4.89	450	1.3770	0.7857	0.6904	0.7095	0.6786

Framework versions

• Transformers 4.35.2
• Pytorch 2.1.0+cu121
• Datasets 2.15.0
• Tokenizers 0.15.0