koneksi_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: 1.0917
• Accuracy: 0.75
• F1: 0.7493
• Precision: 0.7497
• Recall: 0.7491

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	0.52	50	0.5014	0.7812	0.7810	0.7865	0.7839
No log	1.04	100	0.5135	0.7708	0.7708	0.7732	0.7726
No log	1.56	150	0.5564	0.7552	0.7503	0.7924	0.7624
No log	2.08	200	0.5628	0.7604	0.7572	0.7659	0.7570
No log	2.6	250	0.8524	0.7083	0.7037	0.7132	0.7043
No log	3.12	300	0.6830	0.7448	0.7432	0.7456	0.7428
No log	3.65	350	0.9662	0.7292	0.7262	0.7321	0.7261
No log	4.17	400	0.9936	0.7656	0.7656	0.7659	0.7663
No log	4.69	450	1.0558	0.7604	0.7603	0.7604	0.7609

Framework versions

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