results_indobert-large-p2_with_preprocessing

This model is a fine-tuned version of indobenchmark/indobert-large-p2 on the None dataset. It achieves the following results on the evaluation set:

• Loss: 1.4698
• Accuracy: 0.4205
• Precision: 0.4834
• Recall: 0.3837
• F1: 0.3699

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: 32
• eval_batch_size: 32
• seed: 42
• optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 500
• num_epochs: 20

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	Precision	Recall	F1
1.7277	1.0	111	1.6459	0.2432	0.1889	0.1984	0.0945
1.6728	2.0	222	1.5886	0.2523	0.2748	0.2149	0.1631
1.64	3.0	333	1.5661	0.2636	0.2986	0.2273	0.1996
1.6025	4.0	444	1.5510	0.2886	0.3229	0.2493	0.2183
1.6051	5.0	555	1.5366	0.325	0.3733	0.2873	0.2596
1.5794	6.0	666	1.5216	0.35	0.4359	0.3120	0.2937
1.568	7.0	777	1.5081	0.3841	0.5137	0.3478	0.3379
1.5721	8.0	888	1.4969	0.4	0.4983	0.3656	0.3575
1.5385	9.0	999	1.4858	0.3932	0.5169	0.3584	0.3501
1.5405	10.0	1110	1.4779	0.4091	0.5295	0.3719	0.3609
1.5143	11.0	1221	1.4698	0.4205	0.4834	0.3837	0.3699
1.5145	12.0	1332	1.4631	0.4091	0.4961	0.3730	0.3626
1.5121	13.0	1443	1.4567	0.4182	0.4957	0.3802	0.3676

Framework versions

• Transformers 4.52.4
• Pytorch 2.6.0+cu124
• Datasets 3.6.0
• Tokenizers 0.21.2