vensys-click-judge

This model is a fine-tuned version of indobenchmark/indobert-base-p1 on the None dataset. It achieves the following results on the evaluation set:

• Loss: 1.1078

Model description

Model to determine what category of the activity based on activity logs

Training hyperparameters

The following hyperparameters were used during training:

• learning_rate: 4e-05
• train_batch_size: 8
• eval_batch_size: 8
• seed: 42
• optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: cosine
• lr_scheduler_warmup_steps: 0.1
• num_epochs: 10
• label_smoothing_factor: 0.1

Training results

Training Loss	Epoch	Step	Validation Loss
0.9792	1.0	98	1.4379
0.8682	2.0	196	1.2967
0.7972	3.0	294	1.1988
0.7893	4.0	392	1.1542
0.7672	5.0	490	1.1370
0.7408	6.0	588	1.1223
0.7584	7.0	686	1.1147
0.7384	8.0	784	1.1098
0.7426	9.0	882	1.1078
0.7483	10.0	980	1.1078

Framework versions

• Transformers 5.14.0
• Pytorch 2.12.1+cu126
• Datasets 5.0.0
• Tokenizers 0.22.2