elidle/indobert-post-training-fin-sa-2

indobert-post-training-fin-sa-8

This model was trained from scratch on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.2659
• Accuracy: 0.9625
• F1: 0.9621

Model description

elidle/indobert-post-training-fin-sa with strategy = epoch and F1 metric for best model

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: 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
• num_epochs: 15
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	F1
0.2022	1.0	102	0.3728	0.8846	0.8903
0.0819	2.0	204	0.1871	0.9560	0.9555
0.017	3.0	306	0.1603	0.9670	0.9663
0.0833	4.0	408	0.2297	0.9560	0.9560
0.0278	5.0	510	0.2055	0.9670	0.9667
0.0019	6.0	612	0.2263	0.9560	0.9565
0.018	7.0	714	0.3057	0.9560	0.9563
0.0013	8.0	816	0.2599	0.9615	0.9617

Framework versions

• Transformers 4.51.3
• Pytorch 2.6.0+cu124
• Datasets 3.6.0
• Tokenizers 0.21.1