You can deploy this model and start earning money today!

johannawawi/
v6_balanced_dataset_fine-tuning-java-indo-sentiment-analysist-3-class

Name: v6_balanced_dataset_fine-tuning-java-indo-sentiment-analysist-3-class
Rating: 2.5 (10 reviews)

Views

No views yet

results_final

This model is a fine-tuned version of w11wo/indonesian-roberta-base-sentiment-classifier on the None dataset. It achieves the following results on the evaluation set:

More information needed

More information needed

More information needed

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 with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: cosine
lr_scheduler_warmup_ratio: 0.2
num_epochs: 10

Training Loss	Epoch	Step	Validation Loss	Accuracy	F1 Macro	F1 Weighted	Precision Macro	Recall Macro	Precision Weighted	Recall Weighted
0.4024	1.8519	500	0.2951	0.9	0.9002	0.9002	0.9011	0.9000	0.9011	0.9
0.3394	3.7037	1000	0.3384	0.8944	0.8946	0.8946	0.8960	0.8944	0.8960	0.8944
0.2395	5.5556	1500	0.3507	0.9056	0.9055	0.9055	0.9057	0.9056	0.9057	0.9056
0.2222	7.4074	2000	0.3621	0.9	0.9000	0.9000	0.9003	0.9	0.9003	0.9
0.1813	9.2593	2500	0.3718	0.8963	0.8963	0.8963	0.8963	0.8963	0.8963	0.8963