aspect_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: 1.3490
• Accuracy: 0.8084

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: 20

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
No log	1.0	72	0.6516	0.7735
No log	2.0	144	0.6119	0.7909
No log	3.0	216	0.6152	0.8049
No log	4.0	288	0.7480	0.8118
No log	5.0	360	1.0121	0.7770
No log	6.0	432	1.0780	0.7909
0.27	7.0	504	1.1602	0.7840
0.27	8.0	576	1.2136	0.8014
0.27	9.0	648	1.2490	0.8014
0.27	10.0	720	1.3102	0.7840
0.27	11.0	792	1.3184	0.8049
0.27	12.0	864	1.3255	0.8014
0.27	13.0	936	1.3192	0.8049
0.0022	14.0	1008	1.3229	0.7944
0.0022	15.0	1080	1.3415	0.8014
0.0022	16.0	1152	1.3515	0.7909
0.0022	17.0	1224	1.3544	0.7944
0.0022	18.0	1296	1.3529	0.7944
0.0022	19.0	1368	1.3484	0.8084
0.0022	20.0	1440	1.3490	0.8084

Framework versions

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