AptaArkana/indonesian_sentiment_distilbert_base_cased

sentiment2

This model is a fine-tuned version of lxyuan/distilbert-base-multilingual-cased-sentiments-student on the indonlu dataset. It achieves the following results on the evaluation set:

• Loss: 0.6085
• Accuracy: 0.9151
• Precision: 0.9153
• Recall: 0.9151
• F1: 0.9150

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: 5e-05
• train_batch_size: 40
• eval_batch_size: 40
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_ratio: 0.01
• num_epochs: 10

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	Precision	Recall	F1
No log	1.0	275	0.2543	0.9190	0.9213	0.9190	0.9196
0.2191	2.0	550	0.2710	0.9143	0.9133	0.9143	0.9134
0.2191	3.0	825	0.3715	0.9135	0.9144	0.9135	0.9114
0.0714	4.0	1100	0.4751	0.9071	0.9085	0.9071	0.9077
0.0714	5.0	1375	0.4859	0.9206	0.9214	0.9206	0.9203
0.0263	6.0	1650	0.5383	0.9143	0.9155	0.9143	0.9143
0.0263	7.0	1925	0.5630	0.9167	0.9166	0.9167	0.9165
0.0126	8.0	2200	0.5916	0.9151	0.9151	0.9151	0.9146
0.0126	9.0	2475	0.6073	0.9135	0.9130	0.9135	0.9131
0.0056	10.0	2750	0.6085	0.9151	0.9153	0.9151	0.9150

Framework versions

• Transformers 4.35.2
• Pytorch 2.1.0+cu121
• Datasets 2.17.1
• Tokenizers 0.15.2