sentiment-lora-r2a2d0.1-0

This model is a fine-tuned version of indolem/indobert-base-uncased on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.3608
• Accuracy: 0.8471
• Precision: 0.8138
• Recall: 0.8243
• F1: 0.8187

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: 30
• eval_batch_size: 8
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 20.0

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	Precision	Recall	F1
0.5634	1.0	122	0.5108	0.7193	0.6572	0.6489	0.6524
0.5081	2.0	244	0.5049	0.7218	0.6829	0.7082	0.6888
0.4924	3.0	366	0.4667	0.7494	0.6977	0.6977	0.6977
0.4698	4.0	488	0.4392	0.7794	0.7349	0.7114	0.7207
0.4519	5.0	610	0.4548	0.7469	0.7169	0.7534	0.7226
0.4356	6.0	732	0.4111	0.8145	0.7770	0.7713	0.7740
0.421	7.0	854	0.4101	0.7945	0.7538	0.7721	0.7612
0.4039	8.0	976	0.3829	0.8296	0.7949	0.7919	0.7934
0.3887	9.0	1098	0.3800	0.8321	0.7972	0.7987	0.7979
0.3797	10.0	1220	0.3768	0.8371	0.8044	0.7997	0.8020
0.368	11.0	1342	0.3842	0.8221	0.7846	0.8016	0.7918
0.3598	12.0	1464	0.3778	0.8271	0.7902	0.8051	0.7968
0.3548	13.0	1586	0.3624	0.8471	0.8167	0.8118	0.8142
0.3469	14.0	1708	0.3637	0.8446	0.8120	0.8151	0.8135
0.3431	15.0	1830	0.3685	0.8396	0.8049	0.8165	0.8102
0.3275	16.0	1952	0.3664	0.8371	0.8017	0.8172	0.8086
0.3288	17.0	2074	0.3590	0.8396	0.8055	0.8115	0.8084
0.3335	18.0	2196	0.3607	0.8471	0.8138	0.8243	0.8187
0.3239	19.0	2318	0.3613	0.8446	0.8107	0.8226	0.8161
0.327	20.0	2440	0.3608	0.8471	0.8138	0.8243	0.8187

Framework versions

• Transformers 4.39.3
• Pytorch 2.3.0+cu121
• Datasets 2.19.1
• Tokenizers 0.15.2