sentiment-lora-r16

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: 0.2631
• Accuracy: 0.8872
• Precision: 0.8658
• Recall: 0.8602
• F1: 0.8629

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
0.5544	1.0	122	0.5252	0.7218	0.6705	0.6807	0.6746
0.4974	2.0	244	0.4521	0.7845	0.7792	0.6650	0.6840
0.4206	3.0	366	0.3642	0.8296	0.8034	0.7694	0.7829
0.3657	4.0	488	0.3376	0.8471	0.8184	0.8068	0.8122
0.3188	5.0	610	0.3198	0.8496	0.8202	0.8136	0.8167
0.3069	6.0	732	0.3127	0.8546	0.8239	0.8272	0.8255
0.2838	7.0	854	0.3053	0.8672	0.8449	0.8285	0.8360
0.2699	8.0	976	0.2976	0.8747	0.8647	0.8238	0.8404
0.2614	9.0	1098	0.2887	0.8647	0.8398	0.8292	0.8342
0.2515	10.0	1220	0.2852	0.8596	0.8316	0.8282	0.8298
0.2453	11.0	1342	0.2800	0.8697	0.8411	0.8478	0.8443
0.236	12.0	1464	0.2718	0.8797	0.8633	0.8399	0.8502
0.227	13.0	1586	0.2712	0.8797	0.8560	0.8524	0.8541
0.227	14.0	1708	0.2757	0.8697	0.8386	0.8603	0.8479
0.2171	15.0	1830	0.2708	0.8822	0.8530	0.8742	0.8622
0.214	16.0	1952	0.2632	0.8872	0.8658	0.8602	0.8629
0.2124	17.0	2074	0.2639	0.8822	0.8574	0.8592	0.8583
0.2166	18.0	2196	0.2632	0.8872	0.8645	0.8627	0.8636
0.2086	19.0	2318	0.2630	0.8822	0.8585	0.8567	0.8575
0.2113	20.0	2440	0.2631	0.8872	0.8658	0.8602	0.8629

Framework versions

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