sentiment-lora-r8a1d0.2-0

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: 0.3274
• Accuracy: 0.8622
• Precision: 0.8319
• Recall: 0.8400
• F1: 0.8357

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
0.5608	1.0	122	0.5057	0.7218	0.6593	0.6482	0.6527
0.5012	2.0	244	0.4792	0.7519	0.7117	0.7370	0.7193
0.4628	3.0	366	0.4281	0.7694	0.7256	0.7419	0.7321
0.4045	4.0	488	0.3951	0.8170	0.7803	0.7730	0.7765
0.3701	5.0	610	0.4239	0.7995	0.7633	0.7956	0.7736
0.3362	6.0	732	0.3721	0.8296	0.7934	0.8019	0.7974
0.3285	7.0	854	0.3725	0.8346	0.7989	0.8205	0.8078
0.3061	8.0	976	0.3537	0.8421	0.8087	0.8133	0.8109
0.3017	9.0	1098	0.3504	0.8421	0.8087	0.8133	0.8109
0.2942	10.0	1220	0.3391	0.8496	0.8186	0.8186	0.8186
0.2715	11.0	1342	0.3456	0.8496	0.8169	0.8261	0.8212
0.2703	12.0	1464	0.3534	0.8521	0.8190	0.8354	0.8262
0.2759	13.0	1586	0.3326	0.8521	0.8228	0.8179	0.8203
0.2705	14.0	1708	0.3360	0.8571	0.8266	0.8314	0.8289
0.2576	15.0	1830	0.3423	0.8647	0.8340	0.8467	0.8399
0.2513	16.0	1952	0.3394	0.8571	0.8251	0.8389	0.8314
0.2481	17.0	2074	0.3261	0.8571	0.8273	0.8289	0.8281
0.2561	18.0	2196	0.3320	0.8622	0.8314	0.8425	0.8365
0.2478	19.0	2318	0.3269	0.8622	0.8326	0.8375	0.8349
0.2451	20.0	2440	0.3274	0.8622	0.8319	0.8400	0.8357

Framework versions

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