sentiment-seq_bn-rf64-3

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: 0.3414
• Accuracy: 0.8546
• Precision: 0.8284
• Recall: 0.8146
• F1: 0.8210

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
0.5636	1.0	122	0.5152	0.7218	0.6550	0.6307	0.6380
0.5068	2.0	244	0.4980	0.7318	0.6828	0.6953	0.6877
0.4683	3.0	366	0.4659	0.7694	0.7222	0.7244	0.7232
0.4465	4.0	488	0.4401	0.7895	0.7462	0.7385	0.7421
0.4152	5.0	610	0.4214	0.8120	0.7729	0.7845	0.7781
0.3848	6.0	732	0.4166	0.8321	0.7961	0.8187	0.8053
0.3714	7.0	854	0.3987	0.8396	0.8206	0.7765	0.7932
0.3529	8.0	976	0.3900	0.8421	0.8272	0.7758	0.7945
0.3471	9.0	1098	0.3775	0.8521	0.8258	0.8104	0.8174
0.3335	10.0	1220	0.3722	0.8596	0.8325	0.8257	0.8290
0.3333	11.0	1342	0.3652	0.8546	0.8284	0.8146	0.8210
0.3171	12.0	1464	0.3616	0.8521	0.8247	0.8129	0.8184
0.2959	13.0	1586	0.3637	0.8571	0.8463	0.7964	0.8152
0.3177	14.0	1708	0.3496	0.8622	0.8385	0.8225	0.8298
0.2923	15.0	1830	0.3454	0.8596	0.8325	0.8257	0.8290
0.2887	16.0	1952	0.3454	0.8596	0.8325	0.8257	0.8290
0.2916	17.0	2074	0.3442	0.8596	0.8336	0.8232	0.8281
0.2937	18.0	2196	0.3433	0.8596	0.8336	0.8232	0.8281
0.2902	19.0	2318	0.3423	0.8521	0.8258	0.8104	0.8174
0.2928	20.0	2440	0.3414	0.8546	0.8284	0.8146	0.8210

Framework versions

• Transformers 4.40.2
• Pytorch 2.3.0+cu121
• Datasets 2.19.1
• Tokenizers 0.19.1