Alfahluzi/indobert-summarization-bert2bert

bert2bert-model99-last

This model is a fine-tuned version of on the id_liputan6 dataset. It achieves the following results on the evaluation set:

• Loss: 2.8701
• R1 Precision: 0.3001
• R1 Recall: 0.34
• R1 Fmeasure: 0.3156
• R2 Precision: 0.121
• R2 Recall: 0.1366
• R2 Fmeasure: 0.1269
• Rl Precision: 0.239
• Rl Recall: 0.2707
• Rl Fmeasure: 0.2513

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: 18
• eval_batch_size: 18
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 8
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	R1 Precision	R1 Recall	R1 Fmeasure	R2 Precision	R2 Recall	R2 Fmeasure	Rl Precision	Rl Recall	Rl Fmeasure
2.3429	1.0	10772	2.7616	0.29	0.3334	0.3069	0.1175	0.1351	0.1243	0.2329	0.2678	0.2464
1.5227	2.0	21544	2.6637	0.287	0.3356	0.3062	0.1148	0.1338	0.1222	0.2304	0.2693	0.2457
1.3203	3.0	32316	2.6384	0.2934	0.3387	0.3111	0.1195	0.1377	0.1265	0.2355	0.272	0.2498
1.169	4.0	43088	2.6579	0.3004	0.3403	0.3158	0.1228	0.139	0.129	0.2407	0.2726	0.253
1.0416	5.0	53860	2.6894	0.2963	0.3367	0.3121	0.1202	0.1362	0.1264	0.2367	0.2691	0.2494
0.9303	6.0	64632	2.7418	0.2986	0.3417	0.3155	0.1213	0.1384	0.1279	0.2385	0.2727	0.2519
0.8375	7.0	75404	2.8060	0.3009	0.3417	0.3168	0.1223	0.1384	0.1285	0.2402	0.2727	0.2528
0.7675	8.0	86176	2.8701	0.3001	0.34	0.3156	0.121	0.1366	0.1269	0.239	0.2707	0.2513

Framework versions

• Transformers 4.40.0
• Pytorch 2.2.1
• Datasets 2.19.0
• Tokenizers 0.19.1