pretrain_Law_model_bartpho_version2

This model is a fine-tuned version of KingLTD/pretrain_Law_model_bartpho_version1 on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.1794
• Rouge1: 0.4739
• Rouge2: 0.3818
• Rougel: 0.4294
• Rougelsum: 0.4408

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: 2e-05
• train_batch_size: 8
• eval_batch_size: 8
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 10

Training results

Training Loss	Epoch	Step	Validation Loss	Rouge1	Rouge2	Rougel	Rougelsum
No log	1.0	245	0.1490	0.4706	0.3710	0.4217	0.4344
No log	2.0	490	0.1537	0.4694	0.3706	0.4215	0.4338
0.1737	3.0	735	0.1585	0.4705	0.3757	0.4244	0.4366
0.1737	4.0	980	0.1606	0.4694	0.3701	0.4221	0.4349
0.122	5.0	1225	0.1665	0.4702	0.3746	0.4237	0.4357
0.122	6.0	1470	0.1685	0.4726	0.3772	0.4259	0.4363
0.089	7.0	1715	0.1744	0.4747	0.3795	0.4291	0.4409
0.089	8.0	1960	0.1753	0.4742	0.3823	0.4296	0.4410
0.0698	9.0	2205	0.1791	0.4759	0.3838	0.4303	0.4417
0.0698	10.0	2450	0.1794	0.4739	0.3818	0.4294	0.4408

Framework versions

• Transformers 4.32.1
• Pytorch 2.0.1+cu118
• Datasets 2.14.4
• Tokenizers 0.13.3