final_bart_prepro_fix

This model is a fine-tuned version of gogamza/kobart-base-v2 on the None dataset. It achieves the following results on the evaluation set:

• Loss: 2.6100
• Rouge1: 35.5593
• Rouge2: 13.0497
• Rougel: 23.5672
• Bleu1: 29.5206
• Bleu2: 17.3914
• Bleu3: 10.5577
• Bleu4: 6.1502
• Rdass: 0.6449
• Gen Len: 49.7389

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: 3e-05
• train_batch_size: 64
• eval_batch_size: 64
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_ratio: 0.1
• num_epochs: 5.0

Training results

Training Loss	Epoch	Step	Validation Loss	Rouge1	Rouge2	Rougel	Bleu1	Bleu2	Bleu3	Bleu4	Rdass	Gen Len
2.1622	1.51	1000	2.6687	35.4366	12.8631	23.1588	29.4018	17.2004	10.3744	6.052	0.6379	49.4266
2.0114	3.02	2000	2.6090	35.1436	13.0347	23.4682	28.8917	17.0965	10.1873	5.896	0.6389	46.1096
1.8758	4.53	3000	2.6100	35.5593	13.0497	23.5672	29.5206	17.3914	10.5577	6.1502	0.6449	49.7389

Framework versions

• Transformers 4.25.1
• Pytorch 1.13.1+cu117
• Datasets 2.7.1
• Tokenizers 0.13.2