kobart_32_3e-5_datav2_min30_lp5.0_temperature1.0

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: 2.5958
• Rouge1: 35.6403
• Rouge2: 13.1314
• Rougel: 23.8946
• Bleu1: 29.625
• Bleu2: 17.4903
• Bleu3: 10.6018
• Bleu4: 6.0498
• Gen Len: 50.697

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: 32
• eval_batch_size: 128
• 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	Gen Len
1.8239	3.78	5000	2.5958	35.6403	13.1314	23.8946	29.625	17.4903	10.6018	6.0498	50.697

Framework versions

• Transformers 4.25.1
• Pytorch 1.13.0+cu117
• Datasets 2.7.1
• Tokenizers 0.13.2