kobart_32_6e-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: 2.6110
• Rouge1: 35.8879
• Rouge2: 12.9302
• Rougel: 23.7819
• Bleu1: 30.0048
• Bleu2: 17.5297
• Bleu3: 10.3153
• Bleu4: 5.9092
• Gen Len: 50.8508

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: 6e-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
1.5664	3.78	5000	2.6110	35.8879	12.9302	23.7819	30.0048	17.5297	10.3153	5.9092	50.8508

Framework versions

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