KoT5-summarization-mydata

This model is a fine-tuned version of psyche/KoT5-summarization on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.7827
• Rouge1 Precision: 0.5055
• Rouge1 Recall: 0.5287
• Rouge1 F1: 0.5102
• Rouge2 Precision: 0.3635
• Rouge2 Recall: 0.3790
• Rouge2 F1: 0.3660
• Rouge3 Precision: 0.2739
• Rouge3 Recall: 0.2852
• Rouge3 F1: 0.2753

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: 8e-06
• train_batch_size: 2
• eval_batch_size: 2
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 2

Training results

Training Loss	Epoch	Step	Validation Loss	Rouge1 Precision	Rouge1 Recall	Rouge1 F1	Rouge2 Precision	Rouge2 Recall	Rouge2 F1	Rouge3 Precision	Rouge3 Recall	Rouge3 F1
0.8855	1.0	34033	0.7909	0.5110	0.5294	0.5134	0.3681	0.3805	0.3691	0.2803	0.2892	0.2805
0.8206	2.0	68066	0.7827	0.5055	0.5287	0.5102	0.3635	0.3790	0.3660	0.2739	0.2852	0.2753

Framework versions

• Transformers 4.40.2
• Pytorch 2.8.0+cu128
• Datasets 2.19.0
• Tokenizers 0.19.1