Megagon_step3_p1atdev

This model is a fine-tuned version of p1atdev/t5-base-xlsum-ja on the None dataset. It achieves the following results on the evaluation set:

• Loss: 1.2045
• Rouge1: 0.2598
• Rouge2: 0.1099
• Rougel: 0.2579
• Rougelsum: 0.2576
• Gen Len: 10.5676

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: 16
• eval_batch_size: 16
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 4

Training results

Training Loss	Epoch	Step	Validation Loss	Rouge1	Rouge2	Rougel	Rougelsum	Gen Len
No log	1.0	79	2.2677	0.3223	0.1811	0.3225	0.3203	11.4505
No log	2.0	158	1.4330	0.3084	0.1628	0.3087	0.3067	11.1802
No log	3.0	237	1.2345	0.2672	0.1156	0.2652	0.2644	10.6081
No log	4.0	316	1.2045	0.2598	0.1099	0.2579	0.2576	10.5676

Framework versions

• Transformers 4.34.0
• Pytorch 2.0.1+cu118
• Datasets 2.14.5
• Tokenizers 0.14.1