Megagon_step3

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: 1.1857
• Rouge1: 0.2252
• Rouge2: 0.0901
• Rougel: 0.2243
• Rougelsum: 0.2239
• Gen Len: 10.8153

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	2.2342	0.2695	0.1327	0.2702	0.2686	11.036
No log	2.0	158	1.3641	0.267	0.1222	0.2674	0.2634	10.9775
No log	3.0	237	1.2064	0.2307	0.099	0.2297	0.229	10.9324
No log	4.0	316	1.1857	0.2252	0.0901	0.2243	0.2239	10.8153

Framework versions

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