Question_model_2data

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

• Loss: 2.5658
• Rouge1: 0.0429
• Rouge2: 0.0057
• Rougel: 0.0429
• Rougelsum: 0.0429
• Gen Len: 15.1213

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
3.3575	1.0	5704	2.6953	0.0388	0.0054	0.0387	0.0386	14.791
3.2388	2.0	11408	2.6126	0.0404	0.0052	0.0403	0.0403	14.9236
3.1827	3.0	17112	2.5780	0.0425	0.0055	0.0424	0.0424	14.9523
3.1688	4.0	22816	2.5658	0.0429	0.0057	0.0429	0.0429	15.1213

Framework versions

• Transformers 4.44.2
• Pytorch 2.4.1+cu121
• Datasets 3.1.0
• Tokenizers 0.19.1