CMSC_473_t5_ja

This model is a fine-tuned version of google-t5/t5-small on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 3.4437
• Bleu: 1.4633
• Gen Len: 13.1495

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: 0.0001
• train_batch_size: 32
• eval_batch_size: 32
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 3

Training results

Training Loss	Epoch	Step	Validation Loss	Bleu	Gen Len
3.5392	1.0	3125	3.4776	1.478	13.0325
3.4769	2.0	6250	3.4510	1.2928	9.9785
3.4403	3.0	9375	3.4437	1.4633	13.1495

Framework versions

• Transformers 4.40.1
• Pytorch 2.2.1+cu121
• Datasets 2.19.1
• Tokenizers 0.19.1