mt5-small-km-phoneme-reverse

This model is a fine-tuned version of google/mt5-small on the None dataset. It achieves the following results on the evaluation set:

• Loss: 1.2416
• Rouge1: 30.9064
• Rouge2: 15.5474
• Rougel: 30.6746
• Rougelsum: 30.691
• Gen Len: 4.8282

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: 5e-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: 3

Training results

Training Loss	Epoch	Step	Validation Loss	Rouge1	Rouge2	Rougel	Rougelsum	Gen Len
1.6872	1.0	2515	1.3202	28.8555	13.7602	28.6841	28.7043	4.6996
1.5052	2.0	5030	1.2561	30.5921	15.3773	30.3685	30.3818	4.8390
1.5144	3.0	7545	1.2416	30.9064	15.5474	30.6746	30.691	4.8282

Framework versions

• Transformers 4.28.1
• Pytorch 2.0.0+cu117
• Datasets 2.11.0
• Tokenizers 0.13.3