mt5-small-km-phoneme

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: 0.5647
• Rouge1: 86.1261
• Rouge2: 75.069
• Rougel: 85.8365
• Rougelsum: 85.8199
• Gen Len: 9.4504

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
1.0708	1.0	2514	0.7873	81.0997	66.3068	80.6177	80.6219	9.3808
0.8576	2.0	5028	0.6091	85.158	73.3987	84.8532	84.8374	9.4117
0.813	3.0	7542	0.5647	86.1261	75.069	85.8365	85.8199	9.4504

Framework versions

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