t5-russian-spell

This model is a fine-tuned version of UrukHan/t5-russian-spell on the None dataset. It achieves the following results on the evaluation set:

• Loss: 7.9129
• Rouge1: 0.1767
• Rouge2: 0.0
• Rougel: 0.1783
• Rougelsum: 0.1774
• Gen Len: 198.0413

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: 10
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Rouge1	Rouge2	Rougel	Rougelsum	Gen Len
7.8172	9.01	5000	7.9129	0.1767	0.0	0.1783	0.1774	198.0413

Framework versions

• Transformers 4.35.2
• Pytorch 2.1.0+cu121
• Datasets 2.15.0
• Tokenizers 0.15.0