speller-example__

This model is a fine-tuned version of sberbank-ai/ruT5-base on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.1437
• Rouge1: 19.7034
• Rouge2: 8.7571
• Rougel: 19.4209
• Rougelsum: 19.774
• Gen Len: 41.2542

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: 8
• eval_batch_size: 8
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 1
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Rouge1	Rouge2	Rougel	Rougelsum	Gen Len
0.3549	0.1	1500	0.1935	19.7034	8.7571	19.4209	19.774	41.1356
0.3863	0.2	3000	0.1830	19.7034	8.7571	19.4209	19.774	41.1864
0.3164	0.31	4500	0.1746	19.5621	8.4746	19.2797	19.5621	41.2966
0.367	0.41	6000	0.1690	19.7034	8.7571	19.4209	19.774	41.161
0.3002	0.51	7500	0.1578	19.7034	8.7571	19.4209	19.774	41.2458
0.3352	0.61	9000	0.1541	19.7034	8.7571	19.4209	19.774	41.3475
0.2462	0.72	10500	0.1519	19.7034	8.7571	19.4209	19.774	41.3475
0.2736	0.82	12000	0.1510	19.7034	8.7571	19.4209	19.774	41.2797
0.2618	0.92	13500	0.1437	19.7034	8.7571	19.4209	19.774	41.2542

Framework versions

• Transformers 4.26.0
• Pytorch 1.13.1+cu116
• Datasets 2.9.0
• Tokenizers 0.13.2