t5-rebuilder

This model is a fine-tuned version of ai-forever/ruT5-base on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.1184
• Bleu: 94.1519
• Chrf: 97.4152
• Gen Len: 13.3872

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: 0.0003
• 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
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Bleu	Chrf	Gen Len
0.2957	1.0	3832	0.1915	87.926	94.6246	13.3604
0.1356	2.0	7664	0.1307	92.8051	96.7011	13.3754
0.0626	3.0	11496	0.1184	94.1519	97.4152	13.3872

Framework versions

• Transformers 4.39.3
• Pytorch 2.1.2
• Datasets 2.18.0
• Tokenizers 0.15.2