t5-rebuilder-v2

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

• Loss: 0.2206
• Bleu: 86.0134
• Chrf: 93.6573
• Gen Len: 13.4007

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
0.4463	1.0	4321	0.3205	78.6613	90.2004	13.2967
0.24	2.0	8642	0.2379	84.2763	92.7898	13.394
0.118	3.0	12963	0.2206	86.0134	93.6573	13.4007

Framework versions

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