mt5-small-finetuned-xlsum-ru-en-new-2

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: 2.0145
• Rouge1: 20.4759
• Rouge2: 6.8803
• Rougel: 16.8811
• Rougelsum: 16.915

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: 0.0004
• 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: 4

Training results

Training Loss	Epoch	Step	Validation Loss	Rouge1	Rouge2	Rougel	Rougelsum
2.8481	1.0	46096	2.2700	18.2746	5.3316	14.9101	14.9397
2.4194	2.0	92192	2.1316	19.6083	6.2946	16.1841	16.2019
2.2221	3.0	138288	2.0509	20.0895	6.5514	16.5405	16.5662
2.143	4.0	184384	2.0145	20.4759	6.8803	16.8811	16.915

Framework versions

• Transformers 4.38.2
• Pytorch 2.2.1+cu118
• Datasets 2.18.0
• Tokenizers 0.15.2