results

This model is a fine-tuned version of csebuetnlp/mT5_multilingual_XLSum on the None dataset. It achieves the following results on the evaluation set:

• Loss: 1.9889
• Rouge1: 37.6658
• Rouge2: 25.8954
• Rougel: 30.7965
• Rougelsum: 30.7895

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: 2e-05
• train_batch_size: 2
• eval_batch_size: 8
• seed: 42
• gradient_accumulation_steps: 8
• total_train_batch_size: 16
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 3

Training results

Training Loss	Epoch	Step	Validation Loss	Rouge1	Rouge2	Rougel	Rougelsum
2.8494	0.9888	55	2.2040	35.3021	24.7331	29.5323	29.5469
2.3422	1.9955	111	2.0275	37.3011	25.7964	30.7416	30.7363
2.2332	2.9663	165	1.9889	37.6658	25.8954	30.7965	30.7895

Framework versions

• Transformers 4.41.0
• Pytorch 2.3.0+cu121
• Datasets 2.19.1
• Tokenizers 0.19.1