t5-base-dutch-new_finetuned-mt5_nl_large_data

This model is a fine-tuned version of yhavinga/t5-base-dutch on an unknown dataset. It achieves the following results on the evaluation set:

• eval_loss: 0.4797
• eval_rouge1: 0.7735
• eval_rouge2: 0.6122
• eval_rougeL: 0.7616
• eval_rougeLsum: 0.7619
• eval_runtime: 158.5338
• eval_samples_per_second: 5.746
• eval_steps_per_second: 0.416
• epoch: 5.0
• step: 875

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: 5.6e-05
• train_batch_size: 14
• eval_batch_size: 14
• seed: 42
• gradient_accumulation_steps: 2
• total_train_batch_size: 28
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 20

Framework versions

• Transformers 4.38.1
• Pytorch 2.1.0+cu121
• Datasets 2.17.1
• Tokenizers 0.15.2