t5-pegasus-finetuned

This model was trained from scratch on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 4.8469
• Sacrebleu: 1.6544
• Rouge 1: 0.0646
• Rouge 2: 0.0076
• Rouge L: 0.0629
• Bleu 1: 0.2040
• Bleu 2: 0.0959
• Bleu 3: 0.0484
• Bleu 4: 0.0287
• Meteor: 0.0872
• Gen Len: 16.0997

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: 5e-05
• train_batch_size: 512
• eval_batch_size: 256
• seed: 42
• gradient_accumulation_steps: 2
• total_train_batch_size: 1024
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 100
• mixed_precision_training: Native AMP

Training results

Framework versions

• Transformers 4.21.0.dev0
• Pytorch 1.9.1+cu102
• Datasets 2.3.2
• Tokenizers 0.12.1