t5-pegasus-finetuned_test

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

• Loss: 6.0045
• Sacrebleu: 0.8737
• Rouge 1: 0.0237
• Rouge 2: 0.0
• Rouge L: 0.0232
• Bleu 1: 0.1444
• Bleu 2: 0.0447
• Bleu 3: 0.0175
• Bleu 4: 0.0083
• Meteor: 0.0609
• Gen Len: 15.098

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: 128
• eval_batch_size: 64
• seed: 42
• gradient_accumulation_steps: 2
• total_train_batch_size: 256
• 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

Training Loss	Epoch	Step	Validation Loss	Sacrebleu	Rouge 1	Rouge 2	Rouge L	Bleu 1	Bleu 2	Bleu 3	Bleu 4	Meteor	Gen Len
No log	52.5	210	5.9818	0.9114	0.0229	0.0	0.0225	0.1424	0.0436	0.0183	0.0091	0.06	15.126
No log	70.0	280	6.0072	0.876	0.0233	0.0	0.0228	0.1437	0.0452	0.0177	0.0083	0.0607	15.088
No log	87.5	350	6.0017	0.8695	0.0229	0.0	0.0225	0.1445	0.0443	0.0175	0.0082	0.0609	15.12

Framework versions

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