bart-base-finetuned-xsum

This model is a fine-tuned version of facebook/bart-base on the xsum dataset. It achieves the following results on the evaluation set:

• Loss: 1.8584

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: 1
• eval_batch_size: 1
• seed: 42
• distributed_type: IPU
• gradient_accumulation_steps: 16
• total_train_batch_size: 64
• total_eval_batch_size: 24
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 1
• training precision: Mixed Precision

Training results

Training Loss	Epoch	Step	Validation Loss
2.1176	1.0	3188	1.8584

Framework versions

• Transformers 4.20.1
• Pytorch 1.13.0+cpu
• Datasets 2.8.0
• Tokenizers 0.12.1