Edit model card

bart-base

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

  • Loss: 0.2383
  • Rouge1: 43.8254
  • Rouge2: 20.1579
  • Rougel: 36.9652
  • Rougelsum: 39.6438
  • Gen Len: 18.0

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: 1e-05
  • train_batch_size: 4
  • eval_batch_size: 4
  • seed: 42
  • gradient_accumulation_steps: 2
  • total_train_batch_size: 8
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • num_epochs: 2

Training results

Training Loss Epoch Step Validation Loss Rouge1 Rouge2 Rougel Rougelsum Gen Len
0.2152 1.0 4632 0.2446 43.1632 19.3357 36.1382 38.8081 18.0
0.1758 2.0 9264 0.2383 43.8254 20.1579 36.9652 39.6438 18.0

Framework versions

  • Transformers 4.36.1
  • Pytorch 2.1.2
  • Datasets 2.20.0
  • Tokenizers 0.15.2
Downloads last month
0
Safetensors
Model size
139M params
Tensor type
F32
·

Finetuned from