Edit model card

pegasus-x-base_readme_summarization

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

  • Loss: 2.1283
  • Rouge1: 0.4524
  • Rouge2: 0.3245
  • Rougel: 0.4254
  • Rougelsum: 0.4258
  • Gen Len: 52.0983

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
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • num_epochs: 4

Training results

Training Loss Epoch Step Validation Loss Rouge1 Rouge2 Rougel Rougelsum Gen Len
2.4802 1.0 5831 2.2968 0.4311 0.302 0.4037 0.4031 57.5564
2.245 2.0 11662 2.1924 0.455 0.3252 0.4263 0.4261 52.2794
2.0892 3.0 17493 2.1347 0.4578 0.3294 0.4306 0.4305 53.9041
1.9962 4.0 23324 2.1283 0.4524 0.3245 0.4254 0.4258 52.0983

Framework versions

  • Transformers 4.35.1
  • Pytorch 2.1.0+cu121
  • Datasets 2.14.6
  • Tokenizers 0.14.1
Downloads last month
7
Safetensors
Model size
272M params
Tensor type
F32
·

Finetuned from