baek26's picture
Model save
5835480 verified
metadata
license: apache-2.0
base_model: facebook/bart-base
tags:
  - generated_from_trainer
metrics:
  - rouge
model-index:
  - name: wiki_asp-educational_institution_8330_bart-base
    results: []

wiki_asp-educational_institution_8330_bart-base

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

  • Loss: 2.6483
  • Rouge1: 0.1554
  • Rouge2: 0.0598
  • Rougel: 0.1308
  • Rougelsum: 0.1308
  • Gen Len: 19.1331

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: 4
  • eval_batch_size: 4
  • seed: 42
  • gradient_accumulation_steps: 16
  • total_train_batch_size: 64
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • lr_scheduler_warmup_steps: 500
  • num_epochs: 10

Training results

Training Loss Epoch Step Validation Loss Rouge1 Rouge2 Rougel Rougelsum Gen Len
No log 1.81 500 2.8696 0.1509 0.054 0.1261 0.126 19.2999
No log 3.63 1000 2.7162 0.1551 0.0574 0.1292 0.1293 19.1107
No log 5.44 1500 2.6720 0.154 0.0588 0.1297 0.1295 19.071
2.9542 7.26 2000 2.6582 0.1564 0.0602 0.1312 0.1312 19.1116
2.9542 9.07 2500 2.6483 0.1554 0.0598 0.1308 0.1308 19.1331

Framework versions

  • Transformers 4.38.2
  • Pytorch 2.0.0+cu117
  • Datasets 2.18.0
  • Tokenizers 0.15.2