RL-20k-epoch1 / README.md
gianghoang's picture
Update README.md
d446627 verified
metadata
license: bsd-3-clause
base_model: LA1512/Led-pubmed-20K-4096-epoch2
tags:
  - generated_from_trainer
metrics:
  - rouge
model-index:
  - name: RL-20k-epoch1
    results: []

results

This model is a fine-tuned version of LA1512/Led-pubmed-20K-4096-epoch2 on an unknown dataset. It achieves the following results on the evaluation set:

  • Loss: 3.3315
  • Rouge1: 43.8629
  • Rouge2: 14.6606
  • Rougel: 21.757
  • Rougelsum: 38.2488
  • Gen Len: 304.884

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: 2
  • eval_batch_size: 1
  • seed: 42
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • lr_scheduler_warmup_steps: 500
  • num_epochs: 1
  • label_smoothing_factor: 0.1

Training results

Framework versions

  • Transformers 4.41.1
  • Pytorch 2.1.2
  • Datasets 2.19.1
  • Tokenizers 0.19.1