InfinityC's picture
End of training
f5807e2 verified
metadata
license: apache-2.0
base_model: facebook/bart-base
tags:
  - generated_from_trainer
metrics:
  - rouge
model-index:
  - name: test_sum_abs_bart-base_interpret_stops
    results: []

test_sum_abs_bart-base_interpret_stops

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: 3.2138
  • Rouge1: 0.1463
  • Rouge2: 0.033
  • Rougel: 0.1107
  • Rougelsum: 0.1107
  • Gen Len: 20.0

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: 2e-05
  • train_batch_size: 16
  • eval_batch_size: 16
  • seed: 42
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • num_epochs: 4
  • mixed_precision_training: Native AMP

Training results

Training Loss Epoch Step Validation Loss Rouge1 Rouge2 Rougel Rougelsum Gen Len
3.5259 1.0 3109 3.2984 0.1437 0.0332 0.1086 0.1086 20.0
3.4331 2.0 6218 3.2446 0.1464 0.0329 0.1107 0.1108 20.0
3.3512 3.0 9327 3.2226 0.146 0.0325 0.1105 0.1105 20.0
3.319 4.0 12436 3.2138 0.1463 0.033 0.1107 0.1107 20.0

Framework versions

  • Transformers 4.39.3
  • Pytorch 2.1.2
  • Datasets 2.18.0
  • Tokenizers 0.15.2