Edit model card

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
Downloads last month
0
Safetensors
Model size
139M params
Tensor type
F32
·

Finetuned from