bart_updown_sp / README.md
ammonbro's picture
End of training
79e85d8 verified
metadata
library_name: transformers
license: apache-2.0
base_model: facebook/bart-base
tags:
  - generated_from_trainer
model-index:
  - name: bart_updown_sp
    results: []

bart_updown_sp

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: 0.0

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: 8
  • eval_batch_size: 8
  • seed: 42
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • num_epochs: 10

Training results

Training Loss Epoch Step Validation Loss
0.0 1.0 1429 0.0000
0.0 2.0 2858 0.0000
0.0 3.0 4287 0.0000
0.0 4.0 5716 0.0000
0.0 5.0 7145 0.0
0.0 6.0 8574 0.0
0.0 7.0 10003 0.0
0.0 8.0 11432 0.0
0.0 9.0 12861 0.0
0.0 10.0 14290 0.0

Framework versions

  • Transformers 4.45.2
  • Pytorch 2.4.1+cu121
  • Datasets 3.0.1
  • Tokenizers 0.20.1