Hugging Face's logo

eglkan1
/
mBART-TextSimp-LT-BatchSize2-lr1e-4

Text2Text Generation
Transformers
PyTorch
mbart
Generated from Trainer
Inference Endpoints
Model card Files Community
mBART-TextSimp-LT-BatchSize2-lr1e-4 / README.md
eglkan1's picture
eglkan1
End of training
bfee852 verified
preview code
|
raw
history blame
1.5 kB
metadata
license: mit
base_model: facebook/mbart-large-50
tags:
  - generated_from_trainer
model-index:
  - name: mBART-TextSimp-LT-BatchSize4-lr1e-4
    results: []

mBART-TextSimp-LT-BatchSize4-lr1e-4

This model is a fine-tuned version of facebook/mbart-large-50 on the None dataset.

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: 0.0001
  • train_batch_size: 2
  • eval_batch_size: 2
  • seed: 42
  • gradient_accumulation_steps: 2
  • total_train_batch_size: 4
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • lr_scheduler_warmup_steps: 500
  • num_epochs: 1

Training results

Training Loss Epoch Step Validation Loss Rouge1 Rouge2 Rougel Sacrebleu Gen Len
No log 1.0 418 0.0891 0.6619 0.4917 0.6516 38.2708 34.2792

Framework versions

  • Transformers 4.33.0
  • Pytorch 2.1.2+cu121
  • Datasets 2.14.4
  • Tokenizers 0.13.3