Hugging Face's logo

GlycerinLOL
/
LLM_Teach_Bart

Text2Text Generation
Transformers
TensorBoard
Safetensors
bart
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
LLM_Teach_Bart / README.md
GlycerinLOL's picture
GlycerinLOL
End of training
a50b472
preview code
|
raw
history blame
1.89 kB
metadata
license: mit
base_model: facebook/bart-large-xsum
tags:
  - generated_from_trainer
metrics:
  - rouge
model-index:
  - name: LLM_Teach_Bart
    results: []

LLM_Teach_Bart

This model is a fine-tuned version of facebook/bart-large-xsum on an unknown dataset. It achieves the following results on the evaluation set:

  • Loss: 1.5031
  • Rouge1: 0.4864
  • Rouge2: 0.2544
  • Rougel: 0.3759
  • Rougelsum: 0.3762
  • Gen Len: 46.2273

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: 8
  • 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
1.3272 1.0 625 1.3454 0.4901 0.2571 0.3725 0.3724 51.3691
0.9972 2.0 1250 1.3446 0.4857 0.2598 0.3755 0.3759 46.5909
0.8102 3.0 1875 1.4353 0.4881 0.256 0.3754 0.3755 47.3073
0.5636 4.0 2500 1.5031 0.4864 0.2544 0.3759 0.3762 46.2273

Framework versions

  • Transformers 4.36.0
  • Pytorch 2.0.1+cu117
  • Datasets 2.14.5
  • Tokenizers 0.15.0