Hugging Face's logo

gayanin
/
pubmed-abs-sub-01

Text2Text Generation
Transformers
PyTorch
bart
Generated from Trainer
Inference Endpoints
Model card Files Community
pubmed-abs-sub-01 / README.md
gayanin's picture
gayanin
End of training
88a7b3b
preview code
|
raw
history blame contribute delete
2.72 kB
metadata
license: apache-2.0
base_model: facebook/bart-base
tags:
  - generated_from_trainer
model-index:
  - name: pubmed-abs-sub-01
    results: []

pubmed-abs-sub-01

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

  • Loss: 0.0931

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: 5e-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
  • lr_scheduler_warmup_steps: 10
  • num_epochs: 3

Training results

Training Loss Epoch Step Validation Loss
0.2288 0.11 500 0.1670
0.1744 0.21 1000 0.1545
0.1726 0.32 1500 0.1341
0.1622 0.43 2000 0.1329
0.1382 0.54 2500 0.1289
0.1322 0.64 3000 0.1184
0.1288 0.75 3500 0.1182
0.1304 0.86 4000 0.1088
0.1255 0.96 4500 0.1068
0.1039 1.07 5000 0.1093
0.0969 1.18 5500 0.1060
0.1001 1.28 6000 0.1087
0.0966 1.39 6500 0.1027
0.101 1.5 7000 0.0999
0.0851 1.61 7500 0.1010
0.1068 1.71 8000 0.1021
0.1024 1.82 8500 0.0966
0.0852 1.93 9000 0.0962
0.0688 2.03 9500 0.0967
0.0791 2.14 10000 0.0987
0.0606 2.25 10500 0.0978
0.0732 2.35 11000 0.0963
0.0758 2.46 11500 0.0951
0.0765 2.57 12000 0.0945
0.0671 2.68 12500 0.0932
0.0422 2.78 13000 0.0936
0.0493 2.89 13500 0.0942
0.0542 3.0 14000 0.0931

Framework versions

  • Transformers 4.34.1
  • Pytorch 2.1.0
  • Datasets 2.14.6
  • Tokenizers 0.14.1