Led-pubmed-20K-4096 / README.md
LA1512's picture
LA1512/led-pubmed-20K-4096
36876ec verified
metadata
license: bsd-3-clause
base_model: pszemraj/led-base-book-summary
tags:
  - generated_from_trainer
model-index:
  - name: results
    results: []

results

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

  • Loss: 3.2228

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: 2
  • eval_batch_size: 2
  • seed: 42
  • gradient_accumulation_steps: 8
  • total_train_batch_size: 16
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • lr_scheduler_warmup_steps: 500
  • num_epochs: 1
  • label_smoothing_factor: 0.1

Training results

Training Loss Epoch Step Validation Loss
3.7096 0.16 200 3.5407
3.4734 0.32 400 3.3909
3.3782 0.48 600 3.3248
3.3413 0.64 800 3.2736
3.3193 0.8 1000 3.2507
3.4481 0.96 1200 3.2228

Framework versions

  • Transformers 4.39.3
  • Pytorch 2.1.2
  • Datasets 2.18.0
  • Tokenizers 0.15.2