LA1512's picture
LA1512/led-pubmed-20K-4096-epoch-2
17576de verified
metadata
license: bsd-3-clause
base_model: LA1512/Led-pubmed-20K-4096-v2
tags:
  - generated_from_trainer
model-index:
  - name: results
    results: []

results

This model is a fine-tuned version of LA1512/Led-pubmed-20K-4096-v2 on an unknown dataset. It achieves the following results on the evaluation set:

  • Loss: 3.4248

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: 3e-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: 400
  • num_epochs: 1
  • label_smoothing_factor: 0.1

Training results

Training Loss Epoch Step Validation Loss
3.4638 0.16 200 3.4713
3.3407 0.32 400 3.4833
3.2799 0.48 600 3.4805
3.3883 0.64 800 3.4563
3.3559 0.8 1000 3.4350
3.4671 0.96 1200 3.4248

Framework versions

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