purpose-extraction / README.md
nazemi
End of training
5d8e7ae
|
raw
history blame
1.46 kB
metadata
license: apache-2.0
base_model: t5-large
tags:
  - generated_from_trainer
model-index:
  - name: purpose_extractor
    results: []

purpose_extractor

This model is a fine-tuned version of t5-large on an unknown dataset. It achieves the following results on the evaluation set:

  • Loss: 0.4141

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: 4
  • eval_batch_size: 4
  • seed: 42
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • num_epochs: 5

Training results

Training Loss Epoch Step Validation Loss
9.366 1.0 35 6.6269
1.7902 2.0 70 1.5461
0.9568 3.0 105 0.6312
0.6407 4.0 140 0.4544
1.5622 5.0 175 0.4141

Framework versions

  • Transformers 4.35.2
  • Pytorch 2.1.1
  • Datasets 2.15.0
  • Tokenizers 0.15.0