anantoj's picture
commit files to HF hub
2d34e7b
metadata
license: apache-2.0
tags:
  - generated_from_trainer
model-index:
  - name: T5-summarizer-simple-wiki-v2
    results: []

T5-summarizer-simple-wiki-v2

This model is a fine-tuned version of t5-small on the None dataset. It achieves the following results on the evaluation set:

  • Loss: 2.0866

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: 16
  • seed: 42
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • num_epochs: 3
  • mixed_precision_training: Native AMP

Training results

Training Loss Epoch Step Validation Loss
2.2575 1.0 14719 2.1173
2.2663 2.0 29438 2.0926
2.2092 3.0 44157 2.0866

Framework versions

  • Transformers 4.19.4
  • Pytorch 1.11.0
  • Datasets 2.3.2
  • Tokenizers 0.12.1