htriedman's picture
Model save
cce4f1f
metadata
license: apache-2.0
tags:
  - generated_from_trainer
model-index:
  - name: flan-t5-base-finetune
    results: []

flan-t5-base-finetune

This model is a fine-tuned version of htriedman/flan-t5-base-finetune on the None dataset. It achieves the following results on the evaluation set:

  • Loss: 0.0175
  • Rouge2 Precision: 0.8828
  • Rouge2 Recall: 0.1209
  • Rouge2 Fmeasure: 0.2082

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: 4
  • eval_batch_size: 32
  • 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 Rouge2 Precision Rouge2 Recall Rouge2 Fmeasure
0.0258 1.0 54375 0.0238 0.8678 0.119 0.2048
0.0236 2.0 108750 0.0199 0.877 0.1203 0.2071
0.0166 3.0 163125 0.0185 0.88 0.1206 0.2076
0.0134 4.0 217500 0.0177 0.8824 0.1208 0.208
0.0146 5.0 271875 0.0175 0.8828 0.1209 0.2082

Framework versions

  • Transformers 4.28.1
  • Pytorch 2.0.0+cu118
  • Datasets 2.12.0
  • Tokenizers 0.13.3