Edit model card

t5-base-Text-To-Graph

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

  • Loss: 1.2583
  • Rouge1: 15.9211
  • Rouge2: 10.2439
  • Rougel: 15.798
  • Rougelsum: 15.8041
  • Gen Len: 19.0

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: 15
  • mixed_precision_training: Native AMP

Training results

Training Loss Epoch Step Validation Loss Rouge1 Rouge2 Rougel Rougelsum Gen Len
No log 1.0 49 1.9977 8.1859 1.5645 8.0953 8.0998 18.7308
No log 2.0 98 1.7956 12.432 4.5448 12.3804 12.3753 18.7308
No log 3.0 147 1.6533 14.0438 7.0658 13.9349 13.9529 18.7308
No log 4.0 196 1.5491 14.0217 7.7529 13.9337 13.9439 18.7308
No log 5.0 245 1.4763 14.1269 8.3586 14.0359 14.0413 18.7308
No log 6.0 294 1.4205 14.5555 8.9978 14.4438 14.4472 18.7308
No log 7.0 343 1.3769 15.4286 9.6146 15.3249 15.3274 19.0
No log 8.0 392 1.3427 15.3635 9.7892 15.253 15.2568 19.0
No log 9.0 441 1.3177 15.4871 9.9136 15.36 15.371 19.0
No log 10.0 490 1.2978 15.6885 10.1232 15.5719 15.5818 19.0
1.8518 11.0 539 1.2826 15.7429 10.1854 15.6191 15.6226 19.0
1.8518 12.0 588 1.2720 15.8945 10.1937 15.7743 15.7814 19.0
1.8518 13.0 637 1.2645 15.9058 10.2142 15.7815 15.7875 19.0
1.8518 14.0 686 1.2598 15.9154 10.2352 15.7899 15.7952 19.0
1.8518 15.0 735 1.2583 15.9211 10.2439 15.798 15.8041 19.0

Framework versions

  • Transformers 4.38.2
  • Pytorch 2.1.0+cu121
  • Datasets 2.18.0
  • Tokenizers 0.15.2
Downloads last month
6
Safetensors
Model size
60.5M params
Tensor type
F32
·

Finetuned from