Edit model card

flan-t5-base-Cause-finetuned

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

  • Loss: nan
  • Rouge1: 11.7221
  • Rouge2: 8.3773
  • Rougel: 11.3413
  • Rougelsum: 11.3455
  • Gen Len: 17.9486

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: 20
  • mixed_precision_training: Native AMP

Training results

Training Loss Epoch Step Validation Loss Rouge1 Rouge2 Rougel Rougelsum Gen Len
No log 1.0 248 nan 11.7221 8.3773 11.3413 11.3455 17.9486
No log 2.0 496 nan 11.7221 8.3773 11.3413 11.3455 17.9486
0.0 3.0 744 nan 11.7221 8.3773 11.3413 11.3455 17.9486
0.0 4.0 992 nan 11.7221 8.3773 11.3413 11.3455 17.9486
0.0 5.0 1240 nan 11.7221 8.3773 11.3413 11.3455 17.9486
0.0 6.0 1488 nan 11.7221 8.3773 11.3413 11.3455 17.9486
0.0 7.0 1736 nan 11.7221 8.3773 11.3413 11.3455 17.9486
0.0 8.0 1984 nan 11.7221 8.3773 11.3413 11.3455 17.9486
0.0 9.0 2232 nan 11.7221 8.3773 11.3413 11.3455 17.9486
0.0 10.0 2480 nan 11.7221 8.3773 11.3413 11.3455 17.9486
0.0 11.0 2728 nan 11.7221 8.3773 11.3413 11.3455 17.9486
0.0 12.0 2976 nan 11.7221 8.3773 11.3413 11.3455 17.9486
0.0 13.0 3224 nan 11.7221 8.3773 11.3413 11.3455 17.9486
0.0 14.0 3472 nan 11.7221 8.3773 11.3413 11.3455 17.9486
0.0 15.0 3720 nan 11.7221 8.3773 11.3413 11.3455 17.9486
0.0 16.0 3968 nan 11.7221 8.3773 11.3413 11.3455 17.9486
0.0 17.0 4216 nan 11.7221 8.3773 11.3413 11.3455 17.9486
0.0 18.0 4464 nan 11.7221 8.3773 11.3413 11.3455 17.9486
0.0 19.0 4712 nan 11.7221 8.3773 11.3413 11.3455 17.9486
0.0 20.0 4960 nan 11.7221 8.3773 11.3413 11.3455 17.9486

Framework versions

  • Transformers 4.41.1
  • Pytorch 1.13.1+cu117
  • Datasets 2.19.1
  • Tokenizers 0.19.1
Downloads last month
3
Safetensors
Model size
248M params
Tensor type
F32
·

Finetuned from