Hugging Face's logo

roequitz
/
t5-abs-2309-1054-lr-0.001-bs-2-maxep-20

Safetensors
t5
Generated from Trainer
Model card Files Community
t5-abs-2309-1054-lr-0.001-bs-2-maxep-20 / README.md
roequitz's picture
roequitz
End of training
afa26c4 verified
preview code
|
raw
history blame contribute delete
No virus
6.33 kB
metadata
license: apache-2.0
base_model: google-t5/t5-base
tags:
  - generated_from_trainer
model-index:
  - name: t5-abs-2309-1054-lr-0.001-bs-2-maxep-20
    results: []

t5-abs-2309-1054-lr-0.001-bs-2-maxep-20

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

  • Loss: nan
  • Rouge/rouge1: 0.0
  • Rouge/rouge2: 0.0
  • Rouge/rougel: 0.0
  • Rouge/rougelsum: 0.0
  • Bertscore/bertscore-precision: 0.0
  • Bertscore/bertscore-recall: 0.0
  • Bertscore/bertscore-f1: 0.0
  • Meteor: 0.0
  • Gen Len: 0.0

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: 0.001
  • train_batch_size: 2
  • eval_batch_size: 2
  • seed: 42
  • gradient_accumulation_steps: 2
  • total_train_batch_size: 4
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • lr_scheduler_warmup_ratio: 0.1
  • num_epochs: 20
  • mixed_precision_training: Native AMP

Training results

Training Loss Epoch Step Validation Loss Rouge/rouge1 Rouge/rouge2 Rouge/rougel Rouge/rougelsum Bertscore/bertscore-precision Bertscore/bertscore-recall Bertscore/bertscore-f1 Meteor Gen Len
1.0524 1.0 217 1.9798 0.4548 0.2064 0.3831 0.3848 0.8919 0.8942 0.8929 0.4177 41.2636
1.4167 2.0 434 1.9903 0.4327 0.1886 0.3657 0.3672 0.8947 0.8843 0.8893 0.3692 33.8545
1.3767 3.0 651 2.0041 0.4527 0.2062 0.3851 0.3862 0.8945 0.8927 0.8934 0.4073 38.0727
1.0766 4.0 868 2.0268 0.4611 0.2088 0.3905 0.3915 0.8985 0.8923 0.8952 0.4052 36.4182
1.0071 5.0 1085 2.3584 0.4183 0.1611 0.3443 0.3455 0.8901 0.8858 0.8877 0.3591 36.9909
1.1108 6.0 1302 2.5739 0.4169 0.1599 0.3463 0.3463 0.8895 0.8835 0.8861 0.3516 35.2636
1.2043 7.0 1519 2.7884 0.3995 0.1628 0.3339 0.3347 0.8717 0.8827 0.876 0.341 38.7364
1.24 8.0 1736 2.7884 0.3995 0.1628 0.3339 0.3347 0.8717 0.8827 0.876 0.341 38.7364
1.2303 9.0 1953 2.7884 0.3995 0.1628 0.3339 0.3347 0.8717 0.8827 0.876 0.341 38.7364
1.218 10.0 2170 2.7884 0.3995 0.1628 0.3339 0.3347 0.8717 0.8827 0.876 0.341 38.7364
1.2135 11.0 2387 2.7884 0.3995 0.1628 0.3339 0.3347 0.8717 0.8827 0.876 0.341 38.7364
1.2276 12.0 2604 2.7884 0.3995 0.1628 0.3339 0.3347 0.8717 0.8827 0.876 0.341 38.7364
1.2104 13.0 2821 2.7884 0.3995 0.1628 0.3339 0.3347 0.8717 0.8827 0.876 0.341 38.7364
1.2409 14.0 3038 2.7884 0.3995 0.1628 0.3339 0.3347 0.8717 0.8827 0.876 0.341 38.7364
4.1714 15.0 3255 nan 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0
0.0 16.0 3472 nan 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0
0.0 17.0 3689 nan 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0
0.0 18.0 3906 nan 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0
0.0 19.0 4123 nan 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0
0.0 20.0 4340 nan 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0

Framework versions

  • Transformers 4.44.0
  • Pytorch 2.4.0
  • Datasets 2.21.0
  • Tokenizers 0.19.1