arthurmluz's picture
Model save
3b435e0
|
raw
history blame
4.33 kB
metadata
tags:
  - generated_from_trainer
metrics:
  - rouge
model-index:
  - name: ptt5-wikilingua-temario
    results: []

ptt5-wikilingua-temario

This model was trained from scratch on an unknown dataset. It achieves the following results on the evaluation set:

  • Loss: 2.4417
  • Rouge1: 8.787
  • Rouge2: 5.5133
  • Rougel: 7.7732
  • Rougelsum: 8.5033
  • 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: 2
  • eval_batch_size: 2
  • seed: 42
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • num_epochs: 30

Training results

Training Loss Epoch Step Validation Loss Rouge1 Rouge2 Rougel Rougelsum Gen Len
No log 1.0 88 2.7066 7.5069 3.1524 6.0693 7.1909 19.0
No log 2.0 176 2.6314 7.663 3.5887 6.1987 7.3444 19.0
2.9286 3.0 264 2.5823 8.4012 4.3812 7.0272 8.0549 19.0
2.9286 4.0 352 2.5548 8.6227 4.8271 7.1687 8.2419 19.0
2.6522 5.0 440 2.5300 8.6178 4.7726 7.2234 8.2637 19.0
2.6522 6.0 528 2.5124 8.7431 4.8169 7.4449 8.3875 19.0
2.5237 7.0 616 2.4978 8.8796 5.0694 7.5619 8.5038 19.0
2.5237 8.0 704 2.4917 8.7714 5.1832 7.643 8.4577 19.0
2.5237 9.0 792 2.4801 8.7998 5.2361 7.6774 8.4935 19.0
2.4402 10.0 880 2.4716 8.9029 5.254 7.7002 8.5854 19.0
2.4402 11.0 968 2.4668 8.949 5.3352 7.7535 8.6621 19.0
2.3925 12.0 1056 2.4640 8.8126 5.1864 7.5918 8.4955 19.0
2.3925 13.0 1144 2.4581 8.8663 5.293 7.6271 8.537 19.0
2.3189 14.0 1232 2.4516 8.9118 5.3828 7.6637 8.581 19.0
2.3189 15.0 1320 2.4500 8.9342 5.4024 7.7154 8.5934 19.0
2.2561 16.0 1408 2.4502 8.8847 5.5391 7.8322 8.611 19.0
2.2561 17.0 1496 2.4485 8.8129 5.4839 7.7874 8.5371 19.0
2.2561 18.0 1584 2.4448 8.8058 5.4796 7.7881 8.5264 19.0
2.231 19.0 1672 2.4435 8.7837 5.4104 7.7718 8.5261 19.0
2.231 20.0 1760 2.4437 8.7946 5.4966 7.7942 8.5357 19.0
2.2094 21.0 1848 2.4432 8.7801 5.4826 7.7942 8.5156 19.0
2.2094 22.0 1936 2.4452 8.7801 5.4826 7.7942 8.5156 19.0
2.1987 23.0 2024 2.4424 8.8398 5.5067 7.8209 8.5856 19.0
2.1987 24.0 2112 2.4440 8.8398 5.5067 7.8209 8.5856 19.0
2.1643 25.0 2200 2.4397 8.8398 5.5067 7.8209 8.5856 19.0
2.1643 26.0 2288 2.4411 8.8072 5.5271 7.7949 8.5449 19.0
2.1643 27.0 2376 2.4424 8.8192 5.4877 7.7992 8.5387 19.0
2.1376 28.0 2464 2.4423 8.787 5.5133 7.7732 8.5033 19.0
2.1376 29.0 2552 2.4423 8.787 5.5133 7.7732 8.5033 19.0
2.1601 30.0 2640 2.4417 8.787 5.5133 7.7732 8.5033 19.0

Framework versions

  • Transformers 4.34.0
  • Pytorch 2.0.1+cu117
  • Datasets 2.14.5
  • Tokenizers 0.14.1