Thalesian's picture
End of training
2dc7d45 verified
metadata
library_name: transformers
tags:
  - generated_from_trainer
model-index:
  - name: t5-base-p-l-akk-en-20241108-111409
    results: []

t5-base-p-l-akk-en-20241108-111409

This model was trained from scratch on the None dataset. It achieves the following results on the evaluation set:

  • Loss: 0.6284

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: 0.0001
  • train_batch_size: 200
  • eval_batch_size: 200
  • seed: 42
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • lr_scheduler_warmup_steps: 2000
  • num_epochs: 25

Training results

Training Loss Epoch Step Validation Loss
1.0934 1.0 10362 1.0823
0.994 2.0 20724 0.9775
0.9285 3.0 31086 0.9139
0.8822 4.0 41448 0.8726
0.8421 5.0 51810 0.8348
0.8265 6.0 62172 0.8049
0.8011 7.0 72534 0.7857
0.7805 8.0 82896 0.7648
0.7617 9.0 93258 0.7466
0.7468 10.0 103620 0.7355
0.7297 11.0 113982 0.7178
0.7293 12.0 124344 0.7078
0.7112 13.0 134706 0.6956
0.7026 14.0 145068 0.6847
0.6923 15.0 155430 0.6775
0.6855 16.0 165792 0.6726
0.6816 17.0 176154 0.6639
0.6704 18.0 186516 0.6590
0.6652 19.0 196878 0.6481
0.6614 20.0 207240 0.6452
0.6527 21.0 217602 0.6408
0.6489 22.0 227964 0.6354
0.6476 23.0 238326 0.6325
0.6388 24.0 248688 0.6295
0.6384 25.0 259050 0.6284

Framework versions

  • Transformers 4.45.2
  • Pytorch 2.6.0.dev20241022+cu124
  • Datasets 3.0.1
  • Tokenizers 0.20.1