Testing-t5 / README.md
Ashraf-CK's picture
End of training
ed080a2 verified
metadata
library_name: transformers
tags:
  - generated_from_trainer
model-index:
  - name: Testing-t5
    results: []

Testing-t5

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

  • Loss: 0.3656

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: 1e-05
  • train_batch_size: 32
  • eval_batch_size: 32
  • seed: 42
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • num_epochs: 20

Training results

Training Loss Epoch Step Validation Loss
No log 1.0 282 0.4660
0.5546 2.0 564 0.4258
0.5546 3.0 846 0.4089
0.4368 4.0 1128 0.3977
0.4368 5.0 1410 0.3911
0.4116 6.0 1692 0.3860
0.4116 7.0 1974 0.3812
0.3957 8.0 2256 0.3783
0.3872 9.0 2538 0.3754
0.3872 10.0 2820 0.3736
0.3806 11.0 3102 0.3717
0.3806 12.0 3384 0.3707
0.3737 13.0 3666 0.3691
0.3737 14.0 3948 0.3682
0.3693 15.0 4230 0.3675
0.367 16.0 4512 0.3667
0.367 17.0 4794 0.3662
0.3655 18.0 5076 0.3659
0.3655 19.0 5358 0.3657
0.3605 20.0 5640 0.3656

Framework versions

  • Transformers 4.44.2
  • Pytorch 2.4.1+cu121
  • Datasets 3.0.1
  • Tokenizers 0.19.1