Testing-t5 / README.md
Ashraf-CK's picture
End of training
ab137ad verified
|
raw
history blame
2.15 kB
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: 0.4247

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 0.4536
0.4858 2.0 564 0.4485
0.4858 3.0 846 0.4444
0.471 4.0 1128 0.4415
0.471 5.0 1410 0.4384
0.4579 6.0 1692 0.4362
0.4579 7.0 1974 0.4342
0.4511 8.0 2256 0.4326
0.4422 9.0 2538 0.4314
0.4422 10.0 2820 0.4304
0.4405 11.0 3102 0.4288
0.4405 12.0 3384 0.4281
0.4313 13.0 3666 0.4270
0.4313 14.0 3948 0.4267
0.4297 15.0 4230 0.4261
0.4271 16.0 4512 0.4259
0.4271 17.0 4794 0.4255
0.4261 18.0 5076 0.4251
0.4261 19.0 5358 0.4248
0.4254 20.0 5640 0.4247

Framework versions

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