wgcv's picture
End of training
20acc58 verified
|
raw
history blame
2.25 kB
metadata
license: apache-2.0
base_model: google-t5/t5-small
tags:
  - generated_from_trainer
metrics:
  - rouge
model-index:
  - name: tidy-tab-model-t5-small
    results: []

tidy-tab-model-t5-small

This model is a fine-tuned version of google-t5/t5-small on an unknown dataset. It achieves the following results on the evaluation set:

  • Loss: 1.0120
  • Rouge1: 0.7424
  • Rouge2: 0.6202
  • Rougel: 0.7365
  • Rougelsum: 0.7347
  • Gen Len: 7.0385

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: 16
  • eval_batch_size: 16
  • seed: 42
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • num_epochs: 8

Training results

Training Loss Epoch Step Validation Loss Rouge1 Rouge2 Rougel Rougelsum Gen Len
No log 1.0 132 1.2896 0.6823 0.5884 0.6755 0.6759 8.9744
No log 2.0 264 1.1210 0.7277 0.6094 0.7187 0.7176 7.5342
No log 3.0 396 1.0676 0.7358 0.6136 0.7287 0.7273 7.3077
1.5149 4.0 528 1.0409 0.7462 0.6233 0.7386 0.7367 7.1368
1.5149 5.0 660 1.0277 0.7464 0.6233 0.7387 0.7367 7.1068
1.5149 6.0 792 1.0186 0.7463 0.6229 0.7383 0.7362 7.0769
1.5149 7.0 924 1.0135 0.7423 0.6202 0.7364 0.7346 7.0427
1.0709 8.0 1056 1.0120 0.7424 0.6202 0.7365 0.7347 7.0385

Framework versions

  • Transformers 4.41.2
  • Pytorch 2.3.0+cu121
  • Datasets 2.20.0
  • Tokenizers 0.19.1