CoolFace
Modelpublic

pakawadeep/mt5-small-finetuned-ctfl-augmented

sourceHugging Faceapache-2.0updated 2y agoView on Hugging Face
0likes8downloads
Model Card

<!-- This model card has been generated automatically according to the information Keras had access to. You should probably proofread and complete it, then remove this comment. -->

pakawadeep/mt5-small-finetuned-ctfl-augmented

This model is a fine-tuned version of google/mt5-small on an unknown dataset. It achieves the following results on the evaluation set:

  • Train Loss: 0.9381
  • Validation Loss: 0.9416
  • Train Rouge1: 7.9915
  • Train Rouge2: 1.3861
  • Train Rougel: 7.9562
  • Train Rougelsum: 7.9915
  • Train Gen Len: 11.9653
  • Epoch: 29

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:

  • optimizer: {'name': 'AdamWeightDecay', 'learningrate': 2e-05, 'decay': 0.0, 'beta1': 0.9, 'beta2': 0.999, 'epsilon': 1e-07, 'amsgrad': False, 'weightdecay_rate': 0.01}
  • training_precision: float32

Training results

Train LossValidation LossTrain Rouge1Train Rouge2Train RougelTrain RougelsumTrain Gen LenEpoch
10.75773.23030.71640.00.72060.705216.16830
5.88461.98481.55450.01.58461.561416.73761
4.27891.77195.06840.74265.13915.115511.63862
3.48511.75275.23100.94065.23105.207411.10403
2.98921.70386.22350.82516.32256.277711.38124
2.64631.65858.20372.17828.20378.203711.49015
2.38971.59648.69872.17828.69878.486611.70306
2.17941.51128.69872.17828.69878.486611.83177
1.98961.44618.20372.17828.20378.203711.90598
1.83471.37708.20372.17828.20378.203711.97039
1.71011.31558.20372.17828.20378.203711.950510
1.60031.25988.69872.17828.69878.698711.910911
1.50411.23678.69872.17828.69878.698711.950512
1.43091.22868.69872.17828.69878.698711.955413
1.36181.17958.91092.37629.08778.981611.955414
1.30901.16258.91092.37629.08778.981611.945515
1.26691.12108.91092.37629.08778.981611.955416
1.22621.07698.69871.78228.76948.734111.975217
1.19151.07248.45121.38618.48668.451211.975218
1.15621.04448.45121.38618.48668.451211.970319
1.12911.03188.45121.38618.48668.451211.965320
1.10631.03218.45121.38618.48668.451211.955421
1.07861.01248.45121.38618.48668.451211.960422
1.05401.00628.45121.38618.48668.451211.960423
1.02410.97878.45121.38618.48668.451211.965324
1.00860.96838.45121.38618.48668.451211.970325
0.98830.96658.45121.38618.48668.451211.965326
0.96610.95218.45121.38618.48668.451211.970327
0.95430.96938.45121.38618.48668.451211.970328
0.93810.94167.99151.38617.95627.991511.965329

Framework versions

  • Transformers 4.38.2
  • TensorFlow 2.15.0
  • Datasets 2.18.0
  • Tokenizers 0.15.2