CoolFace
Modelpublic

silmi224/exp2-led-risalah_data_v4

sourceHugging Faceupdated 2y agoView on Hugging Face
0likes15downloads
Model Card

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

exp2-led-risalahdatav4

This model is a fine-tuned version of silmi224/finetune-led-35000 on an unknown dataset. It achieves the following results on the evaluation set:

  • —Loss: 1.8431
  • —Rouge1: 16.5193
  • —Rouge2: 8.3503
  • —Rougel: 11.7271
  • —Rougelsum: 15.6162

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-06
  • —trainbatchsize: 1
  • —evalbatchsize: 1
  • —seed: 42
  • —gradientaccumulationsteps: 8
  • —totaltrainbatch_size: 8
  • —optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • —lrschedulertype: linear
  • —lrschedulerwarmup_steps: 300
  • —num_epochs: 30
  • —mixedprecisiontraining: Native AMP

Training results

Training LossEpochStepValidation LossRouge1Rouge2RougelRougelsum
3.37171.0102.90948.80162.31266.27718.3716
3.36492.0202.88989.22962.58646.51698.8408
3.33173.0302.85789.41442.74766.73198.9607
3.28764.0402.81569.20482.64786.81078.8212
3.22445.0502.76517.49662.33825.90946.9392
3.16386.0602.70888.81052.66336.8098.3272
3.0877.0702.64869.37562.69577.20679.0197
3.02018.0802.58599.59752.78856.94189.0329
2.93359.0902.52249.51072.3746.84948.9865
2.860310.01002.45859.80732.87937.44459.4102
2.777411.01102.395410.6042.80257.803510.1927
2.701112.01202.334710.37283.44217.81129.5918
2.63413.01302.278311.05963.30877.968610.047
2.560814.01402.225312.42044.42768.555211.4364
2.486615.01502.178212.80464.42678.878212.2253
2.434916.01602.136913.06684.37638.761912.104
2.385117.01702.101213.76794.60229.187412.7284
2.330218.01802.069113.25124.69119.318711.8059
2.283619.01902.040314.34915.78399.834613.3638
2.23620.02002.015013.97784.94939.579912.6063
2.196521.02101.991014.07955.19269.365313.3801
2.158622.02201.970414.12615.98019.788213.503
2.132523.02301.951314.35756.00749.605313.672
2.09924.02401.933215.61326.377710.353314.9225
2.070325.02501.914116.1456.843710.672915.0299
2.043826.02601.898415.38816.597710.04814.7873
2.018727.02701.884614.15956.37789.468513.3986
1.995428.02801.869314.26316.396610.477413.4271
1.972329.02901.857615.8786.651110.873314.6417
1.946530.03001.843116.51938.350311.727115.6162

Framework versions

  • —Transformers 4.41.2
  • —Pytorch 2.1.2
  • —Datasets 2.19.2
  • —Tokenizers 0.19.1