CoolFace
Modelpublic

basso4/basso4_eng_to_vie_model

sourceHugging Faceupdated 3y agoView on Hugging Face
0likes7downloads
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. -->

basso4engtoviemodel

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

  • —Loss: 0.9999
  • —Bleu: 1.3777
  • —Gen Len: 18.7953

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
  • —trainbatchsize: 16
  • —evalbatchsize: 16
  • —seed: 42
  • —optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • —lrschedulertype: linear
  • —num_epochs: 10

Training results

Training LossEpochStepValidation LossBleuGen Len
1.34851.066661.21510.929418.7893
1.29692.0133321.15101.059318.7881
1.24263.0199981.10531.159818.7873
1.20674.0266641.07131.239318.789
1.18095.0333301.04691.285318.7894
1.15756.0399961.02881.322718.7899
1.14077.0466621.01541.340518.7937
1.12958.0533281.00711.365718.7943
1.12419.0599941.00141.375318.7953
1.120910.0666600.99991.377718.7953

Framework versions

  • —Transformers 4.33.0
  • —Pytorch 2.0.0
  • —Datasets 2.1.0
  • —Tokenizers 0.13.3