CoolFace
Modelpublic

mekjr1/byt5-base-es_guc

sourceHugging Faceapache-2.0updated 3y agoView on Hugging Face
0likes9downloads
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. -->

byt5-base-es_guc

This model is a fine-tuned version of google/byt5-base on an unknown dataset. It achieves the following results on the evaluation set:

  • —Loss: 0.7552
  • —Bleu: 2.594
  • —Gen Len: 100.8294

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: 5e-05
  • —trainbatchsize: 16
  • —evalbatchsize: 16
  • —seed: 65
  • —optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • —lrschedulertype: linear
  • —num_epochs: 10.0

Training results

Training LossEpochStepValidation LossBleuGen Len
No log1.03811.06520.016719.0
1.52882.07620.93390.040219.0
1.0633.011430.86510.031119.0
0.95584.015240.82710.101819.0
0.95585.019050.80430.074419.0
0.89796.022860.78310.078619.0
0.85987.026670.76990.08619.0
0.83468.030480.76300.080319.0
0.83469.034290.75720.117919.0
0.819410.038100.75520.113319.0

Framework versions

  • —Transformers 4.27.4
  • —Pytorch 2.0.0+cu118
  • —Datasets 2.11.0
  • —Tokenizers 0.13.3