kp-umt5-base / README.md
jhpassion0621's picture
End of training
a562c79 verified
|
raw
history blame
1.29 kB
metadata
license: apache-2.0
base_model: google/umt5-base
tags:
  - generated_from_trainer
model-index:
  - name: kp-umt5-base
    results: []

kp-umt5-base

This model is a fine-tuned version of google/umt5-base on an unknown dataset. It achieves the following results on the evaluation set:

  • eval_loss: 1.2530
  • eval_bleu: 21.9541
  • eval_gen_len: 44.6717
  • eval_runtime: 3625.6762
  • eval_samples_per_second: 7.813
  • eval_steps_per_second: 0.244
  • step: 0

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: 32
  • eval_batch_size: 32
  • seed: 42
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • lr_scheduler_warmup_steps: 2500
  • training_steps: 240000

Framework versions

  • Transformers 4.35.2
  • Pytorch 2.1.0+cu121
  • Datasets 2.16.1
  • Tokenizers 0.15.1