M2M100-ja-zh / README.md
Nekofox's picture
Upload 11 files
049c71a
|
raw
history blame
1.18 kB
metadata
tags:
  - generated_from_trainer
model-index:
  - name: M100M-zh-ja
    results: []

M100M-zh-ja

This model was trained from scratch on the None dataset. It achieves the following results on the evaluation set:

  • eval_loss: 1.8243
  • eval_bleu: 25.4595
  • eval_gen_len: 19.6603
  • eval_runtime: 189.5332
  • eval_samples_per_second: 6.073
  • eval_steps_per_second: 0.675
  • epoch: 1.44
  • step: 3500

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: 9
  • eval_batch_size: 9
  • seed: 42
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • num_epochs: 3
  • mixed_precision_training: Native AMP

Framework versions

  • Transformers 4.28.1
  • Pytorch 2.0.0+cu118
  • Datasets 2.12.0
  • Tokenizers 0.13.3