m2m100_418M-fr

This model is a fine-tuned version of facebook/m2m100_418M on the kde4 dataset.

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: 64
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 3

Framework versions

• Transformers 4.12.5
• Pytorch 1.9.0+cpu
• Datasets 1.16.1
• Tokenizers 0.10.3