mt5-translation

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

• Loss: 0.8131
• Bleu: 33.2736
• Gen Len: 15.9643

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: 8
• eval_batch_size: 8
• seed: 42
• gradient_accumulation_steps: 4
• total_train_batch_size: 32
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 4

Training results

Training Loss	Epoch	Step	Validation Loss	Bleu	Gen Len
1.3759	1.0	6352	0.9269	28.6704	16.0318
1.2615	2.0	12704	0.8545	31.4174	15.9769
1.2083	3.0	19056	0.8187	33.0994	15.9707
1.1886	4.0	25408	0.8071	33.5944	15.9657

Framework versions

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