pretrained-mt5-base-ft-bm-fr

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

• Loss: 3.0511
• Bleu: 14.9702

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: 0.001
• 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: constant_with_warmup
• lr_scheduler_warmup_ratio: 0.05
• num_epochs: 8
• label_smoothing_factor: 0.1

Training results

Training Loss	Epoch	Step	Validation Loss	Bleu
3.9341	1.0	1363	3.6982	1.6930
3.4527	2.0	2726	3.2871	7.9359
3.1539	3.0	4089	3.0966	11.2236
2.944	4.0	5453	3.0224	14.3007
2.7403	5.0	6816	3.0066	12.1646
2.5831	6.0	8179	2.9801	16.2894
2.4525	7.0	9542	3.0043	18.4456
2.3356	8.0	10904	3.0511	14.9702

Framework versions

• Transformers 4.36.2
• Pytorch 2.0.0
• Datasets 2.15.0
• Tokenizers 0.15.0