opus-mt-en-mr_en_mr_1

This model is a fine-tuned version of Helsinki-NLP/opus-mt-en-mr on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.4423

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: 0.0005
• train_batch_size: 64
• eval_batch_size: 64
• seed: 42
• gradient_accumulation_steps: 32
• total_train_batch_size: 2048
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 8
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss
No log	1.0	32	0.5390
No log	1.99	64	0.4928
No log	2.99	96	0.4789
No log	3.99	128	0.4641
No log	4.99	160	0.4536
No log	5.98	192	0.4472
No log	6.98	224	0.4437
No log	7.98	256	0.4423

Framework versions

• Transformers 4.38.2
• Pytorch 2.1.2
• Datasets 2.15.0
• Tokenizers 0.15.2