marian-finetuned-kde4-zh-to-en

This model is a fine-tuned version of charliealex123/marian-finetuned-kde4-zh-to-en on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.3645
• Bleu: 77.0389

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: 16
• eval_batch_size: 16
• 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

Training results

Training Loss	Epoch	Step	Validation Loss	Bleu
No log	1.0	255	0.4811	71.9496
0.5435	2.0	510	0.3988	74.3566
0.5435	3.0	765	0.3645	77.0389

Framework versions

• Transformers 4.35.2
• Pytorch 2.1.0+cu121
• Datasets 2.17.0
• Tokenizers 0.15.1