cantonese-chinese-translation-v25

This model is a fine-tuned version of fnlp/bart-base-chinese on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 1.0034
• Bleu: 36.1824
• Chrf: 38.1395
• Gen Len: 13.1415

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: 5e-05
• train_batch_size: 8
• eval_batch_size: 8
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 30
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Bleu	Chrf	Gen Len
1.4545	1.0	13743	1.0034	36.1824	38.1395	13.1415
1.1968	2.0	27486	1.0387	35.6095	37.3961	13.2834
1.029	3.0	41229	1.0799	33.7731	35.6123	13.3209
0.9201	4.0	54972	1.1221	33.9722	35.8562	13.2955

Framework versions

• Transformers 4.28.1
• Pytorch 2.3.0+cu121
• Datasets 2.19.1
• Tokenizers 0.13.3