vinai_v2_meddict_meddictgem_3

This model is a fine-tuned version of vinai/vinai-translate-en2vi-v2 on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.6340
• Bleu: 60.8596
• Gen Len: 43.3792

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: 1e-05
• train_batch_size: 128
• eval_batch_size: 32
• seed: 42
• optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: linear
• lr_scheduler_warmup_ratio: 0.05
• num_epochs: 5.0

Training results

Training Loss	Epoch	Step	Validation Loss	Bleu	Gen Len
0.7871	1.0	1004	0.6378	59.1766	43.3503
0.5081	2.0	2008	0.6202	60.3066	43.4786
0.4583	3.0	3012	0.6221	60.5893	43.3959
0.4635	4.0	4016	0.6283	60.7582	43.3702
0.5007	5.0	5020	0.6340	60.8596	43.3792

Framework versions

• Transformers 4.54.0
• Pytorch 2.7.0
• Datasets 4.1.1
• Tokenizers 0.21.4