vinai_v2_meddict_meddictgem

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: 1.2746
• Bleu: 55.4266
• Gen Len: 43.4087

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: 32
• eval_batch_size: 8
• seed: 42
• gradient_accumulation_steps: 4
• total_train_batch_size: 128
• 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
0.5713	1.0	1004	0.8669	54.3335	43.3722
0.31	2.0	2008	0.9003	54.1622	44.4467
0.1771	3.0	3012	0.9956	55.4098	43.2584
0.1306	4.0	4016	1.1531	55.6861	43.1188
0.1361	5.0	5020	1.2746	55.4266	43.4087

Framework versions

• Transformers 4.54.0.dev0
• Pytorch 2.7.1+cu126
• Datasets 3.6.0
• Tokenizers 0.21.1