test_envit5_finetune

This model is a fine-tuned version of VietAI/envit5-translation on the None dataset. It achieves the following results on the evaluation set:

• Loss: 33.9330
• Bleu: 12.1272
• Gen Len: 18.518

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: 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: 7
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Bleu	Gen Len
No log	1.0	63	49.2942	12.4745	18.558
No log	2.0	126	44.9845	12.6848	18.56
No log	3.0	189	40.2016	12.2549	18.539
No log	4.0	252	37.2002	12.1574	18.542
No log	5.0	315	35.3253	12.1068	18.531
No log	6.0	378	34.2646	12.1376	18.518
No log	7.0	441	33.9330	12.1272	18.518

Framework versions

• PEFT 0.14.0
• Transformers 4.44.2
• Pytorch 2.5.1+cu124
• Datasets 3.5.0
• Tokenizers 0.19.1