envit5-base-iwslt15

This model is a fine-tuned version of VietAI/envit5-base on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 2.2687
• Bleu: 21.8184

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: 3e-05
• train_batch_size: 8
• eval_batch_size: 16
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 100
• num_epochs: 10
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Bleu
2.0209	1.0	1250	1.7844	20.7717
1.5711	2.0	2500	1.7072	22.0149
1.2667	3.0	3750	1.7304	22.3730
1.0436	4.0	5000	1.7903	22.0901
0.8655	5.0	6250	1.8831	22.0823
0.7478	6.0	7500	1.9738	22.0309
0.6292	7.0	8750	2.0935	21.9696
0.5586	8.0	10000	2.1611	22.1045
0.5046	9.0	11250	2.2271	21.7866
0.4626	10.0	12500	2.2687	21.8184

Framework versions

• Transformers 4.41.2
• Pytorch 2.1.2
• Datasets 2.19.2
• Tokenizers 0.19.1