mBART_translator_json_hyperparameter_1

This model is a fine-tuned version of facebook/mbart-large-cc25 on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.0871
• Bleu: 86.6567
• Gen Len: 43.0648

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: 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: 5
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Bleu	Gen Len
2.4912	1.0	1998	0.6319	66.5947	80.0315
1.4069	2.0	3996	0.2170	72.413	64.2111
1.0829	3.0	5994	0.1315	78.7786	40.3136
0.8977	4.0	7992	0.0979	84.3878	42.5152
0.8452	5.0	9990	0.0871	86.6567	43.0648

Framework versions

• Transformers 4.23.1
• Pytorch 1.12.1+cu113
• Datasets 2.6.0
• Tokenizers 0.13.1