mbart-large-50-many-to-many-mmt-finetuned-human-to-assistant

This model is a fine-tuned version of facebook/mbart-large-50-many-to-many-mmt on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.1808

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: 4
• eval_batch_size: 4
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 10
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss
No log	1.0	18	0.1802
No log	2.0	36	0.1812
No log	3.0	54	0.1828
No log	4.0	72	0.1836
No log	5.0	90	0.1839
No log	6.0	108	0.1840
No log	7.0	126	0.1845
No log	8.0	144	0.1809
No log	9.0	162	0.1808
No log	10.0	180	0.1808

Framework versions

• Transformers 4.42.4
• Pytorch 2.3.1+cu121
• Datasets 2.20.0
• Tokenizers 0.19.1