NAS-bilingue

This model was trained from scratch on the None dataset. It achieves the following results on the evaluation set:

• Loss: 3.7187
• Rougelsum: 0.0922

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: 1.3739167643078955e-06
• train_batch_size: 4
• eval_batch_size: 4
• seed: 42
• distributed_type: multi-GPU
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 15
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Rougelsum
No log	1.0	5	4.5936	0.0759
No log	2.0	10	4.4276	0.0759
No log	3.0	15	4.2936	0.0759
No log	4.0	20	4.1820	0.0759
No log	5.0	25	4.0896	0.0881
No log	6.0	30	4.0121	0.0970
No log	7.0	35	3.9451	0.0918
No log	8.0	40	3.8875	0.0922
No log	9.0	45	3.8395	0.0922
No log	10.0	50	3.8011	0.0922
No log	11.0	55	3.7707	0.0922
No log	12.0	60	3.7480	0.0922
No log	13.0	65	3.7320	0.0922
No log	14.0	70	3.7223	0.0922
No log	15.0	75	3.7187	0.0922

Framework versions

• Transformers 4.26.1
• Pytorch 1.13.1+cu117
• Datasets 2.9.0
• Tokenizers 0.13.2