mbart-large-50-finetuned-sah-to-feat

This model is a fine-tuned version of facebook/mbart-large-50 on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.4514
• Bleu: 5.5821
• Gen Len: 199.0

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: 2e-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: 10

Training results

Training Loss	Epoch	Step	Validation Loss	Bleu	Gen Len
12.3174	1.0	24	6.7012	0.0148	199.0
5.2025	2.0	48	3.9396	0.0953	199.0
3.6977	3.0	72	2.1764	1.573	199.0
1.884	4.0	96	1.3887	3.5395	199.0
1.3753	5.0	120	0.9881	5.6111	199.0
0.9707	6.0	144	0.7452	5.2841	199.0
0.8008	7.0	168	0.6060	5.4831	199.0
0.6444	8.0	192	0.5174	5.4302	199.0
0.5689	9.0	216	0.4744	5.6898	199.0
0.5244	10.0	240	0.4514	5.5821	199.0

Framework versions

• Transformers 4.30.2
• Pytorch 2.0.1
• Datasets 2.13.1
• Tokenizers 0.13.3