mbart-large-50-finetuned-2000data-Lp6 – AI Model by Ryandro | AlphaNeural AI

You can deploy this model and start earning money today!

Ryandro/
mbart-large-50-finetuned-2000data-Lp6

like

0

text2text-generation

generated_from_trainer

facebook/mbart-large-50

endpoints_compatible

Views

No views yet

mbart-large-50-finetuned-2000data-Lp6

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

Loss: 1.2995
Rouge1: 41.5865
Rouge2: 24.4116
Rougel: 33.9015
Rougelsum: 37.994
Gen Len: 52.66

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: 2
eval_batch_size: 2
seed: 42
optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: linear
num_epochs: 3
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Rouge1	Rouge2	Rougel	Rougelsum	Gen Len
1.9859	1.0	900	1.2780	38.5273	21.3885	31.157	35.3762	52.145
0.9788	2.0	1800	1.2344	41.4648	24.5551	34.5984	38.4432	53.935
0.6509	3.0	2700	1.2995	41.5865	24.4116	33.9015	37.994	52.66

Framework versions

Transformers 4.55.2
Pytorch 2.8.0+cu126
Datasets 4.0.0
Tokenizers 0.21.4