mbart-large-50-2e-4-finetuned-1000data-Lp6 – AI Model by Ryandro | AlphaNeural AI

You can deploy this model and start earning money today!

Ryandro/
mbart-large-50-2e-4-finetuned-1000data-Lp6

like

0

text2text-generation

generated_from_trainer

facebook/mbart-large-50

endpoints_compatible

Views

No views yet

mbart-large-50-2e-4-finetuned-1000data-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: 1.8332
Rouge1: 37.6313
Rouge2: 21.4371
Rougel: 30.8132
Rougelsum: 35.3956
Gen Len: 49.1

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: 0.0002
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
No log	1.0	450	2.4287	28.5429	15.8339	24.2919	26.7863	54.57
5.5379	2.0	900	1.9403	35.2317	20.4133	28.9874	32.768	46.39
1.7954	3.0	1350	1.8332	37.6313	21.4371	30.8132	35.3956	49.1

Framework versions

Transformers 4.55.2
Pytorch 2.8.0+cu126
Datasets 4.0.0
Tokenizers 0.21.4