mbart_cnn_summarization_model_10K_15ep_1e-5_batch_8_BEST_warmup – AI Model by NastasiaM | AlphaNeural AI

You can deploy this model and start earning money today!

NastasiaM/
mbart_cnn_summarization_model_10K_15ep_1e-5_batch_8_BEST_warmup

like

0

text2text-generation

generated_from_trainer

facebook/mbart-large-50

endpoints_compatible

Views

No views yet

mbart_cnn_summarization_model_10K_15ep_1e-5_batch_8_BEST_warmup

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: 3.0435
Rouge1: 40.7279
Rouge2: 18.808
Rougel: 27.5852
Rougelsum: 27.5758
Gen Len: 79.533

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: 1e-05
train_batch_size: 8
eval_batch_size: 8
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
lr_scheduler_warmup_steps: 0.05
num_epochs: 15
mixed_precision_training: Native AMP
label_smoothing_factor: 0.1

Training results

Training Loss	Epoch	Step	Validation Loss	Rouge1	Rouge2	Rougel	Rougelsum	Gen Len
3.5730	1.0	1250	3.2316	41.8747	19.7077	29.3893	29.3648	85.033
3.1390	2.0	2500	3.0787	40.9212	18.6245	27.3447	27.3301	90.135
2.9738	3.0	3750	3.0435	40.7279	18.808	27.5852	27.5758	79.533

Framework versions

Transformers 5.0.0
Pytorch 2.10.0+cu128
Datasets 4.6.0
Tokenizers 0.22.2