bart-large-cnn-samsum-ElectrifAi_v13

This model is a fine-tuned version of philschmid/bart-large-cnn-samsum on an unknown dataset. It achieves the following results on the evaluation set:

Loss: 2.9198
Rouge1: 46.6683
Rouge2: 22.3077
Rougel: 37.436
Rougelsum: 44.2797
Gen Len: 86.6

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: 4
eval_batch_size: 4
seed: 42
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
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	10	3.0963	46.6161	24.9843	36.3484	42.7551	81.4
No log	2.0	20	2.9398	49.7463	23.695	36.3679	45.2876	84.6
No log	3.0	30	2.9198	46.6683	22.3077	37.436	44.2797	86.6

Framework versions

Transformers 4.25.1
Pytorch 1.13.1+cu117
Datasets 2.8.0
Tokenizers 0.13.2

作者:

Qiliang Huang

数据集大小:

1.52 GB