metadata

license: mit
tags:
  - summarization
  - generated_from_trainer
metrics:
  - rouge
base_model: jiaoqsh/mbart-large-50-finetuned-stock-dividend
model-index:
  - name: mbart-large-50-finetuned-stocks-event-1
    results: []

mbart-large-50-finetuned-stocks-event-1

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

Loss: 0.1419
Rouge1: 0.9120
Rouge2: 0.8056
Rougel: 0.9120
Rougelsum: 0.9120

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: 5.6e-05
train_batch_size: 8
eval_batch_size: 8
seed: 42
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
num_epochs: 8

Training results

Training Loss	Epoch	Step	Validation Loss	Rouge1	Rouge2	Rougel	Rougelsum
0.3179	1.0	20	0.1784	0.8727	0.7639	0.8704	0.8727
0.0569	2.0	40	0.0822	0.9167	0.8333	0.9167	0.9144
0.0284	3.0	60	0.1842	0.9120	0.8194	0.9144	0.9120
0.0153	4.0	80	0.1448	0.9236	0.8472	0.9213	0.9236
0.0066	5.0	100	0.1271	0.9444	0.875	0.9421	0.9444
0.0013	6.0	120	0.1381	0.9190	0.8194	0.9213	0.9213
0.0083	7.0	140	0.1414	0.9190	0.8194	0.9213	0.9213
0.0002	8.0	160	0.1419	0.9120	0.8056	0.9120	0.9120

Framework versions

Transformers 4.26.1
Pytorch 1.13.1+cu116
Datasets 2.9.0
Tokenizers 0.13.2