metadata

license: apache-2.0
base_model: GuysTrans/bart-base-chat-512-seq
tags:
  - generated_from_trainer
metrics:
  - rouge
model-index:
  - name: bart-base-chat-512-seq
    results: []

bart-base-chat-512-seq

This model is a fine-tuned version of GuysTrans/bart-base-chat-512-seq on the None dataset. It achieves the following results on the evaluation set:

Loss: 3.0493
Rouge1: 11.6122
Rouge2: 3.0225
Rougel: 9.3982
Rougelsum: 11.1436
Gen Len: 19.9902

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: 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: 1

Training results

Training Loss	Epoch	Step	Validation Loss	Rouge1	Rouge2	Rougel	Rougelsum	Gen Len
1.5237	1.0	14598	3.0493	11.6122	3.0225	9.3982	11.1436	19.9902

Framework versions

Transformers 4.33.0
Pytorch 2.0.0
Datasets 2.1.0
Tokenizers 0.13.3