metadata

license: apache-2.0
base_model: facebook/bart-base
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 facebook/bart-base on the None dataset. It achieves the following results on the evaluation set:

Loss: 2.9516
Rouge1: 12.1649
Rouge2: 3.7707
Rougel: 10.036
Rougelsum: 11.953
Gen Len: 20.0

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
2.6367	1.0	14598	2.9516	12.1649	3.7707	10.036	11.953	20.0

Framework versions

Transformers 4.34.1
Pytorch 2.0.1+cu118
Datasets 2.14.5
Tokenizers 0.14.1