metadata

license: mit
base_model: VietAI/vit5-base
tags:
  - generated_from_trainer
metrics:
  - rouge
model-index:
  - name: mymodel_LORA_base_10k_2e5_3epoch_batch16_T4
    results: []

mymodel_LORA_base_10k_2e5_3epoch_batch16_T4

This model is a fine-tuned version of VietAI/vit5-base on an unknown dataset. It achieves the following results on the evaluation set:

Loss: 1.9509
Rouge1: 0.5087
Rouge2: 0.21
Rougel: 0.3279
Rougelsum: 0.3278
Gen Len: 47.1885

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: 16
eval_batch_size: 16
seed: 42
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
num_epochs: 3

Training results

Training Loss	Epoch	Step	Validation Loss	Rouge1	Rouge2	Rougel	Rougelsum	Gen Len
2.904	1.0	500	2.0384	0.4986	0.1981	0.323	0.3231	54.0445
2.167	2.0	1000	1.9662	0.5068	0.2053	0.3269	0.3268	54.8295
2.1217	3.0	1500	1.9509	0.5087	0.21	0.3279	0.3278	47.1885

Framework versions

Transformers 4.34.0
Pytorch 2.1.0+cu118
Datasets 2.14.7
Tokenizers 0.14.1