metadata

license: mit
tags:
  - generated_from_trainer
metrics:
  - rouge
model-index:
  - name: kobart_32_4e-5_datav2_min30_lp5.0_temperature1.0
    results: []

kobart_32_4e-5_datav2_min30_lp5.0_temperature1.0

This model is a fine-tuned version of gogamza/kobart-base-v2 on the None dataset. It achieves the following results on the evaluation set:

Loss: 2.6131
Rouge1: 35.7499
Rouge2: 13.0188
Rougel: 23.5089
Bleu1: 29.9409
Bleu2: 17.5869
Bleu3: 10.4195
Bleu4: 6.1345
Gen Len: 50.5967

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: 4e-05
train_batch_size: 32
eval_batch_size: 128
seed: 42
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
lr_scheduler_warmup_ratio: 0.1
num_epochs: 5.0

Training results

Training Loss	Epoch	Step	Validation Loss	Rouge1	Rouge2	Rougel	Bleu1	Bleu2	Bleu3	Bleu4	Gen Len
1.7368	3.78	5000	2.6131	35.7499	13.0188	23.5089	29.9409	17.5869	10.4195	6.1345	50.5967

Framework versions

Transformers 4.25.1
Pytorch 1.13.0+cu117
Datasets 2.7.1
Tokenizers 0.13.2