---
library_name: transformers
license: apache-2.0
base_model: studio-ousia/luke-japanese-base-lite
tags:
- generated_from_trainer
metrics:
- accuracy
- rouge
model-index:
- name: 64fbf67a176c46df0867fd922551d1cd
  results: []
---

<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->

# 64fbf67a176c46df0867fd922551d1cd

This model is a fine-tuned version of [studio-ousia/luke-japanese-base-lite](https://huggingface.co/studio-ousia/luke-japanese-base-lite) on the nyu-mll/glue [qnli] dataset.
It achieves the following results on the evaluation set:
- Loss: 0.6947
- Data Size: 1.0
- Epoch Runtime: 285.4853
- Accuracy: 0.5057
- F1 Macro: 0.3359
- Rouge1: 0.5053
- Rouge2: 0.0
- Rougel: 0.5057
- Rougelsum: 0.5056

## 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: 5e-05
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- distributed_type: multi-GPU
- num_devices: 4
- total_train_batch_size: 32
- total_eval_batch_size: 32
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: constant
- num_epochs: 50

### Training results

| Training Loss | Epoch | Step  | Validation Loss | Data Size | Epoch Runtime | Accuracy | F1 Macro | Rouge1 | Rouge2 | Rougel | Rougelsum |
|:-------------:|:-----:|:-----:|:---------------:|:---------:|:-------------:|:--------:|:--------:|:------:|:------:|:------:|:---------:|
| No log        | 0     | 0     | 0.7348          | 0         | 5.1493        | 0.4943   | 0.3308   | 0.4947 | 0.0    | 0.4943 | 0.4944    |
| No log        | 1     | 3273  | 0.6081          | 0.0078    | 8.7462        | 0.6680   | 0.6445   | 0.6680 | 0.0    | 0.6682 | 0.6678    |
| 0.0102        | 2     | 6546  | 0.5758          | 0.0156    | 9.7289        | 0.7256   | 0.7103   | 0.7256 | 0.0    | 0.725  | 0.7254    |
| 0.5972        | 3     | 9819  | 0.4786          | 0.0312    | 14.8877       | 0.7776   | 0.7773   | 0.7776 | 0.0    | 0.7774 | 0.7774    |
| 0.5346        | 4     | 13092 | 0.5234          | 0.0625    | 23.5677       | 0.7482   | 0.7451   | 0.7483 | 0.0    | 0.7482 | 0.7481    |
| 0.5016        | 5     | 16365 | 0.4684          | 0.125     | 40.0043       | 0.7871   | 0.7869   | 0.7869 | 0.0    | 0.7871 | 0.7873    |
| 0.5366        | 6     | 19638 | 0.5159          | 0.25      | 77.4840       | 0.7384   | 0.7294   | 0.7384 | 0.0    | 0.7388 | 0.7384    |
| 0.5204        | 7     | 22911 | 0.5355          | 0.5       | 143.7341      | 0.7472   | 0.7413   | 0.7473 | 0.0    | 0.7471 | 0.7478    |
| 0.5771        | 8.0   | 26184 | 0.5010          | 1.0       | 283.8218      | 0.7888   | 0.7881   | 0.7888 | 0.0    | 0.7886 | 0.7885    |
| 0.6953        | 9.0   | 29457 | 0.6947          | 1.0       | 285.4853      | 0.5057   | 0.3359   | 0.5053 | 0.0    | 0.5057 | 0.5056    |


### Framework versions

- Transformers 4.57.0
- Pytorch 2.8.0+cu128
- Datasets 4.3.0
- Tokenizers 0.22.1