---
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: adf30ff46484ae174f499deadd84ad2a
  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. -->

# adf30ff46484ae174f499deadd84ad2a

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 [cola] dataset.
It achieves the following results on the evaluation set:
- Loss: 0.6206
- Data Size: 1.0
- Epoch Runtime: 24.4961
- Accuracy: 0.6885
- F1 Macro: 0.4078
- Rouge1: 0.6895
- Rouge2: 0.0
- Rougel: 0.6885
- Rougelsum: 0.6885

## 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    | 0.8334          | 0         | 1.3810        | 0.3115   | 0.2375   | 0.3105 | 0.0    | 0.3115 | 0.3115    |
| No log        | 1     | 267  | 0.6707          | 0.0078    | 2.0702        | 0.6885   | 0.4078   | 0.6895 | 0.0    | 0.6885 | 0.6885    |
| No log        | 2     | 534  | 0.6679          | 0.0156    | 2.0008        | 0.6885   | 0.4078   | 0.6895 | 0.0    | 0.6885 | 0.6885    |
| No log        | 3     | 801  | 0.6399          | 0.0312    | 2.5999        | 0.6885   | 0.4078   | 0.6895 | 0.0    | 0.6885 | 0.6885    |
| No log        | 4     | 1068 | 0.6386          | 0.0625    | 3.3997        | 0.6885   | 0.4078   | 0.6895 | 0.0    | 0.6885 | 0.6885    |
| 0.037         | 5     | 1335 | 0.6324          | 0.125     | 4.9205        | 0.6885   | 0.4078   | 0.6895 | 0.0    | 0.6885 | 0.6885    |
| 0.61          | 6     | 1602 | 0.6276          | 0.25      | 7.8792        | 0.6885   | 0.4078   | 0.6895 | 0.0    | 0.6885 | 0.6885    |
| 0.6173        | 7     | 1869 | 0.6444          | 0.5       | 13.9109       | 0.6885   | 0.4078   | 0.6895 | 0.0    | 0.6885 | 0.6885    |
| 0.6024        | 8.0   | 2136 | 0.6224          | 1.0       | 25.6404       | 0.6885   | 0.4078   | 0.6895 | 0.0    | 0.6885 | 0.6885    |
| 0.6082        | 9.0   | 2403 | 0.6433          | 1.0       | 24.8289       | 0.6885   | 0.4078   | 0.6895 | 0.0    | 0.6885 | 0.6885    |
| 0.6145        | 10.0  | 2670 | 0.6193          | 1.0       | 25.1369       | 0.6885   | 0.4078   | 0.6895 | 0.0    | 0.6885 | 0.6885    |
| 0.6197        | 11.0  | 2937 | 0.6214          | 1.0       | 24.2461       | 0.6885   | 0.4078   | 0.6895 | 0.0    | 0.6885 | 0.6885    |
| 0.6238        | 12.0  | 3204 | 0.6214          | 1.0       | 24.3247       | 0.6885   | 0.4078   | 0.6895 | 0.0    | 0.6885 | 0.6885    |
| 0.6128        | 13.0  | 3471 | 0.6220          | 1.0       | 24.5419       | 0.6885   | 0.4078   | 0.6895 | 0.0    | 0.6885 | 0.6885    |
| 0.6246        | 14.0  | 3738 | 0.6206          | 1.0       | 24.4961       | 0.6885   | 0.4078   | 0.6895 | 0.0    | 0.6885 | 0.6885    |


### Framework versions

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