|
--- |
|
library_name: transformers |
|
license: cc-by-sa-4.0 |
|
base_model: retrieva-jp/t5-base-medium |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- rouge |
|
model-index: |
|
- name: Question_model |
|
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. --> |
|
|
|
# Question_model |
|
|
|
This model is a fine-tuned version of [retrieva-jp/t5-base-medium](https://huggingface.co/retrieva-jp/t5-base-medium) on the None dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 1.3897 |
|
- Rouge1: 0.084 |
|
- Rouge2: 0.0231 |
|
- Rougel: 0.0841 |
|
- Rougelsum: 0.084 |
|
- Gen Len: 16.1261 |
|
|
|
## 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: 4 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len | |
|
|:-------------:|:-----:|:-----:|:---------------:|:------:|:------:|:------:|:---------:|:-------:| |
|
| 1.8553 | 1.0 | 3929 | 1.5122 | 0.0843 | 0.0234 | 0.0843 | 0.0842 | 16.4606 | |
|
| 1.667 | 2.0 | 7858 | 1.4251 | 0.0853 | 0.0244 | 0.0854 | 0.085 | 16.2274 | |
|
| 1.5854 | 3.0 | 11787 | 1.3959 | 0.0814 | 0.0222 | 0.0816 | 0.0814 | 16.0416 | |
|
| 1.56 | 4.0 | 15716 | 1.3897 | 0.084 | 0.0231 | 0.0841 | 0.084 | 16.1261 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.44.2 |
|
- Pytorch 2.4.1+cu121 |
|
- Datasets 3.1.0 |
|
- Tokenizers 0.19.1 |
|
|
