metadata
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: []
Question_model
This model is a fine-tuned version of 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