|
--- |
|
license: apache-2.0 |
|
base_model: google-t5/t5-small |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- rouge |
|
model-index: |
|
- name: t5-small-dagbani |
|
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. --> |
|
|
|
# t5-small-dagbani |
|
|
|
This model is a fine-tuned version of [google-t5/t5-small](https://huggingface.co/google-t5/t5-small) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 3.4567 |
|
- Rouge1: 2.9794 |
|
- Rouge2: 0.0784 |
|
- Rougel: 2.9416 |
|
- Rougelsum: 3.0119 |
|
- Gen Len: 9.5392 |
|
|
|
## 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: 1e-05 |
|
- train_batch_size: 2 |
|
- eval_batch_size: 2 |
|
- seed: 42 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- num_epochs: 5 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len | |
|
|:-------------:|:-----:|:----:|:---------------:|:------:|:------:|:------:|:---------:|:-------:| |
|
| 3.8983 | 1.0 | 455 | 3.6240 | 1.1964 | 0.0 | 1.193 | 1.2108 | 9.7647 | |
|
| 3.6379 | 2.0 | 910 | 3.5350 | 1.3174 | 0.0 | 1.3085 | 1.3079 | 9.4902 | |
|
| 3.9076 | 3.0 | 1365 | 3.4915 | 2.1136 | 0.0 | 2.0703 | 2.1291 | 9.5980 | |
|
| 3.8679 | 4.0 | 1820 | 3.4649 | 2.8498 | 0.0784 | 2.8294 | 2.8802 | 9.5098 | |
|
| 3.9169 | 5.0 | 2275 | 3.4567 | 2.9794 | 0.0784 | 2.9416 | 3.0119 | 9.5392 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.40.1 |
|
- Pytorch 2.2.1+cu121 |
|
- Datasets 2.19.0 |
|
- Tokenizers 0.19.1 |
|
|
