|
--- |
|
library_name: transformers |
|
license: apache-2.0 |
|
base_model: google-t5/t5-small |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- bleu |
|
model-index: |
|
- name: elvish-translator-quenya-t5-small |
|
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. --> |
|
|
|
# elvish-translator-quenya-t5-small |
|
|
|
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: 3.9119 |
|
- Bleu: 0.1206 |
|
- Gen Len: 16.6875 |
|
|
|
## 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: 4 |
|
- eval_batch_size: 4 |
|
- seed: 42 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- num_epochs: 10 |
|
- mixed_precision_training: Native AMP |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Bleu | Gen Len | |
|
|:-------------:|:-----:|:----:|:---------------:|:------:|:-------:| |
|
| 4.9376 | 1.0 | 144 | 4.3320 | 0.1122 | 16.9514 | |
|
| 4.5062 | 2.0 | 288 | 4.1559 | 0.1191 | 15.9653 | |
|
| 4.3624 | 3.0 | 432 | 4.0699 | 0.1118 | 16.7361 | |
|
| 4.2832 | 4.0 | 576 | 4.0222 | 0.1474 | 16.3125 | |
|
| 4.2286 | 5.0 | 720 | 3.9854 | 0.1421 | 16.2778 | |
|
| 4.1762 | 6.0 | 864 | 3.9550 | 0.1107 | 16.9583 | |
|
| 4.14 | 7.0 | 1008 | 3.9386 | 0.1215 | 16.1944 | |
|
| 4.087 | 8.0 | 1152 | 3.9221 | 0.1232 | 16.7153 | |
|
| 4.0988 | 9.0 | 1296 | 3.9154 | 0.1206 | 16.6875 | |
|
| 4.0738 | 10.0 | 1440 | 3.9119 | 0.1206 | 16.6875 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.44.2 |
|
- Pytorch 2.2.1+cu121 |
|
- Datasets 3.0.0 |
|
- Tokenizers 0.19.1 |
|
|
