|
--- |
|
library_name: transformers |
|
license: apache-2.0 |
|
base_model: Mat17892/t5small_enfr_opus |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- bleu |
|
model-index: |
|
- name: t5small_enfr_opus |
|
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. --> |
|
|
|
# t5small_enfr_opus |
|
|
|
This model is a fine-tuned version of [Mat17892/t5small_enfr_opus](https://huggingface.co/Mat17892/t5small_enfr_opus) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 1.4839 |
|
- Bleu: 6.4 |
|
- Gen Len: 17.5697 |
|
|
|
## 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: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments |
|
- lr_scheduler_type: linear |
|
- num_epochs: 4 |
|
- mixed_precision_training: Native AMP |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Bleu | Gen Len | |
|
|:-------------:|:-----:|:-----:|:---------------:|:------:|:-------:| |
|
| 1.7415 | 1.0 | 6355 | 1.5201 | 6.1792 | 17.5724 | |
|
| 1.6892 | 2.0 | 12710 | 1.4981 | 6.2914 | 17.572 | |
|
| 1.6825 | 3.0 | 19065 | 1.4873 | 6.3889 | 17.5701 | |
|
| 1.6803 | 4.0 | 25420 | 1.4839 | 6.4 | 17.5697 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.46.2 |
|
- Pytorch 2.5.1+cu121 |
|
- Datasets 3.1.0 |
|
- Tokenizers 0.20.3 |
|
|