| | --- |
| | tags: |
| | - generated_from_trainer |
| | metrics: |
| | - bleu |
| | model-index: |
| | - name: mt5-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. --> |
| |
|
| | # mt5-small |
| |
|
| | This model was trained from scratch on an unknown dataset. |
| | It achieves the following results on the evaluation set: |
| | - Loss: 2.7308 |
| | - Bleu: 0.0181 |
| | - Gen Len: 27.656 |
| |
|
| | ## 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: 8 |
| | - eval_batch_size: 8 |
| | - seed: 42 |
| | - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
| | - lr_scheduler_type: linear |
| | - num_epochs: 6 |
| |
|
| | ### Training results |
| |
|
| | | Training Loss | Epoch | Step | Validation Loss | Bleu | Gen Len | |
| | |:-------------:|:-----:|:----:|:---------------:|:------:|:-------:| |
| | | No log | 1.0 | 377 | 10.5974 | 0.0027 | 128.0 | |
| | | 16.889 | 2.0 | 754 | 6.2000 | 0.0006 | 127.762 | |
| | | 8.7035 | 3.0 | 1131 | 4.2664 | 0.0024 | 48.7383 | |
| | | 5.0692 | 4.0 | 1508 | 3.3315 | 0.0103 | 30.2219 | |
| | | 5.0692 | 5.0 | 1885 | 2.8775 | 0.0202 | 27.7363 | |
| | | 3.7431 | 6.0 | 2262 | 2.7308 | 0.0181 | 27.656 | |
| |
|
| |
|
| | ### Framework versions |
| |
|
| | - Transformers 4.40.0 |
| | - Pytorch 2.2.1+cu121 |
| | - Datasets 2.19.0 |
| | - Tokenizers 0.19.1 |
| |
|
