| --- |
| library_name: peft |
| license: apache-2.0 |
| base_model: google/mt5-base |
| tags: |
| - base_model:adapter:google/mt5-base |
| - lora |
| - transformers |
| model-index: |
| - name: outputs |
| 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. --> |
|
|
| # outputs |
|
|
| This model is a fine-tuned version of [google/mt5-base](https://huggingface.co/google/mt5-base) on an unknown dataset. |
| It achieves the following results on the evaluation set: |
| - Loss: 4.1438 |
| - Chrf: 0.3504 |
|
|
| ## 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: 0.01 |
| - train_batch_size: 4 |
| - eval_batch_size: 8 |
| - seed: 1 |
| - optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments |
| - lr_scheduler_type: linear |
| - lr_scheduler_warmup_steps: 2000.0 |
| - training_steps: 20000 |
|
|
| ### Training results |
|
|
| | Training Loss | Epoch | Step | Validation Loss | Chrf | |
| |:-------------:|:------:|:-----:|:---------------:|:------:| |
| | 6.5309 | 0.9337 | 2000 | 6.1412 | 0.0 | |
| | 5.0243 | 1.8674 | 4000 | 4.7869 | 0.0 | |
| | 5.8503 | 2.8011 | 6000 | 4.6079 | 0.0 | |
| | 4.8561 | 3.7348 | 8000 | 5.4843 | 0.3906 | |
| | 5.3422 | 4.6685 | 10000 | 4.6969 | 0.1913 | |
| | 5.1278 | 5.6022 | 12000 | 4.5267 | 0.0638 | |
| | 4.7362 | 6.5359 | 14000 | 4.4173 | 0.5746 | |
| | 4.8027 | 7.4697 | 16000 | 4.2625 | 0.1913 | |
| | 4.4404 | 8.4034 | 18000 | 4.1877 | 0.1276 | |
| | 4.3010 | 9.3371 | 20000 | 4.1438 | 0.3504 | |
|
|
|
|
| ### Framework versions |
|
|
| - PEFT 0.19.1 |
| - Transformers 5.0.0 |
| - Pytorch 2.10.0+cu128 |
| - Datasets 4.0.0 |
| - Tokenizers 0.22.2 |
