| | --- |
| | library_name: transformers |
| | license: apache-2.0 |
| | base_model: google/mt5-small |
| | tags: |
| | - generated_from_trainer |
| | model-index: |
| | - name: mt5-small-gigatrue |
| | 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-gigatrue |
| |
|
| | This model is a fine-tuned version of [google/mt5-small](https://huggingface.co/google/mt5-small) on an unknown dataset. |
| | It achieves the following results on the evaluation set: |
| | - Loss: 2.3207 |
| |
|
| | ## 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: 0.0003 |
| | - train_batch_size: 128 |
| | - eval_batch_size: 128 |
| | - seed: 42 |
| | - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
| | - lr_scheduler_type: linear |
| | - num_epochs: 3 |
| |
|
| | ### Training results |
| |
|
| | | Training Loss | Epoch | Step | Validation Loss | |
| | |:-------------:|:------:|:-----:|:---------------:| |
| | | 3.5832 | 0.1015 | 3000 | 2.4570 | |
| | | 2.9906 | 0.2030 | 6000 | 2.3889 | |
| | | 2.9367 | 0.3044 | 9000 | 2.3747 | |
| | | 2.9115 | 0.4059 | 12000 | 2.3593 | |
| | | 2.891 | 0.5074 | 15000 | 2.3491 | |
| | | 2.8835 | 0.6089 | 18000 | 2.3357 | |
| | | 2.8777 | 0.7104 | 21000 | 2.3398 | |
| | | 2.8722 | 0.8119 | 24000 | 2.3358 | |
| | | 2.8663 | 0.9133 | 27000 | 2.3275 | |
| | | 2.8658 | 1.0148 | 30000 | 2.3304 | |
| | | 2.8623 | 1.1163 | 33000 | 2.3300 | |
| | | 2.8579 | 1.2178 | 36000 | 2.3285 | |
| | | 2.857 | 1.3193 | 39000 | 2.3232 | |
| | | 2.8552 | 1.4207 | 42000 | 2.3225 | |
| | | 2.8548 | 1.5222 | 45000 | 2.3206 | |
| | | 2.8518 | 1.6237 | 48000 | 2.3243 | |
| | | 2.8539 | 1.7252 | 51000 | 2.3228 | |
| | | 2.8483 | 1.8267 | 54000 | 2.3198 | |
| | | 2.8512 | 1.9282 | 57000 | 2.3212 | |
| | | 2.8515 | 2.0296 | 60000 | 2.3204 | |
| | | 2.8512 | 2.1311 | 63000 | 2.3205 | |
| | | 2.8492 | 2.2326 | 66000 | 2.3218 | |
| | | 2.851 | 2.3341 | 69000 | 2.3221 | |
| | | 2.8497 | 2.4356 | 72000 | 2.3208 | |
| | | 2.848 | 2.5370 | 75000 | 2.3203 | |
| | | 2.852 | 2.6385 | 78000 | 2.3200 | |
| | | 2.8483 | 2.7400 | 81000 | 2.3212 | |
| | | 2.85 | 2.8415 | 84000 | 2.3206 | |
| | | 2.8503 | 2.9430 | 87000 | 2.3207 | |
| |
|
| |
|
| | ### Framework versions |
| |
|
| | - Transformers 4.45.2 |
| | - Pytorch 2.5.1 |
| | - Datasets 3.2.0 |
| | - Tokenizers 0.20.3 |
| |
|
