| ---
|
| library_name: transformers
|
| license: apache-2.0
|
| base_model: google/mt5-small
|
| tags:
|
| - generated_from_trainer
|
| metrics:
|
| - rouge
|
| model-index:
|
| - name: summary_train
|
| 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. -->
|
|
|
| # summary_train
|
|
|
| This model is a fine-tuned version of [google/mt5-small](https://huggingface.co/google/mt5-small) on the None dataset.
|
| It achieves the following results on the evaluation set:
|
| - Loss: 2.4938
|
| - Rouge1: 0.2611
|
| - Rouge2: 0.0697
|
| - Rougel: 0.2105
|
| - Rougelsum: 0.2108
|
|
|
| ## 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: Use OptimizerNames.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: 8
|
|
|
| ### Training results
|
|
|
| | Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum |
|
| |:-------------:|:-----:|:------:|:---------------:|:------:|:------:|:------:|:---------:|
|
| | 3.7973 | 1.0 | 23107 | 2.7960 | 0.2364 | 0.0537 | 0.1893 | 0.1895 |
|
| | 3.184 | 2.0 | 46214 | 2.6606 | 0.2491 | 0.0608 | 0.1994 | 0.1997 |
|
| | 3.0337 | 3.0 | 69321 | 2.5828 | 0.2536 | 0.0645 | 0.2038 | 0.2042 |
|
| | 2.9501 | 4.0 | 92428 | 2.5492 | 0.2584 | 0.0675 | 0.2080 | 0.2084 |
|
| | 2.8958 | 5.0 | 115535 | 2.5198 | 0.2588 | 0.0678 | 0.2083 | 0.2086 |
|
| | 2.8594 | 6.0 | 138642 | 2.5048 | 0.2593 | 0.0685 | 0.2089 | 0.2093 |
|
| | 2.8376 | 7.0 | 161749 | 2.4979 | 0.2603 | 0.0691 | 0.2099 | 0.2102 |
|
| | 2.8234 | 8.0 | 184856 | 2.4938 | 0.2611 | 0.0697 | 0.2105 | 0.2108 |
|
|
|
|
|
| ### Framework versions
|
|
|
| - Transformers 4.47.0
|
| - Pytorch 2.5.1+cu124
|
| - Datasets 3.1.0
|
| - Tokenizers 0.21.0
|
| |
