| base_model: '' | |
| tags: | |
| - generated_from_trainer | |
| metrics: | |
| - rouge | |
| model-index: | |
| - name: hubert2BertMusicwithNewS | |
| 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. --> | |
| # hubert2BertMusicwithNewS | |
| This model is a fine-tuned version of [](https://huggingface.co/) on an unknown dataset. | |
| It achieves the following results on the evaluation set: | |
| - Loss: 4.9900 | |
| - Rouge1: 26.5585 | |
| - Rouge2: 5.0275 | |
| - Rougel: 20.5156 | |
| - Rougelsum: 20.5605 | |
| - Gen Len: 69.0 | |
| ## 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: 1e-05 | |
| - train_batch_size: 4 | |
| - eval_batch_size: 4 | |
| - 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 | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len | | |
| |:-------------:|:-----:|:----:|:---------------:|:-------:|:------:|:-------:|:---------:|:-------:| | |
| | 5.4468 | 1.0 | 959 | 5.3074 | 26.4524 | 5.1085 | 20.4049 | 20.4327 | 65.39 | | |
| | 4.817 | 2.0 | 1918 | 5.0738 | 26.1836 | 5.119 | 20.2888 | 20.2917 | 64.66 | | |
| | 4.6359 | 3.0 | 2877 | 4.9900 | 26.5585 | 5.0275 | 20.5156 | 20.5605 | 69.0 | | |
| ### Framework versions | |
| - Transformers 4.31.0 | |
| - Pytorch 2.0.1+cu117 | |
| - Datasets 2.14.2 | |
| - Tokenizers 0.13.3 | |