|
--- |
|
base_model: '' |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- rouge |
|
model-index: |
|
- name: hubert2BertMusic200 |
|
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. --> |
|
|
|
# hubert2BertMusic200 |
|
|
|
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: 2.1568 |
|
- Rouge1: 41.9485 |
|
- Rouge2: 16.0177 |
|
- Rougel: 28.1569 |
|
- Rougelsum: 28.2146 |
|
- Gen Len: 32.53 |
|
|
|
## 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: 10 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len | |
|
|:-------------:|:-----:|:----:|:---------------:|:-------:|:-------:|:-------:|:---------:|:-------:| |
|
| 3.1808 | 1.0 | 983 | 2.5483 | 44.2196 | 17.3838 | 29.8836 | 29.9101 | 32.93 | |
|
| 2.7237 | 2.0 | 1966 | 2.4003 | 47.3213 | 18.6129 | 30.9017 | 30.981 | 38.4 | |
|
| 2.6101 | 3.0 | 2949 | 2.3362 | 42.6501 | 16.7451 | 28.8455 | 28.9107 | 34.81 | |
|
| 2.5294 | 4.0 | 3932 | 2.2842 | 41.8623 | 16.4242 | 28.7097 | 28.7267 | 34.84 | |
|
| 2.5019 | 5.0 | 4915 | 2.2421 | 41.5838 | 17.0684 | 28.534 | 28.5982 | 35.7 | |
|
| 2.4511 | 6.0 | 5898 | 2.2094 | 41.6459 | 16.4044 | 27.8617 | 27.9134 | 31.17 | |
|
| 2.4406 | 7.0 | 6881 | 2.1854 | 42.6733 | 16.4912 | 28.6327 | 28.7019 | 33.08 | |
|
| 2.4249 | 8.0 | 7864 | 2.1695 | 42.0305 | 16.279 | 28.1039 | 28.1835 | 32.91 | |
|
| 2.4041 | 9.0 | 8847 | 2.1623 | 41.0736 | 15.3285 | 27.9246 | 27.985 | 30.66 | |
|
| 2.4212 | 10.0 | 9830 | 2.1568 | 41.9485 | 16.0177 | 28.1569 | 28.2146 | 32.53 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.31.0 |
|
- Pytorch 2.0.1+cu117 |
|
- Datasets 2.14.2 |
|
- Tokenizers 0.13.3 |
|
|