metadata
base_model: ''
tags:
- generated_from_trainer
metrics:
- rouge
model-index:
- name: hubert2BertMusicwithNewS
results: []
hubert2BertMusicwithNewS
This model is a fine-tuned version of on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 3.5387
- Rouge1: 45.3465
- Rouge2: 20.3438
- Rougel: 32.6884
- Rougelsum: 32.6636
- Gen Len: 41.51
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 |
|---|---|---|---|---|---|---|---|---|
| 6.1077 | 1.0 | 983 | 4.0188 | 43.2477 | 20.5883 | 32.4924 | 32.4698 | 43.22 |
| 4.1381 | 2.0 | 1966 | 3.6100 | 45.0943 | 20.3874 | 31.9574 | 31.9446 | 42.65 |
| 3.8582 | 3.0 | 2949 | 3.5387 | 45.3465 | 20.3438 | 32.6884 | 32.6636 | 41.51 |
Framework versions
- Transformers 4.31.0
- Pytorch 2.0.1+cu117
- Datasets 2.14.2
- Tokenizers 0.13.3