update model card README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,72 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
base_model: ''
|
| 3 |
+
tags:
|
| 4 |
+
- generated_from_trainer
|
| 5 |
+
metrics:
|
| 6 |
+
- rouge
|
| 7 |
+
model-index:
|
| 8 |
+
- name: hubert2BertMusic100
|
| 9 |
+
results: []
|
| 10 |
+
---
|
| 11 |
+
|
| 12 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 13 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 14 |
+
|
| 15 |
+
# hubert2BertMusic100
|
| 16 |
+
|
| 17 |
+
This model is a fine-tuned version of [](https://huggingface.co/) on an unknown dataset.
|
| 18 |
+
It achieves the following results on the evaluation set:
|
| 19 |
+
- Loss: 2.5867
|
| 20 |
+
- Rouge1: 36.0915
|
| 21 |
+
- Rouge2: 12.101
|
| 22 |
+
- Rougel: 26.2764
|
| 23 |
+
- Rougelsum: 26.2441
|
| 24 |
+
- Gen Len: 25.98
|
| 25 |
+
|
| 26 |
+
## Model description
|
| 27 |
+
|
| 28 |
+
More information needed
|
| 29 |
+
|
| 30 |
+
## Intended uses & limitations
|
| 31 |
+
|
| 32 |
+
More information needed
|
| 33 |
+
|
| 34 |
+
## Training and evaluation data
|
| 35 |
+
|
| 36 |
+
More information needed
|
| 37 |
+
|
| 38 |
+
## Training procedure
|
| 39 |
+
|
| 40 |
+
### Training hyperparameters
|
| 41 |
+
|
| 42 |
+
The following hyperparameters were used during training:
|
| 43 |
+
- learning_rate: 5e-05
|
| 44 |
+
- train_batch_size: 4
|
| 45 |
+
- eval_batch_size: 4
|
| 46 |
+
- seed: 42
|
| 47 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 48 |
+
- lr_scheduler_type: linear
|
| 49 |
+
- num_epochs: 10
|
| 50 |
+
|
| 51 |
+
### Training results
|
| 52 |
+
|
| 53 |
+
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
|
| 54 |
+
|:-------------:|:-----:|:----:|:---------------:|:-------:|:-------:|:-------:|:---------:|:-------:|
|
| 55 |
+
| 5.4394 | 1.0 | 983 | 4.7204 | 22.0764 | 4.0274 | 20.3934 | 20.4011 | 61.19 |
|
| 56 |
+
| 4.8173 | 2.0 | 1966 | 4.2071 | 35.9784 | 15.4735 | 29.1397 | 29.0838 | 34.98 |
|
| 57 |
+
| 4.2216 | 3.0 | 2949 | 3.6499 | 39.0915 | 15.7932 | 29.828 | 29.8062 | 32.73 |
|
| 58 |
+
| 3.7867 | 4.0 | 3932 | 3.3676 | 38.2403 | 15.4761 | 28.9872 | 28.9768 | 28.6 |
|
| 59 |
+
| 3.502 | 5.0 | 4915 | 3.1133 | 41.6179 | 17.8598 | 29.2306 | 29.2435 | 29.2 |
|
| 60 |
+
| 3.2367 | 6.0 | 5898 | 2.8908 | 36.6649 | 13.4593 | 27.1849 | 27.2161 | 26.21 |
|
| 61 |
+
| 3.079 | 7.0 | 6881 | 2.7573 | 35.1153 | 11.8019 | 25.6868 | 25.6664 | 23.17 |
|
| 62 |
+
| 2.9658 | 8.0 | 7864 | 2.6532 | 39.4462 | 13.8979 | 28.2899 | 28.296 | 33.88 |
|
| 63 |
+
| 2.8801 | 9.0 | 8847 | 2.6063 | 39.2319 | 13.9339 | 28.2368 | 28.265 | 30.96 |
|
| 64 |
+
| 2.8509 | 10.0 | 9830 | 2.5867 | 36.0915 | 12.101 | 26.2764 | 26.2441 | 25.98 |
|
| 65 |
+
|
| 66 |
+
|
| 67 |
+
### Framework versions
|
| 68 |
+
|
| 69 |
+
- Transformers 4.31.0
|
| 70 |
+
- Pytorch 2.0.1+cu117
|
| 71 |
+
- Datasets 2.14.2
|
| 72 |
+
- Tokenizers 0.13.3
|