update model card README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,69 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
base_model: ''
|
| 3 |
+
tags:
|
| 4 |
+
- generated_from_trainer
|
| 5 |
+
metrics:
|
| 6 |
+
- rouge
|
| 7 |
+
model-index:
|
| 8 |
+
- name: hubert2BertMusicTestL5e7
|
| 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 |
+
# hubert2BertMusicTestL5e7
|
| 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: 2.2639
|
| 20 |
+
- Rouge1: 28.296
|
| 21 |
+
- Rouge2: 7.1646
|
| 22 |
+
- Rougel: 20.2478
|
| 23 |
+
- Rougelsum: 20.191
|
| 24 |
+
- Gen Len: 58.92
|
| 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: 3e-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: 7
|
| 50 |
+
|
| 51 |
+
### Training results
|
| 52 |
+
|
| 53 |
+
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
|
| 54 |
+
|:-------------:|:-----:|:----:|:---------------:|:-------:|:------:|:-------:|:---------:|:-------:|
|
| 55 |
+
| 4.7701 | 1.0 | 1361 | 3.6345 | 29.4772 | 6.5481 | 21.1446 | 21.1031 | 51.04 |
|
| 56 |
+
| 3.3104 | 2.0 | 2722 | 2.9389 | 24.7952 | 6.9239 | 19.4001 | 19.4318 | 31.01 |
|
| 57 |
+
| 2.9088 | 3.0 | 4083 | 2.6221 | 29.6422 | 7.2219 | 21.0592 | 21.0778 | 57.25 |
|
| 58 |
+
| 2.7274 | 4.0 | 5444 | 2.4599 | 28.0386 | 8.311 | 20.629 | 20.6316 | 50.06 |
|
| 59 |
+
| 2.6417 | 5.0 | 6805 | 2.3503 | 28.7788 | 8.8058 | 21.2309 | 21.2204 | 57.54 |
|
| 60 |
+
| 2.5002 | 6.0 | 8166 | 2.2905 | 31.5292 | 8.3235 | 22.2364 | 22.2584 | 65.09 |
|
| 61 |
+
| 2.4481 | 7.0 | 9527 | 2.2639 | 28.296 | 7.1646 | 20.2478 | 20.191 | 58.92 |
|
| 62 |
+
|
| 63 |
+
|
| 64 |
+
### Framework versions
|
| 65 |
+
|
| 66 |
+
- Transformers 4.31.0
|
| 67 |
+
- Pytorch 2.0.1+cu117
|
| 68 |
+
- Datasets 2.14.2
|
| 69 |
+
- Tokenizers 0.13.3
|