Model save
Browse files
README.md
ADDED
|
@@ -0,0 +1,82 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
base_model: facebook/musicgen-medium
|
| 3 |
+
library_name: peft
|
| 4 |
+
license: cc-by-nc-4.0
|
| 5 |
+
tags:
|
| 6 |
+
- generated_from_trainer
|
| 7 |
+
model-index:
|
| 8 |
+
- name: musicgen-medium
|
| 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 |
+
# musicgen-medium
|
| 16 |
+
|
| 17 |
+
This model is a fine-tuned version of [facebook/musicgen-medium](https://huggingface.co/facebook/musicgen-medium) on an unknown dataset.
|
| 18 |
+
It achieves the following results on the evaluation set:
|
| 19 |
+
- Loss: 5.5468
|
| 20 |
+
- Clap: -0.0809
|
| 21 |
+
|
| 22 |
+
## Model description
|
| 23 |
+
|
| 24 |
+
More information needed
|
| 25 |
+
|
| 26 |
+
## Intended uses & limitations
|
| 27 |
+
|
| 28 |
+
More information needed
|
| 29 |
+
|
| 30 |
+
## Training and evaluation data
|
| 31 |
+
|
| 32 |
+
More information needed
|
| 33 |
+
|
| 34 |
+
## Training procedure
|
| 35 |
+
|
| 36 |
+
### Training hyperparameters
|
| 37 |
+
|
| 38 |
+
The following hyperparameters were used during training:
|
| 39 |
+
- learning_rate: 0.0002
|
| 40 |
+
- train_batch_size: 2
|
| 41 |
+
- eval_batch_size: 1
|
| 42 |
+
- seed: 456
|
| 43 |
+
- gradient_accumulation_steps: 8
|
| 44 |
+
- total_train_batch_size: 16
|
| 45 |
+
- optimizer: Use adamw_torch with betas=(0.9,0.99) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
|
| 46 |
+
- lr_scheduler_type: linear
|
| 47 |
+
- num_epochs: 10.0
|
| 48 |
+
- mixed_precision_training: Native AMP
|
| 49 |
+
|
| 50 |
+
### Training results
|
| 51 |
+
|
| 52 |
+
| Training Loss | Epoch | Step | Validation Loss | Clap |
|
| 53 |
+
|:-------------:|:------:|:----:|:---------------:|:-------:|
|
| 54 |
+
| 44.9355 | 0.4739 | 25 | 6.4378 | -0.0786 |
|
| 55 |
+
| 38.3323 | 0.9479 | 50 | 5.7564 | -0.0774 |
|
| 56 |
+
| 37.6585 | 1.4265 | 75 | 5.9326 | -0.0850 |
|
| 57 |
+
| 35.814 | 1.9005 | 100 | 5.8116 | -0.1029 |
|
| 58 |
+
| 38.6656 | 2.3791 | 125 | 6.4027 | -0.0678 |
|
| 59 |
+
| 39.4825 | 2.8531 | 150 | 14.8689 | 0.1094 |
|
| 60 |
+
| 38.0107 | 3.3318 | 175 | 9.4517 | -0.0727 |
|
| 61 |
+
| 31.663 | 3.8057 | 200 | 6.2469 | -0.0694 |
|
| 62 |
+
| 26.0169 | 4.2844 | 225 | 5.8747 | -0.0536 |
|
| 63 |
+
| 40.9899 | 4.7583 | 250 | 5.7418 | -0.0746 |
|
| 64 |
+
| 32.5293 | 5.2370 | 275 | 5.7128 | -0.0553 |
|
| 65 |
+
| 36.4987 | 5.7109 | 300 | 5.6100 | -0.0852 |
|
| 66 |
+
| 31.5365 | 6.1896 | 325 | 5.6516 | -0.0611 |
|
| 67 |
+
| 28.7596 | 6.6635 | 350 | 5.6693 | -0.0820 |
|
| 68 |
+
| 45.4104 | 7.1422 | 375 | 5.5758 | -0.0880 |
|
| 69 |
+
| 27.6256 | 7.6161 | 400 | 5.5985 | -0.0592 |
|
| 70 |
+
| 35.2245 | 8.0948 | 425 | 5.5941 | -0.0993 |
|
| 71 |
+
| 38.0101 | 8.5687 | 450 | 5.5649 | -0.0683 |
|
| 72 |
+
| 37.5459 | 9.0474 | 475 | 5.5382 | -0.0948 |
|
| 73 |
+
| 35.274 | 9.5213 | 500 | 5.5468 | -0.0809 |
|
| 74 |
+
|
| 75 |
+
|
| 76 |
+
### Framework versions
|
| 77 |
+
|
| 78 |
+
- PEFT 0.13.2
|
| 79 |
+
- Transformers 4.46.0.dev0
|
| 80 |
+
- Pytorch 2.1.2+cu121
|
| 81 |
+
- Datasets 3.0.1
|
| 82 |
+
- Tokenizers 0.20.1
|