Commit
•
718be7e
1
Parent(s):
b2b42d1
update model card README.md
Browse files
README.md
ADDED
@@ -0,0 +1,83 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: apache-2.0
|
3 |
+
tags:
|
4 |
+
- generated_from_trainer
|
5 |
+
datasets:
|
6 |
+
- marsyas/gtzan
|
7 |
+
metrics:
|
8 |
+
- accuracy
|
9 |
+
model-index:
|
10 |
+
- name: hubert-large-ls960-ft-finetuned-gtzan
|
11 |
+
results: []
|
12 |
+
---
|
13 |
+
|
14 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
15 |
+
should probably proofread and complete it, then remove this comment. -->
|
16 |
+
|
17 |
+
# hubert-large-ls960-ft-finetuned-gtzan
|
18 |
+
|
19 |
+
This model is a fine-tuned version of [facebook/hubert-large-ls960-ft](https://huggingface.co/facebook/hubert-large-ls960-ft) on the GTZAN dataset.
|
20 |
+
It achieves the following results on the evaluation set:
|
21 |
+
- Loss: nan
|
22 |
+
- Accuracy: 0.8
|
23 |
+
|
24 |
+
## Model description
|
25 |
+
|
26 |
+
More information needed
|
27 |
+
|
28 |
+
## Intended uses & limitations
|
29 |
+
|
30 |
+
More information needed
|
31 |
+
|
32 |
+
## Training and evaluation data
|
33 |
+
|
34 |
+
More information needed
|
35 |
+
|
36 |
+
## Training procedure
|
37 |
+
|
38 |
+
### Training hyperparameters
|
39 |
+
|
40 |
+
The following hyperparameters were used during training:
|
41 |
+
- learning_rate: 5e-05
|
42 |
+
- train_batch_size: 2
|
43 |
+
- eval_batch_size: 2
|
44 |
+
- seed: 42
|
45 |
+
- gradient_accumulation_steps: 4
|
46 |
+
- total_train_batch_size: 8
|
47 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
48 |
+
- lr_scheduler_type: linear
|
49 |
+
- lr_scheduler_warmup_ratio: 0.1
|
50 |
+
- num_epochs: 20
|
51 |
+
|
52 |
+
### Training results
|
53 |
+
|
54 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
55 |
+
|:-------------:|:-----:|:----:|:---------------:|:--------:|
|
56 |
+
| 2.2564 | 1.0 | 112 | 2.2597 | 0.37 |
|
57 |
+
| 1.6529 | 2.0 | 225 | 1.8087 | 0.27 |
|
58 |
+
| 1.4922 | 3.0 | 337 | 1.4067 | 0.48 |
|
59 |
+
| 1.3749 | 4.0 | 450 | 1.3045 | 0.55 |
|
60 |
+
| 0.9226 | 5.0 | 562 | 1.1160 | 0.64 |
|
61 |
+
| 0.8591 | 6.0 | 675 | 0.8981 | 0.69 |
|
62 |
+
| 0.5988 | 7.0 | 787 | 0.9898 | 0.71 |
|
63 |
+
| 1.0143 | 8.0 | 900 | 1.0200 | 0.69 |
|
64 |
+
| 0.464 | 9.0 | 1012 | 0.5678 | 0.82 |
|
65 |
+
| 0.6969 | 10.0 | 1125 | 0.7087 | 0.81 |
|
66 |
+
| 0.5547 | 11.0 | 1237 | 0.7278 | 0.75 |
|
67 |
+
| 0.2638 | 12.0 | 1350 | 0.7599 | 0.8 |
|
68 |
+
| 0.3504 | 13.0 | 1462 | 0.6778 | 0.85 |
|
69 |
+
| 0.106 | 14.0 | 1575 | 0.7504 | 0.82 |
|
70 |
+
| 0.3392 | 15.0 | 1687 | 0.7514 | 0.84 |
|
71 |
+
| 0.1516 | 16.0 | 1800 | 0.8678 | 0.8 |
|
72 |
+
| 0.1324 | 17.0 | 1912 | 0.7644 | 0.84 |
|
73 |
+
| 0.0827 | 18.0 | 2025 | nan | 0.8 |
|
74 |
+
| 0.45 | 19.0 | 2137 | nan | 0.8 |
|
75 |
+
| 0.2407 | 19.91 | 2240 | nan | 0.8 |
|
76 |
+
|
77 |
+
|
78 |
+
### Framework versions
|
79 |
+
|
80 |
+
- Transformers 4.30.0.dev0
|
81 |
+
- Pytorch 2.0.1+cu117
|
82 |
+
- Datasets 2.13.1
|
83 |
+
- Tokenizers 0.13.3
|