Sandiago21
commited on
Commit
•
a84820d
1
Parent(s):
93f335c
update model card README.md
Browse files
README.md
CHANGED
@@ -18,8 +18,8 @@ should probably proofread and complete it, then remove this comment. -->
|
|
18 |
|
19 |
This model is a fine-tuned version of [facebook/hubert-large-ll60k](https://huggingface.co/facebook/hubert-large-ll60k) on the GTZAN dataset.
|
20 |
It achieves the following results on the evaluation set:
|
21 |
-
- Loss:
|
22 |
-
- Accuracy: 0.
|
23 |
|
24 |
## Model description
|
25 |
|
@@ -38,39 +38,31 @@ More information needed
|
|
38 |
### Training hyperparameters
|
39 |
|
40 |
The following hyperparameters were used during training:
|
41 |
-
- learning_rate:
|
42 |
- train_batch_size: 2
|
43 |
- eval_batch_size: 2
|
44 |
- seed: 42
|
45 |
-
- gradient_accumulation_steps:
|
46 |
-
- total_train_batch_size:
|
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:
|
51 |
|
52 |
### Training results
|
53 |
|
54 |
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
55 |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
|
56 |
-
| 2.
|
57 |
-
|
|
58 |
-
| 1.
|
59 |
-
| 1.
|
60 |
-
|
|
61 |
-
|
|
62 |
-
|
|
63 |
-
|
|
64 |
-
|
|
65 |
-
| 0.
|
66 |
-
| 0.0 | 11.0 | 1237 | nan | 0.1 |
|
67 |
-
| 0.0 | 12.0 | 1350 | nan | 0.1 |
|
68 |
-
| 0.0 | 13.0 | 1462 | nan | 0.1 |
|
69 |
-
| 0.0 | 14.0 | 1575 | nan | 0.1 |
|
70 |
-
| 0.0 | 15.0 | 1687 | nan | 0.1 |
|
71 |
-
| 0.0 | 16.0 | 1800 | nan | 0.1 |
|
72 |
-
| 0.0 | 17.0 | 1912 | nan | 0.1 |
|
73 |
-
| 0.0 | 17.92 | 2016 | nan | 0.1 |
|
74 |
|
75 |
|
76 |
### Framework versions
|
|
|
18 |
|
19 |
This model is a fine-tuned version of [facebook/hubert-large-ll60k](https://huggingface.co/facebook/hubert-large-ll60k) on the GTZAN dataset.
|
20 |
It achieves the following results on the evaluation set:
|
21 |
+
- Loss: 0.9220
|
22 |
+
- Accuracy: 0.73
|
23 |
|
24 |
## Model description
|
25 |
|
|
|
38 |
### Training hyperparameters
|
39 |
|
40 |
The following hyperparameters were used during training:
|
41 |
+
- learning_rate: 7e-05
|
42 |
- train_batch_size: 2
|
43 |
- eval_batch_size: 2
|
44 |
- seed: 42
|
45 |
+
- gradient_accumulation_steps: 8
|
46 |
+
- total_train_batch_size: 16
|
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: 10
|
51 |
|
52 |
### Training results
|
53 |
|
54 |
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
55 |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
|
56 |
+
| 2.2456 | 1.0 | 56 | 2.2312 | 0.34 |
|
57 |
+
| 2.059 | 1.99 | 112 | 1.9662 | 0.32 |
|
58 |
+
| 1.8574 | 2.99 | 168 | 1.6258 | 0.5 |
|
59 |
+
| 1.4447 | 4.0 | 225 | 1.4547 | 0.59 |
|
60 |
+
| 1.4224 | 5.0 | 281 | 1.2372 | 0.65 |
|
61 |
+
| 1.2131 | 5.99 | 337 | 1.0879 | 0.67 |
|
62 |
+
| 1.1151 | 6.99 | 393 | 1.0599 | 0.69 |
|
63 |
+
| 0.9471 | 8.0 | 450 | 1.0339 | 0.68 |
|
64 |
+
| 1.0319 | 9.0 | 506 | 0.9568 | 0.71 |
|
65 |
+
| 0.9313 | 9.96 | 560 | 0.9220 | 0.73 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
66 |
|
67 |
|
68 |
### Framework versions
|