update model card README.md
Browse files
README.md
CHANGED
@@ -22,7 +22,7 @@ model-index:
|
|
22 |
metrics:
|
23 |
- name: Accuracy
|
24 |
type: accuracy
|
25 |
-
value: 0.
|
26 |
---
|
27 |
|
28 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
@@ -32,8 +32,8 @@ should probably proofread and complete it, then remove this comment. -->
|
|
32 |
|
33 |
This model is a fine-tuned version of [ntu-spml/distilhubert](https://huggingface.co/ntu-spml/distilhubert) on the GTZAN dataset.
|
34 |
It achieves the following results on the evaluation set:
|
35 |
-
- Loss:
|
36 |
-
- Accuracy: 0.
|
37 |
|
38 |
## Model description
|
39 |
|
@@ -52,49 +52,69 @@ More information needed
|
|
52 |
### Training hyperparameters
|
53 |
|
54 |
The following hyperparameters were used during training:
|
55 |
-
- learning_rate:
|
56 |
-
- train_batch_size:
|
57 |
-
- eval_batch_size:
|
58 |
- seed: 42
|
59 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
60 |
- lr_scheduler_type: linear
|
61 |
- lr_scheduler_warmup_ratio: 0.1
|
62 |
-
- num_epochs:
|
63 |
|
64 |
### Training results
|
65 |
|
66 |
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
67 |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
|
68 |
-
| 2.
|
69 |
-
|
|
70 |
-
| 1.
|
71 |
-
| 1.
|
72 |
-
|
|
73 |
-
| 0.
|
74 |
-
| 0.
|
75 |
-
| 0.
|
76 |
-
| 0.
|
77 |
-
| 0.
|
78 |
-
| 0.
|
79 |
-
| 0.
|
80 |
-
| 0.
|
81 |
-
| 0.
|
82 |
-
| 0.
|
83 |
-
| 0.
|
84 |
-
| 0.
|
85 |
-
| 0.
|
86 |
-
| 0.
|
87 |
-
| 0.
|
88 |
-
| 0.
|
89 |
-
| 0.
|
90 |
-
| 0.
|
91 |
-
| 0.
|
92 |
-
| 0.
|
93 |
-
| 0.
|
94 |
-
| 0.
|
95 |
-
| 0.
|
96 |
-
| 0.
|
97 |
-
| 0.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
98 |
|
99 |
|
100 |
### Framework versions
|
|
|
22 |
metrics:
|
23 |
- name: Accuracy
|
24 |
type: accuracy
|
25 |
+
value: 0.82
|
26 |
---
|
27 |
|
28 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
|
32 |
|
33 |
This model is a fine-tuned version of [ntu-spml/distilhubert](https://huggingface.co/ntu-spml/distilhubert) on the GTZAN dataset.
|
34 |
It achieves the following results on the evaluation set:
|
35 |
+
- Loss: 1.0389
|
36 |
+
- Accuracy: 0.82
|
37 |
|
38 |
## Model description
|
39 |
|
|
|
52 |
### Training hyperparameters
|
53 |
|
54 |
The following hyperparameters were used during training:
|
55 |
+
- learning_rate: 0.0001
|
56 |
+
- train_batch_size: 32
|
57 |
+
- eval_batch_size: 32
|
58 |
- seed: 42
|
59 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
60 |
- lr_scheduler_type: linear
|
61 |
- lr_scheduler_warmup_ratio: 0.1
|
62 |
+
- num_epochs: 50
|
63 |
|
64 |
### Training results
|
65 |
|
66 |
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
67 |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
|
68 |
+
| 2.2599 | 1.0 | 29 | 2.2083 | 0.3 |
|
69 |
+
| 2.0587 | 2.0 | 58 | 1.9010 | 0.48 |
|
70 |
+
| 1.7008 | 3.0 | 87 | 1.5654 | 0.57 |
|
71 |
+
| 1.3211 | 4.0 | 116 | 1.2700 | 0.64 |
|
72 |
+
| 1.0132 | 5.0 | 145 | 1.0324 | 0.7 |
|
73 |
+
| 0.8396 | 6.0 | 174 | 0.9723 | 0.7 |
|
74 |
+
| 0.6316 | 7.0 | 203 | 0.8609 | 0.78 |
|
75 |
+
| 0.4653 | 8.0 | 232 | 0.7132 | 0.82 |
|
76 |
+
| 0.3607 | 9.0 | 261 | 0.7140 | 0.82 |
|
77 |
+
| 0.2226 | 10.0 | 290 | 0.6465 | 0.85 |
|
78 |
+
| 0.0988 | 11.0 | 319 | 0.6593 | 0.83 |
|
79 |
+
| 0.0767 | 12.0 | 348 | 0.8247 | 0.83 |
|
80 |
+
| 0.0674 | 13.0 | 377 | 0.7143 | 0.84 |
|
81 |
+
| 0.0396 | 14.0 | 406 | 0.9098 | 0.77 |
|
82 |
+
| 0.0467 | 15.0 | 435 | 0.9512 | 0.76 |
|
83 |
+
| 0.0101 | 16.0 | 464 | 0.9639 | 0.79 |
|
84 |
+
| 0.0064 | 17.0 | 493 | 0.7893 | 0.87 |
|
85 |
+
| 0.0322 | 18.0 | 522 | 0.9502 | 0.84 |
|
86 |
+
| 0.0055 | 19.0 | 551 | 0.9125 | 0.82 |
|
87 |
+
| 0.0043 | 20.0 | 580 | 1.1760 | 0.79 |
|
88 |
+
| 0.0033 | 21.0 | 609 | 1.0341 | 0.81 |
|
89 |
+
| 0.0031 | 22.0 | 638 | 0.9639 | 0.82 |
|
90 |
+
| 0.0024 | 23.0 | 667 | 1.0063 | 0.81 |
|
91 |
+
| 0.0022 | 24.0 | 696 | 0.9636 | 0.83 |
|
92 |
+
| 0.0018 | 25.0 | 725 | 1.0178 | 0.82 |
|
93 |
+
| 0.0076 | 26.0 | 754 | 0.9735 | 0.82 |
|
94 |
+
| 0.0018 | 27.0 | 783 | 1.0344 | 0.83 |
|
95 |
+
| 0.0016 | 28.0 | 812 | 0.9294 | 0.83 |
|
96 |
+
| 0.0126 | 29.0 | 841 | 0.9821 | 0.83 |
|
97 |
+
| 0.0153 | 30.0 | 870 | 1.0450 | 0.81 |
|
98 |
+
| 0.0014 | 31.0 | 899 | 0.9760 | 0.82 |
|
99 |
+
| 0.0078 | 32.0 | 928 | 0.9816 | 0.82 |
|
100 |
+
| 0.0012 | 33.0 | 957 | 1.0110 | 0.84 |
|
101 |
+
| 0.0012 | 34.0 | 986 | 1.0529 | 0.84 |
|
102 |
+
| 0.0011 | 35.0 | 1015 | 1.0165 | 0.81 |
|
103 |
+
| 0.0011 | 36.0 | 1044 | 0.9932 | 0.82 |
|
104 |
+
| 0.0011 | 37.0 | 1073 | 1.0577 | 0.83 |
|
105 |
+
| 0.001 | 38.0 | 1102 | 1.0322 | 0.82 |
|
106 |
+
| 0.001 | 39.0 | 1131 | 1.0170 | 0.82 |
|
107 |
+
| 0.001 | 40.0 | 1160 | 1.0243 | 0.84 |
|
108 |
+
| 0.0009 | 41.0 | 1189 | 1.0295 | 0.82 |
|
109 |
+
| 0.0056 | 42.0 | 1218 | 1.0291 | 0.82 |
|
110 |
+
| 0.0066 | 43.0 | 1247 | 1.0272 | 0.82 |
|
111 |
+
| 0.0009 | 44.0 | 1276 | 1.0522 | 0.83 |
|
112 |
+
| 0.0009 | 45.0 | 1305 | 1.0418 | 0.82 |
|
113 |
+
| 0.0009 | 46.0 | 1334 | 1.0448 | 0.82 |
|
114 |
+
| 0.0009 | 47.0 | 1363 | 1.0423 | 0.82 |
|
115 |
+
| 0.0058 | 48.0 | 1392 | 1.0344 | 0.82 |
|
116 |
+
| 0.0054 | 49.0 | 1421 | 1.0364 | 0.82 |
|
117 |
+
| 0.0009 | 50.0 | 1450 | 1.0389 | 0.82 |
|
118 |
|
119 |
|
120 |
### Framework versions
|