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 [ntu-spml/distilhubert](https://huggingface.co/ntu-spml/distilhubert) on the GTZAN dataset.
|
20 |
It achieves the following results on the evaluation set:
|
21 |
-
- Loss:
|
22 |
-
- Accuracy: 0.
|
23 |
|
24 |
## Model description
|
25 |
|
@@ -38,41 +38,53 @@ More information needed
|
|
38 |
### Training hyperparameters
|
39 |
|
40 |
The following hyperparameters were used during training:
|
41 |
-
- learning_rate:
|
42 |
-
- train_batch_size:
|
43 |
-
- eval_batch_size:
|
44 |
- seed: 42
|
45 |
- distributed_type: multi-GPU
|
|
|
|
|
46 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
47 |
- lr_scheduler_type: linear
|
48 |
- lr_scheduler_warmup_ratio: 0.1
|
49 |
-
- num_epochs:
|
50 |
- mixed_precision_training: Native AMP
|
51 |
|
52 |
### Training results
|
53 |
|
54 |
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
55 |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
|
56 |
-
| 2.
|
57 |
-
| 1.
|
58 |
-
| 1.
|
59 |
-
|
|
60 |
-
|
|
61 |
-
|
|
62 |
-
| 0.
|
63 |
-
| 0.
|
64 |
-
| 0.
|
65 |
-
| 0.
|
66 |
-
| 0.
|
67 |
-
| 0.
|
68 |
-
| 0.
|
69 |
-
| 0.
|
70 |
-
| 0.
|
71 |
-
| 0.
|
72 |
-
| 0.
|
73 |
-
| 0.
|
74 |
-
| 0.
|
75 |
-
| 0.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
76 |
|
77 |
|
78 |
### Framework versions
|
|
|
18 |
|
19 |
This model is a fine-tuned version of [ntu-spml/distilhubert](https://huggingface.co/ntu-spml/distilhubert) on the GTZAN dataset.
|
20 |
It achieves the following results on the evaluation set:
|
21 |
+
- Loss: 1.2658
|
22 |
+
- Accuracy: 0.8
|
23 |
|
24 |
## Model description
|
25 |
|
|
|
38 |
### Training hyperparameters
|
39 |
|
40 |
The following hyperparameters were used during training:
|
41 |
+
- learning_rate: 5e-05
|
42 |
+
- train_batch_size: 4
|
43 |
+
- eval_batch_size: 4
|
44 |
- seed: 42
|
45 |
- distributed_type: multi-GPU
|
46 |
+
- gradient_accumulation_steps: 2
|
47 |
+
- total_train_batch_size: 8
|
48 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
49 |
- lr_scheduler_type: linear
|
50 |
- lr_scheduler_warmup_ratio: 0.1
|
51 |
+
- num_epochs: 30
|
52 |
- mixed_precision_training: Native AMP
|
53 |
|
54 |
### Training results
|
55 |
|
56 |
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
57 |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
|
58 |
+
| 2.1071 | 1.0 | 112 | 2.1453 | 0.33 |
|
59 |
+
| 1.6165 | 2.0 | 225 | 1.6129 | 0.59 |
|
60 |
+
| 1.2842 | 3.0 | 337 | 1.2084 | 0.68 |
|
61 |
+
| 0.9805 | 4.0 | 450 | 0.8842 | 0.74 |
|
62 |
+
| 0.5216 | 5.0 | 562 | 0.7350 | 0.78 |
|
63 |
+
| 0.5017 | 6.0 | 675 | 0.8196 | 0.77 |
|
64 |
+
| 0.1998 | 7.0 | 787 | 0.6709 | 0.8 |
|
65 |
+
| 0.3662 | 8.0 | 900 | 0.8483 | 0.78 |
|
66 |
+
| 0.2711 | 9.0 | 1012 | 0.8567 | 0.81 |
|
67 |
+
| 0.0183 | 10.0 | 1125 | 0.8994 | 0.82 |
|
68 |
+
| 0.0299 | 11.0 | 1237 | 1.2142 | 0.8 |
|
69 |
+
| 0.0064 | 12.0 | 1350 | 1.0208 | 0.81 |
|
70 |
+
| 0.004 | 13.0 | 1462 | 1.0619 | 0.81 |
|
71 |
+
| 0.0031 | 14.0 | 1575 | 1.1454 | 0.79 |
|
72 |
+
| 0.0028 | 15.0 | 1687 | 1.1010 | 0.81 |
|
73 |
+
| 0.0023 | 16.0 | 1800 | 1.0595 | 0.8 |
|
74 |
+
| 0.0017 | 17.0 | 1912 | 1.1340 | 0.8 |
|
75 |
+
| 0.0015 | 18.0 | 2025 | 1.1760 | 0.81 |
|
76 |
+
| 0.0014 | 19.0 | 2137 | 1.1361 | 0.81 |
|
77 |
+
| 0.0012 | 20.0 | 2250 | 1.2138 | 0.81 |
|
78 |
+
| 0.0011 | 21.0 | 2362 | 1.1366 | 0.81 |
|
79 |
+
| 0.0012 | 22.0 | 2475 | 1.1662 | 0.8 |
|
80 |
+
| 0.0011 | 23.0 | 2587 | 1.1491 | 0.8 |
|
81 |
+
| 0.0009 | 24.0 | 2700 | 1.1287 | 0.81 |
|
82 |
+
| 0.0009 | 25.0 | 2812 | 1.2027 | 0.81 |
|
83 |
+
| 0.0009 | 26.0 | 2925 | 1.1740 | 0.81 |
|
84 |
+
| 0.0009 | 27.0 | 3037 | 1.2011 | 0.81 |
|
85 |
+
| 0.0009 | 28.0 | 3150 | 1.2523 | 0.8 |
|
86 |
+
| 0.0008 | 29.0 | 3262 | 1.2494 | 0.81 |
|
87 |
+
| 0.0007 | 29.87 | 3360 | 1.2658 | 0.8 |
|
88 |
|
89 |
|
90 |
### Framework versions
|