End of training
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 |
|
@@ -52,50 +52,40 @@ 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 |
- mixed_precision_training: Native AMP
|
64 |
|
65 |
### Training results
|
66 |
|
67 |
-
| Training Loss | Epoch | Step |
|
68 |
-
|
69 |
-
| 2.
|
70 |
-
| 1.
|
71 |
-
|
|
72 |
-
|
|
73 |
-
|
|
74 |
-
|
|
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 |
-
| 0.3051 | 21.0 | 2373 | 0.83 | 0.5843 |
|
90 |
-
| 0.3558 | 22.0 | 2486 | 0.6144 | 0.79 |
|
91 |
-
| 0.3371 | 23.0 | 2599 | 0.5673 | 0.81 |
|
92 |
-
| 0.2882 | 24.0 | 2712 | 0.5365 | 0.84 |
|
93 |
-
| 0.2326 | 25.0 | 2825 | 0.5848 | 0.83 |
|
94 |
-
| 0.192 | 26.0 | 2938 | 0.5406 | 0.85 |
|
95 |
-
| 0.1528 | 27.0 | 3051 | 0.5482 | 0.82 |
|
96 |
-
| 0.1937 | 28.0 | 3164 | 0.5448 | 0.84 |
|
97 |
-
| 0.1264 | 29.0 | 3277 | 0.5487 | 0.84 |
|
98 |
-
| 0.1356 | 30.0 | 3390 | 0.5510 | 0.82 |
|
99 |
|
100 |
|
101 |
### Framework versions
|
|
|
22 |
metrics:
|
23 |
- name: Accuracy
|
24 |
type: accuracy
|
25 |
+
value: 0.87
|
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: 1.1035
|
36 |
+
- Accuracy: 0.87
|
37 |
|
38 |
## Model description
|
39 |
|
|
|
52 |
### Training hyperparameters
|
53 |
|
54 |
The following hyperparameters were used during training:
|
55 |
+
- learning_rate: 5e-05
|
56 |
+
- train_batch_size: 4
|
57 |
+
- eval_batch_size: 4
|
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: 20
|
63 |
- mixed_precision_training: Native AMP
|
64 |
|
65 |
### Training results
|
66 |
|
67 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
68 |
+
|:-------------:|:-----:|:----:|:---------------:|:--------:|
|
69 |
+
| 2.0544 | 1.0 | 225 | 1.9608 | 0.47 |
|
70 |
+
| 1.2995 | 2.0 | 450 | 1.3852 | 0.51 |
|
71 |
+
| 0.8875 | 3.0 | 675 | 0.9288 | 0.71 |
|
72 |
+
| 0.4092 | 4.0 | 900 | 0.8114 | 0.76 |
|
73 |
+
| 0.5624 | 5.0 | 1125 | 0.8704 | 0.77 |
|
74 |
+
| 0.0609 | 6.0 | 1350 | 0.7951 | 0.82 |
|
75 |
+
| 0.1018 | 7.0 | 1575 | 0.7055 | 0.86 |
|
76 |
+
| 0.2941 | 8.0 | 1800 | 0.8832 | 0.83 |
|
77 |
+
| 0.0044 | 9.0 | 2025 | 0.9883 | 0.83 |
|
78 |
+
| 0.0025 | 10.0 | 2250 | 0.9306 | 0.88 |
|
79 |
+
| 0.0016 | 11.0 | 2475 | 0.9535 | 0.86 |
|
80 |
+
| 0.0012 | 12.0 | 2700 | 1.0921 | 0.85 |
|
81 |
+
| 0.001 | 13.0 | 2925 | 1.0428 | 0.86 |
|
82 |
+
| 0.0011 | 14.0 | 3150 | 1.2270 | 0.83 |
|
83 |
+
| 0.0008 | 15.0 | 3375 | 1.1831 | 0.84 |
|
84 |
+
| 0.0007 | 16.0 | 3600 | 1.2124 | 0.84 |
|
85 |
+
| 0.0007 | 17.0 | 3825 | 1.0806 | 0.86 |
|
86 |
+
| 0.2454 | 18.0 | 4050 | 1.1530 | 0.85 |
|
87 |
+
| 0.0006 | 19.0 | 4275 | 1.1078 | 0.86 |
|
88 |
+
| 0.0006 | 20.0 | 4500 | 1.1035 | 0.87 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
89 |
|
90 |
|
91 |
### Framework versions
|
model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 94771728
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1c29763feeb5c84fe05a95fc2df04f78cadfed7ec1b5729ced944f1e763a0843
|
3 |
size 94771728
|
runs/Apr18_16-24-35_60760ba8fdb5/events.out.tfevents.1713458217.60760ba8fdb5.319.0
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0bbb0a798e979558895ea31907c6215c350dc4108047c484123447eb4e28a906
|
3 |
+
size 202424
|