timothy-geiger
commited on
Commit
•
6e1aa35
1
Parent(s):
be55d72
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 |
|
@@ -52,35 +52,30 @@ 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 | Validation Loss | Accuracy |
|
68 |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
|
69 |
-
|
|
70 |
-
| 1.
|
71 |
-
|
|
72 |
-
|
|
73 |
-
| 0.
|
74 |
-
| 0.
|
75 |
-
| 0.
|
76 |
-
| 0.
|
77 |
-
| 0.
|
78 |
-
| 0.
|
79 |
-
| 0.3154 | 11.0 | 1243 | 0.7082 | 0.82 |
|
80 |
-
| 0.252 | 12.0 | 1356 | 0.7222 | 0.81 |
|
81 |
-
| 0.2265 | 13.0 | 1469 | 0.7063 | 0.82 |
|
82 |
-
| 0.2478 | 14.0 | 1582 | 0.6898 | 0.81 |
|
83 |
-
| 0.1386 | 15.0 | 1695 | 0.6734 | 0.81 |
|
84 |
|
85 |
|
86 |
### Framework versions
|
|
|
22 |
metrics:
|
23 |
- name: Accuracy
|
24 |
type: accuracy
|
25 |
+
value: 0.84
|
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: 1.0184
|
36 |
+
- Accuracy: 0.84
|
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: 2
|
57 |
+
- eval_batch_size: 2
|
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: 10
|
63 |
- mixed_precision_training: Native AMP
|
64 |
|
65 |
### Training results
|
66 |
|
67 |
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
68 |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
|
69 |
+
| 1.6293 | 1.0 | 450 | 1.4785 | 0.51 |
|
70 |
+
| 1.4503 | 2.0 | 900 | 1.0904 | 0.68 |
|
71 |
+
| 0.1918 | 3.0 | 1350 | 0.6702 | 0.75 |
|
72 |
+
| 0.0857 | 4.0 | 1800 | 0.7173 | 0.79 |
|
73 |
+
| 0.0601 | 5.0 | 2250 | 0.9274 | 0.77 |
|
74 |
+
| 0.0047 | 6.0 | 2700 | 0.9787 | 0.81 |
|
75 |
+
| 0.6662 | 7.0 | 3150 | 1.0511 | 0.81 |
|
76 |
+
| 0.0012 | 8.0 | 3600 | 1.0870 | 0.84 |
|
77 |
+
| 0.0015 | 9.0 | 4050 | 0.9564 | 0.87 |
|
78 |
+
| 0.0012 | 10.0 | 4500 | 1.0184 | 0.84 |
|
|
|
|
|
|
|
|
|
|
|
79 |
|
80 |
|
81 |
### Framework versions
|
runs/Mar07_20-18-02_3009a6145419/events.out.tfevents.1709842683.3009a6145419.440.1
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 sha256:04fcc6f232de00e8a2de67e01b7a1b81a6914ad42ddc52796bbe27b1fbf2b8fc
|
3 |
+
size 199167
|