End of training
Browse files- README.md +26 -14
- model.safetensors +1 -1
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: 0.
|
36 |
-
- Accuracy: 0.
|
37 |
|
38 |
## Model description
|
39 |
|
@@ -56,26 +56,38 @@ The following hyperparameters were used during training:
|
|
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:
|
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 |
-
| 0.
|
73 |
-
| 0.
|
74 |
-
| 0.
|
75 |
-
| 0.
|
76 |
-
| 0.
|
77 |
-
| 0.
|
78 |
-
| 0.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
79 |
|
80 |
|
81 |
### Framework versions
|
|
|
22 |
metrics:
|
23 |
- name: Accuracy
|
24 |
type: accuracy
|
25 |
+
value: 0.835
|
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: 0.9299
|
36 |
+
- Accuracy: 0.835
|
37 |
|
38 |
## Model description
|
39 |
|
|
|
56 |
- train_batch_size: 2
|
57 |
- eval_batch_size: 2
|
58 |
- seed: 42
|
59 |
+
- gradient_accumulation_steps: 4
|
60 |
+
- total_train_batch_size: 8
|
61 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
62 |
- lr_scheduler_type: linear
|
63 |
- lr_scheduler_warmup_ratio: 0.1
|
64 |
+
- num_epochs: 20
|
65 |
- mixed_precision_training: Native AMP
|
66 |
|
67 |
### Training results
|
68 |
|
69 |
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
70 |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
|
71 |
+
| 2.1474 | 1.0 | 100 | 2.1098 | 0.47 |
|
72 |
+
| 1.5063 | 2.0 | 200 | 1.5695 | 0.575 |
|
73 |
+
| 1.2171 | 3.0 | 300 | 1.1629 | 0.685 |
|
74 |
+
| 0.9388 | 4.0 | 400 | 0.9617 | 0.7 |
|
75 |
+
| 0.6208 | 5.0 | 500 | 0.9273 | 0.685 |
|
76 |
+
| 0.6771 | 6.0 | 600 | 0.7753 | 0.785 |
|
77 |
+
| 0.5799 | 7.0 | 700 | 0.8492 | 0.695 |
|
78 |
+
| 0.1527 | 8.0 | 800 | 0.6581 | 0.805 |
|
79 |
+
| 0.0586 | 9.0 | 900 | 0.6788 | 0.82 |
|
80 |
+
| 0.0355 | 10.0 | 1000 | 0.7627 | 0.81 |
|
81 |
+
| 0.0186 | 11.0 | 1100 | 0.7585 | 0.82 |
|
82 |
+
| 0.0102 | 12.0 | 1200 | 0.8328 | 0.825 |
|
83 |
+
| 0.0074 | 13.0 | 1300 | 0.8543 | 0.835 |
|
84 |
+
| 0.0063 | 14.0 | 1400 | 0.8574 | 0.83 |
|
85 |
+
| 0.0271 | 15.0 | 1500 | 0.8889 | 0.835 |
|
86 |
+
| 0.0043 | 16.0 | 1600 | 0.9197 | 0.83 |
|
87 |
+
| 0.0045 | 17.0 | 1700 | 0.9130 | 0.835 |
|
88 |
+
| 0.0036 | 18.0 | 1800 | 0.9242 | 0.835 |
|
89 |
+
| 0.0042 | 19.0 | 1900 | 0.9279 | 0.835 |
|
90 |
+
| 0.0034 | 20.0 | 2000 | 0.9299 | 0.835 |
|
91 |
|
92 |
|
93 |
### 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 sha256:7642e850199c6cb25e9a133c47dcf851b07ca8216e2aa53bd9ca12552d3124d0
|
3 |
size 94771728
|