End of training, # of epochs increased to 15
Browse files
README.md
CHANGED
@@ -33,7 +33,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
33 |
|
34 |
This model is a fine-tuned version of [ntu-spml/distilhubert](https://huggingface.co/ntu-spml/distilhubert) on the GTZAN dataset.
|
35 |
It achieves the following results on the evaluation set:
|
36 |
-
- Loss: 0.
|
37 |
- Accuracy: 0.86
|
38 |
|
39 |
## Model description
|
@@ -60,23 +60,28 @@ The following hyperparameters were used during training:
|
|
60 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
61 |
- lr_scheduler_type: linear
|
62 |
- lr_scheduler_warmup_ratio: 0.1
|
63 |
-
- num_epochs:
|
64 |
- mixed_precision_training: Native AMP
|
65 |
|
66 |
### Training results
|
67 |
|
68 |
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
69 |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
|
70 |
-
|
|
71 |
-
|
|
72 |
-
| 0.
|
73 |
-
| 0.
|
74 |
-
| 0.
|
75 |
-
| 0.
|
76 |
-
| 0.
|
77 |
-
| 0.
|
78 |
-
| 0.
|
79 |
-
| 0.
|
|
|
|
|
|
|
|
|
|
|
80 |
|
81 |
|
82 |
### Framework versions
|
|
|
33 |
|
34 |
This model is a fine-tuned version of [ntu-spml/distilhubert](https://huggingface.co/ntu-spml/distilhubert) on the GTZAN dataset.
|
35 |
It achieves the following results on the evaluation set:
|
36 |
+
- Loss: 0.8346
|
37 |
- Accuracy: 0.86
|
38 |
|
39 |
## Model description
|
|
|
60 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
61 |
- lr_scheduler_type: linear
|
62 |
- lr_scheduler_warmup_ratio: 0.1
|
63 |
+
- num_epochs: 15
|
64 |
- mixed_precision_training: Native AMP
|
65 |
|
66 |
### Training results
|
67 |
|
68 |
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
69 |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
|
70 |
+
| 0.1361 | 1.0 | 113 | 0.5399 | 0.85 |
|
71 |
+
| 0.3632 | 2.0 | 226 | 0.5833 | 0.86 |
|
72 |
+
| 0.0152 | 3.0 | 339 | 0.5908 | 0.86 |
|
73 |
+
| 0.1117 | 4.0 | 452 | 0.6009 | 0.86 |
|
74 |
+
| 0.0171 | 5.0 | 565 | 0.7137 | 0.84 |
|
75 |
+
| 0.0021 | 6.0 | 678 | 0.8152 | 0.85 |
|
76 |
+
| 0.0032 | 7.0 | 791 | 0.9775 | 0.85 |
|
77 |
+
| 0.0012 | 8.0 | 904 | 0.9153 | 0.84 |
|
78 |
+
| 0.001 | 9.0 | 1017 | 0.8607 | 0.86 |
|
79 |
+
| 0.0091 | 10.0 | 1130 | 0.8902 | 0.85 |
|
80 |
+
| 0.0007 | 11.0 | 1243 | 0.8366 | 0.85 |
|
81 |
+
| 0.0007 | 12.0 | 1356 | 0.8321 | 0.86 |
|
82 |
+
| 0.0007 | 13.0 | 1469 | 0.8330 | 0.86 |
|
83 |
+
| 0.0007 | 14.0 | 1582 | 0.8421 | 0.86 |
|
84 |
+
| 0.0006 | 15.0 | 1695 | 0.8346 | 0.86 |
|
85 |
|
86 |
|
87 |
### 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:bcede37f4498df05ce09b4805038f97d25a6333b0585b95e0b27bbca7c465bd2
|
3 |
size 94771728
|
runs/Sep04_19-09-03_a83f59f8c6fe/events.out.tfevents.1725476957.a83f59f8c6fe.1835.1
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 sha256:5fde3ff473298d2e5f6a61c6486ea3facca7c7dec5c47a6631538a7b08fc165f
|
3 |
+
size 82764
|