End of training
Browse files- README.md +14 -16
- pytorch_model.bin +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 |
|
@@ -59,27 +59,25 @@ The following hyperparameters were used during training:
|
|
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 |
|
64 |
### Training results
|
65 |
|
66 |
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
67 |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
|
68 |
-
| 1.
|
69 |
-
| 1.
|
70 |
-
| 1.
|
71 |
-
| 0.
|
72 |
-
| 0.
|
73 |
-
| 0.
|
74 |
-
| 0.
|
75 |
-
| 0.
|
76 |
-
| 0.0617 | 9.0 | 1161 | 0.6518 | 0.82 |
|
77 |
-
| 0.0323 | 10.0 | 1290 | 0.6443 | 0.81 |
|
78 |
|
79 |
|
80 |
### Framework versions
|
81 |
|
82 |
- Transformers 4.32.0.dev0
|
83 |
-
- Pytorch 2.0.
|
84 |
-
- Datasets 2.
|
85 |
- Tokenizers 0.13.3
|
|
|
22 |
metrics:
|
23 |
- name: Accuracy
|
24 |
type: accuracy
|
25 |
+
value: 0.83
|
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: 0.6209
|
36 |
+
- Accuracy: 0.83
|
37 |
|
38 |
## Model description
|
39 |
|
|
|
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: 8
|
63 |
|
64 |
### Training results
|
65 |
|
66 |
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
67 |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
|
68 |
+
| 1.9413 | 1.0 | 129 | 1.7302 | 0.53 |
|
69 |
+
| 1.25 | 2.0 | 258 | 1.2193 | 0.67 |
|
70 |
+
| 1.1947 | 3.0 | 387 | 0.9074 | 0.73 |
|
71 |
+
| 0.6238 | 4.0 | 516 | 0.7667 | 0.77 |
|
72 |
+
| 0.4228 | 5.0 | 645 | 0.7407 | 0.76 |
|
73 |
+
| 0.3519 | 6.0 | 774 | 0.6948 | 0.8 |
|
74 |
+
| 0.2624 | 7.0 | 903 | 0.5938 | 0.85 |
|
75 |
+
| 0.3789 | 8.0 | 1032 | 0.6209 | 0.83 |
|
|
|
|
|
76 |
|
77 |
|
78 |
### Framework versions
|
79 |
|
80 |
- Transformers 4.32.0.dev0
|
81 |
+
- Pytorch 2.0.0
|
82 |
+
- Datasets 2.1.0
|
83 |
- Tokenizers 0.13.3
|
pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 94783376
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d79227c49e1319235be1304fc5d37b782144792b50bdc120f4c99d0cee1c76c6
|
3 |
size 94783376
|