End of training, 10+1 epochs, 4 batch size, writer batch size: 1000, 1 gradient accumulation steps, learning rate: 5e-05, 30 s
Browse files
README.md
CHANGED
@@ -5,24 +5,9 @@ tags:
|
|
5 |
- generated_from_trainer
|
6 |
datasets:
|
7 |
- marsyas/gtzan
|
8 |
-
metrics:
|
9 |
-
- accuracy
|
10 |
model-index:
|
11 |
- name: distilhubert-finetuned-gtzan
|
12 |
-
results:
|
13 |
-
- task:
|
14 |
-
name: Audio Classification
|
15 |
-
type: audio-classification
|
16 |
-
dataset:
|
17 |
-
name: GTZAN
|
18 |
-
type: marsyas/gtzan
|
19 |
-
config: all
|
20 |
-
split: train
|
21 |
-
args: all
|
22 |
-
metrics:
|
23 |
-
- name: Accuracy
|
24 |
-
type: accuracy
|
25 |
-
value: 0.82
|
26 |
---
|
27 |
|
28 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
@@ -32,8 +17,13 @@ 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 |
-
-
|
36 |
-
-
|
|
|
|
|
|
|
|
|
|
|
37 |
|
38 |
## Model description
|
39 |
|
@@ -62,21 +52,6 @@ The following hyperparameters were used during training:
|
|
62 |
- num_epochs: 9
|
63 |
- mixed_precision_training: Native AMP
|
64 |
|
65 |
-
### Training results
|
66 |
-
|
67 |
-
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
68 |
-
|:-------------:|:-----:|:----:|:---------------:|:--------:|
|
69 |
-
| 1.9236 | 1.0 | 113 | 1.8095 | 0.51 |
|
70 |
-
| 1.1771 | 2.0 | 226 | 1.2024 | 0.66 |
|
71 |
-
| 1.0227 | 3.0 | 339 | 1.0044 | 0.71 |
|
72 |
-
| 0.6925 | 4.0 | 452 | 0.8156 | 0.76 |
|
73 |
-
| 0.5823 | 5.0 | 565 | 0.6761 | 0.79 |
|
74 |
-
| 0.3919 | 6.0 | 678 | 0.6031 | 0.79 |
|
75 |
-
| 0.3968 | 7.0 | 791 | 0.6003 | 0.83 |
|
76 |
-
| 0.1533 | 8.0 | 904 | 0.5785 | 0.81 |
|
77 |
-
| 0.2358 | 9.0 | 1017 | 0.5819 | 0.82 |
|
78 |
-
|
79 |
-
|
80 |
### Framework versions
|
81 |
|
82 |
- Transformers 4.44.0
|
|
|
5 |
- generated_from_trainer
|
6 |
datasets:
|
7 |
- marsyas/gtzan
|
|
|
|
|
8 |
model-index:
|
9 |
- name: distilhubert-finetuned-gtzan
|
10 |
+
results: []
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
11 |
---
|
12 |
|
13 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
|
17 |
|
18 |
This model is a fine-tuned version of [ntu-spml/distilhubert](https://huggingface.co/ntu-spml/distilhubert) on the GTZAN dataset.
|
19 |
It achieves the following results on the evaluation set:
|
20 |
+
- eval_loss: 0.5534
|
21 |
+
- eval_accuracy: 0.88
|
22 |
+
- eval_runtime: 66.8648
|
23 |
+
- eval_samples_per_second: 1.496
|
24 |
+
- eval_steps_per_second: 0.194
|
25 |
+
- epoch: 1.0
|
26 |
+
- step: 113
|
27 |
|
28 |
## Model description
|
29 |
|
|
|
52 |
- num_epochs: 9
|
53 |
- mixed_precision_training: Native AMP
|
54 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
55 |
### Framework versions
|
56 |
|
57 |
- Transformers 4.44.0
|