update model card README.md
Browse files
README.md
CHANGED
@@ -15,6 +15,13 @@ should probably proofread and complete it, then remove this comment. -->
|
|
15 |
# distilhubert-finetuned-gtzan
|
16 |
|
17 |
This model is a fine-tuned version of [MariaK/distilhubert-finetuned-gtzan-v2](https://huggingface.co/MariaK/distilhubert-finetuned-gtzan-v2) on the GTZAN dataset.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
18 |
|
19 |
## Model description
|
20 |
|
@@ -42,13 +49,6 @@ The following hyperparameters were used during training:
|
|
42 |
- lr_scheduler_warmup_ratio: 0.1
|
43 |
- num_epochs: 0.01
|
44 |
|
45 |
-
### Training results
|
46 |
-
|
47 |
-
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
48 |
-
|:-------------:|:-----:|:----:|:---------------:|:--------:|
|
49 |
-
| No log | 0.02 | 2 | 0.4905 | 0.89 |
|
50 |
-
|
51 |
-
|
52 |
### Framework versions
|
53 |
|
54 |
- Transformers 4.30.2
|
|
|
15 |
# distilhubert-finetuned-gtzan
|
16 |
|
17 |
This model is a fine-tuned version of [MariaK/distilhubert-finetuned-gtzan-v2](https://huggingface.co/MariaK/distilhubert-finetuned-gtzan-v2) on the GTZAN dataset.
|
18 |
+
It achieves the following results on the evaluation set:
|
19 |
+
- eval_loss: 0.4883
|
20 |
+
- eval_accuracy: 0.87
|
21 |
+
- eval_runtime: 25.6473
|
22 |
+
- eval_samples_per_second: 3.899
|
23 |
+
- eval_steps_per_second: 0.507
|
24 |
+
- step: 0
|
25 |
|
26 |
## Model description
|
27 |
|
|
|
49 |
- lr_scheduler_warmup_ratio: 0.1
|
50 |
- num_epochs: 0.01
|
51 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
52 |
### Framework versions
|
53 |
|
54 |
- Transformers 4.30.2
|