update model card README.md
Browse files
README.md
CHANGED
@@ -5,6 +5,8 @@ tags:
|
|
5 |
- generated_from_trainer
|
6 |
datasets:
|
7 |
- mir_st500
|
|
|
|
|
8 |
model-index:
|
9 |
- name: wav2vec2-base-mirst500
|
10 |
results: []
|
@@ -16,6 +18,9 @@ should probably proofread and complete it, then remove this comment. -->
|
|
16 |
# wav2vec2-base-mirst500
|
17 |
|
18 |
This model is a fine-tuned version of [facebook/wav2vec2-base](https://huggingface.co/facebook/wav2vec2-base) on the /workspace/datasets/datasets/MIR_ST500/MIR_ST500_AUDIO_CLASSIFICATION.py dataset.
|
|
|
|
|
|
|
19 |
|
20 |
## Model description
|
21 |
|
@@ -36,16 +41,26 @@ More information needed
|
|
36 |
The following hyperparameters were used during training:
|
37 |
- learning_rate: 3e-05
|
38 |
- train_batch_size: 16
|
39 |
-
- eval_batch_size:
|
40 |
- seed: 0
|
|
|
|
|
41 |
- gradient_accumulation_steps: 4
|
42 |
-
- total_train_batch_size:
|
|
|
43 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
44 |
- lr_scheduler_type: linear
|
45 |
- lr_scheduler_warmup_ratio: 0.1
|
46 |
-
- num_epochs:
|
47 |
- mixed_precision_training: Native AMP
|
48 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
49 |
### Framework versions
|
50 |
|
51 |
- Transformers 4.15.0
|
|
|
5 |
- generated_from_trainer
|
6 |
datasets:
|
7 |
- mir_st500
|
8 |
+
metrics:
|
9 |
+
- accuracy
|
10 |
model-index:
|
11 |
- name: wav2vec2-base-mirst500
|
12 |
results: []
|
|
|
18 |
# wav2vec2-base-mirst500
|
19 |
|
20 |
This model is a fine-tuned version of [facebook/wav2vec2-base](https://huggingface.co/facebook/wav2vec2-base) on the /workspace/datasets/datasets/MIR_ST500/MIR_ST500_AUDIO_CLASSIFICATION.py dataset.
|
21 |
+
It achieves the following results on the evaluation set:
|
22 |
+
- Loss: 1.1219
|
23 |
+
- Accuracy: 0.5817
|
24 |
|
25 |
## Model description
|
26 |
|
|
|
41 |
The following hyperparameters were used during training:
|
42 |
- learning_rate: 3e-05
|
43 |
- train_batch_size: 16
|
44 |
+
- eval_batch_size: 1
|
45 |
- seed: 0
|
46 |
+
- distributed_type: multi-GPU
|
47 |
+
- num_devices: 2
|
48 |
- gradient_accumulation_steps: 4
|
49 |
+
- total_train_batch_size: 128
|
50 |
+
- total_eval_batch_size: 2
|
51 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
52 |
- lr_scheduler_type: linear
|
53 |
- lr_scheduler_warmup_ratio: 0.1
|
54 |
+
- num_epochs: 1.0
|
55 |
- mixed_precision_training: Native AMP
|
56 |
|
57 |
+
### Training results
|
58 |
+
|
59 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
60 |
+
|:-------------:|:-----:|:----:|:---------------:|:--------:|
|
61 |
+
| 1.1779 | 1.0 | 1304 | 1.1219 | 0.5817 |
|
62 |
+
|
63 |
+
|
64 |
### Framework versions
|
65 |
|
66 |
- Transformers 4.15.0
|