Hugging Face's logo

Wellyowo
/
hubert-esc50-finetuned

Audio Classification
Transformers
Safetensors
hubert
esc50
Generated from Trainer
Inference Endpoints
Model card Files Community
Wellyowo commited on
Commit
fc2559b
•
1 Parent(s): 87ae23e

End of training

Browse files
Files changed (1) hide show
  1. README.md +33 -13
README.md CHANGED
@@ -20,8 +20,8 @@ should probably proofread and complete it, then remove this comment. -->
20
 
21
  This model is a fine-tuned version of [facebook/hubert-base-ls960](https://huggingface.co/facebook/hubert-base-ls960) on the ESC-50 dataset.
22
  It achieves the following results on the evaluation set:
23
- - Loss: 2.3860
24
- - Accuracy: 0.3625
25
 
26
  ## Model description
27
 
@@ -46,22 +46,42 @@ The following hyperparameters were used during training:
46
  - seed: 42
47
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
48
  - lr_scheduler_type: linear
49
- - num_epochs: 10
50
 
51
  ### Training results
52
 
53
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
54
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
55
- | 3.7931 | 1.0 | 200 | 3.7608 | 0.0275 |
56
- | 3.6397 | 2.0 | 400 | 3.5743 | 0.065 |
57
- | 3.3959 | 3.0 | 600 | 3.3550 | 0.0975 |
58
- | 3.2348 | 4.0 | 800 | 3.1394 | 0.1375 |
59
- | 2.9701 | 5.0 | 1000 | 2.9271 | 0.2175 |
60
- | 2.9462 | 6.0 | 1200 | 2.7442 | 0.23 |
61
- | 2.728 | 7.0 | 1400 | 2.6029 | 0.275 |
62
- | 2.5537 | 8.0 | 1600 | 2.4791 | 0.3125 |
63
- | 2.4586 | 9.0 | 1800 | 2.4028 | 0.35 |
64
- | 2.3136 | 10.0 | 2000 | 2.3860 | 0.3625 |
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
65
 
66
 
67
  ### Framework versions
 
20
 
21
  This model is a fine-tuned version of [facebook/hubert-base-ls960](https://huggingface.co/facebook/hubert-base-ls960) on the ESC-50 dataset.
22
  It achieves the following results on the evaluation set:
23
+ - Loss: 1.0816
24
+ - Accuracy: 0.8325
25
 
26
  ## Model description
27
 
 
46
  - seed: 42
47
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
48
  - lr_scheduler_type: linear
49
+ - num_epochs: 30
50
 
51
  ### Training results
52
 
53
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
54
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
55
+ | 3.5937 | 1.0 | 200 | 3.4961 | 0.1 |
56
+ | 3.1597 | 2.0 | 400 | 3.1798 | 0.1325 |
57
+ | 2.8922 | 3.0 | 600 | 2.8387 | 0.2025 |
58
+ | 2.6376 | 4.0 | 800 | 2.5594 | 0.285 |
59
+ | 2.1292 | 5.0 | 1000 | 2.3671 | 0.35 |
60
+ | 2.1607 | 6.0 | 1200 | 2.0533 | 0.4225 |
61
+ | 1.7886 | 7.0 | 1400 | 1.8790 | 0.42 |
62
+ | 1.626 | 8.0 | 1600 | 1.7147 | 0.52 |
63
+ | 1.5246 | 9.0 | 1800 | 1.6021 | 0.545 |
64
+ | 0.9318 | 10.0 | 2000 | 1.4441 | 0.5825 |
65
+ | 0.9384 | 11.0 | 2200 | 1.2180 | 0.67 |
66
+ | 0.9081 | 12.0 | 2400 | 1.1540 | 0.7075 |
67
+ | 0.803 | 13.0 | 2600 | 1.1317 | 0.72 |
68
+ | 0.4613 | 14.0 | 2800 | 1.0722 | 0.74 |
69
+ | 0.4389 | 15.0 | 3000 | 1.1055 | 0.73 |
70
+ | 0.4175 | 16.0 | 3200 | 1.0409 | 0.725 |
71
+ | 0.2977 | 17.0 | 3400 | 0.9540 | 0.78 |
72
+ | 0.3455 | 18.0 | 3600 | 0.9743 | 0.805 |
73
+ | 0.2237 | 19.0 | 3800 | 1.0938 | 0.7775 |
74
+ | 0.154 | 20.0 | 4000 | 1.0646 | 0.8 |
75
+ | 0.0966 | 21.0 | 4200 | 1.0621 | 0.7875 |
76
+ | 0.172 | 22.0 | 4400 | 1.1815 | 0.7725 |
77
+ | 0.055 | 23.0 | 4600 | 1.1436 | 0.79 |
78
+ | 0.1465 | 24.0 | 4800 | 1.1070 | 0.81 |
79
+ | 0.0458 | 25.0 | 5000 | 1.1053 | 0.82 |
80
+ | 0.0137 | 26.0 | 5200 | 1.0798 | 0.815 |
81
+ | 0.0449 | 27.0 | 5400 | 1.1108 | 0.8225 |
82
+ | 0.0231 | 28.0 | 5600 | 1.1113 | 0.83 |
83
+ | 0.0218 | 29.0 | 5800 | 1.0896 | 0.83 |
84
+ | 0.047 | 30.0 | 6000 | 1.0816 | 0.8325 |
85
 
86
 
87
  ### Framework versions