nimrita commited on
Commit
d8465d4
1 Parent(s): 39c08f8

End of training

Browse files
Files changed (1) hide show
  1. README.md +14 -18
README.md CHANGED
@@ -22,7 +22,7 @@ model-index:
22
  metrics:
23
  - name: Accuracy
24
  type: accuracy
25
- value: 0.85
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: 0.7283
36
- - Accuracy: 0.85
37
 
38
  ## Model description
39
 
@@ -53,30 +53,26 @@ More information needed
53
 
54
  The following hyperparameters were used during training:
55
  - learning_rate: 0.0001
56
- - train_batch_size: 4
57
- - eval_batch_size: 4
58
  - seed: 42
59
- - gradient_accumulation_steps: 2
60
- - total_train_batch_size: 8
61
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
62
  - lr_scheduler_type: linear
63
  - lr_scheduler_warmup_ratio: 0.1
64
- - num_epochs: 10
65
 
66
  ### Training results
67
 
68
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
69
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
70
- | 1.8021 | 1.0 | 112 | 1.6488 | 0.43 |
71
- | 1.0861 | 2.0 | 225 | 1.0086 | 0.67 |
72
- | 0.6939 | 3.0 | 337 | 0.7443 | 0.74 |
73
- | 0.5646 | 4.0 | 450 | 0.8549 | 0.74 |
74
- | 0.3003 | 5.0 | 562 | 0.7615 | 0.78 |
75
- | 0.0586 | 6.0 | 675 | 0.7139 | 0.82 |
76
- | 0.1372 | 7.0 | 787 | 0.7026 | 0.81 |
77
- | 0.0961 | 8.0 | 900 | 0.8469 | 0.83 |
78
- | 0.0118 | 9.0 | 1012 | 0.6534 | 0.85 |
79
- | 0.0742 | 9.96 | 1120 | 0.7283 | 0.85 |
80
 
81
 
82
  ### Framework versions
 
22
  metrics:
23
  - name: Accuracy
24
  type: accuracy
25
+ value: 0.87
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: 0.5522
36
+ - Accuracy: 0.87
37
 
38
  ## Model description
39
 
 
53
 
54
  The following hyperparameters were used during training:
55
  - learning_rate: 0.0001
56
+ - train_batch_size: 8
57
+ - eval_batch_size: 8
58
  - seed: 42
 
 
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
+ | 1.8034 | 1.0 | 113 | 1.5716 | 0.52 |
69
+ | 1.0738 | 2.0 | 226 | 1.0565 | 0.62 |
70
+ | 0.852 | 3.0 | 339 | 0.7845 | 0.76 |
71
+ | 0.7287 | 4.0 | 452 | 0.7007 | 0.78 |
72
+ | 0.4968 | 5.0 | 565 | 0.5528 | 0.82 |
73
+ | 0.1266 | 6.0 | 678 | 0.7303 | 0.81 |
74
+ | 0.1341 | 7.0 | 791 | 0.5915 | 0.85 |
75
+ | 0.0251 | 8.0 | 904 | 0.5522 | 0.87 |
 
 
76
 
77
 
78
  ### Framework versions