Hugging Face's logo

Leotrim
/
distilhubert-finetuned-gtzan

TensorBoard
Safetensors
hubert
Generated from Trainer
Eval Results
Model card Files Metrics Community
Leotrim commited on
Commit
2864940
·
verified ·
1 Parent(s): 48baa87

End of training

Browse files
Files changed (2) hide show
  1. README.md +23 -21
  2. model.safetensors +1 -1
README.md CHANGED
@@ -25,31 +25,31 @@ model-index:
25
  metrics:
26
  - name: Accuracy
27
  type: accuracy
28
- value: 0.7733333333333333
29
  - name: Precision
30
  type: precision
31
- value: 0.775454513809777
32
  - name: Recall
33
  type: recall
34
- value: 0.7733333333333333
35
  - name: F1
36
  type: f1
37
- value: 0.7708532203254443
38
  ---
39
 
40
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
41
  should probably proofread and complete it, then remove this comment. -->
42
 
43
- [<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/raspuntinov_ai/huggingface/runs/xti2wn9w)
44
  # distilhubert-finetuned-gtzan
45
 
46
  This model is a fine-tuned version of [ntu-spml/distilhubert](https://huggingface.co/ntu-spml/distilhubert) on the GTZAN dataset.
47
  It achieves the following results on the evaluation set:
48
- - Loss: 0.7448
49
- - Accuracy: 0.7733
50
- - Precision: 0.7755
51
- - Recall: 0.7733
52
- - F1: 0.7709
53
 
54
  ## Model description
55
 
@@ -75,23 +75,25 @@ The following hyperparameters were used during training:
75
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
76
  - lr_scheduler_type: linear
77
  - lr_scheduler_warmup_ratio: 0.1
78
- - num_epochs: 10
79
  - mixed_precision_training: Native AMP
80
 
81
  ### Training results
82
 
83
  | Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 |
84
  |:-------------:|:-----:|:----:|:---------------:|:--------:|:---------:|:------:|:------:|
85
- | 2.0182 | 1.0 | 88 | 2.0020 | 0.3333 | 0.3990 | 0.3333 | 0.2547 |
86
- | 1.6019 | 2.0 | 176 | 1.4794 | 0.5333 | 0.6597 | 0.5333 | 0.4789 |
87
- | 1.0733 | 3.0 | 264 | 1.2329 | 0.6133 | 0.6930 | 0.6133 | 0.5993 |
88
- | 0.9451 | 4.0 | 352 | 1.1227 | 0.64 | 0.7214 | 0.64 | 0.6289 |
89
- | 0.9232 | 5.0 | 440 | 0.9426 | 0.7133 | 0.7398 | 0.7133 | 0.7071 |
90
- | 0.6552 | 6.0 | 528 | 0.8132 | 0.78 | 0.7795 | 0.78 | 0.7768 |
91
- | 0.4019 | 7.0 | 616 | 0.8478 | 0.7333 | 0.7428 | 0.7333 | 0.7285 |
92
- | 0.2836 | 8.0 | 704 | 0.7369 | 0.7933 | 0.8025 | 0.7933 | 0.7915 |
93
- | 0.207 | 9.0 | 792 | 0.7440 | 0.7933 | 0.7926 | 0.7933 | 0.7879 |
94
- | 0.3091 | 10.0 | 880 | 0.7448 | 0.7733 | 0.7755 | 0.7733 | 0.7709 |
 
 
95
 
96
 
97
  ### Framework versions
 
25
  metrics:
26
  - name: Accuracy
27
  type: accuracy
28
+ value: 0.87
29
  - name: Precision
30
  type: precision
31
+ value: 0.8732395382395381
32
  - name: Recall
33
  type: recall
34
+ value: 0.87
35
  - name: F1
36
  type: f1
37
+ value: 0.8675442617238284
38
  ---
39
 
40
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
41
  should probably proofread and complete it, then remove this comment. -->
42
 
43
+ [<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/raspuntinov_ai/huggingface/runs/cefsu57q)
44
  # distilhubert-finetuned-gtzan
45
 
46
  This model is a fine-tuned version of [ntu-spml/distilhubert](https://huggingface.co/ntu-spml/distilhubert) on the GTZAN dataset.
47
  It achieves the following results on the evaluation set:
48
+ - Loss: 0.6051
49
+ - Accuracy: 0.87
50
+ - Precision: 0.8732
51
+ - Recall: 0.87
52
+ - F1: 0.8675
53
 
54
  ## Model description
55
 
 
75
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
76
  - lr_scheduler_type: linear
77
  - lr_scheduler_warmup_ratio: 0.1
78
+ - num_epochs: 20
79
  - mixed_precision_training: Native AMP
80
 
81
  ### Training results
82
 
83
  | Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 |
84
  |:-------------:|:-----:|:----:|:---------------:|:--------:|:---------:|:------:|:------:|
85
+ | 2.1729 | 1.0 | 113 | 2.0581 | 0.63 | 0.6670 | 0.63 | 0.5957 |
86
+ | 1.6552 | 2.0 | 226 | 1.3957 | 0.7 | 0.6894 | 0.7 | 0.6857 |
87
+ | 1.0753 | 3.0 | 339 | 0.9783 | 0.75 | 0.8154 | 0.75 | 0.7277 |
88
+ | 0.8519 | 4.0 | 452 | 0.8087 | 0.75 | 0.8120 | 0.75 | 0.7380 |
89
+ | 0.8623 | 5.0 | 565 | 0.7393 | 0.75 | 0.7622 | 0.75 | 0.7373 |
90
+ | 0.506 | 6.0 | 678 | 0.6861 | 0.81 | 0.8449 | 0.81 | 0.7997 |
91
+ | 0.2052 | 7.0 | 791 | 0.6505 | 0.81 | 0.8254 | 0.81 | 0.8024 |
92
+ | 0.1583 | 8.0 | 904 | 0.5365 | 0.86 | 0.8770 | 0.86 | 0.8545 |
93
+ | 0.0699 | 9.0 | 1017 | 0.5488 | 0.87 | 0.8753 | 0.87 | 0.8641 |
94
+ | 0.0177 | 10.0 | 1130 | 0.6330 | 0.83 | 0.8312 | 0.83 | 0.8245 |
95
+ | 0.0071 | 11.0 | 1243 | 0.6268 | 0.84 | 0.8410 | 0.84 | 0.8348 |
96
+ | 0.0746 | 12.0 | 1356 | 0.6051 | 0.87 | 0.8732 | 0.87 | 0.8675 |
97
 
98
 
99
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:be994310b55a5391895f2e564f6dab0ea7d8922620d4655c41cc03d302d39775
3
  size 94771728
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4e143341e97c8f78bbc9aa7ccf679fe2651c05ae0442ca15a6a8623f1031a5cd
3
  size 94771728