Hugging Face's logo

Gwenn-LR
/
distilhubert-finetuned-gtzan

Audio Classification
Transformers
Safetensors
hubert
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Community
Gwenn-LR commited on
Commit
bfb8221
·
verified ·
1 Parent(s): be32cbe

End of training

Browse files
Files changed (3) hide show
  1. README.md +24 -24
  2. model.safetensors +1 -1
  3. training_args.bin +1 -1
README.md CHANGED
@@ -23,7 +23,7 @@ model-index:
23
  metrics:
24
  - name: Accuracy
25
  type: accuracy
26
- value: 0.84
27
  ---
28
 
29
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -33,8 +33,8 @@ should probably proofread and complete it, then remove this comment. -->
33
 
34
  This model is a fine-tuned version of [ntu-spml/distilhubert](https://huggingface.co/ntu-spml/distilhubert) on the GTZAN dataset.
35
  It achieves the following results on the evaluation set:
36
- - Loss: 0.6172
37
- - Accuracy: 0.84
38
 
39
  ## Model description
40
 
@@ -56,7 +56,7 @@ The following hyperparameters were used during training:
56
  - learning_rate: 5e-05
57
  - train_batch_size: 8
58
  - eval_batch_size: 8
59
- - seed: 0
60
  - optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
61
  - lr_scheduler_type: cosine_with_restarts
62
  - lr_scheduler_warmup_ratio: 0.1
@@ -66,26 +66,26 @@ The following hyperparameters were used during training:
66
 
67
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
68
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
69
- | 2.1344 | 1.0 | 113 | 2.0255 | 0.45 |
70
- | 1.4917 | 2.0 | 226 | 1.4103 | 0.59 |
71
- | 1.0949 | 3.0 | 339 | 1.1019 | 0.7 |
72
- | 0.7944 | 4.0 | 452 | 0.7862 | 0.8 |
73
- | 0.5372 | 5.0 | 565 | 0.7501 | 0.78 |
74
- | 0.4312 | 6.0 | 678 | 0.6987 | 0.77 |
75
- | 0.5543 | 7.0 | 791 | 0.6172 | 0.84 |
76
- | 0.5502 | 8.0 | 904 | 0.7661 | 0.76 |
77
- | 0.1774 | 9.0 | 1017 | 0.7508 | 0.8 |
78
- | 0.167 | 10.0 | 1130 | 0.7010 | 0.83 |
79
- | 0.1026 | 11.0 | 1243 | 0.6567 | 0.83 |
80
- | 0.0745 | 12.0 | 1356 | 0.6376 | 0.83 |
81
- | 0.0315 | 13.0 | 1469 | 0.8436 | 0.8 |
82
- | 0.1006 | 14.0 | 1582 | 0.9182 | 0.81 |
83
- | 0.0085 | 15.0 | 1695 | 0.9113 | 0.81 |
84
- | 0.0078 | 16.0 | 1808 | 1.1084 | 0.8 |
85
- | 0.004 | 17.0 | 1921 | 1.1201 | 0.81 |
86
- | 0.0037 | 18.0 | 2034 | 1.1404 | 0.83 |
87
- | 0.0031 | 19.0 | 2147 | 1.1049 | 0.84 |
88
- | 0.0024 | 20.0 | 2260 | 1.0574 | 0.82 |
89
 
90
 
91
  ### Framework versions
 
23
  metrics:
24
  - name: Accuracy
25
  type: accuracy
26
+ value: 0.88
27
  ---
28
 
29
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 
33
 
34
  This model is a fine-tuned version of [ntu-spml/distilhubert](https://huggingface.co/ntu-spml/distilhubert) on the GTZAN dataset.
35
  It achieves the following results on the evaluation set:
36
+ - Loss: 0.5321
37
+ - Accuracy: 0.88
38
 
39
  ## Model description
40
 
 
56
  - learning_rate: 5e-05
57
  - train_batch_size: 8
58
  - eval_batch_size: 8
59
+ - seed: 42
60
  - optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
61
  - lr_scheduler_type: cosine_with_restarts
62
  - lr_scheduler_warmup_ratio: 0.1
 
66
 
67
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
68
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
69
+ | 2.1271 | 1.0 | 113 | 2.0529 | 0.47 |
70
+ | 1.4245 | 2.0 | 226 | 1.4173 | 0.6 |
71
+ | 1.1783 | 3.0 | 339 | 1.0567 | 0.71 |
72
+ | 0.7597 | 4.0 | 452 | 0.8387 | 0.75 |
73
+ | 0.6043 | 5.0 | 565 | 0.6876 | 0.81 |
74
+ | 0.4758 | 6.0 | 678 | 0.6897 | 0.79 |
75
+ | 0.4882 | 7.0 | 791 | 0.6507 | 0.79 |
76
+ | 0.2361 | 8.0 | 904 | 0.6232 | 0.84 |
77
+ | 0.209 | 9.0 | 1017 | 0.5800 | 0.82 |
78
+ | 0.0859 | 10.0 | 1130 | 0.5414 | 0.85 |
79
+ | 0.0639 | 11.0 | 1243 | 0.5321 | 0.88 |
80
+ | 0.0405 | 12.0 | 1356 | 0.8187 | 0.82 |
81
+ | 0.0481 | 13.0 | 1469 | 0.7086 | 0.85 |
82
+ | 0.0127 | 14.0 | 1582 | 0.7394 | 0.84 |
83
+ | 0.0071 | 15.0 | 1695 | 0.6890 | 0.86 |
84
+ | 0.0073 | 16.0 | 1808 | 0.7361 | 0.86 |
85
+ | 0.0062 | 17.0 | 1921 | 0.9311 | 0.8 |
86
+ | 0.0028 | 18.0 | 2034 | 0.7819 | 0.84 |
87
+ | 0.0024 | 19.0 | 2147 | 0.8263 | 0.86 |
88
+ | 0.0023 | 20.0 | 2260 | 0.8049 | 0.86 |
89
 
90
 
91
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c22f6b796768dac1a02d1293286d6ee1252ff33bd3e2c585c7db31ffa73fcd65
3
  size 94771728
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3a95089a18ea78d1ee956b096d6290ca9c252d4a72e3eb5655c600ec160ab9b6
3
  size 94771728
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4e77a51b03767a97e95a04e495153b07cee4a21a518ea504599eb5918ff6aa2b
3
  size 5368
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:96ee2f3023bde3b3b532eeea8a412eb7a4ad69b5e40160d93f33c99f1b2ca120
3
  size 5368