Hugging Face's logo

italiyarishi
/
my_awesome_mind_model

Audio Classification
Transformers
TensorBoard
Safetensors
wav2vec2
Generated from Trainer
Eval Results
Model card Files
xet
Metrics Community
italiyarishi commited on
Commit
5a3d591
·
verified ·
1 Parent(s): 10dd150

End of training

Browse files
Files changed (2) hide show
  1. README.md +20 -60
  2. model.safetensors +1 -1
README.md CHANGED
@@ -23,7 +23,7 @@ model-index:
23
  metrics:
24
  - name: Accuracy
25
  type: accuracy
26
- value: 0.02654867256637168
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 [facebook/wav2vec2-base](https://huggingface.co/facebook/wav2vec2-base) on the minds14 dataset.
35
  It achieves the following results on the evaluation set:
36
- - Loss: 2.7381
37
- - Accuracy: 0.0265
38
 
39
  ## Model description
40
 
@@ -53,71 +53,31 @@ More information needed
53
  ### Training hyperparameters
54
 
55
  The following hyperparameters were used during training:
56
- - learning_rate: 3e-05
57
- - train_batch_size: 32
58
  - eval_batch_size: 32
59
  - seed: 42
60
- - gradient_accumulation_steps: 4
61
  - total_train_batch_size: 128
62
  - optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
63
  - lr_scheduler_type: linear
64
- - lr_scheduler_warmup_ratio: 0.1
65
- - num_epochs: 50
66
 
67
  ### Training results
68
 
69
- | Training Loss | Epoch | Step | Validation Loss | Accuracy |
70
- |:-------------:|:-----:|:----:|:---------------:|:--------:|
71
- | No log | 0.8 | 3 | 2.6470 | 0.0354 |
72
- | No log | 1.8 | 6 | 2.6457 | 0.0354 |
73
- | No log | 2.8 | 9 | 2.6457 | 0.0354 |
74
- | 3.0317 | 3.8 | 12 | 2.6457 | 0.0619 |
75
- | 3.0317 | 4.8 | 15 | 2.6525 | 0.0708 |
76
- | 3.0317 | 5.8 | 18 | 2.6569 | 0.0442 |
77
- | 3.0173 | 6.8 | 21 | 2.6608 | 0.0354 |
78
- | 3.0173 | 7.8 | 24 | 2.6629 | 0.0354 |
79
- | 3.0173 | 8.8 | 27 | 2.6678 | 0.0354 |
80
- | 2.991 | 9.8 | 30 | 2.6710 | 0.0619 |
81
- | 2.991 | 10.8 | 33 | 2.6741 | 0.0619 |
82
- | 2.991 | 11.8 | 36 | 2.6732 | 0.0531 |
83
- | 2.991 | 12.8 | 39 | 2.6790 | 0.0442 |
84
- | 3.0907 | 13.8 | 42 | 2.6844 | 0.0531 |
85
- | 3.0907 | 14.8 | 45 | 2.6802 | 0.0619 |
86
- | 3.0907 | 15.8 | 48 | 2.6892 | 0.0354 |
87
- | 2.9381 | 16.8 | 51 | 2.6914 | 0.0619 |
88
- | 2.9381 | 17.8 | 54 | 2.6834 | 0.0531 |
89
- | 2.9381 | 18.8 | 57 | 2.6883 | 0.0531 |
90
- | 2.9068 | 19.8 | 60 | 2.6949 | 0.0354 |
91
- | 2.9068 | 20.8 | 63 | 2.6938 | 0.0531 |
92
- | 2.9068 | 21.8 | 66 | 2.6988 | 0.0531 |
93
- | 2.9068 | 22.8 | 69 | 2.6995 | 0.0531 |
94
- | 3.0013 | 23.8 | 72 | 2.6906 | 0.0531 |
95
- | 3.0013 | 24.8 | 75 | 2.7056 | 0.0354 |
96
- | 3.0013 | 25.8 | 78 | 2.7064 | 0.0442 |
97
- | 2.843 | 26.8 | 81 | 2.7183 | 0.0265 |
98
- | 2.843 | 27.8 | 84 | 2.7108 | 0.0354 |
99
- | 2.843 | 28.8 | 87 | 2.7118 | 0.0531 |
100
- | 2.8108 | 29.8 | 90 | 2.7162 | 0.0531 |
101
- | 2.8108 | 30.8 | 93 | 2.7207 | 0.0531 |
102
- | 2.8108 | 31.8 | 96 | 2.7312 | 0.0708 |
103
- | 2.8108 | 32.8 | 99 | 2.7281 | 0.0354 |
104
- | 2.8923 | 33.8 | 102 | 2.7279 | 0.0531 |
105
- | 2.8923 | 34.8 | 105 | 2.7249 | 0.0354 |
106
- | 2.8923 | 35.8 | 108 | 2.7366 | 0.0442 |
107
- | 2.7271 | 36.8 | 111 | 2.7381 | 0.0531 |
108
- | 2.7271 | 37.8 | 114 | 2.7433 | 0.0354 |
109
- | 2.7271 | 38.8 | 117 | 2.7292 | 0.0442 |
110
- | 2.6975 | 39.8 | 120 | 2.7363 | 0.0442 |
111
- | 2.6975 | 40.8 | 123 | 2.7383 | 0.0442 |
112
- | 2.6975 | 41.8 | 126 | 2.7361 | 0.0531 |
113
- | 2.6975 | 42.8 | 129 | 2.7357 | 0.0442 |
114
- | 2.7795 | 43.8 | 132 | 2.7305 | 0.0442 |
115
- | 2.7795 | 44.8 | 135 | 2.7299 | 0.0531 |
116
- | 2.7795 | 45.8 | 138 | 2.7314 | 0.0531 |
117
- | 2.6519 | 46.8 | 141 | 2.7345 | 0.0354 |
118
- | 2.6519 | 47.8 | 144 | 2.7371 | 0.0354 |
119
- | 2.6519 | 48.8 | 147 | 2.7380 | 0.0354 |
120
- | 2.6385 | 49.8 | 150 | 2.7381 | 0.0265 |
121
 
122
 
123
  ### Framework versions
 
23
  metrics:
24
  - name: Accuracy
25
  type: accuracy
26
+ value: 0.05309734513274336
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 [facebook/wav2vec2-base](https://huggingface.co/facebook/wav2vec2-base) on the minds14 dataset.
35
  It achieves the following results on the evaluation set:
36
+ - Loss: 2.6436
37
+ - Accuracy: 0.0531
38
 
39
  ## Model description
40
 
 
53
  ### Training hyperparameters
54
 
55
  The following hyperparameters were used during training:
56
+ - learning_rate: 1e-05
57
+ - train_batch_size: 16
58
  - eval_batch_size: 32
59
  - seed: 42
60
+ - gradient_accumulation_steps: 8
61
  - total_train_batch_size: 128
62
  - optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
63
  - lr_scheduler_type: linear
64
+ - lr_scheduler_warmup_ratio: 0.2
65
+ - num_epochs: 10
66
 
67
  ### Training results
68
 
69
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy |
70
+ |:-------------:|:------:|:----:|:---------------:|:--------:|
71
+ | No log | 0.8276 | 3 | 2.6388 | 0.0708 |
72
+ | No log | 1.8276 | 6 | 2.6371 | 0.0796 |
73
+ | No log | 2.8276 | 9 | 2.6387 | 0.0708 |
74
+ | 2.8349 | 3.8276 | 12 | 2.6406 | 0.0619 |
75
+ | 2.8349 | 4.8276 | 15 | 2.6412 | 0.0708 |
76
+ | 2.8349 | 5.8276 | 18 | 2.6418 | 0.0619 |
77
+ | 2.8265 | 6.8276 | 21 | 2.6424 | 0.0531 |
78
+ | 2.8265 | 7.8276 | 24 | 2.6431 | 0.0531 |
79
+ | 2.8265 | 8.8276 | 27 | 2.6434 | 0.0531 |
80
+ | 2.8219 | 9.8276 | 30 | 2.6436 | 0.0531 |
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
81
 
82
 
83
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8d69a2cd04060a7b32f7a2b12983dd10caae0a4784d510068a8cb75fec6a99a6
3
  size 378314704
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:be239b27033eaa17c954de9bb32dbd75c9526343e508dbd49a67d48ef02bcc2e
3
  size 378314704