Hugging Face's logo

shiftxie
/
my_awesome_mind

Audio Classification
Transformers
PyTorch
TensorBoard
wav2vec2
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
shiftxie commited on
Commit
288e165
•
1 Parent(s): 79cb56b

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +17 -15
README.md CHANGED
@@ -18,8 +18,8 @@ should probably proofread and complete it, then remove this comment. -->
18
 
19
  This model is a fine-tuned version of [facebook/wav2vec2-base](https://huggingface.co/facebook/wav2vec2-base) on the minds14 dataset.
20
  It achieves the following results on the evaluation set:
21
- - Loss: 2.6391
22
- - Accuracy: 0.0885
23
 
24
  ## Model description
25
 
@@ -47,25 +47,27 @@ The following hyperparameters were used during training:
47
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
48
  - lr_scheduler_type: linear
49
  - lr_scheduler_warmup_ratio: 0.1
50
- - num_epochs: 100
51
 
52
  ### Training results
53
 
54
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
55
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
56
- | 3.2283 | 11.53 | 35 | 2.6432 | 0.1062 |
57
- | 3.4248 | 23.27 | 70 | 2.6394 | 0.0973 |
58
- | 3.4245 | 34.8 | 105 | 2.6404 | 0.0442 |
59
- | 3.2245 | 46.53 | 140 | 2.6405 | 0.0531 |
60
- | 3.2287 | 58.27 | 175 | 2.6416 | 0.0796 |
61
- | 3.2289 | 69.8 | 210 | 2.6424 | 0.0973 |
62
- | 3.2252 | 81.53 | 245 | 2.6396 | 0.1062 |
63
- | 3.424 | 93.27 | 280 | 2.6391 | 0.0885 |
 
 
64
 
65
 
66
  ### Framework versions
67
 
68
- - Transformers 4.11.3
69
- - Pytorch 1.13.1
70
- - Datasets 2.15.0
71
- - Tokenizers 0.10.3
 
18
 
19
  This model is a fine-tuned version of [facebook/wav2vec2-base](https://huggingface.co/facebook/wav2vec2-base) on the minds14 dataset.
20
  It achieves the following results on the evaluation set:
21
+ - Loss: 2.6359
22
+ - Accuracy: 0.0619
23
 
24
  ## Model description
25
 
 
47
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
48
  - lr_scheduler_type: linear
49
  - lr_scheduler_warmup_ratio: 0.1
50
+ - num_epochs: 10
51
 
52
  ### Training results
53
 
54
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
55
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
56
+ | No log | 0.8 | 3 | 2.6579 | 0.0796 |
57
+ | No log | 1.8 | 6 | 2.6500 | 0.0796 |
58
+ | No log | 2.8 | 9 | 2.6507 | 0.0708 |
59
+ | 3.2239 | 3.8 | 12 | 2.6486 | 0.0708 |
60
+ | 3.2239 | 4.8 | 15 | 2.6410 | 0.1150 |
61
+ | 3.2239 | 5.8 | 18 | 2.6365 | 0.0973 |
62
+ | 3.2191 | 6.8 | 21 | 2.6367 | 0.0885 |
63
+ | 3.2191 | 7.8 | 24 | 2.6379 | 0.0708 |
64
+ | 3.2191 | 8.8 | 27 | 2.6353 | 0.0796 |
65
+ | 3.2232 | 9.8 | 30 | 2.6359 | 0.0619 |
66
 
67
 
68
  ### Framework versions
69
 
70
+ - Transformers 4.26.1
71
+ - Pytorch 2.1.0+cu121
72
+ - Datasets 2.17.1
73
+ - Tokenizers 0.13.3