Hugging Face's logo

aisuko
/
ft-wav2vec2-with-minds

Audio Classification
Transformers
Safetensors
wav2vec2
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Community
aisuko commited on
Commit
429faf1
•
1 Parent(s): f6c538e

ft-wav2vec2-with-minds

Browse files
Files changed (3) hide show
  1. README.md +15 -11
  2. model.safetensors +1 -1
  3. training_args.bin +1 -1
README.md CHANGED
@@ -22,7 +22,7 @@ model-index:
22
  metrics:
23
  - name: Accuracy
24
  type: accuracy
25
- value: 0.09734513274336283
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 [facebook/wav2vec2-base](https://huggingface.co/facebook/wav2vec2-base) on the minds14 dataset.
34
  It achieves the following results on the evaluation set:
35
- - Loss: 2.6364
36
- - Accuracy: 0.0973
37
 
38
  ## Model description
39
 
@@ -61,19 +61,23 @@ The following hyperparameters were used during training:
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: 7
 
65
 
66
  ### Training results
67
 
68
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
69
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
70
- | No log | 1.0 | 2 | 2.6374 | 0.0708 |
71
- | No log | 2.0 | 4 | 2.6364 | 0.0973 |
72
- | No log | 3.0 | 6 | 2.6419 | 0.0796 |
73
- | No log | 4.0 | 8 | 2.6457 | 0.0708 |
74
- | 2.633 | 5.0 | 10 | 2.6485 | 0.0619 |
75
- | 2.633 | 6.0 | 12 | 2.6496 | 0.0619 |
76
- | 2.633 | 7.0 | 14 | 2.6497 | 0.0708 |
 
 
 
77
 
78
 
79
  ### Framework versions
 
22
  metrics:
23
  - name: Accuracy
24
  type: accuracy
25
+ value: 0.11504424778761062
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 [facebook/wav2vec2-base](https://huggingface.co/facebook/wav2vec2-base) on the minds14 dataset.
34
  It achieves the following results on the evaluation set:
35
+ - Loss: 2.6358
36
+ - Accuracy: 0.1150
37
 
38
  ## Model description
39
 
 
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
+ - mixed_precision_training: Native AMP
66
 
67
  ### Training results
68
 
69
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
70
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
71
+ | No log | 1.0 | 2 | 2.6358 | 0.1150 |
72
+ | No log | 2.0 | 4 | 2.6403 | 0.1062 |
73
+ | No log | 3.0 | 6 | 2.6474 | 0.0796 |
74
+ | No log | 4.0 | 8 | 2.6491 | 0.0442 |
75
+ | 2.6359 | 5.0 | 10 | 2.6499 | 0.0531 |
76
+ | 2.6359 | 6.0 | 12 | 2.6521 | 0.0531 |
77
+ | 2.6359 | 7.0 | 14 | 2.6526 | 0.0442 |
78
+ | 2.6359 | 8.0 | 16 | 2.6522 | 0.0354 |
79
+ | 2.6359 | 9.0 | 18 | 2.6520 | 0.0354 |
80
+ | 2.625 | 10.0 | 20 | 2.6521 | 0.0442 |
81
 
82
 
83
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8c2347f27e7d246cf2c85d7ec9bcadd3a406df9d048d37ccdad5b756805591dd
3
  size 378314656
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0382fd74185e7c3227601629a0c14fb2565433a305679ab3419aa6f310725115
3
  size 378314656
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:96e45551c5ddb640cbefb7cadbed167a4a1721c4cca0cc1b2fdb681eedec3bde
3
  size 4155
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6db473f77af79e713df093ebff7b6be32038d1c31f667c7d13322b632cb9de41
3
  size 4155