Hugging Face's logo

heado
/
korean_kws2

Audio Classification
Transformers
TensorBoard
Safetensors
wav2vec2
Generated from Trainer
Model card Files
xet
Metrics Community
heado commited on
Commit
b7cd0ff
·
verified ·
1 Parent(s): a24d931

End of training

Browse files
Files changed (5) hide show
  1. README.md +32 -12
  2. model.safetensors +1 -1
  3. runs/Sep30_05-46-30_f8c06321d49d/events.out.tfevents.1759211956.f8c06321d49d.1623.1 +3 -0
  4. runs/Sep30_06-00-59_f8c06321d49d/events.out.tfevents.1759212064.f8c06321d49d.1623.2 +3 -0
  5. training_args.bin +1 -1
README.md CHANGED
@@ -17,7 +17,7 @@ should probably proofread and complete it, then remove this comment. -->
17
 
18
  This model is a fine-tuned version of [Kkonjeong/wav2vec2-base-korean](https://huggingface.co/Kkonjeong/wav2vec2-base-korean) on the None dataset.
19
  It achieves the following results on the evaluation set:
20
- - Loss: 1.0695
21
  - Accuracy: 1.0
22
 
23
  ## Model description
@@ -45,23 +45,43 @@ The following hyperparameters were used during training:
45
  - total_train_batch_size: 32
46
  - optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
47
  - lr_scheduler_type: linear
48
- - num_epochs: 10
49
  - mixed_precision_training: Native AMP
50
 
51
  ### Training results
52
 
53
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
54
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
55
- | No log | 1.0 | 2 | 1.8973 | 0.1053 |
56
- | No log | 2.0 | 4 | 1.8025 | 0.4737 |
57
- | No log | 3.0 | 6 | 1.6736 | 0.6316 |
58
- | No log | 4.0 | 8 | 1.5259 | 0.7895 |
59
- | No log | 5.0 | 10 | 1.3562 | 0.8947 |
60
- | No log | 6.0 | 12 | 1.2217 | 1.0 |
61
- | No log | 7.0 | 14 | 1.1860 | 0.9474 |
62
- | No log | 8.0 | 16 | 1.1302 | 0.9474 |
63
- | No log | 9.0 | 18 | 1.0881 | 0.9474 |
64
- | No log | 10.0 | 20 | 1.0695 | 1.0 |
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
65
 
66
 
67
  ### Framework versions
 
17
 
18
  This model is a fine-tuned version of [Kkonjeong/wav2vec2-base-korean](https://huggingface.co/Kkonjeong/wav2vec2-base-korean) on the None dataset.
19
  It achieves the following results on the evaluation set:
20
+ - Loss: 0.2420
21
  - Accuracy: 1.0
22
 
23
  ## Model description
 
45
  - total_train_batch_size: 32
46
  - optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
47
  - lr_scheduler_type: linear
48
+ - num_epochs: 30
49
  - mixed_precision_training: Native AMP
50
 
51
  ### Training results
52
 
53
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
54
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
55
+ | No log | 1.0 | 2 | 1.9137 | 0.0526 |
56
+ | No log | 2.0 | 4 | 1.7865 | 0.2105 |
57
+ | No log | 3.0 | 6 | 1.6936 | 0.6842 |
58
+ | No log | 4.0 | 8 | 1.4829 | 0.6842 |
59
+ | No log | 5.0 | 10 | 1.2932 | 0.7895 |
60
+ | No log | 6.0 | 12 | 1.1308 | 0.9474 |
61
+ | No log | 7.0 | 14 | 1.0253 | 1.0 |
62
+ | No log | 8.0 | 16 | 0.9139 | 1.0 |
63
+ | No log | 9.0 | 18 | 0.8465 | 1.0 |
64
+ | No log | 10.0 | 20 | 0.7344 | 1.0 |
65
+ | No log | 11.0 | 22 | 0.6424 | 1.0 |
66
+ | No log | 12.0 | 24 | 0.5767 | 1.0 |
67
+ | No log | 13.0 | 26 | 0.5231 | 1.0 |
68
+ | No log | 14.0 | 28 | 0.4666 | 1.0 |
69
+ | No log | 15.0 | 30 | 0.4239 | 1.0 |
70
+ | No log | 16.0 | 32 | 0.3941 | 1.0 |
71
+ | No log | 17.0 | 34 | 0.3693 | 1.0 |
72
+ | No log | 18.0 | 36 | 0.3435 | 1.0 |
73
+ | No log | 19.0 | 38 | 0.3264 | 1.0 |
74
+ | No log | 20.0 | 40 | 0.3090 | 1.0 |
75
+ | No log | 21.0 | 42 | 0.2942 | 1.0 |
76
+ | No log | 22.0 | 44 | 0.2827 | 1.0 |
77
+ | No log | 23.0 | 46 | 0.2750 | 1.0 |
78
+ | No log | 24.0 | 48 | 0.2666 | 1.0 |
79
+ | No log | 25.0 | 50 | 0.2599 | 1.0 |
80
+ | No log | 26.0 | 52 | 0.2537 | 1.0 |
81
+ | No log | 27.0 | 54 | 0.2482 | 1.0 |
82
+ | No log | 28.0 | 56 | 0.2446 | 1.0 |
83
+ | No log | 29.0 | 58 | 0.2427 | 1.0 |
84
+ | No log | 30.0 | 60 | 0.2420 | 1.0 |
85
 
86
 
87
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3b79477142ae6a93f54516a2fbd6fe6f2a2249bf0ff3c35ec0ab4b32a9976557
3
  size 378307508
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3856270cb0170319e65de165013e73aeac0a9682302248a0f35b0f9306767592
3
  size 378307508
runs/Sep30_05-46-30_f8c06321d49d/events.out.tfevents.1759211956.f8c06321d49d.1623.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:37a7d116f934120bf0329003f902edf2f672f935cdfb70678d864a65d1b38a1e
3
+ size 8765
runs/Sep30_06-00-59_f8c06321d49d/events.out.tfevents.1759212064.f8c06321d49d.1623.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5d5ac6af2c6c2bb035de7d5a7de5641e891e912a3fa32c43c37dc4e7eea27a1b
3
+ size 17336
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7e69af5f88ec31038e235f065cc7b63f15ce432f30d76120a5691b6280fba302
3
  size 5841
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:64f065005e972daf0abafe690d62e8ed366b960e9d65d92611eb28a015d76900
3
  size 5841