Hugging Face's logo

giyong
/
distil-large-v2_ADReSSo

Audio Classification
Transformers
TensorBoard
Safetensors
whisper
Generated from Trainer
Eval Results
Model card Files
xet
Metrics Community
giyong commited on
Commit
6f342af
·
verified ·
1 Parent(s): 0a1592b

End of training

Browse files
Files changed (7) hide show
  1. README.md +22 -29
  2. model.safetensors +1 -1
  3. runs/May03_17-41-58_u22/events.out.tfevents.1746261719.u22.1250214.0 +3 -0
  4. runs/May03_17-41-58_u22/events.out.tfevents.1746262514.u22.1250214.1 +3 -0
  5. runs/May03_19-19-55_u22/events.out.tfevents.1746267596.u22.1275706.0 +3 -0
  6. runs/May03_19-19-55_u22/events.out.tfevents.1746268526.u22.1275706.1 +3 -0
  7. training_args.bin +1 -1
README.md CHANGED
@@ -24,10 +24,10 @@ model-index:
24
  metrics:
25
  - name: Accuracy
26
  type: accuracy
27
- value: 0.3380281690140845
28
  - name: F1
29
  type: f1
30
- value: 0.0
31
  ---
32
 
33
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -37,9 +37,9 @@ should probably proofread and complete it, then remove this comment. -->
37
 
38
  This model is a fine-tuned version of [distil-whisper/distil-large-v2](https://huggingface.co/distil-whisper/distil-large-v2) on the audiofolder dataset.
39
  It achieves the following results on the evaluation set:
40
- - Loss: 4.9453
41
- - Accuracy: 0.3380
42
- - F1: 0.0
43
 
44
  ## Model description
45
 
@@ -73,30 +73,23 @@ The following hyperparameters were used during training:
73
 
74
  | Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
75
  |:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|
76
- | 0.6997 | 1.0 | 16 | 0.6905 | 0.5 | 0.0 |
77
- | 0.6835 | 2.0 | 32 | 0.6862 | 0.5 | 0.0 |
78
- | 0.5841 | 3.0 | 48 | 0.6106 | 0.5476 | 0.4242 |
79
- | 0.3549 | 4.0 | 64 | 1.1797 | 0.5952 | 0.3704 |
80
- | 0.0931 | 5.0 | 80 | 1.0641 | 0.7143 | 0.6842 |
81
- | 0.0335 | 6.0 | 96 | 1.1750 | 0.7619 | 0.75 |
82
- | 0.0655 | 7.0 | 112 | 1.5735 | 0.6905 | 0.6061 |
83
- | 0.1226 | 8.0 | 128 | 1.3862 | 0.7381 | 0.7660 |
84
- | 0.8217 | 9.0 | 144 | 2.0068 | 0.5952 | 0.32 |
85
- | 0.1536 | 10.0 | 160 | 2.5503 | 0.5952 | 0.4138 |
86
- | 0.17 | 11.0 | 176 | 2.6287 | 0.5714 | 0.3077 |
87
- | 0.216 | 12.0 | 192 | 1.3225 | 0.7143 | 0.7778 |
88
- | 0.2629 | 13.0 | 208 | 1.0233 | 0.7619 | 0.7826 |
89
- | 0.0013 | 14.0 | 224 | 1.5218 | 0.7857 | 0.8085 |
90
- | 0.0004 | 15.0 | 240 | 2.9578 | 0.6190 | 0.5 |
91
- | 0.0002 | 16.0 | 256 | 1.8743 | 0.7381 | 0.7317 |
92
- | 0.1024 | 17.0 | 272 | 2.0074 | 0.7143 | 0.6667 |
93
- | 0.0004 | 18.0 | 288 | 1.5935 | 0.7619 | 0.7619 |
94
- | 0.0004 | 19.0 | 304 | 1.6041 | 0.7619 | 0.7619 |
95
- | 0.0002 | 20.0 | 320 | 1.7092 | 0.7619 | 0.7619 |
96
- | 0.0002 | 21.0 | 336 | 1.7796 | 0.7619 | 0.7619 |
97
- | 0.0001 | 22.0 | 352 | 1.8367 | 0.7619 | 0.7619 |
98
- | 0.0001 | 23.0 | 368 | 1.8776 | 0.7619 | 0.7619 |
99
- | 0.0001 | 24.0 | 384 | 1.9135 | 0.7619 | 0.7619 |
100
 
101
 
102
  ### Framework versions
 
24
  metrics:
25
  - name: Accuracy
26
  type: accuracy
27
+ value: 0.7323943661971831
28
  - name: F1
29
  type: f1
30
+ value: 0.7532467532467533
31
  ---
32
 
33
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 
37
 
38
  This model is a fine-tuned version of [distil-whisper/distil-large-v2](https://huggingface.co/distil-whisper/distil-large-v2) on the audiofolder dataset.
39
  It achieves the following results on the evaluation set:
40
+ - Loss: 1.1709
41
+ - Accuracy: 0.7324
42
+ - F1: 0.7532
43
 
44
  ## Model description
45
 
 
73
 
74
  | Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
75
  |:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|
76
+ | 0.7006 | 1.0 | 16 | 0.6858 | 0.5952 | 0.4516 |
77
+ | 0.6735 | 2.0 | 32 | 0.6602 | 0.6190 | 0.4286 |
78
+ | 0.5912 | 3.0 | 48 | 0.6098 | 0.6667 | 0.5333 |
79
+ | 0.3306 | 4.0 | 64 | 1.0818 | 0.7381 | 0.6857 |
80
+ | 0.2717 | 5.0 | 80 | 0.9859 | 0.7619 | 0.8 |
81
+ | 0.1669 | 6.0 | 96 | 1.4528 | 0.7143 | 0.6471 |
82
+ | 0.1593 | 7.0 | 112 | 0.9437 | 0.8333 | 0.8293 |
83
+ | 0.2332 | 8.0 | 128 | 0.8084 | 0.7857 | 0.7805 |
84
+ | 0.0096 | 9.0 | 144 | 2.1995 | 0.6429 | 0.4828 |
85
+ | 0.1096 | 10.0 | 160 | 1.7811 | 0.6905 | 0.6486 |
86
+ | 0.1683 | 11.0 | 176 | 2.0866 | 0.6190 | 0.4286 |
87
+ | 0.1243 | 12.0 | 192 | 1.4961 | 0.7143 | 0.6667 |
88
+ | 0.0014 | 13.0 | 208 | 1.5052 | 0.7619 | 0.7917 |
89
+ | 0.089 | 14.0 | 224 | 1.3525 | 0.8095 | 0.8 |
90
+ | 0.0007 | 15.0 | 240 | 1.5248 | 0.7619 | 0.7727 |
91
+ | 0.0006 | 16.0 | 256 | 1.7027 | 0.7619 | 0.7727 |
92
+ | 0.0003 | 17.0 | 272 | 1.7929 | 0.7619 | 0.7727 |
 
 
 
 
 
 
 
93
 
94
 
95
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:52809aac5b2cf66ee2f8e317e8815f4a317dfcb7a03667c3ed1635cc68b93ba8
3
  size 2548506776
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f14d39ea3886362a1495723481e36241192c3ce2c61803f1ae7d95176c1f1051
3
  size 2548506776
runs/May03_17-41-58_u22/events.out.tfevents.1746261719.u22.1250214.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:864d2179dfb80a8667cef133ba6534f7bf97d674a2458f67ddc6272a91fe1481
3
+ size 17637
runs/May03_17-41-58_u22/events.out.tfevents.1746262514.u22.1250214.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:15ad4a4fef48ed4fe1be7fe0232a24613ba43cb8ee8d94ce9ef9d66d79753ebb
3
+ size 457
runs/May03_19-19-55_u22/events.out.tfevents.1746267596.u22.1275706.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a7a7be24bdc26f19ce051d55c79cfe46e36e5eaf332be817e0145a515fec8849
3
+ size 19008
runs/May03_19-19-55_u22/events.out.tfevents.1746268526.u22.1275706.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:baf3eb803ea234760f3907f9a2e761c0bbe4ffd107887fa77f6d2f41bf0e1481
3
+ size 457
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:44e8dda197bb0091e2738e290f9b3cc7ecaec4d62d082af867e098f1232d49a3
3
  size 5304
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:104f1e081e4a7ac0106cc387e4d419743fdfcc469053e0323e31467b7e992ff9
3
  size 5304