mazesmazes commited on
Commit
2d5e50f
·
verified ·
1 Parent(s): a24fa14

Model save

Browse files
Files changed (1) hide show
  1. README.md +0 -13
README.md CHANGED
@@ -13,10 +13,6 @@ should probably proofread and complete it, then remove this comment. -->
13
  # tiny-audio-multitask
14
 
15
  This model is a fine-tuned version of [](https://huggingface.co/) on an unknown dataset.
16
- It achieves the following results on the evaluation set:
17
- - Loss: 1.8849
18
- - Train Loss Sift: 1.8841
19
- - Train Loss Transcription: 1.8856
20
 
21
  ## Model description
22
 
@@ -47,15 +43,6 @@ The following hyperparameters were used during training:
47
 
48
  ### Training results
49
 
50
- | Training Loss | Epoch | Step | Validation Loss | Loss Sift | Loss Transcription |
51
- |:-------------:|:------:|:-----:|:---------------:|:---------:|:------------------:|
52
- | 2.0532 | 0.5636 | 5000 | 2.0112 | 2.0122 | 2.0102 |
53
- | 2.0046 | 1.1273 | 10000 | 1.9566 | 1.9575 | 1.9557 |
54
- | 1.9870 | 1.6909 | 15000 | 1.9285 | 1.9228 | 1.9342 |
55
- | 1.9600 | 2.2545 | 20000 | 1.9108 | 1.9076 | 1.9142 |
56
- | 1.9574 | 2.8182 | 25000 | 1.8970 | 1.8988 | 1.8953 |
57
- | 1.9567 | 3.3818 | 30000 | 1.8913 | 1.8873 | 1.8950 |
58
- | 1.9488 | 3.9454 | 35000 | 1.8849 | 1.8841 | 1.8856 |
59
 
60
 
61
  ### Framework versions
 
13
  # tiny-audio-multitask
14
 
15
  This model is a fine-tuned version of [](https://huggingface.co/) on an unknown dataset.
 
 
 
 
16
 
17
  ## Model description
18
 
 
43
 
44
  ### Training results
45
 
 
 
 
 
 
 
 
 
 
46
 
47
 
48
  ### Framework versions