ummonk commited on
Commit
ca92e13
1 Parent(s): af234f6

Revert "Training in progress, epoch 12"

Browse files

This reverts commit ed960ac569fe81dc42f88652b1ef98993cf9425d.

README.md CHANGED
@@ -32,7 +32,7 @@ should probably proofread and complete it, then remove this comment. -->
32
 
33
  This model is a fine-tuned version of [ntu-spml/distilhubert](https://huggingface.co/ntu-spml/distilhubert) on the audiofolder dataset.
34
  It achieves the following results on the evaluation set:
35
- - Loss: 2.0748
36
  - Accuracy: 0.2708
37
 
38
  ## Model description
@@ -58,28 +58,26 @@ The following hyperparameters were used during training:
58
  - seed: 42
59
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
60
  - lr_scheduler_type: linear
61
- - lr_scheduler_warmup_ratio: 0.7
62
- - num_epochs: 14
63
  - mixed_precision_training: Native AMP
64
 
65
  ### Training results
66
 
67
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
68
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
69
- | 2.4778 | 1.0 | 48 | 2.4807 | 0.0938 |
70
- | 2.4779 | 2.0 | 96 | 2.4651 | 0.1042 |
71
- | 2.4751 | 3.0 | 144 | 2.4365 | 0.1042 |
72
- | 2.3777 | 4.0 | 192 | 2.4187 | 0.1042 |
73
- | 2.3786 | 5.0 | 240 | 2.4050 | 0.1458 |
74
- | 2.3754 | 6.0 | 288 | 2.3446 | 0.1458 |
75
- | 2.1556 | 7.0 | 336 | 2.2284 | 0.2083 |
76
- | 2.1062 | 8.0 | 384 | 2.1533 | 0.2188 |
77
- | 2.0081 | 9.0 | 432 | 2.0765 | 0.2292 |
78
- | 1.813 | 10.0 | 480 | 2.0671 | 0.2083 |
79
- | 1.74 | 11.0 | 528 | 1.9977 | 0.3021 |
80
- | 1.4795 | 12.0 | 576 | 2.0588 | 0.2396 |
81
- | 1.298 | 13.0 | 624 | 2.0652 | 0.3021 |
82
- | 1.2578 | 14.0 | 672 | 2.0748 | 0.2708 |
83
 
84
 
85
  ### Framework versions
 
32
 
33
  This model is a fine-tuned version of [ntu-spml/distilhubert](https://huggingface.co/ntu-spml/distilhubert) on the audiofolder dataset.
34
  It achieves the following results on the evaluation set:
35
+ - Loss: 1.9466
36
  - Accuracy: 0.2708
37
 
38
  ## Model description
 
58
  - seed: 42
59
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
60
  - lr_scheduler_type: linear
61
+ - lr_scheduler_warmup_ratio: 0.8
62
+ - num_epochs: 12
63
  - mixed_precision_training: Native AMP
64
 
65
  ### Training results
66
 
67
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
68
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
69
+ | 2.48 | 1.0 | 48 | 2.4777 | 0.1042 |
70
+ | 2.473 | 2.0 | 96 | 2.4604 | 0.1562 |
71
+ | 2.4772 | 3.0 | 144 | 2.4282 | 0.1042 |
72
+ | 2.3678 | 4.0 | 192 | 2.4007 | 0.1042 |
73
+ | 2.324 | 5.0 | 240 | 2.3261 | 0.2083 |
74
+ | 2.2489 | 6.0 | 288 | 2.2360 | 0.1771 |
75
+ | 1.9909 | 7.0 | 336 | 2.1544 | 0.1875 |
76
+ | 1.9903 | 8.0 | 384 | 2.0937 | 0.1875 |
77
+ | 2.0668 | 9.0 | 432 | 2.0222 | 0.2083 |
78
+ | 1.8473 | 10.0 | 480 | 2.0298 | 0.1875 |
79
+ | 1.8068 | 11.0 | 528 | 1.9965 | 0.25 |
80
+ | 1.699 | 12.0 | 576 | 1.9466 | 0.2708 |
 
 
81
 
82
 
83
  ### Framework versions
runs/Jan18_07-05-11_93f1093dee45/events.out.tfevents.1705561514.93f1093dee45.615.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:70b031124ae801eefda767a66f10bb66e2d5b25daa49d99725e908e62f4e8ae0
3
- size 32095
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0452595db6ab07e2d914acb759092d9f9ed9e6b3904e31758befb37784138559
3
+ size 26219