Hugging Face's logo

efraimdahl
/
syncopation-transformer-spectral

Transformers
Safetensors
Generated from Trainer
Model card Files
xet
 Community
efraimdahl commited on
Commit
7b2b6cd
·
verified ·
1 Parent(s): 732891b

End of training

Browse files
Files changed (2) hide show
  1. README.md +54 -29
  2. model.safetensors +1 -1
README.md CHANGED
@@ -3,18 +3,18 @@ library_name: transformers
3
  tags:
4
  - generated_from_trainer
5
  model-index:
6
- - name: syncopation-transformer-metric
7
  results: []
8
  ---
9
 
10
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
11
  should probably proofread and complete it, then remove this comment. -->
12
 
13
- # syncopation-transformer-metric
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: 0.0544
18
 
19
  ## Model description
20
 
@@ -39,37 +39,62 @@ The following hyperparameters were used during training:
39
  - seed: 42
40
  - optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
41
  - lr_scheduler_type: linear
42
- - num_epochs: 25
43
 
44
  ### Training results
45
 
46
  | Training Loss | Epoch | Step | Validation Loss |
47
  |:-------------:|:-----:|:------:|:---------------:|
48
- | 0.1711 | 1.0 | 4350 | 0.0656 |
49
- | 0.0034 | 2.0 | 8700 | 0.0673 |
50
- | 0.0025 | 3.0 | 13050 | 0.0610 |
51
- | 0.0408 | 4.0 | 17400 | 0.0610 |
52
- | 0.056 | 5.0 | 21750 | 0.0575 |
53
- | 0.0071 | 6.0 | 26100 | 0.0570 |
54
- | 0.0063 | 7.0 | 30450 | 0.0587 |
55
- | 0.0018 | 8.0 | 34800 | 0.0588 |
56
- | 0.0259 | 9.0 | 39150 | 0.0562 |
57
- | 0.0155 | 10.0 | 43500 | 0.0606 |
58
- | 0.0137 | 11.0 | 47850 | 0.0571 |
59
- | 0.0217 | 12.0 | 52200 | 0.0635 |
60
- | 0.0795 | 13.0 | 56550 | 0.0557 |
61
- | 0.0279 | 14.0 | 60900 | 0.0559 |
62
- | 0.3003 | 15.0 | 65250 | 0.0566 |
63
- | 0.0821 | 16.0 | 69600 | 0.0576 |
64
- | 0.0049 | 17.0 | 73950 | 0.0542 |
65
- | 0.0006 | 18.0 | 78300 | 0.0565 |
66
- | 0.0002 | 19.0 | 82650 | 0.0552 |
67
- | 0.0024 | 20.0 | 87000 | 0.0553 |
68
- | 0.033 | 21.0 | 91350 | 0.0545 |
69
- | 0.0002 | 22.0 | 95700 | 0.0567 |
70
- | 0.1018 | 23.0 | 100050 | 0.0546 |
71
- | 0.0013 | 24.0 | 104400 | 0.0537 |
72
- | 0.0165 | 25.0 | 108750 | 0.0544 |
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
73
 
74
 
75
  ### Framework versions
 
3
  tags:
4
  - generated_from_trainer
5
  model-index:
6
+ - name: syncopation-transformer-spectral
7
  results: []
8
  ---
9
 
10
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
11
  should probably proofread and complete it, then remove this comment. -->
12
 
13
+ # syncopation-transformer-spectral
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: 0.0560
18
 
19
  ## Model description
20
 
 
39
  - seed: 42
40
  - optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
41
  - lr_scheduler_type: linear
42
+ - num_epochs: 50
43
 
44
  ### Training results
45
 
46
  | Training Loss | Epoch | Step | Validation Loss |
47
  |:-------------:|:-----:|:------:|:---------------:|
48
+ | 0.0027 | 1.0 | 4355 | 0.0656 |
49
+ | 0.1182 | 2.0 | 8710 | 0.0776 |
50
+ | 0.0195 | 3.0 | 13065 | 0.0601 |
51
+ | 0.0502 | 4.0 | 17420 | 0.0657 |
52
+ | 0.0307 | 5.0 | 21775 | 0.0571 |
53
+ | 0.0 | 6.0 | 26130 | 0.0618 |
54
+ | 0.2242 | 7.0 | 30485 | 0.0675 |
55
+ | 0.0 | 8.0 | 34840 | 0.0628 |
56
+ | 0.0056 | 9.0 | 39195 | 0.0656 |
57
+ | 0.0008 | 10.0 | 43550 | 0.0572 |
58
+ | 0.0781 | 11.0 | 47905 | 0.0580 |
59
+ | 0.0007 | 12.0 | 52260 | 0.0566 |
60
+ | 0.023 | 13.0 | 56615 | 0.0574 |
61
+ | 0.0012 | 14.0 | 60970 | 0.0568 |
62
+ | 0.0083 | 15.0 | 65325 | 0.0653 |
63
+ | 0.0 | 16.0 | 69680 | 0.0571 |
64
+ | 0.0022 | 17.0 | 74035 | 0.0579 |
65
+ | 0.0007 | 18.0 | 78390 | 0.0566 |
66
+ | 0.0016 | 19.0 | 82745 | 0.0603 |
67
+ | 0.0 | 20.0 | 87100 | 0.0580 |
68
+ | 0.0015 | 21.0 | 91455 | 0.0564 |
69
+ | 0.003 | 22.0 | 95810 | 0.0598 |
70
+ | 0.0051 | 23.0 | 100165 | 0.0598 |
71
+ | 0.3308 | 24.0 | 104520 | 0.0580 |
72
+ | 0.0008 | 25.0 | 108875 | 0.0591 |
73
+ | 0.0009 | 26.0 | 113230 | 0.0586 |
74
+ | 0.0058 | 27.0 | 117585 | 0.0580 |
75
+ | 0.0004 | 28.0 | 121940 | 0.0574 |
76
+ | 0.0044 | 29.0 | 126295 | 0.0625 |
77
+ | 0.0 | 30.0 | 130650 | 0.0583 |
78
+ | 0.0 | 31.0 | 135005 | 0.0577 |
79
+ | 0.0073 | 32.0 | 139360 | 0.0604 |
80
+ | 0.0 | 33.0 | 143715 | 0.0581 |
81
+ | 0.0012 | 34.0 | 148070 | 0.0589 |
82
+ | 0.3239 | 35.0 | 152425 | 0.0565 |
83
+ | 0.0001 | 36.0 | 156780 | 0.0603 |
84
+ | 0.0069 | 37.0 | 161135 | 0.0576 |
85
+ | 0.0 | 38.0 | 165490 | 0.0612 |
86
+ | 0.0055 | 39.0 | 169845 | 0.0585 |
87
+ | 0.0013 | 40.0 | 174200 | 0.0564 |
88
+ | 0.003 | 41.0 | 178555 | 0.0570 |
89
+ | 0.0014 | 42.0 | 182910 | 0.0590 |
90
+ | 0.0029 | 43.0 | 187265 | 0.0594 |
91
+ | 0.0017 | 44.0 | 191620 | 0.0596 |
92
+ | 0.0009 | 45.0 | 195975 | 0.0570 |
93
+ | 0.0879 | 46.0 | 200330 | 0.0543 |
94
+ | 0.019 | 47.0 | 204685 | 0.0563 |
95
+ | 0.0002 | 48.0 | 209040 | 0.0573 |
96
+ | 0.0008 | 49.0 | 213395 | 0.0559 |
97
+ | 0.0001 | 50.0 | 217750 | 0.0560 |
98
 
99
 
100
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:38841a9e144a1b00ec1a3d778c00730eba0bfeedf7dc7866977b51d3376776b9
3
  size 11213064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:424cd606a1627a9df9c4e8ac1e8a23db3f056e12317564e5b41958722719a798
3
  size 11213064