Hugging Face's logo

efraimdahl
/
syncopation-transformer-combined

Transformers
Safetensors
Generated from Trainer
Model card Files
xet
 Community
efraimdahl commited on
Commit
ebf1f11
·
verified ·
1 Parent(s): 9b7a5a5

End of training

Browse files
Files changed (2) hide show
  1. README.md +29 -104
  2. model.safetensors +1 -1
README.md CHANGED
@@ -14,7 +14,7 @@ should probably proofread and complete it, then remove this comment. -->
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: 0.1108
18
 
19
  ## Model description
20
 
@@ -39,112 +39,37 @@ 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: 100
43
 
44
  ### Training results
45
 
46
- | Training Loss | Epoch | Step | Validation Loss |
47
- |:-------------:|:-----:|:----:|:---------------:|
48
- | 0.3204 | 1.0 | 2 | 0.2005 |
49
- | 0.0919 | 2.0 | 4 | 0.1535 |
50
- | 0.237 | 3.0 | 6 | 0.1760 |
51
- | 0.2656 | 4.0 | 8 | 0.1979 |
52
- | 0.3188 | 5.0 | 10 | 0.1678 |
53
- | 0.3004 | 6.0 | 12 | 0.1772 |
54
- | 0.2978 | 7.0 | 14 | 0.1631 |
55
- | 0.1303 | 8.0 | 16 | 0.1492 |
56
- | 0.2658 | 9.0 | 18 | 0.1533 |
57
- | 0.0711 | 10.0 | 20 | 0.1458 |
58
- | 0.2174 | 11.0 | 22 | 0.1521 |
59
- | 0.0588 | 12.0 | 24 | 0.1465 |
60
- | 0.0291 | 13.0 | 26 | 0.1554 |
61
- | 0.216 | 14.0 | 28 | 0.2090 |
62
- | 0.0227 | 15.0 | 30 | 0.1778 |
63
- | 0.0295 | 16.0 | 32 | 0.1356 |
64
- | 0.1516 | 17.0 | 34 | 0.1320 |
65
- | 0.1399 | 18.0 | 36 | 0.1417 |
66
- | 0.1466 | 19.0 | 38 | 0.1802 |
67
- | 0.0301 | 20.0 | 40 | 0.1462 |
68
- | 0.0906 | 21.0 | 42 | 0.1282 |
69
- | 0.0737 | 22.0 | 44 | 0.1145 |
70
- | 0.0618 | 23.0 | 46 | 0.1224 |
71
- | 0.0632 | 24.0 | 48 | 0.1860 |
72
- | 0.043 | 25.0 | 50 | 0.1616 |
73
- | 0.019 | 26.0 | 52 | 0.1203 |
74
- | 0.0451 | 27.0 | 54 | 0.1404 |
75
- | 0.0117 | 28.0 | 56 | 0.1622 |
76
- | 0.0392 | 29.0 | 58 | 0.1449 |
77
- | 0.0258 | 30.0 | 60 | 0.1155 |
78
- | 0.0077 | 31.0 | 62 | 0.1328 |
79
- | 0.0101 | 32.0 | 64 | 0.1560 |
80
- | 0.0035 | 33.0 | 66 | 0.1782 |
81
- | 0.0069 | 34.0 | 68 | 0.1546 |
82
- | 0.0387 | 35.0 | 70 | 0.1098 |
83
- | 0.0519 | 36.0 | 72 | 0.1074 |
84
- | 0.0195 | 37.0 | 74 | 0.1232 |
85
- | 0.0434 | 38.0 | 76 | 0.1861 |
86
- | 0.0204 | 39.0 | 78 | 0.1761 |
87
- | 0.0035 | 40.0 | 80 | 0.1410 |
88
- | 0.0143 | 41.0 | 82 | 0.1214 |
89
- | 0.025 | 42.0 | 84 | 0.1252 |
90
- | 0.0299 | 43.0 | 86 | 0.1141 |
91
- | 0.0093 | 44.0 | 88 | 0.1385 |
92
- | 0.0436 | 45.0 | 90 | 0.1980 |
93
- | 0.0267 | 46.0 | 92 | 0.1837 |
94
- | 0.0074 | 47.0 | 94 | 0.1228 |
95
- | 0.0332 | 48.0 | 96 | 0.0988 |
96
- | 0.0408 | 49.0 | 98 | 0.0990 |
97
- | 0.0336 | 50.0 | 100 | 0.1037 |
98
- | 0.0053 | 51.0 | 102 | 0.1642 |
99
- | 0.0684 | 52.0 | 104 | 0.2185 |
100
- | 0.0595 | 53.0 | 106 | 0.1987 |
101
- | 0.0131 | 54.0 | 108 | 0.1363 |
102
- | 0.0222 | 55.0 | 110 | 0.1014 |
103
- | 0.0364 | 56.0 | 112 | 0.0998 |
104
- | 0.0208 | 57.0 | 114 | 0.1108 |
105
- | 0.0124 | 58.0 | 116 | 0.1468 |
106
- | 0.0025 | 59.0 | 118 | 0.1517 |
107
- | 0.0026 | 60.0 | 120 | 0.1379 |
108
- | 0.0231 | 61.0 | 122 | 0.1150 |
109
- | 0.0307 | 62.0 | 124 | 0.0980 |
110
- | 0.0265 | 63.0 | 126 | 0.0980 |
111
- | 0.0273 | 64.0 | 128 | 0.1126 |
112
- | 0.005 | 65.0 | 130 | 0.1476 |
113
- | 0.0106 | 66.0 | 132 | 0.1501 |
114
- | 0.0046 | 67.0 | 134 | 0.1307 |
115
- | 0.0194 | 68.0 | 136 | 0.1038 |
116
- | 0.0219 | 69.0 | 138 | 0.0962 |
117
- | 0.0222 | 70.0 | 140 | 0.1026 |
118
- | 0.0083 | 71.0 | 142 | 0.1166 |
119
- | 0.0246 | 72.0 | 144 | 0.1447 |
120
- | 0.0386 | 73.0 | 146 | 0.1429 |
121
- | 0.0297 | 74.0 | 148 | 0.1260 |
122
- | 0.009 | 75.0 | 150 | 0.1061 |
123
- | 0.0124 | 76.0 | 152 | 0.0980 |
124
- | 0.0069 | 77.0 | 154 | 0.1042 |
125
- | 0.0123 | 78.0 | 156 | 0.1096 |
126
- | 0.0209 | 79.0 | 158 | 0.1221 |
127
- | 0.0169 | 80.0 | 160 | 0.1210 |
128
- | 0.0027 | 81.0 | 162 | 0.1101 |
129
- | 0.0141 | 82.0 | 164 | 0.1073 |
130
- | 0.0132 | 83.0 | 166 | 0.1051 |
131
- | 0.0069 | 84.0 | 168 | 0.0983 |
132
- | 0.0203 | 85.0 | 170 | 0.1027 |
133
- | 0.0056 | 86.0 | 172 | 0.1063 |
134
- | 0.0078 | 87.0 | 174 | 0.1102 |
135
- | 0.0139 | 88.0 | 176 | 0.1143 |
136
- | 0.0114 | 89.0 | 178 | 0.1109 |
137
- | 0.0046 | 90.0 | 180 | 0.1053 |
138
- | 0.0072 | 91.0 | 182 | 0.1040 |
139
- | 0.0075 | 92.0 | 184 | 0.1060 |
140
- | 0.0055 | 93.0 | 186 | 0.1051 |
141
- | 0.0019 | 94.0 | 188 | 0.1074 |
142
- | 0.0035 | 95.0 | 190 | 0.1107 |
143
- | 0.0037 | 96.0 | 192 | 0.1118 |
144
- | 0.0125 | 97.0 | 194 | 0.1134 |
145
- | 0.009 | 98.0 | 196 | 0.1125 |
146
- | 0.005 | 99.0 | 198 | 0.1112 |
147
- | 0.0033 | 100.0 | 200 | 0.1108 |
148
 
149
 
150
  ### Framework versions
 
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: 0.0537
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: 25
43
 
44
  ### Training results
45
 
46
+ | Training Loss | Epoch | Step | Validation Loss |
47
+ |:-------------:|:-----:|:------:|:---------------:|
48
+ | 0.1919 | 1.0 | 4350 | 0.0718 |
49
+ | 0.0072 | 2.0 | 8700 | 0.0734 |
50
+ | 0.0009 | 3.0 | 13050 | 0.0603 |
51
+ | 0.049 | 4.0 | 17400 | 0.0770 |
52
+ | 0.0496 | 5.0 | 21750 | 0.0554 |
53
+ | 0.001 | 6.0 | 26100 | 0.0565 |
54
+ | 0.0027 | 7.0 | 30450 | 0.0561 |
55
+ | 0.0041 | 8.0 | 34800 | 0.0607 |
56
+ | 0.0273 | 9.0 | 39150 | 0.0565 |
57
+ | 0.0344 | 10.0 | 43500 | 0.0580 |
58
+ | 0.0246 | 11.0 | 47850 | 0.0557 |
59
+ | 0.0187 | 12.0 | 52200 | 0.0624 |
60
+ | 0.0828 | 13.0 | 56550 | 0.0523 |
61
+ | 0.059 | 14.0 | 60900 | 0.0537 |
62
+ | 0.2687 | 15.0 | 65250 | 0.0561 |
63
+ | 0.0593 | 16.0 | 69600 | 0.0565 |
64
+ | 0.0015 | 17.0 | 73950 | 0.0541 |
65
+ | 0.0023 | 18.0 | 78300 | 0.0558 |
66
+ | 0.0001 | 19.0 | 82650 | 0.0532 |
67
+ | 0.0026 | 20.0 | 87000 | 0.0547 |
68
+ | 0.0339 | 21.0 | 91350 | 0.0543 |
69
+ | 0.001 | 22.0 | 95700 | 0.0567 |
70
+ | 0.0553 | 23.0 | 100050 | 0.0545 |
71
+ | 0.0038 | 24.0 | 104400 | 0.0536 |
72
+ | 0.012 | 25.0 | 108750 | 0.0537 |
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
73
 
74
 
75
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:37bf1bec0ecd6cab50c0d1445022940a26f4dd14441f902483ebc189c1e3510c
3
  size 11213056
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:71e4e0f44a3581c024ffce11a2f776b97dd399603f1801b43ffc195ae4fb8054
3
  size 11213056