Hugging Face's logo

KanWasTaken
/
WhartonDS_RegressionModel

Transformers
Safetensors
feature_grouping
Generated from Trainer
Model card Files
xet
Community
KanWasTaken commited on
Commit
fabf390
·
verified ·
1 Parent(s): bb9aff9

Model save

Browse files
Files changed (1) hide show
  1. README.md +63 -33
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: 0.0179
18
 
19
  ## Model description
20
 
@@ -38,43 +38,73 @@ The following hyperparameters were used during training:
38
  - eval_batch_size: 64
39
  - seed: 42
40
  - optimizer: Use 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: 30
43
 
44
  ### Training results
45
 
46
  | Training Loss | Epoch | Step | Validation Loss |
47
  |:-------------:|:-----:|:----:|:---------------:|
48
- | 0.1199 | 1.0 | 24 | 0.1082 |
49
- | 0.0995 | 2.0 | 48 | 0.0940 |
50
- | 0.0821 | 3.0 | 72 | 0.0884 |
51
- | 0.0666 | 4.0 | 96 | 0.0775 |
52
- | 0.0532 | 5.0 | 120 | 0.0572 |
53
- | 0.0423 | 6.0 | 144 | 0.0396 |
54
- | 0.034 | 7.0 | 168 | 0.0313 |
55
- | 0.0283 | 8.0 | 192 | 0.0279 |
56
- | 0.0252 | 9.0 | 216 | 0.0243 |
57
- | 0.023 | 10.0 | 240 | 0.0218 |
58
- | 0.0218 | 11.0 | 264 | 0.0230 |
59
- | 0.0207 | 12.0 | 288 | 0.0209 |
60
- | 0.0202 | 13.0 | 312 | 0.0200 |
61
- | 0.02 | 14.0 | 336 | 0.0195 |
62
- | 0.0196 | 15.0 | 360 | 0.0189 |
63
- | 0.0195 | 16.0 | 384 | 0.0189 |
64
- | 0.0191 | 17.0 | 408 | 0.0188 |
65
- | 0.019 | 18.0 | 432 | 0.0185 |
66
- | 0.019 | 19.0 | 456 | 0.0185 |
67
- | 0.0189 | 20.0 | 480 | 0.0185 |
68
- | 0.0189 | 21.0 | 504 | 0.0184 |
69
- | 0.0188 | 22.0 | 528 | 0.0182 |
70
- | 0.0188 | 23.0 | 552 | 0.0183 |
71
- | 0.0187 | 24.0 | 576 | 0.0183 |
72
- | 0.0187 | 25.0 | 600 | 0.0181 |
73
- | 0.0187 | 26.0 | 624 | 0.0180 |
74
- | 0.0186 | 27.0 | 648 | 0.0180 |
75
- | 0.0186 | 28.0 | 672 | 0.0180 |
76
- | 0.0186 | 29.0 | 696 | 0.0180 |
77
- | 0.0186 | 30.0 | 720 | 0.0179 |
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
78
 
79
 
80
  ### 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: 0.0088
18
 
19
  ## Model description
20
 
 
38
  - eval_batch_size: 64
39
  - seed: 42
40
  - optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
41
+ - lr_scheduler_type: cosine
42
+ - num_epochs: 60
43
 
44
  ### Training results
45
 
46
  | Training Loss | Epoch | Step | Validation Loss |
47
  |:-------------:|:-----:|:----:|:---------------:|
48
+ | 0.0604 | 1.0 | 24 | 0.0629 |
49
+ | 0.0497 | 2.0 | 48 | 0.0517 |
50
+ | 0.0402 | 3.0 | 72 | 0.0461 |
51
+ | 0.0316 | 4.0 | 96 | 0.0341 |
52
+ | 0.0246 | 5.0 | 120 | 0.0243 |
53
+ | 0.0193 | 6.0 | 144 | 0.0182 |
54
+ | 0.0155 | 7.0 | 168 | 0.0146 |
55
+ | 0.013 | 8.0 | 192 | 0.0130 |
56
+ | 0.0116 | 9.0 | 216 | 0.0113 |
57
+ | 0.0108 | 10.0 | 240 | 0.0108 |
58
+ | 0.0105 | 11.0 | 264 | 0.0113 |
59
+ | 0.0101 | 12.0 | 288 | 0.0101 |
60
+ | 0.01 | 13.0 | 312 | 0.0100 |
61
+ | 0.0099 | 14.0 | 336 | 0.0097 |
62
+ | 0.0097 | 15.0 | 360 | 0.0097 |
63
+ | 0.0096 | 16.0 | 384 | 0.0098 |
64
+ | 0.0096 | 17.0 | 408 | 0.0095 |
65
+ | 0.0095 | 18.0 | 432 | 0.0094 |
66
+ | 0.0095 | 19.0 | 456 | 0.0094 |
67
+ | 0.0094 | 20.0 | 480 | 0.0092 |
68
+ | 0.0094 | 21.0 | 504 | 0.0093 |
69
+ | 0.0093 | 22.0 | 528 | 0.0092 |
70
+ | 0.0093 | 23.0 | 552 | 0.0092 |
71
+ | 0.0093 | 24.0 | 576 | 0.0094 |
72
+ | 0.0093 | 25.0 | 600 | 0.0090 |
73
+ | 0.0093 | 26.0 | 624 | 0.0090 |
74
+ | 0.0093 | 27.0 | 648 | 0.0092 |
75
+ | 0.0092 | 28.0 | 672 | 0.0091 |
76
+ | 0.0092 | 29.0 | 696 | 0.0090 |
77
+ | 0.0091 | 30.0 | 720 | 0.0090 |
78
+ | 0.0091 | 31.0 | 744 | 0.0091 |
79
+ | 0.0091 | 32.0 | 768 | 0.0090 |
80
+ | 0.0091 | 33.0 | 792 | 0.0090 |
81
+ | 0.009 | 34.0 | 816 | 0.0090 |
82
+ | 0.0091 | 35.0 | 840 | 0.0089 |
83
+ | 0.0091 | 36.0 | 864 | 0.0090 |
84
+ | 0.0091 | 37.0 | 888 | 0.0089 |
85
+ | 0.009 | 38.0 | 912 | 0.0089 |
86
+ | 0.009 | 39.0 | 936 | 0.0089 |
87
+ | 0.009 | 40.0 | 960 | 0.0089 |
88
+ | 0.009 | 41.0 | 984 | 0.0089 |
89
+ | 0.009 | 42.0 | 1008 | 0.0088 |
90
+ | 0.009 | 43.0 | 1032 | 0.0088 |
91
+ | 0.009 | 44.0 | 1056 | 0.0088 |
92
+ | 0.009 | 45.0 | 1080 | 0.0089 |
93
+ | 0.009 | 46.0 | 1104 | 0.0088 |
94
+ | 0.009 | 47.0 | 1128 | 0.0088 |
95
+ | 0.009 | 48.0 | 1152 | 0.0088 |
96
+ | 0.009 | 49.0 | 1176 | 0.0088 |
97
+ | 0.0089 | 50.0 | 1200 | 0.0088 |
98
+ | 0.009 | 51.0 | 1224 | 0.0088 |
99
+ | 0.0089 | 52.0 | 1248 | 0.0088 |
100
+ | 0.009 | 53.0 | 1272 | 0.0088 |
101
+ | 0.009 | 54.0 | 1296 | 0.0088 |
102
+ | 0.009 | 55.0 | 1320 | 0.0088 |
103
+ | 0.0089 | 56.0 | 1344 | 0.0088 |
104
+ | 0.009 | 57.0 | 1368 | 0.0088 |
105
+ | 0.0089 | 58.0 | 1392 | 0.0088 |
106
+ | 0.009 | 59.0 | 1416 | 0.0089 |
107
+ | 0.009 | 60.0 | 1440 | 0.0088 |
108
 
109
 
110
  ### Framework versions