Hugging Face's logo

agawrysiak
/
calculator_model_test

Transformers
Safetensors
encoder-decoder
text2text-generation
Generated from Trainer
Model card Files
xet
 Community
agawrysiak commited on
Commit
6d11d0c
·
verified ·
1 Parent(s): 3e95969

End of training

Browse files
Files changed (1) hide show
  1. README.md +42 -42
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 the None dataset.
16
  It achieves the following results on the evaluation set:
17
- - Loss: 0.1928
18
 
19
  ## Model description
20
 
@@ -33,7 +33,7 @@ More information needed
33
  ### Training hyperparameters
34
 
35
  The following hyperparameters were used during training:
36
- - learning_rate: 0.001
37
  - train_batch_size: 512
38
  - eval_batch_size: 512
39
  - seed: 42
@@ -45,46 +45,46 @@ The following hyperparameters were used during training:
45
 
46
  | Training Loss | Epoch | Step | Validation Loss |
47
  |:-------------:|:-----:|:----:|:---------------:|
48
- | 2.9688 | 1.0 | 6 | 2.2618 |
49
- | 2.0463 | 2.0 | 12 | 1.7658 |
50
- | 1.6335 | 3.0 | 18 | 1.4583 |
51
- | 1.3506 | 4.0 | 24 | 1.1719 |
52
- | 1.0987 | 5.0 | 30 | 1.0086 |
53
- | 0.9764 | 6.0 | 36 | 0.8944 |
54
- | 0.8517 | 7.0 | 42 | 0.7905 |
55
- | 0.7618 | 8.0 | 48 | 0.7111 |
56
- | 0.7292 | 9.0 | 54 | 0.7761 |
57
- | 0.7489 | 10.0 | 60 | 0.7421 |
58
- | 0.6985 | 11.0 | 66 | 0.6558 |
59
- | 0.6412 | 12.0 | 72 | 0.6008 |
60
- | 0.5988 | 13.0 | 78 | 0.5597 |
61
- | 0.5547 | 14.0 | 84 | 0.5069 |
62
- | 0.5208 | 15.0 | 90 | 0.4961 |
63
- | 0.4984 | 16.0 | 96 | 0.4657 |
64
- | 0.4855 | 17.0 | 102 | 0.4406 |
65
- | 0.4615 | 18.0 | 108 | 0.4227 |
66
- | 0.4355 | 19.0 | 114 | 0.4075 |
67
- | 0.4533 | 20.0 | 120 | 0.3955 |
68
- | 0.4188 | 21.0 | 126 | 0.3824 |
69
- | 0.3891 | 22.0 | 132 | 0.3730 |
70
- | 0.3935 | 23.0 | 138 | 0.3467 |
71
- | 0.3709 | 24.0 | 144 | 0.3312 |
72
- | 0.3607 | 25.0 | 150 | 0.3152 |
73
- | 0.3323 | 26.0 | 156 | 0.3217 |
74
- | 0.3469 | 27.0 | 162 | 0.2984 |
75
- | 0.3140 | 28.0 | 168 | 0.2789 |
76
- | 0.3121 | 29.0 | 174 | 0.2604 |
77
- | 0.3038 | 30.0 | 180 | 0.2535 |
78
- | 0.2811 | 31.0 | 186 | 0.2362 |
79
- | 0.2768 | 32.0 | 192 | 0.2282 |
80
- | 0.2747 | 33.0 | 198 | 0.2192 |
81
- | 0.2578 | 34.0 | 204 | 0.2116 |
82
- | 0.2619 | 35.0 | 210 | 0.2085 |
83
- | 0.2396 | 36.0 | 216 | 0.2056 |
84
- | 0.2463 | 37.0 | 222 | 0.1980 |
85
- | 0.2327 | 38.0 | 228 | 0.1969 |
86
- | 0.2426 | 39.0 | 234 | 0.1948 |
87
- | 0.2349 | 40.0 | 240 | 0.1928 |
88
 
89
 
90
  ### Framework versions
 
14
 
15
  This model is a fine-tuned version of [](https://huggingface.co/) on the None dataset.
16
  It achieves the following results on the evaluation set:
17
+ - Loss: 0.9541
18
 
19
  ## Model description
20
 
 
33
  ### Training hyperparameters
34
 
35
  The following hyperparameters were used during training:
36
+ - learning_rate: 0.0001
37
  - train_batch_size: 512
38
  - eval_batch_size: 512
39
  - seed: 42
 
45
 
46
  | Training Loss | Epoch | Step | Validation Loss |
47
  |:-------------:|:-----:|:----:|:---------------:|
48
+ | 3.6580 | 1.0 | 6 | 3.2453 |
49
+ | 3.1079 | 2.0 | 12 | 2.8981 |
50
+ | 2.8039 | 3.0 | 18 | 2.6629 |
51
+ | 2.6131 | 4.0 | 24 | 2.5056 |
52
+ | 2.4617 | 5.0 | 30 | 2.3752 |
53
+ | 2.3350 | 6.0 | 36 | 2.2642 |
54
+ | 2.2296 | 7.0 | 42 | 2.1748 |
55
+ | 2.1459 | 8.0 | 48 | 2.0943 |
56
+ | 2.0633 | 9.0 | 54 | 2.0142 |
57
+ | 1.9671 | 10.0 | 60 | 1.9194 |
58
+ | 1.8781 | 11.0 | 66 | 1.8104 |
59
+ | 1.7735 | 12.0 | 72 | 1.6989 |
60
+ | 1.6788 | 13.0 | 78 | 1.6040 |
61
+ | 1.5891 | 14.0 | 84 | 1.5262 |
62
+ | 1.5152 | 15.0 | 90 | 1.4682 |
63
+ | 1.4592 | 16.0 | 96 | 1.4185 |
64
+ | 1.4132 | 17.0 | 102 | 1.3766 |
65
+ | 1.3728 | 18.0 | 108 | 1.3385 |
66
+ | 1.3356 | 19.0 | 114 | 1.3063 |
67
+ | 1.3025 | 20.0 | 120 | 1.2722 |
68
+ | 1.2656 | 21.0 | 126 | 1.2434 |
69
+ | 1.2433 | 22.0 | 132 | 1.2168 |
70
+ | 1.2150 | 23.0 | 138 | 1.1880 |
71
+ | 1.1891 | 24.0 | 144 | 1.1642 |
72
+ | 1.1656 | 25.0 | 150 | 1.1414 |
73
+ | 1.1386 | 26.0 | 156 | 1.1177 |
74
+ | 1.1159 | 27.0 | 162 | 1.0988 |
75
+ | 1.0934 | 28.0 | 168 | 1.0751 |
76
+ | 1.0739 | 29.0 | 174 | 1.0548 |
77
+ | 1.0619 | 30.0 | 180 | 1.0354 |
78
+ | 1.0372 | 31.0 | 186 | 1.0206 |
79
+ | 1.0235 | 32.0 | 192 | 1.0072 |
80
+ | 1.0175 | 33.0 | 198 | 0.9949 |
81
+ | 1.0034 | 34.0 | 204 | 0.9841 |
82
+ | 0.9859 | 35.0 | 210 | 0.9759 |
83
+ | 0.9895 | 36.0 | 216 | 0.9683 |
84
+ | 0.9779 | 37.0 | 222 | 0.9622 |
85
+ | 0.9706 | 38.0 | 228 | 0.9574 |
86
+ | 0.9735 | 39.0 | 234 | 0.9549 |
87
+ | 0.9607 | 40.0 | 240 | 0.9541 |
88
 
89
 
90
  ### Framework versions