Hugging Face's logo

msanocki
/
calculator_model_test

Transformers
Safetensors
encoder-decoder
text2text-generation
Generated from Trainer
Model card Files
xet
 Community
msanocki commited on
Commit
09ef877
·
verified ·
1 Parent(s): db224ac

End of training

Browse files
Files changed (1) hide show
  1. README.md +104 -43
README.md CHANGED
@@ -1,5 +1,6 @@
1
  ---
2
  library_name: transformers
 
3
  tags:
4
  - generated_from_trainer
5
  model-index:
@@ -12,9 +13,9 @@ should probably proofread and complete it, then remove this comment. -->
12
 
13
  # calculator_model_test
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: 0.0711
18
 
19
  ## Model description
20
 
@@ -39,52 +40,112 @@ The following hyperparameters were used during training:
39
  - seed: 42
40
  - optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED 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: 40
43
 
44
  ### Training results
45
 
46
  | Training Loss | Epoch | Step | Validation Loss |
47
  |:-------------:|:-----:|:----:|:---------------:|
48
- | 3.0184 | 1.0 | 6 | 2.2778 |
49
- | 2.0303 | 2.0 | 12 | 1.7549 |
50
- | 1.5757 | 3.0 | 18 | 1.3384 |
51
- | 1.2324 | 4.0 | 24 | 1.0920 |
52
- | 1.0666 | 5.0 | 30 | 1.0164 |
53
- | 0.9238 | 6.0 | 36 | 0.8245 |
54
- | 0.7851 | 7.0 | 42 | 0.7413 |
55
- | 0.7044 | 8.0 | 48 | 0.6817 |
56
- | 0.6541 | 9.0 | 54 | 0.6095 |
57
- | 0.6084 | 10.0 | 60 | 0.5744 |
58
- | 0.5697 | 11.0 | 66 | 0.5433 |
59
- | 0.5481 | 12.0 | 72 | 0.5173 |
60
- | 0.5066 | 13.0 | 78 | 0.4865 |
61
- | 0.4779 | 14.0 | 84 | 0.4872 |
62
- | 0.4716 | 15.0 | 90 | 0.4400 |
63
- | 0.4263 | 16.0 | 96 | 0.3727 |
64
- | 0.3855 | 17.0 | 102 | 0.3495 |
65
- | 0.3493 | 18.0 | 108 | 0.3225 |
66
- | 0.3193 | 19.0 | 114 | 0.2796 |
67
- | 0.2755 | 20.0 | 120 | 0.2446 |
68
- | 0.2607 | 21.0 | 126 | 0.2228 |
69
- | 0.2401 | 22.0 | 132 | 0.2059 |
70
- | 0.2166 | 23.0 | 138 | 0.1822 |
71
- | 0.1968 | 24.0 | 144 | 0.1585 |
72
- | 0.1758 | 25.0 | 150 | 0.1600 |
73
- | 0.1743 | 26.0 | 156 | 0.1318 |
74
- | 0.1514 | 27.0 | 162 | 0.1226 |
75
- | 0.1505 | 28.0 | 168 | 0.1253 |
76
- | 0.1406 | 29.0 | 174 | 0.1119 |
77
- | 0.1289 | 30.0 | 180 | 0.1053 |
78
- | 0.1244 | 31.0 | 186 | 0.0989 |
79
- | 0.1194 | 32.0 | 192 | 0.0877 |
80
- | 0.1183 | 33.0 | 198 | 0.0857 |
81
- | 0.1097 | 34.0 | 204 | 0.0842 |
82
- | 0.1019 | 35.0 | 210 | 0.0774 |
83
- | 0.1001 | 36.0 | 216 | 0.0771 |
84
- | 0.0991 | 37.0 | 222 | 0.0738 |
85
- | 0.0964 | 38.0 | 228 | 0.0729 |
86
- | 0.0946 | 39.0 | 234 | 0.0728 |
87
- | 0.0901 | 40.0 | 240 | 0.0711 |
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
88
 
89
 
90
  ### Framework versions
 
1
  ---
2
  library_name: transformers
3
+ base_model: msanocki/calculator_model_test
4
  tags:
5
  - generated_from_trainer
6
  model-index:
 
13
 
14
  # calculator_model_test
15
 
16
+ This model is a fine-tuned version of [msanocki/calculator_model_test](https://huggingface.co/msanocki/calculator_model_test) on the None dataset.
17
  It achieves the following results on the evaluation set:
18
+ - Loss: 0.0039
19
 
20
  ## Model description
21
 
 
40
  - seed: 42
41
  - optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
42
  - lr_scheduler_type: linear
43
+ - num_epochs: 100
44
 
45
  ### Training results
46
 
47
  | Training Loss | Epoch | Step | Validation Loss |
48
  |:-------------:|:-----:|:----:|:---------------:|
49
+ | 0.7263 | 1.0 | 6 | 0.5579 |
50
+ | 0.4040 | 2.0 | 12 | 0.3037 |
51
+ | 0.2737 | 3.0 | 18 | 0.1986 |
52
+ | 0.1990 | 4.0 | 24 | 0.1674 |
53
+ | 0.1645 | 5.0 | 30 | 0.1309 |
54
+ | 0.1471 | 6.0 | 36 | 0.1474 |
55
+ | 0.1606 | 7.0 | 42 | 0.1082 |
56
+ | 0.1205 | 8.0 | 48 | 0.1006 |
57
+ | 0.1211 | 9.0 | 54 | 0.1031 |
58
+ | 0.1126 | 10.0 | 60 | 0.0732 |
59
+ | 0.0970 | 11.0 | 66 | 0.1148 |
60
+ | 0.1128 | 12.0 | 72 | 0.0826 |
61
+ | 0.0897 | 13.0 | 78 | 0.0940 |
62
+ | 0.0881 | 14.0 | 84 | 0.0908 |
63
+ | 0.0800 | 15.0 | 90 | 0.0572 |
64
+ | 0.0738 | 16.0 | 96 | 0.0461 |
65
+ | 0.0721 | 17.0 | 102 | 0.0405 |
66
+ | 0.0568 | 18.0 | 108 | 0.0459 |
67
+ | 0.0583 | 19.0 | 114 | 0.0406 |
68
+ | 0.0520 | 20.0 | 120 | 0.0542 |
69
+ | 0.0617 | 21.0 | 126 | 0.0396 |
70
+ | 0.0564 | 22.0 | 132 | 0.0374 |
71
+ | 0.0592 | 23.0 | 138 | 0.0438 |
72
+ | 0.0570 | 24.0 | 144 | 0.0459 |
73
+ | 0.0549 | 25.0 | 150 | 0.0510 |
74
+ | 0.0570 | 26.0 | 156 | 0.0470 |
75
+ | 0.0498 | 27.0 | 162 | 0.0304 |
76
+ | 0.0429 | 28.0 | 168 | 0.0294 |
77
+ | 0.0391 | 29.0 | 174 | 0.0266 |
78
+ | 0.0339 | 30.0 | 180 | 0.0219 |
79
+ | 0.0354 | 31.0 | 186 | 0.0190 |
80
+ | 0.0293 | 32.0 | 192 | 0.0234 |
81
+ | 0.0276 | 33.0 | 198 | 0.0167 |
82
+ | 0.0295 | 34.0 | 204 | 0.0182 |
83
+ | 0.0228 | 35.0 | 210 | 0.0175 |
84
+ | 0.0245 | 36.0 | 216 | 0.0189 |
85
+ | 0.0335 | 37.0 | 222 | 0.0195 |
86
+ | 0.0377 | 38.0 | 228 | 0.0312 |
87
+ | 0.0387 | 39.0 | 234 | 0.0355 |
88
+ | 0.0414 | 40.0 | 240 | 0.0597 |
89
+ | 0.0527 | 41.0 | 246 | 0.0405 |
90
+ | 0.0417 | 42.0 | 252 | 0.0187 |
91
+ | 0.0341 | 43.0 | 258 | 0.0204 |
92
+ | 0.0339 | 44.0 | 264 | 0.0157 |
93
+ | 0.0288 | 45.0 | 270 | 0.0178 |
94
+ | 0.0249 | 46.0 | 276 | 0.0128 |
95
+ | 0.0237 | 47.0 | 282 | 0.0170 |
96
+ | 0.0246 | 48.0 | 288 | 0.0141 |
97
+ | 0.0202 | 49.0 | 294 | 0.0182 |
98
+ | 0.0262 | 50.0 | 300 | 0.0127 |
99
+ | 0.0234 | 51.0 | 306 | 0.0141 |
100
+ | 0.0213 | 52.0 | 312 | 0.0164 |
101
+ | 0.0184 | 53.0 | 318 | 0.0111 |
102
+ | 0.0130 | 54.0 | 324 | 0.0112 |
103
+ | 0.0140 | 55.0 | 330 | 0.0086 |
104
+ | 0.0144 | 56.0 | 336 | 0.0080 |
105
+ | 0.0110 | 57.0 | 342 | 0.0087 |
106
+ | 0.0100 | 58.0 | 348 | 0.0081 |
107
+ | 0.0095 | 59.0 | 354 | 0.0079 |
108
+ | 0.0119 | 60.0 | 360 | 0.0075 |
109
+ | 0.0099 | 61.0 | 366 | 0.0071 |
110
+ | 0.0081 | 62.0 | 372 | 0.0069 |
111
+ | 0.0081 | 63.0 | 378 | 0.0061 |
112
+ | 0.0112 | 64.0 | 384 | 0.0064 |
113
+ | 0.0087 | 65.0 | 390 | 0.0068 |
114
+ | 0.0099 | 66.0 | 396 | 0.0069 |
115
+ | 0.0078 | 67.0 | 402 | 0.0071 |
116
+ | 0.0096 | 68.0 | 408 | 0.0068 |
117
+ | 0.0084 | 69.0 | 414 | 0.0064 |
118
+ | 0.0080 | 70.0 | 420 | 0.0066 |
119
+ | 0.0068 | 71.0 | 426 | 0.0081 |
120
+ | 0.0065 | 72.0 | 432 | 0.0056 |
121
+ | 0.0058 | 73.0 | 438 | 0.0052 |
122
+ | 0.0049 | 74.0 | 444 | 0.0048 |
123
+ | 0.0047 | 75.0 | 450 | 0.0048 |
124
+ | 0.0069 | 76.0 | 456 | 0.0048 |
125
+ | 0.0109 | 77.0 | 462 | 0.0066 |
126
+ | 0.0068 | 78.0 | 468 | 0.0062 |
127
+ | 0.0071 | 79.0 | 474 | 0.0059 |
128
+ | 0.0059 | 80.0 | 480 | 0.0055 |
129
+ | 0.0058 | 81.0 | 486 | 0.0053 |
130
+ | 0.0054 | 82.0 | 492 | 0.0052 |
131
+ | 0.0049 | 83.0 | 498 | 0.0047 |
132
+ | 0.0041 | 84.0 | 504 | 0.0048 |
133
+ | 0.0043 | 85.0 | 510 | 0.0045 |
134
+ | 0.0042 | 86.0 | 516 | 0.0044 |
135
+ | 0.0038 | 87.0 | 522 | 0.0044 |
136
+ | 0.0036 | 88.0 | 528 | 0.0043 |
137
+ | 0.0039 | 89.0 | 534 | 0.0042 |
138
+ | 0.0039 | 90.0 | 540 | 0.0044 |
139
+ | 0.0043 | 91.0 | 546 | 0.0041 |
140
+ | 0.0038 | 92.0 | 552 | 0.0042 |
141
+ | 0.0038 | 93.0 | 558 | 0.0042 |
142
+ | 0.0038 | 94.0 | 564 | 0.0042 |
143
+ | 0.0034 | 95.0 | 570 | 0.0041 |
144
+ | 0.0040 | 96.0 | 576 | 0.0041 |
145
+ | 0.0042 | 97.0 | 582 | 0.0040 |
146
+ | 0.0038 | 98.0 | 588 | 0.0039 |
147
+ | 0.0050 | 99.0 | 594 | 0.0039 |
148
+ | 0.0037 | 100.0 | 600 | 0.0039 |
149
 
150
 
151
  ### Framework versions