ludziej commited on
Commit
e240099
1 Parent(s): d67a818

End of training

Browse files
README.md CHANGED
@@ -12,6 +12,8 @@ should probably proofread and complete it, then remove this comment. -->
12
  # calculator_model_test
13
 
14
  This model is a fine-tuned version of [](https://huggingface.co/) on the None dataset.
 
 
15
 
16
  ## Model description
17
 
@@ -36,13 +38,113 @@ The following hyperparameters were used during training:
36
  - seed: 42
37
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
38
  - lr_scheduler_type: linear
39
- - num_epochs: 1
 
40
 
41
  ### Training results
42
 
43
  | Training Loss | Epoch | Step | Validation Loss |
44
  |:-------------:|:-----:|:----:|:---------------:|
45
- | No log | 1.0 | 6 | 7.7657 |
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
46
 
47
 
48
  ### Framework versions
 
12
  # calculator_model_test
13
 
14
  This model is a fine-tuned version of [](https://huggingface.co/) on the None dataset.
15
+ It achieves the following results on the evaluation set:
16
+ - Loss: 0.7800
17
 
18
  ## Model description
19
 
 
38
  - seed: 42
39
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
40
  - lr_scheduler_type: linear
41
+ - num_epochs: 100
42
+ - mixed_precision_training: Native AMP
43
 
44
  ### Training results
45
 
46
  | Training Loss | Epoch | Step | Validation Loss |
47
  |:-------------:|:-----:|:----:|:---------------:|
48
+ | No log | 1.0 | 6 | 6.5672 |
49
+ | No log | 2.0 | 12 | 5.9069 |
50
+ | No log | 3.0 | 18 | 5.4671 |
51
+ | No log | 4.0 | 24 | 5.0855 |
52
+ | No log | 5.0 | 30 | 4.7085 |
53
+ | No log | 6.0 | 36 | 4.3935 |
54
+ | No log | 7.0 | 42 | 4.1354 |
55
+ | No log | 8.0 | 48 | 3.9330 |
56
+ | No log | 9.0 | 54 | 3.7647 |
57
+ | No log | 10.0 | 60 | 3.6286 |
58
+ | No log | 11.0 | 66 | 3.5173 |
59
+ | No log | 12.0 | 72 | 3.4148 |
60
+ | No log | 13.0 | 78 | 3.3148 |
61
+ | No log | 14.0 | 84 | 3.2218 |
62
+ | No log | 15.0 | 90 | 3.1353 |
63
+ | No log | 16.0 | 96 | 3.0524 |
64
+ | No log | 17.0 | 102 | 2.9751 |
65
+ | No log | 18.0 | 108 | 2.9017 |
66
+ | No log | 19.0 | 114 | 2.8277 |
67
+ | No log | 20.0 | 120 | 2.7534 |
68
+ | No log | 21.0 | 126 | 2.6865 |
69
+ | No log | 22.0 | 132 | 2.6260 |
70
+ | No log | 23.0 | 138 | 2.5597 |
71
+ | No log | 24.0 | 144 | 2.4913 |
72
+ | No log | 25.0 | 150 | 2.4295 |
73
+ | No log | 26.0 | 156 | 2.3668 |
74
+ | No log | 27.0 | 162 | 2.3040 |
75
+ | No log | 28.0 | 168 | 2.2391 |
76
+ | No log | 29.0 | 174 | 2.1745 |
77
+ | No log | 30.0 | 180 | 2.1036 |
78
+ | No log | 31.0 | 186 | 2.0443 |
79
+ | No log | 32.0 | 192 | 1.9919 |
80
+ | No log | 33.0 | 198 | 1.9321 |
81
+ | No log | 34.0 | 204 | 1.8771 |
82
+ | No log | 35.0 | 210 | 1.8386 |
83
+ | No log | 36.0 | 216 | 1.7951 |
84
+ | No log | 37.0 | 222 | 1.7460 |
85
+ | No log | 38.0 | 228 | 1.6974 |
86
+ | No log | 39.0 | 234 | 1.6576 |
87
+ | No log | 40.0 | 240 | 1.6112 |
88
+ | No log | 41.0 | 246 | 1.5811 |
89
+ | No log | 42.0 | 252 | 1.5540 |
90
+ | No log | 43.0 | 258 | 1.5268 |
91
+ | No log | 44.0 | 264 | 1.4873 |
92
+ | No log | 45.0 | 270 | 1.4500 |
93
+ | No log | 46.0 | 276 | 1.4161 |
94
+ | No log | 47.0 | 282 | 1.3738 |
95
+ | No log | 48.0 | 288 | 1.3495 |
96
+ | No log | 49.0 | 294 | 1.3182 |
97
+ | No log | 50.0 | 300 | 1.2899 |
98
+ | No log | 51.0 | 306 | 1.2610 |
99
+ | No log | 52.0 | 312 | 1.2478 |
100
+ | No log | 53.0 | 318 | 1.2238 |
101
+ | No log | 54.0 | 324 | 1.2060 |
102
+ | No log | 55.0 | 330 | 1.1794 |
103
+ | No log | 56.0 | 336 | 1.1774 |
104
+ | No log | 57.0 | 342 | 1.1425 |
105
+ | No log | 58.0 | 348 | 1.1166 |
106
+ | No log | 59.0 | 354 | 1.1044 |
107
+ | No log | 60.0 | 360 | 1.0913 |
108
+ | No log | 61.0 | 366 | 1.0775 |
109
+ | No log | 62.0 | 372 | 1.0694 |
110
+ | No log | 63.0 | 378 | 1.0311 |
111
+ | No log | 64.0 | 384 | 1.0272 |
112
+ | No log | 65.0 | 390 | 1.0249 |
113
+ | No log | 66.0 | 396 | 0.9923 |
114
+ | No log | 67.0 | 402 | 0.9892 |
115
+ | No log | 68.0 | 408 | 0.9762 |
116
+ | No log | 69.0 | 414 | 0.9704 |
117
+ | No log | 70.0 | 420 | 0.9405 |
118
+ | No log | 71.0 | 426 | 0.9394 |
119
+ | No log | 72.0 | 432 | 0.9237 |
120
+ | No log | 73.0 | 438 | 0.9180 |
121
+ | No log | 74.0 | 444 | 0.8926 |
122
+ | No log | 75.0 | 450 | 0.9081 |
123
+ | No log | 76.0 | 456 | 0.8778 |
124
+ | No log | 77.0 | 462 | 0.8785 |
125
+ | No log | 78.0 | 468 | 0.8580 |
126
+ | No log | 79.0 | 474 | 0.8593 |
127
+ | No log | 80.0 | 480 | 0.8553 |
128
+ | No log | 81.0 | 486 | 0.8671 |
129
+ | No log | 82.0 | 492 | 0.8422 |
130
+ | No log | 83.0 | 498 | 0.8403 |
131
+ | 2.0956 | 84.0 | 504 | 0.8355 |
132
+ | 2.0956 | 85.0 | 510 | 0.8188 |
133
+ | 2.0956 | 86.0 | 516 | 0.8149 |
134
+ | 2.0956 | 87.0 | 522 | 0.8285 |
135
+ | 2.0956 | 88.0 | 528 | 0.8063 |
136
+ | 2.0956 | 89.0 | 534 | 0.8166 |
137
+ | 2.0956 | 90.0 | 540 | 0.8008 |
138
+ | 2.0956 | 91.0 | 546 | 0.8127 |
139
+ | 2.0956 | 92.0 | 552 | 0.7921 |
140
+ | 2.0956 | 93.0 | 558 | 0.8015 |
141
+ | 2.0956 | 94.0 | 564 | 0.7882 |
142
+ | 2.0956 | 95.0 | 570 | 0.7844 |
143
+ | 2.0956 | 96.0 | 576 | 0.7862 |
144
+ | 2.0956 | 97.0 | 582 | 0.7810 |
145
+ | 2.0956 | 98.0 | 588 | 0.7808 |
146
+ | 2.0956 | 99.0 | 594 | 0.7810 |
147
+ | 2.0956 | 100.0 | 600 | 0.7800 |
148
 
149
 
150
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1adb0d38cb3a7dc39fb74d9e509c488b7f8f0f461f1fa87705d9c600635e0ae5
3
  size 989518784
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fae817cbabf8915ca265feb78d2fad2a1c3568e7be552c9c73e7b1732c4434af
3
  size 989518784
runs/Feb27_15-36-45_b9753d8dede3/events.out.tfevents.1709048206.b9753d8dede3.176.1 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2b544e6b00fe6fca07ebbe1197b8c74351ab47c3461d167e5fd2843d014f3338
3
- size 31204
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e2453a2ea9fb4881cba8010a22be1c142e41c2f8e77393be283b78dbcc612b8f
3
+ size 35894