Hugging Face's logo

quantumLeopard
/
calculator_model_test

Transformers
Safetensors
encoder-decoder
text2text-generation
Generated from Trainer
Model card Files
xet
 Community
quantumLeopard commited on
Commit
0e51781
·
verified ·
1 Parent(s): 96f88a2

End of training

Browse files
Files changed (2) hide show
  1. README.md +42 -41
  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 the None dataset.
16
  It achieves the following results on the evaluation set:
17
- - Loss: 0.0081
18
 
19
  ## Model description
20
 
@@ -40,51 +40,52 @@ The following hyperparameters were used during training:
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
- | 2.3082 | 1.0 | 13 | 1.5231 |
49
- | 1.1642 | 2.0 | 26 | 0.6529 |
50
- | 0.5406 | 3.0 | 39 | 0.4543 |
51
- | 0.4265 | 4.0 | 52 | 0.3722 |
52
- | 0.3552 | 5.0 | 65 | 0.3185 |
53
- | 0.3062 | 6.0 | 78 | 0.2691 |
54
- | 0.2728 | 7.0 | 91 | 0.2339 |
55
- | 0.2413 | 8.0 | 104 | 0.2233 |
56
- | 0.2198 | 9.0 | 117 | 0.1933 |
57
- | 0.1998 | 10.0 | 130 | 0.1740 |
58
- | 0.1837 | 11.0 | 143 | 0.1533 |
59
- | 0.1708 | 12.0 | 156 | 0.1555 |
60
- | 0.1567 | 13.0 | 169 | 0.1211 |
61
- | 0.1362 | 14.0 | 182 | 0.1083 |
62
- | 0.1219 | 15.0 | 195 | 0.0929 |
63
- | 0.1065 | 16.0 | 208 | 0.0694 |
64
- | 0.0861 | 17.0 | 221 | 0.0588 |
65
- | 0.0690 | 18.0 | 234 | 0.0387 |
66
- | 0.0567 | 19.0 | 247 | 0.0314 |
67
- | 0.0504 | 20.0 | 260 | 0.0283 |
68
- | 0.0448 | 21.0 | 273 | 0.0296 |
69
- | 0.0388 | 22.0 | 286 | 0.0217 |
70
- | 0.0339 | 23.0 | 299 | 0.0192 |
71
- | 0.0304 | 24.0 | 312 | 0.0181 |
72
- | 0.0294 | 25.0 | 325 | 0.0158 |
73
- | 0.0279 | 26.0 | 338 | 0.0138 |
74
- | 0.0249 | 27.0 | 351 | 0.0134 |
75
- | 0.0234 | 28.0 | 364 | 0.0133 |
76
- | 0.0219 | 29.0 | 377 | 0.0113 |
77
- | 0.0204 | 30.0 | 390 | 0.0108 |
78
- | 0.0191 | 31.0 | 403 | 0.0100 |
79
- | 0.0181 | 32.0 | 416 | 0.0097 |
80
- | 0.0179 | 33.0 | 429 | 0.0097 |
81
- | 0.0169 | 34.0 | 442 | 0.0092 |
82
- | 0.0166 | 35.0 | 455 | 0.0085 |
83
- | 0.0161 | 36.0 | 468 | 0.0086 |
84
- | 0.0156 | 37.0 | 481 | 0.0082 |
85
- | 0.0155 | 38.0 | 494 | 0.0081 |
86
- | 0.0149 | 39.0 | 507 | 0.0081 |
87
- | 0.0149 | 40.0 | 520 | 0.0081 |
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: 0.0079
18
 
19
  ## Model description
20
 
 
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
+ - mixed_precision_training: Native AMP
44
 
45
  ### Training results
46
 
47
  | Training Loss | Epoch | Step | Validation Loss |
48
  |:-------------:|:-----:|:----:|:---------------:|
49
+ | 2.3081 | 1.0 | 13 | 1.5233 |
50
+ | 1.1667 | 2.0 | 26 | 0.6557 |
51
+ | 0.5408 | 3.0 | 39 | 0.4523 |
52
+ | 0.4243 | 4.0 | 52 | 0.3792 |
53
+ | 0.3582 | 5.0 | 65 | 0.3195 |
54
+ | 0.3071 | 6.0 | 78 | 0.2719 |
55
+ | 0.2676 | 7.0 | 91 | 0.2468 |
56
+ | 0.2490 | 8.0 | 104 | 0.2108 |
57
+ | 0.2189 | 9.0 | 117 | 0.1874 |
58
+ | 0.1949 | 10.0 | 130 | 0.1616 |
59
+ | 0.1875 | 11.0 | 143 | 0.1690 |
60
+ | 0.1665 | 12.0 | 156 | 0.1327 |
61
+ | 0.1458 | 13.0 | 169 | 0.1161 |
62
+ | 0.1285 | 14.0 | 182 | 0.1057 |
63
+ | 0.1146 | 15.0 | 195 | 0.0887 |
64
+ | 0.1019 | 16.0 | 208 | 0.0703 |
65
+ | 0.0837 | 17.0 | 221 | 0.0496 |
66
+ | 0.0697 | 18.0 | 234 | 0.0432 |
67
+ | 0.0585 | 19.0 | 247 | 0.0365 |
68
+ | 0.0496 | 20.0 | 260 | 0.0258 |
69
+ | 0.0427 | 21.0 | 273 | 0.0254 |
70
+ | 0.0391 | 22.0 | 286 | 0.0223 |
71
+ | 0.0344 | 23.0 | 299 | 0.0216 |
72
+ | 0.0318 | 24.0 | 312 | 0.0167 |
73
+ | 0.0284 | 25.0 | 325 | 0.0155 |
74
+ | 0.0263 | 26.0 | 338 | 0.0139 |
75
+ | 0.0246 | 27.0 | 351 | 0.0126 |
76
+ | 0.0230 | 28.0 | 364 | 0.0128 |
77
+ | 0.0214 | 29.0 | 377 | 0.0115 |
78
+ | 0.0206 | 30.0 | 390 | 0.0103 |
79
+ | 0.0194 | 31.0 | 403 | 0.0096 |
80
+ | 0.0184 | 32.0 | 416 | 0.0098 |
81
+ | 0.0180 | 33.0 | 429 | 0.0104 |
82
+ | 0.0171 | 34.0 | 442 | 0.0089 |
83
+ | 0.0163 | 35.0 | 455 | 0.0084 |
84
+ | 0.0158 | 36.0 | 468 | 0.0082 |
85
+ | 0.0155 | 37.0 | 481 | 0.0081 |
86
+ | 0.0150 | 38.0 | 494 | 0.0081 |
87
+ | 0.0147 | 39.0 | 507 | 0.0080 |
88
+ | 0.0148 | 40.0 | 520 | 0.0079 |
89
 
90
 
91
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f06118d1dd00376438b2dde149e4bf3352a4662309577c8b38a092eb11d30355
3
  size 31232228
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:58632e0b5c962252ccded59a5ce92b5629644a041ec1d5da1ac3797791d0764a
3
  size 31232228