Hugging Face's logo

dsuwala
/
calculator_model_test

Transformers
Safetensors
encoder-decoder
text2text-generation
Generated from Trainer
Model card Files
xet
 Community
dsuwala commited on
Commit
cd7663e
·
verified ·
1 Parent(s): e6374c8

End of training

Browse files
Files changed (1) hide show
  1. README.md +42 -41
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: 0.5990
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
- | 3.5011 | 1.0 | 5 | 2.9098 |
49
- | 2.5679 | 2.0 | 10 | 2.0979 |
50
- | 1.9533 | 3.0 | 15 | 1.7263 |
51
- | 1.6643 | 4.0 | 20 | 1.5940 |
52
- | 1.5773 | 5.0 | 25 | 1.5335 |
53
- | 1.5508 | 6.0 | 30 | 1.5127 |
54
- | 1.5290 | 7.0 | 35 | 1.4828 |
55
- | 1.4819 | 8.0 | 40 | 1.4347 |
56
- | 1.4571 | 9.0 | 45 | 1.5285 |
57
- | 1.4630 | 10.0 | 50 | 1.4265 |
58
- | 1.3942 | 11.0 | 55 | 1.3409 |
59
- | 1.3506 | 12.0 | 60 | 1.3209 |
60
- | 1.3223 | 13.0 | 65 | 1.2914 |
61
- | 1.2856 | 14.0 | 70 | 1.2379 |
62
- | 1.2325 | 15.0 | 75 | 1.1640 |
63
- | 1.2030 | 16.0 | 80 | 1.1480 |
64
- | 1.1457 | 17.0 | 85 | 1.0848 |
65
- | 1.1101 | 18.0 | 90 | 1.0746 |
66
- | 1.0606 | 19.0 | 95 | 0.9998 |
67
- | 1.0178 | 20.0 | 100 | 0.9548 |
68
- | 0.9794 | 21.0 | 105 | 0.9146 |
69
- | 0.9373 | 22.0 | 110 | 0.8770 |
70
- | 0.9062 | 23.0 | 115 | 0.8525 |
71
- | 0.8708 | 24.0 | 120 | 0.8255 |
72
- | 0.8462 | 25.0 | 125 | 0.7827 |
73
- | 0.8156 | 26.0 | 130 | 0.7522 |
74
- | 0.7904 | 27.0 | 135 | 0.7324 |
75
- | 0.7911 | 28.0 | 140 | 0.7292 |
76
- | 0.7757 | 29.0 | 145 | 0.7036 |
77
- | 0.7602 | 30.0 | 150 | 0.7177 |
78
- | 0.7413 | 31.0 | 155 | 0.6796 |
79
- | 0.7222 | 32.0 | 160 | 0.6597 |
80
- | 0.7103 | 33.0 | 165 | 0.6559 |
81
- | 0.6977 | 34.0 | 170 | 0.6391 |
82
- | 0.6959 | 35.0 | 175 | 0.6305 |
83
- | 0.6853 | 36.0 | 180 | 0.6193 |
84
- | 0.6737 | 37.0 | 185 | 0.6142 |
85
- | 0.6696 | 38.0 | 190 | 0.6065 |
86
- | 0.6666 | 39.0 | 195 | 0.6015 |
87
- | 0.6598 | 40.0 | 200 | 0.5990 |
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: 0.0681
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
+ | 3.0932 | 1.0 | 6 | 2.3284 |
50
+ | 2.0708 | 2.0 | 12 | 1.7597 |
51
+ | 1.6188 | 3.0 | 18 | 1.4260 |
52
+ | 1.2984 | 4.0 | 24 | 1.1225 |
53
+ | 1.0571 | 5.0 | 30 | 0.9371 |
54
+ | 0.9006 | 6.0 | 36 | 0.8191 |
55
+ | 0.8187 | 7.0 | 42 | 0.7260 |
56
+ | 0.7281 | 8.0 | 48 | 0.6762 |
57
+ | 0.6804 | 9.0 | 54 | 0.6348 |
58
+ | 0.6251 | 10.0 | 60 | 0.5609 |
59
+ | 0.5701 | 11.0 | 66 | 0.5090 |
60
+ | 0.5325 | 12.0 | 72 | 0.4674 |
61
+ | 0.4973 | 13.0 | 78 | 0.4407 |
62
+ | 0.4619 | 14.0 | 84 | 0.4090 |
63
+ | 0.4408 | 15.0 | 90 | 0.3996 |
64
+ | 0.4311 | 16.0 | 96 | 0.4260 |
65
+ | 0.4237 | 17.0 | 102 | 0.3490 |
66
+ | 0.3734 | 18.0 | 108 | 0.3225 |
67
+ | 0.3387 | 19.0 | 114 | 0.2895 |
68
+ | 0.3111 | 20.0 | 120 | 0.2506 |
69
+ | 0.2790 | 21.0 | 126 | 0.2317 |
70
+ | 0.2652 | 22.0 | 132 | 0.2102 |
71
+ | 0.2521 | 23.0 | 138 | 0.1889 |
72
+ | 0.2293 | 24.0 | 144 | 0.1697 |
73
+ | 0.2031 | 25.0 | 150 | 0.1413 |
74
+ | 0.1844 | 26.0 | 156 | 0.1269 |
75
+ | 0.1856 | 27.0 | 162 | 0.1358 |
76
+ | 0.1787 | 28.0 | 168 | 0.1104 |
77
+ | 0.1549 | 29.0 | 174 | 0.1175 |
78
+ | 0.1644 | 30.0 | 180 | 0.1034 |
79
+ | 0.1406 | 31.0 | 186 | 0.0931 |
80
+ | 0.1379 | 32.0 | 192 | 0.0888 |
81
+ | 0.1299 | 33.0 | 198 | 0.0916 |
82
+ | 0.1265 | 34.0 | 204 | 0.0809 |
83
+ | 0.1216 | 35.0 | 210 | 0.0747 |
84
+ | 0.1160 | 36.0 | 216 | 0.0725 |
85
+ | 0.1106 | 37.0 | 222 | 0.0707 |
86
+ | 0.1092 | 38.0 | 228 | 0.0686 |
87
+ | 0.1076 | 39.0 | 234 | 0.0689 |
88
+ | 0.1113 | 40.0 | 240 | 0.0681 |
89
 
90
 
91
  ### Framework versions