Hugging Face's logo

ka24j13
/
calculator_model_test

Transformers
Safetensors
encoder-decoder
text2text-generation
Generated from Trainer
Model card Files
xet
 Community
ka24j13 commited on
Commit
afa21a9
·
verified ·
1 Parent(s): fae2d49

End of training

Browse files
Files changed (1) hide show
  1. README.md +83 -13
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: 1.1482
18
 
19
  ## Model description
20
 
@@ -39,27 +39,97 @@ 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: 10
43
 
44
  ### Training results
45
 
46
  | Training Loss | Epoch | Step | Validation Loss |
47
  |:-------------:|:-----:|:----:|:---------------:|
48
- | 1.9124 | 1.0 | 5 | 1.7523 |
49
- | 1.5949 | 2.0 | 10 | 1.4888 |
50
- | 1.4837 | 3.0 | 15 | 1.4655 |
51
- | 1.4517 | 4.0 | 20 | 1.4177 |
52
- | 1.4030 | 5.0 | 25 | 1.3661 |
53
- | 1.3564 | 6.0 | 30 | 1.3174 |
54
- | 1.3069 | 7.0 | 35 | 1.2498 |
55
- | 1.2406 | 8.0 | 40 | 1.1865 |
56
- | 1.1917 | 9.0 | 45 | 1.1629 |
57
- | 1.1738 | 10.0 | 50 | 1.1482 |
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
58
 
59
 
60
  ### Framework versions
61
 
62
  - Transformers 5.0.0
63
- - Pytorch 2.10.0+cpu
64
  - Datasets 4.0.0
65
  - Tokenizers 0.22.2
 
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: 0.2400
18
 
19
  ## Model description
20
 
 
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: 80
43
 
44
  ### Training results
45
 
46
  | Training Loss | Epoch | Step | Validation Loss |
47
  |:-------------:|:-----:|:----:|:---------------:|
48
+ | 1.8223 | 1.0 | 6 | 2.6713 |
49
+ | 1.6974 | 2.0 | 12 | 1.2700 |
50
+ | 1.1555 | 3.0 | 18 | 1.0111 |
51
+ | 0.9334 | 4.0 | 24 | 0.9271 |
52
+ | 0.8302 | 5.0 | 30 | 0.8386 |
53
+ | 0.8144 | 6.0 | 36 | 0.6687 |
54
+ | 0.7410 | 7.0 | 42 | 0.8035 |
55
+ | 1.0508 | 8.0 | 48 | 0.7194 |
56
+ | 0.6932 | 9.0 | 54 | 0.6786 |
57
+ | 0.7005 | 10.0 | 60 | 0.6282 |
58
+ | 0.6896 | 11.0 | 66 | 0.7197 |
59
+ | 0.7646 | 12.0 | 72 | 1.0102 |
60
+ | 0.7867 | 13.0 | 78 | 0.7615 |
61
+ | 0.6609 | 14.0 | 84 | 0.5590 |
62
+ | 0.6228 | 15.0 | 90 | 0.5399 |
63
+ | 0.5934 | 16.0 | 96 | 0.6468 |
64
+ | 0.6700 | 17.0 | 102 | 0.9275 |
65
+ | 0.7554 | 18.0 | 108 | 0.5375 |
66
+ | 0.6135 | 19.0 | 114 | 0.4792 |
67
+ | 0.5655 | 20.0 | 120 | 0.5007 |
68
+ | 0.5590 | 21.0 | 126 | 0.4746 |
69
+ | 0.5327 | 22.0 | 132 | 0.5993 |
70
+ | 0.5752 | 23.0 | 138 | 0.4929 |
71
+ | 0.5441 | 24.0 | 144 | 0.5178 |
72
+ | 0.5788 | 25.0 | 150 | 0.6241 |
73
+ | 0.6247 | 26.0 | 156 | 0.4842 |
74
+ | 0.5505 | 27.0 | 162 | 0.4867 |
75
+ | 0.5455 | 28.0 | 168 | 0.4462 |
76
+ | 0.5289 | 29.0 | 174 | 0.5937 |
77
+ | 0.5987 | 30.0 | 180 | 0.6013 |
78
+ | 0.5828 | 31.0 | 186 | 0.5909 |
79
+ | 0.6133 | 32.0 | 192 | 0.4737 |
80
+ | 0.5151 | 33.0 | 198 | 0.5884 |
81
+ | 0.5772 | 34.0 | 204 | 0.4821 |
82
+ | 0.5179 | 35.0 | 210 | 0.4324 |
83
+ | 0.4850 | 36.0 | 216 | 0.4085 |
84
+ | 0.4696 | 37.0 | 222 | 0.4039 |
85
+ | 0.4619 | 38.0 | 228 | 0.5007 |
86
+ | 0.5363 | 39.0 | 234 | 0.5064 |
87
+ | 0.5657 | 40.0 | 240 | 0.4818 |
88
+ | 0.5086 | 41.0 | 246 | 0.4906 |
89
+ | 0.4999 | 42.0 | 252 | 0.5442 |
90
+ | 0.5849 | 43.0 | 258 | 0.3945 |
91
+ | 0.5278 | 44.0 | 264 | 0.4150 |
92
+ | 0.4555 | 45.0 | 270 | 0.3989 |
93
+ | 0.4777 | 46.0 | 276 | 0.4117 |
94
+ | 0.4824 | 47.0 | 282 | 0.3651 |
95
+ | 0.4818 | 48.0 | 288 | 0.3574 |
96
+ | 0.4731 | 49.0 | 294 | 0.3521 |
97
+ | 0.4505 | 50.0 | 300 | 0.3882 |
98
+ | 0.4570 | 51.0 | 306 | 0.3543 |
99
+ | 0.4322 | 52.0 | 312 | 0.3370 |
100
+ | 0.4381 | 53.0 | 318 | 0.3251 |
101
+ | 0.3960 | 54.0 | 324 | 0.3653 |
102
+ | 0.4062 | 55.0 | 330 | 0.3998 |
103
+ | 0.4386 | 56.0 | 336 | 0.3577 |
104
+ | 0.4498 | 57.0 | 342 | 0.3895 |
105
+ | 0.4408 | 58.0 | 348 | 0.3248 |
106
+ | 0.3978 | 59.0 | 354 | 0.3223 |
107
+ | 0.3909 | 60.0 | 360 | 0.3173 |
108
+ | 0.3818 | 61.0 | 366 | 0.2892 |
109
+ | 0.4036 | 62.0 | 372 | 0.2931 |
110
+ | 0.3909 | 63.0 | 378 | 0.2990 |
111
+ | 0.3724 | 64.0 | 384 | 0.2945 |
112
+ | 0.3845 | 65.0 | 390 | 0.3036 |
113
+ | 0.3685 | 66.0 | 396 | 0.3095 |
114
+ | 0.3648 | 67.0 | 402 | 0.3112 |
115
+ | 0.3925 | 68.0 | 408 | 0.2939 |
116
+ | 0.3693 | 69.0 | 414 | 0.2720 |
117
+ | 0.3661 | 70.0 | 420 | 0.2579 |
118
+ | 0.3563 | 71.0 | 426 | 0.2672 |
119
+ | 0.3550 | 72.0 | 432 | 0.2657 |
120
+ | 0.3509 | 73.0 | 438 | 0.2525 |
121
+ | 0.3293 | 74.0 | 444 | 0.2487 |
122
+ | 0.3554 | 75.0 | 450 | 0.2458 |
123
+ | 0.3365 | 76.0 | 456 | 0.2447 |
124
+ | 0.3331 | 77.0 | 462 | 0.2475 |
125
+ | 0.3538 | 78.0 | 468 | 0.2416 |
126
+ | 0.3264 | 79.0 | 474 | 0.2418 |
127
+ | 0.3456 | 80.0 | 480 | 0.2400 |
128
 
129
 
130
  ### Framework versions
131
 
132
  - Transformers 5.0.0
133
+ - Pytorch 2.10.0+cu128
134
  - Datasets 4.0.0
135
  - Tokenizers 0.22.2