AleksanderWojsz commited on
Commit
2ba37ad
·
verified ·
1 Parent(s): 919fc81

End of training

Browse files
Files changed (1) hide show
  1. README.md +42 -42
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: 0.1880
18
 
19
  ## Model description
20
 
@@ -45,51 +45,51 @@ The following hyperparameters were used during training:
45
 
46
  | Training Loss | Epoch | Step | Validation Loss |
47
  |:-------------:|:-----:|:----:|:---------------:|
48
- | 3.0045 | 1.0 | 6 | 2.3270 |
49
- | 2.0454 | 2.0 | 12 | 1.7402 |
50
- | 1.6084 | 3.0 | 18 | 1.4377 |
51
- | 1.3418 | 4.0 | 24 | 1.1845 |
52
- | 1.0953 | 5.0 | 30 | 1.0000 |
53
- | 0.9191 | 6.0 | 36 | 0.8470 |
54
- | 0.8072 | 7.0 | 42 | 0.8226 |
55
- | 0.7778 | 8.0 | 48 | 0.7191 |
56
- | 0.6906 | 9.0 | 54 | 0.6525 |
57
- | 0.6319 | 10.0 | 60 | 0.6184 |
58
- | 0.5979 | 11.0 | 66 | 0.5549 |
59
- | 0.5722 | 12.0 | 72 | 0.5312 |
60
- | 0.5367 | 13.0 | 78 | 0.4926 |
61
- | 0.4985 | 14.0 | 84 | 0.4706 |
62
- | 0.4663 | 15.0 | 90 | 0.4339 |
63
- | 0.4562 | 16.0 | 96 | 0.4163 |
64
- | 0.4373 | 17.0 | 102 | 0.3995 |
65
- | 0.4157 | 18.0 | 108 | 0.4076 |
66
- | 0.4221 | 19.0 | 114 | 0.3909 |
67
- | 0.4132 | 20.0 | 120 | 0.3652 |
68
- | 0.3817 | 21.0 | 126 | 0.3477 |
69
- | 0.3536 | 22.0 | 132 | 0.3285 |
70
- | 0.3523 | 23.0 | 138 | 0.3114 |
71
- | 0.3387 | 24.0 | 144 | 0.2991 |
72
- | 0.3284 | 25.0 | 150 | 0.2980 |
73
- | 0.3220 | 26.0 | 156 | 0.2763 |
74
- | 0.3118 | 27.0 | 162 | 0.3048 |
75
- | 0.3173 | 28.0 | 168 | 0.2546 |
76
- | 0.2964 | 29.0 | 174 | 0.2575 |
77
- | 0.2896 | 30.0 | 180 | 0.2449 |
78
- | 0.2744 | 31.0 | 186 | 0.2392 |
79
- | 0.2714 | 32.0 | 192 | 0.2343 |
80
- | 0.2674 | 33.0 | 198 | 0.2142 |
81
- | 0.2535 | 34.0 | 204 | 0.2109 |
82
- | 0.2483 | 35.0 | 210 | 0.2090 |
83
- | 0.2494 | 36.0 | 216 | 0.1992 |
84
- | 0.2423 | 37.0 | 222 | 0.1947 |
85
- | 0.2292 | 38.0 | 228 | 0.1908 |
86
- | 0.2311 | 39.0 | 234 | 0.1897 |
87
- | 0.2300 | 40.0 | 240 | 0.1880 |
88
 
89
 
90
  ### Framework versions
91
 
92
  - Transformers 5.0.0
93
- - Pytorch 2.10.0+cu128
94
  - Datasets 4.0.0
95
  - 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: 0.0732
18
 
19
  ## Model description
20
 
 
45
 
46
  | Training Loss | Epoch | Step | Validation Loss |
47
  |:-------------:|:-----:|:----:|:---------------:|
48
+ | 3.1329 | 1.0 | 5 | 2.4115 |
49
+ | 2.1734 | 2.0 | 10 | 1.8467 |
50
+ | 1.7271 | 3.0 | 15 | 1.5298 |
51
+ | 1.4359 | 4.0 | 20 | 1.2764 |
52
+ | 1.1968 | 5.0 | 25 | 1.0395 |
53
+ | 0.9850 | 6.0 | 30 | 0.8995 |
54
+ | 0.8588 | 7.0 | 35 | 0.7843 |
55
+ | 0.7775 | 8.0 | 40 | 0.7370 |
56
+ | 0.7156 | 9.0 | 45 | 0.6533 |
57
+ | 0.6477 | 10.0 | 50 | 0.5932 |
58
+ | 0.5889 | 11.0 | 55 | 0.5227 |
59
+ | 0.5340 | 12.0 | 60 | 0.4886 |
60
+ | 0.4974 | 13.0 | 65 | 0.4334 |
61
+ | 0.4522 | 14.0 | 70 | 0.3877 |
62
+ | 0.4190 | 15.0 | 75 | 0.3612 |
63
+ | 0.3872 | 16.0 | 80 | 0.3277 |
64
+ | 0.3550 | 17.0 | 85 | 0.2904 |
65
+ | 0.3289 | 18.0 | 90 | 0.2736 |
66
+ | 0.3074 | 19.0 | 95 | 0.2424 |
67
+ | 0.2834 | 20.0 | 100 | 0.2317 |
68
+ | 0.2678 | 21.0 | 105 | 0.2062 |
69
+ | 0.2496 | 22.0 | 110 | 0.2049 |
70
+ | 0.2352 | 23.0 | 115 | 0.1744 |
71
+ | 0.2159 | 24.0 | 120 | 0.1553 |
72
+ | 0.2043 | 25.0 | 125 | 0.1476 |
73
+ | 0.1886 | 26.0 | 130 | 0.1313 |
74
+ | 0.1749 | 27.0 | 135 | 0.1227 |
75
+ | 0.1676 | 28.0 | 140 | 0.1168 |
76
+ | 0.1610 | 29.0 | 145 | 0.1098 |
77
+ | 0.1508 | 30.0 | 150 | 0.1045 |
78
+ | 0.1424 | 31.0 | 155 | 0.0956 |
79
+ | 0.1354 | 32.0 | 160 | 0.0904 |
80
+ | 0.1315 | 33.0 | 165 | 0.0851 |
81
+ | 0.1257 | 34.0 | 170 | 0.0823 |
82
+ | 0.1228 | 35.0 | 175 | 0.0800 |
83
+ | 0.1173 | 36.0 | 180 | 0.0777 |
84
+ | 0.1132 | 37.0 | 185 | 0.0760 |
85
+ | 0.1131 | 38.0 | 190 | 0.0749 |
86
+ | 0.1136 | 39.0 | 195 | 0.0735 |
87
+ | 0.1115 | 40.0 | 200 | 0.0732 |
88
 
89
 
90
  ### Framework versions
91
 
92
  - Transformers 5.0.0
93
+ - Pytorch 2.10.0+cpu
94
  - Datasets 4.0.0
95
  - Tokenizers 0.22.2