Hugging Face's logo

imdatta0
/
mistral_7b_v_MetaMathQA_40K

PEFT
Safetensors
unsloth
Generated from Trainer
Model card Files Community
imdatta0 commited on
Commit
dfbfb51
•
1 Parent(s): 73a7bf0

End of training

Browse files
Files changed (2) hide show
  1. README.md +48 -48
  2. adapter_model.safetensors +1 -1
README.md CHANGED
@@ -17,7 +17,7 @@ should probably proofread and complete it, then remove this comment. -->
17
 
18
  This model is a fine-tuned version of [mistralai/Mistral-7B-v0.3](https://huggingface.co/mistralai/Mistral-7B-v0.3) on an unknown dataset.
19
  It achieves the following results on the evaluation set:
20
- - Loss: 0.4839
21
 
22
  ## Model description
23
 
@@ -51,53 +51,53 @@ The following hyperparameters were used during training:
51
 
52
  | Training Loss | Epoch | Step | Validation Loss |
53
  |:-------------:|:------:|:----:|:---------------:|
54
- | 0.859 | 0.0211 | 13 | 0.6571 |
55
- | 0.601 | 0.0421 | 26 | 0.6027 |
56
- | 0.5632 | 0.0632 | 39 | 0.5801 |
57
- | 0.5416 | 0.0842 | 52 | 0.5559 |
58
- | 0.5223 | 0.1053 | 65 | 0.5473 |
59
- | 0.5213 | 0.1264 | 78 | 0.5415 |
60
- | 0.5091 | 0.1474 | 91 | 0.5364 |
61
- | 0.5199 | 0.1685 | 104 | 0.5299 |
62
- | 0.5013 | 0.1896 | 117 | 0.5298 |
63
- | 0.5083 | 0.2106 | 130 | 0.5262 |
64
- | 0.4985 | 0.2317 | 143 | 0.5237 |
65
- | 0.4818 | 0.2527 | 156 | 0.5176 |
66
- | 0.4902 | 0.2738 | 169 | 0.5173 |
67
- | 0.4952 | 0.2949 | 182 | 0.5159 |
68
- | 0.4916 | 0.3159 | 195 | 0.5124 |
69
- | 0.4931 | 0.3370 | 208 | 0.5110 |
70
- | 0.4787 | 0.3580 | 221 | 0.5070 |
71
- | 0.4777 | 0.3791 | 234 | 0.5072 |
72
- | 0.4756 | 0.4002 | 247 | 0.5047 |
73
- | 0.4862 | 0.4212 | 260 | 0.5036 |
74
- | 0.4904 | 0.4423 | 273 | 0.5034 |
75
- | 0.4811 | 0.4633 | 286 | 0.5013 |
76
- | 0.4765 | 0.4844 | 299 | 0.4990 |
77
- | 0.4819 | 0.5055 | 312 | 0.4992 |
78
- | 0.4818 | 0.5265 | 325 | 0.4967 |
79
- | 0.4827 | 0.5476 | 338 | 0.4959 |
80
- | 0.4769 | 0.5687 | 351 | 0.4941 |
81
- | 0.4688 | 0.5897 | 364 | 0.4929 |
82
- | 0.4717 | 0.6108 | 377 | 0.4939 |
83
- | 0.4678 | 0.6318 | 390 | 0.4906 |
84
- | 0.4719 | 0.6529 | 403 | 0.4892 |
85
- | 0.4685 | 0.6740 | 416 | 0.4891 |
86
- | 0.458 | 0.6950 | 429 | 0.4892 |
87
- | 0.4779 | 0.7161 | 442 | 0.4880 |
88
- | 0.4634 | 0.7371 | 455 | 0.4867 |
89
- | 0.4702 | 0.7582 | 468 | 0.4856 |
90
- | 0.4722 | 0.7793 | 481 | 0.4853 |
91
- | 0.4731 | 0.8003 | 494 | 0.4852 |
92
- | 0.4646 | 0.8214 | 507 | 0.4857 |
93
- | 0.4611 | 0.8424 | 520 | 0.4852 |
94
- | 0.46 | 0.8635 | 533 | 0.4847 |
95
- | 0.4566 | 0.8846 | 546 | 0.4846 |
96
- | 0.4796 | 0.9056 | 559 | 0.4843 |
97
- | 0.4726 | 0.9267 | 572 | 0.4842 |
98
- | 0.4617 | 0.9478 | 585 | 0.4840 |
99
- | 0.459 | 0.9688 | 598 | 0.4840 |
100
- | 0.4613 | 0.9899 | 611 | 0.4839 |
101
 
102
 
103
  ### Framework versions
 
17
 
18
  This model is a fine-tuned version of [mistralai/Mistral-7B-v0.3](https://huggingface.co/mistralai/Mistral-7B-v0.3) on an unknown dataset.
19
  It achieves the following results on the evaluation set:
20
+ - Loss: 4.0534
21
 
22
  ## Model description
23
 
 
51
 
52
  | Training Loss | Epoch | Step | Validation Loss |
53
  |:-------------:|:------:|:----:|:---------------:|
54
+ | 0.8546 | 0.0211 | 13 | 9.0448 |
55
+ | 8.7033 | 0.0421 | 26 | 6.8246 |
56
+ | 7.1208 | 0.0632 | 39 | 6.6756 |
57
+ | 6.5364 | 0.0842 | 52 | 6.5704 |
58
+ | 6.4506 | 0.1053 | 65 | 6.4165 |
59
+ | 6.3651 | 0.1264 | 78 | 6.4591 |
60
+ | 6.4236 | 0.1474 | 91 | 6.3382 |
61
+ | 6.3751 | 0.1685 | 104 | 6.3491 |
62
+ | 6.29 | 0.1896 | 117 | 6.3231 |
63
+ | 6.1703 | 0.2106 | 130 | 6.1876 |
64
+ | 5.9486 | 0.2317 | 143 | 5.8240 |
65
+ | 5.7357 | 0.2527 | 156 | 5.6677 |
66
+ | 5.5395 | 0.2738 | 169 | 5.7816 |
67
+ | 5.4509 | 0.2949 | 182 | 5.4254 |
68
+ | 5.4296 | 0.3159 | 195 | 5.2703 |
69
+ | 5.3284 | 0.3370 | 208 | 5.1638 |
70
+ | 5.2125 | 0.3580 | 221 | 5.1691 |
71
+ | 5.0807 | 0.3791 | 234 | 5.0448 |
72
+ | 4.9527 | 0.4002 | 247 | 4.9290 |
73
+ | 4.929 | 0.4212 | 260 | 4.9626 |
74
+ | 4.9299 | 0.4423 | 273 | 4.8930 |
75
+ | 4.8363 | 0.4633 | 286 | 4.6863 |
76
+ | 4.6998 | 0.4844 | 299 | 4.6888 |
77
+ | 4.6004 | 0.5055 | 312 | 4.6411 |
78
+ | 4.6229 | 0.5265 | 325 | 4.5178 |
79
+ | 4.4437 | 0.5476 | 338 | 4.4411 |
80
+ | 4.4564 | 0.5687 | 351 | 4.4293 |
81
+ | 4.4144 | 0.5897 | 364 | 4.3946 |
82
+ | 4.3888 | 0.6108 | 377 | 4.3527 |
83
+ | 4.3296 | 0.6318 | 390 | 4.2652 |
84
+ | 4.2489 | 0.6529 | 403 | 4.2610 |
85
+ | 4.2046 | 0.6740 | 416 | 4.2029 |
86
+ | 4.2525 | 0.6950 | 429 | 4.1885 |
87
+ | 4.2439 | 0.7161 | 442 | 4.1833 |
88
+ | 4.141 | 0.7371 | 455 | 4.1576 |
89
+ | 4.1417 | 0.7582 | 468 | 4.1388 |
90
+ | 4.1334 | 0.7793 | 481 | 4.1094 |
91
+ | 4.1319 | 0.8003 | 494 | 4.0910 |
92
+ | 4.1122 | 0.8214 | 507 | 4.1114 |
93
+ | 4.0976 | 0.8424 | 520 | 4.0905 |
94
+ | 4.0836 | 0.8635 | 533 | 4.0963 |
95
+ | 4.061 | 0.8846 | 546 | 4.0767 |
96
+ | 4.1107 | 0.9056 | 559 | 4.0573 |
97
+ | 4.0673 | 0.9267 | 572 | 4.0522 |
98
+ | 4.0283 | 0.9478 | 585 | 4.0558 |
99
+ | 4.045 | 0.9688 | 598 | 4.0532 |
100
+ | 4.0369 | 0.9899 | 611 | 4.0534 |
101
 
102
 
103
  ### Framework versions
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e578b58db4afc20efa16572c581a7416605e1a7cad9ce7ad14f2dcc6a352a50e
3
  size 83945296
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d0410f701a8658b274e26ca3ac0548310f4776a256877195b56d8198e2fbe025
3
  size 83945296