Hugging Face's logo

imdatta0
/
Mistral-7B-v0.3_metamath_ortho

PEFT
Safetensors
unsloth
Generated from Trainer
Model card Files Community
imdatta0 commited on
Commit
5538c91
·
verified ·
1 Parent(s): 328bf74

End of training

Browse files
Files changed (2) hide show
  1. README.md +50 -50
  2. adapter_model.safetensors +1 -1
README.md CHANGED
@@ -1,5 +1,5 @@
1
  ---
2
- base_model: unsloth/mistral-7b-v0.3-bnb-4bit
3
  library_name: peft
4
  license: apache-2.0
5
  tags:
@@ -15,9 +15,9 @@ should probably proofread and complete it, then remove this comment. -->
15
 
16
  # Mistral-7B-v0.3_metamath_ortho
17
 
18
- This model is a fine-tuned version of [unsloth/mistral-7b-v0.3-bnb-4bit](https://huggingface.co/unsloth/mistral-7b-v0.3-bnb-4bit) on an unknown dataset.
19
  It achieves the following results on the evaluation set:
20
- - Loss: 3.6676
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
- | 0.7827 | 0.0211 | 13 | 1.0186 |
55
- | 7.6813 | 0.0421 | 26 | 7.3723 |
56
- | 7.0799 | 0.0632 | 39 | 6.6456 |
57
- | 6.356 | 0.0842 | 52 | 6.2633 |
58
- | 6.2517 | 0.1053 | 65 | 6.2857 |
59
- | 6.2899 | 0.1264 | 78 | 6.2679 |
60
- | 6.285 | 0.1474 | 91 | 6.2945 |
61
- | 6.3073 | 0.1685 | 104 | 6.3867 |
62
- | 6.2797 | 0.1896 | 117 | 6.2024 |
63
- | 6.083 | 0.2106 | 130 | 5.9188 |
64
- | 5.8629 | 0.2317 | 143 | 5.7044 |
65
- | 5.6092 | 0.2527 | 156 | 5.3934 |
66
- | 5.3102 | 0.2738 | 169 | 5.2099 |
67
- | 5.2155 | 0.2949 | 182 | 5.1111 |
68
- | 5.0531 | 0.3159 | 195 | 4.9263 |
69
- | 4.8718 | 0.3370 | 208 | 4.8186 |
70
- | 4.7175 | 0.3580 | 221 | 4.6831 |
71
- | 4.641 | 0.3791 | 234 | 4.6348 |
72
- | 4.5275 | 0.4002 | 247 | 4.5482 |
73
- | 4.4863 | 0.4212 | 260 | 4.4328 |
74
- | 4.4633 | 0.4423 | 273 | 4.3950 |
75
- | 4.4026 | 0.4633 | 286 | 4.3332 |
76
- | 4.3761 | 0.4844 | 299 | 4.2790 |
77
- | 4.2027 | 0.5055 | 312 | 4.1886 |
78
- | 4.1631 | 0.5265 | 325 | 4.1493 |
79
- | 4.0923 | 0.5476 | 338 | 4.1405 |
80
- | 4.1048 | 0.5687 | 351 | 4.0457 |
81
- | 4.0592 | 0.5897 | 364 | 3.9616 |
82
- | 4.0107 | 0.6108 | 377 | 3.9935 |
83
- | 4.021 | 0.6318 | 390 | 3.8987 |
84
- | 3.8899 | 0.6529 | 403 | 3.9228 |
85
- | 3.8158 | 0.6740 | 416 | 3.8781 |
86
- | 3.9124 | 0.6950 | 429 | 3.8955 |
87
- | 3.8687 | 0.7161 | 442 | 3.8612 |
88
- | 3.824 | 0.7371 | 455 | 3.8042 |
89
- | 3.7742 | 0.7582 | 468 | 3.7946 |
90
- | 3.7309 | 0.7793 | 481 | 3.7436 |
91
- | 3.7528 | 0.8003 | 494 | 3.7428 |
92
- | 3.7297 | 0.8214 | 507 | 3.7325 |
93
- | 3.6943 | 0.8424 | 520 | 3.7126 |
94
- | 3.6788 | 0.8635 | 533 | 3.7202 |
95
- | 3.6632 | 0.8846 | 546 | 3.6981 |
96
- | 3.7316 | 0.9056 | 559 | 3.6925 |
97
- | 3.6737 | 0.9267 | 572 | 3.6602 |
98
- | 3.6142 | 0.9478 | 585 | 3.6731 |
99
- | 3.6347 | 0.9688 | 598 | 3.6691 |
100
- | 3.6248 | 0.9899 | 611 | 3.6676 |
101
 
102
 
103
  ### Framework versions
 
1
  ---
2
+ base_model: unsloth/mistral-7b-v0.3
3
  library_name: peft
4
  license: apache-2.0
5
  tags:
 
15
 
16
  # Mistral-7B-v0.3_metamath_ortho
17
 
18
+ This model is a fine-tuned version of [unsloth/mistral-7b-v0.3](https://huggingface.co/unsloth/mistral-7b-v0.3) on an unknown dataset.
19
  It achieves the following results on the evaluation set:
20
+ - Loss: 3.7040
21
 
22
  ## Model description
23
 
 
51
 
52
  | Training Loss | Epoch | Step | Validation Loss |
53
  |:-------------:|:------:|:----:|:---------------:|
54
+ | 0.7777 | 0.0211 | 13 | 0.8341 |
55
+ | 7.0293 | 0.0421 | 26 | 6.8513 |
56
+ | 6.701 | 0.0632 | 39 | 6.3677 |
57
+ | 6.2243 | 0.0842 | 52 | 6.0330 |
58
+ | 5.8724 | 0.1053 | 65 | 5.7326 |
59
+ | 5.6516 | 0.1264 | 78 | 5.5358 |
60
+ | 5.4706 | 0.1474 | 91 | 5.4924 |
61
+ | 5.4721 | 0.1685 | 104 | 5.4835 |
62
+ | 5.3039 | 0.1896 | 117 | 5.2730 |
63
+ | 5.2205 | 0.2106 | 130 | 5.3434 |
64
+ | 5.2713 | 0.2317 | 143 | 5.1822 |
65
+ | 5.3149 | 0.2527 | 156 | 5.1724 |
66
+ | 5.0644 | 0.2738 | 169 | 4.9613 |
67
+ | 4.9846 | 0.2949 | 182 | 4.9757 |
68
+ | 5.0517 | 0.3159 | 195 | 4.9266 |
69
+ | 4.865 | 0.3370 | 208 | 4.8010 |
70
+ | 4.7282 | 0.3580 | 221 | 4.6863 |
71
+ | 4.7043 | 0.3791 | 234 | 4.8179 |
72
+ | 4.625 | 0.4002 | 247 | 4.7745 |
73
+ | 4.6588 | 0.4212 | 260 | 4.5501 |
74
+ | 4.5945 | 0.4423 | 273 | 4.6777 |
75
+ | 4.5486 | 0.4633 | 286 | 4.4474 |
76
+ | 4.5306 | 0.4844 | 299 | 4.2966 |
77
+ | 4.2913 | 0.5055 | 312 | 4.3590 |
78
+ | 4.2849 | 0.5265 | 325 | 4.2581 |
79
+ | 4.2128 | 0.5476 | 338 | 4.2430 |
80
+ | 4.2097 | 0.5687 | 351 | 4.1542 |
81
+ | 4.1464 | 0.5897 | 364 | 4.0493 |
82
+ | 4.0945 | 0.6108 | 377 | 4.1035 |
83
+ | 4.1179 | 0.6318 | 390 | 4.0137 |
84
+ | 3.985 | 0.6529 | 403 | 4.0483 |
85
+ | 3.8947 | 0.6740 | 416 | 3.9081 |
86
+ | 3.9839 | 0.6950 | 429 | 3.9723 |
87
+ | 3.9361 | 0.7161 | 442 | 3.9275 |
88
+ | 3.8458 | 0.7371 | 455 | 3.8235 |
89
+ | 3.8545 | 0.7582 | 468 | 3.8504 |
90
+ | 3.7774 | 0.7793 | 481 | 3.8078 |
91
+ | 3.8065 | 0.8003 | 494 | 3.8017 |
92
+ | 3.7724 | 0.8214 | 507 | 3.7487 |
93
+ | 3.7569 | 0.8424 | 520 | 3.7663 |
94
+ | 3.742 | 0.8635 | 533 | 3.7698 |
95
+ | 3.7114 | 0.8846 | 546 | 3.7603 |
96
+ | 3.7752 | 0.9056 | 559 | 3.7105 |
97
+ | 3.6945 | 0.9267 | 572 | 3.7041 |
98
+ | 3.6581 | 0.9478 | 585 | 3.7017 |
99
+ | 3.6615 | 0.9688 | 598 | 3.7050 |
100
+ | 3.6688 | 0.9899 | 611 | 3.7040 |
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:fb84e5b59371e6514b7b828c1e2089be87562525d79330e84d20169a72916da5
3
  size 83945296
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0456798fef6f1d81ca7c3bd2b758299424ed84c8cb5457eebc76d0d89c379703
3
  size 83945296