Hugging Face's logo

imdatta0
/
Mistral-7B-v0.3_metamath_reverse

PEFT
Safetensors
unsloth
Generated from Trainer
Model card Files Community
imdatta0 commited on
Commit
321234c
·
verified ·
1 Parent(s): 4d811b4

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_reverse
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: 4.0369
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
- | 0.7562 | 0.0211 | 13 | 8.8561 |
55
- | 8.5861 | 0.0421 | 26 | 6.7147 |
56
- | 6.683 | 0.0632 | 39 | 6.4347 |
57
- | 6.3623 | 0.0842 | 52 | 6.2959 |
58
- | 6.1966 | 0.1053 | 65 | 6.1023 |
59
- | 5.9253 | 0.1264 | 78 | 5.8562 |
60
- | 5.6996 | 0.1474 | 91 | 5.7402 |
61
- | 5.654 | 0.1685 | 104 | 5.5460 |
62
- | 5.4346 | 0.1896 | 117 | 5.3902 |
63
- | 5.2399 | 0.2106 | 130 | 5.1306 |
64
- | 5.1411 | 0.2317 | 143 | 5.0223 |
65
- | 5.0468 | 0.2527 | 156 | 4.9554 |
66
- | 4.9675 | 0.2738 | 169 | 4.8488 |
67
- | 4.8723 | 0.2949 | 182 | 4.9092 |
68
- | 4.9509 | 0.3159 | 195 | 4.6985 |
69
- | 4.7385 | 0.3370 | 208 | 4.7031 |
70
- | 4.631 | 0.3580 | 221 | 4.6471 |
71
- | 4.6294 | 0.3791 | 234 | 4.6124 |
72
- | 4.5562 | 0.4002 | 247 | 4.5880 |
73
- | 4.5684 | 0.4212 | 260 | 4.5116 |
74
- | 4.5965 | 0.4423 | 273 | 4.5065 |
75
- | 4.594 | 0.4633 | 286 | 4.4330 |
76
- | 4.5223 | 0.4844 | 299 | 4.4393 |
77
- | 4.4033 | 0.5055 | 312 | 4.4070 |
78
- | 4.3706 | 0.5265 | 325 | 4.3485 |
79
- | 4.3595 | 0.5476 | 338 | 4.3587 |
80
- | 4.3865 | 0.5687 | 351 | 4.2940 |
81
- | 4.342 | 0.5897 | 364 | 4.3082 |
82
- | 4.2976 | 0.6108 | 377 | 4.2683 |
83
- | 4.3627 | 0.6318 | 390 | 4.2331 |
84
- | 4.2364 | 0.6529 | 403 | 4.2331 |
85
- | 4.1543 | 0.6740 | 416 | 4.1827 |
86
- | 4.2475 | 0.6950 | 429 | 4.2243 |
87
- | 4.2247 | 0.7161 | 442 | 4.1690 |
88
- | 4.1115 | 0.7371 | 455 | 4.1257 |
89
- | 4.1388 | 0.7582 | 468 | 4.1157 |
90
- | 4.0912 | 0.7793 | 481 | 4.1659 |
91
- | 4.0903 | 0.8003 | 494 | 4.0926 |
92
- | 4.1036 | 0.8214 | 507 | 4.0859 |
93
- | 4.0692 | 0.8424 | 520 | 4.0732 |
94
- | 4.0634 | 0.8635 | 533 | 4.0823 |
95
- | 4.0463 | 0.8846 | 546 | 4.0597 |
96
- | 4.0948 | 0.9056 | 559 | 4.0447 |
97
- | 4.0496 | 0.9267 | 572 | 4.0293 |
98
- | 3.9855 | 0.9478 | 585 | 4.0449 |
99
- | 4.0289 | 0.9688 | 598 | 4.0360 |
100
- | 4.0147 | 0.9899 | 611 | 4.0369 |
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_reverse
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: 4.4642
21
 
22
  ## Model description
23
 
 
51
 
52
  | Training Loss | Epoch | Step | Validation Loss |
53
  |:-------------:|:------:|:----:|:---------------:|
54
+ | 0.7438 | 0.0211 | 13 | 8.7190 |
55
+ | 10.0767 | 0.0421 | 26 | 7.4982 |
56
+ | 7.2515 | 0.0632 | 39 | 6.8837 |
57
+ | 6.576 | 0.0842 | 52 | 6.7953 |
58
+ | 6.2957 | 0.1053 | 65 | 6.2733 |
59
+ | 6.0661 | 0.1264 | 78 | 6.0673 |
60
+ | 5.9255 | 0.1474 | 91 | 5.8718 |
61
+ | 5.8505 | 0.1685 | 104 | 5.7501 |
62
+ | 5.8001 | 0.1896 | 117 | 5.7454 |
63
+ | 5.6299 | 0.2106 | 130 | 5.6950 |
64
+ | 5.5865 | 0.2317 | 143 | 5.5759 |
65
+ | 5.5062 | 0.2527 | 156 | 5.4837 |
66
+ | 5.4305 | 0.2738 | 169 | 5.4409 |
67
+ | 5.4209 | 0.2949 | 182 | 5.4429 |
68
+ | 5.4976 | 0.3159 | 195 | 5.4370 |
69
+ | 5.3972 | 0.3370 | 208 | 5.4192 |
70
+ | 5.2896 | 0.3580 | 221 | 5.3299 |
71
+ | 5.2499 | 0.3791 | 234 | 5.3241 |
72
+ | 5.2422 | 0.4002 | 247 | 5.2642 |
73
+ | 5.2269 | 0.4212 | 260 | 5.1857 |
74
+ | 5.1564 | 0.4423 | 273 | 5.1017 |
75
+ | 5.1019 | 0.4633 | 286 | 5.0316 |
76
+ | 5.0642 | 0.4844 | 299 | 5.0160 |
77
+ | 4.9382 | 0.5055 | 312 | 4.9836 |
78
+ | 4.8985 | 0.5265 | 325 | 4.9845 |
79
+ | 4.8274 | 0.5476 | 338 | 4.8632 |
80
+ | 4.8791 | 0.5687 | 351 | 4.8729 |
81
+ | 4.8399 | 0.5897 | 364 | 4.8246 |
82
+ | 4.843 | 0.6108 | 377 | 4.7545 |
83
+ | 4.78 | 0.6318 | 390 | 4.7345 |
84
+ | 4.6772 | 0.6529 | 403 | 4.7334 |
85
+ | 4.6519 | 0.6740 | 416 | 4.6307 |
86
+ | 4.6692 | 0.6950 | 429 | 4.6488 |
87
+ | 4.6636 | 0.7161 | 442 | 4.6318 |
88
+ | 4.5804 | 0.7371 | 455 | 4.5739 |
89
+ | 4.566 | 0.7582 | 468 | 4.5556 |
90
+ | 4.5466 | 0.7793 | 481 | 4.5450 |
91
+ | 4.5555 | 0.8003 | 494 | 4.5170 |
92
+ | 4.5352 | 0.8214 | 507 | 4.5036 |
93
+ | 4.5827 | 0.8424 | 520 | 4.4868 |
94
+ | 4.5218 | 0.8635 | 533 | 4.5077 |
95
+ | 4.4692 | 0.8846 | 546 | 4.5098 |
96
+ | 4.522 | 0.9056 | 559 | 4.4963 |
97
+ | 4.5072 | 0.9267 | 572 | 4.4704 |
98
+ | 4.4346 | 0.9478 | 585 | 4.4707 |
99
+ | 4.4893 | 0.9688 | 598 | 4.4659 |
100
+ | 4.4587 | 0.9899 | 611 | 4.4642 |
101
 
102
 
103
  ### Framework versions
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6d1dc1518dd6f0253e2575c967b1ba118eeb29c747aaa2d3b60db7e4e40f0ea9
3
  size 83945296
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f2bd6c505b4bd71ee0eb5756e998411ca22eeccdac6d601fc7655afb7b009bf5
3
  size 83945296