Hugging Face's logo

imdatta0
/
mistral_7b_v_MetaMathQA_40K_reverse

PEFT
Safetensors
unsloth
Generated from Trainer
Model card Files Community
imdatta0 commited on
Commit
ad26cac
•
1 Parent(s): 170672a

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: 0.4421
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
- | 0.7252 | 0.0211 | 13 | 0.6225 |
55
- | 0.5814 | 0.0421 | 26 | 0.5900 |
56
- | 0.5599 | 0.0632 | 39 | 0.5751 |
57
- | 0.548 | 0.0842 | 52 | 0.5708 |
58
- | 0.5371 | 0.1053 | 65 | 0.5625 |
59
- | 0.5347 | 0.1264 | 78 | 0.5600 |
60
- | 0.5232 | 0.1474 | 91 | 0.5529 |
61
- | 0.5382 | 0.1685 | 104 | 0.5478 |
62
- | 0.5178 | 0.1896 | 117 | 0.5482 |
63
- | 0.5272 | 0.2106 | 130 | 0.5423 |
64
- | 0.5135 | 0.2317 | 143 | 0.5397 |
65
- | 0.4943 | 0.2527 | 156 | 0.5321 |
66
- | 0.5012 | 0.2738 | 169 | 0.5323 |
67
- | 0.5077 | 0.2949 | 182 | 0.5300 |
68
- | 0.5031 | 0.3159 | 195 | 0.5233 |
69
- | 0.506 | 0.3370 | 208 | 0.5238 |
70
- | 0.4851 | 0.3580 | 221 | 0.5180 |
71
- | 0.4915 | 0.3791 | 234 | 0.5146 |
72
- | 0.4826 | 0.4002 | 247 | 0.5150 |
73
- | 0.4964 | 0.4212 | 260 | 0.5096 |
74
- | 0.4989 | 0.4423 | 273 | 0.5050 |
75
- | 0.4846 | 0.4633 | 286 | 0.5021 |
76
- | 0.4776 | 0.4844 | 299 | 0.5006 |
77
- | 0.4725 | 0.5055 | 312 | 0.4927 |
78
- | 0.4752 | 0.5265 | 325 | 0.4898 |
79
- | 0.4719 | 0.5476 | 338 | 0.4862 |
80
- | 0.4689 | 0.5687 | 351 | 0.4817 |
81
- | 0.4573 | 0.5897 | 364 | 0.4772 |
82
- | 0.4536 | 0.6108 | 377 | 0.4754 |
83
- | 0.4536 | 0.6318 | 390 | 0.4700 |
84
- | 0.4519 | 0.6529 | 403 | 0.4664 |
85
- | 0.4448 | 0.6740 | 416 | 0.4633 |
86
- | 0.4327 | 0.6950 | 429 | 0.4618 |
87
- | 0.4528 | 0.7161 | 442 | 0.4586 |
88
- | 0.4379 | 0.7371 | 455 | 0.4557 |
89
- | 0.4504 | 0.7582 | 468 | 0.4537 |
90
- | 0.4436 | 0.7793 | 481 | 0.4525 |
91
- | 0.4451 | 0.8003 | 494 | 0.4497 |
92
- | 0.435 | 0.8214 | 507 | 0.4482 |
93
- | 0.4247 | 0.8424 | 520 | 0.4466 |
94
- | 0.4295 | 0.8635 | 533 | 0.4455 |
95
- | 0.4204 | 0.8846 | 546 | 0.4444 |
96
- | 0.4381 | 0.9056 | 559 | 0.4433 |
97
- | 0.4355 | 0.9267 | 572 | 0.4430 |
98
- | 0.4234 | 0.9478 | 585 | 0.4424 |
99
- | 0.4261 | 0.9688 | 598 | 0.4421 |
100
- | 0.4266 | 0.9899 | 611 | 0.4421 |
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: 0.4730
21
 
22
  ## Model description
23
 
 
51
 
52
  | Training Loss | Epoch | Step | Validation Loss |
53
  |:-------------:|:------:|:----:|:---------------:|
54
+ | 0.8354 | 0.0211 | 13 | 0.8810 |
55
+ | 1.4577 | 0.0421 | 26 | 1.4281 |
56
+ | 1.0366 | 0.0632 | 39 | 0.9662 |
57
+ | 0.9024 | 0.0842 | 52 | 0.7634 |
58
+ | 0.694 | 0.1053 | 65 | 0.7062 |
59
+ | 0.665 | 0.1264 | 78 | 0.6924 |
60
+ | 0.6381 | 0.1474 | 91 | 0.6665 |
61
+ | 0.6481 | 0.1685 | 104 | 0.6725 |
62
+ | 0.6394 | 0.1896 | 117 | 0.6697 |
63
+ | 0.6486 | 0.2106 | 130 | 0.6728 |
64
+ | 0.6381 | 0.2317 | 143 | 0.6631 |
65
+ | 0.619 | 0.2527 | 156 | 0.6470 |
66
+ | 0.6245 | 0.2738 | 169 | 0.6530 |
67
+ | 0.6233 | 0.2949 | 182 | 0.6445 |
68
+ | 0.6225 | 0.3159 | 195 | 0.6372 |
69
+ | 0.6105 | 0.3370 | 208 | 0.6283 |
70
+ | 0.5865 | 0.3580 | 221 | 0.6180 |
71
+ | 0.5913 | 0.3791 | 234 | 0.6104 |
72
+ | 0.5769 | 0.4002 | 247 | 0.6011 |
73
+ | 0.586 | 0.4212 | 260 | 0.6021 |
74
+ | 0.5945 | 0.4423 | 273 | 0.5921 |
75
+ | 0.57 | 0.4633 | 286 | 0.5869 |
76
+ | 0.5636 | 0.4844 | 299 | 0.5772 |
77
+ | 0.5563 | 0.5055 | 312 | 0.5713 |
78
+ | 0.5516 | 0.5265 | 325 | 0.5655 |
79
+ | 0.5505 | 0.5476 | 338 | 0.5615 |
80
+ | 0.5421 | 0.5687 | 351 | 0.5520 |
81
+ | 0.5225 | 0.5897 | 364 | 0.5431 |
82
+ | 0.5207 | 0.6108 | 377 | 0.5374 |
83
+ | 0.5163 | 0.6318 | 390 | 0.5351 |
84
+ | 0.5169 | 0.6529 | 403 | 0.5262 |
85
+ | 0.5023 | 0.6740 | 416 | 0.5203 |
86
+ | 0.483 | 0.6950 | 429 | 0.5153 |
87
+ | 0.4999 | 0.7161 | 442 | 0.5074 |
88
+ | 0.487 | 0.7371 | 455 | 0.5027 |
89
+ | 0.4971 | 0.7582 | 468 | 0.4985 |
90
+ | 0.4875 | 0.7793 | 481 | 0.4937 |
91
+ | 0.4881 | 0.8003 | 494 | 0.4904 |
92
+ | 0.4753 | 0.8214 | 507 | 0.4869 |
93
+ | 0.4609 | 0.8424 | 520 | 0.4825 |
94
+ | 0.4657 | 0.8635 | 533 | 0.4794 |
95
+ | 0.4563 | 0.8846 | 546 | 0.4776 |
96
+ | 0.4738 | 0.9056 | 559 | 0.4751 |
97
+ | 0.4685 | 0.9267 | 572 | 0.4743 |
98
+ | 0.4539 | 0.9478 | 585 | 0.4735 |
99
+ | 0.4606 | 0.9688 | 598 | 0.4731 |
100
+ | 0.457 | 0.9899 | 611 | 0.4730 |
101
 
102
 
103
  ### Framework versions
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:48250840b0ed40e3627f04159b57e0e74fe1f9b7f9871ded807da4d1065cd8b3
3
  size 83945296
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:65050c4310f7c51a71763df05a0bef9b2ac708e25e4604102b6f6338397daf4e
3
  size 83945296