imdatta0 commited on
Commit
b97f026
1 Parent(s): 5474373

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 [unsloth/Qwen2-7B](https://huggingface.co/unsloth/Qwen2-7B) on an unknown dataset.
19
  It achieves the following results on the evaluation set:
20
- - Loss: 0.2061
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
- | 0.1901 | 0.0211 | 13 | 0.1752 |
55
- | 0.1801 | 0.0421 | 26 | 0.2122 |
56
- | 0.2158 | 0.0632 | 39 | 0.2351 |
57
- | 0.2309 | 0.0842 | 52 | 0.2526 |
58
- | 0.242 | 0.1053 | 65 | 0.2650 |
59
- | 0.2587 | 0.1264 | 78 | 0.2717 |
60
- | 0.2671 | 0.1474 | 91 | 0.2770 |
61
- | 0.2594 | 0.1685 | 104 | 0.2786 |
62
- | 0.2707 | 0.1896 | 117 | 0.2831 |
63
- | 0.2661 | 0.2106 | 130 | 0.2895 |
64
- | 0.2795 | 0.2317 | 143 | 0.2919 |
65
- | 0.2747 | 0.2527 | 156 | 0.2873 |
66
- | 0.2824 | 0.2738 | 169 | 0.2873 |
67
- | 0.2717 | 0.2949 | 182 | 0.2873 |
68
- | 0.2801 | 0.3159 | 195 | 0.2838 |
69
- | 0.2713 | 0.3370 | 208 | 0.2821 |
70
- | 0.2678 | 0.3580 | 221 | 0.2797 |
71
- | 0.2692 | 0.3791 | 234 | 0.2787 |
72
- | 0.2671 | 0.4002 | 247 | 0.2769 |
73
- | 0.268 | 0.4212 | 260 | 0.2742 |
74
- | 0.2713 | 0.4423 | 273 | 0.2729 |
75
- | 0.26 | 0.4633 | 286 | 0.2679 |
76
- | 0.2677 | 0.4844 | 299 | 0.2628 |
77
- | 0.248 | 0.5055 | 312 | 0.2594 |
78
- | 0.2481 | 0.5265 | 325 | 0.2574 |
79
- | 0.2381 | 0.5476 | 338 | 0.2521 |
80
- | 0.2427 | 0.5687 | 351 | 0.2501 |
81
- | 0.2463 | 0.5897 | 364 | 0.2442 |
82
- | 0.2339 | 0.6108 | 377 | 0.2396 |
83
- | 0.2304 | 0.6318 | 390 | 0.2343 |
84
- | 0.2291 | 0.6529 | 403 | 0.2309 |
85
- | 0.2308 | 0.6740 | 416 | 0.2291 |
86
- | 0.224 | 0.6950 | 429 | 0.2254 |
87
- | 0.2248 | 0.7161 | 442 | 0.2224 |
88
- | 0.2122 | 0.7371 | 455 | 0.2184 |
89
- | 0.2135 | 0.7582 | 468 | 0.2162 |
90
- | 0.2181 | 0.7793 | 481 | 0.2154 |
91
- | 0.213 | 0.8003 | 494 | 0.2133 |
92
- | 0.2022 | 0.8214 | 507 | 0.2115 |
93
- | 0.2084 | 0.8424 | 520 | 0.2093 |
94
- | 0.206 | 0.8635 | 533 | 0.2080 |
95
- | 0.201 | 0.8846 | 546 | 0.2074 |
96
- | 0.1971 | 0.9056 | 559 | 0.2069 |
97
- | 0.1986 | 0.9267 | 572 | 0.2065 |
98
- | 0.2049 | 0.9478 | 585 | 0.2064 |
99
- | 0.2034 | 0.9688 | 598 | 0.2061 |
100
- | 0.2044 | 0.9899 | 611 | 0.2061 |
101
 
102
 
103
  ### Framework versions
 
17
 
18
  This model is a fine-tuned version of [unsloth/Qwen2-7B](https://huggingface.co/unsloth/Qwen2-7B) on an unknown dataset.
19
  It achieves the following results on the evaluation set:
20
+ - Loss: 0.2069
21
 
22
  ## Model description
23
 
 
51
 
52
  | Training Loss | Epoch | Step | Validation Loss |
53
  |:-------------:|:------:|:----:|:---------------:|
54
+ | 0.1901 | 0.0211 | 13 | 0.1745 |
55
+ | 0.1805 | 0.0421 | 26 | 0.2131 |
56
+ | 0.2166 | 0.0632 | 39 | 0.2354 |
57
+ | 0.2322 | 0.0842 | 52 | 0.2523 |
58
+ | 0.2419 | 0.1053 | 65 | 0.2642 |
59
+ | 0.2577 | 0.1264 | 78 | 0.2728 |
60
+ | 0.2667 | 0.1474 | 91 | 0.2756 |
61
+ | 0.2586 | 0.1685 | 104 | 0.2777 |
62
+ | 0.2699 | 0.1896 | 117 | 0.2833 |
63
+ | 0.268 | 0.2106 | 130 | 0.2879 |
64
+ | 0.2792 | 0.2317 | 143 | 0.2897 |
65
+ | 0.2717 | 0.2527 | 156 | 0.2865 |
66
+ | 0.2823 | 0.2738 | 169 | 0.2875 |
67
+ | 0.2717 | 0.2949 | 182 | 0.2862 |
68
+ | 0.2771 | 0.3159 | 195 | 0.2840 |
69
+ | 0.2703 | 0.3370 | 208 | 0.2814 |
70
+ | 0.2684 | 0.3580 | 221 | 0.2790 |
71
+ | 0.2685 | 0.3791 | 234 | 0.2772 |
72
+ | 0.2659 | 0.4002 | 247 | 0.2726 |
73
+ | 0.2665 | 0.4212 | 260 | 0.2728 |
74
+ | 0.2702 | 0.4423 | 273 | 0.2701 |
75
+ | 0.258 | 0.4633 | 286 | 0.2680 |
76
+ | 0.2649 | 0.4844 | 299 | 0.2631 |
77
+ | 0.2465 | 0.5055 | 312 | 0.2600 |
78
+ | 0.2497 | 0.5265 | 325 | 0.2575 |
79
+ | 0.2403 | 0.5476 | 338 | 0.2532 |
80
+ | 0.2409 | 0.5687 | 351 | 0.2501 |
81
+ | 0.2425 | 0.5897 | 364 | 0.2451 |
82
+ | 0.2357 | 0.6108 | 377 | 0.2408 |
83
+ | 0.2294 | 0.6318 | 390 | 0.2359 |
84
+ | 0.2306 | 0.6529 | 403 | 0.2337 |
85
+ | 0.2337 | 0.6740 | 416 | 0.2299 |
86
+ | 0.2249 | 0.6950 | 429 | 0.2261 |
87
+ | 0.2271 | 0.7161 | 442 | 0.2221 |
88
+ | 0.2123 | 0.7371 | 455 | 0.2190 |
89
+ | 0.2137 | 0.7582 | 468 | 0.2166 |
90
+ | 0.2185 | 0.7793 | 481 | 0.2152 |
91
+ | 0.2132 | 0.8003 | 494 | 0.2141 |
92
+ | 0.2008 | 0.8214 | 507 | 0.2118 |
93
+ | 0.2083 | 0.8424 | 520 | 0.2098 |
94
+ | 0.2045 | 0.8635 | 533 | 0.2093 |
95
+ | 0.2011 | 0.8846 | 546 | 0.2086 |
96
+ | 0.1969 | 0.9056 | 559 | 0.2078 |
97
+ | 0.1979 | 0.9267 | 572 | 0.2074 |
98
+ | 0.203 | 0.9478 | 585 | 0.2071 |
99
+ | 0.2037 | 0.9688 | 598 | 0.2068 |
100
+ | 0.2047 | 0.9899 | 611 | 0.2069 |
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:d1a678cce614506cbb2280e9db61dbe59ef014759806fe3394b6fa2a78982972
3
  size 80792096
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1dd914de4d592fff9c2b828fe3817c07a3ebd6dac6dcc5b41f71f2adcabb7da8
3
  size 80792096