imdatta0 commited on
Commit
dcd7bb9
1 Parent(s): 7231846

End of training

Browse files
Files changed (2) hide show
  1. README.md +47 -47
  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: 0.2138
21
 
22
  ## Model description
23
 
@@ -52,52 +52,52 @@ The following hyperparameters were used during training:
52
  | Training Loss | Epoch | Step | Validation Loss |
53
  |:-------------:|:------:|:----:|:---------------:|
54
  | 0.1753 | 0.0211 | 13 | 0.1875 |
55
- | 0.2025 | 0.0421 | 26 | 0.2505 |
56
- | 0.259 | 0.0632 | 39 | 0.2862 |
57
- | 0.2849 | 0.0842 | 52 | 0.3049 |
58
- | 0.2973 | 0.1053 | 65 | 0.3251 |
59
- | 0.3177 | 0.1264 | 78 | 0.3333 |
60
- | 0.325 | 0.1474 | 91 | 0.3354 |
61
- | 0.3151 | 0.1685 | 104 | 0.3331 |
62
- | 0.3285 | 0.1896 | 117 | 0.3399 |
63
- | 0.3239 | 0.2106 | 130 | 0.3437 |
64
- | 0.3332 | 0.2317 | 143 | 0.3472 |
65
- | 0.334 | 0.2527 | 156 | 0.3382 |
66
- | 0.3326 | 0.2738 | 169 | 0.3350 |
67
- | 0.3218 | 0.2949 | 182 | 0.3350 |
68
- | 0.3285 | 0.3159 | 195 | 0.3321 |
69
- | 0.3155 | 0.3370 | 208 | 0.3288 |
70
- | 0.3167 | 0.3580 | 221 | 0.3286 |
71
- | 0.3139 | 0.3791 | 234 | 0.3219 |
72
- | 0.3064 | 0.4002 | 247 | 0.3196 |
73
- | 0.309 | 0.4212 | 260 | 0.3154 |
74
- | 0.3138 | 0.4423 | 273 | 0.3132 |
75
- | 0.298 | 0.4633 | 286 | 0.3069 |
76
- | 0.3019 | 0.4844 | 299 | 0.2991 |
77
- | 0.2823 | 0.5055 | 312 | 0.2951 |
78
- | 0.2875 | 0.5265 | 325 | 0.2882 |
79
- | 0.272 | 0.5476 | 338 | 0.2818 |
80
- | 0.2697 | 0.5687 | 351 | 0.2770 |
81
- | 0.2711 | 0.5897 | 364 | 0.2703 |
82
- | 0.261 | 0.6108 | 377 | 0.2649 |
83
- | 0.2515 | 0.6318 | 390 | 0.2592 |
84
- | 0.253 | 0.6529 | 403 | 0.2546 |
85
- | 0.2529 | 0.6740 | 416 | 0.2493 |
86
- | 0.2424 | 0.6950 | 429 | 0.2447 |
87
- | 0.2448 | 0.7161 | 442 | 0.2404 |
88
- | 0.2278 | 0.7371 | 455 | 0.2340 |
89
- | 0.2289 | 0.7582 | 468 | 0.2313 |
90
- | 0.2315 | 0.7793 | 481 | 0.2279 |
91
- | 0.225 | 0.8003 | 494 | 0.2246 |
92
- | 0.2127 | 0.8214 | 507 | 0.2213 |
93
- | 0.2199 | 0.8424 | 520 | 0.2191 |
94
- | 0.2131 | 0.8635 | 533 | 0.2175 |
95
- | 0.2107 | 0.8846 | 546 | 0.2160 |
96
- | 0.2073 | 0.9056 | 559 | 0.2152 |
97
- | 0.2062 | 0.9267 | 572 | 0.2147 |
98
- | 0.214 | 0.9478 | 585 | 0.2143 |
99
- | 0.2118 | 0.9688 | 598 | 0.2138 |
100
- | 0.2107 | 0.9899 | 611 | 0.2138 |
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: 0.2136
21
 
22
  ## Model description
23
 
 
52
  | Training Loss | Epoch | Step | Validation Loss |
53
  |:-------------:|:------:|:----:|:---------------:|
54
  | 0.1753 | 0.0211 | 13 | 0.1875 |
55
+ | 0.2036 | 0.0421 | 26 | 0.2524 |
56
+ | 0.2585 | 0.0632 | 39 | 0.2876 |
57
+ | 0.2848 | 0.0842 | 52 | 0.3146 |
58
+ | 0.2997 | 0.1053 | 65 | 0.3231 |
59
+ | 0.3196 | 0.1264 | 78 | 0.3350 |
60
+ | 0.3263 | 0.1474 | 91 | 0.3406 |
61
+ | 0.3148 | 0.1685 | 104 | 0.3401 |
62
+ | 0.3297 | 0.1896 | 117 | 0.3456 |
63
+ | 0.3221 | 0.2106 | 130 | 0.3477 |
64
+ | 0.3359 | 0.2317 | 143 | 0.3491 |
65
+ | 0.3296 | 0.2527 | 156 | 0.3399 |
66
+ | 0.3361 | 0.2738 | 169 | 0.3416 |
67
+ | 0.3187 | 0.2949 | 182 | 0.3376 |
68
+ | 0.3285 | 0.3159 | 195 | 0.3370 |
69
+ | 0.3189 | 0.3370 | 208 | 0.3306 |
70
+ | 0.3154 | 0.3580 | 221 | 0.3293 |
71
+ | 0.3149 | 0.3791 | 234 | 0.3263 |
72
+ | 0.3099 | 0.4002 | 247 | 0.3208 |
73
+ | 0.3089 | 0.4212 | 260 | 0.3143 |
74
+ | 0.3125 | 0.4423 | 273 | 0.3104 |
75
+ | 0.2959 | 0.4633 | 286 | 0.3061 |
76
+ | 0.3042 | 0.4844 | 299 | 0.2993 |
77
+ | 0.2829 | 0.5055 | 312 | 0.2940 |
78
+ | 0.2832 | 0.5265 | 325 | 0.2878 |
79
+ | 0.2715 | 0.5476 | 338 | 0.2821 |
80
+ | 0.2702 | 0.5687 | 351 | 0.2753 |
81
+ | 0.2687 | 0.5897 | 364 | 0.2687 |
82
+ | 0.2604 | 0.6108 | 377 | 0.2629 |
83
+ | 0.252 | 0.6318 | 390 | 0.2579 |
84
+ | 0.2537 | 0.6529 | 403 | 0.2529 |
85
+ | 0.2535 | 0.6740 | 416 | 0.2477 |
86
+ | 0.2442 | 0.6950 | 429 | 0.2425 |
87
+ | 0.2451 | 0.7161 | 442 | 0.2378 |
88
+ | 0.2275 | 0.7371 | 455 | 0.2338 |
89
+ | 0.2288 | 0.7582 | 468 | 0.2310 |
90
+ | 0.2323 | 0.7793 | 481 | 0.2294 |
91
+ | 0.2254 | 0.8003 | 494 | 0.2260 |
92
+ | 0.2142 | 0.8214 | 507 | 0.2221 |
93
+ | 0.219 | 0.8424 | 520 | 0.2195 |
94
+ | 0.2133 | 0.8635 | 533 | 0.2180 |
95
+ | 0.2095 | 0.8846 | 546 | 0.2164 |
96
+ | 0.2067 | 0.9056 | 559 | 0.2155 |
97
+ | 0.2073 | 0.9267 | 572 | 0.2146 |
98
+ | 0.2124 | 0.9478 | 585 | 0.2140 |
99
+ | 0.2115 | 0.9688 | 598 | 0.2138 |
100
+ | 0.2127 | 0.9899 | 611 | 0.2136 |
101
 
102
 
103
  ### Framework versions
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5d967d5f4b450bed4078c8951fd243dd12205c41b81bf1431f271b8e46f4e139
3
  size 80792096
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:13ca87c06bde0836d8599106f0da77aba932594cc161b86a7ebf1cc567c6abdf
3
  size 80792096