End of training
Browse files
README.md
CHANGED
|
@@ -18,7 +18,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 18 |
|
| 19 |
This model is a fine-tuned version of [codellama/CodeLlama-7b-Instruct-hf](https://huggingface.co/codellama/CodeLlama-7b-Instruct-hf) on the None dataset.
|
| 20 |
It achieves the following results on the evaluation set:
|
| 21 |
-
- Loss: 0.
|
| 22 |
|
| 23 |
## Model description
|
| 24 |
|
|
@@ -50,98 +50,175 @@ The following hyperparameters were used during training:
|
|
| 50 |
|
| 51 |
| Training Loss | Epoch | Step | Validation Loss |
|
| 52 |
|:-------------:|:------:|:-----:|:---------------:|
|
| 53 |
-
| 0.
|
| 54 |
-
| 0.
|
| 55 |
-
| 0.
|
| 56 |
-
| 0.
|
| 57 |
-
| 0.
|
| 58 |
-
| 0.
|
| 59 |
-
| 0.
|
| 60 |
-
| 0.
|
| 61 |
-
| 0.
|
| 62 |
-
| 0.
|
| 63 |
-
| 0.
|
| 64 |
-
| 0.
|
| 65 |
-
| 0.
|
| 66 |
-
| 0.
|
| 67 |
-
| 0.
|
| 68 |
-
| 0.
|
| 69 |
-
| 0.
|
| 70 |
-
| 0.
|
| 71 |
-
| 0.
|
| 72 |
-
| 0.
|
| 73 |
-
| 0.
|
| 74 |
-
| 0.
|
| 75 |
-
| 0.
|
| 76 |
-
| 0.
|
| 77 |
-
| 0.
|
| 78 |
-
| 0.
|
| 79 |
-
| 0.
|
| 80 |
-
| 0.
|
| 81 |
-
| 0.
|
| 82 |
-
| 0.
|
| 83 |
-
| 0.
|
| 84 |
-
| 0.
|
| 85 |
-
| 0.
|
| 86 |
-
| 0.
|
| 87 |
-
| 0.
|
| 88 |
-
| 0.
|
| 89 |
-
| 0.
|
| 90 |
-
| 0.
|
| 91 |
-
| 0.
|
| 92 |
-
| 0.
|
| 93 |
-
| 0.
|
| 94 |
-
| 0.
|
| 95 |
-
| 0.
|
| 96 |
-
| 0.
|
| 97 |
-
| 0.
|
| 98 |
-
| 0.
|
| 99 |
-
| 0.
|
| 100 |
-
| 0.
|
| 101 |
-
| 0.
|
| 102 |
-
| 0.
|
| 103 |
-
| 0.
|
| 104 |
-
| 0.
|
| 105 |
-
| 0.
|
| 106 |
-
| 0.
|
| 107 |
-
| 0.
|
| 108 |
-
| 0.
|
| 109 |
-
| 0.
|
| 110 |
-
| 0.
|
| 111 |
-
| 0.
|
| 112 |
-
| 0.
|
| 113 |
-
| 0.
|
| 114 |
-
| 0.
|
| 115 |
-
| 0.
|
| 116 |
-
| 0.
|
| 117 |
-
| 0.
|
| 118 |
-
| 0.
|
| 119 |
-
| 0.
|
| 120 |
-
| 0.
|
| 121 |
-
| 0.
|
| 122 |
-
| 0.
|
| 123 |
-
| 0.
|
| 124 |
-
| 0.
|
| 125 |
-
| 0.
|
| 126 |
-
| 0.
|
| 127 |
-
| 0.
|
| 128 |
-
| 0.
|
| 129 |
-
| 0.
|
| 130 |
-
| 0.
|
| 131 |
-
| 0.
|
| 132 |
-
| 0.
|
| 133 |
-
| 0.
|
| 134 |
-
| 0.
|
| 135 |
-
| 0.
|
| 136 |
-
| 0.
|
| 137 |
-
| 0.
|
| 138 |
-
| 0.
|
| 139 |
-
| 0.
|
| 140 |
-
| 0.
|
| 141 |
-
| 0.
|
| 142 |
-
| 0.
|
| 143 |
-
| 0.
|
| 144 |
-
| 0.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 145 |
|
| 146 |
|
| 147 |
### Framework versions
|
|
|
|
| 18 |
|
| 19 |
This model is a fine-tuned version of [codellama/CodeLlama-7b-Instruct-hf](https://huggingface.co/codellama/CodeLlama-7b-Instruct-hf) on the None dataset.
|
| 20 |
It achieves the following results on the evaluation set:
|
| 21 |
+
- Loss: 0.3066
|
| 22 |
|
| 23 |
## Model description
|
| 24 |
|
|
|
|
| 50 |
|
| 51 |
| Training Loss | Epoch | Step | Validation Loss |
|
| 52 |
|:-------------:|:------:|:-----:|:---------------:|
|
| 53 |
+
| 0.197 | 2.6742 | 17000 | 0.2906 |
|
| 54 |
+
| 0.1777 | 2.6821 | 17050 | 0.2934 |
|
| 55 |
+
| 0.1949 | 2.6899 | 17100 | 0.2911 |
|
| 56 |
+
| 0.2131 | 2.6978 | 17150 | 0.2928 |
|
| 57 |
+
| 0.1839 | 2.7057 | 17200 | 0.2921 |
|
| 58 |
+
| 0.2039 | 2.7135 | 17250 | 0.2896 |
|
| 59 |
+
| 0.2187 | 2.7214 | 17300 | 0.2906 |
|
| 60 |
+
| 0.185 | 2.7293 | 17350 | 0.2906 |
|
| 61 |
+
| 0.1837 | 2.7371 | 17400 | 0.2933 |
|
| 62 |
+
| 0.2117 | 2.7450 | 17450 | 0.2889 |
|
| 63 |
+
| 0.2143 | 2.7529 | 17500 | 0.2904 |
|
| 64 |
+
| 0.1814 | 2.7607 | 17550 | 0.2897 |
|
| 65 |
+
| 0.1982 | 2.7686 | 17600 | 0.2898 |
|
| 66 |
+
| 0.2243 | 2.7765 | 17650 | 0.2903 |
|
| 67 |
+
| 0.1817 | 2.7843 | 17700 | 0.2895 |
|
| 68 |
+
| 0.1921 | 2.7922 | 17750 | 0.2919 |
|
| 69 |
+
| 0.2097 | 2.8001 | 17800 | 0.2913 |
|
| 70 |
+
| 0.1883 | 2.8079 | 17850 | 0.2903 |
|
| 71 |
+
| 0.1905 | 2.8158 | 17900 | 0.2882 |
|
| 72 |
+
| 0.2034 | 2.8237 | 17950 | 0.2884 |
|
| 73 |
+
| 0.2008 | 2.8315 | 18000 | 0.2891 |
|
| 74 |
+
| 0.184 | 2.8394 | 18050 | 0.2883 |
|
| 75 |
+
| 0.1732 | 2.8473 | 18100 | 0.2896 |
|
| 76 |
+
| 0.1905 | 2.8551 | 18150 | 0.2895 |
|
| 77 |
+
| 0.1812 | 2.8630 | 18200 | 0.2895 |
|
| 78 |
+
| 0.1941 | 2.8709 | 18250 | 0.2899 |
|
| 79 |
+
| 0.2063 | 2.8787 | 18300 | 0.2879 |
|
| 80 |
+
| 0.1982 | 2.8866 | 18350 | 0.2868 |
|
| 81 |
+
| 0.1946 | 2.8944 | 18400 | 0.2895 |
|
| 82 |
+
| 0.2104 | 2.9023 | 18450 | 0.2874 |
|
| 83 |
+
| 0.1851 | 2.9102 | 18500 | 0.2878 |
|
| 84 |
+
| 0.1968 | 2.9180 | 18550 | 0.2868 |
|
| 85 |
+
| 0.1964 | 2.9259 | 18600 | 0.2880 |
|
| 86 |
+
| 0.1863 | 2.9338 | 18650 | 0.2880 |
|
| 87 |
+
| 0.1875 | 2.9416 | 18700 | 0.2876 |
|
| 88 |
+
| 0.1698 | 2.9495 | 18750 | 0.2863 |
|
| 89 |
+
| 0.2082 | 2.9574 | 18800 | 0.2881 |
|
| 90 |
+
| 0.1962 | 2.9652 | 18850 | 0.2869 |
|
| 91 |
+
| 0.2061 | 2.9731 | 18900 | 0.2860 |
|
| 92 |
+
| 0.2132 | 2.9810 | 18950 | 0.2869 |
|
| 93 |
+
| 0.1854 | 2.9888 | 19000 | 0.2875 |
|
| 94 |
+
| 0.1906 | 2.9967 | 19050 | 0.2879 |
|
| 95 |
+
| 0.144 | 3.0046 | 19100 | 0.3005 |
|
| 96 |
+
| 0.1302 | 3.0124 | 19150 | 0.3097 |
|
| 97 |
+
| 0.1324 | 3.0203 | 19200 | 0.3090 |
|
| 98 |
+
| 0.1344 | 3.0282 | 19250 | 0.3094 |
|
| 99 |
+
| 0.1392 | 3.0360 | 19300 | 0.3064 |
|
| 100 |
+
| 0.1464 | 3.0439 | 19350 | 0.3066 |
|
| 101 |
+
| 0.141 | 3.0518 | 19400 | 0.3070 |
|
| 102 |
+
| 0.1275 | 3.0596 | 19450 | 0.3103 |
|
| 103 |
+
| 0.1284 | 3.0675 | 19500 | 0.3074 |
|
| 104 |
+
| 0.1397 | 3.0754 | 19550 | 0.3111 |
|
| 105 |
+
| 0.1335 | 3.0832 | 19600 | 0.3105 |
|
| 106 |
+
| 0.1302 | 3.0911 | 19650 | 0.3082 |
|
| 107 |
+
| 0.1315 | 3.0989 | 19700 | 0.3094 |
|
| 108 |
+
| 0.128 | 3.1068 | 19750 | 0.3110 |
|
| 109 |
+
| 0.1272 | 3.1147 | 19800 | 0.3094 |
|
| 110 |
+
| 0.1227 | 3.1225 | 19850 | 0.3074 |
|
| 111 |
+
| 0.1375 | 3.1304 | 19900 | 0.3093 |
|
| 112 |
+
| 0.1344 | 3.1383 | 19950 | 0.3092 |
|
| 113 |
+
| 0.1301 | 3.1461 | 20000 | 0.3098 |
|
| 114 |
+
| 0.1339 | 3.1540 | 20050 | 0.3083 |
|
| 115 |
+
| 0.1398 | 3.1619 | 20100 | 0.3100 |
|
| 116 |
+
| 0.132 | 3.1697 | 20150 | 0.3109 |
|
| 117 |
+
| 0.1499 | 3.1776 | 20200 | 0.3070 |
|
| 118 |
+
| 0.1438 | 3.1855 | 20250 | 0.3075 |
|
| 119 |
+
| 0.1267 | 3.1933 | 20300 | 0.3106 |
|
| 120 |
+
| 0.1282 | 3.2012 | 20350 | 0.3082 |
|
| 121 |
+
| 0.1365 | 3.2091 | 20400 | 0.3075 |
|
| 122 |
+
| 0.1239 | 3.2169 | 20450 | 0.3110 |
|
| 123 |
+
| 0.1507 | 3.2248 | 20500 | 0.3087 |
|
| 124 |
+
| 0.1364 | 3.2327 | 20550 | 0.3112 |
|
| 125 |
+
| 0.1281 | 3.2405 | 20600 | 0.3092 |
|
| 126 |
+
| 0.1271 | 3.2484 | 20650 | 0.3104 |
|
| 127 |
+
| 0.1124 | 3.2563 | 20700 | 0.3097 |
|
| 128 |
+
| 0.1382 | 3.2641 | 20750 | 0.3111 |
|
| 129 |
+
| 0.1415 | 3.2720 | 20800 | 0.3101 |
|
| 130 |
+
| 0.1246 | 3.2798 | 20850 | 0.3115 |
|
| 131 |
+
| 0.1337 | 3.2877 | 20900 | 0.3095 |
|
| 132 |
+
| 0.1378 | 3.2956 | 20950 | 0.3069 |
|
| 133 |
+
| 0.1219 | 3.3034 | 21000 | 0.3081 |
|
| 134 |
+
| 0.1303 | 3.3113 | 21050 | 0.3098 |
|
| 135 |
+
| 0.1445 | 3.3192 | 21100 | 0.3081 |
|
| 136 |
+
| 0.134 | 3.3270 | 21150 | 0.3090 |
|
| 137 |
+
| 0.1389 | 3.3349 | 21200 | 0.3098 |
|
| 138 |
+
| 0.1388 | 3.3428 | 21250 | 0.3087 |
|
| 139 |
+
| 0.1317 | 3.3506 | 21300 | 0.3094 |
|
| 140 |
+
| 0.1367 | 3.3585 | 21350 | 0.3080 |
|
| 141 |
+
| 0.1267 | 3.3664 | 21400 | 0.3092 |
|
| 142 |
+
| 0.1333 | 3.3742 | 21450 | 0.3102 |
|
| 143 |
+
| 0.1266 | 3.3821 | 21500 | 0.3102 |
|
| 144 |
+
| 0.1345 | 3.3900 | 21550 | 0.3075 |
|
| 145 |
+
| 0.1279 | 3.3978 | 21600 | 0.3083 |
|
| 146 |
+
| 0.1342 | 3.4057 | 21650 | 0.3078 |
|
| 147 |
+
| 0.141 | 3.4136 | 21700 | 0.3102 |
|
| 148 |
+
| 0.1241 | 3.4214 | 21750 | 0.3066 |
|
| 149 |
+
| 0.14 | 3.4293 | 21800 | 0.3083 |
|
| 150 |
+
| 0.1232 | 3.4372 | 21850 | 0.3070 |
|
| 151 |
+
| 0.1296 | 3.4450 | 21900 | 0.3081 |
|
| 152 |
+
| 0.1286 | 3.4529 | 21950 | 0.3065 |
|
| 153 |
+
| 0.1313 | 3.4608 | 22000 | 0.3071 |
|
| 154 |
+
| 0.1484 | 3.4686 | 22050 | 0.3058 |
|
| 155 |
+
| 0.1395 | 3.4765 | 22100 | 0.3074 |
|
| 156 |
+
| 0.1311 | 3.4843 | 22150 | 0.3064 |
|
| 157 |
+
| 0.1116 | 3.4922 | 22200 | 0.3095 |
|
| 158 |
+
| 0.1269 | 3.5001 | 22250 | 0.3102 |
|
| 159 |
+
| 0.1308 | 3.5079 | 22300 | 0.3067 |
|
| 160 |
+
| 0.127 | 3.5158 | 22350 | 0.3077 |
|
| 161 |
+
| 0.1176 | 3.5237 | 22400 | 0.3086 |
|
| 162 |
+
| 0.1234 | 3.5315 | 22450 | 0.3095 |
|
| 163 |
+
| 0.1359 | 3.5394 | 22500 | 0.3075 |
|
| 164 |
+
| 0.1337 | 3.5473 | 22550 | 0.3083 |
|
| 165 |
+
| 0.1224 | 3.5551 | 22600 | 0.3088 |
|
| 166 |
+
| 0.1286 | 3.5630 | 22650 | 0.3090 |
|
| 167 |
+
| 0.1341 | 3.5709 | 22700 | 0.3076 |
|
| 168 |
+
| 0.1419 | 3.5787 | 22750 | 0.3099 |
|
| 169 |
+
| 0.1478 | 3.5866 | 22800 | 0.3072 |
|
| 170 |
+
| 0.1215 | 3.5945 | 22850 | 0.3080 |
|
| 171 |
+
| 0.1298 | 3.6023 | 22900 | 0.3073 |
|
| 172 |
+
| 0.1368 | 3.6102 | 22950 | 0.3071 |
|
| 173 |
+
| 0.1388 | 3.6181 | 23000 | 0.3070 |
|
| 174 |
+
| 0.1239 | 3.6259 | 23050 | 0.3069 |
|
| 175 |
+
| 0.1202 | 3.6338 | 23100 | 0.3066 |
|
| 176 |
+
| 0.1329 | 3.6417 | 23150 | 0.3060 |
|
| 177 |
+
| 0.1262 | 3.6495 | 23200 | 0.3070 |
|
| 178 |
+
| 0.1221 | 3.6574 | 23250 | 0.3084 |
|
| 179 |
+
| 0.1233 | 3.6653 | 23300 | 0.3068 |
|
| 180 |
+
| 0.1222 | 3.6731 | 23350 | 0.3063 |
|
| 181 |
+
| 0.133 | 3.6810 | 23400 | 0.3067 |
|
| 182 |
+
| 0.1276 | 3.6888 | 23450 | 0.3054 |
|
| 183 |
+
| 0.1214 | 3.6967 | 23500 | 0.3065 |
|
| 184 |
+
| 0.1308 | 3.7046 | 23550 | 0.3072 |
|
| 185 |
+
| 0.1278 | 3.7124 | 23600 | 0.3074 |
|
| 186 |
+
| 0.1177 | 3.7203 | 23650 | 0.3070 |
|
| 187 |
+
| 0.1302 | 3.7282 | 23700 | 0.3067 |
|
| 188 |
+
| 0.1279 | 3.7360 | 23750 | 0.3068 |
|
| 189 |
+
| 0.132 | 3.7439 | 23800 | 0.3078 |
|
| 190 |
+
| 0.143 | 3.7518 | 23850 | 0.3070 |
|
| 191 |
+
| 0.1365 | 3.7596 | 23900 | 0.3068 |
|
| 192 |
+
| 0.1456 | 3.7675 | 23950 | 0.3073 |
|
| 193 |
+
| 0.1312 | 3.7754 | 24000 | 0.3069 |
|
| 194 |
+
| 0.1304 | 3.7832 | 24050 | 0.3073 |
|
| 195 |
+
| 0.1409 | 3.7911 | 24100 | 0.3069 |
|
| 196 |
+
| 0.1369 | 3.7990 | 24150 | 0.3067 |
|
| 197 |
+
| 0.1291 | 3.8068 | 24200 | 0.3065 |
|
| 198 |
+
| 0.1114 | 3.8147 | 24250 | 0.3073 |
|
| 199 |
+
| 0.1294 | 3.8226 | 24300 | 0.3067 |
|
| 200 |
+
| 0.1223 | 3.8304 | 24350 | 0.3071 |
|
| 201 |
+
| 0.1166 | 3.8383 | 24400 | 0.3074 |
|
| 202 |
+
| 0.1233 | 3.8462 | 24450 | 0.3076 |
|
| 203 |
+
| 0.1348 | 3.8540 | 24500 | 0.3073 |
|
| 204 |
+
| 0.1203 | 3.8619 | 24550 | 0.3069 |
|
| 205 |
+
| 0.1326 | 3.8697 | 24600 | 0.3072 |
|
| 206 |
+
| 0.123 | 3.8776 | 24650 | 0.3070 |
|
| 207 |
+
| 0.13 | 3.8855 | 24700 | 0.3069 |
|
| 208 |
+
| 0.1305 | 3.8933 | 24750 | 0.3073 |
|
| 209 |
+
| 0.1366 | 3.9012 | 24800 | 0.3075 |
|
| 210 |
+
| 0.1428 | 3.9091 | 24850 | 0.3078 |
|
| 211 |
+
| 0.1258 | 3.9169 | 24900 | 0.3075 |
|
| 212 |
+
| 0.135 | 3.9248 | 24950 | 0.3073 |
|
| 213 |
+
| 0.1282 | 3.9327 | 25000 | 0.3071 |
|
| 214 |
+
| 0.1323 | 3.9405 | 25050 | 0.3073 |
|
| 215 |
+
| 0.1242 | 3.9484 | 25100 | 0.3072 |
|
| 216 |
+
| 0.1453 | 3.9563 | 25150 | 0.3071 |
|
| 217 |
+
| 0.1441 | 3.9641 | 25200 | 0.3067 |
|
| 218 |
+
| 0.1273 | 3.9720 | 25250 | 0.3066 |
|
| 219 |
+
| 0.115 | 3.9799 | 25300 | 0.3067 |
|
| 220 |
+
| 0.1337 | 3.9877 | 25350 | 0.3067 |
|
| 221 |
+
| 0.1259 | 3.9956 | 25400 | 0.3066 |
|
| 222 |
|
| 223 |
|
| 224 |
### Framework versions
|
adapter_config.json
CHANGED
|
@@ -21,12 +21,12 @@
|
|
| 21 |
"revision": null,
|
| 22 |
"target_modules": [
|
| 23 |
"down_proj",
|
| 24 |
-
"
|
| 25 |
-
"gate_proj",
|
| 26 |
-
"up_proj",
|
| 27 |
"k_proj",
|
| 28 |
"q_proj",
|
| 29 |
-
"
|
|
|
|
|
|
|
| 30 |
],
|
| 31 |
"task_type": "CAUSAL_LM",
|
| 32 |
"use_dora": false,
|
|
|
|
| 21 |
"revision": null,
|
| 22 |
"target_modules": [
|
| 23 |
"down_proj",
|
| 24 |
+
"o_proj",
|
|
|
|
|
|
|
| 25 |
"k_proj",
|
| 26 |
"q_proj",
|
| 27 |
+
"gate_proj",
|
| 28 |
+
"v_proj",
|
| 29 |
+
"up_proj"
|
| 30 |
],
|
| 31 |
"task_type": "CAUSAL_LM",
|
| 32 |
"use_dora": false,
|
adapter_model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 2332095256
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:99d96065daed251701f196a470db6fbbc39963213624893f959bb9cab48b1b3f
|
| 3 |
size 2332095256
|
runs/Oct04_03-01-42_08a568cc6f00/events.out.tfevents.1728010908.08a568cc6f00.12129.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:958211e3f7d58cfa274634ae47b6d54fc006debfe72ef9fa4ba2306f13d9862e
|
| 3 |
+
size 160826
|
training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 5560
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:34d9e83567d3beb472a14841c9158888c402a755601b0a9eac9fb43a1971c742
|
| 3 |
size 5560
|