metadata
base_model: codellama/CodeLlama-7b-Instruct-hf
library_name: peft
license: llama2
tags:
- trl
- sft
- generated_from_trainer
model-index:
- name: Codellama-7b-lora-rps-adapter
results: []
Codellama-7b-lora-rps-adapter
This model is a fine-tuned version of codellama/CodeLlama-7b-Instruct-hf on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.3056
Model description
More information needed
Intended uses & limitations
More information needed
Training and evaluation data
More information needed
Training procedure
Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 0.0002
- train_batch_size: 2
- eval_batch_size: 2
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.03
- num_epochs: 4
Training results
Training Loss | Epoch | Step | Validation Loss |
---|---|---|---|
0.2053 | 2.3256 | 15000 | 0.2969 |
0.1942 | 2.3333 | 15050 | 0.2944 |
0.1871 | 2.3411 | 15100 | 0.2949 |
0.1845 | 2.3488 | 15150 | 0.2954 |
0.2108 | 2.3566 | 15200 | 0.2950 |
0.2065 | 2.3643 | 15250 | 0.2951 |
0.193 | 2.3721 | 15300 | 0.2961 |
0.1947 | 2.3798 | 15350 | 0.2953 |
0.1922 | 2.3876 | 15400 | 0.2949 |
0.1777 | 2.3953 | 15450 | 0.2949 |
0.212 | 2.4031 | 15500 | 0.2949 |
0.1962 | 2.4109 | 15550 | 0.2949 |
0.1789 | 2.4186 | 15600 | 0.2951 |
0.2183 | 2.4264 | 15650 | 0.2923 |
0.1962 | 2.4341 | 15700 | 0.2947 |
0.1907 | 2.4419 | 15750 | 0.2928 |
0.1936 | 2.4496 | 15800 | 0.2956 |
0.2086 | 2.4574 | 15850 | 0.2933 |
0.1895 | 2.4651 | 15900 | 0.2959 |
0.2157 | 2.4729 | 15950 | 0.2932 |
0.1897 | 2.4806 | 16000 | 0.2926 |
0.1862 | 2.4884 | 16050 | 0.2937 |
0.1899 | 2.4961 | 16100 | 0.2955 |
0.187 | 2.5039 | 16150 | 0.2970 |
0.2126 | 2.5116 | 16200 | 0.2941 |
0.1973 | 2.5194 | 16250 | 0.2933 |
0.1743 | 2.5271 | 16300 | 0.2930 |
0.1958 | 2.5349 | 16350 | 0.2938 |
0.2162 | 2.5426 | 16400 | 0.2919 |
0.1872 | 2.5504 | 16450 | 0.2936 |
0.1821 | 2.5581 | 16500 | 0.2940 |
0.2193 | 2.5659 | 16550 | 0.2940 |
0.1983 | 2.5736 | 16600 | 0.2943 |
0.2121 | 2.5814 | 16650 | 0.2941 |
0.1969 | 2.5891 | 16700 | 0.2923 |
0.1963 | 2.5969 | 16750 | 0.2921 |
0.2042 | 2.6047 | 16800 | 0.2938 |
0.1921 | 2.6124 | 16850 | 0.2914 |
0.2081 | 2.6202 | 16900 | 0.2917 |
0.1711 | 2.6279 | 16950 | 0.2923 |
0.1897 | 2.6357 | 17000 | 0.2918 |
0.1917 | 2.6434 | 17050 | 0.2933 |
0.1991 | 2.6512 | 17100 | 0.2909 |
0.2055 | 2.6589 | 17150 | 0.2930 |
0.1932 | 2.6667 | 17200 | 0.2907 |
0.2043 | 2.6744 | 17250 | 0.2937 |
0.1922 | 2.6822 | 17300 | 0.2922 |
0.1785 | 2.6899 | 17350 | 0.2922 |
0.2337 | 2.6977 | 17400 | 0.2908 |
0.1933 | 2.7054 | 17450 | 0.2922 |
0.2012 | 2.7132 | 17500 | 0.2914 |
0.1959 | 2.7209 | 17550 | 0.2910 |
0.1933 | 2.7287 | 17600 | 0.2882 |
0.1824 | 2.7364 | 17650 | 0.2889 |
0.2016 | 2.7442 | 17700 | 0.2898 |
0.2024 | 2.7519 | 17750 | 0.2915 |
0.2101 | 2.7597 | 17800 | 0.2888 |
0.1782 | 2.7674 | 17850 | 0.2908 |
0.2047 | 2.7752 | 17900 | 0.2902 |
0.195 | 2.7829 | 17950 | 0.2895 |
0.2122 | 2.7907 | 18000 | 0.2884 |
0.2099 | 2.7984 | 18050 | 0.2869 |
0.2054 | 2.8062 | 18100 | 0.2882 |
0.193 | 2.8140 | 18150 | 0.2884 |
0.187 | 2.8217 | 18200 | 0.2895 |
0.1997 | 2.8295 | 18250 | 0.2883 |
0.1885 | 2.8372 | 18300 | 0.2896 |
0.1957 | 2.8450 | 18350 | 0.2871 |
0.1905 | 2.8527 | 18400 | 0.2879 |
0.1933 | 2.8605 | 18450 | 0.2880 |
0.1953 | 2.8682 | 18500 | 0.2871 |
0.205 | 2.8760 | 18550 | 0.2865 |
0.191 | 2.8837 | 18600 | 0.2870 |
0.1903 | 2.8915 | 18650 | 0.2870 |
0.1897 | 2.8992 | 18700 | 0.2873 |
0.1966 | 2.9070 | 18750 | 0.2871 |
0.228 | 2.9147 | 18800 | 0.2875 |
0.1948 | 2.9225 | 18850 | 0.2870 |
0.1843 | 2.9302 | 18900 | 0.2859 |
0.2037 | 2.9380 | 18950 | 0.2872 |
0.2087 | 2.9457 | 19000 | 0.2855 |
0.1777 | 2.9535 | 19050 | 0.2864 |
0.1852 | 2.9612 | 19100 | 0.2866 |
0.1879 | 2.9690 | 19150 | 0.2858 |
0.2096 | 2.9767 | 19200 | 0.2848 |
0.1846 | 2.9845 | 19250 | 0.2857 |
0.1782 | 2.9922 | 19300 | 0.2859 |
0.1762 | 3.0 | 19350 | 0.2864 |
0.1339 | 3.0078 | 19400 | 0.3056 |
0.1356 | 3.0155 | 19450 | 0.3067 |
0.136 | 3.0233 | 19500 | 0.3073 |
0.1389 | 3.0310 | 19550 | 0.3089 |
0.1362 | 3.0388 | 19600 | 0.3084 |
0.1384 | 3.0465 | 19650 | 0.3085 |
0.1167 | 3.0543 | 19700 | 0.3092 |
0.1291 | 3.0620 | 19750 | 0.3078 |
0.1292 | 3.0698 | 19800 | 0.3092 |
0.1257 | 3.0775 | 19850 | 0.3099 |
0.1384 | 3.0853 | 19900 | 0.3088 |
0.1355 | 3.0930 | 19950 | 0.3076 |
0.1244 | 3.1008 | 20000 | 0.3088 |
0.141 | 3.1085 | 20050 | 0.3082 |
0.1398 | 3.1163 | 20100 | 0.3080 |
0.1415 | 3.1240 | 20150 | 0.3085 |
0.1521 | 3.1318 | 20200 | 0.3067 |
0.1266 | 3.1395 | 20250 | 0.3097 |
0.1254 | 3.1473 | 20300 | 0.3101 |
0.1403 | 3.1550 | 20350 | 0.3053 |
0.1395 | 3.1628 | 20400 | 0.3085 |
0.1328 | 3.1705 | 20450 | 0.3074 |
0.1381 | 3.1783 | 20500 | 0.3090 |
0.1323 | 3.1860 | 20550 | 0.3058 |
0.1299 | 3.1938 | 20600 | 0.3092 |
0.1432 | 3.2016 | 20650 | 0.3074 |
0.1399 | 3.2093 | 20700 | 0.3071 |
0.1288 | 3.2171 | 20750 | 0.3076 |
0.1464 | 3.2248 | 20800 | 0.3060 |
0.1347 | 3.2326 | 20850 | 0.3066 |
0.1336 | 3.2403 | 20900 | 0.3080 |
0.1245 | 3.2481 | 20950 | 0.3069 |
0.1305 | 3.2558 | 21000 | 0.3080 |
0.1379 | 3.2636 | 21050 | 0.3050 |
0.1269 | 3.2713 | 21100 | 0.3074 |
0.1379 | 3.2791 | 21150 | 0.3067 |
0.1348 | 3.2868 | 21200 | 0.3077 |
0.1261 | 3.2946 | 21250 | 0.3116 |
0.1354 | 3.3023 | 21300 | 0.3064 |
0.1323 | 3.3101 | 21350 | 0.3061 |
0.1255 | 3.3178 | 21400 | 0.3078 |
0.135 | 3.3256 | 21450 | 0.3073 |
0.1354 | 3.3333 | 21500 | 0.3070 |
0.1391 | 3.3411 | 21550 | 0.3066 |
0.1295 | 3.3488 | 21600 | 0.3086 |
0.1215 | 3.3566 | 21650 | 0.3085 |
0.1411 | 3.3643 | 21700 | 0.3072 |
0.1393 | 3.3721 | 21750 | 0.3090 |
0.132 | 3.3798 | 21800 | 0.3086 |
0.1199 | 3.3876 | 21850 | 0.3089 |
0.1349 | 3.3953 | 21900 | 0.3069 |
0.1325 | 3.4031 | 21950 | 0.3084 |
0.1247 | 3.4109 | 22000 | 0.3082 |
0.1178 | 3.4186 | 22050 | 0.3062 |
0.1218 | 3.4264 | 22100 | 0.3090 |
0.131 | 3.4341 | 22150 | 0.3100 |
0.1274 | 3.4419 | 22200 | 0.3070 |
0.136 | 3.4496 | 22250 | 0.3083 |
0.1458 | 3.4574 | 22300 | 0.3076 |
0.1365 | 3.4651 | 22350 | 0.3087 |
0.1362 | 3.4729 | 22400 | 0.3071 |
0.1318 | 3.4806 | 22450 | 0.3073 |
0.138 | 3.4884 | 22500 | 0.3067 |
0.1413 | 3.4961 | 22550 | 0.3080 |
0.1365 | 3.5039 | 22600 | 0.3087 |
0.1236 | 3.5116 | 22650 | 0.3078 |
0.1503 | 3.5194 | 22700 | 0.3063 |
0.1437 | 3.5271 | 22750 | 0.3070 |
0.1338 | 3.5349 | 22800 | 0.3070 |
0.1256 | 3.5426 | 22850 | 0.3080 |
0.1296 | 3.5504 | 22900 | 0.3074 |
0.1286 | 3.5581 | 22950 | 0.3061 |
0.1334 | 3.5659 | 23000 | 0.3075 |
0.133 | 3.5736 | 23050 | 0.3058 |
0.113 | 3.5814 | 23100 | 0.3060 |
0.1238 | 3.5891 | 23150 | 0.3052 |
0.1398 | 3.5969 | 23200 | 0.3044 |
0.142 | 3.6047 | 23250 | 0.3054 |
0.1257 | 3.6124 | 23300 | 0.3059 |
0.1324 | 3.6202 | 23350 | 0.3052 |
0.1376 | 3.6279 | 23400 | 0.3039 |
0.1343 | 3.6357 | 23450 | 0.3037 |
0.1264 | 3.6434 | 23500 | 0.3054 |
0.1263 | 3.6512 | 23550 | 0.3062 |
0.127 | 3.6589 | 23600 | 0.3054 |
0.1187 | 3.6667 | 23650 | 0.3054 |
0.1204 | 3.6744 | 23700 | 0.3059 |
0.1148 | 3.6822 | 23750 | 0.3065 |
0.1205 | 3.6899 | 23800 | 0.3073 |
0.1277 | 3.6977 | 23850 | 0.3067 |
0.1356 | 3.7054 | 23900 | 0.3067 |
0.1518 | 3.7132 | 23950 | 0.3064 |
0.1307 | 3.7209 | 24000 | 0.3062 |
0.1344 | 3.7287 | 24050 | 0.3061 |
0.1326 | 3.7364 | 24100 | 0.3065 |
0.1246 | 3.7442 | 24150 | 0.3074 |
0.1319 | 3.7519 | 24200 | 0.3071 |
0.1436 | 3.7597 | 24250 | 0.3063 |
0.1389 | 3.7674 | 24300 | 0.3064 |
0.1275 | 3.7752 | 24350 | 0.3065 |
0.1353 | 3.7829 | 24400 | 0.3061 |
0.1289 | 3.7907 | 24450 | 0.3056 |
0.1326 | 3.7984 | 24500 | 0.3053 |
0.1244 | 3.8062 | 24550 | 0.3054 |
0.1287 | 3.8140 | 24600 | 0.3056 |
0.1168 | 3.8217 | 24650 | 0.3058 |
0.1298 | 3.8295 | 24700 | 0.3055 |
0.1231 | 3.8372 | 24750 | 0.3057 |
0.1289 | 3.8450 | 24800 | 0.3059 |
0.1184 | 3.8527 | 24850 | 0.3056 |
0.1226 | 3.8605 | 24900 | 0.3055 |
0.1593 | 3.8682 | 24950 | 0.3057 |
0.128 | 3.8760 | 25000 | 0.3064 |
0.1332 | 3.8837 | 25050 | 0.3058 |
0.1397 | 3.8915 | 25100 | 0.3055 |
0.1059 | 3.8992 | 25150 | 0.3058 |
0.1281 | 3.9070 | 25200 | 0.3054 |
0.1277 | 3.9147 | 25250 | 0.3056 |
0.1119 | 3.9225 | 25300 | 0.3059 |
0.1212 | 3.9302 | 25350 | 0.3059 |
0.1131 | 3.9380 | 25400 | 0.3059 |
0.1407 | 3.9457 | 25450 | 0.3059 |
0.1286 | 3.9535 | 25500 | 0.3056 |
0.1252 | 3.9612 | 25550 | 0.3056 |
0.138 | 3.9690 | 25600 | 0.3056 |
0.1245 | 3.9767 | 25650 | 0.3056 |
0.1213 | 3.9845 | 25700 | 0.3056 |
0.1276 | 3.9922 | 25750 | 0.3056 |
0.1328 | 4.0 | 25800 | 0.3056 |
Framework versions
- PEFT 0.12.0
- Transformers 4.44.2
- Pytorch 2.4.1+cu121
- Datasets 3.0.0
- Tokenizers 0.19.1