End of training
Browse files
README.md
CHANGED
|
@@ -16,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 16 |
|
| 17 |
This model is a fine-tuned version of [deepseek-ai/deepseek-coder-6.7b-base](https://huggingface.co/deepseek-ai/deepseek-coder-6.7b-base) on an unknown dataset.
|
| 18 |
It achieves the following results on the evaluation set:
|
| 19 |
-
- Loss: 0.
|
| 20 |
|
| 21 |
## Model description
|
| 22 |
|
|
@@ -52,65 +52,65 @@ The following hyperparameters were used during training:
|
|
| 52 |
|
| 53 |
| Training Loss | Epoch | Step | Validation Loss |
|
| 54 |
|:-------------:|:-------:|:-----:|:---------------:|
|
| 55 |
-
| 0.
|
| 56 |
-
| 0.
|
| 57 |
-
| 0.
|
| 58 |
-
| 0.
|
| 59 |
-
| 0.
|
| 60 |
-
| 0.
|
| 61 |
-
| 0.
|
| 62 |
-
| 0.
|
| 63 |
-
| 0.
|
| 64 |
-
| 0.
|
| 65 |
-
| 0.108 | 2.2006 | 7920 | 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 |
-
| 0.065 | 6.0017 | 21600 | 0.
|
| 85 |
-
| 0.0565 | 6.2017 | 22320 | 0.
|
| 86 |
-
| 0.
|
| 87 |
-
| 0.
|
| 88 |
-
| 0.057 | 6.8019 | 24480 | 0.
|
| 89 |
-
| 0.
|
| 90 |
-
| 0.049 | 7.2020 | 25920 | 0.
|
| 91 |
-
| 0.
|
| 92 |
-
| 0.0481 | 7.6021 | 27360 | 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 |
-
| 0.0254 | 11.4032 | 41040 | 0.
|
| 112 |
-
| 0.
|
| 113 |
-
| 0.
|
| 114 |
|
| 115 |
|
| 116 |
### Framework versions
|
|
|
|
| 16 |
|
| 17 |
This model is a fine-tuned version of [deepseek-ai/deepseek-coder-6.7b-base](https://huggingface.co/deepseek-ai/deepseek-coder-6.7b-base) on an unknown dataset.
|
| 18 |
It achieves the following results on the evaluation set:
|
| 19 |
+
- Loss: 0.1382
|
| 20 |
|
| 21 |
## Model description
|
| 22 |
|
|
|
|
| 52 |
|
| 53 |
| Training Loss | Epoch | Step | Validation Loss |
|
| 54 |
|:-------------:|:-------:|:-----:|:---------------:|
|
| 55 |
+
| 0.2943 | 0.2001 | 720 | 0.2140 |
|
| 56 |
+
| 0.1986 | 0.4001 | 1440 | 0.1763 |
|
| 57 |
+
| 0.1686 | 0.6002 | 2160 | 0.1616 |
|
| 58 |
+
| 0.1577 | 0.8002 | 2880 | 0.1504 |
|
| 59 |
+
| 0.1477 | 1.0003 | 3600 | 0.1454 |
|
| 60 |
+
| 0.1318 | 1.2003 | 4320 | 0.1396 |
|
| 61 |
+
| 0.1269 | 1.4004 | 5040 | 0.1409 |
|
| 62 |
+
| 0.1263 | 1.6004 | 5760 | 0.1312 |
|
| 63 |
+
| 0.1258 | 1.8005 | 6480 | 0.1292 |
|
| 64 |
+
| 0.1201 | 2.0006 | 7200 | 0.1226 |
|
| 65 |
+
| 0.108 | 2.2006 | 7920 | 0.1280 |
|
| 66 |
+
| 0.1055 | 2.4007 | 8640 | 0.1271 |
|
| 67 |
+
| 0.1033 | 2.6007 | 9360 | 0.1222 |
|
| 68 |
+
| 0.1042 | 2.8008 | 10080 | 0.1169 |
|
| 69 |
+
| 0.1032 | 3.0008 | 10800 | 0.1154 |
|
| 70 |
+
| 0.0874 | 3.2009 | 11520 | 0.1194 |
|
| 71 |
+
| 0.0902 | 3.4009 | 12240 | 0.1132 |
|
| 72 |
+
| 0.0891 | 3.6010 | 12960 | 0.1170 |
|
| 73 |
+
| 0.0878 | 3.8011 | 13680 | 0.1136 |
|
| 74 |
+
| 0.088 | 4.0011 | 14400 | 0.1111 |
|
| 75 |
+
| 0.0754 | 4.2012 | 15120 | 0.1146 |
|
| 76 |
+
| 0.076 | 4.4012 | 15840 | 0.1115 |
|
| 77 |
+
| 0.0762 | 4.6013 | 16560 | 0.1125 |
|
| 78 |
+
| 0.0771 | 4.8013 | 17280 | 0.1065 |
|
| 79 |
+
| 0.0749 | 5.0014 | 18000 | 0.1085 |
|
| 80 |
+
| 0.0642 | 5.2014 | 18720 | 0.1124 |
|
| 81 |
+
| 0.0649 | 5.4015 | 19440 | 0.1092 |
|
| 82 |
+
| 0.0656 | 5.6016 | 20160 | 0.1073 |
|
| 83 |
+
| 0.0673 | 5.8016 | 20880 | 0.1055 |
|
| 84 |
+
| 0.065 | 6.0017 | 21600 | 0.1046 |
|
| 85 |
+
| 0.0565 | 6.2017 | 22320 | 0.1111 |
|
| 86 |
+
| 0.0566 | 6.4018 | 23040 | 0.1106 |
|
| 87 |
+
| 0.0567 | 6.6018 | 23760 | 0.1132 |
|
| 88 |
+
| 0.057 | 6.8019 | 24480 | 0.1066 |
|
| 89 |
+
| 0.0564 | 7.0019 | 25200 | 0.1074 |
|
| 90 |
+
| 0.049 | 7.2020 | 25920 | 0.1171 |
|
| 91 |
+
| 0.0478 | 7.4021 | 26640 | 0.1096 |
|
| 92 |
+
| 0.0481 | 7.6021 | 27360 | 0.1151 |
|
| 93 |
+
| 0.0483 | 7.8022 | 28080 | 0.1063 |
|
| 94 |
+
| 0.0487 | 8.0022 | 28800 | 0.1124 |
|
| 95 |
+
| 0.0411 | 8.2023 | 29520 | 0.1167 |
|
| 96 |
+
| 0.0398 | 8.4023 | 30240 | 0.1151 |
|
| 97 |
+
| 0.0401 | 8.6024 | 30960 | 0.1173 |
|
| 98 |
+
| 0.0411 | 8.8024 | 31680 | 0.1139 |
|
| 99 |
+
| 0.0399 | 9.0025 | 32400 | 0.1134 |
|
| 100 |
+
| 0.0333 | 9.2026 | 33120 | 0.1223 |
|
| 101 |
+
| 0.034 | 9.4026 | 33840 | 0.1184 |
|
| 102 |
+
| 0.0345 | 9.6027 | 34560 | 0.1249 |
|
| 103 |
+
| 0.0352 | 9.8027 | 35280 | 0.1201 |
|
| 104 |
+
| 0.0338 | 10.0028 | 36000 | 0.1183 |
|
| 105 |
+
| 0.0288 | 10.2028 | 36720 | 0.1291 |
|
| 106 |
+
| 0.0283 | 10.4029 | 37440 | 0.1312 |
|
| 107 |
+
| 0.0288 | 10.6029 | 38160 | 0.1287 |
|
| 108 |
+
| 0.0289 | 10.8030 | 38880 | 0.1264 |
|
| 109 |
+
| 0.0299 | 11.0031 | 39600 | 0.1309 |
|
| 110 |
+
| 0.0259 | 11.2031 | 40320 | 0.1409 |
|
| 111 |
+
| 0.0254 | 11.4032 | 41040 | 0.1382 |
|
| 112 |
+
| 0.0252 | 11.6032 | 41760 | 0.1400 |
|
| 113 |
+
| 0.0254 | 11.8033 | 42480 | 0.1382 |
|
| 114 |
|
| 115 |
|
| 116 |
### Framework versions
|