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.
|
| 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 |
|
| 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: 0.1322
|
| 20 |
|
| 21 |
## Model description
|
| 22 |
|
|
|
|
| 52 |
|
| 53 |
| Training Loss | Epoch | Step | Validation Loss |
|
| 54 |
|:-------------:|:-------:|:-----:|:---------------:|
|
| 55 |
+
| 0.2967 | 0.2001 | 720 | 0.1984 |
|
| 56 |
+
| 0.1959 | 0.4001 | 1440 | 0.1738 |
|
| 57 |
+
| 0.1636 | 0.6002 | 2160 | 0.1623 |
|
| 58 |
+
| 0.1539 | 0.8002 | 2880 | 0.1537 |
|
| 59 |
+
| 0.1384 | 1.0003 | 3600 | 0.1512 |
|
| 60 |
+
| 0.1317 | 1.2003 | 4320 | 0.1433 |
|
| 61 |
+
| 0.1237 | 1.4004 | 5040 | 0.1368 |
|
| 62 |
+
| 0.1174 | 1.6004 | 5760 | 0.1396 |
|
| 63 |
+
| 0.1178 | 1.8005 | 6480 | 0.1316 |
|
| 64 |
+
| 0.1134 | 2.0006 | 7200 | 0.1312 |
|
| 65 |
+
| 0.1075 | 2.2006 | 7920 | 0.1269 |
|
| 66 |
+
| 0.1018 | 2.4007 | 8640 | 0.1254 |
|
| 67 |
+
| 0.1018 | 2.6007 | 9360 | 0.1270 |
|
| 68 |
+
| 0.0931 | 2.8008 | 10080 | 0.1249 |
|
| 69 |
+
| 0.0924 | 3.0008 | 10800 | 0.1218 |
|
| 70 |
+
| 0.0897 | 3.2009 | 11520 | 0.1216 |
|
| 71 |
+
| 0.0868 | 3.4009 | 12240 | 0.1241 |
|
| 72 |
+
| 0.0865 | 3.6010 | 12960 | 0.1148 |
|
| 73 |
+
| 0.084 | 3.8011 | 13680 | 0.1159 |
|
| 74 |
+
| 0.0815 | 4.0011 | 14400 | 0.1176 |
|
| 75 |
+
| 0.0753 | 4.2012 | 15120 | 0.1139 |
|
| 76 |
+
| 0.0762 | 4.4012 | 15840 | 0.1140 |
|
| 77 |
+
| 0.074 | 4.6013 | 16560 | 0.1131 |
|
| 78 |
+
| 0.0732 | 4.8013 | 17280 | 0.1108 |
|
| 79 |
+
| 0.0685 | 5.0014 | 18000 | 0.1152 |
|
| 80 |
+
| 0.0655 | 5.2014 | 18720 | 0.1140 |
|
| 81 |
+
| 0.0664 | 5.4015 | 19440 | 0.1120 |
|
| 82 |
+
| 0.0648 | 5.6016 | 20160 | 0.1131 |
|
| 83 |
+
| 0.063 | 5.8016 | 20880 | 0.1125 |
|
| 84 |
+
| 0.0609 | 6.0017 | 21600 | 0.1141 |
|
| 85 |
+
| 0.0576 | 6.2017 | 22320 | 0.1105 |
|
| 86 |
+
| 0.0572 | 6.4018 | 23040 | 0.1143 |
|
| 87 |
+
| 0.0554 | 6.6018 | 23760 | 0.1115 |
|
| 88 |
+
| 0.0538 | 6.8019 | 24480 | 0.1113 |
|
| 89 |
+
| 0.052 | 7.0019 | 25200 | 0.1132 |
|
| 90 |
+
| 0.0498 | 7.2020 | 25920 | 0.1132 |
|
| 91 |
+
| 0.0485 | 7.4021 | 26640 | 0.1115 |
|
| 92 |
+
| 0.0483 | 7.6021 | 27360 | 0.1115 |
|
| 93 |
+
| 0.0469 | 7.8022 | 28080 | 0.1126 |
|
| 94 |
+
| 0.0443 | 8.0022 | 28800 | 0.1134 |
|
| 95 |
+
| 0.0421 | 8.2023 | 29520 | 0.1150 |
|
| 96 |
+
| 0.0411 | 8.4023 | 30240 | 0.1144 |
|
| 97 |
+
| 0.0412 | 8.6024 | 30960 | 0.1117 |
|
| 98 |
+
| 0.0391 | 8.8024 | 31680 | 0.1127 |
|
| 99 |
+
| 0.0403 | 9.0025 | 32400 | 0.1162 |
|
| 100 |
+
| 0.0354 | 9.2026 | 33120 | 0.1193 |
|
| 101 |
+
| 0.0354 | 9.4026 | 33840 | 0.1218 |
|
| 102 |
+
| 0.0352 | 9.6027 | 34560 | 0.1196 |
|
| 103 |
+
| 0.0356 | 9.8027 | 35280 | 0.1236 |
|
| 104 |
+
| 0.0331 | 10.0028 | 36000 | 0.1234 |
|
| 105 |
+
| 0.032 | 10.2028 | 36720 | 0.1265 |
|
| 106 |
+
| 0.0302 | 10.4029 | 37440 | 0.1289 |
|
| 107 |
+
| 0.0301 | 10.6029 | 38160 | 0.1280 |
|
| 108 |
+
| 0.0295 | 10.8030 | 38880 | 0.1259 |
|
| 109 |
+
| 0.028 | 11.0031 | 39600 | 0.1295 |
|
| 110 |
+
| 0.0274 | 11.2031 | 40320 | 0.1308 |
|
| 111 |
+
| 0.0271 | 11.4032 | 41040 | 0.1309 |
|
| 112 |
+
| 0.0267 | 11.6032 | 41760 | 0.1339 |
|
| 113 |
+
| 0.0259 | 11.8033 | 42480 | 0.1322 |
|
| 114 |
|
| 115 |
|
| 116 |
### Framework versions
|