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-1.3b-base](https://huggingface.co/deepseek-ai/deepseek-coder-1.3b-base) on an unknown dataset.
|
| 18 |
It achieves the following results on the evaluation set:
|
| 19 |
-
- Loss: 0.
|
| 20 |
|
| 21 |
## Model description
|
| 22 |
|
|
@@ -52,71 +52,71 @@ 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
|
| 117 |
|
| 118 |
-
- PEFT 0.
|
| 119 |
-
- Transformers 4.
|
| 120 |
-
- Pytorch 2.
|
| 121 |
-
- Datasets 4.
|
| 122 |
-
- Tokenizers 0.
|
|
|
|
| 16 |
|
| 17 |
This model is a fine-tuned version of [deepseek-ai/deepseek-coder-1.3b-base](https://huggingface.co/deepseek-ai/deepseek-coder-1.3b-base) on an unknown dataset.
|
| 18 |
It achieves the following results on the evaluation set:
|
| 19 |
+
- Loss: 0.1539
|
| 20 |
|
| 21 |
## Model description
|
| 22 |
|
|
|
|
| 52 |
|
| 53 |
| Training Loss | Epoch | Step | Validation Loss |
|
| 54 |
|:-------------:|:-------:|:-----:|:---------------:|
|
| 55 |
+
| 0.377 | 0.2001 | 720 | 0.2894 |
|
| 56 |
+
| 0.2824 | 0.4001 | 1440 | 0.2605 |
|
| 57 |
+
| 0.2488 | 0.6002 | 2160 | 0.2486 |
|
| 58 |
+
| 0.2424 | 0.8002 | 2880 | 0.2434 |
|
| 59 |
+
| 0.2307 | 1.0003 | 3600 | 0.2332 |
|
| 60 |
+
| 0.2171 | 1.2003 | 4320 | 0.2317 |
|
| 61 |
+
| 0.215 | 1.4004 | 5040 | 0.2200 |
|
| 62 |
+
| 0.2101 | 1.6004 | 5760 | 0.2177 |
|
| 63 |
+
| 0.209 | 1.8005 | 6480 | 0.2163 |
|
| 64 |
+
| 0.2047 | 2.0006 | 7200 | 0.2175 |
|
| 65 |
+
| 0.1972 | 2.2006 | 7920 | 0.2108 |
|
| 66 |
+
| 0.1934 | 2.4007 | 8640 | 0.2045 |
|
| 67 |
+
| 0.1906 | 2.6007 | 9360 | 0.1991 |
|
| 68 |
+
| 0.1889 | 2.8008 | 10080 | 0.2008 |
|
| 69 |
+
| 0.1911 | 3.0008 | 10800 | 0.2007 |
|
| 70 |
+
| 0.1789 | 3.2009 | 11520 | 0.1973 |
|
| 71 |
+
| 0.1799 | 3.4009 | 12240 | 0.1947 |
|
| 72 |
+
| 0.1769 | 3.6010 | 12960 | 0.1933 |
|
| 73 |
+
| 0.176 | 3.8011 | 13680 | 0.1897 |
|
| 74 |
+
| 0.1753 | 4.0011 | 14400 | 0.1833 |
|
| 75 |
+
| 0.1645 | 4.2012 | 15120 | 0.1833 |
|
| 76 |
+
| 0.1684 | 4.4012 | 15840 | 0.1864 |
|
| 77 |
+
| 0.1626 | 4.6013 | 16560 | 0.1839 |
|
| 78 |
+
| 0.1649 | 4.8013 | 17280 | 0.1761 |
|
| 79 |
+
| 0.1613 | 5.0014 | 18000 | 0.1803 |
|
| 80 |
+
| 0.1523 | 5.2014 | 18720 | 0.1755 |
|
| 81 |
+
| 0.1531 | 5.4015 | 19440 | 0.1766 |
|
| 82 |
+
| 0.1539 | 5.6016 | 20160 | 0.1726 |
|
| 83 |
+
| 0.1527 | 5.8016 | 20880 | 0.1778 |
|
| 84 |
+
| 0.1483 | 6.0017 | 21600 | 0.1640 |
|
| 85 |
+
| 0.1404 | 6.2017 | 22320 | 0.1684 |
|
| 86 |
+
| 0.1426 | 6.4018 | 23040 | 0.1666 |
|
| 87 |
+
| 0.1407 | 6.6018 | 23760 | 0.1650 |
|
| 88 |
+
| 0.1413 | 6.8019 | 24480 | 0.1635 |
|
| 89 |
+
| 0.1386 | 7.0019 | 25200 | 0.1640 |
|
| 90 |
+
| 0.1307 | 7.2020 | 25920 | 0.1627 |
|
| 91 |
+
| 0.1291 | 7.4021 | 26640 | 0.1620 |
|
| 92 |
+
| 0.1293 | 7.6021 | 27360 | 0.1626 |
|
| 93 |
+
| 0.128 | 7.8022 | 28080 | 0.1584 |
|
| 94 |
+
| 0.1288 | 8.0022 | 28800 | 0.1580 |
|
| 95 |
+
| 0.1182 | 8.2023 | 29520 | 0.1571 |
|
| 96 |
+
| 0.1166 | 8.4023 | 30240 | 0.1539 |
|
| 97 |
+
| 0.1178 | 8.6024 | 30960 | 0.1571 |
|
| 98 |
+
| 0.1154 | 8.8024 | 31680 | 0.1547 |
|
| 99 |
+
| 0.1163 | 9.0025 | 32400 | 0.1549 |
|
| 100 |
+
| 0.1056 | 9.2026 | 33120 | 0.1567 |
|
| 101 |
+
| 0.1046 | 9.4026 | 33840 | 0.1526 |
|
| 102 |
+
| 0.1063 | 9.6027 | 34560 | 0.1542 |
|
| 103 |
+
| 0.1063 | 9.8027 | 35280 | 0.1481 |
|
| 104 |
+
| 0.1022 | 10.0028 | 36000 | 0.1518 |
|
| 105 |
+
| 0.0939 | 10.2028 | 36720 | 0.1546 |
|
| 106 |
+
| 0.0933 | 10.4029 | 37440 | 0.1507 |
|
| 107 |
+
| 0.0933 | 10.6029 | 38160 | 0.1510 |
|
| 108 |
+
| 0.0927 | 10.8030 | 38880 | 0.1494 |
|
| 109 |
+
| 0.0938 | 11.0031 | 39600 | 0.1498 |
|
| 110 |
+
| 0.085 | 11.2031 | 40320 | 0.1557 |
|
| 111 |
+
| 0.0839 | 11.4032 | 41040 | 0.1534 |
|
| 112 |
+
| 0.0828 | 11.6032 | 41760 | 0.1534 |
|
| 113 |
+
| 0.0829 | 11.8033 | 42480 | 0.1539 |
|
| 114 |
|
| 115 |
|
| 116 |
### Framework versions
|
| 117 |
|
| 118 |
+
- PEFT 0.14.0
|
| 119 |
+
- Transformers 4.47.0
|
| 120 |
+
- Pytorch 2.5.1+cu124
|
| 121 |
+
- Datasets 4.2.0
|
| 122 |
+
- Tokenizers 0.21.0
|