Hugging Face's logo

yalhessi
/
lemexp-task1-v2-template_small-deepseek-coder-1.3b-base-ddp-8lr-v2

PEFT
Safetensors
Generated from Trainer
Model card Files Community
yalhessi commited on
Commit
774b5f3
·
verified ·
1 Parent(s): 51ad510

End of training

Browse files
Files changed (5) hide show
  1. README.md +60 -60
  2. adapter_config.json +2 -2
  3. adapter_model.safetensors +1 -1
  4. loss_plot.png +0 -0
  5. training_args.bin +1 -1
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: 0.1536
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
- | 0.4023 | 0.2002 | 721 | 0.2979 |
56
- | 0.2974 | 0.4003 | 1442 | 0.2705 |
57
- | 0.2625 | 0.6005 | 2163 | 0.2579 |
58
- | 0.2578 | 0.8007 | 2884 | 0.2518 |
59
- | 0.2454 | 1.0008 | 3605 | 0.2368 |
60
- | 0.2309 | 1.2010 | 4326 | 0.2288 |
61
- | 0.228 | 1.4012 | 5047 | 0.2253 |
62
- | 0.223 | 1.6013 | 5768 | 0.2217 |
63
- | 0.2221 | 1.8015 | 6489 | 0.2268 |
64
- | 0.2181 | 2.0017 | 7210 | 0.2157 |
65
- | 0.2081 | 2.2018 | 7931 | 0.2147 |
66
- | 0.2079 | 2.4020 | 8652 | 0.2112 |
67
- | 0.204 | 2.6022 | 9373 | 0.2052 |
68
- | 0.2019 | 2.8023 | 10094 | 0.2038 |
69
- | 0.2002 | 3.0025 | 10815 | 0.2045 |
70
- | 0.1909 | 3.2027 | 11536 | 0.1983 |
71
- | 0.1883 | 3.4028 | 12257 | 0.1964 |
72
- | 0.1874 | 3.6030 | 12978 | 0.2010 |
73
- | 0.1858 | 3.8032 | 13699 | 0.1928 |
74
- | 0.1859 | 4.0033 | 14420 | 0.1917 |
75
- | 0.1738 | 4.2035 | 15141 | 0.1931 |
76
- | 0.1734 | 4.4037 | 15862 | 0.1876 |
77
- | 0.1738 | 4.6038 | 16583 | 0.1848 |
78
- | 0.1746 | 4.8040 | 17304 | 0.1816 |
79
- | 0.1728 | 5.0042 | 18025 | 0.1800 |
80
- | 0.1601 | 5.2043 | 18746 | 0.1832 |
81
- | 0.1612 | 5.4045 | 19467 | 0.1799 |
82
- | 0.1594 | 5.6047 | 20188 | 0.1806 |
83
- | 0.1598 | 5.8048 | 20909 | 0.1768 |
84
- | 0.1595 | 6.0050 | 21630 | 0.1819 |
85
- | 0.15 | 6.2052 | 22351 | 0.1725 |
86
- | 0.1488 | 6.4053 | 23072 | 0.1727 |
87
- | 0.1489 | 6.6055 | 23793 | 0.1706 |
88
- | 0.1487 | 6.8057 | 24514 | 0.1700 |
89
- | 0.1475 | 7.0058 | 25235 | 0.1676 |
90
- | 0.1392 | 7.2060 | 25956 | 0.1658 |
91
- | 0.1375 | 7.4062 | 26677 | 0.1641 |
92
- | 0.1358 | 7.6063 | 27398 | 0.1639 |
93
- | 0.1347 | 7.8065 | 28119 | 0.1613 |
94
- | 0.135 | 8.0067 | 28840 | 0.1595 |
95
- | 0.1223 | 8.2068 | 29561 | 0.1608 |
96
- | 0.1239 | 8.4070 | 30282 | 0.1580 |
97
- | 0.1224 | 8.6072 | 31003 | 0.1562 |
98
- | 0.1234 | 8.8073 | 31724 | 0.1570 |
99
- | 0.1224 | 9.0075 | 32445 | 0.1555 |
100
- | 0.1094 | 9.2077 | 33166 | 0.1561 |
101
- | 0.1088 | 9.4078 | 33887 | 0.1552 |
102
- | 0.1106 | 9.6080 | 34608 | 0.1528 |
103
- | 0.1097 | 9.8082 | 35329 | 0.1520 |
104
- | 0.1101 | 10.0083 | 36050 | 0.1533 |
105
- | 0.0971 | 10.2085 | 36771 | 0.1566 |
106
- | 0.0965 | 10.4087 | 37492 | 0.1528 |
107
- | 0.0975 | 10.6088 | 38213 | 0.1529 |
108
- | 0.0975 | 10.8090 | 38934 | 0.1517 |
109
- | 0.0963 | 11.0092 | 39655 | 0.1528 |
110
- | 0.0887 | 11.2093 | 40376 | 0.1550 |
111
- | 0.0868 | 11.4095 | 41097 | 0.1550 |
112
- | 0.0874 | 11.6097 | 41818 | 0.1542 |
113
- | 0.087 | 11.8098 | 42539 | 0.1536 |
114
 
115
 
116
  ### Framework versions
 
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: 0.1630
20
 
21
  ## Model description
22
 
 
52
 
53
  | Training Loss | Epoch | Step | Validation Loss |
54
  |:-------------:|:-------:|:-----:|:---------------:|
55
+ | 0.3915 | 0.2001 | 720 | 0.3026 |
56
+ | 0.2875 | 0.4001 | 1440 | 0.2625 |
57
+ | 0.254 | 0.6002 | 2160 | 0.2493 |
58
+ | 0.2464 | 0.8002 | 2880 | 0.2448 |
59
+ | 0.2334 | 1.0003 | 3600 | 0.2371 |
60
+ | 0.2206 | 1.2003 | 4320 | 0.2485 |
61
+ | 0.2162 | 1.4004 | 5040 | 0.2268 |
62
+ | 0.2149 | 1.6004 | 5760 | 0.2221 |
63
+ | 0.2132 | 1.8005 | 6480 | 0.2160 |
64
+ | 0.2071 | 2.0006 | 7200 | 0.2112 |
65
+ | 0.1996 | 2.2006 | 7920 | 0.2102 |
66
+ | 0.1972 | 2.4007 | 8640 | 0.2123 |
67
+ | 0.1936 | 2.6007 | 9360 | 0.2065 |
68
+ | 0.1931 | 2.8008 | 10080 | 0.1994 |
69
+ | 0.1937 | 3.0008 | 10800 | 0.2040 |
70
+ | 0.1812 | 3.2009 | 11520 | 0.1981 |
71
+ | 0.1849 | 3.4009 | 12240 | 0.2016 |
72
+ | 0.1791 | 3.6010 | 12960 | 0.2017 |
73
+ | 0.1785 | 3.8011 | 13680 | 0.1919 |
74
+ | 0.1784 | 4.0011 | 14400 | 0.1907 |
75
+ | 0.1683 | 4.2012 | 15120 | 0.1929 |
76
+ | 0.1697 | 4.4012 | 15840 | 0.1862 |
77
+ | 0.1658 | 4.6013 | 16560 | 0.1837 |
78
+ | 0.1673 | 4.8013 | 17280 | 0.1918 |
79
+ | 0.1641 | 5.0014 | 18000 | 0.1847 |
80
+ | 0.1549 | 5.2014 | 18720 | 0.1813 |
81
+ | 0.1542 | 5.4015 | 19440 | 0.1885 |
82
+ | 0.1561 | 5.6016 | 20160 | 0.1792 |
83
+ | 0.1569 | 5.8016 | 20880 | 0.1751 |
84
+ | 0.1513 | 6.0017 | 21600 | 0.1710 |
85
+ | 0.143 | 6.2017 | 22320 | 0.1737 |
86
+ | 0.1443 | 6.4018 | 23040 | 0.1725 |
87
+ | 0.1422 | 6.6018 | 23760 | 0.1689 |
88
+ | 0.1444 | 6.8019 | 24480 | 0.1668 |
89
+ | 0.1406 | 7.0019 | 25200 | 0.1649 |
90
+ | 0.1325 | 7.2020 | 25920 | 0.1691 |
91
+ | 0.1312 | 7.4021 | 26640 | 0.1656 |
92
+ | 0.1307 | 7.6021 | 27360 | 0.1629 |
93
+ | 0.1288 | 7.8022 | 28080 | 0.1638 |
94
+ | 0.131 | 8.0022 | 28800 | 0.1632 |
95
+ | 0.1201 | 8.2023 | 29520 | 0.1647 |
96
+ | 0.1179 | 8.4023 | 30240 | 0.1626 |
97
+ | 0.1188 | 8.6024 | 30960 | 0.1619 |
98
+ | 0.1176 | 8.8024 | 31680 | 0.1569 |
99
+ | 0.1182 | 9.0025 | 32400 | 0.1578 |
100
+ | 0.1067 | 9.2026 | 33120 | 0.1634 |
101
+ | 0.1071 | 9.4026 | 33840 | 0.1586 |
102
+ | 0.1075 | 9.6027 | 34560 | 0.1557 |
103
+ | 0.1067 | 9.8027 | 35280 | 0.1536 |
104
+ | 0.1038 | 10.0028 | 36000 | 0.1572 |
105
+ | 0.0954 | 10.2028 | 36720 | 0.1634 |
106
+ | 0.0949 | 10.4029 | 37440 | 0.1577 |
107
+ | 0.0944 | 10.6029 | 38160 | 0.1591 |
108
+ | 0.0944 | 10.8030 | 38880 | 0.1575 |
109
+ | 0.0943 | 11.0031 | 39600 | 0.1551 |
110
+ | 0.0855 | 11.2031 | 40320 | 0.1632 |
111
+ | 0.0848 | 11.4032 | 41040 | 0.1618 |
112
+ | 0.0841 | 11.6032 | 41760 | 0.1619 |
113
+ | 0.0838 | 11.8033 | 42480 | 0.1630 |
114
 
115
 
116
  ### Framework versions
adapter_config.json CHANGED
@@ -23,8 +23,8 @@
23
  "rank_pattern": {},
24
  "revision": null,
25
  "target_modules": [
26
- "q_proj",
27
- "v_proj"
28
  ],
29
  "task_type": "CAUSAL_LM",
30
  "use_dora": false,
 
23
  "rank_pattern": {},
24
  "revision": null,
25
  "target_modules": [
26
+ "v_proj",
27
+ "q_proj"
28
  ],
29
  "task_type": "CAUSAL_LM",
30
  "use_dora": false,
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c6b7bddf56a74eeb33351b218e3010c35fb8d7771e80d3036cd605bcc1b7ded1
3
  size 268636736
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:97c049090eea2cbad7cdc0dd73e8697fdc46839dab4a18567297e387a47daa47
3
  size 268636736
loss_plot.png CHANGED
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3e44d825022f113ffd7084c31206e840ebe19e783c79aeb9ee3eb0c738fa0ade
3
  size 5496
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:325068971071c30e530f499c3c961b8adb72f367a67b1b2705d6036469313349
3
  size 5496