Hugging Face's logo

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

PEFT
Safetensors
Generated from Trainer
Model card Files Community
yalhessi commited on
Commit
2aad502
·
verified ·
1 Parent(s): a968dcc

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: 0.1670
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
- | 0.4274 | 0.2002 | 721 | 0.3223 |
56
- | 0.3241 | 0.4003 | 1442 | 0.2921 |
57
- | 0.2842 | 0.6005 | 2163 | 0.2797 |
58
- | 0.2777 | 0.8007 | 2884 | 0.2683 |
59
- | 0.2625 | 1.0008 | 3605 | 0.2475 |
60
- | 0.2482 | 1.2010 | 4326 | 0.2520 |
61
- | 0.246 | 1.4012 | 5047 | 0.2444 |
62
- | 0.2384 | 1.6013 | 5768 | 0.2386 |
63
- | 0.235 | 1.8015 | 6489 | 0.2374 |
64
- | 0.2321 | 2.0017 | 7210 | 0.2268 |
65
- | 0.2214 | 2.2018 | 7931 | 0.2185 |
66
- | 0.2202 | 2.4020 | 8652 | 0.2244 |
67
- | 0.2173 | 2.6022 | 9373 | 0.2196 |
68
- | 0.2157 | 2.8023 | 10094 | 0.2204 |
69
- | 0.2132 | 3.0025 | 10815 | 0.2144 |
70
- | 0.2008 | 3.2027 | 11536 | 0.2107 |
71
- | 0.1998 | 3.4028 | 12257 | 0.2060 |
72
- | 0.1988 | 3.6030 | 12978 | 0.2052 |
73
- | 0.197 | 3.8032 | 13699 | 0.2057 |
74
- | 0.1966 | 4.0033 | 14420 | 0.2042 |
75
- | 0.1835 | 4.2035 | 15141 | 0.1965 |
76
- | 0.1834 | 4.4037 | 15862 | 0.1964 |
77
- | 0.1828 | 4.6038 | 16583 | 0.1929 |
78
- | 0.1833 | 4.8040 | 17304 | 0.1939 |
79
- | 0.1826 | 5.0042 | 18025 | 0.1907 |
80
- | 0.1688 | 5.2043 | 18746 | 0.1891 |
81
- | 0.1695 | 5.4045 | 19467 | 0.1891 |
82
- | 0.1682 | 5.6047 | 20188 | 0.1889 |
83
- | 0.1702 | 5.8048 | 20909 | 0.1861 |
84
- | 0.1672 | 6.0050 | 21630 | 0.1856 |
85
- | 0.157 | 6.2052 | 22351 | 0.1853 |
86
- | 0.1559 | 6.4053 | 23072 | 0.1874 |
87
- | 0.1564 | 6.6055 | 23793 | 0.1802 |
88
- | 0.1572 | 6.8057 | 24514 | 0.1761 |
89
- | 0.1544 | 7.0058 | 25235 | 0.1770 |
90
- | 0.1462 | 7.2060 | 25956 | 0.1777 |
91
- | 0.1436 | 7.4062 | 26677 | 0.1752 |
92
- | 0.1431 | 7.6063 | 27398 | 0.1713 |
93
- | 0.1412 | 7.8065 | 28119 | 0.1725 |
94
- | 0.1413 | 8.0067 | 28840 | 0.1716 |
95
- | 0.1276 | 8.2068 | 29561 | 0.1714 |
96
- | 0.1296 | 8.4070 | 30282 | 0.1694 |
97
- | 0.1286 | 8.6072 | 31003 | 0.1682 |
98
- | 0.1298 | 8.8073 | 31724 | 0.1632 |
99
- | 0.1285 | 9.0075 | 32445 | 0.1647 |
100
- | 0.1159 | 9.2077 | 33166 | 0.1655 |
101
- | 0.1136 | 9.4078 | 33887 | 0.1658 |
102
- | 0.1158 | 9.6080 | 34608 | 0.1617 |
103
- | 0.1146 | 9.8082 | 35329 | 0.1634 |
104
- | 0.1152 | 10.0083 | 36050 | 0.1632 |
105
- | 0.1016 | 10.2085 | 36771 | 0.1677 |
106
- | 0.1006 | 10.4087 | 37492 | 0.1610 |
107
- | 0.1016 | 10.6088 | 38213 | 0.1606 |
108
- | 0.1022 | 10.8090 | 38934 | 0.1609 |
109
- | 0.1003 | 11.0092 | 39655 | 0.1645 |
110
- | 0.093 | 11.2093 | 40376 | 0.1672 |
111
- | 0.0909 | 11.4095 | 41097 | 0.1678 |
112
- | 0.0908 | 11.6097 | 41818 | 0.1680 |
113
- | 0.091 | 11.8098 | 42539 | 0.1670 |
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: 0.1711
20
 
21
  ## Model description
22
 
 
52
 
53
  | Training Loss | Epoch | Step | Validation Loss |
54
  |:-------------:|:-------:|:-----:|:---------------:|
55
+ | 0.4293 | 0.2001 | 720 | 0.3388 |
56
+ | 0.324 | 0.4001 | 1440 | 0.2977 |
57
+ | 0.282 | 0.6002 | 2160 | 0.2814 |
58
+ | 0.2707 | 0.8002 | 2880 | 0.2713 |
59
+ | 0.2595 | 1.0003 | 3600 | 0.2822 |
60
+ | 0.2434 | 1.2003 | 4320 | 0.2586 |
61
+ | 0.2403 | 1.4004 | 5040 | 0.2458 |
62
+ | 0.2355 | 1.6004 | 5760 | 0.2513 |
63
+ | 0.2342 | 1.8005 | 6480 | 0.2404 |
64
+ | 0.2284 | 2.0006 | 7200 | 0.2346 |
65
+ | 0.2176 | 2.2006 | 7920 | 0.2339 |
66
+ | 0.2148 | 2.4007 | 8640 | 0.2315 |
67
+ | 0.2127 | 2.6007 | 9360 | 0.2236 |
68
+ | 0.2108 | 2.8008 | 10080 | 0.2300 |
69
+ | 0.2124 | 3.0008 | 10800 | 0.2186 |
70
+ | 0.1962 | 3.2009 | 11520 | 0.2232 |
71
+ | 0.1993 | 3.4009 | 12240 | 0.2160 |
72
+ | 0.1944 | 3.6010 | 12960 | 0.2141 |
73
+ | 0.1945 | 3.8011 | 13680 | 0.2150 |
74
+ | 0.1934 | 4.0011 | 14400 | 0.2132 |
75
+ | 0.182 | 4.2012 | 15120 | 0.2050 |
76
+ | 0.1817 | 4.4012 | 15840 | 0.2079 |
77
+ | 0.1809 | 4.6013 | 16560 | 0.2013 |
78
+ | 0.1805 | 4.8013 | 17280 | 0.2045 |
79
+ | 0.1768 | 5.0014 | 18000 | 0.1979 |
80
+ | 0.1661 | 5.2014 | 18720 | 0.1919 |
81
+ | 0.1673 | 5.4015 | 19440 | 0.1962 |
82
+ | 0.1679 | 5.6016 | 20160 | 0.1925 |
83
+ | 0.168 | 5.8016 | 20880 | 0.1873 |
84
+ | 0.1623 | 6.0017 | 21600 | 0.1869 |
85
+ | 0.155 | 6.2017 | 22320 | 0.1875 |
86
+ | 0.1551 | 6.4018 | 23040 | 0.1869 |
87
+ | 0.1521 | 6.6018 | 23760 | 0.1870 |
88
+ | 0.1536 | 6.8019 | 24480 | 0.1816 |
89
+ | 0.1506 | 7.0019 | 25200 | 0.1825 |
90
+ | 0.1417 | 7.2020 | 25920 | 0.1867 |
91
+ | 0.1405 | 7.4021 | 26640 | 0.1795 |
92
+ | 0.1409 | 7.6021 | 27360 | 0.1808 |
93
+ | 0.1384 | 7.8022 | 28080 | 0.1754 |
94
+ | 0.1409 | 8.0022 | 28800 | 0.1767 |
95
+ | 0.1271 | 8.2023 | 29520 | 0.1753 |
96
+ | 0.1258 | 8.4023 | 30240 | 0.1742 |
97
+ | 0.1279 | 8.6024 | 30960 | 0.1737 |
98
+ | 0.126 | 8.8024 | 31680 | 0.1709 |
99
+ | 0.1255 | 9.0025 | 32400 | 0.1688 |
100
+ | 0.1138 | 9.2026 | 33120 | 0.1734 |
101
+ | 0.1134 | 9.4026 | 33840 | 0.1709 |
102
+ | 0.1149 | 9.6027 | 34560 | 0.1697 |
103
+ | 0.1143 | 9.8027 | 35280 | 0.1681 |
104
+ | 0.1106 | 10.0028 | 36000 | 0.1651 |
105
+ | 0.1011 | 10.2028 | 36720 | 0.1698 |
106
+ | 0.1004 | 10.4029 | 37440 | 0.1672 |
107
+ | 0.1003 | 10.6029 | 38160 | 0.1698 |
108
+ | 0.1004 | 10.8030 | 38880 | 0.1681 |
109
+ | 0.0999 | 11.0031 | 39600 | 0.1660 |
110
+ | 0.091 | 11.2031 | 40320 | 0.1721 |
111
+ | 0.0901 | 11.4032 | 41040 | 0.1714 |
112
+ | 0.0886 | 11.6032 | 41760 | 0.1719 |
113
+ | 0.0885 | 11.8033 | 42480 | 0.1711 |
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 sha256:3b0568097bd1b8a31419e9bf94282284664346c00975d94673ba7ff0aaafc875
3
  size 268636736
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c4e0d964e61bef2f25d4ec5482f38d22dc99bebb79a3eb9a212b74b99cec97d5
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:b7a39810d611461bc058286831a7f0e062684f7159a0f69ef31ddf3c680834d2
3
  size 5496
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4f5bcdae8ea427792167f70b303e168b00e1461e1f0e5c290f33e3344f197a23
3
  size 5496