Hugging Face's logo

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

PEFT
Safetensors
Generated from Trainer
Model card Files
xet
Community
yalhessi commited on
Commit
e5b02a4
·
verified ·
1 Parent(s): ec63689

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 +2 -2
  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: 0.1641
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
- | 0.4654 | 0.2002 | 721 | 0.3459 |
56
- | 0.3418 | 0.4003 | 1442 | 0.3038 |
57
- | 0.2995 | 0.6005 | 2163 | 0.2974 |
58
- | 0.2913 | 0.8007 | 2884 | 0.2784 |
59
- | 0.2789 | 1.0008 | 3605 | 0.2618 |
60
- | 0.2612 | 1.2010 | 4326 | 0.2589 |
61
- | 0.2567 | 1.4012 | 5047 | 0.2588 |
62
- | 0.2497 | 1.6013 | 5768 | 0.2496 |
63
- | 0.2489 | 1.8015 | 6489 | 0.2469 |
64
- | 0.2433 | 2.0017 | 7210 | 0.2394 |
65
- | 0.2331 | 2.2018 | 7931 | 0.2335 |
66
- | 0.2306 | 2.4020 | 8652 | 0.2324 |
67
- | 0.2264 | 2.6022 | 9373 | 0.2260 |
68
- | 0.2246 | 2.8023 | 10094 | 0.2256 |
69
- | 0.2228 | 3.0025 | 10815 | 0.2260 |
70
- | 0.2102 | 3.2027 | 11536 | 0.2248 |
71
- | 0.2095 | 3.4028 | 12257 | 0.2184 |
72
- | 0.2069 | 3.6030 | 12978 | 0.2141 |
73
- | 0.2073 | 3.8032 | 13699 | 0.2108 |
74
- | 0.2056 | 4.0033 | 14420 | 0.2149 |
75
- | 0.1934 | 4.2035 | 15141 | 0.2076 |
76
- | 0.193 | 4.4037 | 15862 | 0.2010 |
77
- | 0.1928 | 4.6038 | 16583 | 0.2015 |
78
- | 0.1913 | 4.8040 | 17304 | 0.2023 |
79
- | 0.1907 | 5.0042 | 18025 | 0.1996 |
80
- | 0.1772 | 5.2043 | 18746 | 0.1973 |
81
- | 0.1794 | 5.4045 | 19467 | 0.1952 |
82
- | 0.1769 | 5.6047 | 20188 | 0.1928 |
83
- | 0.1781 | 5.8048 | 20909 | 0.1935 |
84
- | 0.1752 | 6.0050 | 21630 | 0.1901 |
85
- | 0.1654 | 6.2052 | 22351 | 0.1933 |
86
- | 0.1644 | 6.4053 | 23072 | 0.1909 |
87
- | 0.164 | 6.6055 | 23793 | 0.1839 |
88
- | 0.1639 | 6.8057 | 24514 | 0.1850 |
89
- | 0.1613 | 7.0058 | 25235 | 0.1812 |
90
- | 0.1533 | 7.2060 | 25956 | 0.1854 |
91
- | 0.1509 | 7.4062 | 26677 | 0.1779 |
92
- | 0.1498 | 7.6063 | 27398 | 0.1768 |
93
- | 0.148 | 7.8065 | 28119 | 0.1741 |
94
- | 0.1474 | 8.0067 | 28840 | 0.1720 |
95
- | 0.1343 | 8.2068 | 29561 | 0.1736 |
96
- | 0.1361 | 8.4070 | 30282 | 0.1754 |
97
- | 0.1355 | 8.6072 | 31003 | 0.1705 |
98
- | 0.1356 | 8.8073 | 31724 | 0.1675 |
99
- | 0.1346 | 9.0075 | 32445 | 0.1664 |
100
- | 0.1207 | 9.2077 | 33166 | 0.1702 |
101
- | 0.1194 | 9.4078 | 33887 | 0.1684 |
102
- | 0.1206 | 9.6080 | 34608 | 0.1632 |
103
- | 0.1202 | 9.8082 | 35329 | 0.1626 |
104
- | 0.1208 | 10.0083 | 36050 | 0.1663 |
105
- | 0.1065 | 10.2085 | 36771 | 0.1708 |
106
- | 0.106 | 10.4087 | 37492 | 0.1643 |
107
- | 0.107 | 10.6088 | 38213 | 0.1644 |
108
- | 0.1067 | 10.8090 | 38934 | 0.1629 |
109
- | 0.1053 | 11.0092 | 39655 | 0.1668 |
110
- | 0.097 | 11.2093 | 40376 | 0.1692 |
111
- | 0.095 | 11.4095 | 41097 | 0.1653 |
112
- | 0.0955 | 11.6097 | 41818 | 0.1650 |
113
- | 0.095 | 11.8098 | 42539 | 0.1641 |
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: 0.1621
20
 
21
  ## Model description
22
 
 
52
 
53
  | Training Loss | Epoch | Step | Validation Loss |
54
  |:-------------:|:-------:|:-----:|:---------------:|
55
+ | 0.4452 | 0.2002 | 721 | 0.3364 |
56
+ | 0.335 | 0.4003 | 1442 | 0.3093 |
57
+ | 0.2934 | 0.6005 | 2163 | 0.2821 |
58
+ | 0.286 | 0.8007 | 2884 | 0.2838 |
59
+ | 0.2728 | 1.0008 | 3605 | 0.2613 |
60
+ | 0.256 | 1.2010 | 4326 | 0.2544 |
61
+ | 0.2532 | 1.4012 | 5047 | 0.2482 |
62
+ | 0.2454 | 1.6013 | 5768 | 0.2423 |
63
+ | 0.2446 | 1.8015 | 6489 | 0.2420 |
64
+ | 0.2397 | 2.0017 | 7210 | 0.2351 |
65
+ | 0.2294 | 2.2018 | 7931 | 0.2337 |
66
+ | 0.2279 | 2.4020 | 8652 | 0.2309 |
67
+ | 0.2234 | 2.6022 | 9373 | 0.2254 |
68
+ | 0.2219 | 2.8023 | 10094 | 0.2240 |
69
+ | 0.2203 | 3.0025 | 10815 | 0.2248 |
70
+ | 0.2068 | 3.2027 | 11536 | 0.2194 |
71
+ | 0.2066 | 3.4028 | 12257 | 0.2088 |
72
+ | 0.204 | 3.6030 | 12978 | 0.2115 |
73
+ | 0.204 | 3.8032 | 13699 | 0.2088 |
74
+ | 0.2018 | 4.0033 | 14420 | 0.2117 |
75
+ | 0.1913 | 4.2035 | 15141 | 0.2052 |
76
+ | 0.1893 | 4.4037 | 15862 | 0.2036 |
77
+ | 0.1889 | 4.6038 | 16583 | 0.1969 |
78
+ | 0.1891 | 4.8040 | 17304 | 0.1973 |
79
+ | 0.1868 | 5.0042 | 18025 | 0.1929 |
80
+ | 0.174 | 5.2043 | 18746 | 0.1938 |
81
+ | 0.1752 | 5.4045 | 19467 | 0.1938 |
82
+ | 0.1746 | 5.6047 | 20188 | 0.1941 |
83
+ | 0.175 | 5.8048 | 20909 | 0.1874 |
84
+ | 0.1732 | 6.0050 | 21630 | 0.1849 |
85
+ | 0.1623 | 6.2052 | 22351 | 0.1908 |
86
+ | 0.162 | 6.4053 | 23072 | 0.1886 |
87
+ | 0.1607 | 6.6055 | 23793 | 0.1846 |
88
+ | 0.162 | 6.8057 | 24514 | 0.1824 |
89
+ | 0.1585 | 7.0058 | 25235 | 0.1823 |
90
+ | 0.1511 | 7.2060 | 25956 | 0.1800 |
91
+ | 0.1479 | 7.4062 | 26677 | 0.1777 |
92
+ | 0.1481 | 7.6063 | 27398 | 0.1763 |
93
+ | 0.1458 | 7.8065 | 28119 | 0.1766 |
94
+ | 0.1455 | 8.0067 | 28840 | 0.1732 |
95
+ | 0.1326 | 8.2068 | 29561 | 0.1719 |
96
+ | 0.1337 | 8.4070 | 30282 | 0.1693 |
97
+ | 0.1326 | 8.6072 | 31003 | 0.1684 |
98
+ | 0.1337 | 8.8073 | 31724 | 0.1662 |
99
+ | 0.132 | 9.0075 | 32445 | 0.1665 |
100
+ | 0.1187 | 9.2077 | 33166 | 0.1686 |
101
+ | 0.1175 | 9.4078 | 33887 | 0.1634 |
102
+ | 0.1189 | 9.6080 | 34608 | 0.1663 |
103
+ | 0.1188 | 9.8082 | 35329 | 0.1616 |
104
+ | 0.1189 | 10.0083 | 36050 | 0.1624 |
105
+ | 0.105 | 10.2085 | 36771 | 0.1648 |
106
+ | 0.104 | 10.4087 | 37492 | 0.1617 |
107
+ | 0.1051 | 10.6088 | 38213 | 0.1618 |
108
+ | 0.1047 | 10.8090 | 38934 | 0.1598 |
109
+ | 0.1035 | 11.0092 | 39655 | 0.1619 |
110
+ | 0.0959 | 11.2093 | 40376 | 0.1658 |
111
+ | 0.0936 | 11.4095 | 41097 | 0.1642 |
112
+ | 0.094 | 11.6097 | 41818 | 0.1612 |
113
+ | 0.0937 | 11.8098 | 42539 | 0.1621 |
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 sha256:52a0b9ebb58488d210222ef5c6fe2222a4ba9642eda2d192a22f2c654b716acc
3
- size 268677696
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:576b49e0becc8eedef3ecef8e46bbf1857ac0222831fe7d6eafe93e2cc463945
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:e9720494ef41ed1960419a983c05684c69555a7098d4102e39ae7b962749a54d
3
  size 5496
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a31dfc16655a1a304cc4c396c1a5837a891e5afa174f74cf9ccc20bb4db6503b
3
  size 5496