Hugging Face's logo

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

PEFT
Safetensors
Generated from Trainer
Model card Files
xet
Community
yalhessi commited on
Commit
9c48362
·
verified ·
1 Parent(s): 11de55c

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 +2 -2
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: 0.2309
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
- | 0.5603 | 0.2002 | 721 | 0.4280 |
56
- | 0.4421 | 0.4003 | 1442 | 0.3964 |
57
- | 0.3935 | 0.6005 | 2163 | 0.3718 |
58
- | 0.3807 | 0.8007 | 2884 | 0.3598 |
59
- | 0.3638 | 1.0008 | 3605 | 0.3509 |
60
- | 0.3388 | 1.2010 | 4326 | 0.3377 |
61
- | 0.3318 | 1.4012 | 5047 | 0.3292 |
62
- | 0.3269 | 1.6013 | 5768 | 0.3266 |
63
- | 0.3263 | 1.8015 | 6489 | 0.3187 |
64
- | 0.321 | 2.0017 | 7210 | 0.3129 |
65
- | 0.3035 | 2.2018 | 7931 | 0.3078 |
66
- | 0.2986 | 2.4020 | 8652 | 0.3113 |
67
- | 0.2983 | 2.6022 | 9373 | 0.3003 |
68
- | 0.2932 | 2.8023 | 10094 | 0.2985 |
69
- | 0.295 | 3.0025 | 10815 | 0.2942 |
70
- | 0.2707 | 3.2027 | 11536 | 0.2922 |
71
- | 0.2708 | 3.4028 | 12257 | 0.2888 |
72
- | 0.2692 | 3.6030 | 12978 | 0.2862 |
73
- | 0.2714 | 3.8032 | 13699 | 0.2828 |
74
- | 0.2701 | 4.0033 | 14420 | 0.2790 |
75
- | 0.2473 | 4.2035 | 15141 | 0.2722 |
76
- | 0.2487 | 4.4037 | 15862 | 0.2764 |
77
- | 0.2493 | 4.6038 | 16583 | 0.2731 |
78
- | 0.2491 | 4.8040 | 17304 | 0.2675 |
79
- | 0.2491 | 5.0042 | 18025 | 0.2660 |
80
- | 0.2245 | 5.2043 | 18746 | 0.2611 |
81
- | 0.2279 | 5.4045 | 19467 | 0.2609 |
82
- | 0.2272 | 5.6047 | 20188 | 0.2658 |
83
- | 0.2296 | 5.8048 | 20909 | 0.2536 |
84
- | 0.2294 | 6.0050 | 21630 | 0.2581 |
85
- | 0.2104 | 6.2052 | 22351 | 0.2542 |
86
- | 0.2103 | 6.4053 | 23072 | 0.2537 |
87
- | 0.2086 | 6.6055 | 23793 | 0.2543 |
88
- | 0.2102 | 6.8057 | 24514 | 0.2465 |
89
- | 0.209 | 7.0058 | 25235 | 0.2483 |
90
- | 0.1947 | 7.2060 | 25956 | 0.2485 |
91
- | 0.1927 | 7.4062 | 26677 | 0.2418 |
92
- | 0.191 | 7.6063 | 27398 | 0.2384 |
93
- | 0.1894 | 7.8065 | 28119 | 0.2394 |
94
- | 0.1902 | 8.0067 | 28840 | 0.2380 |
95
- | 0.1689 | 8.2068 | 29561 | 0.2367 |
96
- | 0.1723 | 8.4070 | 30282 | 0.2346 |
97
- | 0.1712 | 8.6072 | 31003 | 0.2330 |
98
- | 0.1715 | 8.8073 | 31724 | 0.2308 |
99
- | 0.1693 | 9.0075 | 32445 | 0.2356 |
100
- | 0.1489 | 9.2077 | 33166 | 0.2351 |
101
- | 0.15 | 9.4078 | 33887 | 0.2284 |
102
- | 0.1519 | 9.6080 | 34608 | 0.2274 |
103
- | 0.153 | 9.8082 | 35329 | 0.2283 |
104
- | 0.1511 | 10.0083 | 36050 | 0.2318 |
105
- | 0.1321 | 10.2085 | 36771 | 0.2320 |
106
- | 0.1316 | 10.4087 | 37492 | 0.2287 |
107
- | 0.1317 | 10.6088 | 38213 | 0.2290 |
108
- | 0.1337 | 10.8090 | 38934 | 0.2251 |
109
- | 0.1318 | 11.0092 | 39655 | 0.2285 |
110
- | 0.1206 | 11.2093 | 40376 | 0.2307 |
111
- | 0.1173 | 11.4095 | 41097 | 0.2312 |
112
- | 0.1187 | 11.6097 | 41818 | 0.2321 |
113
- | 0.1182 | 11.8098 | 42539 | 0.2309 |
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: 0.2634
20
 
21
  ## Model description
22
 
 
52
 
53
  | Training Loss | Epoch | Step | Validation Loss |
54
  |:-------------:|:-------:|:-----:|:---------------:|
55
+ | 0.5858 | 0.2001 | 720 | 0.4896 |
56
+ | 0.4652 | 0.4001 | 1440 | 0.4362 |
57
+ | 0.4072 | 0.6002 | 2160 | 0.4134 |
58
+ | 0.3941 | 0.8002 | 2880 | 0.3971 |
59
+ | 0.3765 | 1.0003 | 3600 | 0.3855 |
60
+ | 0.3457 | 1.2003 | 4320 | 0.3746 |
61
+ | 0.3401 | 1.4004 | 5040 | 0.3664 |
62
+ | 0.3392 | 1.6004 | 5760 | 0.3655 |
63
+ | 0.3354 | 1.8005 | 6480 | 0.3511 |
64
+ | 0.3286 | 2.0006 | 7200 | 0.3507 |
65
+ | 0.3095 | 2.2006 | 7920 | 0.3500 |
66
+ | 0.3046 | 2.4007 | 8640 | 0.3373 |
67
+ | 0.3004 | 2.6007 | 9360 | 0.3278 |
68
+ | 0.2993 | 2.8008 | 10080 | 0.3210 |
69
+ | 0.3009 | 3.0008 | 10800 | 0.3270 |
70
+ | 0.2759 | 3.2009 | 11520 | 0.3232 |
71
+ | 0.2782 | 3.4009 | 12240 | 0.3173 |
72
+ | 0.2768 | 3.6010 | 12960 | 0.3180 |
73
+ | 0.276 | 3.8011 | 13680 | 0.3124 |
74
+ | 0.2772 | 4.0011 | 14400 | 0.3027 |
75
+ | 0.2495 | 4.2012 | 15120 | 0.3122 |
76
+ | 0.2575 | 4.4012 | 15840 | 0.3063 |
77
+ | 0.2525 | 4.6013 | 16560 | 0.2970 |
78
+ | 0.2586 | 4.8013 | 17280 | 0.3007 |
79
+ | 0.2518 | 5.0014 | 18000 | 0.3017 |
80
+ | 0.2297 | 5.2014 | 18720 | 0.2969 |
81
+ | 0.2316 | 5.4015 | 19440 | 0.2911 |
82
+ | 0.2355 | 5.6016 | 20160 | 0.2951 |
83
+ | 0.2358 | 5.8016 | 20880 | 0.2850 |
84
+ | 0.2308 | 6.0017 | 21600 | 0.2823 |
85
+ | 0.2135 | 6.2017 | 22320 | 0.2825 |
86
+ | 0.2151 | 6.4018 | 23040 | 0.2798 |
87
+ | 0.2143 | 6.6018 | 23760 | 0.2780 |
88
+ | 0.2131 | 6.8019 | 24480 | 0.2756 |
89
+ | 0.2126 | 7.0019 | 25200 | 0.2703 |
90
+ | 0.1967 | 7.2020 | 25920 | 0.2741 |
91
+ | 0.1922 | 7.4021 | 26640 | 0.2734 |
92
+ | 0.1928 | 7.6021 | 27360 | 0.2694 |
93
+ | 0.1931 | 7.8022 | 28080 | 0.2635 |
94
+ | 0.1958 | 8.0022 | 28800 | 0.2680 |
95
+ | 0.1732 | 8.2023 | 29520 | 0.2659 |
96
+ | 0.1711 | 8.4023 | 30240 | 0.2651 |
97
+ | 0.1736 | 8.6024 | 30960 | 0.2650 |
98
+ | 0.172 | 8.8024 | 31680 | 0.2565 |
99
+ | 0.1752 | 9.0025 | 32400 | 0.2579 |
100
+ | 0.1521 | 9.2026 | 33120 | 0.2709 |
101
+ | 0.1519 | 9.4026 | 33840 | 0.2620 |
102
+ | 0.1569 | 9.6027 | 34560 | 0.2624 |
103
+ | 0.1548 | 9.8027 | 35280 | 0.2566 |
104
+ | 0.152 | 10.0028 | 36000 | 0.2577 |
105
+ | 0.1338 | 10.2028 | 36720 | 0.2610 |
106
+ | 0.1353 | 10.4029 | 37440 | 0.2582 |
107
+ | 0.1346 | 10.6029 | 38160 | 0.2583 |
108
+ | 0.1347 | 10.8030 | 38880 | 0.2576 |
109
+ | 0.1361 | 11.0031 | 39600 | 0.2593 |
110
+ | 0.1219 | 11.2031 | 40320 | 0.2644 |
111
+ | 0.1203 | 11.4032 | 41040 | 0.2636 |
112
+ | 0.1188 | 11.6032 | 41760 | 0.2645 |
113
+ | 0.1186 | 11.8033 | 42480 | 0.2634 |
114
 
115
 
116
  ### Framework versions
adapter_config.json CHANGED
@@ -23,8 +23,8 @@
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,
 
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,
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:219e6263cfc8898806d2b361be380b22eb02eb44d2259c9325759f5c41a3c549
3
  size 268636736
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:108f7b90853a67fe7f1df1a50a71e779d221661f4104f3a41cf427e6de1a047c
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 sha256:88742265e75aad22b11591dbfbdf157edacb6d8e38bbc22ef9dbe4ece447e0b4
3
- size 5496
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:22424901ebcaa105dfb0d25c3a7031dbf1f5e6731c31dfae89ed99bfd3c6ccfc
3
+ size 5432