Hugging Face's logo

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

PEFT
Safetensors
Generated from Trainer
Model card Files
xet
Community
yalhessi commited on
Commit
0f9fafe
·
verified ·
1 Parent(s): e76fe57

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: 0.2355
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
- | 0.5916 | 0.2002 | 721 | 0.4462 |
56
- | 0.4616 | 0.4003 | 1442 | 0.4030 |
57
- | 0.4076 | 0.6005 | 2163 | 0.3796 |
58
- | 0.395 | 0.8007 | 2884 | 0.3713 |
59
- | 0.3767 | 1.0008 | 3605 | 0.3504 |
60
- | 0.3476 | 1.2010 | 4326 | 0.3514 |
61
- | 0.3426 | 1.4012 | 5047 | 0.3426 |
62
- | 0.3368 | 1.6013 | 5768 | 0.3312 |
63
- | 0.3346 | 1.8015 | 6489 | 0.3218 |
64
- | 0.3293 | 2.0017 | 7210 | 0.3212 |
65
- | 0.3108 | 2.2018 | 7931 | 0.3198 |
66
- | 0.3054 | 2.4020 | 8652 | 0.3138 |
67
- | 0.3039 | 2.6022 | 9373 | 0.3053 |
68
- | 0.3009 | 2.8023 | 10094 | 0.2990 |
69
- | 0.3025 | 3.0025 | 10815 | 0.3017 |
70
- | 0.2766 | 3.2027 | 11536 | 0.3010 |
71
- | 0.2767 | 3.4028 | 12257 | 0.2973 |
72
- | 0.2753 | 3.6030 | 12978 | 0.2948 |
73
- | 0.2779 | 3.8032 | 13699 | 0.2899 |
74
- | 0.2748 | 4.0033 | 14420 | 0.2872 |
75
- | 0.2537 | 4.2035 | 15141 | 0.2931 |
76
- | 0.2538 | 4.4037 | 15862 | 0.2796 |
77
- | 0.2539 | 4.6038 | 16583 | 0.2790 |
78
- | 0.2558 | 4.8040 | 17304 | 0.2732 |
79
- | 0.2548 | 5.0042 | 18025 | 0.2683 |
80
- | 0.2287 | 5.2043 | 18746 | 0.2689 |
81
- | 0.2317 | 5.4045 | 19467 | 0.2710 |
82
- | 0.2316 | 5.6047 | 20188 | 0.2675 |
83
- | 0.2334 | 5.8048 | 20909 | 0.2676 |
84
- | 0.2338 | 6.0050 | 21630 | 0.2707 |
85
- | 0.2135 | 6.2052 | 22351 | 0.2633 |
86
- | 0.2147 | 6.4053 | 23072 | 0.2574 |
87
- | 0.2132 | 6.6055 | 23793 | 0.2578 |
88
- | 0.216 | 6.8057 | 24514 | 0.2537 |
89
- | 0.2129 | 7.0058 | 25235 | 0.2551 |
90
- | 0.1984 | 7.2060 | 25956 | 0.2551 |
91
- | 0.1947 | 7.4062 | 26677 | 0.2533 |
92
- | 0.1952 | 7.6063 | 27398 | 0.2484 |
93
- | 0.1924 | 7.8065 | 28119 | 0.2509 |
94
- | 0.1937 | 8.0067 | 28840 | 0.2478 |
95
- | 0.1722 | 8.2068 | 29561 | 0.2428 |
96
- | 0.1742 | 8.4070 | 30282 | 0.2423 |
97
- | 0.1743 | 8.6072 | 31003 | 0.2409 |
98
- | 0.1745 | 8.8073 | 31724 | 0.2387 |
99
- | 0.1729 | 9.0075 | 32445 | 0.2402 |
100
- | 0.1517 | 9.2077 | 33166 | 0.2385 |
101
- | 0.1528 | 9.4078 | 33887 | 0.2392 |
102
- | 0.1539 | 9.6080 | 34608 | 0.2370 |
103
- | 0.156 | 9.8082 | 35329 | 0.2362 |
104
- | 0.1538 | 10.0083 | 36050 | 0.2372 |
105
- | 0.1346 | 10.2085 | 36771 | 0.2404 |
106
- | 0.1346 | 10.4087 | 37492 | 0.2375 |
107
- | 0.1356 | 10.6088 | 38213 | 0.2357 |
108
- | 0.1362 | 10.8090 | 38934 | 0.2313 |
109
- | 0.1337 | 11.0092 | 39655 | 0.2362 |
110
- | 0.1231 | 11.2093 | 40376 | 0.2389 |
111
- | 0.1188 | 11.4095 | 41097 | 0.2415 |
112
- | 0.1213 | 11.6097 | 41818 | 0.2393 |
113
- | 0.1198 | 11.8098 | 42539 | 0.2355 |
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: 0.2381
20
 
21
  ## Model description
22
 
 
52
 
53
  | Training Loss | Epoch | Step | Validation Loss |
54
  |:-------------:|:-------:|:-----:|:---------------:|
55
+ | 0.5903 | 0.2002 | 721 | 0.4468 |
56
+ | 0.4617 | 0.4003 | 1442 | 0.4101 |
57
+ | 0.4065 | 0.6005 | 2163 | 0.3815 |
58
+ | 0.3953 | 0.8007 | 2884 | 0.3736 |
59
+ | 0.3762 | 1.0008 | 3605 | 0.3610 |
60
+ | 0.3464 | 1.2010 | 4326 | 0.3498 |
61
+ | 0.342 | 1.4012 | 5047 | 0.3414 |
62
+ | 0.3355 | 1.6013 | 5768 | 0.3293 |
63
+ | 0.3346 | 1.8015 | 6489 | 0.3263 |
64
+ | 0.3291 | 2.0017 | 7210 | 0.3199 |
65
+ | 0.3115 | 2.2018 | 7931 | 0.3223 |
66
+ | 0.3056 | 2.4020 | 8652 | 0.3258 |
67
+ | 0.3056 | 2.6022 | 9373 | 0.3144 |
68
+ | 0.301 | 2.8023 | 10094 | 0.3074 |
69
+ | 0.3017 | 3.0025 | 10815 | 0.3054 |
70
+ | 0.2774 | 3.2027 | 11536 | 0.3043 |
71
+ | 0.2761 | 3.4028 | 12257 | 0.2997 |
72
+ | 0.2753 | 3.6030 | 12978 | 0.2922 |
73
+ | 0.2789 | 3.8032 | 13699 | 0.2881 |
74
+ | 0.2735 | 4.0033 | 14420 | 0.2874 |
75
+ | 0.2533 | 4.2035 | 15141 | 0.2853 |
76
+ | 0.254 | 4.4037 | 15862 | 0.2875 |
77
+ | 0.254 | 4.6038 | 16583 | 0.2818 |
78
+ | 0.2547 | 4.8040 | 17304 | 0.2785 |
79
+ | 0.255 | 5.0042 | 18025 | 0.2792 |
80
+ | 0.23 | 5.2043 | 18746 | 0.2723 |
81
+ | 0.2314 | 5.4045 | 19467 | 0.2717 |
82
+ | 0.2314 | 5.6047 | 20188 | 0.2655 |
83
+ | 0.2339 | 5.8048 | 20909 | 0.2682 |
84
+ | 0.2344 | 6.0050 | 21630 | 0.2643 |
85
+ | 0.2147 | 6.2052 | 22351 | 0.2617 |
86
+ | 0.2143 | 6.4053 | 23072 | 0.2637 |
87
+ | 0.2139 | 6.6055 | 23793 | 0.2562 |
88
+ | 0.2156 | 6.8057 | 24514 | 0.2513 |
89
+ | 0.2131 | 7.0058 | 25235 | 0.2564 |
90
+ | 0.1988 | 7.2060 | 25956 | 0.2510 |
91
+ | 0.195 | 7.4062 | 26677 | 0.2510 |
92
+ | 0.1942 | 7.6063 | 27398 | 0.2495 |
93
+ | 0.1929 | 7.8065 | 28119 | 0.2455 |
94
+ | 0.1937 | 8.0067 | 28840 | 0.2456 |
95
+ | 0.1703 | 8.2068 | 29561 | 0.2437 |
96
+ | 0.1748 | 8.4070 | 30282 | 0.2413 |
97
+ | 0.1752 | 8.6072 | 31003 | 0.2385 |
98
+ | 0.174 | 8.8073 | 31724 | 0.2368 |
99
+ | 0.1728 | 9.0075 | 32445 | 0.2406 |
100
+ | 0.1517 | 9.2077 | 33166 | 0.2411 |
101
+ | 0.1526 | 9.4078 | 33887 | 0.2396 |
102
+ | 0.154 | 9.6080 | 34608 | 0.2359 |
103
+ | 0.1561 | 9.8082 | 35329 | 0.2348 |
104
+ | 0.1542 | 10.0083 | 36050 | 0.2369 |
105
+ | 0.1347 | 10.2085 | 36771 | 0.2427 |
106
+ | 0.134 | 10.4087 | 37492 | 0.2374 |
107
+ | 0.1357 | 10.6088 | 38213 | 0.2378 |
108
+ | 0.1357 | 10.8090 | 38934 | 0.2324 |
109
+ | 0.1334 | 11.0092 | 39655 | 0.2344 |
110
+ | 0.1227 | 11.2093 | 40376 | 0.2378 |
111
+ | 0.1193 | 11.4095 | 41097 | 0.2367 |
112
+ | 0.1208 | 11.6097 | 41818 | 0.2378 |
113
+ | 0.1201 | 11.8098 | 42539 | 0.2381 |
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:a07b4354783149fb3c9eb2311e0a0f918d540976e058e4be1a71ee011793fd4d
3
  size 268636736
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6b446f77ccca48941f4d606561f65cfbaf1836e90c6996f669c67bb8fbcc6015
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:a7d470ac1f804272735159395601d8c95aa8babe9d17c8dd17b9735beaab63df
3
  size 5496
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:094693f8093dbcc18edb90791f2a00ebba0341a043c1ffc73a96e024ffa981de
3
  size 5496