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
8716847
·
verified ·
1 Parent(s): fbdc2ff

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: 0.2352
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
- | 0.588 | 0.2002 | 721 | 0.4356 |
56
- | 0.4481 | 0.4003 | 1442 | 0.4067 |
57
- | 0.397 | 0.6005 | 2163 | 0.3795 |
58
- | 0.3841 | 0.8007 | 2884 | 0.3673 |
59
- | 0.3666 | 1.0008 | 3605 | 0.3445 |
60
- | 0.3409 | 1.2010 | 4326 | 0.3416 |
61
- | 0.3347 | 1.4012 | 5047 | 0.3323 |
62
- | 0.3285 | 1.6013 | 5768 | 0.3313 |
63
- | 0.3288 | 1.8015 | 6489 | 0.3217 |
64
- | 0.3232 | 2.0017 | 7210 | 0.3111 |
65
- | 0.3048 | 2.2018 | 7931 | 0.3151 |
66
- | 0.3004 | 2.4020 | 8652 | 0.3155 |
67
- | 0.2994 | 2.6022 | 9373 | 0.3052 |
68
- | 0.2939 | 2.8023 | 10094 | 0.3023 |
69
- | 0.2948 | 3.0025 | 10815 | 0.3001 |
70
- | 0.2702 | 3.2027 | 11536 | 0.2995 |
71
- | 0.2707 | 3.4028 | 12257 | 0.2913 |
72
- | 0.2696 | 3.6030 | 12978 | 0.2870 |
73
- | 0.2729 | 3.8032 | 13699 | 0.2859 |
74
- | 0.2697 | 4.0033 | 14420 | 0.2853 |
75
- | 0.2497 | 4.2035 | 15141 | 0.2815 |
76
- | 0.2497 | 4.4037 | 15862 | 0.2768 |
77
- | 0.2503 | 4.6038 | 16583 | 0.2748 |
78
- | 0.2505 | 4.8040 | 17304 | 0.2728 |
79
- | 0.2491 | 5.0042 | 18025 | 0.2706 |
80
- | 0.2254 | 5.2043 | 18746 | 0.2711 |
81
- | 0.2274 | 5.4045 | 19467 | 0.2669 |
82
- | 0.2283 | 5.6047 | 20188 | 0.2661 |
83
- | 0.2294 | 5.8048 | 20909 | 0.2616 |
84
- | 0.2304 | 6.0050 | 21630 | 0.2598 |
85
- | 0.2099 | 6.2052 | 22351 | 0.2619 |
86
- | 0.2101 | 6.4053 | 23072 | 0.2603 |
87
- | 0.2098 | 6.6055 | 23793 | 0.2579 |
88
- | 0.2105 | 6.8057 | 24514 | 0.2530 |
89
- | 0.2085 | 7.0058 | 25235 | 0.2564 |
90
- | 0.1949 | 7.2060 | 25956 | 0.2512 |
91
- | 0.1914 | 7.4062 | 26677 | 0.2459 |
92
- | 0.1901 | 7.6063 | 27398 | 0.2432 |
93
- | 0.1892 | 7.8065 | 28119 | 0.2481 |
94
- | 0.1893 | 8.0067 | 28840 | 0.2445 |
95
- | 0.1676 | 8.2068 | 29561 | 0.2409 |
96
- | 0.1706 | 8.4070 | 30282 | 0.2376 |
97
- | 0.1713 | 8.6072 | 31003 | 0.2342 |
98
- | 0.1711 | 8.8073 | 31724 | 0.2323 |
99
- | 0.1691 | 9.0075 | 32445 | 0.2403 |
100
- | 0.1485 | 9.2077 | 33166 | 0.2380 |
101
- | 0.1483 | 9.4078 | 33887 | 0.2373 |
102
- | 0.152 | 9.6080 | 34608 | 0.2343 |
103
- | 0.1523 | 9.8082 | 35329 | 0.2318 |
104
- | 0.1505 | 10.0083 | 36050 | 0.2356 |
105
- | 0.1311 | 10.2085 | 36771 | 0.2393 |
106
- | 0.1316 | 10.4087 | 37492 | 0.2324 |
107
- | 0.1324 | 10.6088 | 38213 | 0.2310 |
108
- | 0.1334 | 10.8090 | 38934 | 0.2324 |
109
- | 0.1305 | 11.0092 | 39655 | 0.2367 |
110
- | 0.1194 | 11.2093 | 40376 | 0.2374 |
111
- | 0.1164 | 11.4095 | 41097 | 0.2376 |
112
- | 0.1181 | 11.6097 | 41818 | 0.2369 |
113
- | 0.117 | 11.8098 | 42539 | 0.2352 |
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: 0.2306
20
 
21
  ## Model description
22
 
 
52
 
53
  | Training Loss | Epoch | Step | Validation Loss |
54
  |:-------------:|:-------:|:-----:|:---------------:|
55
+ | 0.5613 | 0.2002 | 721 | 0.4284 |
56
+ | 0.44 | 0.4003 | 1442 | 0.3884 |
57
+ | 0.3929 | 0.6005 | 2163 | 0.3794 |
58
+ | 0.3803 | 0.8007 | 2884 | 0.3589 |
59
+ | 0.3646 | 1.0008 | 3605 | 0.3492 |
60
+ | 0.3378 | 1.2010 | 4326 | 0.3442 |
61
+ | 0.3317 | 1.4012 | 5047 | 0.3342 |
62
+ | 0.3256 | 1.6013 | 5768 | 0.3264 |
63
+ | 0.3268 | 1.8015 | 6489 | 0.3211 |
64
+ | 0.321 | 2.0017 | 7210 | 0.3174 |
65
+ | 0.3037 | 2.2018 | 7931 | 0.3149 |
66
+ | 0.2988 | 2.4020 | 8652 | 0.3114 |
67
+ | 0.2979 | 2.6022 | 9373 | 0.3003 |
68
+ | 0.2939 | 2.8023 | 10094 | 0.2976 |
69
+ | 0.2943 | 3.0025 | 10815 | 0.2961 |
70
+ | 0.2702 | 3.2027 | 11536 | 0.2882 |
71
+ | 0.2703 | 3.4028 | 12257 | 0.2930 |
72
+ | 0.2699 | 3.6030 | 12978 | 0.2876 |
73
+ | 0.2723 | 3.8032 | 13699 | 0.2836 |
74
+ | 0.2698 | 4.0033 | 14420 | 0.2837 |
75
+ | 0.2479 | 4.2035 | 15141 | 0.2796 |
76
+ | 0.2487 | 4.4037 | 15862 | 0.2793 |
77
+ | 0.2482 | 4.6038 | 16583 | 0.2768 |
78
+ | 0.2501 | 4.8040 | 17304 | 0.2705 |
79
+ | 0.2494 | 5.0042 | 18025 | 0.2723 |
80
+ | 0.2255 | 5.2043 | 18746 | 0.2666 |
81
+ | 0.2274 | 5.4045 | 19467 | 0.2644 |
82
+ | 0.2272 | 5.6047 | 20188 | 0.2639 |
83
+ | 0.2293 | 5.8048 | 20909 | 0.2590 |
84
+ | 0.2301 | 6.0050 | 21630 | 0.2586 |
85
+ | 0.2099 | 6.2052 | 22351 | 0.2625 |
86
+ | 0.2087 | 6.4053 | 23072 | 0.2579 |
87
+ | 0.2085 | 6.6055 | 23793 | 0.2506 |
88
+ | 0.2106 | 6.8057 | 24514 | 0.2453 |
89
+ | 0.2088 | 7.0058 | 25235 | 0.2545 |
90
+ | 0.1949 | 7.2060 | 25956 | 0.2471 |
91
+ | 0.1912 | 7.4062 | 26677 | 0.2481 |
92
+ | 0.1906 | 7.6063 | 27398 | 0.2416 |
93
+ | 0.1885 | 7.8065 | 28119 | 0.2388 |
94
+ | 0.1882 | 8.0067 | 28840 | 0.2396 |
95
+ | 0.1676 | 8.2068 | 29561 | 0.2385 |
96
+ | 0.1707 | 8.4070 | 30282 | 0.2383 |
97
+ | 0.1715 | 8.6072 | 31003 | 0.2320 |
98
+ | 0.1717 | 8.8073 | 31724 | 0.2337 |
99
+ | 0.1679 | 9.0075 | 32445 | 0.2362 |
100
+ | 0.1484 | 9.2077 | 33166 | 0.2344 |
101
+ | 0.1492 | 9.4078 | 33887 | 0.2308 |
102
+ | 0.1513 | 9.6080 | 34608 | 0.2321 |
103
+ | 0.1528 | 9.8082 | 35329 | 0.2307 |
104
+ | 0.1507 | 10.0083 | 36050 | 0.2289 |
105
+ | 0.1319 | 10.2085 | 36771 | 0.2332 |
106
+ | 0.131 | 10.4087 | 37492 | 0.2262 |
107
+ | 0.1328 | 10.6088 | 38213 | 0.2263 |
108
+ | 0.1333 | 10.8090 | 38934 | 0.2260 |
109
+ | 0.1311 | 11.0092 | 39655 | 0.2293 |
110
+ | 0.1207 | 11.2093 | 40376 | 0.2344 |
111
+ | 0.1169 | 11.4095 | 41097 | 0.2312 |
112
+ | 0.1184 | 11.6097 | 41818 | 0.2318 |
113
+ | 0.1175 | 11.8098 | 42539 | 0.2306 |
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 sha256:9ed9b21b64650510452ec076e4388225745f4a64b58d2cd6c1a7f3f7177c23ba
3
- size 268677696
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:18dc4e9cb9b26e985c750ecccd0915d64cf277c357856c5950044f6389e28be7
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 sha256:6b6eb95d055d204be52c34b770d5783e4cfae6f9f8c46a2d3eb972a09d2e0958
3
  size 5496
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:35dbfe13f778604ba6994dcb423ee451fbcb491ee42cdc27079f8cc929154420
3
  size 5496