Hugging Face's logo

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

PEFT
Safetensors
Generated from Trainer
Model card Files
xet
Community
yalhessi commited on
Commit
1f2123b
·
verified ·
1 Parent(s): 384c795

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: 0.2403
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
- | 0.6881 | 0.2002 | 721 | 0.4926 |
56
- | 0.5104 | 0.4003 | 1442 | 0.4505 |
57
- | 0.4353 | 0.6005 | 2163 | 0.4146 |
58
- | 0.4206 | 0.8007 | 2884 | 0.3981 |
59
- | 0.3977 | 1.0008 | 3605 | 0.3817 |
60
- | 0.3672 | 1.2010 | 4326 | 0.3654 |
61
- | 0.3603 | 1.4012 | 5047 | 0.3605 |
62
- | 0.3498 | 1.6013 | 5768 | 0.3574 |
63
- | 0.351 | 1.8015 | 6489 | 0.3504 |
64
- | 0.3469 | 2.0017 | 7210 | 0.3429 |
65
- | 0.3255 | 2.2018 | 7931 | 0.3355 |
66
- | 0.3206 | 2.4020 | 8652 | 0.3390 |
67
- | 0.3164 | 2.6022 | 9373 | 0.3182 |
68
- | 0.3129 | 2.8023 | 10094 | 0.3280 |
69
- | 0.3136 | 3.0025 | 10815 | 0.3185 |
70
- | 0.2888 | 3.2027 | 11536 | 0.3133 |
71
- | 0.2865 | 3.4028 | 12257 | 0.3089 |
72
- | 0.2874 | 3.6030 | 12978 | 0.3072 |
73
- | 0.287 | 3.8032 | 13699 | 0.3069 |
74
- | 0.2851 | 4.0033 | 14420 | 0.2991 |
75
- | 0.2627 | 4.2035 | 15141 | 0.2995 |
76
- | 0.264 | 4.4037 | 15862 | 0.3018 |
77
- | 0.2632 | 4.6038 | 16583 | 0.2958 |
78
- | 0.2643 | 4.8040 | 17304 | 0.2872 |
79
- | 0.2633 | 5.0042 | 18025 | 0.2877 |
80
- | 0.2375 | 5.2043 | 18746 | 0.2845 |
81
- | 0.2405 | 5.4045 | 19467 | 0.2876 |
82
- | 0.2409 | 5.6047 | 20188 | 0.2808 |
83
- | 0.2418 | 5.8048 | 20909 | 0.2773 |
84
- | 0.2424 | 6.0050 | 21630 | 0.2718 |
85
- | 0.2217 | 6.2052 | 22351 | 0.2762 |
86
- | 0.2205 | 6.4053 | 23072 | 0.2732 |
87
- | 0.221 | 6.6055 | 23793 | 0.2692 |
88
- | 0.222 | 6.8057 | 24514 | 0.2667 |
89
- | 0.2203 | 7.0058 | 25235 | 0.2676 |
90
- | 0.2053 | 7.2060 | 25956 | 0.2639 |
91
- | 0.2015 | 7.4062 | 26677 | 0.2596 |
92
- | 0.2006 | 7.6063 | 27398 | 0.2549 |
93
- | 0.1982 | 7.8065 | 28119 | 0.2545 |
94
- | 0.1982 | 8.0067 | 28840 | 0.2570 |
95
- | 0.1764 | 8.2068 | 29561 | 0.2501 |
96
- | 0.1799 | 8.4070 | 30282 | 0.2530 |
97
- | 0.1796 | 8.6072 | 31003 | 0.2462 |
98
- | 0.1801 | 8.8073 | 31724 | 0.2465 |
99
- | 0.1769 | 9.0075 | 32445 | 0.2489 |
100
- | 0.1565 | 9.2077 | 33166 | 0.2462 |
101
- | 0.1569 | 9.4078 | 33887 | 0.2463 |
102
- | 0.1594 | 9.6080 | 34608 | 0.2465 |
103
- | 0.1605 | 9.8082 | 35329 | 0.2409 |
104
- | 0.1583 | 10.0083 | 36050 | 0.2427 |
105
- | 0.1389 | 10.2085 | 36771 | 0.2476 |
106
- | 0.1378 | 10.4087 | 37492 | 0.2445 |
107
- | 0.1395 | 10.6088 | 38213 | 0.2436 |
108
- | 0.14 | 10.8090 | 38934 | 0.2418 |
109
- | 0.1375 | 11.0092 | 39655 | 0.2412 |
110
- | 0.1262 | 11.2093 | 40376 | 0.2433 |
111
- | 0.1231 | 11.4095 | 41097 | 0.2439 |
112
- | 0.124 | 11.6097 | 41818 | 0.2440 |
113
- | 0.1233 | 11.8098 | 42539 | 0.2403 |
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: 0.2373
20
 
21
  ## Model description
22
 
 
52
 
53
  | Training Loss | Epoch | Step | Validation Loss |
54
  |:-------------:|:-------:|:-----:|:---------------:|
55
+ | 0.6444 | 0.2002 | 721 | 0.4798 |
56
+ | 0.4987 | 0.4003 | 1442 | 0.4339 |
57
+ | 0.4324 | 0.6005 | 2163 | 0.4100 |
58
+ | 0.4155 | 0.8007 | 2884 | 0.3960 |
59
+ | 0.3968 | 1.0008 | 3605 | 0.3739 |
60
+ | 0.3645 | 1.2010 | 4326 | 0.3639 |
61
+ | 0.3602 | 1.4012 | 5047 | 0.3606 |
62
+ | 0.3492 | 1.6013 | 5768 | 0.3542 |
63
+ | 0.35 | 1.8015 | 6489 | 0.3530 |
64
+ | 0.3443 | 2.0017 | 7210 | 0.3420 |
65
+ | 0.3249 | 2.2018 | 7931 | 0.3301 |
66
+ | 0.3189 | 2.4020 | 8652 | 0.3317 |
67
+ | 0.3161 | 2.6022 | 9373 | 0.3218 |
68
+ | 0.3131 | 2.8023 | 10094 | 0.3158 |
69
+ | 0.3138 | 3.0025 | 10815 | 0.3144 |
70
+ | 0.2886 | 3.2027 | 11536 | 0.3112 |
71
+ | 0.287 | 3.4028 | 12257 | 0.3085 |
72
+ | 0.2864 | 3.6030 | 12978 | 0.3042 |
73
+ | 0.2884 | 3.8032 | 13699 | 0.3027 |
74
+ | 0.2845 | 4.0033 | 14420 | 0.2965 |
75
+ | 0.263 | 4.2035 | 15141 | 0.3005 |
76
+ | 0.264 | 4.4037 | 15862 | 0.2947 |
77
+ | 0.2635 | 4.6038 | 16583 | 0.2897 |
78
+ | 0.2632 | 4.8040 | 17304 | 0.2893 |
79
+ | 0.2634 | 5.0042 | 18025 | 0.2822 |
80
+ | 0.2368 | 5.2043 | 18746 | 0.2793 |
81
+ | 0.2398 | 5.4045 | 19467 | 0.2769 |
82
+ | 0.2407 | 5.6047 | 20188 | 0.2768 |
83
+ | 0.2407 | 5.8048 | 20909 | 0.2750 |
84
+ | 0.2436 | 6.0050 | 21630 | 0.2741 |
85
+ | 0.2219 | 6.2052 | 22351 | 0.2738 |
86
+ | 0.2214 | 6.4053 | 23072 | 0.2717 |
87
+ | 0.2203 | 6.6055 | 23793 | 0.2673 |
88
+ | 0.2219 | 6.8057 | 24514 | 0.2632 |
89
+ | 0.2199 | 7.0058 | 25235 | 0.2589 |
90
+ | 0.206 | 7.2060 | 25956 | 0.2633 |
91
+ | 0.2011 | 7.4062 | 26677 | 0.2573 |
92
+ | 0.1998 | 7.6063 | 27398 | 0.2537 |
93
+ | 0.2006 | 7.8065 | 28119 | 0.2566 |
94
+ | 0.1998 | 8.0067 | 28840 | 0.2525 |
95
+ | 0.1772 | 8.2068 | 29561 | 0.2509 |
96
+ | 0.181 | 8.4070 | 30282 | 0.2532 |
97
+ | 0.1808 | 8.6072 | 31003 | 0.2462 |
98
+ | 0.1801 | 8.8073 | 31724 | 0.2481 |
99
+ | 0.1794 | 9.0075 | 32445 | 0.2442 |
100
+ | 0.1568 | 9.2077 | 33166 | 0.2456 |
101
+ | 0.1575 | 9.4078 | 33887 | 0.2464 |
102
+ | 0.1599 | 9.6080 | 34608 | 0.2442 |
103
+ | 0.1619 | 9.8082 | 35329 | 0.2387 |
104
+ | 0.1589 | 10.0083 | 36050 | 0.2361 |
105
+ | 0.1407 | 10.2085 | 36771 | 0.2423 |
106
+ | 0.1387 | 10.4087 | 37492 | 0.2410 |
107
+ | 0.1407 | 10.6088 | 38213 | 0.2356 |
108
+ | 0.1413 | 10.8090 | 38934 | 0.2370 |
109
+ | 0.1384 | 11.0092 | 39655 | 0.2396 |
110
+ | 0.1267 | 11.2093 | 40376 | 0.2388 |
111
+ | 0.1238 | 11.4095 | 41097 | 0.2397 |
112
+ | 0.1259 | 11.6097 | 41818 | 0.2361 |
113
+ | 0.1249 | 11.8098 | 42539 | 0.2373 |
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:fff4eb8d2aa846cf252083d8ee2c902dce599913fa72e9ed55d2b8a062802de4
3
- size 268677696
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d29e69ead95d71f3beefd601b7f838a567e367e5197fca68bbb84358d1ca17d4
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 sha256:1211aef3c445f6d28d24247d6e3091bfa09946e63a0af720213ed52986e4e90e
3
  size 5496
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:768f26ef191c82e5d195e8104338d12706800f5abfcb5cc1f8db75506dd728df
3
  size 5496