Hugging Face's logo

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

PEFT
Safetensors
Generated from Trainer
Model card Files Community
yalhessi commited on
Commit
4778982
·
verified ·
1 Parent(s): 0fb1de7

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: 0.2406
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
- | 0.5909 | 0.2002 | 721 | 0.4417 |
56
- | 0.4603 | 0.4003 | 1442 | 0.4181 |
57
- | 0.4078 | 0.6005 | 2163 | 0.3868 |
58
- | 0.3972 | 0.8007 | 2884 | 0.3737 |
59
- | 0.3792 | 1.0008 | 3605 | 0.3536 |
60
- | 0.3497 | 1.2010 | 4326 | 0.3495 |
61
- | 0.3435 | 1.4012 | 5047 | 0.3473 |
62
- | 0.3366 | 1.6013 | 5768 | 0.3409 |
63
- | 0.336 | 1.8015 | 6489 | 0.3333 |
64
- | 0.3326 | 2.0017 | 7210 | 0.3275 |
65
- | 0.3129 | 2.2018 | 7931 | 0.3272 |
66
- | 0.3091 | 2.4020 | 8652 | 0.3311 |
67
- | 0.3072 | 2.6022 | 9373 | 0.3099 |
68
- | 0.303 | 2.8023 | 10094 | 0.3078 |
69
- | 0.304 | 3.0025 | 10815 | 0.3098 |
70
- | 0.2778 | 3.2027 | 11536 | 0.3064 |
71
- | 0.2789 | 3.4028 | 12257 | 0.3035 |
72
- | 0.2785 | 3.6030 | 12978 | 0.2998 |
73
- | 0.2812 | 3.8032 | 13699 | 0.2869 |
74
- | 0.275 | 4.0033 | 14420 | 0.2856 |
75
- | 0.2553 | 4.2035 | 15141 | 0.2898 |
76
- | 0.2543 | 4.4037 | 15862 | 0.2794 |
77
- | 0.2565 | 4.6038 | 16583 | 0.2838 |
78
- | 0.2563 | 4.8040 | 17304 | 0.2789 |
79
- | 0.2568 | 5.0042 | 18025 | 0.2752 |
80
- | 0.2315 | 5.2043 | 18746 | 0.2733 |
81
- | 0.233 | 5.4045 | 19467 | 0.2713 |
82
- | 0.2346 | 5.6047 | 20188 | 0.2753 |
83
- | 0.2342 | 5.8048 | 20909 | 0.2681 |
84
- | 0.2356 | 6.0050 | 21630 | 0.2647 |
85
- | 0.216 | 6.2052 | 22351 | 0.2617 |
86
- | 0.2138 | 6.4053 | 23072 | 0.2634 |
87
- | 0.2143 | 6.6055 | 23793 | 0.2575 |
88
- | 0.2152 | 6.8057 | 24514 | 0.2530 |
89
- | 0.2139 | 7.0058 | 25235 | 0.2612 |
90
- | 0.2004 | 7.2060 | 25956 | 0.2551 |
91
- | 0.195 | 7.4062 | 26677 | 0.2511 |
92
- | 0.1956 | 7.6063 | 27398 | 0.2482 |
93
- | 0.1924 | 7.8065 | 28119 | 0.2524 |
94
- | 0.1936 | 8.0067 | 28840 | 0.2459 |
95
- | 0.1719 | 8.2068 | 29561 | 0.2452 |
96
- | 0.1748 | 8.4070 | 30282 | 0.2406 |
97
- | 0.1742 | 8.6072 | 31003 | 0.2434 |
98
- | 0.1756 | 8.8073 | 31724 | 0.2418 |
99
- | 0.1723 | 9.0075 | 32445 | 0.2474 |
100
- | 0.1516 | 9.2077 | 33166 | 0.2446 |
101
- | 0.1516 | 9.4078 | 33887 | 0.2427 |
102
- | 0.1547 | 9.6080 | 34608 | 0.2406 |
103
- | 0.1556 | 9.8082 | 35329 | 0.2378 |
104
- | 0.1541 | 10.0083 | 36050 | 0.2390 |
105
- | 0.1345 | 10.2085 | 36771 | 0.2438 |
106
- | 0.1336 | 10.4087 | 37492 | 0.2384 |
107
- | 0.1358 | 10.6088 | 38213 | 0.2375 |
108
- | 0.1363 | 10.8090 | 38934 | 0.2353 |
109
- | 0.1334 | 11.0092 | 39655 | 0.2384 |
110
- | 0.122 | 11.2093 | 40376 | 0.2441 |
111
- | 0.1184 | 11.4095 | 41097 | 0.2437 |
112
- | 0.1199 | 11.6097 | 41818 | 0.2432 |
113
- | 0.1189 | 11.8098 | 42539 | 0.2406 |
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: 0.2446
20
 
21
  ## Model description
22
 
 
52
 
53
  | Training Loss | Epoch | Step | Validation Loss |
54
  |:-------------:|:-------:|:-----:|:---------------:|
55
+ | 0.5751 | 0.2002 | 721 | 0.4349 |
56
+ | 0.4561 | 0.4003 | 1442 | 0.4072 |
57
+ | 0.405 | 0.6005 | 2163 | 0.3771 |
58
+ | 0.3917 | 0.8007 | 2884 | 0.3676 |
59
+ | 0.3745 | 1.0008 | 3605 | 0.3581 |
60
+ | 0.346 | 1.2010 | 4326 | 0.3523 |
61
+ | 0.3407 | 1.4012 | 5047 | 0.3416 |
62
+ | 0.3358 | 1.6013 | 5768 | 0.3393 |
63
+ | 0.3344 | 1.8015 | 6489 | 0.3297 |
64
+ | 0.3304 | 2.0017 | 7210 | 0.3216 |
65
+ | 0.3118 | 2.2018 | 7931 | 0.3171 |
66
+ | 0.3073 | 2.4020 | 8652 | 0.3246 |
67
+ | 0.3058 | 2.6022 | 9373 | 0.3150 |
68
+ | 0.3017 | 2.8023 | 10094 | 0.3036 |
69
+ | 0.3019 | 3.0025 | 10815 | 0.3016 |
70
+ | 0.2779 | 3.2027 | 11536 | 0.2993 |
71
+ | 0.2754 | 3.4028 | 12257 | 0.2952 |
72
+ | 0.2762 | 3.6030 | 12978 | 0.2937 |
73
+ | 0.2785 | 3.8032 | 13699 | 0.2877 |
74
+ | 0.2743 | 4.0033 | 14420 | 0.2900 |
75
+ | 0.253 | 4.2035 | 15141 | 0.2817 |
76
+ | 0.2556 | 4.4037 | 15862 | 0.2806 |
77
+ | 0.2541 | 4.6038 | 16583 | 0.2814 |
78
+ | 0.256 | 4.8040 | 17304 | 0.2741 |
79
+ | 0.255 | 5.0042 | 18025 | 0.2767 |
80
+ | 0.2291 | 5.2043 | 18746 | 0.2694 |
81
+ | 0.2321 | 5.4045 | 19467 | 0.2699 |
82
+ | 0.2321 | 5.6047 | 20188 | 0.2668 |
83
+ | 0.234 | 5.8048 | 20909 | 0.2652 |
84
+ | 0.2354 | 6.0050 | 21630 | 0.2619 |
85
+ | 0.2141 | 6.2052 | 22351 | 0.2663 |
86
+ | 0.2146 | 6.4053 | 23072 | 0.2654 |
87
+ | 0.2134 | 6.6055 | 23793 | 0.2566 |
88
+ | 0.2146 | 6.8057 | 24514 | 0.2546 |
89
+ | 0.2134 | 7.0058 | 25235 | 0.2523 |
90
+ | 0.2006 | 7.2060 | 25956 | 0.2522 |
91
+ | 0.1938 | 7.4062 | 26677 | 0.2493 |
92
+ | 0.195 | 7.6063 | 27398 | 0.2513 |
93
+ | 0.1924 | 7.8065 | 28119 | 0.2425 |
94
+ | 0.194 | 8.0067 | 28840 | 0.2477 |
95
+ | 0.1723 | 8.2068 | 29561 | 0.2416 |
96
+ | 0.1743 | 8.4070 | 30282 | 0.2439 |
97
+ | 0.1749 | 8.6072 | 31003 | 0.2362 |
98
+ | 0.175 | 8.8073 | 31724 | 0.2410 |
99
+ | 0.1723 | 9.0075 | 32445 | 0.2446 |
100
+ | 0.1515 | 9.2077 | 33166 | 0.2478 |
101
+ | 0.1518 | 9.4078 | 33887 | 0.2419 |
102
+ | 0.1546 | 9.6080 | 34608 | 0.2420 |
103
+ | 0.1555 | 9.8082 | 35329 | 0.2370 |
104
+ | 0.154 | 10.0083 | 36050 | 0.2428 |
105
+ | 0.1342 | 10.2085 | 36771 | 0.2462 |
106
+ | 0.1335 | 10.4087 | 37492 | 0.2425 |
107
+ | 0.1354 | 10.6088 | 38213 | 0.2397 |
108
+ | 0.1362 | 10.8090 | 38934 | 0.2402 |
109
+ | 0.1335 | 11.0092 | 39655 | 0.2439 |
110
+ | 0.1215 | 11.2093 | 40376 | 0.2451 |
111
+ | 0.1189 | 11.4095 | 41097 | 0.2457 |
112
+ | 0.1208 | 11.6097 | 41818 | 0.2465 |
113
+ | 0.1198 | 11.8098 | 42539 | 0.2446 |
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 sha256:95f2358a34407acba96fa80e7f6968009f1b942b230844551dda623819d3d884
3
- size 268677696
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2521589b52a4823770747fecd9308dae2915aa8518a0c26d5aa7a50772ee7a0e
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 sha256:64538974ed32787c0b5dd88472e389be08acbeec85f2c43bab341f6da0d16094
3
  size 5496
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:41623f3ac94fe1415c8574d35e291ba0e77adb25ada85e180ed5f770dddc9b41
3
  size 5496