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
3779778
·
verified ·
1 Parent(s): 8b247b9

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: 0.2394
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
- | 0.5766 | 0.2002 | 721 | 0.4435 |
56
- | 0.4566 | 0.4003 | 1442 | 0.4037 |
57
- | 0.4039 | 0.6005 | 2163 | 0.3775 |
58
- | 0.393 | 0.8007 | 2884 | 0.3650 |
59
- | 0.3755 | 1.0008 | 3605 | 0.3569 |
60
- | 0.3468 | 1.2010 | 4326 | 0.3528 |
61
- | 0.3427 | 1.4012 | 5047 | 0.3334 |
62
- | 0.3348 | 1.6013 | 5768 | 0.3417 |
63
- | 0.3361 | 1.8015 | 6489 | 0.3322 |
64
- | 0.3305 | 2.0017 | 7210 | 0.3202 |
65
- | 0.3113 | 2.2018 | 7931 | 0.3264 |
66
- | 0.3072 | 2.4020 | 8652 | 0.3232 |
67
- | 0.3059 | 2.6022 | 9373 | 0.3140 |
68
- | 0.3017 | 2.8023 | 10094 | 0.3071 |
69
- | 0.3024 | 3.0025 | 10815 | 0.3109 |
70
- | 0.2781 | 3.2027 | 11536 | 0.3022 |
71
- | 0.2784 | 3.4028 | 12257 | 0.3006 |
72
- | 0.2767 | 3.6030 | 12978 | 0.2924 |
73
- | 0.2788 | 3.8032 | 13699 | 0.2929 |
74
- | 0.2758 | 4.0033 | 14420 | 0.2955 |
75
- | 0.2532 | 4.2035 | 15141 | 0.2872 |
76
- | 0.2539 | 4.4037 | 15862 | 0.2880 |
77
- | 0.2544 | 4.6038 | 16583 | 0.2814 |
78
- | 0.2569 | 4.8040 | 17304 | 0.2779 |
79
- | 0.2561 | 5.0042 | 18025 | 0.2708 |
80
- | 0.2299 | 5.2043 | 18746 | 0.2778 |
81
- | 0.2334 | 5.4045 | 19467 | 0.2704 |
82
- | 0.2324 | 5.6047 | 20188 | 0.2673 |
83
- | 0.2347 | 5.8048 | 20909 | 0.2644 |
84
- | 0.2358 | 6.0050 | 21630 | 0.2676 |
85
- | 0.2145 | 6.2052 | 22351 | 0.2634 |
86
- | 0.2141 | 6.4053 | 23072 | 0.2629 |
87
- | 0.2132 | 6.6055 | 23793 | 0.2610 |
88
- | 0.2159 | 6.8057 | 24514 | 0.2526 |
89
- | 0.2128 | 7.0058 | 25235 | 0.2550 |
90
- | 0.2016 | 7.2060 | 25956 | 0.2526 |
91
- | 0.1948 | 7.4062 | 26677 | 0.2528 |
92
- | 0.1946 | 7.6063 | 27398 | 0.2464 |
93
- | 0.1924 | 7.8065 | 28119 | 0.2483 |
94
- | 0.1947 | 8.0067 | 28840 | 0.2451 |
95
- | 0.1715 | 8.2068 | 29561 | 0.2471 |
96
- | 0.1741 | 8.4070 | 30282 | 0.2481 |
97
- | 0.1749 | 8.6072 | 31003 | 0.2408 |
98
- | 0.1746 | 8.8073 | 31724 | 0.2386 |
99
- | 0.1719 | 9.0075 | 32445 | 0.2454 |
100
- | 0.1521 | 9.2077 | 33166 | 0.2416 |
101
- | 0.152 | 9.4078 | 33887 | 0.2431 |
102
- | 0.155 | 9.6080 | 34608 | 0.2364 |
103
- | 0.156 | 9.8082 | 35329 | 0.2342 |
104
- | 0.1541 | 10.0083 | 36050 | 0.2376 |
105
- | 0.1345 | 10.2085 | 36771 | 0.2376 |
106
- | 0.1335 | 10.4087 | 37492 | 0.2393 |
107
- | 0.1351 | 10.6088 | 38213 | 0.2342 |
108
- | 0.1364 | 10.8090 | 38934 | 0.2354 |
109
- | 0.1335 | 11.0092 | 39655 | 0.2380 |
110
- | 0.122 | 11.2093 | 40376 | 0.2368 |
111
- | 0.1192 | 11.4095 | 41097 | 0.2406 |
112
- | 0.1204 | 11.6097 | 41818 | 0.2411 |
113
- | 0.1205 | 11.8098 | 42539 | 0.2394 |
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: 0.2817
20
 
21
  ## Model description
22
 
 
52
 
53
  | Training Loss | Epoch | Step | Validation Loss |
54
  |:-------------:|:-------:|:-----:|:---------------:|
55
+ | 0.6176 | 0.2001 | 720 | 0.5116 |
56
+ | 0.4965 | 0.4001 | 1440 | 0.4646 |
57
+ | 0.4307 | 0.6002 | 2160 | 0.4362 |
58
+ | 0.4144 | 0.8002 | 2880 | 0.4168 |
59
+ | 0.3977 | 1.0003 | 3600 | 0.4030 |
60
+ | 0.3632 | 1.2003 | 4320 | 0.3949 |
61
+ | 0.3596 | 1.4004 | 5040 | 0.3871 |
62
+ | 0.3571 | 1.6004 | 5760 | 0.3772 |
63
+ | 0.3509 | 1.8005 | 6480 | 0.3702 |
64
+ | 0.3437 | 2.0006 | 7200 | 0.3618 |
65
+ | 0.3249 | 2.2006 | 7920 | 0.3660 |
66
+ | 0.3214 | 2.4007 | 8640 | 0.3525 |
67
+ | 0.3149 | 2.6007 | 9360 | 0.3490 |
68
+ | 0.316 | 2.8008 | 10080 | 0.3403 |
69
+ | 0.315 | 3.0008 | 10800 | 0.3452 |
70
+ | 0.288 | 3.2009 | 11520 | 0.3454 |
71
+ | 0.2919 | 3.4009 | 12240 | 0.3368 |
72
+ | 0.2907 | 3.6010 | 12960 | 0.3342 |
73
+ | 0.2876 | 3.8011 | 13680 | 0.3282 |
74
+ | 0.2898 | 4.0011 | 14400 | 0.3280 |
75
+ | 0.2606 | 4.2012 | 15120 | 0.3285 |
76
+ | 0.2691 | 4.4012 | 15840 | 0.3259 |
77
+ | 0.2646 | 4.6013 | 16560 | 0.3245 |
78
+ | 0.2695 | 4.8013 | 17280 | 0.3110 |
79
+ | 0.263 | 5.0014 | 18000 | 0.3142 |
80
+ | 0.2415 | 5.2014 | 18720 | 0.3215 |
81
+ | 0.2428 | 5.4015 | 19440 | 0.3047 |
82
+ | 0.2448 | 5.6016 | 20160 | 0.3056 |
83
+ | 0.2458 | 5.8016 | 20880 | 0.3039 |
84
+ | 0.2416 | 6.0017 | 21600 | 0.3001 |
85
+ | 0.2236 | 6.2017 | 22320 | 0.3052 |
86
+ | 0.2247 | 6.4018 | 23040 | 0.2968 |
87
+ | 0.2232 | 6.6018 | 23760 | 0.2951 |
88
+ | 0.2231 | 6.8019 | 24480 | 0.2924 |
89
+ | 0.2207 | 7.0019 | 25200 | 0.2878 |
90
+ | 0.2058 | 7.2020 | 25920 | 0.2924 |
91
+ | 0.201 | 7.4021 | 26640 | 0.2952 |
92
+ | 0.2004 | 7.6021 | 27360 | 0.2898 |
93
+ | 0.2016 | 7.8022 | 28080 | 0.2772 |
94
+ | 0.205 | 8.0022 | 28800 | 0.2871 |
95
+ | 0.1808 | 8.2023 | 29520 | 0.2853 |
96
+ | 0.179 | 8.4023 | 30240 | 0.2801 |
97
+ | 0.1819 | 8.6024 | 30960 | 0.2835 |
98
+ | 0.1791 | 8.8024 | 31680 | 0.2744 |
99
+ | 0.1821 | 9.0025 | 32400 | 0.2749 |
100
+ | 0.1582 | 9.2026 | 33120 | 0.2867 |
101
+ | 0.1587 | 9.4026 | 33840 | 0.2798 |
102
+ | 0.1632 | 9.6027 | 34560 | 0.2796 |
103
+ | 0.161 | 9.8027 | 35280 | 0.2744 |
104
+ | 0.1586 | 10.0028 | 36000 | 0.2733 |
105
+ | 0.1397 | 10.2028 | 36720 | 0.2841 |
106
+ | 0.1411 | 10.4029 | 37440 | 0.2834 |
107
+ | 0.1411 | 10.6029 | 38160 | 0.2785 |
108
+ | 0.1419 | 10.8030 | 38880 | 0.2800 |
109
+ | 0.1425 | 11.0031 | 39600 | 0.2796 |
110
+ | 0.1274 | 11.2031 | 40320 | 0.2845 |
111
+ | 0.1258 | 11.4032 | 41040 | 0.2793 |
112
+ | 0.1244 | 11.6032 | 41760 | 0.2816 |
113
+ | 0.1229 | 11.8033 | 42480 | 0.2817 |
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 sha256:0506e48158229edd4ab9d71c03c5ed6eb63d0a7a436bd0b9d0065c9dd4e1d0e1
3
  size 268636736
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b8f571bdc8049a922208dea8436a2178b4903b63c74b90d2d67c0c11d6d9edd9
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 sha256:76c48cf9f267e391197f92c5e2582a388596ea034eab21af3425e33cf46093ac
3
  size 5496
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3cc5ed3b5757bb6d0e9b55efed3f952b65ca0f54c9ae60d34076f58d45e2ecc1
3
  size 5496