Hugging Face's logo

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

PEFT
Safetensors
Generated from Trainer
Model card Files Community
yalhessi commited on
Commit
d600997
·
verified ·
1 Parent(s): 11c4096

End of training

Browse files
Files changed (5) hide show
  1. README.md +122 -0
  2. adapter_config.json +32 -0
  3. adapter_model.safetensors +3 -0
  4. loss_plot.png +0 -0
  5. training_args.bin +3 -0
README.md ADDED
@@ -0,0 +1,122 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: peft
3
+ license: other
4
+ base_model: deepseek-ai/deepseek-coder-1.3b-base
5
+ tags:
6
+ - generated_from_trainer
7
+ model-index:
8
+ - name: lemexp-task1-v2-template_small_old_defs-deepseek-coder-1.3b-base-ddp-8lr-v2
9
+ results: []
10
+ ---
11
+
12
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
13
+ should probably proofread and complete it, then remove this comment. -->
14
+
15
+ # lemexp-task1-v2-template_small_old_defs-deepseek-coder-1.3b-base-ddp-8lr-v2
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: 0.1510
20
+
21
+ ## Model description
22
+
23
+ More information needed
24
+
25
+ ## Intended uses & limitations
26
+
27
+ More information needed
28
+
29
+ ## Training and evaluation data
30
+
31
+ More information needed
32
+
33
+ ## Training procedure
34
+
35
+ ### Training hyperparameters
36
+
37
+ The following hyperparameters were used during training:
38
+ - learning_rate: 0.0008
39
+ - train_batch_size: 2
40
+ - eval_batch_size: 2
41
+ - seed: 42
42
+ - distributed_type: multi-GPU
43
+ - num_devices: 8
44
+ - total_train_batch_size: 16
45
+ - total_eval_batch_size: 16
46
+ - optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
47
+ - lr_scheduler_type: linear
48
+ - num_epochs: 12
49
+ - mixed_precision_training: Native AMP
50
+
51
+ ### Training results
52
+
53
+ | Training Loss | Epoch | Step | Validation Loss |
54
+ |:-------------:|:-------:|:-----:|:---------------:|
55
+ | 0.425 | 0.2002 | 721 | 0.3080 |
56
+ | 0.3071 | 0.4003 | 1442 | 0.2725 |
57
+ | 0.2669 | 0.6005 | 2163 | 0.2568 |
58
+ | 0.2608 | 0.8007 | 2884 | 0.2484 |
59
+ | 0.2484 | 1.0008 | 3605 | 0.2393 |
60
+ | 0.2343 | 1.2010 | 4326 | 0.2373 |
61
+ | 0.2334 | 1.4012 | 5047 | 0.2319 |
62
+ | 0.2262 | 1.6013 | 5768 | 0.2233 |
63
+ | 0.2229 | 1.8015 | 6489 | 0.2282 |
64
+ | 0.2196 | 2.0017 | 7210 | 0.2183 |
65
+ | 0.2102 | 2.2018 | 7931 | 0.2168 |
66
+ | 0.2097 | 2.4020 | 8652 | 0.2109 |
67
+ | 0.2046 | 2.6022 | 9373 | 0.2026 |
68
+ | 0.2034 | 2.8023 | 10094 | 0.2002 |
69
+ | 0.2023 | 3.0025 | 10815 | 0.2004 |
70
+ | 0.1906 | 3.2027 | 11536 | 0.1974 |
71
+ | 0.1905 | 3.4028 | 12257 | 0.1967 |
72
+ | 0.1875 | 3.6030 | 12978 | 0.1944 |
73
+ | 0.1852 | 3.8032 | 13699 | 0.1932 |
74
+ | 0.1875 | 4.0033 | 14420 | 0.1944 |
75
+ | 0.1754 | 4.2035 | 15141 | 0.1863 |
76
+ | 0.175 | 4.4037 | 15862 | 0.1834 |
77
+ | 0.1747 | 4.6038 | 16583 | 0.1904 |
78
+ | 0.175 | 4.8040 | 17304 | 0.1841 |
79
+ | 0.1739 | 5.0042 | 18025 | 0.1820 |
80
+ | 0.1604 | 5.2043 | 18746 | 0.1812 |
81
+ | 0.1628 | 5.4045 | 19467 | 0.1794 |
82
+ | 0.1608 | 5.6047 | 20188 | 0.1802 |
83
+ | 0.161 | 5.8048 | 20909 | 0.1737 |
84
+ | 0.1596 | 6.0050 | 21630 | 0.1763 |
85
+ | 0.151 | 6.2052 | 22351 | 0.1731 |
86
+ | 0.1501 | 6.4053 | 23072 | 0.1703 |
87
+ | 0.1487 | 6.6055 | 23793 | 0.1684 |
88
+ | 0.149 | 6.8057 | 24514 | 0.1654 |
89
+ | 0.1474 | 7.0058 | 25235 | 0.1642 |
90
+ | 0.1389 | 7.2060 | 25956 | 0.1641 |
91
+ | 0.1387 | 7.4062 | 26677 | 0.1635 |
92
+ | 0.1361 | 7.6063 | 27398 | 0.1637 |
93
+ | 0.1357 | 7.8065 | 28119 | 0.1627 |
94
+ | 0.1358 | 8.0067 | 28840 | 0.1605 |
95
+ | 0.1225 | 8.2068 | 29561 | 0.1575 |
96
+ | 0.1245 | 8.4070 | 30282 | 0.1540 |
97
+ | 0.1232 | 8.6072 | 31003 | 0.1558 |
98
+ | 0.1238 | 8.8073 | 31724 | 0.1539 |
99
+ | 0.1231 | 9.0075 | 32445 | 0.1525 |
100
+ | 0.1094 | 9.2077 | 33166 | 0.1560 |
101
+ | 0.1091 | 9.4078 | 33887 | 0.1528 |
102
+ | 0.1105 | 9.6080 | 34608 | 0.1505 |
103
+ | 0.1101 | 9.8082 | 35329 | 0.1523 |
104
+ | 0.1106 | 10.0083 | 36050 | 0.1537 |
105
+ | 0.0975 | 10.2085 | 36771 | 0.1569 |
106
+ | 0.0963 | 10.4087 | 37492 | 0.1513 |
107
+ | 0.0981 | 10.6088 | 38213 | 0.1516 |
108
+ | 0.0966 | 10.8090 | 38934 | 0.1507 |
109
+ | 0.0959 | 11.0092 | 39655 | 0.1513 |
110
+ | 0.089 | 11.2093 | 40376 | 0.1534 |
111
+ | 0.0866 | 11.4095 | 41097 | 0.1549 |
112
+ | 0.0871 | 11.6097 | 41818 | 0.1522 |
113
+ | 0.0866 | 11.8098 | 42539 | 0.1510 |
114
+
115
+
116
+ ### Framework versions
117
+
118
+ - PEFT 0.14.0
119
+ - Transformers 4.47.0
120
+ - Pytorch 2.5.1+cu124
121
+ - Datasets 3.2.0
122
+ - Tokenizers 0.21.0
adapter_config.json ADDED
@@ -0,0 +1,32 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "deepseek-ai/deepseek-coder-1.3b-base",
5
+ "bias": "none",
6
+ "eva_config": null,
7
+ "exclude_modules": null,
8
+ "fan_in_fan_out": false,
9
+ "inference_mode": true,
10
+ "init_lora_weights": true,
11
+ "layer_replication": null,
12
+ "layers_pattern": null,
13
+ "layers_to_transform": null,
14
+ "loftq_config": {},
15
+ "lora_alpha": 32,
16
+ "lora_bias": false,
17
+ "lora_dropout": 0.05,
18
+ "megatron_config": null,
19
+ "megatron_core": "megatron.core",
20
+ "modules_to_save": null,
21
+ "peft_type": "LORA",
22
+ "r": 8,
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,
31
+ "use_rslora": false
32
+ }
adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:10bfeff2592c5e9f63514bffb0c0d7d5ff50594e07eb4c3e0a7f236edaf07483
3
+ size 268677696
loss_plot.png ADDED
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d8eb3d1ac6b526fc0d2a69cbe1fdfb567057f00c278c73ccfea6677d19ddefa0
3
+ size 5496