Hugging Face's logo

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

PEFT
Safetensors
Generated from Trainer
Model card Files Community
yalhessi commited on
Commit
b9487c5
·
verified ·
1 Parent(s): e7627ae

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-template_full-deepseek-coder-1.3b-base-ddp-8lr
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-template_full-deepseek-coder-1.3b-base-ddp-8lr
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: 0.1734
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
+ | 0.3452 | 0.2000 | 2902 | 0.3366 |
56
+ | 0.3188 | 0.4001 | 5804 | 0.3166 |
57
+ | 0.3088 | 0.6001 | 8706 | 0.3066 |
58
+ | 0.2989 | 0.8001 | 11608 | 0.2897 |
59
+ | 0.296 | 1.0001 | 14510 | 0.2956 |
60
+ | 0.2886 | 1.2002 | 17412 | 0.2853 |
61
+ | 0.2838 | 1.4002 | 20314 | 0.2798 |
62
+ | 0.2836 | 1.6002 | 23216 | 0.2750 |
63
+ | 0.278 | 1.8002 | 26118 | 0.2719 |
64
+ | 0.2749 | 2.0003 | 29020 | 0.2711 |
65
+ | 0.2722 | 2.2003 | 31922 | 0.2696 |
66
+ | 0.2681 | 2.4003 | 34824 | 0.2643 |
67
+ | 0.2698 | 2.6004 | 37726 | 0.2591 |
68
+ | 0.2634 | 2.8004 | 40628 | 0.2585 |
69
+ | 0.2598 | 3.0004 | 43530 | 0.2632 |
70
+ | 0.2537 | 3.2004 | 46432 | 0.2581 |
71
+ | 0.2529 | 3.4005 | 49334 | 0.2516 |
72
+ | 0.2544 | 3.6005 | 52236 | 0.2481 |
73
+ | 0.2531 | 3.8005 | 55138 | 0.2475 |
74
+ | 0.2505 | 4.0006 | 58040 | 0.2523 |
75
+ | 0.2434 | 4.2006 | 60942 | 0.2439 |
76
+ | 0.2439 | 4.4006 | 63844 | 0.2396 |
77
+ | 0.2415 | 4.6006 | 66746 | 0.2358 |
78
+ | 0.2375 | 4.8007 | 69648 | 0.2346 |
79
+ | 0.2395 | 5.0007 | 72550 | 0.2391 |
80
+ | 0.2319 | 5.2007 | 75452 | 0.2318 |
81
+ | 0.2296 | 5.4007 | 78354 | 0.2310 |
82
+ | 0.2315 | 5.6008 | 81256 | 0.2277 |
83
+ | 0.2264 | 5.8008 | 84158 | 0.2249 |
84
+ | 0.2246 | 6.0008 | 87060 | 0.2228 |
85
+ | 0.2196 | 6.2009 | 89962 | 0.2217 |
86
+ | 0.216 | 6.4009 | 92864 | 0.2182 |
87
+ | 0.2181 | 6.6009 | 95766 | 0.2181 |
88
+ | 0.2156 | 6.8009 | 98668 | 0.2180 |
89
+ | 0.2144 | 7.0010 | 101570 | 0.2139 |
90
+ | 0.2063 | 7.2010 | 104472 | 0.2130 |
91
+ | 0.2055 | 7.4010 | 107374 | 0.2101 |
92
+ | 0.2051 | 7.6010 | 110276 | 0.2074 |
93
+ | 0.2058 | 7.8011 | 113178 | 0.2065 |
94
+ | 0.2037 | 8.0011 | 116080 | 0.2044 |
95
+ | 0.1965 | 8.2011 | 118982 | 0.2010 |
96
+ | 0.1935 | 8.4012 | 121884 | 0.2014 |
97
+ | 0.1945 | 8.6012 | 124786 | 0.1984 |
98
+ | 0.1916 | 8.8012 | 127688 | 0.1983 |
99
+ | 0.19 | 9.0012 | 130590 | 0.1946 |
100
+ | 0.182 | 9.2013 | 133492 | 0.1936 |
101
+ | 0.1831 | 9.4013 | 136394 | 0.1905 |
102
+ | 0.1831 | 9.6013 | 139296 | 0.1874 |
103
+ | 0.1779 | 9.8014 | 142198 | 0.1892 |
104
+ | 0.1781 | 10.0014 | 145100 | 0.1873 |
105
+ | 0.1706 | 10.2014 | 148002 | 0.1840 |
106
+ | 0.1678 | 10.4014 | 150904 | 0.1832 |
107
+ | 0.168 | 10.6015 | 153806 | 0.1817 |
108
+ | 0.1675 | 10.8015 | 156708 | 0.1791 |
109
+ | 0.165 | 11.0015 | 159610 | 0.1767 |
110
+ | 0.1572 | 11.2015 | 162512 | 0.1780 |
111
+ | 0.1566 | 11.4016 | 165414 | 0.1770 |
112
+ | 0.1563 | 11.6016 | 168316 | 0.1738 |
113
+ | 0.1549 | 11.8016 | 171218 | 0.1734 |
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
+ "q_proj",
27
+ "v_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 sha256:4fe538ed48e03ef73df208ea98ad0edd6677afe9244928af321a739dc17c7757
3
+ size 6304096
loss_plot.png ADDED
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a95bbcd9b847e6f84db4dbc79007a4cfe4fa7e533b83cc7ef69380a66d974730
3
+ size 5432