Hugging Face's logo

yalhessi
/
lemexp-task1-min_symbols_template_full-deepseek-coder-1.3b-base-ddp-12lr

PEFT
Safetensors
Generated from Trainer
Model card Files
xet
Community
yalhessi commited on
Commit
ffc8638
·
verified ·
1 Parent(s): 94d116f

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-min_symbols_template_full-deepseek-coder-1.3b-base-ddp-12lr
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-min_symbols_template_full-deepseek-coder-1.3b-base-ddp-12lr
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: 0.1895
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: 0.0012
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
+ | 0.387 | 0.2000 | 2907 | 0.3682 |
56
+ | 0.3641 | 0.4001 | 5814 | 0.3537 |
57
+ | 0.3563 | 0.6001 | 8721 | 0.3494 |
58
+ | 0.3467 | 0.8001 | 11628 | 0.3382 |
59
+ | 0.3373 | 1.0001 | 14535 | 0.3465 |
60
+ | 0.3347 | 1.2002 | 17442 | 0.3315 |
61
+ | 0.3396 | 1.4002 | 20349 | 0.3322 |
62
+ | 0.3317 | 1.6002 | 23256 | 0.3243 |
63
+ | 0.3245 | 1.8002 | 26163 | 0.3237 |
64
+ | 0.3219 | 2.0003 | 29070 | 0.3167 |
65
+ | 0.3166 | 2.2003 | 31977 | 0.3250 |
66
+ | 0.3179 | 2.4003 | 34884 | 0.3165 |
67
+ | 0.3142 | 2.6004 | 37791 | 0.3107 |
68
+ | 0.3102 | 2.8004 | 40698 | 0.3038 |
69
+ | 0.3094 | 3.0004 | 43605 | 0.3081 |
70
+ | 0.3039 | 3.2004 | 46512 | 0.2971 |
71
+ | 0.3023 | 3.4005 | 49419 | 0.2910 |
72
+ | 0.297 | 3.6005 | 52326 | 0.2912 |
73
+ | 0.2947 | 3.8005 | 55233 | 0.2958 |
74
+ | 0.2925 | 4.0006 | 58140 | 0.2862 |
75
+ | 0.2848 | 4.2006 | 61047 | 0.2842 |
76
+ | 0.2842 | 4.4006 | 63954 | 0.2797 |
77
+ | 0.2815 | 4.6006 | 66861 | 0.2815 |
78
+ | 0.2795 | 4.8007 | 69768 | 0.2784 |
79
+ | 0.2735 | 5.0007 | 72675 | 0.2715 |
80
+ | 0.2685 | 5.2007 | 75582 | 0.2766 |
81
+ | 0.2698 | 5.4007 | 78489 | 0.2687 |
82
+ | 0.268 | 5.6008 | 81396 | 0.2648 |
83
+ | 0.2623 | 5.8008 | 84303 | 0.2647 |
84
+ | 0.2613 | 6.0008 | 87210 | 0.2587 |
85
+ | 0.2568 | 6.2009 | 90117 | 0.2573 |
86
+ | 0.2544 | 6.4009 | 93024 | 0.2553 |
87
+ | 0.2519 | 6.6009 | 95931 | 0.2518 |
88
+ | 0.2514 | 6.8009 | 98838 | 0.2525 |
89
+ | 0.2519 | 7.0010 | 101745 | 0.2512 |
90
+ | 0.239 | 7.2010 | 104652 | 0.2441 |
91
+ | 0.2407 | 7.4010 | 107559 | 0.2456 |
92
+ | 0.2397 | 7.6010 | 110466 | 0.2433 |
93
+ | 0.2342 | 7.8011 | 113373 | 0.2364 |
94
+ | 0.2329 | 8.0011 | 116280 | 0.2316 |
95
+ | 0.2232 | 8.2011 | 119187 | 0.2307 |
96
+ | 0.2213 | 8.4012 | 122094 | 0.2294 |
97
+ | 0.2223 | 8.6012 | 125001 | 0.2230 |
98
+ | 0.2199 | 8.8012 | 127908 | 0.2216 |
99
+ | 0.2174 | 9.0012 | 130815 | 0.2211 |
100
+ | 0.208 | 9.2013 | 133722 | 0.2193 |
101
+ | 0.2089 | 9.4013 | 136629 | 0.2162 |
102
+ | 0.2047 | 9.6013 | 139536 | 0.2120 |
103
+ | 0.2028 | 9.8013 | 142443 | 0.2098 |
104
+ | 0.2005 | 10.0014 | 145350 | 0.2064 |
105
+ | 0.1923 | 10.2014 | 148257 | 0.2040 |
106
+ | 0.1926 | 10.4014 | 151164 | 0.2023 |
107
+ | 0.1887 | 10.6015 | 154071 | 0.2010 |
108
+ | 0.1883 | 10.8015 | 156978 | 0.2004 |
109
+ | 0.1865 | 11.0015 | 159885 | 0.1963 |
110
+ | 0.1769 | 11.2015 | 162792 | 0.1954 |
111
+ | 0.1744 | 11.4016 | 165699 | 0.1928 |
112
+ | 0.1721 | 11.6016 | 168606 | 0.1914 |
113
+ | 0.1711 | 11.8016 | 171513 | 0.1895 |
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:e748e2a18337b8a316f9d9ceb13f55fcc605918a4a572f43d40fa96a5c0c34fe
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 sha256:1dd8a15b9537c2abe3b87057f1680c7469d1cf19cd13041125fa8a5a07935720
3
+ size 5496