yalhessi commited on
Commit
5a71d75
·
verified ·
1 Parent(s): d98f7eb

End of training

Browse files
README.md ADDED
@@ -0,0 +1,92 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
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
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: 0.1978
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: 0.001
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: 6
49
+ - mixed_precision_training: Native AMP
50
+
51
+ ### Training results
52
+
53
+ | Training Loss | Epoch | Step | Validation Loss |
54
+ |:-------------:|:------:|:-----:|:---------------:|
55
+ | 0.3666 | 0.2000 | 2907 | 0.3499 |
56
+ | 0.3395 | 0.4001 | 5814 | 0.3318 |
57
+ | 0.3267 | 0.6001 | 8721 | 0.3205 |
58
+ | 0.3174 | 0.8001 | 11628 | 0.3100 |
59
+ | 0.305 | 1.0001 | 14535 | 0.3098 |
60
+ | 0.3004 | 1.2002 | 17442 | 0.2988 |
61
+ | 0.3017 | 1.4002 | 20349 | 0.2947 |
62
+ | 0.2912 | 1.6002 | 23256 | 0.2879 |
63
+ | 0.2843 | 1.8002 | 26163 | 0.2795 |
64
+ | 0.2793 | 2.0003 | 29070 | 0.2770 |
65
+ | 0.27 | 2.2003 | 31977 | 0.2737 |
66
+ | 0.2697 | 2.4003 | 34884 | 0.2725 |
67
+ | 0.2641 | 2.6004 | 37791 | 0.2652 |
68
+ | 0.2586 | 2.8004 | 40698 | 0.2608 |
69
+ | 0.2564 | 3.0004 | 43605 | 0.2545 |
70
+ | 0.2464 | 3.2004 | 46512 | 0.2516 |
71
+ | 0.2428 | 3.4005 | 49419 | 0.2442 |
72
+ | 0.2395 | 3.6005 | 52326 | 0.2403 |
73
+ | 0.234 | 3.8005 | 55233 | 0.2367 |
74
+ | 0.2299 | 4.0006 | 58140 | 0.2311 |
75
+ | 0.2178 | 4.2006 | 61047 | 0.2271 |
76
+ | 0.2163 | 4.4006 | 63954 | 0.2227 |
77
+ | 0.2114 | 4.6006 | 66861 | 0.2175 |
78
+ | 0.2083 | 4.8007 | 69768 | 0.2150 |
79
+ | 0.2026 | 5.0007 | 72675 | 0.2100 |
80
+ | 0.1907 | 5.2007 | 75582 | 0.2065 |
81
+ | 0.1893 | 5.4007 | 78489 | 0.2020 |
82
+ | 0.1874 | 5.6008 | 81396 | 0.1982 |
83
+ | 0.1812 | 5.8008 | 84303 | 0.1978 |
84
+
85
+
86
+ ### Framework versions
87
+
88
+ - PEFT 0.14.0
89
+ - Transformers 4.47.0
90
+ - Pytorch 2.5.1+cu124
91
+ - Datasets 3.2.0
92
+ - 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:cdea246926c32bea9c74fb6333aba32b9b8fddb14668be7f1464b3275bf8dc7f
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:a6ac149eb5cae900414d30cced6c63e90e74b140dbff035c8034897e99e8c15e
3
+ size 5496