Hugging Face's logo

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

PEFT
Safetensors
Generated from Trainer
Model card Files
xet
Community
yalhessi commited on
Commit
7b8a6f3
·
verified ·
1 Parent(s): 0f58bb5

End of training

Browse files
Files changed (5) hide show
  1. README.md +123 -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 +1,123 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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-lemma_object_full_nodefs-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-lemma_object_full_nodefs-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: 0.2426
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
+ | 0.5096 | 0.2 | 3094 | 0.5142 |
56
+ | 0.4699 | 0.4 | 6188 | 0.4815 |
57
+ | 0.4503 | 0.6 | 9282 | 0.4479 |
58
+ | 0.4359 | 0.8 | 12376 | 0.4406 |
59
+ | 0.4266 | 1.0 | 15470 | 0.4249 |
60
+ | 0.4181 | 1.2 | 18564 | 0.4146 |
61
+ | 0.4126 | 1.4 | 21658 | 0.4122 |
62
+ | 0.4076 | 1.6 | 24752 | 0.4043 |
63
+ | 0.4022 | 1.8 | 27846 | 0.4012 |
64
+ | 0.3969 | 2.0 | 30940 | 0.3975 |
65
+ | 0.3874 | 2.2 | 34034 | 0.3964 |
66
+ | 0.3865 | 2.4 | 37128 | 0.3813 |
67
+ | 0.379 | 2.6 | 40222 | 0.3783 |
68
+ | 0.3772 | 2.8 | 43316 | 0.3750 |
69
+ | 0.3735 | 3.0 | 46410 | 0.3765 |
70
+ | 0.3637 | 3.2 | 49504 | 0.3659 |
71
+ | 0.3669 | 3.4 | 52598 | 0.3610 |
72
+ | 0.3577 | 3.6 | 55692 | 0.3615 |
73
+ | 0.3578 | 3.8 | 58786 | 0.3567 |
74
+ | 0.3563 | 4.0 | 61880 | 0.3510 |
75
+ | 0.3442 | 4.2 | 64974 | 0.3461 |
76
+ | 0.3403 | 4.4 | 68068 | 0.3428 |
77
+ | 0.3385 | 4.6 | 71162 | 0.3442 |
78
+ | 0.3309 | 4.8 | 74256 | 0.3399 |
79
+ | 0.3271 | 5.0 | 77350 | 0.3290 |
80
+ | 0.3225 | 5.2 | 80444 | 0.3299 |
81
+ | 0.3241 | 5.4 | 83538 | 0.3253 |
82
+ | 0.321 | 5.6 | 86632 | 0.3258 |
83
+ | 0.3168 | 5.8 | 89726 | 0.3225 |
84
+ | 0.3117 | 6.0 | 92820 | 0.3182 |
85
+ | 0.2992 | 6.2 | 95914 | 0.3187 |
86
+ | 0.2985 | 6.4 | 99008 | 0.3104 |
87
+ | 0.2975 | 6.6 | 102102 | 0.3072 |
88
+ | 0.3021 | 6.8 | 105196 | 0.3018 |
89
+ | 0.2921 | 7.0 | 108290 | 0.3012 |
90
+ | 0.2807 | 7.2 | 111384 | 0.2967 |
91
+ | 0.2758 | 7.4 | 114478 | 0.2962 |
92
+ | 0.2807 | 7.6 | 117572 | 0.2932 |
93
+ | 0.2786 | 7.8 | 120666 | 0.2901 |
94
+ | 0.2778 | 8.0 | 123760 | 0.2846 |
95
+ | 0.2632 | 8.2 | 126854 | 0.2863 |
96
+ | 0.262 | 8.4 | 129948 | 0.2809 |
97
+ | 0.2611 | 8.6 | 133042 | 0.2828 |
98
+ | 0.2648 | 8.8 | 136136 | 0.2762 |
99
+ | 0.2632 | 9.0 | 139230 | 0.2730 |
100
+ | 0.2461 | 9.2 | 142324 | 0.2676 |
101
+ | 0.2443 | 9.4 | 145418 | 0.2669 |
102
+ | 0.2435 | 9.6 | 148512 | 0.2655 |
103
+ | 0.2431 | 9.8 | 151606 | 0.2631 |
104
+ | 0.2379 | 10.0 | 154700 | 0.2599 |
105
+ | 0.2275 | 10.2 | 157794 | 0.2583 |
106
+ | 0.2281 | 10.4 | 160888 | 0.2570 |
107
+ | 0.2243 | 10.6 | 163982 | 0.2530 |
108
+ | 0.2222 | 10.8 | 167076 | 0.2541 |
109
+ | 0.2219 | 11.0 | 170170 | 0.2494 |
110
+ | 0.2112 | 11.2 | 173264 | 0.2495 |
111
+ | 0.2077 | 11.4 | 176358 | 0.2471 |
112
+ | 0.2065 | 11.6 | 179452 | 0.2451 |
113
+ | 0.2029 | 11.8 | 182546 | 0.2432 |
114
+ | 0.2073 | 12.0 | 185640 | 0.2426 |
115
+
116
+
117
+ ### Framework versions
118
+
119
+ - PEFT 0.14.0
120
+ - Transformers 4.47.0
121
+ - Pytorch 2.5.1+cu124
122
+ - Datasets 3.2.0
123
+ - 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 sha256:855a3f75177fe8aec35d18d46aabbdd89a68ebaa6ea5a6e1568cba3be35b4887
3
+ size 268636736
loss_plot.png ADDED
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d98eab5c25087ab2ed8d9c27bb695bca92e33951e4ca6afad357a37bf10cffc5
3
+ size 5432