Hugging Face's logo

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

PEFT
Safetensors
Generated from Trainer
Model card Files Community
yalhessi commited on
Commit
3c46d0a
·
verified ·
1 Parent(s): c187c39

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-lemma_command_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-lemma_command_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: 0.4320
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
+ | 0.7149 | 0.2 | 2121 | 0.6754 |
56
+ | 0.684 | 0.4 | 4242 | 0.6408 |
57
+ | 0.6664 | 0.6 | 6363 | 0.6271 |
58
+ | 0.6568 | 0.8 | 8484 | 0.6106 |
59
+ | 0.6445 | 1.0 | 10605 | 0.6016 |
60
+ | 0.6188 | 1.2 | 12726 | 0.5927 |
61
+ | 0.618 | 1.4 | 14847 | 0.5864 |
62
+ | 0.6161 | 1.6 | 16968 | 0.5864 |
63
+ | 0.6239 | 1.8 | 19089 | 0.5779 |
64
+ | 0.6126 | 2.0 | 21210 | 0.5764 |
65
+ | 0.5882 | 2.2 | 23331 | 0.5680 |
66
+ | 0.5955 | 2.4 | 25452 | 0.5647 |
67
+ | 0.5858 | 2.6 | 27573 | 0.5615 |
68
+ | 0.5882 | 2.8 | 29694 | 0.5574 |
69
+ | 0.5819 | 3.0 | 31815 | 0.5504 |
70
+ | 0.5759 | 3.2 | 33936 | 0.5544 |
71
+ | 0.5647 | 3.4 | 36057 | 0.5479 |
72
+ | 0.5687 | 3.6 | 38178 | 0.5458 |
73
+ | 0.5692 | 3.8 | 40299 | 0.5415 |
74
+ | 0.5633 | 4.0 | 42420 | 0.5398 |
75
+ | 0.5489 | 4.2 | 44541 | 0.5299 |
76
+ | 0.5482 | 4.4 | 46662 | 0.5246 |
77
+ | 0.5443 | 4.6 | 48783 | 0.5246 |
78
+ | 0.5466 | 4.8 | 50904 | 0.5225 |
79
+ | 0.5464 | 5.0 | 53025 | 0.5157 |
80
+ | 0.5249 | 5.2 | 55146 | 0.5203 |
81
+ | 0.5323 | 5.4 | 57267 | 0.5115 |
82
+ | 0.5227 | 5.6 | 59388 | 0.5075 |
83
+ | 0.5277 | 5.8 | 61509 | 0.5074 |
84
+ | 0.5214 | 6.0 | 63630 | 0.5040 |
85
+ | 0.5115 | 6.2 | 65751 | 0.4969 |
86
+ | 0.5088 | 6.4 | 67872 | 0.4950 |
87
+ | 0.511 | 6.6 | 69993 | 0.4912 |
88
+ | 0.5097 | 6.8 | 72114 | 0.4892 |
89
+ | 0.5024 | 7.0 | 74235 | 0.4877 |
90
+ | 0.4842 | 7.2 | 76356 | 0.4860 |
91
+ | 0.484 | 7.4 | 78477 | 0.4832 |
92
+ | 0.493 | 7.6 | 80598 | 0.4816 |
93
+ | 0.4863 | 7.8 | 82719 | 0.4759 |
94
+ | 0.4878 | 8.0 | 84840 | 0.4672 |
95
+ | 0.4644 | 8.2 | 86961 | 0.4705 |
96
+ | 0.4648 | 8.4 | 89082 | 0.4654 |
97
+ | 0.4663 | 8.6 | 91203 | 0.4612 |
98
+ | 0.4715 | 8.8 | 93324 | 0.4636 |
99
+ | 0.4669 | 9.0 | 95445 | 0.4591 |
100
+ | 0.4451 | 9.2 | 97566 | 0.4586 |
101
+ | 0.4457 | 9.4 | 99687 | 0.4580 |
102
+ | 0.4538 | 9.6 | 101808 | 0.4495 |
103
+ | 0.4489 | 9.8 | 103929 | 0.4492 |
104
+ | 0.4466 | 10.0 | 106050 | 0.4458 |
105
+ | 0.4252 | 10.2 | 108171 | 0.4470 |
106
+ | 0.4226 | 10.4 | 110292 | 0.4456 |
107
+ | 0.4244 | 10.6 | 112413 | 0.4402 |
108
+ | 0.4226 | 10.8 | 114534 | 0.4374 |
109
+ | 0.4203 | 11.0 | 116655 | 0.4352 |
110
+ | 0.4124 | 11.2 | 118776 | 0.4361 |
111
+ | 0.4039 | 11.4 | 120897 | 0.4340 |
112
+ | 0.405 | 11.6 | 123018 | 0.4321 |
113
+ | 0.4083 | 11.8 | 125139 | 0.4314 |
114
+ | 0.4025 | 12.0 | 127260 | 0.4320 |
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
+ "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 sha256:51a928eba8e58ff9f15d2ad03e2d3af05ca94aa157b5db3a3f61930473fc860f
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:e1687a91da73e009c8ca0c9343becff8c6cfe717f692ee1a8da722de67a67c37
3
+ size 5496