Hugging Face's logo

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

PEFT
Safetensors
Generated from Trainer
Model card Files Community
yalhessi commited on
Commit
89bef91
·
verified ·
1 Parent(s): e11872c

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_lemma_command_small-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-min_symbols_lemma_command_small-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: 0.5344
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
+ | 0.8566 | 0.2001 | 629 | 0.7667 |
56
+ | 0.7528 | 0.4001 | 1258 | 0.7298 |
57
+ | 0.7249 | 0.6002 | 1887 | 0.6923 |
58
+ | 0.6818 | 0.8003 | 2516 | 0.6711 |
59
+ | 0.6704 | 1.0003 | 3145 | 0.6628 |
60
+ | 0.634 | 1.2004 | 3774 | 0.6499 |
61
+ | 0.624 | 1.4004 | 4403 | 0.6382 |
62
+ | 0.6095 | 1.6005 | 5032 | 0.6322 |
63
+ | 0.6141 | 1.8006 | 5661 | 0.6245 |
64
+ | 0.6067 | 2.0006 | 6290 | 0.6177 |
65
+ | 0.5957 | 2.2007 | 6919 | 0.6074 |
66
+ | 0.5754 | 2.4008 | 7548 | 0.6158 |
67
+ | 0.5699 | 2.6008 | 8177 | 0.6045 |
68
+ | 0.576 | 2.8009 | 8806 | 0.6049 |
69
+ | 0.5713 | 3.0010 | 9435 | 0.5948 |
70
+ | 0.5298 | 3.2010 | 10064 | 0.5902 |
71
+ | 0.5411 | 3.4011 | 10693 | 0.5856 |
72
+ | 0.5377 | 3.6011 | 11322 | 0.5857 |
73
+ | 0.5387 | 3.8012 | 11951 | 0.5770 |
74
+ | 0.5334 | 4.0013 | 12580 | 0.5752 |
75
+ | 0.5052 | 4.2013 | 13209 | 0.5729 |
76
+ | 0.4976 | 4.4014 | 13838 | 0.5732 |
77
+ | 0.5091 | 4.6015 | 14467 | 0.5684 |
78
+ | 0.5019 | 4.8015 | 15096 | 0.5618 |
79
+ | 0.513 | 5.0016 | 15725 | 0.5605 |
80
+ | 0.4797 | 5.2017 | 16354 | 0.5728 |
81
+ | 0.4736 | 5.4017 | 16983 | 0.5593 |
82
+ | 0.4806 | 5.6018 | 17612 | 0.5633 |
83
+ | 0.4747 | 5.8018 | 18241 | 0.5611 |
84
+ | 0.4861 | 6.0019 | 18870 | 0.5459 |
85
+ | 0.4612 | 6.2020 | 19499 | 0.5555 |
86
+ | 0.444 | 6.4020 | 20128 | 0.5491 |
87
+ | 0.4413 | 6.6021 | 20757 | 0.5448 |
88
+ | 0.4481 | 6.8022 | 21386 | 0.5351 |
89
+ | 0.456 | 7.0022 | 22015 | 0.5412 |
90
+ | 0.4159 | 7.2023 | 22644 | 0.5415 |
91
+ | 0.4152 | 7.4024 | 23273 | 0.5381 |
92
+ | 0.422 | 7.6024 | 23902 | 0.5391 |
93
+ | 0.416 | 7.8025 | 24531 | 0.5359 |
94
+ | 0.4199 | 8.0025 | 25160 | 0.5295 |
95
+ | 0.3962 | 8.2026 | 25789 | 0.5408 |
96
+ | 0.3882 | 8.4027 | 26418 | 0.5318 |
97
+ | 0.3887 | 8.6027 | 27047 | 0.5306 |
98
+ | 0.3863 | 8.8028 | 27676 | 0.5246 |
99
+ | 0.3907 | 9.0029 | 28305 | 0.5309 |
100
+ | 0.3755 | 9.2029 | 28934 | 0.5318 |
101
+ | 0.3624 | 9.4030 | 29563 | 0.5293 |
102
+ | 0.359 | 9.6031 | 30192 | 0.5299 |
103
+ | 0.3612 | 9.8031 | 30821 | 0.5245 |
104
+ | 0.3612 | 10.0032 | 31450 | 0.5306 |
105
+ | 0.3345 | 10.2032 | 32079 | 0.5326 |
106
+ | 0.3327 | 10.4033 | 32708 | 0.5267 |
107
+ | 0.3369 | 10.6034 | 33337 | 0.5266 |
108
+ | 0.3353 | 10.8034 | 33966 | 0.5238 |
109
+ | 0.3304 | 11.0035 | 34595 | 0.5254 |
110
+ | 0.3132 | 11.2036 | 35224 | 0.5342 |
111
+ | 0.3082 | 11.4036 | 35853 | 0.5331 |
112
+ | 0.3088 | 11.6037 | 36482 | 0.5356 |
113
+ | 0.3125 | 11.8038 | 37111 | 0.5344 |
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:b6581ff8ad5334dd1a0cd2739ed563eab52a01d8df628ac3c88f0b6cba2e8ed7
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 sha256:29d1d0b3fddd537c848d564a150a22fdda023b0541340c978e69d07d4e8bffd0
3
+ size 5496