yalhessi commited on
Commit
5af4d1a
·
verified ·
1 Parent(s): 90d0057

End of training

Browse files
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-task3-v2-small_no_defs-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-task3-v2-small_no_defs-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: 0.1245
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
+ | 0.4237 | 0.2001 | 720 | 0.2939 |
56
+ | 0.2873 | 0.4001 | 1440 | 0.2619 |
57
+ | 0.2345 | 0.6002 | 2160 | 0.2396 |
58
+ | 0.2212 | 0.8002 | 2880 | 0.2263 |
59
+ | 0.2041 | 1.0003 | 3600 | 0.2142 |
60
+ | 0.1872 | 1.2003 | 4320 | 0.2103 |
61
+ | 0.1829 | 1.4004 | 5040 | 0.1951 |
62
+ | 0.1807 | 1.6004 | 5760 | 0.1921 |
63
+ | 0.1776 | 1.8005 | 6480 | 0.1884 |
64
+ | 0.1759 | 2.0006 | 7200 | 0.1840 |
65
+ | 0.1658 | 2.2006 | 7920 | 0.1791 |
66
+ | 0.1627 | 2.4007 | 8640 | 0.1727 |
67
+ | 0.1574 | 2.6007 | 9360 | 0.1716 |
68
+ | 0.1571 | 2.8008 | 10080 | 0.1727 |
69
+ | 0.1549 | 3.0008 | 10800 | 0.1675 |
70
+ | 0.1441 | 3.2009 | 11520 | 0.1620 |
71
+ | 0.1447 | 3.4009 | 12240 | 0.1606 |
72
+ | 0.1433 | 3.6010 | 12960 | 0.1668 |
73
+ | 0.1409 | 3.8011 | 13680 | 0.1674 |
74
+ | 0.1415 | 4.0011 | 14400 | 0.1585 |
75
+ | 0.1282 | 4.2012 | 15120 | 0.1583 |
76
+ | 0.1332 | 4.4012 | 15840 | 0.1567 |
77
+ | 0.1296 | 4.6013 | 16560 | 0.1559 |
78
+ | 0.1332 | 4.8013 | 17280 | 0.1477 |
79
+ | 0.1268 | 5.0014 | 18000 | 0.1507 |
80
+ | 0.1176 | 5.2014 | 18720 | 0.1490 |
81
+ | 0.1166 | 5.4015 | 19440 | 0.1494 |
82
+ | 0.1196 | 5.6016 | 20160 | 0.1442 |
83
+ | 0.1193 | 5.8016 | 20880 | 0.1416 |
84
+ | 0.1156 | 6.0017 | 21600 | 0.1390 |
85
+ | 0.1067 | 6.2017 | 22320 | 0.1446 |
86
+ | 0.1069 | 6.4018 | 23040 | 0.1418 |
87
+ | 0.1085 | 6.6018 | 23760 | 0.1385 |
88
+ | 0.1062 | 6.8019 | 24480 | 0.1312 |
89
+ | 0.1074 | 7.0019 | 25200 | 0.1343 |
90
+ | 0.0986 | 7.2020 | 25920 | 0.1362 |
91
+ | 0.0965 | 7.4021 | 26640 | 0.1360 |
92
+ | 0.0967 | 7.6021 | 27360 | 0.1335 |
93
+ | 0.0955 | 7.8022 | 28080 | 0.1275 |
94
+ | 0.0986 | 8.0022 | 28800 | 0.1328 |
95
+ | 0.0876 | 8.2023 | 29520 | 0.1348 |
96
+ | 0.0867 | 8.4023 | 30240 | 0.1314 |
97
+ | 0.087 | 8.6024 | 30960 | 0.1290 |
98
+ | 0.0863 | 8.8024 | 31680 | 0.1261 |
99
+ | 0.087 | 9.0025 | 32400 | 0.1244 |
100
+ | 0.0775 | 9.2026 | 33120 | 0.1293 |
101
+ | 0.0768 | 9.4026 | 33840 | 0.1260 |
102
+ | 0.0797 | 9.6027 | 34560 | 0.1277 |
103
+ | 0.0779 | 9.8027 | 35280 | 0.1234 |
104
+ | 0.0765 | 10.0028 | 36000 | 0.1230 |
105
+ | 0.0692 | 10.2028 | 36720 | 0.1267 |
106
+ | 0.0697 | 10.4029 | 37440 | 0.1259 |
107
+ | 0.0691 | 10.6029 | 38160 | 0.1263 |
108
+ | 0.0692 | 10.8030 | 38880 | 0.1229 |
109
+ | 0.0694 | 11.0031 | 39600 | 0.1227 |
110
+ | 0.0647 | 11.2031 | 40320 | 0.1255 |
111
+ | 0.0632 | 11.4032 | 41040 | 0.1250 |
112
+ | 0.0636 | 11.6032 | 41760 | 0.1260 |
113
+ | 0.0626 | 11.8033 | 42480 | 0.1245 |
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 sha256:99bd3081516b1652755be7b24f591e172f7fee70ce97c321e7c4632116e572c6
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 sha256:709024167f5110ea35f5e755889e200cafc20822b15b2093bab55e1d9994dcfe
3
+ size 5496