End of training
Browse files- README.md +122 -0
- adapter_config.json +32 -0
- adapter_model.safetensors +3 -0
- loss_plot.png +0 -0
- 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-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
|