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-task1-v3-template_small_notypes-deepseek-coder-1.3b-base-8lr-12epochs-normal-eos
|
| 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-v3-template_small_notypes-deepseek-coder-1.3b-base-8lr-12epochs-normal-eos
|
| 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: 0.1698
|
| 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 |
+
| 0.43 | 0.2001 | 720 | 0.3401 |
|
| 56 |
+
| 0.3227 | 0.4001 | 1440 | 0.2910 |
|
| 57 |
+
| 0.2819 | 0.6002 | 2160 | 0.2751 |
|
| 58 |
+
| 0.2714 | 0.8002 | 2880 | 0.2636 |
|
| 59 |
+
| 0.2595 | 1.0003 | 3600 | 0.2653 |
|
| 60 |
+
| 0.2446 | 1.2003 | 4320 | 0.2640 |
|
| 61 |
+
| 0.2403 | 1.4004 | 5040 | 0.2476 |
|
| 62 |
+
| 0.2347 | 1.6004 | 5760 | 0.2459 |
|
| 63 |
+
| 0.235 | 1.8005 | 6480 | 0.2404 |
|
| 64 |
+
| 0.2278 | 2.0006 | 7200 | 0.2361 |
|
| 65 |
+
| 0.2191 | 2.2006 | 7920 | 0.2371 |
|
| 66 |
+
| 0.2162 | 2.4007 | 8640 | 0.2295 |
|
| 67 |
+
| 0.2117 | 2.6007 | 9360 | 0.2241 |
|
| 68 |
+
| 0.2106 | 2.8008 | 10080 | 0.2220 |
|
| 69 |
+
| 0.2112 | 3.0008 | 10800 | 0.2189 |
|
| 70 |
+
| 0.1977 | 3.2009 | 11520 | 0.2220 |
|
| 71 |
+
| 0.1992 | 3.4009 | 12240 | 0.2206 |
|
| 72 |
+
| 0.1942 | 3.6010 | 12960 | 0.2162 |
|
| 73 |
+
| 0.1937 | 3.8011 | 13680 | 0.2136 |
|
| 74 |
+
| 0.1947 | 4.0011 | 14400 | 0.2068 |
|
| 75 |
+
| 0.1813 | 4.2012 | 15120 | 0.2078 |
|
| 76 |
+
| 0.1831 | 4.4012 | 15840 | 0.2086 |
|
| 77 |
+
| 0.18 | 4.6013 | 16560 | 0.2040 |
|
| 78 |
+
| 0.1805 | 4.8013 | 17280 | 0.2126 |
|
| 79 |
+
| 0.177 | 5.0014 | 18000 | 0.2038 |
|
| 80 |
+
| 0.1662 | 5.2014 | 18720 | 0.2037 |
|
| 81 |
+
| 0.1665 | 5.4015 | 19440 | 0.2010 |
|
| 82 |
+
| 0.1682 | 5.6016 | 20160 | 0.1968 |
|
| 83 |
+
| 0.1686 | 5.8016 | 20880 | 0.1924 |
|
| 84 |
+
| 0.164 | 6.0017 | 21600 | 0.1909 |
|
| 85 |
+
| 0.1547 | 6.2017 | 22320 | 0.1906 |
|
| 86 |
+
| 0.1553 | 6.4018 | 23040 | 0.1864 |
|
| 87 |
+
| 0.1524 | 6.6018 | 23760 | 0.1870 |
|
| 88 |
+
| 0.1544 | 6.8019 | 24480 | 0.1832 |
|
| 89 |
+
| 0.151 | 7.0019 | 25200 | 0.1843 |
|
| 90 |
+
| 0.1425 | 7.2020 | 25920 | 0.1823 |
|
| 91 |
+
| 0.1414 | 7.4021 | 26640 | 0.1869 |
|
| 92 |
+
| 0.1414 | 7.6021 | 27360 | 0.1821 |
|
| 93 |
+
| 0.1385 | 7.8022 | 28080 | 0.1767 |
|
| 94 |
+
| 0.14 | 8.0022 | 28800 | 0.1760 |
|
| 95 |
+
| 0.1281 | 8.2023 | 29520 | 0.1759 |
|
| 96 |
+
| 0.126 | 8.4023 | 30240 | 0.1748 |
|
| 97 |
+
| 0.1277 | 8.6024 | 30960 | 0.1746 |
|
| 98 |
+
| 0.1256 | 8.8024 | 31680 | 0.1707 |
|
| 99 |
+
| 0.1261 | 9.0025 | 32400 | 0.1692 |
|
| 100 |
+
| 0.1138 | 9.2026 | 33120 | 0.1706 |
|
| 101 |
+
| 0.1134 | 9.4026 | 33840 | 0.1687 |
|
| 102 |
+
| 0.1147 | 9.6027 | 34560 | 0.1717 |
|
| 103 |
+
| 0.1143 | 9.8027 | 35280 | 0.1664 |
|
| 104 |
+
| 0.1111 | 10.0028 | 36000 | 0.1670 |
|
| 105 |
+
| 0.1012 | 10.2028 | 36720 | 0.1677 |
|
| 106 |
+
| 0.1009 | 10.4029 | 37440 | 0.1664 |
|
| 107 |
+
| 0.1001 | 10.6029 | 38160 | 0.1683 |
|
| 108 |
+
| 0.1002 | 10.8030 | 38880 | 0.1657 |
|
| 109 |
+
| 0.1006 | 11.0031 | 39600 | 0.1645 |
|
| 110 |
+
| 0.0909 | 11.2031 | 40320 | 0.1716 |
|
| 111 |
+
| 0.0902 | 11.4032 | 41040 | 0.1694 |
|
| 112 |
+
| 0.0889 | 11.6032 | 41760 | 0.1698 |
|
| 113 |
+
| 0.0885 | 11.8033 | 42480 | 0.1698 |
|
| 114 |
+
|
| 115 |
+
|
| 116 |
+
### Framework versions
|
| 117 |
+
|
| 118 |
+
- PEFT 0.14.0
|
| 119 |
+
- Transformers 4.47.0
|
| 120 |
+
- Pytorch 2.5.1+cu124
|
| 121 |
+
- Datasets 4.2.0
|
| 122 |
+
- Tokenizers 0.21.0
|