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-v2-template_small_notypes-deepseek-coder-1.3b-base-8lr-24epochs-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-v2-template_small_notypes-deepseek-coder-1.3b-base-8lr-24epochs-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: 0.1882
|
| 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: 24
|
| 49 |
+
- mixed_precision_training: Native AMP
|
| 50 |
+
|
| 51 |
+
### Training results
|
| 52 |
+
|
| 53 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
| 54 |
+
|:-------------:|:-------:|:-----:|:---------------:|
|
| 55 |
+
| 0.3243 | 0.4001 | 1440 | 0.2947 |
|
| 56 |
+
| 0.2737 | 0.8002 | 2880 | 0.2755 |
|
| 57 |
+
| 0.2463 | 1.2003 | 4320 | 0.2620 |
|
| 58 |
+
| 0.2389 | 1.6004 | 5760 | 0.2570 |
|
| 59 |
+
| 0.2342 | 2.0006 | 7200 | 0.2518 |
|
| 60 |
+
| 0.2237 | 2.4007 | 8640 | 0.2492 |
|
| 61 |
+
| 0.2216 | 2.8008 | 10080 | 0.2380 |
|
| 62 |
+
| 0.2104 | 3.2009 | 11520 | 0.2318 |
|
| 63 |
+
| 0.2076 | 3.6010 | 12960 | 0.2281 |
|
| 64 |
+
| 0.2087 | 4.0011 | 14400 | 0.2299 |
|
| 65 |
+
| 0.2011 | 4.4012 | 15840 | 0.2211 |
|
| 66 |
+
| 0.199 | 4.8013 | 17280 | 0.2192 |
|
| 67 |
+
| 0.1893 | 5.2014 | 18720 | 0.2117 |
|
| 68 |
+
| 0.1935 | 5.6016 | 20160 | 0.2185 |
|
| 69 |
+
| 0.1895 | 6.0017 | 21600 | 0.2080 |
|
| 70 |
+
| 0.1841 | 6.4018 | 23040 | 0.2015 |
|
| 71 |
+
| 0.184 | 6.8019 | 24480 | 0.2029 |
|
| 72 |
+
| 0.1755 | 7.2020 | 25920 | 0.2010 |
|
| 73 |
+
| 0.1762 | 7.6021 | 27360 | 0.2034 |
|
| 74 |
+
| 0.1775 | 8.0022 | 28800 | 0.1958 |
|
| 75 |
+
| 0.1666 | 8.4023 | 30240 | 0.1979 |
|
| 76 |
+
| 0.1673 | 8.8024 | 31680 | 0.2012 |
|
| 77 |
+
| 0.1606 | 9.2026 | 33120 | 0.1933 |
|
| 78 |
+
| 0.1629 | 9.6027 | 34560 | 0.1895 |
|
| 79 |
+
| 0.1596 | 10.0028 | 36000 | 0.1885 |
|
| 80 |
+
| 0.1526 | 10.4029 | 37440 | 0.1883 |
|
| 81 |
+
| 0.1545 | 10.8030 | 38880 | 0.1863 |
|
| 82 |
+
| 0.1454 | 11.2031 | 40320 | 0.1857 |
|
| 83 |
+
| 0.146 | 11.6032 | 41760 | 0.1823 |
|
| 84 |
+
| 0.1491 | 12.0033 | 43200 | 0.1791 |
|
| 85 |
+
| 0.1395 | 12.4034 | 44640 | 0.1829 |
|
| 86 |
+
| 0.142 | 12.8036 | 46080 | 0.1781 |
|
| 87 |
+
| 0.131 | 13.2037 | 47520 | 0.1792 |
|
| 88 |
+
| 0.1323 | 13.6038 | 48960 | 0.1823 |
|
| 89 |
+
| 0.1339 | 14.0039 | 50400 | 0.1795 |
|
| 90 |
+
| 0.1261 | 14.4040 | 51840 | 0.1737 |
|
| 91 |
+
| 0.1279 | 14.8041 | 53280 | 0.1788 |
|
| 92 |
+
| 0.1168 | 15.2042 | 54720 | 0.1754 |
|
| 93 |
+
| 0.1199 | 15.6043 | 56160 | 0.1740 |
|
| 94 |
+
| 0.121 | 16.0044 | 57600 | 0.1753 |
|
| 95 |
+
| 0.1125 | 16.4046 | 59040 | 0.1723 |
|
| 96 |
+
| 0.1151 | 16.8047 | 60480 | 0.1719 |
|
| 97 |
+
| 0.1053 | 17.2048 | 61920 | 0.1718 |
|
| 98 |
+
| 0.106 | 17.6049 | 63360 | 0.1691 |
|
| 99 |
+
| 0.1073 | 18.0050 | 64800 | 0.1723 |
|
| 100 |
+
| 0.0973 | 18.4051 | 66240 | 0.1691 |
|
| 101 |
+
| 0.1009 | 18.8052 | 67680 | 0.1661 |
|
| 102 |
+
| 0.0908 | 19.2053 | 69120 | 0.1781 |
|
| 103 |
+
| 0.0926 | 19.6054 | 70560 | 0.1742 |
|
| 104 |
+
| 0.093 | 20.0056 | 72000 | 0.1732 |
|
| 105 |
+
| 0.086 | 20.4057 | 73440 | 0.1750 |
|
| 106 |
+
| 0.0881 | 20.8058 | 74880 | 0.1754 |
|
| 107 |
+
| 0.0818 | 21.2059 | 76320 | 0.1779 |
|
| 108 |
+
| 0.0809 | 21.6060 | 77760 | 0.1774 |
|
| 109 |
+
| 0.0815 | 22.0061 | 79200 | 0.1790 |
|
| 110 |
+
| 0.0746 | 22.4062 | 80640 | 0.1856 |
|
| 111 |
+
| 0.0752 | 22.8063 | 82080 | 0.1831 |
|
| 112 |
+
| 0.0706 | 23.2064 | 83520 | 0.1869 |
|
| 113 |
+
| 0.071 | 23.6066 | 84960 | 0.1882 |
|
| 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
|