End of training
Browse files
README.md
ADDED
|
@@ -0,0 +1,123 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
library_name: peft
|
| 3 |
+
license: other
|
| 4 |
+
base_model: deepseek-ai/deepseek-coder-6.7b-base
|
| 5 |
+
tags:
|
| 6 |
+
- generated_from_trainer
|
| 7 |
+
model-index:
|
| 8 |
+
- name: lemexp-task1-v3-template_small-deepseek-coder-6.7b-base
|
| 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-deepseek-coder-6.7b-base
|
| 16 |
+
|
| 17 |
+
This model is a fine-tuned version of [deepseek-ai/deepseek-coder-6.7b-base](https://huggingface.co/deepseek-ai/deepseek-coder-6.7b-base) on an unknown dataset.
|
| 18 |
+
It achieves the following results on the evaluation set:
|
| 19 |
+
- Loss: 0.1445
|
| 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: 0.0004
|
| 39 |
+
- train_batch_size: 2
|
| 40 |
+
- eval_batch_size: 2
|
| 41 |
+
- seed: 42
|
| 42 |
+
- distributed_type: multi-GPU
|
| 43 |
+
- num_devices: 4
|
| 44 |
+
- gradient_accumulation_steps: 2
|
| 45 |
+
- total_train_batch_size: 16
|
| 46 |
+
- total_eval_batch_size: 8
|
| 47 |
+
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
|
| 48 |
+
- lr_scheduler_type: linear
|
| 49 |
+
- num_epochs: 12
|
| 50 |
+
- mixed_precision_training: Native AMP
|
| 51 |
+
|
| 52 |
+
### Training results
|
| 53 |
+
|
| 54 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
| 55 |
+
|:-------------:|:-------:|:-----:|:---------------:|
|
| 56 |
+
| 0.6105 | 0.2001 | 720 | 0.1979 |
|
| 57 |
+
| 0.3924 | 0.4002 | 1440 | 0.1762 |
|
| 58 |
+
| 0.3264 | 0.6003 | 2160 | 0.1657 |
|
| 59 |
+
| 0.3094 | 0.8003 | 2880 | 0.1514 |
|
| 60 |
+
| 0.2879 | 1.0003 | 3600 | 0.1473 |
|
| 61 |
+
| 0.2563 | 1.2004 | 4320 | 0.1422 |
|
| 62 |
+
| 0.2479 | 1.4004 | 5040 | 0.1370 |
|
| 63 |
+
| 0.2451 | 1.6005 | 5760 | 0.1394 |
|
| 64 |
+
| 0.2413 | 1.8006 | 6480 | 0.1315 |
|
| 65 |
+
| 0.2317 | 2.0006 | 7200 | 0.1288 |
|
| 66 |
+
| 0.2101 | 2.2006 | 7920 | 0.1282 |
|
| 67 |
+
| 0.2039 | 2.4007 | 8640 | 0.1231 |
|
| 68 |
+
| 0.2006 | 2.6008 | 9360 | 0.1211 |
|
| 69 |
+
| 0.2003 | 2.8009 | 10080 | 0.1172 |
|
| 70 |
+
| 0.2044 | 3.0008 | 10800 | 0.1192 |
|
| 71 |
+
| 0.1712 | 3.2009 | 11520 | 0.1202 |
|
| 72 |
+
| 0.1762 | 3.4010 | 12240 | 0.1164 |
|
| 73 |
+
| 0.1732 | 3.6011 | 12960 | 0.1136 |
|
| 74 |
+
| 0.1731 | 3.8012 | 13680 | 0.1141 |
|
| 75 |
+
| 0.1723 | 4.0011 | 14400 | 0.1121 |
|
| 76 |
+
| 0.1466 | 4.2012 | 15120 | 0.1163 |
|
| 77 |
+
| 0.1491 | 4.4013 | 15840 | 0.1121 |
|
| 78 |
+
| 0.1485 | 4.6014 | 16560 | 0.1144 |
|
| 79 |
+
| 0.1515 | 4.8014 | 17280 | 0.1088 |
|
| 80 |
+
| 0.1496 | 5.0014 | 18000 | 0.1089 |
|
| 81 |
+
| 0.1261 | 5.2015 | 18720 | 0.1125 |
|
| 82 |
+
| 0.1281 | 5.4016 | 19440 | 0.1087 |
|
| 83 |
+
| 0.1308 | 5.6016 | 20160 | 0.1090 |
|
| 84 |
+
| 0.1319 | 5.8017 | 20880 | 0.1106 |
|
| 85 |
+
| 0.13 | 6.0017 | 21600 | 0.1058 |
|
| 86 |
+
| 0.1119 | 6.2018 | 22320 | 0.1176 |
|
| 87 |
+
| 0.1134 | 6.4018 | 23040 | 0.1124 |
|
| 88 |
+
| 0.1133 | 6.6019 | 23760 | 0.1133 |
|
| 89 |
+
| 0.1141 | 6.8020 | 24480 | 0.1135 |
|
| 90 |
+
| 0.1134 | 7.0019 | 25200 | 0.1110 |
|
| 91 |
+
| 0.1 | 7.2020 | 25920 | 0.1170 |
|
| 92 |
+
| 0.0964 | 7.4021 | 26640 | 0.1099 |
|
| 93 |
+
| 0.0986 | 7.6022 | 27360 | 0.1141 |
|
| 94 |
+
| 0.0984 | 7.8023 | 28080 | 0.1096 |
|
| 95 |
+
| 0.0992 | 8.0022 | 28800 | 0.1101 |
|
| 96 |
+
| 0.0832 | 8.2023 | 29520 | 0.1185 |
|
| 97 |
+
| 0.0808 | 8.4024 | 30240 | 0.1157 |
|
| 98 |
+
| 0.0837 | 8.6025 | 30960 | 0.1191 |
|
| 99 |
+
| 0.0845 | 8.8026 | 31680 | 0.1213 |
|
| 100 |
+
| 0.0834 | 9.0025 | 32400 | 0.1222 |
|
| 101 |
+
| 0.0703 | 9.2026 | 33120 | 0.1285 |
|
| 102 |
+
| 0.0714 | 9.4027 | 33840 | 0.1220 |
|
| 103 |
+
| 0.0725 | 9.6028 | 34560 | 0.1245 |
|
| 104 |
+
| 0.0742 | 9.8028 | 35280 | 0.1253 |
|
| 105 |
+
| 0.0709 | 10.0028 | 36000 | 0.1231 |
|
| 106 |
+
| 0.0618 | 10.2029 | 36720 | 0.1325 |
|
| 107 |
+
| 0.0611 | 10.4029 | 37440 | 0.1318 |
|
| 108 |
+
| 0.0621 | 10.6030 | 38160 | 0.1354 |
|
| 109 |
+
| 0.062 | 10.8031 | 38880 | 0.1352 |
|
| 110 |
+
| 0.063 | 11.0031 | 39600 | 0.1332 |
|
| 111 |
+
| 0.0554 | 11.2031 | 40320 | 0.1455 |
|
| 112 |
+
| 0.0552 | 11.4032 | 41040 | 0.1436 |
|
| 113 |
+
| 0.0546 | 11.6033 | 41760 | 0.1423 |
|
| 114 |
+
| 0.0552 | 11.8034 | 42480 | 0.1445 |
|
| 115 |
+
|
| 116 |
+
|
| 117 |
+
### Framework versions
|
| 118 |
+
|
| 119 |
+
- PEFT 0.14.0
|
| 120 |
+
- Transformers 4.47.0
|
| 121 |
+
- Pytorch 2.5.1+cu124
|
| 122 |
+
- Datasets 3.2.0
|
| 123 |
+
- Tokenizers 0.21.1
|