|
|
--- |
|
|
library_name: peft |
|
|
license: other |
|
|
base_model: deepseek-ai/deepseek-coder-1.3b-base |
|
|
tags: |
|
|
- generated_from_trainer |
|
|
model-index: |
|
|
- name: lemexp-task1-min_symbols_template_small-deepseek-coder-1.3b-base-ddp |
|
|
results: [] |
|
|
--- |
|
|
|
|
|
<!-- This model card has been generated automatically according to the information the Trainer had access to. You |
|
|
should probably proofread and complete it, then remove this comment. --> |
|
|
|
|
|
# lemexp-task1-min_symbols_template_small-deepseek-coder-1.3b-base-ddp |
|
|
|
|
|
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. |
|
|
It achieves the following results on the evaluation set: |
|
|
- Loss: 0.1887 |
|
|
|
|
|
## Model description |
|
|
|
|
|
More information needed |
|
|
|
|
|
## Intended uses & limitations |
|
|
|
|
|
More information needed |
|
|
|
|
|
## Training and evaluation data |
|
|
|
|
|
More information needed |
|
|
|
|
|
## Training procedure |
|
|
|
|
|
### Training hyperparameters |
|
|
|
|
|
The following hyperparameters were used during training: |
|
|
- learning_rate: 0.0001 |
|
|
- train_batch_size: 2 |
|
|
- eval_batch_size: 2 |
|
|
- seed: 42 |
|
|
- distributed_type: multi-GPU |
|
|
- num_devices: 8 |
|
|
- total_train_batch_size: 16 |
|
|
- total_eval_batch_size: 16 |
|
|
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments |
|
|
- lr_scheduler_type: linear |
|
|
- num_epochs: 6 |
|
|
- mixed_precision_training: Native AMP |
|
|
|
|
|
### Training results |
|
|
|
|
|
| Training Loss | Epoch | Step | Validation Loss | |
|
|
|:-------------:|:------:|:-----:|:---------------:| |
|
|
| 0.4557 | 0.2001 | 629 | 0.3633 | |
|
|
| 0.3618 | 0.4001 | 1258 | 0.3296 | |
|
|
| 0.3388 | 0.6002 | 1887 | 0.3132 | |
|
|
| 0.3131 | 0.8003 | 2516 | 0.2975 | |
|
|
| 0.3022 | 1.0003 | 3145 | 0.2878 | |
|
|
| 0.2884 | 1.2004 | 3774 | 0.2849 | |
|
|
| 0.2806 | 1.4004 | 4403 | 0.2791 | |
|
|
| 0.2695 | 1.6005 | 5032 | 0.2651 | |
|
|
| 0.2684 | 1.8006 | 5661 | 0.2560 | |
|
|
| 0.261 | 2.0006 | 6290 | 0.2564 | |
|
|
| 0.2544 | 2.2007 | 6919 | 0.2513 | |
|
|
| 0.2437 | 2.4008 | 7548 | 0.2441 | |
|
|
| 0.2393 | 2.6008 | 8177 | 0.2406 | |
|
|
| 0.2375 | 2.8009 | 8806 | 0.2338 | |
|
|
| 0.2326 | 3.0010 | 9435 | 0.2257 | |
|
|
| 0.2124 | 3.2010 | 10064 | 0.2227 | |
|
|
| 0.2137 | 3.4011 | 10693 | 0.2215 | |
|
|
| 0.2102 | 3.6011 | 11322 | 0.2127 | |
|
|
| 0.2079 | 3.8012 | 11951 | 0.2103 | |
|
|
| 0.2034 | 4.0013 | 12580 | 0.2070 | |
|
|
| 0.1862 | 4.2013 | 13209 | 0.2049 | |
|
|
| 0.1831 | 4.4014 | 13838 | 0.2029 | |
|
|
| 0.185 | 4.6015 | 14467 | 0.1987 | |
|
|
| 0.1754 | 4.8015 | 15096 | 0.1975 | |
|
|
| 0.1753 | 5.0016 | 15725 | 0.1937 | |
|
|
| 0.1622 | 5.2017 | 16354 | 0.1959 | |
|
|
| 0.155 | 5.4017 | 16983 | 0.1912 | |
|
|
| 0.1501 | 5.6018 | 17612 | 0.1897 | |
|
|
| 0.1481 | 5.8018 | 18241 | 0.1887 | |
|
|
|
|
|
|
|
|
### Framework versions |
|
|
|
|
|
- PEFT 0.14.0 |
|
|
- Transformers 4.47.0 |
|
|
- Pytorch 2.5.1+cu124 |
|
|
- Datasets 3.2.0 |
|
|
- Tokenizers 0.21.0 |
