metadata
library_name: transformers
license: other
base_model: deepseek-ai/deepseek-coder-7b-base-v1.5
tags:
- trl
- sft
- generated_from_trainer
model-index:
- name: deepseek_coder_7b_apps_sft
results: []
deepseek_coder_7b_apps_sft
This model is a fine-tuned version of deepseek-ai/deepseek-coder-7b-base-v1.5 on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.7821
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: 2e-05
- train_batch_size: 8
- eval_batch_size: 1
- seed: 42
- gradient_accumulation_steps: 16
- total_train_batch_size: 128
- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- num_epochs: 30
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.7137 | 5.5818 | 100 | 0.7307 |
| 0.6296 | 11.1164 | 200 | 0.7471 |
| 0.5899 | 16.6982 | 300 | 0.7680 |
| 0.5761 | 22.2327 | 400 | 0.7791 |
| 0.5599 | 27.8145 | 500 | 0.7821 |
Framework versions
- Transformers 4.55.4
- Pytorch 2.8.0+cu126
- Datasets 2.19.1
- Tokenizers 0.21.4