metadata
license: other
library_name: peft
tags:
- trl
- sft
- generated_from_trainer
base_model: deepseek-ai/deepseek-coder-1.3b-base
datasets:
- generator
model-index:
- name: hyperparam-rust-sft-lora
results: []
hyperparam-rust-sft-lora
This model is a fine-tuned version of deepseek-ai/deepseek-coder-1.3b-base on the generator dataset. It achieves the following results on the evaluation set:
- Loss: 0.4247
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: 0.0003
- train_batch_size: 1
- eval_batch_size: 1
- seed: 42
- gradient_accumulation_steps: 32
- total_train_batch_size: 32
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_ratio: 0.05
- lr_scheduler_warmup_steps: 20
- num_epochs: 5
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.7919 | 0.3 | 25 | 0.5285 |
| 0.4811 | 0.59 | 50 | 0.4738 |
| 0.4512 | 0.89 | 75 | 0.4567 |
| 0.4367 | 1.18 | 100 | 0.4465 |
| 0.4162 | 1.48 | 125 | 0.4399 |
| 0.4188 | 1.77 | 150 | 0.4352 |
| 0.4127 | 2.07 | 175 | 0.4318 |
| 0.3981 | 2.37 | 200 | 0.4296 |
| 0.3887 | 2.66 | 225 | 0.4281 |
| 0.3943 | 2.96 | 250 | 0.4258 |
| 0.3808 | 3.25 | 275 | 0.4263 |
| 0.3836 | 3.55 | 300 | 0.4251 |
| 0.3824 | 3.84 | 325 | 0.4247 |
| 0.3782 | 4.14 | 350 | 0.4246 |
| 0.377 | 4.43 | 375 | 0.4247 |
| 0.3725 | 4.73 | 400 | 0.4247 |
Framework versions
- PEFT 0.10.0
- Transformers 4.39.3
- Pytorch 2.2.1
- Datasets 2.18.0
- Tokenizers 0.15.2