hyperparam-rust-lora-32-2-epoch
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: 0.4897
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: 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
- num_epochs: 2
Training results
Training Loss | Epoch | Step | Validation Loss |
---|---|---|---|
0.8312 | 0.3 | 25 | 0.6711 |
0.5726 | 0.59 | 50 | 0.5309 |
0.4987 | 0.89 | 75 | 0.5042 |
0.4893 | 1.18 | 100 | 0.4939 |
0.4759 | 1.48 | 125 | 0.4903 |
0.4789 | 1.77 | 150 | 0.4897 |
Framework versions
- PEFT 0.10.0
- Transformers 4.39.3
- Pytorch 2.2.1
- Datasets 2.18.0
- Tokenizers 0.15.2
- Downloads last month
- 2
Model tree for ysr/hyperparam-rust-lora-32-2-epoch
Base model
deepseek-ai/deepseek-coder-1.3b-base
Adapter
this model