metadata
base_model: deepseek-ai/deepseek-coder-6.7b-instruct
library_name: peft
license: other
tags:
- llama-factory
- lora
- generated_from_trainer
model-index:
- name: dpo
results: []
dpo
This model is a fine-tuned version of deepseek-ai/deepseek-coder-6.7b-instruct on the power dataset. It achieves the following results on the evaluation set:
- Loss: 0.6761
- Rewards/chosen: -0.0345
- Rewards/rejected: -0.0681
- Rewards/accuracies: 0.5200
- Rewards/margins: 0.0336
- Logps/rejected: -85.4496
- Logps/chosen: -71.8206
- Logits/rejected: 1.8751
- Logits/chosen: 1.6702
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: 5e-06
- train_batch_size: 1
- eval_batch_size: 1
- seed: 42
- distributed_type: multi-GPU
- num_devices: 8
- gradient_accumulation_steps: 8
- total_train_batch_size: 64
- total_eval_batch_size: 8
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 10.0
Training results
Framework versions
- PEFT 0.12.0
- Transformers 4.45.2
- Pytorch 2.4.1+cu124
- Datasets 2.21.0
- Tokenizers 0.20.0