This model is a fine-tuned version of deepseek-ai/deepseek-coder-1.3b-base on the None dataset.
It achieves the following results on the evaluation set:
Loss: 0.3009
Eval/rewards/chosen: -3.4709
Eval/logps/chosen: -180.6532
Eval/rewards/rejected: -3.3713
Eval/logps/rejected: -209.7531
Eval/rewards/margins: -0.0996
Eval/kl: 0.0
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: 1e-06
train_batch_size: 8
eval_batch_size: 8
seed: 42
gradient_accumulation_steps: 16
total_train_batch_size: 128
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
