ilyasoulk

[Trainer] Changing the dataset dynamically during training

1

Hello, I am currently training a model using DPO, and I'm adapting the dataset dynamically during training. My current approach looks like this: ```python trainer = DPOTrainer( model, None, args=training_args,...

Request for Generation Parameters and Benchmark Setup Details

2

Hello, I am trying to reproduce the benchmark results mentioned in the Qwen2.5-Coder technical report. However, I couldn’t find detailed information about the generation parameters (e.g., temperature, top-k, top-p, num...