Update README.md

README.md

@@ -57,6 +57,7 @@ problem_field = "question"
 solution_field = "answer"
 dataloader_num_workers = 2
 test_size = 0.1
+extract_hash = true
 
 [run]
 run_name = "rl-zariman-7"
@@ -82,6 +83,10 @@ use_peft = true
 # vllm_gpu_memory_utilization = 0.25
 num_generations = 4
 max_completion_length = 1024
+num_iterations = 4          # https://github.com/huggingface/trl/releases/tag/v0.16.0
+scale_rewards = false
+beta = 0.0                  # do not load reference model, do not minimize KL-div. Great memory saving opportunity.
+epsilon_high = 0.28         # Increasing upper bound epsilon leads to higher entropy during generation, promoting better exploration
 
 [lora]
 lora_target_modules = [