name: medium_checkpoint_decoding_grid_1000
checkpoint_path: null
tokenizer_dir: null
tuning_prompts_path: eval_prompts/decoding_tuning.jsonl
holdout_prompts_path: eval_prompts/decoding_tuning_holdout.jsonl
seeds:
  - 1337
holdout_top_k: 4
target_length_ratio: 1.0
ranking_weights:
  prompt_pass_rate: 2.0
  completion_rate: 0.5
  distinct_2: 1.2
  language_consistency: 0.75
  length_closeness: 1.0
  loop_rate: -2.0
  repeated_4gram_rate: -1.5
  language_switch_rate: -0.75
decoding_presets:
  - name: anti_loop_conservative
    max_new_tokens: 1000
    temperature: 0.3
    top_k: 50
    top_p: 0.9
    repetition_penalty: 1.15
    no_repeat_ngram_size: 4
  - name: anti_loop
    max_new_tokens: 1000
    temperature: 0.8
    top_k: 50
    top_p: 0.9
    repetition_penalty: 1.15
    no_repeat_ngram_size: 4
  - name: balanced
    max_new_tokens: 1000
    temperature: 0.8
    top_k: 50
    top_p: 0.95
    repetition_penalty: 1.1
    no_repeat_ngram_size: 0
  - name: creative
    max_new_tokens: 1000
    temperature: 1.0
    top_k: 100
    top_p: 0.95
    repetition_penalty: 1.1
    no_repeat_ngram_size: 0