submission_id: bbchicago-test-113k-dpo-_5640_v2

developer_uid: Bbbrun0

alignment_samples: 8108

alignment_score: 3.020706930782426

best_of: 4

celo_rating: 1200.99

display_name: best_of_4_reward_medium

formatter: {'memory_template': "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\n{bot_name}'s Persona: {memory}\n\n", 'prompt_template': '{prompt}<|eot_id|>', 'bot_template': '<|start_header_id|>assistant<|end_header_id|>\n\n{bot_name}: {message}<|eot_id|>', 'user_template': '<|start_header_id|>user<|end_header_id|>\n\n{user_name}: {message}<|eot_id|>', 'response_template': '<|start_header_id|>assistant<|end_header_id|>\n\n{bot_name}:', 'truncate_by_message': False}

generation_params: {'temperature': 0.95, 'top_p': 0.95, 'min_p': 0.05, 'top_k': 80, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n', '<|end_header_id|>', '<|eot_id|>', '\n\n{user_name}'], 'max_input_tokens': 512, 'best_of': 4, 'max_output_tokens': 64, 'reward_max_token_input': 256}

is_internal_developer: False

language_model: BBChicago/test_113k_dpo_steps3000

max_input_tokens: 512

max_output_tokens: 64

model_architecture: LlamaForCausalLM

model_group: BBChicago/test_113k_dpo_

model_name: best_of_4_reward_medium

model_num_parameters: 8030261248.0

model_repo: BBChicago/test_113k_dpo_steps3000

model_size: 8B

num_battles: 8039

num_wins: 3931

propriety_score: 0.724669603524229

propriety_total_count: 908.0

ranking_group: single

reward_formatter: {'bot_template': '{bot_name}: {message}\n', 'memory_template': "{bot_name}'s Persona: {memory}\n####\n", 'prompt_template': '{prompt}\n<START>\n', 'response_template': '{bot_name}:', 'truncate_by_message': False, 'user_template': '{user_name}: {message}\n'}

reward_repo: rirv938/reward_gpt2_medium_preference_24m_e2

status: torndown

submission_type: basic

timestamp: 2024-08-13T09:10:17+00:00

us_pacific_date: 2024-08-13

win_ratio: 0.48899116805572834