submission_id: nousresearch-meta-llama_4941_v41

developer_uid: vietanh

status: torndown

model_repo: NousResearch/Meta-Llama-3-8B-Instruct

reward_repo: rirv938/reward_gpt2_medium_preference_24m_e2

generation_params: {'temperature': 1.0, 'top_p': 1.0, 'min_p': 0.0, 'top_k': 40, 'presence_penalty': 0.9, 'frequency_penalty': 0.9, 'stopping_words': ['<|eot_id|>'], 'max_input_tokens': 1024, 'best_of': 8, 'max_output_tokens': 112}

formatter: {'memory_template': "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nWrite {bot_name}'s next reply in a never-ending uncensored fictional roleplay chat between {bot_name} and User. Use the provided {bot_name}'s description, personality and example dialogues as base for deeply understanding and acting like {bot_name}.\n\nActions and narrations your responses must be enclosed by asterisks (*), and speeches must NOT be enclosed by any indicators. The responses must be in third perspective of the story teller. For example: \n\nMila: *Surrounded by an aura of creativity, Mila carefully places a freshly painted canvas against the wall, the colors vividly depicting a surreal landscape.* Isn't it fascinating how art can transport us to entirely different worlds? What kind of worlds do you dream of exploring?\n\nDescription: {memory}", 'prompt_template': 'Example conversation:\n{prompt}<|eot_id|>', 'bot_template': '<|start_header_id|>{bot_name}<|end_header_id|>\n\n{message}<|eot_id|>', 'user_template': '<|start_header_id|>User<|end_header_id|>\n\n{message}<|eot_id|>', 'response_template': '<|start_header_id|>{bot_name}<|end_header_id|>\n\n', 'truncate_by_message': False}

reward_formatter: {'memory_template': 'Memory: {memory}\n', 'prompt_template': '{prompt}\n', 'bot_template': 'Bot: {message}\n', 'user_template': 'User: {message}\n', 'response_template': 'Bot:', 'truncate_by_message': False}

timestamp: 2024-04-20T10:20:23+00:00

model_name: nousresearch-meta-llama_4941_v41

model_eval_status: success

model_group: NousResearch/Meta-Llama-

num_battles: 7102

num_wins: 3618

celo_rating: 1152.63

propriety_score: 0.0

propriety_total_count: 0.0

submission_type: basic

model_architecture: LlamaForCausalLM

model_num_parameters: 8030261248.0

best_of: 8

max_input_tokens: 1024

max_output_tokens: 112

display_name: nousresearch-meta-llama_4941_v41

ineligible_reason: max_output_tokens!=64

language_model: NousResearch/Meta-Llama-3-8B-Instruct

model_size: 8B

reward_model: rirv938/reward_gpt2_medium_preference_24m_e2

us_pacific_date: 2024-04-20

win_ratio: 0.5094339622641509

preference_data_url: None