submission_id: bbchicago-brt-8b-l3-v1-_4895_v29

developer_uid: Bbbrun0

alignment_samples: 0

best_of: 16

celo_rating: 1232.8

display_name: brt-v1_7-dpo-s2500-cf

formatter: {'memory_template': "<|start_header_id|>system<|end_header_id|>\n### Instruction:\n{bot_name}'s Persona: {memory}\n", 'prompt_template': '### Input:\n{prompt}<START>\n<|eot_id|>', 'bot_template': '<|start_header_id|>assistant<|end_header_id|>\n{bot_name}: {message}<|eot_id|>', 'user_template': '<|start_header_id|>user<|end_header_id|>\n{user_name}: {message}<|eot_id|>', 'response_template': '<|start_header_id|>assistant<|end_header_id|>\n### Response:\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': 16, 'max_output_tokens': 64, 'reward_max_token_input': 256}

is_internal_developer: False

language_model: BBChicago/Brt-8B-L3_v1.7_with_dpo_lora_s2500

max_input_tokens: 512

max_output_tokens: 64

model_architecture: LlamaForCausalLM

model_group: BBChicago/Brt-8B-L3_v1.7

model_name: brt-v1_7-dpo-s2500-cf

model_num_parameters: 8030261248.0

model_repo: BBChicago/Brt-8B-L3_v1.7_with_dpo_lora_s2500

model_size: 8B

num_battles: 11553

num_wins: 6376

propriety_score: 0.7386934673366834

propriety_total_count: 995.0

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: Jellywibble/gpt2_xl_pairwise_89m_step_347634

status: torndown

submission_type: basic

timestamp: 2024-07-25T08:19:28+00:00

us_pacific_date: 2024-07-25

win_ratio: 0.5518912836492685