submission_id: hastagaras-halu-8b-llama_9226_v3

developer_uid: Hastagaras

status: torndown

model_repo: Hastagaras/HALU-8B-LLAMA3-EXP-2

reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2

generation_params: {'temperature': 1.0, 'top_p': 1.0, 'min_p': 0.0, 'top_k': 40, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n'], 'max_input_tokens': 512, 'best_of': 16, 'max_output_tokens': 64}

formatter: {'memory_template': "<|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}

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

timestamp: 2024-05-31T12:49:30+00:00

model_name: experiment-2-flat-test

model_eval_status: success

model_group: Hastagaras/HALU-8B-LLAMA

num_battles: 8484

num_wins: 4400

celo_rating: 1206.92

propriety_score: 1.0

propriety_total_count: 3.0

submission_type: basic

model_architecture: LlamaForCausalLM

model_num_parameters: 8030261248.0

best_of: 16

max_input_tokens: 512

max_output_tokens: 64

display_name: experiment-2-flat-test

ineligible_reason: propriety_total_count < 800

language_model: Hastagaras/HALU-8B-LLAMA3-EXP-2

model_size: 8B

reward_model: ChaiML/reward_gpt2_medium_preference_24m_e2

us_pacific_date: 2024-05-31

win_ratio: 0.5186232909005186

preference_data_url: None