submission_id: chaiml-elo-alignment-run-3_v2

developer_uid: zonemercy

status: inactive

model_repo: ChaiML/elo_alignment_run_3

reward_repo: ChaiML/gpt2_xl_pairwise_89m_step_347634

generation_params: {'temperature': 0.95, 'top_p': 1.0, 'min_p': 0.08, 'top_k': 40, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n', '<|eot_id|>'], 'max_input_tokens': 512, 'best_of': 16, 'max_output_tokens': 64}

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}

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: 2024-07-12T12:58:14+00:00

model_name: dpo-v2-0710-rm-score-completed

model_group: ChaiML/elo_alignment_run

num_battles: 18961

num_wins: 11601

celo_rating: 1271.94

alignment_score: None

alignment_samples: 0

propriety_score: 0.721636305528923

propriety_total_count: 9387.0

submission_type: basic

model_architecture: LlamaForCausalLM

model_num_parameters: 8030261248.0

best_of: 16

max_input_tokens: 512

max_output_tokens: 64

display_name: dpo-v2-0710-rm-score-completed

ineligible_reason: None

language_model: ChaiML/elo_alignment_run_3

model_size: 8B

reward_model: ChaiML/gpt2_xl_pairwise_89m_step_347634

us_pacific_date: 2024-07-12

win_ratio: 0.6118348188386689

preference_data_url: None