submission_id: visionforge-alien-8b-v1-6-dpo_v1

developer_uid: fredi

status: torndown

model_repo: VisionForge/Alien-8B-v1.6-DPO

reward_repo: rirv938/reward_gpt2_medium_preference_24m_e2

generation_params: {'temperature': 0.7, 'top_p': 0.92, 'min_p': 0.0, 'top_k': 70, 'presence_penalty': 0.0, 'frequency_penalty': 1.3, 'stopping_words': ['<|eot_id|>'], 'max_input_tokens': 512, 'best_of': 16, 'max_output_tokens': 112}

formatter: {'memory_template': "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\n{bot_name}'s persona: {memory}", 'prompt_template': '\n\n### Example dialog:\n{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': '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: 2024-04-21T23:18:08+00:00

model_name: Alien8B-V1-6-DPO

model_eval_status: success

model_group: VisionForge/Alien-8B-v1.

num_battles: 6312

num_wins: 3083

celo_rating: 1136.48

propriety_score: 0.0

propriety_total_count: 0.0

submission_type: basic

model_architecture: LlamaForCausalLM

model_num_parameters: 8030261248.0

best_of: 16

max_input_tokens: 512

max_output_tokens: 112

display_name: Alien8B-V1-6-DPO

ineligible_reason: max_output_tokens!=64

language_model: VisionForge/Alien-8B-v1.6-DPO

model_size: 8B

reward_model: rirv938/reward_gpt2_medium_preference_24m_e2

us_pacific_date: 2024-04-21

win_ratio: 0.4884347275031686

preference_data_url: None