submission_id: alkahestry-llmama3-monol_3361_v4
developer_uid: alkacchi
status: inactive
model_repo: alkahestry/Llmama3-Monologue-8B
reward_repo: Jellywibble/CHAI_alignment_reward_model
generation_params: {'temperature': 1.12, 'top_p': 0.73, 'min_p': 0.075, 'top_k': 1000, 'presence_penalty': 0.82, 'frequency_penalty': 0.8, 'stopping_words': ['\n', '</s>', '<|im_end|>', '\n{{User}}', '<|eot_id|>', '<|end_of_text|>', '\n<'], 'max_input_tokens': 1900, 'best_of': 4, 'max_output_tokens': 64}
formatter: {'memory_template': "<|begin_of_text|><|start_header_id|>system\nYou are now in roleplay chat mode. Engage in an endless chat with {user_name}. Always wait {user_name} turn, next actions and responses. You will fully embody the given character, creating immersive, captivating narratives. Stay true to the character's personality and background, generating responses that not only reflect their core traits but are also accurate to their character. Your responses should evoke emotion, suspense, and anticipation in the user. The more detailed and descriptive your response, the more vivid the narrative becomes. Aim to create a fertile environment for ongoing interaction – introduce new elements, offer choices, or ask questions to invite the user to participate more fully in the conversation. This conversation is a dance, always continuing, always evolving.\nYour character: {bot_name}.\nContext: {memory}<|end_header_id|>", 'prompt_template': '{prompt}<|eot_id|><|start_header_id|>user<|end_header_id|>', 'bot_template': '{bot_name}: {message}<|end_header_id|>', 'user_template': '{user_name}: {message}<|end_header_id|>', 'response_template': '{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: 2024-06-28T10:25:43+00:00
model_name: alkacchi-monologue-8B
model_group: alkahestry/Llmama3-Monol
num_battles: 20400
num_wins: 7388
celo_rating: 1083.71
propriety_score: 0.751134956665291
propriety_total_count: 9692.0
submission_type: basic
model_architecture: LlamaForCausalLM
model_num_parameters: 8030261248.0
best_of: 4
max_input_tokens: 1900
max_output_tokens: 64
display_name: alkacchi-monologue-8B
ineligible_reason: None
language_model: alkahestry/Llmama3-Monologue-8B
model_size: 8B
reward_model: Jellywibble/CHAI_alignment_reward_model
us_pacific_date: 2024-06-28
win_ratio: 0.36215686274509806
Resubmit model
Running pipeline stage MKMLizer
Starting job with name alkahestry-llmama3-monol-3361-v4-mkmlizer
Waiting for job on alkahestry-llmama3-monol-3361-v4-mkmlizer to finish
alkahestry-llmama3-monol-3361-v4-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
alkahestry-llmama3-monol-3361-v4-mkmlizer: ║ _____ __ __ ║
alkahestry-llmama3-monol-3361-v4-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
alkahestry-llmama3-monol-3361-v4-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
alkahestry-llmama3-monol-3361-v4-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
alkahestry-llmama3-monol-3361-v4-mkmlizer: ║ /___/ ║
alkahestry-llmama3-monol-3361-v4-mkmlizer: ║ ║
alkahestry-llmama3-monol-3361-v4-mkmlizer: ║ Version: 0.8.14 ║
alkahestry-llmama3-monol-3361-v4-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
alkahestry-llmama3-monol-3361-v4-mkmlizer: ║ https://mk1.ai ║
alkahestry-llmama3-monol-3361-v4-mkmlizer: ║ ║
alkahestry-llmama3-monol-3361-v4-mkmlizer: ║ The license key for the current software has been verified as ║
alkahestry-llmama3-monol-3361-v4-mkmlizer: ║ belonging to: ║
alkahestry-llmama3-monol-3361-v4-mkmlizer: ║ ║
alkahestry-llmama3-monol-3361-v4-mkmlizer: ║ Chai Research Corp. ║
alkahestry-llmama3-monol-3361-v4-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
alkahestry-llmama3-monol-3361-v4-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
alkahestry-llmama3-monol-3361-v4-mkmlizer: ║ ║
alkahestry-llmama3-monol-3361-v4-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
alkahestry-llmama3-monol-3361-v4-mkmlizer: /opt/conda/lib/python3.10/site-packages/huggingface_hub/utils/_deprecation.py:131: FutureWarning: 'list_files_info' (from 'huggingface_hub.hf_api') is deprecated and will be removed from version '0.23'. Use `list_repo_tree` and `get_paths_info` instead.
alkahestry-llmama3-monol-3361-v4-mkmlizer: warnings.warn(warning_message, FutureWarning)
alkahestry-llmama3-monol-3361-v4-mkmlizer: Downloaded to shared memory in 39.630s
alkahestry-llmama3-monol-3361-v4-mkmlizer: quantizing model to /dev/shm/model_cache
alkahestry-llmama3-monol-3361-v4-mkmlizer: Saving flywheel model at /dev/shm/model_cache
alkahestry-llmama3-monol-3361-v4-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 5%|▍ | 14/291 [00:00<00:02, 128.15it/s] Loading 0: 11%|█ | 32/291 [00:00<00:01, 148.14it/s] Loading 0: 17%|█▋ | 49/291 [00:00<00:01, 144.27it/s] Loading 0: 23%|██▎ | 66/291 [00:00<00:01, 151.90it/s] Loading 0: 28%|██▊ | 82/291 [00:00<00:01, 150.20it/s] Loading 0: 34%|███▎ | 98/291 [00:00<00:02, 79.92it/s] Loading 0: 39%|███▉ | 113/291 [00:01<00:01, 91.75it/s] Loading 0: 45%|████▌ | 131/291 [00:01<00:01, 108.22it/s] Loading 0: 51%|█████ | 149/291 [00:01<00:01, 122.41it/s] Loading 0: 57%|█████▋ | 167/291 [00:01<00:00, 132.63it/s] Loading 0: 64%|██████▍ | 187/291 [00:01<00:01, 94.96it/s] Loading 0: 69%|██████▉ | 202/291 [00:01<00:00, 103.17it/s] Loading 0: 76%|███████▌ | 220/291 [00:01<00:00, 115.77it/s] Loading 0: 81%|████████▏ | 237/291 [00:02<00:00, 127.13it/s] Loading 0: 87%|████████▋ | 252/291 [00:02<00:00, 130.93it/s] Loading 0: 92%|█████████▏| 267/291 [00:02<00:00, 133.10it/s] Loading 0: 97%|█████████▋| 282/291 [00:02<00:00, 135.26it/s] Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
alkahestry-llmama3-monol-3361-v4-mkmlizer: quantized model in 23.580s
alkahestry-llmama3-monol-3361-v4-mkmlizer: Processed model alkahestry/Llmama3-Monologue-8B in 65.742s
alkahestry-llmama3-monol-3361-v4-mkmlizer: creating bucket guanaco-mkml-models
alkahestry-llmama3-monol-3361-v4-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
alkahestry-llmama3-monol-3361-v4-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/alkahestry-llmama3-monol-3361-v4
alkahestry-llmama3-monol-3361-v4-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/alkahestry-llmama3-monol-3361-v4/tokenizer.json
alkahestry-llmama3-monol-3361-v4-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/alkahestry-llmama3-monol-3361-v4/tokenizer_config.json
alkahestry-llmama3-monol-3361-v4-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/alkahestry-llmama3-monol-3361-v4/special_tokens_map.json
alkahestry-llmama3-monol-3361-v4-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/alkahestry-llmama3-monol-3361-v4/config.json
alkahestry-llmama3-monol-3361-v4-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/alkahestry-llmama3-monol-3361-v4/flywheel_model.0.safetensors
alkahestry-llmama3-monol-3361-v4-mkmlizer: loading reward model from Jellywibble/CHAI_alignment_reward_model
alkahestry-llmama3-monol-3361-v4-mkmlizer: /opt/conda/lib/python3.10/site-packages/transformers/models/auto/configuration_auto.py:913: FutureWarning: The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers. Please use `token` instead.
alkahestry-llmama3-monol-3361-v4-mkmlizer: warnings.warn(
alkahestry-llmama3-monol-3361-v4-mkmlizer: /opt/conda/lib/python3.10/site-packages/transformers/models/auto/tokenization_auto.py:757: FutureWarning: The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers. Please use `token` instead.
alkahestry-llmama3-monol-3361-v4-mkmlizer: warnings.warn(
alkahestry-llmama3-monol-3361-v4-mkmlizer: /opt/conda/lib/python3.10/site-packages/transformers/models/auto/auto_factory.py:468: FutureWarning: The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers. Please use `token` instead.
alkahestry-llmama3-monol-3361-v4-mkmlizer: warnings.warn(
alkahestry-llmama3-monol-3361-v4-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
alkahestry-llmama3-monol-3361-v4-mkmlizer: Saving duration: 0.155s
alkahestry-llmama3-monol-3361-v4-mkmlizer: Processed model Jellywibble/CHAI_alignment_reward_model in 3.414s
alkahestry-llmama3-monol-3361-v4-mkmlizer: creating bucket guanaco-reward-models
Job alkahestry-llmama3-monol-3361-v4-mkmlizer completed after 93.46s with status: succeeded
Stopping job with name alkahestry-llmama3-monol-3361-v4-mkmlizer
Pipeline stage MKMLizer completed in 94.63s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.10s
Running pipeline stage ISVCDeployer
Creating inference service alkahestry-llmama3-monol-3361-v4
Waiting for inference service alkahestry-llmama3-monol-3361-v4 to be ready
Inference service alkahestry-llmama3-monol-3361-v4 ready after 40.18231558799744s
Pipeline stage ISVCDeployer completed in 48.22s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.112002372741699s
Received healthy response to inference request in 1.19553542137146s
Received healthy response to inference request in 1.078552484512329s
Received healthy response to inference request in 1.1990687847137451s
Received healthy response to inference request in 1.202521800994873s
5 requests
0 failed requests
5th percentile: 1.1019490718841554
10th percentile: 1.1253456592559814
20th percentile: 1.1721388339996337
30th percentile: 1.196242094039917
40th percentile: 1.197655439376831
50th percentile: 1.1990687847137451
60th percentile: 1.2004499912261963
70th percentile: 1.2018311977386475
80th percentile: 1.3844179153442384
90th percentile: 1.748210144042969
95th percentile: 1.9301062583923339
99th percentile: 2.0756231498718263
mean time: 1.3575361728668214
Pipeline stage StressChecker completed in 8.02s
alkahestry-llmama3-monol_3361_v4 status is now deployed due to DeploymentManager action
alkahestry-llmama3-monol_3361_v4 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics