submission_id: neversleep-noromaid-v0-_8068_v82
developer_uid: robert_irvine
status: inactive
model_repo: NeverSleep/Noromaid-v0.1-mixtral-8x7b-Instruct-v3
reward_repo: rirv938/reward_gpt2_medium_preference_24m_e2
generation_params: {'temperature': 1.0, 'top_p': 1.0, 'min_p': 0.0, 'top_k': 50, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['</s>', '<|user|>', '###', '\n'], 'max_input_tokens': 512, 'best_of': 4, 'max_output_tokens': 64}
formatter: {'memory_template': '<s>[INST] This is an entertaining conversation. You are {bot_name} who has the persona: {memory}.\nPlay the role of {bot_name}. You goal is to make sure the conversation is always novel and creative. [/INST]\n', 'prompt_template': '{prompt}\n', 'bot_template': '{bot_name}: {message}</s>', 'user_template': '[INST] {user_name}: {message} [/INST]', 'response_template': '[INST] {bot_name} should ask an engaging question [/INST]{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: 2024-06-10T21:56:02+00:00
model_name: neversleep-noromaid-v0-_8068_v82
model_eval_status: pending
model_group: NeverSleep/Noromaid-v0.1
num_battles: 45676
num_wins: 21655
celo_rating: 1137.14
propriety_score: 0.69616183267466
propriety_total_count: 14929.0
submission_type: basic
model_architecture: MixtralForCausalLM
model_num_parameters: 46702792704.0
best_of: 4
max_input_tokens: 512
max_output_tokens: 64
display_name: neversleep-noromaid-v0-_8068_v82
ineligible_reason: None
language_model: NeverSleep/Noromaid-v0.1-mixtral-8x7b-Instruct-v3
model_size: 47B
reward_model: rirv938/reward_gpt2_medium_preference_24m_e2
us_pacific_date: 2024-06-10
win_ratio: 0.4741001839040196
Resubmit model
Running pipeline stage MKMLizer
Starting job with name neversleep-noromaid-v0-8068-v82-mkmlizer
Waiting for job on neversleep-noromaid-v0-8068-v82-mkmlizer to finish
neversleep-noromaid-v0-8068-v82-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
neversleep-noromaid-v0-8068-v82-mkmlizer: ║ _____ __ __ ║
neversleep-noromaid-v0-8068-v82-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
neversleep-noromaid-v0-8068-v82-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
neversleep-noromaid-v0-8068-v82-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
neversleep-noromaid-v0-8068-v82-mkmlizer: ║ /___/ ║
neversleep-noromaid-v0-8068-v82-mkmlizer: ║ ║
neversleep-noromaid-v0-8068-v82-mkmlizer: ║ Version: 0.8.14 ║
neversleep-noromaid-v0-8068-v82-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
neversleep-noromaid-v0-8068-v82-mkmlizer: ║ https://mk1.ai ║
neversleep-noromaid-v0-8068-v82-mkmlizer: ║ ║
neversleep-noromaid-v0-8068-v82-mkmlizer: ║ The license key for the current software has been verified as ║
neversleep-noromaid-v0-8068-v82-mkmlizer: ║ belonging to: ║
neversleep-noromaid-v0-8068-v82-mkmlizer: ║ ║
neversleep-noromaid-v0-8068-v82-mkmlizer: ║ Chai Research Corp. ║
neversleep-noromaid-v0-8068-v82-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
neversleep-noromaid-v0-8068-v82-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
neversleep-noromaid-v0-8068-v82-mkmlizer: ║ ║
neversleep-noromaid-v0-8068-v82-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
neversleep-noromaid-v0-8068-v82-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.
neversleep-noromaid-v0-8068-v82-mkmlizer: warnings.warn(warning_message, FutureWarning)
neversleep-noromaid-v0-8068-v82-mkmlizer: Downloaded to shared memory in 74.259s
neversleep-noromaid-v0-8068-v82-mkmlizer: quantizing model to /dev/shm/model_cache
neversleep-noromaid-v0-8068-v82-mkmlizer: Saving flywheel model at /dev/shm/model_cache
neversleep-noromaid-v0-8068-v82-mkmlizer: quantized model in 72.611s
neversleep-noromaid-v0-8068-v82-mkmlizer: Processed model NeverSleep/Noromaid-v0.1-mixtral-8x7b-Instruct-v3 in 153.285s
neversleep-noromaid-v0-8068-v82-mkmlizer: creating bucket guanaco-mkml-models
neversleep-noromaid-v0-8068-v82-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
neversleep-noromaid-v0-8068-v82-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v82
neversleep-noromaid-v0-8068-v82-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v82/config.json
neversleep-noromaid-v0-8068-v82-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v82/tokenizer_config.json
neversleep-noromaid-v0-8068-v82-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v82/tokenizer.json
neversleep-noromaid-v0-8068-v82-mkmlizer: cp /dev/shm/model_cache/tokenizer.model s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v82/tokenizer.model
neversleep-noromaid-v0-8068-v82-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v82/special_tokens_map.json
neversleep-noromaid-v0-8068-v82-mkmlizer: cp /dev/shm/model_cache/flywheel_model.3.safetensors s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v82/flywheel_model.3.safetensors
neversleep-noromaid-v0-8068-v82-mkmlizer: cp /dev/shm/model_cache/flywheel_model.2.safetensors s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v82/flywheel_model.2.safetensors
neversleep-noromaid-v0-8068-v82-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v82/flywheel_model.1.safetensors
neversleep-noromaid-v0-8068-v82-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v82/flywheel_model.0.safetensors
neversleep-noromaid-v0-8068-v82-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.
neversleep-noromaid-v0-8068-v82-mkmlizer: warnings.warn(
neversleep-noromaid-v0-8068-v82-mkmlizer: /opt/conda/lib/python3.10/site-packages/torch/_utils.py:831: UserWarning: TypedStorage is deprecated. It will be removed in the future and UntypedStorage will be the only storage class. This should only matter to you if you are using storages directly. To access UntypedStorage directly, use tensor.untyped_storage() instead of tensor.storage()
neversleep-noromaid-v0-8068-v82-mkmlizer: return self.fget.__get__(instance, owner)()
neversleep-noromaid-v0-8068-v82-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
neversleep-noromaid-v0-8068-v82-mkmlizer: Saving duration: 0.227s
neversleep-noromaid-v0-8068-v82-mkmlizer: Processed model rirv938/reward_gpt2_medium_preference_24m_e2 in 3.320s
neversleep-noromaid-v0-8068-v82-mkmlizer: creating bucket guanaco-reward-models
neversleep-noromaid-v0-8068-v82-mkmlizer: Bucket 's3://guanaco-reward-models/' created
neversleep-noromaid-v0-8068-v82-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/neversleep-noromaid-v0-8068-v82_reward
neversleep-noromaid-v0-8068-v82-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/neversleep-noromaid-v0-8068-v82_reward/config.json
neversleep-noromaid-v0-8068-v82-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/neversleep-noromaid-v0-8068-v82_reward/merges.txt
neversleep-noromaid-v0-8068-v82-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/neversleep-noromaid-v0-8068-v82_reward/vocab.json
neversleep-noromaid-v0-8068-v82-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/neversleep-noromaid-v0-8068-v82_reward/special_tokens_map.json
neversleep-noromaid-v0-8068-v82-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/neversleep-noromaid-v0-8068-v82_reward/tokenizer_config.json
neversleep-noromaid-v0-8068-v82-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/neversleep-noromaid-v0-8068-v82_reward/tokenizer.json
neversleep-noromaid-v0-8068-v82-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/neversleep-noromaid-v0-8068-v82_reward/reward.tensors
Job neversleep-noromaid-v0-8068-v82-mkmlizer completed after 186.34s with status: succeeded
Stopping job with name neversleep-noromaid-v0-8068-v82-mkmlizer
Pipeline stage MKMLizer completed in 188.75s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.42s
Running pipeline stage ISVCDeployer
Creating inference service neversleep-noromaid-v0-8068-v82
Waiting for inference service neversleep-noromaid-v0-8068-v82 to be ready
Inference service neversleep-noromaid-v0-8068-v82 ready after 60.83951711654663s
Pipeline stage ISVCDeployer completed in 67.79s
Running pipeline stage StressChecker
Received healthy response to inference request in 12.515738487243652s
Received healthy response to inference request in 12.314155578613281s
%s, retrying in %s seconds...
Received healthy response to inference request in 2.5430378913879395s
Received healthy response to inference request in 2.4617202281951904s
Received healthy response to inference request in 2.2343993186950684s
Received healthy response to inference request in 2.3321568965911865s
Received healthy response to inference request in 2.6144490242004395s
5 requests
0 failed requests
5th percentile: 2.253950834274292
10th percentile: 2.2735023498535156
20th percentile: 2.312605381011963
30th percentile: 2.358069562911987
40th percentile: 2.409894895553589
50th percentile: 2.4617202281951904
60th percentile: 2.49424729347229
70th percentile: 2.52677435874939
80th percentile: 2.5573201179504395
90th percentile: 2.5858845710754395
95th percentile: 2.6001667976379395
99th percentile: 2.6115925788879393
mean time: 2.4371526718139647
Pipeline stage StressChecker completed in 61.31s
Running pipeline stage DaemonicModelEvalScorer
Pipeline stage DaemonicModelEvalScorer completed in 0.12s
Running pipeline stage DaemonicSafetyScorer
Pipeline stage DaemonicSafetyScorer completed in 0.17s
Running M-Eval for topic stay_in_character
%s, retrying in %s seconds...
neversleep-noromaid-v0-_8068_v82 status is now deployed due to DeploymentManager action
M-Eval Dataset for topic stay_in_character is loaded
%s, retrying in %s seconds...
neversleep-noromaid-v0-_8068_v82 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics