submission_id: neversleep-noromaid-v0-_8068_v83
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}. Your goal is to make sure the conversation is always novel and creative. {bot_name} should ask lots of questions. [/INST]\n', 'prompt_template': '{prompt}\n', 'bot_template': '{bot_name}: {message}</s>', 'user_template': '[INST] {user_name}: {message} [/INST]', 'response_template': '{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: 2024-06-10T22:04:52+00:00
model_name: neversleep-noromaid-v0-_8068_v83
model_eval_status: pending
model_group: NeverSleep/Noromaid-v0.1
num_battles: 52990
num_wins: 28223
celo_rating: 1169.28
propriety_score: 0.6980992065757178
propriety_total_count: 17519.0
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_v83
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: 0.5326099264012077
Resubmit model
Running pipeline stage MKMLizer
Starting job with name neversleep-noromaid-v0-8068-v83-mkmlizer
Waiting for job on neversleep-noromaid-v0-8068-v83-mkmlizer to finish
neversleep-noromaid-v0-8068-v83-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
neversleep-noromaid-v0-8068-v83-mkmlizer: ║ _____ __ __ ║
neversleep-noromaid-v0-8068-v83-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
neversleep-noromaid-v0-8068-v83-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
neversleep-noromaid-v0-8068-v83-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
neversleep-noromaid-v0-8068-v83-mkmlizer: ║ /___/ ║
neversleep-noromaid-v0-8068-v83-mkmlizer: ║ ║
neversleep-noromaid-v0-8068-v83-mkmlizer: ║ Version: 0.8.14 ║
neversleep-noromaid-v0-8068-v83-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
neversleep-noromaid-v0-8068-v83-mkmlizer: ║ https://mk1.ai ║
neversleep-noromaid-v0-8068-v83-mkmlizer: ║ ║
neversleep-noromaid-v0-8068-v83-mkmlizer: ║ The license key for the current software has been verified as ║
neversleep-noromaid-v0-8068-v83-mkmlizer: ║ belonging to: ║
neversleep-noromaid-v0-8068-v83-mkmlizer: ║ ║
neversleep-noromaid-v0-8068-v83-mkmlizer: ║ Chai Research Corp. ║
neversleep-noromaid-v0-8068-v83-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
neversleep-noromaid-v0-8068-v83-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
neversleep-noromaid-v0-8068-v83-mkmlizer: ║ ║
neversleep-noromaid-v0-8068-v83-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
neversleep-noromaid-v0-8068-v83-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-v83-mkmlizer: warnings.warn(warning_message, FutureWarning)
neversleep-noromaid-v0-8068-v83-mkmlizer: Downloaded to shared memory in 76.024s
neversleep-noromaid-v0-8068-v83-mkmlizer: quantizing model to /dev/shm/model_cache
neversleep-noromaid-v0-8068-v83-mkmlizer: Saving flywheel model at /dev/shm/model_cache
neversleep-noromaid-v0-8068-v83-mkmlizer: quantized model in 74.520s
neversleep-noromaid-v0-8068-v83-mkmlizer: Processed model NeverSleep/Noromaid-v0.1-mixtral-8x7b-Instruct-v3 in 156.879s
neversleep-noromaid-v0-8068-v83-mkmlizer: creating bucket guanaco-mkml-models
neversleep-noromaid-v0-8068-v83-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
neversleep-noromaid-v0-8068-v83-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v83
neversleep-noromaid-v0-8068-v83-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v83/config.json
neversleep-noromaid-v0-8068-v83-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v83/special_tokens_map.json
neversleep-noromaid-v0-8068-v83-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v83/tokenizer_config.json
neversleep-noromaid-v0-8068-v83-mkmlizer: cp /dev/shm/model_cache/tokenizer.model s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v83/tokenizer.model
neversleep-noromaid-v0-8068-v83-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v83/tokenizer.json
neversleep-noromaid-v0-8068-v83-mkmlizer: cp /dev/shm/model_cache/flywheel_model.3.safetensors s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v83/flywheel_model.3.safetensors
neversleep-noromaid-v0-8068-v83-mkmlizer: cp /dev/shm/model_cache/flywheel_model.2.safetensors s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v83/flywheel_model.2.safetensors
neversleep-noromaid-v0-8068-v83-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v83/flywheel_model.1.safetensors
neversleep-noromaid-v0-8068-v83-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v83/flywheel_model.0.safetensors
neversleep-noromaid-v0-8068-v83-mkmlizer: loading reward model from rirv938/reward_gpt2_medium_preference_24m_e2
neversleep-noromaid-v0-8068-v83-mkmlizer: Loading 0: 0%| | 0/995 [00:00<?, ?it/s] Loading 0: 5%|▌ | 52/995 [00:00<00:15, 59.49it/s] Loading 0: 11%|█ | 107/995 [00:01<00:14, 63.10it/s] Loading 0: 16%|█▋ | 162/995 [00:02<00:12, 64.26it/s] Loading 0: 21%|██ | 210/995 [00:03<00:12, 60.73it/s] Loading 0: 27%|██▋ | 265/995 [00:04<00:11, 62.49it/s] Loading 0: 28%|██▊ | 278/995 [00:19<01:41, 7.04it/s] Loading 0: 32%|███▏ | 320/995 [00:20<01:08, 9.79it/s] Loading 0: 37%|███▋ | 368/995 [00:20<00:45, 13.93it/s] Loading 0: 43%|████▎ | 423/995 [00:21<00:29, 19.66it/s] Loading 0: 48%|████▊ | 478/995 [00:22<00:19, 26.04it/s] Loading 0: 53%|█████▎ | 526/995 [00:23<00:14, 31.30it/s] Loading 0: 57%|█████▋ | 565/995 [00:38<00:53, 8.07it/s] Loading 0: 58%|█████▊ | 581/995 [00:39<00:48, 8.57it/s] Loading 0: 64%|██████▍ | 636/995 [00:40<00:27, 13.03it/s] Loading 0: 69%|██████▉ | 691/995 [00:41<00:16, 18.36it/s] Loading 0: 74%|███████▍ | 739/995 [00:42<00:11, 21.79it/s] Loading 0: 80%|███████▉ | 794/995 [00:43<00:07, 25.73it/s] Loading 0: 85%|████████▌ | 846/995 [00:59<00:17, 8.42it/s] Loading 0: 85%|████████▌ | 849/995 [01:00<00:18, 7.76it/s] Loading 0: 90%|█████████ | 897/995 [01:02<00:09, 10.86it/s] Loading 0: 96%|█████████▌| 952/995 [01:03<00:02, 15.44it/s] Loading 0: 100%|██████████| 995/995 [01:04<00:00, 18.47it/s] /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.
neversleep-noromaid-v0-8068-v83-mkmlizer: warnings.warn(
neversleep-noromaid-v0-8068-v83-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.
neversleep-noromaid-v0-8068-v83-mkmlizer: warnings.warn(
neversleep-noromaid-v0-8068-v83-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-v83-mkmlizer: warnings.warn(
neversleep-noromaid-v0-8068-v83-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-v83-mkmlizer: return self.fget.__get__(instance, owner)()
neversleep-noromaid-v0-8068-v83-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
neversleep-noromaid-v0-8068-v83-mkmlizer: Saving duration: 0.228s
neversleep-noromaid-v0-8068-v83-mkmlizer: Processed model rirv938/reward_gpt2_medium_preference_24m_e2 in 4.115s
neversleep-noromaid-v0-8068-v83-mkmlizer: creating bucket guanaco-reward-models
neversleep-noromaid-v0-8068-v83-mkmlizer: Bucket 's3://guanaco-reward-models/' created
neversleep-noromaid-v0-8068-v83-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/neversleep-noromaid-v0-8068-v83_reward
neversleep-noromaid-v0-8068-v83-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/neversleep-noromaid-v0-8068-v83_reward/config.json
neversleep-noromaid-v0-8068-v83-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/neversleep-noromaid-v0-8068-v83_reward/special_tokens_map.json
neversleep-noromaid-v0-8068-v83-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/neversleep-noromaid-v0-8068-v83_reward/tokenizer_config.json
neversleep-noromaid-v0-8068-v83-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/neversleep-noromaid-v0-8068-v83_reward/vocab.json
neversleep-noromaid-v0-8068-v83-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/neversleep-noromaid-v0-8068-v83_reward/merges.txt
neversleep-noromaid-v0-8068-v83-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/neversleep-noromaid-v0-8068-v83_reward/tokenizer.json
neversleep-noromaid-v0-8068-v83-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/neversleep-noromaid-v0-8068-v83_reward/reward.tensors
Job neversleep-noromaid-v0-8068-v83-mkmlizer completed after 198.25s with status: succeeded
Stopping job with name neversleep-noromaid-v0-8068-v83-mkmlizer
Pipeline stage MKMLizer completed in 200.61s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.41s
Running pipeline stage ISVCDeployer
Creating inference service neversleep-noromaid-v0-8068-v83
Waiting for inference service neversleep-noromaid-v0-8068-v83 to be ready
Inference service neversleep-noromaid-v0-8068-v83 ready after 192.8096957206726s
Pipeline stage ISVCDeployer completed in 199.80s
Running pipeline stage StressChecker
Received healthy response to inference request in 17.333614587783813s
Received healthy response to inference request in 2.366945743560791s
Received healthy response to inference request in 2.5258078575134277s
Received healthy response to inference request in 2.2017884254455566s
Received healthy response to inference request in 2.6488096714019775s
5 requests
0 failed requests
5th percentile: 2.2348198890686035
10th percentile: 2.2678513526916504
20th percentile: 2.333914279937744
30th percentile: 2.398718166351318
40th percentile: 2.462263011932373
50th percentile: 2.5258078575134277
60th percentile: 2.575008583068848
70th percentile: 2.6242093086242675
80th percentile: 5.585770654678347
90th percentile: 11.459692621231081
95th percentile: 14.396653604507444
99th percentile: 16.74622239112854
mean time: 5.415393257141114
Pipeline stage StressChecker completed in 30.10s
Running pipeline stage DaemonicModelEvalScorer
Pipeline stage DaemonicModelEvalScorer completed in 0.13s
Running pipeline stage DaemonicSafetyScorer
Running M-Eval for topic stay_in_character
Pipeline stage DaemonicSafetyScorer completed in 0.16s
%s, retrying in %s seconds...
M-Eval Dataset for topic stay_in_character is loaded
neversleep-noromaid-v0-_8068_v83 status is now deployed due to DeploymentManager action
%s, retrying in %s seconds...
neversleep-noromaid-v0-_8068_v83 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics