developer_uid: robert_irvine
submission_id: neversleep-noromaid-v0-_8068_v43
model_name: neversleep-noromaid-v0-_8068_v43
model_group: NeverSleep/Noromaid-v0.1
status: torndown
timestamp: 2024-05-15T21:43:54+00:00
num_battles: 17947
num_wins: 8900
celo_rating: 1165.49
family_friendly_score: 0.0
submission_type: basic
model_repo: NeverSleep/Noromaid-v0.1-mixtral-8x7b-Instruct-v3
model_architecture: MixtralForCausalLM
reward_repo: rirv938/reward_gpt2_medium_preference_24m_e2
model_num_parameters: 46702792704.0
best_of: 4
max_input_tokens: 512
max_output_tokens: 64
display_name: neversleep-noromaid-v0-_8068_v43
is_internal_developer: True
language_model: NeverSleep/Noromaid-v0.1-mixtral-8x7b-Instruct-v3
model_size: 47B
ranking_group: single
us_pacific_date: 2024-05-15
win_ratio: 0.4959046080124812
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': '### Instruction:\nThis is an entertaining conversation. You are {bot_name} who has persona: {memory}.\nPlay the role of {bot_name}. Engage in a chat with {user_name} while staying in character. You should create a fun dialogue which entertains {user_name}.\n', 'prompt_template': '{prompt}\n\n', 'bot_template': '### Response:\n{bot_name}: {message}\n\n', 'user_template': '### Input:\n{user_name}: {message}\n\n', 'response_template': '### Response:\n{bot_name}:', 'truncate_by_message': False}
model_eval_status: pending
reward_formatter: {'bot_template': 'Bot: {message}\n', 'memory_template': 'Memory: {memory}\n', 'prompt_template': '{prompt}\n', 'response_template': 'Bot:', 'truncate_by_message': False, 'user_template': 'User: {message}\n'}
Resubmit model
Running pipeline stage MKMLizer
Starting job with name neversleep-noromaid-v0-8068-v43-mkmlizer
Waiting for job on neversleep-noromaid-v0-8068-v43-mkmlizer to finish
neversleep-noromaid-v0-8068-v43-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
neversleep-noromaid-v0-8068-v43-mkmlizer: ║     _____            __           __                                ║
neversleep-noromaid-v0-8068-v43-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
neversleep-noromaid-v0-8068-v43-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
neversleep-noromaid-v0-8068-v43-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
neversleep-noromaid-v0-8068-v43-mkmlizer: ║       /___/                                                         ║
neversleep-noromaid-v0-8068-v43-mkmlizer: ║                                                                     ║
neversleep-noromaid-v0-8068-v43-mkmlizer: ║  Version: 0.8.14                                                    ║
neversleep-noromaid-v0-8068-v43-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
neversleep-noromaid-v0-8068-v43-mkmlizer: ║  https://mk1.ai                                                     ║
neversleep-noromaid-v0-8068-v43-mkmlizer: ║                                                                     ║
neversleep-noromaid-v0-8068-v43-mkmlizer: ║  The license key for the current software has been verified as      ║
neversleep-noromaid-v0-8068-v43-mkmlizer: ║  belonging to:                                                      ║
neversleep-noromaid-v0-8068-v43-mkmlizer: ║                                                                     ║
neversleep-noromaid-v0-8068-v43-mkmlizer: ║  Chai Research Corp.                                                ║
neversleep-noromaid-v0-8068-v43-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
neversleep-noromaid-v0-8068-v43-mkmlizer: ║  Expiration: 2024-07-15 23:59:59                                    ║
neversleep-noromaid-v0-8068-v43-mkmlizer: ║                                                                     ║
neversleep-noromaid-v0-8068-v43-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
neversleep-noromaid-v0-8068-v43-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-v43-mkmlizer:   warnings.warn(warning_message, FutureWarning)
neversleep-noromaid-v0-8068-v43-mkmlizer: Downloaded to shared memory in 76.810s
neversleep-noromaid-v0-8068-v43-mkmlizer: quantizing model to /dev/shm/model_cache
neversleep-noromaid-v0-8068-v43-mkmlizer: Saving flywheel model at /dev/shm/model_cache
neversleep-noromaid-v0-8068-v43-mkmlizer: quantized model in 53.410s
neversleep-noromaid-v0-8068-v43-mkmlizer: Processed model NeverSleep/Noromaid-v0.1-mixtral-8x7b-Instruct-v3 in 136.833s
neversleep-noromaid-v0-8068-v43-mkmlizer: creating bucket guanaco-mkml-models
neversleep-noromaid-v0-8068-v43-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
neversleep-noromaid-v0-8068-v43-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v43
neversleep-noromaid-v0-8068-v43-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v43/special_tokens_map.json
neversleep-noromaid-v0-8068-v43-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v43/config.json
neversleep-noromaid-v0-8068-v43-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v43/tokenizer_config.json
neversleep-noromaid-v0-8068-v43-mkmlizer: cp /dev/shm/model_cache/tokenizer.model s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v43/tokenizer.model
neversleep-noromaid-v0-8068-v43-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v43/tokenizer.json
neversleep-noromaid-v0-8068-v43-mkmlizer: cp /dev/shm/model_cache/flywheel_model.3.safetensors s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v43/flywheel_model.3.safetensors
neversleep-noromaid-v0-8068-v43-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v43/flywheel_model.0.safetensors
neversleep-noromaid-v0-8068-v43-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v43/flywheel_model.1.safetensors
neversleep-noromaid-v0-8068-v43-mkmlizer: loading reward model from rirv938/reward_gpt2_medium_preference_24m_e2
neversleep-noromaid-v0-8068-v43-mkmlizer: 
Loading 0:   0%|          | 0/995 [00:00<?, ?it/s]
Loading 0:   5%|▌         | 52/995 [00:00<00:17, 54.62it/s]
Loading 0:  11%|█         | 107/995 [00:01<00:15, 58.48it/s]
Loading 0:  16%|█▋        | 162/995 [00:02<00:13, 60.07it/s]
Loading 0:  21%|██        | 210/995 [00:03<00:13, 57.41it/s]
Loading 0:  27%|██▋       | 265/995 [00:04<00:12, 59.21it/s]
Loading 0:  28%|██▊       | 278/995 [00:13<01:05, 11.03it/s]
Loading 0:  32%|███▏      | 320/995 [00:14<00:46, 14.48it/s]
Loading 0:  37%|███▋      | 368/995 [00:15<00:33, 18.75it/s]
Loading 0:  43%|████▎     | 423/995 [00:16<00:22, 25.23it/s]
Loading 0:  48%|████▊     | 478/995 [00:17<00:16, 31.92it/s]
Loading 0:  53%|█████▎    | 526/995 [00:18<00:12, 36.47it/s]
Loading 0:  57%|█████▋    | 565/995 [00:27<00:36, 11.86it/s]
Loading 0:  58%|█████▊    | 581/995 [00:29<00:34, 12.15it/s]
Loading 0:  64%|██████▍   | 636/995 [00:29<00:20, 17.78it/s]
Loading 0:  69%|██████▉   | 691/995 [00:30<00:12, 23.89it/s]
Loading 0:  74%|███████▍  | 739/995 [00:31<00:08, 28.92it/s]
Loading 0:  80%|███████▉  | 794/995 [00:32<00:05, 35.57it/s]
Loading 0:  85%|████████▌ | 846/995 [00:41<00:11, 13.11it/s]
Loading 0:  85%|████████▌ | 850/995 [00:43<00:11, 12.10it/s]
Loading 0:  90%|█████████ | 897/995 [00:43<00:05, 16.66it/s]
Loading 0:  96%|█████████▌| 952/995 [00:44<00:01, 23.32it/s]
Loading 0:  99%|█████████▉| 986/995 [00:44<00:00, 30.34it/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-v43-mkmlizer:   warnings.warn(
neversleep-noromaid-v0-8068-v43-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-v43-mkmlizer:   warnings.warn(
neversleep-noromaid-v0-8068-v43-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-v43-mkmlizer:   warnings.warn(
neversleep-noromaid-v0-8068-v43-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-v43-mkmlizer:   return self.fget.__get__(instance, owner)()
neversleep-noromaid-v0-8068-v43-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
neversleep-noromaid-v0-8068-v43-mkmlizer: Saving duration: 0.282s
neversleep-noromaid-v0-8068-v43-mkmlizer: Processed model rirv938/reward_gpt2_medium_preference_24m_e2 in 3.721s
neversleep-noromaid-v0-8068-v43-mkmlizer: creating bucket guanaco-reward-models
neversleep-noromaid-v0-8068-v43-mkmlizer: Bucket 's3://guanaco-reward-models/' created
neversleep-noromaid-v0-8068-v43-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/neversleep-noromaid-v0-8068-v43_reward
neversleep-noromaid-v0-8068-v43-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/neversleep-noromaid-v0-8068-v43_reward/config.json
neversleep-noromaid-v0-8068-v43-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/neversleep-noromaid-v0-8068-v43_reward/special_tokens_map.json
neversleep-noromaid-v0-8068-v43-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/neversleep-noromaid-v0-8068-v43_reward/tokenizer_config.json
neversleep-noromaid-v0-8068-v43-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/neversleep-noromaid-v0-8068-v43_reward/merges.txt
neversleep-noromaid-v0-8068-v43-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/neversleep-noromaid-v0-8068-v43_reward/tokenizer.json
neversleep-noromaid-v0-8068-v43-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/neversleep-noromaid-v0-8068-v43_reward/vocab.json
neversleep-noromaid-v0-8068-v43-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/neversleep-noromaid-v0-8068-v43_reward/reward.tensors
Job neversleep-noromaid-v0-8068-v43-mkmlizer completed after 226.32s with status: succeeded
Stopping job with name neversleep-noromaid-v0-8068-v43-mkmlizer
Pipeline stage MKMLizer completed in 227.92s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.33s
Running pipeline stage ISVCDeployer
Creating inference service neversleep-noromaid-v0-8068-v43
Waiting for inference service neversleep-noromaid-v0-8068-v43 to be ready
Inference service neversleep-noromaid-v0-8068-v43 ready after 121.6299033164978s
Pipeline stage ISVCDeployer completed in 128.66s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.5593276023864746s
Received healthy response to inference request in 2.094154119491577s
Received healthy response to inference request in 2.1165812015533447s
Received healthy response to inference request in 2.1583635807037354s
Received healthy response to inference request in 1.5628299713134766s
5 requests
0 failed requests
5th percentile: 1.6690948009490967
10th percentile: 1.7753596305847168
20th percentile: 1.987889289855957
30th percentile: 2.0986395359039305
40th percentile: 2.1076103687286376
50th percentile: 2.1165812015533447
60th percentile: 2.133294153213501
70th percentile: 2.1500071048736573
80th percentile: 2.238556385040283
90th percentile: 2.398941993713379
95th percentile: 2.4791347980499268
99th percentile: 2.543289041519165
mean time: 2.098251295089722
Pipeline stage StressChecker completed in 13.46s
Running pipeline stage DaemonicModelEvalScorer
Pipeline stage DaemonicModelEvalScorer completed in 0.15s
Running M-Eval for topic stay_in_character
Running pipeline stage DaemonicSafetyScorer
M-Eval Dataset for topic stay_in_character is loaded
Pipeline stage DaemonicSafetyScorer completed in 0.27s
%s, retrying in %s seconds...
neversleep-noromaid-v0-_8068_v43 status is now deployed due to DeploymentManager action
%s, retrying in %s seconds...
Scoring model output for bot %s
neversleep-noromaid-v0-_8068_v43 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of neversleep-noromaid-v0-_8068_v43
Running pipeline stage ISVCDeleter
Checking if service neversleep-noromaid-v0-8068-v43 is running
Tearing down inference service neversleep-noromaid-v0-8068-v43
Toredown service neversleep-noromaid-v0-8068-v43
Pipeline stage ISVCDeleter completed in 3.85s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key neversleep-noromaid-v0-8068-v43/config.json from bucket guanaco-mkml-models
Deleting key neversleep-noromaid-v0-8068-v43/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key neversleep-noromaid-v0-8068-v43/flywheel_model.1.safetensors from bucket guanaco-mkml-models
Deleting key neversleep-noromaid-v0-8068-v43/flywheel_model.2.safetensors from bucket guanaco-mkml-models
Deleting key neversleep-noromaid-v0-8068-v43/flywheel_model.3.safetensors from bucket guanaco-mkml-models
Deleting key neversleep-noromaid-v0-8068-v43/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key neversleep-noromaid-v0-8068-v43/tokenizer.json from bucket guanaco-mkml-models
Deleting key neversleep-noromaid-v0-8068-v43/tokenizer.model from bucket guanaco-mkml-models
Deleting key neversleep-noromaid-v0-8068-v43/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key neversleep-noromaid-v0-8068-v43_reward/config.json from bucket guanaco-reward-models
Deleting key neversleep-noromaid-v0-8068-v43_reward/merges.txt from bucket guanaco-reward-models
Deleting key neversleep-noromaid-v0-8068-v43_reward/reward.tensors from bucket guanaco-reward-models
Deleting key neversleep-noromaid-v0-8068-v43_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key neversleep-noromaid-v0-8068-v43_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key neversleep-noromaid-v0-8068-v43_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key neversleep-noromaid-v0-8068-v43_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 5.47s
neversleep-noromaid-v0-_8068_v43 status is now torndown due to DeploymentManager action