developer_uid: robert_irvine
submission_id: neversleep-noromaid-v0-_8068_v73
model_name: neversleep-noromaid-v0-_8068_v73
model_group: NeverSleep/Noromaid-v0.1
status: torndown
timestamp: 2024-06-09T21:02:36+00:00
num_battles: 6608
num_wins: 3248
celo_rating: 1177.53
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: 1024
max_output_tokens: 64
display_name: neversleep-noromaid-v0-_8068_v73
is_internal_developer: True
language_model: NeverSleep/Noromaid-v0.1-mixtral-8x7b-Instruct-v3
model_size: 47B
ranking_group: single
us_pacific_date: 2024-06-09
win_ratio: 0.4915254237288136
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': 1024, '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: {'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'}
model_eval_status: success
Resubmit model
Running pipeline stage MKMLizer
Starting job with name neversleep-noromaid-v0-8068-v73-mkmlizer
Waiting for job on neversleep-noromaid-v0-8068-v73-mkmlizer to finish
neversleep-noromaid-v0-8068-v73-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
neversleep-noromaid-v0-8068-v73-mkmlizer: ║     _____            __           __                                ║
neversleep-noromaid-v0-8068-v73-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
neversleep-noromaid-v0-8068-v73-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
neversleep-noromaid-v0-8068-v73-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
neversleep-noromaid-v0-8068-v73-mkmlizer: ║       /___/                                                         ║
neversleep-noromaid-v0-8068-v73-mkmlizer: ║                                                                     ║
neversleep-noromaid-v0-8068-v73-mkmlizer: ║  Version: 0.8.14                                                    ║
neversleep-noromaid-v0-8068-v73-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
neversleep-noromaid-v0-8068-v73-mkmlizer: ║  https://mk1.ai                                                     ║
neversleep-noromaid-v0-8068-v73-mkmlizer: ║                                                                     ║
neversleep-noromaid-v0-8068-v73-mkmlizer: ║  The license key for the current software has been verified as      ║
neversleep-noromaid-v0-8068-v73-mkmlizer: ║  belonging to:                                                      ║
neversleep-noromaid-v0-8068-v73-mkmlizer: ║                                                                     ║
neversleep-noromaid-v0-8068-v73-mkmlizer: ║  Chai Research Corp.                                                ║
neversleep-noromaid-v0-8068-v73-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
neversleep-noromaid-v0-8068-v73-mkmlizer: ║  Expiration: 2024-07-15 23:59:59                                    ║
neversleep-noromaid-v0-8068-v73-mkmlizer: ║                                                                     ║
neversleep-noromaid-v0-8068-v73-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
neversleep-noromaid-v0-8068-v73-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-v73-mkmlizer:   warnings.warn(warning_message, FutureWarning)
neversleep-noromaid-v0-8068-v73-mkmlizer: Downloaded to shared memory in 61.852s
neversleep-noromaid-v0-8068-v73-mkmlizer: quantizing model to /dev/shm/model_cache
neversleep-noromaid-v0-8068-v73-mkmlizer: Saving flywheel model at /dev/shm/model_cache
neversleep-noromaid-v0-8068-v73-mkmlizer: quantized model in 52.965s
neversleep-noromaid-v0-8068-v73-mkmlizer: creating bucket guanaco-mkml-models
neversleep-noromaid-v0-8068-v73-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
neversleep-noromaid-v0-8068-v73-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v73
neversleep-noromaid-v0-8068-v73-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v73/tokenizer_config.json
neversleep-noromaid-v0-8068-v73-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v73/config.json
neversleep-noromaid-v0-8068-v73-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v73/special_tokens_map.json
neversleep-noromaid-v0-8068-v73-mkmlizer: cp /dev/shm/model_cache/tokenizer.model s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v73/tokenizer.model
neversleep-noromaid-v0-8068-v73-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v73/tokenizer.json
neversleep-noromaid-v0-8068-v73-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v73/flywheel_model.0.safetensors
neversleep-noromaid-v0-8068-v73-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v73/flywheel_model.1.safetensors
neversleep-noromaid-v0-8068-v73-mkmlizer: cp /dev/shm/model_cache/flywheel_model.2.safetensors s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v73/flywheel_model.2.safetensors
neversleep-noromaid-v0-8068-v73-mkmlizer: loading reward model from rirv938/reward_gpt2_medium_preference_24m_e2
neversleep-noromaid-v0-8068-v73-mkmlizer: 
Loading 0:   0%|          | 0/995 [00:00<?, ?it/s]
Loading 0:   5%|▌         | 52/995 [00:00<00:15, 60.85it/s]
Loading 0:  11%|█         | 107/995 [00:01<00:13, 63.94it/s]
Loading 0:  16%|█▋        | 162/995 [00:02<00:12, 65.11it/s]
Loading 0:  21%|██        | 210/995 [00:03<00:12, 62.15it/s]
Loading 0:  27%|██▋       | 265/995 [00:04<00:11, 63.90it/s]
Loading 0:  28%|██▊       | 278/995 [00:13<01:05, 10.89it/s]
Loading 0:  32%|███▏      | 320/995 [00:14<00:46, 14.48it/s]
Loading 0:  37%|███▋      | 368/995 [00:15<00:31, 19.79it/s]
Loading 0:  43%|████▎     | 423/995 [00:15<00:21, 26.73it/s]
Loading 0:  48%|████▊     | 478/995 [00:16<00:15, 33.73it/s]
Loading 0:  53%|█████▎    | 526/995 [00:17<00:12, 38.70it/s]
Loading 0:  57%|█████▋    | 565/995 [00:27<00:37, 11.51it/s]
Loading 0:  58%|█████▊    | 581/995 [00:28<00:34, 11.85it/s]
Loading 0:  64%|██████▍   | 636/995 [00:29<00:20, 17.47it/s]
Loading 0:  69%|██████▉   | 691/995 [00:30<00:12, 23.76it/s]
Loading 0:  74%|███████▍  | 739/995 [00:31<00:08, 29.12it/s]
Loading 0:  80%|███████▉  | 794/995 [00:32<00:05, 35.82it/s]
Loading 0:  85%|████████▌ | 846/995 [00:42<00:11, 12.75it/s]
Loading 0:  86%|████████▌ | 851/995 [00:43<00:12, 11.87it/s]
Loading 0:  90%|█████████ | 897/995 [00:43<00:05, 16.43it/s]
Loading 0:  96%|█████████▌| 952/995 [00:44<00:01, 23.28it/s]
Loading 0: 100%|██████████| 995/995 [00:45<00:00, 26.12it/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-v73-mkmlizer:   warnings.warn(
neversleep-noromaid-v0-8068-v73-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-v73-mkmlizer:   warnings.warn(
neversleep-noromaid-v0-8068-v73-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-v73-mkmlizer:   warnings.warn(
neversleep-noromaid-v0-8068-v73-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-v73-mkmlizer:   return self.fget.__get__(instance, owner)()
neversleep-noromaid-v0-8068-v73-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
neversleep-noromaid-v0-8068-v73-mkmlizer: Saving duration: 0.222s
neversleep-noromaid-v0-8068-v73-mkmlizer: Processed model rirv938/reward_gpt2_medium_preference_24m_e2 in 7.035s
neversleep-noromaid-v0-8068-v73-mkmlizer: creating bucket guanaco-reward-models
neversleep-noromaid-v0-8068-v73-mkmlizer: Bucket 's3://guanaco-reward-models/' created
neversleep-noromaid-v0-8068-v73-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/neversleep-noromaid-v0-8068-v73_reward
neversleep-noromaid-v0-8068-v73-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/neversleep-noromaid-v0-8068-v73_reward/special_tokens_map.json
neversleep-noromaid-v0-8068-v73-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/neversleep-noromaid-v0-8068-v73_reward/config.json
neversleep-noromaid-v0-8068-v73-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/neversleep-noromaid-v0-8068-v73_reward/tokenizer_config.json
neversleep-noromaid-v0-8068-v73-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/neversleep-noromaid-v0-8068-v73_reward/vocab.json
neversleep-noromaid-v0-8068-v73-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/neversleep-noromaid-v0-8068-v73_reward/merges.txt
neversleep-noromaid-v0-8068-v73-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/neversleep-noromaid-v0-8068-v73_reward/tokenizer.json
neversleep-noromaid-v0-8068-v73-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/neversleep-noromaid-v0-8068-v73_reward/reward.tensors
Job neversleep-noromaid-v0-8068-v73-mkmlizer completed after 155.25s with status: succeeded
Stopping job with name neversleep-noromaid-v0-8068-v73-mkmlizer
Pipeline stage MKMLizer completed in 157.52s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.09s
Running pipeline stage ISVCDeployer
Creating inference service neversleep-noromaid-v0-8068-v73
Waiting for inference service neversleep-noromaid-v0-8068-v73 to be ready
Failed to get response for submission blend_kefet_2024-05-01: ('http://mistralai-mixtral-8x7b-3473-v33-predictor-default.tenant-chaiml-guanaco.knative.ord1.coreweave.cloud/v1/models/GPT-J-6B-lit-v2:predict', 'upstream connect error or disconnect/reset before headers. reset reason: overflow')
Tearing down inference service neversleep-noromaid-v0-8068-v73
%s, retrying in %s seconds...
Creating inference service neversleep-noromaid-v0-8068-v73
Waiting for inference service neversleep-noromaid-v0-8068-v73 to be ready
Inference service neversleep-noromaid-v0-8068-v73 ready after 321.9100260734558s
Pipeline stage ISVCDeployer completed in 938.29s
Running pipeline stage StressChecker
Received healthy response to inference request in 3.2596518993377686s
Received healthy response to inference request in 2.2916452884674072s
Received healthy response to inference request in 2.4126641750335693s
Received healthy response to inference request in 2.3271334171295166s
Received healthy response to inference request in 1.9109175205230713s
5 requests
0 failed requests
5th percentile: 1.9870630741119384
10th percentile: 2.0632086277008055
20th percentile: 2.21549973487854
30th percentile: 2.298742914199829
40th percentile: 2.312938165664673
50th percentile: 2.3271334171295166
60th percentile: 2.361345720291138
70th percentile: 2.3955580234527587
80th percentile: 2.5820617198944094
90th percentile: 2.920856809616089
95th percentile: 3.0902543544769285
99th percentile: 3.2257723903656004
mean time: 2.440402460098267
Pipeline stage StressChecker completed in 12.81s
Running pipeline stage DaemonicModelEvalScorer
Pipeline stage DaemonicModelEvalScorer completed in 0.03s
Running pipeline stage DaemonicSafetyScorer
Running M-Eval for topic stay_in_character
Pipeline stage DaemonicSafetyScorer completed in 0.03s
M-Eval Dataset for topic stay_in_character is loaded
neversleep-noromaid-v0-_8068_v73 status is now deployed due to DeploymentManager action
neversleep-noromaid-v0-_8068_v73 status is now inactive due to admin request
neversleep-noromaid-v0-_8068_v73 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of neversleep-noromaid-v0-_8068_v73
Running pipeline stage ISVCDeleter
Checking if service neversleep-noromaid-v0-8068-v73 is running
Skipping teardown as no inference service was found
Pipeline stage ISVCDeleter completed in 2.23s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key neversleep-noromaid-v0-8068-v73/config.json from bucket guanaco-mkml-models
Deleting key neversleep-noromaid-v0-8068-v73/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key neversleep-noromaid-v0-8068-v73/flywheel_model.1.safetensors from bucket guanaco-mkml-models
admin requested tearing down of neversleep-noromaid-v0-_8068_v73
Running pipeline stage ISVCDeleter
Pipeline stage %s skipped, reason=%s
Pipeline stage ISVCDeleter completed in 0.45s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key neversleep-noromaid-v0-8068-v73/flywheel_model.2.safetensors from bucket guanaco-mkml-models
Deleting key neversleep-noromaid-v0-8068-v73/flywheel_model.3.safetensors from bucket guanaco-mkml-models
Deleting key neversleep-noromaid-v0-8068-v73/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key neversleep-noromaid-v0-8068-v73/tokenizer.json from bucket guanaco-mkml-models
Deleting key neversleep-noromaid-v0-8068-v73/tokenizer.model from bucket guanaco-mkml-models
Deleting key neversleep-noromaid-v0-8068-v73/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key neversleep-noromaid-v0-8068-v73_reward/config.json from bucket guanaco-reward-models
Deleting key neversleep-noromaid-v0-8068-v73_reward/merges.txt from bucket guanaco-reward-models
Deleting key neversleep-noromaid-v0-8068-v73_reward/reward.tensors from bucket guanaco-reward-models
Deleting key neversleep-noromaid-v0-8068-v73_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key neversleep-noromaid-v0-8068-v73_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key neversleep-noromaid-v0-8068-v73_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key neversleep-noromaid-v0-8068-v73_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 7.73s
neversleep-noromaid-v0-_8068_v73 status is now torndown due to DeploymentManager action