developer_uid: robert_irvine
submission_id: neversleep-noromaid-v0-_8068_v65
model_name: neversleep-noromaid-v0-_8068_v65
model_group: NeverSleep/Noromaid-v0.1
status: torndown
timestamp: 2024-06-07T18:58:24+00:00
num_battles: 28305
num_wins: 13918
celo_rating: 1171.01
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_v65
is_internal_developer: True
language_model: NeverSleep/Noromaid-v0.1-mixtral-8x7b-Instruct-v3
model_size: 47B
ranking_group: single
us_pacific_date: 2024-06-07
win_ratio: 0.49171524465642114
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}. Ask lots of personal questions to {user_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 respond in a novel and creative way. {bot_name} should ask lots of personal questions to {user_name} [/INST]{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-v65-mkmlizer
Waiting for job on neversleep-noromaid-v0-8068-v65-mkmlizer to finish
neversleep-noromaid-v0-8068-v65-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
neversleep-noromaid-v0-8068-v65-mkmlizer: ║     _____            __           __                                ║
neversleep-noromaid-v0-8068-v65-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
neversleep-noromaid-v0-8068-v65-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
neversleep-noromaid-v0-8068-v65-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
neversleep-noromaid-v0-8068-v65-mkmlizer: ║       /___/                                                         ║
neversleep-noromaid-v0-8068-v65-mkmlizer: ║                                                                     ║
neversleep-noromaid-v0-8068-v65-mkmlizer: ║  Version: 0.8.14                                                    ║
neversleep-noromaid-v0-8068-v65-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
neversleep-noromaid-v0-8068-v65-mkmlizer: ║  https://mk1.ai                                                     ║
neversleep-noromaid-v0-8068-v65-mkmlizer: ║                                                                     ║
neversleep-noromaid-v0-8068-v65-mkmlizer: ║  The license key for the current software has been verified as      ║
neversleep-noromaid-v0-8068-v65-mkmlizer: ║  belonging to:                                                      ║
neversleep-noromaid-v0-8068-v65-mkmlizer: ║                                                                     ║
neversleep-noromaid-v0-8068-v65-mkmlizer: ║  Chai Research Corp.                                                ║
neversleep-noromaid-v0-8068-v65-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
neversleep-noromaid-v0-8068-v65-mkmlizer: ║  Expiration: 2024-07-15 23:59:59                                    ║
neversleep-noromaid-v0-8068-v65-mkmlizer: ║                                                                     ║
neversleep-noromaid-v0-8068-v65-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
neversleep-noromaid-v0-8068-v65-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-v65-mkmlizer:   warnings.warn(warning_message, FutureWarning)
neversleep-noromaid-v0-8068-v65-mkmlizer: Downloaded to shared memory in 58.682s
neversleep-noromaid-v0-8068-v65-mkmlizer: quantizing model to /dev/shm/model_cache
neversleep-noromaid-v0-8068-v65-mkmlizer: Saving flywheel model at /dev/shm/model_cache
neversleep-noromaid-v0-8068-v65-mkmlizer: quantized model in 53.000s
neversleep-noromaid-v0-8068-v65-mkmlizer: Processed model NeverSleep/Noromaid-v0.1-mixtral-8x7b-Instruct-v3 in 118.225s
neversleep-noromaid-v0-8068-v65-mkmlizer: creating bucket guanaco-mkml-models
neversleep-noromaid-v0-8068-v65-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
neversleep-noromaid-v0-8068-v65-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v65
neversleep-noromaid-v0-8068-v65-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v65/config.json
neversleep-noromaid-v0-8068-v65-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v65/special_tokens_map.json
neversleep-noromaid-v0-8068-v65-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v65/tokenizer_config.json
neversleep-noromaid-v0-8068-v65-mkmlizer: cp /dev/shm/model_cache/tokenizer.model s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v65/tokenizer.model
neversleep-noromaid-v0-8068-v65-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v65/tokenizer.json
neversleep-noromaid-v0-8068-v65-mkmlizer: cp /dev/shm/model_cache/flywheel_model.3.safetensors s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v65/flywheel_model.3.safetensors
neversleep-noromaid-v0-8068-v65-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v65/flywheel_model.0.safetensors
neversleep-noromaid-v0-8068-v65-mkmlizer: cp /dev/shm/model_cache/flywheel_model.2.safetensors s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v65/flywheel_model.2.safetensors
neversleep-noromaid-v0-8068-v65-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v65/flywheel_model.1.safetensors
neversleep-noromaid-v0-8068-v65-mkmlizer: loading reward model from rirv938/reward_gpt2_medium_preference_24m_e2
neversleep-noromaid-v0-8068-v65-mkmlizer: 
Loading 0:   0%|          | 0/995 [00:00<?, ?it/s]
Loading 0:   5%|▌         | 52/995 [00:00<00:17, 54.28it/s]
Loading 0:  11%|█         | 107/995 [00:01<00:15, 59.20it/s]
Loading 0:  16%|█▋        | 162/995 [00:02<00:13, 60.49it/s]
Loading 0:  21%|██        | 210/995 [00:03<00:13, 57.89it/s]
Loading 0:  27%|██▋       | 265/995 [00:04<00:12, 58.49it/s]
Loading 0:  28%|██▊       | 278/995 [00:14<01:10, 10.22it/s]
Loading 0:  32%|███▏      | 320/995 [00:15<00:49, 13.58it/s]
Loading 0:  37%|███▋      | 368/995 [00:16<00:33, 18.54it/s]
Loading 0:  43%|████▎     | 423/995 [00:17<00:22, 25.06it/s]
Loading 0:  48%|████▊     | 478/995 [00:17<00:16, 31.86it/s]
Loading 0:  53%|█████▎    | 526/995 [00:18<00:12, 36.47it/s]
Loading 0:  57%|█████▋    | 565/995 [00:28<00:35, 12.08it/s]
Loading 0:  58%|█████▊    | 581/995 [00:29<00:33, 12.34it/s]
Loading 0:  64%|██████▍   | 636/995 [00:30<00:19, 18.04it/s]
Loading 0:  69%|██████▉   | 691/995 [00:30<00:12, 24.31it/s]
Loading 0:  74%|███████▍  | 739/995 [00:31<00:08, 29.22it/s]
Loading 0:  80%|███████▉  | 794/995 [00:32<00:05, 35.10it/s]
Loading 0:  85%|████████▌ | 846/995 [00:42<00:11, 12.95it/s]
Loading 0:  85%|████████▌ | 850/995 [00:43<00:12, 11.87it/s]
Loading 0:  90%|█████████ | 897/995 [00:44<00:05, 16.39it/s]
Loading 0:  96%|█████████▌| 952/995 [00:45<00:01, 22.90it/s]
Loading 0: 100%|██████████| 995/995 [00:46<00:00, 25.75it/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-v65-mkmlizer:   warnings.warn(
neversleep-noromaid-v0-8068-v65-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-v65-mkmlizer:   warnings.warn(
neversleep-noromaid-v0-8068-v65-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-v65-mkmlizer:   warnings.warn(
neversleep-noromaid-v0-8068-v65-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-v65-mkmlizer:   return self.fget.__get__(instance, owner)()
neversleep-noromaid-v0-8068-v65-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
neversleep-noromaid-v0-8068-v65-mkmlizer: Saving duration: 0.534s
neversleep-noromaid-v0-8068-v65-mkmlizer: Processed model rirv938/reward_gpt2_medium_preference_24m_e2 in 7.697s
neversleep-noromaid-v0-8068-v65-mkmlizer: creating bucket guanaco-reward-models
neversleep-noromaid-v0-8068-v65-mkmlizer: Bucket 's3://guanaco-reward-models/' created
neversleep-noromaid-v0-8068-v65-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/neversleep-noromaid-v0-8068-v65_reward
neversleep-noromaid-v0-8068-v65-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/neversleep-noromaid-v0-8068-v65_reward/config.json
neversleep-noromaid-v0-8068-v65-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/neversleep-noromaid-v0-8068-v65_reward/special_tokens_map.json
neversleep-noromaid-v0-8068-v65-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/neversleep-noromaid-v0-8068-v65_reward/tokenizer_config.json
neversleep-noromaid-v0-8068-v65-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/neversleep-noromaid-v0-8068-v65_reward/merges.txt
neversleep-noromaid-v0-8068-v65-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/neversleep-noromaid-v0-8068-v65_reward/vocab.json
neversleep-noromaid-v0-8068-v65-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/neversleep-noromaid-v0-8068-v65_reward/tokenizer.json
neversleep-noromaid-v0-8068-v65-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/neversleep-noromaid-v0-8068-v65_reward/reward.tensors
Job neversleep-noromaid-v0-8068-v65-mkmlizer completed after 360.39s with status: succeeded
Stopping job with name neversleep-noromaid-v0-8068-v65-mkmlizer
Pipeline stage MKMLizer completed in 360.99s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.09s
Running pipeline stage ISVCDeployer
Creating inference service neversleep-noromaid-v0-8068-v65
Waiting for inference service neversleep-noromaid-v0-8068-v65 to be ready
Inference service neversleep-noromaid-v0-8068-v65 ready after 70.43639254570007s
Pipeline stage ISVCDeployer completed in 76.24s
Running pipeline stage StressChecker
Received healthy response to inference request in 3.2771754264831543s
Received healthy response to inference request in 2.513106107711792s
Received healthy response to inference request in 2.515231132507324s
Received healthy response to inference request in 2.2940773963928223s
Received healthy response to inference request in 2.3693199157714844s
5 requests
0 failed requests
5th percentile: 2.3091259002685547
10th percentile: 2.324174404144287
20th percentile: 2.354271411895752
30th percentile: 2.398077154159546
40th percentile: 2.455591630935669
50th percentile: 2.513106107711792
60th percentile: 2.5139561176300047
70th percentile: 2.514806127548218
80th percentile: 2.6676199913024905
90th percentile: 2.972397708892822
95th percentile: 3.124786567687988
99th percentile: 3.246697654724121
mean time: 2.5937819957733153
Pipeline stage StressChecker completed in 13.61s
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_v65 status is now deployed due to DeploymentManager action
neversleep-noromaid-v0-_8068_v65 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of neversleep-noromaid-v0-_8068_v65
Running pipeline stage ISVCDeleter
Checking if service neversleep-noromaid-v0-8068-v65 is running
Skipping teardown as no inference service was found
Pipeline stage ISVCDeleter completed in 2.86s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key neversleep-noromaid-v0-8068-v65/config.json from bucket guanaco-mkml-models
Deleting key neversleep-noromaid-v0-8068-v65/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key neversleep-noromaid-v0-8068-v65/flywheel_model.1.safetensors from bucket guanaco-mkml-models
Deleting key neversleep-noromaid-v0-8068-v65/flywheel_model.2.safetensors from bucket guanaco-mkml-models
Deleting key neversleep-noromaid-v0-8068-v65/flywheel_model.3.safetensors from bucket guanaco-mkml-models
Deleting key neversleep-noromaid-v0-8068-v65/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key neversleep-noromaid-v0-8068-v65/tokenizer.json from bucket guanaco-mkml-models
Deleting key neversleep-noromaid-v0-8068-v65/tokenizer.model from bucket guanaco-mkml-models
Deleting key neversleep-noromaid-v0-8068-v65/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key neversleep-noromaid-v0-8068-v65_reward/config.json from bucket guanaco-reward-models
Deleting key neversleep-noromaid-v0-8068-v65_reward/merges.txt from bucket guanaco-reward-models
Deleting key neversleep-noromaid-v0-8068-v65_reward/reward.tensors from bucket guanaco-reward-models
Deleting key neversleep-noromaid-v0-8068-v65_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key neversleep-noromaid-v0-8068-v65_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key neversleep-noromaid-v0-8068-v65_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key neversleep-noromaid-v0-8068-v65_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 7.28s
neversleep-noromaid-v0-_8068_v65 status is now torndown due to DeploymentManager action