neversleep-noromaid-v0-_8068

developer_uid: robert_irvine

submission_id: neversleep-noromaid-v0-_8068_v66

model_name: neversleep-noromaid-v0-_8068_v66

model_group: NeverSleep/Noromaid-v0.1

status: torndown

timestamp: 2024-06-09T20:42:19+00:00

num_battles: 17212

num_wins: 7847

celo_rating: 1152.83

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_v66

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: 0.4559028584708343

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': '[INST] {bot_name} should ask an engaging question [/INST]{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-v66-mkmlizer
Waiting for job on neversleep-noromaid-v0-8068-v66-mkmlizer to finish
neversleep-noromaid-v0-8068-v66-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
neversleep-noromaid-v0-8068-v66-mkmlizer: ║     _____            __           __                                ║
neversleep-noromaid-v0-8068-v66-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
neversleep-noromaid-v0-8068-v66-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
neversleep-noromaid-v0-8068-v66-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
neversleep-noromaid-v0-8068-v66-mkmlizer: ║       /___/                                                         ║
neversleep-noromaid-v0-8068-v66-mkmlizer: ║                                                                     ║
neversleep-noromaid-v0-8068-v66-mkmlizer: ║  Version: 0.8.14                                                    ║
neversleep-noromaid-v0-8068-v66-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
neversleep-noromaid-v0-8068-v66-mkmlizer: ║  https://mk1.ai                                                     ║
neversleep-noromaid-v0-8068-v66-mkmlizer: ║                                                                     ║
neversleep-noromaid-v0-8068-v66-mkmlizer: ║  The license key for the current software has been verified as      ║
neversleep-noromaid-v0-8068-v66-mkmlizer: ║  belonging to:                                                      ║
neversleep-noromaid-v0-8068-v66-mkmlizer: ║                                                                     ║
neversleep-noromaid-v0-8068-v66-mkmlizer: ║  Chai Research Corp.                                                ║
neversleep-noromaid-v0-8068-v66-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
neversleep-noromaid-v0-8068-v66-mkmlizer: ║  Expiration: 2024-07-15 23:59:59                                    ║
neversleep-noromaid-v0-8068-v66-mkmlizer: ║                                                                     ║
neversleep-noromaid-v0-8068-v66-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
neversleep-noromaid-v0-8068-v66-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-v66-mkmlizer:   warnings.warn(warning_message, FutureWarning)
neversleep-noromaid-v0-8068-v66-mkmlizer: Downloaded to shared memory in 122.954s
neversleep-noromaid-v0-8068-v66-mkmlizer: quantizing model to /dev/shm/model_cache
neversleep-noromaid-v0-8068-v66-mkmlizer: Saving flywheel model at /dev/shm/model_cache
neversleep-noromaid-v0-8068-v66-mkmlizer: quantized model in 53.288s
neversleep-noromaid-v0-8068-v66-mkmlizer: Processed model NeverSleep/Noromaid-v0.1-mixtral-8x7b-Instruct-v3 in 181.637s
neversleep-noromaid-v0-8068-v66-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v66/tokenizer_config.json
neversleep-noromaid-v0-8068-v66-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v66/tokenizer.json
neversleep-noromaid-v0-8068-v66-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v66/config.json
neversleep-noromaid-v0-8068-v66-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v66/special_tokens_map.json
neversleep-noromaid-v0-8068-v66-mkmlizer: cp /dev/shm/model_cache/tokenizer.model s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v66/tokenizer.model
neversleep-noromaid-v0-8068-v66-mkmlizer: cp /dev/shm/model_cache/flywheel_model.3.safetensors s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v66/flywheel_model.3.safetensors
neversleep-noromaid-v0-8068-v66-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v66/flywheel_model.0.safetensors
neversleep-noromaid-v0-8068-v66-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v66/flywheel_model.1.safetensors
neversleep-noromaid-v0-8068-v66-mkmlizer: cp /dev/shm/model_cache/flywheel_model.2.safetensors s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v66/flywheel_model.2.safetensors
neversleep-noromaid-v0-8068-v66-mkmlizer: loading reward model from rirv938/reward_gpt2_medium_preference_24m_e2
neversleep-noromaid-v0-8068-v66-mkmlizer: 
Loading 0:   0%|          | 0/995 [00:00<?, ?it/s]
Loading 0:   5%|▌         | 52/995 [00:00<00:15, 59.48it/s]
Loading 0:  11%|█         | 107/995 [00:01<00:13, 63.49it/s]
Loading 0:  16%|█▋        | 162/995 [00:02<00:12, 65.25it/s]
Loading 0:  21%|██        | 210/995 [00:03<00:12, 62.71it/s]
Loading 0:  27%|██▋       | 265/995 [00:04<00:11, 64.25it/s]
Loading 0:  28%|██▊       | 278/995 [00:13<01:06, 10.86it/s]
Loading 0:  32%|███▏      | 320/995 [00:14<00:46, 14.41it/s]
Loading 0:  37%|███▋      | 368/995 [00:15<00:32, 19.57it/s]
Loading 0:  43%|████▎     | 423/995 [00:16<00:21, 26.38it/s]
Loading 0:  48%|████▊     | 478/995 [00:16<00:15, 33.12it/s]
Loading 0:  53%|█████▎    | 526/995 [00:17<00:12, 37.61it/s]
Loading 0:  57%|█████▋    | 564/995 [00:27<00:11, 37.61it/s]
Loading 0:  57%|█████▋    | 565/995 [00:27<00:37, 11.45it/s]
Loading 0:  58%|█████▊    | 581/995 [00:29<00:35, 11.79it/s]
Loading 0:  64%|██████▍   | 636/995 [00:29<00:20, 17.43it/s]
Loading 0:  69%|██████▉   | 691/995 [00:30<00:12, 23.60it/s]
Loading 0:  74%|███████▍  | 739/995 [00:31<00:08, 28.96it/s]
Loading 0:  80%|███████▉  | 794/995 [00:32<00:05, 35.91it/s]
Loading 0:  85%|████████▍ | 845/995 [00:42<00:04, 35.91it/s]
Loading 0:  85%|████████▌ | 846/995 [00:42<00:11, 12.57it/s]
Loading 0:  85%|████████▌ | 849/995 [00:43<00:12, 11.57it/s]
Loading 0:  90%|█████████ | 897/995 [00:44<00:05, 16.37it/s]
Loading 0:  96%|█████████▌| 952/995 [00:44<00:01, 23.13it/s]
Loading 0: 100%|██████████| 995/995 [00:46<00:00, 26.04it/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-v66-mkmlizer:   warnings.warn(
neversleep-noromaid-v0-8068-v66-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-v66-mkmlizer:   warnings.warn(
neversleep-noromaid-v0-8068-v66-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-v66-mkmlizer:   warnings.warn(
neversleep-noromaid-v0-8068-v66-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-v66-mkmlizer:   return self.fget.__get__(instance, owner)()
neversleep-noromaid-v0-8068-v66-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
neversleep-noromaid-v0-8068-v66-mkmlizer: Saving duration: 0.224s
neversleep-noromaid-v0-8068-v66-mkmlizer: Processed model rirv938/reward_gpt2_medium_preference_24m_e2 in 7.322s
neversleep-noromaid-v0-8068-v66-mkmlizer: creating bucket guanaco-reward-models
neversleep-noromaid-v0-8068-v66-mkmlizer: Bucket 's3://guanaco-reward-models/' created
neversleep-noromaid-v0-8068-v66-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/neversleep-noromaid-v0-8068-v66_reward
neversleep-noromaid-v0-8068-v66-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/neversleep-noromaid-v0-8068-v66_reward/config.json
neversleep-noromaid-v0-8068-v66-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/neversleep-noromaid-v0-8068-v66_reward/special_tokens_map.json
neversleep-noromaid-v0-8068-v66-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/neversleep-noromaid-v0-8068-v66_reward/merges.txt
neversleep-noromaid-v0-8068-v66-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/neversleep-noromaid-v0-8068-v66_reward/vocab.json
neversleep-noromaid-v0-8068-v66-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/neversleep-noromaid-v0-8068-v66_reward/tokenizer_config.json
neversleep-noromaid-v0-8068-v66-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/neversleep-noromaid-v0-8068-v66_reward/tokenizer.json
neversleep-noromaid-v0-8068-v66-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/neversleep-noromaid-v0-8068-v66_reward/reward.tensors
Job neversleep-noromaid-v0-8068-v66-mkmlizer completed after 217.12s with status: succeeded
Stopping job with name neversleep-noromaid-v0-8068-v66-mkmlizer
Pipeline stage MKMLizer completed in 220.50s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.09s
Running pipeline stage ISVCDeployer
Creating inference service neversleep-noromaid-v0-8068-v66
Waiting for inference service neversleep-noromaid-v0-8068-v66 to be ready
Inference service neversleep-noromaid-v0-8068-v66 ready after 100.65319347381592s
Pipeline stage ISVCDeployer completed in 107.68s
Running pipeline stage StressChecker
%s, retrying in %s seconds...
Received healthy response to inference request in 3.335904359817505s
Received healthy response to inference request in 2.3680362701416016s
Received healthy response to inference request in 2.4159348011016846s
Received healthy response to inference request in 2.3881595134735107s
Received healthy response to inference request in 2.2822718620300293s
5 requests
0 failed requests
5th percentile: 2.299424743652344
10th percentile: 2.3165776252746584
20th percentile: 2.350883388519287
30th percentile: 2.3720609188079833
40th percentile: 2.3801102161407472
50th percentile: 2.3881595134735107
60th percentile: 2.39926962852478
70th percentile: 2.41037974357605
80th percentile: 2.5999287128448487
90th percentile: 2.967916536331177
95th percentile: 3.1519104480743407
99th percentile: 3.2991055774688722
mean time: 2.558061361312866
Pipeline stage StressChecker completed in 18.69s
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_v66 status is now deployed due to DeploymentManager action
neversleep-noromaid-v0-_8068_v66 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of neversleep-noromaid-v0-_8068_v66
Running pipeline stage ISVCDeleter
Checking if service neversleep-noromaid-v0-8068-v66 is running
Skipping teardown as no inference service was found
Pipeline stage ISVCDeleter completed in 2.38s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key neversleep-noromaid-v0-8068-v66/config.json from bucket guanaco-mkml-models
Deleting key neversleep-noromaid-v0-8068-v66/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key neversleep-noromaid-v0-8068-v66/flywheel_model.1.safetensors from bucket guanaco-mkml-models
Deleting key neversleep-noromaid-v0-8068-v66/flywheel_model.2.safetensors from bucket guanaco-mkml-models
Deleting key neversleep-noromaid-v0-8068-v66/flywheel_model.3.safetensors from bucket guanaco-mkml-models
Deleting key neversleep-noromaid-v0-8068-v66/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key neversleep-noromaid-v0-8068-v66/tokenizer.json from bucket guanaco-mkml-models
Deleting key neversleep-noromaid-v0-8068-v66/tokenizer.model from bucket guanaco-mkml-models
Deleting key neversleep-noromaid-v0-8068-v66/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key neversleep-noromaid-v0-8068-v66_reward/config.json from bucket guanaco-reward-models
Deleting key neversleep-noromaid-v0-8068-v66_reward/merges.txt from bucket guanaco-reward-models
Deleting key neversleep-noromaid-v0-8068-v66_reward/reward.tensors from bucket guanaco-reward-models
Deleting key neversleep-noromaid-v0-8068-v66_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key neversleep-noromaid-v0-8068-v66_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key neversleep-noromaid-v0-8068-v66_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key neversleep-noromaid-v0-8068-v66_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 6.95s
neversleep-noromaid-v0-_8068_v66 status is now torndown due to DeploymentManager action