neversleep-noromaid-v0-_8068

developer_uid: robert_irvine

submission_id: neversleep-noromaid-v0-_8068_v48

model_name: neversleep-noromaid-v0-_8068_v48

model_group: NeverSleep/Noromaid-v0.1

status: torndown

timestamp: 2024-05-16T16:36:34+00:00

num_battles: 27997

num_wins: 13846

celo_rating: 1153.74

family_friendly_score: 0.0

submission_type: basic

model_repo: NeverSleep/Noromaid-v0.1-mixtral-8x7b-Instruct-v3

model_architecture: MixtralForCausalLM

reward_repo: rirv938/gpt2_balanced_data_rm_400k

model_num_parameters: 46702792704.0

best_of: 4

max_input_tokens: 512

max_output_tokens: 64

display_name: neversleep-noromaid-v0-_8068_v48

is_internal_developer: True

language_model: NeverSleep/Noromaid-v0.1-mixtral-8x7b-Instruct-v3

model_size: 47B

ranking_group: single

us_pacific_date: 2024-05-16

win_ratio: 0.4945529878201236

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}. 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', '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: pending

Resubmit model

Running pipeline stage MKMLizer
Starting job with name neversleep-noromaid-v0-8068-v48-mkmlizer
Waiting for job on neversleep-noromaid-v0-8068-v48-mkmlizer to finish
neversleep-noromaid-v0-8068-v48-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
neversleep-noromaid-v0-8068-v48-mkmlizer: ║     _____            __           __                                ║
neversleep-noromaid-v0-8068-v48-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
neversleep-noromaid-v0-8068-v48-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
neversleep-noromaid-v0-8068-v48-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
neversleep-noromaid-v0-8068-v48-mkmlizer: ║       /___/                                                         ║
neversleep-noromaid-v0-8068-v48-mkmlizer: ║                                                                     ║
neversleep-noromaid-v0-8068-v48-mkmlizer: ║  Version: 0.8.14                                                    ║
neversleep-noromaid-v0-8068-v48-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
neversleep-noromaid-v0-8068-v48-mkmlizer: ║  https://mk1.ai                                                     ║
neversleep-noromaid-v0-8068-v48-mkmlizer: ║                                                                     ║
neversleep-noromaid-v0-8068-v48-mkmlizer: ║  The license key for the current software has been verified as      ║
neversleep-noromaid-v0-8068-v48-mkmlizer: ║  belonging to:                                                      ║
neversleep-noromaid-v0-8068-v48-mkmlizer: ║                                                                     ║
neversleep-noromaid-v0-8068-v48-mkmlizer: ║  Chai Research Corp.                                                ║
neversleep-noromaid-v0-8068-v48-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
neversleep-noromaid-v0-8068-v48-mkmlizer: ║  Expiration: 2024-07-15 23:59:59                                    ║
neversleep-noromaid-v0-8068-v48-mkmlizer: ║                                                                     ║
neversleep-noromaid-v0-8068-v48-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
neversleep-noromaid-v0-8068-v48-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-v48-mkmlizer:   warnings.warn(warning_message, FutureWarning)
neversleep-noromaid-v0-8068-v48-mkmlizer: Downloaded to shared memory in 96.126s
neversleep-noromaid-v0-8068-v48-mkmlizer: quantizing model to /dev/shm/model_cache
neversleep-noromaid-v0-8068-v48-mkmlizer: Saving flywheel model at /dev/shm/model_cache
neversleep-noromaid-v0-8068-v48-mkmlizer: quantized model in 60.396s
neversleep-noromaid-v0-8068-v48-mkmlizer: creating bucket guanaco-mkml-models
neversleep-noromaid-v0-8068-v48-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
neversleep-noromaid-v0-8068-v48-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v48
neversleep-noromaid-v0-8068-v48-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v48/config.json
neversleep-noromaid-v0-8068-v48-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v48/tokenizer_config.json
neversleep-noromaid-v0-8068-v48-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v48/special_tokens_map.json
neversleep-noromaid-v0-8068-v48-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v48/tokenizer.json
neversleep-noromaid-v0-8068-v48-mkmlizer: cp /dev/shm/model_cache/tokenizer.model s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v48/tokenizer.model
neversleep-noromaid-v0-8068-v48-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v48/flywheel_model.0.safetensors
neversleep-noromaid-v0-8068-v48-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v48/flywheel_model.1.safetensors
neversleep-noromaid-v0-8068-v48-mkmlizer: cp /dev/shm/model_cache/flywheel_model.2.safetensors s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v48/flywheel_model.2.safetensors
neversleep-noromaid-v0-8068-v48-mkmlizer: loading reward model from rirv938/gpt2_balanced_data_rm_400k
neversleep-noromaid-v0-8068-v48-mkmlizer: 
Loading 0:   0%|          | 0/995 [00:00<?, ?it/s]
Loading 0:   5%|▌         | 52/995 [00:01<00:22, 42.74it/s]
Loading 0:  11%|█         | 107/995 [00:02<00:19, 45.49it/s]
Loading 0:  16%|█▋        | 162/995 [00:03<00:17, 47.23it/s]
Loading 0:  21%|██        | 210/995 [00:04<00:17, 45.88it/s]
Loading 0:  27%|██▋       | 265/995 [00:05<00:15, 47.30it/s]
Loading 0:  28%|██▊       | 277/995 [00:15<00:15, 47.30it/s]
Loading 0:  28%|██▊       | 278/995 [00:15<01:16,  9.39it/s]
Loading 0:  32%|███▏      | 320/995 [00:17<00:55, 12.22it/s]
Loading 0:  37%|███▋      | 368/995 [00:18<00:38, 16.41it/s]
Loading 0:  43%|████▎     | 423/995 [00:19<00:26, 21.64it/s]
Loading 0:  48%|████▊     | 478/995 [00:20<00:19, 26.57it/s]
Loading 0:  53%|█████▎    | 526/995 [00:21<00:15, 29.94it/s]
Loading 0:  57%|█████▋    | 564/995 [00:32<00:14, 29.94it/s]
Loading 0:  57%|█████▋    | 565/995 [00:32<00:39, 10.81it/s]
Loading 0:  58%|█████▊    | 581/995 [00:33<00:37, 10.90it/s]
Loading 0:  64%|██████▍   | 636/995 [00:34<00:23, 15.60it/s]
Loading 0:  69%|██████▉   | 691/995 [00:35<00:14, 20.62it/s]
Loading 0:  74%|███████▍  | 739/995 [00:36<00:10, 24.73it/s]
Loading 0:  80%|███████▉  | 794/995 [00:37<00:06, 29.82it/s]
Loading 0:  85%|████████▍ | 845/995 [00:47<00:05, 29.82it/s]
Loading 0:  85%|████████▌ | 846/995 [00:47<00:12, 12.01it/s]
Loading 0:  85%|████████▌ | 849/995 [00:49<00:13, 10.77it/s]
Loading 0:  90%|█████████ | 897/995 [00:50<00:06, 14.87it/s]
Loading 0:  96%|█████████▌| 952/995 [00:51<00:02, 20.58it/s]
Loading 0: 100%|██████████| 995/995 [00:52<00:00, 23.41it/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-v48-mkmlizer:   warnings.warn(
neversleep-noromaid-v0-8068-v48-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-v48-mkmlizer:   warnings.warn(
neversleep-noromaid-v0-8068-v48-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-v48-mkmlizer:   warnings.warn(
neversleep-noromaid-v0-8068-v48-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
neversleep-noromaid-v0-8068-v48-mkmlizer: Saving duration: 0.117s
neversleep-noromaid-v0-8068-v48-mkmlizer: Processed model rirv938/gpt2_balanced_data_rm_400k in 3.888s
neversleep-noromaid-v0-8068-v48-mkmlizer: creating bucket guanaco-reward-models
neversleep-noromaid-v0-8068-v48-mkmlizer: Bucket 's3://guanaco-reward-models/' created
neversleep-noromaid-v0-8068-v48-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/neversleep-noromaid-v0-8068-v48_reward
neversleep-noromaid-v0-8068-v48-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/neversleep-noromaid-v0-8068-v48_reward/config.json
neversleep-noromaid-v0-8068-v48-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/neversleep-noromaid-v0-8068-v48_reward/special_tokens_map.json
neversleep-noromaid-v0-8068-v48-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/neversleep-noromaid-v0-8068-v48_reward/tokenizer_config.json
neversleep-noromaid-v0-8068-v48-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/neversleep-noromaid-v0-8068-v48_reward/merges.txt
neversleep-noromaid-v0-8068-v48-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/neversleep-noromaid-v0-8068-v48_reward/vocab.json
neversleep-noromaid-v0-8068-v48-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/neversleep-noromaid-v0-8068-v48_reward/tokenizer.json
neversleep-noromaid-v0-8068-v48-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/neversleep-noromaid-v0-8068-v48_reward/reward.tensors
Job neversleep-noromaid-v0-8068-v48-mkmlizer completed after 246.93s with status: succeeded
Stopping job with name neversleep-noromaid-v0-8068-v48-mkmlizer
Pipeline stage MKMLizer completed in 248.74s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.32s
Running pipeline stage ISVCDeployer
Creating inference service neversleep-noromaid-v0-8068-v48
Waiting for inference service neversleep-noromaid-v0-8068-v48 to be ready
Inference service neversleep-noromaid-v0-8068-v48 ready after 91.09248805046082s
Pipeline stage ISVCDeployer completed in 97.59s
Running pipeline stage StressChecker
Received healthy response to inference request in 3.0305113792419434s
Received healthy response to inference request in 2.170339345932007s
Received healthy response to inference request in 2.099461555480957s
Received healthy response to inference request in 2.3409817218780518s
Received healthy response to inference request in 2.145742893218994s
5 requests
0 failed requests
5th percentile: 2.1087178230285644
10th percentile: 2.1179740905761717
20th percentile: 2.136486625671387
30th percentile: 2.1506621837615967
40th percentile: 2.1605007648468018
50th percentile: 2.170339345932007
60th percentile: 2.238596296310425
70th percentile: 2.306853246688843
80th percentile: 2.47888765335083
90th percentile: 2.7546995162963865
95th percentile: 2.892605447769165
99th percentile: 3.0029301929473875
mean time: 2.3574073791503904
Pipeline stage StressChecker completed in 14.20s
Running pipeline stage DaemonicModelEvalScorer
Pipeline stage DaemonicModelEvalScorer completed in 0.14s
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 0.28s
%s, retrying in %s seconds...
neversleep-noromaid-v0-_8068_v48 status is now deployed due to DeploymentManager action
%s, retrying in %s seconds...
neversleep-noromaid-v0-_8068_v48 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of neversleep-noromaid-v0-_8068_v48
Running pipeline stage ISVCDeleter
Checking if service neversleep-noromaid-v0-8068-v48 is running
Tearing down inference service neversleep-noromaid-v0-8068-v48
Toredown service neversleep-noromaid-v0-8068-v48
Pipeline stage ISVCDeleter completed in 6.10s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key neversleep-noromaid-v0-8068-v48/config.json from bucket guanaco-mkml-models
admin requested tearing down of nitral-ai-pp-0-71a_v1
Deleting key neversleep-noromaid-v0-8068-v48/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Running pipeline stage ISVCDeleter
Checking if service nitral-ai-pp-0-71a-v1 is running
Deleting key neversleep-noromaid-v0-8068-v48/flywheel_model.1.safetensors from bucket guanaco-mkml-models
Deleting key neversleep-noromaid-v0-8068-v48/flywheel_model.2.safetensors from bucket guanaco-mkml-models
Deleting key neversleep-noromaid-v0-8068-v48/flywheel_model.3.safetensors from bucket guanaco-mkml-models
Tearing down inference service nitral-ai-pp-0-71a-v1
Toredown service nitral-ai-pp-0-71a-v1
Deleting key neversleep-noromaid-v0-8068-v48/special_tokens_map.json from bucket guanaco-mkml-models
Pipeline stage ISVCDeleter completed in 5.03s
Deleting key neversleep-noromaid-v0-8068-v48/tokenizer.json from bucket guanaco-mkml-models
Running pipeline stage MKMLModelDeleter
Deleting key neversleep-noromaid-v0-8068-v48/tokenizer.model from bucket guanaco-mkml-models
Cleaning model data from S3
Deleting key neversleep-noromaid-v0-8068-v48/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Cleaning model data from model cache
Deleting key nitral-ai-pp-0-71a-v1/config.json from bucket guanaco-mkml-models
Deleting key neversleep-noromaid-v0-8068-v48_reward/config.json from bucket guanaco-reward-models
Deleting key nitral-ai-pp-0-71a-v1/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key neversleep-noromaid-v0-8068-v48_reward/merges.txt from bucket guanaco-reward-models
Deleting key neversleep-noromaid-v0-8068-v48_reward/reward.tensors from bucket guanaco-reward-models
Deleting key neversleep-noromaid-v0-8068-v48_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key neversleep-noromaid-v0-8068-v48_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key nitral-ai-pp-0-71a-v1/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key neversleep-noromaid-v0-8068-v48_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key nitral-ai-pp-0-71a-v1/tokenizer.json from bucket guanaco-mkml-models
Deleting key neversleep-noromaid-v0-8068-v48_reward/vocab.json from bucket guanaco-reward-models
Deleting key nitral-ai-pp-0-71a-v1/tokenizer_config.json from bucket guanaco-mkml-models
Pipeline stage MKMLModelDeleter completed in 7.12s
Cleaning model data from model cache
neversleep-noromaid-v0-_8068_v48 status is now torndown due to DeploymentManager action