submission_id: neversleep-noromaid-v0-_8068_v80
developer_uid: robert_irvine
status: inactive
model_repo: NeverSleep/Noromaid-v0.1-mixtral-8x7b-Instruct-v3
reward_repo: rirv938/reward_gpt2_medium_preference_24m_e2
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}. 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': '{bot_name}:', 'truncate_by_message': False}
reward_formatter: {'memory_template': 'Memory: {memory}\n', 'prompt_template': '{prompt}\n', 'bot_template': 'Bot: {message}\n', 'user_template': 'User: {message}\n', 'response_template': 'Bot:', 'truncate_by_message': False}
timestamp: 2024-06-10T21:39:47+00:00
model_name: neversleep-noromaid-v0-_8068_v80
model_eval_status: pending
model_group: NeverSleep/Noromaid-v0.1
num_battles: 61476
num_wins: 32966
celo_rating: 1170.8
propriety_score: 0.6993592902907836
propriety_total_count: 20290.0
submission_type: basic
model_architecture: MixtralForCausalLM
model_num_parameters: 46702792704.0
best_of: 4
max_input_tokens: 512
max_output_tokens: 64
display_name: neversleep-noromaid-v0-_8068_v80
ineligible_reason: None
language_model: NeverSleep/Noromaid-v0.1-mixtral-8x7b-Instruct-v3
model_size: 47B
reward_model: rirv938/reward_gpt2_medium_preference_24m_e2
us_pacific_date: 2024-06-10
win_ratio: 0.5362417854121934
Resubmit model
Running pipeline stage MKMLizer
Starting job with name neversleep-noromaid-v0-8068-v80-mkmlizer
Waiting for job on neversleep-noromaid-v0-8068-v80-mkmlizer to finish
neversleep-noromaid-v0-8068-v80-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
neversleep-noromaid-v0-8068-v80-mkmlizer: ║ _____ __ __ ║
neversleep-noromaid-v0-8068-v80-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
neversleep-noromaid-v0-8068-v80-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
neversleep-noromaid-v0-8068-v80-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
neversleep-noromaid-v0-8068-v80-mkmlizer: ║ /___/ ║
neversleep-noromaid-v0-8068-v80-mkmlizer: ║ ║
neversleep-noromaid-v0-8068-v80-mkmlizer: ║ Version: 0.8.14 ║
neversleep-noromaid-v0-8068-v80-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
neversleep-noromaid-v0-8068-v80-mkmlizer: ║ https://mk1.ai ║
neversleep-noromaid-v0-8068-v80-mkmlizer: ║ ║
neversleep-noromaid-v0-8068-v80-mkmlizer: ║ The license key for the current software has been verified as ║
neversleep-noromaid-v0-8068-v80-mkmlizer: ║ belonging to: ║
neversleep-noromaid-v0-8068-v80-mkmlizer: ║ ║
neversleep-noromaid-v0-8068-v80-mkmlizer: ║ Chai Research Corp. ║
neversleep-noromaid-v0-8068-v80-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
neversleep-noromaid-v0-8068-v80-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
neversleep-noromaid-v0-8068-v80-mkmlizer: ║ ║
neversleep-noromaid-v0-8068-v80-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
neversleep-noromaid-v0-8068-v80-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-v80-mkmlizer: warnings.warn(warning_message, FutureWarning)
neversleep-noromaid-v0-8068-v80-mkmlizer: Downloaded to shared memory in 75.484s
neversleep-noromaid-v0-8068-v80-mkmlizer: quantizing model to /dev/shm/model_cache
neversleep-noromaid-v0-8068-v80-mkmlizer: Saving flywheel model at /dev/shm/model_cache
neversleep-noromaid-v0-8068-v80-mkmlizer: quantized model in 71.483s
neversleep-noromaid-v0-8068-v80-mkmlizer: Processed model NeverSleep/Noromaid-v0.1-mixtral-8x7b-Instruct-v3 in 153.165s
neversleep-noromaid-v0-8068-v80-mkmlizer: creating bucket guanaco-mkml-models
neversleep-noromaid-v0-8068-v80-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
neversleep-noromaid-v0-8068-v80-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v80
neversleep-noromaid-v0-8068-v80-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v80/special_tokens_map.json
neversleep-noromaid-v0-8068-v80-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v80/config.json
neversleep-noromaid-v0-8068-v80-mkmlizer: cp /dev/shm/model_cache/tokenizer.model s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v80/tokenizer.model
neversleep-noromaid-v0-8068-v80-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v80/tokenizer_config.json
neversleep-noromaid-v0-8068-v80-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v80/tokenizer.json
neversleep-noromaid-v0-8068-v80-mkmlizer: cp /dev/shm/model_cache/flywheel_model.3.safetensors s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v80/flywheel_model.3.safetensors
neversleep-noromaid-v0-8068-v80-mkmlizer: loading reward model from rirv938/reward_gpt2_medium_preference_24m_e2
neversleep-noromaid-v0-8068-v80-mkmlizer: Loading 0: 0%| | 0/995 [00:00<?, ?it/s] Loading 0: 5%|▌ | 52/995 [00:00<00:15, 60.53it/s] Loading 0: 11%|█ | 107/995 [00:01<00:13, 63.87it/s] Loading 0: 16%|█▋ | 162/995 [00:02<00:12, 65.34it/s] Loading 0: 21%|██ | 210/995 [00:03<00:12, 62.06it/s] Loading 0: 27%|██▋ | 265/995 [00:04<00:11, 63.08it/s] Loading 0: 28%|██▊ | 278/995 [00:19<01:41, 7.04it/s] Loading 0: 32%|███▏ | 320/995 [00:20<01:08, 9.79it/s] Loading 0: 37%|███▋ | 368/995 [00:20<00:45, 13.93it/s] Loading 0: 43%|████▎ | 423/995 [00:21<00:29, 19.69it/s] Loading 0: 48%|████▊ | 478/995 [00:22<00:19, 26.09it/s] Loading 0: 53%|█████▎ | 526/995 [00:23<00:14, 31.35it/s] Loading 0: 57%|█████▋ | 564/995 [00:37<00:13, 31.35it/s] Loading 0: 57%|█████▋ | 565/995 [00:37<00:49, 8.64it/s] Loading 0: 58%|█████▊ | 581/995 [00:38<00:45, 9.15it/s] Loading 0: 64%|██████▍ | 636/995 [00:39<00:25, 13.84it/s] Loading 0: 69%|██████▉ | 691/995 [00:39<00:15, 19.38it/s] Loading 0: 74%|███████▍ | 739/995 [00:41<00:11, 23.08it/s] Loading 0: 80%|███████▉ | 794/995 [00:42<00:07, 27.83it/s] Loading 0: 85%|████████▌ | 846/995 [00:56<00:16, 8.96it/s] Loading 0: 85%|████████▌ | 849/995 [00:58<00:17, 8.22it/s] Loading 0: 90%|█████████ | 897/995 [00:59<00:08, 11.51it/s] Loading 0: 96%|█████████▌| 952/995 [01:00<00:02, 16.14it/s] Loading 0: 100%|██████████| 995/995 [01:02<00:00, 18.92it/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-v80-mkmlizer: warnings.warn(
neversleep-noromaid-v0-8068-v80-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-v80-mkmlizer: warnings.warn(
neversleep-noromaid-v0-8068-v80-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-v80-mkmlizer: warnings.warn(
neversleep-noromaid-v0-8068-v80-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-v80-mkmlizer: return self.fget.__get__(instance, owner)()
neversleep-noromaid-v0-8068-v80-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
neversleep-noromaid-v0-8068-v80-mkmlizer: Saving duration: 0.227s
neversleep-noromaid-v0-8068-v80-mkmlizer: Processed model rirv938/reward_gpt2_medium_preference_24m_e2 in 4.269s
neversleep-noromaid-v0-8068-v80-mkmlizer: creating bucket guanaco-reward-models
neversleep-noromaid-v0-8068-v80-mkmlizer: Bucket 's3://guanaco-reward-models/' created
neversleep-noromaid-v0-8068-v80-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/neversleep-noromaid-v0-8068-v80_reward
neversleep-noromaid-v0-8068-v80-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/neversleep-noromaid-v0-8068-v80_reward/config.json
neversleep-noromaid-v0-8068-v80-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/neversleep-noromaid-v0-8068-v80_reward/tokenizer_config.json
neversleep-noromaid-v0-8068-v80-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/neversleep-noromaid-v0-8068-v80_reward/special_tokens_map.json
neversleep-noromaid-v0-8068-v80-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/neversleep-noromaid-v0-8068-v80_reward/merges.txt
neversleep-noromaid-v0-8068-v80-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/neversleep-noromaid-v0-8068-v80_reward/vocab.json
neversleep-noromaid-v0-8068-v80-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/neversleep-noromaid-v0-8068-v80_reward/tokenizer.json
neversleep-noromaid-v0-8068-v80-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/neversleep-noromaid-v0-8068-v80_reward/reward.tensors
Job neversleep-noromaid-v0-8068-v80-mkmlizer completed after 195.05s with status: succeeded
Stopping job with name neversleep-noromaid-v0-8068-v80-mkmlizer
Pipeline stage MKMLizer completed in 197.19s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.36s
Running pipeline stage ISVCDeployer
Creating inference service neversleep-noromaid-v0-8068-v80
Waiting for inference service neversleep-noromaid-v0-8068-v80 to be ready
Inference service neversleep-noromaid-v0-8068-v80 ready after 61.2567777633667s
Pipeline stage ISVCDeployer completed in 67.88s
Running pipeline stage StressChecker
Received healthy response to inference request in 4.568156957626343s
Received healthy response to inference request in 2.2407233715057373s
Received healthy response to inference request in 14.14960503578186s
Received healthy response to inference request in 1.8622069358825684s
Received healthy response to inference request in 2.145702600479126s
5 requests
0 failed requests
5th percentile: 1.91890606880188
10th percentile: 1.9756052017211914
20th percentile: 2.0890034675598144
30th percentile: 2.164706754684448
40th percentile: 2.2027150630950927
50th percentile: 2.2407233715057373
60th percentile: 3.1716968059539794
70th percentile: 4.1026702404022215
80th percentile: 6.484446573257448
90th percentile: 10.317025804519654
95th percentile: 12.233315420150756
99th percentile: 13.76634711265564
mean time: 4.993278980255127
Pipeline stage StressChecker completed in 28.08s
Running pipeline stage DaemonicModelEvalScorer
Pipeline stage DaemonicModelEvalScorer completed in 0.13s
Running pipeline stage DaemonicSafetyScorer
Pipeline stage DaemonicSafetyScorer completed in 0.14s
%s, retrying in %s seconds...
neversleep-noromaid-v0-_8068_v80 status is now deployed due to DeploymentManager action
Running M-Eval for topic stay_in_character
%s, retrying in %s seconds...
M-Eval Dataset for topic stay_in_character is loaded
neversleep-noromaid-v0-_8068_v80 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics