submission_id: neversleep-noromaid-v0-_8068_v36
developer_uid: alexdaoud
status: deployed
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': ['\n', '</s>', '<|user|>', '###'], '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: {'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: 2024-04-30T15:50:45+00:00
model_name: neversleep-noromaid-v0-_8068_v36
model_eval_status: success
double_thumbs_up: 157089
thumbs_up: 225655
thumbs_down: 91307
num_battles: 13151294
num_wins: 6654427
celo_rating: 1173.03
entertaining: 7.08
stay_in_character: 8.44
user_preference: 7.7
safety_score: 0.96
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_v36
double_thumbs_up_ratio: 0.33137573805350057
feedback_count: 474051
ineligible_reason: None
language_model: NeverSleep/Noromaid-v0.1-mixtral-8x7b-Instruct-v3
model_score: 7.739999999999999
model_size: 47B
reward_model: rirv938/reward_gpt2_medium_preference_24m_e2
single_thumbs_up_ratio: 0.4760141841278681
thumbs_down_ratio: 0.19261007781863132
thumbs_up_ratio: 0.8073899221813686
us_pacific_date: 2024-04-30
win_ratio: 0.5059902850624433
Resubmit model
Running pipeline stage MKMLizer
Starting job with name neversleep-noromaid-v0-8068-v36-mkmlizer
Waiting for job on neversleep-noromaid-v0-8068-v36-mkmlizer to finish
Stopping job with name neversleep-noromaid-v0-8068-v36-mkmlizer
%s, retrying in %s seconds...
Starting job with name neversleep-noromaid-v0-8068-v36-mkmlizer
Waiting for job on neversleep-noromaid-v0-8068-v36-mkmlizer to finish
neversleep-noromaid-v0-8068-v36-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
neversleep-noromaid-v0-8068-v36-mkmlizer: ║ _____ __ __ ║
neversleep-noromaid-v0-8068-v36-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
neversleep-noromaid-v0-8068-v36-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
neversleep-noromaid-v0-8068-v36-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
neversleep-noromaid-v0-8068-v36-mkmlizer: ║ /___/ ║
neversleep-noromaid-v0-8068-v36-mkmlizer: ║ ║
neversleep-noromaid-v0-8068-v36-mkmlizer: ║ Version: 0.8.10 ║
neversleep-noromaid-v0-8068-v36-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
neversleep-noromaid-v0-8068-v36-mkmlizer: ║ ║
neversleep-noromaid-v0-8068-v36-mkmlizer: ║ The license key for the current software has been verified as ║
neversleep-noromaid-v0-8068-v36-mkmlizer: ║ belonging to: ║
neversleep-noromaid-v0-8068-v36-mkmlizer: ║ ║
neversleep-noromaid-v0-8068-v36-mkmlizer: ║ Chai Research Corp. ║
neversleep-noromaid-v0-8068-v36-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
neversleep-noromaid-v0-8068-v36-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
neversleep-noromaid-v0-8068-v36-mkmlizer: ║ ║
neversleep-noromaid-v0-8068-v36-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
neversleep-noromaid-v0-8068-v36-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-v36-mkmlizer: warnings.warn(warning_message, FutureWarning)
neversleep-noromaid-v0-8068-v36-mkmlizer: Downloaded to shared memory in 175.823s
neversleep-noromaid-v0-8068-v36-mkmlizer: quantizing model to /dev/shm/model_cache
neversleep-noromaid-v0-8068-v36-mkmlizer: Saving flywheel model at /dev/shm/model_cache
neversleep-noromaid-v0-8068-v36-mkmlizer: quantized model in 52.538s
neversleep-noromaid-v0-8068-v36-mkmlizer: Processed model NeverSleep/Noromaid-v0.1-mixtral-8x7b-Instruct-v3 in 233.840s
neversleep-noromaid-v0-8068-v36-mkmlizer: creating bucket guanaco-mkml-models
neversleep-noromaid-v0-8068-v36-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
neversleep-noromaid-v0-8068-v36-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v36
neversleep-noromaid-v0-8068-v36-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v36/config.json
neversleep-noromaid-v0-8068-v36-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v36/special_tokens_map.json
neversleep-noromaid-v0-8068-v36-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v36/tokenizer_config.json
neversleep-noromaid-v0-8068-v36-mkmlizer: cp /dev/shm/model_cache/tokenizer.model s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v36/tokenizer.model
neversleep-noromaid-v0-8068-v36-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v36/tokenizer.json
neversleep-noromaid-v0-8068-v36-mkmlizer: cp /dev/shm/model_cache/flywheel_model.3.safetensors s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v36/flywheel_model.3.safetensors
neversleep-noromaid-v0-8068-v36-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v36/flywheel_model.0.safetensors
neversleep-noromaid-v0-8068-v36-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v36/flywheel_model.1.safetensors
neversleep-noromaid-v0-8068-v36-mkmlizer: cp /dev/shm/model_cache/flywheel_model.2.safetensors s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v36/flywheel_model.2.safetensors
neversleep-noromaid-v0-8068-v36-mkmlizer: loading reward model from rirv938/reward_gpt2_medium_preference_24m_e2
neversleep-noromaid-v0-8068-v36-mkmlizer: Loading 0: 0%| | 0/995 [00:00<?, ?it/s] Loading 0: 11%|█ | 107/995 [00:01<00:14, 61.92it/s] Loading 0: 21%|██ | 210/995 [00:03<00:12, 61.65it/s] Loading 0: 28%|██▊ | 278/995 [00:13<00:45, 15.63it/s] Loading 0: 32%|███▏ | 320/995 [00:14<00:36, 18.26it/s] Loading 0: 43%|████▎ | 423/995 [00:16<00:21, 26.85it/s] Loading 0: 53%|█████▎ | 526/995 [00:18<00:13, 34.44it/s] Loading 0: 57%|█████▋ | 565/995 [00:27<00:29, 14.74it/s] Loading 0: 58%|█████▊ | 581/995 [00:28<00:28, 14.76it/s] Loading 0: 69%|██████▉ | 691/995 [00:30<00:12, 23.60it/s] Loading 0: 80%|███████▉ | 794/995 [00:32<00:06, 31.38it/s] Loading 0: 85%|████████▌ | 846/995 [00:41<00:09, 15.61it/s] Loading 0: 96%|█████████▌| 952/995 [00:43<00:02, 20.63it/s] Loading 0: 100%|██████████| 995/995 [00:45<00:00, 22.36it/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-v36-mkmlizer: warnings.warn(
neversleep-noromaid-v0-8068-v36-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-v36-mkmlizer: warnings.warn(
neversleep-noromaid-v0-8068-v36-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-v36-mkmlizer: warnings.warn(
neversleep-noromaid-v0-8068-v36-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
neversleep-noromaid-v0-8068-v36-mkmlizer: Saving duration: 0.224s
neversleep-noromaid-v0-8068-v36-mkmlizer: Processed model rirv938/reward_gpt2_medium_preference_24m_e2 in 7.880s
neversleep-noromaid-v0-8068-v36-mkmlizer: creating bucket guanaco-reward-models
neversleep-noromaid-v0-8068-v36-mkmlizer: Bucket 's3://guanaco-reward-models/' created
neversleep-noromaid-v0-8068-v36-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/neversleep-noromaid-v0-8068-v36_reward
neversleep-noromaid-v0-8068-v36-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/neversleep-noromaid-v0-8068-v36_reward/config.json
neversleep-noromaid-v0-8068-v36-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/neversleep-noromaid-v0-8068-v36_reward/tokenizer_config.json
neversleep-noromaid-v0-8068-v36-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/neversleep-noromaid-v0-8068-v36_reward/special_tokens_map.json
neversleep-noromaid-v0-8068-v36-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/neversleep-noromaid-v0-8068-v36_reward/merges.txt
neversleep-noromaid-v0-8068-v36-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/neversleep-noromaid-v0-8068-v36_reward/vocab.json
neversleep-noromaid-v0-8068-v36-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/neversleep-noromaid-v0-8068-v36_reward/tokenizer.json
neversleep-noromaid-v0-8068-v36-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/neversleep-noromaid-v0-8068-v36_reward/reward.tensors
Job neversleep-noromaid-v0-8068-v36-mkmlizer completed after 279.12s with status: succeeded
Stopping job with name neversleep-noromaid-v0-8068-v36-mkmlizer
Pipeline stage MKMLizer completed in 283.19s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.10s
Running pipeline stage ISVCDeployer
Creating inference service neversleep-noromaid-v0-8068-v36
Waiting for inference service neversleep-noromaid-v0-8068-v36 to be ready
Inference service neversleep-noromaid-v0-8068-v36 ready after 60.326364040374756s
Pipeline stage ISVCDeployer completed in 67.23s
Running pipeline stage StressChecker
Received healthy response to inference request in 3.3304882049560547s
Received healthy response to inference request in 2.1264116764068604s
Received healthy response to inference request in 1.7952864170074463s
Received healthy response to inference request in 2.1391985416412354s
Received healthy response to inference request in 1.7196240425109863s
5 requests
0 failed requests
5th percentile: 1.7347565174102784
10th percentile: 1.7498889923095704
20th percentile: 1.7801539421081543
30th percentile: 1.861511468887329
40th percentile: 1.9939615726470947
50th percentile: 2.1264116764068604
60th percentile: 2.1315264225006105
70th percentile: 2.1366411685943603
80th percentile: 2.3774564743041995
90th percentile: 2.8539723396301273
95th percentile: 3.0922302722930906
99th percentile: 3.282836618423462
mean time: 2.222201776504517
Pipeline stage StressChecker completed in 11.79s
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 0.04s
M-Eval Dataset for topic stay_in_character is loaded
neversleep-noromaid-v0-_8068_v36 status is now deployed due to DeploymentManager action

Usage Metrics

Latency Metrics