submission_id: neversleep-noromaid-v0-_8068_v51
developer_uid: zonemercy
best_of: 4
celo_rating: 1170.93
display_name: neversleep-noromaid-v0-_8068_v51
family_friendly_score: 0.0
formatter: {'memory_template': "{bot_name}'s Persona: {memory}\n####\n", 'prompt_template': '{prompt}\n<START>\n', 'bot_template': '{bot_name}: {message}\n', 'user_template': '{user_name}: {message}\n', 'response_template': '{bot_name}:', 'truncate_by_message': False}
generation_params: {'temperature': 0.8, 'top_p': 0.9, 'min_p': 0.0, 'top_k': 70, 'presence_penalty': 0.9, 'frequency_penalty': 0.9, 'stopping_words': ['\n'], 'max_input_tokens': 512, 'best_of': 4, 'max_output_tokens': 64}
ineligible_reason: model is not deployable
is_internal_developer: True
language_model: NeverSleep/Noromaid-v0.1-mixtral-8x7b-Instruct-v3
max_input_tokens: 512
max_output_tokens: 64
model_architecture: MixtralForCausalLM
model_eval_status: error
model_group: NeverSleep/Noromaid-v0.1
model_name: neversleep-noromaid-v0-_8068_v51
model_num_parameters: 46702792704.0
model_repo: NeverSleep/Noromaid-v0.1-mixtral-8x7b-Instruct-v3
model_size: 47B
num_battles: 2622
num_wins: 1299
ranking_group: single
reward_formatter: {'bot_template': '{bot_name}: {message}\n', 'memory_template': "{bot_name}'s Persona: {memory}\n####\n", 'prompt_template': '{prompt}\n<START>\n', 'response_template': '{bot_name}:', 'truncate_by_message': False, 'user_template': '{user_name}: {message}\n'}
reward_repo: rirv938/reward_gpt2_medium_preference_24m_e2
status: rejected
submission_type: basic
timestamp: 2024-05-21T23:39:59+00:00
us_pacific_date: 2024-05-21
win_ratio: 0.4954233409610984
Resubmit model
Running pipeline stage MKMLizer
Starting job with name neversleep-noromaid-v0-8068-v51-mkmlizer
Waiting for job on neversleep-noromaid-v0-8068-v51-mkmlizer to finish
neversleep-noromaid-v0-8068-v51-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
neversleep-noromaid-v0-8068-v51-mkmlizer: ║ _____ __ __ ║
neversleep-noromaid-v0-8068-v51-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
neversleep-noromaid-v0-8068-v51-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
neversleep-noromaid-v0-8068-v51-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
neversleep-noromaid-v0-8068-v51-mkmlizer: ║ /___/ ║
neversleep-noromaid-v0-8068-v51-mkmlizer: ║ ║
neversleep-noromaid-v0-8068-v51-mkmlizer: ║ Version: 0.8.14 ║
neversleep-noromaid-v0-8068-v51-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
neversleep-noromaid-v0-8068-v51-mkmlizer: ║ https://mk1.ai ║
neversleep-noromaid-v0-8068-v51-mkmlizer: ║ ║
neversleep-noromaid-v0-8068-v51-mkmlizer: ║ The license key for the current software has been verified as ║
neversleep-noromaid-v0-8068-v51-mkmlizer: ║ belonging to: ║
neversleep-noromaid-v0-8068-v51-mkmlizer: ║ ║
neversleep-noromaid-v0-8068-v51-mkmlizer: ║ Chai Research Corp. ║
neversleep-noromaid-v0-8068-v51-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
neversleep-noromaid-v0-8068-v51-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
neversleep-noromaid-v0-8068-v51-mkmlizer: ║ ║
neversleep-noromaid-v0-8068-v51-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
neversleep-noromaid-v0-8068-v51-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-v51-mkmlizer: warnings.warn(warning_message, FutureWarning)
neversleep-noromaid-v0-8068-v51-mkmlizer: quantized model in 51.892s
neversleep-noromaid-v0-8068-v51-mkmlizer: Processed model NeverSleep/Noromaid-v0.1-mixtral-8x7b-Instruct-v3 in 234.912s
neversleep-noromaid-v0-8068-v51-mkmlizer: creating bucket guanaco-mkml-models
neversleep-noromaid-v0-8068-v51-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
neversleep-noromaid-v0-8068-v51-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v51
neversleep-noromaid-v0-8068-v51-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v51/tokenizer_config.json
neversleep-noromaid-v0-8068-v51-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v51/special_tokens_map.json
neversleep-noromaid-v0-8068-v51-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v51/config.json
neversleep-noromaid-v0-8068-v51-mkmlizer: cp /dev/shm/model_cache/tokenizer.model s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v51/tokenizer.model
neversleep-noromaid-v0-8068-v51-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v51/tokenizer.json
neversleep-noromaid-v0-8068-v51-mkmlizer: cp /dev/shm/model_cache/flywheel_model.3.safetensors s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v51/flywheel_model.3.safetensors
neversleep-noromaid-v0-8068-v51-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v51/flywheel_model.0.safetensors
neversleep-noromaid-v0-8068-v51-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v51/flywheel_model.1.safetensors
neversleep-noromaid-v0-8068-v51-mkmlizer: cp /dev/shm/model_cache/flywheel_model.2.safetensors s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v51/flywheel_model.2.safetensors
neversleep-noromaid-v0-8068-v51-mkmlizer: loading reward model from rirv938/reward_gpt2_medium_preference_24m_e2
neversleep-noromaid-v0-8068-v51-mkmlizer: Loading 0: 0%| | 0/995 [00:00<?, ?it/s] Loading 0: 5%|▌ | 52/995 [00:00<00:16, 57.30it/s] Loading 0: 11%|█ | 107/995 [00:01<00:14, 60.81it/s] Loading 0: 16%|█▋ | 162/995 [00:02<00:13, 62.64it/s] Loading 0: 21%|██ | 210/995 [00:03<00:13, 59.39it/s] Loading 0: 27%|██▋ | 265/995 [00:04<00:12, 58.19it/s] Loading 0: 28%|██▊ | 278/995 [00:13<01:06, 10.76it/s] Loading 0: 32%|███▏ | 320/995 [00:14<00:47, 14.26it/s] Loading 0: 37%|███▋ | 368/995 [00:15<00:32, 19.40it/s] Loading 0: 43%|████▎ | 423/995 [00:16<00:21, 26.23it/s] Loading 0: 48%|████▊ | 478/995 [00:17<00:15, 33.36it/s] Loading 0: 53%|█████▎ | 526/995 [00:18<00:12, 36.19it/s] Loading 0: 57%|█████▋ | 565/995 [00:27<00:34, 12.33it/s] Loading 0: 58%|█████▊ | 581/995 [00:28<00:32, 12.55it/s] Loading 0: 64%|██████▍ | 636/995 [00:29<00:19, 18.29it/s] Loading 0: 69%|██████▉ | 691/995 [00:30<00:12, 24.31it/s] Loading 0: 74%|███████▍ | 739/995 [00:31<00:08, 28.91it/s] Loading 0: 80%|███████▉ | 794/995 [00:32<00:05, 35.72it/s] Loading 0: 85%|████████▌ | 846/995 [00:41<00:11, 13.54it/s] Loading 0: 85%|████████▌ | 850/995 [00:42<00:11, 12.42it/s] Loading 0: 90%|█████████ | 897/995 [00:43<00:05, 17.12it/s] Loading 0: 96%|█████████▌| 952/995 [00:43<00:01, 24.12it/s] Loading 0: 100%|██████████| 995/995 [00:44<00:00, 27.27it/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-v51-mkmlizer: warnings.warn(
neversleep-noromaid-v0-8068-v51-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-v51-mkmlizer: warnings.warn(
neversleep-noromaid-v0-8068-v51-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-v51-mkmlizer: warnings.warn(
neversleep-noromaid-v0-8068-v51-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-v51-mkmlizer: return self.fget.__get__(instance, owner)()
neversleep-noromaid-v0-8068-v51-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
neversleep-noromaid-v0-8068-v51-mkmlizer: Saving duration: 0.238s
neversleep-noromaid-v0-8068-v51-mkmlizer: Processed model rirv938/reward_gpt2_medium_preference_24m_e2 in 6.164s
neversleep-noromaid-v0-8068-v51-mkmlizer: creating bucket guanaco-reward-models
neversleep-noromaid-v0-8068-v51-mkmlizer: Bucket 's3://guanaco-reward-models/' created
neversleep-noromaid-v0-8068-v51-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/neversleep-noromaid-v0-8068-v51_reward
neversleep-noromaid-v0-8068-v51-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/neversleep-noromaid-v0-8068-v51_reward/config.json
neversleep-noromaid-v0-8068-v51-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/neversleep-noromaid-v0-8068-v51_reward/special_tokens_map.json
neversleep-noromaid-v0-8068-v51-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/neversleep-noromaid-v0-8068-v51_reward/tokenizer_config.json
neversleep-noromaid-v0-8068-v51-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/neversleep-noromaid-v0-8068-v51_reward/merges.txt
neversleep-noromaid-v0-8068-v51-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/neversleep-noromaid-v0-8068-v51_reward/vocab.json
neversleep-noromaid-v0-8068-v51-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/neversleep-noromaid-v0-8068-v51_reward/tokenizer.json
neversleep-noromaid-v0-8068-v51-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/neversleep-noromaid-v0-8068-v51_reward/reward.tensors
Job neversleep-noromaid-v0-8068-v51-mkmlizer completed after 278.26s with status: succeeded
Stopping job with name neversleep-noromaid-v0-8068-v51-mkmlizer
Pipeline stage MKMLizer completed in 283.88s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.10s
Running pipeline stage ISVCDeployer
Creating inference service neversleep-noromaid-v0-8068-v51
Waiting for inference service neversleep-noromaid-v0-8068-v51 to be ready
Inference service neversleep-noromaid-v0-8068-v51 ready after 70.42572283744812s
Pipeline stage ISVCDeployer completed in 77.80s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.49757981300354s
Received healthy response to inference request in 2.221184253692627s
Received healthy response to inference request in 1.7751226425170898s
Received healthy response to inference request in 1.1817500591278076s
Received healthy response to inference request in 1.7114715576171875s
5 requests
0 failed requests
5th percentile: 1.2876943588256835
10th percentile: 1.3936386585235596
20th percentile: 1.6055272579193116
30th percentile: 1.724201774597168
40th percentile: 1.749662208557129
50th percentile: 1.7751226425170898
60th percentile: 1.9535472869873047
70th percentile: 2.1319719314575196
80th percentile: 2.2764633655548097
90th percentile: 2.3870215892791746
95th percentile: 2.4423007011413573
99th percentile: 2.4865239906311034
mean time: 1.8774216651916504
Pipeline stage StressChecker completed in 10.39s
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_v51 status is now deployed due to DeploymentManager action
neversleep-noromaid-v0-_8068_v51 status is now rejected due to a failure to get M-Eval score. Please try again in five minutes.