submission_id: neversleep-noromaid-v0-_8068_v81
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': '[INST] {bot_name} should ask lots of personal questions to {user_name} [/INST]{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: 2024-06-10T21:47:52+00:00
model_name: neversleep-noromaid-v0-_8068_v81
model_eval_status: pending
model_group: NeverSleep/Noromaid-v0.1
num_battles: 48086
num_wins: 21980
celo_rating: 1127.82
propriety_score: 0.691222767913361
propriety_total_count: 15882.0
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_v81
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: 0.45709769995424865
Resubmit model
Running pipeline stage MKMLizer
Starting job with name neversleep-noromaid-v0-8068-v81-mkmlizer
Waiting for job on neversleep-noromaid-v0-8068-v81-mkmlizer to finish
neversleep-noromaid-v0-8068-v81-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
neversleep-noromaid-v0-8068-v81-mkmlizer: ║ _____ __ __ ║
neversleep-noromaid-v0-8068-v81-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
neversleep-noromaid-v0-8068-v81-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
neversleep-noromaid-v0-8068-v81-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
neversleep-noromaid-v0-8068-v81-mkmlizer: ║ /___/ ║
neversleep-noromaid-v0-8068-v81-mkmlizer: ║ ║
neversleep-noromaid-v0-8068-v81-mkmlizer: ║ Version: 0.8.14 ║
neversleep-noromaid-v0-8068-v81-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
neversleep-noromaid-v0-8068-v81-mkmlizer: ║ https://mk1.ai ║
neversleep-noromaid-v0-8068-v81-mkmlizer: ║ ║
neversleep-noromaid-v0-8068-v81-mkmlizer: ║ The license key for the current software has been verified as ║
neversleep-noromaid-v0-8068-v81-mkmlizer: ║ belonging to: ║
neversleep-noromaid-v0-8068-v81-mkmlizer: ║ ║
neversleep-noromaid-v0-8068-v81-mkmlizer: ║ Chai Research Corp. ║
neversleep-noromaid-v0-8068-v81-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
neversleep-noromaid-v0-8068-v81-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
neversleep-noromaid-v0-8068-v81-mkmlizer: ║ ║
neversleep-noromaid-v0-8068-v81-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
neversleep-noromaid-v0-8068-v81-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-v81-mkmlizer: warnings.warn(warning_message, FutureWarning)
neversleep-noromaid-v0-8068-v81-mkmlizer: Downloaded to shared memory in 72.160s
neversleep-noromaid-v0-8068-v81-mkmlizer: quantizing model to /dev/shm/model_cache
neversleep-noromaid-v0-8068-v81-mkmlizer: Saving flywheel model at /dev/shm/model_cache
neversleep-noromaid-v0-8068-v81-mkmlizer: quantized model in 76.693s
neversleep-noromaid-v0-8068-v81-mkmlizer: Processed model NeverSleep/Noromaid-v0.1-mixtral-8x7b-Instruct-v3 in 154.971s
neversleep-noromaid-v0-8068-v81-mkmlizer: creating bucket guanaco-mkml-models
neversleep-noromaid-v0-8068-v81-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
neversleep-noromaid-v0-8068-v81-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v81
neversleep-noromaid-v0-8068-v81-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v81/tokenizer_config.json
neversleep-noromaid-v0-8068-v81-mkmlizer: cp /dev/shm/model_cache/tokenizer.model s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v81/tokenizer.model
neversleep-noromaid-v0-8068-v81-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v81/config.json
neversleep-noromaid-v0-8068-v81-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v81/special_tokens_map.json
neversleep-noromaid-v0-8068-v81-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v81/tokenizer.json
neversleep-noromaid-v0-8068-v81-mkmlizer: cp /dev/shm/model_cache/flywheel_model.3.safetensors s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v81/flywheel_model.3.safetensors
neversleep-noromaid-v0-8068-v81-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v81/flywheel_model.1.safetensors
neversleep-noromaid-v0-8068-v81-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v81/flywheel_model.0.safetensors
neversleep-noromaid-v0-8068-v81-mkmlizer: cp /dev/shm/model_cache/flywheel_model.2.safetensors s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v81/flywheel_model.2.safetensors
neversleep-noromaid-v0-8068-v81-mkmlizer: loading reward model from rirv938/reward_gpt2_medium_preference_24m_e2
neversleep-noromaid-v0-8068-v81-mkmlizer: Loading 0: 0%| | 0/995 [00:00<?, ?it/s] Loading 0: 5%|▌ | 52/995 [00:00<00:15, 60.23it/s] Loading 0: 11%|█ | 107/995 [00:01<00:14, 62.07it/s] Loading 0: 16%|█▋ | 162/995 [00:02<00:12, 64.41it/s] Loading 0: 21%|██ | 210/995 [00:03<00:12, 61.92it/s] Loading 0: 27%|██▋ | 265/995 [00:04<00:14, 51.87it/s] Loading 0: 28%|██▊ | 277/995 [00:19<00:13, 51.87it/s] Loading 0: 28%|██▊ | 278/995 [00:19<01:45, 6.78it/s] Loading 0: 32%|███▏ | 320/995 [00:20<01:11, 9.45it/s] Loading 0: 37%|███▋ | 368/995 [00:21<00:46, 13.48it/s] Loading 0: 43%|████▎ | 423/995 [00:22<00:29, 19.13it/s] Loading 0: 48%|████▊ | 478/995 [00:23<00:20, 25.43it/s] Loading 0: 53%|█████▎ | 526/995 [00:24<00:15, 30.60it/s] Loading 0: 57%|█████▋ | 565/995 [00:39<00:53, 7.97it/s] Loading 0: 58%|█████▊ | 581/995 [00:40<00:48, 8.49it/s] Loading 0: 64%|██████▍ | 636/995 [00:41<00:27, 12.89it/s] Loading 0: 69%|██████▉ | 691/995 [00:42<00:16, 18.20it/s] Loading 0: 74%|███████▍ | 739/995 [00:43<00:11, 21.72it/s] Loading 0: 80%|███████▉ | 794/995 [00:44<00:07, 25.79it/s] Loading 0: 85%|████████▍ | 845/995 [01:00<00:05, 25.79it/s] Loading 0: 85%|████████▌ | 846/995 [01:00<00:17, 8.41it/s] Loading 0: 85%|████████▌ | 849/995 [01:01<00:18, 7.75it/s] Loading 0: 90%|█████████ | 897/995 [01:03<00:09, 10.87it/s] Loading 0: 96%|█████████▌| 952/995 [01:04<00:02, 15.35it/s] Loading 0: 100%|██████████| 995/995 [01:05<00:00, 18.00it/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-v81-mkmlizer: warnings.warn(
neversleep-noromaid-v0-8068-v81-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-v81-mkmlizer: warnings.warn(
neversleep-noromaid-v0-8068-v81-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-v81-mkmlizer: warnings.warn(
neversleep-noromaid-v0-8068-v81-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-v81-mkmlizer: return self.fget.__get__(instance, owner)()
neversleep-noromaid-v0-8068-v81-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
neversleep-noromaid-v0-8068-v81-mkmlizer: Saving duration: 0.234s
neversleep-noromaid-v0-8068-v81-mkmlizer: Processed model rirv938/reward_gpt2_medium_preference_24m_e2 in 4.991s
neversleep-noromaid-v0-8068-v81-mkmlizer: creating bucket guanaco-reward-models
neversleep-noromaid-v0-8068-v81-mkmlizer: Bucket 's3://guanaco-reward-models/' created
neversleep-noromaid-v0-8068-v81-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/neversleep-noromaid-v0-8068-v81_reward
neversleep-noromaid-v0-8068-v81-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/neversleep-noromaid-v0-8068-v81_reward/special_tokens_map.json
neversleep-noromaid-v0-8068-v81-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/neversleep-noromaid-v0-8068-v81_reward/tokenizer_config.json
neversleep-noromaid-v0-8068-v81-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/neversleep-noromaid-v0-8068-v81_reward/merges.txt
neversleep-noromaid-v0-8068-v81-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/neversleep-noromaid-v0-8068-v81_reward/vocab.json
neversleep-noromaid-v0-8068-v81-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/neversleep-noromaid-v0-8068-v81_reward/config.json
neversleep-noromaid-v0-8068-v81-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/neversleep-noromaid-v0-8068-v81_reward/tokenizer.json
neversleep-noromaid-v0-8068-v81-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/neversleep-noromaid-v0-8068-v81_reward/reward.tensors
Job neversleep-noromaid-v0-8068-v81-mkmlizer completed after 197.05s with status: succeeded
Stopping job with name neversleep-noromaid-v0-8068-v81-mkmlizer
Pipeline stage MKMLizer completed in 199.82s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.39s
Running pipeline stage ISVCDeployer
Creating inference service neversleep-noromaid-v0-8068-v81
Waiting for inference service neversleep-noromaid-v0-8068-v81 to be ready
Inference service neversleep-noromaid-v0-8068-v81 ready after 71.01010465621948s
Pipeline stage ISVCDeployer completed in 77.82s
Running pipeline stage StressChecker
Received healthy response to inference request in 3.1338322162628174s
Received healthy response to inference request in 3.4559764862060547s
Received healthy response to inference request in 2.300825357437134s
Received healthy response to inference request in 2.6458280086517334s
Received healthy response to inference request in 11.017133235931396s
5 requests
0 failed requests
5th percentile: 2.3698258876800535
10th percentile: 2.4388264179229737
20th percentile: 2.5768274784088137
30th percentile: 2.74342885017395
40th percentile: 2.938630533218384
50th percentile: 3.1338322162628174
60th percentile: 3.2626899242401124
70th percentile: 3.391547632217407
80th percentile: 4.968207836151125
90th percentile: 7.992670536041261
95th percentile: 9.504901885986326
99th percentile: 10.714686965942382
mean time: 4.510719060897827
Pipeline stage StressChecker completed in 25.59s
Running pipeline stage DaemonicModelEvalScorer
Pipeline stage DaemonicModelEvalScorer completed in 0.16s
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 0.37s
%s, retrying in %s seconds...
neversleep-noromaid-v0-_8068_v81 status is now deployed due to DeploymentManager action
%s, retrying in %s seconds...
neversleep-noromaid-v0-_8068_v81 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics