developer_uid: robert_irvine
submission_id: neversleep-noromaid-v0-_8068_v57
model_name: neversleep-noromaid-v0-_8068_v57
model_group: NeverSleep/Noromaid-v0.1
status: torndown
timestamp: 2024-05-27T20:27:44+00:00
num_battles: 32396
num_wins: 16554
celo_rating: 1178.01
family_friendly_score: 0.0
submission_type: basic
model_repo: NeverSleep/Noromaid-v0.1-mixtral-8x7b-Instruct-v3
model_architecture: MixtralForCausalLM
reward_repo: rirv938/scaleup_medium_1000000_step_31250
model_num_parameters: 46702792704.0
best_of: 8
max_input_tokens: 512
max_output_tokens: 64
display_name: neversleep-noromaid-v0-_8068_v57
is_internal_developer: True
language_model: NeverSleep/Noromaid-v0.1-mixtral-8x7b-Instruct-v3
model_size: 47B
ranking_group: single
us_pacific_date: 2024-05-27
win_ratio: 0.510989010989011
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': 8, '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}
model_eval_status: success
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'}
Resubmit model
Running pipeline stage MKMLizer
Starting job with name neversleep-noromaid-v0-8068-v57-mkmlizer
Waiting for job on neversleep-noromaid-v0-8068-v57-mkmlizer to finish
Stopping job with name neversleep-noromaid-v0-8068-v57-mkmlizer
%s, retrying in %s seconds...
Starting job with name neversleep-noromaid-v0-8068-v57-mkmlizer
Waiting for job on neversleep-noromaid-v0-8068-v57-mkmlizer to finish
neversleep-noromaid-v0-8068-v57-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
neversleep-noromaid-v0-8068-v57-mkmlizer: ║ _____ __ __ ║
neversleep-noromaid-v0-8068-v57-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
neversleep-noromaid-v0-8068-v57-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
neversleep-noromaid-v0-8068-v57-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
neversleep-noromaid-v0-8068-v57-mkmlizer: ║ /___/ ║
neversleep-noromaid-v0-8068-v57-mkmlizer: ║ ║
neversleep-noromaid-v0-8068-v57-mkmlizer: ║ Version: 0.8.14 ║
neversleep-noromaid-v0-8068-v57-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
neversleep-noromaid-v0-8068-v57-mkmlizer: ║ https://mk1.ai ║
neversleep-noromaid-v0-8068-v57-mkmlizer: ║ ║
neversleep-noromaid-v0-8068-v57-mkmlizer: ║ The license key for the current software has been verified as ║
neversleep-noromaid-v0-8068-v57-mkmlizer: ║ belonging to: ║
neversleep-noromaid-v0-8068-v57-mkmlizer: ║ ║
neversleep-noromaid-v0-8068-v57-mkmlizer: ║ Chai Research Corp. ║
neversleep-noromaid-v0-8068-v57-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
neversleep-noromaid-v0-8068-v57-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
neversleep-noromaid-v0-8068-v57-mkmlizer: ║ ║
neversleep-noromaid-v0-8068-v57-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
neversleep-noromaid-v0-8068-v57-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-v57-mkmlizer: warnings.warn(warning_message, FutureWarning)
neversleep-noromaid-v0-8068-v57-mkmlizer: Downloaded to shared memory in 60.259s
neversleep-noromaid-v0-8068-v57-mkmlizer: quantizing model to /dev/shm/model_cache
neversleep-noromaid-v0-8068-v57-mkmlizer: Saving flywheel model at /dev/shm/model_cache
neversleep-noromaid-v0-8068-v57-mkmlizer: quantized model in 52.892s
neversleep-noromaid-v0-8068-v57-mkmlizer: Processed model NeverSleep/Noromaid-v0.1-mixtral-8x7b-Instruct-v3 in 118.541s
neversleep-noromaid-v0-8068-v57-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v57/special_tokens_map.json
neversleep-noromaid-v0-8068-v57-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v57/tokenizer_config.json
neversleep-noromaid-v0-8068-v57-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v57/tokenizer.json
neversleep-noromaid-v0-8068-v57-mkmlizer: cp /dev/shm/model_cache/flywheel_model.3.safetensors s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v57/flywheel_model.3.safetensors
neversleep-noromaid-v0-8068-v57-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v57/flywheel_model.0.safetensors
neversleep-noromaid-v0-8068-v57-mkmlizer: cp /dev/shm/model_cache/flywheel_model.2.safetensors s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v57/flywheel_model.2.safetensors
neversleep-noromaid-v0-8068-v57-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v57/flywheel_model.1.safetensors
neversleep-noromaid-v0-8068-v57-mkmlizer: loading reward model from rirv938/scaleup_medium_1000000_step_31250
neversleep-noromaid-v0-8068-v57-mkmlizer: Loading 0: 0%| | 0/995 [00:00<?, ?it/s] Loading 0: 5%|▌ | 52/995 [00:00<00:16, 58.66it/s] Loading 0: 11%|█ | 107/995 [00:01<00:14, 60.82it/s] Loading 0: 16%|█▋ | 162/995 [00:02<00:13, 63.08it/s] Loading 0: 21%|██ | 210/995 [00:03<00:12, 60.80it/s] Loading 0: 27%|██▋ | 265/995 [00:04<00:12, 60.46it/s] Loading 0: 28%|██▊ | 278/995 [00:13<01:06, 10.81it/s] Loading 0: 32%|███▏ | 320/995 [00:14<00:46, 14.38it/s] Loading 0: 37%|███▋ | 368/995 [00:15<00:31, 19.63it/s] Loading 0: 43%|████▎ | 423/995 [00:16<00:21, 26.43it/s] Loading 0: 48%|████▊ | 478/995 [00:16<00:15, 33.38it/s] Loading 0: 53%|█████▎ | 526/995 [00:17<00:12, 38.26it/s] Loading 0: 57%|█████▋ | 565/995 [00:27<00:36, 11.93it/s] Loading 0: 58%|█████▊ | 581/995 [00:28<00:33, 12.21it/s] Loading 0: 64%|██████▍ | 636/995 [00:29<00:20, 17.95it/s] Loading 0: 69%|██████▉ | 691/995 [00:30<00:12, 24.30it/s] Loading 0: 74%|███████▍ | 739/995 [00:31<00:08, 29.32it/s] Loading 0: 80%|███████▉ | 794/995 [00:32<00:05, 35.94it/s] Loading 0: 85%|████████▌ | 846/995 [00:41<00:11, 12.88it/s] Loading 0: 86%|████████▌ | 851/995 [00:42<00:12, 11.97it/s] Loading 0: 90%|█████████ | 897/995 [00:43<00:05, 16.52it/s] Loading 0: 96%|█████████▌| 952/995 [00:44<00:01, 23.35it/s] Loading 0: 100%|██████████| 995/995 [00:45<00:00, 26.18it/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-v57-mkmlizer: warnings.warn(
neversleep-noromaid-v0-8068-v57-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-v57-mkmlizer: warnings.warn(
neversleep-noromaid-v0-8068-v57-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-v57-mkmlizer: warnings.warn(
neversleep-noromaid-v0-8068-v57-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
neversleep-noromaid-v0-8068-v57-mkmlizer: Saving duration: 0.225s
neversleep-noromaid-v0-8068-v57-mkmlizer: Processed model rirv938/scaleup_medium_1000000_step_31250 in 6.741s
neversleep-noromaid-v0-8068-v57-mkmlizer: creating bucket guanaco-reward-models
neversleep-noromaid-v0-8068-v57-mkmlizer: Bucket 's3://guanaco-reward-models/' created
neversleep-noromaid-v0-8068-v57-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/neversleep-noromaid-v0-8068-v57_reward
neversleep-noromaid-v0-8068-v57-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/neversleep-noromaid-v0-8068-v57_reward/special_tokens_map.json
neversleep-noromaid-v0-8068-v57-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/neversleep-noromaid-v0-8068-v57_reward/config.json
neversleep-noromaid-v0-8068-v57-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/neversleep-noromaid-v0-8068-v57_reward/tokenizer_config.json
neversleep-noromaid-v0-8068-v57-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/neversleep-noromaid-v0-8068-v57_reward/merges.txt
neversleep-noromaid-v0-8068-v57-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/neversleep-noromaid-v0-8068-v57_reward/vocab.json
neversleep-noromaid-v0-8068-v57-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/neversleep-noromaid-v0-8068-v57_reward/tokenizer.json
neversleep-noromaid-v0-8068-v57-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/neversleep-noromaid-v0-8068-v57_reward/reward.tensors
Job neversleep-noromaid-v0-8068-v57-mkmlizer completed after 155.15s with status: succeeded
Stopping job with name neversleep-noromaid-v0-8068-v57-mkmlizer
Pipeline stage MKMLizer completed in 158.44s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.10s
Running pipeline stage ISVCDeployer
Creating inference service neversleep-noromaid-v0-8068-v57
Waiting for inference service neversleep-noromaid-v0-8068-v57 to be ready
Inference service neversleep-noromaid-v0-8068-v57 ready after 60.31383967399597s
Pipeline stage ISVCDeployer completed in 66.35s
Running pipeline stage StressChecker
Received healthy response to inference request in 3.3955180644989014s
Received healthy response to inference request in 2.425102949142456s
Received healthy response to inference request in 2.484043836593628s
Received healthy response to inference request in 2.548301935195923s
Received healthy response to inference request in 2.657027006149292s
5 requests
0 failed requests
5th percentile: 2.4368911266326903
10th percentile: 2.448679304122925
20th percentile: 2.4722556591033937
30th percentile: 2.496895456314087
40th percentile: 2.522598695755005
50th percentile: 2.548301935195923
60th percentile: 2.5917919635772706
70th percentile: 2.6352819919586183
80th percentile: 2.804725217819214
90th percentile: 3.1001216411590575
95th percentile: 3.2478198528289792
99th percentile: 3.365978422164917
mean time: 2.70199875831604
Pipeline stage StressChecker completed in 14.28s
Running pipeline stage DaemonicModelEvalScorer
Pipeline stage DaemonicModelEvalScorer completed in 0.03s
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 0.06s
neversleep-noromaid-v0-_8068_v57 status is now deployed due to DeploymentManager action
neversleep-noromaid-v0-_8068_v57 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of neversleep-noromaid-v0-_8068_v57
Running pipeline stage ISVCDeleter
Checking if service neversleep-noromaid-v0-8068-v57 is running
Skipping teardown as no inference service was found
Pipeline stage ISVCDeleter completed in 2.97s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key neversleep-noromaid-v0-8068-v57/config.json from bucket guanaco-mkml-models
Deleting key neversleep-noromaid-v0-8068-v57/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key neversleep-noromaid-v0-8068-v57/flywheel_model.1.safetensors from bucket guanaco-mkml-models
Deleting key neversleep-noromaid-v0-8068-v57/flywheel_model.2.safetensors from bucket guanaco-mkml-models
Deleting key neversleep-noromaid-v0-8068-v57/flywheel_model.3.safetensors from bucket guanaco-mkml-models
Deleting key neversleep-noromaid-v0-8068-v57/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key neversleep-noromaid-v0-8068-v57/tokenizer.json from bucket guanaco-mkml-models
Deleting key neversleep-noromaid-v0-8068-v57/tokenizer.model from bucket guanaco-mkml-models
Deleting key neversleep-noromaid-v0-8068-v57/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key neversleep-noromaid-v0-8068-v57_reward/config.json from bucket guanaco-reward-models
Deleting key neversleep-noromaid-v0-8068-v57_reward/merges.txt from bucket guanaco-reward-models
Deleting key neversleep-noromaid-v0-8068-v57_reward/reward.tensors from bucket guanaco-reward-models
Deleting key neversleep-noromaid-v0-8068-v57_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key neversleep-noromaid-v0-8068-v57_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key neversleep-noromaid-v0-8068-v57_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key neversleep-noromaid-v0-8068-v57_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 7.96s
neversleep-noromaid-v0-_8068_v57 status is now torndown due to DeploymentManager action