developer_uid: robert_irvine
submission_id: neversleep-noromaid-v0-_8068_v63
model_name: neversleep-noromaid-v0-_8068_v63
model_group: NeverSleep/Noromaid-v0.1
status: torndown
timestamp: 2024-06-07T18:51:58+00:00
num_battles: 37930
num_wins: 18480
celo_rating: 1168.7
family_friendly_score: 0.0
submission_type: basic
model_repo: NeverSleep/Noromaid-v0.1-mixtral-8x7b-Instruct-v3
model_architecture: MixtralForCausalLM
reward_repo: rirv938/reward_gpt2_medium_preference_24m_e2
model_num_parameters: 46702792704.0
best_of: 4
max_input_tokens: 512
max_output_tokens: 64
display_name: neversleep-noromaid-v0-_8068_v63
is_internal_developer: True
language_model: NeverSleep/Noromaid-v0.1-mixtral-8x7b-Instruct-v3
model_size: 47B
ranking_group: single
us_pacific_date: 2024-06-07
win_ratio: 0.48721328763511734
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}. 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: {'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'}
model_eval_status: success
Resubmit model
Running pipeline stage MKMLizer
Starting job with name neversleep-noromaid-v0-8068-v63-mkmlizer
Waiting for job on neversleep-noromaid-v0-8068-v63-mkmlizer to finish
neversleep-noromaid-v0-8068-v63-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
neversleep-noromaid-v0-8068-v63-mkmlizer: ║     _____            __           __                                ║
neversleep-noromaid-v0-8068-v63-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
neversleep-noromaid-v0-8068-v63-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
neversleep-noromaid-v0-8068-v63-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
neversleep-noromaid-v0-8068-v63-mkmlizer: ║       /___/                                                         ║
neversleep-noromaid-v0-8068-v63-mkmlizer: ║                                                                     ║
neversleep-noromaid-v0-8068-v63-mkmlizer: ║  Version: 0.8.14                                                    ║
neversleep-noromaid-v0-8068-v63-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
neversleep-noromaid-v0-8068-v63-mkmlizer: ║  https://mk1.ai                                                     ║
neversleep-noromaid-v0-8068-v63-mkmlizer: ║                                                                     ║
neversleep-noromaid-v0-8068-v63-mkmlizer: ║  The license key for the current software has been verified as      ║
neversleep-noromaid-v0-8068-v63-mkmlizer: ║  belonging to:                                                      ║
neversleep-noromaid-v0-8068-v63-mkmlizer: ║                                                                     ║
neversleep-noromaid-v0-8068-v63-mkmlizer: ║  Chai Research Corp.                                                ║
neversleep-noromaid-v0-8068-v63-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
neversleep-noromaid-v0-8068-v63-mkmlizer: ║  Expiration: 2024-07-15 23:59:59                                    ║
neversleep-noromaid-v0-8068-v63-mkmlizer: ║                                                                     ║
neversleep-noromaid-v0-8068-v63-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
neversleep-noromaid-v0-8068-v63-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-v63-mkmlizer:   warnings.warn(warning_message, FutureWarning)
neversleep-noromaid-v0-8068-v63-mkmlizer: Downloaded to shared memory in 168.548s
neversleep-noromaid-v0-8068-v63-mkmlizer: quantizing model to /dev/shm/model_cache
neversleep-noromaid-v0-8068-v63-mkmlizer: Saving flywheel model at /dev/shm/model_cache
neversleep-noromaid-v0-8068-v63-mkmlizer: quantized model in 49.646s
neversleep-noromaid-v0-8068-v63-mkmlizer: Processed model NeverSleep/Noromaid-v0.1-mixtral-8x7b-Instruct-v3 in 223.454s
neversleep-noromaid-v0-8068-v63-mkmlizer: creating bucket guanaco-mkml-models
neversleep-noromaid-v0-8068-v63-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
neversleep-noromaid-v0-8068-v63-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v63
neversleep-noromaid-v0-8068-v63-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v63/tokenizer_config.json
neversleep-noromaid-v0-8068-v63-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v63/special_tokens_map.json
neversleep-noromaid-v0-8068-v63-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v63/config.json
neversleep-noromaid-v0-8068-v63-mkmlizer: cp /dev/shm/model_cache/tokenizer.model s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v63/tokenizer.model
neversleep-noromaid-v0-8068-v63-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v63/tokenizer.json
neversleep-noromaid-v0-8068-v63-mkmlizer: cp /dev/shm/model_cache/flywheel_model.3.safetensors s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v63/flywheel_model.3.safetensors
neversleep-noromaid-v0-8068-v63-mkmlizer: cp /dev/shm/model_cache/flywheel_model.2.safetensors s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v63/flywheel_model.2.safetensors
neversleep-noromaid-v0-8068-v63-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v63/flywheel_model.1.safetensors
neversleep-noromaid-v0-8068-v63-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v63/flywheel_model.0.safetensors
neversleep-noromaid-v0-8068-v63-mkmlizer: loading reward model from rirv938/reward_gpt2_medium_preference_24m_e2
neversleep-noromaid-v0-8068-v63-mkmlizer: 
Loading 0:   0%|          | 0/995 [00:00<?, ?it/s]
Loading 0:   5%|▌         | 52/995 [00:00<00:15, 62.54it/s]
Loading 0:  11%|█         | 107/995 [00:01<00:13, 65.06it/s]
Loading 0:  16%|█▋        | 162/995 [00:02<00:12, 66.41it/s]
Loading 0:  21%|██        | 210/995 [00:03<00:12, 63.40it/s]
Loading 0:  27%|██▋       | 265/995 [00:04<00:11, 64.99it/s]
Loading 0:  28%|██▊       | 278/995 [00:12<01:04, 11.09it/s]
Loading 0:  32%|███▏      | 320/995 [00:14<00:45, 14.71it/s]
Loading 0:  37%|███▋      | 368/995 [00:14<00:31, 20.06it/s]
Loading 0:  43%|████▎     | 423/995 [00:15<00:21, 26.99it/s]
Loading 0:  48%|████▊     | 478/995 [00:16<00:15, 34.16it/s]
Loading 0:  53%|█████▎    | 526/995 [00:17<00:12, 39.04it/s]
Loading 0:  57%|█████▋    | 565/995 [00:26<00:34, 12.58it/s]
Loading 0:  58%|█████▊    | 581/995 [00:27<00:32, 12.85it/s]
Loading 0:  64%|██████▍   | 636/995 [00:28<00:19, 18.88it/s]
Loading 0:  69%|██████▉   | 691/995 [00:29<00:11, 25.48it/s]
Loading 0:  74%|███████▍  | 739/995 [00:29<00:08, 30.96it/s]
Loading 0:  80%|███████▉  | 794/995 [00:30<00:05, 37.81it/s]
Loading 0:  85%|████████▌ | 846/995 [00:39<00:10, 14.00it/s]
Loading 0:  86%|████████▌ | 851/995 [00:40<00:11, 12.96it/s]
Loading 0:  90%|█████████ | 897/995 [00:41<00:05, 17.78it/s]
Loading 0:  96%|█████████▌| 952/995 [00:42<00:01, 25.01it/s]
Loading 0: 100%|██████████| 995/995 [00:43<00:00, 27.88it/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-v63-mkmlizer:   warnings.warn(
neversleep-noromaid-v0-8068-v63-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-v63-mkmlizer:   warnings.warn(
neversleep-noromaid-v0-8068-v63-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-v63-mkmlizer:   warnings.warn(
neversleep-noromaid-v0-8068-v63-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-v63-mkmlizer:   return self.fget.__get__(instance, owner)()
neversleep-noromaid-v0-8068-v63-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
neversleep-noromaid-v0-8068-v63-mkmlizer: Saving duration: 0.204s
neversleep-noromaid-v0-8068-v63-mkmlizer: Processed model rirv938/reward_gpt2_medium_preference_24m_e2 in 5.860s
neversleep-noromaid-v0-8068-v63-mkmlizer: creating bucket guanaco-reward-models
neversleep-noromaid-v0-8068-v63-mkmlizer: Bucket 's3://guanaco-reward-models/' created
neversleep-noromaid-v0-8068-v63-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/neversleep-noromaid-v0-8068-v63_reward
neversleep-noromaid-v0-8068-v63-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/neversleep-noromaid-v0-8068-v63_reward/special_tokens_map.json
neversleep-noromaid-v0-8068-v63-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/neversleep-noromaid-v0-8068-v63_reward/tokenizer_config.json
neversleep-noromaid-v0-8068-v63-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/neversleep-noromaid-v0-8068-v63_reward/merges.txt
neversleep-noromaid-v0-8068-v63-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/neversleep-noromaid-v0-8068-v63_reward/vocab.json
neversleep-noromaid-v0-8068-v63-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/neversleep-noromaid-v0-8068-v63_reward/tokenizer.json
neversleep-noromaid-v0-8068-v63-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/neversleep-noromaid-v0-8068-v63_reward/config.json
neversleep-noromaid-v0-8068-v63-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/neversleep-noromaid-v0-8068-v63_reward/reward.tensors
Job neversleep-noromaid-v0-8068-v63-mkmlizer completed after 257.98s with status: succeeded
Stopping job with name neversleep-noromaid-v0-8068-v63-mkmlizer
Pipeline stage MKMLizer completed in 259.03s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.09s
Running pipeline stage ISVCDeployer
Creating inference service neversleep-noromaid-v0-8068-v63
Waiting for inference service neversleep-noromaid-v0-8068-v63 to be ready
Inference service neversleep-noromaid-v0-8068-v63 ready after 331.9047498703003s
Pipeline stage ISVCDeployer completed in 337.97s
Running pipeline stage StressChecker
Received healthy response to inference request in 3.0375125408172607s
Received healthy response to inference request in 2.05078125s
Received healthy response to inference request in 2.141310453414917s
Received healthy response to inference request in 2.3087384700775146s
Received healthy response to inference request in 1.9621708393096924s
5 requests
0 failed requests
5th percentile: 1.9798929214477539
10th percentile: 1.9976150035858153
20th percentile: 2.0330591678619383
30th percentile: 2.0688870906829835
40th percentile: 2.10509877204895
50th percentile: 2.141310453414917
60th percentile: 2.208281660079956
70th percentile: 2.275252866744995
80th percentile: 2.454493284225464
90th percentile: 2.7460029125213623
95th percentile: 2.8917577266693115
99th percentile: 3.008361577987671
mean time: 2.300102710723877
Pipeline stage StressChecker completed in 12.13s
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 0.03s
M-Eval Dataset for topic stay_in_character is loaded
neversleep-noromaid-v0-_8068_v63 status is now deployed due to DeploymentManager action
neversleep-noromaid-v0-_8068_v63 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of neversleep-noromaid-v0-_8068_v63
Running pipeline stage ISVCDeleter
Checking if service neversleep-noromaid-v0-8068-v63 is running
Skipping teardown as no inference service was found
Pipeline stage ISVCDeleter completed in 2.37s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key neversleep-noromaid-v0-8068-v63/config.json from bucket guanaco-mkml-models
Deleting key neversleep-noromaid-v0-8068-v63/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key neversleep-noromaid-v0-8068-v63/flywheel_model.1.safetensors from bucket guanaco-mkml-models
Deleting key neversleep-noromaid-v0-8068-v63/flywheel_model.2.safetensors from bucket guanaco-mkml-models
Deleting key neversleep-noromaid-v0-8068-v63/flywheel_model.3.safetensors from bucket guanaco-mkml-models
Deleting key neversleep-noromaid-v0-8068-v63/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key neversleep-noromaid-v0-8068-v63/tokenizer.json from bucket guanaco-mkml-models
Deleting key neversleep-noromaid-v0-8068-v63/tokenizer.model from bucket guanaco-mkml-models
Deleting key neversleep-noromaid-v0-8068-v63/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key neversleep-noromaid-v0-8068-v63_reward/config.json from bucket guanaco-reward-models
Deleting key neversleep-noromaid-v0-8068-v63_reward/merges.txt from bucket guanaco-reward-models
Deleting key neversleep-noromaid-v0-8068-v63_reward/reward.tensors from bucket guanaco-reward-models
Deleting key neversleep-noromaid-v0-8068-v63_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key neversleep-noromaid-v0-8068-v63_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key neversleep-noromaid-v0-8068-v63_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key neversleep-noromaid-v0-8068-v63_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 7.44s
neversleep-noromaid-v0-_8068_v63 status is now torndown due to DeploymentManager action