developer_uid: robert_irvine
submission_id: neversleep-noromaid-v0_8068_v107
model_name: neversleep-noromaid-v0_8068_v107
model_group: NeverSleep/Noromaid-v0.1
status: torndown
timestamp: 2024-07-02T03:09:55+00:00
num_battles: 10819
num_wins: 4788
celo_rating: 1134.38
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_v107
is_internal_developer: True
language_model: NeverSleep/Noromaid-v0.1-mixtral-8x7b-Instruct-v3
model_size: 47B
ranking_group: single
us_pacific_date: 2024-07-01
win_ratio: 0.44255476476569
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': '[INST] respond with something weird [/INST]{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'}
Resubmit model
Running pipeline stage MKMLizer
Starting job with name neversleep-noromaid-v0-8068-v107-mkmlizer
Waiting for job on neversleep-noromaid-v0-8068-v107-mkmlizer to finish
neversleep-noromaid-v0-8068-v107-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
neversleep-noromaid-v0-8068-v107-mkmlizer: ║     _____            __           __                                ║
neversleep-noromaid-v0-8068-v107-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
neversleep-noromaid-v0-8068-v107-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
neversleep-noromaid-v0-8068-v107-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
neversleep-noromaid-v0-8068-v107-mkmlizer: ║       /___/                                                         ║
neversleep-noromaid-v0-8068-v107-mkmlizer: ║                                                                     ║
neversleep-noromaid-v0-8068-v107-mkmlizer: ║  Version: 0.8.14                                                    ║
neversleep-noromaid-v0-8068-v107-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
neversleep-noromaid-v0-8068-v107-mkmlizer: ║  https://mk1.ai                                                     ║
neversleep-noromaid-v0-8068-v107-mkmlizer: ║                                                                     ║
neversleep-noromaid-v0-8068-v107-mkmlizer: ║  The license key for the current software has been verified as      ║
neversleep-noromaid-v0-8068-v107-mkmlizer: ║  belonging to:                                                      ║
neversleep-noromaid-v0-8068-v107-mkmlizer: ║                                                                     ║
neversleep-noromaid-v0-8068-v107-mkmlizer: ║  Chai Research Corp.                                                ║
neversleep-noromaid-v0-8068-v107-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
neversleep-noromaid-v0-8068-v107-mkmlizer: ║  Expiration: 2024-07-15 23:59:59                                    ║
neversleep-noromaid-v0-8068-v107-mkmlizer: ║                                                                     ║
neversleep-noromaid-v0-8068-v107-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
neversleep-noromaid-v0-8068-v107-mkmlizer: Downloaded to shared memory in 108.916s
neversleep-noromaid-v0-8068-v107-mkmlizer: quantizing model to /dev/shm/model_cache
neversleep-noromaid-v0-8068-v107-mkmlizer: Saving flywheel model at /dev/shm/model_cache
neversleep-noromaid-v0-8068-v107-mkmlizer: quantized model in 84.929s
neversleep-noromaid-v0-8068-v107-mkmlizer: Processed model NeverSleep/Noromaid-v0.1-mixtral-8x7b-Instruct-v3 in 193.846s
neversleep-noromaid-v0-8068-v107-mkmlizer: creating bucket guanaco-mkml-models
neversleep-noromaid-v0-8068-v107-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
neversleep-noromaid-v0-8068-v107-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v107
neversleep-noromaid-v0-8068-v107-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v107/special_tokens_map.json
neversleep-noromaid-v0-8068-v107-mkmlizer: cp /dev/shm/model_cache/tokenizer.model s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v107/tokenizer.model
neversleep-noromaid-v0-8068-v107-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v107/tokenizer.json
neversleep-noromaid-v0-8068-v107-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v107/config.json
neversleep-noromaid-v0-8068-v107-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v107/tokenizer_config.json
neversleep-noromaid-v0-8068-v107-mkmlizer: cp /dev/shm/model_cache/flywheel_model.3.safetensors s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v107/flywheel_model.3.safetensors
neversleep-noromaid-v0-8068-v107-mkmlizer: cp /dev/shm/model_cache/flywheel_model.2.safetensors s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v107/flywheel_model.2.safetensors
neversleep-noromaid-v0-8068-v107-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v107/flywheel_model.0.safetensors
neversleep-noromaid-v0-8068-v107-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v107/flywheel_model.1.safetensors
neversleep-noromaid-v0-8068-v107-mkmlizer: loading reward model from rirv938/reward_gpt2_medium_preference_24m_e2
neversleep-noromaid-v0-8068-v107-mkmlizer: 
Loading 0:   0%|          | 0/995 [00:00<?, ?it/s]
Loading 0:   5%|▌         | 52/995 [00:01<00:22, 41.99it/s]
Loading 0:  11%|█         | 107/995 [00:02<00:20, 43.99it/s]
Loading 0:  16%|█▋        | 162/995 [00:03<00:18, 44.93it/s]
Loading 0:  21%|██        | 210/995 [00:04<00:17, 43.88it/s]
Loading 0:  27%|██▋       | 265/995 [00:05<00:15, 46.13it/s]
Loading 0:  28%|██▊       | 277/995 [00:22<00:15, 46.13it/s]
Loading 0:  28%|██▊       | 278/995 [00:22<01:57,  6.11it/s]
Loading 0:  32%|███▏      | 320/995 [00:23<01:20,  8.43it/s]
Loading 0:  37%|███▋      | 368/995 [00:25<00:53, 11.82it/s]
Loading 0:  43%|████▎     | 423/995 [00:26<00:34, 16.35it/s]
Loading 0:  48%|████▊     | 478/995 [00:27<00:24, 21.23it/s]
Loading 0:  53%|█████▎    | 526/995 [00:28<00:18, 24.97it/s]
Loading 0:  57%|█████▋    | 564/995 [00:45<00:17, 24.97it/s]
Loading 0:  57%|█████▋    | 565/995 [00:45<01:00,  7.06it/s]
Loading 0:  58%|█████▊    | 581/995 [00:46<00:55,  7.44it/s]
Loading 0:  64%|██████▍   | 636/995 [00:47<00:32, 11.18it/s]
Loading 0:  69%|██████▉   | 691/995 [00:48<00:19, 15.54it/s]
Loading 0:  74%|███████▍  | 739/995 [00:50<00:13, 19.39it/s]
Loading 0:  80%|███████▉  | 794/995 [00:51<00:08, 24.50it/s]
Loading 0:  85%|████████▍ | 845/995 [01:07<00:06, 24.50it/s]
Loading 0:  85%|████████▌ | 846/995 [01:07<00:19,  7.73it/s]
Loading 0:  85%|████████▌ | 849/995 [01:09<00:20,  7.27it/s]
Loading 0:  90%|█████████ | 897/995 [01:10<00:09, 10.40it/s]
Loading 0:  96%|█████████▌| 952/995 [01:11<00:02, 14.65it/s]
Loading 0: 100%|██████████| 995/995 [01:13<00:00, 17.44it/s]
                                                            
/opt/conda/lib/python3.10/site-packages/transformers/models/auto/configuration_auto.py:919: FutureWarning: The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers. Please use `token` instead.
neversleep-noromaid-v0-8068-v107-mkmlizer:   warnings.warn(
neversleep-noromaid-v0-8068-v107-mkmlizer: /opt/conda/lib/python3.10/site-packages/huggingface_hub/file_download.py:1132: FutureWarning: `resume_download` is deprecated and will be removed in version 1.0.0. Downloads always resume when possible. If you want to force a new download, use `force_download=True`.
neversleep-noromaid-v0-8068-v107-mkmlizer:   warnings.warn(
neversleep-noromaid-v0-8068-v107-mkmlizer: /opt/conda/lib/python3.10/site-packages/transformers/models/auto/tokenization_auto.py:769: FutureWarning: The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers. Please use `token` instead.
neversleep-noromaid-v0-8068-v107-mkmlizer:   warnings.warn(
neversleep-noromaid-v0-8068-v107-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-v107-mkmlizer:   warnings.warn(
neversleep-noromaid-v0-8068-v107-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-v107-mkmlizer:   return self.fget.__get__(instance, owner)()
neversleep-noromaid-v0-8068-v107-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
neversleep-noromaid-v0-8068-v107-mkmlizer: Saving duration: 0.386s
neversleep-noromaid-v0-8068-v107-mkmlizer: Processed model rirv938/reward_gpt2_medium_preference_24m_e2 in 4.689s
neversleep-noromaid-v0-8068-v107-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/neversleep-noromaid-v0-8068-v107_reward/reward.tensors
Job neversleep-noromaid-v0-8068-v107-mkmlizer completed after 237.77s with status: succeeded
Stopping job with name neversleep-noromaid-v0-8068-v107-mkmlizer
Pipeline stage MKMLizer completed in 238.68s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.10s
Running pipeline stage ISVCDeployer
Creating inference service neversleep-noromaid-v0-8068-v107
Waiting for inference service neversleep-noromaid-v0-8068-v107 to be ready
Inference service neversleep-noromaid-v0-8068-v107 ready after 80.4066755771637s
Pipeline stage ISVCDeployer completed in 87.35s
Running pipeline stage StressChecker
Received healthy response to inference request in 3.259615182876587s
Received healthy response to inference request in 2.380464792251587s
Received healthy response to inference request in 2.3015079498291016s
Received healthy response to inference request in 2.3983535766601562s
Received healthy response to inference request in 2.280756950378418s
5 requests
0 failed requests
5th percentile: 2.2849071502685545
10th percentile: 2.2890573501586915
20th percentile: 2.297357749938965
30th percentile: 2.317299318313599
40th percentile: 2.348882055282593
50th percentile: 2.380464792251587
60th percentile: 2.3876203060150147
70th percentile: 2.3947758197784426
80th percentile: 2.5706058979034427
90th percentile: 2.915110540390015
95th percentile: 3.0873628616333004
99th percentile: 3.2251647186279295
mean time: 2.5241396903991697
Pipeline stage StressChecker completed in 13.58s
neversleep-noromaid-v0_8068_v107 status is now deployed due to DeploymentManager action
neversleep-noromaid-v0_8068_v107 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of neversleep-noromaid-v0_8068_v107
Running pipeline stage ISVCDeleter
Checking if service neversleep-noromaid-v0-8068-v107 is running
Skipping teardown as no inference service was found
Pipeline stage ISVCDeleter completed in 4.66s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key neversleep-noromaid-v0-8068-v107/config.json from bucket guanaco-mkml-models
Deleting key neversleep-noromaid-v0-8068-v107/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key neversleep-noromaid-v0-8068-v107/flywheel_model.1.safetensors from bucket guanaco-mkml-models
Deleting key neversleep-noromaid-v0-8068-v107/flywheel_model.2.safetensors from bucket guanaco-mkml-models
Deleting key neversleep-noromaid-v0-8068-v107/flywheel_model.3.safetensors from bucket guanaco-mkml-models
Deleting key neversleep-noromaid-v0-8068-v107/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key neversleep-noromaid-v0-8068-v107/tokenizer.json from bucket guanaco-mkml-models
Deleting key neversleep-noromaid-v0-8068-v107/tokenizer.model from bucket guanaco-mkml-models
Deleting key neversleep-noromaid-v0-8068-v107/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key neversleep-noromaid-v0-8068-v107_reward/config.json from bucket guanaco-reward-models
Deleting key neversleep-noromaid-v0-8068-v107_reward/merges.txt from bucket guanaco-reward-models
Deleting key neversleep-noromaid-v0-8068-v107_reward/reward.tensors from bucket guanaco-reward-models
Deleting key neversleep-noromaid-v0-8068-v107_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key neversleep-noromaid-v0-8068-v107_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key neversleep-noromaid-v0-8068-v107_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key neversleep-noromaid-v0-8068-v107_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 9.50s
neversleep-noromaid-v0_8068_v107 status is now torndown due to DeploymentManager action