submission_id: neversleep-noromaid-v0-_8068_v95
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}. 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 humour [/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: 2024-07-01T22:43:26+00:00
model_name: neversleep-noromaid-v0-_8068_v95
model_group: NeverSleep/Noromaid-v0.1
num_battles: 14032
num_wins: 6393
celo_rating: 1127.34
propriety_score: 0.7207524086251721
propriety_total_count: 6539.0
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_v95
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: 2024-07-01
win_ratio: 0.45560148232611175
Resubmit model
Running pipeline stage MKMLizer
Starting job with name neversleep-noromaid-v0-8068-v95-mkmlizer
Waiting for job on neversleep-noromaid-v0-8068-v95-mkmlizer to finish
neversleep-noromaid-v0-8068-v95-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
neversleep-noromaid-v0-8068-v95-mkmlizer: ║ _____ __ __ ║
neversleep-noromaid-v0-8068-v95-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
neversleep-noromaid-v0-8068-v95-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
neversleep-noromaid-v0-8068-v95-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
neversleep-noromaid-v0-8068-v95-mkmlizer: ║ /___/ ║
neversleep-noromaid-v0-8068-v95-mkmlizer: ║ ║
neversleep-noromaid-v0-8068-v95-mkmlizer: ║ Version: 0.8.14 ║
neversleep-noromaid-v0-8068-v95-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
neversleep-noromaid-v0-8068-v95-mkmlizer: ║ https://mk1.ai ║
neversleep-noromaid-v0-8068-v95-mkmlizer: ║ ║
neversleep-noromaid-v0-8068-v95-mkmlizer: ║ The license key for the current software has been verified as ║
neversleep-noromaid-v0-8068-v95-mkmlizer: ║ belonging to: ║
neversleep-noromaid-v0-8068-v95-mkmlizer: ║ ║
neversleep-noromaid-v0-8068-v95-mkmlizer: ║ Chai Research Corp. ║
neversleep-noromaid-v0-8068-v95-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
neversleep-noromaid-v0-8068-v95-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
neversleep-noromaid-v0-8068-v95-mkmlizer: ║ ║
neversleep-noromaid-v0-8068-v95-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
neversleep-noromaid-v0-8068-v95-mkmlizer: Downloaded to shared memory in 118.289s
neversleep-noromaid-v0-8068-v95-mkmlizer: quantizing model to /dev/shm/model_cache
neversleep-noromaid-v0-8068-v95-mkmlizer: Saving flywheel model at /dev/shm/model_cache
neversleep-noromaid-v0-8068-v95-mkmlizer: quantized model in 92.923s
neversleep-noromaid-v0-8068-v95-mkmlizer: Processed model NeverSleep/Noromaid-v0.1-mixtral-8x7b-Instruct-v3 in 211.212s
neversleep-noromaid-v0-8068-v95-mkmlizer: creating bucket guanaco-mkml-models
neversleep-noromaid-v0-8068-v95-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
neversleep-noromaid-v0-8068-v95-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v95
neversleep-noromaid-v0-8068-v95-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v95/config.json
neversleep-noromaid-v0-8068-v95-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v95/tokenizer.json
neversleep-noromaid-v0-8068-v95-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v95/special_tokens_map.json
neversleep-noromaid-v0-8068-v95-mkmlizer: cp /dev/shm/model_cache/flywheel_model.3.safetensors s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v95/flywheel_model.3.safetensors
neversleep-noromaid-v0-8068-v95-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v95/flywheel_model.0.safetensors
neversleep-noromaid-v0-8068-v95-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v95/flywheel_model.1.safetensors
neversleep-noromaid-v0-8068-v95-mkmlizer: cp /dev/shm/model_cache/flywheel_model.2.safetensors s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v95/flywheel_model.2.safetensors
neversleep-noromaid-v0-8068-v95-mkmlizer: loading reward model from rirv938/reward_gpt2_medium_preference_24m_e2
neversleep-noromaid-v0-8068-v95-mkmlizer: Loading 0: 0%| | 0/995 [00:00<?, ?it/s] Loading 0: 5%|▌ | 52/995 [00:01<00:26, 36.27it/s] Loading 0: 11%|█ | 107/995 [00:02<00:24, 36.55it/s] Loading 0: 16%|█▋ | 162/995 [00:04<00:21, 38.46it/s] Loading 0: 21%|██ | 210/995 [00:05<00:21, 37.35it/s] Loading 0: 27%|██▋ | 265/995 [00:06<00:18, 39.65it/s] Loading 0: 28%|██▊ | 277/995 [00:24<00:18, 39.65it/s] Loading 0: 28%|██▊ | 278/995 [00:24<02:03, 5.82it/s] Loading 0: 32%|███▏ | 320/995 [00:25<01:24, 8.00it/s] Loading 0: 37%|███▋ | 368/995 [00:26<00:56, 11.18it/s] Loading 0: 43%|████▎ | 423/995 [00:28<00:36, 15.51it/s] Loading 0: 48%|████▊ | 478/995 [00:29<00:25, 20.19it/s] Loading 0: 53%|█████▎ | 526/995 [00:30<00:19, 23.74it/s] Loading 0: 57%|█████▋ | 564/995 [00:47<00:18, 23.74it/s] Loading 0: 57%|█████▋ | 565/995 [00:47<01:02, 6.88it/s] Loading 0: 58%|█████▊ | 581/995 [00:49<00:57, 7.20it/s] Loading 0: 64%|██████▍ | 636/995 [00:50<00:33, 10.75it/s] Loading 0: 69%|██████▉ | 691/995 [00:51<00:20, 14.88it/s] Loading 0: 74%|███████▍ | 739/995 [00:52<00:13, 18.32it/s] Loading 0: 80%|███████▉ | 794/995 [00:54<00:09, 22.03it/s] Loading 0: 85%|████████▍ | 845/995 [01:11<00:06, 22.03it/s] Loading 0: 85%|████████▌ | 846/995 [01:11<00:19, 7.49it/s] Loading 0: 85%|████████▌ | 849/995 [01:12<00:20, 7.03it/s] Loading 0: 90%|█████████ | 897/995 [01:14<00:09, 10.04it/s] Loading 0: 96%|█████████▌| 952/995 [01:15<00:03, 14.20it/s] Loading 0: 100%|██████████| 995/995 [01:16<00:00, 16.90it/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-v95-mkmlizer: warnings.warn(
neversleep-noromaid-v0-8068-v95-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-v95-mkmlizer: warnings.warn(
neversleep-noromaid-v0-8068-v95-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-v95-mkmlizer: warnings.warn(
neversleep-noromaid-v0-8068-v95-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-v95-mkmlizer: warnings.warn(
neversleep-noromaid-v0-8068-v95-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-v95-mkmlizer: return self.fget.__get__(instance, owner)()
neversleep-noromaid-v0-8068-v95-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
neversleep-noromaid-v0-8068-v95-mkmlizer: Saving duration: 0.418s
neversleep-noromaid-v0-8068-v95-mkmlizer: Processed model rirv938/reward_gpt2_medium_preference_24m_e2 in 4.263s
neversleep-noromaid-v0-8068-v95-mkmlizer: creating bucket guanaco-reward-models
neversleep-noromaid-v0-8068-v95-mkmlizer: Bucket 's3://guanaco-reward-models/' created
neversleep-noromaid-v0-8068-v95-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/neversleep-noromaid-v0-8068-v95_reward
neversleep-noromaid-v0-8068-v95-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/neversleep-noromaid-v0-8068-v95_reward/config.json
neversleep-noromaid-v0-8068-v95-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/neversleep-noromaid-v0-8068-v95_reward/tokenizer_config.json
neversleep-noromaid-v0-8068-v95-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/neversleep-noromaid-v0-8068-v95_reward/special_tokens_map.json
neversleep-noromaid-v0-8068-v95-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/neversleep-noromaid-v0-8068-v95_reward/vocab.json
neversleep-noromaid-v0-8068-v95-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/neversleep-noromaid-v0-8068-v95_reward/merges.txt
neversleep-noromaid-v0-8068-v95-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/neversleep-noromaid-v0-8068-v95_reward/tokenizer.json
neversleep-noromaid-v0-8068-v95-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/neversleep-noromaid-v0-8068-v95_reward/reward.tensors
Job neversleep-noromaid-v0-8068-v95-mkmlizer completed after 258.61s with status: succeeded
Stopping job with name neversleep-noromaid-v0-8068-v95-mkmlizer
Pipeline stage MKMLizer completed in 259.45s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.11s
Running pipeline stage ISVCDeployer
Creating inference service neversleep-noromaid-v0-8068-v95
Waiting for inference service neversleep-noromaid-v0-8068-v95 to be ready
Inference service neversleep-noromaid-v0-8068-v95 ready after 70.39707493782043s
Pipeline stage ISVCDeployer completed in 77.11s
Running pipeline stage StressChecker
Received healthy response to inference request in 3.2707033157348633s
Received healthy response to inference request in 2.50319766998291s
Received healthy response to inference request in 2.497774124145508s
Received healthy response to inference request in 2.481480598449707s
Received healthy response to inference request in 2.495091676712036s
5 requests
0 failed requests
5th percentile: 2.484202814102173
10th percentile: 2.4869250297546386
20th percentile: 2.49236946105957
30th percentile: 2.4956281661987303
40th percentile: 2.496701145172119
50th percentile: 2.497774124145508
60th percentile: 2.4999435424804686
70th percentile: 2.5021129608154298
80th percentile: 2.656698799133301
90th percentile: 2.963701057434082
95th percentile: 3.1172021865844726
99th percentile: 3.240003089904785
mean time: 2.649649477005005
Pipeline stage StressChecker completed in 14.08s
neversleep-noromaid-v0-_8068_v95 status is now deployed due to DeploymentManager action
neversleep-noromaid-v0-_8068_v95 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics