submission_id: neversleep-noromaid-v0-_8068_v96
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 a personal question [/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: 2024-07-01T22:50:11+00:00
model_name: neversleep-noromaid-v0-_8068_v96
model_group: NeverSleep/Noromaid-v0.1
num_battles: 13350
num_wins: 6295
celo_rating: 1136.75
propriety_score: 0.7272025921925629
propriety_total_count: 6481.0
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_v96
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: 0.4715355805243446
Resubmit model
Running pipeline stage MKMLizer
Starting job with name neversleep-noromaid-v0-8068-v96-mkmlizer
Waiting for job on neversleep-noromaid-v0-8068-v96-mkmlizer to finish
neversleep-noromaid-v0-8068-v96-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
neversleep-noromaid-v0-8068-v96-mkmlizer: ║ _____ __ __ ║
neversleep-noromaid-v0-8068-v96-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
neversleep-noromaid-v0-8068-v96-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
neversleep-noromaid-v0-8068-v96-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
neversleep-noromaid-v0-8068-v96-mkmlizer: ║ /___/ ║
neversleep-noromaid-v0-8068-v96-mkmlizer: ║ ║
neversleep-noromaid-v0-8068-v96-mkmlizer: ║ Version: 0.8.14 ║
neversleep-noromaid-v0-8068-v96-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
neversleep-noromaid-v0-8068-v96-mkmlizer: ║ https://mk1.ai ║
neversleep-noromaid-v0-8068-v96-mkmlizer: ║ ║
neversleep-noromaid-v0-8068-v96-mkmlizer: ║ The license key for the current software has been verified as ║
neversleep-noromaid-v0-8068-v96-mkmlizer: ║ belonging to: ║
neversleep-noromaid-v0-8068-v96-mkmlizer: ║ ║
neversleep-noromaid-v0-8068-v96-mkmlizer: ║ Chai Research Corp. ║
neversleep-noromaid-v0-8068-v96-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
neversleep-noromaid-v0-8068-v96-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
neversleep-noromaid-v0-8068-v96-mkmlizer: ║ ║
neversleep-noromaid-v0-8068-v96-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
neversleep-noromaid-v0-8068-v96-mkmlizer: Downloaded to shared memory in 127.064s
neversleep-noromaid-v0-8068-v96-mkmlizer: quantizing model to /dev/shm/model_cache
neversleep-noromaid-v0-8068-v96-mkmlizer: Saving flywheel model at /dev/shm/model_cache
neversleep-noromaid-v0-8068-v96-mkmlizer: quantized model in 84.519s
neversleep-noromaid-v0-8068-v96-mkmlizer: Processed model NeverSleep/Noromaid-v0.1-mixtral-8x7b-Instruct-v3 in 211.584s
neversleep-noromaid-v0-8068-v96-mkmlizer: creating bucket guanaco-mkml-models
neversleep-noromaid-v0-8068-v96-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
neversleep-noromaid-v0-8068-v96-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v96
neversleep-noromaid-v0-8068-v96-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v96/special_tokens_map.json
neversleep-noromaid-v0-8068-v96-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v96/tokenizer_config.json
neversleep-noromaid-v0-8068-v96-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v96/config.json
neversleep-noromaid-v0-8068-v96-mkmlizer: cp /dev/shm/model_cache/tokenizer.model s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v96/tokenizer.model
neversleep-noromaid-v0-8068-v96-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v96/tokenizer.json
neversleep-noromaid-v0-8068-v96-mkmlizer: cp /dev/shm/model_cache/flywheel_model.3.safetensors s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v96/flywheel_model.3.safetensors
neversleep-noromaid-v0-8068-v96-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v96/flywheel_model.0.safetensors
neversleep-noromaid-v0-8068-v96-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v96/flywheel_model.1.safetensors
neversleep-noromaid-v0-8068-v96-mkmlizer: cp /dev/shm/model_cache/flywheel_model.2.safetensors s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v96/flywheel_model.2.safetensors
neversleep-noromaid-v0-8068-v96-mkmlizer: loading reward model from rirv938/reward_gpt2_medium_preference_24m_e2
neversleep-noromaid-v0-8068-v96-mkmlizer: Loading 0: 0%| | 0/995 [00:00<?, ?it/s] Loading 0: 5%|▍ | 46/995 [00:00<00:02, 425.44it/s] Loading 0: 9%|▉ | 89/995 [00:01<00:13, 67.08it/s] Loading 0: 11%|█ | 109/995 [00:02<00:21, 40.44it/s] Loading 0: 16%|█▋ | 162/995 [00:03<00:18, 44.10it/s] Loading 0: 21%|██ | 210/995 [00:04<00:17, 44.96it/s] Loading 0: 27%|██▋ | 265/995 [00:05<00:15, 48.27it/s] Loading 0: 28%|██▊ | 277/995 [00:21<00:14, 48.27it/s] Loading 0: 28%|██▊ | 278/995 [00:21<02:00, 5.97it/s] Loading 0: 32%|███▏ | 320/995 [00:23<01:20, 8.41it/s] Loading 0: 37%|███▋ | 368/995 [00:24<00:53, 11.66it/s] Loading 0: 43%|████▎ | 423/995 [00:25<00:35, 16.01it/s] Loading 0: 48%|████▊ | 478/995 [00:26<00:25, 20.57it/s] Loading 0: 53%|█████▎ | 526/995 [00:28<00:19, 23.60it/s] Loading 0: 57%|█████▋ | 564/995 [00:45<00:18, 23.60it/s] Loading 0: 57%|█████▋ | 565/995 [00:45<01:01, 7.00it/s] Loading 0: 58%|█████▊ | 581/995 [00:46<00:56, 7.29it/s] Loading 0: 64%|██████▍ | 636/995 [00:47<00:32, 11.04it/s] Loading 0: 69%|██████▉ | 691/995 [00:48<00:19, 15.41it/s] Loading 0: 74%|███████▍ | 739/995 [00:49<00:13, 19.09it/s] Loading 0: 80%|███████▉ | 794/995 [00:51<00:08, 23.91it/s] Loading 0: 85%|████████▍ | 845/995 [01:07<00:06, 23.91it/s] Loading 0: 85%|████████▌ | 846/995 [01:07<00:19, 7.68it/s] Loading 0: 85%|████████▌ | 849/995 [01:09<00:20, 7.25it/s] Loading 0: 90%|█████████ | 897/995 [01:10<00:09, 10.45it/s] Loading 0: 96%|█████████▌| 952/995 [01:11<00:02, 15.05it/s] Loading 0: 100%|██████████| 995/995 [01:12<00:00, 17.84it/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-v96-mkmlizer: warnings.warn(
neversleep-noromaid-v0-8068-v96-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-v96-mkmlizer: warnings.warn(
neversleep-noromaid-v0-8068-v96-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-v96-mkmlizer: warnings.warn(
neversleep-noromaid-v0-8068-v96-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-v96-mkmlizer: warnings.warn(
neversleep-noromaid-v0-8068-v96-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-v96-mkmlizer: return self.fget.__get__(instance, owner)()
neversleep-noromaid-v0-8068-v96-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
Retrying (%r) after connection broken by '%r': %s
Connection pool is full, discarding connection: %s
Connection pool is full, discarding connection: %s
Job neversleep-noromaid-v0-8068-v96-mkmlizer completed after 454.68s with status: succeeded
Stopping job with name neversleep-noromaid-v0-8068-v96-mkmlizer
Pipeline stage MKMLizer completed in 455.85s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.15s
Running pipeline stage ISVCDeployer
Creating inference service neversleep-noromaid-v0-8068-v96
Connection pool is full, discarding connection: %s
Connection pool is full, discarding connection: %s
Connection pool is full, discarding connection: %s
Connection pool is full, discarding connection: %s
Connection pool is full, discarding connection: %s
Waiting for inference service neversleep-noromaid-v0-8068-v96 to be ready
Inference service neversleep-noromaid-v0-8068-v96 ready after 70.33673071861267s
Pipeline stage ISVCDeployer completed in 77.56s
Running pipeline stage StressChecker
Received healthy response to inference request in 3.037569046020508s
Connection pool is full, discarding connection: %s
Connection pool is full, discarding connection: %s
Connection pool is full, discarding connection: %s
Received healthy response to inference request in 2.208024740219116s
Received healthy response to inference request in 2.204421043395996s
Received healthy response to inference request in 1.7197117805480957s
Received healthy response to inference request in 1.929802656173706s
5 requests
0 failed requests
5th percentile: 1.7617299556732178
10th percentile: 1.8037481307983398
20th percentile: 1.887784481048584
30th percentile: 1.984726333618164
40th percentile: 2.0945736885070803
50th percentile: 2.204421043395996
60th percentile: 2.205862522125244
70th percentile: 2.207304000854492
80th percentile: 2.373933601379395
90th percentile: 2.705751323699951
95th percentile: 2.8716601848602292
99th percentile: 3.0043872737884523
mean time: 2.2199058532714844
Pipeline stage StressChecker completed in 11.90s
neversleep-noromaid-v0-_8068_v96 status is now deployed due to DeploymentManager action
neversleep-noromaid-v0-_8068_v96 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics