submission_id: neversleep-noromaid-v0_8068_v131
developer_uid: robert_irvine
status: inactive
model_repo: NeverSleep/Noromaid-v0.1-mixtral-8x7b-Instruct-v3
reward_repo: ChaiML/gpt2_medium_pairwise_60m_step_937500
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': '""', 'prompt_template': '""', 'bot_template': 'Bot: {message}\n', 'user_template': 'User: {message}\n', 'response_template': 'Bot:', 'truncate_by_message': False}
timestamp: 2024-07-11T20:31:12+00:00
model_name: neversleep-noromaid-v0_8068_v131
model_group: NeverSleep/Noromaid-v0.1
num_battles: 34209
num_wins: 14625
celo_rating: 1144.58
propriety_score: 0.715527950310559
propriety_total_count: 5635.0
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_v131
ineligible_reason: None
language_model: NeverSleep/Noromaid-v0.1-mixtral-8x7b-Instruct-v3
model_size: 47B
reward_model: ChaiML/gpt2_medium_pairwise_60m_step_937500
us_pacific_date: 2024-07-11
win_ratio: 0.4275190739279137
preference_data_url: None
Resubmit model
Running pipeline stage MKMLizer
Starting job with name neversleep-noromaid-v0-8068-v131-mkmlizer
Waiting for job on neversleep-noromaid-v0-8068-v131-mkmlizer to finish
Failed to get response for submission chaiml-sao10k-l3-rp-v3-3_v21: ('http://chaiml-sao10k-l3-rp-v3-3-v21-predictor-default.tenant-chaiml-guanaco.knative.ord1.coreweave.cloud/v1/models/GPT-J-6B-lit-v2:predict', 'read tcp 127.0.0.1:54548->127.0.0.1:8080: read: connection reset by peer\n')
neversleep-noromaid-v0-8068-v131-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
neversleep-noromaid-v0-8068-v131-mkmlizer: ║ _____ __ __ ║
neversleep-noromaid-v0-8068-v131-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
neversleep-noromaid-v0-8068-v131-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
neversleep-noromaid-v0-8068-v131-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
neversleep-noromaid-v0-8068-v131-mkmlizer: ║ /___/ ║
neversleep-noromaid-v0-8068-v131-mkmlizer: ║ ║
neversleep-noromaid-v0-8068-v131-mkmlizer: ║ Version: 0.8.14 ║
neversleep-noromaid-v0-8068-v131-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
neversleep-noromaid-v0-8068-v131-mkmlizer: ║ https://mk1.ai ║
neversleep-noromaid-v0-8068-v131-mkmlizer: ║ ║
neversleep-noromaid-v0-8068-v131-mkmlizer: ║ The license key for the current software has been verified as ║
neversleep-noromaid-v0-8068-v131-mkmlizer: ║ belonging to: ║
neversleep-noromaid-v0-8068-v131-mkmlizer: ║ ║
neversleep-noromaid-v0-8068-v131-mkmlizer: ║ Chai Research Corp. ║
neversleep-noromaid-v0-8068-v131-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
neversleep-noromaid-v0-8068-v131-mkmlizer: ║ Expiration: 2024-10-15 23:59:59 ║
neversleep-noromaid-v0-8068-v131-mkmlizer: ║ ║
neversleep-noromaid-v0-8068-v131-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
neversleep-noromaid-v0-8068-v131-mkmlizer: Downloaded to shared memory in 87.610s
neversleep-noromaid-v0-8068-v131-mkmlizer: quantizing model to /dev/shm/model_cache
neversleep-noromaid-v0-8068-v131-mkmlizer: Saving flywheel model at /dev/shm/model_cache
neversleep-noromaid-v0-8068-v131-mkmlizer: quantized model in 208.903s
neversleep-noromaid-v0-8068-v131-mkmlizer: Processed model NeverSleep/Noromaid-v0.1-mixtral-8x7b-Instruct-v3 in 296.514s
neversleep-noromaid-v0-8068-v131-mkmlizer: creating bucket guanaco-mkml-models
neversleep-noromaid-v0-8068-v131-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
neversleep-noromaid-v0-8068-v131-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v131
neversleep-noromaid-v0-8068-v131-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v131/config.json
neversleep-noromaid-v0-8068-v131-mkmlizer: cp /dev/shm/model_cache/tokenizer.model s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v131/tokenizer.model
neversleep-noromaid-v0-8068-v131-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v131/tokenizer_config.json
neversleep-noromaid-v0-8068-v131-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v131/special_tokens_map.json
neversleep-noromaid-v0-8068-v131-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v131/tokenizer.json
Connection pool is full, discarding connection: %s
neversleep-noromaid-v0-8068-v131-mkmlizer: cp /dev/shm/model_cache/flywheel_model.3.safetensors s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v131/flywheel_model.3.safetensors
neversleep-noromaid-v0-8068-v131-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v131/flywheel_model.0.safetensors
neversleep-noromaid-v0-8068-v131-mkmlizer: cp /dev/shm/model_cache/flywheel_model.2.safetensors s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v131/flywheel_model.2.safetensors
neversleep-noromaid-v0-8068-v131-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v131/flywheel_model.1.safetensors
neversleep-noromaid-v0-8068-v131-mkmlizer: loading reward model from ChaiML/gpt2_medium_pairwise_60m_step_937500
neversleep-noromaid-v0-8068-v131-mkmlizer: Loading 0: 0%| | 0/995 [00:00<?, ?it/s] Loading 0: 5%|▌ | 52/995 [00:09<02:54, 5.39it/s] Loading 0: 11%|█ | 107/995 [00:10<01:15, 11.70it/s] Loading 0: 16%|█▋ | 162/995 [00:12<00:47, 17.45it/s] Loading 0: 21%|██ | 210/995 [00:13<00:39, 20.07it/s] Loading 0: 27%|██▋ | 265/995 [00:17<00:43, 16.91it/s] Loading 0: 28%|██▊ | 278/995 [00:28<01:45, 6.79it/s] Loading 0: 32%|███▏ | 320/995 [00:35<01:42, 6.55it/s] Loading 0: 37%|███▋ | 368/995 [00:42<01:34, 6.64it/s] Loading 0: 43%|████▎ | 423/995 [00:48<01:18, 7.33it/s] Loading 0: 48%|████▊ | 478/995 [00:50<00:50, 10.27it/s] Loading 0: 53%|█████▎ | 526/995 [00:51<00:35, 13.18it/s] Loading 0: 57%|█████▋ | 564/995 [01:02<00:32, 13.18it/s] Loading 0: 57%|█████▋ | 565/995 [01:02<00:54, 7.89it/s] Loading 0: 58%|█████▊ | 581/995 [01:03<00:50, 8.23it/s] Loading 0: 64%|██████▍ | 636/995 [01:04<00:29, 12.18it/s] Loading 0: 69%|██████▉ | 691/995 [01:05<00:18, 16.83it/s] Loading 0: 74%|███████▍ | 739/995 [01:06<00:12, 20.94it/s] Loading 0: 80%|███████▉ | 794/995 [01:07<00:07, 25.93it/s] Loading 0: 85%|████████▍ | 845/995 [01:18<00:05, 25.93it/s] Loading 0: 85%|████████▌ | 846/995 [01:18<00:13, 11.29it/s] Loading 0: 85%|████████▌ | 849/995 [01:19<00:14, 10.26it/s] Loading 0: 90%|█████████ | 897/995 [01:20<00:06, 14.37it/s] Loading 0: 96%|█████████▌| 952/995 [01:21<00:02, 20.17it/s] Loading 0: 100%|██████████| 995/995 [01:22<00:00, 22.53it/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-v131-mkmlizer: warnings.warn(
neversleep-noromaid-v0-8068-v131-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-v131-mkmlizer: warnings.warn(
neversleep-noromaid-v0-8068-v131-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-v131-mkmlizer: warnings.warn(
neversleep-noromaid-v0-8068-v131-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-v131-mkmlizer: warnings.warn(
neversleep-noromaid-v0-8068-v131-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
neversleep-noromaid-v0-8068-v131-mkmlizer: Saving duration: 0.244s
neversleep-noromaid-v0-8068-v131-mkmlizer: Processed model ChaiML/gpt2_medium_pairwise_60m_step_937500 in 7.112s
neversleep-noromaid-v0-8068-v131-mkmlizer: creating bucket guanaco-reward-models
neversleep-noromaid-v0-8068-v131-mkmlizer: Bucket 's3://guanaco-reward-models/' created
neversleep-noromaid-v0-8068-v131-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/neversleep-noromaid-v0-8068-v131_reward
neversleep-noromaid-v0-8068-v131-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/neversleep-noromaid-v0-8068-v131_reward/special_tokens_map.json
neversleep-noromaid-v0-8068-v131-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/neversleep-noromaid-v0-8068-v131_reward/tokenizer_config.json
neversleep-noromaid-v0-8068-v131-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/neversleep-noromaid-v0-8068-v131_reward/config.json
neversleep-noromaid-v0-8068-v131-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/neversleep-noromaid-v0-8068-v131_reward/merges.txt
neversleep-noromaid-v0-8068-v131-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/neversleep-noromaid-v0-8068-v131_reward/vocab.json
neversleep-noromaid-v0-8068-v131-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/neversleep-noromaid-v0-8068-v131_reward/tokenizer.json
neversleep-noromaid-v0-8068-v131-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/neversleep-noromaid-v0-8068-v131_reward/reward.tensors
Job neversleep-noromaid-v0-8068-v131-mkmlizer completed after 381.88s with status: succeeded
Stopping job with name neversleep-noromaid-v0-8068-v131-mkmlizer
Pipeline stage MKMLizer completed in 383.56s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.12s
Running pipeline stage ISVCDeployer
Creating inference service neversleep-noromaid-v0-8068-v131
Waiting for inference service neversleep-noromaid-v0-8068-v131 to be ready
Inference service neversleep-noromaid-v0-8068-v131 ready after 70.4358823299408s
Pipeline stage ISVCDeployer completed in 77.35s
Running pipeline stage StressChecker
Received healthy response to inference request in 3.2605679035186768s
Received healthy response to inference request in 2.4229049682617188s
Received healthy response to inference request in 2.3699676990509033s
Received healthy response to inference request in 2.286289691925049s
Received healthy response to inference request in 2.1519148349761963s
5 requests
0 failed requests
5th percentile: 2.178789806365967
10th percentile: 2.205664777755737
20th percentile: 2.259414720535278
30th percentile: 2.3030252933502195
40th percentile: 2.3364964962005614
50th percentile: 2.3699676990509033
60th percentile: 2.3911426067352295
70th percentile: 2.4123175144195557
80th percentile: 2.5904375553131107
90th percentile: 2.9255027294158937
95th percentile: 3.093035316467285
99th percentile: 3.2270613861083985
mean time: 2.498329019546509
Pipeline stage StressChecker completed in 13.18s
neversleep-noromaid-v0_8068_v131 status is now deployed due to DeploymentManager action
neversleep-noromaid-v0_8068_v131 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics