submission_id: neversleep-noromaid-v0-_8068_v93
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 plot twist [/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: 2024-07-01T22:41:53+00:00
model_name: neversleep-noromaid-v0-_8068_v93
model_group: NeverSleep/Noromaid-v0.1
num_battles: 11099
num_wins: 5099
celo_rating: 1142.45
propriety_score: 0.7155547155547155
propriety_total_count: 5291.0
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_v93
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: 0.45941075772592127
Resubmit model
Running pipeline stage MKMLizer
Starting job with name neversleep-noromaid-v0-8068-v93-mkmlizer
Waiting for job on neversleep-noromaid-v0-8068-v93-mkmlizer to finish
neversleep-noromaid-v0-8068-v93-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
neversleep-noromaid-v0-8068-v93-mkmlizer: ║ _____ __ __ ║
neversleep-noromaid-v0-8068-v93-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
neversleep-noromaid-v0-8068-v93-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
neversleep-noromaid-v0-8068-v93-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
neversleep-noromaid-v0-8068-v93-mkmlizer: ║ /___/ ║
neversleep-noromaid-v0-8068-v93-mkmlizer: ║ ║
neversleep-noromaid-v0-8068-v93-mkmlizer: ║ Version: 0.8.14 ║
neversleep-noromaid-v0-8068-v93-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
neversleep-noromaid-v0-8068-v93-mkmlizer: ║ https://mk1.ai ║
neversleep-noromaid-v0-8068-v93-mkmlizer: ║ ║
neversleep-noromaid-v0-8068-v93-mkmlizer: ║ The license key for the current software has been verified as ║
neversleep-noromaid-v0-8068-v93-mkmlizer: ║ belonging to: ║
neversleep-noromaid-v0-8068-v93-mkmlizer: ║ ║
neversleep-noromaid-v0-8068-v93-mkmlizer: ║ Chai Research Corp. ║
neversleep-noromaid-v0-8068-v93-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
neversleep-noromaid-v0-8068-v93-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
neversleep-noromaid-v0-8068-v93-mkmlizer: ║ ║
neversleep-noromaid-v0-8068-v93-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
neversleep-noromaid-v0-8068-v93-mkmlizer: Downloaded to shared memory in 135.369s
neversleep-noromaid-v0-8068-v93-mkmlizer: quantizing model to /dev/shm/model_cache
neversleep-noromaid-v0-8068-v93-mkmlizer: Saving flywheel model at /dev/shm/model_cache
neversleep-noromaid-v0-8068-v93-mkmlizer: quantized model in 89.716s
neversleep-noromaid-v0-8068-v93-mkmlizer: Processed model NeverSleep/Noromaid-v0.1-mixtral-8x7b-Instruct-v3 in 225.085s
neversleep-noromaid-v0-8068-v93-mkmlizer: creating bucket guanaco-mkml-models
neversleep-noromaid-v0-8068-v93-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
neversleep-noromaid-v0-8068-v93-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v93
neversleep-noromaid-v0-8068-v93-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v93/special_tokens_map.json
neversleep-noromaid-v0-8068-v93-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v93/config.json
neversleep-noromaid-v0-8068-v93-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v93/tokenizer_config.json
neversleep-noromaid-v0-8068-v93-mkmlizer: cp /dev/shm/model_cache/tokenizer.model s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v93/tokenizer.model
neversleep-noromaid-v0-8068-v93-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v93/tokenizer.json
neversleep-noromaid-v0-8068-v93-mkmlizer: cp /dev/shm/model_cache/flywheel_model.3.safetensors s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v93/flywheel_model.3.safetensors
Connection pool is full, discarding connection: %s
neversleep-noromaid-v0-8068-v93-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v93/flywheel_model.1.safetensors
neversleep-noromaid-v0-8068-v93-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v93/flywheel_model.0.safetensors
neversleep-noromaid-v0-8068-v93-mkmlizer: cp /dev/shm/model_cache/flywheel_model.2.safetensors s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v93/flywheel_model.2.safetensors
neversleep-noromaid-v0-8068-v93-mkmlizer: loading reward model from rirv938/reward_gpt2_medium_preference_24m_e2
neversleep-noromaid-v0-8068-v93-mkmlizer: Loading 0: 0%| | 0/995 [00:00<?, ?it/s] Loading 0: 5%|▌ | 52/995 [00:01<00:18, 49.77it/s] Loading 0: 11%|█ | 107/995 [00:02<00:17, 51.80it/s] Loading 0: 16%|█▋ | 162/995 [00:03<00:15, 53.45it/s] Loading 0: 21%|██ | 210/995 [00:04<00:15, 51.06it/s] Loading 0: 27%|██▋ | 265/995 [00:05<00:13, 53.12it/s] Loading 0: 28%|██▊ | 277/995 [00:23<00:13, 53.12it/s] Loading 0: 28%|██▊ | 278/995 [00:23<02:06, 5.67it/s] Loading 0: 32%|███▏ | 320/995 [00:24<01:25, 7.93it/s] Loading 0: 37%|███▋ | 368/995 [00:25<00:55, 11.22it/s] Loading 0: 43%|████▎ | 423/995 [00:27<00:36, 15.53it/s] Loading 0: 48%|████▊ | 478/995 [00:28<00:25, 19.97it/s] Loading 0: 53%|█████▎ | 526/995 [00:29<00:20, 23.42it/s] Loading 0: 57%|█████▋ | 564/995 [00:47<00:18, 23.42it/s] Loading 0: 57%|█████▋ | 565/995 [00:47<01:03, 6.77it/s] Loading 0: 58%|█████▊ | 581/995 [00:48<00:57, 7.14it/s] Loading 0: 64%|██████▍ | 636/995 [00:49<00:34, 10.48it/s] Loading 0: 69%|██████▉ | 691/995 [00:51<00:20, 14.55it/s] Loading 0: 74%|███████▍ | 739/995 [00:52<00:14, 18.16it/s] Loading 0: 80%|███████▉ | 794/995 [00:53<00:08, 22.84it/s] Loading 0: 85%|████████▍ | 845/995 [01:10<00:06, 22.84it/s] Loading 0: 85%|████████▌ | 846/995 [01:10<00:19, 7.62it/s] Loading 0: 85%|████████▌ | 849/995 [01:11<00:20, 7.14it/s] Loading 0: 90%|█████████ | 897/995 [01:12<00:09, 10.17it/s] Loading 0: 96%|█████████▌| 952/995 [01:14<00:02, 14.47it/s] Loading 0: 100%|██████████| 995/995 [01:15<00:00, 17.08it/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-v93-mkmlizer: warnings.warn(
neversleep-noromaid-v0-8068-v93-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-v93-mkmlizer: warnings.warn(
neversleep-noromaid-v0-8068-v93-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-v93-mkmlizer: warnings.warn(
neversleep-noromaid-v0-8068-v93-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-v93-mkmlizer: warnings.warn(
neversleep-noromaid-v0-8068-v93-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-v93-mkmlizer: return self.fget.__get__(instance, owner)()
neversleep-noromaid-v0-8068-v93-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
neversleep-noromaid-v0-8068-v93-mkmlizer: Saving duration: 1.281s
neversleep-noromaid-v0-8068-v93-mkmlizer: Processed model rirv938/reward_gpt2_medium_preference_24m_e2 in 5.247s
neversleep-noromaid-v0-8068-v93-mkmlizer: creating bucket guanaco-reward-models
neversleep-noromaid-v0-8068-v93-mkmlizer: Bucket 's3://guanaco-reward-models/' created
neversleep-noromaid-v0-8068-v93-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/neversleep-noromaid-v0-8068-v93_reward
neversleep-noromaid-v0-8068-v93-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/neversleep-noromaid-v0-8068-v93_reward/config.json
neversleep-noromaid-v0-8068-v93-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/neversleep-noromaid-v0-8068-v93_reward/tokenizer_config.json
neversleep-noromaid-v0-8068-v93-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/neversleep-noromaid-v0-8068-v93_reward/special_tokens_map.json
neversleep-noromaid-v0-8068-v93-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/neversleep-noromaid-v0-8068-v93_reward/merges.txt
neversleep-noromaid-v0-8068-v93-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/neversleep-noromaid-v0-8068-v93_reward/vocab.json
neversleep-noromaid-v0-8068-v93-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/neversleep-noromaid-v0-8068-v93_reward/tokenizer.json
neversleep-noromaid-v0-8068-v93-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/neversleep-noromaid-v0-8068-v93_reward/reward.tensors
Connection pool is full, discarding connection: %s
Connection pool is full, discarding connection: %s
Job neversleep-noromaid-v0-8068-v93-mkmlizer completed after 319.99s with status: succeeded
Stopping job with name neversleep-noromaid-v0-8068-v93-mkmlizer
Pipeline stage MKMLizer completed in 320.97s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.13s
Running pipeline stage ISVCDeployer
Creating inference service neversleep-noromaid-v0-8068-v93
Waiting for inference service neversleep-noromaid-v0-8068-v93 to be ready
Inference service neversleep-noromaid-v0-8068-v93 ready after 60.38266038894653s
Pipeline stage ISVCDeployer completed in 67.37s
Running pipeline stage StressChecker
Received healthy response to inference request in 3.0776355266571045s
Received healthy response to inference request in 2.3321216106414795s
Received healthy response to inference request in 2.389770269393921s
Received healthy response to inference request in 2.236060619354248s
Received healthy response to inference request in 2.265974760055542s
5 requests
0 failed requests
5th percentile: 2.242043447494507
10th percentile: 2.2480262756347655
20th percentile: 2.259991931915283
30th percentile: 2.2792041301727295
40th percentile: 2.3056628704071045
50th percentile: 2.3321216106414795
60th percentile: 2.355181074142456
70th percentile: 2.378240537643433
80th percentile: 2.527343320846558
90th percentile: 2.802489423751831
95th percentile: 2.9400624752044675
99th percentile: 3.050120916366577
mean time: 2.460312557220459
Pipeline stage StressChecker completed in 13.12s
neversleep-noromaid-v0-_8068_v93 status is now deployed due to DeploymentManager action
neversleep-noromaid-v0-_8068_v93 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics