submission_id: neversleep-noromaid-v0_8068_v108
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 something unexpected [/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: 2024-07-02T03:22:33+00:00
model_name: neversleep-noromaid-v0_8068_v108
model_group: NeverSleep/Noromaid-v0.1
num_battles: 12745
num_wins: 5963
celo_rating: 1152.13
propriety_score: 0.7175292153589315
propriety_total_count: 5990.0
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_v108
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: 0.46786975284425264
Resubmit model
Running pipeline stage MKMLizer
Starting job with name neversleep-noromaid-v0-8068-v108-mkmlizer
Waiting for job on neversleep-noromaid-v0-8068-v108-mkmlizer to finish
neversleep-noromaid-v0-8068-v108-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
neversleep-noromaid-v0-8068-v108-mkmlizer: ║ _____ __ __ ║
neversleep-noromaid-v0-8068-v108-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
neversleep-noromaid-v0-8068-v108-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
neversleep-noromaid-v0-8068-v108-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
neversleep-noromaid-v0-8068-v108-mkmlizer: ║ /___/ ║
neversleep-noromaid-v0-8068-v108-mkmlizer: ║ ║
neversleep-noromaid-v0-8068-v108-mkmlizer: ║ Version: 0.8.14 ║
neversleep-noromaid-v0-8068-v108-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
neversleep-noromaid-v0-8068-v108-mkmlizer: ║ https://mk1.ai ║
neversleep-noromaid-v0-8068-v108-mkmlizer: ║ ║
neversleep-noromaid-v0-8068-v108-mkmlizer: ║ The license key for the current software has been verified as ║
neversleep-noromaid-v0-8068-v108-mkmlizer: ║ belonging to: ║
neversleep-noromaid-v0-8068-v108-mkmlizer: ║ ║
neversleep-noromaid-v0-8068-v108-mkmlizer: ║ Chai Research Corp. ║
neversleep-noromaid-v0-8068-v108-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
neversleep-noromaid-v0-8068-v108-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
neversleep-noromaid-v0-8068-v108-mkmlizer: ║ ║
neversleep-noromaid-v0-8068-v108-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
neversleep-noromaid-v0-8068-v108-mkmlizer: Downloaded to shared memory in 206.245s
neversleep-noromaid-v0-8068-v108-mkmlizer: quantizing model to /dev/shm/model_cache
neversleep-noromaid-v0-8068-v108-mkmlizer: Saving flywheel model at /dev/shm/model_cache
neversleep-noromaid-v0-8068-v108-mkmlizer: quantized model in 148.119s
neversleep-noromaid-v0-8068-v108-mkmlizer: Processed model NeverSleep/Noromaid-v0.1-mixtral-8x7b-Instruct-v3 in 354.364s
neversleep-noromaid-v0-8068-v108-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
neversleep-noromaid-v0-8068-v108-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v108
neversleep-noromaid-v0-8068-v108-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v108/config.json
neversleep-noromaid-v0-8068-v108-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v108/tokenizer_config.json
neversleep-noromaid-v0-8068-v108-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v108/special_tokens_map.json
neversleep-noromaid-v0-8068-v108-mkmlizer: cp /dev/shm/model_cache/tokenizer.model s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v108/tokenizer.model
neversleep-noromaid-v0-8068-v108-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v108/tokenizer.json
neversleep-noromaid-v0-8068-v108-mkmlizer: cp /dev/shm/model_cache/flywheel_model.3.safetensors s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v108/flywheel_model.3.safetensors
neversleep-noromaid-v0-8068-v108-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v108/flywheel_model.0.safetensors
neversleep-noromaid-v0-8068-v108-mkmlizer: cp /dev/shm/model_cache/flywheel_model.2.safetensors s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v108/flywheel_model.2.safetensors
neversleep-noromaid-v0-8068-v108-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v108/flywheel_model.1.safetensors
neversleep-noromaid-v0-8068-v108-mkmlizer: loading reward model from rirv938/reward_gpt2_medium_preference_24m_e2
neversleep-noromaid-v0-8068-v108-mkmlizer: Loading 0: 0%| | 0/995 [00:00<?, ?it/s] Loading 0: 5%|▌ | 52/995 [00:04<01:28, 10.63it/s] Loading 0: 11%|█ | 107/995 [00:10<01:30, 9.82it/s] Loading 0: 16%|█▋ | 162/995 [00:15<01:21, 10.26it/s] Loading 0: 21%|██ | 210/995 [00:18<01:01, 12.73it/s] Loading 0: 27%|██▋ | 265/995 [00:19<00:40, 17.85it/s] Loading 0: 28%|██▊ | 277/995 [00:30<00:40, 17.85it/s] Loading 0: 28%|██▊ | 278/995 [00:38<02:33, 4.68it/s] Loading 0: 32%|███▏ | 320/995 [00:44<02:10, 5.16it/s] Loading 0: 37%|███▋ | 368/995 [00:51<01:51, 5.64it/s] Loading 0: 43%|████▎ | 423/995 [00:57<01:25, 6.69it/s] Loading 0: 48%|████▊ | 478/995 [00:59<00:59, 8.74it/s] Loading 0: 53%|█████▎ | 526/995 [01:02<00:45, 10.28it/s] Loading 0: 57%|█████▋ | 564/995 [01:22<00:41, 10.28it/s] Loading 0: 57%|█████▋ | 565/995 [01:22<01:26, 4.99it/s] Loading 0: 58%|█████▊ | 581/995 [01:24<01:21, 5.07it/s] Loading 0: 64%|██████▍ | 636/995 [01:27<00:49, 7.21it/s] Loading 0: 69%|██████▉ | 691/995 [01:30<00:32, 9.50it/s] Loading 0: 74%|███████▍ | 739/995 [01:32<00:22, 11.27it/s] Loading 0: 80%|███████▉ | 794/995 [01:36<00:16, 11.99it/s] Loading 0: 85%|████████▍ | 845/995 [01:55<00:12, 11.99it/s] Loading 0: 85%|████████▌ | 846/995 [01:55<00:25, 5.77it/s] Loading 0: 85%|████████▌ | 849/995 [02:00<00:30, 4.74it/s] Loading 0: 90%|█████████ | 897/995 [02:05<00:16, 5.83it/s] Loading 0: 96%|█████████▌| 952/995 [02:09<00:05, 7.45it/s] Loading 0: 100%|██████████| 995/995 [02:11<00:00, 9.59it/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-v108-mkmlizer: warnings.warn(
neversleep-noromaid-v0-8068-v108-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-v108-mkmlizer: warnings.warn(
neversleep-noromaid-v0-8068-v108-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-v108-mkmlizer: warnings.warn(
neversleep-noromaid-v0-8068-v108-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-v108-mkmlizer: warnings.warn(
neversleep-noromaid-v0-8068-v108-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-v108-mkmlizer: return self.fget.__get__(instance, owner)()
neversleep-noromaid-v0-8068-v108-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
neversleep-noromaid-v0-8068-v108-mkmlizer: Bucket 's3://guanaco-reward-models/' created
neversleep-noromaid-v0-8068-v108-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/neversleep-noromaid-v0-8068-v108_reward
neversleep-noromaid-v0-8068-v108-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/neversleep-noromaid-v0-8068-v108_reward/tokenizer_config.json
neversleep-noromaid-v0-8068-v108-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/neversleep-noromaid-v0-8068-v108_reward/config.json
neversleep-noromaid-v0-8068-v108-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/neversleep-noromaid-v0-8068-v108_reward/special_tokens_map.json
neversleep-noromaid-v0-8068-v108-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/neversleep-noromaid-v0-8068-v108_reward/merges.txt
neversleep-noromaid-v0-8068-v108-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/neversleep-noromaid-v0-8068-v108_reward/vocab.json
neversleep-noromaid-v0-8068-v108-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/neversleep-noromaid-v0-8068-v108_reward/tokenizer.json
neversleep-noromaid-v0-8068-v108-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/neversleep-noromaid-v0-8068-v108_reward/reward.tensors
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
Connection pool is full, discarding connection: %s
Job neversleep-noromaid-v0-8068-v108-mkmlizer completed after 604.44s with status: succeeded
Stopping job with name neversleep-noromaid-v0-8068-v108-mkmlizer
Pipeline stage MKMLizer completed in 605.26s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.09s
Running pipeline stage ISVCDeployer
Creating inference service neversleep-noromaid-v0-8068-v108
Waiting for inference service neversleep-noromaid-v0-8068-v108 to be ready
Inference service neversleep-noromaid-v0-8068-v108 ready after 70.3077163696289s
Pipeline stage ISVCDeployer completed in 77.00s
Running pipeline stage StressChecker
Received healthy response to inference request in 3.305025100708008s
Received healthy response to inference request in 2.341965675354004s
Received healthy response to inference request in 2.451584577560425s
Received healthy response to inference request in 2.2881107330322266s
Received healthy response to inference request in 2.4259557723999023s
5 requests
0 failed requests
5th percentile: 2.298881721496582
10th percentile: 2.3096527099609374
20th percentile: 2.3311946868896483
30th percentile: 2.3587636947631836
40th percentile: 2.392359733581543
50th percentile: 2.4259557723999023
60th percentile: 2.4362072944641113
70th percentile: 2.4464588165283203
80th percentile: 2.6222726821899416
90th percentile: 2.9636488914489747
95th percentile: 3.134336996078491
99th percentile: 3.2708874797821044
mean time: 2.562528371810913
Pipeline stage StressChecker completed in 13.40s
neversleep-noromaid-v0_8068_v108 status is now deployed due to DeploymentManager action
neversleep-noromaid-v0_8068_v108 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics