submission_id: neversleep-noromaid-v0_8068_v105
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] describe the scene [/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: 2024-07-02T02:58:58+00:00
model_name: neversleep-noromaid-v0_8068_v105
model_group: NeverSleep/Noromaid-v0.1
num_battles: 11174
num_wins: 4726
celo_rating: 1120.45
propriety_score: 0.7341328413284133
propriety_total_count: 5420.0
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_v105
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: 0.4229461249328799
Resubmit model
Running pipeline stage MKMLizer
Starting job with name neversleep-noromaid-v0-8068-v105-mkmlizer
Waiting for job on neversleep-noromaid-v0-8068-v105-mkmlizer to finish
neversleep-noromaid-v0-8068-v105-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
neversleep-noromaid-v0-8068-v105-mkmlizer: ║ _____ __ __ ║
neversleep-noromaid-v0-8068-v105-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
neversleep-noromaid-v0-8068-v105-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
neversleep-noromaid-v0-8068-v105-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
neversleep-noromaid-v0-8068-v105-mkmlizer: ║ /___/ ║
neversleep-noromaid-v0-8068-v105-mkmlizer: ║ ║
neversleep-noromaid-v0-8068-v105-mkmlizer: ║ Version: 0.8.14 ║
neversleep-noromaid-v0-8068-v105-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
neversleep-noromaid-v0-8068-v105-mkmlizer: ║ https://mk1.ai ║
neversleep-noromaid-v0-8068-v105-mkmlizer: ║ ║
neversleep-noromaid-v0-8068-v105-mkmlizer: ║ The license key for the current software has been verified as ║
neversleep-noromaid-v0-8068-v105-mkmlizer: ║ belonging to: ║
neversleep-noromaid-v0-8068-v105-mkmlizer: ║ ║
neversleep-noromaid-v0-8068-v105-mkmlizer: ║ Chai Research Corp. ║
neversleep-noromaid-v0-8068-v105-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
neversleep-noromaid-v0-8068-v105-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
neversleep-noromaid-v0-8068-v105-mkmlizer: ║ ║
neversleep-noromaid-v0-8068-v105-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
neversleep-noromaid-v0-8068-v105-mkmlizer: quantized model in 83.599s
neversleep-noromaid-v0-8068-v105-mkmlizer: Processed model NeverSleep/Noromaid-v0.1-mixtral-8x7b-Instruct-v3 in 192.664s
neversleep-noromaid-v0-8068-v105-mkmlizer: creating bucket guanaco-mkml-models
neversleep-noromaid-v0-8068-v105-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
neversleep-noromaid-v0-8068-v105-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v105
neversleep-noromaid-v0-8068-v105-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v105/special_tokens_map.json
neversleep-noromaid-v0-8068-v105-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v105/tokenizer_config.json
neversleep-noromaid-v0-8068-v105-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v105/config.json
neversleep-noromaid-v0-8068-v105-mkmlizer: cp /dev/shm/model_cache/tokenizer.model s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v105/tokenizer.model
neversleep-noromaid-v0-8068-v105-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v105/tokenizer.json
neversleep-noromaid-v0-8068-v105-mkmlizer: cp /dev/shm/model_cache/flywheel_model.3.safetensors s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v105/flywheel_model.3.safetensors
neversleep-noromaid-v0-8068-v105-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v105/flywheel_model.0.safetensors
neversleep-noromaid-v0-8068-v105-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v105/flywheel_model.1.safetensors
neversleep-noromaid-v0-8068-v105-mkmlizer: cp /dev/shm/model_cache/flywheel_model.2.safetensors s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v105/flywheel_model.2.safetensors
neversleep-noromaid-v0-8068-v105-mkmlizer: loading reward model from rirv938/reward_gpt2_medium_preference_24m_e2
neversleep-noromaid-v0-8068-v105-mkmlizer: Loading 0: 0%| | 0/995 [00:00<?, ?it/s] Loading 0: 5%|▌ | 52/995 [00:01<00:22, 42.54it/s] Loading 0: 11%|█ | 107/995 [00:02<00:19, 44.59it/s] Loading 0: 16%|█▋ | 162/995 [00:03<00:18, 44.10it/s] Loading 0: 21%|██ | 210/995 [00:04<00:18, 42.83it/s] Loading 0: 27%|██▋ | 265/995 [00:05<00:16, 45.18it/s] Loading 0: 28%|██▊ | 277/995 [00:22<00:15, 45.18it/s] Loading 0: 28%|██▊ | 278/995 [00:22<01:55, 6.19it/s] Loading 0: 32%|███▏ | 320/995 [00:23<01:19, 8.54it/s] Loading 0: 37%|███▋ | 368/995 [00:24<00:52, 11.98it/s] Loading 0: 43%|████▎ | 423/995 [00:25<00:34, 16.59it/s] Loading 0: 48%|████▊ | 478/995 [00:27<00:24, 21.43it/s] Loading 0: 53%|█████▎ | 526/995 [00:28<00:18, 25.07it/s] Loading 0: 57%|█████▋ | 564/995 [00:44<00:17, 25.07it/s] Loading 0: 57%|█████▋ | 565/995 [00:44<01:00, 7.14it/s] Loading 0: 58%|█████▊ | 581/995 [00:46<00:55, 7.52it/s] Loading 0: 64%|██████▍ | 636/995 [00:47<00:31, 11.29it/s] Loading 0: 69%|██████▉ | 691/995 [00:48<00:19, 15.57it/s] Loading 0: 74%|███████▍ | 739/995 [00:49<00:13, 19.48it/s] Loading 0: 80%|███████▉ | 794/995 [00:50<00:08, 24.54it/s] Loading 0: 85%|████████▍ | 845/995 [01:07<00:06, 24.54it/s] Loading 0: 85%|████████▌ | 846/995 [01:07<00:19, 7.77it/s] Loading 0: 85%|████████▌ | 849/995 [01:08<00:20, 7.26it/s] Loading 0: 90%|█████████ | 897/995 [01:10<00:09, 10.12it/s] Loading 0: 96%|█████████▌| 952/995 [01:11<00:02, 14.36it/s] Loading 0: 100%|██████████| 995/995 [01:12<00:00, 17.30it/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-v105-mkmlizer: warnings.warn(
neversleep-noromaid-v0-8068-v105-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-v105-mkmlizer: warnings.warn(
neversleep-noromaid-v0-8068-v105-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-v105-mkmlizer: warnings.warn(
neversleep-noromaid-v0-8068-v105-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-v105-mkmlizer: warnings.warn(
neversleep-noromaid-v0-8068-v105-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-v105-mkmlizer: return self.fget.__get__(instance, owner)()
neversleep-noromaid-v0-8068-v105-mkmlizer: creating bucket guanaco-reward-models
neversleep-noromaid-v0-8068-v105-mkmlizer: Bucket 's3://guanaco-reward-models/' created
neversleep-noromaid-v0-8068-v105-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/neversleep-noromaid-v0-8068-v105_reward
neversleep-noromaid-v0-8068-v105-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/neversleep-noromaid-v0-8068-v105_reward/config.json
neversleep-noromaid-v0-8068-v105-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/neversleep-noromaid-v0-8068-v105_reward/merges.txt
neversleep-noromaid-v0-8068-v105-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/neversleep-noromaid-v0-8068-v105_reward/vocab.json
neversleep-noromaid-v0-8068-v105-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/neversleep-noromaid-v0-8068-v105_reward/special_tokens_map.json
neversleep-noromaid-v0-8068-v105-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/neversleep-noromaid-v0-8068-v105_reward/tokenizer_config.json
neversleep-noromaid-v0-8068-v105-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/neversleep-noromaid-v0-8068-v105_reward/tokenizer.json
neversleep-noromaid-v0-8068-v105-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/neversleep-noromaid-v0-8068-v105_reward/reward.tensors
Job neversleep-noromaid-v0-8068-v105-mkmlizer completed after 237.62s with status: succeeded
Stopping job with name neversleep-noromaid-v0-8068-v105-mkmlizer
Pipeline stage MKMLizer completed in 238.45s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.10s
Running pipeline stage ISVCDeployer
Creating inference service neversleep-noromaid-v0-8068-v105
Waiting for inference service neversleep-noromaid-v0-8068-v105 to be ready
Inference service neversleep-noromaid-v0-8068-v105 ready after 120.53569602966309s
Pipeline stage ISVCDeployer completed in 127.53s
Running pipeline stage StressChecker
Failed to get response for submission mistralai-mixtral-8x7b-_3473_v33: ('http://mistralai-mixtral-8x7b-3473-v33-predictor-default.tenant-chaiml-guanaco.knative.ord1.coreweave.cloud/v1/models/GPT-J-6B-lit-v2:predict', 'read tcp 127.0.0.1:60662->127.0.0.1:8080: read: connection reset by peer\n')
Received healthy response to inference request in 5.931465148925781s
Received healthy response to inference request in 13.561484098434448s
Received healthy response to inference request in 2.4315383434295654s
Received healthy response to inference request in 2.3805336952209473s
Received healthy response to inference request in 2.3906314373016357s
5 requests
0 failed requests
5th percentile: 2.382553243637085
10th percentile: 2.3845727920532225
20th percentile: 2.388611888885498
30th percentile: 2.3988128185272215
40th percentile: 2.4151755809783935
50th percentile: 2.4315383434295654
60th percentile: 3.8315090656280515
70th percentile: 5.2314797878265376
80th percentile: 7.457468938827516
90th percentile: 10.509476518630983
95th percentile: 12.035480308532714
99th percentile: 13.256283340454102
mean time: 5.339130544662476
%s, retrying in %s seconds...
Received healthy response to inference request in 2.4351680278778076s
Received healthy response to inference request in 2.440803050994873s
Received healthy response to inference request in 2.464014768600464s
Received healthy response to inference request in 2.429478883743286s
Received healthy response to inference request in 2.43485689163208s
5 requests
0 failed requests
5th percentile: 2.430554485321045
10th percentile: 2.431630086898804
20th percentile: 2.433781290054321
30th percentile: 2.4349191188812256
40th percentile: 2.4350435733795166
50th percentile: 2.4351680278778076
60th percentile: 2.437422037124634
70th percentile: 2.43967604637146
80th percentile: 2.4454453945159913
90th percentile: 2.4547300815582274
95th percentile: 2.4593724250793456
99th percentile: 2.4630862998962404
mean time: 2.440864324569702
Pipeline stage StressChecker completed in 40.26s
neversleep-noromaid-v0_8068_v105 status is now deployed due to DeploymentManager action
neversleep-noromaid-v0_8068_v105 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics