submission_id: neversleep-noromaid-v0_8068_v129
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 drama [/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: 2024-07-11T20:10:57+00:00
model_name: neversleep-noromaid-v0_8068_v129
model_group: NeverSleep/Noromaid-v0.1
num_battles: 35735
num_wins: 15401
celo_rating: 1146.98
alignment_score: None
alignment_samples: 0
propriety_score: 0.7259296994396333
propriety_total_count: 5889.0
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_v129
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: 0.4309780327410102
preference_data_url: None
Resubmit model
Running pipeline stage MKMLizer
Starting job with name neversleep-noromaid-v0-8068-v129-mkmlizer
Waiting for job on neversleep-noromaid-v0-8068-v129-mkmlizer to finish
neversleep-noromaid-v0-8068-v129-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
neversleep-noromaid-v0-8068-v129-mkmlizer: ║ _____ __ __ ║
neversleep-noromaid-v0-8068-v129-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
neversleep-noromaid-v0-8068-v129-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
neversleep-noromaid-v0-8068-v129-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
neversleep-noromaid-v0-8068-v129-mkmlizer: ║ /___/ ║
neversleep-noromaid-v0-8068-v129-mkmlizer: ║ ║
neversleep-noromaid-v0-8068-v129-mkmlizer: ║ Version: 0.8.14 ║
neversleep-noromaid-v0-8068-v129-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
neversleep-noromaid-v0-8068-v129-mkmlizer: ║ https://mk1.ai ║
neversleep-noromaid-v0-8068-v129-mkmlizer: ║ ║
neversleep-noromaid-v0-8068-v129-mkmlizer: ║ The license key for the current software has been verified as ║
neversleep-noromaid-v0-8068-v129-mkmlizer: ║ belonging to: ║
neversleep-noromaid-v0-8068-v129-mkmlizer: ║ ║
neversleep-noromaid-v0-8068-v129-mkmlizer: ║ Chai Research Corp. ║
neversleep-noromaid-v0-8068-v129-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
neversleep-noromaid-v0-8068-v129-mkmlizer: ║ Expiration: 2024-10-15 23:59:59 ║
neversleep-noromaid-v0-8068-v129-mkmlizer: ║ ║
neversleep-noromaid-v0-8068-v129-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
neversleep-noromaid-v0-8068-v129-mkmlizer: Downloaded to shared memory in 136.855s
neversleep-noromaid-v0-8068-v129-mkmlizer: quantizing model to /dev/shm/model_cache
neversleep-noromaid-v0-8068-v129-mkmlizer: Saving flywheel model at /dev/shm/model_cache
neversleep-noromaid-v0-8068-v129-mkmlizer: quantized model in 103.573s
neversleep-noromaid-v0-8068-v129-mkmlizer: Processed model NeverSleep/Noromaid-v0.1-mixtral-8x7b-Instruct-v3 in 240.428s
neversleep-noromaid-v0-8068-v129-mkmlizer: creating bucket guanaco-mkml-models
neversleep-noromaid-v0-8068-v129-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
neversleep-noromaid-v0-8068-v129-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v129
neversleep-noromaid-v0-8068-v129-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v129/config.json
neversleep-noromaid-v0-8068-v129-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v129/special_tokens_map.json
neversleep-noromaid-v0-8068-v129-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v129/tokenizer_config.json
neversleep-noromaid-v0-8068-v129-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v129/tokenizer.json
neversleep-noromaid-v0-8068-v129-mkmlizer: cp /dev/shm/model_cache/tokenizer.model s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v129/tokenizer.model
neversleep-noromaid-v0-8068-v129-mkmlizer: cp /dev/shm/model_cache/flywheel_model.3.safetensors s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v129/flywheel_model.3.safetensors
neversleep-noromaid-v0-8068-v129-mkmlizer: cp /dev/shm/model_cache/flywheel_model.2.safetensors s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v129/flywheel_model.2.safetensors
neversleep-noromaid-v0-8068-v129-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v129/flywheel_model.1.safetensors
neversleep-noromaid-v0-8068-v129-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v129/flywheel_model.0.safetensors
neversleep-noromaid-v0-8068-v129-mkmlizer: loading reward model from ChaiML/gpt2_medium_pairwise_60m_step_937500
neversleep-noromaid-v0-8068-v129-mkmlizer: Loading 0: 0%| | 0/995 [00:00<?, ?it/s] Loading 0: 5%|▌ | 52/995 [00:01<00:25, 37.59it/s] Loading 0: 11%|█ | 107/995 [00:02<00:23, 38.57it/s] Loading 0: 16%|█▋ | 162/995 [00:04<00:21, 39.13it/s] Loading 0: 21%|██ | 210/995 [00:05<00:20, 37.54it/s] Loading 0: 27%|██▋ | 265/995 [00:06<00:18, 38.92it/s] Loading 0: 28%|██▊ | 277/995 [00:20<00:18, 38.92it/s] Loading 0: 28%|██▊ | 278/995 [00:27<02:22, 5.02it/s] Loading 0: 32%|███▏ | 320/995 [00:28<01:36, 6.97it/s] Loading 0: 37%|███▋ | 368/995 [00:30<01:05, 9.64it/s] Loading 0: 43%|████▎ | 423/995 [00:31<00:42, 13.51it/s] Loading 0: 48%|████▊ | 478/995 [00:33<00:29, 17.51it/s] Loading 0: 53%|█████▎ | 526/995 [00:34<00:22, 20.80it/s] Loading 0: 57%|█████▋ | 564/995 [00:47<00:20, 20.80it/s] Loading 0: 57%|█████▋ | 565/995 [00:54<01:14, 5.79it/s] Loading 0: 58%|█████▊ | 581/995 [00:56<01:07, 6.13it/s] Loading 0: 64%|██████▍ | 636/995 [00:57<00:38, 9.24it/s] Loading 0: 69%|██████▉ | 691/995 [00:59<00:23, 12.89it/s] Loading 0: 74%|███████▍ | 739/995 [01:00<00:15, 16.14it/s] Loading 0: 80%|███████▉ | 794/995 [01:01<00:09, 20.32it/s] Loading 0: 85%|████████▍ | 845/995 [01:14<00:07, 20.32it/s] Loading 0: 85%|████████▌ | 846/995 [01:22<00:23, 6.28it/s] Loading 0: 85%|████████▌ | 849/995 [01:24<00:24, 5.96it/s] Loading 0: 90%|█████████ | 897/995 [01:25<00:11, 8.55it/s] Loading 0: 96%|█████████▌| 952/995 [01:26<00:03, 12.17it/s] Loading 0: 100%|██████████| 995/995 [01:28<00:00, 14.29it/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-v129-mkmlizer: warnings.warn(
neversleep-noromaid-v0-8068-v129-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-v129-mkmlizer: warnings.warn(
neversleep-noromaid-v0-8068-v129-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-v129-mkmlizer: warnings.warn(
neversleep-noromaid-v0-8068-v129-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-v129-mkmlizer: warnings.warn(
neversleep-noromaid-v0-8068-v129-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
neversleep-noromaid-v0-8068-v129-mkmlizer: Saving duration: 0.506s
neversleep-noromaid-v0-8068-v129-mkmlizer: Processed model ChaiML/gpt2_medium_pairwise_60m_step_937500 in 4.882s
neversleep-noromaid-v0-8068-v129-mkmlizer: creating bucket guanaco-reward-models
neversleep-noromaid-v0-8068-v129-mkmlizer: Bucket 's3://guanaco-reward-models/' created
neversleep-noromaid-v0-8068-v129-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/neversleep-noromaid-v0-8068-v129_reward
neversleep-noromaid-v0-8068-v129-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/neversleep-noromaid-v0-8068-v129_reward/config.json
neversleep-noromaid-v0-8068-v129-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/neversleep-noromaid-v0-8068-v129_reward/tokenizer_config.json
neversleep-noromaid-v0-8068-v129-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/neversleep-noromaid-v0-8068-v129_reward/special_tokens_map.json
neversleep-noromaid-v0-8068-v129-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/neversleep-noromaid-v0-8068-v129_reward/merges.txt
neversleep-noromaid-v0-8068-v129-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/neversleep-noromaid-v0-8068-v129_reward/vocab.json
neversleep-noromaid-v0-8068-v129-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/neversleep-noromaid-v0-8068-v129_reward/tokenizer.json
neversleep-noromaid-v0-8068-v129-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/neversleep-noromaid-v0-8068-v129_reward/reward.tensors
Job neversleep-noromaid-v0-8068-v129-mkmlizer completed after 290.39s with status: succeeded
Stopping job with name neversleep-noromaid-v0-8068-v129-mkmlizer
Pipeline stage MKMLizer completed in 291.32s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.10s
Running pipeline stage ISVCDeployer
Creating inference service neversleep-noromaid-v0-8068-v129
Waiting for inference service neversleep-noromaid-v0-8068-v129 to be ready
Inference service neversleep-noromaid-v0-8068-v129 ready after 70.37341618537903s
Pipeline stage ISVCDeployer completed in 77.39s
Running pipeline stage StressChecker
Received healthy response to inference request in 3.377501964569092s
Received healthy response to inference request in 2.2766594886779785s
Received healthy response to inference request in 2.411278486251831s
Received healthy response to inference request in 2.4011316299438477s
Received healthy response to inference request in 2.1855740547180176s
5 requests
0 failed requests
5th percentile: 2.2037911415100098
10th percentile: 2.222008228302002
20th percentile: 2.2584424018859863
30th percentile: 2.3015539169311525
40th percentile: 2.3513427734375
50th percentile: 2.4011316299438477
60th percentile: 2.405190372467041
70th percentile: 2.409249114990234
80th percentile: 2.604523181915283
90th percentile: 2.9910125732421875
95th percentile: 3.1842572689056396
99th percentile: 3.3388530254364013
mean time: 2.5304291248321533
Pipeline stage StressChecker completed in 13.43s
neversleep-noromaid-v0_8068_v129 status is now deployed due to DeploymentManager action
neversleep-noromaid-v0_8068_v129 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics