submission_id: neversleep-noromaid-v0-_8068_v89
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': '{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: 2024-07-01T21:49:00+00:00
model_name: neversleep-noromaid-v0-_8068_v89
model_group: NeverSleep/Noromaid-v0.1
num_battles: 15243
num_wins: 8079
celo_rating: 1173.63
propriety_score: 0.7166956090300174
propriety_total_count: 20155.0
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_v89
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: 0.5300137768155875
Resubmit model
Running pipeline stage MKMLizer
Starting job with name neversleep-noromaid-v0-8068-v89-mkmlizer
Waiting for job on neversleep-noromaid-v0-8068-v89-mkmlizer to finish
neversleep-noromaid-v0-8068-v89-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
neversleep-noromaid-v0-8068-v89-mkmlizer: ║ _____ __ __ ║
neversleep-noromaid-v0-8068-v89-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
neversleep-noromaid-v0-8068-v89-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
neversleep-noromaid-v0-8068-v89-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
neversleep-noromaid-v0-8068-v89-mkmlizer: ║ /___/ ║
neversleep-noromaid-v0-8068-v89-mkmlizer: ║ ║
neversleep-noromaid-v0-8068-v89-mkmlizer: ║ Version: 0.8.14 ║
neversleep-noromaid-v0-8068-v89-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
neversleep-noromaid-v0-8068-v89-mkmlizer: ║ https://mk1.ai ║
neversleep-noromaid-v0-8068-v89-mkmlizer: ║ ║
neversleep-noromaid-v0-8068-v89-mkmlizer: ║ The license key for the current software has been verified as ║
neversleep-noromaid-v0-8068-v89-mkmlizer: ║ belonging to: ║
neversleep-noromaid-v0-8068-v89-mkmlizer: ║ ║
neversleep-noromaid-v0-8068-v89-mkmlizer: ║ Chai Research Corp. ║
neversleep-noromaid-v0-8068-v89-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
neversleep-noromaid-v0-8068-v89-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
neversleep-noromaid-v0-8068-v89-mkmlizer: ║ ║
neversleep-noromaid-v0-8068-v89-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
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
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
neversleep-noromaid-v0-8068-v89-mkmlizer: Downloaded to shared memory in 125.852s
neversleep-noromaid-v0-8068-v89-mkmlizer: quantizing model to /dev/shm/model_cache
neversleep-noromaid-v0-8068-v89-mkmlizer: Saving flywheel model at /dev/shm/model_cache
neversleep-noromaid-v0-8068-v89-mkmlizer: quantized model in 193.461s
neversleep-noromaid-v0-8068-v89-mkmlizer: Processed model NeverSleep/Noromaid-v0.1-mixtral-8x7b-Instruct-v3 in 319.313s
neversleep-noromaid-v0-8068-v89-mkmlizer: creating bucket guanaco-mkml-models
neversleep-noromaid-v0-8068-v89-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
neversleep-noromaid-v0-8068-v89-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v89
neversleep-noromaid-v0-8068-v89-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v89/config.json
neversleep-noromaid-v0-8068-v89-mkmlizer: cp /dev/shm/model_cache/tokenizer.model s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v89/tokenizer.model
neversleep-noromaid-v0-8068-v89-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v89/tokenizer.json
neversleep-noromaid-v0-8068-v89-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v89/tokenizer_config.json
neversleep-noromaid-v0-8068-v89-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v89/special_tokens_map.json
neversleep-noromaid-v0-8068-v89-mkmlizer: cp /dev/shm/model_cache/flywheel_model.3.safetensors s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v89/flywheel_model.3.safetensors
neversleep-noromaid-v0-8068-v89-mkmlizer: cp /dev/shm/model_cache/flywheel_model.2.safetensors s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v89/flywheel_model.2.safetensors
neversleep-noromaid-v0-8068-v89-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v89/flywheel_model.0.safetensors
neversleep-noromaid-v0-8068-v89-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v89/flywheel_model.1.safetensors
neversleep-noromaid-v0-8068-v89-mkmlizer: loading reward model from rirv938/reward_gpt2_medium_preference_24m_e2
neversleep-noromaid-v0-8068-v89-mkmlizer: Loading 0: 0%| | 0/995 [00:00<?, ?it/s] Loading 0: 5%|▌ | 52/995 [00:01<00:25, 37.27it/s] Loading 0: 11%|█ | 107/995 [00:02<00:22, 40.20it/s] Loading 0: 16%|█▋ | 162/995 [00:03<00:19, 41.96it/s] Loading 0: 21%|██ | 210/995 [00:05<00:19, 39.71it/s] Loading 0: 27%|██▋ | 265/995 [00:06<00:17, 41.11it/s] Loading 0: 28%|██▊ | 277/995 [00:17<00:17, 41.11it/s] Loading 0: 28%|██▊ | 278/995 [00:23<02:03, 5.83it/s] Loading 0: 32%|███▏ | 320/995 [00:30<01:51, 6.06it/s] Loading 0: 37%|███▋ | 368/995 [00:31<01:12, 8.64it/s] Loading 0: 43%|████▎ | 423/995 [00:32<00:46, 12.22it/s] Loading 0: 48%|████▊ | 478/995 [00:34<00:32, 15.67it/s] Loading 0: 53%|█████▎ | 526/995 [00:35<00:24, 19.09it/s] Loading 0: 57%|█████▋ | 564/995 [00:53<00:22, 19.09it/s] Loading 0: 57%|█████▋ | 565/995 [00:53<01:06, 6.49it/s] Loading 0: 58%|█████▊ | 581/995 [01:02<01:26, 4.78it/s] Loading 0: 64%|██████▍ | 636/995 [01:04<00:51, 6.95it/s] Loading 0: 69%|██████▉ | 691/995 [01:06<00:30, 9.89it/s] Loading 0: 74%|███████▍ | 739/995 [01:07<00:20, 12.79it/s] Loading 0: 80%|███████▉ | 794/995 [01:08<00:11, 16.78it/s] Loading 0: 85%|████████▍ | 845/995 [01:26<00:08, 16.78it/s] Loading 0: 85%|████████▌ | 846/995 [01:26<00:21, 6.85it/s] Loading 0: 85%|████████▌ | 849/995 [01:27<00:22, 6.50it/s] Loading 0: 90%|█████████ | 897/995 [01:28<00:10, 9.39it/s] Loading 0: 96%|█████████▌| 952/995 [01:29<00:03, 13.51it/s] Loading 0: 100%|██████████| 995/995 [01:31<00:00, 16.31it/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-v89-mkmlizer: warnings.warn(
neversleep-noromaid-v0-8068-v89-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-v89-mkmlizer: warnings.warn(
neversleep-noromaid-v0-8068-v89-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-v89-mkmlizer: warnings.warn(
neversleep-noromaid-v0-8068-v89-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-v89-mkmlizer: return self.fget.__get__(instance, owner)()
neversleep-noromaid-v0-8068-v89-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
neversleep-noromaid-v0-8068-v89-mkmlizer: Saving duration: 0.424s
neversleep-noromaid-v0-8068-v89-mkmlizer: Processed model rirv938/reward_gpt2_medium_preference_24m_e2 in 7.936s
neversleep-noromaid-v0-8068-v89-mkmlizer: creating bucket guanaco-reward-models
neversleep-noromaid-v0-8068-v89-mkmlizer: Bucket 's3://guanaco-reward-models/' created
neversleep-noromaid-v0-8068-v89-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/neversleep-noromaid-v0-8068-v89_reward
neversleep-noromaid-v0-8068-v89-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/neversleep-noromaid-v0-8068-v89_reward/config.json
neversleep-noromaid-v0-8068-v89-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/neversleep-noromaid-v0-8068-v89_reward/special_tokens_map.json
neversleep-noromaid-v0-8068-v89-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/neversleep-noromaid-v0-8068-v89_reward/tokenizer_config.json
neversleep-noromaid-v0-8068-v89-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/neversleep-noromaid-v0-8068-v89_reward/vocab.json
neversleep-noromaid-v0-8068-v89-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/neversleep-noromaid-v0-8068-v89_reward/merges.txt
neversleep-noromaid-v0-8068-v89-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/neversleep-noromaid-v0-8068-v89_reward/tokenizer.json
neversleep-noromaid-v0-8068-v89-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/neversleep-noromaid-v0-8068-v89_reward/reward.tensors
Job neversleep-noromaid-v0-8068-v89-mkmlizer completed after 371.1s with status: succeeded
Stopping job with name neversleep-noromaid-v0-8068-v89-mkmlizer
Pipeline stage MKMLizer completed in 372.37s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.11s
Running pipeline stage ISVCDeployer
Creating inference service neversleep-noromaid-v0-8068-v89
Waiting for inference service neversleep-noromaid-v0-8068-v89 to be ready
Inference service neversleep-noromaid-v0-8068-v89 ready after 90.45932745933533s
Pipeline stage ISVCDeployer completed in 97.56s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.9642012119293213s
Received healthy response to inference request in 2.4037301540374756s
Received healthy response to inference request in 2.2169578075408936s
Received healthy response to inference request in 2.0028927326202393s
Received healthy response to inference request in 2.069669008255005s
5 requests
0 failed requests
5th percentile: 2.0162479877471924
10th percentile: 2.0296032428741455
20th percentile: 2.0563137531280518
30th percentile: 2.099126768112183
40th percentile: 2.158042287826538
50th percentile: 2.2169578075408936
60th percentile: 2.2916667461395264
70th percentile: 2.366375684738159
80th percentile: 2.515824365615845
90th percentile: 2.740012788772583
95th percentile: 2.852107000350952
99th percentile: 2.9417823696136476
mean time: 2.331490182876587
Pipeline stage StressChecker completed in 12.42s
neversleep-noromaid-v0-_8068_v89 status is now deployed due to DeploymentManager action
neversleep-noromaid-v0-_8068_v89 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics