submission_id: neversleep-noromaid-v0_8068_v103
developer_uid: alexdaoud
status: inactive
model_repo: NeverSleep/Noromaid-v0.1-mixtral-8x7b-Instruct-v3
reward_repo: ChaiML/gpt2_xl_pairwise_89m_step_347634
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': ['\n', '</s>', '<|user|>', '###'], '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: 2024-07-02T01:47:45+00:00
model_name: neversleep-noromaid-v0_8068_v103
model_group: NeverSleep/Noromaid-v0.1
num_battles: 12022
num_wins: 6123
celo_rating: 1181.7
propriety_score: 0.7261701400751622
propriety_total_count: 5854.0
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_v103
ineligible_reason: None
language_model: NeverSleep/Noromaid-v0.1-mixtral-8x7b-Instruct-v3
model_size: 47B
reward_model: ChaiML/gpt2_xl_pairwise_89m_step_347634
us_pacific_date: 2024-07-01
win_ratio: 0.5093162535351855
Resubmit model
Running pipeline stage MKMLizer
Starting job with name neversleep-noromaid-v0-8068-v103-mkmlizer
Waiting for job on neversleep-noromaid-v0-8068-v103-mkmlizer to finish
neversleep-noromaid-v0-8068-v103-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
neversleep-noromaid-v0-8068-v103-mkmlizer: ║ _____ __ __ ║
neversleep-noromaid-v0-8068-v103-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
neversleep-noromaid-v0-8068-v103-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
neversleep-noromaid-v0-8068-v103-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
neversleep-noromaid-v0-8068-v103-mkmlizer: ║ /___/ ║
neversleep-noromaid-v0-8068-v103-mkmlizer: ║ ║
neversleep-noromaid-v0-8068-v103-mkmlizer: ║ Version: 0.8.14 ║
neversleep-noromaid-v0-8068-v103-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
neversleep-noromaid-v0-8068-v103-mkmlizer: ║ https://mk1.ai ║
neversleep-noromaid-v0-8068-v103-mkmlizer: ║ ║
neversleep-noromaid-v0-8068-v103-mkmlizer: ║ The license key for the current software has been verified as ║
neversleep-noromaid-v0-8068-v103-mkmlizer: ║ belonging to: ║
neversleep-noromaid-v0-8068-v103-mkmlizer: ║ ║
neversleep-noromaid-v0-8068-v103-mkmlizer: ║ Chai Research Corp. ║
neversleep-noromaid-v0-8068-v103-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
neversleep-noromaid-v0-8068-v103-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
neversleep-noromaid-v0-8068-v103-mkmlizer: ║ ║
neversleep-noromaid-v0-8068-v103-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
neversleep-noromaid-v0-8068-v103-mkmlizer: Downloaded to shared memory in 127.425s
neversleep-noromaid-v0-8068-v103-mkmlizer: quantizing model to /dev/shm/model_cache
neversleep-noromaid-v0-8068-v103-mkmlizer: Saving flywheel model at /dev/shm/model_cache
neversleep-noromaid-v0-8068-v103-mkmlizer: quantized model in 85.798s
neversleep-noromaid-v0-8068-v103-mkmlizer: Processed model NeverSleep/Noromaid-v0.1-mixtral-8x7b-Instruct-v3 in 213.223s
neversleep-noromaid-v0-8068-v103-mkmlizer: creating bucket guanaco-mkml-models
neversleep-noromaid-v0-8068-v103-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
neversleep-noromaid-v0-8068-v103-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v103
neversleep-noromaid-v0-8068-v103-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v103/tokenizer_config.json
neversleep-noromaid-v0-8068-v103-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v103/special_tokens_map.json
neversleep-noromaid-v0-8068-v103-mkmlizer: cp /dev/shm/model_cache/tokenizer.model s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v103/tokenizer.model
neversleep-noromaid-v0-8068-v103-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v103/tokenizer.json
neversleep-noromaid-v0-8068-v103-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v103/config.json
neversleep-noromaid-v0-8068-v103-mkmlizer: cp /dev/shm/model_cache/flywheel_model.3.safetensors s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v103/flywheel_model.3.safetensors
neversleep-noromaid-v0-8068-v103-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v103/flywheel_model.0.safetensors
neversleep-noromaid-v0-8068-v103-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v103/flywheel_model.1.safetensors
neversleep-noromaid-v0-8068-v103-mkmlizer: cp /dev/shm/model_cache/flywheel_model.2.safetensors s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v103/flywheel_model.2.safetensors
neversleep-noromaid-v0-8068-v103-mkmlizer: Loading 0: 0%| | 0/995 [00:00<?, ?it/s] Loading 0: 5%|▌ | 52/995 [00:01<00:22, 42.48it/s] Loading 0: 11%|█ | 107/995 [00:02<00:19, 44.48it/s] Loading 0: 16%|█▋ | 162/995 [00:03<00:18, 45.01it/s] Loading 0: 21%|██ | 210/995 [00:04<00:18, 43.61it/s] Loading 0: 27%|██▋ | 265/995 [00:05<00:15, 45.70it/s] Loading 0: 28%|██▊ | 277/995 [00:22<00:15, 45.70it/s] Loading 0: 28%|██▊ | 278/995 [00:22<01:59, 6.02it/s] Loading 0: 32%|███▏ | 320/995 [00:24<01:21, 8.30it/s] Loading 0: 37%|███▋ | 368/995 [00:25<00:53, 11.64it/s] Loading 0: 43%|████▎ | 423/995 [00:26<00:35, 16.10it/s] Loading 0: 48%|████▊ | 478/995 [00:27<00:24, 20.95it/s] Loading 0: 53%|█████▎ | 526/995 [00:28<00:18, 24.93it/s] Loading 0: 57%|█████▋ | 564/995 [00:45<00:17, 24.93it/s] Loading 0: 57%|█████▋ | 565/995 [00:45<01:01, 6.97it/s] Loading 0: 58%|█████▊ | 581/995 [00:47<00:56, 7.37it/s] Loading 0: 64%|██████▍ | 636/995 [00:48<00:32, 11.07it/s] Loading 0: 69%|██████▉ | 691/995 [00:49<00:19, 15.31it/s] Loading 0: 74%|███████▍ | 739/995 [00:50<00:13, 18.99it/s] Loading 0: 80%|███████▉ | 794/995 [00:51<00:08, 23.82it/s] Loading 0: 85%|████████▍ | 845/995 [01:09<00:06, 23.82it/s] Loading 0: 85%|████████▌ | 846/995 [01:09<00:19, 7.55it/s] Loading 0: 85%|████████▌ | 849/995 [01:10<00:20, 7.11it/s] Loading 0: 90%|█████████ | 897/995 [01:11<00:09, 10.23it/s] Loading 0: 96%|█████████▌| 952/995 [01:12<00:02, 14.70it/s] Loading 0: 100%|██████████| 995/995 [01:13<00:00, 17.47it/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-v103-mkmlizer: warnings.warn(
neversleep-noromaid-v0-8068-v103-mkmlizer: loading reward model from ChaiML/gpt2_xl_pairwise_89m_step_347634
neversleep-noromaid-v0-8068-v103-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-v103-mkmlizer: warnings.warn(
neversleep-noromaid-v0-8068-v103-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-v103-mkmlizer: warnings.warn(
neversleep-noromaid-v0-8068-v103-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-v103-mkmlizer: warnings.warn(
neversleep-noromaid-v0-8068-v103-mkmlizer: Downloading shards: 0%| | 0/2 [00:00<?, ?it/s] Downloading shards: 50%|█████ | 1/2 [00:05<00:05, 5.51s/it] Downloading shards: 100%|██████████| 2/2 [00:09<00:00, 4.46s/it] Downloading shards: 100%|██████████| 2/2 [00:09<00:00, 4.62s/it]
neversleep-noromaid-v0-8068-v103-mkmlizer: Loading checkpoint shards: 0%| | 0/2 [00:00<?, ?it/s] Loading checkpoint shards: 50%|█████ | 1/2 [00:00<00:00, 1.15it/s] Loading checkpoint shards: 100%|██████████| 2/2 [00:01<00:00, 2.04it/s] Loading checkpoint shards: 100%|██████████| 2/2 [00:01<00:00, 1.82it/s]
neversleep-noromaid-v0-8068-v103-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
neversleep-noromaid-v0-8068-v103-mkmlizer: Saving duration: 1.677s
neversleep-noromaid-v0-8068-v103-mkmlizer: Processed model ChaiML/gpt2_xl_pairwise_89m_step_347634 in 13.488s
neversleep-noromaid-v0-8068-v103-mkmlizer: creating bucket guanaco-reward-models
neversleep-noromaid-v0-8068-v103-mkmlizer: Bucket 's3://guanaco-reward-models/' created
neversleep-noromaid-v0-8068-v103-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/neversleep-noromaid-v0-8068-v103_reward
neversleep-noromaid-v0-8068-v103-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/neversleep-noromaid-v0-8068-v103_reward/config.json
neversleep-noromaid-v0-8068-v103-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/neversleep-noromaid-v0-8068-v103_reward/special_tokens_map.json
neversleep-noromaid-v0-8068-v103-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/neversleep-noromaid-v0-8068-v103_reward/merges.txt
neversleep-noromaid-v0-8068-v103-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/neversleep-noromaid-v0-8068-v103_reward/vocab.json
neversleep-noromaid-v0-8068-v103-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/neversleep-noromaid-v0-8068-v103_reward/tokenizer_config.json
neversleep-noromaid-v0-8068-v103-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/neversleep-noromaid-v0-8068-v103_reward/tokenizer.json
Job neversleep-noromaid-v0-8068-v103-mkmlizer completed after 285.96s with status: succeeded
Stopping job with name neversleep-noromaid-v0-8068-v103-mkmlizer
Pipeline stage MKMLizer completed in 286.90s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.34s
Running pipeline stage ISVCDeployer
Creating inference service neversleep-noromaid-v0-8068-v103
Waiting for inference service neversleep-noromaid-v0-8068-v103 to be ready
Inference service neversleep-noromaid-v0-8068-v103 ready after 70.38204336166382s
Pipeline stage ISVCDeployer completed in 77.32s
Running pipeline stage StressChecker
Received healthy response to inference request in 3.2783634662628174s
Received healthy response to inference request in 2.2978460788726807s
Received healthy response to inference request in 2.44494891166687s
Received healthy response to inference request in 2.3685545921325684s
Received healthy response to inference request in 2.3854641914367676s
5 requests
0 failed requests
5th percentile: 2.311987781524658
10th percentile: 2.3261294841766356
20th percentile: 2.354412889480591
30th percentile: 2.3719365119934084
40th percentile: 2.378700351715088
50th percentile: 2.3854641914367676
60th percentile: 2.4092580795288088
70th percentile: 2.4330519676208495
80th percentile: 2.6116318225860597
90th percentile: 2.9449976444244386
95th percentile: 3.1116805553436278
99th percentile: 3.2450268840789795
mean time: 2.555035448074341
Pipeline stage StressChecker completed in 13.57s
neversleep-noromaid-v0_8068_v103 status is now deployed due to DeploymentManager action
neversleep-noromaid-v0_8068_v103 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics