submission_id: neversleep-noromaid-v0_8068_v110
developer_uid: dzhao1
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_name}: {message}\n', 'user_template': '{user_name}: {message}\n', 'response_template': '{bot_name}:', 'truncate_by_message': False}
timestamp: 2024-07-02T20:02:55+00:00
model_name: neversleep-noromaid-v0_8068_v110
model_group: NeverSleep/Noromaid-v0.1
num_battles: 10814
num_wins: 5670
celo_rating: 1191.2
propriety_score: 0.7250806910955003
propriety_total_count: 5267.0
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_v110
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: 2024-07-02
win_ratio: 0.5243203255039763
Resubmit model
Running pipeline stage MKMLizer
Starting job with name neversleep-noromaid-v0-8068-v110-mkmlizer
Waiting for job on neversleep-noromaid-v0-8068-v110-mkmlizer to finish
neversleep-noromaid-v0-8068-v110-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
neversleep-noromaid-v0-8068-v110-mkmlizer: ║ _____ __ __ ║
neversleep-noromaid-v0-8068-v110-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
neversleep-noromaid-v0-8068-v110-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
neversleep-noromaid-v0-8068-v110-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
neversleep-noromaid-v0-8068-v110-mkmlizer: ║ /___/ ║
neversleep-noromaid-v0-8068-v110-mkmlizer: ║ ║
neversleep-noromaid-v0-8068-v110-mkmlizer: ║ Version: 0.8.14 ║
neversleep-noromaid-v0-8068-v110-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
neversleep-noromaid-v0-8068-v110-mkmlizer: ║ https://mk1.ai ║
neversleep-noromaid-v0-8068-v110-mkmlizer: ║ ║
neversleep-noromaid-v0-8068-v110-mkmlizer: ║ The license key for the current software has been verified as ║
neversleep-noromaid-v0-8068-v110-mkmlizer: ║ belonging to: ║
neversleep-noromaid-v0-8068-v110-mkmlizer: ║ ║
neversleep-noromaid-v0-8068-v110-mkmlizer: ║ Chai Research Corp. ║
neversleep-noromaid-v0-8068-v110-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
neversleep-noromaid-v0-8068-v110-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
neversleep-noromaid-v0-8068-v110-mkmlizer: ║ ║
neversleep-noromaid-v0-8068-v110-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
neversleep-noromaid-v0-8068-v110-mkmlizer: Downloaded to shared memory in 118.014s
neversleep-noromaid-v0-8068-v110-mkmlizer: quantizing model to /dev/shm/model_cache
neversleep-noromaid-v0-8068-v110-mkmlizer: Saving flywheel model at /dev/shm/model_cache
neversleep-noromaid-v0-8068-v110-mkmlizer: quantized model in 178.383s
neversleep-noromaid-v0-8068-v110-mkmlizer: Processed model NeverSleep/Noromaid-v0.1-mixtral-8x7b-Instruct-v3 in 296.397s
neversleep-noromaid-v0-8068-v110-mkmlizer: creating bucket guanaco-mkml-models
neversleep-noromaid-v0-8068-v110-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
neversleep-noromaid-v0-8068-v110-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v110
neversleep-noromaid-v0-8068-v110-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v110/tokenizer_config.json
neversleep-noromaid-v0-8068-v110-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v110/config.json
neversleep-noromaid-v0-8068-v110-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v110/special_tokens_map.json
neversleep-noromaid-v0-8068-v110-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v110/tokenizer.json
neversleep-noromaid-v0-8068-v110-mkmlizer: cp /dev/shm/model_cache/tokenizer.model s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v110/tokenizer.model
neversleep-noromaid-v0-8068-v110-mkmlizer: cp /dev/shm/model_cache/flywheel_model.3.safetensors s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v110/flywheel_model.3.safetensors
neversleep-noromaid-v0-8068-v110-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v110/flywheel_model.1.safetensors
neversleep-noromaid-v0-8068-v110-mkmlizer: cp /dev/shm/model_cache/flywheel_model.2.safetensors s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v110/flywheel_model.2.safetensors
neversleep-noromaid-v0-8068-v110-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v110/flywheel_model.0.safetensors
neversleep-noromaid-v0-8068-v110-mkmlizer: loading reward model from ChaiML/gpt2_xl_pairwise_89m_step_347634
neversleep-noromaid-v0-8068-v110-mkmlizer: Loading 0: 0%| | 0/995 [00:00<?, ?it/s] Loading 0: 5%|▌ | 52/995 [00:01<00:22, 42.35it/s] Loading 0: 11%|█ | 107/995 [00:02<00:20, 43.43it/s] Loading 0: 16%|█▋ | 162/995 [00:03<00:18, 44.98it/s] Loading 0: 21%|██ | 209/995 [00:15<00:17, 44.98it/s] Loading 0: 21%|██ | 210/995 [01:19<07:42, 1.70it/s] Loading 0: 27%|██▋ | 265/995 [01:36<05:56, 2.05it/s] Loading 0: 28%|██▊ | 278/995 [01:53<06:56, 1.72it/s] Loading 0: 32%|███▏ | 320/995 [01:56<04:32, 2.47it/s] Loading 0: 37%|███▋ | 368/995 [01:57<02:48, 3.73it/s] Loading 0: 43%|████▎ | 423/995 [01:58<01:41, 5.66it/s] Loading 0: 48%|████▊ | 478/995 [02:00<01:03, 8.08it/s] Loading 0: 51%|█████ | 507/995 [02:00<00:48, 10.11it/s] Loading 0: 53%|█████▎ | 526/995 [02:01<00:43, 10.69it/s] Loading 0: 57%|█████▋ | 564/995 [02:18<00:40, 10.69it/s] Loading 0: 57%|█████▋ | 565/995 [02:18<01:27, 4.92it/s] Loading 0: 58%|█████▊ | 581/995 [02:19<01:16, 5.41it/s] Loading 0: 64%|██████▍ | 636/995 [02:20<00:40, 8.87it/s] Loading 0: 69%|██████▉ | 691/995 [02:21<00:23, 12.92it/s] Loading 0: 74%|███████▍ | 739/995 [02:23<00:15, 16.73it/s] Loading 0: 80%|███████▉ | 794/995 [02:24<00:09, 21.74it/s] Loading 0: 85%|████████▍ | 845/995 [02:41<00:06, 21.74it/s] Loading 0: 85%|████████▌ | 846/995 [02:41<00:20, 7.37it/s] Loading 0: 85%|████████▌ | 849/995 [02:42<00:20, 6.95it/s] Loading 0: 90%|█████████ | 897/995 [02:43<00:09, 9.87it/s] Loading 0: 96%|█████████▌| 952/995 [02:45<00:03, 14.03it/s] Loading 0: 100%|██████████| 995/995 [02:46<00:00, 16.76it/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-v110-mkmlizer: warnings.warn(
neversleep-noromaid-v0-8068-v110-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-v110-mkmlizer: warnings.warn(
neversleep-noromaid-v0-8068-v110-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-v110-mkmlizer: warnings.warn(
neversleep-noromaid-v0-8068-v110-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-v110-mkmlizer: warnings.warn(
neversleep-noromaid-v0-8068-v110-mkmlizer: Downloading shards: 0%| | 0/2 [00:00<?, ?it/s] Downloading shards: 50%|█████ | 1/2 [00:07<00:07, 7.79s/it] Downloading shards: 100%|██████████| 2/2 [00:15<00:00, 7.48s/it] Downloading shards: 100%|██████████| 2/2 [00:15<00:00, 7.53s/it]
neversleep-noromaid-v0-8068-v110-mkmlizer: Loading checkpoint shards: 0%| | 0/2 [00:00<?, ?it/s] Loading checkpoint shards: 50%|█████ | 1/2 [00:00<00:00, 1.56it/s] Loading checkpoint shards: 100%|██████████| 2/2 [00:00<00:00, 2.73it/s] Loading checkpoint shards: 100%|██████████| 2/2 [00:00<00:00, 2.45it/s]
neversleep-noromaid-v0-8068-v110-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
neversleep-noromaid-v0-8068-v110-mkmlizer: Saving duration: 1.648s
neversleep-noromaid-v0-8068-v110-mkmlizer: Processed model ChaiML/gpt2_xl_pairwise_89m_step_347634 in 19.151s
neversleep-noromaid-v0-8068-v110-mkmlizer: creating bucket guanaco-reward-models
neversleep-noromaid-v0-8068-v110-mkmlizer: Bucket 's3://guanaco-reward-models/' created
neversleep-noromaid-v0-8068-v110-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/neversleep-noromaid-v0-8068-v110_reward
neversleep-noromaid-v0-8068-v110-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/neversleep-noromaid-v0-8068-v110_reward/config.json
neversleep-noromaid-v0-8068-v110-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/neversleep-noromaid-v0-8068-v110_reward/special_tokens_map.json
neversleep-noromaid-v0-8068-v110-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/neversleep-noromaid-v0-8068-v110_reward/merges.txt
neversleep-noromaid-v0-8068-v110-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/neversleep-noromaid-v0-8068-v110_reward/tokenizer_config.json
neversleep-noromaid-v0-8068-v110-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/neversleep-noromaid-v0-8068-v110_reward/vocab.json
neversleep-noromaid-v0-8068-v110-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/neversleep-noromaid-v0-8068-v110_reward/tokenizer.json
neversleep-noromaid-v0-8068-v110-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/neversleep-noromaid-v0-8068-v110_reward/reward.tensors
Job neversleep-noromaid-v0-8068-v110-mkmlizer completed after 360.04s with status: succeeded
Stopping job with name neversleep-noromaid-v0-8068-v110-mkmlizer
Pipeline stage MKMLizer completed in 360.94s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.11s
Running pipeline stage ISVCDeployer
Creating inference service neversleep-noromaid-v0-8068-v110
Waiting for inference service neversleep-noromaid-v0-8068-v110 to be ready
Inference service neversleep-noromaid-v0-8068-v110 ready after 90.48525094985962s
Pipeline stage ISVCDeployer completed in 97.25s
Running pipeline stage StressChecker
Received healthy response to inference request in 3.5525336265563965s
Received healthy response to inference request in 2.1953701972961426s
Received healthy response to inference request in 2.359156847000122s
Received healthy response to inference request in 2.2755467891693115s
Received healthy response to inference request in 2.3484561443328857s
5 requests
0 failed requests
5th percentile: 2.2114055156707764
10th percentile: 2.22744083404541
20th percentile: 2.2595114707946777
30th percentile: 2.2901286602020265
40th percentile: 2.319292402267456
50th percentile: 2.3484561443328857
60th percentile: 2.3527364253997805
70th percentile: 2.3570167064666747
80th percentile: 2.597832202911377
90th percentile: 3.0751829147338867
95th percentile: 3.3138582706451416
99th percentile: 3.5047985553741454
mean time: 2.5462127208709715
Pipeline stage StressChecker completed in 13.41s
neversleep-noromaid-v0_8068_v110 status is now deployed due to DeploymentManager action
neversleep-noromaid-v0_8068_v110 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics