submission_id: neversleep-noromaid-v0_8068_v111
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': '""', 'prompt_template': '""', 'bot_template': 'Bot: {message}\n', 'user_template': 'User: {message}\n', 'response_template': 'Bot:', 'truncate_by_message': False}
timestamp: 2024-07-02T21:37:39+00:00
model_name: neversleep-noromaid-v0_8068_v111
model_group: NeverSleep/Noromaid-v0.1
num_battles: 13590
num_wins: 6922
celo_rating: 1182.95
propriety_score: 0.724375
propriety_total_count: 6400.0
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_v111
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: 0.5093451066961001
Resubmit model
Running pipeline stage MKMLizer
Starting job with name neversleep-noromaid-v0-8068-v111-mkmlizer
Waiting for job on neversleep-noromaid-v0-8068-v111-mkmlizer to finish
neversleep-noromaid-v0-8068-v111-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
neversleep-noromaid-v0-8068-v111-mkmlizer: ║ _____ __ __ ║
neversleep-noromaid-v0-8068-v111-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
neversleep-noromaid-v0-8068-v111-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
neversleep-noromaid-v0-8068-v111-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
neversleep-noromaid-v0-8068-v111-mkmlizer: ║ /___/ ║
neversleep-noromaid-v0-8068-v111-mkmlizer: ║ ║
neversleep-noromaid-v0-8068-v111-mkmlizer: ║ Version: 0.8.14 ║
neversleep-noromaid-v0-8068-v111-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
neversleep-noromaid-v0-8068-v111-mkmlizer: ║ https://mk1.ai ║
neversleep-noromaid-v0-8068-v111-mkmlizer: ║ ║
neversleep-noromaid-v0-8068-v111-mkmlizer: ║ The license key for the current software has been verified as ║
neversleep-noromaid-v0-8068-v111-mkmlizer: ║ belonging to: ║
neversleep-noromaid-v0-8068-v111-mkmlizer: ║ ║
neversleep-noromaid-v0-8068-v111-mkmlizer: ║ Chai Research Corp. ║
neversleep-noromaid-v0-8068-v111-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
neversleep-noromaid-v0-8068-v111-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
neversleep-noromaid-v0-8068-v111-mkmlizer: ║ ║
neversleep-noromaid-v0-8068-v111-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
neversleep-noromaid-v0-8068-v111-mkmlizer: Downloaded to shared memory in 95.319s
neversleep-noromaid-v0-8068-v111-mkmlizer: quantizing model to /dev/shm/model_cache
neversleep-noromaid-v0-8068-v111-mkmlizer: Saving flywheel model at /dev/shm/model_cache
Connection pool is full, discarding connection: %s
neversleep-noromaid-v0-8068-v111-mkmlizer: quantized model in 201.593s
neversleep-noromaid-v0-8068-v111-mkmlizer: Processed model NeverSleep/Noromaid-v0.1-mixtral-8x7b-Instruct-v3 in 296.912s
neversleep-noromaid-v0-8068-v111-mkmlizer: creating bucket guanaco-mkml-models
neversleep-noromaid-v0-8068-v111-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
neversleep-noromaid-v0-8068-v111-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v111
neversleep-noromaid-v0-8068-v111-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v111/special_tokens_map.json
neversleep-noromaid-v0-8068-v111-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v111/tokenizer_config.json
neversleep-noromaid-v0-8068-v111-mkmlizer: cp /dev/shm/model_cache/tokenizer.model s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v111/tokenizer.model
neversleep-noromaid-v0-8068-v111-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v111/config.json
neversleep-noromaid-v0-8068-v111-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v111/tokenizer.json
neversleep-noromaid-v0-8068-v111-mkmlizer: cp /dev/shm/model_cache/flywheel_model.3.safetensors s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v111/flywheel_model.3.safetensors
neversleep-noromaid-v0-8068-v111-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v111/flywheel_model.1.safetensors
neversleep-noromaid-v0-8068-v111-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v111/flywheel_model.0.safetensors
neversleep-noromaid-v0-8068-v111-mkmlizer: cp /dev/shm/model_cache/flywheel_model.2.safetensors s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v111/flywheel_model.2.safetensors
neversleep-noromaid-v0-8068-v111-mkmlizer: loading reward model from ChaiML/gpt2_xl_pairwise_89m_step_347634
neversleep-noromaid-v0-8068-v111-mkmlizer: Loading 0: 0%| | 0/995 [00:00<?, ?it/s] Loading 0: 5%|▌ | 52/995 [00:08<02:38, 5.94it/s] Loading 0: 11%|█ | 107/995 [00:15<02:08, 6.91it/s] Loading 0: 16%|█▋ | 162/995 [00:19<01:31, 9.08it/s] Loading 0: 21%|██ | 210/995 [00:21<01:07, 11.57it/s] Loading 0: 27%|██▋ | 265/995 [00:22<00:44, 16.28it/s] Loading 0: 28%|██▊ | 278/995 [00:34<01:47, 6.66it/s] Loading 0: 32%|███▏ | 320/995 [00:40<01:44, 6.46it/s] Loading 0: 37%|███▋ | 368/995 [00:43<01:15, 8.33it/s] Loading 0: 43%|████▎ | 423/995 [00:44<00:47, 12.09it/s] Loading 0: 48%|████▊ | 478/995 [00:47<00:35, 14.52it/s] Loading 0: 53%|█████▎ | 526/995 [00:49<00:29, 15.93it/s] Loading 0: 57%|█████▋ | 564/995 [01:00<00:27, 15.93it/s] Loading 0: 57%|█████▋ | 565/995 [01:00<00:51, 8.39it/s] Loading 0: 58%|█████▊ | 581/995 [01:01<00:48, 8.62it/s] Loading 0: 64%|██████▍ | 636/995 [01:03<00:28, 12.53it/s] Loading 0: 69%|██████▉ | 691/995 [01:04<00:18, 16.46it/s] Loading 0: 74%|███████▍ | 739/995 [01:06<00:13, 19.21it/s] Loading 0: 80%|███████▉ | 794/995 [01:07<00:08, 23.30it/s] Loading 0: 85%|████████▍ | 845/995 [01:18<00:06, 23.30it/s] Loading 0: 85%|████████▌ | 846/995 [01:18<00:14, 10.61it/s] Loading 0: 85%|████████▌ | 849/995 [01:20<00:15, 9.39it/s] Loading 0: 90%|█████████ | 897/995 [01:21<00:07, 12.41it/s] Loading 0: 96%|█████████▌| 952/995 [01:22<00:02, 17.14it/s] Loading 0: 100%|██████████| 995/995 [01:24<00:00, 19.88it/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-v111-mkmlizer: warnings.warn(
neversleep-noromaid-v0-8068-v111-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-v111-mkmlizer: warnings.warn(
neversleep-noromaid-v0-8068-v111-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-v111-mkmlizer: warnings.warn(
neversleep-noromaid-v0-8068-v111-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-v111-mkmlizer: warnings.warn(
neversleep-noromaid-v0-8068-v111-mkmlizer: Downloading shards: 0%| | 0/2 [00:00<?, ?it/s] Downloading shards: 50%|█████ | 1/2 [00:04<00:04, 4.12s/it] Downloading shards: 100%|██████████| 2/2 [00:05<00:00, 2.72s/it] Downloading shards: 100%|██████████| 2/2 [00:05<00:00, 2.93s/it]
neversleep-noromaid-v0-8068-v111-mkmlizer: Loading checkpoint shards: 0%| | 0/2 [00:00<?, ?it/s] Loading checkpoint shards: 50%|█████ | 1/2 [00:00<00:00, 1.70it/s] Loading checkpoint shards: 100%|██████████| 2/2 [00:00<00:00, 2.84it/s] Loading checkpoint shards: 100%|██████████| 2/2 [00:00<00:00, 2.58it/s]
neversleep-noromaid-v0-8068-v111-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
neversleep-noromaid-v0-8068-v111-mkmlizer: Saving duration: 1.115s
neversleep-noromaid-v0-8068-v111-mkmlizer: Processed model ChaiML/gpt2_xl_pairwise_89m_step_347634 in 9.922s
neversleep-noromaid-v0-8068-v111-mkmlizer: creating bucket guanaco-reward-models
neversleep-noromaid-v0-8068-v111-mkmlizer: Bucket 's3://guanaco-reward-models/' created
neversleep-noromaid-v0-8068-v111-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/neversleep-noromaid-v0-8068-v111_reward
neversleep-noromaid-v0-8068-v111-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/neversleep-noromaid-v0-8068-v111_reward/config.json
neversleep-noromaid-v0-8068-v111-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/neversleep-noromaid-v0-8068-v111_reward/tokenizer_config.json
neversleep-noromaid-v0-8068-v111-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/neversleep-noromaid-v0-8068-v111_reward/special_tokens_map.json
neversleep-noromaid-v0-8068-v111-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/neversleep-noromaid-v0-8068-v111_reward/merges.txt
neversleep-noromaid-v0-8068-v111-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/neversleep-noromaid-v0-8068-v111_reward/tokenizer.json
neversleep-noromaid-v0-8068-v111-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/neversleep-noromaid-v0-8068-v111_reward/vocab.json
neversleep-noromaid-v0-8068-v111-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/neversleep-noromaid-v0-8068-v111_reward/reward.tensors
Connection pool is full, discarding connection: %s
Job neversleep-noromaid-v0-8068-v111-mkmlizer completed after 362.98s with status: succeeded
Stopping job with name neversleep-noromaid-v0-8068-v111-mkmlizer
Pipeline stage MKMLizer completed in 363.97s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.12s
Running pipeline stage ISVCDeployer
Creating inference service neversleep-noromaid-v0-8068-v111
Waiting for inference service neversleep-noromaid-v0-8068-v111 to be ready
Connection pool is full, discarding connection: %s
Inference service neversleep-noromaid-v0-8068-v111 ready after 80.38558650016785s
Pipeline stage ISVCDeployer completed in 88.42s
Running pipeline stage StressChecker
Received healthy response to inference request in 3.341703414916992s
Received healthy response to inference request in 2.3523170948028564s
Received healthy response to inference request in 2.357295036315918s
Received healthy response to inference request in 2.3349835872650146s
Received healthy response to inference request in 2.1516499519348145s
5 requests
0 failed requests
5th percentile: 2.1883166790008546
10th percentile: 2.2249834060668947
20th percentile: 2.2983168601989745
30th percentile: 2.338450288772583
40th percentile: 2.3453836917877195
50th percentile: 2.3523170948028564
60th percentile: 2.354308271408081
70th percentile: 2.3562994480133055
80th percentile: 2.554176712036133
90th percentile: 2.9479400634765627
95th percentile: 3.144821739196777
99th percentile: 3.302327079772949
mean time: 2.507589817047119
Pipeline stage StressChecker completed in 13.38s
neversleep-noromaid-v0_8068_v111 status is now deployed due to DeploymentManager action
neversleep-noromaid-v0_8068_v111 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics