submission_id: neversleep-noromaid-v0_8068_v112
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: 2024-07-02T21:38:35+00:00
model_name: neversleep-noromaid-v0_8068_v112
model_group: NeverSleep/Noromaid-v0.1
num_battles: 13395
num_wins: 6463
celo_rating: 1164.85
propriety_score: 0.714557262791066
propriety_total_count: 6313.0
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_v112
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: 2024-07-02
win_ratio: 0.48249346771183277
Resubmit model
Running pipeline stage MKMLizer
Starting job with name neversleep-noromaid-v0-8068-v112-mkmlizer
Waiting for job on neversleep-noromaid-v0-8068-v112-mkmlizer to finish
neversleep-noromaid-v0-8068-v112-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
neversleep-noromaid-v0-8068-v112-mkmlizer: ║ _____ __ __ ║
neversleep-noromaid-v0-8068-v112-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
neversleep-noromaid-v0-8068-v112-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
neversleep-noromaid-v0-8068-v112-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
neversleep-noromaid-v0-8068-v112-mkmlizer: ║ /___/ ║
neversleep-noromaid-v0-8068-v112-mkmlizer: ║ ║
neversleep-noromaid-v0-8068-v112-mkmlizer: ║ Version: 0.8.14 ║
neversleep-noromaid-v0-8068-v112-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
neversleep-noromaid-v0-8068-v112-mkmlizer: ║ https://mk1.ai ║
neversleep-noromaid-v0-8068-v112-mkmlizer: ║ ║
neversleep-noromaid-v0-8068-v112-mkmlizer: ║ The license key for the current software has been verified as ║
neversleep-noromaid-v0-8068-v112-mkmlizer: ║ belonging to: ║
neversleep-noromaid-v0-8068-v112-mkmlizer: ║ ║
neversleep-noromaid-v0-8068-v112-mkmlizer: ║ Chai Research Corp. ║
neversleep-noromaid-v0-8068-v112-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
neversleep-noromaid-v0-8068-v112-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
neversleep-noromaid-v0-8068-v112-mkmlizer: ║ ║
neversleep-noromaid-v0-8068-v112-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
neversleep-noromaid-v0-8068-v112-mkmlizer: Downloaded to shared memory in 88.743s
neversleep-noromaid-v0-8068-v112-mkmlizer: quantizing model to /dev/shm/model_cache
neversleep-noromaid-v0-8068-v112-mkmlizer: Saving flywheel model at /dev/shm/model_cache
Retrying (%r) after connection broken by '%r': %s
neversleep-noromaid-v0-8068-v112-mkmlizer: quantized model in 204.265s
neversleep-noromaid-v0-8068-v112-mkmlizer: Processed model NeverSleep/Noromaid-v0.1-mixtral-8x7b-Instruct-v3 in 293.008s
neversleep-noromaid-v0-8068-v112-mkmlizer: creating bucket guanaco-mkml-models
neversleep-noromaid-v0-8068-v112-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
neversleep-noromaid-v0-8068-v112-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v112
neversleep-noromaid-v0-8068-v112-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v112/special_tokens_map.json
neversleep-noromaid-v0-8068-v112-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v112/config.json
neversleep-noromaid-v0-8068-v112-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v112/tokenizer_config.json
neversleep-noromaid-v0-8068-v112-mkmlizer: cp /dev/shm/model_cache/tokenizer.model s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v112/tokenizer.model
neversleep-noromaid-v0-8068-v112-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v112/tokenizer.json
neversleep-noromaid-v0-8068-v112-mkmlizer: cp /dev/shm/model_cache/flywheel_model.3.safetensors s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v112/flywheel_model.3.safetensors
neversleep-noromaid-v0-8068-v112-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v112/flywheel_model.0.safetensors
neversleep-noromaid-v0-8068-v112-mkmlizer: cp /dev/shm/model_cache/flywheel_model.2.safetensors s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v112/flywheel_model.2.safetensors
neversleep-noromaid-v0-8068-v112-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v112/flywheel_model.1.safetensors
neversleep-noromaid-v0-8068-v112-mkmlizer: loading reward model from rirv938/reward_gpt2_medium_preference_24m_e2
neversleep-noromaid-v0-8068-v112-mkmlizer: Loading 0: 0%| | 0/995 [00:00<?, ?it/s] Loading 0: 5%|▌ | 52/995 [00:05<01:34, 10.02it/s] Loading 0: 11%|█ | 107/995 [00:06<00:45, 19.44it/s] Loading 0: 16%|█▋ | 162/995 [00:09<00:43, 19.34it/s] Loading 0: 21%|██ | 210/995 [00:10<00:31, 24.85it/s] Loading 0: 27%|██▋ | 265/995 [00:11<00:23, 30.96it/s] Loading 0: 28%|██▊ | 277/995 [00:22<00:23, 30.96it/s] Loading 0: 28%|██▊ | 278/995 [00:22<01:29, 8.04it/s] Loading 0: 32%|███▏ | 320/995 [00:23<01:04, 10.53it/s] Loading 0: 37%|███▋ | 368/995 [00:26<00:48, 12.87it/s] Loading 0: 43%|████▎ | 423/995 [00:27<00:32, 17.79it/s] Loading 0: 48%|████▊ | 478/995 [00:28<00:22, 23.02it/s] Loading 0: 53%|█████▎ | 526/995 [00:29<00:17, 27.04it/s] Loading 0: 57%|█████▋ | 565/995 [00:40<00:43, 9.94it/s] Loading 0: 58%|█████▊ | 581/995 [00:44<00:51, 8.03it/s] Loading 0: 64%|██████▍ | 636/995 [00:47<00:33, 10.88it/s] Loading 0: 69%|██████▉ | 691/995 [00:48<00:20, 15.02it/s] Loading 0: 74%|███████▍ | 739/995 [00:49<00:13, 18.90it/s] Loading 0: 80%|███████▉ | 794/995 [00:50<00:08, 23.78it/s] Loading 0: 85%|████████▌ | 846/995 [01:01<00:14, 10.64it/s] Loading 0: 85%|████████▌ | 849/995 [01:02<00:15, 9.70it/s] Loading 0: 90%|█████████ | 897/995 [01:03<00:07, 13.47it/s] Loading 0: 96%|█████████▌| 952/995 [01:04<00:02, 18.93it/s] Loading 0: 100%|██████████| 995/995 [01:05<00:00, 21.89it/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-v112-mkmlizer: warnings.warn(
neversleep-noromaid-v0-8068-v112-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-v112-mkmlizer: warnings.warn(
neversleep-noromaid-v0-8068-v112-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-v112-mkmlizer: warnings.warn(
neversleep-noromaid-v0-8068-v112-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-v112-mkmlizer: warnings.warn(
neversleep-noromaid-v0-8068-v112-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-v112-mkmlizer: return self.fget.__get__(instance, owner)()
neversleep-noromaid-v0-8068-v112-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
neversleep-noromaid-v0-8068-v112-mkmlizer: Saving duration: 0.306s
neversleep-noromaid-v0-8068-v112-mkmlizer: Processed model rirv938/reward_gpt2_medium_preference_24m_e2 in 5.350s
neversleep-noromaid-v0-8068-v112-mkmlizer: creating bucket guanaco-reward-models
neversleep-noromaid-v0-8068-v112-mkmlizer: Bucket 's3://guanaco-reward-models/' created
neversleep-noromaid-v0-8068-v112-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/neversleep-noromaid-v0-8068-v112_reward
neversleep-noromaid-v0-8068-v112-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/neversleep-noromaid-v0-8068-v112_reward/config.json
neversleep-noromaid-v0-8068-v112-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/neversleep-noromaid-v0-8068-v112_reward/tokenizer_config.json
neversleep-noromaid-v0-8068-v112-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/neversleep-noromaid-v0-8068-v112_reward/vocab.json
neversleep-noromaid-v0-8068-v112-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/neversleep-noromaid-v0-8068-v112_reward/merges.txt
neversleep-noromaid-v0-8068-v112-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/neversleep-noromaid-v0-8068-v112_reward/special_tokens_map.json
neversleep-noromaid-v0-8068-v112-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/neversleep-noromaid-v0-8068-v112_reward/tokenizer.json
neversleep-noromaid-v0-8068-v112-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/neversleep-noromaid-v0-8068-v112_reward/reward.tensors
Job neversleep-noromaid-v0-8068-v112-mkmlizer completed after 381.61s with status: succeeded
Stopping job with name neversleep-noromaid-v0-8068-v112-mkmlizer
Pipeline stage MKMLizer completed in 382.50s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.10s
Running pipeline stage ISVCDeployer
Creating inference service neversleep-noromaid-v0-8068-v112
Waiting for inference service neversleep-noromaid-v0-8068-v112 to be ready
Inference service neversleep-noromaid-v0-8068-v112 ready after 80.4641706943512s
Pipeline stage ISVCDeployer completed in 87.88s
Running pipeline stage StressChecker
Received healthy response to inference request in 3.274399757385254s
Received healthy response to inference request in 2.2298331260681152s
Received healthy response to inference request in 2.3088808059692383s
Received healthy response to inference request in 2.2040247917175293s
Received healthy response to inference request in 2.3940377235412598s
5 requests
0 failed requests
5th percentile: 2.2091864585876464
10th percentile: 2.2143481254577635
20th percentile: 2.224671459197998
30th percentile: 2.24564266204834
40th percentile: 2.277261734008789
50th percentile: 2.3088808059692383
60th percentile: 2.342943572998047
70th percentile: 2.3770063400268553
80th percentile: 2.570110130310059
90th percentile: 2.922254943847656
95th percentile: 3.098327350616455
99th percentile: 3.239185276031494
mean time: 2.482235240936279
Pipeline stage StressChecker completed in 13.20s
neversleep-noromaid-v0_8068_v112 status is now deployed due to DeploymentManager action
neversleep-noromaid-v0_8068_v112 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics