submission_id: neversleep-noromaid-v0-_8068_v97
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': '[INST] respond with drama [/INST]{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: 2024-07-01T22:53:34+00:00
model_name: neversleep-noromaid-v0-_8068_v97
model_group: NeverSleep/Noromaid-v0.1
num_battles: 13351
num_wins: 6486
celo_rating: 1145.42
propriety_score: 0.7266865859411857
propriety_total_count: 6359.0
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_v97
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: 0.4858063066436971
Resubmit model
Running pipeline stage MKMLizer
Starting job with name neversleep-noromaid-v0-8068-v97-mkmlizer
Waiting for job on neversleep-noromaid-v0-8068-v97-mkmlizer to finish
neversleep-noromaid-v0-8068-v97-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
neversleep-noromaid-v0-8068-v97-mkmlizer: ║ _____ __ __ ║
neversleep-noromaid-v0-8068-v97-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
neversleep-noromaid-v0-8068-v97-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
neversleep-noromaid-v0-8068-v97-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
neversleep-noromaid-v0-8068-v97-mkmlizer: ║ /___/ ║
neversleep-noromaid-v0-8068-v97-mkmlizer: ║ ║
neversleep-noromaid-v0-8068-v97-mkmlizer: ║ Version: 0.8.14 ║
neversleep-noromaid-v0-8068-v97-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
neversleep-noromaid-v0-8068-v97-mkmlizer: ║ https://mk1.ai ║
neversleep-noromaid-v0-8068-v97-mkmlizer: ║ ║
neversleep-noromaid-v0-8068-v97-mkmlizer: ║ The license key for the current software has been verified as ║
neversleep-noromaid-v0-8068-v97-mkmlizer: ║ belonging to: ║
neversleep-noromaid-v0-8068-v97-mkmlizer: ║ ║
neversleep-noromaid-v0-8068-v97-mkmlizer: ║ Chai Research Corp. ║
neversleep-noromaid-v0-8068-v97-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
neversleep-noromaid-v0-8068-v97-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
neversleep-noromaid-v0-8068-v97-mkmlizer: ║ ║
neversleep-noromaid-v0-8068-v97-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
neversleep-noromaid-v0-8068-v97-mkmlizer: Downloaded to shared memory in 121.828s
neversleep-noromaid-v0-8068-v97-mkmlizer: quantizing model to /dev/shm/model_cache
neversleep-noromaid-v0-8068-v97-mkmlizer: Saving flywheel model at /dev/shm/model_cache
neversleep-noromaid-v0-8068-v97-mkmlizer: quantized model in 87.238s
neversleep-noromaid-v0-8068-v97-mkmlizer: Processed model NeverSleep/Noromaid-v0.1-mixtral-8x7b-Instruct-v3 in 209.066s
neversleep-noromaid-v0-8068-v97-mkmlizer: creating bucket guanaco-mkml-models
neversleep-noromaid-v0-8068-v97-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
neversleep-noromaid-v0-8068-v97-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v97
neversleep-noromaid-v0-8068-v97-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v97/config.json
neversleep-noromaid-v0-8068-v97-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v97/special_tokens_map.json
neversleep-noromaid-v0-8068-v97-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v97/tokenizer_config.json
neversleep-noromaid-v0-8068-v97-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v97/tokenizer.json
neversleep-noromaid-v0-8068-v97-mkmlizer: cp /dev/shm/model_cache/tokenizer.model s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v97/tokenizer.model
neversleep-noromaid-v0-8068-v97-mkmlizer: cp /dev/shm/model_cache/flywheel_model.3.safetensors s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v97/flywheel_model.3.safetensors
neversleep-noromaid-v0-8068-v97-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v97/flywheel_model.0.safetensors
neversleep-noromaid-v0-8068-v97-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v97/flywheel_model.1.safetensors
neversleep-noromaid-v0-8068-v97-mkmlizer: cp /dev/shm/model_cache/flywheel_model.2.safetensors s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v97/flywheel_model.2.safetensors
neversleep-noromaid-v0-8068-v97-mkmlizer: loading reward model from rirv938/reward_gpt2_medium_preference_24m_e2
neversleep-noromaid-v0-8068-v97-mkmlizer: Loading 0: 0%| | 0/995 [00:00<?, ?it/s] Loading 0: 5%|▌ | 52/995 [00:01<00:25, 37.67it/s] Loading 0: 11%|█ | 107/995 [00:02<00:22, 39.31it/s] Loading 0: 16%|█▋ | 162/995 [00:04<00:20, 40.31it/s] Loading 0: 21%|██ | 210/995 [00:05<00:20, 38.81it/s] Loading 0: 27%|██▋ | 265/995 [00:06<00:18, 40.18it/s] Loading 0: 28%|██▊ | 277/995 [00:23<00:17, 40.18it/s] Loading 0: 28%|██▊ | 278/995 [00:23<02:01, 5.90it/s] Loading 0: 32%|███▏ | 320/995 [00:25<01:23, 8.09it/s] Loading 0: 37%|███▋ | 368/995 [00:26<00:55, 11.30it/s] Loading 0: 43%|████▎ | 423/995 [00:27<00:36, 15.63it/s] Loading 0: 48%|████▊ | 478/995 [00:28<00:25, 20.21it/s] Loading 0: 53%|█████▎ | 526/995 [00:30<00:19, 23.73it/s] Loading 0: 57%|█████▋ | 564/995 [00:47<00:18, 23.73it/s] Loading 0: 57%|█████▋ | 565/995 [00:47<01:02, 6.91it/s] Loading 0: 58%|█████▊ | 581/995 [00:48<00:57, 7.19it/s] Loading 0: 64%|██████▍ | 636/995 [00:50<00:33, 10.74it/s] Loading 0: 69%|██████▉ | 691/995 [00:51<00:20, 14.72it/s] Loading 0: 74%|███████▍ | 739/995 [00:52<00:13, 18.30it/s] Loading 0: 80%|███████▉ | 794/995 [00:53<00:08, 22.74it/s] Loading 0: 85%|████████▍ | 845/995 [01:10<00:06, 22.74it/s] Loading 0: 85%|████████▌ | 846/995 [01:10<00:19, 7.53it/s] Loading 0: 85%|████████▌ | 849/995 [01:12<00:20, 7.05it/s] Loading 0: 90%|█████████ | 897/995 [01:13<00:09, 10.07it/s] Loading 0: 96%|█████████▌| 952/995 [01:14<00:02, 14.42it/s] Loading 0: 100%|██████████| 995/995 [01:15<00:00, 17.25it/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-v97-mkmlizer: warnings.warn(
neversleep-noromaid-v0-8068-v97-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-v97-mkmlizer: warnings.warn(
neversleep-noromaid-v0-8068-v97-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-v97-mkmlizer: warnings.warn(
neversleep-noromaid-v0-8068-v97-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-v97-mkmlizer: warnings.warn(
neversleep-noromaid-v0-8068-v97-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-v97-mkmlizer: return self.fget.__get__(instance, owner)()
neversleep-noromaid-v0-8068-v97-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
neversleep-noromaid-v0-8068-v97-mkmlizer: Saving duration: 0.449s
neversleep-noromaid-v0-8068-v97-mkmlizer: Processed model rirv938/reward_gpt2_medium_preference_24m_e2 in 5.444s
neversleep-noromaid-v0-8068-v97-mkmlizer: creating bucket guanaco-reward-models
neversleep-noromaid-v0-8068-v97-mkmlizer: Bucket 's3://guanaco-reward-models/' created
neversleep-noromaid-v0-8068-v97-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/neversleep-noromaid-v0-8068-v97_reward
neversleep-noromaid-v0-8068-v97-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/neversleep-noromaid-v0-8068-v97_reward/config.json
neversleep-noromaid-v0-8068-v97-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/neversleep-noromaid-v0-8068-v97_reward/special_tokens_map.json
neversleep-noromaid-v0-8068-v97-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/neversleep-noromaid-v0-8068-v97_reward/tokenizer_config.json
neversleep-noromaid-v0-8068-v97-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/neversleep-noromaid-v0-8068-v97_reward/vocab.json
neversleep-noromaid-v0-8068-v97-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/neversleep-noromaid-v0-8068-v97_reward/merges.txt
neversleep-noromaid-v0-8068-v97-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/neversleep-noromaid-v0-8068-v97_reward/tokenizer.json
neversleep-noromaid-v0-8068-v97-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/neversleep-noromaid-v0-8068-v97_reward/reward.tensors
Job neversleep-noromaid-v0-8068-v97-mkmlizer completed after 258.53s with status: succeeded
Stopping job with name neversleep-noromaid-v0-8068-v97-mkmlizer
Pipeline stage MKMLizer completed in 259.35s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.13s
Running pipeline stage ISVCDeployer
Creating inference service neversleep-noromaid-v0-8068-v97
Waiting for inference service neversleep-noromaid-v0-8068-v97 to be ready
Inference service neversleep-noromaid-v0-8068-v97 ready after 70.34759283065796s
Pipeline stage ISVCDeployer completed in 77.06s
Running pipeline stage StressChecker
Received healthy response to inference request in 3.178926944732666s
Received healthy response to inference request in 2.40960955619812s
Received healthy response to inference request in 2.3533520698547363s
Received healthy response to inference request in 2.384155511856079s
Received healthy response to inference request in 2.3481621742248535s
5 requests
0 failed requests
5th percentile: 2.34920015335083
10th percentile: 2.3502381324768065
20th percentile: 2.35231409072876
30th percentile: 2.359512758255005
40th percentile: 2.371834135055542
50th percentile: 2.384155511856079
60th percentile: 2.3943371295928957
70th percentile: 2.404518747329712
80th percentile: 2.5634730339050296
90th percentile: 2.8711999893188476
95th percentile: 3.0250634670257566
99th percentile: 3.148154249191284
mean time: 2.534841251373291
Pipeline stage StressChecker completed in 13.47s
neversleep-noromaid-v0-_8068_v97 status is now deployed due to DeploymentManager action
neversleep-noromaid-v0-_8068_v97 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics