submission_id: neversleep-noromaid-v0-_8068_v28
developer_uid: chai_backend_admin
status: inactive
model_repo: NeverSleep/Noromaid-v0.1-mixtral-8x7b-Instruct-v3
reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2
generation_params: {'temperature': 0.9, 'top_p': 1.0, 'top_k': 50, 'presence_penalty': 0.5, 'frequency_penalty': 0.5, 'stopping_words': ['\n', '</s>', '<|user|>', '###'], 'max_input_tokens': 512, 'best_of': 1, 'max_output_tokens': 64}
formatter: {'memory_template': "{bot_name}'s Persona: {memory}\n####\n", 'prompt_template': '{prompt}\n<START>\n', 'bot_template': '{bot_name}: {message}\n', 'user_template': '{user_name}: {message}\n', 'response_template': '{bot_name}:'}
reward_formatter: {'memory_template': "{bot_name}'s Persona: {memory}\n####\n", 'prompt_template': '{prompt}\n<START>\n', 'bot_template': '{bot_name}: {message}\n', 'user_template': '{user_name}: {message}\n', 'response_template': '{bot_name}:'}
timestamp: 2024-04-01T19:33:52+00:00
model_name: auto_submit_ukiji_avisojem
model_eval_status: success
safety_score: 0.97
entertaining: 6.84
stay_in_character: 8.38
user_preference: 7.14
double_thumbs_up: 66
thumbs_up: 125
thumbs_down: 55
num_battles: 6244
num_wins: 2822
win_ratio: 0.45195387572069184
celo_rating: 1127.67
Resubmit model
Running pipeline stage MKMLizer
Starting job with name neversleep-noromaid-v0-8068-v28-mkmlizer
Waiting for job on neversleep-noromaid-v0-8068-v28-mkmlizer to finish
neversleep-noromaid-v0-8068-v28-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
neversleep-noromaid-v0-8068-v28-mkmlizer: ║ _____ __ __ ║
neversleep-noromaid-v0-8068-v28-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
neversleep-noromaid-v0-8068-v28-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
neversleep-noromaid-v0-8068-v28-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
neversleep-noromaid-v0-8068-v28-mkmlizer: ║ /___/ ║
neversleep-noromaid-v0-8068-v28-mkmlizer: ║ ║
neversleep-noromaid-v0-8068-v28-mkmlizer: ║ Version: 0.8.6 ║
neversleep-noromaid-v0-8068-v28-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
neversleep-noromaid-v0-8068-v28-mkmlizer: ║ ║
neversleep-noromaid-v0-8068-v28-mkmlizer: ║ The license key for the current software has been verified as ║
neversleep-noromaid-v0-8068-v28-mkmlizer: ║ belonging to: ║
neversleep-noromaid-v0-8068-v28-mkmlizer: ║ ║
neversleep-noromaid-v0-8068-v28-mkmlizer: ║ Chai Research Corp. ║
neversleep-noromaid-v0-8068-v28-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
neversleep-noromaid-v0-8068-v28-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
neversleep-noromaid-v0-8068-v28-mkmlizer: ║ ║
neversleep-noromaid-v0-8068-v28-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
neversleep-noromaid-v0-8068-v28-mkmlizer: /opt/conda/lib/python3.10/site-packages/huggingface_hub/utils/_deprecation.py:131: FutureWarning: 'list_files_info' (from 'huggingface_hub.hf_api') is deprecated and will be removed from version '0.23'. Use `list_repo_tree` and `get_paths_info` instead.
neversleep-noromaid-v0-8068-v28-mkmlizer: warnings.warn(warning_message, FutureWarning)
neversleep-noromaid-v0-8068-v28-mkmlizer: Downloaded to shared memory in 71.309s
neversleep-noromaid-v0-8068-v28-mkmlizer: quantizing model to /dev/shm/model_cache
neversleep-noromaid-v0-8068-v28-mkmlizer: Saving flywheel model at /dev/shm/model_cache
neversleep-noromaid-v0-8068-v28-mkmlizer: quantized model in 62.434s
neversleep-noromaid-v0-8068-v28-mkmlizer: Processed model NeverSleep/Noromaid-v0.1-mixtral-8x7b-Instruct-v3 in 140.191s
neversleep-noromaid-v0-8068-v28-mkmlizer: creating bucket guanaco-mkml-models
neversleep-noromaid-v0-8068-v28-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
neversleep-noromaid-v0-8068-v28-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v28
neversleep-noromaid-v0-8068-v28-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v28/config.json
neversleep-noromaid-v0-8068-v28-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v28/tokenizer_config.json
neversleep-noromaid-v0-8068-v28-mkmlizer: cp /dev/shm/model_cache/tokenizer.model s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v28/tokenizer.model
neversleep-noromaid-v0-8068-v28-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v28/tokenizer.json
neversleep-noromaid-v0-8068-v28-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v28/special_tokens_map.json
neversleep-noromaid-v0-8068-v28-mkmlizer: cp /dev/shm/model_cache/flywheel_model.3.safetensors s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v28/flywheel_model.3.safetensors
neversleep-noromaid-v0-8068-v28-mkmlizer: cp /dev/shm/model_cache/flywheel_model.2.safetensors s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v28/flywheel_model.2.safetensors
neversleep-noromaid-v0-8068-v28-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v28/flywheel_model.1.safetensors
neversleep-noromaid-v0-8068-v28-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v28/flywheel_model.0.safetensors
neversleep-noromaid-v0-8068-v28-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
neversleep-noromaid-v0-8068-v28-mkmlizer: Loading 0: 0%| | 0/995 [00:00<?, ?it/s] Loading 0: 5%|▌ | 52/995 [00:01<00:22, 42.59it/s] Loading 0: 11%|█ | 107/995 [00:02<00:21, 41.48it/s] Loading 0: 16%|█▋ | 162/995 [00:03<00:18, 44.37it/s] Loading 0: 21%|██ | 210/995 [00:05<00:19, 41.11it/s] Loading 0: 27%|██▋ | 265/995 [00:06<00:17, 41.73it/s] Loading 0: 28%|██▊ | 278/995 [00:16<01:18, 9.13it/s] Loading 0: 32%|███▏ | 320/995 [00:17<00:56, 11.95it/s] Loading 0: 37%|███▋ | 368/995 [00:19<00:41, 15.02it/s] Loading 0: 43%|████▎ | 423/995 [00:20<00:28, 20.03it/s] Loading 0: 48%|████▊ | 478/995 [00:22<00:20, 24.79it/s] Loading 0: 53%|█████▎ | 526/995 [00:23<00:16, 28.06it/s] Loading 0: 57%|█████▋ | 565/995 [00:33<00:40, 10.66it/s] Loading 0: 58%|█████▊ | 581/995 [00:34<00:38, 10.78it/s] Loading 0: 64%|██████▍ | 636/995 [00:35<00:23, 15.50it/s] Loading 0: 69%|██████▉ | 691/995 [00:37<00:14, 20.46it/s] Loading 0: 74%|███████▍ | 739/995 [00:38<00:10, 23.58it/s] Loading 0: 80%|███████▉ | 794/995 [00:39<00:07, 27.71it/s] Loading 0: 85%|████████▌ | 846/995 [00:49<00:12, 11.87it/s] Loading 0: 85%|████████▌ | 849/995 [00:51<00:13, 10.63it/s] Loading 0: 90%|█████████ | 897/995 [00:52<00:06, 14.27it/s] Loading 0: 96%|█████████▌| 952/995 [00:53<00:02, 19.65it/s] Loading 0: 100%|██████████| 995/995 [00:54<00:00, 22.45it/s] /opt/conda/lib/python3.10/site-packages/transformers/models/auto/configuration_auto.py:1096: FutureWarning: The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers. Please use `token` instead.
neversleep-noromaid-v0-8068-v28-mkmlizer: warnings.warn(
neversleep-noromaid-v0-8068-v28-mkmlizer: /opt/conda/lib/python3.10/site-packages/transformers/models/auto/tokenization_auto.py:720: FutureWarning: The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers. Please use `token` instead.
neversleep-noromaid-v0-8068-v28-mkmlizer: warnings.warn(
neversleep-noromaid-v0-8068-v28-mkmlizer: /opt/conda/lib/python3.10/site-packages/transformers/models/auto/auto_factory.py:466: FutureWarning: The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers. Please use `token` instead.
neversleep-noromaid-v0-8068-v28-mkmlizer: warnings.warn(
neversleep-noromaid-v0-8068-v28-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-v28-mkmlizer: return self.fget.__get__(instance, owner)()
neversleep-noromaid-v0-8068-v28-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
neversleep-noromaid-v0-8068-v28-mkmlizer: Saving duration: 0.266s
neversleep-noromaid-v0-8068-v28-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 5.083s
neversleep-noromaid-v0-8068-v28-mkmlizer: creating bucket guanaco-reward-models
neversleep-noromaid-v0-8068-v28-mkmlizer: Bucket 's3://guanaco-reward-models/' created
neversleep-noromaid-v0-8068-v28-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/neversleep-noromaid-v0-8068-v28_reward
neversleep-noromaid-v0-8068-v28-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/neversleep-noromaid-v0-8068-v28_reward/config.json
neversleep-noromaid-v0-8068-v28-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/neversleep-noromaid-v0-8068-v28_reward/special_tokens_map.json
neversleep-noromaid-v0-8068-v28-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/neversleep-noromaid-v0-8068-v28_reward/tokenizer_config.json
neversleep-noromaid-v0-8068-v28-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/neversleep-noromaid-v0-8068-v28_reward/merges.txt
neversleep-noromaid-v0-8068-v28-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/neversleep-noromaid-v0-8068-v28_reward/vocab.json
neversleep-noromaid-v0-8068-v28-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/neversleep-noromaid-v0-8068-v28_reward/tokenizer.json
neversleep-noromaid-v0-8068-v28-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/neversleep-noromaid-v0-8068-v28_reward/reward.tensors
Job neversleep-noromaid-v0-8068-v28-mkmlizer completed after 178.47s with status: succeeded
Stopping job with name neversleep-noromaid-v0-8068-v28-mkmlizer
Pipeline stage MKMLizer completed in 183.78s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.13s
Running pipeline stage ISVCDeployer
Creating inference service neversleep-noromaid-v0-8068-v28
Waiting for inference service neversleep-noromaid-v0-8068-v28 to be ready
Inference service neversleep-noromaid-v0-8068-v28 ready after 80.77272701263428s
Pipeline stage ISVCDeployer completed in 88.61s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.0019991397857666s
Received healthy response to inference request in 1.5959675312042236s
Received healthy response to inference request in 1.0366809368133545s
Received healthy response to inference request in 0.8849875926971436s
Received healthy response to inference request in 0.749643087387085s
5 requests
0 failed requests
5th percentile: 0.7767119884490967
10th percentile: 0.8037808895111084
20th percentile: 0.8579186916351318
30th percentile: 0.9153262615203858
40th percentile: 0.9760035991668701
50th percentile: 1.0366809368133545
60th percentile: 1.2603955745697022
70th percentile: 1.4841102123260497
80th percentile: 1.6771738529205322
90th percentile: 1.8395864963531494
95th percentile: 1.920792818069458
99th percentile: 1.985757875442505
mean time: 1.2538556575775146
Pipeline stage StressChecker completed in 7.01s
Running pipeline stage DaemonicModelEvalScorer
Pipeline stage DaemonicModelEvalScorer completed in 0.04s
Running pipeline stage DaemonicSafetyScorer
Pipeline stage DaemonicSafetyScorer completed in 0.04s
Running M-Eval for topic stay_in_character
neversleep-noromaid-v0-_8068_v28 status is now deployed due to DeploymentManager action
M-Eval Dataset for topic stay_in_character is loaded
neversleep-noromaid-v0-_8068_v28 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics