submission_id: neversleep-noromaid-v0-_8068_v37
developer_uid: chai_backend_admin
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': ['\n', '</s>', '<|user|>', '###'], 'max_input_tokens': 512, 'best_of': 4, 'max_output_tokens': 96}
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: 2024-05-06T02:38:51+00:00
model_name: neversleep-noromaid-v0-_8068_v37
model_eval_status: success
double_thumbs_up: 229
thumbs_up: 334
thumbs_down: 123
num_battles: 12978
num_wins: 6743
celo_rating: 1199.18
entertaining: 7.46
stay_in_character: 8.71
user_preference: 7.76
safety_score: None
submission_type: basic
model_architecture: MixtralForCausalLM
model_num_parameters: 46702792704.0
best_of: 4
max_input_tokens: 512
max_output_tokens: 96
display_name: neversleep-noromaid-v0-_8068_v37
double_thumbs_up_ratio: 0.3338192419825073
feedback_count: 686
ineligible_reason: max_output_tokens!=64
language_model: NeverSleep/Noromaid-v0.1-mixtral-8x7b-Instruct-v3
model_score: 7.976666666666667
model_size: 47B
reward_model: rirv938/reward_gpt2_medium_preference_24m_e2
single_thumbs_up_ratio: 0.4868804664723032
thumbs_down_ratio: 0.1793002915451895
thumbs_up_ratio: 0.8206997084548106
us_pacific_date: 2024-05-05
win_ratio: 0.5195715826783788
Resubmit model
Running pipeline stage MKMLizer
Starting job with name neversleep-noromaid-v0-8068-v37-mkmlizer
Waiting for job on neversleep-noromaid-v0-8068-v37-mkmlizer to finish
neversleep-noromaid-v0-8068-v37-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
neversleep-noromaid-v0-8068-v37-mkmlizer: ║ _____ __ __ ║
neversleep-noromaid-v0-8068-v37-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
neversleep-noromaid-v0-8068-v37-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
neversleep-noromaid-v0-8068-v37-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
neversleep-noromaid-v0-8068-v37-mkmlizer: ║ /___/ ║
neversleep-noromaid-v0-8068-v37-mkmlizer: ║ ║
neversleep-noromaid-v0-8068-v37-mkmlizer: ║ Version: 0.8.10 ║
neversleep-noromaid-v0-8068-v37-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
neversleep-noromaid-v0-8068-v37-mkmlizer: ║ ║
neversleep-noromaid-v0-8068-v37-mkmlizer: ║ The license key for the current software has been verified as ║
neversleep-noromaid-v0-8068-v37-mkmlizer: ║ belonging to: ║
neversleep-noromaid-v0-8068-v37-mkmlizer: ║ ║
neversleep-noromaid-v0-8068-v37-mkmlizer: ║ Chai Research Corp. ║
neversleep-noromaid-v0-8068-v37-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
neversleep-noromaid-v0-8068-v37-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
neversleep-noromaid-v0-8068-v37-mkmlizer: ║ ║
neversleep-noromaid-v0-8068-v37-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
neversleep-noromaid-v0-8068-v37-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-v37-mkmlizer: warnings.warn(warning_message, FutureWarning)
neversleep-noromaid-v0-8068-v37-mkmlizer: Downloaded to shared memory in 286.076s
neversleep-noromaid-v0-8068-v37-mkmlizer: quantizing model to /dev/shm/model_cache
neversleep-noromaid-v0-8068-v37-mkmlizer: Saving flywheel model at /dev/shm/model_cache
neversleep-noromaid-v0-8068-v37-mkmlizer: quantized model in 52.134s
neversleep-noromaid-v0-8068-v37-mkmlizer: Processed model NeverSleep/Noromaid-v0.1-mixtral-8x7b-Instruct-v3 in 344.645s
neversleep-noromaid-v0-8068-v37-mkmlizer: creating bucket guanaco-mkml-models
neversleep-noromaid-v0-8068-v37-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
neversleep-noromaid-v0-8068-v37-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v37
neversleep-noromaid-v0-8068-v37-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v37/config.json
neversleep-noromaid-v0-8068-v37-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v37/special_tokens_map.json
neversleep-noromaid-v0-8068-v37-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v37/tokenizer_config.json
neversleep-noromaid-v0-8068-v37-mkmlizer: cp /dev/shm/model_cache/tokenizer.model s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v37/tokenizer.model
neversleep-noromaid-v0-8068-v37-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v37/tokenizer.json
neversleep-noromaid-v0-8068-v37-mkmlizer: cp /dev/shm/model_cache/flywheel_model.3.safetensors s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v37/flywheel_model.3.safetensors
neversleep-noromaid-v0-8068-v37-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v37/flywheel_model.1.safetensors
neversleep-noromaid-v0-8068-v37-mkmlizer: loading reward model from rirv938/reward_gpt2_medium_preference_24m_e2
neversleep-noromaid-v0-8068-v37-mkmlizer: Loading 0: 0%| | 0/995 [00:00<?, ?it/s] Loading 0: 11%|█ | 107/995 [00:01<00:15, 57.29it/s] Loading 0: 21%|██ | 210/995 [00:03<00:14, 55.69it/s] Loading 0: 28%|██▊ | 278/995 [00:13<00:44, 16.18it/s] Loading 0: 32%|███▏ | 320/995 [00:14<00:36, 18.67it/s] Loading 0: 43%|████▎ | 423/995 [00:16<00:21, 26.83it/s] Loading 0: 53%|█████▎ | 526/995 [00:18<00:13, 34.06it/s] Loading 0: 57%|█████▋ | 565/995 [00:27<00:27, 15.48it/s] Loading 0: 58%|█████▊ | 581/995 [00:28<00:26, 15.36it/s] Loading 0: 69%|██████▉ | 691/995 [00:29<00:12, 24.12it/s] Loading 0: 80%|███████▉ | 794/995 [00:31<00:06, 31.64it/s] Loading 0: 85%|████████▌ | 846/995 [00:40<00:09, 16.17it/s] Loading 0: 96%|█████████▌| 952/995 [00:43<00:02, 20.81it/s] Loading 0: 100%|██████████| 995/995 [00:44<00:00, 22.58it/s] /opt/conda/lib/python3.10/site-packages/transformers/models/auto/configuration_auto.py:913: FutureWarning: The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers. Please use `token` instead.
neversleep-noromaid-v0-8068-v37-mkmlizer: warnings.warn(
neversleep-noromaid-v0-8068-v37-mkmlizer: /opt/conda/lib/python3.10/site-packages/transformers/models/auto/tokenization_auto.py:757: FutureWarning: The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers. Please use `token` instead.
neversleep-noromaid-v0-8068-v37-mkmlizer: warnings.warn(
neversleep-noromaid-v0-8068-v37-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-v37-mkmlizer: warnings.warn(
neversleep-noromaid-v0-8068-v37-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-v37-mkmlizer: return self.fget.__get__(instance, owner)()
neversleep-noromaid-v0-8068-v37-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
neversleep-noromaid-v0-8068-v37-mkmlizer: Saving duration: 0.252s
neversleep-noromaid-v0-8068-v37-mkmlizer: Processed model rirv938/reward_gpt2_medium_preference_24m_e2 in 10.752s
neversleep-noromaid-v0-8068-v37-mkmlizer: creating bucket guanaco-reward-models
neversleep-noromaid-v0-8068-v37-mkmlizer: Bucket 's3://guanaco-reward-models/' created
neversleep-noromaid-v0-8068-v37-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/neversleep-noromaid-v0-8068-v37_reward
neversleep-noromaid-v0-8068-v37-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/neversleep-noromaid-v0-8068-v37_reward/config.json
neversleep-noromaid-v0-8068-v37-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/neversleep-noromaid-v0-8068-v37_reward/special_tokens_map.json
neversleep-noromaid-v0-8068-v37-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/neversleep-noromaid-v0-8068-v37_reward/tokenizer_config.json
neversleep-noromaid-v0-8068-v37-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/neversleep-noromaid-v0-8068-v37_reward/merges.txt
neversleep-noromaid-v0-8068-v37-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/neversleep-noromaid-v0-8068-v37_reward/vocab.json
neversleep-noromaid-v0-8068-v37-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/neversleep-noromaid-v0-8068-v37_reward/tokenizer.json
neversleep-noromaid-v0-8068-v37-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/neversleep-noromaid-v0-8068-v37_reward/reward.tensors
Job neversleep-noromaid-v0-8068-v37-mkmlizer completed after 392.75s with status: succeeded
Stopping job with name neversleep-noromaid-v0-8068-v37-mkmlizer
Pipeline stage MKMLizer completed in 394.26s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.41s
Running pipeline stage ISVCDeployer
Creating inference service neversleep-noromaid-v0-8068-v37
Waiting for inference service neversleep-noromaid-v0-8068-v37 to be ready
Inference service neversleep-noromaid-v0-8068-v37 ready after 91.29377698898315s
Pipeline stage ISVCDeployer completed in 92.85s
Running pipeline stage StressChecker
HTTP Request: %s %s "%s %d %s"
Received healthy response to inference request in 4.096860885620117s
HTTP Request: %s %s "%s %d %s"
Received healthy response to inference request in 2.504244089126587s
HTTP Request: %s %s "%s %d %s"
Received healthy response to inference request in 3.144167900085449s
HTTP Request: %s %s "%s %d %s"
Received healthy response to inference request in 3.5223188400268555s
HTTP Request: %s %s "%s %d %s"
Received healthy response to inference request in 3.492671012878418s
5 requests
0 failed requests
5th percentile: 2.6322288513183594
10th percentile: 2.760213613510132
20th percentile: 3.0161831378936768
30th percentile: 3.213868522644043
40th percentile: 3.3532697677612306
50th percentile: 3.492671012878418
60th percentile: 3.504530143737793
70th percentile: 3.516389274597168
80th percentile: 3.637227249145508
90th percentile: 3.8670440673828126
95th percentile: 3.9819524765014647
99th percentile: 4.073879203796387
mean time: 3.3520525455474854
Pipeline stage StressChecker completed in 20.47s
Running pipeline stage DaemonicModelEvalScorer
Pipeline stage DaemonicModelEvalScorer completed in 0.16s
Running pipeline stage DaemonicSafetyScorer
Running M-Eval for topic stay_in_character
Pipeline stage DaemonicSafetyScorer completed in 0.22s
%s, retrying in %s seconds...
M-Eval Dataset for topic stay_in_character is loaded
neversleep-noromaid-v0-_8068_v37 status is now deployed due to DeploymentManager action
%s, retrying in %s seconds...
neversleep-noromaid-v0-_8068_v37 status is now inactive due to admin request

Usage Metrics

Latency Metrics