submission_id: neversleep-noromaid-v0-_8068_v33
developer_uid: chaiverse_console_tests
status: torndown
model_repo: NeverSleep/Noromaid-v0.1-mixtral-8x7b-Instruct-v3
reward_repo: rirv938/reward_gpt2_medium_preference_24m_e2
generation_params: {'temperature': 0.8, 'top_p': 0.9, 'min_p': 0.0, 'top_k': 70, 'presence_penalty': 0.9, 'frequency_penalty': 0.9, 'stopping_words': ['\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}.\nEngage in a chat with {user_name} while staying in character. Try to flirt with {user_name}. Engage in *roleplay* actions. Describe the scene dramatically. \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: 2024-04-27T02:44:22+00:00
model_name: neversleep_v3
model_eval_status: success
model_group: NeverSleep/Noromaid-v0.1
num_battles: 8277
num_wins: 4390
celo_rating: 1178.78
propriety_score: 0.0
propriety_total_count: 0.0
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_v3
ineligible_reason: propriety_total_count < 800
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: 2024-04-26
win_ratio: 0.530385405340099
preference_data_url: None
Resubmit model
Running pipeline stage MKMLizer
Starting job with name neversleep-noromaid-v0-8068-v33-mkmlizer
Waiting for job on neversleep-noromaid-v0-8068-v33-mkmlizer to finish
neversleep-noromaid-v0-8068-v33-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
neversleep-noromaid-v0-8068-v33-mkmlizer: ║ _____ __ __ ║
neversleep-noromaid-v0-8068-v33-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
neversleep-noromaid-v0-8068-v33-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
neversleep-noromaid-v0-8068-v33-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
neversleep-noromaid-v0-8068-v33-mkmlizer: ║ /___/ ║
neversleep-noromaid-v0-8068-v33-mkmlizer: ║ ║
neversleep-noromaid-v0-8068-v33-mkmlizer: ║ Version: 0.8.10 ║
neversleep-noromaid-v0-8068-v33-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
neversleep-noromaid-v0-8068-v33-mkmlizer: ║ ║
neversleep-noromaid-v0-8068-v33-mkmlizer: ║ The license key for the current software has been verified as ║
neversleep-noromaid-v0-8068-v33-mkmlizer: ║ belonging to: ║
neversleep-noromaid-v0-8068-v33-mkmlizer: ║ ║
neversleep-noromaid-v0-8068-v33-mkmlizer: ║ Chai Research Corp. ║
neversleep-noromaid-v0-8068-v33-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
neversleep-noromaid-v0-8068-v33-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
neversleep-noromaid-v0-8068-v33-mkmlizer: ║ ║
neversleep-noromaid-v0-8068-v33-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
neversleep-noromaid-v0-8068-v33-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-v33-mkmlizer: warnings.warn(warning_message, FutureWarning)
neversleep-noromaid-v0-8068-v33-mkmlizer: Downloaded to shared memory in 63.611s
neversleep-noromaid-v0-8068-v33-mkmlizer: quantizing model to /dev/shm/model_cache
neversleep-noromaid-v0-8068-v33-mkmlizer: Saving flywheel model at /dev/shm/model_cache
neversleep-noromaid-v0-8068-v33-mkmlizer: quantized model in 51.479s
neversleep-noromaid-v0-8068-v33-mkmlizer: Processed model NeverSleep/Noromaid-v0.1-mixtral-8x7b-Instruct-v3 in 121.838s
neversleep-noromaid-v0-8068-v33-mkmlizer: creating bucket guanaco-mkml-models
neversleep-noromaid-v0-8068-v33-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
neversleep-noromaid-v0-8068-v33-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v33
neversleep-noromaid-v0-8068-v33-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v33/special_tokens_map.json
neversleep-noromaid-v0-8068-v33-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v33/config.json
neversleep-noromaid-v0-8068-v33-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v33/tokenizer.json
neversleep-noromaid-v0-8068-v33-mkmlizer: cp /dev/shm/model_cache/tokenizer.model s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v33/tokenizer.model
neversleep-noromaid-v0-8068-v33-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v33/tokenizer_config.json
neversleep-noromaid-v0-8068-v33-mkmlizer: cp /dev/shm/model_cache/flywheel_model.3.safetensors s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v33/flywheel_model.3.safetensors
neversleep-noromaid-v0-8068-v33-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v33/flywheel_model.0.safetensors
neversleep-noromaid-v0-8068-v33-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v33/flywheel_model.1.safetensors
neversleep-noromaid-v0-8068-v33-mkmlizer: cp /dev/shm/model_cache/flywheel_model.2.safetensors s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v33/flywheel_model.2.safetensors
neversleep-noromaid-v0-8068-v33-mkmlizer: loading reward model from rirv938/reward_gpt2_medium_preference_24m_e2
neversleep-noromaid-v0-8068-v33-mkmlizer: Loading 0: 0%| | 0/995 [00:00<?, ?it/s] Loading 0: 5%|▌ | 54/995 [00:00<00:17, 54.03it/s] Loading 0: 16%|█▋ | 162/995 [00:02<00:14, 57.68it/s] Loading 0: 27%|██▋ | 265/995 [00:04<00:12, 56.99it/s] Loading 0: 28%|██▊ | 278/995 [00:13<00:51, 13.90it/s] Loading 0: 32%|███▏ | 320/995 [00:14<00:40, 16.79it/s] Loading 0: 43%|████▎ | 423/995 [00:16<00:22, 25.80it/s] Loading 0: 53%|█████▎ | 526/995 [00:18<00:14, 33.49it/s] Loading 0: 57%|█████▋ | 565/995 [00:27<00:28, 14.98it/s] Loading 0: 58%|█████▊ | 581/995 [00:28<00:27, 14.93it/s] Loading 0: 69%|██████▉ | 691/995 [00:30<00:12, 23.57it/s] Loading 0: 80%|███████▉ | 794/995 [00:31<00:06, 30.99it/s] Loading 0: 85%|████████▌ | 846/995 [00:40<00:09, 16.00it/s] Loading 0: 96%|█████████▌| 952/995 [00:43<00:02, 20.58it/s] Loading 0: 100%|██████████| 995/995 [00:44<00:00, 22.62it/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-v33-mkmlizer: warnings.warn(
neversleep-noromaid-v0-8068-v33-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-v33-mkmlizer: warnings.warn(
neversleep-noromaid-v0-8068-v33-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-v33-mkmlizer: warnings.warn(
neversleep-noromaid-v0-8068-v33-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-v33-mkmlizer: return self.fget.__get__(instance, owner)()
neversleep-noromaid-v0-8068-v33-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
neversleep-noromaid-v0-8068-v33-mkmlizer: Saving duration: 0.229s
neversleep-noromaid-v0-8068-v33-mkmlizer: Processed model rirv938/reward_gpt2_medium_preference_24m_e2 in 5.283s
neversleep-noromaid-v0-8068-v33-mkmlizer: creating bucket guanaco-reward-models
neversleep-noromaid-v0-8068-v33-mkmlizer: Bucket 's3://guanaco-reward-models/' created
neversleep-noromaid-v0-8068-v33-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/neversleep-noromaid-v0-8068-v33_reward
neversleep-noromaid-v0-8068-v33-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/neversleep-noromaid-v0-8068-v33_reward/config.json
neversleep-noromaid-v0-8068-v33-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/neversleep-noromaid-v0-8068-v33_reward/special_tokens_map.json
neversleep-noromaid-v0-8068-v33-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/neversleep-noromaid-v0-8068-v33_reward/tokenizer_config.json
neversleep-noromaid-v0-8068-v33-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/neversleep-noromaid-v0-8068-v33_reward/vocab.json
neversleep-noromaid-v0-8068-v33-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/neversleep-noromaid-v0-8068-v33_reward/merges.txt
neversleep-noromaid-v0-8068-v33-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/neversleep-noromaid-v0-8068-v33_reward/tokenizer.json
neversleep-noromaid-v0-8068-v33-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/neversleep-noromaid-v0-8068-v33_reward/reward.tensors
Job neversleep-noromaid-v0-8068-v33-mkmlizer completed after 168.85s with status: succeeded
Stopping job with name neversleep-noromaid-v0-8068-v33-mkmlizer
Pipeline stage MKMLizer completed in 173.42s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.10s
Running pipeline stage ISVCDeployer
Creating inference service neversleep-noromaid-v0-8068-v33
Waiting for inference service neversleep-noromaid-v0-8068-v33 to be ready
Inference service neversleep-noromaid-v0-8068-v33 ready after 50.2907657623291s
Pipeline stage ISVCDeployer completed in 57.38s
Running pipeline stage StressChecker
Received healthy response to inference request in 3.008131980895996s
Received healthy response to inference request in 2.5881576538085938s
Received healthy response to inference request in 1.9584910869598389s
Received healthy response to inference request in 1.629218578338623s
Received healthy response to inference request in 1.6184651851654053s
5 requests
0 failed requests
5th percentile: 1.6206158638000487
10th percentile: 1.6227665424346924
20th percentile: 1.6270678997039796
30th percentile: 1.6950730800628662
40th percentile: 1.8267820835113526
50th percentile: 1.9584910869598389
60th percentile: 2.2103577136993406
70th percentile: 2.462224340438843
80th percentile: 2.672152519226074
90th percentile: 2.840142250061035
95th percentile: 2.9241371154785156
99th percentile: 2.9913330078125
mean time: 2.1604928970336914
Pipeline stage StressChecker completed in 11.42s
Running pipeline stage DaemonicModelEvalScorer
Pipeline stage DaemonicModelEvalScorer completed in 0.03s
Running pipeline stage DaemonicSafetyScorer
Running M-Eval for topic stay_in_character
Pipeline stage DaemonicSafetyScorer completed in 0.04s
%s, retrying in %s seconds...
M-Eval Dataset for topic stay_in_character is loaded
neversleep-noromaid-v0-_8068_v33 status is now deployed due to DeploymentManager action
%s, retrying in %s seconds...
neversleep-noromaid-v0-_8068_v33 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of neversleep-noromaid-v0-_8068_v33
Running pipeline stage ISVCDeleter
Checking if service neversleep-noromaid-v0-8068-v33 is running
Tearing down inference service neversleep-noromaid-v0-8068-v33
Toredown service neversleep-noromaid-v0-8068-v33
Pipeline stage ISVCDeleter completed in 6.85s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key neversleep-noromaid-v0-8068-v33/config.json from bucket guanaco-mkml-models
Deleting key neversleep-noromaid-v0-8068-v33/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key neversleep-noromaid-v0-8068-v33/flywheel_model.1.safetensors from bucket guanaco-mkml-models
Deleting key neversleep-noromaid-v0-8068-v33/flywheel_model.2.safetensors from bucket guanaco-mkml-models
Deleting key neversleep-noromaid-v0-8068-v33/flywheel_model.3.safetensors from bucket guanaco-mkml-models
Deleting key neversleep-noromaid-v0-8068-v33/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key neversleep-noromaid-v0-8068-v33/tokenizer.json from bucket guanaco-mkml-models
Deleting key neversleep-noromaid-v0-8068-v33/tokenizer.model from bucket guanaco-mkml-models
Deleting key neversleep-noromaid-v0-8068-v33/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key neversleep-noromaid-v0-8068-v33_reward/config.json from bucket guanaco-reward-models
Deleting key neversleep-noromaid-v0-8068-v33_reward/merges.txt from bucket guanaco-reward-models
Deleting key neversleep-noromaid-v0-8068-v33_reward/reward.tensors from bucket guanaco-reward-models
Deleting key neversleep-noromaid-v0-8068-v33_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key neversleep-noromaid-v0-8068-v33_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key neversleep-noromaid-v0-8068-v33_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key neversleep-noromaid-v0-8068-v33_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 5.55s
neversleep-noromaid-v0-_8068_v33 status is now torndown due to DeploymentManager action

Usage Metrics

Latency Metrics