submission_id: neversleep-noromaid-v0-_8068_v27
developer_uid: chai_backend_admin
status: torndown
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: 2024-04-01T19:32:45+00:00
model_name: auto_submit_ukiji_avisojem
model_eval_status: success
safety_score: 0.97
entertaining: 6.86
stay_in_character: 8.23
user_preference: 7.26
double_thumbs_up: 81
thumbs_up: 101
thumbs_down: 41
num_battles: 5168
num_wins: 2378
win_ratio: 0.4601393188854489
celo_rating: 1132.65
Resubmit model
Running pipeline stage MKMLizer
Starting job with name neversleep-noromaid-v0-8068-v27-mkmlizer
Waiting for job on neversleep-noromaid-v0-8068-v27-mkmlizer to finish
Stopping job with name neversleep-noromaid-v0-8068-v27-mkmlizer
%s, retrying in %s seconds...
Starting job with name neversleep-noromaid-v0-8068-v27-mkmlizer
Waiting for job on neversleep-noromaid-v0-8068-v27-mkmlizer to finish
neversleep-noromaid-v0-8068-v27-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
neversleep-noromaid-v0-8068-v27-mkmlizer: ║ _____ __ __ ║
neversleep-noromaid-v0-8068-v27-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
neversleep-noromaid-v0-8068-v27-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
neversleep-noromaid-v0-8068-v27-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
neversleep-noromaid-v0-8068-v27-mkmlizer: ║ /___/ ║
neversleep-noromaid-v0-8068-v27-mkmlizer: ║ ║
neversleep-noromaid-v0-8068-v27-mkmlizer: ║ Version: 0.8.6 ║
neversleep-noromaid-v0-8068-v27-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
neversleep-noromaid-v0-8068-v27-mkmlizer: ║ ║
neversleep-noromaid-v0-8068-v27-mkmlizer: ║ The license key for the current software has been verified as ║
neversleep-noromaid-v0-8068-v27-mkmlizer: ║ belonging to: ║
neversleep-noromaid-v0-8068-v27-mkmlizer: ║ ║
neversleep-noromaid-v0-8068-v27-mkmlizer: ║ Chai Research Corp. ║
neversleep-noromaid-v0-8068-v27-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
neversleep-noromaid-v0-8068-v27-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
neversleep-noromaid-v0-8068-v27-mkmlizer: ║ ║
neversleep-noromaid-v0-8068-v27-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
neversleep-noromaid-v0-8068-v27-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-v27-mkmlizer: warnings.warn(warning_message, FutureWarning)
neversleep-noromaid-v0-8068-v27-mkmlizer: Downloaded to shared memory in 87.717s
neversleep-noromaid-v0-8068-v27-mkmlizer: quantizing model to /dev/shm/model_cache
neversleep-noromaid-v0-8068-v27-mkmlizer: Saving flywheel model at /dev/shm/model_cache
neversleep-noromaid-v0-8068-v27-mkmlizer: quantized model in 73.142s
neversleep-noromaid-v0-8068-v27-mkmlizer: Processed model NeverSleep/Noromaid-v0.1-mixtral-8x7b-Instruct-v3 in 169.457s
neversleep-noromaid-v0-8068-v27-mkmlizer: creating bucket guanaco-mkml-models
neversleep-noromaid-v0-8068-v27-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
neversleep-noromaid-v0-8068-v27-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v27
neversleep-noromaid-v0-8068-v27-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v27/tokenizer_config.json
neversleep-noromaid-v0-8068-v27-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v27/config.json
neversleep-noromaid-v0-8068-v27-mkmlizer: cp /dev/shm/model_cache/tokenizer.model s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v27/tokenizer.model
neversleep-noromaid-v0-8068-v27-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v27/tokenizer.json
neversleep-noromaid-v0-8068-v27-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v27/special_tokens_map.json
neversleep-noromaid-v0-8068-v27-mkmlizer: cp /dev/shm/model_cache/flywheel_model.3.safetensors s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v27/flywheel_model.3.safetensors
neversleep-noromaid-v0-8068-v27-mkmlizer: cp /dev/shm/model_cache/flywheel_model.2.safetensors s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v27/flywheel_model.2.safetensors
neversleep-noromaid-v0-8068-v27-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v27/flywheel_model.1.safetensors
neversleep-noromaid-v0-8068-v27-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v27/flywheel_model.0.safetensors
neversleep-noromaid-v0-8068-v27-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
neversleep-noromaid-v0-8068-v27-mkmlizer: Loading 0: 0%| | 0/995 [00:00<?, ?it/s] Loading 0: 5%|▌ | 52/995 [00:01<00:22, 41.98it/s] Loading 0: 11%|█ | 107/995 [00:02<00:22, 39.47it/s] Loading 0: 16%|█▋ | 162/995 [00:03<00:20, 40.80it/s] Loading 0: 21%|██ | 210/995 [00:05<00:23, 33.01it/s] Loading 0: 27%|██▋ | 265/995 [00:07<00:23, 31.72it/s] Loading 0: 28%|██▊ | 278/995 [00:19<01:29, 7.98it/s] Loading 0: 32%|███▏ | 320/995 [00:20<01:05, 10.30it/s] Loading 0: 37%|███▋ | 368/995 [00:22<00:46, 13.37it/s] Loading 0: 43%|████▎ | 423/995 [00:24<00:33, 17.22it/s] Loading 0: 48%|████▊ | 478/995 [00:25<00:25, 20.53it/s] Loading 0: 53%|█████▎ | 526/995 [00:27<00:21, 22.26it/s] Loading 0: 57%|█████▋ | 565/995 [00:38<00:46, 9.19it/s] Loading 0: 58%|█████▊ | 581/995 [00:40<00:45, 9.10it/s] Loading 0: 64%|██████▍ | 636/995 [00:42<00:27, 13.01it/s] Loading 0: 69%|██████▉ | 691/995 [00:43<00:18, 16.74it/s] Loading 0: 74%|███████▍ | 739/995 [00:45<00:12, 20.04it/s] Loading 0: 80%|███████▉ | 794/995 [00:46<00:08, 23.84it/s] Loading 0: 85%|████████▌ | 846/995 [00:57<00:14, 10.38it/s] Loading 0: 85%|████████▌ | 849/995 [00:59<00:15, 9.16it/s] Loading 0: 90%|█████████ | 897/995 [01:01<00:07, 12.31it/s] Loading 0: 96%|█████████▌| 952/995 [01:02<00:02, 16.26it/s] Loading 0: 100%|██████████| 995/995 [01:04<00:00, 18.70it/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-v27-mkmlizer: warnings.warn(
neversleep-noromaid-v0-8068-v27-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-v27-mkmlizer: warnings.warn(
neversleep-noromaid-v0-8068-v27-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-v27-mkmlizer: warnings.warn(
neversleep-noromaid-v0-8068-v27-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-v27-mkmlizer: return self.fget.__get__(instance, owner)()
neversleep-noromaid-v0-8068-v27-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
neversleep-noromaid-v0-8068-v27-mkmlizer: Saving duration: 0.293s
neversleep-noromaid-v0-8068-v27-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 3.910s
neversleep-noromaid-v0-8068-v27-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/neversleep-noromaid-v0-8068-v27_reward/reward.tensors
Job neversleep-noromaid-v0-8068-v27-mkmlizer completed after 209.22s with status: succeeded
Stopping job with name neversleep-noromaid-v0-8068-v27-mkmlizer
Pipeline stage MKMLizer completed in 211.22s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.09s
Running pipeline stage ISVCDeployer
Creating inference service neversleep-noromaid-v0-8068-v27
Waiting for inference service neversleep-noromaid-v0-8068-v27 to be ready
Inference service neversleep-noromaid-v0-8068-v27 ready after 60.39341950416565s
Pipeline stage ISVCDeployer completed in 66.18s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.6199593544006348s
Received healthy response to inference request in 0.8180632591247559s
Received healthy response to inference request in 1.6495575904846191s
Received healthy response to inference request in 0.9449124336242676s
Received healthy response to inference request in 0.8576450347900391s
5 requests
0 failed requests
5th percentile: 0.8259796142578125
10th percentile: 0.8338959693908692
20th percentile: 0.8497286796569824
30th percentile: 0.8750985145568848
40th percentile: 0.9100054740905762
50th percentile: 0.9449124336242676
60th percentile: 1.2149312019348144
70th percentile: 1.4849499702453612
80th percentile: 1.6258790016174316
90th percentile: 1.6377182960510255
95th percentile: 1.6436379432678223
99th percentile: 1.6483736610412598
mean time: 1.1780275344848632
Pipeline stage StressChecker completed in 6.60s
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
M-Eval Dataset for topic stay_in_character is loaded
neversleep-noromaid-v0-_8068_v27 status is now deployed due to DeploymentManager action
admin requested tearing down of neversleep-noromaid-v0-_8068_v27
Running pipeline stage ISVCDeleter
Checking if service neversleep-noromaid-v0-8068-v27 is running
Tearing down inference service neversleep-noromaid-v0-8068-v27
Toredown service neversleep-noromaid-v0-8068-v27
Pipeline stage ISVCDeleter completed in 6.64s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key neversleep-noromaid-v0-8068-v27/config.json from bucket guanaco-mkml-models
Deleting key neversleep-noromaid-v0-8068-v27/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key neversleep-noromaid-v0-8068-v27/flywheel_model.1.safetensors from bucket guanaco-mkml-models
Deleting key neversleep-noromaid-v0-8068-v27/flywheel_model.2.safetensors from bucket guanaco-mkml-models
Deleting key neversleep-noromaid-v0-8068-v27/flywheel_model.3.safetensors from bucket guanaco-mkml-models
Deleting key neversleep-noromaid-v0-8068-v27/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key neversleep-noromaid-v0-8068-v27/tokenizer.json from bucket guanaco-mkml-models
Deleting key neversleep-noromaid-v0-8068-v27/tokenizer.model from bucket guanaco-mkml-models
Deleting key neversleep-noromaid-v0-8068-v27/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key neversleep-noromaid-v0-8068-v27_reward/config.json from bucket guanaco-reward-models
Deleting key neversleep-noromaid-v0-8068-v27_reward/merges.txt from bucket guanaco-reward-models
Deleting key neversleep-noromaid-v0-8068-v27_reward/reward.tensors from bucket guanaco-reward-models
Deleting key neversleep-noromaid-v0-8068-v27_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key neversleep-noromaid-v0-8068-v27_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key neversleep-noromaid-v0-8068-v27_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key neversleep-noromaid-v0-8068-v27_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 7.02s
neversleep-noromaid-v0-_8068_v27 status is now torndown due to DeploymentManager action

Usage Metrics

Latency Metrics