submission_id: neversleep-noromaid-v0-_8068_v24
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: 2024-04-01T19:25:38+00:00
model_name: auto_submit_etiye_uraremow
model_eval_status: success
safety_score: 0.96
entertaining: 6.54
stay_in_character: 8.33
user_preference: 7.48
double_thumbs_up: 67
thumbs_up: 114
thumbs_down: 48
num_battles: 6331
num_wins: 2902
win_ratio: 0.4583794029379245
celo_rating: 1132.08
Resubmit model
Running pipeline stage MKMLizer
Starting job with name neversleep-noromaid-v0-8068-v24-mkmlizer
Waiting for job on neversleep-noromaid-v0-8068-v24-mkmlizer to finish
Failed to get response for submission neversleep-noromaidxopen_2041_v2: ('http://neversleep-noromaidxopen-2041-v2-predictor-default.tenant-chaiml-guanaco.knative.ord1.coreweave.cloud/v1/models/GPT-J-6B-lit-v2:predict', 'read tcp 127.0.0.1:34270->127.0.0.1:8080: read: connection reset by peer\n')
Failed to get response for submission anhnv125-llama-op-v17-1_v27: ('http://anhnv125-llama-op-v17-1-v27-predictor-default.tenant-chaiml-guanaco.knative.ord1.coreweave.cloud/v1/models/GPT-J-6B-lit-v2:predict', 'read tcp 127.0.0.1:52550->127.0.0.1:8080: read: connection reset by peer\n')
neversleep-noromaid-v0-8068-v24-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
neversleep-noromaid-v0-8068-v24-mkmlizer: ║ _____ __ __ ║
neversleep-noromaid-v0-8068-v24-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
neversleep-noromaid-v0-8068-v24-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
neversleep-noromaid-v0-8068-v24-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
neversleep-noromaid-v0-8068-v24-mkmlizer: ║ /___/ ║
neversleep-noromaid-v0-8068-v24-mkmlizer: ║ ║
neversleep-noromaid-v0-8068-v24-mkmlizer: ║ Version: 0.8.6 ║
neversleep-noromaid-v0-8068-v24-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
neversleep-noromaid-v0-8068-v24-mkmlizer: ║ ║
neversleep-noromaid-v0-8068-v24-mkmlizer: ║ The license key for the current software has been verified as ║
neversleep-noromaid-v0-8068-v24-mkmlizer: ║ belonging to: ║
neversleep-noromaid-v0-8068-v24-mkmlizer: ║ ║
neversleep-noromaid-v0-8068-v24-mkmlizer: ║ Chai Research Corp. ║
neversleep-noromaid-v0-8068-v24-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
neversleep-noromaid-v0-8068-v24-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
neversleep-noromaid-v0-8068-v24-mkmlizer: ║ ║
neversleep-noromaid-v0-8068-v24-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
neversleep-noromaid-v0-8068-v24-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-v24-mkmlizer: warnings.warn(warning_message, FutureWarning)
neversleep-noromaid-v0-8068-v24-mkmlizer: Downloaded to shared memory in 112.369s
neversleep-noromaid-v0-8068-v24-mkmlizer: quantizing model to /dev/shm/model_cache
neversleep-noromaid-v0-8068-v24-mkmlizer: Saving flywheel model at /dev/shm/model_cache
neversleep-noromaid-v0-8068-v24-mkmlizer: quantized model in 60.823s
neversleep-noromaid-v0-8068-v24-mkmlizer: creating bucket guanaco-mkml-models
neversleep-noromaid-v0-8068-v24-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
neversleep-noromaid-v0-8068-v24-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v24
neversleep-noromaid-v0-8068-v24-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v24/tokenizer.json
neversleep-noromaid-v0-8068-v24-mkmlizer: cp /dev/shm/model_cache/tokenizer.model s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v24/tokenizer.model
neversleep-noromaid-v0-8068-v24-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v24/tokenizer_config.json
neversleep-noromaid-v0-8068-v24-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v24/config.json
neversleep-noromaid-v0-8068-v24-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v24/special_tokens_map.json
neversleep-noromaid-v0-8068-v24-mkmlizer: cp /dev/shm/model_cache/flywheel_model.3.safetensors s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v24/flywheel_model.3.safetensors
neversleep-noromaid-v0-8068-v24-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v24/flywheel_model.1.safetensors
neversleep-noromaid-v0-8068-v24-mkmlizer: cp /dev/shm/model_cache/flywheel_model.2.safetensors s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v24/flywheel_model.2.safetensors
neversleep-noromaid-v0-8068-v24-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v24/flywheel_model.0.safetensors
neversleep-noromaid-v0-8068-v24-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
neversleep-noromaid-v0-8068-v24-mkmlizer: Loading 0: 0%| | 0/995 [00:00<?, ?it/s] Loading 0: 5%|▌ | 52/995 [00:01<00:21, 43.93it/s] Loading 0: 11%|█ | 107/995 [00:02<00:19, 46.04it/s] Loading 0: 16%|█▋ | 162/995 [00:03<00:18, 46.19it/s] Loading 0: 21%|██ | 210/995 [00:04<00:18, 43.51it/s] Loading 0: 27%|██▋ | 265/995 [00:05<00:16, 44.06it/s] Loading 0: 28%|██▊ | 278/995 [00:16<01:17, 9.24it/s] Loading 0: 32%|███▏ | 320/995 [00:17<00:55, 12.08it/s] Loading 0: 37%|███▋ | 368/995 [00:18<00:38, 16.25it/s] Loading 0: 43%|████▎ | 423/995 [00:19<00:26, 21.63it/s] Loading 0: 48%|████▊ | 478/995 [00:20<00:18, 27.26it/s] Loading 0: 53%|█████▎ | 526/995 [00:21<00:15, 30.68it/s] Loading 0: 57%|█████▋ | 565/995 [00:31<00:38, 11.05it/s] Loading 0: 58%|█████▊ | 581/995 [00:33<00:36, 11.24it/s] Loading 0: 64%|██████▍ | 636/995 [00:34<00:22, 16.05it/s] Loading 0: 69%|██████▉ | 691/995 [00:35<00:14, 20.93it/s] Loading 0: 74%|███████▍ | 739/995 [00:36<00:10, 24.68it/s] Loading 0: 80%|███████▉ | 794/995 [00:37<00:06, 29.55it/s] Loading 0: 85%|████████▌ | 846/995 [00:47<00:12, 12.21it/s] Loading 0: 85%|████████▌ | 850/995 [00:48<00:13, 11.09it/s] Loading 0: 90%|█████████ | 897/995 [00:50<00:06, 14.99it/s] Loading 0: 96%|█████████▌| 952/995 [00:51<00:02, 20.48it/s] Loading 0: 100%|██████████| 995/995 [00:52<00:00, 23.15it/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-v24-mkmlizer: warnings.warn(
neversleep-noromaid-v0-8068-v24-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-v24-mkmlizer: warnings.warn(
neversleep-noromaid-v0-8068-v24-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-v24-mkmlizer: warnings.warn(
neversleep-noromaid-v0-8068-v24-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-v24-mkmlizer: return self.fget.__get__(instance, owner)()
neversleep-noromaid-v0-8068-v24-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
neversleep-noromaid-v0-8068-v24-mkmlizer: Saving duration: 0.252s
neversleep-noromaid-v0-8068-v24-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 3.461s
neversleep-noromaid-v0-8068-v24-mkmlizer: creating bucket guanaco-reward-models
neversleep-noromaid-v0-8068-v24-mkmlizer: Bucket 's3://guanaco-reward-models/' created
neversleep-noromaid-v0-8068-v24-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/neversleep-noromaid-v0-8068-v24_reward
neversleep-noromaid-v0-8068-v24-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/neversleep-noromaid-v0-8068-v24_reward/special_tokens_map.json
neversleep-noromaid-v0-8068-v24-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/neversleep-noromaid-v0-8068-v24_reward/tokenizer_config.json
neversleep-noromaid-v0-8068-v24-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/neversleep-noromaid-v0-8068-v24_reward/config.json
neversleep-noromaid-v0-8068-v24-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/neversleep-noromaid-v0-8068-v24_reward/merges.txt
neversleep-noromaid-v0-8068-v24-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/neversleep-noromaid-v0-8068-v24_reward/vocab.json
neversleep-noromaid-v0-8068-v24-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/neversleep-noromaid-v0-8068-v24_reward/tokenizer.json
neversleep-noromaid-v0-8068-v24-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/neversleep-noromaid-v0-8068-v24_reward/reward.tensors
Job neversleep-noromaid-v0-8068-v24-mkmlizer completed after 313.33s with status: succeeded
Stopping job with name neversleep-noromaid-v0-8068-v24-mkmlizer
Pipeline stage MKMLizer completed in 317.85s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.09s
Running pipeline stage ISVCDeployer
Creating inference service neversleep-noromaid-v0-8068-v24
Waiting for inference service neversleep-noromaid-v0-8068-v24 to be ready
Inference service neversleep-noromaid-v0-8068-v24 ready after 60.42159390449524s
Pipeline stage ISVCDeployer completed in 67.81s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.061065673828125s
Received healthy response to inference request in 1.1101608276367188s
Received healthy response to inference request in 0.8243799209594727s
Received healthy response to inference request in 0.9626903533935547s
Received healthy response to inference request in 1.1130588054656982s
5 requests
0 failed requests
5th percentile: 0.8520420074462891
10th percentile: 0.8797040939331054
20th percentile: 0.9350282669067382
30th percentile: 0.9921844482421875
40th percentile: 1.051172637939453
50th percentile: 1.1101608276367188
60th percentile: 1.1113200187683105
70th percentile: 1.1124792098999023
80th percentile: 1.3026601791381838
90th percentile: 1.6818629264831544
95th percentile: 1.8714643001556395
99th percentile: 2.023145399093628
mean time: 1.214271116256714
Pipeline stage StressChecker completed in 6.85s
Running pipeline stage DaemonicModelEvalScorer
Pipeline stage DaemonicModelEvalScorer completed in 0.03s
Running M-Eval for topic stay_in_character
Running pipeline stage DaemonicSafetyScorer
M-Eval Dataset for topic stay_in_character is loaded
Pipeline stage DaemonicSafetyScorer completed in 0.06s
neversleep-noromaid-v0-_8068_v24 status is now deployed due to DeploymentManager action
neversleep-noromaid-v0-_8068_v24 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics