submission_id: neversleep-noromaid-v0-_8068_v23
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: 2024-04-01T19:25:26+00:00
model_name: auto_submit_etiye_uraremow
model_eval_status: success
safety_score: 0.97
entertaining: 6.7
stay_in_character: 8.44
user_preference: 7.32
double_thumbs_up: 80
thumbs_up: 111
thumbs_down: 49
num_battles: 6333
num_wins: 2902
win_ratio: 0.45823464392862784
celo_rating: 1131.32
Resubmit model
Running pipeline stage MKMLizer
Starting job with name neversleep-noromaid-v0-8068-v23-mkmlizer
Waiting for job on neversleep-noromaid-v0-8068-v23-mkmlizer to finish
Failed to get response for submission anhnv125-llama-op-v17-1_v27: HTTPConnectionPool(host='anhnv125-llama-op-v17-1-v27-predictor-default.tenant-chaiml-guanaco.knative.ord1.coreweave.cloud', port=80): Read timed out. (read timeout=5.5)
neversleep-noromaid-v0-8068-v23-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
neversleep-noromaid-v0-8068-v23-mkmlizer: ║ _____ __ __ ║
neversleep-noromaid-v0-8068-v23-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
neversleep-noromaid-v0-8068-v23-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
neversleep-noromaid-v0-8068-v23-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
neversleep-noromaid-v0-8068-v23-mkmlizer: ║ /___/ ║
neversleep-noromaid-v0-8068-v23-mkmlizer: ║ ║
neversleep-noromaid-v0-8068-v23-mkmlizer: ║ Version: 0.8.6 ║
neversleep-noromaid-v0-8068-v23-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
neversleep-noromaid-v0-8068-v23-mkmlizer: ║ ║
neversleep-noromaid-v0-8068-v23-mkmlizer: ║ The license key for the current software has been verified as ║
neversleep-noromaid-v0-8068-v23-mkmlizer: ║ belonging to: ║
neversleep-noromaid-v0-8068-v23-mkmlizer: ║ ║
neversleep-noromaid-v0-8068-v23-mkmlizer: ║ Chai Research Corp. ║
neversleep-noromaid-v0-8068-v23-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
neversleep-noromaid-v0-8068-v23-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
neversleep-noromaid-v0-8068-v23-mkmlizer: ║ ║
neversleep-noromaid-v0-8068-v23-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
neversleep-noromaid-v0-8068-v23-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-v23-mkmlizer: warnings.warn(warning_message, FutureWarning)
Failed to get response for submission thanhdaonguyen-once-upon-a-t_v37: HTTPConnectionPool(host='thanhdaonguyen-once-upon-a-t-v37-predictor-default.tenant-chaiml-guanaco.knative.ord1.coreweave.cloud', port=80): Read timed out. (read timeout=5.5)
neversleep-noromaid-v0-8068-v23-mkmlizer: Downloaded to shared memory in 100.742s
neversleep-noromaid-v0-8068-v23-mkmlizer: quantizing model to /dev/shm/model_cache
neversleep-noromaid-v0-8068-v23-mkmlizer: Saving flywheel model at /dev/shm/model_cache
neversleep-noromaid-v0-8068-v23-mkmlizer: quantized model in 64.211s
neversleep-noromaid-v0-8068-v23-mkmlizer: Processed model NeverSleep/Noromaid-v0.1-mixtral-8x7b-Instruct-v3 in 172.497s
neversleep-noromaid-v0-8068-v23-mkmlizer: creating bucket guanaco-mkml-models
neversleep-noromaid-v0-8068-v23-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
neversleep-noromaid-v0-8068-v23-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v23
neversleep-noromaid-v0-8068-v23-mkmlizer: cp /dev/shm/model_cache/flywheel_model.3.safetensors s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v23/flywheel_model.3.safetensors
neversleep-noromaid-v0-8068-v23-mkmlizer: cp /dev/shm/model_cache/flywheel_model.2.safetensors s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v23/flywheel_model.2.safetensors
neversleep-noromaid-v0-8068-v23-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v23/flywheel_model.1.safetensors
neversleep-noromaid-v0-8068-v23-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v23/flywheel_model.0.safetensors
neversleep-noromaid-v0-8068-v23-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
neversleep-noromaid-v0-8068-v23-mkmlizer: Loading 0: 0%| | 0/995 [00:00<?, ?it/s] Loading 0: 5%|▌ | 52/995 [00:01<00:22, 42.41it/s] Loading 0: 11%|█ | 107/995 [00:02<00:20, 44.28it/s] Loading 0: 16%|█▋ | 162/995 [00:03<00:18, 44.78it/s] Loading 0: 21%|██ | 210/995 [00:04<00:18, 42.48it/s] Loading 0: 27%|██▋ | 265/995 [00:06<00:16, 43.73it/s] Loading 0: 28%|██▊ | 278/995 [00:16<01:20, 8.89it/s] Loading 0: 32%|███▏ | 320/995 [00:18<00:59, 11.42it/s] Loading 0: 37%|███▋ | 368/995 [00:19<00:41, 14.95it/s] Loading 0: 43%|████▎ | 423/995 [00:21<00:28, 19.99it/s] Loading 0: 48%|████▊ | 478/995 [00:22<00:20, 25.10it/s] Loading 0: 53%|█████▎ | 526/995 [00:23<00:16, 28.59it/s] Loading 0: 57%|█████▋ | 564/995 [00:33<00:15, 28.59it/s] Loading 0: 57%|█████▋ | 565/995 [00:33<00:40, 10.50it/s] Loading 0: 58%|█████▊ | 581/995 [00:35<00:39, 10.60it/s] Loading 0: 64%|██████▍ | 636/995 [00:36<00:23, 15.30it/s] Loading 0: 69%|██████▉ | 691/995 [00:37<00:14, 20.32it/s] Loading 0: 74%|███████▍ | 739/995 [00:38<00:10, 23.94it/s] Loading 0: 80%|███████▉ | 794/995 [00:39<00:07, 28.57it/s] Loading 0: 85%|████████▍ | 845/995 [00:50<00:05, 28.57it/s] Loading 0: 85%|████████▌ | 846/995 [00:50<00:12, 11.61it/s] Loading 0: 85%|████████▌ | 849/995 [00:51<00:14, 10.42it/s] Loading 0: 90%|█████████ | 897/995 [00:52<00:06, 14.23it/s] Loading 0: 96%|█████████▌| 952/995 [00:53<00:02, 19.39it/s] Loading 0: 100%|██████████| 995/995 [00:55<00:00, 21.74it/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-v23-mkmlizer: warnings.warn(
neversleep-noromaid-v0-8068-v23-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-v23-mkmlizer: warnings.warn(
neversleep-noromaid-v0-8068-v23-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-v23-mkmlizer: warnings.warn(
neversleep-noromaid-v0-8068-v23-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-v23-mkmlizer: return self.fget.__get__(instance, owner)()
neversleep-noromaid-v0-8068-v23-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
neversleep-noromaid-v0-8068-v23-mkmlizer: Saving duration: 0.303s
neversleep-noromaid-v0-8068-v23-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 4.842s
neversleep-noromaid-v0-8068-v23-mkmlizer: creating bucket guanaco-reward-models
neversleep-noromaid-v0-8068-v23-mkmlizer: Bucket 's3://guanaco-reward-models/' created
neversleep-noromaid-v0-8068-v23-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/neversleep-noromaid-v0-8068-v23_reward
neversleep-noromaid-v0-8068-v23-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/neversleep-noromaid-v0-8068-v23_reward/vocab.json
neversleep-noromaid-v0-8068-v23-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/neversleep-noromaid-v0-8068-v23_reward/merges.txt
neversleep-noromaid-v0-8068-v23-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/neversleep-noromaid-v0-8068-v23_reward/config.json
neversleep-noromaid-v0-8068-v23-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/neversleep-noromaid-v0-8068-v23_reward/special_tokens_map.json
neversleep-noromaid-v0-8068-v23-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/neversleep-noromaid-v0-8068-v23_reward/tokenizer_config.json
neversleep-noromaid-v0-8068-v23-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/neversleep-noromaid-v0-8068-v23_reward/tokenizer.json
neversleep-noromaid-v0-8068-v23-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/neversleep-noromaid-v0-8068-v23_reward/reward.tensors
Job neversleep-noromaid-v0-8068-v23-mkmlizer completed after 220.13s with status: succeeded
Stopping job with name neversleep-noromaid-v0-8068-v23-mkmlizer
Pipeline stage MKMLizer completed in 225.89s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.11s
Running pipeline stage ISVCDeployer
Creating inference service neversleep-noromaid-v0-8068-v23
Waiting for inference service neversleep-noromaid-v0-8068-v23 to be ready
Inference service neversleep-noromaid-v0-8068-v23 ready after 70.42911839485168s
Pipeline stage ISVCDeployer completed in 79.18s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.5632460117340088s
Received healthy response to inference request in 1.5514581203460693s
Received healthy response to inference request in 1.1433603763580322s
Received healthy response to inference request in 1.789628028869629s
Received healthy response to inference request in 1.8506348133087158s
5 requests
0 failed requests
5th percentile: 1.2249799251556397
10th percentile: 1.3065994739532472
20th percentile: 1.4698385715484619
30th percentile: 1.5538156986236573
40th percentile: 1.558530855178833
50th percentile: 1.5632460117340088
60th percentile: 1.6537988185882568
70th percentile: 1.7443516254425049
80th percentile: 1.8018293857574463
90th percentile: 1.826232099533081
95th percentile: 1.8384334564208984
99th percentile: 1.8481945419311523
mean time: 1.579665470123291
Pipeline stage StressChecker completed in 9.03s
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_v23 status is now deployed due to DeploymentManager action
neversleep-noromaid-v0-_8068_v23 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics