submission_id: neversleep-noromaid-v0-_8068_v22
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': 0.8, 'top_p': 0.9, 'top_k': 70, 'presence_penalty': 0.9, 'frequency_penalty': 0.9, 'stopping_words': ['\n', '</s>', '<|user|>', '###'], 'max_input_tokens': 512, 'best_of': 8, 'max_output_tokens': 156}
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}:'}
reward_formatter: {'memory_template': 'Memory: {memory}\n', 'prompt_template': '{prompt}\n', 'bot_template': 'Bot: {message}\n', 'user_template': 'User: {message}\n', 'response_template': 'Bot:'}
timestamp: 2024-03-31T02:15:50+00:00
model_name: Noromaid-v0-1-156
model_eval_status: success
safety_score: 0.97
entertaining: 7.48
stay_in_character: 8.73
user_preference: 7.86
double_thumbs_up: 3378
thumbs_up: 4349
thumbs_down: 1843
num_battles: 312986
num_wins: 186216
win_ratio: 0.5949659090182947
celo_rating: 1223.68
Resubmit model
Running pipeline stage MKMLizer
Starting job with name neversleep-noromaid-v0-8068-v22-mkmlizer
Waiting for job on neversleep-noromaid-v0-8068-v22-mkmlizer to finish
neversleep-noromaid-v0-8068-v22-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
neversleep-noromaid-v0-8068-v22-mkmlizer: ║ _____ __ __ ║
neversleep-noromaid-v0-8068-v22-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
neversleep-noromaid-v0-8068-v22-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
neversleep-noromaid-v0-8068-v22-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
neversleep-noromaid-v0-8068-v22-mkmlizer: ║ /___/ ║
neversleep-noromaid-v0-8068-v22-mkmlizer: ║ ║
neversleep-noromaid-v0-8068-v22-mkmlizer: ║ Version: 0.8.6 ║
neversleep-noromaid-v0-8068-v22-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
neversleep-noromaid-v0-8068-v22-mkmlizer: ║ ║
neversleep-noromaid-v0-8068-v22-mkmlizer: ║ The license key for the current software has been verified as ║
neversleep-noromaid-v0-8068-v22-mkmlizer: ║ belonging to: ║
neversleep-noromaid-v0-8068-v22-mkmlizer: ║ ║
neversleep-noromaid-v0-8068-v22-mkmlizer: ║ Chai Research Corp. ║
neversleep-noromaid-v0-8068-v22-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
neversleep-noromaid-v0-8068-v22-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
neversleep-noromaid-v0-8068-v22-mkmlizer: ║ ║
neversleep-noromaid-v0-8068-v22-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
neversleep-noromaid-v0-8068-v22-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-v22-mkmlizer: warnings.warn(warning_message, FutureWarning)
%s, retrying in %s seconds...
neversleep-noromaid-v0-8068-v22-mkmlizer: Downloaded to shared memory in 154.924s
neversleep-noromaid-v0-8068-v22-mkmlizer: quantizing model to /dev/shm/model_cache
neversleep-noromaid-v0-8068-v22-mkmlizer: Saving flywheel model at /dev/shm/model_cache
neversleep-noromaid-v0-8068-v22-mkmlizer: quantized model in 60.363s
neversleep-noromaid-v0-8068-v22-mkmlizer: Processed model NeverSleep/Noromaid-v0.1-mixtral-8x7b-Instruct-v3 in 222.056s
neversleep-noromaid-v0-8068-v22-mkmlizer: creating bucket guanaco-mkml-models
neversleep-noromaid-v0-8068-v22-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
neversleep-noromaid-v0-8068-v22-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v22
neversleep-noromaid-v0-8068-v22-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v22/config.json
neversleep-noromaid-v0-8068-v22-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v22/special_tokens_map.json
neversleep-noromaid-v0-8068-v22-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v22/tokenizer_config.json
neversleep-noromaid-v0-8068-v22-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v22/tokenizer.json
neversleep-noromaid-v0-8068-v22-mkmlizer: cp /dev/shm/model_cache/tokenizer.model s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v22/tokenizer.model
neversleep-noromaid-v0-8068-v22-mkmlizer: cp /dev/shm/model_cache/flywheel_model.3.safetensors s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v22/flywheel_model.3.safetensors
neversleep-noromaid-v0-8068-v22-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v22/flywheel_model.0.safetensors
neversleep-noromaid-v0-8068-v22-mkmlizer: cp /dev/shm/model_cache/flywheel_model.2.safetensors s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v22/flywheel_model.2.safetensors
neversleep-noromaid-v0-8068-v22-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v22/flywheel_model.1.safetensors
neversleep-noromaid-v0-8068-v22-mkmlizer: loading reward model from rirv938/reward_gpt2_medium_preference_24m_e2
neversleep-noromaid-v0-8068-v22-mkmlizer: Loading 0: 0%| | 0/995 [00:00<?, ?it/s] Loading 0: 5%|▌ | 52/995 [00:01<00:22, 41.47it/s] Loading 0: 11%|█ | 107/995 [00:02<00:19, 46.28it/s] Loading 0: 16%|█▋ | 162/995 [00:03<00:17, 47.51it/s] Loading 0: 21%|██ | 210/995 [00:04<00:17, 45.32it/s] Loading 0: 27%|██▋ | 265/995 [00:05<00:16, 45.35it/s] Loading 0: 28%|██▊ | 278/995 [00:15<01:14, 9.62it/s] Loading 0: 32%|███▏ | 320/995 [00:17<00:54, 12.47it/s] Loading 0: 37%|███▋ | 368/995 [00:18<00:38, 16.33it/s] Loading 0: 43%|████▎ | 423/995 [00:19<00:26, 21.45it/s] Loading 0: 48%|████▊ | 478/995 [00:20<00:19, 26.36it/s] Loading 0: 53%|█████▎ | 526/995 [00:21<00:16, 29.13it/s] Loading 0: 57%|█████▋ | 565/995 [00:31<00:38, 11.07it/s] Loading 0: 58%|█████▊ | 581/995 [00:33<00:38, 10.79it/s] Loading 0: 64%|██████▍ | 636/995 [00:34<00:23, 15.18it/s] Loading 0: 69%|██████▉ | 691/995 [00:36<00:15, 19.94it/s] Loading 0: 74%|███████▍ | 739/995 [00:37<00:10, 23.60it/s] Loading 0: 80%|███████▉ | 794/995 [00:38<00:07, 28.13it/s] Loading 0: 85%|████████▌ | 846/995 [00:48<00:12, 12.06it/s] Loading 0: 85%|████████▌ | 849/995 [00:49<00:13, 10.79it/s] Loading 0: 90%|█████████ | 897/995 [00:50<00:06, 14.90it/s] Loading 0: 96%|█████████▌| 952/995 [00:51<00:02, 20.55it/s] Loading 0: 100%|██████████| 995/995 [00:52<00:00, 23.11it/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-v22-mkmlizer: warnings.warn(
neversleep-noromaid-v0-8068-v22-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-v22-mkmlizer: warnings.warn(
neversleep-noromaid-v0-8068-v22-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-v22-mkmlizer: warnings.warn(
neversleep-noromaid-v0-8068-v22-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
neversleep-noromaid-v0-8068-v22-mkmlizer: Saving duration: 0.273s
neversleep-noromaid-v0-8068-v22-mkmlizer: Processed model rirv938/reward_gpt2_medium_preference_24m_e2 in 5.428s
neversleep-noromaid-v0-8068-v22-mkmlizer: creating bucket guanaco-reward-models
neversleep-noromaid-v0-8068-v22-mkmlizer: Bucket 's3://guanaco-reward-models/' created
neversleep-noromaid-v0-8068-v22-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/neversleep-noromaid-v0-8068-v22_reward
neversleep-noromaid-v0-8068-v22-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/neversleep-noromaid-v0-8068-v22_reward/special_tokens_map.json
neversleep-noromaid-v0-8068-v22-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/neversleep-noromaid-v0-8068-v22_reward/config.json
neversleep-noromaid-v0-8068-v22-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/neversleep-noromaid-v0-8068-v22_reward/tokenizer_config.json
neversleep-noromaid-v0-8068-v22-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/neversleep-noromaid-v0-8068-v22_reward/merges.txt
neversleep-noromaid-v0-8068-v22-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/neversleep-noromaid-v0-8068-v22_reward/vocab.json
neversleep-noromaid-v0-8068-v22-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/neversleep-noromaid-v0-8068-v22_reward/tokenizer.json
neversleep-noromaid-v0-8068-v22-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/neversleep-noromaid-v0-8068-v22_reward/reward.tensors
Job neversleep-noromaid-v0-8068-v22-mkmlizer completed after 260.89s with status: succeeded
Stopping job with name neversleep-noromaid-v0-8068-v22-mkmlizer
Pipeline stage MKMLizer completed in 261.22s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.09s
Running pipeline stage ISVCDeployer
Creating inference service neversleep-noromaid-v0-8068-v22
Waiting for inference service neversleep-noromaid-v0-8068-v22 to be ready
Inference service neversleep-noromaid-v0-8068-v22 ready after 70.66810369491577s
Pipeline stage ISVCDeployer completed in 76.30s
Running pipeline stage StressChecker
Received healthy response to inference request in 3.780012607574463s
Received healthy response to inference request in 2.7617528438568115s
Received healthy response to inference request in 4.155905246734619s
Received healthy response to inference request in 4.255332708358765s
%s, retrying in %s seconds...
%s, retrying in %s seconds...
Received healthy response to inference request in 4.421945810317993s
Received healthy response to inference request in 3.264036178588867s
Received healthy response to inference request in 2.997903823852539s
Received healthy response to inference request in 4.837133407592773s
Received healthy response to inference request in 2.3683764934539795s
5 requests
0 failed requests
5th percentile: 2.4942819595336916
10th percentile: 2.6201874256134032
20th percentile: 2.871998357772827
30th percentile: 3.0511302947998047
40th percentile: 3.157583236694336
50th percentile: 3.264036178588867
60th percentile: 3.7272000312805176
70th percentile: 4.190363883972168
80th percentile: 4.50498332977295
90th percentile: 4.6710583686828615
95th percentile: 4.754095888137817
99th percentile: 4.820525903701782
mean time: 3.5778791427612306
Pipeline stage StressChecker completed in 73.87s
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 0.05s
M-Eval Dataset for topic stay_in_character is loaded
neversleep-noromaid-v0-_8068_v22 status is now deployed due to DeploymentManager action
neversleep-noromaid-v0-_8068_v22 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics