submission_id: neversleep-noromaid-v0-_8068_v19
developer_uid: robert_irvine
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': ['</s>', '<|user|>', '###', '\n'], 'max_input_tokens': 512, 'best_of': 8, '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}:'}
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: 2024-03-28T20:04:21+00:00
model_name: neversleep-noromaid-v0-_8068_v19
model_eval_status: pending
safety_score: None
entertaining: None
stay_in_character: None
user_preference: None
double_thumbs_up: 3428
thumbs_up: 4582
thumbs_down: 1802
num_battles: 341262
num_wins: 202281
win_ratio: 0.5927439914200819
celo_rating: 1222.17
Resubmit model
Running pipeline stage MKMLizer
Starting job with name neversleep-noromaid-v0-8068-v19-mkmlizer
Waiting for job on neversleep-noromaid-v0-8068-v19-mkmlizer to finish
neversleep-noromaid-v0-8068-v19-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
neversleep-noromaid-v0-8068-v19-mkmlizer: ║ _____ __ __ ║
neversleep-noromaid-v0-8068-v19-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
neversleep-noromaid-v0-8068-v19-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
neversleep-noromaid-v0-8068-v19-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
neversleep-noromaid-v0-8068-v19-mkmlizer: ║ /___/ ║
neversleep-noromaid-v0-8068-v19-mkmlizer: ║ ║
neversleep-noromaid-v0-8068-v19-mkmlizer: ║ Version: 0.8.6 ║
neversleep-noromaid-v0-8068-v19-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
neversleep-noromaid-v0-8068-v19-mkmlizer: ║ ║
neversleep-noromaid-v0-8068-v19-mkmlizer: ║ The license key for the current software has been verified as ║
neversleep-noromaid-v0-8068-v19-mkmlizer: ║ belonging to: ║
neversleep-noromaid-v0-8068-v19-mkmlizer: ║ ║
neversleep-noromaid-v0-8068-v19-mkmlizer: ║ Chai Research Corp. ║
neversleep-noromaid-v0-8068-v19-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
neversleep-noromaid-v0-8068-v19-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
neversleep-noromaid-v0-8068-v19-mkmlizer: ║ ║
neversleep-noromaid-v0-8068-v19-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
neversleep-noromaid-v0-8068-v19-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-v19-mkmlizer: warnings.warn(warning_message, FutureWarning)
neversleep-noromaid-v0-8068-v19-mkmlizer: Downloaded to shared memory in 72.154s
neversleep-noromaid-v0-8068-v19-mkmlizer: quantizing model to /dev/shm/model_cache
neversleep-noromaid-v0-8068-v19-mkmlizer: Saving flywheel model at /dev/shm/model_cache
neversleep-noromaid-v0-8068-v19-mkmlizer: quantized model in 69.263s
neversleep-noromaid-v0-8068-v19-mkmlizer: Processed model NeverSleep/Noromaid-v0.1-mixtral-8x7b-Instruct-v3 in 147.622s
neversleep-noromaid-v0-8068-v19-mkmlizer: creating bucket guanaco-mkml-models
neversleep-noromaid-v0-8068-v19-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
neversleep-noromaid-v0-8068-v19-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v19
neversleep-noromaid-v0-8068-v19-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v19/config.json
neversleep-noromaid-v0-8068-v19-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v19/special_tokens_map.json
neversleep-noromaid-v0-8068-v19-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v19/tokenizer_config.json
neversleep-noromaid-v0-8068-v19-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v19/tokenizer.json
neversleep-noromaid-v0-8068-v19-mkmlizer: cp /dev/shm/model_cache/tokenizer.model s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v19/tokenizer.model
neversleep-noromaid-v0-8068-v19-mkmlizer: cp /dev/shm/model_cache/flywheel_model.3.safetensors s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v19/flywheel_model.3.safetensors
neversleep-noromaid-v0-8068-v19-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v19/flywheel_model.1.safetensors
neversleep-noromaid-v0-8068-v19-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v19/flywheel_model.0.safetensors
neversleep-noromaid-v0-8068-v19-mkmlizer: cp /dev/shm/model_cache/flywheel_model.2.safetensors s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v19/flywheel_model.2.safetensors
neversleep-noromaid-v0-8068-v19-mkmlizer: loading reward model from rirv938/reward_gpt2_medium_preference_24m_e2
neversleep-noromaid-v0-8068-v19-mkmlizer: Loading 0: 0%| | 0/995 [00:00<?, ?it/s] Loading 0: 5%|▌ | 52/995 [00:01<00:19, 47.79it/s] Loading 0: 11%|█ | 107/995 [00:01<00:16, 54.62it/s] Loading 0: 16%|█▋ | 162/995 [00:02<00:14, 57.37it/s] Loading 0: 21%|██ | 210/995 [00:03<00:14, 56.07it/s] Loading 0: 27%|██▋ | 265/995 [00:04<00:12, 58.80it/s] Loading 0: 28%|██▊ | 277/995 [00:17<00:12, 58.80it/s] Loading 0: 28%|██▊ | 278/995 [00:17<01:31, 7.79it/s] Loading 0: 32%|███▏ | 320/995 [00:18<01:03, 10.63it/s] Loading 0: 37%|███▋ | 368/995 [00:19<00:42, 14.92it/s] Loading 0: 43%|████▎ | 423/995 [00:20<00:27, 20.45it/s] Loading 0: 48%|████▊ | 478/995 [00:21<00:19, 26.55it/s] Loading 0: 53%|█████▎ | 526/995 [00:22<00:14, 31.72it/s] Loading 0: 57%|█████▋ | 565/995 [00:35<00:48, 8.91it/s] Loading 0: 58%|█████▊ | 581/995 [00:37<00:44, 9.28it/s] Loading 0: 64%|██████▍ | 636/995 [00:38<00:25, 13.97it/s] Loading 0: 69%|██████▉ | 691/995 [00:39<00:16, 18.94it/s] Loading 0: 74%|███████▍ | 739/995 [00:40<00:10, 23.49it/s] Loading 0: 80%|███████▉ | 794/995 [00:41<00:07, 26.75it/s] Loading 0: 85%|████████▌ | 846/995 [00:54<00:15, 9.70it/s] Loading 0: 85%|████████▌ | 849/995 [00:55<00:16, 8.89it/s] Loading 0: 90%|█████████ | 897/995 [00:56<00:07, 12.50it/s] Loading 0: 96%|█████████▌| 952/995 [00:57<00:02, 17.58it/s] Loading 0: 100%|██████████| 995/995 [00:59<00:00, 20.13it/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-v19-mkmlizer: warnings.warn(
neversleep-noromaid-v0-8068-v19-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-v19-mkmlizer: warnings.warn(
neversleep-noromaid-v0-8068-v19-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-v19-mkmlizer: warnings.warn(
neversleep-noromaid-v0-8068-v19-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-v19-mkmlizer: return self.fget.__get__(instance, owner)()
neversleep-noromaid-v0-8068-v19-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
neversleep-noromaid-v0-8068-v19-mkmlizer: Saving duration: 0.229s
neversleep-noromaid-v0-8068-v19-mkmlizer: Processed model rirv938/reward_gpt2_medium_preference_24m_e2 in 3.541s
neversleep-noromaid-v0-8068-v19-mkmlizer: creating bucket guanaco-reward-models
neversleep-noromaid-v0-8068-v19-mkmlizer: Bucket 's3://guanaco-reward-models/' created
neversleep-noromaid-v0-8068-v19-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/neversleep-noromaid-v0-8068-v19_reward
neversleep-noromaid-v0-8068-v19-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/neversleep-noromaid-v0-8068-v19_reward/special_tokens_map.json
neversleep-noromaid-v0-8068-v19-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/neversleep-noromaid-v0-8068-v19_reward/tokenizer_config.json
neversleep-noromaid-v0-8068-v19-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/neversleep-noromaid-v0-8068-v19_reward/config.json
neversleep-noromaid-v0-8068-v19-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/neversleep-noromaid-v0-8068-v19_reward/merges.txt
neversleep-noromaid-v0-8068-v19-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/neversleep-noromaid-v0-8068-v19_reward/vocab.json
neversleep-noromaid-v0-8068-v19-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/neversleep-noromaid-v0-8068-v19_reward/tokenizer.json
neversleep-noromaid-v0-8068-v19-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/neversleep-noromaid-v0-8068-v19_reward/reward.tensors
Job neversleep-noromaid-v0-8068-v19-mkmlizer completed after 197.18s with status: succeeded
Stopping job with name neversleep-noromaid-v0-8068-v19-mkmlizer
Pipeline stage MKMLizer completed in 199.27s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.27s
Running pipeline stage ISVCDeployer
Creating inference service neversleep-noromaid-v0-8068-v19
Waiting for inference service neversleep-noromaid-v0-8068-v19 to be ready
Inference service neversleep-noromaid-v0-8068-v19 ready after 60.65610432624817s
Pipeline stage ISVCDeployer completed in 67.58s
Running pipeline stage StressChecker
Received healthy response to inference request in 4.094596862792969s
Received healthy response to inference request in 3.2762908935546875s
Received healthy response to inference request in 3.5873072147369385s
Received healthy response to inference request in 3.8838818073272705s
Received healthy response to inference request in 2.6183407306671143s
5 requests
0 failed requests
5th percentile: 2.749930763244629
10th percentile: 2.8815207958221434
20th percentile: 3.144700860977173
30th percentile: 3.338494157791138
40th percentile: 3.462900686264038
50th percentile: 3.5873072147369385
60th percentile: 3.705937051773071
70th percentile: 3.824566888809204
80th percentile: 3.92602481842041
90th percentile: 4.01031084060669
95th percentile: 4.052453851699829
99th percentile: 4.086168260574341
mean time: 3.492083501815796
Pipeline stage StressChecker completed in 21.94s
Running pipeline stage DaemonicModelEvalScorer
Pipeline stage DaemonicModelEvalScorer completed in 0.11s
Running pipeline stage DaemonicSafetyScorer
Running M-Eval for topic stay_in_character
Pipeline stage DaemonicSafetyScorer completed in 0.45s
%s, retrying in %s seconds...
M-Eval Dataset for topic stay_in_character is loaded
neversleep-noromaid-v0-_8068_v19 status is now deployed due to DeploymentManager action
%s, retrying in %s seconds...
neversleep-noromaid-v0-_8068_v19 status is now inactive due to admin request
neversleep-noromaid-v0-_8068_v19 status is now deployed due to admin request
neversleep-noromaid-v0-_8068_v19 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics