submission_id: neversleep-noromaid-v0-_8068_v20
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': 48}
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: 2024-03-31T02:15:24+00:00
model_name: Noromaid-v0-1-48
model_eval_status: success
safety_score: 0.92
entertaining: 7.16
stay_in_character: 8.35
user_preference: 7.62
double_thumbs_up: 1408
thumbs_up: 1847
thumbs_down: 684
num_battles: 129189
num_wins: 65390
win_ratio: 0.5061576450007353
celo_rating: 1156.92
Resubmit model
Running pipeline stage MKMLizer
Starting job with name neversleep-noromaid-v0-8068-v20-mkmlizer
Waiting for job on neversleep-noromaid-v0-8068-v20-mkmlizer to finish
%s
%s
neversleep-noromaid-v0-8068-v20-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
neversleep-noromaid-v0-8068-v20-mkmlizer: ║ _____ __ __ ║
neversleep-noromaid-v0-8068-v20-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
neversleep-noromaid-v0-8068-v20-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
neversleep-noromaid-v0-8068-v20-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
neversleep-noromaid-v0-8068-v20-mkmlizer: ║ /___/ ║
neversleep-noromaid-v0-8068-v20-mkmlizer: ║ ║
neversleep-noromaid-v0-8068-v20-mkmlizer: ║ Version: 0.8.6 ║
neversleep-noromaid-v0-8068-v20-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
neversleep-noromaid-v0-8068-v20-mkmlizer: ║ ║
neversleep-noromaid-v0-8068-v20-mkmlizer: ║ The license key for the current software has been verified as ║
neversleep-noromaid-v0-8068-v20-mkmlizer: ║ belonging to: ║
neversleep-noromaid-v0-8068-v20-mkmlizer: ║ ║
neversleep-noromaid-v0-8068-v20-mkmlizer: ║ Chai Research Corp. ║
neversleep-noromaid-v0-8068-v20-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
neversleep-noromaid-v0-8068-v20-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
neversleep-noromaid-v0-8068-v20-mkmlizer: ║ ║
neversleep-noromaid-v0-8068-v20-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
neversleep-noromaid-v0-8068-v20-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-v20-mkmlizer: warnings.warn(warning_message, FutureWarning)
neversleep-noromaid-v0-8068-v20-mkmlizer: Downloaded to shared memory in 152.027s
neversleep-noromaid-v0-8068-v20-mkmlizer: quantizing model to /dev/shm/model_cache
neversleep-noromaid-v0-8068-v20-mkmlizer: Saving flywheel model at /dev/shm/model_cache
neversleep-noromaid-v0-8068-v20-mkmlizer: quantized model in 69.744s
neversleep-noromaid-v0-8068-v20-mkmlizer: Processed model NeverSleep/Noromaid-v0.1-mixtral-8x7b-Instruct-v3 in 231.260s
neversleep-noromaid-v0-8068-v20-mkmlizer: creating bucket guanaco-mkml-models
neversleep-noromaid-v0-8068-v20-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
neversleep-noromaid-v0-8068-v20-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v20
neversleep-noromaid-v0-8068-v20-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v20/special_tokens_map.json
neversleep-noromaid-v0-8068-v20-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v20/config.json
neversleep-noromaid-v0-8068-v20-mkmlizer: cp /dev/shm/model_cache/tokenizer.model s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v20/tokenizer.model
neversleep-noromaid-v0-8068-v20-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v20/tokenizer.json
neversleep-noromaid-v0-8068-v20-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v20/tokenizer_config.json
neversleep-noromaid-v0-8068-v20-mkmlizer: cp /dev/shm/model_cache/flywheel_model.3.safetensors s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v20/flywheel_model.3.safetensors
neversleep-noromaid-v0-8068-v20-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v20/flywheel_model.0.safetensors
neversleep-noromaid-v0-8068-v20-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v20/flywheel_model.1.safetensors
neversleep-noromaid-v0-8068-v20-mkmlizer: cp /dev/shm/model_cache/flywheel_model.2.safetensors s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v20/flywheel_model.2.safetensors
neversleep-noromaid-v0-8068-v20-mkmlizer: loading reward model from rirv938/reward_gpt2_medium_preference_24m_e2
neversleep-noromaid-v0-8068-v20-mkmlizer: Loading 0: 0%| | 0/995 [00:00<?, ?it/s] Loading 0: 5%|▌ | 52/995 [00:01<00:28, 33.35it/s] Loading 0: 11%|█ | 107/995 [00:03<00:24, 35.97it/s] Loading 0: 16%|█▋ | 162/995 [00:04<00:22, 36.84it/s] Loading 0: 21%|██ | 210/995 [00:05<00:21, 35.87it/s] Loading 0: 27%|██▋ | 265/995 [00:07<00:19, 37.01it/s] Loading 0: 28%|██▊ | 277/995 [00:17<00:19, 37.01it/s] Loading 0: 28%|██▊ | 278/995 [00:17<01:22, 8.72it/s] Loading 0: 32%|███▏ | 320/995 [00:19<01:00, 11.22it/s] Loading 0: 37%|███▋ | 368/995 [00:20<00:42, 14.77it/s] Loading 0: 43%|████▎ | 423/995 [00:22<00:30, 19.07it/s] Loading 0: 48%|████▊ | 478/995 [00:23<00:22, 22.54it/s] Loading 0: 53%|█████▎ | 526/995 [00:25<00:19, 24.21it/s] Loading 0: 57%|█████▋ | 565/995 [00:36<00:43, 9.85it/s] Loading 0: 58%|█████▊ | 581/995 [00:37<00:42, 9.79it/s] Loading 0: 64%|██████▍ | 636/995 [00:39<00:26, 13.59it/s] Loading 0: 69%|██████▉ | 691/995 [00:41<00:17, 17.46it/s] Loading 0: 74%|███████▍ | 739/995 [00:42<00:12, 20.15it/s] Loading 0: 80%|███████▉ | 794/995 [00:44<00:08, 23.72it/s] Loading 0: 85%|████████▌ | 846/995 [00:54<00:13, 10.80it/s] Loading 0: 85%|████████▌ | 849/995 [00:56<00:15, 9.46it/s] Loading 0: 90%|█████████ | 897/995 [00:58<00:07, 12.82it/s] Loading 0: 96%|█████████▌| 952/995 [00:59<00:02, 17.57it/s] Loading 0: 100%|██████████| 995/995 [01:00<00:00, 20.26it/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-v20-mkmlizer: warnings.warn(
neversleep-noromaid-v0-8068-v20-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-v20-mkmlizer: warnings.warn(
neversleep-noromaid-v0-8068-v20-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-v20-mkmlizer: warnings.warn(
neversleep-noromaid-v0-8068-v20-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-v20-mkmlizer: return self.fget.__get__(instance, owner)()
neversleep-noromaid-v0-8068-v20-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
neversleep-noromaid-v0-8068-v20-mkmlizer: Saving duration: 0.309s
neversleep-noromaid-v0-8068-v20-mkmlizer: Processed model rirv938/reward_gpt2_medium_preference_24m_e2 in 3.777s
neversleep-noromaid-v0-8068-v20-mkmlizer: creating bucket guanaco-reward-models
neversleep-noromaid-v0-8068-v20-mkmlizer: Bucket 's3://guanaco-reward-models/' created
neversleep-noromaid-v0-8068-v20-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/neversleep-noromaid-v0-8068-v20_reward
neversleep-noromaid-v0-8068-v20-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/neversleep-noromaid-v0-8068-v20_reward/config.json
neversleep-noromaid-v0-8068-v20-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/neversleep-noromaid-v0-8068-v20_reward/special_tokens_map.json
neversleep-noromaid-v0-8068-v20-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/neversleep-noromaid-v0-8068-v20_reward/tokenizer_config.json
neversleep-noromaid-v0-8068-v20-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/neversleep-noromaid-v0-8068-v20_reward/merges.txt
neversleep-noromaid-v0-8068-v20-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/neversleep-noromaid-v0-8068-v20_reward/vocab.json
neversleep-noromaid-v0-8068-v20-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/neversleep-noromaid-v0-8068-v20_reward/tokenizer.json
neversleep-noromaid-v0-8068-v20-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/neversleep-noromaid-v0-8068-v20_reward/reward.tensors
Job neversleep-noromaid-v0-8068-v20-mkmlizer completed after 376.38s with status: succeeded
Stopping job with name neversleep-noromaid-v0-8068-v20-mkmlizer
Pipeline stage MKMLizer completed in 376.75s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.11s
Running pipeline stage ISVCDeployer
Creating inference service neversleep-noromaid-v0-8068-v20
Waiting for inference service neversleep-noromaid-v0-8068-v20 to be ready
Inference service neversleep-noromaid-v0-8068-v20 ready after 60.388688802719116s
Pipeline stage ISVCDeployer completed in 65.94s
Running pipeline stage StressChecker
Received healthy response to inference request in 3.415673017501831s
Received healthy response to inference request in 2.6831860542297363s
Received healthy response to inference request in 2.736036539077759s
Received healthy response to inference request in 2.541008234024048s
Received healthy response to inference request in 2.5576229095458984s
5 requests
0 failed requests
5th percentile: 2.544331169128418
10th percentile: 2.5476541042327883
20th percentile: 2.5542999744415282
30th percentile: 2.582735538482666
40th percentile: 2.632960796356201
50th percentile: 2.6831860542297363
60th percentile: 2.7043262481689454
70th percentile: 2.7254664421081545
80th percentile: 2.8719638347625733
90th percentile: 3.143818426132202
95th percentile: 3.2797457218170165
99th percentile: 3.388487558364868
mean time: 2.7867053508758546
Pipeline stage StressChecker completed in 14.63s
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_v20 status is now deployed due to DeploymentManager action
AUTO_DEACTIVATION: submission %s deactivated %s
neversleep-noromaid-v0-_8068_v20 status is now inactive due to auto deactivation removed underperforming models
neversleep-noromaid-v0-_8068_v20 status is now deployed due to admin request
neversleep-noromaid-v0-_8068_v20 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics