developer_uid: robert_irvine
submission_id: neversleep-noromaid-v0-_8068_v68
model_name: neversleep-noromaid-v0-_8068_v68
model_group: NeverSleep/Noromaid-v0.1
status: torndown
timestamp: 2024-06-09T20:44:07+00:00
num_battles: 5319
num_wins: 2685
celo_rating: 1179.35
family_friendly_score: 0.0
submission_type: basic
model_repo: NeverSleep/Noromaid-v0.1-mixtral-8x7b-Instruct-v3
model_architecture: MixtralForCausalLM
reward_repo: rirv938/reward_gpt2_medium_preference_24m_e2
model_num_parameters: 46702792704.0
best_of: 4
max_input_tokens: 1024
max_output_tokens: 64
display_name: neversleep-noromaid-v0-_8068_v68
is_internal_developer: True
language_model: NeverSleep/Noromaid-v0.1-mixtral-8x7b-Instruct-v3
model_size: 47B
ranking_group: single
us_pacific_date: 2024-06-09
win_ratio: 0.5047941342357586
generation_params: {'temperature': 1.0, 'top_p': 1.0, 'min_p': 0.0, 'top_k': 50, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['</s>', '<|user|>', '###', '\n'], 'max_input_tokens': 1024, 'best_of': 4, 'max_output_tokens': 64}
formatter: {'memory_template': '<s>[INST] This is an entertaining conversation. You are {bot_name} who has the persona: {memory}.\nPlay the role of {bot_name}. Your goal is to make sure the conversation is always novel and creative. {bot_name} should ask lots of questions. [/INST]\n', 'prompt_template': '{prompt}\n', 'bot_template': '{bot_name}: {message}</s>', 'user_template': '[INST] {user_name}: {message} [/INST]', 'response_template': '{bot_name}:', 'truncate_by_message': False}
model_eval_status: success
reward_formatter: {'bot_template': 'Bot: {message}\n', 'memory_template': 'Memory: {memory}\n', 'prompt_template': '{prompt}\n', 'response_template': 'Bot:', 'truncate_by_message': False, 'user_template': 'User: {message}\n'}
Resubmit model
Running pipeline stage MKMLizer
Starting job with name neversleep-noromaid-v0-8068-v68-mkmlizer
Waiting for job on neversleep-noromaid-v0-8068-v68-mkmlizer to finish
neversleep-noromaid-v0-8068-v68-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
neversleep-noromaid-v0-8068-v68-mkmlizer: ║ _____ __ __ ║
neversleep-noromaid-v0-8068-v68-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
neversleep-noromaid-v0-8068-v68-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
neversleep-noromaid-v0-8068-v68-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
neversleep-noromaid-v0-8068-v68-mkmlizer: ║ /___/ ║
neversleep-noromaid-v0-8068-v68-mkmlizer: ║ ║
neversleep-noromaid-v0-8068-v68-mkmlizer: ║ Version: 0.8.14 ║
neversleep-noromaid-v0-8068-v68-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
neversleep-noromaid-v0-8068-v68-mkmlizer: ║ https://mk1.ai ║
neversleep-noromaid-v0-8068-v68-mkmlizer: ║ ║
neversleep-noromaid-v0-8068-v68-mkmlizer: ║ The license key for the current software has been verified as ║
neversleep-noromaid-v0-8068-v68-mkmlizer: ║ belonging to: ║
neversleep-noromaid-v0-8068-v68-mkmlizer: ║ ║
neversleep-noromaid-v0-8068-v68-mkmlizer: ║ Chai Research Corp. ║
neversleep-noromaid-v0-8068-v68-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
neversleep-noromaid-v0-8068-v68-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
neversleep-noromaid-v0-8068-v68-mkmlizer: ║ ║
neversleep-noromaid-v0-8068-v68-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
neversleep-noromaid-v0-8068-v68-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-v68-mkmlizer: warnings.warn(warning_message, FutureWarning)
neversleep-noromaid-v0-8068-v68-mkmlizer: Downloaded to shared memory in 75.738s
neversleep-noromaid-v0-8068-v68-mkmlizer: quantizing model to /dev/shm/model_cache
neversleep-noromaid-v0-8068-v68-mkmlizer: Saving flywheel model at /dev/shm/model_cache
neversleep-noromaid-v0-8068-v68-mkmlizer: quantized model in 58.203s
neversleep-noromaid-v0-8068-v68-mkmlizer: creating bucket guanaco-mkml-models
neversleep-noromaid-v0-8068-v68-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
neversleep-noromaid-v0-8068-v68-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v68
neversleep-noromaid-v0-8068-v68-mkmlizer: cp /dev/shm/model_cache/tokenizer.model s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v68/tokenizer.model
neversleep-noromaid-v0-8068-v68-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v68/config.json
neversleep-noromaid-v0-8068-v68-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v68/tokenizer.json
neversleep-noromaid-v0-8068-v68-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v68/tokenizer_config.json
neversleep-noromaid-v0-8068-v68-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v68/special_tokens_map.json
neversleep-noromaid-v0-8068-v68-mkmlizer: cp /dev/shm/model_cache/flywheel_model.3.safetensors s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v68/flywheel_model.3.safetensors
neversleep-noromaid-v0-8068-v68-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v68/flywheel_model.0.safetensors
neversleep-noromaid-v0-8068-v68-mkmlizer: cp /dev/shm/model_cache/flywheel_model.2.safetensors s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v68/flywheel_model.2.safetensors
neversleep-noromaid-v0-8068-v68-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v68/flywheel_model.1.safetensors
neversleep-noromaid-v0-8068-v68-mkmlizer: loading reward model from rirv938/reward_gpt2_medium_preference_24m_e2
neversleep-noromaid-v0-8068-v68-mkmlizer: Loading 0: 0%| | 0/995 [00:00<?, ?it/s] Loading 0: 5%|▌ | 52/995 [00:01<00:18, 50.58it/s] Loading 0: 11%|█ | 107/995 [00:01<00:16, 54.14it/s] Loading 0: 16%|█▋ | 162/995 [00:02<00:14, 56.29it/s] Loading 0: 21%|██ | 210/995 [00:04<00:18, 42.05it/s] Loading 0: 27%|██▋ | 265/995 [00:05<00:15, 46.94it/s] Loading 0: 28%|██▊ | 278/995 [00:15<01:15, 9.52it/s] Loading 0: 32%|███▏ | 320/995 [00:16<00:53, 12.73it/s] Loading 0: 37%|███▋ | 368/995 [00:17<00:35, 17.44it/s] Loading 0: 43%|████▎ | 423/995 [00:18<00:24, 23.51it/s] Loading 0: 48%|████▊ | 478/995 [00:19<00:17, 28.89it/s] Loading 0: 53%|█████▎ | 526/995 [00:20<00:14, 32.28it/s] Loading 0: 57%|█████▋ | 565/995 [00:30<00:38, 11.31it/s] Loading 0: 58%|█████▊ | 581/995 [00:31<00:36, 11.42it/s] Loading 0: 64%|██████▍ | 636/995 [00:32<00:21, 16.41it/s] Loading 0: 69%|██████▉ | 691/995 [00:34<00:14, 21.69it/s] Loading 0: 74%|███████▍ | 739/995 [00:35<00:09, 25.73it/s] Loading 0: 80%|███████▉ | 794/995 [00:36<00:06, 31.24it/s] Loading 0: 85%|████████▌ | 846/995 [00:46<00:12, 12.14it/s] Loading 0: 85%|████████▌ | 849/995 [00:47<00:13, 10.89it/s] Loading 0: 90%|█████████ | 897/995 [00:48<00:06, 14.98it/s] Loading 0: 96%|█████████▌| 952/995 [00:49<00:02, 20.76it/s] Loading 0: 100%|██████████| 995/995 [00:50<00:00, 23.43it/s] /opt/conda/lib/python3.10/site-packages/transformers/models/auto/configuration_auto.py:913: FutureWarning: The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers. Please use `token` instead.
neversleep-noromaid-v0-8068-v68-mkmlizer: warnings.warn(
neversleep-noromaid-v0-8068-v68-mkmlizer: /opt/conda/lib/python3.10/site-packages/transformers/models/auto/tokenization_auto.py:757: FutureWarning: The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers. Please use `token` instead.
neversleep-noromaid-v0-8068-v68-mkmlizer: warnings.warn(
neversleep-noromaid-v0-8068-v68-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-v68-mkmlizer: return self.fget.__get__(instance, owner)()
neversleep-noromaid-v0-8068-v68-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
neversleep-noromaid-v0-8068-v68-mkmlizer: Saving duration: 0.238s
neversleep-noromaid-v0-8068-v68-mkmlizer: Processed model rirv938/reward_gpt2_medium_preference_24m_e2 in 8.343s
neversleep-noromaid-v0-8068-v68-mkmlizer: creating bucket guanaco-reward-models
neversleep-noromaid-v0-8068-v68-mkmlizer: Bucket 's3://guanaco-reward-models/' created
neversleep-noromaid-v0-8068-v68-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/neversleep-noromaid-v0-8068-v68_reward
neversleep-noromaid-v0-8068-v68-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/neversleep-noromaid-v0-8068-v68_reward/config.json
neversleep-noromaid-v0-8068-v68-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/neversleep-noromaid-v0-8068-v68_reward/tokenizer_config.json
neversleep-noromaid-v0-8068-v68-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/neversleep-noromaid-v0-8068-v68_reward/special_tokens_map.json
neversleep-noromaid-v0-8068-v68-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/neversleep-noromaid-v0-8068-v68_reward/vocab.json
neversleep-noromaid-v0-8068-v68-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/neversleep-noromaid-v0-8068-v68_reward/merges.txt
neversleep-noromaid-v0-8068-v68-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/neversleep-noromaid-v0-8068-v68_reward/tokenizer.json
neversleep-noromaid-v0-8068-v68-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/neversleep-noromaid-v0-8068-v68_reward/reward.tensors
Job neversleep-noromaid-v0-8068-v68-mkmlizer completed after 185.84s with status: succeeded
Stopping job with name neversleep-noromaid-v0-8068-v68-mkmlizer
Pipeline stage MKMLizer completed in 189.71s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.10s
Running pipeline stage ISVCDeployer
Creating inference service neversleep-noromaid-v0-8068-v68
Waiting for inference service neversleep-noromaid-v0-8068-v68 to be ready
Inference service neversleep-noromaid-v0-8068-v68 ready after 110.63041806221008s
Pipeline stage ISVCDeployer completed in 118.09s
Running pipeline stage StressChecker
Received healthy response to inference request in 3.287327766418457s
Received healthy response to inference request in 2.4040355682373047s
Received healthy response to inference request in 2.393728256225586s
Received healthy response to inference request in 2.214773416519165s
Received healthy response to inference request in 4.730758905410767s
5 requests
0 failed requests
5th percentile: 2.250564384460449
10th percentile: 2.2863553524017335
20th percentile: 2.357937288284302
30th percentile: 2.3957897186279298
40th percentile: 2.399912643432617
50th percentile: 2.4040355682373047
60th percentile: 2.7573524475097657
70th percentile: 3.1106693267822263
80th percentile: 3.576013994216919
90th percentile: 4.153386449813842
95th percentile: 4.4420726776123045
99th percentile: 4.6730216598510745
mean time: 3.0061247825622557
Pipeline stage StressChecker completed in 15.68s
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 0.03s
M-Eval Dataset for topic stay_in_character is loaded
neversleep-noromaid-v0-_8068_v68 status is now deployed due to DeploymentManager action
neversleep-noromaid-v0-_8068_v68 status is now inactive due to admin request
admin requested tearing down of neversleep-noromaid-v0-_8068_v68
Running pipeline stage ISVCDeleter
Checking if service neversleep-noromaid-v0-8068-v68 is running
Skipping teardown as no inference service was found
Pipeline stage ISVCDeleter completed in 2.48s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key neversleep-noromaid-v0-8068-v68/config.json from bucket guanaco-mkml-models
Deleting key neversleep-noromaid-v0-8068-v68/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key neversleep-noromaid-v0-8068-v68/flywheel_model.1.safetensors from bucket guanaco-mkml-models
Deleting key neversleep-noromaid-v0-8068-v68/flywheel_model.2.safetensors from bucket guanaco-mkml-models
Deleting key neversleep-noromaid-v0-8068-v68/flywheel_model.3.safetensors from bucket guanaco-mkml-models
Deleting key neversleep-noromaid-v0-8068-v68/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key neversleep-noromaid-v0-8068-v68/tokenizer.json from bucket guanaco-mkml-models
Deleting key neversleep-noromaid-v0-8068-v68/tokenizer.model from bucket guanaco-mkml-models
Deleting key neversleep-noromaid-v0-8068-v68/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key neversleep-noromaid-v0-8068-v68_reward/config.json from bucket guanaco-reward-models
Deleting key neversleep-noromaid-v0-8068-v68_reward/merges.txt from bucket guanaco-reward-models
Deleting key neversleep-noromaid-v0-8068-v68_reward/reward.tensors from bucket guanaco-reward-models
Deleting key neversleep-noromaid-v0-8068-v68_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key neversleep-noromaid-v0-8068-v68_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key neversleep-noromaid-v0-8068-v68_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key neversleep-noromaid-v0-8068-v68_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 7.49s
neversleep-noromaid-v0-_8068_v68 status is now torndown due to DeploymentManager action