Running pipeline stage MKMLizer
Starting job with name neversleep-noromaid-v0-8068-v59-mkmlizer
Waiting for job on neversleep-noromaid-v0-8068-v59-mkmlizer to finish
neversleep-noromaid-v0-8068-v59-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
neversleep-noromaid-v0-8068-v59-mkmlizer: ║ _____ __ __ ║
neversleep-noromaid-v0-8068-v59-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
neversleep-noromaid-v0-8068-v59-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
neversleep-noromaid-v0-8068-v59-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
neversleep-noromaid-v0-8068-v59-mkmlizer: ║ /___/ ║
neversleep-noromaid-v0-8068-v59-mkmlizer: ║ ║
neversleep-noromaid-v0-8068-v59-mkmlizer: ║ Version: 0.8.14 ║
neversleep-noromaid-v0-8068-v59-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
neversleep-noromaid-v0-8068-v59-mkmlizer: ║ https://mk1.ai ║
neversleep-noromaid-v0-8068-v59-mkmlizer: ║ ║
neversleep-noromaid-v0-8068-v59-mkmlizer: ║ The license key for the current software has been verified as ║
neversleep-noromaid-v0-8068-v59-mkmlizer: ║ belonging to: ║
neversleep-noromaid-v0-8068-v59-mkmlizer: ║ ║
neversleep-noromaid-v0-8068-v59-mkmlizer: ║ Chai Research Corp. ║
neversleep-noromaid-v0-8068-v59-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
neversleep-noromaid-v0-8068-v59-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
neversleep-noromaid-v0-8068-v59-mkmlizer: ║ ║
neversleep-noromaid-v0-8068-v59-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
neversleep-noromaid-v0-8068-v59-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-v59-mkmlizer: warnings.warn(warning_message, FutureWarning)
neversleep-noromaid-v0-8068-v59-mkmlizer: Downloaded to shared memory in 65.068s
neversleep-noromaid-v0-8068-v59-mkmlizer: quantizing model to /dev/shm/model_cache
neversleep-noromaid-v0-8068-v59-mkmlizer: Saving flywheel model at /dev/shm/model_cache
neversleep-noromaid-v0-8068-v59-mkmlizer: quantized model in 53.277s
neversleep-noromaid-v0-8068-v59-mkmlizer: Processed model NeverSleep/Noromaid-v0.1-mixtral-8x7b-Instruct-v3 in 123.846s
neversleep-noromaid-v0-8068-v59-mkmlizer: creating bucket guanaco-mkml-models
neversleep-noromaid-v0-8068-v59-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
neversleep-noromaid-v0-8068-v59-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v59
neversleep-noromaid-v0-8068-v59-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v59/special_tokens_map.json
neversleep-noromaid-v0-8068-v59-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v59/config.json
neversleep-noromaid-v0-8068-v59-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v59/tokenizer.json
neversleep-noromaid-v0-8068-v59-mkmlizer: cp /dev/shm/model_cache/tokenizer.model s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v59/tokenizer.model
neversleep-noromaid-v0-8068-v59-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v59/tokenizer_config.json
neversleep-noromaid-v0-8068-v59-mkmlizer: cp /dev/shm/model_cache/flywheel_model.3.safetensors s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v59/flywheel_model.3.safetensors
neversleep-noromaid-v0-8068-v59-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v59/flywheel_model.0.safetensors
neversleep-noromaid-v0-8068-v59-mkmlizer: cp /dev/shm/model_cache/flywheel_model.2.safetensors s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v59/flywheel_model.2.safetensors
neversleep-noromaid-v0-8068-v59-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/neversleep-noromaid-v0-8068-v59/flywheel_model.1.safetensors
neversleep-noromaid-v0-8068-v59-mkmlizer: loading reward model from rirv938/scaleup_medium_4000000_step_125000
neversleep-noromaid-v0-8068-v59-mkmlizer:
Loading 0: 0%| | 0/995 [00:00<?, ?it/s]
Loading 0: 5%|▌ | 52/995 [00:00<00:15, 59.59it/s]
Loading 0: 11%|█ | 107/995 [00:01<00:14, 61.30it/s]
Loading 0: 16%|█▋ | 162/995 [00:02<00:13, 63.33it/s]
Loading 0: 21%|██ | 210/995 [00:03<00:12, 60.93it/s]
Loading 0: 27%|██▋ | 265/995 [00:04<00:11, 61.74it/s]
Loading 0: 28%|██▊ | 278/995 [00:13<01:06, 10.85it/s]
Loading 0: 32%|███▏ | 320/995 [00:14<00:46, 14.40it/s]
Loading 0: 37%|███▋ | 368/995 [00:15<00:31, 19.65it/s]
Loading 0: 43%|████▎ | 423/995 [00:16<00:21, 26.48it/s]
Loading 0: 48%|████▊ | 478/995 [00:16<00:15, 33.43it/s]
Loading 0: 53%|█████▎ | 526/995 [00:17<00:12, 38.16it/s]
Loading 0: 57%|█████▋ | 565/995 [00:27<00:35, 11.99it/s]
Loading 0: 58%|█████▊ | 581/995 [00:28<00:33, 12.28it/s]
Loading 0: 64%|██████▍ | 636/995 [00:29<00:19, 18.04it/s]
Loading 0: 69%|██████▉ | 691/995 [00:30<00:12, 24.46it/s]
Loading 0: 74%|███████▍ | 739/995 [00:30<00:08, 29.78it/s]
Loading 0: 80%|███████▉ | 794/995 [00:31<00:05, 36.53it/s]
Loading 0: 85%|████████▌ | 846/995 [00:41<00:11, 12.94it/s]
Loading 0: 86%|████████▌ | 851/995 [00:42<00:12, 11.66it/s]
Loading 0: 90%|█████████ | 897/995 [00:43<00:06, 15.94it/s]
Loading 0: 96%|█████████▌| 952/995 [00:44<00:01, 22.54it/s]
Loading 0: 100%|██████████| 995/995 [00:45<00:00, 25.28it/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-v59-mkmlizer: warnings.warn(
neversleep-noromaid-v0-8068-v59-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-v59-mkmlizer: warnings.warn(
neversleep-noromaid-v0-8068-v59-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
neversleep-noromaid-v0-8068-v59-mkmlizer: Saving duration: 0.248s
neversleep-noromaid-v0-8068-v59-mkmlizer: Processed model rirv938/scaleup_medium_4000000_step_125000 in 6.058s
neversleep-noromaid-v0-8068-v59-mkmlizer: creating bucket guanaco-reward-models
neversleep-noromaid-v0-8068-v59-mkmlizer: Bucket 's3://guanaco-reward-models/' created
neversleep-noromaid-v0-8068-v59-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/neversleep-noromaid-v0-8068-v59_reward
neversleep-noromaid-v0-8068-v59-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/neversleep-noromaid-v0-8068-v59_reward/special_tokens_map.json
neversleep-noromaid-v0-8068-v59-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/neversleep-noromaid-v0-8068-v59_reward/config.json
neversleep-noromaid-v0-8068-v59-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/neversleep-noromaid-v0-8068-v59_reward/tokenizer_config.json
neversleep-noromaid-v0-8068-v59-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/neversleep-noromaid-v0-8068-v59_reward/vocab.json
neversleep-noromaid-v0-8068-v59-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/neversleep-noromaid-v0-8068-v59_reward/merges.txt
neversleep-noromaid-v0-8068-v59-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/neversleep-noromaid-v0-8068-v59_reward/tokenizer.json
neversleep-noromaid-v0-8068-v59-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/neversleep-noromaid-v0-8068-v59_reward/reward.tensors
Job neversleep-noromaid-v0-8068-v59-mkmlizer completed after 165.47s with status: succeeded
Stopping job with name neversleep-noromaid-v0-8068-v59-mkmlizer
Pipeline stage MKMLizer completed in 169.82s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.10s
Running pipeline stage ISVCDeployer
Creating inference service neversleep-noromaid-v0-8068-v59
Waiting for inference service neversleep-noromaid-v0-8068-v59 to be ready
Inference service neversleep-noromaid-v0-8068-v59 ready after 70.37861371040344s
Pipeline stage ISVCDeployer completed in 78.60s
Running pipeline stage StressChecker
Received healthy response to inference request in 3.737103223800659s
Received healthy response to inference request in 2.894136428833008s
Received healthy response to inference request in 2.8335185050964355s
%s, retrying in %s seconds...
Received healthy response to inference request in 3.0734121799468994s
Received healthy response to inference request in 3.3205955028533936s
Received healthy response to inference request in 2.6937341690063477s
Received healthy response to inference request in 2.717236280441284s
Received healthy response to inference request in 2.8823633193969727s
5 requests
0 failed requests
5th percentile: 2.698434591293335
10th percentile: 2.7031350135803223
20th percentile: 2.712535858154297
30th percentile: 2.750261688232422
40th percentile: 2.8163125038146974
50th percentile: 2.8823633193969727
60th percentile: 2.9587828636169435
70th percentile: 3.035202407836914
80th percentile: 3.1228488445281983
90th percentile: 3.2217221736907957
95th percentile: 3.2711588382720946
99th percentile: 3.3107081699371337
mean time: 2.9374682903289795
Pipeline stage StressChecker completed in 44.94s
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_v59 status is now deployed due to DeploymentManager action
neversleep-noromaid-v0-_8068_v59 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of neversleep-noromaid-v0-_8068_v59
Running pipeline stage ISVCDeleter
Checking if service neversleep-noromaid-v0-8068-v59 is running
Skipping teardown as no inference service was found
Pipeline stage ISVCDeleter completed in 2.23s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key neversleep-noromaid-v0-8068-v59/config.json from bucket guanaco-mkml-models
Deleting key neversleep-noromaid-v0-8068-v59/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key neversleep-noromaid-v0-8068-v59/flywheel_model.1.safetensors from bucket guanaco-mkml-models
Deleting key neversleep-noromaid-v0-8068-v59/flywheel_model.2.safetensors from bucket guanaco-mkml-models
Deleting key neversleep-noromaid-v0-8068-v59/flywheel_model.3.safetensors from bucket guanaco-mkml-models
Deleting key neversleep-noromaid-v0-8068-v59/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key neversleep-noromaid-v0-8068-v59/tokenizer.json from bucket guanaco-mkml-models
Deleting key neversleep-noromaid-v0-8068-v59/tokenizer.model from bucket guanaco-mkml-models
Deleting key neversleep-noromaid-v0-8068-v59/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key neversleep-noromaid-v0-8068-v59_reward/config.json from bucket guanaco-reward-models
Deleting key neversleep-noromaid-v0-8068-v59_reward/merges.txt from bucket guanaco-reward-models
Deleting key neversleep-noromaid-v0-8068-v59_reward/reward.tensors from bucket guanaco-reward-models
Deleting key neversleep-noromaid-v0-8068-v59_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key neversleep-noromaid-v0-8068-v59_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key neversleep-noromaid-v0-8068-v59_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key neversleep-noromaid-v0-8068-v59_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 7.62s
neversleep-noromaid-v0-_8068_v59 status is now torndown due to DeploymentManager action