submission_id: chaiml-live-rm-20260216-_8340_v2
developer_uid: rirv938
status: torndown
model_repo: ChaiML/live_rm_20260216_1024_cp390_from_prev
generation_params: {'temperature': 1.0, 'top_p': 1.0, 'min_p': 0.0, 'top_k': 40, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n'], 'max_input_tokens': 1024, 'best_of': 1, 'max_output_tokens': 1}
formatter: {'memory_template': '', 'prompt_template': '', 'bot_template': '{bot_name}: {message}\n', 'user_template': '{user_name}: {message}\n', 'response_template': '', 'truncate_by_message': True}
timestamp: 2026-02-16T21:06:12+00:00
model_name: chaiml-live-rm-20260216-_8340_v2
Resubmit model
Shutdown handler not registered because Python interpreter is not running in the main thread
run pipeline %s
run pipeline stage %s
Running pipeline stage MKMLizer
Starting job with name chaiml-live-rm-20260216-8340-v2-mkmlizer
Waiting for job on chaiml-live-rm-20260216-8340-v2-mkmlizer to finish
chaiml-llama-8b-202503-16869-v38-mkmlizer: bash: cannot set terminal process group (-1): Inappropriate ioctl for device
chaiml-llama-8b-202503-16869-v38-mkmlizer: bash: no job control in this shell
chaiml-llama-8b-202503-16869-v38-mkmlizer: /root/miniconda3/envs/nvidia/lib/python3.11/site-packages/mk1/__init__.py:1: UserWarning: pkg_resources is deprecated as an API. See https://setuptools.pypa.io/en/latest/pkg_resources.html. The pkg_resources package is slated for removal as early as 2025-11-30. Refrain from using this package or pin to Setuptools<81.
chaiml-llama-8b-202503-16869-v38-mkmlizer:   __import__('pkg_resources').declare_namespace(__name__)
chaiml-llama-8b-202503-16869-v38-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-llama-8b-202503-16869-v38-mkmlizer: ║                                                                     ║
chaiml-llama-8b-202503-16869-v38-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
chaiml-llama-8b-202503-16869-v38-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
chaiml-llama-8b-202503-16869-v38-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
chaiml-llama-8b-202503-16869-v38-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
chaiml-llama-8b-202503-16869-v38-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
chaiml-llama-8b-202503-16869-v38-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
chaiml-llama-8b-202503-16869-v38-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
chaiml-llama-8b-202503-16869-v38-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
chaiml-llama-8b-202503-16869-v38-mkmlizer: ║                                                                     ║
chaiml-llama-8b-202503-16869-v38-mkmlizer: ║  Version: 0.30.6+torch280                                           ║
chaiml-llama-8b-202503-16869-v38-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
chaiml-llama-8b-202503-16869-v38-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
chaiml-llama-8b-202503-16869-v38-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-live-rm-20260216-8340-v2-mkmlizer: bash: cannot set terminal process group (-1): Inappropriate ioctl for device
chaiml-llama-8b-202503-16869-v38-mkmlizer: ║                                                                     ║
chaiml-live-rm-20260216-8340-v2-mkmlizer: bash: no job control in this shell
chaiml-llama-8b-202503-16869-v38-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-live-rm-20260216-8340-v2-mkmlizer: /root/miniconda3/envs/nvidia/lib/python3.11/site-packages/mk1/__init__.py:1: UserWarning: pkg_resources is deprecated as an API. See https://setuptools.pypa.io/en/latest/pkg_resources.html. The pkg_resources package is slated for removal as early as 2025-11-30. Refrain from using this package or pin to Setuptools<81.
chaiml-llama-8b-202503-16869-v38-mkmlizer: ║  belonging to:                                                      ║
chaiml-live-rm-20260216-8340-v2-mkmlizer:   __import__('pkg_resources').declare_namespace(__name__)
chaiml-llama-8b-202503-16869-v38-mkmlizer: ║                                                                     ║
chaiml-live-rm-20260216-8340-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-llama-8b-202503-16869-v38-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-live-rm-20260216-8340-v2-mkmlizer: ║                                                                     ║
chaiml-llama-8b-202503-16869-v38-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-live-rm-20260216-8340-v2-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
chaiml-llama-8b-202503-16869-v38-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
chaiml-live-rm-20260216-8340-v2-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
chaiml-llama-8b-202503-16869-v38-mkmlizer: ║                                                                     ║
chaiml-live-rm-20260216-8340-v2-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
chaiml-llama-8b-202503-16869-v38-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-live-rm-20260216-8340-v2-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
chaiml-live-rm-20260216-8340-v2-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
chaiml-live-rm-20260216-8340-v2-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
chaiml-live-rm-20260216-8340-v2-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
chaiml-live-rm-20260216-8340-v2-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
chaiml-live-rm-20260216-8340-v2-mkmlizer: ║                                                                     ║
chaiml-live-rm-20260216-8340-v2-mkmlizer: ║  Version: 0.30.6+torch280                                           ║
chaiml-live-rm-20260216-8340-v2-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
chaiml-live-rm-20260216-8340-v2-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
chaiml-live-rm-20260216-8340-v2-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-live-rm-20260216-8340-v2-mkmlizer: ║                                                                     ║
chaiml-live-rm-20260216-8340-v2-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-live-rm-20260216-8340-v2-mkmlizer: ║  belonging to:                                                      ║
chaiml-live-rm-20260216-8340-v2-mkmlizer: ║                                                                     ║
chaiml-live-rm-20260216-8340-v2-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-live-rm-20260216-8340-v2-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-live-rm-20260216-8340-v2-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
chaiml-live-rm-20260216-8340-v2-mkmlizer: ║                                                                     ║
chaiml-live-rm-20260216-8340-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-llama-8b-202503-16869-v38-mkmlizer: Downloaded to shared memory in 14.482s
chaiml-llama-8b-202503-16869-v38-mkmlizer: Checking if ChaiML/llama_8b_202503_1m_nemo_safety already exists in ChaiML
chaiml-llama-8b-202503-16869-v38-mkmlizer: quantizing model to /dev/shm/model_cache, profile:t0, folder:/tmp/tmpq2z3y3gl, device:0
chaiml-llama-8b-202503-16869-v38-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-live-rm-20260216-8340-v2-mkmlizer: Downloaded to shared memory in 15.701s
chaiml-live-rm-20260216-8340-v2-mkmlizer: Checking if ChaiML/live_rm_20260216_1024_cp390_from_prev already exists in ChaiML
chaiml-live-rm-20260216-8340-v2-mkmlizer: quantizing model to /dev/shm/model_cache, profile:t0, folder:/tmp/tmp6tbsf3ux, device:0
chaiml-live-rm-20260216-8340-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-llama-8b-202503-16869-v38-mkmlizer: 
Loading 0:   0%|          | 0.00/291 [00:00<?, ?it/s]
Loading 0:  14%|█▍        | 41.0/291 [00:01<00:06, 40.9it/s]
Loading 0:  14%|█▍        | 41.0/291 [00:01<00:06, 40.9it/s]
Loading 0:  29%|██▊       | 83.0/291 [00:02<00:05, 38.5it/s]
Loading 0:  29%|██▊       | 83.0/291 [00:02<00:05, 38.5it/s]
Loading 0:  42%|████▏     | 122/291 [00:03<00:04, 38.6it/s] 
Loading 0:  42%|████▏     | 122/291 [00:03<00:04, 38.6it/s]
Loading 0:  57%|█████▋    | 167/291 [00:04<00:03, 40.5it/s]
Loading 0:  57%|█████▋    | 167/291 [00:04<00:03, 40.5it/s]
Loading 0:  70%|██████▉   | 203/291 [00:05<00:02, 38.5it/s]
Loading 0:  70%|██████▉   | 203/291 [00:05<00:02, 38.5it/s]
Loading 0:  85%|████████▌ | 248/291 [00:06<00:01, 40.1it/s]
Loading 0:  85%|████████▌ | 248/291 [00:06<00:01, 40.1it/s]
Loading 0:  99%|█████████▊| 287/291 [00:07<00:00, 38.4it/s]
Loading 0:  99%|█████████▊| 287/291 [00:07<00:00, 38.4it/s]
Loading 0: 100%|██████████| 291/291 [00:07<00:00, 38.2it/s]
Loading 0: 100%|██████████| 291/291 [00:07<00:00, 38.2it/s]
                                                           

Loading 0: 100%|██████████| 291/291 [00:07<00:00, 38.9it/s]
chaiml-live-rm-20260216-8340-v2-mkmlizer: 
Loading 0:   0%|          | 0.00/291 [00:00<?, ?it/s]
Loading 0:  13%|█▎        | 37.0/291 [00:01<00:07, 32.3it/s]
Loading 0:  13%|█▎        | 37.0/291 [00:01<00:07, 32.3it/s]
Loading 0:  22%|██▏       | 64.0/291 [00:02<00:08, 27.9it/s]
Loading 0:  22%|██▏       | 64.0/291 [00:02<00:08, 27.9it/s]
Loading 0:  29%|██▉       | 85.0/291 [00:03<00:08, 24.8it/s]
Loading 0:  29%|██▉       | 85.0/291 [00:03<00:08, 24.8it/s]
Loading 0:  42%|████▏     | 122/291 [00:04<00:05, 29.1it/s] 
Loading 0:  42%|████▏     | 122/291 [00:04<00:05, 29.1it/s]
Loading 0:  57%|█████▋    | 167/291 [00:05<00:03, 34.6it/s]
Loading 0:  57%|█████▋    | 167/291 [00:05<00:03, 34.6it/s]
Loading 0:  70%|██████▉   | 203/291 [00:06<00:02, 35.1it/s]
Loading 0:  70%|██████▉   | 203/291 [00:06<00:02, 35.1it/s]
Loading 0:  85%|████████▌ | 248/291 [00:07<00:01, 37.9it/s]
Loading 0:  85%|████████▌ | 248/291 [00:07<00:01, 37.9it/s]
Loading 0:  99%|█████████▊| 287/291 [00:08<00:00, 37.5it/s]
Loading 0:  99%|█████████▊| 287/291 [00:08<00:00, 37.5it/s]
Loading 0: 100%|██████████| 291/291 [00:08<00:00, 37.5it/s]
Loading 0: 100%|██████████| 291/291 [00:08<00:00, 37.5it/s]
                                                           

Loading 0: 100%|██████████| 291/291 [00:08<00:00, 34.3it/s]
chaiml-llama-8b-202503-16869-v38-mkmlizer: quantized model in 18.648s
chaiml-llama-8b-202503-16869-v38-mkmlizer: Processed model ChaiML/llama_8b_202503_1m_nemo_safety in 33.131s
chaiml-llama-8b-202503-16869-v38-mkmlizer: creating bucket guanaco-mkml-models
chaiml-llama-8b-202503-16869-v38-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-llama-8b-202503-16869-v38-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-llama-8b-202503-16869-v38/nvidia
chaiml-llama-8b-202503-16869-v38-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-llama-8b-202503-16869-v38/nvidia/config.json
chaiml-llama-8b-202503-16869-v38-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-llama-8b-202503-16869-v38/nvidia/special_tokens_map.json
chaiml-llama-8b-202503-16869-v38-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-llama-8b-202503-16869-v38/nvidia/tokenizer_config.json
chaiml-llama-8b-202503-16869-v38-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-llama-8b-202503-16869-v38/nvidia/tokenizer.json
chaiml-live-rm-20260216-8340-v2-mkmlizer: quantized model in 19.392s
chaiml-live-rm-20260216-8340-v2-mkmlizer: Processed model ChaiML/live_rm_20260216_1024_cp390_from_prev in 35.094s
chaiml-live-rm-20260216-8340-v2-mkmlizer: creating bucket guanaco-mkml-models
chaiml-live-rm-20260216-8340-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-live-rm-20260216-8340-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-live-rm-20260216-8340-v2/nvidia
chaiml-live-rm-20260216-8340-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-live-rm-20260216-8340-v2/nvidia/config.json
chaiml-live-rm-20260216-8340-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-live-rm-20260216-8340-v2/nvidia/special_tokens_map.json
chaiml-live-rm-20260216-8340-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-live-rm-20260216-8340-v2/nvidia/tokenizer_config.json
chaiml-live-rm-20260216-8340-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-live-rm-20260216-8340-v2/nvidia/tokenizer.json
chaiml-llama-8b-202503-16869-v38-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-llama-8b-202503-16869-v38/nvidia/flywheel_model.0.safetensors
Job chaiml-llama-8b-202503-16869-v38-mkmlizer completed after 146.82s with status: succeeded
Stopping job with name chaiml-llama-8b-202503-16869-v38-mkmlizer
Pipeline stage MKMLizer completed in 148.41s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.41s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-llama-8b-202503-16869-v38
Waiting for inference service chaiml-llama-8b-202503-16869-v38 to be ready
chaiml-live-rm-20260216-8340-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-live-rm-20260216-8340-v2/nvidia/flywheel_model.0.safetensors
Job chaiml-live-rm-20260216-8340-v2-mkmlizer completed after 146.86s with status: succeeded
Stopping job with name chaiml-live-rm-20260216-8340-v2-mkmlizer
Pipeline stage MKMLizer completed in 148.53s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.48s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-live-rm-20260216-8340-v2
Waiting for inference service chaiml-live-rm-20260216-8340-v2 to be ready
Inference service chaiml-llama-8b-202503-16869-v38 ready after 162.0737705230713s
Pipeline stage MKMLDeployer completed in 163.68s
run pipeline stage %s
Running pipeline stage StressChecker
Inference service chaiml-live-rm-20260216-8340-v2 ready after 162.5830750465393s
Pipeline stage MKMLDeployer completed in 164.11s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 7.514412879943848s
Received healthy response to inference request in 5.186239004135132s
Received healthy response to inference request in 5.918688774108887s
Received healthy response to inference request in 7.606865406036377s
Received healthy response to inference request in 6.387980937957764s
Received healthy response to inference request in 6.506086826324463s
Received healthy response to inference request in 4.798445463180542s
Received healthy response to inference request in 5.624589443206787s
5 requests
Received healthy response to inference request in 6.191808700561523s
0 failed requests
5th percentile: 4.963674259185791
10th percentile: 5.12890305519104
20th percentile: 5.459360647201538
30th percentile: 5.683409309387207
40th percentile: 5.801049041748047
50th percentile: 5.918688774108887
60th percentile: 6.106405639648438
70th percentile: 6.294122505187988
80th percentile: 6.613267326354981
90th percentile: 7.063840103149414
95th percentile: 7.2891264915466305
99th percentile: 7.469355602264404
mean time: 6.048823499679566
%s, retrying in %s seconds...
Received healthy response to inference request in 7.361376762390137s
5 requests
0 failed requests
5th percentile: 5.38735294342041
10th percentile: 5.5884668827056885
20th percentile: 5.990694761276245
30th percentile: 6.254664325714112
40th percentile: 6.380375576019287
Received healthy response to inference request in 5.006708145141602s
50th percentile: 6.506086826324463
60th percentile: 6.848202800750732
70th percentile: 7.190318775177002
80th percentile: 7.410474491119385
90th percentile: 7.5086699485778805
95th percentile: 7.557767677307129
99th percentile: 7.597045860290527
mean time: 6.570475339889526
%s, retrying in %s seconds...
Received healthy response to inference request in 6.624146223068237s
Received healthy response to inference request in 5.728978633880615s
Received healthy response to inference request in 2.297630548477173s
Received healthy response to inference request in 4.7685706615448s
Received healthy response to inference request in 5.8833606243133545s
Received healthy response to inference request in 6.460174083709717s
Received healthy response to inference request in 5.548783779144287s
5 requests
0 failed requests
5th percentile: 2.8394460678100586
10th percentile: 3.3812615871429443
20th percentile: 4.464892625808716
30th percentile: 5.115123271942139
40th percentile: 5.331953525543213
50th percentile: 5.548783779144287
60th percentile: 5.682614517211914
70th percentile: 5.816445255279541
80th percentile: 6.031517744064331
90th percentile: 6.327831983566284
95th percentile: 6.475989103317261
99th percentile: 6.594514799118042
mean time: 5.072125864028931
Pipeline stage StressChecker completed in 70.04s
Received healthy response to inference request in 6.317852258682251s
run pipeline stage %s
Running pipeline stage OfflineFamilyFriendlyTriggerPipeline
run_pipeline:run_in_cloud %s
starting trigger_guanaco_pipeline args=%s
triggered trigger_guanaco_pipeline args=%s
Pipeline stage OfflineFamilyFriendlyTriggerPipeline completed in 2.06s
run pipeline stage %s
Running pipeline stage TriggerMKMLProfilingPipeline
run_pipeline:run_in_cloud %s
starting trigger_guanaco_pipeline args=%s
triggered trigger_guanaco_pipeline args=%s
Pipeline stage TriggerMKMLProfilingPipeline completed in 1.83s
Shutdown handler de-registered
chaiml-llama-8b-202503_16869_v38 status is now deployed due to DeploymentManager action
Received healthy response to inference request in 6.008444547653198s
5 requests
0 failed requests
5th percentile: 4.960652256011963
10th percentile: 5.152733850479126
20th percentile: 5.536897039413452
30th percentile: 5.784871816635132
40th percentile: 5.896658182144165
50th percentile: 6.008444547653198
60th percentile: 6.132207632064819
70th percentile: 6.25597071647644
80th percentile: 6.346316623687744
90th percentile: 6.403245353698731
95th percentile: 6.431709718704224
99th percentile: 6.454481210708618
mean time: 5.856804037094117
%s, retrying in %s seconds...
Received healthy response to inference request in 5.616637468338013s
Received healthy response to inference request in 7.048452377319336s
Received healthy response to inference request in 4.228388786315918s
Received healthy response to inference request in 7.236344575881958s
Received healthy response to inference request in 5.506155490875244s
5 requests
0 failed requests
5th percentile: 4.483942127227783
10th percentile: 4.739495468139649
20th percentile: 5.250602149963379
30th percentile: 5.528251886367798
40th percentile: 5.572444677352905
50th percentile: 5.616637468338013
60th percentile: 6.189363431930542
70th percentile: 6.762089395523071
80th percentile: 7.08603081703186
90th percentile: 7.161187696456909
95th percentile: 7.198766136169434
99th percentile: 7.2288288879394536
mean time: 5.927195739746094
clean up pipeline due to error=DeploymentChecksError('Unacceptable 70th percentile latency 6.762089395523071s')
Shutdown handler de-registered
chaiml-live-rm-20260216-_8340_v2 status is now failed due to DeploymentManager action
chaiml-live-rm-20260216-_8340_v2 status is now torndown due to DeploymentManager action