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-qwen-32b-sft-exp-38408-v1-mkmlizer
Waiting for job on chaiml-qwen-32b-sft-exp-38408-v1-mkmlizer to finish
chaiml-qwen-32b-sft-exp-38408-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-qwen-32b-sft-exp-38408-v1-mkmlizer: ║ _____ __ __ ║
chaiml-qwen-32b-sft-exp-38408-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
chaiml-qwen-32b-sft-exp-38408-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
chaiml-qwen-32b-sft-exp-38408-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
chaiml-qwen-32b-sft-exp-38408-v1-mkmlizer: ║ /___/ ║
chaiml-qwen-32b-sft-exp-38408-v1-mkmlizer: ║ ║
chaiml-qwen-32b-sft-exp-38408-v1-mkmlizer: ║ Version: 0.12.8 ║
chaiml-qwen-32b-sft-exp-38408-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
chaiml-qwen-32b-sft-exp-38408-v1-mkmlizer: ║ https://mk1.ai ║
chaiml-qwen-32b-sft-exp-38408-v1-mkmlizer: ║ ║
chaiml-qwen-32b-sft-exp-38408-v1-mkmlizer: ║ The license key for the current software has been verified as ║
chaiml-qwen-32b-sft-exp-38408-v1-mkmlizer: ║ belonging to: ║
chaiml-qwen-32b-sft-exp-38408-v1-mkmlizer: ║ ║
chaiml-qwen-32b-sft-exp-38408-v1-mkmlizer: ║ Chai Research Corp. ║
chaiml-qwen-32b-sft-exp-38408-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
chaiml-qwen-32b-sft-exp-38408-v1-mkmlizer: ║ Expiration: 2028-03-31 23:59:59 ║
chaiml-qwen-32b-sft-exp-38408-v1-mkmlizer: ║ ║
chaiml-qwen-32b-sft-exp-38408-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-qwen-32b-sft-exp-38408-v1-mkmlizer: Downloaded to shared memory in 107.631s
chaiml-qwen-32b-sft-exp-38408-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpmk9oam3g, device:0
chaiml-qwen-32b-sft-exp-38408-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-qwen-32b-sft-exp-38408-v1-mkmlizer: quantized model in 64.024s
chaiml-qwen-32b-sft-exp-38408-v1-mkmlizer: Processed model ChaiML/qwen-32b-sft-exp2-retrysftdata-full in 171.656s
chaiml-qwen-32b-sft-exp-38408-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-qwen-32b-sft-exp-38408-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-qwen-32b-sft-exp-38408-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-qwen-32b-sft-exp-38408-v1
chaiml-qwen-32b-sft-exp-38408-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-qwen-32b-sft-exp-38408-v1/config.json
chaiml-qwen-32b-sft-exp-38408-v1-mkmlizer: cp /dev/shm/model_cache/added_tokens.json s3://guanaco-mkml-models/chaiml-qwen-32b-sft-exp-38408-v1/added_tokens.json
chaiml-qwen-32b-sft-exp-38408-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-qwen-32b-sft-exp-38408-v1/special_tokens_map.json
chaiml-qwen-32b-sft-exp-38408-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-qwen-32b-sft-exp-38408-v1/tokenizer_config.json
chaiml-qwen-32b-sft-exp-38408-v1-mkmlizer: cp /dev/shm/model_cache/merges.txt s3://guanaco-mkml-models/chaiml-qwen-32b-sft-exp-38408-v1/merges.txt
chaiml-qwen-32b-sft-exp-38408-v1-mkmlizer: cp /dev/shm/model_cache/vocab.json s3://guanaco-mkml-models/chaiml-qwen-32b-sft-exp-38408-v1/vocab.json
chaiml-qwen-32b-sft-exp-38408-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-qwen-32b-sft-exp-38408-v1/tokenizer.json
chaiml-qwen-32b-sft-exp-38408-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.2.safetensors s3://guanaco-mkml-models/chaiml-qwen-32b-sft-exp-38408-v1/flywheel_model.2.safetensors
chaiml-qwen-32b-sft-exp-38408-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-qwen-32b-sft-exp-38408-v1/flywheel_model.1.safetensors
chaiml-qwen-32b-sft-exp-38408-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-qwen-32b-sft-exp-38408-v1/flywheel_model.0.safetensors
chaiml-qwen-32b-sft-exp-38408-v1-mkmlizer:
Loading 0: 0%| | 0/771 [00:00<?, ?it/s]
Loading 0: 1%| | 5/771 [00:00<00:19, 39.05it/s]
Loading 0: 2%|▏ | 16/771 [00:00<00:10, 74.38it/s]
Loading 0: 4%|▎ | 27/771 [00:00<00:08, 88.05it/s]
Loading 0: 5%|▍ | 37/771 [00:00<00:08, 90.54it/s]
Loading 0: 6%|▌ | 47/771 [00:00<00:13, 53.67it/s]
Loading 0: 7%|▋ | 55/771 [00:00<00:13, 51.28it/s]
Loading 0: 8%|▊ | 64/771 [00:01<00:11, 58.96it/s]
Loading 0: 10%|▉ | 75/771 [00:01<00:10, 69.59it/s]
Loading 0: 11%|█ | 84/771 [00:01<00:09, 73.91it/s]
Loading 0: 12%|█▏ | 93/771 [00:01<00:09, 70.98it/s]
Loading 0: 14%|█▎ | 106/771 [00:01<00:10, 61.41it/s]
Loading 0: 15%|█▍ | 113/771 [00:01<00:11, 58.63it/s]
Loading 0: 16%|█▌ | 121/771 [00:01<00:11, 59.02it/s]
Loading 0: 17%|█▋ | 132/771 [00:02<00:09, 69.68it/s]
Loading 0: 18%|█▊ | 142/771 [00:02<00:08, 76.48it/s]
Loading 0: 20%|█▉ | 152/771 [00:02<00:07, 81.41it/s]
Loading 0: 21%|██ | 161/771 [00:02<00:07, 76.28it/s]
Loading 0: 22%|██▏ | 169/771 [00:02<00:11, 52.76it/s]
Loading 0: 23%|██▎ | 176/771 [00:02<00:11, 53.06it/s]
Loading 0: 24%|██▍ | 184/771 [00:02<00:09, 58.76it/s]
Loading 0: 25%|██▌ | 195/771 [00:02<00:08, 69.87it/s]
Loading 0: 26%|██▋ | 203/771 [00:03<00:07, 71.81it/s]
Loading 0: 27%|██▋ | 211/771 [00:03<00:08, 68.46it/s]
Loading 0: 29%|██▉ | 226/771 [00:03<00:08, 61.75it/s]
Loading 0: 30%|███ | 233/771 [00:03<00:10, 50.72it/s]
Loading 0: 32%|███▏ | 244/771 [00:03<00:08, 61.17it/s]
Loading 0: 33%|███▎ | 255/771 [00:03<00:07, 70.50it/s]
Loading 0: 34%|███▍ | 264/771 [00:04<00:06, 73.25it/s]
Loading 0: 35%|███▌ | 273/771 [00:04<00:07, 70.52it/s]
Loading 0: 37%|███▋ | 286/771 [00:04<00:07, 61.47it/s]
Loading 0: 38%|███▊ | 293/771 [00:04<00:09, 51.60it/s]
Loading 0: 39%|███▉ | 303/771 [00:19<03:36, 2.17it/s]
Loading 0: 40%|████ | 311/771 [00:19<02:38, 2.90it/s]
Loading 0: 41%|████ | 318/771 [00:19<01:59, 3.79it/s]
Loading 0: 43%|████▎ | 328/771 [00:19<01:19, 5.58it/s]
Loading 0: 44%|████▍ | 338/771 [00:19<00:53, 8.03it/s]
Loading 0: 45%|████▍ | 346/771 [00:19<00:42, 10.00it/s]
Loading 0: 46%|████▌ | 353/771 [00:20<00:35, 11.66it/s]
Loading 0: 47%|████▋ | 364/771 [00:20<00:23, 17.18it/s]
Loading 0: 49%|████▊ | 375/771 [00:20<00:16, 24.04it/s]
Loading 0: 50%|████▉ | 383/771 [00:20<00:13, 29.35it/s]
Loading 0: 51%|█████ | 391/771 [00:20<00:11, 34.29it/s]
Loading 0: 53%|█████▎ | 406/771 [00:20<00:09, 40.53it/s]
Loading 0: 54%|█████▎ | 413/771 [00:21<00:09, 38.22it/s]
Loading 0: 55%|█████▍ | 424/771 [00:21<00:07, 48.35it/s]
Loading 0: 56%|█████▋ | 435/771 [00:21<00:05, 58.38it/s]
Loading 0: 58%|█████▊ | 444/771 [00:21<00:05, 64.17it/s]
Loading 0: 59%|█████▉ | 453/771 [00:21<00:04, 64.42it/s]
Loading 0: 60%|██████ | 466/771 [00:21<00:05, 59.20it/s]
Loading 0: 61%|██████▏ | 473/771 [00:21<00:05, 50.65it/s]
Loading 0: 63%|██████▎ | 484/771 [00:22<00:04, 61.14it/s]
Loading 0: 64%|██████▍ | 495/771 [00:22<00:03, 70.54it/s]
Loading 0: 65%|██████▌ | 504/771 [00:22<00:03, 74.50it/s]
Loading 0: 67%|██████▋ | 513/771 [00:22<00:03, 71.31it/s]
Loading 0: 68%|██████▊ | 526/771 [00:22<00:03, 62.08it/s]
Loading 0: 69%|██████▉ | 533/771 [00:22<00:04, 51.88it/s]
Loading 0: 71%|███████ | 544/771 [00:22<00:03, 62.27it/s]
Loading 0: 72%|███████▏ | 555/771 [00:23<00:03, 71.84it/s]
Loading 0: 73%|███████▎ | 564/771 [00:23<00:02, 74.72it/s]
Loading 0: 74%|███████▍ | 573/771 [00:23<00:02, 72.00it/s]
Loading 0: 76%|███████▌ | 586/771 [00:23<00:02, 62.68it/s]
Loading 0: 77%|███████▋ | 593/771 [00:23<00:03, 52.39it/s]
Loading 0: 78%|███████▊ | 604/771 [00:23<00:02, 62.48it/s]
Loading 0: 80%|███████▉ | 615/771 [00:24<00:02, 72.09it/s]
Loading 0: 81%|████████ | 624/771 [00:24<00:01, 74.47it/s]
Loading 0: 82%|████████▏ | 633/771 [00:38<01:04, 2.14it/s]
Loading 0: 84%|████████▍ | 646/771 [00:39<00:38, 3.28it/s]
Loading 0: 85%|████████▍ | 654/771 [00:39<00:28, 4.15it/s]
Loading 0: 86%|████████▌ | 664/771 [00:39<00:18, 5.85it/s]
Loading 0: 88%|████████▊ | 675/771 [00:39<00:11, 8.41it/s]
Loading 0: 89%|████████▊ | 683/771 [00:39<00:08, 10.84it/s]
Loading 0: 90%|████████▉ | 691/771 [00:39<00:05, 13.82it/s]
Loading 0: 92%|█████████▏| 706/771 [00:40<00:03, 19.97it/s]
Loading 0: 92%|█████████▏| 713/771 [00:40<00:02, 21.87it/s]
Loading 0: 94%|█████████▍| 724/771 [00:40<00:01, 29.53it/s]
Loading 0: 95%|█████████▌| 735/771 [00:40<00:00, 38.36it/s]
Loading 0: 96%|█████████▋| 744/771 [00:40<00:00, 45.24it/s]
Loading 0: 98%|█████████▊| 753/771 [00:40<00:00, 49.47it/s]
Loading 0: 99%|█████████▉| 766/771 [00:48<00:01, 4.28it/s]
Job chaiml-qwen-32b-sft-exp-38408-v1-mkmlizer completed after 207.46s with status: succeeded
Stopping job with name chaiml-qwen-32b-sft-exp-38408-v1-mkmlizer
Pipeline stage MKMLizer completed in 207.98s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.18s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-qwen-32b-sft-exp-38408-v1
Waiting for inference service chaiml-qwen-32b-sft-exp-38408-v1 to be ready
Inference service chaiml-qwen-32b-sft-exp-38408-v1 ready after 140.97047924995422s
Pipeline stage MKMLDeployer completed in 141.44s
run pipeline stage %s
Running pipeline stage StressChecker
HTTPConnectionPool(host='guanaco-submitter.guanaco-backend.k2.chaiverse.com', port=80): Read timed out. (read timeout=20)
Received unhealthy response to inference request!
Received healthy response to inference request in 3.4377264976501465s
Received healthy response to inference request in 2.79030179977417s
Received healthy response to inference request in 2.6895663738250732s
Received healthy response to inference request in 2.9003045558929443s
5 requests
1 failed requests
5th percentile: 2.7097134590148926
10th percentile: 2.729860544204712
20th percentile: 2.7701547145843506
30th percentile: 2.812302350997925
40th percentile: 2.8563034534454346
50th percentile: 2.9003045558929443
60th percentile: 3.1152733325958253
70th percentile: 3.330242109298706
80th percentile: 6.779253387451175
90th percentile: 13.462307167053224
95th percentile: 16.803834056854246
99th percentile: 19.477055568695068
mean time: 6.3926520347595215
%s, retrying in %s seconds...
Received healthy response to inference request in 2.828871488571167s
Received healthy response to inference request in 2.892692804336548s
Received healthy response to inference request in 2.5297818183898926s
Received healthy response to inference request in 2.7516775131225586s
Received healthy response to inference request in 2.7183117866516113s
5 requests
0 failed requests
5th percentile: 2.5674878120422364
10th percentile: 2.6051938056945803
20th percentile: 2.6806057929992675
30th percentile: 2.7249849319458006
40th percentile: 2.7383312225341796
50th percentile: 2.7516775131225586
60th percentile: 2.782555103302002
70th percentile: 2.8134326934814453
80th percentile: 2.841635751724243
90th percentile: 2.8671642780303954
95th percentile: 2.879928541183472
99th percentile: 2.8901399517059327
mean time: 2.7442670822143556
Pipeline stage StressChecker completed in 48.51s
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 0.97s
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 0.70s
Shutdown handler de-registered
chaiml-qwen-32b-sft-exp_38408_v1 status is now deployed due to DeploymentManager action
Shutdown handler registered
run pipeline %s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Skipping teardown as no inference service was successfully deployed
Pipeline stage MKMLProfilerDeleter completed in 0.13s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.10s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service chaiml-qwen-32b-sft-exp-38408-v1-profiler
Waiting for inference service chaiml-qwen-32b-sft-exp-38408-v1-profiler to be ready
Shutdown handler registered
run pipeline %s
run pipeline stage %s
Running pipeline stage OfflineFamilyFriendlyScorer
Evaluating %s Family Friendly Score with %s threads
Pipeline stage OfflineFamilyFriendlyScorer completed in 3593.52s
Shutdown handler de-registered
chaiml-qwen-32b-sft-exp_38408_v1 status is now inactive due to auto deactivation removed underperforming models
chaiml-qwen-32b-sft-exp_38408_v1 status is now torndown due to DeploymentManager action