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-qwq32b-sft-exp1-del1k-v1-mkmlizer
Waiting for job on chaiml-qwq32b-sft-exp1-del1k-v1-mkmlizer to finish
chaiml-qwq32b-sft-exp1-del1k-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-qwq32b-sft-exp1-del1k-v1-mkmlizer: ║ _____ __ __ ║
chaiml-qwq32b-sft-exp1-del1k-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
chaiml-qwq32b-sft-exp1-del1k-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
chaiml-qwq32b-sft-exp1-del1k-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
chaiml-qwq32b-sft-exp1-del1k-v1-mkmlizer: ║ /___/ ║
chaiml-qwq32b-sft-exp1-del1k-v1-mkmlizer: ║ ║
chaiml-qwq32b-sft-exp1-del1k-v1-mkmlizer: ║ Version: 0.12.8 ║
chaiml-qwq32b-sft-exp1-del1k-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
chaiml-qwq32b-sft-exp1-del1k-v1-mkmlizer: ║ https://mk1.ai ║
chaiml-qwq32b-sft-exp1-del1k-v1-mkmlizer: ║ ║
chaiml-qwq32b-sft-exp1-del1k-v1-mkmlizer: ║ The license key for the current software has been verified as ║
chaiml-qwq32b-sft-exp1-del1k-v1-mkmlizer: ║ belonging to: ║
chaiml-qwq32b-sft-exp1-del1k-v1-mkmlizer: ║ ║
chaiml-qwq32b-sft-exp1-del1k-v1-mkmlizer: ║ Chai Research Corp. ║
chaiml-qwq32b-sft-exp1-del1k-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
chaiml-qwq32b-sft-exp1-del1k-v1-mkmlizer: ║ Expiration: 2025-04-15 23:59:59 ║
chaiml-qwq32b-sft-exp1-del1k-v1-mkmlizer: ║ ║
chaiml-qwq32b-sft-exp1-del1k-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
Failed to get response for submission chaiml-sft-gemma2-28b-v_83370_v5: HTTPConnectionPool(host='chaiml-sft-gemma2-28b-v-83370-v5-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
chaiml-qwq32b-sft-exp1-del1k-v1-mkmlizer: Downloaded to shared memory in 120.173s
chaiml-qwq32b-sft-exp1-del1k-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp81pyxo0w, device:0
chaiml-qwq32b-sft-exp1-del1k-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-qwq32b-sft-exp1-del1k-v1-mkmlizer: quantized model in 64.177s
chaiml-qwq32b-sft-exp1-del1k-v1-mkmlizer: Processed model ChaiML/qwq32b-sft-exp1-del1k in 184.350s
chaiml-qwq32b-sft-exp1-del1k-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-qwq32b-sft-exp1-del1k-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-qwq32b-sft-exp1-del1k-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-qwq32b-sft-exp1-del1k-v1
chaiml-qwq32b-sft-exp1-del1k-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-qwq32b-sft-exp1-del1k-v1/config.json
chaiml-qwq32b-sft-exp1-del1k-v1-mkmlizer: cp /dev/shm/model_cache/added_tokens.json s3://guanaco-mkml-models/chaiml-qwq32b-sft-exp1-del1k-v1/added_tokens.json
chaiml-qwq32b-sft-exp1-del1k-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-qwq32b-sft-exp1-del1k-v1/special_tokens_map.json
chaiml-qwq32b-sft-exp1-del1k-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-qwq32b-sft-exp1-del1k-v1/tokenizer_config.json
chaiml-qwq32b-sft-exp1-del1k-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.2.safetensors s3://guanaco-mkml-models/chaiml-qwq32b-sft-exp1-del1k-v1/flywheel_model.2.safetensors
chaiml-qwq32b-sft-exp1-del1k-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-qwq32b-sft-exp1-del1k-v1/flywheel_model.1.safetensors
chaiml-qwq32b-sft-exp1-del1k-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-qwq32b-sft-exp1-del1k-v1/flywheel_model.0.safetensors
chaiml-qwq32b-sft-exp1-del1k-v1-mkmlizer:
Loading 0: 0%| | 0/771 [00:00<?, ?it/s]
Loading 0: 1%| | 5/771 [00:00<00:20, 36.68it/s]
Loading 0: 2%|▏ | 16/771 [00:00<00:10, 70.56it/s]
Loading 0: 4%|▎ | 27/771 [00:00<00:08, 83.96it/s]
Loading 0: 5%|▍ | 36/771 [00:00<00:08, 83.53it/s]
Loading 0: 6%|▌ | 46/771 [00:00<00:13, 53.16it/s]
Loading 0: 7%|▋ | 53/771 [00:00<00:15, 45.21it/s]
Loading 0: 8%|▊ | 64/771 [00:01<00:12, 57.75it/s]
Loading 0: 10%|▉ | 75/771 [00:01<00:10, 68.82it/s]
Loading 0: 11%|█ | 84/771 [00:01<00:09, 73.15it/s]
Loading 0: 12%|█▏ | 93/771 [00:01<00:09, 70.58it/s]
Loading 0: 14%|█▎ | 106/771 [00:01<00:10, 61.16it/s]
Loading 0: 15%|█▍ | 113/771 [00:01<00:11, 57.78it/s]
Loading 0: 16%|█▌ | 121/771 [00:01<00:11, 58.08it/s]
Loading 0: 17%|█▋ | 132/771 [00:02<00:09, 68.80it/s]
Loading 0: 18%|█▊ | 142/771 [00:02<00:08, 74.91it/s]
Loading 0: 20%|█▉ | 152/771 [00:02<00:07, 80.15it/s]
Loading 0: 21%|██ | 161/771 [00:02<00:08, 75.24it/s]
Loading 0: 22%|██▏ | 169/771 [00:02<00:11, 52.02it/s]
Loading 0: 23%|██▎ | 176/771 [00:02<00:11, 52.56it/s]
Loading 0: 24%|██▍ | 184/771 [00:02<00:10, 57.89it/s]
Loading 0: 25%|██▌ | 195/771 [00:03<00:08, 69.41it/s]
Loading 0: 26%|██▋ | 203/771 [00:03<00:07, 71.52it/s]
Loading 0: 27%|██▋ | 211/771 [00:03<00:08, 68.89it/s]
Loading 0: 29%|██▉ | 226/771 [00:03<00:08, 61.51it/s]
Loading 0: 30%|███ | 233/771 [00:03<00:10, 50.71it/s]
Loading 0: 32%|███▏ | 244/771 [00:03<00:08, 60.97it/s]
Loading 0: 33%|███▎ | 255/771 [00:03<00:07, 70.24it/s]
Loading 0: 34%|███▍ | 264/771 [00:04<00:06, 73.78it/s]
Loading 0: 35%|███▌ | 273/771 [00:04<00:06, 71.19it/s]
Loading 0: 37%|███▋ | 286/771 [00:04<00:07, 62.24it/s]
Loading 0: 38%|███▊ | 293/771 [00:04<00:09, 51.77it/s]
Loading 0: 39%|███▉ | 303/771 [00:19<03:33, 2.19it/s]
Loading 0: 40%|████ | 311/771 [00:19<02:36, 2.93it/s]
Loading 0: 41%|████ | 318/771 [00:19<01:58, 3.82it/s]
Loading 0: 43%|████▎ | 328/771 [00:19<01:18, 5.64it/s]
Loading 0: 44%|████▍ | 338/771 [00:19<00:53, 8.10it/s]
Loading 0: 45%|████▍ | 346/771 [00:19<00:42, 10.10it/s]
Loading 0: 46%|████▌ | 353/771 [00:20<00:35, 11.67it/s]
Loading 0: 47%|████▋ | 364/771 [00:20<00:23, 17.13it/s]
Loading 0: 49%|████▊ | 375/771 [00:20<00:16, 23.95it/s]
Loading 0: 50%|████▉ | 383/771 [00:20<00:13, 29.15it/s]
Loading 0: 51%|█████ | 391/771 [00:20<00:11, 34.01it/s]
Loading 0: 53%|█████▎ | 406/771 [00:20<00:09, 39.70it/s]
Loading 0: 54%|█████▎ | 413/771 [00:21<00:09, 37.73it/s]
Loading 0: 55%|█████▍ | 424/771 [00:21<00:07, 47.75it/s]
Loading 0: 56%|█████▋ | 435/771 [00:21<00:05, 57.77it/s]
Loading 0: 58%|█████▊ | 444/771 [00:21<00:05, 63.46it/s]
Loading 0: 59%|█████▉ | 453/771 [00:21<00:04, 64.31it/s]
Loading 0: 60%|██████ | 466/771 [00:21<00:05, 59.48it/s]
Loading 0: 61%|██████▏ | 474/771 [00:21<00:05, 51.65it/s]
Loading 0: 63%|██████▎ | 484/771 [00:22<00:04, 60.43it/s]
Loading 0: 64%|██████▍ | 495/771 [00:22<00:03, 70.25it/s]
Loading 0: 65%|██████▌ | 504/771 [00:22<00:03, 74.33it/s]
Loading 0: 67%|██████▋ | 513/771 [00:22<00:03, 71.66it/s]
Loading 0: 68%|██████▊ | 526/771 [00:22<00:03, 62.11it/s]
Loading 0: 69%|██████▉ | 534/771 [00:22<00:04, 52.82it/s]
Loading 0: 71%|███████ | 544/771 [00:22<00:03, 61.37it/s]
Loading 0: 72%|███████▏ | 555/771 [00:23<00:03, 69.91it/s]
Loading 0: 73%|███████▎ | 563/771 [00:23<00:02, 71.24it/s]
Loading 0: 74%|███████▍ | 571/771 [00:23<00:02, 68.16it/s]
Loading 0: 76%|███████▌ | 586/771 [00:23<00:02, 63.48it/s]
Loading 0: 77%|███████▋ | 593/771 [00:23<00:03, 52.54it/s]
Loading 0: 78%|███████▊ | 604/771 [00:23<00:02, 62.99it/s]
Loading 0: 80%|███████▉ | 615/771 [00:23<00:02, 72.34it/s]
Loading 0: 81%|████████ | 624/771 [00:24<00:01, 75.66it/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, 4.16it/s]
Loading 0: 86%|████████▌ | 664/771 [00:39<00:18, 5.85it/s]
Loading 0: 88%|████████▊ | 675/771 [00:39<00:11, 8.42it/s]
Loading 0: 89%|████████▊ | 684/771 [00:39<00:07, 11.18it/s]
Loading 0: 90%|████████▉ | 693/771 [00:39<00:05, 14.58it/s]
Loading 0: 92%|█████████▏| 706/771 [00:40<00:03, 19.84it/s]
Loading 0: 92%|█████████▏| 713/771 [00:40<00:02, 21.71it/s]
Loading 0: 94%|█████████▍| 724/771 [00:40<00:01, 29.48it/s]
Loading 0: 95%|█████████▌| 735/771 [00:40<00:00, 38.43it/s]
Loading 0: 96%|█████████▋| 744/771 [00:40<00:00, 45.37it/s]
Loading 0: 98%|█████████▊| 753/771 [00:40<00:00, 49.48it/s]
Loading 0: 99%|█████████▉| 766/771 [00:48<00:01, 4.27it/s]
Job chaiml-qwq32b-sft-exp1-del1k-v1-mkmlizer completed after 217.44s with status: succeeded
Stopping job with name chaiml-qwq32b-sft-exp1-del1k-v1-mkmlizer
Pipeline stage MKMLizer completed in 217.91s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.31s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-qwq32b-sft-exp1-del1k-v1
Waiting for inference service chaiml-qwq32b-sft-exp1-del1k-v1 to be ready
Inference service chaiml-qwq32b-sft-exp1-del1k-v1 ready after 120.44545316696167s
Pipeline stage MKMLDeployer completed in 120.94s
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 3.0738253593444824s
Received healthy response to inference request in 1.0819759368896484s
{"detail":"HTTPConnectionPool(host='chaiml-qwq32b-sft-exp1-del1k-v1-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Max retries exceeded with url: /v1/models/GPT-J-6B-lit-v2:predict (Caused by ConnectTimeoutError(<urllib3.connection.HTTPConnection object at 0x7c5e5c277890>, 'Connection to chaiml-qwq32b-sft-exp1-del1k-v1-predictor.tenant-chaiml-guanaco.k.chaiverse.com timed out. (connect timeout=12.0)'))"}
Received unhealthy response to inference request!
Received healthy response to inference request in 2.671285390853882s
5 requests
2 failed requests
5th percentile: 1.3998378276824952
10th percentile: 1.717699718475342
20th percentile: 2.353423500061035
30th percentile: 2.751793384552002
40th percentile: 2.912809371948242
50th percentile: 3.0738253593444824
60th percentile: 6.721742725372314
70th percentile: 10.369660091400146
80th percentile: 13.780725431442262
90th percentile: 16.95493874549866
95th percentile: 18.542045402526853
99th percentile: 19.811730728149413
mean time: 7.829971504211426
%s, retrying in %s seconds...
Received healthy response to inference request in 3.0906755924224854s
Received healthy response to inference request in 2.5720291137695312s
Received healthy response to inference request in 3.133270025253296s
Received healthy response to inference request in 3.085885763168335s
Received healthy response to inference request in 2.6802937984466553s
5 requests
0 failed requests
5th percentile: 2.593682050704956
10th percentile: 2.615334987640381
20th percentile: 2.6586408615112305
30th percentile: 2.761412191390991
40th percentile: 2.923648977279663
50th percentile: 3.085885763168335
60th percentile: 3.087801694869995
70th percentile: 3.0897176265716553
80th percentile: 3.0991944789886476
90th percentile: 3.1162322521209718
95th percentile: 3.1247511386871336
99th percentile: 3.1315662479400634
mean time: 2.9124308586120606
Pipeline stage StressChecker completed in 55.99s
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 0.69s
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 0.67s
Shutdown handler de-registered
chaiml-qwq32b-sft-exp1-del1k_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 0.11s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service chaiml-qwq32b-sft-exp1-del1k-v1-profiler
Waiting for inference service chaiml-qwq32b-sft-exp1-del1k-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 2538.93s
Shutdown handler de-registered
chaiml-qwq32b-sft-exp1-del1k_v1 status is now inactive due to auto deactivation removed underperforming models