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-sft-gemma2it-28b-47770-v2-mkmlizer
Waiting for job on chaiml-sft-gemma2it-28b-47770-v2-mkmlizer to finish
chaiml-sft-gemma2it-28b-47770-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-sft-gemma2it-28b-47770-v2-mkmlizer: ║ _____ __ __ ║
chaiml-sft-gemma2it-28b-47770-v2-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
chaiml-sft-gemma2it-28b-47770-v2-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
chaiml-sft-gemma2it-28b-47770-v2-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
chaiml-sft-gemma2it-28b-47770-v2-mkmlizer: ║ /___/ ║
chaiml-sft-gemma2it-28b-47770-v2-mkmlizer: ║ ║
chaiml-sft-gemma2it-28b-47770-v2-mkmlizer: ║ Version: 0.12.8 ║
chaiml-sft-gemma2it-28b-47770-v2-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
chaiml-sft-gemma2it-28b-47770-v2-mkmlizer: ║ https://mk1.ai ║
chaiml-sft-gemma2it-28b-47770-v2-mkmlizer: ║ ║
chaiml-sft-gemma2it-28b-47770-v2-mkmlizer: ║ The license key for the current software has been verified as ║
chaiml-sft-gemma2it-28b-47770-v2-mkmlizer: ║ belonging to: ║
chaiml-sft-gemma2it-28b-47770-v2-mkmlizer: ║ ║
chaiml-sft-gemma2it-28b-47770-v2-mkmlizer: ║ Chai Research Corp. ║
chaiml-sft-gemma2it-28b-47770-v2-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
chaiml-sft-gemma2it-28b-47770-v2-mkmlizer: ║ Expiration: 2025-04-15 23:59:59 ║
chaiml-sft-gemma2it-28b-47770-v2-mkmlizer: ║ ║
chaiml-sft-gemma2it-28b-47770-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-sft-gemma2it-28b-47770-v2-mkmlizer: Downloaded to shared memory in 78.445s
chaiml-sft-gemma2it-28b-47770-v2-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp8d4o076u, device:0
chaiml-sft-gemma2it-28b-47770-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-sft-gemma2it-28b-47770-v2-mkmlizer: quantized model in 69.430s
chaiml-sft-gemma2it-28b-47770-v2-mkmlizer: Processed model ChaiML/sft-gemma2it-28b-v2-exp1 in 147.876s
chaiml-sft-gemma2it-28b-47770-v2-mkmlizer: creating bucket guanaco-mkml-models
chaiml-sft-gemma2it-28b-47770-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-sft-gemma2it-28b-47770-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-sft-gemma2it-28b-47770-v2
chaiml-sft-gemma2it-28b-47770-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-sft-gemma2it-28b-47770-v2/config.json
chaiml-sft-gemma2it-28b-47770-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-sft-gemma2it-28b-47770-v2/special_tokens_map.json
chaiml-sft-gemma2it-28b-47770-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-sft-gemma2it-28b-47770-v2/tokenizer_config.json
chaiml-sft-gemma2it-28b-47770-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.model s3://guanaco-mkml-models/chaiml-sft-gemma2it-28b-47770-v2/tokenizer.model
chaiml-sft-gemma2it-28b-47770-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-sft-gemma2it-28b-47770-v2/tokenizer.json
chaiml-sft-gemma2it-28b-47770-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.2.safetensors s3://guanaco-mkml-models/chaiml-sft-gemma2it-28b-47770-v2/flywheel_model.2.safetensors
chaiml-sft-gemma2it-28b-47770-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-sft-gemma2it-28b-47770-v2/flywheel_model.0.safetensors
chaiml-sft-gemma2it-28b-47770-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-sft-gemma2it-28b-47770-v2/flywheel_model.1.safetensors
chaiml-sft-gemma2it-28b-47770-v2-mkmlizer:
Loading 0: 0%| | 0/508 [00:00<?, ?it/s]
Loading 0: 1%| | 4/508 [00:00<00:12, 38.82it/s]
Loading 0: 2%|▏ | 12/508 [00:00<00:11, 44.33it/s]
Loading 0: 3%|▎ | 17/508 [00:00<00:14, 33.37it/s]
Loading 0: 5%|▍ | 25/508 [00:00<00:10, 45.95it/s]
Loading 0: 6%|▌ | 31/508 [00:00<00:17, 27.15it/s]
Loading 0: 7%|▋ | 37/508 [00:01<00:14, 32.81it/s]
Loading 0: 9%|▉ | 45/508 [00:01<00:11, 39.22it/s]
Loading 0: 10%|▉ | 50/508 [00:01<00:12, 36.03it/s]
Loading 0: 11%|█ | 56/508 [00:01<00:11, 40.99it/s]
Loading 0: 12%|█▏ | 61/508 [00:01<00:12, 37.05it/s]
Loading 0: 13%|█▎ | 68/508 [00:01<00:11, 38.46it/s]
Loading 0: 14%|█▍ | 73/508 [00:02<00:15, 28.69it/s]
Loading 0: 15%|█▌ | 78/508 [00:02<00:14, 29.93it/s]
Loading 0: 16%|█▌ | 82/508 [00:02<00:14, 29.85it/s]
Loading 0: 17%|█▋ | 87/508 [00:02<00:12, 33.80it/s]
Loading 0: 19%|█▊ | 95/508 [00:02<00:10, 40.85it/s]
Loading 0: 20%|█▉ | 100/508 [00:02<00:11, 36.15it/s]
Loading 0: 21%|██ | 106/508 [00:02<00:10, 39.63it/s]
Loading 0: 22%|██▏ | 111/508 [00:03<00:11, 34.75it/s]
Loading 0: 23%|██▎ | 118/508 [00:03<00:12, 31.25it/s]
Loading 0: 24%|██▍ | 124/508 [00:03<00:10, 36.07it/s]
Loading 0: 25%|██▌ | 129/508 [00:03<00:09, 38.34it/s]
Loading 0: 27%|██▋ | 135/508 [00:03<00:09, 38.29it/s]
Loading 0: 28%|██▊ | 140/508 [00:03<00:09, 40.21it/s]
Loading 0: 29%|██▊ | 145/508 [00:03<00:08, 42.44it/s]
Loading 0: 30%|██▉ | 150/508 [00:04<00:09, 36.57it/s]
Loading 0: 31%|███ | 157/508 [00:04<00:09, 38.37it/s]
Loading 0: 32%|███▏ | 162/508 [00:04<00:08, 39.93it/s]
Loading 0: 33%|███▎ | 167/508 [00:04<00:08, 41.43it/s]
Loading 0: 34%|███▍ | 172/508 [00:04<00:11, 28.42it/s]
Loading 0: 35%|███▍ | 176/508 [00:04<00:10, 30.19it/s]
Loading 0: 35%|███▌ | 180/508 [00:05<00:10, 31.95it/s]
Loading 0: 37%|███▋ | 188/508 [00:05<00:08, 38.91it/s]
Loading 0: 38%|███▊ | 193/508 [00:19<04:19, 1.21it/s]
Loading 0: 39%|███▉ | 199/508 [00:20<02:55, 1.76it/s]
Loading 0: 40%|████ | 204/508 [00:20<02:10, 2.32it/s]
Loading 0: 42%|████▏ | 211/508 [00:20<01:24, 3.50it/s]
Loading 0: 43%|████▎ | 216/508 [00:20<01:04, 4.50it/s]
Loading 0: 43%|████▎ | 220/508 [00:20<00:50, 5.67it/s]
Loading 0: 44%|████▍ | 224/508 [00:20<00:39, 7.21it/s]
Loading 0: 46%|████▌ | 232/508 [00:21<00:24, 11.37it/s]
Loading 0: 47%|████▋ | 237/508 [00:21<00:20, 13.52it/s]
Loading 0: 48%|████▊ | 245/508 [00:21<00:14, 18.66it/s]
Loading 0: 49%|████▉ | 250/508 [00:21<00:11, 22.06it/s]
Loading 0: 50%|█████ | 255/508 [00:21<00:10, 23.79it/s]
Loading 0: 51%|█████ | 260/508 [00:21<00:09, 26.30it/s]
Loading 0: 52%|█████▏ | 264/508 [00:22<00:10, 23.74it/s]
Loading 0: 53%|█████▎ | 268/508 [00:22<00:09, 26.45it/s]
Loading 0: 54%|█████▍ | 276/508 [00:22<00:06, 34.15it/s]
Loading 0: 55%|█████▌ | 281/508 [00:22<00:07, 32.24it/s]
Loading 0: 57%|█████▋ | 289/508 [00:22<00:05, 36.79it/s]
Loading 0: 58%|█████▊ | 294/508 [00:22<00:05, 38.74it/s]
Loading 0: 59%|█████▉ | 300/508 [00:22<00:05, 38.12it/s]
Loading 0: 60%|██████ | 305/508 [00:23<00:05, 40.19it/s]
Loading 0: 61%|██████ | 311/508 [00:23<00:04, 43.80it/s]
Loading 0: 62%|██████▏ | 316/508 [00:23<00:06, 28.91it/s]
Loading 0: 63%|██████▎ | 322/508 [00:23<00:05, 34.36it/s]
Loading 0: 64%|██████▍ | 327/508 [00:23<00:04, 37.15it/s]
Loading 0: 66%|██████▌ | 333/508 [00:23<00:04, 37.39it/s]
Loading 0: 67%|██████▋ | 338/508 [00:23<00:04, 39.69it/s]
Loading 0: 68%|██████▊ | 344/508 [00:24<00:04, 38.67it/s]
Loading 0: 69%|██████▊ | 349/508 [00:24<00:03, 40.77it/s]
Loading 0: 70%|██████▉ | 354/508 [00:24<00:04, 38.14it/s]
Loading 0: 71%|███████ | 359/508 [00:24<00:04, 31.14it/s]
Loading 0: 71%|███████▏ | 363/508 [00:24<00:04, 32.68it/s]
Loading 0: 72%|███████▏ | 367/508 [00:24<00:04, 34.05it/s]
Loading 0: 74%|███████▍ | 375/508 [00:24<00:03, 39.95it/s]
Loading 0: 75%|███████▍ | 380/508 [00:25<00:03, 35.37it/s]
Loading 0: 76%|███████▋ | 388/508 [00:25<00:03, 38.85it/s]
Loading 0: 77%|███████▋ | 392/508 [00:25<00:03, 38.43it/s]
Loading 0: 78%|███████▊ | 398/508 [00:25<00:02, 37.13it/s]
Loading 0: 79%|███████▉ | 403/508 [00:25<00:02, 36.52it/s]
Loading 0: 80%|████████ | 407/508 [00:25<00:03, 29.35it/s]
Loading 0: 81%|████████ | 411/508 [00:26<00:03, 31.25it/s]
Loading 0: 82%|████████▏ | 419/508 [00:26<00:02, 38.20it/s]
Loading 0: 83%|████████▎ | 423/508 [00:26<00:02, 32.54it/s]
Loading 0: 85%|████████▌ | 432/508 [00:26<00:01, 39.36it/s]
Loading 0: 86%|████████▌ | 437/508 [00:26<00:01, 40.98it/s]
Loading 0: 87%|████████▋ | 443/508 [00:26<00:01, 39.45it/s]
Loading 0: 88%|████████▊ | 448/508 [00:26<00:01, 41.21it/s]
Loading 0: 89%|████████▉ | 451/508 [00:41<00:01, 41.21it/s]
Loading 0: 89%|████████▉ | 452/508 [00:41<00:48, 1.16it/s]
Loading 0: 90%|████████▉ | 456/508 [00:41<00:33, 1.53it/s]
Loading 0: 91%|█████████ | 461/508 [00:41<00:22, 2.11it/s]
Loading 0: 92%|█████████▏| 466/508 [00:42<00:14, 2.99it/s]
Loading 0: 93%|█████████▎| 474/508 [00:42<00:06, 4.88it/s]
Loading 0: 94%|█████████▍| 479/508 [00:42<00:04, 6.26it/s]
Loading 0: 96%|█████████▌| 487/508 [00:42<00:02, 9.46it/s]
Loading 0: 97%|█████████▋| 492/508 [00:42<00:01, 11.85it/s]
Loading 0: 98%|█████████▊| 497/508 [00:42<00:00, 14.17it/s]
Loading 0: 99%|█████████▉| 502/508 [00:43<00:00, 15.53it/s]
Loading 0: 100%|█████████▉| 506/508 [00:43<00:00, 18.00it/s]
Job chaiml-sft-gemma2it-28b-47770-v2-mkmlizer completed after 179.0s with status: succeeded
Stopping job with name chaiml-sft-gemma2it-28b-47770-v2-mkmlizer
Pipeline stage MKMLizer completed in 180.30s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.15s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-sft-gemma2it-28b-47770-v2
Waiting for inference service chaiml-sft-gemma2it-28b-47770-v2 to be ready
Inference service chaiml-sft-gemma2it-28b-47770-v2 ready after 120.46220970153809s
Pipeline stage MKMLDeployer completed in 120.97s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 3.9671976566314697s
Received healthy response to inference request in 3.188748359680176s
Received healthy response to inference request in 3.1846811771392822s
Received healthy response to inference request in 3.2850711345672607s
Received healthy response to inference request in 3.1767213344573975s
5 requests
0 failed requests
5th percentile: 3.1783133029937742
10th percentile: 3.1799052715301515
20th percentile: 3.1830892086029055
30th percentile: 3.185494613647461
40th percentile: 3.1871214866638184
50th percentile: 3.188748359680176
60th percentile: 3.22727746963501
70th percentile: 3.2658065795898437
80th percentile: 3.421496438980103
90th percentile: 3.694347047805786
95th percentile: 3.8307723522186277
99th percentile: 3.9399125957489014
mean time: 3.360483932495117
Pipeline stage StressChecker completed in 18.18s
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 0.66s
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 0.63s
Shutdown handler de-registered
chaiml-sft-gemma2it-28b_47770_v2 status is now deployed due to DeploymentManager action
Shutdown handler registered
run pipeline %s
run pipeline stage %s
Running pipeline stage OfflineFamilyFriendlyScorer
Evaluating %s Family Friendly Score with %s threads
%s, retrying in %s seconds...
Evaluating %s Family Friendly Score with %s threads
Pipeline stage OfflineFamilyFriendlyScorer completed in 6147.81s
Shutdown handler de-registered
chaiml-sft-gemma2it-28b_47770_v2 status is now inactive due to auto deactivation removed underperforming models
chaiml-sft-gemma2it-28b_47770_v2 status is now torndown due to DeploymentManager action