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-gy-exp137-dpo-ex-33370-v1-mkmlizer
Waiting for job on chaiml-gy-exp137-dpo-ex-33370-v1-mkmlizer to finish
chaiml-gy-exp137-dpo-ex-33370-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-gy-exp137-dpo-ex-33370-v1-mkmlizer: ║ ║
chaiml-gy-exp137-dpo-ex-33370-v1-mkmlizer: ║ ██████ ██████ █████ ████ ████ ║
chaiml-gy-exp137-dpo-ex-33370-v1-mkmlizer: ║ ░░██████ ██████ ░░███ ███░ ░░███ ║
chaiml-gy-exp137-dpo-ex-33370-v1-mkmlizer: ║ ░███░█████░███ ░███ ███ ░███ ║
chaiml-gy-exp137-dpo-ex-33370-v1-mkmlizer: ║ ░███░░███ ░███ ░███████ ░███ ║
chaiml-gy-exp137-dpo-ex-33370-v1-mkmlizer: ║ ░███ ░░░ ░███ ░███░░███ ░███ ║
chaiml-gy-exp137-dpo-ex-33370-v1-mkmlizer: ║ ░███ ░███ ░███ ░░███ ░███ ║
chaiml-gy-exp137-dpo-ex-33370-v1-mkmlizer: ║ █████ █████ █████ ░░████ █████ ║
chaiml-gy-exp137-dpo-ex-33370-v1-mkmlizer: ║ ░░░░░ ░░░░░ ░░░░░ ░░░░ ░░░░░ ║
chaiml-gy-exp137-dpo-ex-33370-v1-mkmlizer: ║ ║
chaiml-gy-exp137-dpo-ex-33370-v1-mkmlizer: ║ Version: 0.29.15 ║
chaiml-gy-exp137-dpo-ex-33370-v1-mkmlizer: ║ Features: FLYWHEEL, CUDA ║
chaiml-gy-exp137-dpo-ex-33370-v1-mkmlizer: ║ Copyright 2023-2025 MK ONE TECHNOLOGIES Inc. ║
chaiml-gy-exp137-dpo-ex-33370-v1-mkmlizer: ║ https://mk1.ai ║
chaiml-gy-exp137-dpo-ex-33370-v1-mkmlizer: ║ ║
chaiml-gy-exp137-dpo-ex-33370-v1-mkmlizer: ║ The license key for the current software has been verified as ║
chaiml-gy-exp137-dpo-ex-33370-v1-mkmlizer: ║ belonging to: ║
chaiml-gy-exp137-dpo-ex-33370-v1-mkmlizer: ║ ║
chaiml-gy-exp137-dpo-ex-33370-v1-mkmlizer: ║ Chai Research Corp. ║
chaiml-gy-exp137-dpo-ex-33370-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
chaiml-gy-exp137-dpo-ex-33370-v1-mkmlizer: ║ Expiration: 2028-03-31 23:59:59 ║
chaiml-gy-exp137-dpo-ex-33370-v1-mkmlizer: ║ ║
chaiml-gy-exp137-dpo-ex-33370-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
Unable to record family friendly update due to error: Invalid JSON input: JSON must contain 'User Safety' and 'Response Safety' fields
chaiml-gy-exp137-dpo-ex-33370-v1-mkmlizer: Downloaded to shared memory in 102.593s
chaiml-gy-exp137-dpo-ex-33370-v1-mkmlizer: Checking if ChaiML/gy-exp137-dpo-exp126ep2s3-gy-exp120-122-126-payloads-gt0.7-diffgt0-lpdifflt0-ep2 already exists in ChaiML
chaiml-gy-exp137-dpo-ex-33370-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpypllwpbs, device:0
chaiml-gy-exp137-dpo-ex-33370-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-gy-exp137-dpo-ex-33370-v1-mkmlizer: quantized model in 81.112s
chaiml-gy-exp137-dpo-ex-33370-v1-mkmlizer: Processed model ChaiML/gy-exp137-dpo-exp126ep2s3-gy-exp120-122-126-payloads-gt0.7-diffgt0-lpdifflt0-ep2 in 183.707s
chaiml-gy-exp137-dpo-ex-33370-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-gy-exp137-dpo-ex-33370-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-gy-exp137-dpo-ex-33370-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-gy-exp137-dpo-ex-33370-v1/nvidia
chaiml-gy-exp137-dpo-ex-33370-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-gy-exp137-dpo-ex-33370-v1/nvidia/config.json
chaiml-gy-exp137-dpo-ex-33370-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-gy-exp137-dpo-ex-33370-v1/nvidia/special_tokens_map.json
chaiml-gy-exp137-dpo-ex-33370-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-gy-exp137-dpo-ex-33370-v1/nvidia/tokenizer_config.json
chaiml-gy-exp137-dpo-ex-33370-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-gy-exp137-dpo-ex-33370-v1/nvidia/tokenizer.json
chaiml-gy-exp137-dpo-ex-33370-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-gy-exp137-dpo-ex-33370-v1/nvidia/flywheel_model.1.safetensors
chaiml-gy-exp137-dpo-ex-33370-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-gy-exp137-dpo-ex-33370-v1/nvidia/flywheel_model.0.safetensors
chaiml-gy-exp137-dpo-ex-33370-v1-mkmlizer:
Loading 0: 0%| | 0/363 [00:00<?, ?it/s]
Loading 0: 1%| | 4/363 [00:00<00:14, 24.03it/s]
Loading 0: 2%|▏ | 7/363 [00:00<00:21, 16.90it/s]
Loading 0: 3%|▎ | 10/363 [00:00<00:17, 19.97it/s]
Loading 0: 4%|▎ | 13/363 [00:00<00:18, 18.62it/s]
Loading 0: 4%|▍ | 15/363 [00:00<00:21, 16.54it/s]
Loading 0: 5%|▌ | 19/363 [00:00<00:15, 21.80it/s]
Loading 0: 6%|▌ | 22/363 [00:01<00:16, 20.90it/s]
Loading 0: 7%|▋ | 25/363 [00:01<00:16, 20.05it/s]
Loading 0: 8%|▊ | 28/363 [00:01<00:15, 21.56it/s]
Loading 0: 9%|▉ | 32/363 [00:01<00:13, 24.33it/s]
Loading 0: 10%|▉ | 35/363 [00:02<00:25, 12.77it/s]
Loading 0: 10%|█ | 37/363 [00:02<00:25, 12.58it/s]
Loading 0: 11%|█ | 40/363 [00:02<00:23, 13.77it/s]
Loading 0: 12%|█▏ | 42/363 [00:02<00:25, 12.69it/s]
Loading 0: 13%|█▎ | 46/363 [00:02<00:19, 16.61it/s]
Loading 0: 13%|█▎ | 49/363 [00:02<00:18, 17.18it/s]
Loading 0: 14%|█▍ | 51/363 [00:03<00:19, 15.88it/s]
Loading 0: 15%|█▌ | 55/363 [00:03<00:15, 19.85it/s]
Loading 0: 16%|█▌ | 58/363 [00:03<00:15, 19.13it/s]
Loading 0: 17%|█▋ | 61/363 [00:03<00:17, 17.75it/s]
Loading 0: 18%|█▊ | 64/363 [00:03<00:15, 18.88it/s]
Loading 0: 19%|█▊ | 68/363 [00:03<00:12, 23.01it/s]
Loading 0: 20%|█▉ | 71/363 [00:04<00:21, 13.42it/s]
Loading 0: 20%|██ | 73/363 [00:04<00:23, 12.18it/s]
Loading 0: 21%|██▏ | 78/363 [00:04<00:16, 17.72it/s]
Loading 0: 22%|██▏ | 81/363 [00:04<00:18, 15.05it/s]
Loading 0: 23%|██▎ | 85/363 [00:04<00:14, 19.07it/s]
Loading 0: 24%|██▍ | 88/363 [00:05<00:16, 16.24it/s]
Loading 0: 25%|██▌ | 91/363 [00:05<00:16, 16.51it/s]
Loading 0: 26%|██▌ | 94/363 [00:05<00:16, 16.59it/s]
Loading 0: 27%|██▋ | 97/363 [00:05<00:14, 18.14it/s]
Loading 0: 28%|██▊ | 100/363 [00:05<00:14, 18.54it/s]
Loading 0: 28%|██▊ | 103/363 [00:06<00:14, 17.66it/s]
Loading 0: 29%|██▉ | 106/363 [00:06<00:13, 19.68it/s]
Loading 0: 30%|███ | 109/363 [00:06<00:17, 14.43it/s]
Loading 0: 31%|███ | 112/363 [00:06<00:15, 15.95it/s]
Loading 0: 31%|███▏ | 114/363 [00:06<00:17, 14.55it/s]
Loading 0: 33%|███▎ | 118/363 [00:06<00:13, 18.77it/s]
Loading 0: 33%|███▎ | 121/363 [00:07<00:12, 18.78it/s]
Loading 0: 34%|███▍ | 124/363 [00:07<00:13, 18.00it/s]
Loading 0: 35%|███▍ | 127/363 [00:07<00:11, 20.04it/s]
Loading 0: 36%|███▌ | 130/363 [00:07<00:11, 19.82it/s]
Loading 0: 37%|███▋ | 133/363 [00:07<00:12, 18.77it/s]
Loading 0: 37%|███▋ | 136/363 [00:07<00:11, 19.72it/s]
Loading 0: 38%|███▊ | 139/363 [00:08<00:12, 18.60it/s]
Loading 0: 39%|███▉ | 141/363 [00:08<00:13, 16.12it/s]
Loading 0: 40%|███▉ | 145/363 [00:08<00:10, 19.95it/s]
Loading 0: 41%|████ | 149/363 [00:08<00:09, 22.23it/s]
Loading 0: 42%|████▏ | 152/363 [00:08<00:17, 12.34it/s]
Loading 0: 42%|████▏ | 154/363 [00:09<00:17, 12.21it/s]
Loading 0: 43%|████▎ | 157/363 [00:09<00:15, 13.60it/s]
Loading 0: 44%|████▍ | 159/363 [00:09<00:15, 13.41it/s]
Loading 0: 45%|████▍ | 163/363 [00:09<00:12, 16.51it/s]
Loading 0: 46%|████▌ | 166/363 [00:09<00:11, 17.76it/s]
Loading 0: 46%|████▋ | 168/363 [00:09<00:11, 16.42it/s]
Loading 0: 47%|████▋ | 172/363 [00:10<00:09, 20.50it/s]
Loading 0: 48%|████▊ | 175/363 [00:10<00:09, 19.79it/s]
Loading 0: 49%|████▉ | 178/363 [00:10<00:09, 18.85it/s]
Loading 0: 50%|████▉ | 181/363 [00:10<00:09, 20.20it/s]
Loading 0: 51%|█████ | 185/363 [00:10<00:07, 24.18it/s]
Loading 0: 52%|█████▏ | 188/363 [00:11<00:12, 14.16it/s]
Loading 0: 53%|█████▎ | 191/363 [00:11<00:11, 15.11it/s]
Loading 0: 53%|█████▎ | 193/363 [00:11<00:11, 14.30it/s]
Loading 0: 54%|█████▎ | 195/363 [00:11<00:12, 13.61it/s]
Loading 0: 55%|█████▍ | 199/363 [00:11<00:09, 17.60it/s]
Loading 0: 55%|█████▌ | 200/363 [00:36<00:09, 17.60it/s]
Loading 0: 55%|█████▌ | 201/363 [00:36<07:34, 2.80s/it]
Loading 0: 56%|█████▌ | 203/363 [00:36<05:45, 2.16s/it]
Loading 0: 57%|█████▋ | 208/363 [00:36<03:02, 1.18s/it]
Loading 0: 58%|█████▊ | 211/363 [00:37<02:11, 1.15it/s]
Loading 0: 59%|█████▊ | 213/363 [00:37<01:45, 1.43it/s]
Loading 0: 60%|█████▉ | 217/363 [00:37<01:05, 2.24it/s]
Loading 0: 61%|██████ | 220/363 [00:37<00:49, 2.91it/s]
Loading 0: 61%|██████▏ | 223/363 [00:37<00:35, 3.90it/s]
Loading 0: 62%|██████▏ | 225/363 [00:38<00:33, 4.15it/s]
Loading 0: 63%|██████▎ | 229/363 [00:38<00:21, 6.12it/s]
Loading 0: 64%|██████▎ | 231/363 [00:38<00:19, 6.75it/s]
Loading 0: 65%|██████▍ | 235/363 [00:38<00:13, 9.58it/s]
Loading 0: 66%|██████▌ | 238/363 [00:38<00:11, 10.80it/s]
Loading 0: 66%|██████▌ | 240/363 [00:39<00:11, 10.83it/s]
Loading 0: 67%|██████▋ | 244/363 [00:39<00:08, 13.84it/s]
Loading 0: 68%|██████▊ | 247/363 [00:39<00:07, 14.85it/s]
Loading 0: 69%|██████▊ | 249/363 [00:39<00:08, 13.87it/s]
Loading 0: 70%|██████▉ | 253/363 [00:39<00:06, 17.21it/s]
Loading 0: 71%|███████ | 256/363 [00:39<00:06, 17.27it/s]
Loading 0: 71%|███████ | 258/363 [00:40<00:06, 15.78it/s]
Loading 0: 72%|███████▏ | 262/363 [00:40<00:05, 19.78it/s]
Loading 0: 73%|███████▎ | 266/363 [00:40<00:04, 23.28it/s]
Loading 0: 74%|███████▍ | 269/363 [00:40<00:06, 13.96it/s]
Loading 0: 75%|███████▍ | 272/363 [00:40<00:06, 14.51it/s]
Loading 0: 75%|███████▌ | 274/363 [00:41<00:06, 13.64it/s]
Loading 0: 76%|███████▌ | 276/363 [00:41<00:06, 12.70it/s]
Loading 0: 77%|███████▋ | 280/363 [00:41<00:05, 16.33it/s]
Loading 0: 78%|███████▊ | 283/363 [00:41<00:04, 16.91it/s]
Loading 0: 79%|███████▊ | 285/363 [00:41<00:05, 15.27it/s]
Loading 0: 80%|███████▉ | 289/363 [00:41<00:03, 18.86it/s]
Loading 0: 80%|████████ | 292/363 [00:42<00:03, 18.39it/s]
Loading 0: 81%|████████ | 294/363 [00:42<00:04, 16.19it/s]
Loading 0: 82%|████████▏ | 298/363 [00:42<00:03, 20.04it/s]
Loading 0: 83%|████████▎ | 301/363 [00:42<00:02, 21.70it/s]
Loading 0: 84%|████████▎ | 304/363 [00:42<00:04, 14.27it/s]
Loading 0: 84%|████████▍ | 306/363 [00:43<00:04, 12.27it/s]
Loading 0: 85%|████████▌ | 310/363 [00:43<00:03, 14.99it/s]
Loading 0: 86%|████████▌ | 312/363 [00:43<00:03, 14.38it/s]
Loading 0: 87%|████████▋ | 316/363 [00:43<00:02, 17.73it/s]
Loading 0: 88%|████████▊ | 319/363 [00:43<00:02, 18.06it/s]
Loading 0: 88%|████████▊ | 321/363 [00:43<00:02, 15.78it/s]
Loading 0: 90%|████████▉ | 325/363 [00:44<00:02, 19.00it/s]
Loading 0: 90%|█████████ | 328/363 [00:44<00:01, 18.20it/s]
Loading 0: 91%|█████████ | 330/363 [00:44<00:02, 15.33it/s]
Loading 0: 92%|█████████▏| 334/363 [00:44<00:01, 19.72it/s]
Loading 0: 93%|█████████▎| 337/363 [00:44<00:01, 16.65it/s]
Loading 0: 94%|█████████▎| 340/363 [00:44<00:01, 18.91it/s]
Loading 0: 94%|█████████▍| 343/363 [00:45<00:01, 10.10it/s]
Loading 0: 96%|█████████▌| 347/363 [00:45<00:01, 13.02it/s]
Loading 0: 96%|█████████▌| 349/363 [00:45<00:01, 12.71it/s]
Loading 0: 97%|█████████▋| 353/363 [00:46<00:00, 15.89it/s]
Loading 0: 98%|█████████▊| 356/363 [00:46<00:00, 16.72it/s]
Loading 0: 99%|█████████▉| 359/363 [00:46<00:00, 16.02it/s]
Loading 0: 100%|█████████▉| 362/363 [00:46<00:00, 18.39it/s]
Job chaiml-gy-exp137-dpo-ex-33370-v1-mkmlizer completed after 229.43s with status: succeeded
Stopping job with name chaiml-gy-exp137-dpo-ex-33370-v1-mkmlizer
Pipeline stage MKMLizer completed in 230.31s
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-gy-exp137-dpo-ex-33370-v1
Waiting for inference service chaiml-gy-exp137-dpo-ex-33370-v1 to be ready
Inference service chaiml-gy-exp137-dpo-ex-33370-v1 ready after 211.07479166984558s
Pipeline stage MKMLDeployer completed in 211.64s
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!
read tcp 127.0.0.1:43958->127.0.0.1:8080: read: connection reset by peer
Received unhealthy response to inference request!
Received healthy response to inference request in 2.8107552528381348s
Received healthy response to inference request in 2.047060251235962s
Received healthy response to inference request in 2.2869057655334473s
5 requests
2 failed requests
5th percentile: 0.5517918109893799
10th percentile: 0.9256089210510254
20th percentile: 1.6732431411743165
30th percentile: 2.095029354095459
40th percentile: 2.190967559814453
50th percentile: 2.2869057655334473
60th percentile: 2.496445560455322
70th percentile: 2.705985355377197
80th percentile: 6.285315465927127
90th percentile: 13.234435892105104
95th percentile: 16.70899610519409
99th percentile: 19.488644275665283
mean time: 5.501250457763672
%s, retrying in %s seconds...
Received healthy response to inference request in 1.9757866859436035s
Received healthy response to inference request in 2.524132490158081s
Received healthy response to inference request in 2.2629454135894775s
Received healthy response to inference request in 1.9437706470489502s
Received healthy response to inference request in 1.9434373378753662s
5 requests
0 failed requests
5th percentile: 1.943503999710083
10th percentile: 1.9435706615447998
20th percentile: 1.9437039852142335
30th percentile: 1.9501738548278809
40th percentile: 1.9629802703857422
50th percentile: 1.9757866859436035
60th percentile: 2.090650177001953
70th percentile: 2.2055136680603025
80th percentile: 2.315182828903198
90th percentile: 2.41965765953064
95th percentile: 2.4718950748443604
99th percentile: 2.513685007095337
mean time: 2.130014514923096
Pipeline stage StressChecker completed in 41.17s
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 0.77s
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 0.78s
Shutdown handler de-registered
chaiml-gy-exp137-dpo-ex_33370_v1 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
Pipeline stage OfflineFamilyFriendlyScorer completed in 3155.65s
Shutdown handler de-registered
chaiml-gy-exp137-dpo-ex_33370_v1 status is now inactive due to auto deactivation removed underperforming models
chaiml-gy-exp137-dpo-ex_33370_v1 status is now torndown due to DeploymentManager action