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 cloudyu-nemo-dpo-v23-v5-mkmlizer
Waiting for job on cloudyu-nemo-dpo-v23-v5-mkmlizer to finish
cloudyu-nemo-dpo-v23-v5-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cloudyu-nemo-dpo-v23-v5-mkmlizer: ║ _____ __ __ ║
cloudyu-nemo-dpo-v23-v5-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
cloudyu-nemo-dpo-v23-v5-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
cloudyu-nemo-dpo-v23-v5-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
cloudyu-nemo-dpo-v23-v5-mkmlizer: ║ /___/ ║
cloudyu-nemo-dpo-v23-v5-mkmlizer: ║ ║
cloudyu-nemo-dpo-v23-v5-mkmlizer: ║ Version: 0.11.12 ║
cloudyu-nemo-dpo-v23-v5-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
cloudyu-nemo-dpo-v23-v5-mkmlizer: ║ https://mk1.ai ║
cloudyu-nemo-dpo-v23-v5-mkmlizer: ║ ║
cloudyu-nemo-dpo-v23-v5-mkmlizer: ║ The license key for the current software has been verified as ║
cloudyu-nemo-dpo-v23-v5-mkmlizer: ║ belonging to: ║
cloudyu-nemo-dpo-v23-v5-mkmlizer: ║ ║
cloudyu-nemo-dpo-v23-v5-mkmlizer: ║ Chai Research Corp. ║
cloudyu-nemo-dpo-v23-v5-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
cloudyu-nemo-dpo-v23-v5-mkmlizer: ║ Expiration: 2025-04-15 23:59:59 ║
cloudyu-nemo-dpo-v23-v5-mkmlizer: ║ ║
cloudyu-nemo-dpo-v23-v5-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
Failed to get response for submission cgato-nemo-12b-humanize_89106_v2: HTTPConnectionPool(host='cgato-nemo-12b-humanize-89106-v2-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
cloudyu-nemo-dpo-v23-v5-mkmlizer: Downloaded to shared memory in 33.474s
cloudyu-nemo-dpo-v23-v5-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpwusvxjb3, device:0
cloudyu-nemo-dpo-v23-v5-mkmlizer: Saving flywheel model at /dev/shm/model_cache
Failed to get response for submission cgato-nemo-12b-humanize_89106_v2: HTTPConnectionPool(host='cgato-nemo-12b-humanize-89106-v2-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
cloudyu-nemo-dpo-v23-v5-mkmlizer: quantized model in 35.965s
cloudyu-nemo-dpo-v23-v5-mkmlizer: Processed model cloudyu/Nemo-DPO-V23 in 69.439s
cloudyu-nemo-dpo-v23-v5-mkmlizer: creating bucket guanaco-mkml-models
cloudyu-nemo-dpo-v23-v5-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cloudyu-nemo-dpo-v23-v5-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/cloudyu-nemo-dpo-v23-v5
cloudyu-nemo-dpo-v23-v5-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/cloudyu-nemo-dpo-v23-v5/config.json
cloudyu-nemo-dpo-v23-v5-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/cloudyu-nemo-dpo-v23-v5/special_tokens_map.json
cloudyu-nemo-dpo-v23-v5-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/cloudyu-nemo-dpo-v23-v5/tokenizer_config.json
cloudyu-nemo-dpo-v23-v5-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/cloudyu-nemo-dpo-v23-v5/tokenizer.json
cloudyu-nemo-dpo-v23-v5-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/cloudyu-nemo-dpo-v23-v5/flywheel_model.0.safetensors
cloudyu-nemo-dpo-v23-v5-mkmlizer:
Loading 0: 0%| | 0/363 [00:00<?, ?it/s]
Loading 0: 1%| | 2/363 [00:06<18:15, 3.03s/it]
Loading 0: 2%|▏ | 6/363 [00:06<04:51, 1.22it/s]
Loading 0: 4%|▎ | 13/363 [00:06<01:44, 3.36it/s]
Loading 0: 5%|▌ | 19/363 [00:06<00:59, 5.77it/s]
Loading 0: 7%|▋ | 24/363 [00:06<00:42, 7.99it/s]
Loading 0: 9%|▉ | 32/363 [00:06<00:25, 13.14it/s]
Loading 0: 10%|█ | 38/363 [00:06<00:19, 16.81it/s]
Loading 0: 12%|█▏ | 43/363 [00:07<00:19, 16.79it/s]
Loading 0: 14%|█▍ | 50/363 [00:07<00:13, 22.56it/s]
Loading 0: 15%|█▌ | 56/363 [00:07<00:11, 26.20it/s]
Loading 0: 17%|█▋ | 61/363 [00:07<00:10, 28.71it/s]
Loading 0: 19%|█▊ | 68/363 [00:07<00:08, 35.05it/s]
Loading 0: 20%|██ | 74/363 [00:07<00:07, 36.67it/s]
Loading 0: 22%|██▏ | 79/363 [00:07<00:07, 37.95it/s]
Loading 0: 24%|██▎ | 86/363 [00:08<00:06, 43.41it/s]
Loading 0: 25%|██▌ | 92/363 [00:08<00:06, 42.98it/s]
Loading 0: 27%|██▋ | 97/363 [00:08<00:06, 42.90it/s]
Loading 0: 29%|██▊ | 104/363 [00:08<00:05, 47.60it/s]
Loading 0: 30%|███ | 110/363 [00:08<00:05, 45.42it/s]
Loading 0: 32%|███▏ | 115/363 [00:08<00:05, 44.23it/s]
Loading 0: 33%|███▎ | 121/363 [00:08<00:06, 34.65it/s]
Loading 0: 34%|███▍ | 125/363 [00:09<00:06, 34.69it/s]
Loading 0: 36%|███▌ | 131/363 [00:09<00:05, 39.09it/s]
Loading 0: 38%|███▊ | 137/363 [00:09<00:05, 40.01it/s]
Loading 0: 39%|███▉ | 142/363 [00:09<00:05, 39.01it/s]
Loading 0: 41%|████ | 148/363 [00:09<00:05, 42.83it/s]
Loading 0: 42%|████▏ | 153/363 [00:09<00:04, 42.55it/s]
Loading 0: 44%|████▎ | 158/363 [00:09<00:04, 43.84it/s]
Loading 0: 45%|████▌ | 164/363 [00:09<00:04, 42.62it/s]
Loading 0: 47%|████▋ | 169/363 [00:10<00:04, 42.22it/s]
Loading 0: 48%|████▊ | 176/363 [00:10<00:03, 47.43it/s]
Loading 0: 50%|█████ | 182/363 [00:10<00:03, 45.94it/s]
Loading 0: 52%|█████▏ | 187/363 [00:10<00:03, 44.73it/s]
Loading 0: 53%|█████▎ | 194/363 [00:10<00:03, 49.42it/s]
Loading 0: 55%|█████▌ | 200/363 [00:10<00:03, 47.46it/s]
Loading 0: 56%|█████▋ | 205/363 [00:10<00:04, 33.08it/s]
Loading 0: 58%|█████▊ | 212/363 [00:11<00:03, 39.15it/s]
Loading 0: 60%|█████▉ | 217/363 [00:11<00:03, 41.22it/s]
Loading 0: 61%|██████ | 222/363 [00:11<00:03, 36.97it/s]
Loading 0: 63%|██████▎ | 230/363 [00:11<00:02, 44.90it/s]
Loading 0: 65%|██████▌ | 236/363 [00:11<00:02, 43.91it/s]
Loading 0: 66%|██████▋ | 241/363 [00:11<00:02, 43.44it/s]
Loading 0: 68%|██████▊ | 247/363 [00:11<00:02, 46.92it/s]
Loading 0: 69%|██████▉ | 252/363 [00:11<00:02, 45.69it/s]
Loading 0: 71%|███████ | 257/363 [00:12<00:02, 45.69it/s]
Loading 0: 72%|███████▏ | 263/363 [00:12<00:02, 43.70it/s]
Loading 0: 74%|███████▍ | 268/363 [00:12<00:02, 41.43it/s]
Loading 0: 75%|███████▌ | 274/363 [00:12<00:01, 44.73it/s]
Loading 0: 77%|███████▋ | 279/363 [00:12<00:01, 43.36it/s]
Loading 0: 78%|███████▊ | 284/363 [00:12<00:02, 31.75it/s]
Loading 0: 80%|███████▉ | 289/363 [00:12<00:02, 35.03it/s]
Loading 0: 81%|████████ | 293/363 [00:13<00:01, 36.04it/s]
Loading 0: 82%|████████▏ | 299/363 [00:13<00:01, 36.92it/s]
Loading 0: 83%|████████▎ | 303/363 [00:13<00:01, 35.76it/s]
Loading 0: 86%|████████▌ | 311/363 [00:13<00:01, 44.12it/s]
Loading 0: 87%|████████▋ | 316/363 [00:13<00:01, 43.98it/s]
Loading 0: 88%|████████▊ | 321/363 [00:13<00:01, 37.33it/s]
Loading 0: 90%|█████████ | 328/363 [00:13<00:00, 44.47it/s]
Loading 0: 92%|█████████▏| 333/363 [00:14<00:00, 43.57it/s]
Loading 0: 93%|█████████▎| 338/363 [00:14<00:00, 43.26it/s]
Loading 0: 94%|█████████▍| 343/363 [00:14<00:00, 44.62it/s]
Loading 0: 96%|█████████▌| 348/363 [00:14<00:00, 38.97it/s]
Loading 0: 98%|█████████▊| 355/363 [00:14<00:00, 45.80it/s]
Loading 0: 99%|█████████▉| 360/363 [00:14<00:00, 45.47it/s]
Job cloudyu-nemo-dpo-v23-v5-mkmlizer completed after 94.02s with status: succeeded
Stopping job with name cloudyu-nemo-dpo-v23-v5-mkmlizer
Pipeline stage MKMLizer completed in 94.49s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.16s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service cloudyu-nemo-dpo-v23-v5
Waiting for inference service cloudyu-nemo-dpo-v23-v5 to be ready
Failed to get response for submission cgato-nemo-12b-humanize_89106_v2: HTTPConnectionPool(host='cgato-nemo-12b-humanize-89106-v2-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
Failed to get response for submission cgato-nemo-12b-humanize_89106_v2: HTTPConnectionPool(host='cgato-nemo-12b-humanize-89106-v2-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
Inference service cloudyu-nemo-dpo-v23-v5 ready after 372.5123612880707s
Pipeline stage MKMLDeployer completed in 373.22s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.6791810989379883s
Received healthy response to inference request in 1.6321468353271484s
Received healthy response to inference request in 1.9185993671417236s
Received healthy response to inference request in 1.8113408088684082s
Failed to get response for submission cgato-nemo-12b-humanize_89106_v2: HTTPConnectionPool(host='cgato-nemo-12b-humanize-89106-v2-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
Received healthy response to inference request in 1.7123115062713623s
5 requests
0 failed requests
5th percentile: 1.6481797695159912
10th percentile: 1.664212703704834
20th percentile: 1.6962785720825195
30th percentile: 1.7321173667907714
40th percentile: 1.77172908782959
50th percentile: 1.8113408088684082
60th percentile: 1.8542442321777344
70th percentile: 1.8971476554870605
80th percentile: 2.070715713500977
90th percentile: 2.3749484062194823
95th percentile: 2.527064752578735
99th percentile: 2.648757829666138
mean time: 1.950715923309326
Pipeline stage StressChecker completed in 11.77s
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 0.76s
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 0.74s
Shutdown handler de-registered
cloudyu-nemo-dpo-v23_v5 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 2787.41s
Shutdown handler de-registered
cloudyu-nemo-dpo-v23_v5 status is now inactive due to auto deactivation removed underperforming models
cloudyu-nemo-dpo-v23_v5 status is now torndown due to DeploymentManager action