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 rirv938-exp-grpo-cp624-38275-v2-mkmlizer
Waiting for job on rirv938-exp-grpo-cp624-38275-v2-mkmlizer to finish
rirv938-exp-grpo-cp624-38275-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
rirv938-exp-grpo-cp624-38275-v2-mkmlizer: ║ _____ __ __ ║
rirv938-exp-grpo-cp624-38275-v2-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
rirv938-exp-grpo-cp624-38275-v2-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
rirv938-exp-grpo-cp624-38275-v2-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
rirv938-exp-grpo-cp624-38275-v2-mkmlizer: ║ /___/ ║
rirv938-exp-grpo-cp624-38275-v2-mkmlizer: ║ ║
rirv938-exp-grpo-cp624-38275-v2-mkmlizer: ║ Version: 0.12.8 ║
rirv938-exp-grpo-cp624-38275-v2-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
rirv938-exp-grpo-cp624-38275-v2-mkmlizer: ║ https://mk1.ai ║
rirv938-exp-grpo-cp624-38275-v2-mkmlizer: ║ ║
rirv938-exp-grpo-cp624-38275-v2-mkmlizer: ║ The license key for the current software has been verified as ║
rirv938-exp-grpo-cp624-38275-v2-mkmlizer: ║ belonging to: ║
rirv938-exp-grpo-cp624-38275-v2-mkmlizer: ║ ║
rirv938-exp-grpo-cp624-38275-v2-mkmlizer: ║ Chai Research Corp. ║
rirv938-exp-grpo-cp624-38275-v2-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
rirv938-exp-grpo-cp624-38275-v2-mkmlizer: ║ Expiration: 2028-03-31 23:59:59 ║
rirv938-exp-grpo-cp624-38275-v2-mkmlizer: ║ ║
rirv938-exp-grpo-cp624-38275-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
rirv938-exp-grpo-cp624-38275-v2-mkmlizer: Downloaded to shared memory in 181.244s
rirv938-exp-grpo-cp624-38275-v2-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpyaq1uclh, device:0
rirv938-exp-grpo-cp624-38275-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
Failed to get response for submission blend_tulon_2025-05-22: ('http://alexdaoud-trainer-bajem-28556-v2-predictor.tenant-chaiml-guanaco.k2.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'read tcp 127.0.0.1:38348->127.0.0.1:8080: read: connection reset by peer\n')
rirv938-exp-grpo-cp624-38275-v2-mkmlizer: quantized model in 63.142s
rirv938-exp-grpo-cp624-38275-v2-mkmlizer: Processed model rirv938/exp_grpo_cp624_96ff_b8_r1_merged in 244.387s
rirv938-exp-grpo-cp624-38275-v2-mkmlizer: creating bucket guanaco-mkml-models
rirv938-exp-grpo-cp624-38275-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
rirv938-exp-grpo-cp624-38275-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/rirv938-exp-grpo-cp624-38275-v2
rirv938-exp-grpo-cp624-38275-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/rirv938-exp-grpo-cp624-38275-v2/config.json
rirv938-exp-grpo-cp624-38275-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/rirv938-exp-grpo-cp624-38275-v2/special_tokens_map.json
rirv938-exp-grpo-cp624-38275-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/rirv938-exp-grpo-cp624-38275-v2/tokenizer_config.json
rirv938-exp-grpo-cp624-38275-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/rirv938-exp-grpo-cp624-38275-v2/tokenizer.json
rirv938-exp-grpo-cp624-38275-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/rirv938-exp-grpo-cp624-38275-v2/flywheel_model.1.safetensors
rirv938-exp-grpo-cp624-38275-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/rirv938-exp-grpo-cp624-38275-v2/flywheel_model.0.safetensors
rirv938-exp-grpo-cp624-38275-v2-mkmlizer:
Loading 0: 0%| | 0/363 [00:00<?, ?it/s]
Loading 0: 1%| | 3/363 [00:00<00:12, 28.70it/s]
Loading 0: 2%|▏ | 6/363 [00:00<00:25, 13.93it/s]
Loading 0: 3%|▎ | 11/363 [00:00<00:16, 21.89it/s]
Loading 0: 4%|▍ | 14/363 [00:00<00:25, 13.54it/s]
Loading 0: 4%|▍ | 16/363 [00:01<00:26, 13.09it/s]
Loading 0: 6%|▌ | 21/363 [00:01<00:20, 16.68it/s]
Loading 0: 6%|▋ | 23/363 [00:01<00:25, 13.23it/s]
Loading 0: 8%|▊ | 29/363 [00:01<00:16, 20.58it/s]
Loading 0: 9%|▉ | 33/363 [00:01<00:17, 18.95it/s]
Loading 0: 10%|▉ | 36/363 [00:02<00:22, 14.32it/s]
Loading 0: 11%|█ | 39/363 [00:02<00:19, 16.36it/s]
Loading 0: 12%|█▏ | 42/363 [00:02<00:21, 14.71it/s]
Loading 0: 13%|█▎ | 46/363 [00:02<00:16, 18.71it/s]
Loading 0: 14%|█▍ | 50/363 [00:02<00:13, 22.62it/s]
Loading 0: 15%|█▍ | 53/363 [00:03<00:19, 15.76it/s]
Loading 0: 15%|█▌ | 56/363 [00:03<00:18, 16.35it/s]
Loading 0: 16%|█▋ | 59/363 [00:03<00:24, 12.58it/s]
Loading 0: 18%|█▊ | 64/363 [00:03<00:16, 17.90it/s]
Loading 0: 19%|█▊ | 68/363 [00:03<00:13, 21.59it/s]
Loading 0: 20%|█▉ | 72/363 [00:04<00:21, 13.50it/s]
Loading 0: 21%|██ | 75/363 [00:04<00:18, 15.36it/s]
Loading 0: 21%|██▏ | 78/363 [00:04<00:20, 13.94it/s]
Loading 0: 23%|██▎ | 82/363 [00:05<00:16, 17.21it/s]
Loading 0: 24%|██▎ | 86/363 [00:05<00:13, 20.69it/s]
Loading 0: 25%|██▍ | 89/363 [00:05<00:18, 14.96it/s]
Loading 0: 25%|██▌ | 92/363 [00:05<00:17, 15.39it/s]
Loading 0: 26%|██▋ | 96/363 [00:05<00:13, 19.20it/s]
Loading 0: 28%|██▊ | 101/363 [00:05<00:12, 21.48it/s]
Loading 0: 29%|██▊ | 104/363 [00:06<00:14, 17.89it/s]
Loading 0: 29%|██▉ | 107/363 [00:06<00:18, 13.53it/s]
Loading 0: 30%|███ | 109/363 [00:06<00:19, 13.12it/s]
Loading 0: 31%|███ | 111/363 [00:06<00:18, 13.93it/s]
Loading 0: 31%|███ | 113/363 [00:07<00:21, 11.72it/s]
Loading 0: 33%|███▎ | 118/363 [00:07<00:13, 17.94it/s]
Loading 0: 34%|███▎ | 122/363 [00:07<00:10, 21.91it/s]
Loading 0: 34%|███▍ | 125/363 [00:07<00:15, 15.54it/s]
Loading 0: 35%|███▌ | 128/363 [00:07<00:14, 16.09it/s]
Loading 0: 36%|███▌ | 131/363 [00:08<00:18, 12.52it/s]
Loading 0: 37%|███▋ | 136/363 [00:08<00:12, 17.68it/s]
Loading 0: 39%|███▊ | 140/363 [00:08<00:10, 20.90it/s]
Loading 0: 39%|███▉ | 143/363 [00:08<00:14, 15.33it/s]
Loading 0: 40%|████ | 146/363 [00:08<00:13, 15.92it/s]
Loading 0: 41%|████ | 149/363 [00:09<00:17, 12.59it/s]
Loading 0: 42%|████▏ | 154/363 [00:09<00:11, 17.76it/s]
Loading 0: 44%|████▎ | 158/363 [00:09<00:09, 21.43it/s]
Loading 0: 45%|████▍ | 162/363 [00:10<00:14, 14.01it/s]
Loading 0: 45%|████▌ | 165/363 [00:10<00:12, 15.96it/s]
Loading 0: 46%|████▋ | 168/363 [00:10<00:13, 14.61it/s]
Loading 0: 47%|████▋ | 172/363 [00:10<00:10, 18.39it/s]
Loading 0: 48%|████▊ | 176/363 [00:10<00:08, 22.14it/s]
Loading 0: 49%|████▉ | 179/363 [00:10<00:11, 15.69it/s]
Loading 0: 50%|█████ | 182/363 [00:11<00:11, 16.28it/s]
Loading 0: 51%|█████ | 185/363 [00:11<00:14, 12.69it/s]
Loading 0: 52%|█████▏ | 190/363 [00:11<00:09, 17.82it/s]
Loading 0: 53%|█████▎ | 194/363 [00:11<00:07, 21.49it/s]
Loading 0: 55%|█████▍ | 198/363 [00:12<00:11, 13.94it/s]
Loading 0: 55%|█████▌ | 201/363 [00:26<03:26, 1.27s/it]
Loading 0: 56%|█████▌ | 203/363 [00:27<02:49, 1.06s/it]
Loading 0: 57%|█████▋ | 207/363 [00:27<01:47, 1.44it/s]
Loading 0: 58%|█████▊ | 210/363 [00:27<01:18, 1.95it/s]
Loading 0: 59%|█████▊ | 213/363 [00:27<00:58, 2.55it/s]
Loading 0: 60%|█████▉ | 216/363 [00:28<00:46, 3.18it/s]
Loading 0: 60%|██████ | 219/363 [00:28<00:33, 4.28it/s]
Loading 0: 61%|██████ | 221/363 [00:28<00:29, 4.74it/s]
Loading 0: 63%|██████▎ | 227/363 [00:28<00:16, 8.46it/s]
Loading 0: 64%|██████▎ | 231/363 [00:28<00:13, 10.05it/s]
Loading 0: 64%|██████▍ | 234/363 [00:29<00:13, 9.50it/s]
Loading 0: 65%|██████▌ | 237/363 [00:29<00:10, 11.48it/s]
Loading 0: 66%|██████▌ | 240/363 [00:29<00:10, 11.46it/s]
Loading 0: 67%|██████▋ | 244/363 [00:29<00:07, 15.16it/s]
Loading 0: 68%|██████▊ | 248/363 [00:29<00:06, 18.94it/s]
Loading 0: 69%|██████▉ | 251/363 [00:30<00:07, 14.42it/s]
Loading 0: 70%|██████▉ | 254/363 [00:30<00:07, 15.30it/s]
Loading 0: 71%|███████ | 257/363 [00:30<00:08, 12.22it/s]
Loading 0: 72%|███████▏ | 262/363 [00:30<00:05, 17.42it/s]
Loading 0: 73%|███████▎ | 266/363 [00:30<00:04, 21.00it/s]
Loading 0: 74%|███████▍ | 270/363 [00:31<00:06, 13.65it/s]
Loading 0: 75%|███████▌ | 273/363 [00:31<00:05, 15.58it/s]
Loading 0: 76%|███████▌ | 276/363 [00:31<00:06, 14.20it/s]
Loading 0: 77%|███████▋ | 280/363 [00:31<00:04, 18.06it/s]
Loading 0: 78%|███████▊ | 284/363 [00:31<00:03, 20.41it/s]
Loading 0: 79%|███████▉ | 287/363 [00:32<00:04, 15.20it/s]
Loading 0: 80%|███████▉ | 290/363 [00:32<00:04, 15.94it/s]
Loading 0: 81%|████████ | 293/363 [00:32<00:05, 12.62it/s]
Loading 0: 82%|████████▏ | 298/363 [00:32<00:03, 17.84it/s]
Loading 0: 83%|████████▎ | 302/363 [00:33<00:02, 21.25it/s]
Loading 0: 84%|████████▍ | 305/363 [00:33<00:03, 15.77it/s]
Loading 0: 85%|████████▍ | 308/363 [00:33<00:03, 16.37it/s]
Loading 0: 86%|████████▌ | 311/363 [00:33<00:04, 12.81it/s]
Loading 0: 87%|████████▋ | 316/363 [00:34<00:02, 18.12it/s]
Loading 0: 88%|████████▊ | 320/363 [00:34<00:01, 21.76it/s]
Loading 0: 89%|████████▉ | 324/363 [00:34<00:02, 14.17it/s]
Loading 0: 90%|█████████ | 327/363 [00:34<00:02, 16.00it/s]
Loading 0: 91%|█████████ | 330/363 [00:35<00:02, 14.51it/s]
Loading 0: 92%|█████████▏| 334/363 [00:35<00:01, 18.20it/s]
Loading 0: 93%|█████████▎| 338/363 [00:35<00:01, 21.63it/s]
Loading 0: 94%|█████████▍| 341/363 [00:35<00:01, 15.69it/s]
Loading 0: 95%|█████████▍| 344/363 [00:35<00:01, 16.12it/s]
Loading 0: 96%|█████████▌| 347/363 [00:36<00:01, 12.13it/s]
Loading 0: 97%|█████████▋| 352/363 [00:36<00:00, 16.82it/s]
Loading 0: 98%|█████████▊| 356/363 [00:36<00:00, 20.16it/s]
Loading 0: 99%|█████████▉| 359/363 [00:43<00:02, 1.59it/s]
Loading 0: 99%|█████████▉| 361/363 [00:43<00:01, 1.87it/s]
Job rirv938-exp-grpo-cp624-38275-v2-mkmlizer completed after 278.74s with status: succeeded
Stopping job with name rirv938-exp-grpo-cp624-38275-v2-mkmlizer
Pipeline stage MKMLizer completed in 279.39s
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 rirv938-exp-grpo-cp624-38275-v2
Waiting for inference service rirv938-exp-grpo-cp624-38275-v2 to be ready
Inference service rirv938-exp-grpo-cp624-38275-v2 ready after 160.7103555202484s
Pipeline stage MKMLDeployer completed in 161.23s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.695521831512451s
Received healthy response to inference request in 2.013561964035034s
Received healthy response to inference request in 2.217618942260742s
Received healthy response to inference request in 1.9712727069854736s
Received healthy response to inference request in 1.8874058723449707s
5 requests
0 failed requests
5th percentile: 1.9041792392730712
10th percentile: 1.920952606201172
20th percentile: 1.9544993400573731
30th percentile: 1.9797305583953857
40th percentile: 1.99664626121521
50th percentile: 2.013561964035034
60th percentile: 2.0951847553253176
70th percentile: 2.1768075466156005
80th percentile: 2.313199520111084
90th percentile: 2.5043606758117676
95th percentile: 2.5999412536621094
99th percentile: 2.6764057159423826
mean time: 2.1570762634277343
Pipeline stage StressChecker completed in 12.30s
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 1.03s
Shutdown handler de-registered
rirv938-exp-grpo-cp624-_38275_v2 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 0.10s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.09s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service rirv938-exp-grpo-cp624-38275-v2-profiler
Waiting for inference service rirv938-exp-grpo-cp624-38275-v2-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 2998.53s
Shutdown handler de-registered
rirv938-exp-grpo-cp624-_38275_v2 status is now inactive due to auto deactivation removed underperforming models
rirv938-exp-grpo-cp624-_38275_v2 status is now torndown due to DeploymentManager action