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-mistral-24b-dpo-96566-v1-mkmlizer
Waiting for job on rirv938-mistral-24b-dpo-96566-v1-mkmlizer to finish
rirv938-mistral-24b-dpo-96566-v1-mkmlizer: Downloaded to shared memory in 171.848s
rirv938-mistral-24b-dpo-96566-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpw1phcs24, device:0
rirv938-mistral-24b-dpo-96566-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
rirv938-mistral-24b-dpo-96566-v1-mkmlizer: quantized model in 65.333s
rirv938-mistral-24b-dpo-96566-v1-mkmlizer: Processed model rirv938/mistral_24b_dpo_kl_40k_beta4_1250_v3 in 237.192s
rirv938-mistral-24b-dpo-96566-v1-mkmlizer: creating bucket guanaco-mkml-models
rirv938-mistral-24b-dpo-96566-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
rirv938-mistral-24b-dpo-96566-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/rirv938-mistral-24b-dpo-96566-v1
rirv938-mistral-24b-dpo-96566-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/rirv938-mistral-24b-dpo-96566-v1/config.json
rirv938-mistral-24b-dpo-96566-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/rirv938-mistral-24b-dpo-96566-v1/special_tokens_map.json
rirv938-mistral-24b-dpo-96566-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/rirv938-mistral-24b-dpo-96566-v1/tokenizer_config.json
rirv938-mistral-24b-dpo-96566-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/rirv938-mistral-24b-dpo-96566-v1/tokenizer.json
rirv938-mistral-24b-dpo-96566-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/rirv938-mistral-24b-dpo-96566-v1/flywheel_model.1.safetensors
rirv938-mistral-24b-dpo-96566-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/rirv938-mistral-24b-dpo-96566-v1/flywheel_model.0.safetensors
rirv938-mistral-24b-dpo-96566-v1-mkmlizer:
Loading 0: 0%| | 0/363 [00:00<?, ?it/s]
Loading 0: 1%| | 3/363 [00:00<00:14, 25.32it/s]
Loading 0: 2%|▏ | 6/363 [00:00<00:29, 11.93it/s]
Loading 0: 3%|▎ | 10/363 [00:00<00:19, 17.67it/s]
Loading 0: 4%|▎ | 13/363 [00:00<00:29, 11.97it/s]
Loading 0: 4%|▍ | 15/363 [00:01<00:36, 9.51it/s]
Loading 0: 5%|▌ | 19/363 [00:01<00:25, 13.71it/s]
Loading 0: 6%|▌ | 22/363 [00:01<00:26, 13.03it/s]
Loading 0: 7%|▋ | 24/363 [00:01<00:27, 12.50it/s]
Loading 0: 8%|▊ | 28/363 [00:01<00:20, 16.70it/s]
Loading 0: 9%|▉ | 32/363 [00:02<00:16, 20.35it/s]
Loading 0: 10%|▉ | 35/363 [00:02<00:23, 13.82it/s]
Loading 0: 10%|█ | 37/363 [00:02<00:24, 13.09it/s]
Loading 0: 11%|█ | 39/363 [00:02<00:23, 13.74it/s]
Loading 0: 11%|█▏ | 41/363 [00:03<00:29, 10.79it/s]
Loading 0: 13%|█▎ | 46/363 [00:03<00:19, 16.47it/s]
Loading 0: 14%|█▍ | 50/363 [00:03<00:15, 19.91it/s]
Loading 0: 15%|█▍ | 53/363 [00:03<00:22, 13.48it/s]
Loading 0: 15%|█▌ | 55/363 [00:04<00:25, 12.11it/s]
Loading 0: 16%|█▌ | 57/363 [00:04<00:23, 12.82it/s]
Loading 0: 16%|█▋ | 59/363 [00:04<00:28, 10.58it/s]
Loading 0: 18%|█▊ | 64/363 [00:04<00:18, 16.15it/s]
Loading 0: 19%|█▊ | 68/363 [00:04<00:14, 19.69it/s]
Loading 0: 20%|█▉ | 71/363 [00:05<00:20, 13.99it/s]
Loading 0: 20%|██ | 73/363 [00:05<00:21, 13.57it/s]
Loading 0: 21%|██ | 75/363 [00:05<00:20, 14.35it/s]
Loading 0: 21%|██ | 77/363 [00:05<00:24, 11.64it/s]
Loading 0: 23%|██▎ | 83/363 [00:05<00:14, 19.50it/s]
Loading 0: 24%|██▍ | 87/363 [00:05<00:15, 18.36it/s]
Loading 0: 25%|██▍ | 90/363 [00:06<00:19, 13.99it/s]
Loading 0: 26%|██▌ | 95/363 [00:06<00:14, 19.10it/s]
Loading 0: 28%|██▊ | 101/363 [00:06<00:11, 22.42it/s]
Loading 0: 29%|██▊ | 104/363 [00:06<00:14, 18.49it/s]
Loading 0: 29%|██▉ | 107/363 [00:07<00:18, 14.16it/s]
Loading 0: 30%|███ | 109/363 [00:07<00:18, 13.66it/s]
Loading 0: 31%|███ | 111/363 [00:07<00:17, 14.29it/s]
Loading 0: 31%|███ | 113/363 [00:07<00:21, 11.85it/s]
Loading 0: 33%|███▎ | 119/363 [00:07<00:12, 19.40it/s]
Loading 0: 34%|███▍ | 123/363 [00:08<00:13, 18.07it/s]
Loading 0: 35%|███▍ | 126/363 [00:08<00:17, 13.52it/s]
Loading 0: 36%|███▌ | 129/363 [00:08<00:15, 15.40it/s]
Loading 0: 36%|███▋ | 132/363 [00:08<00:16, 13.94it/s]
Loading 0: 37%|███▋ | 136/363 [00:09<00:12, 17.61it/s]
Loading 0: 39%|███▊ | 140/363 [00:09<00:10, 21.07it/s]
Loading 0: 39%|███▉ | 143/363 [00:09<00:14, 14.95it/s]
Loading 0: 40%|████ | 146/363 [00:09<00:13, 15.63it/s]
Loading 0: 41%|████ | 149/363 [00:10<00:17, 12.24it/s]
Loading 0: 42%|████▏ | 154/363 [00:10<00:12, 17.20it/s]
Loading 0: 44%|████▎ | 158/363 [00:10<00:09, 20.62it/s]
Loading 0: 44%|████▍ | 161/363 [00:10<00:13, 15.04it/s]
Loading 0: 45%|████▌ | 164/363 [00:10<00:12, 15.54it/s]
Loading 0: 46%|████▌ | 167/363 [00:11<00:16, 12.20it/s]
Loading 0: 47%|████▋ | 172/363 [00:11<00:11, 16.63it/s]
Loading 0: 48%|████▊ | 176/363 [00:11<00:09, 19.47it/s]
Loading 0: 49%|████▉ | 179/363 [00:11<00:13, 14.03it/s]
Loading 0: 50%|█████ | 182/363 [00:12<00:12, 14.82it/s]
Loading 0: 51%|█████ | 184/363 [00:12<00:13, 13.29it/s]
Loading 0: 51%|█████ | 186/363 [00:12<00:13, 12.94it/s]
Loading 0: 52%|█████▏ | 190/363 [00:12<00:10, 17.19it/s]
Loading 0: 53%|█████▎ | 194/363 [00:12<00:07, 21.22it/s]
Loading 0: 54%|█████▍ | 197/363 [00:13<00:11, 14.69it/s]
Loading 0: 55%|█████▌ | 200/363 [00:13<00:10, 15.47it/s]
Loading 0: 56%|█████▌ | 202/363 [00:27<04:19, 1.61s/it]
Loading 0: 56%|█████▌ | 203/363 [00:28<03:47, 1.42s/it]
Loading 0: 57%|█████▋ | 207/363 [00:28<02:08, 1.22it/s]
Loading 0: 58%|█████▊ | 210/363 [00:28<01:28, 1.73it/s]
Loading 0: 59%|█████▊ | 213/363 [00:28<01:03, 2.35it/s]
Loading 0: 59%|█████▉ | 215/363 [00:28<00:52, 2.85it/s]
Loading 0: 60%|█████▉ | 217/363 [00:28<00:41, 3.48it/s]
Loading 0: 60%|██████ | 219/363 [00:29<00:32, 4.41it/s]
Loading 0: 61%|██████ | 221/363 [00:29<00:28, 4.96it/s]
Loading 0: 62%|██████▏ | 226/363 [00:29<00:15, 8.74it/s]
Loading 0: 63%|██████▎ | 230/363 [00:29<00:11, 11.88it/s]
Loading 0: 64%|██████▍ | 233/363 [00:29<00:12, 10.76it/s]
Loading 0: 65%|██████▌ | 236/363 [00:30<00:10, 12.11it/s]
Loading 0: 66%|██████▌ | 238/363 [00:30<00:10, 11.47it/s]
Loading 0: 66%|██████▌ | 240/363 [00:30<00:10, 11.63it/s]
Loading 0: 67%|██████▋ | 244/363 [00:30<00:07, 16.07it/s]
Loading 0: 68%|██████▊ | 248/363 [00:30<00:05, 19.85it/s]
Loading 0: 69%|██████▉ | 251/363 [00:31<00:07, 14.48it/s]
Loading 0: 70%|██████▉ | 254/363 [00:31<00:07, 15.29it/s]
Loading 0: 71%|███████ | 256/363 [00:31<00:07, 13.53it/s]
Loading 0: 71%|███████ | 258/363 [00:31<00:07, 13.19it/s]
Loading 0: 72%|███████▏ | 262/363 [00:31<00:05, 18.00it/s]
Loading 0: 73%|███████▎ | 266/363 [00:31<00:04, 22.32it/s]
Loading 0: 74%|███████▍ | 269/363 [00:32<00:06, 15.46it/s]
Loading 0: 75%|███████▍ | 272/363 [00:32<00:05, 16.09it/s]
Loading 0: 76%|███████▌ | 275/363 [00:32<00:07, 12.23it/s]
Loading 0: 77%|███████▋ | 280/363 [00:32<00:04, 16.88it/s]
Loading 0: 78%|███████▊ | 284/363 [00:32<00:03, 19.83it/s]
Loading 0: 79%|███████▉ | 287/363 [00:33<00:05, 14.48it/s]
Loading 0: 80%|███████▉ | 290/363 [00:33<00:04, 15.25it/s]
Loading 0: 80%|████████ | 292/363 [00:33<00:05, 13.30it/s]
Loading 0: 81%|████████ | 294/363 [00:33<00:05, 12.77it/s]
Loading 0: 82%|████████▏ | 298/363 [00:33<00:03, 17.21it/s]
Loading 0: 83%|████████▎ | 302/363 [00:34<00:02, 20.86it/s]
Loading 0: 84%|████████▍ | 305/363 [00:34<00:03, 14.70it/s]
Loading 0: 85%|████████▍ | 308/363 [00:34<00:03, 15.36it/s]
Loading 0: 85%|████████▌ | 310/363 [00:34<00:03, 13.44it/s]
Loading 0: 86%|████████▌ | 312/363 [00:35<00:03, 12.79it/s]
Loading 0: 87%|████████▋ | 316/363 [00:35<00:02, 16.99it/s]
Loading 0: 88%|████████▊ | 320/363 [00:35<00:02, 20.82it/s]
Loading 0: 89%|████████▉ | 323/363 [00:35<00:02, 14.61it/s]
Loading 0: 90%|████████▉ | 325/363 [00:35<00:02, 13.84it/s]
Loading 0: 90%|█████████ | 327/363 [00:35<00:02, 14.47it/s]
Loading 0: 91%|█████████ | 329/363 [00:36<00:02, 11.65it/s]
Loading 0: 92%|█████████▏| 334/363 [00:36<00:01, 18.06it/s]
Loading 0: 93%|█████████▎| 338/363 [00:36<00:01, 22.19it/s]
Loading 0: 94%|█████████▍| 341/363 [00:36<00:01, 15.40it/s]
Loading 0: 95%|█████████▍| 344/363 [00:36<00:01, 15.80it/s]
Loading 0: 96%|█████████▌| 347/363 [00:37<00:01, 12.44it/s]
Loading 0: 97%|█████████▋| 352/363 [00:37<00:00, 17.72it/s]
Loading 0: 98%|█████████▊| 356/363 [00:37<00:00, 21.43it/s]
Loading 0: 99%|█████████▉| 359/363 [00:44<00:02, 1.58it/s]
Loading 0: 100%|█████████▉| 362/363 [00:44<00:00, 2.05it/s]
Job rirv938-mistral-24b-dpo-96566-v1-mkmlizer completed after 293.81s with status: succeeded
Stopping job with name rirv938-mistral-24b-dpo-96566-v1-mkmlizer
Pipeline stage MKMLizer completed in 294.27s
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 rirv938-mistral-24b-dpo-96566-v1
Waiting for inference service rirv938-mistral-24b-dpo-96566-v1 to be ready
Inference service rirv938-mistral-24b-dpo-96566-v1 ready after 100.68201160430908s
Pipeline stage MKMLDeployer completed in 101.17s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.996851682662964s
Received healthy response to inference request in 2.4657363891601562s
Received healthy response to inference request in 2.4802136421203613s
Received healthy response to inference request in 2.466623067855835s
Received healthy response to inference request in 2.4809787273406982s
5 requests
0 failed requests
5th percentile: 2.465913724899292
10th percentile: 2.4660910606384276
20th percentile: 2.466445732116699
30th percentile: 2.46934118270874
40th percentile: 2.474777412414551
50th percentile: 2.4802136421203613
60th percentile: 2.480519676208496
70th percentile: 2.4808257102966307
80th percentile: 2.5841533184051513
90th percentile: 2.790502500534058
95th percentile: 2.893677091598511
99th percentile: 2.9762167644500734
mean time: 2.5780807018280028
Pipeline stage StressChecker completed in 14.04s
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 0.70s
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 0.60s
Shutdown handler de-registered
rirv938-mistral-24b-dpo_96566_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 2935.00s
Shutdown handler de-registered
rirv938-mistral-24b-dpo_96566_v1 status is now inactive due to auto deactivation removed underperforming models
rirv938-mistral-24b-dpo_96566_v1 status is now torndown due to DeploymentManager action