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 alexxi19-ft-v1-nemo-base-lora-v1-mkmlizer
Waiting for job on alexxi19-ft-v1-nemo-base-lora-v1-mkmlizer to finish
alexxi19-ft-v1-nemo-base-lora-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
alexxi19-ft-v1-nemo-base-lora-v1-mkmlizer: ║ _____ __ __ ║
alexxi19-ft-v1-nemo-base-lora-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
alexxi19-ft-v1-nemo-base-lora-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
alexxi19-ft-v1-nemo-base-lora-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
alexxi19-ft-v1-nemo-base-lora-v1-mkmlizer: ║ /___/ ║
alexxi19-ft-v1-nemo-base-lora-v1-mkmlizer: ║ ║
alexxi19-ft-v1-nemo-base-lora-v1-mkmlizer: ║ Version: 0.11.12 ║
alexxi19-ft-v1-nemo-base-lora-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
alexxi19-ft-v1-nemo-base-lora-v1-mkmlizer: ║ https://mk1.ai ║
alexxi19-ft-v1-nemo-base-lora-v1-mkmlizer: ║ ║
alexxi19-ft-v1-nemo-base-lora-v1-mkmlizer: ║ The license key for the current software has been verified as ║
alexxi19-ft-v1-nemo-base-lora-v1-mkmlizer: ║ belonging to: ║
alexxi19-ft-v1-nemo-base-lora-v1-mkmlizer: ║ ║
alexxi19-ft-v1-nemo-base-lora-v1-mkmlizer: ║ Chai Research Corp. ║
alexxi19-ft-v1-nemo-base-lora-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
alexxi19-ft-v1-nemo-base-lora-v1-mkmlizer: ║ Expiration: 2025-04-15 23:59:59 ║
alexxi19-ft-v1-nemo-base-lora-v1-mkmlizer: ║ ║
alexxi19-ft-v1-nemo-base-lora-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
alexxi19-ft-v1-nemo-base-lora-v1-mkmlizer: Downloaded to shared memory in 46.335s
alexxi19-ft-v1-nemo-base-lora-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpmmkqr_br, device:0
alexxi19-ft-v1-nemo-base-lora-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
alexxi19-ft-v1-nemo-base-lora-v1-mkmlizer: /opt/conda/lib/python3.10/site-packages/mk1/flywheel/functional/loader.py:55: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
alexxi19-ft-v1-nemo-base-lora-v1-mkmlizer: tensors = torch.load(model_shard_filename, map_location=torch.device(self.device), mmap=True)
alexxi19-ft-v1-nemo-base-lora-v1-mkmlizer: quantized model in 35.694s
alexxi19-ft-v1-nemo-base-lora-v1-mkmlizer: Processed model alexxi19/ft-v1-nemo-base-lora in 82.029s
alexxi19-ft-v1-nemo-base-lora-v1-mkmlizer: creating bucket guanaco-mkml-models
alexxi19-ft-v1-nemo-base-lora-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
alexxi19-ft-v1-nemo-base-lora-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/alexxi19-ft-v1-nemo-base-lora-v1
alexxi19-ft-v1-nemo-base-lora-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/alexxi19-ft-v1-nemo-base-lora-v1/config.json
alexxi19-ft-v1-nemo-base-lora-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/alexxi19-ft-v1-nemo-base-lora-v1/special_tokens_map.json
alexxi19-ft-v1-nemo-base-lora-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/alexxi19-ft-v1-nemo-base-lora-v1/tokenizer_config.json
alexxi19-ft-v1-nemo-base-lora-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/alexxi19-ft-v1-nemo-base-lora-v1/tokenizer.json
alexxi19-ft-v1-nemo-base-lora-v1-mkmlizer:
Loading 0: 0%| | 0/363 [00:00<?, ?it/s]
Loading 0: 2%|▏ | 7/363 [00:00<00:07, 47.30it/s]
Loading 0: 4%|▍ | 16/363 [00:00<00:05, 64.52it/s]
Loading 0: 9%|▊ | 31/363 [00:00<00:03, 83.61it/s]
Loading 0: 12%|█▏ | 42/363 [00:00<00:03, 92.05it/s]
Loading 0: 14%|█▍ | 52/363 [00:00<00:03, 78.69it/s]
Loading 0: 17%|█▋ | 61/363 [00:01<00:14, 20.78it/s]
Loading 0: 19%|█▉ | 70/363 [00:01<00:10, 26.90it/s]
Loading 0: 22%|██▏ | 79/363 [00:02<00:08, 33.88it/s]
Loading 0: 24%|██▍ | 88/363 [00:02<00:06, 40.53it/s]
Loading 0: 27%|██▋ | 97/363 [00:02<00:05, 47.37it/s]
Loading 0: 29%|██▉ | 106/363 [00:02<00:04, 54.91it/s]
Loading 0: 32%|███▏ | 115/363 [00:02<00:04, 61.74it/s]
Loading 0: 34%|███▍ | 124/363 [00:02<00:03, 64.63it/s]
Loading 0: 37%|███▋ | 133/363 [00:02<00:03, 66.33it/s]
Loading 0: 39%|███▉ | 142/363 [00:03<00:10, 20.52it/s]
Loading 0: 42%|████▏ | 151/363 [00:04<00:08, 26.41it/s]
Loading 0: 44%|████▍ | 160/363 [00:04<00:06, 32.86it/s]
Loading 0: 47%|████▋ | 169/363 [00:04<00:04, 40.47it/s]
Loading 0: 49%|████▉ | 178/363 [00:04<00:03, 46.99it/s]
Loading 0: 52%|█████▏ | 187/363 [00:04<00:03, 52.73it/s]
Loading 0: 54%|█████▍ | 196/363 [00:04<00:02, 59.90it/s]
Loading 0: 56%|█████▋ | 205/363 [00:04<00:02, 66.24it/s]
Loading 0: 59%|█████▉ | 214/363 [00:04<00:02, 69.72it/s]
Loading 0: 61%|██████▏ | 223/363 [00:05<00:06, 20.32it/s]
Loading 0: 64%|██████▍ | 233/363 [00:06<00:04, 27.32it/s]
Loading 0: 68%|██████▊ | 247/363 [00:06<00:03, 38.12it/s]
Loading 0: 71%|███████ | 256/363 [00:06<00:02, 44.45it/s]
Loading 0: 73%|███████▎ | 265/363 [00:06<00:01, 49.96it/s]
Loading 0: 75%|███████▌ | 274/363 [00:06<00:01, 56.76it/s]
Loading 0: 79%|███████▊ | 285/363 [00:06<00:01, 67.45it/s]
Loading 0: 81%|████████▏ | 295/363 [00:06<00:01, 67.78it/s]
Loading 0: 84%|████████▎ | 304/363 [00:07<00:02, 21.31it/s]
Loading 0: 86%|████████▌ | 313/363 [00:08<00:01, 27.15it/s]
Loading 0: 89%|████████▉ | 323/363 [00:08<00:01, 35.02it/s]
Loading 0: 91%|█████████▏| 332/363 [00:08<00:00, 42.40it/s]
Loading 0: 94%|█████████▍| 341/363 [00:08<00:00, 48.48it/s]
Loading 0: 96%|█████████▌| 349/363 [00:08<00:00, 53.23it/s]
Loading 0: 99%|█████████▉| 359/363 [00:08<00:00, 62.47it/s]
Job alexxi19-ft-v1-nemo-base-lora-v1-mkmlizer completed after 114.07s with status: succeeded
Stopping job with name alexxi19-ft-v1-nemo-base-lora-v1-mkmlizer
Pipeline stage MKMLizer completed in 114.56s
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 alexxi19-ft-v1-nemo-base-lora-v1
Waiting for inference service alexxi19-ft-v1-nemo-base-lora-v1 to be ready
Inference service alexxi19-ft-v1-nemo-base-lora-v1 ready after 170.57097911834717s
Pipeline stage MKMLDeployer completed in 171.08s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.3968844413757324s
Received healthy response to inference request in 1.2743852138519287s
Received healthy response to inference request in 0.825005292892456s
Received healthy response to inference request in 0.8576581478118896s
Received healthy response to inference request in 1.1943328380584717s
5 requests
0 failed requests
5th percentile: 0.8315358638763428
10th percentile: 0.8380664348602295
20th percentile: 0.8511275768280029
30th percentile: 0.9249930858612061
40th percentile: 1.0596629619598388
50th percentile: 1.1943328380584717
60th percentile: 1.2263537883758544
70th percentile: 1.2583747386932373
80th percentile: 1.2988850593566894
90th percentile: 1.347884750366211
95th percentile: 1.3723845958709717
99th percentile: 1.3919844722747803
mean time: 1.1096531867980957
Pipeline stage StressChecker completed in 6.78s
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 0.67s
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 0.69s
Shutdown handler de-registered
alexxi19-ft-v1-nemo-base-lora_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 2618.55s
Shutdown handler de-registered
alexxi19-ft-v1-nemo-base-lora_v1 status is now inactive due to auto deactivation removed underperforming models
alexxi19-ft-v1-nemo-base-lora_v1 status is now torndown due to DeploymentManager action