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 koboldai-llama2-13b-tie-20758-v5-mkmlizer
Waiting for job on koboldai-llama2-13b-tie-20758-v5-mkmlizer to finish
koboldai-llama2-13b-tie-20758-v5-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
koboldai-llama2-13b-tie-20758-v5-mkmlizer: ║ _____ __ __ ║
koboldai-llama2-13b-tie-20758-v5-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
koboldai-llama2-13b-tie-20758-v5-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
koboldai-llama2-13b-tie-20758-v5-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
koboldai-llama2-13b-tie-20758-v5-mkmlizer: ║ /___/ ║
koboldai-llama2-13b-tie-20758-v5-mkmlizer: ║ ║
koboldai-llama2-13b-tie-20758-v5-mkmlizer: ║ Version: 0.12.8 ║
koboldai-llama2-13b-tie-20758-v5-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
koboldai-llama2-13b-tie-20758-v5-mkmlizer: ║ https://mk1.ai ║
koboldai-llama2-13b-tie-20758-v5-mkmlizer: ║ ║
koboldai-llama2-13b-tie-20758-v5-mkmlizer: ║ The license key for the current software has been verified as ║
koboldai-llama2-13b-tie-20758-v5-mkmlizer: ║ belonging to: ║
koboldai-llama2-13b-tie-20758-v5-mkmlizer: ║ ║
koboldai-llama2-13b-tie-20758-v5-mkmlizer: ║ Chai Research Corp. ║
koboldai-llama2-13b-tie-20758-v5-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
koboldai-llama2-13b-tie-20758-v5-mkmlizer: ║ Expiration: 2025-04-15 23:59:59 ║
koboldai-llama2-13b-tie-20758-v5-mkmlizer: ║ ║
koboldai-llama2-13b-tie-20758-v5-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
koboldai-llama2-13b-tie-20758-v5-mkmlizer: Downloaded to shared memory in 27.475s
koboldai-llama2-13b-tie-20758-v5-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpfvku5f1w, device:0
koboldai-llama2-13b-tie-20758-v5-mkmlizer: Saving flywheel model at /dev/shm/model_cache
koboldai-llama2-13b-tie-20758-v5-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.
koboldai-llama2-13b-tie-20758-v5-mkmlizer: tensors = torch.load(model_shard_filename, map_location=torch.device(self.device), mmap=True)
koboldai-llama2-13b-tie-20758-v5-mkmlizer: quantized model in 27.168s
koboldai-llama2-13b-tie-20758-v5-mkmlizer: Processed model KoboldAI/LLaMA2-13B-Tiefighter in 54.644s
koboldai-llama2-13b-tie-20758-v5-mkmlizer: creating bucket guanaco-mkml-models
koboldai-llama2-13b-tie-20758-v5-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
koboldai-llama2-13b-tie-20758-v5-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/koboldai-llama2-13b-tie-20758-v5
koboldai-llama2-13b-tie-20758-v5-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/koboldai-llama2-13b-tie-20758-v5/config.json
koboldai-llama2-13b-tie-20758-v5-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/koboldai-llama2-13b-tie-20758-v5/special_tokens_map.json
koboldai-llama2-13b-tie-20758-v5-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/koboldai-llama2-13b-tie-20758-v5/tokenizer_config.json
koboldai-llama2-13b-tie-20758-v5-mkmlizer: cp /dev/shm/model_cache/tokenizer.model s3://guanaco-mkml-models/koboldai-llama2-13b-tie-20758-v5/tokenizer.model
koboldai-llama2-13b-tie-20758-v5-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/koboldai-llama2-13b-tie-20758-v5/tokenizer.json
koboldai-llama2-13b-tie-20758-v5-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/koboldai-llama2-13b-tie-20758-v5/flywheel_model.0.safetensors
koboldai-llama2-13b-tie-20758-v5-mkmlizer:
Loading 0: 0%| | 0/363 [00:00<?, ?it/s]
Loading 0: 1%| | 4/363 [00:00<00:10, 33.50it/s]
Loading 0: 4%|▎ | 13/363 [00:00<00:05, 63.58it/s]
Loading 0: 7%|▋ | 25/363 [00:00<00:04, 76.45it/s]
Loading 0: 11%|█ | 40/363 [00:00<00:03, 91.41it/s]
Loading 0: 14%|█▍ | 52/363 [00:00<00:03, 89.44it/s]
Loading 0: 18%|█▊ | 67/363 [00:00<00:03, 97.14it/s]
Loading 0: 22%|██▏ | 79/363 [00:00<00:02, 95.03it/s]
Loading 0: 26%|██▌ | 94/363 [00:01<00:02, 99.66it/s]
Loading 0: 29%|██▊ | 104/363 [00:01<00:02, 97.29it/s]
Loading 0: 32%|███▏ | 115/363 [00:01<00:02, 91.62it/s]
Loading 0: 36%|███▌ | 130/363 [00:01<00:02, 97.78it/s]
Loading 0: 39%|███▉ | 142/363 [00:01<00:02, 94.33it/s]
Loading 0: 42%|████▏ | 152/363 [00:03<00:13, 15.55it/s]
Loading 0: 46%|████▌ | 166/363 [00:03<00:09, 21.84it/s]
Loading 0: 48%|████▊ | 175/363 [00:03<00:07, 26.60it/s]
Loading 0: 51%|█████ | 184/363 [00:04<00:05, 32.30it/s]
Loading 0: 54%|█████▍ | 196/363 [00:04<00:04, 40.49it/s]
Loading 0: 56%|█████▋ | 205/363 [00:04<00:03, 46.38it/s]
Loading 0: 61%|██████ | 220/363 [00:04<00:02, 58.97it/s]
Loading 0: 64%|██████▍ | 232/363 [00:04<00:02, 64.58it/s]
Loading 0: 66%|██████▋ | 241/363 [00:04<00:01, 68.76it/s]
Loading 0: 69%|██████▉ | 250/363 [00:04<00:01, 70.67it/s]
Loading 0: 71%|███████▏ | 259/363 [00:04<00:01, 74.14it/s]
Loading 0: 74%|███████▍ | 268/363 [00:05<00:01, 77.51it/s]
Loading 0: 78%|███████▊ | 283/363 [00:05<00:00, 86.99it/s]
Loading 0: 81%|████████ | 294/363 [00:06<00:02, 23.91it/s]
Loading 0: 83%|████████▎ | 301/363 [00:06<00:02, 27.48it/s]
Loading 0: 85%|████████▌ | 310/363 [00:06<00:01, 34.04it/s]
Loading 0: 89%|████████▊ | 322/363 [00:06<00:00, 43.26it/s]
Loading 0: 91%|█████████▏| 332/363 [00:06<00:00, 51.76it/s]
Loading 0: 95%|█████████▌| 346/363 [00:07<00:00, 63.36it/s]
Loading 0: 99%|█████████▊| 358/363 [00:07<00:00, 69.69it/s]
Job koboldai-llama2-13b-tie-20758-v5-mkmlizer completed after 83.61s with status: succeeded
Stopping job with name koboldai-llama2-13b-tie-20758-v5-mkmlizer
Pipeline stage MKMLizer completed in 84.05s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.14s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service koboldai-llama2-13b-tie-20758-v5
Waiting for inference service koboldai-llama2-13b-tie-20758-v5 to be ready
Failed to get response for submission chaiml-dn-20250217-c-4ep_8638_v1: HTTPConnectionPool(host='chaiml-dn-20250217-c-4ep-8638-v1-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
Inference service koboldai-llama2-13b-tie-20758-v5 ready after 200.9694037437439s
Pipeline stage MKMLDeployer completed in 201.46s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.6909525394439697s
Received healthy response to inference request in 1.8752646446228027s
Received healthy response to inference request in 1.9287621974945068s
Received healthy response to inference request in 1.8136565685272217s
Received healthy response to inference request in 1.9167835712432861s
5 requests
0 failed requests
5th percentile: 1.8259781837463378
10th percentile: 1.8382997989654541
20th percentile: 1.8629430294036866
30th percentile: 1.8835684299468993
40th percentile: 1.9001760005950927
50th percentile: 1.9167835712432861
60th percentile: 1.9215750217437744
70th percentile: 1.9263664722442626
80th percentile: 2.0812002658843998
90th percentile: 2.3860764026641847
95th percentile: 2.538514471054077
99th percentile: 2.660464925765991
mean time: 2.0450839042663573
Pipeline stage StressChecker completed in 11.45s
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 0.63s
Shutdown handler de-registered
koboldai-llama2-13b-tie_20758_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
%s, retrying in %s seconds...
Evaluating %s Family Friendly Score with %s threads
Pipeline stage OfflineFamilyFriendlyScorer completed in 4690.26s
Shutdown handler de-registered
koboldai-llama2-13b-tie_20758_v5 status is now inactive due to auto deactivation removed underperforming models
koboldai-llama2-13b-tie_20758_v5 status is now torndown due to DeploymentManager action
koboldai-llama2-13b-tie_20758_v5 status is now torndown due to DeploymentManager action
koboldai-llama2-13b-tie_20758_v5 status is now torndown due to DeploymentManager action