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-v4-mkmlizer
Waiting for job on koboldai-llama2-13b-tie-20758-v4-mkmlizer to finish
koboldai-llama2-13b-tie-20758-v4-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
koboldai-llama2-13b-tie-20758-v4-mkmlizer: ║ _____ __ __ ║
koboldai-llama2-13b-tie-20758-v4-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
koboldai-llama2-13b-tie-20758-v4-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
koboldai-llama2-13b-tie-20758-v4-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
koboldai-llama2-13b-tie-20758-v4-mkmlizer: ║ /___/ ║
koboldai-llama2-13b-tie-20758-v4-mkmlizer: ║ ║
koboldai-llama2-13b-tie-20758-v4-mkmlizer: ║ Version: 0.12.8 ║
koboldai-llama2-13b-tie-20758-v4-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
koboldai-llama2-13b-tie-20758-v4-mkmlizer: ║ https://mk1.ai ║
koboldai-llama2-13b-tie-20758-v4-mkmlizer: ║ ║
koboldai-llama2-13b-tie-20758-v4-mkmlizer: ║ The license key for the current software has been verified as ║
koboldai-llama2-13b-tie-20758-v4-mkmlizer: ║ belonging to: ║
koboldai-llama2-13b-tie-20758-v4-mkmlizer: ║ ║
koboldai-llama2-13b-tie-20758-v4-mkmlizer: ║ Chai Research Corp. ║
koboldai-llama2-13b-tie-20758-v4-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
koboldai-llama2-13b-tie-20758-v4-mkmlizer: ║ Expiration: 2025-04-15 23:59:59 ║
koboldai-llama2-13b-tie-20758-v4-mkmlizer: ║ ║
koboldai-llama2-13b-tie-20758-v4-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
koboldai-llama2-13b-tie-20758-v4-mkmlizer: Downloaded to shared memory in 29.100s
koboldai-llama2-13b-tie-20758-v4-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp5cipya4r, device:0
koboldai-llama2-13b-tie-20758-v4-mkmlizer: Saving flywheel model at /dev/shm/model_cache
koboldai-llama2-13b-tie-20758-v4-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-v4-mkmlizer: tensors = torch.load(model_shard_filename, map_location=torch.device(self.device), mmap=True)
koboldai-llama2-13b-tie-20758-v4-mkmlizer: quantized model in 26.783s
koboldai-llama2-13b-tie-20758-v4-mkmlizer: Processed model KoboldAI/LLaMA2-13B-Tiefighter in 55.884s
koboldai-llama2-13b-tie-20758-v4-mkmlizer: creating bucket guanaco-mkml-models
koboldai-llama2-13b-tie-20758-v4-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
koboldai-llama2-13b-tie-20758-v4-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/koboldai-llama2-13b-tie-20758-v4
koboldai-llama2-13b-tie-20758-v4-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/koboldai-llama2-13b-tie-20758-v4/config.json
koboldai-llama2-13b-tie-20758-v4-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/koboldai-llama2-13b-tie-20758-v4/special_tokens_map.json
koboldai-llama2-13b-tie-20758-v4-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/koboldai-llama2-13b-tie-20758-v4/tokenizer_config.json
koboldai-llama2-13b-tie-20758-v4-mkmlizer: cp /dev/shm/model_cache/tokenizer.model s3://guanaco-mkml-models/koboldai-llama2-13b-tie-20758-v4/tokenizer.model
koboldai-llama2-13b-tie-20758-v4-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/koboldai-llama2-13b-tie-20758-v4/tokenizer.json
koboldai-llama2-13b-tie-20758-v4-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/koboldai-llama2-13b-tie-20758-v4/flywheel_model.0.safetensors
koboldai-llama2-13b-tie-20758-v4-mkmlizer:
Loading 0: 0%| | 0/363 [00:00<?, ?it/s]
Loading 0: 1%| | 4/363 [00:00<00:09, 38.84it/s]
Loading 0: 4%|▎ | 13/363 [00:00<00:05, 67.57it/s]
Loading 0: 6%|▋ | 23/363 [00:00<00:04, 81.89it/s]
Loading 0: 9%|▉ | 32/363 [00:00<00:03, 84.33it/s]
Loading 0: 11%|█▏ | 41/363 [00:00<00:03, 84.17it/s]
Loading 0: 14%|█▍ | 50/363 [00:00<00:03, 84.99it/s]
Loading 0: 16%|█▋ | 59/363 [00:00<00:03, 85.50it/s]
Loading 0: 19%|█▉ | 70/363 [00:00<00:03, 81.67it/s]
Loading 0: 23%|██▎ | 85/363 [00:01<00:03, 90.22it/s]
Loading 0: 26%|██▌ | 94/363 [00:01<00:03, 89.41it/s]
Loading 0: 29%|██▊ | 104/363 [00:01<00:02, 92.25it/s]
Loading 0: 31%|███▏ | 114/363 [00:01<00:02, 91.76it/s]
Loading 0: 34%|███▍ | 124/363 [00:01<00:02, 83.65it/s]
Loading 0: 37%|███▋ | 133/363 [00:01<00:02, 84.77it/s]
Loading 0: 39%|███▉ | 142/363 [00:01<00:02, 83.62it/s]
Loading 0: 42%|████▏ | 151/363 [00:03<00:16, 12.68it/s]
Loading 0: 44%|████▍ | 161/363 [00:03<00:11, 17.46it/s]
Loading 0: 47%|████▋ | 171/363 [00:04<00:08, 23.45it/s]
Loading 0: 50%|████▉ | 180/363 [00:04<00:06, 28.99it/s]
Loading 0: 52%|█████▏ | 188/363 [00:04<00:05, 34.75it/s]
Loading 0: 56%|█████▌ | 202/363 [00:04<00:03, 46.66it/s]
Loading 0: 59%|█████▉ | 214/363 [00:04<00:02, 54.47it/s]
Loading 0: 61%|██████▏ | 223/363 [00:04<00:02, 60.42it/s]
Loading 0: 64%|██████▍ | 232/363 [00:04<00:01, 65.86it/s]
Loading 0: 68%|██████▊ | 247/363 [00:04<00:01, 76.98it/s]
Loading 0: 71%|███████▏ | 259/363 [00:05<00:01, 78.72it/s]
Loading 0: 74%|███████▍ | 268/363 [00:05<00:01, 80.83it/s]
Loading 0: 76%|███████▋ | 277/363 [00:05<00:01, 82.65it/s]
Loading 0: 80%|████████ | 292/363 [00:05<00:00, 89.83it/s]
Loading 0: 83%|████████▎ | 302/363 [00:06<00:02, 24.17it/s]
Loading 0: 85%|████████▌ | 310/363 [00:06<00:01, 28.85it/s]
Loading 0: 88%|████████▊ | 319/363 [00:06<00:01, 35.37it/s]
Loading 0: 91%|█████████ | 331/363 [00:07<00:00, 43.94it/s]
Loading 0: 94%|█████████▎| 340/363 [00:07<00:00, 50.76it/s]
Loading 0: 96%|█████████▌| 349/363 [00:07<00:00, 57.34it/s]
Loading 0: 100%|██████████| 363/363 [00:08<00:00, 18.36it/s]
Job koboldai-llama2-13b-tie-20758-v4-mkmlizer completed after 83.68s with status: succeeded
Stopping job with name koboldai-llama2-13b-tie-20758-v4-mkmlizer
Pipeline stage MKMLizer completed in 84.20s
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 koboldai-llama2-13b-tie-20758-v4
Waiting for inference service koboldai-llama2-13b-tie-20758-v4 to be ready
Failed to get response for submission mistralai-mistral-nem_93303_v347: name 'requests' is not defined
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)
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)
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-v4 ready after 211.11660599708557s
Pipeline stage MKMLDeployer completed in 211.54s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.518866539001465s
Received healthy response to inference request in 2.087418794631958s
Received healthy response to inference request in 1.847219467163086s
Received healthy response to inference request in 1.7454113960266113s
Received healthy response to inference request in 1.9935364723205566s
5 requests
0 failed requests
5th percentile: 1.7657730102539062
10th percentile: 1.786134624481201
20th percentile: 1.826857852935791
30th percentile: 1.87648286819458
40th percentile: 1.9350096702575683
50th percentile: 1.9935364723205566
60th percentile: 2.0310894012451173
70th percentile: 2.068642330169678
80th percentile: 2.1737083435058593
90th percentile: 2.3462874412536623
95th percentile: 2.4325769901275636
99th percentile: 2.5016086292266846
mean time: 2.0384905338287354
Pipeline stage StressChecker completed in 11.49s
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 0.63s
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 0.59s
Shutdown handler de-registered
koboldai-llama2-13b-tie_20758_v4 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 5278.52s
Shutdown handler de-registered
koboldai-llama2-13b-tie_20758_v4 status is now inactive due to auto deactivation removed underperforming models
koboldai-llama2-13b-tie_20758_v4 status is now torndown due to DeploymentManager action
koboldai-llama2-13b-tie_20758_v4 status is now torndown due to DeploymentManager action
koboldai-llama2-13b-tie_20758_v4 status is now torndown due to DeploymentManager action