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 sao10k-mn-backyardai-par-1350-v2-mkmlizer
Waiting for job on sao10k-mn-backyardai-par-1350-v2-mkmlizer to finish
sao10k-mn-backyardai-par-1350-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
sao10k-mn-backyardai-par-1350-v2-mkmlizer: ║ _____ __ __ ║
sao10k-mn-backyardai-par-1350-v2-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
sao10k-mn-backyardai-par-1350-v2-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
sao10k-mn-backyardai-par-1350-v2-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
sao10k-mn-backyardai-par-1350-v2-mkmlizer: ║ /___/ ║
sao10k-mn-backyardai-par-1350-v2-mkmlizer: ║ ║
sao10k-mn-backyardai-par-1350-v2-mkmlizer: ║ Version: 0.11.12 ║
sao10k-mn-backyardai-par-1350-v2-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
sao10k-mn-backyardai-par-1350-v2-mkmlizer: ║ https://mk1.ai ║
sao10k-mn-backyardai-par-1350-v2-mkmlizer: ║ ║
sao10k-mn-backyardai-par-1350-v2-mkmlizer: ║ The license key for the current software has been verified as ║
sao10k-mn-backyardai-par-1350-v2-mkmlizer: ║ belonging to: ║
sao10k-mn-backyardai-par-1350-v2-mkmlizer: ║ ║
sao10k-mn-backyardai-par-1350-v2-mkmlizer: ║ Chai Research Corp. ║
sao10k-mn-backyardai-par-1350-v2-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
sao10k-mn-backyardai-par-1350-v2-mkmlizer: ║ Expiration: 2024-10-15 23:59:59 ║
sao10k-mn-backyardai-par-1350-v2-mkmlizer: ║ ║
sao10k-mn-backyardai-par-1350-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
Failed to get response for submission sao10k-mn-12b-lyra-v4a1_v3: ('http://sao10k-mn-12b-lyra-v4a1-v3-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'read tcp 127.0.0.1:38094->127.0.0.1:8080: read: connection reset by peer\n')
sao10k-mn-backyardai-par-1350-v2-mkmlizer: Downloaded to shared memory in 48.284s
sao10k-mn-backyardai-par-1350-v2-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp_22ifoqs, device:0
sao10k-mn-backyardai-par-1350-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
sao10k-mn-backyardai-par-1350-v2-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.
sao10k-mn-backyardai-par-1350-v2-mkmlizer: tensors = torch.load(model_shard_filename, map_location=torch.device(self.device), mmap=True)
sao10k-mn-backyardai-par-1350-v2-mkmlizer: quantized model in 37.939s
sao10k-mn-backyardai-par-1350-v2-mkmlizer: Processed model Sao10K/MN-BackyardAI-Party-12B-v1 in 86.223s
sao10k-mn-backyardai-par-1350-v2-mkmlizer: creating bucket guanaco-mkml-models
sao10k-mn-backyardai-par-1350-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
sao10k-mn-backyardai-par-1350-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/sao10k-mn-backyardai-par-1350-v2
sao10k-mn-backyardai-par-1350-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/sao10k-mn-backyardai-par-1350-v2/config.json
sao10k-mn-backyardai-par-1350-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/sao10k-mn-backyardai-par-1350-v2/special_tokens_map.json
sao10k-mn-backyardai-par-1350-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/sao10k-mn-backyardai-par-1350-v2/tokenizer_config.json
sao10k-mn-backyardai-par-1350-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/sao10k-mn-backyardai-par-1350-v2/tokenizer.json
sao10k-mn-backyardai-par-1350-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/sao10k-mn-backyardai-par-1350-v2/flywheel_model.0.safetensors
sao10k-mn-backyardai-par-1350-v2-mkmlizer:
Loading 0: 0%| | 0/363 [00:00<?, ?it/s]
Loading 0: 1%| | 4/363 [00:00<00:09, 38.36it/s]
Loading 0: 4%|▎ | 13/363 [00:00<00:05, 63.59it/s]
Loading 0: 6%|▌ | 22/363 [00:00<00:04, 71.51it/s]
Loading 0: 9%|▊ | 31/363 [00:00<00:04, 74.64it/s]
Loading 0: 11%|█ | 40/363 [00:00<00:04, 73.58it/s]
Loading 0: 13%|█▎ | 49/363 [00:00<00:04, 77.26it/s]
Loading 0: 16%|█▌ | 58/363 [00:00<00:03, 80.74it/s]
Loading 0: 18%|█▊ | 67/363 [00:02<00:16, 18.37it/s]
Loading 0: 21%|██ | 76/363 [00:02<00:11, 24.41it/s]
Loading 0: 24%|██▎ | 86/363 [00:02<00:08, 32.56it/s]
Loading 0: 26%|██▌ | 94/363 [00:02<00:06, 38.90it/s]
Loading 0: 28%|██▊ | 103/363 [00:02<00:05, 46.29it/s]
Loading 0: 31%|███ | 112/363 [00:02<00:04, 52.69it/s]
Loading 0: 33%|███▎ | 121/363 [00:02<00:04, 59.86it/s]
Loading 0: 36%|███▌ | 130/363 [00:02<00:03, 65.87it/s]
Loading 0: 38%|███▊ | 139/363 [00:02<00:03, 66.60it/s]
Loading 0: 40%|████ | 147/363 [00:04<00:11, 19.01it/s]
Loading 0: 42%|████▏ | 153/363 [00:04<00:09, 21.93it/s]
Loading 0: 44%|████▍ | 160/363 [00:04<00:07, 27.02it/s]
Loading 0: 47%|████▋ | 169/363 [00:04<00:05, 35.07it/s]
Loading 0: 49%|████▉ | 178/363 [00:04<00:04, 41.28it/s]
Loading 0: 52%|█████▏ | 187/363 [00:04<00:03, 49.11it/s]
Loading 0: 54%|█████▍ | 196/363 [00:04<00:02, 57.12it/s]
Loading 0: 56%|█████▋ | 205/363 [00:04<00:02, 64.34it/s]
Loading 0: 59%|█████▉ | 214/363 [00:05<00:02, 67.78it/s]
Loading 0: 61%|██████▏ | 223/363 [00:06<00:07, 19.26it/s]
Loading 0: 64%|██████▍ | 232/363 [00:06<00:05, 25.18it/s]
Loading 0: 66%|██████▋ | 241/363 [00:06<00:03, 31.83it/s]
Loading 0: 69%|██████▉ | 250/363 [00:06<00:02, 38.39it/s]
Loading 0: 71%|███████▏ | 259/363 [00:06<00:02, 45.64it/s]
Loading 0: 74%|███████▍ | 268/363 [00:06<00:01, 51.70it/s]
Loading 0: 76%|███████▋ | 277/363 [00:06<00:01, 56.40it/s]
Loading 0: 79%|███████▉ | 286/363 [00:07<00:01, 60.22it/s]
Loading 0: 81%|████████▏ | 295/363 [00:07<00:01, 65.72it/s]
Loading 0: 84%|████████▎ | 304/363 [00:08<00:03, 19.28it/s]
Loading 0: 86%|████████▌ | 313/363 [00:08<00:02, 24.87it/s]
Loading 0: 89%|████████▊ | 322/363 [00:08<00:01, 30.74it/s]
Loading 0: 91%|█████████ | 331/363 [00:08<00:00, 38.23it/s]
Loading 0: 94%|█████████▎| 340/363 [00:08<00:00, 46.09it/s]
Loading 0: 96%|█████████▌| 349/363 [00:08<00:00, 53.92it/s]
Loading 0: 99%|█████████▊| 358/363 [00:09<00:00, 58.48it/s]
Job sao10k-mn-backyardai-par-1350-v2-mkmlizer completed after 114.67s with status: succeeded
Stopping job with name sao10k-mn-backyardai-par-1350-v2-mkmlizer
Pipeline stage MKMLizer completed in 115.27s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.21s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service sao10k-mn-backyardai-par-1350-v2
Waiting for inference service sao10k-mn-backyardai-par-1350-v2 to be ready
Inference service sao10k-mn-backyardai-par-1350-v2 ready after 140.88518476486206s
Pipeline stage MKMLDeployer completed in 141.82s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.100212574005127s
Received healthy response to inference request in 1.5086450576782227s
Received healthy response to inference request in 1.5785694122314453s
Received healthy response to inference request in 1.445084810256958s
Received healthy response to inference request in 1.509035348892212s
5 requests
0 failed requests
5th percentile: 1.457796859741211
10th percentile: 1.470508909225464
20th percentile: 1.4959330081939697
30th percentile: 1.5087231159210206
40th percentile: 1.5088792324066163
50th percentile: 1.509035348892212
60th percentile: 1.5368489742279052
70th percentile: 1.5646625995635985
80th percentile: 1.6828980445861816
90th percentile: 1.8915553092956543
95th percentile: 1.9958839416503906
99th percentile: 2.07934684753418
mean time: 1.628309440612793
Pipeline stage StressChecker completed in 9.78s
Shutdown handler de-registered
sao10k-mn-backyardai-par_1350_v2 status is now deployed due to DeploymentManager action
sao10k-mn-backyardai-par_1350_v2 status is now inactive due to auto deactivation removed underperforming models
sao10k-mn-backyardai-par_1350_v2 status is now torndown due to DeploymentManager action