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 gryphe-mythomax-l2-13b-v51-mkmlizer
Waiting for job on gryphe-mythomax-l2-13b-v51-mkmlizer to finish
gryphe-mythomax-l2-13b-v51-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
gryphe-mythomax-l2-13b-v51-mkmlizer: ║ _____ __ __ ║
gryphe-mythomax-l2-13b-v51-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
gryphe-mythomax-l2-13b-v51-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
gryphe-mythomax-l2-13b-v51-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
gryphe-mythomax-l2-13b-v51-mkmlizer: ║ /___/ ║
gryphe-mythomax-l2-13b-v51-mkmlizer: ║ ║
gryphe-mythomax-l2-13b-v51-mkmlizer: ║ Version: 0.11.28 ║
gryphe-mythomax-l2-13b-v51-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
gryphe-mythomax-l2-13b-v51-mkmlizer: ║ https://mk1.ai ║
gryphe-mythomax-l2-13b-v51-mkmlizer: ║ ║
gryphe-mythomax-l2-13b-v51-mkmlizer: ║ The license key for the current software has been verified as ║
gryphe-mythomax-l2-13b-v51-mkmlizer: ║ belonging to: ║
gryphe-mythomax-l2-13b-v51-mkmlizer: ║ ║
gryphe-mythomax-l2-13b-v51-mkmlizer: ║ Chai Research Corp. ║
gryphe-mythomax-l2-13b-v51-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
gryphe-mythomax-l2-13b-v51-mkmlizer: ║ Expiration: 2025-01-15 23:59:59 ║
gryphe-mythomax-l2-13b-v51-mkmlizer: ║ ║
gryphe-mythomax-l2-13b-v51-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
Connection pool is full, discarding connection: %s. Connection pool size: %s
gryphe-mythomax-l2-13b-v51-mkmlizer: Downloaded to shared memory in 173.965s
gryphe-mythomax-l2-13b-v51-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp5nvp5e94, device:0
gryphe-mythomax-l2-13b-v51-mkmlizer: Saving flywheel model at /dev/shm/model_cache
gryphe-mythomax-l2-13b-v51-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.
gryphe-mythomax-l2-13b-v51-mkmlizer: tensors = torch.load(model_shard_filename, map_location=torch.device(self.device), mmap=True)
gryphe-mythomax-l2-13b-v51-mkmlizer: quantized model in 30.195s
gryphe-mythomax-l2-13b-v51-mkmlizer: Processed model Gryphe/MythoMax-L2-13b in 204.160s
gryphe-mythomax-l2-13b-v51-mkmlizer: creating bucket guanaco-mkml-models
gryphe-mythomax-l2-13b-v51-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
gryphe-mythomax-l2-13b-v51-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/gryphe-mythomax-l2-13b-v51
gryphe-mythomax-l2-13b-v51-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/gryphe-mythomax-l2-13b-v51/config.json
gryphe-mythomax-l2-13b-v51-mkmlizer: cp /dev/shm/model_cache/added_tokens.json s3://guanaco-mkml-models/gryphe-mythomax-l2-13b-v51/added_tokens.json
gryphe-mythomax-l2-13b-v51-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/gryphe-mythomax-l2-13b-v51/special_tokens_map.json
gryphe-mythomax-l2-13b-v51-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/gryphe-mythomax-l2-13b-v51/tokenizer_config.json
gryphe-mythomax-l2-13b-v51-mkmlizer: cp /dev/shm/model_cache/tokenizer.model s3://guanaco-mkml-models/gryphe-mythomax-l2-13b-v51/tokenizer.model
gryphe-mythomax-l2-13b-v51-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/gryphe-mythomax-l2-13b-v51/tokenizer.json
gryphe-mythomax-l2-13b-v51-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/gryphe-mythomax-l2-13b-v51/flywheel_model.0.safetensors
gryphe-mythomax-l2-13b-v51-mkmlizer:
Loading 0: 0%| | 0/363 [00:00<?, ?it/s]
Loading 0: 1%| | 4/363 [00:00<00:10, 34.35it/s]
Loading 0: 4%|▎ | 13/363 [00:00<00:05, 61.31it/s]
Loading 0: 6%|▌ | 22/363 [00:00<00:04, 69.46it/s]
Loading 0: 8%|▊ | 29/363 [00:00<00:13, 24.52it/s]
Loading 0: 9%|▉ | 34/363 [00:01<00:12, 26.93it/s]
Loading 0: 12%|█▏ | 43/363 [00:01<00:09, 35.00it/s]
Loading 0: 14%|█▍ | 52/363 [00:01<00:07, 43.40it/s]
Loading 0: 16%|█▌ | 58/363 [00:01<00:13, 23.40it/s]
Loading 0: 18%|█▊ | 67/363 [00:02<00:09, 30.80it/s]
Loading 0: 21%|██ | 76/363 [00:02<00:07, 37.88it/s]
Loading 0: 23%|██▎ | 85/363 [00:02<00:06, 45.20it/s]
Loading 0: 25%|██▌ | 92/363 [00:02<00:09, 27.36it/s]
Loading 0: 27%|██▋ | 97/363 [00:02<00:09, 28.80it/s]
Loading 0: 29%|██▉ | 106/363 [00:03<00:07, 36.47it/s]
Loading 0: 31%|███▏ | 114/363 [00:03<00:10, 24.14it/s]
Loading 0: 33%|███▎ | 121/363 [00:03<00:08, 27.80it/s]
Loading 0: 36%|███▌ | 130/363 [00:03<00:06, 35.70it/s]
Loading 0: 38%|███▊ | 139/363 [00:04<00:05, 43.59it/s]
Loading 0: 40%|████ | 146/363 [00:04<00:08, 26.17it/s]
Loading 0: 42%|████▏ | 151/363 [00:04<00:07, 28.94it/s]
Loading 0: 44%|████▍ | 160/363 [00:04<00:05, 37.14it/s]
Loading 0: 47%|████▋ | 169/363 [00:05<00:04, 43.28it/s]
Loading 0: 48%|████▊ | 175/363 [00:05<00:07, 24.85it/s]
Loading 0: 51%|█████ | 184/363 [00:05<00:05, 32.49it/s]
Loading 0: 53%|█████▎ | 193/363 [00:05<00:04, 40.48it/s]
Loading 0: 55%|█████▌ | 200/363 [00:06<00:06, 26.18it/s]
Loading 0: 56%|█████▋ | 205/363 [00:06<00:05, 26.90it/s]
Loading 0: 59%|█████▉ | 214/363 [00:06<00:04, 34.63it/s]
Loading 0: 61%|██████▏ | 223/363 [00:06<00:03, 42.83it/s]
Loading 0: 63%|██████▎ | 230/363 [00:07<00:04, 27.48it/s]
Loading 0: 66%|██████▌ | 238/363 [00:07<00:03, 32.04it/s]
Loading 0: 68%|██████▊ | 247/363 [00:07<00:02, 38.89it/s]
Loading 0: 71%|███████ | 256/363 [00:07<00:02, 46.88it/s]
Loading 0: 72%|███████▏ | 263/363 [00:08<00:03, 28.30it/s]
Loading 0: 74%|███████▍ | 268/363 [00:08<00:03, 30.94it/s]
Loading 0: 76%|███████▋ | 277/363 [00:08<00:02, 39.89it/s]
Loading 0: 79%|███████▉ | 286/363 [00:08<00:03, 25.05it/s]
Loading 0: 81%|████████▏ | 295/363 [00:09<00:02, 31.44it/s]
Loading 0: 84%|████████▎ | 304/363 [00:09<00:01, 37.30it/s]
Loading 0: 86%|████████▌ | 313/363 [00:09<00:01, 42.70it/s]
Loading 0: 88%|████████▊ | 319/363 [00:09<00:01, 25.73it/s]
Loading 0: 90%|█████████ | 328/363 [00:10<00:01, 32.87it/s]
Loading 0: 93%|█████████▎| 337/363 [00:10<00:00, 40.30it/s]
Loading 0: 95%|█████████▍| 344/363 [00:10<00:00, 28.99it/s]
Loading 0: 96%|█████████▌| 349/363 [00:10<00:00, 30.76it/s]
Loading 0: 99%|█████████▊| 358/363 [00:10<00:00, 38.14it/s]
Job gryphe-mythomax-l2-13b-v51-mkmlizer completed after 229.09s with status: succeeded
Stopping job with name gryphe-mythomax-l2-13b-v51-mkmlizer
Pipeline stage MKMLizer completed in 229.69s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.19s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service gryphe-mythomax-l2-13b-v51
Waiting for inference service gryphe-mythomax-l2-13b-v51 to be ready
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Inference service gryphe-mythomax-l2-13b-v51 ready after 170.6156120300293s
Pipeline stage MKMLDeployer completed in 171.18s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.3926336765289307s
Received healthy response to inference request in 1.701073169708252s
Received healthy response to inference request in 1.6116538047790527s
Received healthy response to inference request in 1.9270927906036377s
Received healthy response to inference request in 1.6084315776824951s
5 requests
0 failed requests
5th percentile: 1.6090760231018066
10th percentile: 1.6097204685211182
20th percentile: 1.6110093593597412
30th percentile: 1.6295376777648927
40th percentile: 1.6653054237365723
50th percentile: 1.701073169708252
60th percentile: 1.7914810180664062
70th percentile: 1.8818888664245605
80th percentile: 2.0202009677886963
90th percentile: 2.2064173221588135
95th percentile: 2.299525499343872
99th percentile: 2.3740120410919188
mean time: 1.8481770038604737
Pipeline stage StressChecker completed in 10.83s
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 2.76s
Shutdown handler de-registered
gryphe-mythomax-l2-13b_v51 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 3036.10s
Shutdown handler de-registered
gryphe-mythomax-l2-13b_v51 status is now inactive due to auto deactivation removed underperforming models
gryphe-mythomax-l2-13b_v51 status is now torndown due to DeploymentManager action