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 rinen0721-mistral-dpo-0104-v3-mkmlizer
Waiting for job on rinen0721-mistral-dpo-0104-v3-mkmlizer to finish
rinen0721-mistral-dpo-0104-v3-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
rinen0721-mistral-dpo-0104-v3-mkmlizer: ║ _____ __ __ ║
rinen0721-mistral-dpo-0104-v3-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
rinen0721-mistral-dpo-0104-v3-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
rinen0721-mistral-dpo-0104-v3-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
rinen0721-mistral-dpo-0104-v3-mkmlizer: ║ /___/ ║
rinen0721-mistral-dpo-0104-v3-mkmlizer: ║ ║
rinen0721-mistral-dpo-0104-v3-mkmlizer: ║ Version: 0.11.12 ║
rinen0721-mistral-dpo-0104-v3-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
rinen0721-mistral-dpo-0104-v3-mkmlizer: ║ https://mk1.ai ║
rinen0721-mistral-dpo-0104-v3-mkmlizer: ║ ║
rinen0721-mistral-dpo-0104-v3-mkmlizer: ║ The license key for the current software has been verified as ║
rinen0721-mistral-dpo-0104-v3-mkmlizer: ║ belonging to: ║
rinen0721-mistral-dpo-0104-v3-mkmlizer: ║ ║
rinen0721-mistral-dpo-0104-v3-mkmlizer: ║ Chai Research Corp. ║
rinen0721-mistral-dpo-0104-v3-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
rinen0721-mistral-dpo-0104-v3-mkmlizer: ║ Expiration: 2025-04-15 23:59:59 ║
rinen0721-mistral-dpo-0104-v3-mkmlizer: ║ ║
rinen0721-mistral-dpo-0104-v3-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
rinen0721-mistral-dpo-0104-v3-mkmlizer: Downloaded to shared memory in 46.583s
rinen0721-mistral-dpo-0104-v3-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpc8cpr6_9, device:0
rinen0721-mistral-dpo-0104-v3-mkmlizer: Saving flywheel model at /dev/shm/model_cache
rinen0721-mistral-dpo-0104-v3-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.
rinen0721-mistral-dpo-0104-v3-mkmlizer: tensors = torch.load(model_shard_filename, map_location=torch.device(self.device), mmap=True)
rinen0721-mistral-dpo-0104-v3-mkmlizer: quantized model in 36.604s
rinen0721-mistral-dpo-0104-v3-mkmlizer: Processed model rinen0721/Mistral-dpo-0104 in 83.187s
rinen0721-mistral-dpo-0104-v3-mkmlizer: creating bucket guanaco-mkml-models
rinen0721-mistral-dpo-0104-v3-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/rinen0721-mistral-dpo-0104-v3/config.json
rinen0721-mistral-dpo-0104-v3-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/rinen0721-mistral-dpo-0104-v3/special_tokens_map.json
rinen0721-mistral-dpo-0104-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/rinen0721-mistral-dpo-0104-v3/tokenizer_config.json
rinen0721-mistral-dpo-0104-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/rinen0721-mistral-dpo-0104-v3/tokenizer.json
rinen0721-mistral-dpo-0104-v3-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/rinen0721-mistral-dpo-0104-v3/flywheel_model.0.safetensors
rinen0721-mistral-dpo-0104-v3-mkmlizer:
Loading 0: 0%| | 0/363 [00:00<?, ?it/s]
Loading 0: 2%|▏ | 7/363 [00:00<00:07, 48.26it/s]
Loading 0: 6%|▌ | 22/363 [00:00<00:04, 80.69it/s]
Loading 0: 9%|▊ | 31/363 [00:00<00:04, 81.56it/s]
Loading 0: 12%|█▏ | 42/363 [00:00<00:03, 90.75it/s]
Loading 0: 14%|█▍ | 52/363 [00:00<00:03, 80.44it/s]
Loading 0: 17%|█▋ | 61/363 [00:01<00:15, 19.78it/s]
Loading 0: 19%|█▉ | 70/363 [00:01<00:11, 25.92it/s]
Loading 0: 22%|██▏ | 79/363 [00:02<00:08, 32.72it/s]
Loading 0: 24%|██▍ | 88/363 [00:02<00:06, 39.67it/s]
Loading 0: 27%|██▋ | 97/363 [00:02<00:05, 47.08it/s]
Loading 0: 29%|██▉ | 106/363 [00:02<00:04, 53.95it/s]
Loading 0: 32%|███▏ | 115/363 [00:02<00:04, 59.50it/s]
Loading 0: 34%|███▍ | 124/363 [00:02<00:03, 63.46it/s]
Loading 0: 37%|███▋ | 133/363 [00:02<00:03, 68.80it/s]
Loading 0: 39%|███▉ | 142/363 [00:03<00:10, 20.55it/s]
Loading 0: 42%|████▏ | 151/363 [00:04<00:08, 26.26it/s]
Loading 0: 44%|████▍ | 160/363 [00:04<00:06, 32.97it/s]
Loading 0: 47%|████▋ | 169/363 [00:04<00:04, 40.16it/s]
Loading 0: 49%|████▉ | 178/363 [00:04<00:03, 47.98it/s]
Loading 0: 52%|█████▏ | 187/363 [00:04<00:03, 52.69it/s]
Loading 0: 54%|█████▍ | 196/363 [00:04<00:02, 58.85it/s]
Loading 0: 56%|█████▋ | 205/363 [00:04<00:02, 64.49it/s]
Loading 0: 59%|█████▉ | 214/363 [00:04<00:02, 67.40it/s]
Loading 0: 61%|██████▏ | 223/363 [00:05<00:06, 20.34it/s]
Loading 0: 64%|██████▍ | 232/363 [00:06<00:04, 26.48it/s]
Loading 0: 67%|██████▋ | 242/363 [00:06<00:03, 34.60it/s]
Loading 0: 69%|██████▉ | 250/363 [00:06<00:02, 40.62it/s]
Loading 0: 71%|███████▏ | 259/363 [00:06<00:02, 47.36it/s]
Loading 0: 74%|███████▍ | 269/363 [00:06<00:01, 56.78it/s]
Loading 0: 77%|███████▋ | 279/363 [00:06<00:01, 65.77it/s]
Loading 0: 79%|███████▉ | 288/363 [00:06<00:01, 70.93it/s]
Loading 0: 82%|████████▏ | 297/363 [00:06<00:00, 72.37it/s]
Loading 0: 84%|████████▍ | 306/363 [00:07<00:02, 21.24it/s]
Loading 0: 86%|████████▌ | 313/363 [00:08<00:02, 24.92it/s]
Loading 0: 89%|████████▊ | 322/363 [00:08<00:01, 30.86it/s]
Loading 0: 91%|█████████ | 331/363 [00:08<00:00, 37.67it/s]
Loading 0: 94%|█████████▎| 340/363 [00:08<00:00, 45.00it/s]
Loading 0: 96%|█████████▌| 349/363 [00:08<00:00, 51.14it/s]
Loading 0: 99%|█████████▊| 358/363 [00:08<00:00, 57.33it/s]
Job rinen0721-mistral-dpo-0104-v3-mkmlizer completed after 104.36s with status: succeeded
Stopping job with name rinen0721-mistral-dpo-0104-v3-mkmlizer
Pipeline stage MKMLizer completed in 104.86s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.16s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service rinen0721-mistral-dpo-0104-v3
Waiting for inference service rinen0721-mistral-dpo-0104-v3 to be ready
Failed to get response for submission riverise-lima-safe-sft_v2: HTTPConnectionPool(host='riverise-lima-safe-sft-v2-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
Failed to get response for submission riverise-lima-safe-sft_v1: HTTPConnectionPool(host='riverise-lima-safe-sft-v1-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
Failed to get response for submission riverise-lima-safe-sft_v1: HTTPConnectionPool(host='riverise-lima-safe-sft-v1-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
Failed to get response for submission riverise-lima-safe-sft_v1: HTTPConnectionPool(host='riverise-lima-safe-sft-v1-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
Failed to get response for submission riverise-lima-safe-sft_v2: HTTPConnectionPool(host='riverise-lima-safe-sft-v2-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
Failed to get response for submission riverise-lima-safe-sft_v1: HTTPConnectionPool(host='riverise-lima-safe-sft-v1-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
Failed to get response for submission riverise-lima-safe-sft_v2: HTTPConnectionPool(host='riverise-lima-safe-sft-v2-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
Failed to get response for submission riverise-lima-safe-sft_v2: HTTPConnectionPool(host='riverise-lima-safe-sft-v2-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
Failed to get response for submission riverise-lima-safe-sft_v2: HTTPConnectionPool(host='riverise-lima-safe-sft-v2-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
Failed to get response for submission riverise-lima-safe-sft_v2: HTTPConnectionPool(host='riverise-lima-safe-sft-v2-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
Inference service rinen0721-mistral-dpo-0104-v3 ready after 422.0140333175659s
Pipeline stage MKMLDeployer completed in 422.55s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.5033438205718994s
Received healthy response to inference request in 1.414628505706787s
Received healthy response to inference request in 1.6331639289855957s
Received healthy response to inference request in 1.7161672115325928s
Received healthy response to inference request in 1.8241689205169678s
5 requests
0 failed requests
5th percentile: 1.4583355903625488
10th percentile: 1.5020426750183105
20th percentile: 1.589456844329834
30th percentile: 1.6497645854949952
40th percentile: 1.6829658985137939
50th percentile: 1.7161672115325928
60th percentile: 1.7593678951263427
70th percentile: 1.8025685787200927
80th percentile: 1.9600039005279541
90th percentile: 2.2316738605499267
95th percentile: 2.367508840560913
99th percentile: 2.476176824569702
mean time: 1.8182944774627685
Pipeline stage StressChecker completed in 10.52s
run pipeline stage %s
Failed to get response for submission riverise-lima-safe-sft_v2: HTTPConnectionPool(host='riverise-lima-safe-sft-v2-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
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 0.91s
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 0.84s
Shutdown handler de-registered
rinen0721-mistral-dpo-0104_v3 status is now deployed due to DeploymentManager action
Shutdown handler registered
run pipeline %s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Skipping teardown as no inference service was successfully deployed
Pipeline stage MKMLProfilerDeleter completed in 0.13s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.10s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service rinen0721-mistral-dpo-0104-v3-profiler
Waiting for inference service rinen0721-mistral-dpo-0104-v3-profiler to be ready
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 2828.26s
Shutdown handler de-registered
rinen0721-mistral-dpo-0104_v3 status is now inactive due to auto deactivation removed underperforming models
rinen0721-mistral-dpo-0104_v3 status is now torndown due to DeploymentManager action
rinen0721-mistral-dpo-0104_v3 status is now torndown due to DeploymentManager action
rinen0721-mistral-dpo-0104_v3 status is now torndown due to DeploymentManager action