Running pipeline stage MKMLizer
Starting job with name cycy233-l3-ba-e-v0-c1-v10-mkmlizer
Waiting for job on cycy233-l3-ba-e-v0-c1-v10-mkmlizer to finish
cycy233-l3-ba-e-v0-c1-v10-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cycy233-l3-ba-e-v0-c1-v10-mkmlizer: ║ _____ __ __ ║
cycy233-l3-ba-e-v0-c1-v10-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
cycy233-l3-ba-e-v0-c1-v10-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
cycy233-l3-ba-e-v0-c1-v10-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
cycy233-l3-ba-e-v0-c1-v10-mkmlizer: ║ /___/ ║
cycy233-l3-ba-e-v0-c1-v10-mkmlizer: ║ ║
cycy233-l3-ba-e-v0-c1-v10-mkmlizer: ║ Version: 0.9.7 ║
cycy233-l3-ba-e-v0-c1-v10-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
cycy233-l3-ba-e-v0-c1-v10-mkmlizer: ║ https://mk1.ai ║
cycy233-l3-ba-e-v0-c1-v10-mkmlizer: ║ ║
cycy233-l3-ba-e-v0-c1-v10-mkmlizer: ║ The license key for the current software has been verified as ║
cycy233-l3-ba-e-v0-c1-v10-mkmlizer: ║ belonging to: ║
cycy233-l3-ba-e-v0-c1-v10-mkmlizer: ║ ║
cycy233-l3-ba-e-v0-c1-v10-mkmlizer: ║ Chai Research Corp. ║
cycy233-l3-ba-e-v0-c1-v10-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
cycy233-l3-ba-e-v0-c1-v10-mkmlizer: ║ Expiration: 2024-10-15 23:59:59 ║
cycy233-l3-ba-e-v0-c1-v10-mkmlizer: ║ ║
cycy233-l3-ba-e-v0-c1-v10-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
cycy233-l3-ba-e-v0-c1-v10-mkmlizer: Downloaded to shared memory in 31.076s
cycy233-l3-ba-e-v0-c1-v10-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpntsvlvma, device:0
cycy233-l3-ba-e-v0-c1-v10-mkmlizer: Saving flywheel model at /dev/shm/model_cache
cycy233-l3-ba-e-v0-c1-v10-mkmlizer: quantized model in 26.318s
cycy233-l3-ba-e-v0-c1-v10-mkmlizer: Processed model cycy233/L3-ba-e-v0-c1 in 57.394s
cycy233-l3-ba-e-v0-c1-v10-mkmlizer: creating bucket guanaco-mkml-models
cycy233-l3-ba-e-v0-c1-v10-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cycy233-l3-ba-e-v0-c1-v10-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/cycy233-l3-ba-e-v0-c1-v10
cycy233-l3-ba-e-v0-c1-v10-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/cycy233-l3-ba-e-v0-c1-v10/config.json
cycy233-l3-ba-e-v0-c1-v10-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/cycy233-l3-ba-e-v0-c1-v10/special_tokens_map.json
cycy233-l3-ba-e-v0-c1-v10-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/cycy233-l3-ba-e-v0-c1-v10/tokenizer_config.json
cycy233-l3-ba-e-v0-c1-v10-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/cycy233-l3-ba-e-v0-c1-v10/tokenizer.json
cycy233-l3-ba-e-v0-c1-v10-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/cycy233-l3-ba-e-v0-c1-v10/flywheel_model.0.safetensors
cycy233-l3-ba-e-v0-c1-v10-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
cycy233-l3-ba-e-v0-c1-v10-mkmlizer:
Loading 0: 0%| | 0/291 [00:00<?, ?it/s]
Loading 0: 2%|▏ | 5/291 [00:00<00:08, 32.23it/s]
Loading 0: 4%|▍ | 13/291 [00:00<00:05, 54.39it/s]
Loading 0: 7%|▋ | 19/291 [00:00<00:05, 47.81it/s]
Loading 0: 9%|▊ | 25/291 [00:00<00:05, 50.18it/s]
Loading 0: 11%|█ | 32/291 [00:00<00:05, 45.20it/s]
Loading 0: 14%|█▎ | 40/291 [00:00<00:04, 53.26it/s]
Loading 0: 16%|█▌ | 46/291 [00:00<00:05, 46.56it/s]
Loading 0: 18%|█▊ | 51/291 [00:01<00:05, 46.16it/s]
Loading 0: 20%|█▉ | 58/291 [00:01<00:04, 50.05it/s]
Loading 0: 22%|██▏ | 64/291 [00:01<00:04, 47.30it/s]
Loading 0: 24%|██▎ | 69/291 [00:01<00:04, 45.97it/s]
Loading 0: 26%|██▌ | 76/291 [00:01<00:04, 50.53it/s]
Loading 0: 28%|██▊ | 82/291 [00:01<00:04, 45.96it/s]
Loading 0: 30%|██▉ | 87/291 [00:02<00:06, 31.09it/s]
Loading 0: 32%|███▏ | 93/291 [00:02<00:05, 36.10it/s]
Loading 0: 34%|███▎ | 98/291 [00:02<00:05, 37.03it/s]
Loading 0: 35%|███▌ | 103/291 [00:02<00:04, 39.62it/s]
Loading 0: 37%|███▋ | 108/291 [00:02<00:04, 41.10it/s]
Loading 0: 39%|███▉ | 113/291 [00:02<00:05, 34.88it/s]
Loading 0: 42%|████▏ | 121/291 [00:02<00:03, 43.96it/s]
Loading 0: 44%|████▎ | 127/291 [00:02<00:03, 43.07it/s]
Loading 0: 45%|████▌ | 132/291 [00:03<00:03, 42.18it/s]
Loading 0: 48%|████▊ | 139/291 [00:03<00:03, 48.45it/s]
Loading 0: 50%|████▉ | 145/291 [00:03<00:03, 44.83it/s]
Loading 0: 52%|█████▏ | 150/291 [00:03<00:03, 44.26it/s]
Loading 0: 54%|█████▍ | 158/291 [00:03<00:02, 45.49it/s]
Loading 0: 57%|█████▋ | 166/291 [00:03<00:02, 52.90it/s]
Loading 0: 59%|█████▉ | 172/291 [00:03<00:02, 47.92it/s]
Loading 0: 62%|██████▏ | 179/291 [00:03<00:02, 51.92it/s]
Loading 0: 64%|██████▍ | 186/291 [00:04<00:02, 51.09it/s]
Loading 0: 66%|██████▌ | 192/291 [00:04<00:02, 36.88it/s]
Loading 0: 68%|██████▊ | 199/291 [00:04<00:02, 39.84it/s]
Loading 0: 70%|███████ | 205/291 [00:04<00:01, 43.77it/s]
Loading 0: 73%|███████▎ | 212/291 [00:04<00:01, 42.12it/s]
Loading 0: 75%|███████▌ | 219/291 [00:04<00:01, 47.94it/s]
Loading 0: 77%|███████▋ | 225/291 [00:05<00:01, 49.91it/s]
Loading 0: 79%|███████▉ | 231/291 [00:05<00:01, 45.69it/s]
Loading 0: 82%|████████▏ | 238/291 [00:05<00:01, 50.52it/s]
Loading 0: 84%|████████▍ | 244/291 [00:05<00:00, 49.60it/s]
Loading 0: 86%|████████▌ | 250/291 [00:05<00:00, 51.58it/s]
Loading 0: 88%|████████▊ | 257/291 [00:05<00:00, 48.93it/s]
Loading 0: 91%|█████████ | 265/291 [00:05<00:00, 55.62it/s]
Loading 0: 93%|█████████▎| 271/291 [00:05<00:00, 53.37it/s]
Loading 0: 95%|█████████▌| 277/291 [00:06<00:00, 37.28it/s]
Loading 0: 97%|█████████▋| 282/291 [00:06<00:00, 35.33it/s]
Loading 0: 99%|█████████▊| 287/291 [00:11<00:01, 3.30it/s]
/opt/conda/lib/python3.10/site-packages/transformers/models/auto/configuration_auto.py:957: FutureWarning: The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers. Please use `token` instead.
cycy233-l3-ba-e-v0-c1-v10-mkmlizer: warnings.warn(
cycy233-l3-ba-e-v0-c1-v10-mkmlizer: /opt/conda/lib/python3.10/site-packages/transformers/models/auto/auto_factory.py:469: FutureWarning: The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers. Please use `token` instead.
cycy233-l3-ba-e-v0-c1-v10-mkmlizer: warnings.warn(
cycy233-l3-ba-e-v0-c1-v10-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
cycy233-l3-ba-e-v0-c1-v10-mkmlizer: Saving duration: 0.352s
cycy233-l3-ba-e-v0-c1-v10-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 6.466s
cycy233-l3-ba-e-v0-c1-v10-mkmlizer: creating bucket guanaco-reward-models
cycy233-l3-ba-e-v0-c1-v10-mkmlizer: Bucket 's3://guanaco-reward-models/' created
cycy233-l3-ba-e-v0-c1-v10-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/cycy233-l3-ba-e-v0-c1-v10_reward
cycy233-l3-ba-e-v0-c1-v10-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/cycy233-l3-ba-e-v0-c1-v10_reward/config.json
cycy233-l3-ba-e-v0-c1-v10-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/cycy233-l3-ba-e-v0-c1-v10_reward/special_tokens_map.json
cycy233-l3-ba-e-v0-c1-v10-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/cycy233-l3-ba-e-v0-c1-v10_reward/tokenizer_config.json
cycy233-l3-ba-e-v0-c1-v10-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/cycy233-l3-ba-e-v0-c1-v10_reward/merges.txt
cycy233-l3-ba-e-v0-c1-v10-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/cycy233-l3-ba-e-v0-c1-v10_reward/vocab.json
cycy233-l3-ba-e-v0-c1-v10-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/cycy233-l3-ba-e-v0-c1-v10_reward/tokenizer.json
cycy233-l3-ba-e-v0-c1-v10-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/cycy233-l3-ba-e-v0-c1-v10_reward/reward.tensors
Job cycy233-l3-ba-e-v0-c1-v10-mkmlizer completed after 94.91s with status: succeeded
Stopping job with name cycy233-l3-ba-e-v0-c1-v10-mkmlizer
Pipeline stage MKMLizer completed in 96.10s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.10s
Running pipeline stage ISVCDeployer
Creating inference service cycy233-l3-ba-e-v0-c1-v10
Waiting for inference service cycy233-l3-ba-e-v0-c1-v10 to be ready
Inference service cycy233-l3-ba-e-v0-c1-v10 ready after 80.63821244239807s
Pipeline stage ISVCDeployer completed in 82.32s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.015784502029419s
Received healthy response to inference request in 1.1433799266815186s
Received healthy response to inference request in 1.014981746673584s
Received healthy response to inference request in 0.9910461902618408s
Received healthy response to inference request in 1.0823538303375244s
5 requests
0 failed requests
5th percentile: 0.9958333015441895
10th percentile: 1.0006204128265381
20th percentile: 1.0101946353912354
30th percentile: 1.028456163406372
40th percentile: 1.0554049968719483
50th percentile: 1.0823538303375244
60th percentile: 1.106764268875122
70th percentile: 1.1311747074127196
80th percentile: 1.3178608417510989
90th percentile: 1.6668226718902588
95th percentile: 1.8413035869598386
99th percentile: 1.9808883190155029
mean time: 1.2495092391967773
Pipeline stage StressChecker completed in 6.93s
cycy233-l3-ba-e-v0-c1_v10 status is now deployed due to DeploymentManager action
cycy233-l3-ba-e-v0-c1_v10 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of cycy233-l3-ba-e-v0-c1_v10
Running pipeline stage ISVCDeleter
Checking if service cycy233-l3-ba-e-v0-c1-v10 is running
Tearing down inference service cycy233-l3-ba-e-v0-c1-v10
Service cycy233-l3-ba-e-v0-c1-v10 has been torndown
Pipeline stage ISVCDeleter completed in 5.66s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key cycy233-l3-ba-e-v0-c1-v10/config.json from bucket guanaco-mkml-models
Deleting key cycy233-l3-ba-e-v0-c1-v10/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key cycy233-l3-ba-e-v0-c1-v10/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key cycy233-l3-ba-e-v0-c1-v10/tokenizer.json from bucket guanaco-mkml-models
Deleting key cycy233-l3-ba-e-v0-c1-v10/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key cycy233-l3-ba-e-v0-c1-v10_reward/config.json from bucket guanaco-reward-models
Deleting key cycy233-l3-ba-e-v0-c1-v10_reward/merges.txt from bucket guanaco-reward-models
Deleting key cycy233-l3-ba-e-v0-c1-v10_reward/reward.tensors from bucket guanaco-reward-models
Deleting key cycy233-l3-ba-e-v0-c1-v10_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key cycy233-l3-ba-e-v0-c1-v10_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key cycy233-l3-ba-e-v0-c1-v10_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key cycy233-l3-ba-e-v0-c1-v10_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 5.38s
cycy233-l3-ba-e-v0-c1_v10 status is now torndown due to DeploymentManager action