Running pipeline stage MKMLizer
Starting job with name cycy233-l3-b-c-v0-c1-v7-mkmlizer
Waiting for job on cycy233-l3-b-c-v0-c1-v7-mkmlizer to finish
cycy233-l3-b-c-v0-c1-v7-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cycy233-l3-b-c-v0-c1-v7-mkmlizer: ║ _____ __ __ ║
cycy233-l3-b-c-v0-c1-v7-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
cycy233-l3-b-c-v0-c1-v7-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
cycy233-l3-b-c-v0-c1-v7-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
cycy233-l3-b-c-v0-c1-v7-mkmlizer: ║ /___/ ║
cycy233-l3-b-c-v0-c1-v7-mkmlizer: ║ ║
cycy233-l3-b-c-v0-c1-v7-mkmlizer: ║ Version: 0.9.7 ║
cycy233-l3-b-c-v0-c1-v7-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
cycy233-l3-b-c-v0-c1-v7-mkmlizer: ║ https://mk1.ai ║
cycy233-l3-b-c-v0-c1-v7-mkmlizer: ║ ║
cycy233-l3-b-c-v0-c1-v7-mkmlizer: ║ The license key for the current software has been verified as ║
cycy233-l3-b-c-v0-c1-v7-mkmlizer: ║ belonging to: ║
cycy233-l3-b-c-v0-c1-v7-mkmlizer: ║ ║
cycy233-l3-b-c-v0-c1-v7-mkmlizer: ║ Chai Research Corp. ║
cycy233-l3-b-c-v0-c1-v7-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
cycy233-l3-b-c-v0-c1-v7-mkmlizer: ║ Expiration: 2024-10-15 23:59:59 ║
cycy233-l3-b-c-v0-c1-v7-mkmlizer: ║ ║
cycy233-l3-b-c-v0-c1-v7-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
cycy233-l3-b-c-v0-c1-v7-mkmlizer: Downloaded to shared memory in 21.300s
cycy233-l3-b-c-v0-c1-v7-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpj1i9dvda, device:0
cycy233-l3-b-c-v0-c1-v7-mkmlizer: Saving flywheel model at /dev/shm/model_cache
Inference service cycy233-l3-e-v2-c1-v25 ready after 111.10350441932678s
Pipeline stage ISVCDeployer completed in 112.33s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.2468812465667725s
cycy233-l3-b-c-v0-c1-v7-mkmlizer: quantized model in 27.527s
cycy233-l3-b-c-v0-c1-v7-mkmlizer: Processed model cycy233/L3-b-c-v0-c1 in 48.827s
cycy233-l3-b-c-v0-c1-v7-mkmlizer: creating bucket guanaco-mkml-models
cycy233-l3-b-c-v0-c1-v7-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cycy233-l3-b-c-v0-c1-v7-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/cycy233-l3-b-c-v0-c1-v7
cycy233-l3-b-c-v0-c1-v7-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/cycy233-l3-b-c-v0-c1-v7/config.json
cycy233-l3-b-c-v0-c1-v7-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/cycy233-l3-b-c-v0-c1-v7/special_tokens_map.json
cycy233-l3-b-c-v0-c1-v7-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/cycy233-l3-b-c-v0-c1-v7/tokenizer_config.json
cycy233-l3-b-c-v0-c1-v7-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/cycy233-l3-b-c-v0-c1-v7/tokenizer.json
Received healthy response to inference request in 1.4162261486053467s
Received healthy response to inference request in 1.4400725364685059s
Received healthy response to inference request in 1.410069227218628s
Received healthy response to inference request in 1.4950249195098877s
5 requests
0 failed requests
5th percentile: 1.4113006114959716
10th percentile: 1.4125319957733153
20th percentile: 1.414994764328003
30th percentile: 1.4209954261779785
40th percentile: 1.4305339813232423
50th percentile: 1.4400725364685059
60th percentile: 1.4620534896850585
70th percentile: 1.4840344429016112
80th percentile: 1.6453961849212648
90th percentile: 1.9461387157440186
95th percentile: 2.0965099811553953
99th percentile: 2.216806993484497
mean time: 1.6016548156738282
Pipeline stage StressChecker completed in 9.45s
cycy233-l3-e-v2-c1_v25 status is now deployed due to DeploymentManager action
cycy233-l3-b-c-v0-c1-v7-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/cycy233-l3-b-c-v0-c1-v7/flywheel_model.0.safetensors
cycy233-l3-b-c-v0-c1-v7-mkmlizer: loading reward model from rirv938/reward_gpt2_medium_preference_24m_e2
cycy233-l3-b-c-v0-c1-v7-mkmlizer:
Loading 0: 0%| | 0/291 [00:00<?, ?it/s]
Loading 0: 2%|▏ | 5/291 [00:00<00:07, 36.07it/s]
Loading 0: 4%|▍ | 13/291 [00:00<00:04, 55.65it/s]
Loading 0: 7%|▋ | 19/291 [00:00<00:05, 47.08it/s]
Loading 0: 8%|▊ | 24/291 [00:00<00:05, 45.98it/s]
Loading 0: 11%|█ | 31/291 [00:00<00:05, 51.96it/s]
Loading 0: 13%|█▎ | 37/291 [00:00<00:05, 45.95it/s]
Loading 0: 14%|█▍ | 42/291 [00:00<00:05, 45.13it/s]
Loading 0: 17%|█▋ | 49/291 [00:01<00:04, 50.14it/s]
Loading 0: 19%|█▉ | 55/291 [00:01<00:05, 44.52it/s]
Loading 0: 21%|██ | 60/291 [00:01<00:05, 43.75it/s]
Loading 0: 23%|██▎ | 67/291 [00:01<00:04, 48.57it/s]
Loading 0: 25%|██▌ | 73/291 [00:01<00:04, 44.54it/s]
Loading 0: 27%|██▋ | 78/291 [00:01<00:04, 42.78it/s]
Loading 0: 29%|██▊ | 83/291 [00:01<00:06, 31.80it/s]
Loading 0: 30%|██▉ | 87/291 [00:02<00:06, 32.15it/s]
Loading 0: 32%|███▏ | 93/291 [00:02<00:05, 38.12it/s]
Loading 0: 34%|███▎ | 98/291 [00:02<00:04, 39.67it/s]
Loading 0: 35%|███▌ | 103/291 [00:02<00:04, 41.39it/s]
Loading 0: 37%|███▋ | 108/291 [00:02<00:04, 43.43it/s]
Loading 0: 39%|███▉ | 113/291 [00:02<00:04, 36.14it/s]
Loading 0: 42%|████▏ | 121/291 [00:02<00:03, 44.58it/s]
Loading 0: 44%|████▎ | 127/291 [00:02<00:03, 42.30it/s]
Loading 0: 45%|████▌ | 132/291 [00:03<00:03, 41.73it/s]
Loading 0: 47%|████▋ | 138/291 [00:03<00:03, 45.80it/s]
Loading 0: 49%|████▉ | 143/291 [00:03<00:03, 45.48it/s]
Loading 0: 51%|█████ | 148/291 [00:03<00:03, 45.26it/s]
Loading 0: 53%|█████▎ | 153/291 [00:03<00:02, 46.29it/s]
Loading 0: 54%|█████▍ | 158/291 [00:03<00:03, 36.86it/s]
Loading 0: 56%|█████▌ | 163/291 [00:03<00:03, 37.07it/s]
Loading 0: 57%|█████▋ | 167/291 [00:04<00:03, 35.43it/s]
Loading 0: 60%|█████▉ | 174/291 [00:04<00:02, 43.63it/s]
Loading 0: 62%|██████▏ | 180/291 [00:04<00:02, 46.41it/s]
Loading 0: 64%|██████▍ | 186/291 [00:04<00:02, 44.89it/s]
Loading 0: 66%|██████▌ | 191/291 [00:04<00:03, 33.16it/s]
Loading 0: 67%|██████▋ | 195/291 [00:04<00:02, 33.61it/s]
Loading 0: 69%|██████▉ | 202/291 [00:04<00:02, 40.64it/s]
Loading 0: 71%|███████▏ | 208/291 [00:04<00:02, 40.97it/s]
Loading 0: 73%|███████▎ | 213/291 [00:05<00:01, 42.19it/s]
Loading 0: 76%|███████▌ | 220/291 [00:05<00:01, 47.45it/s]
Loading 0: 78%|███████▊ | 226/291 [00:05<00:01, 45.14it/s]
Loading 0: 79%|███████▉ | 231/291 [00:05<00:01, 44.85it/s]
Loading 0: 82%|████████▏ | 238/291 [00:05<00:01, 49.71it/s]
Loading 0: 84%|████████▍ | 244/291 [00:05<00:01, 45.91it/s]
Loading 0: 86%|████████▌ | 249/291 [00:05<00:00, 44.40it/s]
Loading 0: 88%|████████▊ | 255/291 [00:05<00:00, 48.26it/s]
Loading 0: 90%|████████▉ | 261/291 [00:06<00:00, 50.94it/s]
Loading 0: 92%|█████████▏| 267/291 [00:06<00:00, 42.75it/s]
Loading 0: 94%|█████████▍| 274/291 [00:06<00:00, 47.85it/s]
Loading 0: 96%|█████████▌| 280/291 [00:06<00:00, 45.50it/s]
Loading 0: 98%|█████████▊| 285/291 [00:06<00:00, 43.49it/s]
Loading 0: 100%|█████████▉| 290/291 [00:12<00:00, 3.04it/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-b-c-v0-c1-v7-mkmlizer: warnings.warn(
cycy233-l3-b-c-v0-c1-v7-mkmlizer: /opt/conda/lib/python3.10/site-packages/transformers/models/auto/tokenization_auto.py:785: FutureWarning: The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers. Please use `token` instead.
cycy233-l3-b-c-v0-c1-v7-mkmlizer: warnings.warn(
cycy233-l3-b-c-v0-c1-v7-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-b-c-v0-c1-v7-mkmlizer: warnings.warn(
cycy233-l3-b-c-v0-c1-v7-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
cycy233-l3-b-c-v0-c1-v7-mkmlizer: Saving duration: 0.338s
cycy233-l3-b-c-v0-c1-v7-mkmlizer: Processed model rirv938/reward_gpt2_medium_preference_24m_e2 in 6.162s
cycy233-l3-b-c-v0-c1-v7-mkmlizer: creating bucket guanaco-reward-models
cycy233-l3-b-c-v0-c1-v7-mkmlizer: Bucket 's3://guanaco-reward-models/' created
cycy233-l3-b-c-v0-c1-v7-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/cycy233-l3-b-c-v0-c1-v7_reward
cycy233-l3-b-c-v0-c1-v7-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/cycy233-l3-b-c-v0-c1-v7_reward/merges.txt
cycy233-l3-b-c-v0-c1-v7-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/cycy233-l3-b-c-v0-c1-v7_reward/vocab.json
cycy233-l3-b-c-v0-c1-v7-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/cycy233-l3-b-c-v0-c1-v7_reward/tokenizer.json
cycy233-l3-b-c-v0-c1-v7-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/cycy233-l3-b-c-v0-c1-v7_reward/reward.tensors
Job cycy233-l3-b-c-v0-c1-v7-mkmlizer completed after 85.66s with status: succeeded
Stopping job with name cycy233-l3-b-c-v0-c1-v7-mkmlizer
Pipeline stage MKMLizer completed in 86.22s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.10s
Running pipeline stage ISVCDeployer
Creating inference service cycy233-l3-b-c-v0-c1-v7
Waiting for inference service cycy233-l3-b-c-v0-c1-v7 to be ready
Inference service cycy233-l3-b-c-v0-c1-v7 ready after 110.79960227012634s
Pipeline stage ISVCDeployer completed in 111.22s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.9808752536773682s
Received healthy response to inference request in 1.260227918624878s
Received healthy response to inference request in 1.2847259044647217s
Received healthy response to inference request in 1.2044613361358643s
Received healthy response to inference request in 1.2794604301452637s
5 requests
0 failed requests
5th percentile: 1.215614652633667
10th percentile: 1.2267679691314697
20th percentile: 1.249074602127075
30th percentile: 1.2640744209289552
40th percentile: 1.2717674255371094
50th percentile: 1.2794604301452637
60th percentile: 1.2815666198730469
70th percentile: 1.28367280960083
80th percentile: 1.423955774307251
90th percentile: 1.7024155139923096
95th percentile: 1.8416453838348388
99th percentile: 1.9530292797088622
mean time: 1.4019501686096192
Pipeline stage StressChecker completed in 8.01s
cycy233-l3-b-c-v0-c1_v7 status is now deployed due to DeploymentManager action
cycy233-l3-b-c-v0-c1_v7 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of cycy233-l3-b-c-v0-c1_v7
Running pipeline stage ISVCDeleter
Checking if service cycy233-l3-b-c-v0-c1-v7 is running
Tearing down inference service cycy233-l3-b-c-v0-c1-v7
Service cycy233-l3-b-c-v0-c1-v7 has been torndown
Pipeline stage ISVCDeleter completed in 5.10s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key cycy233-l3-b-c-v0-c1-v7/config.json from bucket guanaco-mkml-models
Deleting key cycy233-l3-b-c-v0-c1-v7/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key cycy233-l3-b-c-v0-c1-v7/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key cycy233-l3-b-c-v0-c1-v7/tokenizer.json from bucket guanaco-mkml-models
Deleting key cycy233-l3-b-c-v0-c1-v7/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key cycy233-l3-b-c-v0-c1-v7_reward/config.json from bucket guanaco-reward-models
Deleting key cycy233-l3-b-c-v0-c1-v7_reward/merges.txt from bucket guanaco-reward-models
Deleting key cycy233-l3-b-c-v0-c1-v7_reward/reward.tensors from bucket guanaco-reward-models
Deleting key cycy233-l3-b-c-v0-c1-v7_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key cycy233-l3-b-c-v0-c1-v7_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key cycy233-l3-b-c-v0-c1-v7_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key cycy233-l3-b-c-v0-c1-v7_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 5.52s
cycy233-l3-b-c-v0-c1_v7 status is now torndown due to DeploymentManager action