Running pipeline stage MKMLizer
Starting job with name cycy233-l3-s-v1-c4-v2-mkmlizer
Waiting for job on cycy233-l3-s-v1-c4-v2-mkmlizer to finish
Stopping job with name cycy233-l3-s-v1-c4-v2-mkmlizer
%s, retrying in %s seconds...
Starting job with name cycy233-l3-s-v1-c4-v2-mkmlizer
Waiting for job on cycy233-l3-s-v1-c4-v2-mkmlizer to finish
cycy233-l3-s-v1-c4-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cycy233-l3-s-v1-c4-v2-mkmlizer: ║ _____ __ __ ║
cycy233-l3-s-v1-c4-v2-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
cycy233-l3-s-v1-c4-v2-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
cycy233-l3-s-v1-c4-v2-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
cycy233-l3-s-v1-c4-v2-mkmlizer: ║ /___/ ║
cycy233-l3-s-v1-c4-v2-mkmlizer: ║ ║
cycy233-l3-s-v1-c4-v2-mkmlizer: ║ Version: 0.9.9 ║
cycy233-l3-s-v1-c4-v2-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
cycy233-l3-s-v1-c4-v2-mkmlizer: ║ https://mk1.ai ║
cycy233-l3-s-v1-c4-v2-mkmlizer: ║ ║
cycy233-l3-s-v1-c4-v2-mkmlizer: ║ The license key for the current software has been verified as ║
cycy233-l3-s-v1-c4-v2-mkmlizer: ║ belonging to: ║
cycy233-l3-s-v1-c4-v2-mkmlizer: ║ ║
cycy233-l3-s-v1-c4-v2-mkmlizer: ║ Chai Research Corp. ║
cycy233-l3-s-v1-c4-v2-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
cycy233-l3-s-v1-c4-v2-mkmlizer: ║ Expiration: 2024-10-15 23:59:59 ║
cycy233-l3-s-v1-c4-v2-mkmlizer: ║ ║
cycy233-l3-s-v1-c4-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
cycy233-l3-s-v1-c4-v2-mkmlizer: Downloaded to shared memory in 25.252s
cycy233-l3-s-v1-c4-v2-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpbw1yhr2a, device:0
cycy233-l3-s-v1-c4-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
cycy233-l3-s-v1-c4-v2-mkmlizer: quantized model in 25.387s
cycy233-l3-s-v1-c4-v2-mkmlizer: Processed model cycy233/L3-s-v1-c4 in 50.639s
cycy233-l3-s-v1-c4-v2-mkmlizer: creating bucket guanaco-mkml-models
cycy233-l3-s-v1-c4-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cycy233-l3-s-v1-c4-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/cycy233-l3-s-v1-c4-v2
cycy233-l3-s-v1-c4-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/cycy233-l3-s-v1-c4-v2/config.json
cycy233-l3-s-v1-c4-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/cycy233-l3-s-v1-c4-v2/special_tokens_map.json
cycy233-l3-s-v1-c4-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/cycy233-l3-s-v1-c4-v2/tokenizer_config.json
cycy233-l3-s-v1-c4-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/cycy233-l3-s-v1-c4-v2/tokenizer.json
cycy233-l3-s-v1-c4-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/cycy233-l3-s-v1-c4-v2/flywheel_model.0.safetensors
cycy233-l3-s-v1-c4-v2-mkmlizer: loading reward model from rirv938/reward_gpt2_medium_preference_24m_e2
cycy233-l3-s-v1-c4-v2-mkmlizer:
Loading 0: 0%| | 0/291 [00:00<?, ?it/s]
Loading 0: 2%|▏ | 6/291 [00:00<00:04, 59.70it/s]
Loading 0: 5%|▍ | 14/291 [00:00<00:03, 71.62it/s]
Loading 0: 9%|▊ | 25/291 [00:00<00:03, 73.50it/s]
Loading 0: 14%|█▎ | 40/291 [00:00<00:02, 87.62it/s]
Loading 0: 18%|█▊ | 52/291 [00:00<00:02, 86.89it/s]
Loading 0: 21%|██ | 61/291 [00:00<00:02, 87.48it/s]
Loading 0: 26%|██▌ | 76/291 [00:00<00:02, 92.83it/s]
Loading 0: 30%|██▉ | 86/291 [00:02<00:08, 25.37it/s]
Loading 0: 32%|███▏ | 94/291 [00:02<00:06, 30.07it/s]
Loading 0: 35%|███▌ | 103/291 [00:02<00:05, 36.95it/s]
Loading 0: 40%|███▉ | 115/291 [00:02<00:03, 45.89it/s]
Loading 0: 43%|████▎ | 124/291 [00:02<00:03, 52.09it/s]
Loading 0: 46%|████▌ | 133/291 [00:02<00:02, 58.62it/s]
Loading 0: 51%|█████ | 148/291 [00:02<00:02, 71.04it/s]
Loading 0: 55%|█████▍ | 160/291 [00:02<00:01, 73.30it/s]
Loading 0: 58%|█████▊ | 169/291 [00:02<00:01, 75.98it/s]
Loading 0: 61%|██████ | 178/291 [00:03<00:01, 78.15it/s]
Loading 0: 64%|██████▍ | 187/291 [00:04<00:04, 23.63it/s]
Loading 0: 67%|██████▋ | 196/291 [00:04<00:03, 29.43it/s]
Loading 0: 70%|███████ | 205/291 [00:04<00:02, 36.11it/s]
Loading 0: 76%|███████▌ | 220/291 [00:04<00:01, 49.15it/s]
Loading 0: 79%|███████▉ | 230/291 [00:04<00:01, 57.21it/s]
Loading 0: 83%|████████▎ | 241/291 [00:04<00:00, 61.30it/s]
Loading 0: 87%|████████▋ | 254/291 [00:04<00:00, 74.71it/s]
Loading 0: 91%|█████████ | 265/291 [00:05<00:00, 72.16it/s]
Loading 0: 95%|█████████▌| 277/291 [00:05<00:00, 75.87it/s]
Loading 0: 99%|█████████▊| 287/291 [00:05<00:00, 47.74it/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-s-v1-c4-v2-mkmlizer: warnings.warn(
cycy233-l3-s-v1-c4-v2-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-s-v1-c4-v2-mkmlizer: warnings.warn(
cycy233-l3-s-v1-c4-v2-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-s-v1-c4-v2-mkmlizer: warnings.warn(
cycy233-l3-s-v1-c4-v2-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
cycy233-l3-s-v1-c4-v2-mkmlizer: Saving duration: 0.327s
cycy233-l3-s-v1-c4-v2-mkmlizer: Processed model rirv938/reward_gpt2_medium_preference_24m_e2 in 6.791s
cycy233-l3-s-v1-c4-v2-mkmlizer: creating bucket guanaco-reward-models
cycy233-l3-s-v1-c4-v2-mkmlizer: Bucket 's3://guanaco-reward-models/' created
cycy233-l3-s-v1-c4-v2-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/cycy233-l3-s-v1-c4-v2_reward
cycy233-l3-s-v1-c4-v2-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/cycy233-l3-s-v1-c4-v2_reward/config.json
cycy233-l3-s-v1-c4-v2-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/cycy233-l3-s-v1-c4-v2_reward/special_tokens_map.json
cycy233-l3-s-v1-c4-v2-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/cycy233-l3-s-v1-c4-v2_reward/tokenizer_config.json
cycy233-l3-s-v1-c4-v2-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/cycy233-l3-s-v1-c4-v2_reward/merges.txt
cycy233-l3-s-v1-c4-v2-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/cycy233-l3-s-v1-c4-v2_reward/vocab.json
cycy233-l3-s-v1-c4-v2-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/cycy233-l3-s-v1-c4-v2_reward/tokenizer.json
cycy233-l3-s-v1-c4-v2-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/cycy233-l3-s-v1-c4-v2_reward/reward.tensors
Job cycy233-l3-s-v1-c4-v2-mkmlizer completed after 84.43s with status: succeeded
Stopping job with name cycy233-l3-s-v1-c4-v2-mkmlizer
Pipeline stage MKMLizer completed in 86.61s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.09s
Running pipeline stage ISVCDeployer
Creating inference service cycy233-l3-s-v1-c4-v2
Waiting for inference service cycy233-l3-s-v1-c4-v2 to be ready
Inference service cycy233-l3-s-v1-c4-v2 ready after 201.24206972122192s
Pipeline stage ISVCDeployer completed in 202.95s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.0033559799194336s
Received healthy response to inference request in 1.1278595924377441s
Received healthy response to inference request in 1.1142590045928955s
Received healthy response to inference request in 1.0998923778533936s
Received healthy response to inference request in 1.1110999584197998s
5 requests
0 failed requests
5th percentile: 1.1021338939666747
10th percentile: 1.104375410079956
20th percentile: 1.1088584423065186
30th percentile: 1.111731767654419
40th percentile: 1.1129953861236572
50th percentile: 1.1142590045928955
60th percentile: 1.119699239730835
70th percentile: 1.1251394748687744
80th percentile: 1.3029588699340822
90th percentile: 1.653157424926758
95th percentile: 1.8282567024230956
99th percentile: 1.968336124420166
mean time: 1.2912933826446533
Pipeline stage StressChecker completed in 7.19s
cycy233-l3-s-v1-c4_v2 status is now deployed due to DeploymentManager action
cycy233-l3-s-v1-c4_v2 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of cycy233-l3-s-v1-c4_v2
Running pipeline stage ISVCDeleter
Checking if service cycy233-l3-s-v1-c4-v2 is running
Tearing down inference service cycy233-l3-s-v1-c4-v2
Service cycy233-l3-s-v1-c4-v2 has been torndown
Pipeline stage ISVCDeleter completed in 4.48s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key cycy233-l3-s-v1-c4-v2/config.json from bucket guanaco-mkml-models
Deleting key cycy233-l3-s-v1-c4-v2/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key cycy233-l3-s-v1-c4-v2/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key cycy233-l3-s-v1-c4-v2/tokenizer.json from bucket guanaco-mkml-models
Deleting key cycy233-l3-s-v1-c4-v2/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key cycy233-l3-s-v1-c4-v2_reward/config.json from bucket guanaco-reward-models
Deleting key cycy233-l3-s-v1-c4-v2_reward/merges.txt from bucket guanaco-reward-models
Deleting key cycy233-l3-s-v1-c4-v2_reward/reward.tensors from bucket guanaco-reward-models
Deleting key cycy233-l3-s-v1-c4-v2_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key cycy233-l3-s-v1-c4-v2_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key cycy233-l3-s-v1-c4-v2_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key cycy233-l3-s-v1-c4-v2_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 5.80s
cycy233-l3-s-v1-c4_v2 status is now torndown due to DeploymentManager action
cycy233-l3-s-v1-c4_v2 status is now torndown due to DeploymentManager action