Running pipeline stage MKMLizer
Starting job with name chaoticneutrals-poppy-po-3816-v4-mkmlizer
Waiting for job on chaoticneutrals-poppy-po-3816-v4-mkmlizer to finish
chaoticneutrals-poppy-po-3816-v4-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaoticneutrals-poppy-po-3816-v4-mkmlizer: ║ _____ __ __ ║
chaoticneutrals-poppy-po-3816-v4-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
chaoticneutrals-poppy-po-3816-v4-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
chaoticneutrals-poppy-po-3816-v4-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
chaoticneutrals-poppy-po-3816-v4-mkmlizer: ║ /___/ ║
chaoticneutrals-poppy-po-3816-v4-mkmlizer: ║ ║
chaoticneutrals-poppy-po-3816-v4-mkmlizer: ║ Version: 0.8.14 ║
chaoticneutrals-poppy-po-3816-v4-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
chaoticneutrals-poppy-po-3816-v4-mkmlizer: ║ https://mk1.ai ║
chaoticneutrals-poppy-po-3816-v4-mkmlizer: ║ ║
chaoticneutrals-poppy-po-3816-v4-mkmlizer: ║ The license key for the current software has been verified as ║
chaoticneutrals-poppy-po-3816-v4-mkmlizer: ║ belonging to: ║
chaoticneutrals-poppy-po-3816-v4-mkmlizer: ║ ║
chaoticneutrals-poppy-po-3816-v4-mkmlizer: ║ Chai Research Corp. ║
chaoticneutrals-poppy-po-3816-v4-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
chaoticneutrals-poppy-po-3816-v4-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
chaoticneutrals-poppy-po-3816-v4-mkmlizer: ║ ║
chaoticneutrals-poppy-po-3816-v4-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaoticneutrals-poppy-po-3816-v4-mkmlizer: /opt/conda/lib/python3.10/site-packages/huggingface_hub/utils/_deprecation.py:131: FutureWarning: 'list_files_info' (from 'huggingface_hub.hf_api') is deprecated and will be removed from version '0.23'. Use `list_repo_tree` and `get_paths_info` instead.
chaoticneutrals-poppy-po-3816-v4-mkmlizer: warnings.warn(warning_message, FutureWarning)
chaoticneutrals-poppy-po-3816-v4-mkmlizer: Downloaded to shared memory in 13.216s
chaoticneutrals-poppy-po-3816-v4-mkmlizer: quantizing model to /dev/shm/model_cache
chaoticneutrals-poppy-po-3816-v4-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaoticneutrals-poppy-po-3816-v4-mkmlizer:
Loading 0: 0%| | 0/291 [00:00<?, ?it/s]
Loading 0: 7%|▋ | 20/291 [00:00<00:01, 189.43it/s]
Loading 0: 14%|█▍ | 42/291 [00:00<00:02, 106.96it/s]
Loading 0: 21%|██ | 60/291 [00:00<00:01, 128.30it/s]
Loading 0: 27%|██▋ | 80/291 [00:00<00:02, 104.26it/s]
Loading 0: 34%|███▍ | 99/291 [00:00<00:01, 121.22it/s]
Loading 0: 41%|████ | 120/291 [00:00<00:01, 142.65it/s]
Loading 0: 47%|████▋ | 137/291 [00:10<00:24, 6.21it/s]
Loading 0: 51%|█████ | 149/291 [00:10<00:18, 7.79it/s]
Loading 0: 60%|█████▉ | 174/291 [00:10<00:09, 12.77it/s]
Loading 0: 65%|██████▍ | 188/291 [00:10<00:06, 15.76it/s]
Loading 0: 73%|███████▎ | 212/291 [00:10<00:03, 24.16it/s]
Loading 0: 78%|███████▊ | 227/291 [00:10<00:02, 28.71it/s]
Loading 0: 86%|████████▌ | 250/291 [00:11<00:00, 41.49it/s]
Loading 0: 91%|█████████▏| 266/291 [00:11<00:00, 47.91it/s]
Loading 0: 99%|█████████▊| 287/291 [00:11<00:00, 64.15it/s]
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
chaoticneutrals-poppy-po-3816-v4-mkmlizer: quantized model in 17.386s
chaoticneutrals-poppy-po-3816-v4-mkmlizer: Processed model ChaoticNeutrals/Poppy_Porpoise-0.72-L3-8B in 31.598s
chaoticneutrals-poppy-po-3816-v4-mkmlizer: creating bucket guanaco-mkml-models
chaoticneutrals-poppy-po-3816-v4-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaoticneutrals-poppy-po-3816-v4-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaoticneutrals-poppy-po-3816-v4
chaoticneutrals-poppy-po-3816-v4-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaoticneutrals-poppy-po-3816-v4/config.json
chaoticneutrals-poppy-po-3816-v4-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaoticneutrals-poppy-po-3816-v4/special_tokens_map.json
chaoticneutrals-poppy-po-3816-v4-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaoticneutrals-poppy-po-3816-v4/tokenizer_config.json
chaoticneutrals-poppy-po-3816-v4-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaoticneutrals-poppy-po-3816-v4/tokenizer.json
chaoticneutrals-poppy-po-3816-v4-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaoticneutrals-poppy-po-3816-v4/flywheel_model.0.safetensors
chaoticneutrals-poppy-po-3816-v4-mkmlizer: loading reward model from rirv938/gpt2_medium_pairwise_60m_step_187500
chaoticneutrals-poppy-po-3816-v4-mkmlizer: /opt/conda/lib/python3.10/site-packages/transformers/models/auto/configuration_auto.py:913: FutureWarning: The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers. Please use `token` instead.
chaoticneutrals-poppy-po-3816-v4-mkmlizer: warnings.warn(
chaoticneutrals-poppy-po-3816-v4-mkmlizer: /opt/conda/lib/python3.10/site-packages/transformers/models/auto/tokenization_auto.py:757: FutureWarning: The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers. Please use `token` instead.
chaoticneutrals-poppy-po-3816-v4-mkmlizer: warnings.warn(
chaoticneutrals-poppy-po-3816-v4-mkmlizer: /opt/conda/lib/python3.10/site-packages/transformers/models/auto/auto_factory.py:468: FutureWarning: The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers. Please use `token` instead.
chaoticneutrals-poppy-po-3816-v4-mkmlizer: warnings.warn(
chaoticneutrals-poppy-po-3816-v4-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
chaoticneutrals-poppy-po-3816-v4-mkmlizer: Saving duration: 0.218s
chaoticneutrals-poppy-po-3816-v4-mkmlizer: Processed model rirv938/gpt2_medium_pairwise_60m_step_187500 in 3.356s
chaoticneutrals-poppy-po-3816-v4-mkmlizer: creating bucket guanaco-reward-models
chaoticneutrals-poppy-po-3816-v4-mkmlizer: Bucket 's3://guanaco-reward-models/' created
chaoticneutrals-poppy-po-3816-v4-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/chaoticneutrals-poppy-po-3816-v4_reward
chaoticneutrals-poppy-po-3816-v4-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/chaoticneutrals-poppy-po-3816-v4_reward/config.json
chaoticneutrals-poppy-po-3816-v4-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/chaoticneutrals-poppy-po-3816-v4_reward/tokenizer_config.json
chaoticneutrals-poppy-po-3816-v4-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/chaoticneutrals-poppy-po-3816-v4_reward/merges.txt
chaoticneutrals-poppy-po-3816-v4-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/chaoticneutrals-poppy-po-3816-v4_reward/special_tokens_map.json
chaoticneutrals-poppy-po-3816-v4-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/chaoticneutrals-poppy-po-3816-v4_reward/vocab.json
chaoticneutrals-poppy-po-3816-v4-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/chaoticneutrals-poppy-po-3816-v4_reward/tokenizer.json
chaoticneutrals-poppy-po-3816-v4-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/chaoticneutrals-poppy-po-3816-v4_reward/reward.tensors
Job chaoticneutrals-poppy-po-3816-v4-mkmlizer completed after 52.49s with status: succeeded
Stopping job with name chaoticneutrals-poppy-po-3816-v4-mkmlizer
Pipeline stage MKMLizer completed in 56.30s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.09s
Running pipeline stage ISVCDeployer
Creating inference service chaoticneutrals-poppy-po-3816-v4
Waiting for inference service chaoticneutrals-poppy-po-3816-v4 to be ready
Inference service chaoticneutrals-poppy-po-3816-v4 ready after 40.30960273742676s
Pipeline stage ISVCDeployer completed in 47.66s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.980381727218628s
Received healthy response to inference request in 1.1774380207061768s
Received healthy response to inference request in 1.168959617614746s
Received healthy response to inference request in 1.1822528839111328s
Received healthy response to inference request in 1.174499750137329s
5 requests
0 failed requests
5th percentile: 1.1700676441192628
10th percentile: 1.1711756706237793
20th percentile: 1.1733917236328124
30th percentile: 1.1750874042510986
40th percentile: 1.1762627124786378
50th percentile: 1.1774380207061768
60th percentile: 1.1793639659881592
70th percentile: 1.1812899112701416
80th percentile: 1.341878652572632
90th percentile: 1.6611301898956299
95th percentile: 1.8207559585571287
99th percentile: 1.9484565734863282
mean time: 1.3367063999176025
Pipeline stage StressChecker completed in 7.28s
Running pipeline stage DaemonicModelEvalScorer
Pipeline stage DaemonicModelEvalScorer completed in 0.03s
Running pipeline stage DaemonicSafetyScorer
Running M-Eval for topic stay_in_character
Pipeline stage DaemonicSafetyScorer completed in 0.04s
M-Eval Dataset for topic stay_in_character is loaded
chaoticneutrals-poppy-po_3816_v4 status is now deployed due to DeploymentManager action
chaoticneutrals-poppy-po_3816_v4 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of chaoticneutrals-poppy-po_3816_v4
Running pipeline stage ISVCDeleter
Checking if service chaoticneutrals-poppy-po-3816-v4 is running
Skipping teardown as no inference service was found
Pipeline stage ISVCDeleter completed in 2.38s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key chaoticneutrals-poppy-po-3816-v4/config.json from bucket guanaco-mkml-models
Deleting key chaoticneutrals-poppy-po-3816-v4/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key chaoticneutrals-poppy-po-3816-v4/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key chaoticneutrals-poppy-po-3816-v4/tokenizer.json from bucket guanaco-mkml-models
Deleting key chaoticneutrals-poppy-po-3816-v4/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key chaoticneutrals-poppy-po-3816-v4_reward/config.json from bucket guanaco-reward-models
Deleting key chaoticneutrals-poppy-po-3816-v4_reward/merges.txt from bucket guanaco-reward-models
Deleting key chaoticneutrals-poppy-po-3816-v4_reward/reward.tensors from bucket guanaco-reward-models
Deleting key chaoticneutrals-poppy-po-3816-v4_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key chaoticneutrals-poppy-po-3816-v4_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key chaoticneutrals-poppy-po-3816-v4_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key chaoticneutrals-poppy-po-3816-v4_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 3.68s
chaoticneutrals-poppy-po_3816_v4 status is now torndown due to DeploymentManager action