Running pipeline stage MKMLizer
Starting job with name bbchicago-llama3-8b-lora-3778-v4-mkmlizer
Waiting for job on bbchicago-llama3-8b-lora-3778-v4-mkmlizer to finish
bbchicago-llama3-8b-lora-3778-v4-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
bbchicago-llama3-8b-lora-3778-v4-mkmlizer: ║ _____ __ __ ║
bbchicago-llama3-8b-lora-3778-v4-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
bbchicago-llama3-8b-lora-3778-v4-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
bbchicago-llama3-8b-lora-3778-v4-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
bbchicago-llama3-8b-lora-3778-v4-mkmlizer: ║ /___/ ║
bbchicago-llama3-8b-lora-3778-v4-mkmlizer: ║ ║
bbchicago-llama3-8b-lora-3778-v4-mkmlizer: ║ Version: 0.8.14 ║
bbchicago-llama3-8b-lora-3778-v4-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
bbchicago-llama3-8b-lora-3778-v4-mkmlizer: ║ https://mk1.ai ║
bbchicago-llama3-8b-lora-3778-v4-mkmlizer: ║ ║
bbchicago-llama3-8b-lora-3778-v4-mkmlizer: ║ The license key for the current software has been verified as ║
bbchicago-llama3-8b-lora-3778-v4-mkmlizer: ║ belonging to: ║
bbchicago-llama3-8b-lora-3778-v4-mkmlizer: ║ ║
bbchicago-llama3-8b-lora-3778-v4-mkmlizer: ║ Chai Research Corp. ║
bbchicago-llama3-8b-lora-3778-v4-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
bbchicago-llama3-8b-lora-3778-v4-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
bbchicago-llama3-8b-lora-3778-v4-mkmlizer: ║ ║
bbchicago-llama3-8b-lora-3778-v4-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
bbchicago-llama3-8b-lora-3778-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.
bbchicago-llama3-8b-lora-3778-v4-mkmlizer: warnings.warn(warning_message, FutureWarning)
bbchicago-llama3-8b-lora-3778-v4-mkmlizer: Downloaded to shared memory in 29.542s
bbchicago-llama3-8b-lora-3778-v4-mkmlizer: quantizing model to /dev/shm/model_cache
bbchicago-llama3-8b-lora-3778-v4-mkmlizer: Saving flywheel model at /dev/shm/model_cache
bbchicago-llama3-8b-lora-3778-v4-mkmlizer:
Loading 0: 0%| | 0/291 [00:00<?, ?it/s]
Loading 0: 1%| | 2/291 [00:00<00:17, 16.67it/s]
Loading 0: 5%|▌ | 16/291 [00:00<00:03, 83.24it/s]
Loading 0: 9%|▊ | 25/291 [00:00<00:03, 77.12it/s]
Loading 0: 14%|█▎ | 40/291 [00:00<00:02, 101.79it/s]
Loading 0: 18%|█▊ | 51/291 [00:00<00:02, 84.27it/s]
Loading 0: 21%|██▏ | 62/291 [00:00<00:02, 82.22it/s]
Loading 0: 26%|██▋ | 77/291 [00:00<00:02, 97.16it/s]
Loading 0: 30%|███ | 88/291 [00:01<00:02, 87.83it/s]
Loading 0: 36%|███▌ | 105/291 [00:01<00:01, 93.33it/s]
Loading 0: 41%|████ | 119/291 [00:01<00:01, 101.89it/s]
Loading 0: 45%|████▍ | 130/291 [00:01<00:01, 89.83it/s]
Loading 0: 49%|████▉ | 143/291 [00:01<00:01, 87.46it/s]
Loading 0: 54%|█████▍ | 158/291 [00:01<00:01, 99.41it/s]
Loading 0: 58%|█████▊ | 169/291 [00:01<00:01, 91.20it/s]
Loading 0: 64%|██████▍ | 186/291 [00:02<00:01, 95.49it/s]
Loading 0: 69%|██████▊ | 200/291 [00:02<00:00, 102.37it/s]
Loading 0: 73%|███████▎ | 211/291 [00:02<00:00, 90.80it/s]
Loading 0: 77%|███████▋ | 224/291 [00:02<00:00, 88.05it/s]
Loading 0: 82%|████████▏ | 239/291 [00:02<00:00, 99.05it/s]
Loading 0: 86%|████████▌ | 250/291 [00:02<00:00, 91.23it/s]
Loading 0: 92%|█████████▏| 267/291 [00:02<00:00, 95.06it/s]
Loading 0: 96%|█████████▌| 279/291 [00:03<00:00, 100.55it/s]
Loading 0: 100%|█████████▉| 290/291 [00:03<00:00, 90.41it/s]
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
bbchicago-llama3-8b-lora-3778-v4-mkmlizer: quantized model in 23.274s
bbchicago-llama3-8b-lora-3778-v4-mkmlizer: Processed model BBChicago/llama3-8b-lora-v0.0.0 in 55.318s
bbchicago-llama3-8b-lora-3778-v4-mkmlizer: creating bucket guanaco-mkml-models
bbchicago-llama3-8b-lora-3778-v4-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
bbchicago-llama3-8b-lora-3778-v4-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/bbchicago-llama3-8b-lora-3778-v4
bbchicago-llama3-8b-lora-3778-v4-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/bbchicago-llama3-8b-lora-3778-v4/config.json
bbchicago-llama3-8b-lora-3778-v4-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/bbchicago-llama3-8b-lora-3778-v4/special_tokens_map.json
bbchicago-llama3-8b-lora-3778-v4-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/bbchicago-llama3-8b-lora-3778-v4/tokenizer_config.json
bbchicago-llama3-8b-lora-3778-v4-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/bbchicago-llama3-8b-lora-3778-v4/tokenizer.json
bbchicago-llama3-8b-lora-3778-v4-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/bbchicago-llama3-8b-lora-3778-v4/flywheel_model.0.safetensors
bbchicago-llama3-8b-lora-3778-v4-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
bbchicago-llama3-8b-lora-3778-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.
bbchicago-llama3-8b-lora-3778-v4-mkmlizer: warnings.warn(
bbchicago-llama3-8b-lora-3778-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.
bbchicago-llama3-8b-lora-3778-v4-mkmlizer: warnings.warn(
bbchicago-llama3-8b-lora-3778-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.
bbchicago-llama3-8b-lora-3778-v4-mkmlizer: warnings.warn(
bbchicago-llama3-8b-lora-3778-v4-mkmlizer: /opt/conda/lib/python3.10/site-packages/torch/_utils.py:831: UserWarning: TypedStorage is deprecated. It will be removed in the future and UntypedStorage will be the only storage class. This should only matter to you if you are using storages directly. To access UntypedStorage directly, use tensor.untyped_storage() instead of tensor.storage()
bbchicago-llama3-8b-lora-3778-v4-mkmlizer: return self.fget.__get__(instance, owner)()
bbchicago-llama3-8b-lora-3778-v4-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
bbchicago-llama3-8b-lora-3778-v4-mkmlizer: Saving duration: 0.395s
bbchicago-llama3-8b-lora-3778-v4-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 7.098s
bbchicago-llama3-8b-lora-3778-v4-mkmlizer: creating bucket guanaco-reward-models
bbchicago-llama3-8b-lora-3778-v4-mkmlizer: Bucket 's3://guanaco-reward-models/' created
bbchicago-llama3-8b-lora-3778-v4-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/bbchicago-llama3-8b-lora-3778-v4_reward
bbchicago-llama3-8b-lora-3778-v4-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/bbchicago-llama3-8b-lora-3778-v4_reward/config.json
bbchicago-llama3-8b-lora-3778-v4-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/bbchicago-llama3-8b-lora-3778-v4_reward/special_tokens_map.json
bbchicago-llama3-8b-lora-3778-v4-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/bbchicago-llama3-8b-lora-3778-v4_reward/merges.txt
bbchicago-llama3-8b-lora-3778-v4-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/bbchicago-llama3-8b-lora-3778-v4_reward/tokenizer_config.json
bbchicago-llama3-8b-lora-3778-v4-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/bbchicago-llama3-8b-lora-3778-v4_reward/vocab.json
bbchicago-llama3-8b-lora-3778-v4-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/bbchicago-llama3-8b-lora-3778-v4_reward/tokenizer.json
bbchicago-llama3-8b-lora-3778-v4-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/bbchicago-llama3-8b-lora-3778-v4_reward/reward.tensors
Job bbchicago-llama3-8b-lora-3778-v4-mkmlizer completed after 83.71s with status: succeeded
Stopping job with name bbchicago-llama3-8b-lora-3778-v4-mkmlizer
Pipeline stage MKMLizer completed in 84.43s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.10s
Running pipeline stage ISVCDeployer
Creating inference service bbchicago-llama3-8b-lora-3778-v4
Waiting for inference service bbchicago-llama3-8b-lora-3778-v4 to be ready
Inference service bbchicago-llama3-8b-lora-3778-v4 ready after 40.2810959815979s
Pipeline stage ISVCDeployer completed in 46.12s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.045541763305664s
Received healthy response to inference request in 2.920193910598755s
Received healthy response to inference request in 1.119532823562622s
Received healthy response to inference request in 1.1113271713256836s
Received healthy response to inference request in 1.113673210144043s
5 requests
0 failed requests
5th percentile: 1.1117963790893555
10th percentile: 1.1122655868530273
20th percentile: 1.113204002380371
30th percentile: 1.1148451328277589
40th percentile: 1.1171889781951905
50th percentile: 1.119532823562622
60th percentile: 1.4899363994598387
70th percentile: 1.8603399753570555
80th percentile: 2.2204721927642823
90th percentile: 2.570333051681519
95th percentile: 2.7452634811401366
99th percentile: 2.8852078247070314
mean time: 1.6620537757873535
Pipeline stage StressChecker completed in 8.96s
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
bbchicago-llama3-8b-lora_3778_v4 status is now deployed due to DeploymentManager action
bbchicago-llama3-8b-lora_3778_v4 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of bbchicago-llama3-8b-lora_3778_v4
Running pipeline stage ISVCDeleter
Checking if service bbchicago-llama3-8b-lora-3778-v4 is running
Skipping teardown as no inference service was found
Pipeline stage ISVCDeleter completed in 2.87s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key bbchicago-llama3-8b-lora-3778-v4/config.json from bucket guanaco-mkml-models
Deleting key bbchicago-llama3-8b-lora-3778-v4/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key bbchicago-llama3-8b-lora-3778-v4/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key bbchicago-llama3-8b-lora-3778-v4/tokenizer.json from bucket guanaco-mkml-models
Deleting key bbchicago-llama3-8b-lora-3778-v4/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key bbchicago-llama3-8b-lora-3778-v4_reward/config.json from bucket guanaco-reward-models
Deleting key bbchicago-llama3-8b-lora-3778-v4_reward/merges.txt from bucket guanaco-reward-models
Deleting key bbchicago-llama3-8b-lora-3778-v4_reward/reward.tensors from bucket guanaco-reward-models
Deleting key bbchicago-llama3-8b-lora-3778-v4_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key bbchicago-llama3-8b-lora-3778-v4_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key bbchicago-llama3-8b-lora-3778-v4_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key bbchicago-llama3-8b-lora-3778-v4_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 3.72s
bbchicago-llama3-8b-lora_3778_v4 status is now torndown due to DeploymentManager action