Running pipeline stage MKMLizer
Starting job with name hastagaras-esekembrew-8b-4166-v1-mkmlizer
Waiting for job on hastagaras-esekembrew-8b-4166-v1-mkmlizer to finish
hastagaras-esekembrew-8b-4166-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
hastagaras-esekembrew-8b-4166-v1-mkmlizer: ║ _____ __ __ ║
hastagaras-esekembrew-8b-4166-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
hastagaras-esekembrew-8b-4166-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
hastagaras-esekembrew-8b-4166-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
hastagaras-esekembrew-8b-4166-v1-mkmlizer: ║ /___/ ║
hastagaras-esekembrew-8b-4166-v1-mkmlizer: ║ ║
hastagaras-esekembrew-8b-4166-v1-mkmlizer: ║ Version: 0.8.14 ║
hastagaras-esekembrew-8b-4166-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
hastagaras-esekembrew-8b-4166-v1-mkmlizer: ║ https://mk1.ai ║
hastagaras-esekembrew-8b-4166-v1-mkmlizer: ║ ║
hastagaras-esekembrew-8b-4166-v1-mkmlizer: ║ The license key for the current software has been verified as ║
hastagaras-esekembrew-8b-4166-v1-mkmlizer: ║ belonging to: ║
hastagaras-esekembrew-8b-4166-v1-mkmlizer: ║ ║
hastagaras-esekembrew-8b-4166-v1-mkmlizer: ║ Chai Research Corp. ║
hastagaras-esekembrew-8b-4166-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
hastagaras-esekembrew-8b-4166-v1-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
hastagaras-esekembrew-8b-4166-v1-mkmlizer: ║ ║
hastagaras-esekembrew-8b-4166-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
hastagaras-esekembrew-8b-4166-v1-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.
hastagaras-esekembrew-8b-4166-v1-mkmlizer: warnings.warn(warning_message, FutureWarning)
hastagaras-esekembrew-8b-4166-v1-mkmlizer: Downloaded to shared memory in 33.627s
hastagaras-esekembrew-8b-4166-v1-mkmlizer: quantizing model to /dev/shm/model_cache
hastagaras-esekembrew-8b-4166-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
hastagaras-esekembrew-8b-4166-v1-mkmlizer:
Loading 0: 0%| | 0/291 [00:00<?, ?it/s]
Loading 0: 4%|▍ | 13/291 [00:00<00:02, 124.77it/s]
Loading 0: 11%|█ | 31/291 [00:00<00:01, 148.25it/s]
Loading 0: 17%|█▋ | 49/291 [00:00<00:01, 152.63it/s]
Loading 0: 23%|██▎ | 67/291 [00:00<00:01, 156.75it/s]
Loading 0: 29%|██▊ | 83/291 [00:00<00:02, 83.93it/s]
Loading 0: 33%|███▎ | 97/291 [00:00<00:02, 95.38it/s]
Loading 0: 39%|███▉ | 113/291 [00:01<00:01, 107.91it/s]
Loading 0: 45%|████▌ | 131/291 [00:01<00:01, 123.00it/s]
Loading 0: 51%|█████ | 149/291 [00:01<00:01, 135.05it/s]
Loading 0: 57%|█████▋ | 167/291 [00:01<00:00, 144.30it/s]
Loading 0: 64%|██████▍ | 187/291 [00:01<00:01, 97.35it/s]
Loading 0: 69%|██████▉ | 202/291 [00:01<00:00, 105.07it/s]
Loading 0: 76%|███████▌ | 220/291 [00:01<00:00, 118.82it/s]
Loading 0: 82%|████████▏ | 238/291 [00:01<00:00, 130.92it/s]
Loading 0: 88%|████████▊ | 256/291 [00:02<00:00, 140.40it/s]
Loading 0: 94%|█████████▍| 274/291 [00:02<00:00, 147.84it/s]
Loading 0: 100%|█████████▉| 290/291 [00:07<00:00, 9.79it/s]
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
hastagaras-esekembrew-8b-4166-v1-mkmlizer: quantized model in 23.286s
hastagaras-esekembrew-8b-4166-v1-mkmlizer: Processed model Hastagaras/Esekembrew-8B-Llama3-0.5 in 59.534s
hastagaras-esekembrew-8b-4166-v1-mkmlizer: creating bucket guanaco-mkml-models
hastagaras-esekembrew-8b-4166-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
hastagaras-esekembrew-8b-4166-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/hastagaras-esekembrew-8b-4166-v1
hastagaras-esekembrew-8b-4166-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/hastagaras-esekembrew-8b-4166-v1/tokenizer_config.json
hastagaras-esekembrew-8b-4166-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/hastagaras-esekembrew-8b-4166-v1/special_tokens_map.json
hastagaras-esekembrew-8b-4166-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/hastagaras-esekembrew-8b-4166-v1/config.json
hastagaras-esekembrew-8b-4166-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/hastagaras-esekembrew-8b-4166-v1/tokenizer.json
hastagaras-esekembrew-8b-4166-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/hastagaras-esekembrew-8b-4166-v1/flywheel_model.0.safetensors
hastagaras-esekembrew-8b-4166-v1-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
hastagaras-esekembrew-8b-4166-v1-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.
hastagaras-esekembrew-8b-4166-v1-mkmlizer: warnings.warn(
hastagaras-esekembrew-8b-4166-v1-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.
hastagaras-esekembrew-8b-4166-v1-mkmlizer: warnings.warn(
hastagaras-esekembrew-8b-4166-v1-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()
hastagaras-esekembrew-8b-4166-v1-mkmlizer: return self.fget.__get__(instance, owner)()
hastagaras-esekembrew-8b-4166-v1-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
hastagaras-esekembrew-8b-4166-v1-mkmlizer: Saving duration: 0.398s
hastagaras-esekembrew-8b-4166-v1-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 4.475s
hastagaras-esekembrew-8b-4166-v1-mkmlizer: creating bucket guanaco-reward-models
hastagaras-esekembrew-8b-4166-v1-mkmlizer: Bucket 's3://guanaco-reward-models/' created
hastagaras-esekembrew-8b-4166-v1-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/hastagaras-esekembrew-8b-4166-v1_reward
hastagaras-esekembrew-8b-4166-v1-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/hastagaras-esekembrew-8b-4166-v1_reward/config.json
hastagaras-esekembrew-8b-4166-v1-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/hastagaras-esekembrew-8b-4166-v1_reward/special_tokens_map.json
hastagaras-esekembrew-8b-4166-v1-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/hastagaras-esekembrew-8b-4166-v1_reward/tokenizer_config.json
hastagaras-esekembrew-8b-4166-v1-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/hastagaras-esekembrew-8b-4166-v1_reward/merges.txt
hastagaras-esekembrew-8b-4166-v1-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/hastagaras-esekembrew-8b-4166-v1_reward/vocab.json
hastagaras-esekembrew-8b-4166-v1-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/hastagaras-esekembrew-8b-4166-v1_reward/tokenizer.json
hastagaras-esekembrew-8b-4166-v1-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/hastagaras-esekembrew-8b-4166-v1_reward/reward.tensors
Job hastagaras-esekembrew-8b-4166-v1-mkmlizer completed after 82.9s with status: succeeded
Stopping job with name hastagaras-esekembrew-8b-4166-v1-mkmlizer
Pipeline stage MKMLizer completed in 83.62s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.08s
Running pipeline stage ISVCDeployer
Creating inference service hastagaras-esekembrew-8b-4166-v1
Waiting for inference service hastagaras-esekembrew-8b-4166-v1 to be ready
Inference service hastagaras-esekembrew-8b-4166-v1 ready after 30.15202283859253s
Pipeline stage ISVCDeployer completed in 36.06s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.261700391769409s
Received healthy response to inference request in 1.345287799835205s
%s, retrying in %s seconds...
Received healthy response to inference request in 1.2650690078735352s
Received healthy response to inference request in 1.336441993713379s
Received healthy response to inference request in 1.3335962295532227s
Received healthy response to inference request in 1.2634265422821045s
Received healthy response to inference request in 1.3359935283660889s
5 requests
0 failed requests
5th percentile: 1.2637550354003906
10th percentile: 1.2640835285186767
20th percentile: 1.264740514755249
30th percentile: 1.2787744522094726
40th percentile: 1.3061853408813477
50th percentile: 1.3335962295532227
60th percentile: 1.3345551490783691
70th percentile: 1.3355140686035156
80th percentile: 1.336083221435547
90th percentile: 1.3362626075744628
95th percentile: 1.3363523006439209
99th percentile: 1.3364240550994873
mean time: 1.306905460357666
Pipeline stage StressChecker completed in 30.87s
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
hastagaras-esekembrew-8b_4166_v1 status is now deployed due to DeploymentManager action
hastagaras-esekembrew-8b_4166_v1 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of hastagaras-esekembrew-8b_4166_v1
Running pipeline stage ISVCDeleter
Checking if service hastagaras-esekembrew-8b-4166-v1 is running
Skipping teardown as no inference service was found
Pipeline stage ISVCDeleter completed in 2.36s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key hastagaras-esekembrew-8b-4166-v1/config.json from bucket guanaco-mkml-models
Deleting key hastagaras-esekembrew-8b-4166-v1/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key hastagaras-esekembrew-8b-4166-v1/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key hastagaras-esekembrew-8b-4166-v1/tokenizer.json from bucket guanaco-mkml-models
Deleting key hastagaras-esekembrew-8b-4166-v1/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key hastagaras-esekembrew-8b-4166-v1_reward/config.json from bucket guanaco-reward-models
Deleting key hastagaras-esekembrew-8b-4166-v1_reward/merges.txt from bucket guanaco-reward-models
Deleting key hastagaras-esekembrew-8b-4166-v1_reward/reward.tensors from bucket guanaco-reward-models
Deleting key hastagaras-esekembrew-8b-4166-v1_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key hastagaras-esekembrew-8b-4166-v1_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key hastagaras-esekembrew-8b-4166-v1_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key hastagaras-esekembrew-8b-4166-v1_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 3.58s
hastagaras-esekembrew-8b_4166_v1 status is now torndown due to DeploymentManager action