Running pipeline stage MKMLizer
Starting job with name anhnv125-hyper-l3-v3-mkmlizer
Waiting for job on anhnv125-hyper-l3-v3-mkmlizer to finish
anhnv125-hyper-l3-v3-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
anhnv125-hyper-l3-v3-mkmlizer: ║ _____ __ __ ║
anhnv125-hyper-l3-v3-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
anhnv125-hyper-l3-v3-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
anhnv125-hyper-l3-v3-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
anhnv125-hyper-l3-v3-mkmlizer: ║ /___/ ║
anhnv125-hyper-l3-v3-mkmlizer: ║ ║
anhnv125-hyper-l3-v3-mkmlizer: ║ Version: 0.8.10 ║
anhnv125-hyper-l3-v3-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
anhnv125-hyper-l3-v3-mkmlizer: ║ ║
anhnv125-hyper-l3-v3-mkmlizer: ║ The license key for the current software has been verified as ║
anhnv125-hyper-l3-v3-mkmlizer: ║ belonging to: ║
anhnv125-hyper-l3-v3-mkmlizer: ║ ║
anhnv125-hyper-l3-v3-mkmlizer: ║ Chai Research Corp. ║
anhnv125-hyper-l3-v3-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
anhnv125-hyper-l3-v3-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
anhnv125-hyper-l3-v3-mkmlizer: ║ ║
anhnv125-hyper-l3-v3-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
anhnv125-hyper-l3-v3-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.
anhnv125-hyper-l3-v3-mkmlizer: warnings.warn(warning_message, FutureWarning)
anhnv125-hyper-l3-v3-mkmlizer: Downloaded to shared memory in 13.001s
anhnv125-hyper-l3-v3-mkmlizer: quantizing model to /dev/shm/model_cache
anhnv125-hyper-l3-v3-mkmlizer: Saving flywheel model at /dev/shm/model_cache
anhnv125-hyper-l3-v3-mkmlizer:
Loading 0: 0%| | 0/291 [00:00<?, ?it/s]
Loading 0: 38%|███▊ | 112/291 [00:01<00:01, 111.53it/s]
Loading 0: 64%|██████▍ | 187/291 [00:07<00:04, 22.07it/s]
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
anhnv125-hyper-l3-v3-mkmlizer: quantized model in 19.653s
anhnv125-hyper-l3-v3-mkmlizer: Processed model anhnv125/Hyper-L3 in 33.623s
anhnv125-hyper-l3-v3-mkmlizer: creating bucket guanaco-mkml-models
anhnv125-hyper-l3-v3-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
anhnv125-hyper-l3-v3-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/anhnv125-hyper-l3-v3
anhnv125-hyper-l3-v3-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/anhnv125-hyper-l3-v3/config.json
anhnv125-hyper-l3-v3-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/anhnv125-hyper-l3-v3/special_tokens_map.json
anhnv125-hyper-l3-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/anhnv125-hyper-l3-v3/tokenizer_config.json
anhnv125-hyper-l3-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/anhnv125-hyper-l3-v3/tokenizer.json
anhnv125-hyper-l3-v3-mkmlizer: loading reward model from rirv938/reward_gpt2_medium_preference_24m_e2
anhnv125-hyper-l3-v3-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.
anhnv125-hyper-l3-v3-mkmlizer: warnings.warn(
anhnv125-hyper-l3-v3-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.
anhnv125-hyper-l3-v3-mkmlizer: warnings.warn(
anhnv125-hyper-l3-v3-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.
anhnv125-hyper-l3-v3-mkmlizer: warnings.warn(
anhnv125-hyper-l3-v3-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()
anhnv125-hyper-l3-v3-mkmlizer: return self.fget.__get__(instance, owner)()
anhnv125-hyper-l3-v3-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
anhnv125-hyper-l3-v3-mkmlizer: Saving duration: 0.262s
anhnv125-hyper-l3-v3-mkmlizer: Processed model rirv938/reward_gpt2_medium_preference_24m_e2 in 7.044s
anhnv125-hyper-l3-v3-mkmlizer: creating bucket guanaco-reward-models
anhnv125-hyper-l3-v3-mkmlizer: Bucket 's3://guanaco-reward-models/' created
anhnv125-hyper-l3-v3-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/anhnv125-hyper-l3-v3_reward
anhnv125-hyper-l3-v3-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/anhnv125-hyper-l3-v3_reward/tokenizer_config.json
anhnv125-hyper-l3-v3-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/anhnv125-hyper-l3-v3_reward/merges.txt
anhnv125-hyper-l3-v3-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/anhnv125-hyper-l3-v3_reward/config.json
anhnv125-hyper-l3-v3-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/anhnv125-hyper-l3-v3_reward/vocab.json
anhnv125-hyper-l3-v3-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/anhnv125-hyper-l3-v3_reward/special_tokens_map.json
anhnv125-hyper-l3-v3-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/anhnv125-hyper-l3-v3_reward/tokenizer.json
anhnv125-hyper-l3-v3-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/anhnv125-hyper-l3-v3_reward/reward.tensors
Job anhnv125-hyper-l3-v3-mkmlizer completed after 63.32s with status: succeeded
Stopping job with name anhnv125-hyper-l3-v3-mkmlizer
Pipeline stage MKMLizer completed in 67.02s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.09s
Running pipeline stage ISVCDeployer
Creating inference service anhnv125-hyper-l3-v3
Waiting for inference service anhnv125-hyper-l3-v3 to be ready
Inference service anhnv125-hyper-l3-v3 ready after 60.31867742538452s
Pipeline stage ISVCDeployer completed in 67.35s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.1979029178619385s
Received healthy response to inference request in 1.3379294872283936s
Received healthy response to inference request in 1.664665699005127s
Received healthy response to inference request in 1.4009158611297607s
Received healthy response to inference request in 1.3535301685333252s
5 requests
0 failed requests
5th percentile: 1.3410496234893798
10th percentile: 1.3441697597503661
20th percentile: 1.350410032272339
30th percentile: 1.3630073070526123
40th percentile: 1.3819615840911865
50th percentile: 1.4009158611297607
60th percentile: 1.5064157962799072
70th percentile: 1.6119157314300536
80th percentile: 1.7713131427764894
90th percentile: 1.984608030319214
95th percentile: 2.091255474090576
99th percentile: 2.176573429107666
mean time: 1.590988826751709
Pipeline stage StressChecker completed in 8.57s
Running pipeline stage DaemonicModelEvalScorer
Pipeline stage DaemonicModelEvalScorer completed in 0.04s
Running pipeline stage DaemonicSafetyScorer
Running M-Eval for topic stay_in_character
Pipeline stage DaemonicSafetyScorer completed in 0.03s
M-Eval Dataset for topic stay_in_character is loaded
anhnv125-hyper-l3_v3 status is now deployed due to DeploymentManager action
anhnv125-hyper-l3_v3 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of anhnv125-hyper-l3_v3
Running pipeline stage ISVCDeleter
Checking if service anhnv125-hyper-l3-v3 is running
Tearing down inference service anhnv125-hyper-l3-v3
Toredown service anhnv125-hyper-l3-v3
Pipeline stage ISVCDeleter completed in 4.61s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key anhnv125-hyper-l3-v3/config.json from bucket guanaco-mkml-models
Deleting key anhnv125-hyper-l3-v3/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key anhnv125-hyper-l3-v3/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key anhnv125-hyper-l3-v3/tokenizer.json from bucket guanaco-mkml-models
Deleting key anhnv125-hyper-l3-v3/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key anhnv125-hyper-l3-v3_reward/config.json from bucket guanaco-reward-models
Deleting key anhnv125-hyper-l3-v3_reward/merges.txt from bucket guanaco-reward-models
Deleting key anhnv125-hyper-l3-v3_reward/reward.tensors from bucket guanaco-reward-models
Deleting key anhnv125-hyper-l3-v3_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key anhnv125-hyper-l3-v3_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key anhnv125-hyper-l3-v3_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key anhnv125-hyper-l3-v3_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 2.52s
anhnv125-hyper-l3_v3 status is now torndown due to DeploymentManager action