Running pipeline stage MKMLizer
Starting job with name cgato-l3-thespice-8b-sto-9357-v2-mkmlizer
Waiting for job on cgato-l3-thespice-8b-sto-9357-v2-mkmlizer to finish
cgato-l3-thespice-8b-sto-9357-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cgato-l3-thespice-8b-sto-9357-v2-mkmlizer: ║ _____ __ __ ║
cgato-l3-thespice-8b-sto-9357-v2-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
cgato-l3-thespice-8b-sto-9357-v2-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
cgato-l3-thespice-8b-sto-9357-v2-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
cgato-l3-thespice-8b-sto-9357-v2-mkmlizer: ║ /___/ ║
cgato-l3-thespice-8b-sto-9357-v2-mkmlizer: ║ ║
cgato-l3-thespice-8b-sto-9357-v2-mkmlizer: ║ Version: 0.8.14 ║
cgato-l3-thespice-8b-sto-9357-v2-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
cgato-l3-thespice-8b-sto-9357-v2-mkmlizer: ║ https://mk1.ai ║
cgato-l3-thespice-8b-sto-9357-v2-mkmlizer: ║ ║
cgato-l3-thespice-8b-sto-9357-v2-mkmlizer: ║ The license key for the current software has been verified as ║
cgato-l3-thespice-8b-sto-9357-v2-mkmlizer: ║ belonging to: ║
cgato-l3-thespice-8b-sto-9357-v2-mkmlizer: ║ ║
cgato-l3-thespice-8b-sto-9357-v2-mkmlizer: ║ Chai Research Corp. ║
cgato-l3-thespice-8b-sto-9357-v2-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
cgato-l3-thespice-8b-sto-9357-v2-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
cgato-l3-thespice-8b-sto-9357-v2-mkmlizer: ║ ║
cgato-l3-thespice-8b-sto-9357-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
cgato-l3-thespice-8b-sto-9357-v2-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.
cgato-l3-thespice-8b-sto-9357-v2-mkmlizer: warnings.warn(warning_message, FutureWarning)
cgato-l3-thespice-8b-sto-9357-v2-mkmlizer: Downloaded to shared memory in 34.868s
cgato-l3-thespice-8b-sto-9357-v2-mkmlizer: quantizing model to /dev/shm/model_cache
cgato-l3-thespice-8b-sto-9357-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
cgato-l3-thespice-8b-sto-9357-v2-mkmlizer:
Loading 0: 0%| | 0/291 [00:00<?, ?it/s]
Loading 0: 29%|██▊ | 83/291 [00:01<00:02, 79.21it/s]
Loading 0: 64%|██████▍ | 187/291 [00:01<00:01, 97.19it/s]
Loading 0: 99%|█████████▊| 287/291 [00:02<00:00, 137.61it/s]
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
cgato-l3-thespice-8b-sto-9357-v2-mkmlizer: quantized model in 18.648s
cgato-l3-thespice-8b-sto-9357-v2-mkmlizer: Processed model cgato/L3-TheSpice-8b-Stoic-Snow-9 in 54.743s
cgato-l3-thespice-8b-sto-9357-v2-mkmlizer: creating bucket guanaco-mkml-models
cgato-l3-thespice-8b-sto-9357-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cgato-l3-thespice-8b-sto-9357-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/cgato-l3-thespice-8b-sto-9357-v2
cgato-l3-thespice-8b-sto-9357-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/cgato-l3-thespice-8b-sto-9357-v2/special_tokens_map.json
cgato-l3-thespice-8b-sto-9357-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/cgato-l3-thespice-8b-sto-9357-v2/config.json
cgato-l3-thespice-8b-sto-9357-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/cgato-l3-thespice-8b-sto-9357-v2/tokenizer_config.json
cgato-l3-thespice-8b-sto-9357-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/cgato-l3-thespice-8b-sto-9357-v2/tokenizer.json
cgato-l3-thespice-8b-sto-9357-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/cgato-l3-thespice-8b-sto-9357-v2/flywheel_model.0.safetensors
cgato-l3-thespice-8b-sto-9357-v2-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
cgato-l3-thespice-8b-sto-9357-v2-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.
cgato-l3-thespice-8b-sto-9357-v2-mkmlizer: warnings.warn(
cgato-l3-thespice-8b-sto-9357-v2-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.
cgato-l3-thespice-8b-sto-9357-v2-mkmlizer: warnings.warn(
cgato-l3-thespice-8b-sto-9357-v2-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.
cgato-l3-thespice-8b-sto-9357-v2-mkmlizer: warnings.warn(
cgato-l3-thespice-8b-sto-9357-v2-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()
cgato-l3-thespice-8b-sto-9357-v2-mkmlizer: return self.fget.__get__(instance, owner)()
cgato-l3-thespice-8b-sto-9357-v2-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
cgato-l3-thespice-8b-sto-9357-v2-mkmlizer: Saving duration: 0.246s
cgato-l3-thespice-8b-sto-9357-v2-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 7.792s
cgato-l3-thespice-8b-sto-9357-v2-mkmlizer: creating bucket guanaco-reward-models
cgato-l3-thespice-8b-sto-9357-v2-mkmlizer: Bucket 's3://guanaco-reward-models/' created
cgato-l3-thespice-8b-sto-9357-v2-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/cgato-l3-thespice-8b-sto-9357-v2_reward
cgato-l3-thespice-8b-sto-9357-v2-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/cgato-l3-thespice-8b-sto-9357-v2_reward/config.json
cgato-l3-thespice-8b-sto-9357-v2-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/cgato-l3-thespice-8b-sto-9357-v2_reward/tokenizer_config.json
cgato-l3-thespice-8b-sto-9357-v2-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/cgato-l3-thespice-8b-sto-9357-v2_reward/merges.txt
cgato-l3-thespice-8b-sto-9357-v2-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/cgato-l3-thespice-8b-sto-9357-v2_reward/special_tokens_map.json
cgato-l3-thespice-8b-sto-9357-v2-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/cgato-l3-thespice-8b-sto-9357-v2_reward/vocab.json
cgato-l3-thespice-8b-sto-9357-v2-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/cgato-l3-thespice-8b-sto-9357-v2_reward/tokenizer.json
cgato-l3-thespice-8b-sto-9357-v2-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/cgato-l3-thespice-8b-sto-9357-v2_reward/reward.tensors
Job cgato-l3-thespice-8b-sto-9357-v2-mkmlizer completed after 83.15s with status: succeeded
Stopping job with name cgato-l3-thespice-8b-sto-9357-v2-mkmlizer
Pipeline stage MKMLizer completed in 86.63s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.12s
Running pipeline stage ISVCDeployer
Creating inference service cgato-l3-thespice-8b-sto-9357-v2
Waiting for inference service cgato-l3-thespice-8b-sto-9357-v2 to be ready
Inference service cgato-l3-thespice-8b-sto-9357-v2 ready after 40.236947536468506s
Pipeline stage ISVCDeployer completed in 47.20s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.136082172393799s
Received healthy response to inference request in 1.4198734760284424s
Received healthy response to inference request in 1.3663201332092285s
Received healthy response to inference request in 1.2725965976715088s
Received healthy response to inference request in 1.2590291500091553s
5 requests
0 failed requests
5th percentile: 1.261742639541626
10th percentile: 1.2644561290740968
20th percentile: 1.269883108139038
30th percentile: 1.2913413047790527
40th percentile: 1.3288307189941406
50th percentile: 1.3663201332092285
60th percentile: 1.387741470336914
70th percentile: 1.4091628074645997
80th percentile: 1.5631152153015138
90th percentile: 1.8495986938476563
95th percentile: 1.9928404331207275
99th percentile: 2.1074338245391844
mean time: 1.4907803058624267
Pipeline stage StressChecker completed in 8.06s
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
cgato-l3-thespice-8b-sto_9357_v2 status is now deployed due to DeploymentManager action
cgato-l3-thespice-8b-sto_9357_v2 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of cgato-l3-thespice-8b-sto_9357_v2
Running pipeline stage ISVCDeleter
Checking if service cgato-l3-thespice-8b-sto-9357-v2 is running
Deleting key cgato-l3-thespice-8b-sto-5210-v2/config.json from bucket guanaco-mkml-models
Deleting key cgato-l3-thespice-8b-sto-5210-v2/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key cgato-l3-thespice-8b-sto-5210-v2/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key cgato-l3-thespice-8b-sto-5210-v2/tokenizer.json from bucket guanaco-mkml-models
Deleting key cgato-l3-thespice-8b-sto-5210-v2/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key cgato-l3-thespice-8b-sto-5210-v2_reward/config.json from bucket guanaco-reward-models
Deleting key cgato-l3-thespice-8b-sto-5210-v2_reward/merges.txt from bucket guanaco-reward-models
Deleting key cgato-l3-thespice-8b-sto-5210-v2_reward/reward.tensors from bucket guanaco-reward-models
Deleting key cgato-l3-thespice-8b-sto-5210-v2_reward/special_tokens_map.json from bucket guanaco-reward-models
Tearing down inference service cgato-l3-thespice-8b-sto-9357-v2
Deleting key cgato-l3-thespice-8b-sto-5210-v2_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key cgato-l3-thespice-8b-sto-5210-v2_reward/tokenizer_config.json from bucket guanaco-reward-models
Toredown service cgato-l3-thespice-8b-sto-9357-v2
Deleting key cgato-l3-thespice-8b-sto-5210-v2_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage ISVCDeleter completed in 3.68s
Pipeline stage MKMLModelDeleter completed in 4.28s
Running pipeline stage MKMLModelDeleter
cgato-l3-thespice-8b-sto_5210_v2 status is now torndown due to DeploymentManager action
Cleaning model data from model cache
Deleting key cgato-l3-thespice-8b-sto-9357-v2/config.json from bucket guanaco-mkml-models
Deleting key cgato-l3-thespice-8b-sto-9357-v2/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key cgato-l3-thespice-8b-sto-9357-v2/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key cgato-l3-thespice-8b-sto-9357-v2/tokenizer.json from bucket guanaco-mkml-models
Deleting key cgato-l3-thespice-8b-sto-9357-v2/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key cgato-l3-thespice-8b-sto-9357-v2_reward/config.json from bucket guanaco-reward-models
Deleting key cgato-l3-thespice-8b-sto-9357-v2_reward/merges.txt from bucket guanaco-reward-models
Deleting key cgato-l3-thespice-8b-sto-9357-v2_reward/reward.tensors from bucket guanaco-reward-models
Deleting key cgato-l3-thespice-8b-sto-9357-v2_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key cgato-l3-thespice-8b-sto-9357-v2_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key cgato-l3-thespice-8b-sto-9357-v2_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key cgato-l3-thespice-8b-sto-9357-v2_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 2.07s
cgato-l3-thespice-8b-sto_9357_v2 status is now torndown due to DeploymentManager action