Running pipeline stage MKMLizer
Starting job with name cgato-l3-thespice-8b-v1-2-v1-mkmlizer
Waiting for job on cgato-l3-thespice-8b-v1-2-v1-mkmlizer to finish
Stopping job with name cgato-l3-thespice-8b-v1-2-v1-mkmlizer
%s, retrying in %s seconds...
Starting job with name cgato-l3-thespice-8b-v1-2-v1-mkmlizer
Waiting for job on cgato-l3-thespice-8b-v1-2-v1-mkmlizer to finish
cgato-l3-thespice-8b-v1-2-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cgato-l3-thespice-8b-v1-2-v1-mkmlizer: ║ _____ __ __ ║
cgato-l3-thespice-8b-v1-2-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
cgato-l3-thespice-8b-v1-2-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
cgato-l3-thespice-8b-v1-2-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
cgato-l3-thespice-8b-v1-2-v1-mkmlizer: ║ /___/ ║
cgato-l3-thespice-8b-v1-2-v1-mkmlizer: ║ ║
cgato-l3-thespice-8b-v1-2-v1-mkmlizer: ║ Version: 0.8.10 ║
cgato-l3-thespice-8b-v1-2-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
cgato-l3-thespice-8b-v1-2-v1-mkmlizer: ║ ║
cgato-l3-thespice-8b-v1-2-v1-mkmlizer: ║ The license key for the current software has been verified as ║
cgato-l3-thespice-8b-v1-2-v1-mkmlizer: ║ belonging to: ║
cgato-l3-thespice-8b-v1-2-v1-mkmlizer: ║ ║
cgato-l3-thespice-8b-v1-2-v1-mkmlizer: ║ Chai Research Corp. ║
cgato-l3-thespice-8b-v1-2-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
cgato-l3-thespice-8b-v1-2-v1-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
cgato-l3-thespice-8b-v1-2-v1-mkmlizer: ║ ║
cgato-l3-thespice-8b-v1-2-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
cgato-l3-thespice-8b-v1-2-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.
cgato-l3-thespice-8b-v1-2-v1-mkmlizer: warnings.warn(warning_message, FutureWarning)
cgato-l3-thespice-8b-v1-2-v1-mkmlizer: Downloaded to shared memory in 49.733s
cgato-l3-thespice-8b-v1-2-v1-mkmlizer: quantizing model to /dev/shm/model_cache
cgato-l3-thespice-8b-v1-2-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
cgato-l3-thespice-8b-v1-2-v1-mkmlizer:
Loading 0: 0%| | 0/291 [00:00<?, ?it/s]
Loading 0: 32%|███▏ | 93/291 [00:01<00:02, 92.04it/s]
Loading 0: 65%|██████▍ | 188/291 [00:02<00:01, 93.13it/s]
Loading 0: 99%|█████████▊| 287/291 [00:07<00:00, 29.82it/s]
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
cgato-l3-thespice-8b-v1-2-v1-mkmlizer: quantized model in 19.348s
cgato-l3-thespice-8b-v1-2-v1-mkmlizer: Processed model cgato/L3-TheSpice-8b-v1.2 in 70.134s
cgato-l3-thespice-8b-v1-2-v1-mkmlizer: creating bucket guanaco-mkml-models
cgato-l3-thespice-8b-v1-2-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cgato-l3-thespice-8b-v1-2-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/cgato-l3-thespice-8b-v1-2-v1
cgato-l3-thespice-8b-v1-2-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/cgato-l3-thespice-8b-v1-2-v1/config.json
cgato-l3-thespice-8b-v1-2-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/cgato-l3-thespice-8b-v1-2-v1/special_tokens_map.json
cgato-l3-thespice-8b-v1-2-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/cgato-l3-thespice-8b-v1-2-v1/tokenizer_config.json
cgato-l3-thespice-8b-v1-2-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/cgato-l3-thespice-8b-v1-2-v1/tokenizer.json
cgato-l3-thespice-8b-v1-2-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/cgato-l3-thespice-8b-v1-2-v1/flywheel_model.0.safetensors
cgato-l3-thespice-8b-v1-2-v1-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
cgato-l3-thespice-8b-v1-2-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.
cgato-l3-thespice-8b-v1-2-v1-mkmlizer: warnings.warn(
cgato-l3-thespice-8b-v1-2-v1-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-v1-2-v1-mkmlizer: warnings.warn(
cgato-l3-thespice-8b-v1-2-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.
cgato-l3-thespice-8b-v1-2-v1-mkmlizer: warnings.warn(
cgato-l3-thespice-8b-v1-2-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()
cgato-l3-thespice-8b-v1-2-v1-mkmlizer: return self.fget.__get__(instance, owner)()
cgato-l3-thespice-8b-v1-2-v1-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
cgato-l3-thespice-8b-v1-2-v1-mkmlizer: Saving duration: 0.259s
cgato-l3-thespice-8b-v1-2-v1-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 5.669s
cgato-l3-thespice-8b-v1-2-v1-mkmlizer: creating bucket guanaco-reward-models
cgato-l3-thespice-8b-v1-2-v1-mkmlizer: Bucket 's3://guanaco-reward-models/' created
cgato-l3-thespice-8b-v1-2-v1-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/cgato-l3-thespice-8b-v1-2-v1_reward
cgato-l3-thespice-8b-v1-2-v1-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/cgato-l3-thespice-8b-v1-2-v1_reward/tokenizer_config.json
cgato-l3-thespice-8b-v1-2-v1-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/cgato-l3-thespice-8b-v1-2-v1_reward/special_tokens_map.json
cgato-l3-thespice-8b-v1-2-v1-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/cgato-l3-thespice-8b-v1-2-v1_reward/config.json
cgato-l3-thespice-8b-v1-2-v1-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/cgato-l3-thespice-8b-v1-2-v1_reward/vocab.json
cgato-l3-thespice-8b-v1-2-v1-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/cgato-l3-thespice-8b-v1-2-v1_reward/merges.txt
cgato-l3-thespice-8b-v1-2-v1-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/cgato-l3-thespice-8b-v1-2-v1_reward/tokenizer.json
cgato-l3-thespice-8b-v1-2-v1-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/cgato-l3-thespice-8b-v1-2-v1_reward/reward.tensors
Job cgato-l3-thespice-8b-v1-2-v1-mkmlizer completed after 98.43s with status: succeeded
Stopping job with name cgato-l3-thespice-8b-v1-2-v1-mkmlizer
Pipeline stage MKMLizer completed in 103.29s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.09s
Running pipeline stage ISVCDeployer
Creating inference service cgato-l3-thespice-8b-v1-2-v1
Waiting for inference service cgato-l3-thespice-8b-v1-2-v1 to be ready
Inference service cgato-l3-thespice-8b-v1-2-v1 ready after 30.584184408187866s
Pipeline stage ISVCDeployer completed in 38.39s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.1499390602111816s
Received healthy response to inference request in 1.951829433441162s
Received healthy response to inference request in 1.3263866901397705s
Received healthy response to inference request in 1.2942144870758057s
Received healthy response to inference request in 1.3370559215545654s
5 requests
0 failed requests
5th percentile: 1.3006489276885986
10th percentile: 1.3070833683013916
20th percentile: 1.3199522495269775
30th percentile: 1.3285205364227295
40th percentile: 1.3327882289886475
50th percentile: 1.3370559215545654
60th percentile: 1.582965326309204
70th percentile: 1.8288747310638427
80th percentile: 1.991451358795166
90th percentile: 2.0706952095031737
95th percentile: 2.1103171348571776
99th percentile: 2.142014675140381
mean time: 1.6118851184844971
Pipeline stage StressChecker completed in 8.74s
Running pipeline stage DaemonicModelEvalScorer
Pipeline stage DaemonicModelEvalScorer completed in 0.05s
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
cgato-l3-thespice-8b-v1-2_v1 status is now deployed due to DeploymentManager action
cgato-l3-thespice-8b-v1-2_v1 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of cgato-l3-thespice-8b-v1-2_v1
Running pipeline stage ISVCDeleter
Checking if service cgato-l3-thespice-8b-v1-2-v1 is running
Tearing down inference service cgato-l3-thespice-8b-v1-2-v1
Toredown service cgato-l3-thespice-8b-v1-2-v1
Pipeline stage ISVCDeleter completed in 4.44s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key cgato-l3-thespice-8b-v1-2-v1/config.json from bucket guanaco-mkml-models
Deleting key cgato-l3-thespice-8b-v1-2-v1/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key cgato-l3-thespice-8b-v1-2-v1/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key cgato-l3-thespice-8b-v1-2-v1/tokenizer.json from bucket guanaco-mkml-models
Deleting key cgato-l3-thespice-8b-v1-2-v1/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key cgato-l3-thespice-8b-v1-2-v1_reward/config.json from bucket guanaco-reward-models
Deleting key cgato-l3-thespice-8b-v1-2-v1_reward/merges.txt from bucket guanaco-reward-models
Deleting key cgato-l3-thespice-8b-v1-2-v1_reward/reward.tensors from bucket guanaco-reward-models
Deleting key cgato-l3-thespice-8b-v1-2-v1_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key cgato-l3-thespice-8b-v1-2-v1_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key cgato-l3-thespice-8b-v1-2-v1_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key cgato-l3-thespice-8b-v1-2-v1_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 2.83s
cgato-l3-thespice-8b-v1-2_v1 status is now torndown due to DeploymentManager action