Running pipeline stage MKMLizer
Starting job with name saishf-merge-mayhem-l3-v2-v5-mkmlizer
Waiting for job on saishf-merge-mayhem-l3-v2-v5-mkmlizer to finish
saishf-merge-mayhem-l3-v2-v5-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
saishf-merge-mayhem-l3-v2-v5-mkmlizer: ║ _____ __ __ ║
saishf-merge-mayhem-l3-v2-v5-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
saishf-merge-mayhem-l3-v2-v5-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
saishf-merge-mayhem-l3-v2-v5-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
saishf-merge-mayhem-l3-v2-v5-mkmlizer: ║ /___/ ║
saishf-merge-mayhem-l3-v2-v5-mkmlizer: ║ ║
saishf-merge-mayhem-l3-v2-v5-mkmlizer: ║ Version: 0.8.10 ║
saishf-merge-mayhem-l3-v2-v5-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
saishf-merge-mayhem-l3-v2-v5-mkmlizer: ║ ║
saishf-merge-mayhem-l3-v2-v5-mkmlizer: ║ The license key for the current software has been verified as ║
saishf-merge-mayhem-l3-v2-v5-mkmlizer: ║ belonging to: ║
saishf-merge-mayhem-l3-v2-v5-mkmlizer: ║ ║
saishf-merge-mayhem-l3-v2-v5-mkmlizer: ║ Chai Research Corp. ║
saishf-merge-mayhem-l3-v2-v5-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
saishf-merge-mayhem-l3-v2-v5-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
saishf-merge-mayhem-l3-v2-v5-mkmlizer: ║ ║
saishf-merge-mayhem-l3-v2-v5-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
saishf-merge-mayhem-l3-v2-v5-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.
saishf-merge-mayhem-l3-v2-v5-mkmlizer: warnings.warn(warning_message, FutureWarning)
saishf-merge-mayhem-l3-v2-v5-mkmlizer: Downloaded to shared memory in 16.056s
saishf-merge-mayhem-l3-v2-v5-mkmlizer: quantizing model to /dev/shm/model_cache
saishf-merge-mayhem-l3-v2-v5-mkmlizer: Saving flywheel model at /dev/shm/model_cache
saishf-merge-mayhem-l3-v2-v5-mkmlizer:
Loading 0: 0%| | 0/291 [00:00<?, ?it/s]
Loading 0: 1%| | 2/291 [00:04<09:41, 2.01s/it]
Loading 0: 42%|████▏ | 122/291 [00:05<00:05, 29.85it/s]
Loading 0: 89%|████████▉ | 259/291 [00:06<00:00, 57.71it/s]
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
saishf-merge-mayhem-l3-v2-v5-mkmlizer: quantized model in 18.085s
saishf-merge-mayhem-l3-v2-v5-mkmlizer: Processed model saishf/Merge-Mayhem-L3-V2 in 35.279s
saishf-merge-mayhem-l3-v2-v5-mkmlizer: creating bucket guanaco-mkml-models
saishf-merge-mayhem-l3-v2-v5-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
saishf-merge-mayhem-l3-v2-v5-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/saishf-merge-mayhem-l3-v2-v5
saishf-merge-mayhem-l3-v2-v5-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/saishf-merge-mayhem-l3-v2-v5/tokenizer_config.json
saishf-merge-mayhem-l3-v2-v5-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/saishf-merge-mayhem-l3-v2-v5/special_tokens_map.json
saishf-merge-mayhem-l3-v2-v5-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/saishf-merge-mayhem-l3-v2-v5/config.json
saishf-merge-mayhem-l3-v2-v5-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/saishf-merge-mayhem-l3-v2-v5/tokenizer.json
saishf-merge-mayhem-l3-v2-v5-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/saishf-merge-mayhem-l3-v2-v5/flywheel_model.0.safetensors
saishf-merge-mayhem-l3-v2-v5-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
saishf-merge-mayhem-l3-v2-v5-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.
saishf-merge-mayhem-l3-v2-v5-mkmlizer: warnings.warn(
saishf-merge-mayhem-l3-v2-v5-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.
saishf-merge-mayhem-l3-v2-v5-mkmlizer: warnings.warn(
saishf-merge-mayhem-l3-v2-v5-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.
saishf-merge-mayhem-l3-v2-v5-mkmlizer: warnings.warn(
saishf-merge-mayhem-l3-v2-v5-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()
saishf-merge-mayhem-l3-v2-v5-mkmlizer: return self.fget.__get__(instance, owner)()
saishf-merge-mayhem-l3-v2-v5-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
saishf-merge-mayhem-l3-v2-v5-mkmlizer: Saving duration: 0.240s
saishf-merge-mayhem-l3-v2-v5-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 7.080s
saishf-merge-mayhem-l3-v2-v5-mkmlizer: creating bucket guanaco-reward-models
saishf-merge-mayhem-l3-v2-v5-mkmlizer: Bucket 's3://guanaco-reward-models/' created
saishf-merge-mayhem-l3-v2-v5-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/saishf-merge-mayhem-l3-v2-v5_reward
saishf-merge-mayhem-l3-v2-v5-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/saishf-merge-mayhem-l3-v2-v5_reward/config.json
saishf-merge-mayhem-l3-v2-v5-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/saishf-merge-mayhem-l3-v2-v5_reward/special_tokens_map.json
saishf-merge-mayhem-l3-v2-v5-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/saishf-merge-mayhem-l3-v2-v5_reward/tokenizer_config.json
saishf-merge-mayhem-l3-v2-v5-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/saishf-merge-mayhem-l3-v2-v5_reward/vocab.json
saishf-merge-mayhem-l3-v2-v5-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/saishf-merge-mayhem-l3-v2-v5_reward/merges.txt
saishf-merge-mayhem-l3-v2-v5-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/saishf-merge-mayhem-l3-v2-v5_reward/tokenizer.json
saishf-merge-mayhem-l3-v2-v5-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/saishf-merge-mayhem-l3-v2-v5_reward/reward.tensors
Job saishf-merge-mayhem-l3-v2-v5-mkmlizer completed after 72.88s with status: succeeded
Stopping job with name saishf-merge-mayhem-l3-v2-v5-mkmlizer
Pipeline stage MKMLizer completed in 75.52s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.66s
Running pipeline stage ISVCDeployer
Creating inference service saishf-merge-mayhem-l3-v2-v5
Waiting for inference service saishf-merge-mayhem-l3-v2-v5 to be ready
Inference service saishf-merge-mayhem-l3-v2-v5 ready after 140.72892498970032s
Pipeline stage ISVCDeployer completed in 147.59s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.3613314628601074s
Received healthy response to inference request in 1.6016428470611572s
Received healthy response to inference request in 1.3433458805084229s
Received healthy response to inference request in 1.3075082302093506s
Received healthy response to inference request in 1.3992843627929688s
5 requests
0 failed requests
5th percentile: 1.314675760269165
10th percentile: 1.3218432903289794
20th percentile: 1.3361783504486084
30th percentile: 1.354533576965332
40th percentile: 1.3769089698791503
50th percentile: 1.3992843627929688
60th percentile: 1.4802277565002442
70th percentile: 1.5611711502075194
80th percentile: 1.7535805702209475
90th percentile: 2.0574560165405273
95th percentile: 2.2093937397003174
99th percentile: 2.3309439182281495
mean time: 1.6026225566864014
Pipeline stage StressChecker completed in 8.61s
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 0.05s
M-Eval Dataset for topic stay_in_character is loaded
saishf-merge-mayhem-l3-v2_v5 status is now deployed due to DeploymentManager action
saishf-merge-mayhem-l3-v2_v5 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of saishf-merge-mayhem-l3-v2_v5
Running pipeline stage ISVCDeleter
Checking if service saishf-merge-mayhem-l3-v2-v5 is running
Tearing down inference service saishf-merge-mayhem-l3-v2-v5
Toredown service saishf-merge-mayhem-l3-v2-v5
Pipeline stage ISVCDeleter completed in 3.51s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key saishf-merge-mayhem-l3-v2-v5/config.json from bucket guanaco-mkml-models
Deleting key saishf-merge-mayhem-l3-v2-v5/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key saishf-merge-mayhem-l3-v2-v5/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key saishf-merge-mayhem-l3-v2-v5/tokenizer.json from bucket guanaco-mkml-models
Deleting key saishf-merge-mayhem-l3-v2-v5/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key saishf-merge-mayhem-l3-v2-v5_reward/config.json from bucket guanaco-reward-models
Deleting key saishf-merge-mayhem-l3-v2-v5_reward/merges.txt from bucket guanaco-reward-models
Deleting key saishf-merge-mayhem-l3-v2-v5_reward/reward.tensors from bucket guanaco-reward-models
Deleting key saishf-merge-mayhem-l3-v2-v5_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key saishf-merge-mayhem-l3-v2-v5_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key saishf-merge-mayhem-l3-v2-v5_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key saishf-merge-mayhem-l3-v2-v5_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 1.78s
saishf-merge-mayhem-l3-v2_v5 status is now torndown due to DeploymentManager action