Running pipeline stage MKMLizer
Starting job with name saishf-merge-mayhem-l3-v2-1-v7-mkmlizer
Waiting for job on saishf-merge-mayhem-l3-v2-1-v7-mkmlizer to finish
saishf-merge-mayhem-l3-v2-1-v7-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
saishf-merge-mayhem-l3-v2-1-v7-mkmlizer: ║ _____ __ __ ║
saishf-merge-mayhem-l3-v2-1-v7-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
saishf-merge-mayhem-l3-v2-1-v7-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
saishf-merge-mayhem-l3-v2-1-v7-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
saishf-merge-mayhem-l3-v2-1-v7-mkmlizer: ║ /___/ ║
saishf-merge-mayhem-l3-v2-1-v7-mkmlizer: ║ ║
saishf-merge-mayhem-l3-v2-1-v7-mkmlizer: ║ Version: 0.8.10 ║
saishf-merge-mayhem-l3-v2-1-v7-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
saishf-merge-mayhem-l3-v2-1-v7-mkmlizer: ║ ║
saishf-merge-mayhem-l3-v2-1-v7-mkmlizer: ║ The license key for the current software has been verified as ║
saishf-merge-mayhem-l3-v2-1-v7-mkmlizer: ║ belonging to: ║
saishf-merge-mayhem-l3-v2-1-v7-mkmlizer: ║ ║
saishf-merge-mayhem-l3-v2-1-v7-mkmlizer: ║ Chai Research Corp. ║
saishf-merge-mayhem-l3-v2-1-v7-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
saishf-merge-mayhem-l3-v2-1-v7-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
saishf-merge-mayhem-l3-v2-1-v7-mkmlizer: ║ ║
saishf-merge-mayhem-l3-v2-1-v7-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
saishf-merge-mayhem-l3-v2-1-v7-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-v2-1-v7-mkmlizer: warnings.warn(warning_message, FutureWarning)
saishf-merge-mayhem-l3-v2-1-v7-mkmlizer: Downloaded to shared memory in 13.040s
saishf-merge-mayhem-l3-v2-1-v7-mkmlizer: quantizing model to /dev/shm/model_cache
saishf-merge-mayhem-l3-v2-1-v7-mkmlizer: Saving flywheel model at /dev/shm/model_cache
saishf-merge-mayhem-l3-v2-1-v7-mkmlizer:
Loading 0: 0%| | 0/291 [00:00<?, ?it/s]
Loading 0: 1%| | 2/291 [00:04<10:41, 2.22s/it]
Loading 0: 42%|████▏ | 122/291 [00:05<00:06, 27.77it/s]
Loading 0: 91%|█████████▏| 266/291 [00:06<00:00, 56.25it/s]
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
saishf-merge-mayhem-l3-v2-1-v7-mkmlizer: quantized model in 18.892s
saishf-merge-mayhem-l3-v2-1-v7-mkmlizer: Processed model saishf/Merge-Mayhem-L3-V2.1 in 33.027s
saishf-merge-mayhem-l3-v2-1-v7-mkmlizer: creating bucket guanaco-mkml-models
saishf-merge-mayhem-l3-v2-1-v7-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
saishf-merge-mayhem-l3-v2-1-v7-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/saishf-merge-mayhem-l3-v2-1-v7
saishf-merge-mayhem-l3-v2-1-v7-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/saishf-merge-mayhem-l3-v2-1-v7/config.json
saishf-merge-mayhem-l3-v2-1-v7-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/saishf-merge-mayhem-l3-v2-1-v7/tokenizer_config.json
saishf-merge-mayhem-l3-v2-1-v7-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/saishf-merge-mayhem-l3-v2-1-v7/special_tokens_map.json
saishf-merge-mayhem-l3-v2-1-v7-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/saishf-merge-mayhem-l3-v2-1-v7/tokenizer.json
saishf-merge-mayhem-l3-v2-1-v7-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/saishf-merge-mayhem-l3-v2-1-v7/flywheel_model.0.safetensors
saishf-merge-mayhem-l3-v2-1-v7-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-v2-1-v7-mkmlizer: warnings.warn(
saishf-merge-mayhem-l3-v2-1-v7-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
saishf-merge-mayhem-l3-v2-1-v7-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-v2-1-v7-mkmlizer: warnings.warn(
saishf-merge-mayhem-l3-v2-1-v7-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-v2-1-v7-mkmlizer: warnings.warn(
saishf-merge-mayhem-l3-v2-1-v7-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-v2-1-v7-mkmlizer: return self.fget.__get__(instance, owner)()
saishf-merge-mayhem-l3-v2-1-v7-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
saishf-merge-mayhem-l3-v2-1-v7-mkmlizer: Saving duration: 0.225s
saishf-merge-mayhem-l3-v2-1-v7-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 6.931s
saishf-merge-mayhem-l3-v2-1-v7-mkmlizer: creating bucket guanaco-reward-models
saishf-merge-mayhem-l3-v2-1-v7-mkmlizer: Bucket 's3://guanaco-reward-models/' created
saishf-merge-mayhem-l3-v2-1-v7-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/saishf-merge-mayhem-l3-v2-1-v7_reward
saishf-merge-mayhem-l3-v2-1-v7-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/saishf-merge-mayhem-l3-v2-1-v7_reward/special_tokens_map.json
saishf-merge-mayhem-l3-v2-1-v7-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/saishf-merge-mayhem-l3-v2-1-v7_reward/tokenizer_config.json
saishf-merge-mayhem-l3-v2-1-v7-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/saishf-merge-mayhem-l3-v2-1-v7_reward/config.json
saishf-merge-mayhem-l3-v2-1-v7-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/saishf-merge-mayhem-l3-v2-1-v7_reward/vocab.json
saishf-merge-mayhem-l3-v2-1-v7-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/saishf-merge-mayhem-l3-v2-1-v7_reward/merges.txt
saishf-merge-mayhem-l3-v2-1-v7-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/saishf-merge-mayhem-l3-v2-1-v7_reward/tokenizer.json
saishf-merge-mayhem-l3-v2-1-v7-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/saishf-merge-mayhem-l3-v2-1-v7_reward/reward.tensors
Job saishf-merge-mayhem-l3-v2-1-v7-mkmlizer completed after 74.21s with status: succeeded
Stopping job with name saishf-merge-mayhem-l3-v2-1-v7-mkmlizer
Pipeline stage MKMLizer completed in 76.50s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.11s
Running pipeline stage ISVCDeployer
Creating inference service saishf-merge-mayhem-l3-v2-1-v7
Waiting for inference service saishf-merge-mayhem-l3-v2-1-v7 to be ready
Inference service saishf-merge-mayhem-l3-v2-1-v7 ready after 40.23542094230652s
Pipeline stage ISVCDeployer completed in 47.16s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.3377914428710938s
Received healthy response to inference request in 1.3514924049377441s
Received healthy response to inference request in 1.3372035026550293s
Received healthy response to inference request in 1.2876086235046387s
Received healthy response to inference request in 1.3771543502807617s
5 requests
0 failed requests
5th percentile: 1.2975275993347168
10th percentile: 1.307446575164795
20th percentile: 1.3272845268249511
30th percentile: 1.3400612831115724
40th percentile: 1.3457768440246582
50th percentile: 1.3514924049377441
60th percentile: 1.361757183074951
70th percentile: 1.3720219612121582
80th percentile: 1.5692817687988283
90th percentile: 1.953536605834961
95th percentile: 2.145664024353027
99th percentile: 2.2993659591674804
mean time: 1.5382500648498536
Pipeline stage StressChecker completed in 8.32s
Running pipeline stage DaemonicModelEvalScorer
Pipeline stage DaemonicModelEvalScorer completed in 0.03s
Running M-Eval for topic stay_in_character
Running pipeline stage DaemonicSafetyScorer
M-Eval Dataset for topic stay_in_character is loaded
Pipeline stage DaemonicSafetyScorer completed in 0.06s
saishf-merge-mayhem-l3-v2-1_v7 status is now deployed due to DeploymentManager action
saishf-merge-mayhem-l3-v2-1_v7 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of saishf-merge-mayhem-l3-v2-1_v7
Running pipeline stage ISVCDeleter
Checking if service saishf-merge-mayhem-l3-v2-1-v7 is running
Tearing down inference service saishf-merge-mayhem-l3-v2-1-v7
Toredown service saishf-merge-mayhem-l3-v2-1-v7
Pipeline stage ISVCDeleter completed in 7.71s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key saishf-merge-mayhem-l3-v2-1-v7/config.json from bucket guanaco-mkml-models
Deleting key saishf-merge-mayhem-l3-v2-1-v7/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key saishf-merge-mayhem-l3-v2-1-v7/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key saishf-merge-mayhem-l3-v2-1-v7/tokenizer.json from bucket guanaco-mkml-models
Deleting key saishf-merge-mayhem-l3-v2-1-v7/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key saishf-merge-mayhem-l3-v2-1-v7_reward/config.json from bucket guanaco-reward-models
Deleting key saishf-merge-mayhem-l3-v2-1-v7_reward/merges.txt from bucket guanaco-reward-models
Deleting key saishf-merge-mayhem-l3-v2-1-v7_reward/reward.tensors from bucket guanaco-reward-models
Deleting key saishf-merge-mayhem-l3-v2-1-v7_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key saishf-merge-mayhem-l3-v2-1-v7_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key saishf-merge-mayhem-l3-v2-1-v7_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key saishf-merge-mayhem-l3-v2-1-v7_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 1.90s
saishf-merge-mayhem-l3-v2-1_v7 status is now torndown due to DeploymentManager action