Running pipeline stage MKMLizer
Starting job with name cgato-blipblop-l3-8b-dpo-8001-v1-mkmlizer
Waiting for job on cgato-blipblop-l3-8b-dpo-8001-v1-mkmlizer to finish
cgato-blipblop-l3-8b-dpo-8001-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cgato-blipblop-l3-8b-dpo-8001-v1-mkmlizer: ║ _____ __ __ ║
cgato-blipblop-l3-8b-dpo-8001-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
cgato-blipblop-l3-8b-dpo-8001-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
cgato-blipblop-l3-8b-dpo-8001-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
cgato-blipblop-l3-8b-dpo-8001-v1-mkmlizer: ║ /___/ ║
cgato-blipblop-l3-8b-dpo-8001-v1-mkmlizer: ║ ║
cgato-blipblop-l3-8b-dpo-8001-v1-mkmlizer: ║ Version: 0.8.14 ║
cgato-blipblop-l3-8b-dpo-8001-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
cgato-blipblop-l3-8b-dpo-8001-v1-mkmlizer: ║ https://mk1.ai ║
cgato-blipblop-l3-8b-dpo-8001-v1-mkmlizer: ║ ║
cgato-blipblop-l3-8b-dpo-8001-v1-mkmlizer: ║ The license key for the current software has been verified as ║
cgato-blipblop-l3-8b-dpo-8001-v1-mkmlizer: ║ belonging to: ║
cgato-blipblop-l3-8b-dpo-8001-v1-mkmlizer: ║ ║
cgato-blipblop-l3-8b-dpo-8001-v1-mkmlizer: ║ Chai Research Corp. ║
cgato-blipblop-l3-8b-dpo-8001-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
cgato-blipblop-l3-8b-dpo-8001-v1-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
cgato-blipblop-l3-8b-dpo-8001-v1-mkmlizer: ║ ║
cgato-blipblop-l3-8b-dpo-8001-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
cgato-blipblop-l3-8b-dpo-8001-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-blipblop-l3-8b-dpo-8001-v1-mkmlizer: warnings.warn(warning_message, FutureWarning)
cgato-blipblop-l3-8b-dpo-8001-v1-mkmlizer: Downloaded to shared memory in 27.224s
cgato-blipblop-l3-8b-dpo-8001-v1-mkmlizer: quantizing model to /dev/shm/model_cache
cgato-blipblop-l3-8b-dpo-8001-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
cgato-blipblop-l3-8b-dpo-8001-v1-mkmlizer:
Loading 0: 0%| | 0/291 [00:00<?, ?it/s]
Loading 0: 29%|██▊ | 83/291 [00:00<00:02, 95.41it/s]
Loading 0: 64%|██████▍ | 187/291 [00:01<00:00, 112.57it/s]
Loading 0: 99%|█████████▊| 287/291 [00:02<00:00, 160.06it/s]
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
cgato-blipblop-l3-8b-dpo-8001-v1-mkmlizer: quantized model in 17.358s
cgato-blipblop-l3-8b-dpo-8001-v1-mkmlizer: Processed model cgato/BlipBlop-L3-8b-DPO-v0.1.1-e0.2 in 45.566s
cgato-blipblop-l3-8b-dpo-8001-v1-mkmlizer: creating bucket guanaco-mkml-models
cgato-blipblop-l3-8b-dpo-8001-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cgato-blipblop-l3-8b-dpo-8001-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/cgato-blipblop-l3-8b-dpo-8001-v1
cgato-blipblop-l3-8b-dpo-8001-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/cgato-blipblop-l3-8b-dpo-8001-v1/config.json
cgato-blipblop-l3-8b-dpo-8001-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/cgato-blipblop-l3-8b-dpo-8001-v1/special_tokens_map.json
cgato-blipblop-l3-8b-dpo-8001-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/cgato-blipblop-l3-8b-dpo-8001-v1/tokenizer_config.json
cgato-blipblop-l3-8b-dpo-8001-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/cgato-blipblop-l3-8b-dpo-8001-v1/tokenizer.json
cgato-blipblop-l3-8b-dpo-8001-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/cgato-blipblop-l3-8b-dpo-8001-v1/flywheel_model.0.safetensors
cgato-blipblop-l3-8b-dpo-8001-v1-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
cgato-blipblop-l3-8b-dpo-8001-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-blipblop-l3-8b-dpo-8001-v1-mkmlizer: warnings.warn(
cgato-blipblop-l3-8b-dpo-8001-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-blipblop-l3-8b-dpo-8001-v1-mkmlizer: warnings.warn(
cgato-blipblop-l3-8b-dpo-8001-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-blipblop-l3-8b-dpo-8001-v1-mkmlizer: warnings.warn(
cgato-blipblop-l3-8b-dpo-8001-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-blipblop-l3-8b-dpo-8001-v1-mkmlizer: return self.fget.__get__(instance, owner)()
cgato-blipblop-l3-8b-dpo-8001-v1-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
cgato-blipblop-l3-8b-dpo-8001-v1-mkmlizer: Saving duration: 0.233s
cgato-blipblop-l3-8b-dpo-8001-v1-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 7.289s
cgato-blipblop-l3-8b-dpo-8001-v1-mkmlizer: creating bucket guanaco-reward-models
cgato-blipblop-l3-8b-dpo-8001-v1-mkmlizer: Bucket 's3://guanaco-reward-models/' created
cgato-blipblop-l3-8b-dpo-8001-v1-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/cgato-blipblop-l3-8b-dpo-8001-v1_reward
cgato-blipblop-l3-8b-dpo-8001-v1-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/cgato-blipblop-l3-8b-dpo-8001-v1_reward/tokenizer_config.json
cgato-blipblop-l3-8b-dpo-8001-v1-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/cgato-blipblop-l3-8b-dpo-8001-v1_reward/config.json
cgato-blipblop-l3-8b-dpo-8001-v1-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/cgato-blipblop-l3-8b-dpo-8001-v1_reward/special_tokens_map.json
cgato-blipblop-l3-8b-dpo-8001-v1-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/cgato-blipblop-l3-8b-dpo-8001-v1_reward/vocab.json
cgato-blipblop-l3-8b-dpo-8001-v1-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/cgato-blipblop-l3-8b-dpo-8001-v1_reward/merges.txt
cgato-blipblop-l3-8b-dpo-8001-v1-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/cgato-blipblop-l3-8b-dpo-8001-v1_reward/tokenizer.json
cgato-blipblop-l3-8b-dpo-8001-v1-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/cgato-blipblop-l3-8b-dpo-8001-v1_reward/reward.tensors
Job cgato-blipblop-l3-8b-dpo-8001-v1-mkmlizer completed after 73.48s with status: succeeded
Stopping job with name cgato-blipblop-l3-8b-dpo-8001-v1-mkmlizer
Pipeline stage MKMLizer completed in 77.71s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.08s
Running pipeline stage ISVCDeployer
Creating inference service cgato-blipblop-l3-8b-dpo-8001-v1
Waiting for inference service cgato-blipblop-l3-8b-dpo-8001-v1 to be ready
Tearing down inference service cgato-blipblop-l3-8b-dpo-8001-v1
%s, retrying in %s seconds...
Creating inference service cgato-blipblop-l3-8b-dpo-8001-v1
Waiting for inference service cgato-blipblop-l3-8b-dpo-8001-v1 to be ready
Inference service cgato-blipblop-l3-8b-dpo-8001-v1 ready after 412.12502241134644s
Pipeline stage ISVCDeployer completed in 1028.25s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.223583698272705s
Received healthy response to inference request in 1.308223009109497s
Received healthy response to inference request in 1.3018791675567627s
Received healthy response to inference request in 6.754003524780273s
Received healthy response to inference request in 1.299177885055542s
5 requests
0 failed requests
5th percentile: 1.2997181415557861
10th percentile: 1.3002583980560303
20th percentile: 1.3013389110565186
30th percentile: 1.3031479358673095
40th percentile: 1.3056854724884033
50th percentile: 1.308223009109497
60th percentile: 1.6743672847747801
70th percentile: 2.040511560440063
80th percentile: 3.1296676635742195
90th percentile: 4.941835594177246
95th percentile: 5.847919559478759
99th percentile: 6.572786731719971
mean time: 2.5773734569549562
Pipeline stage StressChecker completed in 13.52s
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-blipblop-l3-8b-dpo_8001_v1 status is now deployed due to DeploymentManager action
cgato-blipblop-l3-8b-dpo_8001_v1 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of cgato-blipblop-l3-8b-dpo_8001_v1
Running pipeline stage ISVCDeleter
Checking if service cgato-blipblop-l3-8b-dpo-8001-v1 is running
Skipping teardown as no inference service was found
Pipeline stage ISVCDeleter completed in 1.93s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key cgato-blipblop-l3-8b-dpo-8001-v1/config.json from bucket guanaco-mkml-models
Deleting key cgato-blipblop-l3-8b-dpo-8001-v1/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key cgato-blipblop-l3-8b-dpo-8001-v1/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key cgato-blipblop-l3-8b-dpo-8001-v1/tokenizer.json from bucket guanaco-mkml-models
Deleting key cgato-blipblop-l3-8b-dpo-8001-v1/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key cgato-blipblop-l3-8b-dpo-8001-v1_reward/config.json from bucket guanaco-reward-models
Deleting key cgato-blipblop-l3-8b-dpo-8001-v1_reward/merges.txt from bucket guanaco-reward-models
Deleting key cgato-blipblop-l3-8b-dpo-8001-v1_reward/reward.tensors from bucket guanaco-reward-models
Deleting key cgato-blipblop-l3-8b-dpo-8001-v1_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key cgato-blipblop-l3-8b-dpo-8001-v1_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key cgato-blipblop-l3-8b-dpo-8001-v1_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key cgato-blipblop-l3-8b-dpo-8001-v1_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 3.27s
cgato-blipblop-l3-8b-dpo_8001_v1 status is now torndown due to DeploymentManager action