Running pipeline stage MKMLizer
Starting job with name cgato-l3-thespice-8b-dpo-3749-v1-mkmlizer
Waiting for job on cgato-l3-thespice-8b-dpo-3749-v1-mkmlizer to finish
cgato-l3-thespice-8b-dpo-3749-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cgato-l3-thespice-8b-dpo-3749-v1-mkmlizer: ║ _____ __ __ ║
cgato-l3-thespice-8b-dpo-3749-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
cgato-l3-thespice-8b-dpo-3749-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
cgato-l3-thespice-8b-dpo-3749-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
cgato-l3-thespice-8b-dpo-3749-v1-mkmlizer: ║ /___/ ║
cgato-l3-thespice-8b-dpo-3749-v1-mkmlizer: ║ ║
cgato-l3-thespice-8b-dpo-3749-v1-mkmlizer: ║ Version: 0.8.10 ║
cgato-l3-thespice-8b-dpo-3749-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
cgato-l3-thespice-8b-dpo-3749-v1-mkmlizer: ║ ║
cgato-l3-thespice-8b-dpo-3749-v1-mkmlizer: ║ The license key for the current software has been verified as ║
cgato-l3-thespice-8b-dpo-3749-v1-mkmlizer: ║ belonging to: ║
cgato-l3-thespice-8b-dpo-3749-v1-mkmlizer: ║ ║
cgato-l3-thespice-8b-dpo-3749-v1-mkmlizer: ║ Chai Research Corp. ║
cgato-l3-thespice-8b-dpo-3749-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
cgato-l3-thespice-8b-dpo-3749-v1-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
cgato-l3-thespice-8b-dpo-3749-v1-mkmlizer: ║ ║
cgato-l3-thespice-8b-dpo-3749-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
cgato-l3-thespice-8b-dpo-3749-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-dpo-3749-v1-mkmlizer: warnings.warn(warning_message, FutureWarning)
cgato-l3-thespice-8b-dpo-3749-v1-mkmlizer: Downloaded to shared memory in 25.046s
cgato-l3-thespice-8b-dpo-3749-v1-mkmlizer: quantizing model to /dev/shm/model_cache
cgato-l3-thespice-8b-dpo-3749-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
Failed to get response for submission blend_kefet_2024-05-01: ('http://mistralai-mixtral-8x7b-3473-v33-predictor-default.tenant-chaiml-guanaco.knative.ord1.coreweave.cloud/v1/models/GPT-J-6B-lit-v2:predict', 'upstream connect error or disconnect/reset before headers. reset reason: overflow')
cgato-l3-thespice-8b-dpo-3749-v1-mkmlizer:
Loading 0: 0%| | 0/291 [00:00<?, ?it/s]
Loading 0: 64%|██████▍ | 187/291 [00:01<00:01, 97.09it/s]
Loading 0: 100%|██████████| 291/291 [00:06<00:00, 37.63it/s]
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
cgato-l3-thespice-8b-dpo-3749-v1-mkmlizer: quantized model in 18.192s
cgato-l3-thespice-8b-dpo-3749-v1-mkmlizer: Processed model cgato/L3-TheSpice-8b-DPO-v2.3-e6.1 in 44.323s
cgato-l3-thespice-8b-dpo-3749-v1-mkmlizer: creating bucket guanaco-mkml-models
cgato-l3-thespice-8b-dpo-3749-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cgato-l3-thespice-8b-dpo-3749-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/cgato-l3-thespice-8b-dpo-3749-v1
cgato-l3-thespice-8b-dpo-3749-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/cgato-l3-thespice-8b-dpo-3749-v1/config.json
cgato-l3-thespice-8b-dpo-3749-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/cgato-l3-thespice-8b-dpo-3749-v1/tokenizer_config.json
cgato-l3-thespice-8b-dpo-3749-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/cgato-l3-thespice-8b-dpo-3749-v1/special_tokens_map.json
cgato-l3-thespice-8b-dpo-3749-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/cgato-l3-thespice-8b-dpo-3749-v1/tokenizer.json
cgato-l3-thespice-8b-dpo-3749-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/cgato-l3-thespice-8b-dpo-3749-v1/flywheel_model.0.safetensors
cgato-l3-thespice-8b-dpo-3749-v1-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
cgato-l3-thespice-8b-dpo-3749-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-dpo-3749-v1-mkmlizer: warnings.warn(
cgato-l3-thespice-8b-dpo-3749-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-dpo-3749-v1-mkmlizer: warnings.warn(
cgato-l3-thespice-8b-dpo-3749-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-dpo-3749-v1-mkmlizer: warnings.warn(
cgato-l3-thespice-8b-dpo-3749-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-dpo-3749-v1-mkmlizer: return self.fget.__get__(instance, owner)()
cgato-l3-thespice-8b-dpo-3749-v1-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
cgato-l3-thespice-8b-dpo-3749-v1-mkmlizer: Saving duration: 0.259s
cgato-l3-thespice-8b-dpo-3749-v1-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 3.747s
cgato-l3-thespice-8b-dpo-3749-v1-mkmlizer: creating bucket guanaco-reward-models
cgato-l3-thespice-8b-dpo-3749-v1-mkmlizer: Bucket 's3://guanaco-reward-models/' created
cgato-l3-thespice-8b-dpo-3749-v1-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/cgato-l3-thespice-8b-dpo-3749-v1_reward
cgato-l3-thespice-8b-dpo-3749-v1-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/cgato-l3-thespice-8b-dpo-3749-v1_reward/config.json
cgato-l3-thespice-8b-dpo-3749-v1-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/cgato-l3-thespice-8b-dpo-3749-v1_reward/tokenizer_config.json
cgato-l3-thespice-8b-dpo-3749-v1-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/cgato-l3-thespice-8b-dpo-3749-v1_reward/merges.txt
cgato-l3-thespice-8b-dpo-3749-v1-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/cgato-l3-thespice-8b-dpo-3749-v1_reward/special_tokens_map.json
cgato-l3-thespice-8b-dpo-3749-v1-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/cgato-l3-thespice-8b-dpo-3749-v1_reward/vocab.json
cgato-l3-thespice-8b-dpo-3749-v1-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/cgato-l3-thespice-8b-dpo-3749-v1_reward/tokenizer.json
cgato-l3-thespice-8b-dpo-3749-v1-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/cgato-l3-thespice-8b-dpo-3749-v1_reward/reward.tensors
Job cgato-l3-thespice-8b-dpo-3749-v1-mkmlizer completed after 73.14s with status: succeeded
Stopping job with name cgato-l3-thespice-8b-dpo-3749-v1-mkmlizer
Pipeline stage MKMLizer completed in 76.32s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.10s
Running pipeline stage ISVCDeployer
Creating inference service cgato-l3-thespice-8b-dpo-3749-v1
Waiting for inference service cgato-l3-thespice-8b-dpo-3749-v1 to be ready
Inference service cgato-l3-thespice-8b-dpo-3749-v1 ready after 30.176103353500366s
Pipeline stage ISVCDeployer completed in 36.89s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.1996397972106934s
Received healthy response to inference request in 1.3007259368896484s
Received healthy response to inference request in 1.289478063583374s
Received healthy response to inference request in 1.2906639575958252s
Received healthy response to inference request in 1.3055295944213867s
5 requests
0 failed requests
5th percentile: 1.2897152423858642
10th percentile: 1.2899524211883544
20th percentile: 1.290426778793335
30th percentile: 1.2926763534545898
40th percentile: 1.296701145172119
50th percentile: 1.3007259368896484
60th percentile: 1.3026473999023438
70th percentile: 1.3045688629150392
80th percentile: 1.4843516349792483
90th percentile: 1.8419957160949707
95th percentile: 2.020817756652832
99th percentile: 2.163875389099121
mean time: 1.4772074699401856
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-dpo_3749_v1 status is now deployed due to DeploymentManager action
cgato-l3-thespice-8b-dpo_3749_v1 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of cgato-l3-thespice-8b-dpo_3749_v1
Running pipeline stage ISVCDeleter
Checking if service cgato-l3-thespice-8b-dpo-3749-v1 is running
Tearing down inference service cgato-l3-thespice-8b-dpo-3749-v1
Toredown service cgato-l3-thespice-8b-dpo-3749-v1
Pipeline stage ISVCDeleter completed in 5.14s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key cgato-l3-thespice-8b-dpo-3749-v1/config.json from bucket guanaco-mkml-models
Deleting key cgato-l3-thespice-8b-dpo-3749-v1/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key cgato-l3-thespice-8b-dpo-3749-v1/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key cgato-l3-thespice-8b-dpo-3749-v1/tokenizer.json from bucket guanaco-mkml-models
Deleting key cgato-l3-thespice-8b-dpo-3749-v1/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key cgato-l3-thespice-8b-dpo-3749-v1_reward/config.json from bucket guanaco-reward-models
Deleting key cgato-l3-thespice-8b-dpo-3749-v1_reward/merges.txt from bucket guanaco-reward-models
Deleting key cgato-l3-thespice-8b-dpo-3749-v1_reward/reward.tensors from bucket guanaco-reward-models
Deleting key cgato-l3-thespice-8b-dpo-3749-v1_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key cgato-l3-thespice-8b-dpo-3749-v1_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key cgato-l3-thespice-8b-dpo-3749-v1_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key cgato-l3-thespice-8b-dpo-3749-v1_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 2.72s
cgato-l3-thespice-8b-dpo_3749_v1 status is now torndown due to DeploymentManager action