Running pipeline stage MKMLizer
Starting job with name cgato-l3-thespice-8b-v0-3-3-v2-mkmlizer
Waiting for job on cgato-l3-thespice-8b-v0-3-3-v2-mkmlizer to finish
cgato-l3-thespice-8b-v0-3-3-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cgato-l3-thespice-8b-v0-3-3-v2-mkmlizer: ║ _____ __ __ ║
cgato-l3-thespice-8b-v0-3-3-v2-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
cgato-l3-thespice-8b-v0-3-3-v2-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
cgato-l3-thespice-8b-v0-3-3-v2-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
cgato-l3-thespice-8b-v0-3-3-v2-mkmlizer: ║ /___/ ║
cgato-l3-thespice-8b-v0-3-3-v2-mkmlizer: ║ ║
cgato-l3-thespice-8b-v0-3-3-v2-mkmlizer: ║ Version: 0.8.10 ║
cgato-l3-thespice-8b-v0-3-3-v2-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
cgato-l3-thespice-8b-v0-3-3-v2-mkmlizer: ║ ║
cgato-l3-thespice-8b-v0-3-3-v2-mkmlizer: ║ The license key for the current software has been verified as ║
cgato-l3-thespice-8b-v0-3-3-v2-mkmlizer: ║ belonging to: ║
cgato-l3-thespice-8b-v0-3-3-v2-mkmlizer: ║ ║
cgato-l3-thespice-8b-v0-3-3-v2-mkmlizer: ║ Chai Research Corp. ║
cgato-l3-thespice-8b-v0-3-3-v2-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
cgato-l3-thespice-8b-v0-3-3-v2-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
cgato-l3-thespice-8b-v0-3-3-v2-mkmlizer: ║ ║
cgato-l3-thespice-8b-v0-3-3-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
cgato-l3-thespice-8b-v0-3-3-v2-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-v0-3-3-v2-mkmlizer: warnings.warn(warning_message, FutureWarning)
cgato-l3-thespice-8b-v0-3-3-v2-mkmlizer: Downloaded to shared memory in 15.477s
cgato-l3-thespice-8b-v0-3-3-v2-mkmlizer: quantizing model to /dev/shm/model_cache
cgato-l3-thespice-8b-v0-3-3-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
cgato-l3-thespice-8b-v0-3-3-v2-mkmlizer:
Loading 0: 0%| | 0/291 [00:00<?, ?it/s]
Loading 0: 42%|████▏ | 122/291 [00:01<00:01, 120.73it/s]
Loading 0: 88%|████████▊ | 256/291 [00:02<00:00, 127.73it/s]
Loading 0: 99%|█████████▊| 287/291 [00:07<00:00, 27.68it/s]
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
cgato-l3-thespice-8b-v0-3-3-v2-mkmlizer: quantized model in 18.975s
cgato-l3-thespice-8b-v0-3-3-v2-mkmlizer: Processed model cgato/L3-TheSpice-8b-v0.3.3 in 35.561s
cgato-l3-thespice-8b-v0-3-3-v2-mkmlizer: creating bucket guanaco-mkml-models
cgato-l3-thespice-8b-v0-3-3-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cgato-l3-thespice-8b-v0-3-3-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/cgato-l3-thespice-8b-v0-3-3-v2
cgato-l3-thespice-8b-v0-3-3-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/cgato-l3-thespice-8b-v0-3-3-v2/config.json
cgato-l3-thespice-8b-v0-3-3-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/cgato-l3-thespice-8b-v0-3-3-v2/tokenizer_config.json
cgato-l3-thespice-8b-v0-3-3-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/cgato-l3-thespice-8b-v0-3-3-v2/special_tokens_map.json
cgato-l3-thespice-8b-v0-3-3-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/cgato-l3-thespice-8b-v0-3-3-v2/tokenizer.json
cgato-l3-thespice-8b-v0-3-3-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/cgato-l3-thespice-8b-v0-3-3-v2/flywheel_model.0.safetensors
cgato-l3-thespice-8b-v0-3-3-v2-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
cgato-l3-thespice-8b-v0-3-3-v2-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-v0-3-3-v2-mkmlizer: warnings.warn(
cgato-l3-thespice-8b-v0-3-3-v2-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-v0-3-3-v2-mkmlizer: warnings.warn(
cgato-l3-thespice-8b-v0-3-3-v2-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-v0-3-3-v2-mkmlizer: warnings.warn(
cgato-l3-thespice-8b-v0-3-3-v2-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-v0-3-3-v2-mkmlizer: return self.fget.__get__(instance, owner)()
cgato-l3-thespice-8b-v0-3-3-v2-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
cgato-l3-thespice-8b-v0-3-3-v2-mkmlizer: Saving duration: 0.260s
cgato-l3-thespice-8b-v0-3-3-v2-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 3.406s
cgato-l3-thespice-8b-v0-3-3-v2-mkmlizer: creating bucket guanaco-reward-models
cgato-l3-thespice-8b-v0-3-3-v2-mkmlizer: Bucket 's3://guanaco-reward-models/' created
cgato-l3-thespice-8b-v0-3-3-v2-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/cgato-l3-thespice-8b-v0-3-3-v2_reward
cgato-l3-thespice-8b-v0-3-3-v2-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/cgato-l3-thespice-8b-v0-3-3-v2_reward/config.json
cgato-l3-thespice-8b-v0-3-3-v2-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/cgato-l3-thespice-8b-v0-3-3-v2_reward/special_tokens_map.json
cgato-l3-thespice-8b-v0-3-3-v2-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/cgato-l3-thespice-8b-v0-3-3-v2_reward/merges.txt
cgato-l3-thespice-8b-v0-3-3-v2-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/cgato-l3-thespice-8b-v0-3-3-v2_reward/tokenizer_config.json
cgato-l3-thespice-8b-v0-3-3-v2-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/cgato-l3-thespice-8b-v0-3-3-v2_reward/vocab.json
cgato-l3-thespice-8b-v0-3-3-v2-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/cgato-l3-thespice-8b-v0-3-3-v2_reward/tokenizer.json
cgato-l3-thespice-8b-v0-3-3-v2-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/cgato-l3-thespice-8b-v0-3-3-v2_reward/reward.tensors
Job cgato-l3-thespice-8b-v0-3-3-v2-mkmlizer completed after 63.58s with status: succeeded
Stopping job with name cgato-l3-thespice-8b-v0-3-3-v2-mkmlizer
Pipeline stage MKMLizer completed in 67.61s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.25s
Running pipeline stage ISVCDeployer
Creating inference service cgato-l3-thespice-8b-v0-3-3-v2
Waiting for inference service cgato-l3-thespice-8b-v0-3-3-v2 to be ready
Inference service cgato-l3-thespice-8b-v0-3-3-v2 ready after 40.231801986694336s
Pipeline stage ISVCDeployer completed in 47.41s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.068269968032837s
Received healthy response to inference request in 1.3537898063659668s
Received healthy response to inference request in 1.2912986278533936s
Failed to get response for submission blend_mugub_2024-02-25: ('http://chaiml-phase2-winner-13b2-v232-predictor-default.tenant-chaiml-guanaco.knative.ord1.coreweave.cloud/v1/models/GPT-J-6B-lit-v2:predict', 'readfrom tcp 127.0.0.1:56558->127.0.0.1:8080: write tcp 127.0.0.1:56558->127.0.0.1:8080: use of closed network connection\n')
Received healthy response to inference request in 1.2771587371826172s
Received healthy response to inference request in 1.3388397693634033s
5 requests
0 failed requests
5th percentile: 1.2799867153167725
10th percentile: 1.2828146934509277
20th percentile: 1.2884706497192382
30th percentile: 1.3008068561553956
40th percentile: 1.3198233127593995
50th percentile: 1.3388397693634033
60th percentile: 1.3448197841644287
70th percentile: 1.350799798965454
80th percentile: 1.496685838699341
90th percentile: 1.782477903366089
95th percentile: 1.9253739356994628
99th percentile: 2.039690761566162
mean time: 1.4658713817596436
Pipeline stage StressChecker completed in 8.03s
Running pipeline stage DaemonicModelEvalScorer
Pipeline stage DaemonicModelEvalScorer completed in 0.03s
Running pipeline stage DaemonicSafetyScorer
Pipeline stage DaemonicSafetyScorer completed in 0.03s
Running M-Eval for topic stay_in_character
cgato-l3-thespice-8b-v0-3-3_v2 status is now deployed due to DeploymentManager action
M-Eval Dataset for topic stay_in_character is loaded
cgato-l3-thespice-8b-v0-3-3_v2 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of cgato-l3-thespice-8b-v0-3-3_v2
Running pipeline stage ISVCDeleter
Checking if service cgato-l3-thespice-8b-v0-3-3-v2 is running
Tearing down inference service cgato-l3-thespice-8b-v0-3-3-v2
Toredown service cgato-l3-thespice-8b-v0-3-3-v2
Pipeline stage ISVCDeleter completed in 5.41s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key cgato-l3-thespice-8b-v0-3-3-v2/config.json from bucket guanaco-mkml-models
Deleting key cgato-l3-thespice-8b-v0-3-3-v2/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key cgato-l3-thespice-8b-v0-3-3-v2/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key cgato-l3-thespice-8b-v0-3-3-v2/tokenizer.json from bucket guanaco-mkml-models
Deleting key cgato-l3-thespice-8b-v0-3-3-v2/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key cgato-l3-thespice-8b-v0-3-3-v2_reward/config.json from bucket guanaco-reward-models
Deleting key cgato-l3-thespice-8b-v0-3-3-v2_reward/merges.txt from bucket guanaco-reward-models
Deleting key cgato-l3-thespice-8b-v0-3-3-v2_reward/reward.tensors from bucket guanaco-reward-models
Deleting key cgato-l3-thespice-8b-v0-3-3-v2_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key cgato-l3-thespice-8b-v0-3-3-v2_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key cgato-l3-thespice-8b-v0-3-3-v2_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key cgato-l3-thespice-8b-v0-3-3-v2_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 2.71s
cgato-l3-thespice-8b-v0-3-3_v2 status is now torndown due to DeploymentManager action