Running pipeline stage MKMLizer
Starting job with name cgato-l3-thespice-8b-v3-2-v9-mkmlizer
Waiting for job on cgato-l3-thespice-8b-v3-2-v9-mkmlizer to finish
Stopping job with name cgato-l3-thespice-8b-v3-2-v9-mkmlizer
%s, retrying in %s seconds...
Starting job with name cgato-l3-thespice-8b-v3-2-v9-mkmlizer
Waiting for job on cgato-l3-thespice-8b-v3-2-v9-mkmlizer to finish
Stopping job with name cgato-l3-thespice-8b-v3-2-v9-mkmlizer
%s, retrying in %s seconds...
Starting job with name cgato-l3-thespice-8b-v3-2-v9-mkmlizer
Waiting for job on cgato-l3-thespice-8b-v3-2-v9-mkmlizer to finish
cgato-l3-thespice-8b-v3-2-v9-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cgato-l3-thespice-8b-v3-2-v9-mkmlizer: ║ _____ __ __ ║
cgato-l3-thespice-8b-v3-2-v9-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
cgato-l3-thespice-8b-v3-2-v9-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
cgato-l3-thespice-8b-v3-2-v9-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
cgato-l3-thespice-8b-v3-2-v9-mkmlizer: ║ /___/ ║
cgato-l3-thespice-8b-v3-2-v9-mkmlizer: ║ ║
cgato-l3-thespice-8b-v3-2-v9-mkmlizer: ║ Version: 0.8.14 ║
cgato-l3-thespice-8b-v3-2-v9-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
cgato-l3-thespice-8b-v3-2-v9-mkmlizer: ║ https://mk1.ai ║
cgato-l3-thespice-8b-v3-2-v9-mkmlizer: ║ ║
cgato-l3-thespice-8b-v3-2-v9-mkmlizer: ║ The license key for the current software has been verified as ║
cgato-l3-thespice-8b-v3-2-v9-mkmlizer: ║ belonging to: ║
cgato-l3-thespice-8b-v3-2-v9-mkmlizer: ║ ║
cgato-l3-thespice-8b-v3-2-v9-mkmlizer: ║ Chai Research Corp. ║
cgato-l3-thespice-8b-v3-2-v9-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
cgato-l3-thespice-8b-v3-2-v9-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
cgato-l3-thespice-8b-v3-2-v9-mkmlizer: ║ ║
cgato-l3-thespice-8b-v3-2-v9-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
cgato-l3-thespice-8b-v3-2-v9-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-v3-2-v9-mkmlizer: warnings.warn(warning_message, FutureWarning)
cgato-l3-thespice-8b-v3-2-v9-mkmlizer: Downloaded to shared memory in 12.877s
cgato-l3-thespice-8b-v3-2-v9-mkmlizer: quantizing model to /dev/shm/model_cache
cgato-l3-thespice-8b-v3-2-v9-mkmlizer: Saving flywheel model at /dev/shm/model_cache
cgato-l3-thespice-8b-v3-2-v9-mkmlizer:
Loading 0: 0%| | 0/291 [00:00<?, ?it/s]
Loading 0: 5%|▍ | 14/291 [00:00<00:02, 133.82it/s]
Loading 0: 12%|█▏ | 35/291 [00:00<00:01, 177.16it/s]
Loading 0: 18%|█▊ | 53/291 [00:00<00:01, 158.70it/s]
Loading 0: 25%|██▍ | 72/291 [00:00<00:01, 169.32it/s]
Loading 0: 31%|███ | 90/291 [00:00<00:02, 79.39it/s]
Loading 0: 37%|███▋ | 107/291 [00:00<00:01, 95.83it/s]
Loading 0: 44%|████▍ | 129/291 [00:01<00:01, 118.84it/s]
Loading 0: 51%|█████ | 148/291 [00:01<00:01, 131.43it/s]
Loading 0: 57%|█████▋ | 166/291 [00:01<00:00, 141.50it/s]
Loading 0: 64%|██████▍ | 187/291 [00:01<00:01, 85.68it/s]
Loading 0: 69%|██████▉ | 202/291 [00:01<00:00, 94.34it/s]
Loading 0: 76%|███████▌ | 221/291 [00:01<00:00, 110.35it/s]
Loading 0: 83%|████████▎ | 242/291 [00:02<00:00, 130.42it/s]
Loading 0: 89%|████████▉ | 260/291 [00:02<00:00, 141.59it/s]
Loading 0: 96%|█████████▌| 279/291 [00:02<00:00, 153.27it/s]
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
cgato-l3-thespice-8b-v3-2-v9-mkmlizer: quantized model in 17.921s
cgato-l3-thespice-8b-v3-2-v9-mkmlizer: Processed model cgato/L3-TheSpice-8b-v3.2 in 31.896s
cgato-l3-thespice-8b-v3-2-v9-mkmlizer: creating bucket guanaco-mkml-models
cgato-l3-thespice-8b-v3-2-v9-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cgato-l3-thespice-8b-v3-2-v9-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/cgato-l3-thespice-8b-v3-2-v9
cgato-l3-thespice-8b-v3-2-v9-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/cgato-l3-thespice-8b-v3-2-v9/special_tokens_map.json
cgato-l3-thespice-8b-v3-2-v9-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/cgato-l3-thespice-8b-v3-2-v9/config.json
cgato-l3-thespice-8b-v3-2-v9-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/cgato-l3-thespice-8b-v3-2-v9/tokenizer_config.json
cgato-l3-thespice-8b-v3-2-v9-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/cgato-l3-thespice-8b-v3-2-v9/tokenizer.json
cgato-l3-thespice-8b-v3-2-v9-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/cgato-l3-thespice-8b-v3-2-v9/flywheel_model.0.safetensors
cgato-l3-thespice-8b-v3-2-v9-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
cgato-l3-thespice-8b-v3-2-v9-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-v3-2-v9-mkmlizer: warnings.warn(
cgato-l3-thespice-8b-v3-2-v9-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-v3-2-v9-mkmlizer: warnings.warn(
cgato-l3-thespice-8b-v3-2-v9-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-v3-2-v9-mkmlizer: warnings.warn(
cgato-l3-thespice-8b-v3-2-v9-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-v3-2-v9-mkmlizer: return self.fget.__get__(instance, owner)()
cgato-l3-thespice-8b-v3-2-v9-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
cgato-l3-thespice-8b-v3-2-v9-mkmlizer: Saving duration: 0.247s
cgato-l3-thespice-8b-v3-2-v9-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 3.249s
cgato-l3-thespice-8b-v3-2-v9-mkmlizer: creating bucket guanaco-reward-models
cgato-l3-thespice-8b-v3-2-v9-mkmlizer: Bucket 's3://guanaco-reward-models/' created
cgato-l3-thespice-8b-v3-2-v9-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/cgato-l3-thespice-8b-v3-2-v9_reward
cgato-l3-thespice-8b-v3-2-v9-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/cgato-l3-thespice-8b-v3-2-v9_reward/special_tokens_map.json
cgato-l3-thespice-8b-v3-2-v9-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/cgato-l3-thespice-8b-v3-2-v9_reward/config.json
cgato-l3-thespice-8b-v3-2-v9-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/cgato-l3-thespice-8b-v3-2-v9_reward/tokenizer_config.json
cgato-l3-thespice-8b-v3-2-v9-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/cgato-l3-thespice-8b-v3-2-v9_reward/merges.txt
cgato-l3-thespice-8b-v3-2-v9-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/cgato-l3-thespice-8b-v3-2-v9_reward/vocab.json
cgato-l3-thespice-8b-v3-2-v9-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/cgato-l3-thespice-8b-v3-2-v9_reward/tokenizer.json
cgato-l3-thespice-8b-v3-2-v9-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/cgato-l3-thespice-8b-v3-2-v9_reward/reward.tensors
Job cgato-l3-thespice-8b-v3-2-v9-mkmlizer completed after 104.62s with status: succeeded
Stopping job with name cgato-l3-thespice-8b-v3-2-v9-mkmlizer
Pipeline stage MKMLizer completed in 110.87s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.12s
Running pipeline stage ISVCDeployer
Creating inference service cgato-l3-thespice-8b-v3-2-v9
Waiting for inference service cgato-l3-thespice-8b-v3-2-v9 to be ready
Inference service cgato-l3-thespice-8b-v3-2-v9 ready after 30.178478717803955s
Pipeline stage ISVCDeployer completed in 37.99s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.2786216735839844s
Received healthy response to inference request in 1.299588918685913s
Received healthy response to inference request in 1.2871496677398682s
Received healthy response to inference request in 1.2922358512878418s
Received healthy response to inference request in 1.4306025505065918s
5 requests
0 failed requests
5th percentile: 1.2881669044494628
10th percentile: 1.2891841411590577
20th percentile: 1.2912186145782472
30th percentile: 1.293706464767456
40th percentile: 1.2966476917266845
50th percentile: 1.299588918685913
60th percentile: 1.3519943714141847
70th percentile: 1.404399824142456
80th percentile: 1.6002063751220705
90th percentile: 1.9394140243530273
95th percentile: 2.109017848968506
99th percentile: 2.2447009086608887
mean time: 1.51763973236084
Pipeline stage StressChecker completed in 8.19s
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-v3-2_v9 status is now deployed due to DeploymentManager action
cgato-l3-thespice-8b-v3-2_v9 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of cgato-l3-thespice-8b-v3-2_v9
Running pipeline stage ISVCDeleter
Checking if service cgato-l3-thespice-8b-v3-2-v9 is running
Tearing down inference service cgato-l3-thespice-8b-v3-2-v9
Toredown service cgato-l3-thespice-8b-v3-2-v9
Pipeline stage ISVCDeleter completed in 4.74s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key cgato-l3-thespice-8b-v3-2-v9/config.json from bucket guanaco-mkml-models
Deleting key cgato-l3-thespice-8b-v3-2-v9/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key cgato-l3-thespice-8b-v3-2-v9/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key cgato-l3-thespice-8b-v3-2-v9/tokenizer.json from bucket guanaco-mkml-models
Deleting key cgato-l3-thespice-8b-v3-2-v9/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key cgato-l3-thespice-8b-v3-2-v9_reward/config.json from bucket guanaco-reward-models
Deleting key cgato-l3-thespice-8b-v3-2-v9_reward/merges.txt from bucket guanaco-reward-models
Deleting key cgato-l3-thespice-8b-v3-2-v9_reward/reward.tensors from bucket guanaco-reward-models
Deleting key cgato-l3-thespice-8b-v3-2-v9_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key cgato-l3-thespice-8b-v3-2-v9_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key cgato-l3-thespice-8b-v3-2-v9_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key cgato-l3-thespice-8b-v3-2-v9_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 2.92s
cgato-l3-thespice-8b-v3-2_v9 status is now torndown due to DeploymentManager action