Running pipeline stage MKMLizer
Starting job with name cgato-l3-thespice-8b-lun-3374-v1-mkmlizer
Waiting for job on cgato-l3-thespice-8b-lun-3374-v1-mkmlizer to finish
Stopping job with name cgato-l3-thespice-8b-lun-3374-v1-mkmlizer
%s, retrying in %s seconds...
Starting job with name cgato-l3-thespice-8b-lun-3374-v1-mkmlizer
Waiting for job on cgato-l3-thespice-8b-lun-3374-v1-mkmlizer to finish
cgato-l3-thespice-8b-lun-3374-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cgato-l3-thespice-8b-lun-3374-v1-mkmlizer: ║ _____ __ __ ║
cgato-l3-thespice-8b-lun-3374-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
cgato-l3-thespice-8b-lun-3374-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
cgato-l3-thespice-8b-lun-3374-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
cgato-l3-thespice-8b-lun-3374-v1-mkmlizer: ║ /___/ ║
cgato-l3-thespice-8b-lun-3374-v1-mkmlizer: ║ ║
cgato-l3-thespice-8b-lun-3374-v1-mkmlizer: ║ Version: 0.8.14 ║
cgato-l3-thespice-8b-lun-3374-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
cgato-l3-thespice-8b-lun-3374-v1-mkmlizer: ║ https://mk1.ai ║
cgato-l3-thespice-8b-lun-3374-v1-mkmlizer: ║ ║
cgato-l3-thespice-8b-lun-3374-v1-mkmlizer: ║ The license key for the current software has been verified as ║
cgato-l3-thespice-8b-lun-3374-v1-mkmlizer: ║ belonging to: ║
cgato-l3-thespice-8b-lun-3374-v1-mkmlizer: ║ ║
cgato-l3-thespice-8b-lun-3374-v1-mkmlizer: ║ Chai Research Corp. ║
cgato-l3-thespice-8b-lun-3374-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
cgato-l3-thespice-8b-lun-3374-v1-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
cgato-l3-thespice-8b-lun-3374-v1-mkmlizer: ║ ║
cgato-l3-thespice-8b-lun-3374-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
cgato-l3-thespice-8b-lun-3374-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-lun-3374-v1-mkmlizer: warnings.warn(warning_message, FutureWarning)
cgato-l3-thespice-8b-lun-3374-v1-mkmlizer: Downloaded to shared memory in 30.620s
cgato-l3-thespice-8b-lun-3374-v1-mkmlizer: quantizing model to /dev/shm/model_cache
cgato-l3-thespice-8b-lun-3374-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
cgato-l3-thespice-8b-lun-3374-v1-mkmlizer:
Loading 0: 0%| | 0/291 [00:00<?, ?it/s]
Loading 0: 29%|██▊ | 83/291 [00:00<00:02, 93.59it/s]
Loading 0: 64%|██████▍ | 187/291 [00:01<00:00, 112.85it/s]
Loading 0: 99%|█████████▊| 287/291 [00:02<00:00, 161.95it/s]
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
cgato-l3-thespice-8b-lun-3374-v1-mkmlizer: quantized model in 17.581s
cgato-l3-thespice-8b-lun-3374-v1-mkmlizer: Processed model cgato/L3-TheSpice-8b-Lunar-Eon-8 in 49.144s
cgato-l3-thespice-8b-lun-3374-v1-mkmlizer: creating bucket guanaco-mkml-models
cgato-l3-thespice-8b-lun-3374-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cgato-l3-thespice-8b-lun-3374-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/cgato-l3-thespice-8b-lun-3374-v1/flywheel_model.0.safetensors
cgato-l3-thespice-8b-lun-3374-v1-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
cgato-l3-thespice-8b-lun-3374-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-lun-3374-v1-mkmlizer: warnings.warn(
cgato-l3-thespice-8b-lun-3374-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-lun-3374-v1-mkmlizer: warnings.warn(
cgato-l3-thespice-8b-lun-3374-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-lun-3374-v1-mkmlizer: warnings.warn(
cgato-l3-thespice-8b-lun-3374-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-lun-3374-v1-mkmlizer: return self.fget.__get__(instance, owner)()
cgato-l3-thespice-8b-lun-3374-v1-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
cgato-l3-thespice-8b-lun-3374-v1-mkmlizer: Saving duration: 0.242s
cgato-l3-thespice-8b-lun-3374-v1-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 3.407s
cgato-l3-thespice-8b-lun-3374-v1-mkmlizer: creating bucket guanaco-reward-models
cgato-l3-thespice-8b-lun-3374-v1-mkmlizer: Bucket 's3://guanaco-reward-models/' created
cgato-l3-thespice-8b-lun-3374-v1-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/cgato-l3-thespice-8b-lun-3374-v1_reward
cgato-l3-thespice-8b-lun-3374-v1-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/cgato-l3-thespice-8b-lun-3374-v1_reward/special_tokens_map.json
cgato-l3-thespice-8b-lun-3374-v1-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/cgato-l3-thespice-8b-lun-3374-v1_reward/tokenizer_config.json
cgato-l3-thespice-8b-lun-3374-v1-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/cgato-l3-thespice-8b-lun-3374-v1_reward/merges.txt
cgato-l3-thespice-8b-lun-3374-v1-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/cgato-l3-thespice-8b-lun-3374-v1_reward/vocab.json
cgato-l3-thespice-8b-lun-3374-v1-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/cgato-l3-thespice-8b-lun-3374-v1_reward/tokenizer.json
cgato-l3-thespice-8b-lun-3374-v1-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/cgato-l3-thespice-8b-lun-3374-v1_reward/config.json
cgato-l3-thespice-8b-lun-3374-v1-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/cgato-l3-thespice-8b-lun-3374-v1_reward/reward.tensors
Job cgato-l3-thespice-8b-lun-3374-v1-mkmlizer completed after 75.9s with status: succeeded
Stopping job with name cgato-l3-thespice-8b-lun-3374-v1-mkmlizer
Pipeline stage MKMLizer completed in 82.74s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.12s
Running pipeline stage ISVCDeployer
Creating inference service cgato-l3-thespice-8b-lun-3374-v1
Waiting for inference service cgato-l3-thespice-8b-lun-3374-v1 to be ready
Inference service cgato-l3-thespice-8b-lun-3374-v1 ready after 40.295650005340576s
Pipeline stage ISVCDeployer completed in 47.39s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.0728251934051514s
Received healthy response to inference request in 1.1153321266174316s
Received healthy response to inference request in 1.1152238845825195s
Received healthy response to inference request in 1.1205203533172607s
Received healthy response to inference request in 1.1164193153381348s
5 requests
0 failed requests
5th percentile: 1.115245532989502
10th percentile: 1.1152671813964843
20th percentile: 1.1153104782104493
30th percentile: 1.1155495643615723
40th percentile: 1.1159844398498535
50th percentile: 1.1164193153381348
60th percentile: 1.1180597305297852
70th percentile: 1.1197001457214355
80th percentile: 1.3109813213348391
90th percentile: 1.6919032573699953
95th percentile: 1.882364225387573
99th percentile: 2.0347329998016357
mean time: 1.3080641746520996
Pipeline stage StressChecker completed in 7.23s
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 0.03s
M-Eval Dataset for topic stay_in_character is loaded
cgato-l3-thespice-8b-lun_3374_v1 status is now deployed due to DeploymentManager action
cgato-l3-thespice-8b-lun_3374_v1 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of cgato-l3-thespice-8b-lun_3374_v1
Running pipeline stage ISVCDeleter
Checking if service cgato-l3-thespice-8b-lun-3374-v1 is running
Tearing down inference service cgato-l3-thespice-8b-lun-3374-v1
Toredown service cgato-l3-thespice-8b-lun-3374-v1
Pipeline stage ISVCDeleter completed in 4.46s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key cgato-l3-thespice-8b-lun-3374-v1/config.json from bucket guanaco-mkml-models
Deleting key cgato-l3-thespice-8b-lun-3374-v1/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key cgato-l3-thespice-8b-lun-3374-v1/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key cgato-l3-thespice-8b-lun-3374-v1/tokenizer.json from bucket guanaco-mkml-models
Deleting key cgato-l3-thespice-8b-lun-3374-v1/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key cgato-l3-thespice-8b-lun-3374-v1_reward/config.json from bucket guanaco-reward-models
Deleting key cgato-l3-thespice-8b-lun-3374-v1_reward/merges.txt from bucket guanaco-reward-models
Deleting key cgato-l3-thespice-8b-lun-3374-v1_reward/reward.tensors from bucket guanaco-reward-models
Deleting key cgato-l3-thespice-8b-lun-3374-v1_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key cgato-l3-thespice-8b-lun-3374-v1_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key cgato-l3-thespice-8b-lun-3374-v1_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key cgato-l3-thespice-8b-lun-3374-v1_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 2.67s
cgato-l3-thespice-8b-lun_3374_v1 status is now torndown due to DeploymentManager action