Running pipeline stage MKMLizer
Starting job with name cgato-l3-thespice-8b-dpo-9135-v1-mkmlizer
Waiting for job on cgato-l3-thespice-8b-dpo-9135-v1-mkmlizer to finish
cgato-l3-thespice-8b-dpo-9135-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cgato-l3-thespice-8b-dpo-9135-v1-mkmlizer: ║ _____ __ __ ║
cgato-l3-thespice-8b-dpo-9135-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
cgato-l3-thespice-8b-dpo-9135-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
cgato-l3-thespice-8b-dpo-9135-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
cgato-l3-thespice-8b-dpo-9135-v1-mkmlizer: ║ /___/ ║
cgato-l3-thespice-8b-dpo-9135-v1-mkmlizer: ║ ║
cgato-l3-thespice-8b-dpo-9135-v1-mkmlizer: ║ Version: 0.8.10 ║
cgato-l3-thespice-8b-dpo-9135-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
cgato-l3-thespice-8b-dpo-9135-v1-mkmlizer: ║ ║
cgato-l3-thespice-8b-dpo-9135-v1-mkmlizer: ║ The license key for the current software has been verified as ║
cgato-l3-thespice-8b-dpo-9135-v1-mkmlizer: ║ belonging to: ║
cgato-l3-thespice-8b-dpo-9135-v1-mkmlizer: ║ ║
cgato-l3-thespice-8b-dpo-9135-v1-mkmlizer: ║ Chai Research Corp. ║
cgato-l3-thespice-8b-dpo-9135-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
cgato-l3-thespice-8b-dpo-9135-v1-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
cgato-l3-thespice-8b-dpo-9135-v1-mkmlizer: ║ ║
cgato-l3-thespice-8b-dpo-9135-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
cgato-l3-thespice-8b-dpo-9135-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-9135-v1-mkmlizer: warnings.warn(warning_message, FutureWarning)
cgato-l3-thespice-8b-dpo-9135-v1-mkmlizer: Downloaded to shared memory in 33.500s
cgato-l3-thespice-8b-dpo-9135-v1-mkmlizer: quantizing model to /dev/shm/model_cache
cgato-l3-thespice-8b-dpo-9135-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
cgato-l3-thespice-8b-dpo-9135-v1-mkmlizer:
Loading 0: 0%| | 0/291 [00:00<?, ?it/s]
Loading 0: 64%|██████▍ | 187/291 [00:01<00:01, 100.40it/s]
Loading 0: 100%|██████████| 291/291 [00:06<00:00, 38.15it/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-9135-v1-mkmlizer: quantized model in 17.829s
cgato-l3-thespice-8b-dpo-9135-v1-mkmlizer: Processed model cgato/L3-TheSpice-8b-DPO-v3.2-e6.1 in 52.255s
cgato-l3-thespice-8b-dpo-9135-v1-mkmlizer: creating bucket guanaco-mkml-models
cgato-l3-thespice-8b-dpo-9135-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cgato-l3-thespice-8b-dpo-9135-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/cgato-l3-thespice-8b-dpo-9135-v1
cgato-l3-thespice-8b-dpo-9135-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/cgato-l3-thespice-8b-dpo-9135-v1/config.json
cgato-l3-thespice-8b-dpo-9135-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/cgato-l3-thespice-8b-dpo-9135-v1/special_tokens_map.json
cgato-l3-thespice-8b-dpo-9135-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/cgato-l3-thespice-8b-dpo-9135-v1/tokenizer_config.json
cgato-l3-thespice-8b-dpo-9135-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/cgato-l3-thespice-8b-dpo-9135-v1/tokenizer.json
cgato-l3-thespice-8b-dpo-9135-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/cgato-l3-thespice-8b-dpo-9135-v1/flywheel_model.0.safetensors
cgato-l3-thespice-8b-dpo-9135-v1-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
cgato-l3-thespice-8b-dpo-9135-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-9135-v1-mkmlizer: warnings.warn(
cgato-l3-thespice-8b-dpo-9135-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-9135-v1-mkmlizer: warnings.warn(
cgato-l3-thespice-8b-dpo-9135-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-9135-v1-mkmlizer: warnings.warn(
cgato-l3-thespice-8b-dpo-9135-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-9135-v1-mkmlizer: return self.fget.__get__(instance, owner)()
cgato-l3-thespice-8b-dpo-9135-v1-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
cgato-l3-thespice-8b-dpo-9135-v1-mkmlizer: Saving duration: 0.216s
cgato-l3-thespice-8b-dpo-9135-v1-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 2.861s
cgato-l3-thespice-8b-dpo-9135-v1-mkmlizer: creating bucket guanaco-reward-models
cgato-l3-thespice-8b-dpo-9135-v1-mkmlizer: Bucket 's3://guanaco-reward-models/' created
cgato-l3-thespice-8b-dpo-9135-v1-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/cgato-l3-thespice-8b-dpo-9135-v1_reward
cgato-l3-thespice-8b-dpo-9135-v1-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/cgato-l3-thespice-8b-dpo-9135-v1_reward/special_tokens_map.json
cgato-l3-thespice-8b-dpo-9135-v1-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/cgato-l3-thespice-8b-dpo-9135-v1_reward/config.json
cgato-l3-thespice-8b-dpo-9135-v1-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/cgato-l3-thespice-8b-dpo-9135-v1_reward/vocab.json
cgato-l3-thespice-8b-dpo-9135-v1-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/cgato-l3-thespice-8b-dpo-9135-v1_reward/merges.txt
cgato-l3-thespice-8b-dpo-9135-v1-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/cgato-l3-thespice-8b-dpo-9135-v1_reward/tokenizer_config.json
cgato-l3-thespice-8b-dpo-9135-v1-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/cgato-l3-thespice-8b-dpo-9135-v1_reward/tokenizer.json
cgato-l3-thespice-8b-dpo-9135-v1-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/cgato-l3-thespice-8b-dpo-9135-v1_reward/reward.tensors
Job cgato-l3-thespice-8b-dpo-9135-v1-mkmlizer completed after 73.66s with status: succeeded
Stopping job with name cgato-l3-thespice-8b-dpo-9135-v1-mkmlizer
Pipeline stage MKMLizer completed in 74.64s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.08s
Running pipeline stage ISVCDeployer
Creating inference service cgato-l3-thespice-8b-dpo-9135-v1
Waiting for inference service cgato-l3-thespice-8b-dpo-9135-v1 to be ready
Inference service cgato-l3-thespice-8b-dpo-9135-v1 ready after 40.25197196006775s
Pipeline stage ISVCDeployer completed in 46.10s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.1161398887634277s
Received healthy response to inference request in 1.2634825706481934s
Received healthy response to inference request in 1.2896978855133057s
Received healthy response to inference request in 1.2788708209991455s
Received healthy response to inference request in 1.2798562049865723s
5 requests
0 failed requests
5th percentile: 1.2665602207183837
10th percentile: 1.2696378707885743
20th percentile: 1.2757931709289552
30th percentile: 1.2790678977966308
40th percentile: 1.2794620513916015
50th percentile: 1.2798562049865723
60th percentile: 1.2837928771972655
70th percentile: 1.287729549407959
80th percentile: 1.4549862861633303
90th percentile: 1.785563087463379
95th percentile: 1.9508514881134031
99th percentile: 2.0830822086334226
mean time: 1.4456094741821288
Pipeline stage StressChecker completed in 7.81s
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-dpo_9135_v1 status is now deployed due to DeploymentManager action
M-Eval Dataset for topic stay_in_character is loaded
cgato-l3-thespice-8b-dpo_9135_v1 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of cgato-l3-thespice-8b-dpo_9135_v1
Running pipeline stage ISVCDeleter
Checking if service cgato-l3-thespice-8b-dpo-9135-v1 is running
admin requested tearing down of cgato-l3-thespice-8b-dpo_9713_v1
Running pipeline stage ISVCDeleter
Checking if service cgato-l3-thespice-8b-dpo-9713-v1 is running
Tearing down inference service cgato-l3-thespice-8b-dpo-9135-v1
Toredown service cgato-l3-thespice-8b-dpo-9135-v1
Pipeline stage ISVCDeleter completed in 3.79s
Running pipeline stage MKMLModelDeleter
Tearing down inference service cgato-l3-thespice-8b-dpo-9713-v1
Cleaning model data from S3
Cleaning model data from model cache
Toredown service cgato-l3-thespice-8b-dpo-9713-v1
Deleting key cgato-l3-thespice-8b-dpo-9135-v1/config.json from bucket guanaco-mkml-models
Pipeline stage ISVCDeleter completed in 3.47s
Deleting key cgato-l3-thespice-8b-dpo-9135-v1/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key cgato-l3-thespice-8b-dpo-9713-v1/config.json from bucket guanaco-mkml-models
Deleting key cgato-l3-thespice-8b-dpo-9135-v1/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key cgato-l3-thespice-8b-dpo-9713-v1/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key cgato-l3-thespice-8b-dpo-9135-v1/tokenizer.json from bucket guanaco-mkml-models
Deleting key cgato-l3-thespice-8b-dpo-9135-v1/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key cgato-l3-thespice-8b-dpo-9135-v1_reward/config.json from bucket guanaco-reward-models
Deleting key cgato-l3-thespice-8b-dpo-9713-v1/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key cgato-l3-thespice-8b-dpo-9135-v1_reward/merges.txt from bucket guanaco-reward-models
Deleting key cgato-l3-thespice-8b-dpo-9713-v1/tokenizer.json from bucket guanaco-mkml-models
Deleting key cgato-l3-thespice-8b-dpo-9135-v1_reward/reward.tensors from bucket guanaco-reward-models
Deleting key cgato-l3-thespice-8b-dpo-9713-v1/tokenizer_config.json from bucket guanaco-mkml-models
Deleting key cgato-l3-thespice-8b-dpo-9135-v1_reward/special_tokens_map.json from bucket guanaco-reward-models
Cleaning model data from model cache
Deleting key cgato-l3-thespice-8b-dpo-9135-v1_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key cgato-l3-thespice-8b-dpo-9135-v1_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key cgato-l3-thespice-8b-dpo-9713-v1_reward/config.json from bucket guanaco-reward-models
Deleting key cgato-l3-thespice-8b-dpo-9135-v1_reward/vocab.json from bucket guanaco-reward-models
Deleting key cgato-l3-thespice-8b-dpo-9713-v1_reward/merges.txt from bucket guanaco-reward-models
Deleting key cgato-l3-thespice-8b-dpo-9713-v1_reward/reward.tensors from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 3.54s
Deleting key cgato-l3-thespice-8b-dpo-9713-v1_reward/special_tokens_map.json from bucket guanaco-reward-models
cgato-l3-thespice-8b-dpo_9135_v1 status is now torndown due to DeploymentManager action
Deleting key cgato-l3-thespice-8b-dpo-9713-v1_reward/tokenizer.json from bucket guanaco-reward-models