Running pipeline stage MKMLizer
Starting job with name fizzarolli-duloxetine-4b-2941-v1-mkmlizer
Waiting for job on fizzarolli-duloxetine-4b-2941-v1-mkmlizer to finish
fizzarolli-duloxetine-4b-2941-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
fizzarolli-duloxetine-4b-2941-v1-mkmlizer: ║ _____ __ __ ║
fizzarolli-duloxetine-4b-2941-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
fizzarolli-duloxetine-4b-2941-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
fizzarolli-duloxetine-4b-2941-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
fizzarolli-duloxetine-4b-2941-v1-mkmlizer: ║ /___/ ║
fizzarolli-duloxetine-4b-2941-v1-mkmlizer: ║ ║
fizzarolli-duloxetine-4b-2941-v1-mkmlizer: ║ Version: 0.8.14 ║
fizzarolli-duloxetine-4b-2941-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
fizzarolli-duloxetine-4b-2941-v1-mkmlizer: ║ https://mk1.ai ║
fizzarolli-duloxetine-4b-2941-v1-mkmlizer: ║ ║
fizzarolli-duloxetine-4b-2941-v1-mkmlizer: ║ The license key for the current software has been verified as ║
fizzarolli-duloxetine-4b-2941-v1-mkmlizer: ║ belonging to: ║
fizzarolli-duloxetine-4b-2941-v1-mkmlizer: ║ ║
fizzarolli-duloxetine-4b-2941-v1-mkmlizer: ║ Chai Research Corp. ║
fizzarolli-duloxetine-4b-2941-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
fizzarolli-duloxetine-4b-2941-v1-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
fizzarolli-duloxetine-4b-2941-v1-mkmlizer: ║ ║
fizzarolli-duloxetine-4b-2941-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
fizzarolli-duloxetine-4b-2941-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.
fizzarolli-duloxetine-4b-2941-v1-mkmlizer: warnings.warn(warning_message, FutureWarning)
fizzarolli-duloxetine-4b-2941-v1-mkmlizer: Downloaded to shared memory in 26.067s
fizzarolli-duloxetine-4b-2941-v1-mkmlizer: quantizing model to /dev/shm/model_cache
fizzarolli-duloxetine-4b-2941-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
fizzarolli-duloxetine-4b-2941-v1-mkmlizer:
Loading 0: 0%| | 0/523 [00:00<?, ?it/s]
Loading 0: 10%|█ | 53/523 [00:00<00:00, 529.85it/s]
Loading 0: 20%|██ | 106/523 [00:03<00:16, 24.67it/s]
Loading 0: 32%|███▏ | 166/523 [00:03<00:07, 46.32it/s]
Loading 0: 39%|███▉ | 206/523 [00:03<00:05, 60.92it/s]
Loading 0: 49%|████▉ | 256/523 [00:04<00:03, 87.50it/s]
Loading 0: 61%|██████ | 319/523 [00:04<00:01, 132.25it/s]
Loading 0: 69%|██████▉ | 363/523 [00:04<00:01, 147.48it/s]
Loading 0: 81%|████████ | 424/523 [00:04<00:00, 201.37it/s]
Loading 0: 93%|█████████▎| 487/523 [00:04<00:00, 262.23it/s]
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
fizzarolli-duloxetine-4b-2941-v1-mkmlizer: quantized model in 13.339s
fizzarolli-duloxetine-4b-2941-v1-mkmlizer: Processed model Fizzarolli/duloxetine-4b-v1-llamaify in 40.657s
fizzarolli-duloxetine-4b-2941-v1-mkmlizer: creating bucket guanaco-mkml-models
fizzarolli-duloxetine-4b-2941-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
fizzarolli-duloxetine-4b-2941-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/fizzarolli-duloxetine-4b-2941-v1
fizzarolli-duloxetine-4b-2941-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/fizzarolli-duloxetine-4b-2941-v1/config.json
fizzarolli-duloxetine-4b-2941-v1-mkmlizer: cp /dev/shm/model_cache/added_tokens.json s3://guanaco-mkml-models/fizzarolli-duloxetine-4b-2941-v1/added_tokens.json
fizzarolli-duloxetine-4b-2941-v1-mkmlizer: cp /dev/shm/model_cache/vocab.json s3://guanaco-mkml-models/fizzarolli-duloxetine-4b-2941-v1/vocab.json
fizzarolli-duloxetine-4b-2941-v1-mkmlizer: cp /dev/shm/model_cache/merges.txt s3://guanaco-mkml-models/fizzarolli-duloxetine-4b-2941-v1/merges.txt
fizzarolli-duloxetine-4b-2941-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/fizzarolli-duloxetine-4b-2941-v1/special_tokens_map.json
fizzarolli-duloxetine-4b-2941-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/fizzarolli-duloxetine-4b-2941-v1/tokenizer_config.json
fizzarolli-duloxetine-4b-2941-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/fizzarolli-duloxetine-4b-2941-v1/tokenizer.json
fizzarolli-duloxetine-4b-2941-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/fizzarolli-duloxetine-4b-2941-v1/flywheel_model.0.safetensors
fizzarolli-duloxetine-4b-2941-v1-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
fizzarolli-duloxetine-4b-2941-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.
fizzarolli-duloxetine-4b-2941-v1-mkmlizer: warnings.warn(
fizzarolli-duloxetine-4b-2941-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.
fizzarolli-duloxetine-4b-2941-v1-mkmlizer: warnings.warn(
fizzarolli-duloxetine-4b-2941-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.
fizzarolli-duloxetine-4b-2941-v1-mkmlizer: warnings.warn(
fizzarolli-duloxetine-4b-2941-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()
fizzarolli-duloxetine-4b-2941-v1-mkmlizer: return self.fget.__get__(instance, owner)()
fizzarolli-duloxetine-4b-2941-v1-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
fizzarolli-duloxetine-4b-2941-v1-mkmlizer: Saving duration: 0.412s
fizzarolli-duloxetine-4b-2941-v1-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 4.213s
fizzarolli-duloxetine-4b-2941-v1-mkmlizer: creating bucket guanaco-reward-models
fizzarolli-duloxetine-4b-2941-v1-mkmlizer: Bucket 's3://guanaco-reward-models/' created
fizzarolli-duloxetine-4b-2941-v1-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/fizzarolli-duloxetine-4b-2941-v1_reward
fizzarolli-duloxetine-4b-2941-v1-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/fizzarolli-duloxetine-4b-2941-v1_reward/config.json
fizzarolli-duloxetine-4b-2941-v1-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/fizzarolli-duloxetine-4b-2941-v1_reward/special_tokens_map.json
fizzarolli-duloxetine-4b-2941-v1-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/fizzarolli-duloxetine-4b-2941-v1_reward/merges.txt
fizzarolli-duloxetine-4b-2941-v1-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/fizzarolli-duloxetine-4b-2941-v1_reward/vocab.json
fizzarolli-duloxetine-4b-2941-v1-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/fizzarolli-duloxetine-4b-2941-v1_reward/tokenizer_config.json
fizzarolli-duloxetine-4b-2941-v1-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/fizzarolli-duloxetine-4b-2941-v1_reward/tokenizer.json
fizzarolli-duloxetine-4b-2941-v1-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/fizzarolli-duloxetine-4b-2941-v1_reward/reward.tensors
Job fizzarolli-duloxetine-4b-2941-v1-mkmlizer completed after 103.75s with status: succeeded
Stopping job with name fizzarolli-duloxetine-4b-2941-v1-mkmlizer
Pipeline stage MKMLizer completed in 107.93s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.09s
Running pipeline stage ISVCDeployer
Creating inference service fizzarolli-duloxetine-4b-2941-v1
Waiting for inference service fizzarolli-duloxetine-4b-2941-v1 to be ready
Inference service fizzarolli-duloxetine-4b-2941-v1 ready after 30.18619155883789s
Pipeline stage ISVCDeployer completed in 37.81s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.890228271484375s
%s, retrying in %s seconds...
Received healthy response to inference request in 0.9873542785644531s
Received healthy response to inference request in 0.9631588459014893s
Received healthy response to inference request in 0.9550738334655762s
Received healthy response to inference request in 0.9979641437530518s
Received healthy response to inference request in 1.237267017364502s
5 requests
0 failed requests
5th percentile: 0.9566908359527588
10th percentile: 0.9583078384399414
20th percentile: 0.9615418434143066
30th percentile: 0.967997932434082
40th percentile: 0.9776761054992675
50th percentile: 0.9873542785644531
60th percentile: 0.9915982246398926
70th percentile: 0.995842170715332
80th percentile: 1.0458247184753418
90th percentile: 1.141545867919922
95th percentile: 1.189406442642212
99th percentile: 1.2276949024200439
mean time: 1.0281636238098144
Pipeline stage StressChecker completed in 27.73s
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
fizzarolli-duloxetine-4b_2941_v1 status is now deployed due to DeploymentManager action
fizzarolli-duloxetine-4b_2941_v1 status is now rejected due to its M-Eval score being less than the acceptable minimum 6.5 to serve to users. Please consider iterating on your model's ability to adhere to prompts to improve this score.